Merge branch 'dir-deleg' into bakeathonbakeathon

23 files changed, 727 insertions, 129 deletions

diff --git a/fs/locks.c b/fs/locks.c
index 90c8746874dedb..ba6b6f9ea4c750 100644
--- a/fs/locks.c
+++ b/fs/locks.c
@@ -1822,6 +1822,11 @@ generic_add_lease(struct file *filp, int arg, struct file_lease **flp, void **pr
 			continue;
 		}
 
+		/* Allow the lease manager to veto the setlease */
+		if (lease->fl_lmops->lm_set_conflict &&
+		    lease->fl_lmops->lm_set_conflict(lease, fl))
+			goto out;
+
 		/*
 		 * No exclusive leases if someone else has a lease on
 		 * this file:
@@ -1925,6 +1930,11 @@ static int generic_delete_lease(struct file *filp, void *owner)
 int generic_setlease(struct file *filp, int arg, struct file_lease **flp,
 			void **priv)
 {
+	struct inode *inode = file_inode(filp);
+
+	if (!S_ISREG(inode->i_mode) && !S_ISDIR(inode->i_mode))
+		return -EINVAL;
+
 	switch (arg) {
 	case F_UNLCK:
 		return generic_delete_lease(filp, *priv);
@@ -2014,8 +2024,6 @@ vfs_setlease(struct file *filp, int arg, struct file_lease **lease, void **priv)
 
 	if ((!vfsuid_eq_kuid(vfsuid, current_fsuid())) && !capable(CAP_LEASE))
 		return -EACCES;
-	if (!S_ISREG(inode->i_mode))
-		return -EINVAL;
 	error = security_file_lock(filp, arg);
 	if (error)
 		return error;
diff --git a/fs/namei.c b/fs/namei.c
index c5b2a25be7d048..b93a0b61c55706 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -3164,6 +3164,32 @@ static inline umode_t vfs_prepare_mode(struct mnt_idmap *idmap,
 	return mode;
 }
 
+static int __vfs_create(struct mnt_idmap *idmap, struct inode *dir,
+			struct dentry *dentry, umode_t mode, bool want_excl,
+			struct inode **delegated_inode)
+{
+	int error;
+
+	error = may_create(idmap, dir, dentry);
+	if (error)
+		return error;
+
+	if (!dir->i_op->create)
+		return -EACCES;	/* shouldn't it be ENOSYS? */
+
+	mode = vfs_prepare_mode(idmap, dir, mode, S_IALLUGO, S_IFREG);
+	error = security_inode_create(dir, dentry, mode);
+	if (error)
+		return error;
+	error = try_break_deleg(dir, delegated_inode);
+	if (error)
+		return error;
+	error = dir->i_op->create(idmap, dir, dentry, mode, want_excl);
+	if (!error)
+		fsnotify_create(dir, dentry);
+	return error;
+}
+
 /**
  * vfs_create - create new file
  * @idmap:	idmap of the mount the inode was found from
@@ -3183,23 +3209,7 @@ static inline umode_t vfs_prepare_mode(struct mnt_idmap *idmap,
 int vfs_create(struct mnt_idmap *idmap, struct inode *dir,
 	       struct dentry *dentry, umode_t mode, bool want_excl)
 {
-	int error;
-
-	error = may_create(idmap, dir, dentry);
-	if (error)
-		return error;
-
-	if (!dir->i_op->create)
-		return -EACCES;	/* shouldn't it be ENOSYS? */
-
-	mode = vfs_prepare_mode(idmap, dir, mode, S_IALLUGO, S_IFREG);
-	error = security_inode_create(dir, dentry, mode);
-	if (error)
-		return error;
-	error = dir->i_op->create(idmap, dir, dentry, mode, want_excl);
-	if (!error)
-		fsnotify_create(dir, dentry);
-	return error;
+	return __vfs_create(idmap, dir, dentry, mode, want_excl, NULL);
 }
 EXPORT_SYMBOL(vfs_create);
 
@@ -3401,7 +3411,7 @@ static struct dentry *atomic_open(struct nameidata *nd, struct dentry *dentry,
  */
 static struct dentry *lookup_open(struct nameidata *nd, struct file *file,
 				  const struct open_flags *op,
-				  bool got_write)
+				  bool got_write, struct inode **delegated_inode)
 {
 	struct mnt_idmap *idmap;
 	struct dentry *dir = nd->path.dentry;
@@ -3487,6 +3497,11 @@ static struct dentry *lookup_open(struct nameidata *nd, struct file *file,
 
 	/* Negative dentry, just create the file */
 	if (!dentry->d_inode && (open_flag & O_CREAT)) {
+		/* but break the directory lease first! */
+		error = try_break_deleg(dir_inode, delegated_inode);
+		if (error)
+			goto out_dput;
+
 		file->f_mode |= FMODE_CREATED;
 		audit_inode_child(dir_inode, dentry, AUDIT_TYPE_CHILD_CREATE);
 		if (!dir_inode->i_op->create) {
@@ -3514,6 +3529,7 @@ static const char *open_last_lookups(struct nameidata *nd,
 		   struct file *file, const struct open_flags *op)
 {
 	struct dentry *dir = nd->path.dentry;
+	struct inode *delegated_inode = NULL;
 	int open_flag = op->open_flag;
 	bool got_write = false;
 	struct dentry *dentry;
@@ -3550,7 +3566,7 @@ static const char *open_last_lookups(struct nameidata *nd,
 		if (unlikely(nd->last.name[nd->last.len]))
 			return ERR_PTR(-EISDIR);
 	}
-
+retry:
 	if (open_flag & (O_CREAT | O_TRUNC | O_WRONLY | O_RDWR)) {
 		got_write = !mnt_want_write(nd->path.mnt);
 		/*
@@ -3563,7 +3579,7 @@ static const char *open_last_lookups(struct nameidata *nd,
 		inode_lock(dir->d_inode);
 	else
 		inode_lock_shared(dir->d_inode);
-	dentry = lookup_open(nd, file, op, got_write);
+	dentry = lookup_open(nd, file, op, got_write, &delegated_inode);
 	if (!IS_ERR(dentry) && (file->f_mode & FMODE_CREATED))
 		fsnotify_create(dir->d_inode, dentry);
 	if (open_flag & O_CREAT)
@@ -3574,8 +3590,16 @@ static const char *open_last_lookups(struct nameidata *nd,
 	if (got_write)
 		mnt_drop_write(nd->path.mnt);
 
-	if (IS_ERR(dentry))
+	if (IS_ERR(dentry)) {
+		if (delegated_inode) {
+			int error = break_deleg_wait(&delegated_inode);
+
+			if (!error)
+				goto retry;
+			return ERR_PTR(error);
+		}
 		return ERR_CAST(dentry);
+	}
 
 	if (file->f_mode & (FMODE_OPENED | FMODE_CREATED)) {
 		dput(nd->path.dentry);
@@ -3957,24 +3981,9 @@ inline struct dentry *user_path_create(int dfd, const char __user *pathname,
 }
 EXPORT_SYMBOL(user_path_create);
 
-/**
- * vfs_mknod - create device node or file
- * @idmap:	idmap of the mount the inode was found from
- * @dir:	inode of @dentry
- * @dentry:	pointer to dentry of the base directory
- * @mode:	mode of the new device node or file
- * @dev:	device number of device to create
- *
- * Create a device node or file.
- *
- * If the inode has been found through an idmapped mount the idmap of
- * the vfsmount must be passed through @idmap. This function will then take
- * care to map the inode according to @idmap before checking permissions.
- * On non-idmapped mounts or if permission checking is to be performed on the
- * raw inode simply pass @nop_mnt_idmap.
- */
-int vfs_mknod(struct mnt_idmap *idmap, struct inode *dir,
-	      struct dentry *dentry, umode_t mode, dev_t dev)
+static int __vfs_mknod(struct mnt_idmap *idmap, struct inode *dir,
+		       struct dentry *dentry, umode_t mode, dev_t dev,
+		       struct inode **delegated_inode)
 {
 	bool is_whiteout = S_ISCHR(mode) && dev == WHITEOUT_DEV;
 	int error = may_create(idmap, dir, dentry);
@@ -3998,11 +4007,37 @@ int vfs_mknod(struct mnt_idmap *idmap, struct inode *dir,
 	if (error)
 		return error;
 
