[PATCH 00/24] vfs/nfsd: add support for CB_NOTIFY callbacks in directory delegations

[PATCH 00/24] vfs/nfsd: add support for CB_NOTIFY callbacks in directory delegations

[Jeff Layton]

This patchset builds on the directory delegation work we did a few
months ago, to add support for CB_NOTIFY callbacks for some events. In
particular, creates, unlinks and renames. The server also sends updated
directory attributes in the notifications. With this support, the client
can register interest in a directory and get notifications about changes
within it without losing its lease.

The series starts with patches to allow the vfs to ignore certain types
of events on directories. nfsd can then request these sorts of
delegations on directories, and then set up inotify watches on the
directory to trigger sending CB_NOTIFY events.

This has mainly been tested with pynfs, with some new testcases that
I'll be posting soon. They seem to work fine with those tests, but I
don't think we'll want to merge these until we have a complete
client-side implementation to test against.

Signed-off-by: Jeff Layton <jlayton@kernel.org>
---
Jeff Layton (24):
      filelock: add support for ignoring deleg breaks for dir change events
      filelock: add a tracepoint to start of break_lease()
      filelock: add an inode_lease_ignore_mask helper
      nfsd: add protocol support for CB_NOTIFY
      nfs_common: add new NOTIFY4_* flags proposed in RFC8881bis
      nfsd: allow nfsd to get a dir lease with an ignore mask
      vfs: add fsnotify_modify_mark_mask()
      nfsd: update the fsnotify mark when setting or removing a dir delegation
      nfsd: make nfsd4_callback_ops->prepare operation bool return
      nfsd: add callback encoding and decoding linkages for CB_NOTIFY
      nfsd: use RCU to protect fi_deleg_file
      nfsd: add data structures for handling CB_NOTIFY
      nfsd: add notification handlers for dir events
      nfsd: add tracepoint to dir_event handler
      nfsd: apply the notify mask to the delegation when requested
      nfsd: add helper to marshal a fattr4 from completed args
      nfsd: allow nfsd4_encode_fattr4_change() to work with no export
      nfsd: send basic file attributes in CB_NOTIFY
      nfsd: allow encoding a filehandle into fattr4 without a svc_fh
      nfsd: add a fi_connectable flag to struct nfs4_file
      nfsd: add the filehandle to returned attributes in CB_NOTIFY
      nfsd: properly track requested child attributes
      nfsd: track requested dir attributes
      nfsd: add support to CB_NOTIFY for dir attribute changes

 Documentation/sunrpc/xdr/nfs4_1.x    | 264 ++++++++++++++-
 fs/attr.c                            |   2 +-
 fs/locks.c                           |  89 +++++-
 fs/namei.c                           |  31 +-
 fs/nfsd/filecache.c                  |  57 +++-
 fs/nfsd/nfs4callback.c               |  60 +++-
 fs/nfsd/nfs4layouts.c                |   5 +-
 fs/nfsd/nfs4proc.c                   |  15 +
 fs/nfsd/nfs4state.c                  | 524 ++++++++++++++++++++++++++----
 fs/nfsd/nfs4xdr.c                    | 300 ++++++++++++++---
 fs/nfsd/nfs4xdr_gen.c                | 601 ++++++++++++++++++++++++++++++++++-
 fs/nfsd/nfs4xdr_gen.h                |  20 +-
 fs/nfsd/state.h                      |  70 +++-
 fs/nfsd/trace.h                      |  21 ++
 fs/nfsd/xdr4.h                       |   5 +
 fs/nfsd/xdr4cb.h                     |  12 +
 fs/notify/mark.c                     |  29 ++
 fs/posix_acl.c                       |   4 +-
 fs/xattr.c                           |   4 +-
 include/linux/filelock.h             |  54 +++-
 include/linux/fsnotify_backend.h     |   1 +
 include/linux/nfs4.h                 | 127 --------
 include/linux/sunrpc/xdrgen/nfs4_1.h | 291 ++++++++++++++++-
 include/trace/events/filelock.h      |  38 ++-
 include/uapi/linux/nfs4.h            |   2 -
 25 files changed, 2321 insertions(+), 305 deletions(-)
---
base-commit: bd5b9fd5e3d55bc412cec4bebe5a11da2151de4a
change-id: 20260325-dir-deleg-339066dd1017

Best regards,
-- 
Jeff Layton <jlayton@kernel.org>

[PATCH 01/24] filelock: add support for ignoring deleg breaks for dir change events

[Jeff Layton]

If a NFS client requests a directory delegation with a notification
bitmask covering directory change events, the server shouldn't recall
the delegation. Instead the client will be notified of the change after
the fact.

Add support for ignoring lease breaks on directory changes. Add a new
flags parameter to try_break_deleg() and teach __break_lease how to
ignore certain types of delegation break events.

Signed-off-by: Jeff Layton <jlayton@kernel.org>
---
 fs/attr.c                       |  2 +-
 fs/locks.c                      | 55 +++++++++++++++++++++++++++++++++++------
 fs/namei.c                      | 31 ++++++++++++-----------
 fs/posix_acl.c                  |  4 +--
 fs/xattr.c                      |  4 +--
 include/linux/filelock.h        | 53 +++++++++++++++++++++++++++------------
 include/trace/events/filelock.h |  5 +++-
 7 files changed, 110 insertions(+), 44 deletions(-)

diff --git a/fs/attr.c b/fs/attr.c
index e7d7c6d19fe9..28744f0e9ff4 100644
--- a/fs/attr.c
+++ b/fs/attr.c
@@ -547,7 +547,7 @@ int notify_change(struct mnt_idmap *idmap, struct dentry *dentry,
 	 * breaking the delegation in this case.
 	 */
 	if (!(ia_valid & ATTR_DELEG)) {
-		error = try_break_deleg(inode, delegated_inode);
+		error = try_break_deleg(inode, 0, delegated_inode);
 		if (error)
 			return error;
 	}
diff --git a/fs/locks.c b/fs/locks.c
index 8e44b1f6c15a..dafa0752fdce 100644
--- a/fs/locks.c
+++ b/fs/locks.c
@@ -1597,15 +1597,52 @@ any_leases_conflict(struct inode *inode, struct file_lease *breaker)
 	return false;
 }
 
+static bool
+ignore_dir_deleg_break(struct file_lease *fl, unsigned int flags)
+{
+	if ((flags & LEASE_BREAK_DIR_CREATE) && (fl->c.flc_flags & FL_IGN_DIR_CREATE))
+		return true;
+	if ((flags & LEASE_BREAK_DIR_DELETE) && (fl->c.flc_flags & FL_IGN_DIR_DELETE))
+		return true;
+	if ((flags & LEASE_BREAK_DIR_RENAME) && (fl->c.flc_flags & FL_IGN_DIR_RENAME))
+		return true;
+
+	return false;
+}
+
+static bool
+visible_leases_remaining(struct inode *inode, unsigned int flags)
+{
+	struct file_lock_context *ctx = locks_inode_context(inode);
+	struct file_lease *fl;
+
+	lockdep_assert_held(&ctx->flc_lock);
+
+	if (list_empty(&ctx->flc_lease))
+		return false;
+
+	if (!S_ISDIR(inode->i_mode))
+		return true;
+
+	list_for_each_entry(fl, &ctx->flc_lease, c.flc_list) {
+		if (!ignore_dir_deleg_break(fl, flags))
+			return true;
+	}
+	return false;
+}
+
 /**
- *	__break_lease	-	revoke all outstanding leases on file
- *	@inode: the inode of the file to return
- *	@flags: LEASE_BREAK_* flags
+ * __break_lease	-	revoke all outstanding leases on file
+ * @inode: the inode of the file to return
+ * @flags: LEASE_BREAK_* flags
  *
- *	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 block waiting for the
- *	lease break unless you specify LEASE_BREAK_NONBLOCK.
+ * break_lease (inlined for speed) has checked there already is at least
+ * some kind of lock (maybe a lease) on this file. Leases and Delegations
+ * are broken on a call to open() or truncate(). Delegations are also
+ * broken on any event that would change the ctime. Directory delegations
+ * are broken whenever the directory changes (unless the delegation is set
+ * up to ignore the event). This function can block waiting for the lease
+ * break unless you specify LEASE_BREAK_NONBLOCK.
  */
 int __break_lease(struct inode *inode, unsigned int flags)
 {
@@ -1655,6 +1692,8 @@ int __break_lease(struct inode *inode, unsigned int flags)
 	list_for_each_entry_safe(fl, tmp, &ctx->flc_lease, c.flc_list) {
 		if (!leases_conflict(&fl->c, &new_fl->c))
 			continue;
+		if (S_ISDIR(inode->i_mode) && ignore_dir_deleg_break(fl, flags))
+			continue;
 		if (want_write) {
 			if (fl->c.flc_flags & FL_UNLOCK_PENDING)
 				continue;
@@ -1670,7 +1709,7 @@ int __break_lease(struct inode *inode, unsigned int flags)
 			locks_delete_lock_ctx(&fl->c, &dispose);
 	}
 
-	if (list_empty(&ctx->flc_lease))
+	if (!visible_leases_remaining(inode, flags))
 		goto out;
 
 	if (flags & LEASE_BREAK_NONBLOCK) {
diff --git a/fs/namei.c b/fs/namei.c
index 9e5500dad14f..e3cbd9f877bd 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -4176,7 +4176,7 @@ int vfs_create(struct mnt_idmap *idmap, struct dentry *dentry, umode_t mode,
 	error = security_inode_create(dir, dentry, mode);
 	if (error)
 		return error;
-	error = try_break_deleg(dir, di);
+	error = try_break_deleg(dir, LEASE_BREAK_DIR_CREATE, di);
 	if (error)
 		return error;
 	error = dir->i_op->create(idmap, dir, dentry, mode, true);
@@ -4475,7 +4475,7 @@ 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);
+		error = try_break_deleg(dir_inode, LEASE_BREAK_DIR_CREATE, delegated_inode);
 		if (error)
 			goto out_dput;
 
@@ -5091,7 +5091,7 @@ int vfs_mknod(struct mnt_idmap *idmap, struct inode *dir,
 	if (error)
 		return error;
 
-	error = try_break_deleg(dir, delegated_inode);
+	error = try_break_deleg(dir, LEASE_BREAK_DIR_CREATE, delegated_inode);
 	if (error)
 		return error;
 
@@ -5232,7 +5232,7 @@ struct dentry *vfs_mkdir(struct mnt_idmap *idmap, struct inode *dir,
 	if (max_links && dir->i_nlink >= max_links)
 		goto err;
 
-	error = try_break_deleg(dir, delegated_inode);
+	error = try_break_deleg(dir, LEASE_BREAK_DIR_CREATE, delegated_inode);
 	if (error)
 		goto err;
 
@@ -5337,7 +5337,7 @@ int vfs_rmdir(struct mnt_idmap *idmap, struct inode *dir,
 	if (error)
 		goto out;
 
-	error = try_break_deleg(dir, delegated_inode);
+	error = try_break_deleg(dir, LEASE_BREAK_DIR_DELETE, delegated_inode);
 	if (error)
 		goto out;
 
@@ -5467,10 +5467,10 @@ 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);
+			error = try_break_deleg(dir, LEASE_BREAK_DIR_DELETE, delegated_inode);
 			if (error)
 				goto out;
-			error = try_break_deleg(target, delegated_inode);
+			error = try_break_deleg(target, 0, delegated_inode);
 			if (error)
 				goto out;
 			error = dir->i_op->unlink(dir, dentry);
@@ -5614,7 +5614,7 @@ int vfs_symlink(struct mnt_idmap *idmap, struct inode *dir,
 	if (error)
 		return error;
 
-	error = try_break_deleg(dir, delegated_inode);
+	error = try_break_deleg(dir, LEASE_BREAK_DIR_CREATE, delegated_inode);
 	if (error)
 		return error;
 
@@ -5745,9 +5745,9 @@ 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(dir, delegated_inode);
+		error = try_break_deleg(dir, LEASE_BREAK_DIR_CREATE, delegated_inode);
 		if (!error)
-			error = try_break_deleg(inode, delegated_inode);
+			error = try_break_deleg(inode, 0, delegated_inode);
 		if (!error)
 			error = dir->i_op->link(old_dentry, dir, new_dentry);
 	}
@@ -6011,21 +6011,24 @@ int vfs_rename(struct renamedata *rd)
 		    old_dir->i_nlink >= max_links)
 			goto out;
 	}
-	error = try_break_deleg(old_dir, delegated_inode);
+	error = try_break_deleg(old_dir,
+				old_dir == new_dir ? LEASE_BREAK_DIR_RENAME :
+						     LEASE_BREAK_DIR_DELETE,
+				delegated_inode);
 	if (error)
 		goto out;
 	if (new_dir != old_dir) {
-		error = try_break_deleg(new_dir, delegated_inode);
+		error = try_break_deleg(new_dir, LEASE_BREAK_DIR_CREATE, delegated_inode);
 		if (error)
 			goto out;
 	}
 	if (!is_dir) {
-		error = try_break_deleg(source, delegated_inode);
+		error = try_break_deleg(source, 0, delegated_inode);
 		if (error)
 			goto out;
 	}
 	if (target && !new_is_dir) {
-		error = try_break_deleg(target, delegated_inode);
+		error = try_break_deleg(target, 0, delegated_inode);
 		if (error)
 			goto out;
 	}
diff --git a/fs/posix_acl.c b/fs/posix_acl.c
index 12591c95c925..b4bfe4ddf64e 100644
--- a/fs/posix_acl.c
+++ b/fs/posix_acl.c
@@ -1126,7 +1126,7 @@ int vfs_set_acl(struct mnt_idmap *idmap, struct dentry *dentry,
 	if (error)
 		goto out_inode_unlock;
 
-	error = try_break_deleg(inode, &delegated_inode);
+	error = try_break_deleg(inode, 0, &delegated_inode);
 	if (error)
 		goto out_inode_unlock;
 
@@ -1234,7 +1234,7 @@ int vfs_remove_acl(struct mnt_idmap *idmap, struct dentry *dentry,
 	if (error)
 		goto out_inode_unlock;
 
-	error = try_break_deleg(inode, &delegated_inode);
+	error = try_break_deleg(inode, 0, &delegated_inode);
 	if (error)
 		goto out_inode_unlock;
 
diff --git a/fs/xattr.c b/fs/xattr.c
index 3e49e612e1ba..6b67a6e76eeb 100644
--- a/fs/xattr.c
+++ b/fs/xattr.c
@@ -288,7 +288,7 @@ __vfs_setxattr_locked(struct mnt_idmap *idmap, struct dentry *dentry,
 	if (error)
 		goto out;
 
-	error = try_break_deleg(inode, delegated_inode);
+	error = try_break_deleg(inode, 0, delegated_inode);
 	if (error)
 		goto out;
 
@@ -546,7 +546,7 @@ __vfs_removexattr_locked(struct mnt_idmap *idmap,
 	if (error)
 		goto out;
 
-	error = try_break_deleg(inode, delegated_inode);
+	error = try_break_deleg(inode, 0, delegated_inode);
 	if (error)
 		goto out;
 
diff --git a/include/linux/filelock.h b/include/linux/filelock.h
index 5f0a2fb31450..5a19cdb047da 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)	/* POSIX lock */
+#define FL_FLOCK		BIT(1)	/* BSD lock */
+#define FL_LEASE		BIT(2)	/* file lease */
+#define FL_DELEG		BIT(3)	/* NFSv4 delegation */
+#define FL_LAYOUT		BIT(4)	/* outstanding pNFS layout */
+#define FL_ACCESS		BIT(5)	/* not trying to lock, just looking */
+#define FL_EXISTS		BIT(6)	/* when unlocking, test for existence */
+#define FL_CLOSE		BIT(7)	/* unlock on close */
+#define FL_SLEEP		BIT(8)	/* A blocking lock */
+#define FL_DOWNGRADE_PENDING	BIT(9)	/* Lease is being downgraded */
+#define FL_UNLOCK_PENDING	BIT(10) /* Lease is being broken */
+#define FL_OFDLCK		BIT(11) /* POSIX lock "owned" by struct file */
+#define FL_RECLAIM		BIT(12) /* reclaiming from a reboot server */
+#define FL_IGN_DIR_CREATE	BIT(13) /* ignore DIR_CREATE events */
+#define FL_IGN_DIR_DELETE	BIT(14) /* ignore DIR_DELETE events */
+#define FL_IGN_DIR_RENAME	BIT(15) /* ignore DIR_RENAME events */
 
 #define FL_CLOSE_POSIX (FL_POSIX | FL_CLOSE)
 
@@ -222,6 +225,10 @@ struct file_lease *locks_alloc_lease(void);
 #define LEASE_BREAK_LAYOUT		BIT(2)	// break layouts only
 #define LEASE_BREAK_NONBLOCK		BIT(3)	// non-blocking break
 #define LEASE_BREAK_OPEN_RDONLY		BIT(4)	// readonly open event
+#define LEASE_BREAK_DIR_CREATE		BIT(6)  // dir deleg create event
+#define LEASE_BREAK_DIR_DELETE		BIT(7)  // dir deleg delete event
+#define LEASE_BREAK_DIR_RENAME		BIT(8)  // dir deleg rename event
+
 
 int __break_lease(struct inode *inode, unsigned int flags);
 void lease_get_mtime(struct inode *, struct timespec64 *time);
@@ -516,12 +523,26 @@ static inline bool is_delegated(struct delegated_inode *di)
 	return di->di_inode;
 }
 
-static inline int try_break_deleg(struct inode *inode,
+/**
+ * try_break_deleg - do a non-blocking delegation break
+ * @inode: inode that should have its delegations broken
+ * @flags: extra LEASE_BREAK_* flags to pass to break_deleg()
+ * @di: returns pointer to delegated inode (may be NULL)
+ *
+ * Break delegations in a non-blocking fashion. If there are
+ * outstanding delegations and @di is set, then an extra reference
+ * will be taken on @inode and @di->di_inode will be populated so
+ * that it may be waited upon.
+ *
+ * Returns 0 if there is no need to wait or an error. If -EWOULDBLOCK
+ * is returned, then @di will be populated (if non-NULL).
+ */
+static inline int try_break_deleg(struct inode *inode, unsigned int flags,
 				  struct delegated_inode *di)
 {
 	int ret;
 
-	ret = break_deleg(inode, LEASE_BREAK_NONBLOCK);
+	ret = break_deleg(inode, flags | LEASE_BREAK_NONBLOCK);
 	if (ret == -EWOULDBLOCK && di) {
 		di->di_inode = inode;
 		ihold(inode);
@@ -574,7 +595,7 @@ static inline int break_deleg(struct inode *inode, unsigned int flags)
 	return 0;
 }
 
-static inline int try_break_deleg(struct inode *inode,
+static inline int try_break_deleg(struct inode *inode, unsigned int flags,
 				  struct delegated_inode *delegated_inode)
 {
 	return 0;
diff --git a/include/trace/events/filelock.h b/include/trace/events/filelock.h
index 370016c38a5b..ef4bb0afb86a 100644
--- a/include/trace/events/filelock.h
+++ b/include/trace/events/filelock.h
@@ -28,7 +28,10 @@
 		{ FL_DOWNGRADE_PENDING,	"FL_DOWNGRADE_PENDING" },	\
 		{ FL_UNLOCK_PENDING,	"FL_UNLOCK_PENDING" },		\
 		{ FL_OFDLCK,		"FL_OFDLCK" },			\
-		{ FL_RECLAIM,		"FL_RECLAIM"})
+		{ FL_RECLAIM,		"FL_RECLAIM" },			\
+		{ FL_IGN_DIR_CREATE,	"FL_IGN_DIR_CREATE" },		\
+		{ FL_IGN_DIR_DELETE,	"FL_IGN_DIR_DELETE" },		\
+		{ FL_IGN_DIR_RENAME,	"FL_IGN_DIR_RENAME" })
 
 #define show_fl_type(val)				\
 	__print_symbolic(val,				\

-- 
2.53.0

[PATCH 02/24] filelock: add a tracepoint to start of break_lease()

[Jeff Layton]

...mostly to show the LEASE_BREAK_* flags.

Signed-off-by: Jeff Layton <jlayton@kernel.org>
---
 fs/locks.c                      |  2 ++
 include/trace/events/filelock.h | 33 +++++++++++++++++++++++++++++++++
 2 files changed, 35 insertions(+)

diff --git a/fs/locks.c b/fs/locks.c
index dafa0752fdce..5af6dca2d46c 100644
--- a/fs/locks.c
+++ b/fs/locks.c
@@ -1654,6 +1654,8 @@ int __break_lease(struct inode *inode, unsigned int flags)
 	bool want_write = !(flags & LEASE_BREAK_OPEN_RDONLY);
 	int error = 0;
 
+	trace_break_lease(inode, flags);
+
 	if (flags & LEASE_BREAK_LEASE)
 		type = FL_LEASE;
 	else if (flags & LEASE_BREAK_DELEG)
diff --git a/include/trace/events/filelock.h b/include/trace/events/filelock.h
index ef4bb0afb86a..fff0ee2d452d 100644
--- a/include/trace/events/filelock.h
+++ b/include/trace/events/filelock.h
@@ -120,6 +120,39 @@ DEFINE_EVENT(filelock_lock, flock_lock_inode,
 		TP_PROTO(struct inode *inode, struct file_lock *fl, int ret),
 		TP_ARGS(inode, fl, ret));
 
+#define show_lease_break_flags(val)					\
+	__print_flags(val, "|",						\
+		{ LEASE_BREAK_LEASE,		"LEASE" },		\
+		{ LEASE_BREAK_DELEG,		"DELEG" },		\
+		{ LEASE_BREAK_LAYOUT,		"LAYOUT" },		\
+		{ LEASE_BREAK_NONBLOCK,		"NONBLOCK" },		\
+		{ LEASE_BREAK_OPEN_RDONLY,	"OPEN_RDONLY" },	\
+		{ LEASE_BREAK_DIR_CREATE,	"DIR_CREATE" },		\
+		{ LEASE_BREAK_DIR_DELETE,	"DIR_DELETE" },		\
+		{ LEASE_BREAK_DIR_RENAME,	"DIR_RENAME" })
+
+TRACE_EVENT(break_lease,
+	TP_PROTO(struct inode *inode, unsigned int flags),
+
+	TP_ARGS(inode, flags),
+
+	TP_STRUCT__entry(
+		__field(unsigned long, i_ino)
+		__field(dev_t, s_dev)
+		__field(unsigned int, flags)
+	),
+
+	TP_fast_assign(
+		__entry->s_dev = inode->i_sb->s_dev;
+		__entry->i_ino = inode->i_ino;
+		__entry->flags = flags;
+	),
+
+	TP_printk("dev=0x%x:0x%x ino=0x%lx flags=%s",
+		  MAJOR(__entry->s_dev), MINOR(__entry->s_dev),
+		  __entry->i_ino, show_lease_break_flags(__entry->flags))
+);
+
 DECLARE_EVENT_CLASS(filelock_lease,
 	TP_PROTO(struct inode *inode, struct file_lease *fl),
 

-- 
2.53.0

[PATCH 03/24] filelock: add an inode_lease_ignore_mask helper

[Jeff Layton]

Add a new routine that returns a mask of all dir change events that are
currently ignored by any leases. nfsd will use this to determine how to
configure the fsnotify_mark mask.

Signed-off-by: Jeff Layton <jlayton@kernel.org>
---
 fs/locks.c               | 32 ++++++++++++++++++++++++++++++++
 include/linux/filelock.h |  1 +
 2 files changed, 33 insertions(+)

diff --git a/fs/locks.c b/fs/locks.c
index 5af6dca2d46c..04980b065734 100644
--- a/fs/locks.c
+++ b/fs/locks.c
@@ -1597,6 +1597,38 @@ any_leases_conflict(struct inode *inode, struct file_lease *breaker)
 	return false;
 }
 
+#define IGNORE_MASK	(FL_IGN_DIR_CREATE | FL_IGN_DIR_DELETE | FL_IGN_DIR_RENAME)
+
+/**
+ * inode_lease_ignore_mask - return union of all ignored inode events for this inode
+ * @inode: inode of which to get ignore mask
+ *
+ * Walk the list of leases, and return the result of all of
+ * their FL_IGN_DIR_* bits or'ed together.
+ */
+u32
+inode_lease_ignore_mask(struct inode *inode)
+{
+	struct file_lock_context *ctx;
+	struct file_lock_core *flc;
+	u32 mask = 0;
+
+	ctx = locks_inode_context(inode);
+	if (!ctx)
+		return 0;
+
+	spin_lock(&ctx->flc_lock);
+	list_for_each_entry(flc, &ctx->flc_lease, flc_list) {
+		mask |= flc->flc_flags & IGNORE_MASK;
+		/* If we already have everything, we can stop */
+		if (mask == IGNORE_MASK)
+			break;
+	}
+	spin_unlock(&ctx->flc_lock);
+	return mask;
+}
+EXPORT_SYMBOL_GPL(inode_lease_ignore_mask);
+
 static bool
 ignore_dir_deleg_break(struct file_lease *fl, unsigned int flags)
 {
diff --git a/include/linux/filelock.h b/include/linux/filelock.h
index 5a19cdb047da..416483b136f1 100644
--- a/include/linux/filelock.h
+++ b/include/linux/filelock.h
@@ -236,6 +236,7 @@ int generic_setlease(struct file *, int, struct file_lease **, void **priv);
 int kernel_setlease(struct file *, int, struct file_lease **, void **);
 int vfs_setlease(struct file *, int, struct file_lease **, void **);
 int lease_modify(struct file_lease *, int, struct list_head *);
+u32 inode_lease_ignore_mask(struct inode *inode);
 
 struct notifier_block;
 int lease_register_notifier(struct notifier_block *);

-- 
2.53.0

[PATCH 04/24] nfsd: add protocol support for CB_NOTIFY

[Jeff Layton]

Add the necessary bits to nfs4_1.x and remove the duplicate definitions
from nfs4.h and the uapi nfs4 header. Regenerate the xdr files.

