nfsd: add data structures for handling CB_NOTIFY

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>
Link: https://patch.msgid.link/20260616-dir-deleg-v7-9-6cbc7eac0ade@kernel.org
Signed-off-by: Chuck Lever <cel@kernel.org>

fs/nfsd/nfs4state.c

@@ -126,6 +126,7 @@ 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;
 
@@ -1123,29 +1124,31 @@ static void block_delegations(struct knfsd_fh *fh)
 }
 
 static struct nfs4_delegation *
-alloc_init_deleg(struct nfs4_client *clp, struct nfs4_file *fp,
+__alloc_init_deleg(struct nfs4_client *clp, struct nfs4_file *fp,
-		 struct nfs4_clnt_odstate *odstate, u32 dl_type)
+		   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, sc_free);
-	stid = nfs4_alloc_stid(clp, deleg_slab, nfs4_free_deleg);
 	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);
@@ -1155,19 +1158,79 @@ 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]);
+	kfree(ncn->ncn_nf);
+	for (i = 0; i < NOTIFY4_PAGE_ARRAY_SIZE; i++) {
+		if (!ncn->ncn_pages[i])
+			break;
+		put_page(ncn->ncn_pages[i]);
+	}
+	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_put_stid(&dp->dl_stid);
+		return NULL;
+	}
+
+	ncn->ncn_nf = kcalloc(NOTIFY4_EVENT_QUEUE_SIZE, sizeof(*ncn->ncn_nf), GFP_KERNEL);
+	if (!ncn->ncn_nf) {
+		nfs4_put_stid(&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)
 {
@@ -3422,6 +3485,30 @@ 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,
@@ -3434,6 +3521,12 @@ 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 =
@@ -9810,7 +9903,7 @@ 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)

fs/nfsd/state.h

@@ -197,6 +197,45 @@ 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
+	bool				ncn_encode_err;	// did encoding fail?
+	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 +272,12 @@ struct nfs4_delegation {
 	bool			dl_written;
 	bool			dl_setattr;
 
-	/* for CB_GETATTR */
+	union {
-	struct nfs4_cb_fattr    dl_cb_fattr;
+		/* 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;