+	error = try_break_deleg(dir, delegated_inode);
+	if (error)
+		return error;
+
 	error = dir->i_op->mknod(idmap, dir, dentry, mode, dev);
 	if (!error)
 		fsnotify_create(dir, dentry);
 	return error;
 }
+
+/**
+ * vfs_mknod - create device node or file
+ * @idmap:	idmap of the mount the inode was found from
+ * @dir:	inode of @dentry
+ * @dentry:	pointer to dentry of the base directory
+ * @mode:	mode of the new device node or file
+ * @dev:	device number of device to create
+ *
+ * Create a device node or file.
+ *
+ * If the inode has been found through an idmapped mount the idmap of
+ * the vfsmount must be passed through @idmap. This function will then take
+ * care to map the inode according to @idmap before checking permissions.
+ * On non-idmapped mounts or if permission checking is to be performed on the
+ * raw inode simply pass @nop_mnt_idmap.
+ */
+int vfs_mknod(struct mnt_idmap *idmap, struct inode *dir,
+	      struct dentry *dentry, umode_t mode, dev_t dev)
+{
+	return __vfs_mknod(idmap, dir, dentry, mode, dev, NULL);
+}
 EXPORT_SYMBOL(vfs_mknod);
 
 static int may_mknod(umode_t mode)
@@ -4030,6 +4065,7 @@ static int do_mknodat(int dfd, struct filename *name, umode_t mode,
 	struct path path;
 	int error;
 	unsigned int lookup_flags = 0;
+	struct inode *delegated_inode = NULL;
 
 	error = may_mknod(mode);
 	if (error)
@@ -4048,22 +4084,30 @@ retry:
 	idmap = mnt_idmap(path.mnt);
 	switch (mode & S_IFMT) {
 		case 0: case S_IFREG:
-			error = vfs_create(idmap, path.dentry->d_inode,
-					   dentry, mode, true);
+			error = __vfs_create(idmap, path.dentry->d_inode,
+					     dentry, mode, true,
+					     &delegated_inode);
 			if (!error)
 				security_path_post_mknod(idmap, dentry);
 			break;
 		case S_IFCHR: case S_IFBLK:
-			error = vfs_mknod(idmap, path.dentry->d_inode,
-					  dentry, mode, new_decode_dev(dev));
+			error = __vfs_mknod(idmap, path.dentry->d_inode,
+					    dentry, mode, new_decode_dev(dev),
+					    &delegated_inode);
 			break;
 		case S_IFIFO: case S_IFSOCK:
-			error = vfs_mknod(idmap, path.dentry->d_inode,
-					  dentry, mode, 0);
+			error = __vfs_mknod(idmap, path.dentry->d_inode,
+					    dentry, mode, 0,
+					    &delegated_inode);
 			break;
 	}
 out2:
 	done_path_create(&path, dentry);
+	if (delegated_inode) {
+		error = break_deleg_wait(&delegated_inode);
+		if (!error)
+			goto retry;
+	}
 	if (retry_estale(error, lookup_flags)) {
 		lookup_flags |= LOOKUP_REVAL;
 		goto retry;
@@ -4084,23 +4128,9 @@ SYSCALL_DEFINE3(mknod, const char __user *, filename, umode_t, mode, unsigned, d
 	return do_mknodat(AT_FDCWD, getname(filename), mode, dev);
 }
 
-/**
- * vfs_mkdir - create directory
- * @idmap:	idmap of the mount the inode was found from
- * @dir:	inode of @dentry
- * @dentry:	pointer to dentry of the base directory
- * @mode:	mode of the new directory
- *
- * Create a directory.
- *
- * If the inode has been found through an idmapped mount the idmap of
- * the vfsmount must be passed through @idmap. This function will then take
- * care to map the inode according to @idmap before checking permissions.
- * On non-idmapped mounts or if permission checking is to be performed on the
- * raw inode simply pass @nop_mnt_idmap.
- */
-int vfs_mkdir(struct mnt_idmap *idmap, struct inode *dir,
-	      struct dentry *dentry, umode_t mode)
+static int __vfs_mkdir(struct mnt_idmap *idmap, struct inode *dir,
+		       struct dentry *dentry, umode_t mode,
+		       struct inode **delegated_inode)
 {
 	int error;
 	unsigned max_links = dir->i_sb->s_max_links;
@@ -4120,11 +4150,36 @@ int vfs_mkdir(struct mnt_idmap *idmap, struct inode *dir,
 	if (max_links && dir->i_nlink >= max_links)
 		return -EMLINK;
 
+	error = try_break_deleg(dir, delegated_inode);
+	if (error)
+		return error;
+
 	error = dir->i_op->mkdir(idmap, dir, dentry, mode);
 	if (!error)
 		fsnotify_mkdir(dir, dentry);
 	return error;
 }
+
+/**
+ * vfs_mkdir - create directory
+ * @idmap:	idmap of the mount the inode was found from
+ * @dir:	inode of @dentry
+ * @dentry:	pointer to dentry of the base directory
+ * @mode:	mode of the new directory
+ *
+ * Create a directory.
+ *
+ * If the inode has been found through an idmapped mount the idmap of
+ * the vfsmount must be passed through @idmap. This function will then take
+ * care to map the inode according to @idmap before checking permissions.
+ * On non-idmapped mounts or if permission checking is to be performed on the
+ * raw inode simply pass @nop_mnt_idmap.
+ */
+int vfs_mkdir(struct mnt_idmap *idmap, struct inode *dir,
+	      struct dentry *dentry, umode_t mode)
+{
+	return __vfs_mkdir(idmap, dir, dentry, mode, NULL);
+}
 EXPORT_SYMBOL(vfs_mkdir);
 
 int do_mkdirat(int dfd, struct filename *name, umode_t mode)
@@ -4133,6 +4188,7 @@ int do_mkdirat(int dfd, struct filename *name, umode_t mode)
 	struct path path;
 	int error;
 	unsigned int lookup_flags = LOOKUP_DIRECTORY;
+	struct inode *delegated_inode = NULL;
 
 retry:
 	dentry = filename_create(dfd, name, &path, lookup_flags);
@@ -4142,11 +4198,15 @@ retry:
 
 	error = security_path_mkdir(&path, dentry,
 			mode_strip_umask(path.dentry->d_inode, mode));
-	if (!error) {
-		error = vfs_mkdir(mnt_idmap(path.mnt), path.dentry->d_inode,
-				  dentry, mode);
-	}
+	if (!error)
+		error = __vfs_mkdir(mnt_idmap(path.mnt), path.dentry->d_inode,
+				    dentry, mode, &delegated_inode);
 	done_path_create(&path, dentry);
+	if (delegated_inode) {
+		error = break_deleg_wait(&delegated_inode);
+		if (!error)
+			goto retry;
+	}
 	if (retry_estale(error, lookup_flags)) {
 		lookup_flags |= LOOKUP_REVAL;
 		goto retry;
@@ -4166,22 +4226,8 @@ SYSCALL_DEFINE2(mkdir, const char __user *, pathname, umode_t, mode)
 	return do_mkdirat(AT_FDCWD, getname(pathname), mode);
 }
 
-/**
- * vfs_rmdir - remove directory
- * @idmap:	idmap of the mount the inode was found from
- * @dir:	inode of @dentry
- * @dentry:	pointer to dentry of the base directory
- *
- * Remove a directory.
- *
- * If the inode has been found through an idmapped mount the idmap of
- * the vfsmount must be passed through @idmap. This function will then take
- * care to map the inode according to @idmap before checking permissions.
- * On non-idmapped mounts or if permission checking is to be performed on the
- * raw inode simply pass @nop_mnt_idmap.
- */
-int vfs_rmdir(struct mnt_idmap *idmap, struct inode *dir,
-		     struct dentry *dentry)
+static int __vfs_rmdir(struct mnt_idmap *idmap, struct inode *dir,
+		       struct dentry *dentry, struct inode **delegated_inode)
 {
 	int error = may_delete(idmap, dir, dentry, 1);
 
@@ -4203,6 +4249,10 @@ int vfs_rmdir(struct mnt_idmap *idmap, struct inode *dir,
 	if (error)
 		goto out;
 