Signed-off-by: Jeff Layton <jlayton@kernel.org>
---
 Documentation/sunrpc/xdr/nfs4_1.x    | 250 ++++++++++++++-
 fs/nfsd/nfs4xdr_gen.c                | 590 ++++++++++++++++++++++++++++++++++-
 fs/nfsd/nfs4xdr_gen.h                |  20 +-
 fs/nfsd/trace.h                      |   1 +
 include/linux/nfs4.h                 | 127 --------
 include/linux/sunrpc/xdrgen/nfs4_1.h | 280 ++++++++++++++++-
 include/uapi/linux/nfs4.h            |   2 -
 7 files changed, 1129 insertions(+), 141 deletions(-)

diff --git a/Documentation/sunrpc/xdr/nfs4_1.x b/Documentation/sunrpc/xdr/nfs4_1.x
index 5b45547b2ebc..632f5b579c39 100644
--- a/Documentation/sunrpc/xdr/nfs4_1.x
+++ b/Documentation/sunrpc/xdr/nfs4_1.x
@@ -45,19 +45,165 @@ pragma header nfs4;
 /*
  * Basic typedefs for RFC 1832 data type definitions
  */
-typedef hyper		int64_t;
-typedef unsigned int	uint32_t;
+typedef int                  int32_t;
+typedef unsigned int         uint32_t;
+typedef hyper                int64_t;
+typedef unsigned hyper       uint64_t;
+
+const NFS4_VERIFIER_SIZE        = 8;
+const NFS4_FHSIZE               = 128;
+
+enum nfsstat4 {
+ NFS4_OK                = 0,    /* everything is okay      */
+ NFS4ERR_PERM           = 1,    /* caller not privileged   */
+ NFS4ERR_NOENT          = 2,    /* no such file/directory  */
+ NFS4ERR_IO             = 5,    /* hard I/O error          */
+ NFS4ERR_NXIO           = 6,    /* no such device          */
+ NFS4ERR_ACCESS         = 13,   /* access denied           */
+ NFS4ERR_EXIST          = 17,   /* file already exists     */
+ NFS4ERR_XDEV           = 18,   /* different filesystems   */
+
+ /*
+  * Please do not allocate value 19; it was used in NFSv3
+  * and we do not want a value in NFSv3 to have a different
+  * meaning in NFSv4.x.
+  */
+
+ NFS4ERR_NOTDIR         = 20,   /* should be a directory   */
+ NFS4ERR_ISDIR          = 21,   /* should not be directory */
+ NFS4ERR_INVAL          = 22,   /* invalid argument        */
+ NFS4ERR_FBIG           = 27,   /* file exceeds server max */
+ NFS4ERR_NOSPC          = 28,   /* no space on filesystem  */
+ NFS4ERR_ROFS           = 30,   /* read-only filesystem    */
+ NFS4ERR_MLINK          = 31,   /* too many hard links     */
+ NFS4ERR_NAMETOOLONG    = 63,   /* name exceeds server max */
+ NFS4ERR_NOTEMPTY       = 66,   /* directory not empty     */
+ NFS4ERR_DQUOT          = 69,   /* hard quota limit reached*/
+ NFS4ERR_STALE          = 70,   /* file no longer exists   */
+ NFS4ERR_BADHANDLE      = 10001,/* Illegal filehandle      */
+ NFS4ERR_BAD_COOKIE     = 10003,/* READDIR cookie is stale */
+ NFS4ERR_NOTSUPP        = 10004,/* operation not supported */
+ NFS4ERR_TOOSMALL       = 10005,/* response limit exceeded */
+ NFS4ERR_SERVERFAULT    = 10006,/* undefined server error  */
+ NFS4ERR_BADTYPE        = 10007,/* type invalid for CREATE */
+ NFS4ERR_DELAY          = 10008,/* file "busy" - retry     */
+ NFS4ERR_SAME           = 10009,/* nverify says attrs same */
+ NFS4ERR_DENIED         = 10010,/* lock unavailable        */
+ NFS4ERR_EXPIRED        = 10011,/* lock lease expired      */
+ NFS4ERR_LOCKED         = 10012,/* I/O failed due to lock  */
+ NFS4ERR_GRACE          = 10013,/* in grace period         */
+ NFS4ERR_FHEXPIRED      = 10014,/* filehandle expired      */
+ NFS4ERR_SHARE_DENIED   = 10015,/* share reserve denied    */
+ NFS4ERR_WRONGSEC       = 10016,/* wrong security flavor   */
+ NFS4ERR_CLID_INUSE     = 10017,/* clientid in use         */
+
+ /* NFS4ERR_RESOURCE is not a valid error in NFSv4.1 */
+ NFS4ERR_RESOURCE       = 10018,/* resource exhaustion     */
+
+ NFS4ERR_MOVED          = 10019,/* filesystem relocated    */
+ NFS4ERR_NOFILEHANDLE   = 10020,/* current FH is not set   */
+ NFS4ERR_MINOR_VERS_MISMATCH= 10021,/* minor vers not supp */
+ NFS4ERR_STALE_CLIENTID = 10022,/* server has rebooted     */
+ NFS4ERR_STALE_STATEID  = 10023,/* server has rebooted     */
+ NFS4ERR_OLD_STATEID    = 10024,/* state is out of sync    */
+ NFS4ERR_BAD_STATEID    = 10025,/* incorrect stateid       */
+ NFS4ERR_BAD_SEQID      = 10026,/* request is out of seq.  */
+ NFS4ERR_NOT_SAME       = 10027,/* verify - attrs not same */
+ NFS4ERR_LOCK_RANGE     = 10028,/* overlapping lock range  */
+ NFS4ERR_SYMLINK        = 10029,/* should be file/directory*/
+ NFS4ERR_RESTOREFH      = 10030,/* no saved filehandle     */
+ NFS4ERR_LEASE_MOVED    = 10031,/* some filesystem moved   */
+ NFS4ERR_ATTRNOTSUPP    = 10032,/* recommended attr not sup*/
+ NFS4ERR_NO_GRACE       = 10033,/* reclaim outside of grace*/
+ NFS4ERR_RECLAIM_BAD    = 10034,/* reclaim error at server */
+ NFS4ERR_RECLAIM_CONFLICT= 10035,/* conflict on reclaim    */
+ NFS4ERR_BADXDR         = 10036,/* XDR decode failed       */
+ NFS4ERR_LOCKS_HELD     = 10037,/* file locks held at CLOSE*/
+ NFS4ERR_OPENMODE       = 10038,/* conflict in OPEN and I/O*/
+ NFS4ERR_BADOWNER       = 10039,/* owner translation bad   */
+ NFS4ERR_BADCHAR        = 10040,/* utf-8 char not supported*/
+ NFS4ERR_BADNAME        = 10041,/* name not supported      */
+ NFS4ERR_BAD_RANGE      = 10042,/* lock range not supported*/
+ NFS4ERR_LOCK_NOTSUPP   = 10043,/* no atomic up/downgrade  */
+ NFS4ERR_OP_ILLEGAL     = 10044,/* undefined operation     */
+ NFS4ERR_DEADLOCK       = 10045,/* file locking deadlock   */
+ NFS4ERR_FILE_OPEN      = 10046,/* open file blocks op.    */
+ NFS4ERR_ADMIN_REVOKED  = 10047,/* lockowner state revoked */
+ NFS4ERR_CB_PATH_DOWN   = 10048,/* callback path down      */
+
+ /* NFSv4.1 errors start here. */
+
+ NFS4ERR_BADIOMODE      = 10049,
+ NFS4ERR_BADLAYOUT      = 10050,
+ NFS4ERR_BAD_SESSION_DIGEST = 10051,
+ NFS4ERR_BADSESSION     = 10052,
+ NFS4ERR_BADSLOT        = 10053,
+ NFS4ERR_COMPLETE_ALREADY = 10054,
+ NFS4ERR_CONN_NOT_BOUND_TO_SESSION = 10055,
+ NFS4ERR_DELEG_ALREADY_WANTED = 10056,
+ NFS4ERR_BACK_CHAN_BUSY = 10057,/*backchan reqs outstanding*/
+ NFS4ERR_LAYOUTTRYLATER = 10058,
+ NFS4ERR_LAYOUTUNAVAILABLE = 10059,
+ NFS4ERR_NOMATCHING_LAYOUT = 10060,
+ NFS4ERR_RECALLCONFLICT = 10061,
+ NFS4ERR_UNKNOWN_LAYOUTTYPE = 10062,
+ NFS4ERR_SEQ_MISORDERED = 10063,/* unexpected seq.ID in req*/
+ NFS4ERR_SEQUENCE_POS   = 10064,/* [CB_]SEQ. op not 1st op */
+ NFS4ERR_REQ_TOO_BIG    = 10065,/* request too big         */
+ NFS4ERR_REP_TOO_BIG    = 10066,/* reply too big           */
+ NFS4ERR_REP_TOO_BIG_TO_CACHE =10067,/* rep. not all cached*/
+ NFS4ERR_RETRY_UNCACHED_REP =10068,/* retry & rep. uncached*/
+ NFS4ERR_UNSAFE_COMPOUND =10069,/* retry/recovery too hard */
+ NFS4ERR_TOO_MANY_OPS   = 10070,/*too many ops in [CB_]COMP*/
+ NFS4ERR_OP_NOT_IN_SESSION =10071,/* op needs [CB_]SEQ. op */
+ NFS4ERR_HASH_ALG_UNSUPP = 10072, /* hash alg. not supp.   */
+                                /* Error 10073 is unused.  */
+ NFS4ERR_CLIENTID_BUSY  = 10074,/* clientid has state      */
+ NFS4ERR_PNFS_IO_HOLE   = 10075,/* IO to _SPARSE file hole */
+ NFS4ERR_SEQ_FALSE_RETRY= 10076,/* Retry != original req.  */
+ NFS4ERR_BAD_HIGH_SLOT  = 10077,/* req has bad highest_slot*/
+ NFS4ERR_DEADSESSION    = 10078,/*new req sent to dead sess*/
+ NFS4ERR_ENCR_ALG_UNSUPP= 10079,/* encr alg. not supp.     */
+ NFS4ERR_PNFS_NO_LAYOUT = 10080,/* I/O without a layout    */
+ NFS4ERR_NOT_ONLY_OP    = 10081,/* addl ops not allowed    */
+ NFS4ERR_WRONG_CRED     = 10082,/* op done by wrong cred   */
+ NFS4ERR_WRONG_TYPE     = 10083,/* op on wrong type object */
+ NFS4ERR_DIRDELEG_UNAVAIL=10084,/* delegation not avail.   */
+ NFS4ERR_REJECT_DELEG   = 10085,/* cb rejected delegation  */
+ NFS4ERR_RETURNCONFLICT = 10086,/* layout get before return*/
+ NFS4ERR_DELEG_REVOKED  = 10087, /* deleg./layout revoked   */
+ NFS4ERR_PARTNER_NOTSUPP = 10088,
+ NFS4ERR_PARTNER_NO_AUTH = 10089,
+ NFS4ERR_UNION_NOTSUPP = 10090,
+ NFS4ERR_OFFLOAD_DENIED = 10091,
+ NFS4ERR_WRONG_LFS = 10092,
+ NFS4ERR_BADLABEL = 10093,
+ NFS4ERR_OFFLOAD_NO_REQS = 10094,
+ NFS4ERR_NOXATTR = 10095,
+ NFS4ERR_XATTR2BIG = 10096,
+
+ /* always set this to one more than the last one in the enum */
+ NFS4ERR_FIRST_FREE = 10097
+};
 
 /*
  * Basic data types
  */
+typedef opaque		attrlist4<>;
 typedef uint32_t	bitmap4<>;
+typedef opaque		verifier4[NFS4_VERIFIER_SIZE];
+typedef uint64_t        nfs_cookie4;
+typedef opaque		nfs_fh4<NFS4_FHSIZE>;
 
 typedef opaque		utf8string<>;
 typedef utf8string	utf8str_cis;
 typedef utf8string	utf8str_cs;
 typedef utf8string	utf8str_mixed;
 
+typedef utf8str_cs      component4;
+typedef utf8str_cs      linktext4;
+typedef component4      pathname4<>;
+
 /*
  * Timeval
  */
@@ -66,6 +212,21 @@ struct nfstime4 {
 	uint32_t	nseconds;
 };
 
+/*
+ * File attribute container
+ */
+struct fattr4 {
+        bitmap4         attrmask;
+        attrlist4       attr_vals;
+};
+
+/*
+ * Stateid
+ */
+struct stateid4 {
+        uint32_t        seqid;
+        opaque          other[12];
+};
 
 /*
  * The following content was extracted from draft-ietf-nfsv4-delstid
@@ -245,3 +406,88 @@ const FATTR4_ACL_TRUEFORM	= 89;
 const FATTR4_ACL_TRUEFORM_SCOPE	= 90;
 const FATTR4_POSIX_DEFAULT_ACL	= 91;
 const FATTR4_POSIX_ACCESS_ACL	= 92;
+
+/*
+ * Directory notification types.
+ */
+enum notify_type4 {
+        NOTIFY4_CHANGE_CHILD_ATTRS = 0,
+        NOTIFY4_CHANGE_DIR_ATTRS = 1,
+        NOTIFY4_REMOVE_ENTRY = 2,
+        NOTIFY4_ADD_ENTRY = 3,
+        NOTIFY4_RENAME_ENTRY = 4,
+        NOTIFY4_CHANGE_COOKIE_VERIFIER = 5
+};
+
+/* Changed entry information.  */
+struct notify_entry4 {
+        component4      ne_file;
+        fattr4          ne_attrs;
+};
+
+/* Previous entry information */
+struct prev_entry4 {
+        notify_entry4   pe_prev_entry;
+        /* what READDIR returned for this entry */
+        nfs_cookie4     pe_prev_entry_cookie;
+};
+
+struct notify_remove4 {
+        notify_entry4   nrm_old_entry;
+        nfs_cookie4     nrm_old_entry_cookie;
+};
+pragma public notify_remove4;
+
+struct notify_add4 {
+        /*
+         * Information on object
+         * possibly renamed over.
+         */
+        notify_remove4      nad_old_entry<1>;
+        notify_entry4       nad_new_entry;
+        /* what READDIR would have returned for this entry */
+        nfs_cookie4         nad_new_entry_cookie<1>;
+        prev_entry4         nad_prev_entry<1>;
+        bool                nad_last_entry;
+};
+pragma public notify_add4;
+
+struct notify_attr4 {
+        notify_entry4   na_changed_entry;
+};
+pragma public notify_attr4;
+
+struct notify_rename4 {
+        notify_remove4  nrn_old_entry;
+        notify_add4     nrn_new_entry;
+};
+pragma public notify_rename4;
+
+struct notify_verifier4 {
+        verifier4       nv_old_cookieverf;
+        verifier4       nv_new_cookieverf;
+};
+
+/*
+ * Objects of type notify_<>4 and
+ * notify_device_<>4 are encoded in this.
+ */
+typedef opaque notifylist4<>;
+
+struct notify4 {
+        /* composed from notify_type4 or notify_deviceid_type4 */
+        bitmap4         notify_mask;
+        notifylist4     notify_vals;
+};
+
+struct CB_NOTIFY4args {
+        stateid4    cna_stateid;
+        nfs_fh4     cna_fh;
+        notify4     cna_changes<>;
+};
+pragma public CB_NOTIFY4args;
+
+struct CB_NOTIFY4res {
+        nfsstat4    cnr_status;
+};
+pragma public CB_NOTIFY4res;
diff --git a/fs/nfsd/nfs4xdr_gen.c b/fs/nfsd/nfs4xdr_gen.c
index 824497051b87..5e656d6bbb8e 100644
--- a/fs/nfsd/nfs4xdr_gen.c
+++ b/fs/nfsd/nfs4xdr_gen.c
@@ -1,16 +1,16 @@
 // SPDX-License-Identifier: GPL-2.0
 // Generated by xdrgen. Manual edits will be lost.
 // XDR specification file: ../../Documentation/sunrpc/xdr/nfs4_1.x
-// XDR specification modification time: Thu Jan  8 23:12:07 2026
+// XDR specification modification time: Wed Mar 25 11:39:22 2026
 
 #include <linux/sunrpc/svc.h>
 
 #include "nfs4xdr_gen.h"
 
 static bool __maybe_unused
-xdrgen_decode_int64_t(struct xdr_stream *xdr, int64_t *ptr)
+xdrgen_decode_int32_t(struct xdr_stream *xdr, int32_t *ptr)
 {
-	return xdrgen_decode_hyper(xdr, ptr);
+	return xdrgen_decode_int(xdr, ptr);
 }
 
 static bool __maybe_unused
@@ -19,6 +19,155 @@ xdrgen_decode_uint32_t(struct xdr_stream *xdr, uint32_t *ptr)
 	return xdrgen_decode_unsigned_int(xdr, ptr);
 }
 
+static bool __maybe_unused
+xdrgen_decode_int64_t(struct xdr_stream *xdr, int64_t *ptr)
+{
+	return xdrgen_decode_hyper(xdr, ptr);
+}
+
+static bool __maybe_unused
+xdrgen_decode_uint64_t(struct xdr_stream *xdr, uint64_t *ptr)
+{
+	return xdrgen_decode_unsigned_hyper(xdr, ptr);
+}
+
+static bool __maybe_unused
+xdrgen_decode_nfsstat4(struct xdr_stream *xdr, nfsstat4 *ptr)
+{
+	u32 val;
+
+	if (xdr_stream_decode_u32(xdr, &val) < 0)
+		return false;
+	/* Compiler may optimize to a range check for dense enums */
+	switch (val) {
+	case NFS4_OK:
+	case NFS4ERR_PERM:
+	case NFS4ERR_NOENT:
+	case NFS4ERR_IO:
+	case NFS4ERR_NXIO:
+	case NFS4ERR_ACCESS:
+	case NFS4ERR_EXIST:
+	case NFS4ERR_XDEV:
+	case NFS4ERR_NOTDIR:
+	case NFS4ERR_ISDIR:
+	case NFS4ERR_INVAL:
+	case NFS4ERR_FBIG:
+	case NFS4ERR_NOSPC:
+	case NFS4ERR_ROFS:
+	case NFS4ERR_MLINK:
+	case NFS4ERR_NAMETOOLONG:
+	case NFS4ERR_NOTEMPTY:
+	case NFS4ERR_DQUOT:
+	case NFS4ERR_STALE:
+	case NFS4ERR_BADHANDLE:
+	case NFS4ERR_BAD_COOKIE:
+	case NFS4ERR_NOTSUPP:
+	case NFS4ERR_TOOSMALL:
+	case NFS4ERR_SERVERFAULT:
+	case NFS4ERR_BADTYPE:
+	case NFS4ERR_DELAY:
+	case NFS4ERR_SAME:
+	case NFS4ERR_DENIED:
+	case NFS4ERR_EXPIRED:
+	case NFS4ERR_LOCKED:
+	case NFS4ERR_GRACE:
+	case NFS4ERR_FHEXPIRED:
+	case NFS4ERR_SHARE_DENIED:
+	case NFS4ERR_WRONGSEC:
+	case NFS4ERR_CLID_INUSE:
+	case NFS4ERR_RESOURCE:
+	case NFS4ERR_MOVED:
+	case NFS4ERR_NOFILEHANDLE:
+	case NFS4ERR_MINOR_VERS_MISMATCH:
+	case NFS4ERR_STALE_CLIENTID:
+	case NFS4ERR_STALE_STATEID:
+	case NFS4ERR_OLD_STATEID:
+	case NFS4ERR_BAD_STATEID:
+	case NFS4ERR_BAD_SEQID:
+	case NFS4ERR_NOT_SAME:
+	case NFS4ERR_LOCK_RANGE:
+	case NFS4ERR_SYMLINK:
+	case NFS4ERR_RESTOREFH:
+	case NFS4ERR_LEASE_MOVED:
+	case NFS4ERR_ATTRNOTSUPP:
+	case NFS4ERR_NO_GRACE:
+	case NFS4ERR_RECLAIM_BAD:
+	case NFS4ERR_RECLAIM_CONFLICT:
+	case NFS4ERR_BADXDR:
+	case NFS4ERR_LOCKS_HELD:
+	case NFS4ERR_OPENMODE:
+	case NFS4ERR_BADOWNER:
+	case NFS4ERR_BADCHAR:
+	case NFS4ERR_BADNAME:
+	case NFS4ERR_BAD_RANGE:
+	case NFS4ERR_LOCK_NOTSUPP:
+	case NFS4ERR_OP_ILLEGAL:
+	case NFS4ERR_DEADLOCK:
+	case NFS4ERR_FILE_OPEN:
+	case NFS4ERR_ADMIN_REVOKED:
+	case NFS4ERR_CB_PATH_DOWN:
+	case NFS4ERR_BADIOMODE:
+	case NFS4ERR_BADLAYOUT:
+	case NFS4ERR_BAD_SESSION_DIGEST:
+	case NFS4ERR_BADSESSION:
+	case NFS4ERR_BADSLOT:
+	case NFS4ERR_COMPLETE_ALREADY:
+	case NFS4ERR_CONN_NOT_BOUND_TO_SESSION:
+	case NFS4ERR_DELEG_ALREADY_WANTED:
+	case NFS4ERR_BACK_CHAN_BUSY:
+	case NFS4ERR_LAYOUTTRYLATER:
+	case NFS4ERR_LAYOUTUNAVAILABLE:
+	case NFS4ERR_NOMATCHING_LAYOUT:
+	case NFS4ERR_RECALLCONFLICT:
+	case NFS4ERR_UNKNOWN_LAYOUTTYPE:
+	case NFS4ERR_SEQ_MISORDERED:
+	case NFS4ERR_SEQUENCE_POS:
+	case NFS4ERR_REQ_TOO_BIG:
+	case NFS4ERR_REP_TOO_BIG:
+	case NFS4ERR_REP_TOO_BIG_TO_CACHE:
+	case NFS4ERR_RETRY_UNCACHED_REP:
+	case NFS4ERR_UNSAFE_COMPOUND:
+	case NFS4ERR_TOO_MANY_OPS:
+	case NFS4ERR_OP_NOT_IN_SESSION:
+	case NFS4ERR_HASH_ALG_UNSUPP:
+	case NFS4ERR_CLIENTID_BUSY:
+	case NFS4ERR_PNFS_IO_HOLE:
+	case NFS4ERR_SEQ_FALSE_RETRY:
+	case NFS4ERR_BAD_HIGH_SLOT:
+	case NFS4ERR_DEADSESSION:
+	case NFS4ERR_ENCR_ALG_UNSUPP:
+	case NFS4ERR_PNFS_NO_LAYOUT:
+	case NFS4ERR_NOT_ONLY_OP:
+	case NFS4ERR_WRONG_CRED:
+	case NFS4ERR_WRONG_TYPE:
+	case NFS4ERR_DIRDELEG_UNAVAIL:
+	case NFS4ERR_REJECT_DELEG:
+	case NFS4ERR_RETURNCONFLICT:
+	case NFS4ERR_DELEG_REVOKED:
+	case NFS4ERR_PARTNER_NOTSUPP:
+	case NFS4ERR_PARTNER_NO_AUTH:
+	case NFS4ERR_UNION_NOTSUPP:
+	case NFS4ERR_OFFLOAD_DENIED:
+	case NFS4ERR_WRONG_LFS:
+	case NFS4ERR_BADLABEL:
+	case NFS4ERR_OFFLOAD_NO_REQS:
+	case NFS4ERR_NOXATTR:
+	case NFS4ERR_XATTR2BIG:
+	case NFS4ERR_FIRST_FREE:
+		break;
+	default:
+		return false;
+	}
+	*ptr = val;
+	return true;
+}
+
+static bool __maybe_unused
+xdrgen_decode_attrlist4(struct xdr_stream *xdr, attrlist4 *ptr)
+{
+	return xdrgen_decode_opaque(xdr, ptr, 0);
+}
+
 static bool __maybe_unused
 xdrgen_decode_bitmap4(struct xdr_stream *xdr, bitmap4 *ptr)
 {
@@ -30,6 +179,24 @@ xdrgen_decode_bitmap4(struct xdr_stream *xdr, bitmap4 *ptr)
 	return true;
 }
 
+static bool __maybe_unused
+xdrgen_decode_verifier4(struct xdr_stream *xdr, verifier4 *ptr)
+{
+	return xdr_stream_decode_opaque_fixed(xdr, ptr, NFS4_VERIFIER_SIZE) == 0;
+}
+
+static bool __maybe_unused
+xdrgen_decode_nfs_cookie4(struct xdr_stream *xdr, nfs_cookie4 *ptr)
+{
+	return xdrgen_decode_uint64_t(xdr, ptr);
+}
+
+static bool __maybe_unused
+xdrgen_decode_nfs_fh4(struct xdr_stream *xdr, nfs_fh4 *ptr)
+{
+	return xdrgen_decode_opaque(xdr, ptr, NFS4_FHSIZE);
+}
+
 static bool __maybe_unused
 xdrgen_decode_utf8string(struct xdr_stream *xdr, utf8string *ptr)
 {
@@ -54,6 +221,29 @@ xdrgen_decode_utf8str_mixed(struct xdr_stream *xdr, utf8str_mixed *ptr)
 	return xdrgen_decode_utf8string(xdr, ptr);
 }
 
+static bool __maybe_unused
+xdrgen_decode_component4(struct xdr_stream *xdr, component4 *ptr)
+{
+	return xdrgen_decode_utf8str_cs(xdr, ptr);
+}
+
+static bool __maybe_unused
+xdrgen_decode_linktext4(struct xdr_stream *xdr, linktext4 *ptr)
+{
+	return xdrgen_decode_utf8str_cs(xdr, ptr);
+}
+
+static bool __maybe_unused
+xdrgen_decode_pathname4(struct xdr_stream *xdr, pathname4 *ptr)
+{
+	if (xdr_stream_decode_u32(xdr, &ptr->count) < 0)
+		return false;
+	for (u32 i = 0; i < ptr->count; i++)
+		if (!xdrgen_decode_component4(xdr, &ptr->element[i]))
+			return false;
+	return true;
+}
+
 static bool __maybe_unused
 xdrgen_decode_nfstime4(struct xdr_stream *xdr, struct nfstime4 *ptr)
 {
@@ -64,6 +254,26 @@ xdrgen_decode_nfstime4(struct xdr_stream *xdr, struct nfstime4 *ptr)
 	return true;
 }
 
+static bool __maybe_unused
+xdrgen_decode_fattr4(struct xdr_stream *xdr, struct fattr4 *ptr)
+{
+	if (!xdrgen_decode_bitmap4(xdr, &ptr->attrmask))
+		return false;
+	if (!xdrgen_decode_attrlist4(xdr, &ptr->attr_vals))
+		return false;
+	return true;
+}
+
+static bool __maybe_unused
+xdrgen_decode_stateid4(struct xdr_stream *xdr, struct stateid4 *ptr)
+{
+	if (!xdrgen_decode_uint32_t(xdr, &ptr->seqid))
+		return false;
+	if (xdr_stream_decode_opaque_fixed(xdr, ptr->other, 12) < 0)
+		return false;
+	return true;
+}
+
 static bool __maybe_unused
 xdrgen_decode_fattr4_offline(struct xdr_stream *xdr, fattr4_offline *ptr)
 {
@@ -366,9 +576,160 @@ xdrgen_decode_fattr4_posix_access_acl(struct xdr_stream *xdr, fattr4_posix_acces
  */
 
 static bool __maybe_unused
-xdrgen_encode_int64_t(struct xdr_stream *xdr, const int64_t value)
+xdrgen_decode_notify_type4(struct xdr_stream *xdr, notify_type4 *ptr)
 {
-	return xdrgen_encode_hyper(xdr, value);
+	u32 val;
+
+	if (xdr_stream_decode_u32(xdr, &val) < 0)
+		return false;
+	/* Compiler may optimize to a range check for dense enums */
+	switch (val) {
+	case NOTIFY4_CHANGE_CHILD_ATTRS:
+	case NOTIFY4_CHANGE_DIR_ATTRS:
+	case NOTIFY4_REMOVE_ENTRY:
+	case NOTIFY4_ADD_ENTRY:
+	case NOTIFY4_RENAME_ENTRY:
+	case NOTIFY4_CHANGE_COOKIE_VERIFIER:
+		break;
+	default:
+		return false;
+	}
+	*ptr = val;
+	return true;
+}
+
+static bool __maybe_unused
+xdrgen_decode_notify_entry4(struct xdr_stream *xdr, struct notify_entry4 *ptr)
+{
+	if (!xdrgen_decode_component4(xdr, &ptr->ne_file))
+		return false;
+	if (!xdrgen_decode_fattr4(xdr, &ptr->ne_attrs))
+		return false;
+	return true;
+}
+
+static bool __maybe_unused
+xdrgen_decode_prev_entry4(struct xdr_stream *xdr, struct prev_entry4 *ptr)
+{
+	if (!xdrgen_decode_notify_entry4(xdr, &ptr->pe_prev_entry))
+		return false;
+	if (!xdrgen_decode_nfs_cookie4(xdr, &ptr->pe_prev_entry_cookie))
+		return false;
+	return true;
+}
+
+bool
+xdrgen_decode_notify_remove4(struct xdr_stream *xdr, struct notify_remove4 *ptr)
+{
+	if (!xdrgen_decode_notify_entry4(xdr, &ptr->nrm_old_entry))
+		return false;
+	if (!xdrgen_decode_nfs_cookie4(xdr, &ptr->nrm_old_entry_cookie))
+		return false;
+	return true;
+}
+
+bool
+xdrgen_decode_notify_add4(struct xdr_stream *xdr, struct notify_add4 *ptr)
+{
+	if (xdr_stream_decode_u32(xdr, &ptr->nad_old_entry.count) < 0)
+		return false;
+	if (ptr->nad_old_entry.count > 1)
+		return false;
+	for (u32 i = 0; i < ptr->nad_old_entry.count; i++)
+		if (!xdrgen_decode_notify_remove4(xdr, &ptr->nad_old_entry.element[i]))
+			return false;
+	if (!xdrgen_decode_notify_entry4(xdr, &ptr->nad_new_entry))
+		return false;
+	if (xdr_stream_decode_u32(xdr, &ptr->nad_new_entry_cookie.count) < 0)
+		return false;
+	if (ptr->nad_new_entry_cookie.count > 1)
+		return false;
+	for (u32 i = 0; i < ptr->nad_new_entry_cookie.count; i++)
+		if (!xdrgen_decode_nfs_cookie4(xdr, &ptr->nad_new_entry_cookie.element[i]))
+			return false;
+	if (xdr_stream_decode_u32(xdr, &ptr->nad_prev_entry.count) < 0)
+		return false;
+	if (ptr->nad_prev_entry.count > 1)
+		return false;
+	for (u32 i = 0; i < ptr->nad_prev_entry.count; i++)
+		if (!xdrgen_decode_prev_entry4(xdr, &ptr->nad_prev_entry.element[i]))
+			return false;
+	if (!xdrgen_decode_bool(xdr, &ptr->nad_last_entry))
+		return false;
+	return true;
+}
+
+bool
+xdrgen_decode_notify_attr4(struct xdr_stream *xdr, struct notify_attr4 *ptr)
+{
+	if (!xdrgen_decode_notify_entry4(xdr, &ptr->na_changed_entry))
+		return false;
+	return true;
+}
+
+bool
+xdrgen_decode_notify_rename4(struct xdr_stream *xdr, struct notify_rename4 *ptr)
+{
+	if (!xdrgen_decode_notify_remove4(xdr, &ptr->nrn_old_entry))
+		return false;
+	if (!xdrgen_decode_notify_add4(xdr, &ptr->nrn_new_entry))
+		return false;
+	return true;
+}
+
+static bool __maybe_unused
+xdrgen_decode_notify_verifier4(struct xdr_stream *xdr, struct notify_verifier4 *ptr)
+{
+	if (!xdrgen_decode_verifier4(xdr, &ptr->nv_old_cookieverf))
+		return false;
+	if (!xdrgen_decode_verifier4(xdr, &ptr->nv_new_cookieverf))
+		return false;
+	return true;
+}
+
+static bool __maybe_unused
+xdrgen_decode_notifylist4(struct xdr_stream *xdr, notifylist4 *ptr)
+{
+	return xdrgen_decode_opaque(xdr, ptr, 0);
+}
+
+static bool __maybe_unused
+xdrgen_decode_notify4(struct xdr_stream *xdr, struct notify4 *ptr)
+{
+	if (!xdrgen_decode_bitmap4(xdr, &ptr->notify_mask))
+		return false;
+	if (!xdrgen_decode_notifylist4(xdr, &ptr->notify_vals))
+		return false;
+	return true;
+}
+
+bool
+xdrgen_decode_CB_NOTIFY4args(struct xdr_stream *xdr, struct CB_NOTIFY4args *ptr)
+{
+	if (!xdrgen_decode_stateid4(xdr, &ptr->cna_stateid))
+		return false;
+	if (!xdrgen_decode_nfs_fh4(xdr, &ptr->cna_fh))
+		return false;
+	if (xdr_stream_decode_u32(xdr, &ptr->cna_changes.count) < 0)
+		return false;
+	for (u32 i = 0; i < ptr->cna_changes.count; i++)
+		if (!xdrgen_decode_notify4(xdr, &ptr->cna_changes.element[i]))
+			return false;
+	return true;
+}
+
+bool
+xdrgen_decode_CB_NOTIFY4res(struct xdr_stream *xdr, struct CB_NOTIFY4res *ptr)
+{
+	if (!xdrgen_decode_nfsstat4(xdr, &ptr->cnr_status))
+		return false;
+	return true;
+}
+
+static bool __maybe_unused
+xdrgen_encode_int32_t(struct xdr_stream *xdr, const int32_t value)
+{
+	return xdrgen_encode_int(xdr, value);
 }
 
 static bool __maybe_unused
@@ -377,6 +738,30 @@ xdrgen_encode_uint32_t(struct xdr_stream *xdr, const uint32_t value)
 	return xdrgen_encode_unsigned_int(xdr, value);
 }
 
+static bool __maybe_unused
+xdrgen_encode_int64_t(struct xdr_stream *xdr, const int64_t value)
+{
+	return xdrgen_encode_hyper(xdr, value);
+}
+
+static bool __maybe_unused
+xdrgen_encode_uint64_t(struct xdr_stream *xdr, const uint64_t value)
+{
+	return xdrgen_encode_unsigned_hyper(xdr, value);
+}
+
+static bool __maybe_unused
+xdrgen_encode_nfsstat4(struct xdr_stream *xdr, nfsstat4 value)
+{
+	return xdr_stream_encode_u32(xdr, value) == XDR_UNIT;
+}
+
+static bool __maybe_unused
+xdrgen_encode_attrlist4(struct xdr_stream *xdr, const attrlist4 value)
+{
+	return xdr_stream_encode_opaque(xdr, value.data, value.len) >= 0;
+}
+
 static bool __maybe_unused
 xdrgen_encode_bitmap4(struct xdr_stream *xdr, const bitmap4 value)
 {
@@ -388,6 +773,24 @@ xdrgen_encode_bitmap4(struct xdr_stream *xdr, const bitmap4 value)
 	return true;
 }
 
+static bool __maybe_unused
+xdrgen_encode_verifier4(struct xdr_stream *xdr, const verifier4 value)
+{
+	return xdr_stream_encode_opaque_fixed(xdr, value, NFS4_VERIFIER_SIZE) >= 0;
+}
+
+static bool __maybe_unused
+xdrgen_encode_nfs_cookie4(struct xdr_stream *xdr, const nfs_cookie4 value)
+{
+	return xdrgen_encode_uint64_t(xdr, value);
+}
+
+static bool __maybe_unused
+xdrgen_encode_nfs_fh4(struct xdr_stream *xdr, const nfs_fh4 value)
+{
+	return xdr_stream_encode_opaque(xdr, value.data, value.len) >= 0;
+}
+
 static bool __maybe_unused
 xdrgen_encode_utf8string(struct xdr_stream *xdr, const utf8string value)
 {
@@ -412,6 +815,29 @@ xdrgen_encode_utf8str_mixed(struct xdr_stream *xdr, const utf8str_mixed value)
 	return xdrgen_encode_utf8string(xdr, value);
 }
 
+static bool __maybe_unused
+xdrgen_encode_component4(struct xdr_stream *xdr, const component4 value)
+{
+	return xdrgen_encode_utf8str_cs(xdr, value);
+}
+
+static bool __maybe_unused
+xdrgen_encode_linktext4(struct xdr_stream *xdr, const linktext4 value)
+{
+	return xdrgen_encode_utf8str_cs(xdr, value);
+}
+
+static bool __maybe_unused
+xdrgen_encode_pathname4(struct xdr_stream *xdr, const pathname4 value)
+{
+	if (xdr_stream_encode_u32(xdr, value.count) != XDR_UNIT)
+		return false;
+	for (u32 i = 0; i < value.count; i++)
+		if (!xdrgen_encode_component4(xdr, value.element[i]))
+			return false;
+	return true;
+}
+
 static bool __maybe_unused
 xdrgen_encode_nfstime4(struct xdr_stream *xdr, const struct nfstime4 *value)
 {
@@ -422,6 +848,26 @@ xdrgen_encode_nfstime4(struct xdr_stream *xdr, const struct nfstime4 *value)
 	return true;
 }
 
+static bool __maybe_unused
+xdrgen_encode_fattr4(struct xdr_stream *xdr, const struct fattr4 *value)
+{
+	if (!xdrgen_encode_bitmap4(xdr, value->attrmask))
+		return false;
+	if (!xdrgen_encode_attrlist4(xdr, value->attr_vals))
+		return false;
+	return true;
+}
+
+static bool __maybe_unused
+xdrgen_encode_stateid4(struct xdr_stream *xdr, const struct stateid4 *value)
+{
+	if (!xdrgen_encode_uint32_t(xdr, value->seqid))
+		return false;
+	if (xdr_stream_encode_opaque_fixed(xdr, value->other, 12) < 0)
+		return false;
+	return true;
+}
+
 static bool __maybe_unused
 xdrgen_encode_fattr4_offline(struct xdr_stream *xdr, const fattr4_offline value)
 {
@@ -567,3 +1013,137 @@ xdrgen_encode_fattr4_posix_access_acl(struct xdr_stream *xdr, const fattr4_posix
 			return false;
 	return true;
 }
+
+static bool __maybe_unused
+xdrgen_encode_notify_type4(struct xdr_stream *xdr, notify_type4 value)
+{
+	return xdr_stream_encode_u32(xdr, value) == XDR_UNIT;
+}
+
+static bool __maybe_unused
+xdrgen_encode_notify_entry4(struct xdr_stream *xdr, const struct notify_entry4 *value)
+{
+	if (!xdrgen_encode_component4(xdr, value->ne_file))
+		return false;
+	if (!xdrgen_encode_fattr4(xdr, &value->ne_attrs))
+		return false;
+	return true;
+}
+
+static bool __maybe_unused
+xdrgen_encode_prev_entry4(struct xdr_stream *xdr, const struct prev_entry4 *value)
+{
+	if (!xdrgen_encode_notify_entry4(xdr, &value->pe_prev_entry))
+		return false;
+	if (!xdrgen_encode_nfs_cookie4(xdr, value->pe_prev_entry_cookie))
+		return false;
+	return true;
+}
+
+bool
+xdrgen_encode_notify_remove4(struct xdr_stream *xdr, const struct notify_remove4 *value)
+{
+	if (!xdrgen_encode_notify_entry4(xdr, &value->nrm_old_entry))
+		return false;
+	if (!xdrgen_encode_nfs_cookie4(xdr, value->nrm_old_entry_cookie))
+		return false;
+	return true;
+}
+
+bool
+xdrgen_encode_notify_add4(struct xdr_stream *xdr, const struct notify_add4 *value)
+{
+	if (value->nad_old_entry.count > 1)
+		return false;
+	if (xdr_stream_encode_u32(xdr, value->nad_old_entry.count) != XDR_UNIT)
+		return false;
+	for (u32 i = 0; i < value->nad_old_entry.count; i++)
+		if (!xdrgen_encode_notify_remove4(xdr, &value->nad_old_entry.element[i]))
+			return false;
+	if (!xdrgen_encode_notify_entry4(xdr, &value->nad_new_entry))
+		return false;
+	if (value->nad_new_entry_cookie.count > 1)
+		return false;
+	if (xdr_stream_encode_u32(xdr, value->nad_new_entry_cookie.count) != XDR_UNIT)
+		return false;
+	for (u32 i = 0; i < value->nad_new_entry_cookie.count; i++)
+		if (!xdrgen_encode_nfs_cookie4(xdr, value->nad_new_entry_cookie.element[i]))
+			return false;
+	if (value->nad_prev_entry.count > 1)
+		return false;
+	if (xdr_stream_encode_u32(xdr, value->nad_prev_entry.count) != XDR_UNIT)
+		return false;
+	for (u32 i = 0; i < value->nad_prev_entry.count; i++)
+		if (!xdrgen_encode_prev_entry4(xdr, &value->nad_prev_entry.element[i]))
+			return false;
+	if (!xdrgen_encode_bool(xdr, value->nad_last_entry))
+		return false;
+	return true;
+}
+
+bool
+xdrgen_encode_notify_attr4(struct xdr_stream *xdr, const struct notify_attr4 *value)
+{
+	if (!xdrgen_encode_notify_entry4(xdr, &value->na_changed_entry))
+		return false;
+	return true;
+}
+
+bool
+xdrgen_encode_notify_rename4(struct xdr_stream *xdr, const struct notify_rename4 *value)
+{
+	if (!xdrgen_encode_notify_remove4(xdr, &value->nrn_old_entry))
+		return false;
+	if (!xdrgen_encode_notify_add4(xdr, &value->nrn_new_entry))
+		return false;
+	return true;
+}
+
+static bool __maybe_unused
+xdrgen_encode_notify_verifier4(struct xdr_stream *xdr, const struct notify_verifier4 *value)
+{
+	if (!xdrgen_encode_verifier4(xdr, value->nv_old_cookieverf))
+		return false;
+	if (!xdrgen_encode_verifier4(xdr, value->nv_new_cookieverf))
+		return false;
+	return true;
+}
+
+static bool __maybe_unused
+xdrgen_encode_notifylist4(struct xdr_stream *xdr, const notifylist4 value)
+{
+	return xdr_stream_encode_opaque(xdr, value.data, value.len) >= 0;
+}
+
+static bool __maybe_unused
+xdrgen_encode_notify4(struct xdr_stream *xdr, const struct notify4 *value)
+{
+	if (!xdrgen_encode_bitmap4(xdr, value->notify_mask))
+		return false;
+	if (!xdrgen_encode_notifylist4(xdr, value->notify_vals))
+		return false;
+	return true;
+}
+
+bool
+xdrgen_encode_CB_NOTIFY4args(struct xdr_stream *xdr, const struct CB_NOTIFY4args *value)
+{
+	if (!xdrgen_encode_stateid4(xdr, &value->cna_stateid))
+		return false;
+	if (!xdrgen_encode_nfs_fh4(xdr, value->cna_fh))
+		return false;
+	if (xdr_stream_encode_u32(xdr, value->cna_changes.count) != XDR_UNIT)
+		return false;
+	for (u32 i = 0; i < value->cna_changes.count; i++)
+		if (!xdrgen_encode_notify4(xdr, &value->cna_changes.element[i]))
+			return false;
+	return true;
+}
+
+bool
+xdrgen_encode_CB_NOTIFY4res(struct xdr_stream *xdr, const struct CB_NOTIFY4res *value)
+{
+	if (!xdrgen_encode_nfsstat4(xdr, value->cnr_status))
+		return false;
+	return true;
+}
diff --git a/fs/nfsd/nfs4xdr_gen.h b/fs/nfsd/nfs4xdr_gen.h
index 1c487f1a11ab..503fe2ccba51 100644
--- a/fs/nfsd/nfs4xdr_gen.h
+++ b/fs/nfsd/nfs4xdr_gen.h
@@ -1,7 +1,7 @@
 /* SPDX-License-Identifier: GPL-2.0 */
 /* Generated by xdrgen. Manual edits will be lost. */
 /* XDR specification file: ../../Documentation/sunrpc/xdr/nfs4_1.x */
-/* XDR specification modification time: Thu Jan  8 23:12:07 2026 */
+/* XDR specification modification time: Wed Mar 25 11:39:22 2026 */
 
 #ifndef _LINUX_XDRGEN_NFS4_1_DECL_H
 #define _LINUX_XDRGEN_NFS4_1_DECL_H
@@ -32,4 +32,22 @@ bool xdrgen_decode_posixaceperm4(struct xdr_stream *xdr, posixaceperm4 *ptr);
 bool xdrgen_encode_posixaceperm4(struct xdr_stream *xdr, const posixaceperm4 value);
 
 
+bool xdrgen_decode_notify_remove4(struct xdr_stream *xdr, struct notify_remove4 *ptr);
+bool xdrgen_encode_notify_remove4(struct xdr_stream *xdr, const struct notify_remove4 *value);
+
+bool xdrgen_decode_notify_add4(struct xdr_stream *xdr, struct notify_add4 *ptr);
+bool xdrgen_encode_notify_add4(struct xdr_stream *xdr, const struct notify_add4 *value);
+
+bool xdrgen_decode_notify_attr4(struct xdr_stream *xdr, struct notify_attr4 *ptr);
+bool xdrgen_encode_notify_attr4(struct xdr_stream *xdr, const struct notify_attr4 *value);
+
+bool xdrgen_decode_notify_rename4(struct xdr_stream *xdr, struct notify_rename4 *ptr);
+bool xdrgen_encode_notify_rename4(struct xdr_stream *xdr, const struct notify_rename4 *value);
+
+bool xdrgen_decode_CB_NOTIFY4args(struct xdr_stream *xdr, struct CB_NOTIFY4args *ptr);
+bool xdrgen_encode_CB_NOTIFY4args(struct xdr_stream *xdr, const struct CB_NOTIFY4args *value);
+
+bool xdrgen_decode_CB_NOTIFY4res(struct xdr_stream *xdr, struct CB_NOTIFY4res *ptr);
+bool xdrgen_encode_CB_NOTIFY4res(struct xdr_stream *xdr, const struct CB_NOTIFY4res *value);
+
 #endif /* _LINUX_XDRGEN_NFS4_1_DECL_H */
diff --git a/fs/nfsd/trace.h b/fs/nfsd/trace.h
index a13d18447324..60cacf64181c 100644
--- a/fs/nfsd/trace.h
+++ b/fs/nfsd/trace.h
@@ -1677,6 +1677,7 @@ TRACE_EVENT(nfsd_cb_setup_err,
 		{ OP_CB_RECALL,			"CB_RECALL" },		\
 		{ OP_CB_LAYOUTRECALL,		"CB_LAYOUTRECALL" },	\
 		{ OP_CB_RECALL_ANY,		"CB_RECALL_ANY" },	\
+		{ OP_CB_NOTIFY,			"CB_NOTIFY" },		\
 		{ OP_CB_NOTIFY_LOCK,		"CB_NOTIFY_LOCK" },	\
 		{ OP_CB_OFFLOAD,		"CB_OFFLOAD" })
 
diff --git a/include/linux/nfs4.h b/include/linux/nfs4.h
index d87be1f25273..44e5e9fa12e1 100644
--- a/include/linux/nfs4.h
+++ b/include/linux/nfs4.h
@@ -171,133 +171,6 @@ Needs to be updated if more operations are defined in future.*/
 #define LAST_NFS42_OP	OP_REMOVEXATTR
 #define LAST_NFS4_OP	LAST_NFS42_OP
 
-enum nfsstat4 {
-	NFS4_OK = 0,
-	NFS4ERR_PERM = 1,
-	NFS4ERR_NOENT = 2,
-	NFS4ERR_IO = 5,
-	NFS4ERR_NXIO = 6,
-	NFS4ERR_ACCESS = 13,
-	NFS4ERR_EXIST = 17,
-	NFS4ERR_XDEV = 18,
-	/* Unused/reserved 19 */
-	NFS4ERR_NOTDIR = 20,
-	NFS4ERR_ISDIR = 21,
-	NFS4ERR_INVAL = 22,
-	NFS4ERR_FBIG = 27,
-	NFS4ERR_NOSPC = 28,
-	NFS4ERR_ROFS = 30,
-	NFS4ERR_MLINK = 31,
-	NFS4ERR_NAMETOOLONG = 63,
-	NFS4ERR_NOTEMPTY = 66,
-	NFS4ERR_DQUOT = 69,
-	NFS4ERR_STALE = 70,
-	NFS4ERR_BADHANDLE = 10001,
-	NFS4ERR_BAD_COOKIE = 10003,
-	NFS4ERR_NOTSUPP = 10004,
-	NFS4ERR_TOOSMALL = 10005,
-	NFS4ERR_SERVERFAULT = 10006,
-	NFS4ERR_BADTYPE = 10007,
-	NFS4ERR_DELAY = 10008,
-	NFS4ERR_SAME = 10009,
-	NFS4ERR_DENIED = 10010,
-	NFS4ERR_EXPIRED = 10011,
-	NFS4ERR_LOCKED = 10012,
-	NFS4ERR_GRACE = 10013,
-	NFS4ERR_FHEXPIRED = 10014,
-	NFS4ERR_SHARE_DENIED = 10015,
-	NFS4ERR_WRONGSEC = 10016,
-	NFS4ERR_CLID_INUSE = 10017,
-	NFS4ERR_RESOURCE = 10018,
-	NFS4ERR_MOVED = 10019,
-	NFS4ERR_NOFILEHANDLE = 10020,
-	NFS4ERR_MINOR_VERS_MISMATCH = 10021,
-	NFS4ERR_STALE_CLIENTID = 10022,
-	NFS4ERR_STALE_STATEID = 10023,
-	NFS4ERR_OLD_STATEID = 10024,
-	NFS4ERR_BAD_STATEID = 10025,
-	NFS4ERR_BAD_SEQID = 10026,
-	NFS4ERR_NOT_SAME = 10027,
-	NFS4ERR_LOCK_RANGE = 10028,
-	NFS4ERR_SYMLINK = 10029,
-	NFS4ERR_RESTOREFH = 10030,
-	NFS4ERR_LEASE_MOVED = 10031,
-	NFS4ERR_ATTRNOTSUPP = 10032,
-	NFS4ERR_NO_GRACE = 10033,
-	NFS4ERR_RECLAIM_BAD = 10034,
-	NFS4ERR_RECLAIM_CONFLICT = 10035,
-	NFS4ERR_BADXDR = 10036,
-	NFS4ERR_LOCKS_HELD = 10037,
-	NFS4ERR_OPENMODE = 10038,
-	NFS4ERR_BADOWNER = 10039,
-	NFS4ERR_BADCHAR = 10040,
-	NFS4ERR_BADNAME = 10041,
-	NFS4ERR_BAD_RANGE = 10042,
-	NFS4ERR_LOCK_NOTSUPP = 10043,
-	NFS4ERR_OP_ILLEGAL = 10044,
-	NFS4ERR_DEADLOCK = 10045,
-	NFS4ERR_FILE_OPEN = 10046,
-	NFS4ERR_ADMIN_REVOKED = 10047,
-	NFS4ERR_CB_PATH_DOWN = 10048,
-
-	/* nfs41 */
-	NFS4ERR_BADIOMODE	= 10049,
-	NFS4ERR_BADLAYOUT	= 10050,
-	NFS4ERR_BAD_SESSION_DIGEST = 10051,
-	NFS4ERR_BADSESSION	= 10052,
-	NFS4ERR_BADSLOT		= 10053,
-	NFS4ERR_COMPLETE_ALREADY = 10054,
-	NFS4ERR_CONN_NOT_BOUND_TO_SESSION = 10055,
-	NFS4ERR_DELEG_ALREADY_WANTED = 10056,
-	NFS4ERR_BACK_CHAN_BUSY	= 10057,	/* backchan reqs outstanding */
-	NFS4ERR_LAYOUTTRYLATER	= 10058,
-	NFS4ERR_LAYOUTUNAVAILABLE = 10059,
-	NFS4ERR_NOMATCHING_LAYOUT = 10060,
-	NFS4ERR_RECALLCONFLICT	= 10061,
-	NFS4ERR_UNKNOWN_LAYOUTTYPE = 10062,
-	NFS4ERR_SEQ_MISORDERED = 10063, 	/* unexpected seq.id in req */
-	NFS4ERR_SEQUENCE_POS	= 10064,	/* [CB_]SEQ. op not 1st op */
-	NFS4ERR_REQ_TOO_BIG	= 10065,	/* request too big */
-	NFS4ERR_REP_TOO_BIG	= 10066,	/* reply too big */
-	NFS4ERR_REP_TOO_BIG_TO_CACHE = 10067,	/* rep. not all cached */
-	NFS4ERR_RETRY_UNCACHED_REP = 10068,	/* retry & rep. uncached */
-	NFS4ERR_UNSAFE_COMPOUND = 10069,	/* retry/recovery too hard */
-	NFS4ERR_TOO_MANY_OPS	= 10070,	/* too many ops in [CB_]COMP */
-	NFS4ERR_OP_NOT_IN_SESSION = 10071,	/* op needs [CB_]SEQ. op */
-	NFS4ERR_HASH_ALG_UNSUPP = 10072,	/* hash alg. not supp. */
-						/* Error 10073 is unused. */
-	NFS4ERR_CLIENTID_BUSY	= 10074,	/* clientid has state */
-	NFS4ERR_PNFS_IO_HOLE	= 10075,	/* IO to _SPARSE file hole */
-	NFS4ERR_SEQ_FALSE_RETRY	= 10076,	/* retry not original */
-	NFS4ERR_BAD_HIGH_SLOT	= 10077,	/* sequence arg bad */
-	NFS4ERR_DEADSESSION	= 10078,	/* persistent session dead */
-	NFS4ERR_ENCR_ALG_UNSUPP = 10079,	/* SSV alg mismatch */
-	NFS4ERR_PNFS_NO_LAYOUT	= 10080,	/* direct I/O with no layout */
-	NFS4ERR_NOT_ONLY_OP	= 10081,	/* bad compound */
-	NFS4ERR_WRONG_CRED	= 10082,	/* permissions:state change */
-	NFS4ERR_WRONG_TYPE	= 10083,	/* current operation mismatch */
-	NFS4ERR_DIRDELEG_UNAVAIL = 10084,	/* no directory delegation */
-	NFS4ERR_REJECT_DELEG	= 10085,	/* on callback */
-	NFS4ERR_RETURNCONFLICT	= 10086,	/* outstanding layoutreturn */
-	NFS4ERR_DELEG_REVOKED	= 10087,	/* deleg./layout revoked */
-
-	/* nfs42 */
-	NFS4ERR_PARTNER_NOTSUPP	= 10088,
-	NFS4ERR_PARTNER_NO_AUTH	= 10089,
-	NFS4ERR_UNION_NOTSUPP	= 10090,
-	NFS4ERR_OFFLOAD_DENIED	= 10091,
-	NFS4ERR_WRONG_LFS	= 10092,
-	NFS4ERR_BADLABEL	= 10093,
-	NFS4ERR_OFFLOAD_NO_REQS	= 10094,
-
-	/* xattr (RFC8276) */
-	NFS4ERR_NOXATTR		= 10095,
-	NFS4ERR_XATTR2BIG	= 10096,
-
-	/* can be used for internal errors */
-	NFS4ERR_FIRST_FREE
-};
-
 /* error codes for internal client use */
 #define NFS4ERR_RESET_TO_MDS   12001
 #define NFS4ERR_RESET_TO_PNFS  12002
diff --git a/include/linux/sunrpc/xdrgen/nfs4_1.h b/include/linux/sunrpc/xdrgen/nfs4_1.h
index 4ac54bdbd335..f761c3ddb4c7 100644
--- a/include/linux/sunrpc/xdrgen/nfs4_1.h
+++ b/include/linux/sunrpc/xdrgen/nfs4_1.h
@@ -1,7 +1,7 @@
 /* SPDX-License-Identifier: GPL-2.0 */
 /* Generated by xdrgen. Manual edits will be lost. */
 /* XDR specification file: ../../Documentation/sunrpc/xdr/nfs4_1.x */
-/* XDR specification modification time: Thu Jan  8 23:12:07 2026 */
+/* XDR specification modification time: Wed Mar 25 11:39:22 2026 */
 