+	error = try_break_deleg(dir, delegated_inode);
+	if (error)
+		goto out;
+
 	error = dir->i_op->rmdir(dir, dentry);
 	if (error)
 		goto out;
@@ -4219,6 +4269,25 @@ out:
 		d_delete_notify(dir, dentry);
 	return error;
 }
+
+/**
+ * vfs_rmdir - remove directory
+ * @idmap:	idmap of the mount the inode was found from
+ * @dir:	inode of @dentry
+ * @dentry:	pointer to dentry of the base directory
+ *
+ * Remove a directory.
+ *
+ * If the inode has been found through an idmapped mount the idmap of
+ * the vfsmount must be passed through @idmap. This function will then take
+ * care to map the inode according to @idmap before checking permissions.
+ * On non-idmapped mounts or if permission checking is to be performed on the
+ * raw inode simply pass @nop_mnt_idmap.
+ */
+int vfs_rmdir(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry)
+{
+	return __vfs_rmdir(idmap, dir, dentry, NULL);
+}
 EXPORT_SYMBOL(vfs_rmdir);
 
 int do_rmdir(int dfd, struct filename *name)
@@ -4229,6 +4298,7 @@ int do_rmdir(int dfd, struct filename *name)
 	struct qstr last;
 	int type;
 	unsigned int lookup_flags = 0;
+	struct inode *delegated_inode = NULL;
 retry:
 	error = filename_parentat(dfd, name, lookup_flags, &path, &last, &type);
 	if (error)
@@ -4262,7 +4332,8 @@ retry:
 	error = security_path_rmdir(&path, dentry);
 	if (error)
 		goto exit4;
-	error = vfs_rmdir(mnt_idmap(path.mnt), path.dentry->d_inode, dentry);
+	error = __vfs_rmdir(mnt_idmap(path.mnt), path.dentry->d_inode,
+			    dentry, &delegated_inode);
 exit4:
 	dput(dentry);
 exit3:
@@ -4270,6 +4341,11 @@ exit3:
 	mnt_drop_write(path.mnt);
 exit2:
 	path_put(&path);
+	if (delegated_inode) {
+		error = break_deleg_wait(&delegated_inode);
+		if (!error)
+			goto retry;
+	}
 	if (retry_estale(error, lookup_flags)) {
 		lookup_flags |= LOOKUP_REVAL;
 		goto retry;
@@ -4329,6 +4405,9 @@ int vfs_unlink(struct mnt_idmap *idmap, struct inode *dir,
 	else {
 		error = security_inode_unlink(dir, dentry);
 		if (!error) {
+			error = try_break_deleg(dir, delegated_inode);
+			if (error)
+				goto out;
 			error = try_break_deleg(target, delegated_inode);
 			if (error)
 				goto out;
@@ -4600,7 +4679,9 @@ int vfs_link(struct dentry *old_dentry, struct mnt_idmap *idmap,
 	else if (max_links && inode->i_nlink >= max_links)
 		error = -EMLINK;
 	else {
-		error = try_break_deleg(inode, delegated_inode);
+		error = try_break_deleg(dir, delegated_inode);
+		if (!error)
+			error = try_break_deleg(inode, delegated_inode);
 		if (!error)
 			error = dir->i_op->link(old_dentry, dir, new_dentry);
 	}
@@ -4867,6 +4948,14 @@ int vfs_rename(struct renamedata *rd)
 		    old_dir->i_nlink >= max_links)
 			goto out;
 	}
+	error = try_break_deleg(old_dir, delegated_inode);
+	if (error)
+		goto out;
+	if (new_dir != old_dir) {
+		error = try_break_deleg(new_dir, delegated_inode);
+		if (error)
+			goto out;
+	}
 	if (!is_dir) {
 		error = try_break_deleg(source, delegated_inode);
 		if (error)
diff --git a/fs/nfs/delegation.c b/fs/nfs/delegation.c
index 6bace5fece04e2..d333fc5f87d0d9 100644
--- a/fs/nfs/delegation.c
+++ b/fs/nfs/delegation.c
@@ -338,6 +338,8 @@ nfs_detach_delegation_locked(struct nfs_inode *nfsi,
 		rcu_dereference_protected(nfsi->delegation,
 				lockdep_is_held(&clp->cl_lock));
 
+	trace_nfs4_detach_delegation(&nfsi->vfs_inode, delegation->type);
+
 	if (deleg_cur == NULL || delegation != deleg_cur)
 		return NULL;
 
@@ -350,6 +352,7 @@ nfs_detach_delegation_locked(struct nfs_inode *nfsi,
 	delegation->inode = NULL;
 	rcu_assign_pointer(nfsi->delegation, NULL);
 	spin_unlock(&delegation->lock);
+	clear_bit(NFS_INO_GDD_GETATTR, &nfsi->flags);
 	return delegation;
 }
 
@@ -565,6 +568,8 @@ static bool nfs_delegation_need_return(struct nfs_delegation *delegation)
 {
 	bool ret = false;
 
+	trace_nfs_delegation_need_return(delegation);
+
 	if (test_and_clear_bit(NFS_DELEGATION_RETURN, &delegation->flags))
 		ret = true;
 	else if (test_bit(NFS_DELEGATION_RETURN_IF_CLOSED, &delegation->flags)) {
diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index ac505671efbdb7..930fe7e1491403 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -1504,12 +1504,20 @@ static int nfs_dentry_verify_change(struct inode *dir, struct dentry *dentry)
 static int nfs_check_verifier(struct inode *dir, struct dentry *dentry,
 			      int rcu_walk)
 {
+	struct nfs_inode *nfsi = NFS_I(dir);
+
 	if (IS_ROOT(dentry))
 		return 1;
 	if (NFS_SERVER(dir)->flags & NFS_MOUNT_LOOKUP_CACHE_NONE)
 		return 0;
 	if (!nfs_dentry_verify_change(dir, dentry))
 		return 0;
+	/*
+	 * The dentry matches the directory's change attribute, so
+	 * we're likely revalidating here. Flag the dir so that we
+	 * ask for a delegation on the next getattr.
+	 */
+	set_bit(NFS_INO_GDD_GETATTR, &nfsi->flags);
 	/* Revalidate nfsi->cache_change_attribute before we declare a match */
 	if (nfs_mapping_need_revalidate_inode(dir)) {
 		if (rcu_walk)
@@ -2189,6 +2197,15 @@ no_open:
 EXPORT_SYMBOL_GPL(nfs_atomic_open);
 
 static int
+nfs_lookup_revalidate_delegated_parent(struct inode *dir, struct dentry *dentry,
+				       struct inode *inode)
+{
+	return nfs_lookup_revalidate_done(dir, dentry, inode,
+					  nfs_verify_change_attribute(dir, dentry->d_time) ?
+					  1 : 0);
+}
+
+static int
 nfs4_do_lookup_revalidate(struct inode *dir, struct dentry *dentry,
 			  unsigned int flags)
 {
@@ -2212,6 +2229,9 @@ nfs4_do_lookup_revalidate(struct inode *dir, struct dentry *dentry,
 	if (nfs_verifier_is_delegated(dentry))
 		return nfs_lookup_revalidate_delegated(dir, dentry, inode);
 
+	if (nfs_have_delegated_attributes(dir))
+		return nfs_lookup_revalidate_delegated_parent(dir, dentry, inode);
+
 	/* NFS only supports OPEN on regular files */
 	if (!S_ISREG(inode->i_mode))
 		goto full_reval;
diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h
index 06253695fe53f0..41e3532cceb5ea 100644
--- a/fs/nfs/internal.h
+++ b/fs/nfs/internal.h
@@ -866,7 +866,7 @@ static inline u32 nfs_stateid_hash(const nfs4_stateid *stateid)
 				NFS4_STATEID_OTHER_SIZE);
 }
 #else
-static inline u32 nfs_stateid_hash(nfs4_stateid *stateid)
+static inline u32 nfs_stateid_hash(const nfs4_stateid *stateid)
 {
 	return 0;
 }
diff --git a/fs/nfs/nfs4file.c b/fs/nfs/nfs4file.c
index 1cd9652f3c2803..b7630a437ad22f 100644
--- a/fs/nfs/nfs4file.c
+++ b/fs/nfs/nfs4file.c
@@ -442,6 +442,8 @@ void nfs42_ssc_unregister_ops(void)
 static int nfs4_setlease(struct file *file, int arg, struct file_lease **lease,
 			 void **priv)
 {
+	if (!S_ISREG(file_inode(file)->i_mode))
+		return -EINVAL;
 	return nfs4_proc_setlease(file, arg, lease, priv);
 }
 
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index ea390db94b622f..c624358ff0b33f 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -4313,6 +4313,34 @@ out:
 	return status;
 }
 