 #ifndef _LINUX_XDRGEN_NFS4_1_DEF_H
 #define _LINUX_XDRGEN_NFS4_1_DEF_H
@@ -9,15 +9,150 @@
 #include <linux/types.h>
 #include <linux/sunrpc/xdrgen/_defs.h>
 
-typedef s64 int64_t;
+typedef s32 int32_t;
 
 typedef u32 uint32_t;
 
+typedef s64 int64_t;
+
+typedef u64 uint64_t;
+
+enum { NFS4_VERIFIER_SIZE = 8 };
+
+enum { NFS4_FHSIZE = 128 };
+
+enum nfsstat4 {
+	NFS4_OK = 0,
+	NFS4ERR_PERM = 1,
+	NFS4ERR_NOENT = 2,
+	NFS4ERR_IO = 5,
+	NFS4ERR_NXIO = 6,
+	NFS4ERR_ACCESS = 13,
+	NFS4ERR_EXIST = 17,
+	NFS4ERR_XDEV = 18,
+	NFS4ERR_NOTDIR = 20,
+	NFS4ERR_ISDIR = 21,
+	NFS4ERR_INVAL = 22,
+	NFS4ERR_FBIG = 27,
+	NFS4ERR_NOSPC = 28,
+	NFS4ERR_ROFS = 30,
+	NFS4ERR_MLINK = 31,
+	NFS4ERR_NAMETOOLONG = 63,
+	NFS4ERR_NOTEMPTY = 66,
+	NFS4ERR_DQUOT = 69,
+	NFS4ERR_STALE = 70,
+	NFS4ERR_BADHANDLE = 10001,
+	NFS4ERR_BAD_COOKIE = 10003,
+	NFS4ERR_NOTSUPP = 10004,
+	NFS4ERR_TOOSMALL = 10005,
+	NFS4ERR_SERVERFAULT = 10006,
+	NFS4ERR_BADTYPE = 10007,
+	NFS4ERR_DELAY = 10008,
+	NFS4ERR_SAME = 10009,
+	NFS4ERR_DENIED = 10010,
+	NFS4ERR_EXPIRED = 10011,
+	NFS4ERR_LOCKED = 10012,
+	NFS4ERR_GRACE = 10013,
+	NFS4ERR_FHEXPIRED = 10014,
+	NFS4ERR_SHARE_DENIED = 10015,
+	NFS4ERR_WRONGSEC = 10016,
+	NFS4ERR_CLID_INUSE = 10017,
+	NFS4ERR_RESOURCE = 10018,
+	NFS4ERR_MOVED = 10019,
+	NFS4ERR_NOFILEHANDLE = 10020,
+	NFS4ERR_MINOR_VERS_MISMATCH = 10021,
+	NFS4ERR_STALE_CLIENTID = 10022,
+	NFS4ERR_STALE_STATEID = 10023,
+	NFS4ERR_OLD_STATEID = 10024,
+	NFS4ERR_BAD_STATEID = 10025,
+	NFS4ERR_BAD_SEQID = 10026,
+	NFS4ERR_NOT_SAME = 10027,
+	NFS4ERR_LOCK_RANGE = 10028,
+	NFS4ERR_SYMLINK = 10029,
+	NFS4ERR_RESTOREFH = 10030,
+	NFS4ERR_LEASE_MOVED = 10031,
+	NFS4ERR_ATTRNOTSUPP = 10032,
+	NFS4ERR_NO_GRACE = 10033,
+	NFS4ERR_RECLAIM_BAD = 10034,
+	NFS4ERR_RECLAIM_CONFLICT = 10035,
+	NFS4ERR_BADXDR = 10036,
+	NFS4ERR_LOCKS_HELD = 10037,
+	NFS4ERR_OPENMODE = 10038,
+	NFS4ERR_BADOWNER = 10039,
+	NFS4ERR_BADCHAR = 10040,
+	NFS4ERR_BADNAME = 10041,
+	NFS4ERR_BAD_RANGE = 10042,
+	NFS4ERR_LOCK_NOTSUPP = 10043,
+	NFS4ERR_OP_ILLEGAL = 10044,
+	NFS4ERR_DEADLOCK = 10045,
+	NFS4ERR_FILE_OPEN = 10046,
+	NFS4ERR_ADMIN_REVOKED = 10047,
+	NFS4ERR_CB_PATH_DOWN = 10048,
+	NFS4ERR_BADIOMODE = 10049,
+	NFS4ERR_BADLAYOUT = 10050,
+	NFS4ERR_BAD_SESSION_DIGEST = 10051,
+	NFS4ERR_BADSESSION = 10052,
+	NFS4ERR_BADSLOT = 10053,
+	NFS4ERR_COMPLETE_ALREADY = 10054,
+	NFS4ERR_CONN_NOT_BOUND_TO_SESSION = 10055,
+	NFS4ERR_DELEG_ALREADY_WANTED = 10056,
+	NFS4ERR_BACK_CHAN_BUSY = 10057,
+	NFS4ERR_LAYOUTTRYLATER = 10058,
+	NFS4ERR_LAYOUTUNAVAILABLE = 10059,
+	NFS4ERR_NOMATCHING_LAYOUT = 10060,
+	NFS4ERR_RECALLCONFLICT = 10061,
+	NFS4ERR_UNKNOWN_LAYOUTTYPE = 10062,
+	NFS4ERR_SEQ_MISORDERED = 10063,
+	NFS4ERR_SEQUENCE_POS = 10064,
+	NFS4ERR_REQ_TOO_BIG = 10065,
+	NFS4ERR_REP_TOO_BIG = 10066,
+	NFS4ERR_REP_TOO_BIG_TO_CACHE = 10067,
+	NFS4ERR_RETRY_UNCACHED_REP = 10068,
+	NFS4ERR_UNSAFE_COMPOUND = 10069,
+	NFS4ERR_TOO_MANY_OPS = 10070,
+	NFS4ERR_OP_NOT_IN_SESSION = 10071,
+	NFS4ERR_HASH_ALG_UNSUPP = 10072,
+	NFS4ERR_CLIENTID_BUSY = 10074,
+	NFS4ERR_PNFS_IO_HOLE = 10075,
+	NFS4ERR_SEQ_FALSE_RETRY = 10076,
+	NFS4ERR_BAD_HIGH_SLOT = 10077,
+	NFS4ERR_DEADSESSION = 10078,
+	NFS4ERR_ENCR_ALG_UNSUPP = 10079,
+	NFS4ERR_PNFS_NO_LAYOUT = 10080,
+	NFS4ERR_NOT_ONLY_OP = 10081,
+	NFS4ERR_WRONG_CRED = 10082,
+	NFS4ERR_WRONG_TYPE = 10083,
+	NFS4ERR_DIRDELEG_UNAVAIL = 10084,
+	NFS4ERR_REJECT_DELEG = 10085,
+	NFS4ERR_RETURNCONFLICT = 10086,
+	NFS4ERR_DELEG_REVOKED = 10087,
+	NFS4ERR_PARTNER_NOTSUPP = 10088,
+	NFS4ERR_PARTNER_NO_AUTH = 10089,
+	NFS4ERR_UNION_NOTSUPP = 10090,
+	NFS4ERR_OFFLOAD_DENIED = 10091,
+	NFS4ERR_WRONG_LFS = 10092,
+	NFS4ERR_BADLABEL = 10093,
+	NFS4ERR_OFFLOAD_NO_REQS = 10094,
+	NFS4ERR_NOXATTR = 10095,
+	NFS4ERR_XATTR2BIG = 10096,
+	NFS4ERR_FIRST_FREE = 10097,
+};
+
+typedef enum nfsstat4 nfsstat4;
+
+typedef opaque attrlist4;
+
 typedef struct {
 	u32 count;
 	uint32_t *element;
 } bitmap4;
 
+typedef u8 verifier4[NFS4_VERIFIER_SIZE];
+
+typedef uint64_t nfs_cookie4;
+
+typedef opaque nfs_fh4;
+
 typedef opaque utf8string;
 
 typedef utf8string utf8str_cis;
@@ -26,11 +161,30 @@ typedef utf8string utf8str_cs;
 
 typedef utf8string utf8str_mixed;
 
+typedef utf8str_cs component4;
+
+typedef utf8str_cs linktext4;
+
+typedef struct {
+	u32 count;
+	component4 *element;
+} pathname4;
+
 struct nfstime4 {
 	int64_t seconds;
 	uint32_t nseconds;
 };
 
+struct fattr4 {
+	bitmap4 attrmask;
+	attrlist4 attr_vals;
+};
+
+struct stateid4 {
+	uint32_t seqid;
+	u8 other[12];
+};
+
 typedef bool fattr4_offline;
 
 enum { FATTR4_OFFLINE = 83 };
@@ -216,11 +370,98 @@ enum { FATTR4_POSIX_DEFAULT_ACL = 91 };
 
 enum { FATTR4_POSIX_ACCESS_ACL = 92 };
 
-#define NFS4_int64_t_sz                 \
-	(XDR_hyper)
+enum notify_type4 {
+	NOTIFY4_CHANGE_CHILD_ATTRS = 0,
+	NOTIFY4_CHANGE_DIR_ATTRS = 1,
+	NOTIFY4_REMOVE_ENTRY = 2,
+	NOTIFY4_ADD_ENTRY = 3,
+	NOTIFY4_RENAME_ENTRY = 4,
+	NOTIFY4_CHANGE_COOKIE_VERIFIER = 5,
+};
+
+typedef enum notify_type4 notify_type4;
+
+struct notify_entry4 {
+	component4 ne_file;
+	struct fattr4 ne_attrs;
+};
+
+struct prev_entry4 {
+	struct notify_entry4 pe_prev_entry;
+	nfs_cookie4 pe_prev_entry_cookie;
+};
+
+struct notify_remove4 {
+	struct notify_entry4 nrm_old_entry;
+	nfs_cookie4 nrm_old_entry_cookie;
+};
+
+struct notify_add4 {
+	struct {
+		u32 count;
+		struct notify_remove4 *element;
+	} nad_old_entry;
+	struct notify_entry4 nad_new_entry;
+	struct {
+		u32 count;
+		nfs_cookie4 *element;
+	} nad_new_entry_cookie;
+	struct {
+		u32 count;
+		struct prev_entry4 *element;
+	} nad_prev_entry;
+	bool nad_last_entry;
+};
+
+struct notify_attr4 {
+	struct notify_entry4 na_changed_entry;
+};
+
+struct notify_rename4 {
+	struct notify_remove4 nrn_old_entry;
+	struct notify_add4 nrn_new_entry;
+};
+
+struct notify_verifier4 {
+	verifier4 nv_old_cookieverf;
+	verifier4 nv_new_cookieverf;
+};
+
+typedef opaque notifylist4;
+
+struct notify4 {
+	bitmap4 notify_mask;
+	notifylist4 notify_vals;
+};
+
+struct CB_NOTIFY4args {
+	struct stateid4 cna_stateid;
+	nfs_fh4 cna_fh;
+	struct {
+		u32 count;
+		struct notify4 *element;
+	} cna_changes;
+};
+
+struct CB_NOTIFY4res {
+	nfsstat4 cnr_status;
+};
+
+#define NFS4_int32_t_sz                 \
+	(XDR_int)
 #define NFS4_uint32_t_sz                \
 	(XDR_unsigned_int)
+#define NFS4_int64_t_sz                 \
+	(XDR_hyper)
+#define NFS4_uint64_t_sz                \
+	(XDR_unsigned_hyper)
+#define NFS4_nfsstat4_sz                (XDR_int)
+#define NFS4_attrlist4_sz               (XDR_unsigned_int)
 #define NFS4_bitmap4_sz                 (XDR_unsigned_int)
+#define NFS4_verifier4_sz               (XDR_QUADLEN(NFS4_VERIFIER_SIZE))
+#define NFS4_nfs_cookie4_sz             \
+	(NFS4_uint64_t_sz)
+#define NFS4_nfs_fh4_sz                 (XDR_unsigned_int + XDR_QUADLEN(NFS4_FHSIZE))
 #define NFS4_utf8string_sz              (XDR_unsigned_int)
 #define NFS4_utf8str_cis_sz             \
 	(NFS4_utf8string_sz)
@@ -228,8 +469,17 @@ enum { FATTR4_POSIX_ACCESS_ACL = 92 };
 	(NFS4_utf8string_sz)
 #define NFS4_utf8str_mixed_sz           \
 	(NFS4_utf8string_sz)
+#define NFS4_component4_sz              \
+	(NFS4_utf8str_cs_sz)
+#define NFS4_linktext4_sz               \
+	(NFS4_utf8str_cs_sz)
+#define NFS4_pathname4_sz               (XDR_unsigned_int)
 #define NFS4_nfstime4_sz                \
 	(NFS4_int64_t_sz + NFS4_uint32_t_sz)
+#define NFS4_fattr4_sz                  \
+	(NFS4_bitmap4_sz + NFS4_attrlist4_sz)
+#define NFS4_stateid4_sz                \
+	(NFS4_uint32_t_sz + XDR_QUADLEN(12))
 #define NFS4_fattr4_offline_sz          \
 	(XDR_bool)
 #define NFS4_open_arguments4_sz         \
@@ -259,5 +509,27 @@ enum { FATTR4_POSIX_ACCESS_ACL = 92 };
 	(NFS4_aclscope4_sz)
 #define NFS4_fattr4_posix_default_acl_sz (XDR_unsigned_int)
 #define NFS4_fattr4_posix_access_acl_sz (XDR_unsigned_int)
+#define NFS4_notify_type4_sz            (XDR_int)
+#define NFS4_notify_entry4_sz           \
+	(NFS4_component4_sz + NFS4_fattr4_sz)
+#define NFS4_prev_entry4_sz             \
+	(NFS4_notify_entry4_sz + NFS4_nfs_cookie4_sz)
+#define NFS4_notify_remove4_sz          \
+	(NFS4_notify_entry4_sz + NFS4_nfs_cookie4_sz)
+#define NFS4_notify_add4_sz             \
+	(XDR_unsigned_int + (1 * (NFS4_notify_remove4_sz)) + NFS4_notify_entry4_sz + XDR_unsigned_int + (1 * (NFS4_nfs_cookie4_sz)) + XDR_unsigned_int + (1 * (NFS4_prev_entry4_sz)) + XDR_bool)
+#define NFS4_notify_attr4_sz            \
+	(NFS4_notify_entry4_sz)
+#define NFS4_notify_rename4_sz          \
+	(NFS4_notify_remove4_sz + NFS4_notify_add4_sz)
+#define NFS4_notify_verifier4_sz        \
+	(NFS4_verifier4_sz + NFS4_verifier4_sz)
+#define NFS4_notifylist4_sz             (XDR_unsigned_int)
+#define NFS4_notify4_sz                 \
+	(NFS4_bitmap4_sz + NFS4_notifylist4_sz)
+#define NFS4_CB_NOTIFY4args_sz          \
+	(NFS4_stateid4_sz + NFS4_nfs_fh4_sz + XDR_unsigned_int)
+#define NFS4_CB_NOTIFY4res_sz           \
+	(NFS4_nfsstat4_sz)
 
 #endif /* _LINUX_XDRGEN_NFS4_1_DEF_H */
diff --git a/include/uapi/linux/nfs4.h b/include/uapi/linux/nfs4.h
index 4273e0249fcb..289205b53a08 100644
--- a/include/uapi/linux/nfs4.h
+++ b/include/uapi/linux/nfs4.h
@@ -17,11 +17,9 @@
 #include <linux/types.h>
 
 #define NFS4_BITMAP_SIZE	3
-#define NFS4_VERIFIER_SIZE	8
 #define NFS4_STATEID_SEQID_SIZE 4
 #define NFS4_STATEID_OTHER_SIZE 12
 #define NFS4_STATEID_SIZE	(NFS4_STATEID_SEQID_SIZE + NFS4_STATEID_OTHER_SIZE)
-#define NFS4_FHSIZE		128
 #define NFS4_MAXPATHLEN		PATH_MAX
 #define NFS4_MAXNAMLEN		NAME_MAX
 #define NFS4_OPAQUE_LIMIT	1024

-- 
2.53.0

[PATCH 05/24] nfs_common: add new NOTIFY4_* flags proposed in RFC8881bis

[Jeff Layton]

RFC8881bis adds some new flags to GET_DIR_DELEGATION that we very much
need to support.

Signed-off-by: Jeff Layton <jlayton@kernel.org>
---
 Documentation/sunrpc/xdr/nfs4_1.x    | 16 +++++++++++++++-
 fs/nfsd/nfs4xdr_gen.c                | 13 ++++++++++++-
 fs/nfsd/nfs4xdr_gen.h                |  2 +-
 include/linux/sunrpc/xdrgen/nfs4_1.h | 13 ++++++++++++-
 4 files changed, 40 insertions(+), 4 deletions(-)

diff --git a/Documentation/sunrpc/xdr/nfs4_1.x b/Documentation/sunrpc/xdr/nfs4_1.x
index 632f5b579c39..aa14b590b524 100644
--- a/Documentation/sunrpc/xdr/nfs4_1.x
+++ b/Documentation/sunrpc/xdr/nfs4_1.x
@@ -416,7 +416,21 @@ enum notify_type4 {
         NOTIFY4_REMOVE_ENTRY = 2,
         NOTIFY4_ADD_ENTRY = 3,
         NOTIFY4_RENAME_ENTRY = 4,
-        NOTIFY4_CHANGE_COOKIE_VERIFIER = 5
+        NOTIFY4_CHANGE_COOKIE_VERIFIER = 5,
+        /*
+         * Added in NFSv4.1 bis document
+         */
+        NOTIFY4_GFLAG_EXTEND = 6,
+        NOTIFY4_AUFLAG_VALID = 7,
+        NOTIFY4_AUFLAG_USER = 8,
+        NOTIFY4_AUFLAG_GROUP = 9,
+        NOTIFY4_AUFLAG_OTHER = 10,
+        NOTIFY4_CHANGE_AUTH = 11,
+        NOTIFY4_CFLAG_ORDER = 12,
+        NOTIFY4_AUFLAG_GANOW = 13,
+        NOTIFY4_AUFLAG_GALATER = 14,
+        NOTIFY4_CHANGE_GA = 15,
+        NOTIFY4_CHANGE_AMASK = 16
 };
 
 /* Changed entry information.  */
diff --git a/fs/nfsd/nfs4xdr_gen.c b/fs/nfsd/nfs4xdr_gen.c
index 5e656d6bbb8e..80369139ef7e 100644
--- a/fs/nfsd/nfs4xdr_gen.c
+++ b/fs/nfsd/nfs4xdr_gen.c
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 // Generated by xdrgen. Manual edits will be lost.
 // XDR specification file: ../../Documentation/sunrpc/xdr/nfs4_1.x
-// XDR specification modification time: Wed Mar 25 11:39:22 2026
+// XDR specification modification time: Wed Mar 25 11:40:02 2026
 
 #include <linux/sunrpc/svc.h>
 
@@ -590,6 +590,17 @@ xdrgen_decode_notify_type4(struct xdr_stream *xdr, notify_type4 *ptr)
 	case NOTIFY4_ADD_ENTRY:
 	case NOTIFY4_RENAME_ENTRY:
 	case NOTIFY4_CHANGE_COOKIE_VERIFIER:
+	case NOTIFY4_GFLAG_EXTEND:
+	case NOTIFY4_AUFLAG_VALID:
+	case NOTIFY4_AUFLAG_USER:
+	case NOTIFY4_AUFLAG_GROUP:
+	case NOTIFY4_AUFLAG_OTHER:
+	case NOTIFY4_CHANGE_AUTH:
+	case NOTIFY4_CFLAG_ORDER:
+	case NOTIFY4_AUFLAG_GANOW:
+	case NOTIFY4_AUFLAG_GALATER:
+	case NOTIFY4_CHANGE_GA:
+	case NOTIFY4_CHANGE_AMASK:
 		break;
 	default:
 		return false;
diff --git a/fs/nfsd/nfs4xdr_gen.h b/fs/nfsd/nfs4xdr_gen.h
index 503fe2ccba51..092a1ed399c7 100644
--- a/fs/nfsd/nfs4xdr_gen.h
+++ b/fs/nfsd/nfs4xdr_gen.h
@@ -1,7 +1,7 @@
 /* SPDX-License-Identifier: GPL-2.0 */
 /* Generated by xdrgen. Manual edits will be lost. */
 /* XDR specification file: ../../Documentation/sunrpc/xdr/nfs4_1.x */
-/* XDR specification modification time: Wed Mar 25 11:39:22 2026 */
+/* XDR specification modification time: Wed Mar 25 11:40:02 2026 */
 
 #ifndef _LINUX_XDRGEN_NFS4_1_DECL_H
 #define _LINUX_XDRGEN_NFS4_1_DECL_H
diff --git a/include/linux/sunrpc/xdrgen/nfs4_1.h b/include/linux/sunrpc/xdrgen/nfs4_1.h
index f761c3ddb4c7..537504069f24 100644
--- a/include/linux/sunrpc/xdrgen/nfs4_1.h
+++ b/include/linux/sunrpc/xdrgen/nfs4_1.h
@@ -1,7 +1,7 @@
 /* SPDX-License-Identifier: GPL-2.0 */
 /* Generated by xdrgen. Manual edits will be lost. */
 /* XDR specification file: ../../Documentation/sunrpc/xdr/nfs4_1.x */
-/* XDR specification modification time: Wed Mar 25 11:39:22 2026 */
+/* XDR specification modification time: Wed Mar 25 11:40:02 2026 */
 
 #ifndef _LINUX_XDRGEN_NFS4_1_DEF_H
 #define _LINUX_XDRGEN_NFS4_1_DEF_H
@@ -377,6 +377,17 @@ enum notify_type4 {
 	NOTIFY4_ADD_ENTRY = 3,
 	NOTIFY4_RENAME_ENTRY = 4,
 	NOTIFY4_CHANGE_COOKIE_VERIFIER = 5,
+	NOTIFY4_GFLAG_EXTEND = 6,
+	NOTIFY4_AUFLAG_VALID = 7,
+	NOTIFY4_AUFLAG_USER = 8,
+	NOTIFY4_AUFLAG_GROUP = 9,
+	NOTIFY4_AUFLAG_OTHER = 10,
+	NOTIFY4_CHANGE_AUTH = 11,
+	NOTIFY4_CFLAG_ORDER = 12,
+	NOTIFY4_AUFLAG_GANOW = 13,
+	NOTIFY4_AUFLAG_GALATER = 14,
+	NOTIFY4_CHANGE_GA = 15,
+	NOTIFY4_CHANGE_AMASK = 16,
 };
 
 typedef enum notify_type4 notify_type4;

-- 
2.53.0

[PATCH 06/24] nfsd: allow nfsd to get a dir lease with an ignore mask

[Jeff Layton]

When requesting a directory lease, enable the FL_IGN_DIR_* bits that
correspond to the requested notification types.

Signed-off-by: Jeff Layton <jlayton@kernel.org>
---
 fs/nfsd/nfs4state.c | 26 ++++++++++++++++++++------
 1 file changed, 20 insertions(+), 6 deletions(-)

diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index fa657badf5f8..c8fb84c38637 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -6021,7 +6021,22 @@ static bool nfsd4_cb_channel_good(struct nfs4_client *clp)
 	return clp->cl_minorversion && clp->cl_cb_state == NFSD4_CB_UNKNOWN;
 }
 
-static struct file_lease *nfs4_alloc_init_lease(struct nfs4_delegation *dp)
+static unsigned int
+nfsd_notify_to_ignore(u32 notify)
+{
+	unsigned int mask = 0;
+
+	if (notify & BIT(NOTIFY4_REMOVE_ENTRY))
+		mask |= FL_IGN_DIR_DELETE;
+	if (notify & BIT(NOTIFY4_ADD_ENTRY))
+		mask |= FL_IGN_DIR_CREATE;
+	if (notify & BIT(NOTIFY4_RENAME_ENTRY))
+		mask |= FL_IGN_DIR_RENAME;
+
+	return mask;
+}
+
+static struct file_lease *nfs4_alloc_init_lease(struct nfs4_delegation *dp, u32 notify)
 {
 	struct file_lease *fl;
 
@@ -6029,7 +6044,7 @@ static struct file_lease *nfs4_alloc_init_lease(struct nfs4_delegation *dp)
 	if (!fl)
 		return NULL;
 	fl->fl_lmops = &nfsd_lease_mng_ops;
-	fl->c.flc_flags = FL_DELEG;
+	fl->c.flc_flags = FL_DELEG | nfsd_notify_to_ignore(notify);
 	fl->c.flc_type = deleg_is_read(dp->dl_type) ? F_RDLCK : F_WRLCK;
 	fl->c.flc_owner = (fl_owner_t)dp;
 	fl->c.flc_pid = current->tgid;
@@ -6246,7 +6261,7 @@ nfs4_set_delegation(struct nfsd4_open *open, struct nfs4_ol_stateid *stp,
 	if (stp->st_stid.sc_export)
 		dp->dl_stid.sc_export = exp_get(stp->st_stid.sc_export);
 
-	fl = nfs4_alloc_init_lease(dp);
+	fl = nfs4_alloc_init_lease(dp, 0);
 	if (!fl)
 		goto out_clnt_odstate;
 
@@ -9612,12 +9627,11 @@ nfsd_get_dir_deleg(struct nfsd4_compound_state *cstate,
 		dp->dl_stid.sc_export =
 			exp_get(cstate->current_fh.fh_export);
 
-	fl = nfs4_alloc_init_lease(dp);
+	fl = nfs4_alloc_init_lease(dp, gdd->gddr_notification[0]);
 	if (!fl)
 		goto out_put_stid;
 
-	status = kernel_setlease(nf->nf_file,
-				 fl->c.flc_type, &fl, NULL);
+	status = kernel_setlease(nf->nf_file, fl->c.flc_type, &fl, NULL);
 	if (fl)
 		locks_free_lease(fl);
 	if (status)

-- 
2.53.0

[PATCH 07/24] vfs: add fsnotify_modify_mark_mask()

[Jeff Layton]

nfsd needs to be able to modify the mask on an existing mark when new
directory delegations are set or unset. Add an exported function that
allows the caller to set and clear bits in the mark->mask, and does
the recalculation if something changed.