+#ifdef CONFIG_NFS_V4_1
+static bool dir_delegations_enabled = true;
+module_param(dir_delegations_enabled, bool, 0644);
+MODULE_PARM_DESC(dir_delegations_enabled, "Enable directory delegations?");
+
+static bool should_request_dir_deleg(struct inode *inode)
+{
+	if (!dir_delegations_enabled)
+		return false;
+	if (!inode)
+		return false;
+	if (!S_ISDIR(inode->i_mode))
+		return false;
+	if (!nfs_server_capable(inode, NFS_CAP_GET_DIR_DELEG))
+		return false;
+	if (!test_and_clear_bit(NFS_INO_GDD_GETATTR, &(NFS_I(inode)->flags)))
+		return false;
+	if (nfs4_have_delegation(inode, FMODE_READ))
+		return false;
+	return true;
+}
+#else
+static bool should_request_dir_deleg(struct inode *inode)
+{
+	return false;
+}
+#endif
+
 static int _nfs4_proc_getattr(struct nfs_server *server, struct nfs_fh *fhandle,
 				struct nfs_fattr *fattr, struct inode *inode)
 {
@@ -4326,11 +4354,12 @@ static int _nfs4_proc_getattr(struct nfs_server *server, struct nfs_fh *fhandle,
 		.server = server,
 	};
 	struct rpc_message msg = {
-		.rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_GETATTR],
 		.rpc_argp = &args,
 		.rpc_resp = &res,
 	};
 	unsigned short task_flags = 0;
+	bool gdd;
+	int status;
 
 	if (nfs4_has_session(server->nfs_client))
 		task_flags = RPC_TASK_MOVEABLE;
@@ -4339,11 +4368,32 @@ static int _nfs4_proc_getattr(struct nfs_server *server, struct nfs_fh *fhandle,
 	if (inode && (server->flags & NFS_MOUNT_SOFTREVAL))
 		task_flags |= RPC_TASK_TIMEOUT;
 
+retry:
+	gdd = should_request_dir_deleg(inode);
+	if (gdd)
+		msg.rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_GDD_GETATTR];
+	else
+		msg.rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_GETATTR];
+
 	nfs4_bitmap_copy_adjust(bitmask, nfs4_bitmask(server, fattr->label), inode, 0);
 	nfs_fattr_init(fattr);
 	nfs4_init_sequence(&args.seq_args, &res.seq_res, 0, 0);
-	return nfs4_do_call_sync(server->client, server, &msg,
-			&args.seq_args, &res.seq_res, task_flags);
+	status = nfs4_do_call_sync(server->client, server, &msg,
+				   &args.seq_args, &res.seq_res, task_flags);
+	switch (status) {
+	case 0:
+		if (gdd && res.nf_status == GDD4_OK)
+			status = nfs_inode_set_delegation(inode, current_cred(), FMODE_READ,
+							  &res.deleg, 0);
+		break;
+	case -ENOTSUPP:
+		/* If the server doesn't support GET_DIR_DELEGATION, retry without it */
+		if (gdd) {
+			server->caps &= ~NFS_CAP_GET_DIR_DELEG;
+			goto retry;
+		}
+	}
+	return status;
 }
 
 int nfs4_proc_getattr(struct nfs_server *server, struct nfs_fh *fhandle,
@@ -10429,6 +10479,8 @@ nfs41_free_lock_state(struct nfs_server *server, struct nfs4_lock_state *lsp)
 static bool nfs41_match_stateid(const nfs4_stateid *s1,
 		const nfs4_stateid *s2)
 {
+	trace_nfs41_match_stateid(s1, s2);
+
 	if (s1->type != s2->type)
 		return false;
 
@@ -10446,6 +10498,8 @@ static bool nfs41_match_stateid(const nfs4_stateid *s1,
 static bool nfs4_match_stateid(const nfs4_stateid *s1,
 		const nfs4_stateid *s2)
 {
+	trace_nfs4_match_stateid(s1, s2);
+
 	return nfs4_stateid_match(s1, s2);
 }
 
@@ -10545,6 +10599,7 @@ static const struct nfs4_minor_version_ops nfs_v4_1_minor_ops = {
 	.minor_version = 1,
 	.init_caps = NFS_CAP_READDIRPLUS
 		| NFS_CAP_ATOMIC_OPEN
+		| NFS_CAP_GET_DIR_DELEG
 		| NFS_CAP_POSIX_LOCK
 		| NFS_CAP_STATEID_NFSV41
 		| NFS_CAP_ATOMIC_OPEN_V1
@@ -10571,6 +10626,7 @@ static const struct nfs4_minor_version_ops nfs_v4_2_minor_ops = {
 	.minor_version = 2,
 	.init_caps = NFS_CAP_READDIRPLUS
 		| NFS_CAP_ATOMIC_OPEN
+		| NFS_CAP_GET_DIR_DELEG
 		| NFS_CAP_POSIX_LOCK
 		| NFS_CAP_STATEID_NFSV41
 		| NFS_CAP_ATOMIC_OPEN_V1
diff --git a/fs/nfs/nfs4trace.h b/fs/nfs/nfs4trace.h
index 10985a4b8259dd..92ad63fd43e147 100644
--- a/fs/nfs/nfs4trace.h
+++ b/fs/nfs/nfs4trace.h
@@ -14,6 +14,8 @@
 #include <trace/misc/fs.h>
 #include <trace/misc/nfs.h>
 
+#include "delegation.h"
+
 #define show_nfs_fattr_flags(valid) \
 	__print_flags((unsigned long)valid, "|", \
 		{ NFS_ATTR_FATTR_TYPE, "TYPE" }, \
@@ -956,6 +958,52 @@ DECLARE_EVENT_CLASS(nfs4_set_delegation_event,
 			TP_ARGS(inode, fmode))
 DEFINE_NFS4_SET_DELEGATION_EVENT(nfs4_set_delegation);
 DEFINE_NFS4_SET_DELEGATION_EVENT(nfs4_reclaim_delegation);
+DEFINE_NFS4_SET_DELEGATION_EVENT(nfs4_detach_delegation);
+
+#define show_delegation_flags(flags) \
+	__print_flags(flags, "|", \
+		{ BIT(NFS_DELEGATION_NEED_RECLAIM), "NEED_RECLAIM" }, \
+		{ BIT(NFS_DELEGATION_RETURN), "RETURN" }, \
+		{ BIT(NFS_DELEGATION_RETURN_IF_CLOSED), "RETURN_IF_CLOSED" }, \
+		{ BIT(NFS_DELEGATION_REFERENCED), "REFERENCED" }, \
+		{ BIT(NFS_DELEGATION_RETURNING), "RETURNING" }, \
+		{ BIT(NFS_DELEGATION_REVOKED), "REVOKED" }, \
+		{ BIT(NFS_DELEGATION_TEST_EXPIRED), "TEST_EXPIRED" }, \
+		{ BIT(NFS_DELEGATION_INODE_FREEING), "INODE_FREEING" }, \
+		{ BIT(NFS_DELEGATION_RETURN_DELAYED), "RETURN_DELAYED" })
+
+DECLARE_EVENT_CLASS(nfs4_delegation_event,
+		TP_PROTO(
+			const struct nfs_delegation *delegation
+		),
+
+		TP_ARGS(delegation),
+
+		TP_STRUCT__entry(
+			__field(u32, fhandle)
+			__field(unsigned int, fmode)
+			__field(unsigned long, flags)
+		),
+
+		TP_fast_assign(
+			__entry->fhandle = nfs_fhandle_hash(NFS_FH(delegation->inode));
+			__entry->fmode = delegation->type;
+			__entry->flags = delegation->flags;
+		),
+
+		TP_printk(
+			"fhandle=0x%08x fmode=%s flags=%s",
+			__entry->fhandle, show_fs_fmode_flags(__entry->fmode),
+			show_delegation_flags(__entry->flags)
+		)
+);
+#define DEFINE_NFS4_DELEGATION_EVENT(name) \
+	DEFINE_EVENT(nfs4_delegation_event, name, \
+			TP_PROTO( \
+				const struct nfs_delegation *delegation \
+			), \
+			TP_ARGS(delegation))
+DEFINE_NFS4_DELEGATION_EVENT(nfs_delegation_need_return);
 
 TRACE_EVENT(nfs4_delegreturn_exit,
 		TP_PROTO(
@@ -1449,6 +1497,62 @@ DECLARE_EVENT_CLASS(nfs4_inode_stateid_callback_event,
 DEFINE_NFS4_INODE_STATEID_CALLBACK_EVENT(nfs4_cb_recall);
 DEFINE_NFS4_INODE_STATEID_CALLBACK_EVENT(nfs4_cb_layoutrecall_file);
 