Suggested-by: Jan Kara <jack@suse.cz>
Signed-off-by: Jeff Layton <jlayton@kernel.org>
---
 fs/notify/mark.c                 | 29 +++++++++++++++++++++++++++++
 include/linux/fsnotify_backend.h |  1 +
 2 files changed, 30 insertions(+)

diff --git a/fs/notify/mark.c b/fs/notify/mark.c
index c2ed5b11b0fe..b1e73c6fd382 100644
--- a/fs/notify/mark.c
+++ b/fs/notify/mark.c
@@ -310,6 +310,35 @@ void fsnotify_recalc_mask(struct fsnotify_mark_connector *conn)
 		fsnotify_conn_set_children_dentry_flags(conn);
 }
 
+/**
+ * fsnotify_modify_mark_mask - set and/or clear flags in a mark's mask
+ * @mark: mark to be modified
+ * @set: bits to be set in mask
+ * @clear: bits to be cleared in mask
+ *
+ * Modify a fsnotify_mark mask as directed, and update its associated conn.
+ * The caller is expected to hold a reference to the mark.
+ */
+void fsnotify_modify_mark_mask(struct fsnotify_mark *mark, u32 set, u32 clear)
+{
+	bool recalc = false;
+	u32 mask;
+
+	WARN_ON_ONCE(clear & set);
+
+	spin_lock(&mark->lock);
+	mask = mark->mask;
+	mark->mask |= set;
+	mark->mask &= ~clear;
+	if (mark->mask != mask)
+		recalc = true;
+	spin_unlock(&mark->lock);
+
+	if (recalc)
+		fsnotify_recalc_mask(mark->connector);
+}
+EXPORT_SYMBOL_GPL(fsnotify_modify_mark_mask);
+
 /* Free all connectors queued for freeing once SRCU period ends */
 static void fsnotify_connector_destroy_workfn(struct work_struct *work)
 {
diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h
index 95985400d3d8..66e185bd1b1b 100644
--- a/include/linux/fsnotify_backend.h
+++ b/include/linux/fsnotify_backend.h
@@ -917,6 +917,7 @@ extern void fsnotify_get_mark(struct fsnotify_mark *mark);
 extern void fsnotify_put_mark(struct fsnotify_mark *mark);
 extern void fsnotify_finish_user_wait(struct fsnotify_iter_info *iter_info);
 extern bool fsnotify_prepare_user_wait(struct fsnotify_iter_info *iter_info);
+extern void fsnotify_modify_mark_mask(struct fsnotify_mark *mark, u32 set, u32 clear);
 
 static inline void fsnotify_init_event(struct fsnotify_event *event)
 {

-- 
2.53.0

[PATCH 08/24] nfsd: update the fsnotify mark when setting or removing a dir delegation

[Jeff Layton]

Add a new helper function that will update the mask on the nfsd_file's
fsnotify_mark to be a union of all current directory delegations on an
inode. Call that when directory delegations are added or removed.

Signed-off-by: Jeff Layton <jlayton@kernel.org>
---
 fs/nfsd/nfs4state.c | 33 +++++++++++++++++++++++++++++++++
 1 file changed, 33 insertions(+)

diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index c8fb84c38637..9a4cff08c67d 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -1258,6 +1258,37 @@ static void nfsd4_finalize_deleg_timestamps(struct nfs4_delegation *dp, struct f
 	}
 }
 
+static void nfsd_fsnotify_recalc_mask(struct nfsd_file *nf)
+{
+	struct fsnotify_mark *mark = &nf->nf_mark->nfm_mark;
+	struct inode *inode = file_inode(nf->nf_file);
+	u32 lease_mask, set = 0, clear = 0;
+
+	/* This is only needed when adding or removing dir delegs */
+	if (!S_ISDIR(inode->i_mode))
+		return;
+
+	/* Set up notifications for any ignored delegation events */
+	lease_mask = inode_lease_ignore_mask(inode);
+
+	if (lease_mask & FL_IGN_DIR_CREATE)
+		set |= FS_CREATE;
+	else
+		clear |= FS_CREATE;
+
+	if (lease_mask & FL_IGN_DIR_DELETE)
+		set |= FS_DELETE;
+	else
+		clear |= FS_DELETE;
+
+	if (lease_mask & FL_IGN_DIR_RENAME)
+		set |= FS_RENAME;
+	else
+		clear |= FS_RENAME;
+
+	fsnotify_modify_mark_mask(mark, set, clear);
+}
+
 static void nfs4_unlock_deleg_lease(struct nfs4_delegation *dp)
 {
 	struct nfs4_file *fp = dp->dl_stid.sc_file;
@@ -1266,6 +1297,7 @@ static void nfs4_unlock_deleg_lease(struct nfs4_delegation *dp)
 	WARN_ON_ONCE(!fp->fi_delegees);
 
 	nfsd4_finalize_deleg_timestamps(dp, nf->nf_file);
+	nfsd_fsnotify_recalc_mask(nf);
 	kernel_setlease(nf->nf_file, F_UNLCK, NULL, (void **)&dp);
 	put_deleg_file(fp);
 }
@@ -9652,6 +9684,7 @@ nfsd_get_dir_deleg(struct nfsd4_compound_state *cstate,
 
 	if (!status) {
 		put_nfs4_file(fp);
+		nfsd_fsnotify_recalc_mask(nf);
 		return dp;
 	}
 

-- 
2.53.0

[PATCH 09/24] nfsd: make nfsd4_callback_ops->prepare operation bool return

[Jeff Layton]

For a CB_NOTIFY operation, we need to stop processing the callback
if an allocation fails. Change the ->prepare callback operation to
return true if processing should continue, and false otherwise.

Signed-off-by: Jeff Layton <jlayton@kernel.org>
---
 fs/nfsd/nfs4callback.c | 5 ++++-
 fs/nfsd/nfs4layouts.c  | 3 ++-
 fs/nfsd/nfs4state.c    | 6 ++++--
 fs/nfsd/state.h        | 6 +++---
 4 files changed, 13 insertions(+), 7 deletions(-)

diff --git a/fs/nfsd/nfs4callback.c b/fs/nfsd/nfs4callback.c
index 50827405468d..25bbf5b8814d 100644
--- a/fs/nfsd/nfs4callback.c
+++ b/fs/nfsd/nfs4callback.c
@@ -1715,7 +1715,10 @@ nfsd4_run_cb_work(struct work_struct *work)
 
 	if (!test_and_clear_bit(NFSD4_CALLBACK_REQUEUE, &cb->cb_flags)) {
 		if (cb->cb_ops && cb->cb_ops->prepare)
-			cb->cb_ops->prepare(cb);
+			if (!cb->cb_ops->prepare(cb)) {
+				nfsd41_destroy_cb(cb);
+				return;
+			}
 	}
 
 	cb->cb_msg.rpc_cred = clp->cl_cb_cred;
diff --git a/fs/nfsd/nfs4layouts.c b/fs/nfsd/nfs4layouts.c
index c550b83f4432..8974e3d85d75 100644
--- a/fs/nfsd/nfs4layouts.c
+++ b/fs/nfsd/nfs4layouts.c
@@ -654,7 +654,7 @@ nfsd4_cb_layout_fail(struct nfs4_layout_stateid *ls, struct nfsd_file *file)
 	}
 }
 
-static void
+static bool
 nfsd4_cb_layout_prepare(struct nfsd4_callback *cb)
 {
 	struct nfs4_layout_stateid *ls =
@@ -663,6 +663,7 @@ nfsd4_cb_layout_prepare(struct nfsd4_callback *cb)
 	mutex_lock(&ls->ls_mutex);
 	nfs4_inc_and_copy_stateid(&ls->ls_recall_sid, &ls->ls_stid);
 	mutex_unlock(&ls->ls_mutex);
+	return true;
 }
 
 static int
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 9a4cff08c67d..fd3d7cd427e1 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -355,12 +355,13 @@ remove_blocked_locks(struct nfs4_lockowner *lo)
 	}
 }
 
-static void
+static bool
 nfsd4_cb_notify_lock_prepare(struct nfsd4_callback *cb)
 {
 	struct nfsd4_blocked_lock	*nbl = container_of(cb,
 						struct nfsd4_blocked_lock, nbl_cb);
 	locks_delete_block(&nbl->nbl_lock);
+	return true;
 }
 
 static int
@@ -5538,7 +5539,7 @@ bool nfsd_wait_for_delegreturn(struct svc_rqst *rqstp, struct inode *inode)
 	return timeo > 0;
 }
 
-static void nfsd4_cb_recall_prepare(struct nfsd4_callback *cb)
+static bool nfsd4_cb_recall_prepare(struct nfsd4_callback *cb)
 {
 	struct nfs4_delegation *dp = cb_to_delegation(cb);
 	struct nfsd_net *nn = net_generic(dp->dl_stid.sc_client->net,
@@ -5559,6 +5560,7 @@ static void nfsd4_cb_recall_prepare(struct nfsd4_callback *cb)
 		list_add_tail(&dp->dl_recall_lru, &nn->del_recall_lru);
 	}
 	spin_unlock(&nn->deleg_lock);
+	return true;
 }
 
 static int nfsd4_cb_recall_done(struct nfsd4_callback *cb,
diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h
index 811c148f36fc..7d2afe7dcc3e 100644
--- a/fs/nfsd/state.h
+++ b/fs/nfsd/state.h
@@ -98,9 +98,9 @@ struct nfsd4_callback {
 };
 
 struct nfsd4_callback_ops {
-	void (*prepare)(struct nfsd4_callback *);
-	int (*done)(struct nfsd4_callback *, struct rpc_task *);
-	void (*release)(struct nfsd4_callback *);
+	bool (*prepare)(struct nfsd4_callback *cb);
+	int (*done)(struct nfsd4_callback *cb, struct rpc_task *task);
+	void (*release)(struct nfsd4_callback *cb);
 	uint32_t opcode;
 };
 

-- 
2.53.0

[PATCH 10/24] nfsd: add callback encoding and decoding linkages for CB_NOTIFY

[Jeff Layton]

Add routines for encoding and decoding CB_NOTIFY messages. These call
into the code generated by xdrgen to do the actual encoding and
decoding.

Signed-off-by: Jeff Layton <jlayton@kernel.org>
---
 fs/nfsd/nfs4callback.c | 46 ++++++++++++++++++++++++++++++++++++++++++++++
 fs/nfsd/state.h        |  8 ++++++++
 fs/nfsd/xdr4cb.h       | 12 ++++++++++++
 3 files changed, 66 insertions(+)

diff --git a/fs/nfsd/nfs4callback.c b/fs/nfsd/nfs4callback.c
index 25bbf5b8814d..ea3e7deb06fa 100644
--- a/fs/nfsd/nfs4callback.c
+++ b/fs/nfsd/nfs4callback.c
@@ -865,6 +865,51 @@ static void encode_stateowner(struct xdr_stream *xdr, struct nfs4_stateowner *so
 	xdr_encode_opaque(p, so->so_owner.data, so->so_owner.len);
 }
 
+static void nfs4_xdr_enc_cb_notify(struct rpc_rqst *req,
+				   struct xdr_stream *xdr,
+				   const void *data)
+{
+	const struct nfsd4_callback *cb = data;
+	struct nfs4_cb_compound_hdr hdr = {
+		.ident = 0,
+		.minorversion = cb->cb_clp->cl_minorversion,
+	};
+	struct CB_NOTIFY4args args = { };
+
+	WARN_ON_ONCE(hdr.minorversion == 0);
+
+	encode_cb_compound4args(xdr, &hdr);
+	encode_cb_sequence4args(xdr, cb, &hdr);
+
+	/*
+	 * FIXME: get stateid and fh from delegation. Inline the cna_changes
+	 * buffer, and zero it.
+	 */
+	WARN_ON_ONCE(!xdrgen_encode_CB_NOTIFY4args(xdr, &args));
+
+	hdr.nops++;
+	encode_cb_nops(&hdr);
+}
+
+static int nfs4_xdr_dec_cb_notify(struct rpc_rqst *rqstp,
+				  struct xdr_stream *xdr,
+				  void *data)
+{
+	struct nfsd4_callback *cb = data;
+	struct nfs4_cb_compound_hdr hdr;
+	int status;
+
+	status = decode_cb_compound4res(xdr, &hdr);
+	if (unlikely(status))
+		return status;
+
+	status = decode_cb_sequence4res(xdr, cb);
+	if (unlikely(status || cb->cb_seq_status))
+		return status;
+
+	return decode_cb_op_status(xdr, OP_CB_NOTIFY, &cb->cb_status);
+}
+
 static void nfs4_xdr_enc_cb_notify_lock(struct rpc_rqst *req,
 					struct xdr_stream *xdr,
 					const void *data)
@@ -1026,6 +1071,7 @@ static const struct rpc_procinfo nfs4_cb_procedures[] = {
 #ifdef CONFIG_NFSD_PNFS
 	PROC(CB_LAYOUT,	COMPOUND,	cb_layout,	cb_layout),
 #endif
+	PROC(CB_NOTIFY,		COMPOUND,	cb_notify,	cb_notify),
 	PROC(CB_NOTIFY_LOCK,	COMPOUND,	cb_notify_lock,	cb_notify_lock),
 	PROC(CB_OFFLOAD,	COMPOUND,	cb_offload,	cb_offload),
 	PROC(CB_RECALL_ANY,	COMPOUND,	cb_recall_any,	cb_recall_any),
diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h
index 7d2afe7dcc3e..22c9a1e7d8fd 100644
--- a/fs/nfsd/state.h
+++ b/fs/nfsd/state.h
@@ -190,6 +190,13 @@ struct nfs4_cb_fattr {
 	u64 ncf_cur_fsize;
 };
 
+/*
+ * FIXME: the current backchannel encoder can't handle a send buffer longer
+ *        than a single page (see bc_alloc/bc_free).
+ */
+#define NOTIFY4_EVENT_QUEUE_SIZE	3
+#define NOTIFY4_PAGE_ARRAY_SIZE		1
+
 /*
  * Represents a delegation stateid. The nfs4_client holds references to these
  * and they are put when it is being destroyed or when the delegation is
@@ -774,6 +781,7 @@ enum nfsd4_cb_op {
 	NFSPROC4_CLNT_CB_NOTIFY_LOCK,
 	NFSPROC4_CLNT_CB_RECALL_ANY,
 	NFSPROC4_CLNT_CB_GETATTR,
+	NFSPROC4_CLNT_CB_NOTIFY,
 };
 
 /* Returns true iff a is later than b: */
diff --git a/fs/nfsd/xdr4cb.h b/fs/nfsd/xdr4cb.h
index f4e29c0c701c..b06d0170d7c4 100644
--- a/fs/nfsd/xdr4cb.h
+++ b/fs/nfsd/xdr4cb.h
@@ -33,6 +33,18 @@
 					cb_sequence_dec_sz +            \
 					op_dec_sz)
 
+#define NFS4_enc_cb_notify_sz		(cb_compound_enc_hdr_sz +       \
+					cb_sequence_enc_sz +            \
+					1 + enc_stateid_sz +            \
+					enc_nfs4_fh_sz +		\
+					1 +				\
+					NOTIFY4_EVENT_QUEUE_SIZE *	\
+					(2 + (NFS4_OPAQUE_LIMIT >> 2)))
+
+#define NFS4_dec_cb_notify_sz		(cb_compound_dec_hdr_sz  +      \
+					cb_sequence_dec_sz +            \
+					op_dec_sz)
+
 #define NFS4_enc_cb_notify_lock_sz	(cb_compound_enc_hdr_sz +        \
 					cb_sequence_enc_sz +             \
 					2 + 1 +				 \

-- 
2.53.0

[PATCH 11/24] nfsd: use RCU to protect fi_deleg_file

[Jeff Layton]

fi_deleg_file can be NULLed by put_deleg_file() when fi_delegees drops
to zero during delegation teardown (e.g. DELEGRETURN). Concurrent
accesses from workqueue callbacks -- such as CB_NOTIFY -- can
dereference a NULL pointer if they race with this teardown.

Annotate fi_deleg_file with __rcu and convert all accessors to use
proper RCU primitives:

- rcu_assign_pointer() / RCU_INIT_POINTER() for stores
- rcu_dereference_protected() for reads under fi_lock or where
  fi_delegees > 0 guarantees stability

This prepares for a subsequent patch that will use rcu_read_lock +
rcu_dereference + nfsd_file_get to safely acquire a reference from
the CB_NOTIFY callback path without holding fi_lock.

Signed-off-by: Jeff Layton <jlayton@kernel.org>
---
 fs/nfsd/nfs4layouts.c |  2 +-
 fs/nfsd/nfs4state.c   | 40 ++++++++++++++++++++++++----------------
 fs/nfsd/state.h       |  2 +-
 3 files changed, 26 insertions(+), 18 deletions(-)

diff --git a/fs/nfsd/nfs4layouts.c b/fs/nfsd/nfs4layouts.c
index 8974e3d85d75..d32cc6b38c23 100644
--- a/fs/nfsd/nfs4layouts.c
+++ b/fs/nfsd/nfs4layouts.c
@@ -248,7 +248,7 @@ nfsd4_alloc_layout_stateid(struct nfsd4_compound_state *cstate,
 			NFSPROC4_CLNT_CB_LAYOUT);
 
 	if (parent->sc_type == SC_TYPE_DELEG)
-		ls->ls_file = nfsd_file_get(fp->fi_deleg_file);
+		ls->ls_file = nfsd_file_get(rcu_dereference_protected(fp->fi_deleg_file, 1));
 	else
 		ls->ls_file = find_any_file(fp);
 	BUG_ON(!ls->ls_file);
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index fd3d7cd427e1..4afe7e68fb51 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -1210,7 +1210,9 @@ static void put_deleg_file(struct nfs4_file *fp)
 
 	spin_lock(&fp->fi_lock);
 	if (--fp->fi_delegees == 0) {
-		swap(nf, fp->fi_deleg_file);
+		nf = rcu_dereference_protected(fp->fi_deleg_file,
+					       lockdep_is_held(&fp->fi_lock));
+		rcu_assign_pointer(fp->fi_deleg_file, NULL);
 		swap(rnf, fp->fi_rdeleg_file);
 	}
 	spin_unlock(&fp->fi_lock);
@@ -1293,7 +1295,7 @@ static void nfsd_fsnotify_recalc_mask(struct nfsd_file *nf)
 static void nfs4_unlock_deleg_lease(struct nfs4_delegation *dp)
 {
 	struct nfs4_file *fp = dp->dl_stid.sc_file;
-	struct nfsd_file *nf = fp->fi_deleg_file;
+	struct nfsd_file *nf = rcu_dereference_protected(fp->fi_deleg_file, 1);
 
 	WARN_ON_ONCE(!fp->fi_delegees);
 
@@ -3159,7 +3161,8 @@ static int nfs4_show_deleg(struct seq_file *s, struct nfs4_stid *st)
 	/* XXX: lease time, whether it's being recalled. */
 
 	spin_lock(&nf->fi_lock);
-	file = nf->fi_deleg_file;
+	file = rcu_dereference_protected(nf->fi_deleg_file,
+					 lockdep_is_held(&nf->fi_lock));
 	if (file) {
 		seq_puts(s, ", ");
 		nfs4_show_superblock(s, file);
@@ -4941,7 +4944,7 @@ static void nfsd4_file_init(const struct svc_fh *fh, struct nfs4_file *fp)
 	INIT_LIST_HEAD(&fp->fi_delegations);
 	INIT_LIST_HEAD(&fp->fi_clnt_odstate);
 	fh_copy_shallow(&fp->fi_fhandle, &fh->fh_handle);
-	fp->fi_deleg_file = NULL;
+	RCU_INIT_POINTER(fp->fi_deleg_file, NULL);
 	fp->fi_rdeleg_file = NULL;
 	fp->fi_had_conflict = false;
 	fp->fi_share_deny = 0;
@@ -6082,7 +6085,7 @@ static struct file_lease *nfs4_alloc_init_lease(struct nfs4_delegation *dp, u32
 	fl->c.flc_type = deleg_is_read(dp->dl_type) ? 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->c.flc_file = rcu_dereference_protected(dp->dl_stid.sc_file->fi_deleg_file, 1)->nf_file;
 	return fl;
 }
 
@@ -6090,7 +6093,7 @@ static int nfsd4_check_conflicting_opens(struct nfs4_client *clp,
 					 struct nfs4_file *fp)
 {
 	struct nfs4_ol_stateid *st;
-	struct file *f = fp->fi_deleg_file->nf_file;
+	struct file *f = rcu_dereference_protected(fp->fi_deleg_file, 1)->nf_file;
 	struct inode *ino = file_inode(f);
 	int writes;
 
@@ -6167,7 +6170,7 @@ nfsd4_verify_deleg_dentry(struct nfsd4_open *open, struct nfs4_file *fp,
 
 	exp_put(exp);
 	dput(child);
-	if (child != file_dentry(fp->fi_deleg_file->nf_file))
+	if (child != file_dentry(rcu_dereference_protected(fp->fi_deleg_file, 1)->nf_file))
 		return -EAGAIN;
 
 	return 0;
@@ -6273,8 +6276,9 @@ nfs4_set_delegation(struct nfsd4_open *open, struct nfs4_ol_stateid *stp,
 		status = -EAGAIN;
 	else if (nfsd4_verify_setuid_write(open, nf))
 		status = -EAGAIN;
-	else if (!fp->fi_deleg_file) {
-		fp->fi_deleg_file = nf;
+	else if (!rcu_dereference_protected(fp->fi_deleg_file,
+					    lockdep_is_held(&fp->fi_lock))) {
+		rcu_assign_pointer(fp->fi_deleg_file, nf);
 		/* increment early to prevent fi_deleg_file from being
 		 * cleared */
 		fp->fi_delegees = 1;
@@ -6299,7 +6303,7 @@ nfs4_set_delegation(struct nfsd4_open *open, struct nfs4_ol_stateid *stp,
 	if (!fl)
 		goto out_clnt_odstate;
 
-	status = kernel_setlease(fp->fi_deleg_file->nf_file,
+	status = kernel_setlease(rcu_dereference_protected(fp->fi_deleg_file, 1)->nf_file,
 				      fl->c.flc_type, &fl, NULL);
 	if (fl)
 		locks_free_lease(fl);
@@ -6320,7 +6324,7 @@ nfs4_set_delegation(struct nfsd4_open *open, struct nfs4_ol_stateid *stp,
 	 * Now that the deleg is set, check again to ensure that nothing
 	 * raced in and changed the mode while we weren't looking.
 	 */
-	status = nfsd4_verify_setuid_write(open, fp->fi_deleg_file);
+	status = nfsd4_verify_setuid_write(open, rcu_dereference_protected(fp->fi_deleg_file, 1));
 	if (status)
 		goto out_unlock;
 
@@ -6341,7 +6345,8 @@ nfs4_set_delegation(struct nfsd4_open *open, struct nfs4_ol_stateid *stp,
 
 	return dp;
 out_unlock:
-	kernel_setlease(fp->fi_deleg_file->nf_file, F_UNLCK, NULL, (void **)&dp);
+	kernel_setlease(rcu_dereference_protected(fp->fi_deleg_file, 1)->nf_file,
+			F_UNLCK, NULL, (void **)&dp);
 out_clnt_odstate:
 	put_clnt_odstate(dp->dl_clnt_odstate);
 	nfs4_put_stid(&dp->dl_stid);
@@ -6498,8 +6503,9 @@ nfs4_open_delegation(struct svc_rqst *rqstp, struct nfsd4_open *open,
 	memcpy(&open->op_delegate_stateid, &dp->dl_stid.sc_stateid, sizeof(dp->dl_stid.sc_stateid));
 
 	if (open->op_share_access & NFS4_SHARE_ACCESS_WRITE) {
-		struct file *f = dp->dl_stid.sc_file->fi_deleg_file->nf_file;
+		struct file *f;
 
+		f = rcu_dereference_protected(dp->dl_stid.sc_file->fi_deleg_file, 1)->nf_file;
 		if (!nfsd4_add_rdaccess_to_wrdeleg(rqstp, open, fh, stp) ||
 				!nfs4_delegation_stat(dp, currentfh, &stat)) {
 			nfs4_put_stid(&dp->dl_stid);
@@ -9638,8 +9644,9 @@ nfsd_get_dir_deleg(struct nfsd4_compound_state *cstate,
 	/* existing delegation? */
 	if (nfs4_delegation_exists(clp, fp)) {
 		status = -EAGAIN;
-	} else if (!fp->fi_deleg_file) {
-		fp->fi_deleg_file = nfsd_file_get(nf);
+	} else if (!rcu_dereference_protected(fp->fi_deleg_file,
+					      lockdep_is_held(&fp->fi_lock))) {
+		rcu_assign_pointer(fp->fi_deleg_file, nfsd_file_get(nf));
 		fp->fi_delegees = 1;
 	} else {
 		++fp->fi_delegees;
@@ -9691,7 +9698,8 @@ nfsd_get_dir_deleg(struct nfsd4_compound_state *cstate,
 	}
 
 	/* Something failed. Drop the lease and clean up the stid */
-	kernel_setlease(fp->fi_deleg_file->nf_file, F_UNLCK, NULL, (void **)&dp);
+	kernel_setlease(rcu_dereference_protected(fp->fi_deleg_file, 1)->nf_file,
+			F_UNLCK, NULL, (void **)&dp);
 out_put_stid:
 	nfs4_put_stid(&dp->dl_stid);
 out_delegees:
diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h
index 22c9a1e7d8fd..eb5946b0999e 100644
--- a/fs/nfsd/state.h
+++ b/fs/nfsd/state.h
@@ -698,7 +698,7 @@ struct nfs4_file {
 	 */
 	atomic_t		fi_access[2];
 	u32			fi_share_deny;
-	struct nfsd_file	*fi_deleg_file;
+	struct nfsd_file __rcu	*fi_deleg_file;
 	struct nfsd_file	*fi_rdeleg_file;
 	int			fi_delegees;
 	struct knfsd_fh		fi_fhandle;

-- 
2.53.0

[PATCH 12/24] nfsd: add data structures for handling CB_NOTIFY

[Jeff Layton]

Add the data structures, allocation helpers, and callback operations
needed for directory delegation CB_NOTIFY support:

- struct nfsd_notify_event: carries fsnotify events for CB_NOTIFY
- struct nfsd4_cb_notify: per-delegation state for notification handling
- Union dl_cb_fattr with dl_cb_notify in nfs4_delegation since a
  delegation is either a regular file delegation or a directory
  delegation, never both

Refactor alloc_init_deleg() into a common __alloc_init_deleg() base
with a pluggable sc_free callback, and add alloc_init_dir_deleg() which
allocates the page array and notify4 buffer needed for CB_NOTIFY
encoding.

Add skeleton nfsd4_cb_notify_ops with done/release handlers that will
be filled in when the notification path is wired up.

Signed-off-by: Jeff Layton <jlayton@kernel.org>
---
 fs/nfsd/nfs4state.c | 117 +++++++++++++++++++++++++++++++++++++++++++++-------
 fs/nfsd/state.h     |  46 ++++++++++++++++++++-
 2 files changed, 147 insertions(+), 16 deletions(-)

diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 4afe7e68fb51..b2b8c454fc0f 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -124,6 +124,7 @@ static void free_session(struct nfsd4_session *);
 static const struct nfsd4_callback_ops nfsd4_cb_recall_ops;
 static const struct nfsd4_callback_ops nfsd4_cb_notify_lock_ops;
 static const struct nfsd4_callback_ops nfsd4_cb_getattr_ops;
+static const struct nfsd4_callback_ops nfsd4_cb_notify_ops;
 
 static struct workqueue_struct *laundry_wq;
 
@@ -1121,29 +1122,31 @@ static void block_delegations(struct knfsd_fh *fh)
 }
 
 static struct nfs4_delegation *
-alloc_init_deleg(struct nfs4_client *clp, struct nfs4_file *fp,
-		 struct nfs4_clnt_odstate *odstate, u32 dl_type)
+__alloc_init_deleg(struct nfs4_client *clp, struct nfs4_file *fp,
+		   struct nfs4_clnt_odstate *odstate, u32 dl_type,
+		   void (*sc_free)(struct nfs4_stid *))
 {
 	struct nfs4_delegation *dp;
 	struct nfs4_stid *stid;
 	long n;
 
-	dprintk("NFSD alloc_init_deleg\n");
+	if (delegation_blocked(&fp->fi_fhandle))
+		return NULL;
+
 	n = atomic_long_inc_return(&num_delegations);
 	if (n < 0 || n > max_delegations)
 		goto out_dec;
-	if (delegation_blocked(&fp->fi_fhandle))
-		goto out_dec;
-	stid = nfs4_alloc_stid(clp, deleg_slab, nfs4_free_deleg);
+
+	stid = nfs4_alloc_stid(clp, deleg_slab, sc_free);
 	if (stid == NULL)
 		goto out_dec;
-	dp = delegstateid(stid);
 
 	/*
 	 * delegation seqid's are never incremented.  The 4.1 special
 	 * meaning of seqid 0 isn't meaningful, really, but let's avoid
-	 * 0 anyway just for consistency and use 1:
+	 * 0 anyway just for consistency and use 1.
 	 */
+	dp = delegstateid(stid);
 	dp->dl_stid.sc_stateid.si_generation = 1;
 	INIT_LIST_HEAD(&dp->dl_perfile);
 	INIT_LIST_HEAD(&dp->dl_perclnt);
@@ -1153,19 +1156,75 @@ alloc_init_deleg(struct nfs4_client *clp, struct nfs4_file *fp,
 	dp->dl_type = dl_type;
 	dp->dl_retries = 1;
 	dp->dl_recalled = false;
-	nfsd4_init_cb(&dp->dl_recall, dp->dl_stid.sc_client,
-		      &nfsd4_cb_recall_ops, NFSPROC4_CLNT_CB_RECALL);
-	nfsd4_init_cb(&dp->dl_cb_fattr.ncf_getattr, dp->dl_stid.sc_client,
-			&nfsd4_cb_getattr_ops, NFSPROC4_CLNT_CB_GETATTR);
-	dp->dl_cb_fattr.ncf_file_modified = false;
 	get_nfs4_file(fp);
 	dp->dl_stid.sc_file = fp;
+	nfsd4_init_cb(&dp->dl_recall, dp->dl_stid.sc_client,
+		      &nfsd4_cb_recall_ops, NFSPROC4_CLNT_CB_RECALL);
 	return dp;
 out_dec:
 	atomic_long_dec(&num_delegations);
 	return NULL;
 }
 
+static struct nfs4_delegation *
+alloc_init_deleg(struct nfs4_client *clp, struct nfs4_file *fp,
+		 struct nfs4_clnt_odstate *odstate, u32 dl_type)
+{
+	struct nfs4_delegation *dp;
+
+	dp = __alloc_init_deleg(clp, fp, odstate, dl_type, nfs4_free_deleg);
+	if (!dp)
+		return NULL;
+
+	nfsd4_init_cb(&dp->dl_cb_fattr.ncf_getattr, dp->dl_stid.sc_client,
+			&nfsd4_cb_getattr_ops, NFSPROC4_CLNT_CB_GETATTR);
+	dp->dl_cb_fattr.ncf_file_modified = false;
+	return dp;
+}
+
+static void nfs4_free_dir_deleg(struct nfs4_stid *stid)
+{
+	struct nfs4_delegation	*dp = delegstateid(stid);
+	struct nfsd4_cb_notify *ncn = &dp->dl_cb_notify;
+	int i;
+
+	for (i = 0; i < ncn->ncn_evt_cnt; ++i)
+		nfsd_notify_event_put(ncn->ncn_evt[i]);
+	release_pages(ncn->ncn_pages, NOTIFY4_PAGE_ARRAY_SIZE);
+	kfree(ncn->ncn_nf);
+	nfs4_free_deleg(stid);
+}
+
+static struct nfs4_delegation *
+alloc_init_dir_deleg(struct nfs4_client *clp, struct nfs4_file *fp)
+{
+	struct nfs4_delegation *dp;
+	struct nfsd4_cb_notify *ncn;
+	int npages;
+
+	dp = __alloc_init_deleg(clp, fp, NULL, NFS4_OPEN_DELEGATE_READ, nfs4_free_dir_deleg);
+	if (!dp)
+		return NULL;
+
+	ncn = &dp->dl_cb_notify;
+
+	npages = alloc_pages_bulk(GFP_KERNEL, NOTIFY4_PAGE_ARRAY_SIZE, ncn->ncn_pages);
+	if (npages != NOTIFY4_PAGE_ARRAY_SIZE) {
+		nfs4_free_dir_deleg(&dp->dl_stid);
+		return NULL;
+	}
+
+	ncn->ncn_nf = kcalloc(NOTIFY4_EVENT_QUEUE_SIZE, sizeof(*ncn->ncn_nf), GFP_KERNEL);
+	if (!ncn->ncn_nf) {
+		nfs4_free_dir_deleg(&dp->dl_stid);
+		return NULL;
+	}
+	spin_lock_init(&ncn->ncn_lock);
+	nfsd4_init_cb(&ncn->ncn_cb, dp->dl_stid.sc_client,
+			&nfsd4_cb_notify_ops, NFSPROC4_CLNT_CB_NOTIFY);
+	return dp;
+}
+
 void
 nfs4_put_stid(struct nfs4_stid *s)
 {
@@ -3381,6 +3440,30 @@ nfsd4_cb_getattr_release(struct nfsd4_callback *cb)
 	nfs4_put_stid(&dp->dl_stid);
 }
 
+static int
+nfsd4_cb_notify_done(struct nfsd4_callback *cb,
+				struct rpc_task *task)
+{
+	switch (task->tk_status) {
+	case -NFS4ERR_DELAY:
+		rpc_delay(task, 2 * HZ);
+		return 0;
+	default:
+		return 1;
+	}
+}
+
+static void
+nfsd4_cb_notify_release(struct nfsd4_callback *cb)
+{
+	struct nfsd4_cb_notify *ncn =
+			container_of(cb, struct nfsd4_cb_notify, ncn_cb);
+	struct nfs4_delegation *dp =
+			container_of(ncn, struct nfs4_delegation, dl_cb_notify);
+
+	nfs4_put_stid(&dp->dl_stid);
+}
+
 static const struct nfsd4_callback_ops nfsd4_cb_recall_any_ops = {
 	.done		= nfsd4_cb_recall_any_done,
 	.release	= nfsd4_cb_recall_any_release,
@@ -3393,6 +3476,12 @@ static const struct nfsd4_callback_ops nfsd4_cb_getattr_ops = {
 	.opcode		= OP_CB_GETATTR,
 };
 
+static const struct nfsd4_callback_ops nfsd4_cb_notify_ops = {
+	.done		= nfsd4_cb_notify_done,
+	.release	= nfsd4_cb_notify_release,
+	.opcode		= OP_CB_NOTIFY,
+};
+
 static void nfs4_cb_getattr(struct nfs4_cb_fattr *ncf)
 {
 	struct nfs4_delegation *dp =
@@ -9661,7 +9750,7 @@ nfsd_get_dir_deleg(struct nfsd4_compound_state *cstate,
 
 	/* Try to set up the lease */
 	status = -ENOMEM;
-	dp = alloc_init_deleg(clp, fp, NULL, NFS4_OPEN_DELEGATE_READ);
+	dp = alloc_init_dir_deleg(clp, fp);
 	if (!dp)
 		goto out_delegees;
 	if (cstate->current_fh.fh_export)
diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h
index eb5946b0999e..500e07e47909 100644
--- a/fs/nfsd/state.h
+++ b/fs/nfsd/state.h
@@ -197,6 +197,44 @@ struct nfs4_cb_fattr {
 #define NOTIFY4_EVENT_QUEUE_SIZE	3
 #define NOTIFY4_PAGE_ARRAY_SIZE		1
 
+struct nfsd_notify_event {
+	refcount_t	ne_ref;		// refcount
+	u32		ne_mask;	// FS_* mask from fsnotify callback
+	struct dentry	*ne_dentry;	// dentry reference to target
+	u32		ne_namelen;	// length of ne_name
+	char		ne_name[];	// name of dentry being changed
+};
+
+static inline struct nfsd_notify_event *nfsd_notify_event_get(struct nfsd_notify_event *ne)
+{
+	refcount_inc(&ne->ne_ref);
+	return ne;
+}
+
+static inline void nfsd_notify_event_put(struct nfsd_notify_event *ne)
+{
+	if (refcount_dec_and_test(&ne->ne_ref)) {
+		dput(ne->ne_dentry);
+		kfree(ne);
+	}
+}
+
+/*
+ * Represents a directory delegation. The callback is for handling CB_NOTIFYs.
+ * As notifications from fsnotify come in, allocate a new event, take the ncn_lock,
+ * and add it to the ncn_evt queue. The CB_NOTIFY prepare handler will take the
+ * lock, clean out the list and process it.
+ */
+struct nfsd4_cb_notify {
+	spinlock_t			ncn_lock;	// protects the evt queue and count
+	int				ncn_evt_cnt;	// count of events in ncn_evt
+	int				ncn_nf_cnt;	// count of valid entries in ncn_nf
+	struct nfsd_notify_event	*ncn_evt[NOTIFY4_EVENT_QUEUE_SIZE]; // list of events
+	struct page			*ncn_pages[NOTIFY4_PAGE_ARRAY_SIZE]; // for encoding
+	struct notify4			*ncn_nf;	// array of notify4's to be sent
+	struct nfsd4_callback		ncn_cb;		// notify4 callback
+};
+
 /*
  * Represents a delegation stateid. The nfs4_client holds references to these
  * and they are put when it is being destroyed or when the delegation is
@@ -233,8 +271,12 @@ struct nfs4_delegation {
 	bool			dl_written;
 	bool			dl_setattr;
 
-	/* for CB_GETATTR */
-	struct nfs4_cb_fattr    dl_cb_fattr;
+	union {
+		/* for CB_GETATTR */
+		struct nfs4_cb_fattr    dl_cb_fattr;
+		/* for CB_NOTIFY */
+		struct nfsd4_cb_notify	dl_cb_notify;
+	};
 
 	/* For delegated timestamps */
 	struct timespec64	dl_atime;

-- 
2.53.0

[PATCH 13/24] nfsd: add notification handlers for dir events

[Jeff Layton]

Add the necessary parts to accept a fsnotify callback for directory
change event and create a CB_NOTIFY request for it. When a dir nfsd_file
is created set a handle_event callback to handle the notification.

Use that to allocate a nfsd_notify_event object and then hand off a
reference to each delegation's CB_NOTIFY. If anything fails along the
way, recall any affected delegations.

Signed-off-by: Jeff Layton <jlayton@kernel.org>
---
 fs/nfsd/filecache.c    |  57 ++++++++----
 fs/nfsd/nfs4callback.c |  19 +++-
 fs/nfsd/nfs4state.c    | 248 ++++++++++++++++++++++++++++++++++++++++++++-----
 fs/nfsd/nfs4xdr.c      |  96 +++++++++++++++++++
 fs/nfsd/state.h        |   2 +
 fs/nfsd/xdr4.h         |   3 +
 6 files changed, 383 insertions(+), 42 deletions(-)

diff --git a/fs/nfsd/filecache.c b/fs/nfsd/filecache.c
index 24511c3208db..56889fca6dca 100644
--- a/fs/nfsd/filecache.c
+++ b/fs/nfsd/filecache.c
@@ -72,6 +72,7 @@ static struct kmem_cache		*nfsd_file_mark_slab;
 static struct list_lru			nfsd_file_lru;
 static unsigned long			nfsd_file_flags;
 static struct fsnotify_group		*nfsd_file_fsnotify_group;
+static struct fsnotify_group		*nfsd_dir_fsnotify_group;
 static struct delayed_work		nfsd_filecache_laundrette;
 static struct rhltable			nfsd_file_rhltable
 						____cacheline_aligned_in_smp;
@@ -147,7 +148,7 @@ static void
 nfsd_file_mark_put(struct nfsd_file_mark *nfm)
 {
 	if (refcount_dec_and_test(&nfm->nfm_ref)) {
-		fsnotify_destroy_mark(&nfm->nfm_mark, nfsd_file_fsnotify_group);
+		fsnotify_destroy_mark(&nfm->nfm_mark, nfm->nfm_mark.group);
 		fsnotify_put_mark(&nfm->nfm_mark);
 	}
 }
@@ -155,35 +156,37 @@ nfsd_file_mark_put(struct nfsd_file_mark *nfm)
 static struct nfsd_file_mark *
 nfsd_file_mark_find_or_create(struct inode *inode)
 {
-	int			err;
-	struct fsnotify_mark	*mark;
 	struct nfsd_file_mark	*nfm = NULL, *new;
+	struct fsnotify_group	*group;
+	struct fsnotify_mark	*mark;
+	int			err;
+
+	group = S_ISDIR(inode->i_mode) ? nfsd_dir_fsnotify_group : nfsd_file_fsnotify_group;
 
 	do {
-		fsnotify_group_lock(nfsd_file_fsnotify_group);
-		mark = fsnotify_find_inode_mark(inode,
-						nfsd_file_fsnotify_group);
+		fsnotify_group_lock(group);
+		mark = fsnotify_find_inode_mark(inode, group);
 		if (mark) {
 			nfm = nfsd_file_mark_get(container_of(mark,
 						 struct nfsd_file_mark,
 						 nfm_mark));
-			fsnotify_group_unlock(nfsd_file_fsnotify_group);
+			fsnotify_group_unlock(group);
 			if (nfm) {
 				fsnotify_put_mark(mark);
 				break;
 			}
 			/* Avoid soft lockup race with nfsd_file_mark_put() */
-			fsnotify_destroy_mark(mark, nfsd_file_fsnotify_group);
+			fsnotify_destroy_mark(mark, group);
 			fsnotify_put_mark(mark);
 		} else {
-			fsnotify_group_unlock(nfsd_file_fsnotify_group);
+			fsnotify_group_unlock(group);
 		}
 
 		/* allocate a new nfm */
 		new = kmem_cache_alloc(nfsd_file_mark_slab, GFP_KERNEL);
 		if (!new)
 			return NULL;
-		fsnotify_init_mark(&new->nfm_mark, nfsd_file_fsnotify_group);
+		fsnotify_init_mark(&new->nfm_mark, group);
 		new->nfm_mark.mask = FS_ATTRIB|FS_DELETE_SELF;
 		refcount_set(&new->nfm_ref, 1);
 
@@ -812,12 +815,25 @@ nfsd_file_fsnotify_handle_event(struct fsnotify_mark *mark, u32 mask,
 	return 0;
 }
 
+static int
+nfsd_dir_fsnotify_handle_event(struct fsnotify_group *group, u32 mask,
+			       const void *data, int data_type, struct inode *dir,
+			       const struct qstr *name, u32 cookie,
+			       struct fsnotify_iter_info *iter_info)
+{
+	return nfsd_handle_dir_event(mask, dir, data, data_type, name);
+}
 
 static const struct fsnotify_ops nfsd_file_fsnotify_ops = {
 	.handle_inode_event = nfsd_file_fsnotify_handle_event,
 	.free_mark = nfsd_file_mark_free,
 };
 
+static const struct fsnotify_ops nfsd_dir_fsnotify_ops = {
+	.handle_event = nfsd_dir_fsnotify_handle_event,
+	.free_mark = nfsd_file_mark_free,
+};
+
 int
 nfsd_file_cache_init(void)
 {
@@ -869,8 +885,7 @@ nfsd_file_cache_init(void)
 		goto out_shrinker;
 	}
 
-	nfsd_file_fsnotify_group = fsnotify_alloc_group(&nfsd_file_fsnotify_ops,
-							0);
+	nfsd_file_fsnotify_group = fsnotify_alloc_group(&nfsd_file_fsnotify_ops, 0);
 	if (IS_ERR(nfsd_file_fsnotify_group)) {
 		pr_err("nfsd: unable to create fsnotify group: %ld\n",
 			PTR_ERR(nfsd_file_fsnotify_group));
@@ -879,11 +894,23 @@ nfsd_file_cache_init(void)
 		goto out_notifier;
 	}
 
+	nfsd_dir_fsnotify_group = fsnotify_alloc_group(&nfsd_dir_fsnotify_ops, 0);
+	if (IS_ERR(nfsd_dir_fsnotify_group)) {
+		pr_err("nfsd: unable to create fsnotify group: %ld\n",
+			PTR_ERR(nfsd_dir_fsnotify_group));
+		ret = PTR_ERR(nfsd_dir_fsnotify_group);
+		nfsd_dir_fsnotify_group = NULL;
+		goto out_notify_group;
+	}
+
 	INIT_DELAYED_WORK(&nfsd_filecache_laundrette, nfsd_file_gc_worker);
 out:
 	if (ret)
 		clear_bit(NFSD_FILE_CACHE_UP, &nfsd_file_flags);
 	return ret;
+out_notify_group:
+	fsnotify_put_group(nfsd_file_fsnotify_group);
+	nfsd_file_fsnotify_group = NULL;
 out_notifier:
 	lease_unregister_notifier(&nfsd_file_lease_notifier);
 out_shrinker:
@@ -1223,10 +1250,8 @@ nfsd_file_do_acquire(struct svc_rqst *rqstp, struct net *net,
 open_file:
 	trace_nfsd_file_alloc(nf);
 
-	if (type == S_IFREG)
-		nf->nf_mark = nfsd_file_mark_find_or_create(inode);
-
-	if (type != S_IFREG || nf->nf_mark) {
+	nf->nf_mark = nfsd_file_mark_find_or_create(inode);
+	if (nf->nf_mark) {
 		if (file) {
 			get_file(file);
 			nf->nf_file = file;
diff --git a/fs/nfsd/nfs4callback.c b/fs/nfsd/nfs4callback.c
index ea3e7deb06fa..1964a213f80e 100644
--- a/fs/nfsd/nfs4callback.c
+++ b/fs/nfsd/nfs4callback.c
@@ -870,21 +870,30 @@ static void nfs4_xdr_enc_cb_notify(struct rpc_rqst *req,
 				   const void *data)
 {
 	const struct nfsd4_callback *cb = data;
+	struct nfsd4_cb_notify *ncn = container_of(cb, struct nfsd4_cb_notify, ncn_cb);
+	struct nfs4_delegation *dp = container_of(ncn, struct nfs4_delegation, dl_cb_notify);
 	struct nfs4_cb_compound_hdr hdr = {
 		.ident = 0,
 		.minorversion = cb->cb_clp->cl_minorversion,
 	};
-	struct CB_NOTIFY4args args = { };
+	struct CB_NOTIFY4args args;
+	__be32 *p;
 
 	WARN_ON_ONCE(hdr.minorversion == 0);
 
 	encode_cb_compound4args(xdr, &hdr);
 	encode_cb_sequence4args(xdr, cb, &hdr);
 
-	/*
-	 * FIXME: get stateid and fh from delegation. Inline the cna_changes
-	 * buffer, and zero it.
-	 */
+	p = xdr_reserve_space(xdr, 4);
+	*p = cpu_to_be32(OP_CB_NOTIFY);
+
+	args.cna_stateid.seqid = dp->dl_stid.sc_stateid.si_generation;
+	memcpy(&args.cna_stateid.other, &dp->dl_stid.sc_stateid.si_opaque,
+	       ARRAY_SIZE(args.cna_stateid.other));
+	args.cna_fh.len = dp->dl_stid.sc_file->fi_fhandle.fh_size;
+	args.cna_fh.data = dp->dl_stid.sc_file->fi_fhandle.fh_raw;
+	args.cna_changes.count = ncn->ncn_nf_cnt;
+	args.cna_changes.element = ncn->ncn_nf;
 	WARN_ON_ONCE(!xdrgen_encode_CB_NOTIFY4args(xdr, &args));
 
 	hdr.nops++;
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index b2b8c454fc0f..339c3d0bb575 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -55,6 +55,7 @@
 #include "netns.h"
 #include "pnfs.h"
 #include "filecache.h"
+#include "nfs4xdr_gen.h"
 #include "trace.h"
 
 #define NFSDDBG_FACILITY                NFSDDBG_PROC
@@ -3440,15 +3441,125 @@ nfsd4_cb_getattr_release(struct nfsd4_callback *cb)
 	nfs4_put_stid(&dp->dl_stid);
 }
 
+static void nfsd_break_one_deleg(struct nfs4_delegation *dp)
+{
+	bool queued;
+
+	if (test_and_set_bit(NFSD4_CALLBACK_RUNNING, &dp->dl_recall.cb_flags))
+		return;
+
+	/*
+	 * We're assuming the state code never drops its reference
+	 * without first removing the lease.  Since we're in this lease
+	 * callback (and since the lease code is serialized by the
+	 * flc_lock) we know the server hasn't removed the lease yet, and
+	 * we know it's safe to take a reference.
+	 */
+	refcount_inc(&dp->dl_stid.sc_count);
+	queued = nfsd4_run_cb(&dp->dl_recall);
+	WARN_ON_ONCE(!queued);
+	if (!queued)
+		refcount_dec(&dp->dl_stid.sc_count);
+}
+
+static bool
+nfsd4_cb_notify_prepare(struct nfsd4_callback *cb)
+{
+	struct nfsd4_cb_notify *ncn = container_of(cb, struct nfsd4_cb_notify, ncn_cb);
+	struct nfs4_delegation *dp = container_of(ncn, struct nfs4_delegation, dl_cb_notify);
+	struct nfsd_notify_event *events[NOTIFY4_EVENT_QUEUE_SIZE];
+	struct xdr_buf xdr = { .buflen = PAGE_SIZE * NOTIFY4_PAGE_ARRAY_SIZE,
+			       .pages  = ncn->ncn_pages };
+	struct xdr_stream stream;
+	struct nfsd_file *nf;
+	int count, i;
+	bool error = false;
+
+	xdr_init_encode_pages(&stream, &xdr);
+
+	spin_lock(&ncn->ncn_lock);
+	count = ncn->ncn_evt_cnt;
+
+	/* spurious queueing? */
+	if (count == 0) {
+		spin_unlock(&ncn->ncn_lock);
+		return false;
+	}
+
+	/* we can't keep up! */
+	if (count > NOTIFY4_EVENT_QUEUE_SIZE) {
+		spin_unlock(&ncn->ncn_lock);
+		goto out_recall;
+	}
+
+	memcpy(events, ncn->ncn_evt, sizeof(*events) * count);
+	ncn->ncn_evt_cnt = 0;
+	spin_unlock(&ncn->ncn_lock);
+
+	rcu_read_lock();
+	nf = nfsd_file_get(rcu_dereference(dp->dl_stid.sc_file->fi_deleg_file));
+	rcu_read_unlock();
+	if (!nf) {
+		for (i = 0; i < count; ++i)
+			nfsd_notify_event_put(events[i]);
+		goto out_recall;
+	}
+
+	for (i = 0; i < count; ++i) {
+		struct nfsd_notify_event *nne = events[i];
+
+		if (!error) {
+			u32 *maskp = (u32 *)xdr_reserve_space(&stream, sizeof(*maskp));
+			u8 *p;
+
+			if (!maskp) {
+				error = true;
+				goto put_event;
+			}
+
+			p = nfsd4_encode_notify_event(&stream, nne, dp, nf, maskp);
+			if (!p) {
+				pr_notice("Count not generate CB_NOTIFY from fsnotify mask 0x%x\n",
+					  nne->ne_mask);
+				error = true;
+				goto put_event;
+			}
+
+			ncn->ncn_nf[i].notify_mask.count = 1;
+			ncn->ncn_nf[i].notify_mask.element = maskp;
+			ncn->ncn_nf[i].notify_vals.data = p;
+			ncn->ncn_nf[i].notify_vals.len = (u8 *)stream.p - p;
+		}
+put_event:
+		nfsd_notify_event_put(nne);
+	}
+	if (!error) {
+		ncn->ncn_nf_cnt = count;
+		nfsd_file_put(nf);
+		return true;
+	}
+	nfsd_file_put(nf);
+out_recall:
+	nfsd_break_one_deleg(dp);
+	return false;
+}
+
 static int
 nfsd4_cb_notify_done(struct nfsd4_callback *cb,
 				struct rpc_task *task)
 {
+	struct nfsd4_cb_notify *ncn = container_of(cb, struct nfsd4_cb_notify, ncn_cb);
+	struct nfs4_delegation *dp = container_of(ncn, struct nfs4_delegation, dl_cb_notify);
+
 	switch (task->tk_status) {
 	case -NFS4ERR_DELAY:
 		rpc_delay(task, 2 * HZ);
 		return 0;
 	default:
+		/* For any other hard error, recall the deleg */
+		nfsd_break_one_deleg(dp);
+		fallthrough;
+	case 0:
 		return 1;
 	}
 }
@@ -3477,6 +3588,7 @@ static const struct nfsd4_callback_ops nfsd4_cb_getattr_ops = {
 };
 
 static const struct nfsd4_callback_ops nfsd4_cb_notify_ops = {
+	.prepare	= nfsd4_cb_notify_prepare,
 	.done		= nfsd4_cb_notify_done,
 	.release	= nfsd4_cb_notify_release,
 	.opcode		= OP_CB_NOTIFY,
@@ -5702,27 +5814,6 @@ static const struct nfsd4_callback_ops nfsd4_cb_recall_ops = {
 	.opcode		= OP_CB_RECALL,
 };
 