+#define show_stateid_type(type) \
+	__print_symbolic(type, \
+		{ NFS4_INVALID_STATEID_TYPE, "INVALID" }, \
+		{ NFS4_SPECIAL_STATEID_TYPE, "SPECIAL" }, \
+		{ NFS4_OPEN_STATEID_TYPE, "OPEN" }, \
+		{ NFS4_LOCK_STATEID_TYPE, "LOCK" }, \
+		{ NFS4_DELEGATION_STATEID_TYPE, "DELEGATION" }, \
+		{ NFS4_LAYOUT_STATEID_TYPE, "LAYOUT" },	\
+		{ NFS4_PNFS_DS_STATEID_TYPE, "PNFS_DS" }, \
+		{ NFS4_REVOKED_STATEID_TYPE, "REVOKED" })
+
+DECLARE_EVENT_CLASS(nfs4_match_stateid_event,
+		TP_PROTO(
+			const nfs4_stateid *s1,
+			const nfs4_stateid *s2
+		),
+
+		TP_ARGS(s1, s2),
+
+		TP_STRUCT__entry(
+			__field(int, s1_seq)
+			__field(int, s2_seq)
+			__field(u32, s1_hash)
+			__field(u32, s2_hash)
+			__field(int, s1_type)
+			__field(int, s2_type)
+		),
+
+		TP_fast_assign(
+			__entry->s1_seq = s1->seqid;
+			__entry->s1_hash = nfs_stateid_hash(s1);
+			__entry->s1_type = s1->type;
+			__entry->s2_seq = s2->seqid;
+			__entry->s2_hash = nfs_stateid_hash(s2);
+			__entry->s2_type = s2->type;
+		),
+
+		TP_printk(
+			"s1=%s:%x:%u s2=%s:%x:%u",
+			show_stateid_type(__entry->s1_type),
+			__entry->s1_hash, __entry->s1_seq,
+			show_stateid_type(__entry->s2_type),
+			__entry->s2_hash, __entry->s2_seq
+		)
+);
+
+#define DEFINE_NFS4_MATCH_STATEID_EVENT(name) \
+	DEFINE_EVENT(nfs4_match_stateid_event, name, \
+			TP_PROTO( \
+				const nfs4_stateid *s1, \
+				const nfs4_stateid *s2 \
+			), \
+			TP_ARGS(s1, s2))
+DEFINE_NFS4_MATCH_STATEID_EVENT(nfs41_match_stateid);
+DEFINE_NFS4_MATCH_STATEID_EVENT(nfs4_match_stateid);
+
 DECLARE_EVENT_CLASS(nfs4_idmap_event,
 		TP_PROTO(
 			const char *name,
diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c
index 1416099dfcd159..94241bb5a885ea 100644
--- a/fs/nfs/nfs4xdr.c
+++ b/fs/nfs/nfs4xdr.c
@@ -391,6 +391,22 @@ static int decode_layoutget(struct xdr_stream *xdr, struct rpc_rqst *req,
 				XDR_QUADLEN(NFS4_MAX_SESSIONID_LEN) + 5)
 #define encode_reclaim_complete_maxsz	(op_encode_hdr_maxsz + 4)
 #define decode_reclaim_complete_maxsz	(op_decode_hdr_maxsz + 4)
+#define encode_get_dir_delegation_maxsz (op_encode_hdr_maxsz +				\
+					 4 /* gdda_signal_deleg_avail */ +		\
+					 8 /* gdda_notification_types */ +		\
+					 nfstime4_maxsz  /* gdda_child_attr_delay */ +	\
+					 nfstime4_maxsz  /* gdda_dir_attr_delay */ +	\
+					 nfs4_fattr_bitmap_maxsz /* gdda_child_attributes */ + \
+					 nfs4_fattr_bitmap_maxsz /* gdda_dir_attributes */)
+
+#define decode_get_dir_delegation_maxsz (op_encode_hdr_maxsz +				\
+					 4 /* gddrnf_status */ +			\
+					 encode_verifier_maxsz /* gddr_cookieverf */ +	\
+					 encode_stateid_maxsz /* gddr_stateid */ +	\
+					 8 /* gddr_notification */ +			\
+					 nfs4_fattr_bitmap_maxsz /* gddr_child_attributes */ + \
+					 nfs4_fattr_bitmap_maxsz /* gddr_dir_attributes */)
+
 #define encode_getdeviceinfo_maxsz (op_encode_hdr_maxsz + \
 				XDR_QUADLEN(NFS4_DEVICEID4_SIZE) + \
 				1 /* layout type */ + \
@@ -636,6 +652,18 @@ static int decode_layoutget(struct xdr_stream *xdr, struct rpc_rqst *req,
 				decode_putfh_maxsz + \
 				decode_getattr_maxsz + \
 				decode_renew_maxsz)
+#define NFS4_enc_gdd_getattr_sz	(compound_encode_hdr_maxsz + \
+				encode_sequence_maxsz + \
+				encode_putfh_maxsz + \
+				encode_get_dir_delegation_maxsz + \
+				encode_getattr_maxsz + \
+				encode_renew_maxsz)
+#define NFS4_dec_gdd_getattr_sz	(compound_decode_hdr_maxsz + \
+				decode_sequence_maxsz + \
+				decode_putfh_maxsz + \
+				decode_get_dir_delegation_maxsz + \
+				decode_getattr_maxsz + \
+				decode_renew_maxsz)
 #define NFS4_enc_lookup_sz	(compound_encode_hdr_maxsz + \
 				encode_sequence_maxsz + \
 				encode_putfh_maxsz + \
@@ -1982,6 +2010,30 @@ static void encode_sequence(struct xdr_stream *xdr,
 
 #ifdef CONFIG_NFS_V4_1
 static void
+encode_get_dir_delegation(struct xdr_stream *xdr, struct compound_hdr *hdr)
+{
+	__be32 *p;
+	struct timespec64 ts = {};
+	u32 zerobm[1] = {};
+
+	encode_op_hdr(xdr, OP_GET_DIR_DELEGATION, decode_get_dir_delegation_maxsz, hdr);
+
+	/* We can't handle CB_RECALLABLE_OBJ_AVAIL yet */
+	xdr_stream_encode_bool(xdr, false);
+
+	/* for now, we request no notification types */
+	xdr_encode_bitmap4(xdr, zerobm, ARRAY_SIZE(zerobm));
+
+	/* Request no attribute updates */
+	p = reserve_space(xdr, 12 + 12);
+	p = xdr_encode_nfstime4(p, &ts);
+	xdr_encode_nfstime4(p, &ts);
+
+	xdr_encode_bitmap4(xdr, zerobm, ARRAY_SIZE(zerobm));
+	xdr_encode_bitmap4(xdr, zerobm, ARRAY_SIZE(zerobm));
+}
+
+static void
 encode_getdeviceinfo(struct xdr_stream *xdr,
 		     const struct nfs4_getdeviceinfo_args *args,
 		     struct compound_hdr *hdr)
@@ -3179,6 +3231,25 @@ static void nfs4_xdr_enc_free_stateid(struct rpc_rqst *req,
 	encode_free_stateid(xdr, args, &hdr);
 	encode_nops(&hdr);
 }
+
+/*
+ * Encode GDD_GETATTR request
+ */
+static void nfs4_xdr_enc_gdd_getattr(struct rpc_rqst *req, struct xdr_stream *xdr,
+				     const void *data)
+{
+	const struct nfs4_getattr_arg *args = data;
+	struct compound_hdr hdr = {
+		.minorversion = nfs4_xdr_minorversion(&args->seq_args),
+	};
+
+	encode_compound_hdr(xdr, req, &hdr);
+	encode_sequence(xdr, &args->seq_args, &hdr);
+	encode_putfh(xdr, args->fh, &hdr);
+	encode_get_dir_delegation(xdr, &hdr);
+	encode_getfattr(xdr, args->bitmask, &hdr);
+	encode_nops(&hdr);
+}
 #endif /* CONFIG_NFS_V4_1 */
 
 static int decode_opaque_inline(struct xdr_stream *xdr, unsigned int *len, char **string)
@@ -5919,6 +5990,43 @@ static int decode_layout_stateid(struct xdr_stream *xdr, nfs4_stateid *stateid)
 	return decode_stateid(xdr, stateid);
 }
 