-static void nfsd_break_one_deleg(struct nfs4_delegation *dp)
-{
-	bool queued;
-
-	if (test_and_set_bit(NFSD4_CALLBACK_RUNNING, &dp->dl_recall.cb_flags))
-		return;
-
-	/*
-	 * We're assuming the state code never drops its reference
-	 * without first removing the lease.  Since we're in this lease
-	 * callback (and since the lease code is serialized by the
-	 * flc_lock) we know the server hasn't removed the lease yet, and
-	 * we know it's safe to take a reference.
-	 */
-	refcount_inc(&dp->dl_stid.sc_count);
-	queued = nfsd4_run_cb(&dp->dl_recall);
-	WARN_ON_ONCE(!queued);
-	if (!queued)
-		refcount_dec(&dp->dl_stid.sc_count);
-}
-
 /* Called from break_lease() with flc_lock held. */
 static bool
 nfsd_break_deleg_cb(struct file_lease *fl)
@@ -9796,3 +9887,118 @@ nfsd_get_dir_deleg(struct nfsd4_compound_state *cstate,
 	put_nfs4_file(fp);
 	return ERR_PTR(status);
 }
+
+static void
+nfsd4_run_cb_notify(struct nfsd4_cb_notify *ncn)
+{
+	struct nfs4_delegation *dp = container_of(ncn, struct nfs4_delegation, dl_cb_notify);
+
+	if (test_and_set_bit(NFSD4_CALLBACK_RUNNING, &ncn->ncn_cb.cb_flags))
+		return;
+
+	if (!refcount_inc_not_zero(&dp->dl_stid.sc_count))
+		clear_bit(NFSD4_CALLBACK_RUNNING, &ncn->ncn_cb.cb_flags);
+	else
+		nfsd4_run_cb(&ncn->ncn_cb);
+}
+
+static struct nfsd_notify_event *
+alloc_nfsd_notify_event(u32 mask, const struct qstr *q, struct dentry *dentry)
+{
+	struct nfsd_notify_event *ne;
+
+	ne = kmalloc(sizeof(*ne) + q->len + 1, GFP_KERNEL);
+	if (!ne)
+		return NULL;
+
+	memcpy(&ne->ne_name, q->name, q->len);
+	refcount_set(&ne->ne_ref, 1);
+	ne->ne_mask = mask;
+	ne->ne_name[q->len] = '\0';
+	ne->ne_namelen = q->len;
+	ne->ne_dentry = dget(dentry);
+	return ne;
+}
+
+static bool
+should_notify_deleg(u32 mask, struct file_lease *fl)
+{
+	/* Only nfsd leases */
+	if (fl->fl_lmops != &nfsd_lease_mng_ops)
+		return false;
+
+	/* Skip if this event wasn't ignored by the lease */
+	if ((mask & FS_DELETE) && !(fl->c.flc_flags & FL_IGN_DIR_DELETE))
+		return false;
+	if ((mask & FS_CREATE) && !(fl->c.flc_flags & FL_IGN_DIR_CREATE))
+		return false;
+	if ((mask & FS_RENAME) && !(fl->c.flc_flags & FL_IGN_DIR_RENAME))
+		return false;
+
+	return true;
+}
+
+static void
+nfsd_recall_all_dir_delegs(const struct inode *dir)
+{
+	struct file_lock_context *ctx = locks_inode_context(dir);
+	struct file_lock_core *flc;
+
+	spin_lock(&ctx->flc_lock);
+	list_for_each_entry(flc, &ctx->flc_lease, flc_list) {
+		struct file_lease *fl = container_of(flc, struct file_lease, c);
+
+		if (fl->fl_lmops == &nfsd_lease_mng_ops)
+			nfsd_break_deleg_cb(fl);
+	}
+	spin_unlock(&ctx->flc_lock);
+}
+
+int
+nfsd_handle_dir_event(u32 mask, const struct inode *dir, const void *data,
+		      int data_type, const struct qstr *name)
+{
+	struct dentry *dentry = fsnotify_data_dentry(data, data_type);
+	struct file_lock_context *ctx;
+	struct file_lock_core *flc;
+	struct nfsd_notify_event *evt;
+
+	/* Don't do anything if this is not an expected event */
+	if (!(mask & (FS_CREATE|FS_DELETE|FS_RENAME)))
+		return 0;
+
+	ctx = locks_inode_context(dir);
+	if (!ctx || list_empty(&ctx->flc_lease))
+		return 0;
+
+	evt = alloc_nfsd_notify_event(mask, name, dentry);
+	if (!evt) {
+		nfsd_recall_all_dir_delegs(dir);
+		return 0;
+	}
+
+	spin_lock(&ctx->flc_lock);
+	list_for_each_entry(flc, &ctx->flc_lease, flc_list) {
+		struct file_lease *fl = container_of(flc, struct file_lease, c);
+		struct nfs4_delegation *dp = flc->flc_owner;
+		struct nfsd4_cb_notify *ncn = &dp->dl_cb_notify;
+
+		if (!should_notify_deleg(mask, fl))
+			continue;
+
+		spin_lock(&ncn->ncn_lock);
+		if (ncn->ncn_evt_cnt >= NOTIFY4_EVENT_QUEUE_SIZE) {
+			/* We're generating notifications too fast. Recall. */
+			spin_unlock(&ncn->ncn_lock);
+			nfsd_break_deleg_cb(fl);
+			continue;
+		}
+		ncn->ncn_evt[ncn->ncn_evt_cnt++] = nfsd_notify_event_get(evt);
+		spin_unlock(&ncn->ncn_lock);
+
+		nfsd4_run_cb_notify(ncn);
+	}
+	spin_unlock(&ctx->flc_lock);
+	nfsd_notify_event_put(evt);
+	return 0;
+}
diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c
index 2a0946c630e1..9ad13f96c219 100644
--- a/fs/nfsd/nfs4xdr.c
+++ b/fs/nfsd/nfs4xdr.c
@@ -4098,6 +4098,102 @@ nfsd4_encode_fattr4(struct svc_rqst *rqstp, struct xdr_stream *xdr,
 	goto out;
 }
 
+static bool
+nfsd4_setup_notify_entry4(struct notify_entry4 *ne, struct xdr_stream *xdr,
+			  struct dentry *dentry, struct nfs4_delegation *dp,
+			  struct nfsd_file *nf, char *name, u32 namelen)
+{
+	uint32_t *attrmask;
+
+	/* Reserve space for attrmask */
+	attrmask = xdr_reserve_space(xdr, 3 * sizeof(uint32_t));
+	if (!attrmask)
+		return false;
+
+	ne->ne_file.data = name;
+	ne->ne_file.len = namelen;
+	ne->ne_attrs.attrmask.element = attrmask;
+
+	attrmask[0] = 0;
+	attrmask[1] = 0;
+	attrmask[2] = 0;
+	ne->ne_attrs.attr_vals.data = NULL;
+	ne->ne_attrs.attr_vals.len = 0;
+	ne->ne_attrs.attrmask.count = 1;
+	return true;
+}
+
+/**
+ * nfsd4_encode_notify_event - encode a notify
+ * @xdr: stream to which to encode the fattr4
+ * @nne: nfsd_notify_event to encode
+ * @dp: delegation where the event occurred
+ * @notify_mask: pointer to word where notification mask should be set
+ *
+ * Encode @nne into @xdr. Returns a pointer to the start of the event, or NULL if
+ * the event couldn't be encoded. The appropriate bit in the notify_mask will also
+ * be set on success.
+ */
+u8 *nfsd4_encode_notify_event(struct xdr_stream *xdr, struct nfsd_notify_event *nne,
+			      struct nfs4_delegation *dp, struct nfsd_file *nf,
+			      u32 *notify_mask)
+{
+	u8 *p = NULL;
+
+	*notify_mask = 0;
+
+	if (nne->ne_mask & FS_DELETE) {
+		struct notify_remove4 nr = { };
+
+		if (!nfsd4_setup_notify_entry4(&nr.nrm_old_entry, xdr, nne->ne_dentry, dp,
+					       nf, nne->ne_name, nne->ne_namelen))
+			goto out_err;
+		p = (u8 *)xdr->p;
+		if (!xdrgen_encode_notify_remove4(xdr, &nr))
+			goto out_err;
+		*notify_mask |= BIT(NOTIFY4_REMOVE_ENTRY);
+	} else if (nne->ne_mask & FS_CREATE) {
+		struct notify_add4 na = { };
+
+		if (!nfsd4_setup_notify_entry4(&na.nad_new_entry, xdr, nne->ne_dentry, dp,
+					       nf, nne->ne_name, nne->ne_namelen))
+			goto out_err;
+
+		p = (u8 *)xdr->p;
+		if (!xdrgen_encode_notify_add4(xdr, &na))
+			goto out_err;
+
+		*notify_mask |= BIT(NOTIFY4_ADD_ENTRY);
+	} else if (nne->ne_mask & FS_RENAME) {
+		struct notify_rename4 nr = { };
+		struct name_snapshot n;
+		bool ret;
+
+		/* Don't send any attributes in the old_entry since they're the same in new */
+		if (!nfsd4_setup_notify_entry4(&nr.nrn_old_entry.nrm_old_entry, xdr,
+					       NULL, dp, nf, nne->ne_name,
+					       nne->ne_namelen))
+			goto out_err;
+
+		take_dentry_name_snapshot(&n, nne->ne_dentry);
+		ret = nfsd4_setup_notify_entry4(&nr.nrn_new_entry.nad_new_entry, xdr,
+					       nne->ne_dentry, dp, nf, (char *)n.name.name,
+					       n.name.len);
+		if (ret) {
+			p = (u8 *)xdr->p;
+			ret = xdrgen_encode_notify_rename4(xdr, &nr);
+		}
+		release_dentry_name_snapshot(&n);
+		if (!ret)
+			goto out_err;
+		*notify_mask |= BIT(NOTIFY4_RENAME_ENTRY);
+	}
+	return p;
+out_err:
+	pr_warn("nfsd: unable to marshal notify_rename4 to xdr stream\n");
+	return NULL;
+}
+
 static void svcxdr_init_encode_from_buffer(struct xdr_stream *xdr,
 				struct xdr_buf *buf, __be32 *p, int bytes)
 {
diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h
index 500e07e47909..dbeacbb7a5c8 100644
--- a/fs/nfsd/state.h
+++ b/fs/nfsd/state.h
@@ -897,6 +897,8 @@ bool nfsd4_has_active_async_copies(struct nfs4_client *clp);
 extern struct nfs4_client_reclaim *nfs4_client_to_reclaim(struct xdr_netobj name,
 				struct xdr_netobj princhash, struct nfsd_net *nn);
 extern bool nfs4_has_reclaimed_state(struct xdr_netobj name, struct nfsd_net *nn);
+int nfsd_handle_dir_event(u32 mask, const struct inode *dir, const void *data,
+			  int data_type, const struct qstr *name);
 
 void put_nfs4_file(struct nfs4_file *fi);
 extern void nfs4_put_cpntf_state(struct nfsd_net *nn,
diff --git a/fs/nfsd/xdr4.h b/fs/nfsd/xdr4.h
index 417e9ad9fbb3..d276840aca50 100644
--- a/fs/nfsd/xdr4.h
+++ b/fs/nfsd/xdr4.h
@@ -955,6 +955,9 @@ __be32 nfsd4_encode_fattr_to_buf(__be32 **p, int words,
 		struct svc_fh *fhp, struct svc_export *exp,
 		struct dentry *dentry,
 		u32 *bmval, struct svc_rqst *, int ignore_crossmnt);
+u8 *nfsd4_encode_notify_event(struct xdr_stream *xdr, struct nfsd_notify_event *nne,
+			      struct nfs4_delegation *dd, struct nfsd_file *nf,
+			      u32 *notify_mask);
 extern __be32 nfsd4_setclientid(struct svc_rqst *rqstp,
 		struct nfsd4_compound_state *, union nfsd4_op_u *u);
 extern __be32 nfsd4_setclientid_confirm(struct svc_rqst *rqstp,

-- 
2.53.0

[PATCH 14/24] nfsd: add tracepoint to dir_event handler

[Jeff Layton]

Add some extra visibility around the fsnotify handlers.

Signed-off-by: Jeff Layton <jlayton@kernel.org>
---
 fs/nfsd/nfs4state.c |  2 ++
 fs/nfsd/trace.h     | 20 ++++++++++++++++++++
 2 files changed, 22 insertions(+)

diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 339c3d0bb575..f3bf572b0ada 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -9963,6 +9963,8 @@ nfsd_handle_dir_event(u32 mask, const struct inode *dir, const void *data,
 	struct file_lock_core *flc;
 	struct nfsd_notify_event *evt;
 
+	trace_nfsd_file_fsnotify_handle_dir_event(mask, dir, name);
+
 	/* Don't do anything if this is not an expected event */
 	if (!(mask & (FS_CREATE|FS_DELETE|FS_RENAME)))
 		return 0;
diff --git a/fs/nfsd/trace.h b/fs/nfsd/trace.h
index 60cacf64181c..3302cb926254 100644
--- a/fs/nfsd/trace.h
+++ b/fs/nfsd/trace.h
@@ -1377,6 +1377,26 @@ TRACE_EVENT(nfsd_file_fsnotify_handle_event,
 			__entry->nlink, __entry->mode, __entry->mask)
 );
 
+TRACE_EVENT(nfsd_file_fsnotify_handle_dir_event,
+	TP_PROTO(u32 mask, const struct inode *dir, const struct qstr *name),
+	TP_ARGS(mask, dir, name),
+	TP_STRUCT__entry(
+		__field(u32, mask)
+		__field(dev_t, s_dev)
+		__field(ino_t, i_ino)
+		__string_len(name, name->name, name->len)
+	),
+	TP_fast_assign(
+		__entry->mask = mask;
+		__entry->s_dev = dir->i_sb->s_dev;
+		__entry->i_ino = dir->i_ino;
+		__assign_str(name);
+	),
+	TP_printk("inode=0x%x:0x%x:0x%lx mask=0x%x name=%s",
+			MAJOR(__entry->s_dev), MINOR(__entry->s_dev),
+			__entry->i_ino, __entry->mask, __get_str(name))
+);
+
 DECLARE_EVENT_CLASS(nfsd_file_gc_class,
 	TP_PROTO(
 		const struct nfsd_file *nf

-- 
2.53.0

[PATCH 15/24] nfsd: apply the notify mask to the delegation when requested

[Jeff Layton]

If the client requests a directory delegation with notifications
enabled, set the appropriate return mask in gddr_notification[0]. This
will ensure the lease acquisition sets the appropriate ignore mask.

If the client doesn't set NOTIFY4_GFLAG_EXTEND, then don't offer any
notifications, as nfsd won't provide directory offset information, and
"classic" notifications require them.

Signed-off-by: Jeff Layton <jlayton@kernel.org>
---
 fs/nfsd/nfs4proc.c | 12 ++++++++++++
 1 file changed, 12 insertions(+)

diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c
index 2797da8cc950..01e3bf9e1839 100644
--- a/fs/nfsd/nfs4proc.c
+++ b/fs/nfsd/nfs4proc.c
@@ -2506,12 +2506,18 @@ nfsd4_verify(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	return status == nfserr_same ? nfs_ok : status;
 }
 
+#define SUPPORTED_NOTIFY_MASK	(BIT(NOTIFY4_REMOVE_ENTRY) |	\
+				 BIT(NOTIFY4_ADD_ENTRY) |	\
+				 BIT(NOTIFY4_RENAME_ENTRY) |	\
+				 BIT(NOTIFY4_GFLAG_EXTEND))
+
 static __be32
 nfsd4_get_dir_delegation(struct svc_rqst *rqstp,
 			 struct nfsd4_compound_state *cstate,
 			 union nfsd4_op_u *u)
 {
 	struct nfsd4_get_dir_delegation *gdd = &u->get_dir_delegation;
+	u32 requested = gdd->gdda_notification_types[0];
 	struct nfs4_delegation *dd;
 	struct nfsd_file *nf;
 	__be32 status;
@@ -2520,6 +2526,12 @@ nfsd4_get_dir_delegation(struct svc_rqst *rqstp,
 	if (status != nfs_ok)
 		return status;
 
+	/* No notifications if you don't set NOTIFY4_GFLAG_EXTEND! */
+	if (!(requested & BIT(NOTIFY4_GFLAG_EXTEND)))
+		requested = 0;
+
+	gdd->gddr_notification[0] = requested & SUPPORTED_NOTIFY_MASK;
+
 	/*
 	 * RFC 8881, section 18.39.3 says:
 	 *

-- 
2.53.0

[PATCH 16/24] nfsd: add helper to marshal a fattr4 from completed args

[Jeff Layton]

Break the loop that encodes the actual attr_vals field into a separate
function.

Signed-off-by: Jeff Layton <jlayton@kernel.org>
---
 fs/nfsd/nfs4xdr.c | 46 ++++++++++++++++++++++++++--------------------
 1 file changed, 26 insertions(+), 20 deletions(-)

diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c
index 9ad13f96c219..2ba3fcadb742 100644
--- a/fs/nfsd/nfs4xdr.c
+++ b/fs/nfsd/nfs4xdr.c
@@ -3852,6 +3852,22 @@ static const nfsd4_enc_attr nfsd4_enc_fattr4_encode_ops[] = {
 #endif
 };
 
+static __be32
+nfsd4_encode_attr_vals(struct xdr_stream *xdr, u32 *attrmask, struct nfsd4_fattr_args *args)
+{
+	DECLARE_BITMAP(attr_bitmap, ARRAY_SIZE(nfsd4_enc_fattr4_encode_ops));
+	unsigned long bit;
+	__be32 status;
+
+	bitmap_from_arr32(attr_bitmap, attrmask, ARRAY_SIZE(nfsd4_enc_fattr4_encode_ops));
+	for_each_set_bit(bit, attr_bitmap, ARRAY_SIZE(nfsd4_enc_fattr4_encode_ops)) {
+		status = nfsd4_enc_fattr4_encode_ops[bit](xdr, args);
+		if (status != nfs_ok)
+			return status;
+	}
+	return nfs_ok;
+}
+
 /*
  * Note: @fhp can be NULL; in this case, we might have to compose the filehandle
  * ourselves.
@@ -3862,7 +3878,6 @@ nfsd4_encode_fattr4(struct svc_rqst *rqstp, struct xdr_stream *xdr,
 		    struct dentry *dentry, const u32 *bmval,
 		    int ignore_crossmnt)
 {
-	DECLARE_BITMAP(attr_bitmap, ARRAY_SIZE(nfsd4_enc_fattr4_encode_ops));
 	struct nfs4_delegation *dp = NULL;
 	struct nfsd4_fattr_args args;
 	struct svc_fh *tempfh = NULL;
@@ -3877,7 +3892,6 @@ nfsd4_encode_fattr4(struct svc_rqst *rqstp, struct xdr_stream *xdr,
 		.mnt	= exp->ex_path.mnt,
 		.dentry	= dentry,
 	};
-	unsigned long bit;
 
 	WARN_ON_ONCE(bmval[1] & NFSD_WRITEONLY_ATTRS_WORD1);
 	WARN_ON_ONCE(!nfsd_attrs_supported(minorversion, bmval));
@@ -4050,27 +4064,22 @@ nfsd4_encode_fattr4(struct svc_rqst *rqstp, struct xdr_stream *xdr,
 #endif /* CONFIG_NFSD_V4_POSIX_ACLS */
 
 	/* attrmask */
-	status = nfsd4_encode_bitmap4(xdr, attrmask[0], attrmask[1],
-				      attrmask[2]);
+	status = nfsd4_encode_bitmap4(xdr, attrmask[0], attrmask[1], attrmask[2]);
 	if (status)
-		goto out;
+		return status;
 
 	/* attr_vals */
 	attrlen_offset = xdr->buf->len;
-	if (unlikely(!xdr_reserve_space(xdr, XDR_UNIT)))
-		goto out_resource;
-	bitmap_from_arr32(attr_bitmap, attrmask,
-			  ARRAY_SIZE(nfsd4_enc_fattr4_encode_ops));
-	for_each_set_bit(bit, attr_bitmap,
-			 ARRAY_SIZE(nfsd4_enc_fattr4_encode_ops)) {
-		status = nfsd4_enc_fattr4_encode_ops[bit](xdr, &args);
-		if (status != nfs_ok)
-			goto out;
+	if (unlikely(!xdr_reserve_space(xdr, XDR_UNIT))) {
+		status = nfserr_resource;
+		goto out;
 	}
-	attrlen = cpu_to_be32(xdr->buf->len - attrlen_offset - XDR_UNIT);
-	write_bytes_to_xdr_buf(xdr->buf, attrlen_offset, &attrlen, XDR_UNIT);
-	status = nfs_ok;
 
+	status = nfsd4_encode_attr_vals(xdr, attrmask, &args);
+	if (status == nfs_ok) {
+		attrlen = cpu_to_be32(xdr->buf->len - attrlen_offset - XDR_UNIT);
+		write_bytes_to_xdr_buf(xdr->buf, attrlen_offset, &attrlen, XDR_UNIT);
+	}
 out:
 #ifdef CONFIG_NFSD_V4_POSIX_ACLS
 	if (args.dpacl)
@@ -4093,9 +4102,6 @@ nfsd4_encode_fattr4(struct svc_rqst *rqstp, struct xdr_stream *xdr,
 out_nfserr:
 	status = nfserrno(err);
 	goto out;
-out_resource:
-	status = nfserr_resource;
-	goto out;
 }
 
 static bool

-- 
2.53.0

[PATCH 17/24] nfsd: allow nfsd4_encode_fattr4_change() to work with no export

[Jeff Layton]

In the context of a CB_NOTIFY callback, we may not have easy access to
a svc_export. nfsd will not currently grant a delegation on a the V4 root
however, so this should be safe.

Signed-off-by: Jeff Layton <jlayton@kernel.org>
---
 fs/nfsd/nfs4xdr.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c
index 2ba3fcadb742..49ca24851707 100644
--- a/fs/nfsd/nfs4xdr.c
+++ b/fs/nfsd/nfs4xdr.c
@@ -3257,7 +3257,7 @@ static __be32 nfsd4_encode_fattr4_change(struct xdr_stream *xdr,
 {
 	const struct svc_export *exp = args->exp;
 
-	if (unlikely(exp->ex_flags & NFSEXP_V4ROOT)) {
+	if (exp && unlikely(exp->ex_flags & NFSEXP_V4ROOT)) {
 		u32 flush_time = convert_to_wallclock(exp->cd->flush_time);
 
 		if (xdr_stream_encode_u32(xdr, flush_time) != XDR_UNIT)

-- 
2.53.0

[PATCH 18/24] nfsd: send basic file attributes in CB_NOTIFY

[Jeff Layton]

In addition to the filename, send attributes about the inode in a
CB_NOTIFY event. This patch just adds a the basic inode information that
can be acquired via GETATTR.

Signed-off-by: Jeff Layton <jlayton@kernel.org>
---
 fs/nfsd/nfs4xdr.c | 44 ++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 44 insertions(+)

diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c
index 49ca24851707..0cdce460f9c8 100644
--- a/fs/nfsd/nfs4xdr.c
+++ b/fs/nfsd/nfs4xdr.c
@@ -4104,12 +4104,21 @@ nfsd4_encode_fattr4(struct svc_rqst *rqstp, struct xdr_stream *xdr,
 	goto out;
 }
 
+#define CB_NOTIFY_STATX_REQUEST_MASK (STATX_BASIC_STATS   | \
+				      STATX_BTIME	  | \
+				      STATX_CHANGE_COOKIE)
+
 static bool
 nfsd4_setup_notify_entry4(struct notify_entry4 *ne, struct xdr_stream *xdr,
 			  struct dentry *dentry, struct nfs4_delegation *dp,
 			  struct nfsd_file *nf, char *name, u32 namelen)
 {
+	struct path path =  { .mnt = nf->nf_file->f_path.mnt,
+			      .dentry = dentry };
+	struct nfsd4_fattr_args args = { };
 	uint32_t *attrmask;
+	__be32 status;
+	int ret;
 
 	/* Reserve space for attrmask */
 	attrmask = xdr_reserve_space(xdr, 3 * sizeof(uint32_t));
@@ -4120,6 +4129,41 @@ nfsd4_setup_notify_entry4(struct notify_entry4 *ne, struct xdr_stream *xdr,
 	ne->ne_file.len = namelen;
 	ne->ne_attrs.attrmask.element = attrmask;
 
+	/* FIXME: d_find_alias for inode ? */
+	if (!path.dentry || !d_inode(path.dentry))
+		goto noattrs;
+
+	/*
+	 * It is possible that the client was granted a delegation when a file
+	 * was created. Note that we don't issue a CB_GETATTR here since stale
+	 * attributes are presumably ok.
+	 */
+	ret = vfs_getattr(&path, &args.stat, CB_NOTIFY_STATX_REQUEST_MASK, AT_STATX_SYNC_AS_STAT);
+	if (ret)
+		goto noattrs;
+
+	args.change_attr = nfsd4_change_attribute(&args.stat);
+
+	attrmask[0] = FATTR4_WORD0_TYPE | FATTR4_WORD0_CHANGE |
+		      FATTR4_WORD0_SIZE | FATTR4_WORD0_FILEID;
+	attrmask[1] = FATTR4_WORD1_MODE | FATTR4_WORD1_NUMLINKS | FATTR4_WORD1_RAWDEV |
+		      FATTR4_WORD1_SPACE_USED | FATTR4_WORD1_TIME_ACCESS |
+		      FATTR4_WORD1_TIME_METADATA | FATTR4_WORD1_TIME_MODIFY;
+	attrmask[2] = 0;
+
+	if (args.stat.result_mask & STATX_BTIME)
+		attrmask[1] |= FATTR4_WORD1_TIME_CREATE;
+
+	ne->ne_attrs.attrmask.count = 2;
+	ne->ne_attrs.attr_vals.data = (u8 *)xdr->p;
+
+	status = nfsd4_encode_attr_vals(xdr, attrmask, &args);
+	if (status != nfs_ok)
+		goto noattrs;
+
+	ne->ne_attrs.attr_vals.len = (u8 *)xdr->p - ne->ne_attrs.attr_vals.data;
+	return true;
+noattrs:
 	attrmask[0] = 0;
 	attrmask[1] = 0;
 	attrmask[2] = 0;

-- 
2.53.0

[PATCH 19/24] nfsd: allow encoding a filehandle into fattr4 without a svc_fh

[Jeff Layton]

The current fattr4 encoder requires a svc_fh in order to encode the
filehandle. This is not available in a CB_NOTIFY callback. Add a a new
"fhandle" field to struct nfsd4_fattr_args and copy the filehandle into
there from the svc_fh. CB_NOTIFY will populate it via other means.