+static int decode_get_dir_delegation(struct xdr_stream *xdr,
+				     struct nfs4_getattr_res *res)
+{
+	nfs4_verifier	cookieverf;
+	int		status;
+	u32		bm[1];
+
+	status = decode_op_hdr(xdr, OP_GET_DIR_DELEGATION);
+	if (status)
+		return status;
+
+	if (xdr_stream_decode_u32(xdr, &res->nf_status))
+		return -EIO;
+
+	if (res->nf_status == GDD4_UNAVAIL)
+		return xdr_inline_decode(xdr, 4) ? 0 : -EIO;
+
+	status = decode_verifier(xdr, &cookieverf);
+	if (status)
+		return status;
+
+	status = decode_delegation_stateid(xdr, &res->deleg);
+	if (status)
+		return status;
+
+	status = decode_bitmap4(xdr, bm, ARRAY_SIZE(bm));
+	if (status < 0)
+		return status;
+	status = decode_bitmap4(xdr, bm, ARRAY_SIZE(bm));
+	if (status < 0)
+		return status;
+	status = decode_bitmap4(xdr, bm, ARRAY_SIZE(bm));
+	if (status < 0)
+		return status;
+	return 0;
+}
+
 static int decode_getdeviceinfo(struct xdr_stream *xdr,
 				struct nfs4_getdeviceinfo_res *res)
 {
@@ -7469,6 +7577,33 @@ static int nfs4_xdr_dec_free_stateid(struct rpc_rqst *rqstp,
 out:
 	return status;
 }
+
+/*
+ * Decode GDD_GETATTR response
+ */
+static int nfs4_xdr_dec_gdd_getattr(struct rpc_rqst *rqstp, struct xdr_stream *xdr,
+				    void *data)
+{
+	struct nfs4_getattr_res *res = data;
+	struct compound_hdr hdr;
+	int status;
+
+	status = decode_compound_hdr(xdr, &hdr);
+	if (status)
+		goto out;
+	status = decode_sequence(xdr, &res->seq_res, rqstp);
+	if (status)
+		goto out;
+	status = decode_putfh(xdr);
+	if (status)
+		goto out;
+	status = decode_get_dir_delegation(xdr, res);
+	if (status)
+		goto out;
+	status = decode_getfattr(xdr, res->fattr, res->server);
+out:
+	return status;
+}
 #endif /* CONFIG_NFS_V4_1 */
 
 /**
@@ -7704,6 +7839,7 @@ const struct rpc_procinfo nfs4_procedures[] = {
 	PROC41(BIND_CONN_TO_SESSION,
 			enc_bind_conn_to_session, dec_bind_conn_to_session),
 	PROC41(DESTROY_CLIENTID,enc_destroy_clientid,	dec_destroy_clientid),
+	PROC41(GDD_GETATTR,	enc_gdd_getattr,	dec_gdd_getattr),
 	PROC42(SEEK,		enc_seek,		dec_seek),
 	PROC42(ALLOCATE,	enc_allocate,		dec_allocate),
 	PROC42(DEALLOCATE,	enc_deallocate,		dec_deallocate),
diff --git a/fs/nfs/nfstrace.h b/fs/nfs/nfstrace.h
index afedb449b54fd3..e0cd3601d1f758 100644
--- a/fs/nfs/nfstrace.h
+++ b/fs/nfs/nfstrace.h
@@ -56,6 +56,7 @@ DECLARE_EVENT_CLASS(nfs_inode_event,
 			__field(u32, fhandle)
 			__field(u64, fileid)
 			__field(u64, version)
+			__field(unsigned long, cache_validity)
 		),
 
 		TP_fast_assign(
@@ -64,14 +65,17 @@ DECLARE_EVENT_CLASS(nfs_inode_event,
 			__entry->fileid = nfsi->fileid;
 			__entry->fhandle = nfs_fhandle_hash(&nfsi->fh);
 			__entry->version = inode_peek_iversion_raw(inode);
+			__entry->cache_validity = nfsi->cache_validity;
 		),
 
 		TP_printk(
-			"fileid=%02x:%02x:%llu fhandle=0x%08x version=%llu ",
+			"fileid=%02x:%02x:%llu fhandle=0x%08x version=%llu cache_validity=0x%lx (%s)",
 			MAJOR(__entry->dev), MINOR(__entry->dev),
 			(unsigned long long)__entry->fileid,
 			__entry->fhandle,
-			(unsigned long long)__entry->version
+			(unsigned long long)__entry->version,
+			__entry->cache_validity,
+			nfs_show_cache_validity(__entry->cache_validity)
 		)
 );
 
diff --git a/fs/nfsd/filecache.c b/fs/nfsd/filecache.c
index ddd3e0d9cfa63e..ba66d571d56750 100644
--- a/fs/nfsd/filecache.c
+++ b/fs/nfsd/filecache.c
@@ -979,7 +979,7 @@ nfsd_file_is_cached(struct inode *inode)
 static __be32
 nfsd_file_do_acquire(struct svc_rqst *rqstp, struct svc_fh *fhp,
 		     unsigned int may_flags, struct file *file,
-		     struct nfsd_file **pnf, bool want_gc)
+		     umode_t type, bool want_gc, struct nfsd_file **pnf)
 {
 	unsigned char need = may_flags & NFSD_FILE_MAY_MASK;
 	struct net *net = SVC_NET(rqstp);
@@ -991,7 +991,7 @@ nfsd_file_do_acquire(struct svc_rqst *rqstp, struct svc_fh *fhp,
 	int ret;
 
 retry:
-	status = fh_verify(rqstp, fhp, S_IFREG,
+	status = fh_verify(rqstp, fhp, type,
 				may_flags|NFSD_MAY_OWNER_OVERRIDE);
 	if (status != nfs_ok)
 		return status;
@@ -1083,7 +1083,7 @@ open_file:
 			trace_nfsd_file_opened(nf, status);
 		} else {
 			ret = nfsd_open_verified(rqstp, fhp, may_flags,
-						 &nf->nf_file);
+						 type, &nf->nf_file);
 			if (ret == -EOPENSTALE && stale_retry) {
 				stale_retry = false;
 				nfsd_file_unhash(nf);
@@ -1139,7 +1139,7 @@ __be32
 nfsd_file_acquire_gc(struct svc_rqst *rqstp, struct svc_fh *fhp,
 		     unsigned int may_flags, struct nfsd_file **pnf)
 {
-	return nfsd_file_do_acquire(rqstp, fhp, may_flags, NULL, pnf, true);
+	return nfsd_file_do_acquire(rqstp, fhp, may_flags, NULL, S_IFREG, true, pnf);
 }
 
 /**
@@ -1163,7 +1163,7 @@ __be32
 nfsd_file_acquire(struct svc_rqst *rqstp, struct svc_fh *fhp,
 		  unsigned int may_flags, struct nfsd_file **pnf)
 {
-	return nfsd_file_do_acquire(rqstp, fhp, may_flags, NULL, pnf, false);
+	return nfsd_file_do_acquire(rqstp, fhp, may_flags, NULL, S_IFREG, false, pnf);
 }
 
 /**
@@ -1189,7 +1189,32 @@ nfsd_file_acquire_opened(struct svc_rqst *rqstp, struct svc_fh *fhp,
 			 unsigned int may_flags, struct file *file,
 			 struct nfsd_file **pnf)
 {
-	return nfsd_file_do_acquire(rqstp, fhp, may_flags, file, pnf, false);
+	return nfsd_file_do_acquire(rqstp, fhp, may_flags, file, S_IFREG, false, pnf);
+}
+
+/**
+ * nfsd_file_acquire_dir - Get a struct nfsd_file with an open directory
+ * @rqstp: the RPC transaction being executed
+ * @fhp: the NFS filehandle of the file to be opened
+ * @pnf: OUT: new or found "struct nfsd_file" object
+ *
+ * The nfsd_file_object returned by this API is reference-counted
+ * but not garbage-collected. The object is unhashed after the
+ * final nfsd_file_put(). This opens directories only, and only
+ * in O_RDONLY mode.
+ *
+ * Return values:
+ *   %nfs_ok - @pnf points to an nfsd_file with its reference
+ *   count boosted.
+ *
+ * On error, an nfsstat value in network byte order is returned.
+ */
+__be32
+nfsd_file_acquire_dir(struct svc_rqst *rqstp, struct svc_fh *fhp,
+		  struct nfsd_file **pnf)
+{
+	return nfsd_file_do_acquire(rqstp, fhp, NFSD_MAY_READ|NFSD_MAY_64BIT_COOKIE,
+				    NULL, S_IFDIR, false, pnf);
 }
 
 /*
diff --git a/fs/nfsd/filecache.h b/fs/nfsd/filecache.h
index c61884def906d0..de29a1c9d949d2 100644
--- a/fs/nfsd/filecache.h
+++ b/fs/nfsd/filecache.h
@@ -65,5 +65,7 @@ __be32 nfsd_file_acquire(struct svc_rqst *rqstp, struct svc_fh *fhp,
 __be32 nfsd_file_acquire_opened(struct svc_rqst *rqstp, struct svc_fh *fhp,
 		  unsigned int may_flags, struct file *file,
 		  struct nfsd_file **nfp);
+__be32 nfsd_file_acquire_dir(struct svc_rqst *rqstp, struct svc_fh *fhp,
+		  struct nfsd_file **pnf);
 int nfsd_file_cache_stats_show(struct seq_file *m, void *v);
 #endif /* _FS_NFSD_FILECACHE_H */
diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c
index 3dc173b29803ff..ac3d532f19b232 100644
--- a/fs/nfsd/nfs4proc.c
+++ b/fs/nfsd/nfs4proc.c
@@ -2160,20 +2160,27 @@ nfsd4_get_dir_delegation(struct svc_rqst *rqstp,
 			 union nfsd4_op_u *u)
 {
 	struct nfsd4_get_dir_delegation *gdd = &u->get_dir_delegation;
+	struct nfs4_delegation *dd;
+	struct nfsd_file *nf;
+	__be32 status;
 