Signed-off-by: Jeff Layton <jlayton@kernel.org>
---
 fs/nfsd/nfs4xdr.c | 35 ++++++++++++++++++++---------------
 1 file changed, 20 insertions(+), 15 deletions(-)

diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c
index 0cdce460f9c8..faf0c3d35dee 100644
--- a/fs/nfsd/nfs4xdr.c
+++ b/fs/nfsd/nfs4xdr.c
@@ -2701,7 +2701,7 @@ nfsd4_decode_compound(struct nfsd4_compoundargs *argp)
 }
 
 static __be32 nfsd4_encode_nfs_fh4(struct xdr_stream *xdr,
-				   struct knfsd_fh *fh_handle)
+				   const struct knfsd_fh *fh_handle)
 {
 	return nfsd4_encode_opaque(xdr, fh_handle->fh_raw, fh_handle->fh_size);
 }
@@ -3144,6 +3144,7 @@ struct nfsd4_fattr_args {
 	struct svc_fh		*fhp;
 	struct svc_export	*exp;
 	struct dentry		*dentry;
+	struct knfsd_fh		fhandle;
 	struct kstat		stat;
 	struct kstatfs		statfs;
 	struct nfs4_acl		*acl;
@@ -3359,7 +3360,7 @@ static __be32 nfsd4_encode_fattr4_acl(struct xdr_stream *xdr,
 static __be32 nfsd4_encode_fattr4_filehandle(struct xdr_stream *xdr,
 					     const struct nfsd4_fattr_args *args)
 {
-	return nfsd4_encode_nfs_fh4(xdr, &args->fhp->fh_handle);
+	return nfsd4_encode_nfs_fh4(xdr, &args->fhandle);
 }
 
 static __be32 nfsd4_encode_fattr4_fileid(struct xdr_stream *xdr,
@@ -3969,19 +3970,23 @@ nfsd4_encode_fattr4(struct svc_rqst *rqstp, struct xdr_stream *xdr,
 		if (err)
 			goto out_nfserr;
 	}
-	if ((attrmask[0] & (FATTR4_WORD0_FILEHANDLE | FATTR4_WORD0_FSID)) &&
-	    !fhp) {
-		tempfh = kmalloc_obj(struct svc_fh);
-		status = nfserr_jukebox;
-		if (!tempfh)
-			goto out;
-		fh_init(tempfh, NFS4_FHSIZE);
-		status = fh_compose(tempfh, exp, dentry, NULL);
-		if (status)
-			goto out;
-		args.fhp = tempfh;
-	} else
-		args.fhp = fhp;
+
+	args.fhp = fhp;
+	if ((attrmask[0] & (FATTR4_WORD0_FILEHANDLE | FATTR4_WORD0_FSID))) {
+		if (!args.fhp) {
+			tempfh = kmalloc_obj(struct svc_fh);
+			status = nfserr_jukebox;
+			if (!tempfh)
+				goto out;
+			fh_init(tempfh, NFS4_FHSIZE);
+			status = fh_compose(tempfh, exp, dentry, NULL);
+			if (status)
+				goto out;
+			args.fhp = tempfh;
+		}
+		if (args.fhp)
+			fh_copy_shallow(&args.fhandle, &args.fhp->fh_handle);
+	}
 
 	if (attrmask[0] & FATTR4_WORD0_ACL) {
 		err = nfsd4_get_nfs4_acl(rqstp, dentry, &args.acl);

-- 
2.53.0

[PATCH 20/24] nfsd: add a fi_connectable flag to struct nfs4_file

[Jeff Layton]

When encoding a filehandle for a CB_NOTIFY, there is no svc_export
available, but the server needs to know whether to encode a connectable
filehandle. Add a flag to the nfs4_file that tells whether the
svc_export under which a directory delegation was acquired requires
connectable filehandles.

Signed-off-by: Jeff Layton <jlayton@kernel.org>
---
 fs/nfsd/nfs4state.c | 1 +
 fs/nfsd/state.h     | 1 +
 2 files changed, 2 insertions(+)

diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index f3bf572b0ada..0580c935d804 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -5153,6 +5153,7 @@ static void nfsd4_file_init(const struct svc_fh *fh, struct nfs4_file *fp)
 	memset(fp->fi_access, 0, sizeof(fp->fi_access));
 	fp->fi_aliased = false;
 	fp->fi_inode = d_inode(fh->fh_dentry);
+	fp->fi_connectable = fh->fh_export->ex_flags & EXPORT_FH_CONNECTABLE;
 #ifdef CONFIG_NFSD_PNFS
 	INIT_LIST_HEAD(&fp->fi_lo_states);
 	atomic_set(&fp->fi_lo_recalls, 0);
diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h
index dbeacbb7a5c8..d060d70c5820 100644
--- a/fs/nfsd/state.h
+++ b/fs/nfsd/state.h
@@ -745,6 +745,7 @@ struct nfs4_file {
 	int			fi_delegees;
 	struct knfsd_fh		fi_fhandle;
 	bool			fi_had_conflict;
+	bool			fi_connectable;
 #ifdef CONFIG_NFSD_PNFS
 	struct list_head	fi_lo_states;
 	atomic_t		fi_lo_recalls;

-- 
2.53.0

[PATCH 21/24] nfsd: add the filehandle to returned attributes in CB_NOTIFY

[Jeff Layton]

nfsd's usual fh_compose routine requires a svc_export and fills out a
svc_fh. In the context of a CB_NOTIFY there is no such export to
consult.

Add a new routine that composes a filehandle with only a parent
filehandle and nfs4_file. Use that to fill out the fhandle field in the
nfsd4_fattr_args.

Signed-off-by: Jeff Layton <jlayton@kernel.org>
---
 fs/nfsd/nfs4xdr.c | 37 +++++++++++++++++++++++++++++++++++++
 1 file changed, 37 insertions(+)

diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c
index faf0c3d35dee..e468cbc087ad 100644
--- a/fs/nfsd/nfs4xdr.c
+++ b/fs/nfsd/nfs4xdr.c
@@ -4109,6 +4109,39 @@ nfsd4_encode_fattr4(struct svc_rqst *rqstp, struct xdr_stream *xdr,
 	goto out;
 }
 
+static bool
+setup_notify_fhandle(struct dentry *dentry, struct nfs4_file *fi,
+		     struct nfsd_file *nf, struct nfsd4_fattr_args *args)
+{
+	int fileid_type, fsid_len, maxsize, flags = 0;
+	struct knfsd_fh *fhp = &args->fhandle;
+	struct inode *inode = d_inode(dentry);
+	struct inode *parent = NULL;
+	struct fid *fid;
+
+	fsid_len = key_len(fi->fi_fhandle.fh_fsid_type);
+	fhp->fh_size = 4 + fsid_len;
+
+	/* Copy first 4 bytes + fsid */
+	memcpy(&fhp->fh_raw, &fi->fi_fhandle.fh_raw, fhp->fh_size);
+
+	fid = (struct fid *)(fh_fsid(fhp) + fsid_len/4);
+	maxsize = (NFS4_FHSIZE - fhp->fh_size)/4;
+
+	if (fi->fi_connectable && !S_ISDIR(inode->i_mode)) {
+		parent = d_inode(nf->nf_file->f_path.dentry);
+		flags = EXPORT_FH_CONNECTABLE;
+	}
+
+	fileid_type = exportfs_encode_inode_fh(inode, fid, &maxsize, parent, flags);
+	if (fileid_type < 0)
+		return false;
+
+	fhp->fh_fileid_type = fileid_type;
+	fhp->fh_size += maxsize * 4;
+	return true;
+}
+
 #define CB_NOTIFY_STATX_REQUEST_MASK (STATX_BASIC_STATS   | \
 				      STATX_BTIME	  | \
 				      STATX_CHANGE_COOKIE)
@@ -4118,6 +4151,7 @@ nfsd4_setup_notify_entry4(struct notify_entry4 *ne, struct xdr_stream *xdr,
 			  struct dentry *dentry, struct nfs4_delegation *dp,
 			  struct nfsd_file *nf, char *name, u32 namelen)
 {
+	struct nfs4_file *fi = dp->dl_stid.sc_file;
 	struct path path =  { .mnt = nf->nf_file->f_path.mnt,
 			      .dentry = dentry };
 	struct nfsd4_fattr_args args = { };
@@ -4156,6 +4190,9 @@ nfsd4_setup_notify_entry4(struct notify_entry4 *ne, struct xdr_stream *xdr,
 		      FATTR4_WORD1_TIME_METADATA | FATTR4_WORD1_TIME_MODIFY;
 	attrmask[2] = 0;
 
+	if (setup_notify_fhandle(dentry, fi, nf, &args))
+		attrmask[0] |= FATTR4_WORD0_FILEHANDLE;
+
 	if (args.stat.result_mask & STATX_BTIME)
 		attrmask[1] |= FATTR4_WORD1_TIME_CREATE;
 

-- 
2.53.0

[PATCH 22/24] nfsd: properly track requested child attributes

[Jeff Layton]

Track the union of requested and supported child attributes in the
delegation, and only encode the attributes in that union when sending
add/remove/rename updates.

Signed-off-by: Jeff Layton <jlayton@kernel.org>
---
 fs/nfsd/nfs4proc.c  |  2 ++
 fs/nfsd/nfs4state.c | 18 ++++++++++++++++++
 fs/nfsd/nfs4xdr.c   | 15 ++++++---------
 fs/nfsd/state.h     |  3 +++
 4 files changed, 29 insertions(+), 9 deletions(-)

diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c
index 01e3bf9e1839..a807a55dddf9 100644
--- a/fs/nfsd/nfs4proc.c
+++ b/fs/nfsd/nfs4proc.c
@@ -2553,6 +2553,8 @@ nfsd4_get_dir_delegation(struct svc_rqst *rqstp,
 
 	gdd->gddrnf_status = GDD4_OK;
 	memcpy(&gdd->gddr_stateid, &dd->dl_stid.sc_stateid, sizeof(gdd->gddr_stateid));
+	gdd->gddr_child_attributes[0] = dd->dl_child_attrs[0];
+	gdd->gddr_child_attributes[1] = dd->dl_child_attrs[1];
 	nfs4_put_stid(&dd->dl_stid);
 	return nfs_ok;
 }
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 0580c935d804..59a9b1ca836b 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -9780,6 +9780,21 @@ nfsd4_deleg_getattr_conflict(struct svc_rqst *rqstp, struct dentry *dentry,
 	return status;
 }
 
+#define GDD_WORD0_CHILD_ATTRS	(FATTR4_WORD0_TYPE |		\
+				 FATTR4_WORD0_CHANGE |		\
+				 FATTR4_WORD0_SIZE |		\
+				 FATTR4_WORD0_FILEID |		\
+				 FATTR4_WORD0_FILEHANDLE)
+
+#define GDD_WORD1_CHILD_ATTRS	(FATTR4_WORD1_MODE |		\
+				 FATTR4_WORD1_NUMLINKS |	\
+				 FATTR4_WORD1_RAWDEV |		\
+				 FATTR4_WORD1_SPACE_USED |	\
+				 FATTR4_WORD1_TIME_ACCESS |	\
+				 FATTR4_WORD1_TIME_METADATA |	\
+				 FATTR4_WORD1_TIME_MODIFY |	\
+				 FATTR4_WORD1_TIME_CREATE)
+
 /**
  * nfsd_get_dir_deleg - attempt to get a directory delegation
  * @cstate: compound state
@@ -9849,6 +9864,9 @@ nfsd_get_dir_deleg(struct nfsd4_compound_state *cstate,
 		dp->dl_stid.sc_export =
 			exp_get(cstate->current_fh.fh_export);
 
+	dp->dl_child_attrs[0] = gdd->gdda_child_attributes[0] & GDD_WORD0_CHILD_ATTRS;
+	dp->dl_child_attrs[1] = gdd->gdda_child_attributes[1] & GDD_WORD1_CHILD_ATTRS;
+
 	fl = nfs4_alloc_init_lease(dp, gdd->gddr_notification[0]);
 	if (!fl)
 		goto out_put_stid;
diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c
index e468cbc087ad..35646809becb 100644
--- a/fs/nfsd/nfs4xdr.c
+++ b/fs/nfsd/nfs4xdr.c
@@ -4183,18 +4183,15 @@ nfsd4_setup_notify_entry4(struct notify_entry4 *ne, struct xdr_stream *xdr,
 
 	args.change_attr = nfsd4_change_attribute(&args.stat);
 
-	attrmask[0] = FATTR4_WORD0_TYPE | FATTR4_WORD0_CHANGE |
-		      FATTR4_WORD0_SIZE | FATTR4_WORD0_FILEID;
-	attrmask[1] = FATTR4_WORD1_MODE | FATTR4_WORD1_NUMLINKS | FATTR4_WORD1_RAWDEV |
-		      FATTR4_WORD1_SPACE_USED | FATTR4_WORD1_TIME_ACCESS |
-		      FATTR4_WORD1_TIME_METADATA | FATTR4_WORD1_TIME_MODIFY;
+	attrmask[0] = dp->dl_child_attrs[0];
+	attrmask[1] = dp->dl_child_attrs[1];
 	attrmask[2] = 0;
 
-	if (setup_notify_fhandle(dentry, fi, nf, &args))
-		attrmask[0] |= FATTR4_WORD0_FILEHANDLE;
+	if (!setup_notify_fhandle(dentry, fi, nf, &args))
+		attrmask[0] &= ~FATTR4_WORD0_FILEHANDLE;
 
-	if (args.stat.result_mask & STATX_BTIME)
-		attrmask[1] |= FATTR4_WORD1_TIME_CREATE;
+	if (!(args.stat.result_mask & STATX_BTIME))
+		attrmask[1] &= ~FATTR4_WORD1_TIME_CREATE;
 
 	ne->ne_attrs.attrmask.count = 2;
 	ne->ne_attrs.attr_vals.data = (u8 *)xdr->p;
diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h
index d060d70c5820..7ca5ef9caafe 100644
--- a/fs/nfsd/state.h
+++ b/fs/nfsd/state.h
@@ -282,6 +282,9 @@ struct nfs4_delegation {
 	struct timespec64	dl_atime;
 	struct timespec64	dl_mtime;
 	struct timespec64	dl_ctime;
+
+	/* For dir delegations */
+	uint32_t		dl_child_attrs[2];
 };
 
 static inline bool deleg_is_read(u32 dl_type)

-- 
2.53.0

[PATCH 23/24] nfsd: track requested dir attributes

[Jeff Layton]

Track the union of requested and supported dir attributes in the
delegation, and only encode the attributes in that union when sending
add/remove/rename updates.

Signed-off-by: Jeff Layton <jlayton@kernel.org>
---
 fs/nfsd/nfs4proc.c  |  7 ++++---
 fs/nfsd/nfs4state.c | 14 +++++++++++++-
 fs/nfsd/state.h     |  2 ++
 3 files changed, 19 insertions(+), 4 deletions(-)

diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c
index a807a55dddf9..82d7c473e4d3 100644
--- a/fs/nfsd/nfs4proc.c
+++ b/fs/nfsd/nfs4proc.c
@@ -2506,9 +2506,10 @@ nfsd4_verify(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	return status == nfserr_same ? nfs_ok : status;
 }
 
-#define SUPPORTED_NOTIFY_MASK	(BIT(NOTIFY4_REMOVE_ENTRY) |	\
-				 BIT(NOTIFY4_ADD_ENTRY) |	\
-				 BIT(NOTIFY4_RENAME_ENTRY) |	\
+#define SUPPORTED_NOTIFY_MASK	(BIT(NOTIFY4_CHANGE_DIR_ATTRS) |	\
+				 BIT(NOTIFY4_REMOVE_ENTRY) |		\
+				 BIT(NOTIFY4_ADD_ENTRY) |		\
+				 BIT(NOTIFY4_RENAME_ENTRY) |		\
 				 BIT(NOTIFY4_GFLAG_EXTEND))
 
 static __be32
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index 59a9b1ca836b..c4b6f4d65a47 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -9795,6 +9795,15 @@ nfsd4_deleg_getattr_conflict(struct svc_rqst *rqstp, struct dentry *dentry,
 				 FATTR4_WORD1_TIME_MODIFY |	\
 				 FATTR4_WORD1_TIME_CREATE)
 
+#define GDD_WORD0_DIR_ATTRS	(FATTR4_WORD0_CHANGE |		\
+				 FATTR4_WORD0_SIZE)
+
+#define GDD_WORD1_DIR_ATTRS	(FATTR4_WORD1_NUMLINKS |	\
+				 FATTR4_WORD1_SPACE_USED |	\
+				 FATTR4_WORD1_TIME_ACCESS |	\
+				 FATTR4_WORD1_TIME_METADATA |	\
+				 FATTR4_WORD1_TIME_MODIFY)
+
 /**
  * nfsd_get_dir_deleg - attempt to get a directory delegation
  * @cstate: compound state
@@ -9864,10 +9873,13 @@ nfsd_get_dir_deleg(struct nfsd4_compound_state *cstate,
 		dp->dl_stid.sc_export =
 			exp_get(cstate->current_fh.fh_export);
 
+	dp->dl_notify_mask = gdd->gddr_notification[0];
 	dp->dl_child_attrs[0] = gdd->gdda_child_attributes[0] & GDD_WORD0_CHILD_ATTRS;
 	dp->dl_child_attrs[1] = gdd->gdda_child_attributes[1] & GDD_WORD1_CHILD_ATTRS;
+	dp->dl_dir_attrs[0] = gdd->gdda_dir_attributes[0] & GDD_WORD0_DIR_ATTRS;
+	dp->dl_dir_attrs[1] = gdd->gdda_dir_attributes[1] & GDD_WORD1_DIR_ATTRS;
 
-	fl = nfs4_alloc_init_lease(dp, gdd->gddr_notification[0]);
+	fl = nfs4_alloc_init_lease(dp, dp->dl_notify_mask);
 	if (!fl)
 		goto out_put_stid;
 
diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h
index 7ca5ef9caafe..56a3cfb12e65 100644
--- a/fs/nfsd/state.h
+++ b/fs/nfsd/state.h
@@ -284,7 +284,9 @@ struct nfs4_delegation {
 	struct timespec64	dl_ctime;
 
 	/* For dir delegations */
+	uint32_t		dl_notify_mask;
 	uint32_t		dl_child_attrs[2];
+	uint32_t		dl_dir_attrs[2];
 };
 
 static inline bool deleg_is_read(u32 dl_type)

-- 
2.53.0

[PATCH 24/24] nfsd: add support to CB_NOTIFY for dir attribute changes

[Jeff Layton]

If the client requested dir attribute change notifications, send those
alongside any set of add/remove/rename events. Note that the server will
still recall the delegation on a SETATTR, so these are only sent for
changes to child dirents.

Signed-off-by: Jeff Layton <jlayton@kernel.org>
---
 fs/nfsd/nfs4state.c | 25 ++++++++++++++++++++--
 fs/nfsd/nfs4xdr.c   | 61 +++++++++++++++++++++++++++++++++++++++++++++--------
 fs/nfsd/xdr4.h      |  2 ++
 3 files changed, 77 insertions(+), 11 deletions(-)

diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index c4b6f4d65a47..01a2fb11dc0e 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -3470,10 +3470,15 @@ nfsd4_cb_notify_prepare(struct nfsd4_callback *cb)
 	struct nfsd_notify_event *events[NOTIFY4_EVENT_QUEUE_SIZE];
 	struct xdr_buf xdr = { .buflen = PAGE_SIZE * NOTIFY4_PAGE_ARRAY_SIZE,
 			       .pages  = ncn->ncn_pages };
+	int limit = NOTIFY4_EVENT_QUEUE_SIZE;
 	struct xdr_stream stream;
 	struct nfsd_file *nf;
-	int count, i;
 	bool error = false;
+	int count, i;
+
+	/* Save a slot for dir attr update if requested */
+	if (dp->dl_notify_mask & BIT(NOTIFY4_CHANGE_DIR_ATTRS))
+		--limit;
 
 	xdr_init_encode_pages(&stream, &xdr);
 
@@ -3487,7 +3492,7 @@ nfsd4_cb_notify_prepare(struct nfsd4_callback *cb)
 	}
 
 	/* we can't keep up! */
-	if (count > NOTIFY4_EVENT_QUEUE_SIZE) {
+	if (count > limit) {
 		spin_unlock(&ncn->ncn_lock);
 		goto out_recall;
 	}
@@ -3534,6 +3539,22 @@ nfsd4_cb_notify_prepare(struct nfsd4_callback *cb)
 		nfsd_notify_event_put(nne);
 	}
 	if (!error) {
+		if (dp->dl_notify_mask & BIT(NOTIFY4_CHANGE_DIR_ATTRS)) {
+			u32 *maskp = (u32 *)xdr_reserve_space(&stream, sizeof(*maskp));
+
+			if (maskp) {
+				u8 *p = nfsd4_encode_dir_attr_change(&stream, dp, nf);
+
+				if (p) {
+					*maskp = BIT(NOTIFY4_CHANGE_DIR_ATTRS);
+					ncn->ncn_nf[count].notify_mask.count = 1;
+					ncn->ncn_nf[count].notify_mask.element = maskp;
+					ncn->ncn_nf[count].notify_vals.data = p;
+					ncn->ncn_nf[count].notify_vals.len = (u8 *)stream.p - p;
+					++count;
+				}
+			}
+		}
 		ncn->ncn_nf_cnt = count;
 		nfsd_file_put(nf);
 		return true;
diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c
index 35646809becb..6e76502ca149 100644
--- a/fs/nfsd/nfs4xdr.c
+++ b/fs/nfsd/nfs4xdr.c
@@ -4152,11 +4152,11 @@ nfsd4_setup_notify_entry4(struct notify_entry4 *ne, struct xdr_stream *xdr,
 			  struct nfsd_file *nf, char *name, u32 namelen)
 {
 	struct nfs4_file *fi = dp->dl_stid.sc_file;
-	struct path path =  { .mnt = nf->nf_file->f_path.mnt,
-			      .dentry = dentry };
+	struct path path = nf->nf_file->f_path;
 	struct nfsd4_fattr_args args = { };
 	uint32_t *attrmask;
 	__be32 status;
+	bool parent;
 	int ret;
 
 	/* Reserve space for attrmask */
@@ -4168,6 +4168,9 @@ nfsd4_setup_notify_entry4(struct notify_entry4 *ne, struct xdr_stream *xdr,
 	ne->ne_file.len = namelen;
 	ne->ne_attrs.attrmask.element = attrmask;
 
+	parent = (dentry == path.dentry);
+	path.dentry = dentry;
+
 	/* FIXME: d_find_alias for inode ? */
 	if (!path.dentry || !d_inode(path.dentry))
 		goto noattrs;
@@ -4183,15 +4186,20 @@ nfsd4_setup_notify_entry4(struct notify_entry4 *ne, struct xdr_stream *xdr,
 
 	args.change_attr = nfsd4_change_attribute(&args.stat);
 
-	attrmask[0] = dp->dl_child_attrs[0];
-	attrmask[1] = dp->dl_child_attrs[1];
-	attrmask[2] = 0;
+	if (parent) {
+		attrmask[0] = dp->dl_dir_attrs[0];
+		attrmask[1] = dp->dl_dir_attrs[1];
+	} else {
+		attrmask[0] = dp->dl_child_attrs[0];
+		attrmask[1] = dp->dl_child_attrs[1];
 
-	if (!setup_notify_fhandle(dentry, fi, nf, &args))
-		attrmask[0] &= ~FATTR4_WORD0_FILEHANDLE;
+		if (!setup_notify_fhandle(dentry, fi, nf, &args))
+			attrmask[0] &= ~FATTR4_WORD0_FILEHANDLE;
 
-	if (!(args.stat.result_mask & STATX_BTIME))
-		attrmask[1] &= ~FATTR4_WORD1_TIME_CREATE;
+		if (!(args.stat.result_mask & STATX_BTIME))
+			attrmask[1] &= ~FATTR4_WORD1_TIME_CREATE;
+	}
+	attrmask[2] = 0;
 
 	ne->ne_attrs.attrmask.count = 2;
 	ne->ne_attrs.attr_vals.data = (u8 *)xdr->p;
@@ -4283,6 +4291,41 @@ u8 *nfsd4_encode_notify_event(struct xdr_stream *xdr, struct nfsd_notify_event *
 	return NULL;
 }
 
+/**
+ * nfsd4_encode_dir_attr_change
+ * @xdr: stream to which to encode the fattr4
+ * @dp: delegation where the event occurred
+ * @nf: nfsd_file opened on the directory
+ *
+ * Encode a dir attr change event.
+ */
+u8 *nfsd4_encode_dir_attr_change(struct xdr_stream *xdr, struct nfs4_delegation *dp,
+				 struct nfsd_file *nf)
+{
+	struct dentry *dentry = nf->nf_file->f_path.dentry;
+	struct notify_attr4 na = { };
+	struct name_snapshot n;
+	bool ret;
+	u8 *p = NULL;
+
+	if (!(dp->dl_notify_mask & BIT(NOTIFY4_CHANGE_DIR_ATTRS)))
+		return NULL;
+
+	take_dentry_name_snapshot(&n, dentry);
+	ret = nfsd4_setup_notify_entry4(&na.na_changed_entry, xdr,
+					dentry, dp, nf, (char *)n.name.name,
+					n.name.len);
+
+	/* Don't bother with the event if we're not encoding attrs */
+	if (ret && na.na_changed_entry.ne_attrs.attr_vals.len) {
+		p = (u8 *)xdr->p;
+		if (!xdrgen_encode_notify_attr4(xdr, &na))
+			p = NULL;
+	}
+	release_dentry_name_snapshot(&n);
+	return p;
+}
+
 static void svcxdr_init_encode_from_buffer(struct xdr_stream *xdr,
 				struct xdr_buf *buf, __be32 *p, int bytes)
 {
diff --git a/fs/nfsd/xdr4.h b/fs/nfsd/xdr4.h
index d276840aca50..cf7f0df68d63 100644
--- a/fs/nfsd/xdr4.h
+++ b/fs/nfsd/xdr4.h
@@ -958,6 +958,8 @@ __be32 nfsd4_encode_fattr_to_buf(__be32 **p, int words,
 u8 *nfsd4_encode_notify_event(struct xdr_stream *xdr, struct nfsd_notify_event *nne,
 			      struct nfs4_delegation *dd, struct nfsd_file *nf,
 			      u32 *notify_mask);
+u8 *nfsd4_encode_dir_attr_change(struct xdr_stream *xdr, struct nfs4_delegation *dp,
+				 struct nfsd_file *nf);
 extern __be32 nfsd4_setclientid(struct svc_rqst *rqstp,
 		struct nfsd4_compound_state *, union nfsd4_op_u *u);
 extern __be32 nfsd4_setclientid_confirm(struct svc_rqst *rqstp,

-- 
2.53.0