-	/*
-	 * RFC 8881, section 18.39.3 says:
-	 *
-	 * "The server may refuse to grant the delegation. In that case, the
-	 *  server will return NFS4ERR_DIRDELEG_UNAVAIL."
-	 *
-	 * This is sub-optimal, since it means that the server would need to
-	 * abort compound processing just because the delegation wasn't
-	 * available. RFC8881bis should change this to allow the server to
-	 * return NFS4_OK with a non-fatal status of GDD4_UNAVAIL in this
-	 * situation.
-	 */
-	gdd->gddrnf_status = GDD4_UNAVAIL;
+	status = nfsd_file_acquire_dir(rqstp, &cstate->current_fh, &nf);
+	if (status != nfs_ok)
+		return status;
+
+	dd = nfsd_get_dir_deleg(cstate, gdd, nf);
+	if (IS_ERR(dd)) {
+		int err = PTR_ERR(dd);
+
+		if (err != -EAGAIN)
+			return nfserrno(err);
+		gdd->gddrnf_status = GDD4_UNAVAIL;
+		return nfs_ok;
+	}
+
+	gdd->gddrnf_status = GDD4_OK;
+	memcpy(&gdd->gddr_stateid, &dd->dl_stid.sc_stateid, sizeof(gdd->gddr_stateid));
+	nfs4_put_stid(&dd->dl_stid);
 	return nfs_ok;
 }
 
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index a20c2c9d7d457f..f762ce61e20704 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -88,6 +88,7 @@ void nfsd4_end_grace(struct nfsd_net *nn);
 static void _free_cpntf_state_locked(struct nfsd_net *nn, struct nfs4_cpntf_state *cps);
 static void nfsd4_file_hash_remove(struct nfs4_file *fi);
 static void deleg_reaper(struct nfsd_net *nn);
+static bool nfsd_dir_deleg_conflict(struct file_lease *new, struct file_lease *old);
 
 /* Locking: */
 
@@ -5305,6 +5306,31 @@ static const struct lease_manager_operations nfsd_lease_mng_ops = {
 	.lm_change = nfsd_change_deleg_cb,
 };
 
+static const struct lease_manager_operations nfsd_dir_lease_mng_ops = {
+	.lm_breaker_owns_lease = nfsd_breaker_owns_lease,
+	.lm_break = nfsd_break_deleg_cb,
+	.lm_change = nfsd_change_deleg_cb,
+	.lm_set_conflict = nfsd_dir_deleg_conflict,
+};
+
+static bool
+nfsd_dir_deleg_conflict(struct file_lease *new, struct file_lease *old)
+{
+	struct nfs4_delegation *od, *nd;
+
+	/* Only conflicts with other nfsd dir delegs */
+	if (old->fl_lmops != &nfsd_dir_lease_mng_ops)
+		return false;
+
+	od = old->c.flc_owner;
+	nd = new->c.flc_owner;
+
+	/* Are these for the same client? No bueno if so */
+	if (od->dl_stid.sc_client == nd->dl_stid.sc_client)
+		return true;
+	return false;
+}
+
 static __be32 nfsd4_check_seqid(struct nfsd4_compound_state *cstate, struct nfs4_stateowner *so, u32 seqid)
 {
 	if (nfsd4_has_session(cstate))
@@ -5644,12 +5670,13 @@ static struct file_lease *nfs4_alloc_init_lease(struct nfs4_delegation *dp,
 	fl = locks_alloc_lease();
 	if (!fl)
 		return NULL;
-	fl->fl_lmops = &nfsd_lease_mng_ops;
 	fl->c.flc_flags = FL_DELEG;
 	fl->c.flc_type = flag == NFS4_OPEN_DELEGATE_READ? F_RDLCK: F_WRLCK;
 	fl->c.flc_owner = (fl_owner_t)dp;
 	fl->c.flc_pid = current->tgid;
 	fl->c.flc_file = dp->dl_stid.sc_file->fi_deleg_file->nf_file;
+	fl->fl_lmops = S_ISDIR(file_inode(fl->c.flc_file)->i_mode) ?
+				&nfsd_dir_lease_mng_ops : &nfsd_lease_mng_ops;
 	return fl;
 }
 
@@ -7466,7 +7493,7 @@ nfsd4_delegreturn(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	__be32 status;
 	struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id);
 
-	if ((status = fh_verify(rqstp, &cstate->current_fh, S_IFREG, 0)))
+	if ((status = fh_verify(rqstp, &cstate->current_fh, 0, 0)))
 		return status;
 
 	status = nfsd4_lookup_stateid(cstate, stateid, SC_TYPE_DELEG, 0, &s, nn);
@@ -8904,3 +8931,85 @@ break_lease:
 	spin_unlock(&ctx->flc_lock);
 	return 0;
 }
+
+/**
+ * nfsd_get_dir_delegation - attempt to get a directory delegation
+ * @cstate: compound state
+ * @gdd: GET_DIR_DELEGATION arg/resp structure
+ * @nf: nfsd_file opened on the directory
+ *
+ * Given a GET_DIR_DELEGATION request @gdd, attempt to acquire a delegation on
+ * on the directory to which @nf refers. Note that this does not set up any
+ * sort of async notifications for the delegation.
+ */
+struct nfs4_delegation *
+nfsd_get_dir_deleg(struct nfsd4_compound_state *cstate,
+		   struct nfsd4_get_dir_delegation *gdd,
+		   struct nfsd_file *nf)
+{
+	struct nfs4_client *clp = cstate->clp;
+	struct nfs4_delegation *dp;
+	struct file_lease *fl;
+	struct nfs4_file *fp;
+	int status = 0;
+
+	fp = nfsd4_alloc_file();
+	if (!fp)
+		return ERR_PTR(-ENOMEM);
+
+	nfsd4_file_init(&cstate->current_fh, fp);
+	fp->fi_deleg_file = nf;
+	fp->fi_delegees = 1;
+
+	/* if this client already has one, return that it's unavailable */
+	spin_lock(&state_lock);
+	spin_lock(&fp->fi_lock);
+	if (nfs4_delegation_exists(clp, fp))
+		status = -EAGAIN;
+	spin_unlock(&fp->fi_lock);
+	spin_unlock(&state_lock);
+
+	if (status)
+		goto out_delegees;
+
+	/* Try to set up the lease */
+	status = -ENOMEM;
+	dp = alloc_init_deleg(clp, fp, NULL, NFS4_OPEN_DELEGATE_READ);
+	if (!dp)
+		goto out_delegees;
+
+	fl = nfs4_alloc_init_lease(dp, NFS4_OPEN_DELEGATE_READ);
+	if (!fl)
+		goto out_put_stid;
+
+	status = kernel_setlease(nf->nf_file,
+				 fl->c.flc_type, &fl, NULL);
+	if (fl)
+		locks_free_lease(fl);
+	if (status)
+		goto out_put_stid;
+
+	/*
+	 * Now, try to hash it. This can fail if we race another nfsd task
+	 * trying to set a delegation on the same file. If that happens,
+	 * then just say UNAVAIL.
+	 */
+	spin_lock(&state_lock);
+	spin_lock(&clp->cl_lock);
+	spin_lock(&fp->fi_lock);
+	status = hash_delegation_locked(dp, fp);
+	spin_unlock(&fp->fi_lock);
+	spin_unlock(&clp->cl_lock);
+	spin_unlock(&state_lock);
+
+	if (!status)
+		return dp;
+
+	/* Something failed. Drop the lease and clean up the stid */
+	kernel_setlease(fp->fi_deleg_file->nf_file, F_UNLCK, NULL, (void **)&dp);
+out_put_stid:
+	nfs4_put_stid(&dp->dl_stid);
+out_delegees:
+	put_deleg_file(fp);
+	return ERR_PTR(status);
+}
diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h
index f42d8d782c8459..4a5c26ddf91f7b 100644
--- a/fs/nfsd/state.h
+++ b/fs/nfsd/state.h
@@ -782,4 +782,9 @@ static inline bool try_to_expire_client(struct nfs4_client *clp)
 
 extern __be32 nfsd4_deleg_getattr_conflict(struct svc_rqst *rqstp,
 		struct inode *inode, bool *file_modified, u64 *size);
+
+struct nfsd4_get_dir_delegation;
+struct nfs4_delegation *nfsd_get_dir_deleg(struct nfsd4_compound_state *cstate,
+						struct nfsd4_get_dir_delegation *gdd,
+						struct nfsd_file *nf);
 #endif   /* NFSD4_STATE_H */
diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c
index 2e41eb4c3cec76..35321fd0089328 100644
--- a/fs/nfsd/vfs.c
+++ b/fs/nfsd/vfs.c
@@ -949,6 +949,7 @@ retry:
  * nfsd_open_verified - Open a regular file for the filecache
  * @rqstp: RPC request
  * @fhp: NFS filehandle of the file to open
+ * @type: S_IFMT inode type allowed (0 means any type is allowed)
  * @may_flags: internal permission flags
  * @filp: OUT: open "struct file *"
  *
@@ -956,9 +957,9 @@ retry:
  */
 int
 nfsd_open_verified(struct svc_rqst *rqstp, struct svc_fh *fhp, int may_flags,
-		   struct file **filp)
+		   umode_t type, struct file **filp)
 {
-	return __nfsd_open(rqstp, fhp, S_IFREG, may_flags, filp);
+	return __nfsd_open(rqstp, fhp, type, may_flags, filp);
 }
 
 /*
diff --git a/fs/nfsd/vfs.h b/fs/nfsd/vfs.h
index c60fdb6200fded..c7f0349c179e2f 100644
--- a/fs/nfsd/vfs.h
+++ b/fs/nfsd/vfs.h
@@ -105,7 +105,7 @@ int 		nfsd_open_break_lease(struct inode *, int);
 __be32		nfsd_open(struct svc_rqst *, struct svc_fh *, umode_t,
 				int, struct file **);
 int		nfsd_open_verified(struct svc_rqst *rqstp, struct svc_fh *fhp,
-				   int may_flags, struct file **filp);
+				   int may_flags, umode_t type, struct file **filp);
 __be32		nfsd_splice_read(struct svc_rqst *rqstp, struct svc_fh *fhp,
 				struct file *file, loff_t offset,
 				unsigned long *count,
diff --git a/fs/smb/client/cifsfs.c b/fs/smb/client/cifsfs.c
index d41eedbff674ab..947229da88bf23 100644
--- a/fs/smb/client/cifsfs.c
+++ b/fs/smb/client/cifsfs.c
@@ -1093,6 +1093,9 @@ cifs_setlease(struct file *file, int arg, struct file_lease **lease, void **priv
 	struct inode *inode = file_inode(file);
 	struct cifsFileInfo *cfile = file->private_data;
 
+	if (!S_ISREG(inode->i_mode))
+		return -EINVAL;
+
 	/* Check if file is oplocked if this is request for new lease */
 	if (arg == F_UNLCK ||
 	    ((arg == F_RDLCK) && CIFS_CACHE_READ(CIFS_I(inode))) ||
diff --git a/include/linux/filelock.h b/include/linux/filelock.h
index daee999d05f390..ca45c5724f2bb9 100644
--- a/include/linux/filelock.h
+++ b/include/linux/filelock.h
@@ -4,19 +4,22 @@
 
 #include <linux/fs.h>
 
-#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 */
-#define FL_CLOSE	64	/* unlock on close */
-#define FL_SLEEP	128	/* A blocking lock */
-#define FL_DOWNGRADE_PENDING	256 /* Lease is being downgraded */
-#define FL_UNLOCK_PENDING	512 /* Lease is being broken */
-#define FL_OFDLCK	1024	/* lock is "owned" by struct file */
-#define FL_LAYOUT	2048	/* outstanding pNFS layout */
-#define FL_RECLAIM	4096	/* reclaiming from a reboot server */
+#define FL_POSIX	BIT(0)
+#define FL_FLOCK	BIT(1)
+#define FL_DELEG	BIT(2)	/* NFSv4 delegation */
+#define FL_ACCESS	BIT(3)	/* not trying to lock, just looking */
+#define FL_EXISTS	BIT(4)	/* when unlocking, test for existence */
+#define FL_LEASE	BIT(5)	/* lease held on this file */
+#define FL_CLOSE	BIT(6)	/* unlock on close */
+#define FL_SLEEP	BIT(7)	/* A blocking lock */
+#define FL_DOWNGRADE_PENDING BIT(8) /* Lease is being downgraded */
+#define FL_UNLOCK_PENDING BIT(9) /* Lease is being broken */
+#define FL_OFDLCK	BIT(10)	/* lock is "owned" by struct file */
+#define FL_LAYOUT	BIT(11)	/* outstanding pNFS layout */
+#define FL_RECLAIM	BIT(12)	/* reclaiming from a reboot server */
+#define FL_IGN_CREATE	BIT(13) /* ignore create events in directories */
+#define FL_IGN_REMOVE	BIT(14) /* ignore remove events in directories */
+#define FL_IGN_RENAME	BIT(15) /* ignore rename events in directories */
 
 #define FL_CLOSE_POSIX (FL_POSIX | FL_CLOSE)
 
@@ -49,6 +52,20 @@ struct lease_manager_operations {
 	int (*lm_change)(struct file_lease *, int, struct list_head *);
 	void (*lm_setup)(struct file_lease *, void **);
 	bool (*lm_breaker_owns_lease)(struct file_lease *);
+
+	/**
+	 * lm_set_conflict - extra conditions for setlease
+	 * @new: new file_lease being set
+	 * @old: old (extant) file_lease
+	 *
+	 * This allows the lease manager to add extra conditions when
+	 * setting a lease.
+	 *
+	 * Return values:
+	 *   %true: @new and @old conflict
+	 *   %false: No conflict detected
+	 */
+	bool (*lm_set_conflict)(struct file_lease *new, struct file_lease *old);
 };
 
 struct lock_manager {
diff --git a/include/linux/nfs4.h b/include/linux/nfs4.h
index 0d896ce296cec5..d72c23f778e1d5 100644
--- a/include/linux/nfs4.h
+++ b/include/linux/nfs4.h
@@ -681,6 +681,7 @@ enum {
 	NFSPROC4_CLNT_LISTXATTRS,
 	NFSPROC4_CLNT_REMOVEXATTR,
 	NFSPROC4_CLNT_READ_PLUS,
+	NFSPROC4_CLNT_GDD_GETATTR,
 };
 
 /* nfs41 types */
diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h
index d59116ac82099d..15fc4d65055750 100644
--- a/include/linux/nfs_fs.h
+++ b/include/linux/nfs_fs.h
@@ -318,6 +318,7 @@ struct nfs4_copy_state {
 #define NFS_INO_LAYOUTCOMMITTING (10)		/* layoutcommit inflight */
 #define NFS_INO_LAYOUTSTATS	(11)		/* layoutstats inflight */
 #define NFS_INO_ODIRECT		(12)		/* I/O setting is O_DIRECT */
+#define NFS_INO_GDD_GETATTR	(13)		/* Ask for dir deleg on next GETATTR */
 
 static inline struct nfs_inode *NFS_I(const struct inode *inode)
 {
diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h
index 92de074e63b98c..0ab744cf52d7b5 100644
--- a/include/linux/nfs_fs_sb.h
+++ b/include/linux/nfs_fs_sb.h
@@ -278,6 +278,7 @@ struct nfs_server {
 #define NFS_CAP_LGOPEN		(1U << 5)
 #define NFS_CAP_CASE_INSENSITIVE	(1U << 6)
 #define NFS_CAP_CASE_PRESERVING	(1U << 7)
+#define NFS_CAP_GET_DIR_DELEG	(1U << 13)
 #define NFS_CAP_POSIX_LOCK	(1U << 14)
 #define NFS_CAP_UIDGID_NOMAP	(1U << 15)
 #define NFS_CAP_STATEID_NFSV41	(1U << 16)
diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h
index d09b9773b20c82..85ee37ccc25e6c 100644
--- a/include/linux/nfs_xdr.h
+++ b/include/linux/nfs_xdr.h
@@ -1072,6 +1072,8 @@ struct nfs4_getattr_res {
 	struct nfs4_sequence_res	seq_res;
 	const struct nfs_server *	server;
 	struct nfs_fattr *		fattr;
+	nfs4_stateid			deleg;
+	u32				nf_status;
 };
 
 struct nfs4_link_arg {