NFSD: Add NFSD_CMD_UNLOCK_EXPORT netlink command

When a filesystem is exported to NFS clients, NFSv4 state
(opens, locks, delegations, layouts) holds references that
prevent the underlying filesystem from being unmounted.
NFSD_CMD_UNLOCK_FILESYSTEM addresses this at superblock
granularity, but administrators unexporting a single path on a
shared filesystem (e.g., one of several exports on the same device)
need finer control.

Add NFSD_CMD_UNLOCK_EXPORT, which revokes NFSv4 state acquired
through exports of a specific path.  Matching is by path identity
(dentry + vfsmount) via the sc_export field on each nfs4_stid,
so multiple svc_export objects for the same path -- one per
auth_domain -- are handled correctly without requiring the caller
to name a specific client.

The command takes a single "path" attribute.  Userspace (exportfs
-u) sends this after removing the last client for a given path,
enabling the underlying filesystem to be unmounted.  When multiple
clients share an export path, individual unexports do not trigger
state revocation; only the final one does.

Reviewed-by: Jeff Layton <jlayton@kernel.org>
Tested-by: Dai Ngo <dai.ngo@oracle.com>
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>

Documentation/netlink/specs/nfsd.yaml

@@ -317,6 +317,19 @@ attribute-sets:
         name: path
         type: string
         doc: Filesystem path whose state should be released.
+  -
+    name: unlock-export
+    attributes:
+      -
+        name: path
+        type: string
+        doc: >-
+          Export path whose NFSv4 state should be revoked.
+          All state (opens, locks, delegations, layouts) acquired
+          through any export of this path is revoked, regardless
+          of which client holds the state. Intended for use after
+          all clients have been unexported from a given path,
+          enabling the underlying filesystem to be unmounted.
 
 operations:
   list:
@@ -489,6 +502,20 @@ operations:
         request:
           attributes:
             - path
+    -
+      name: unlock-export
+      doc: >-
+        Revoke NFSv4 state acquired through exports of a given path.
+        Unlike unlock-filesystem, which operates at superblock granularity,
+        this command targets only state associated with a specific export
+        path. Userspace (exportfs -u) sends this after removing the last
+        client for a path so the underlying filesystem can be unmounted.
+      attribute-set: unlock-export
+      flags: [admin-perm]
+      do:
+        request:
+          attributes:
+            - path
 
 mcast-groups:
   list:

fs/nfsd/netlink.c

@@ -113,6 +113,11 @@ static const struct nla_policy nfsd_unlock_filesystem_nl_policy[NFSD_A_UNLOCK_FI
 	[NFSD_A_UNLOCK_FILESYSTEM_PATH] = { .type = NLA_NUL_STRING, },
 };
 
+/* NFSD_CMD_UNLOCK_EXPORT - do */
+static const struct nla_policy nfsd_unlock_export_nl_policy[NFSD_A_UNLOCK_EXPORT_PATH + 1] = {
+	[NFSD_A_UNLOCK_EXPORT_PATH] = { .type = NLA_NUL_STRING, },
+};
+
 /* Ops table for nfsd */
 static const struct genl_split_ops nfsd_nl_ops[] = {
 	{
@@ -213,6 +218,13 @@ static const struct genl_split_ops nfsd_nl_ops[] = {
 		.maxattr	= NFSD_A_UNLOCK_FILESYSTEM_PATH,
 		.flags		= GENL_ADMIN_PERM | GENL_CMD_CAP_DO,
 	},
+	{
+		.cmd		= NFSD_CMD_UNLOCK_EXPORT,
+		.doit		= nfsd_nl_unlock_export_doit,
+		.policy		= nfsd_unlock_export_nl_policy,
+		.maxattr	= NFSD_A_UNLOCK_EXPORT_PATH,
+		.flags		= GENL_ADMIN_PERM | GENL_CMD_CAP_DO,
+	},
 };
 
 static const struct genl_multicast_group nfsd_nl_mcgrps[] = {

fs/nfsd/netlink.h

@@ -41,6 +41,7 @@ int nfsd_nl_expkey_set_reqs_doit(struct sk_buff *skb, struct genl_info *info);
 int nfsd_nl_cache_flush_doit(struct sk_buff *skb, struct genl_info *info);
 int nfsd_nl_unlock_ip_doit(struct sk_buff *skb, struct genl_info *info);
 int nfsd_nl_unlock_filesystem_doit(struct sk_buff *skb, struct genl_info *info);
+int nfsd_nl_unlock_export_doit(struct sk_buff *skb, struct genl_info *info);
 
 enum {
 	NFSD_NLGRP_NONE,

fs/nfsd/nfs4state.c

@@ -1911,6 +1911,73 @@ void nfsd4_revoke_states(struct nfsd_net *nn, struct super_block *sb)
 	spin_unlock(&nn->client_lock);
 }
 
+static struct nfs4_stid *find_one_export_stid(struct nfs4_client *clp,
+					     const struct path *path,
+					     unsigned int sc_types)
+{
+	unsigned long id = 0;
+	struct nfs4_stid *stid;
+
+	spin_lock(&clp->cl_lock);
+	while ((stid = idr_get_next_ul(&clp->cl_stateids, &id)) != NULL) {
+		if ((stid->sc_type & sc_types) &&
+		    stid->sc_status == 0 &&
+		    stid->sc_export &&
+		    path_equal(&stid->sc_export->ex_path, path)) {
+			refcount_inc(&stid->sc_count);
+			break;
+		}
+		id++;
+	}
+	spin_unlock(&clp->cl_lock);
+	return stid;
+}
+
+/**
+ * nfsd4_revoke_export_states - revoke nfsv4 states acquired through an export
+ * @nn:   used to identify instance of nfsd (there is one per net namespace)
+ * @path: export path whose states should be revoked
+ *
+ * All nfs4 states (open, lock, delegation, layout) acquired through any
+ * export matching @path are revoked, regardless of which client holds
+ * them.  Matching is by path identity (dentry + vfsmount), so multiple
+ * svc_export objects for the same path -- one per auth_domain -- are
+ * handled correctly.
+ *
+ * Userspace (exportfs -u) sends this after removing the last client
+ * for a path, enabling the underlying filesystem to be unmounted.
+ */
+void nfsd4_revoke_export_states(struct nfsd_net *nn, const struct path *path)
+{
+	unsigned int idhashval;
+	unsigned int sc_types;
+
+	sc_types = SC_TYPE_OPEN | SC_TYPE_LOCK | SC_TYPE_DELEG | SC_TYPE_LAYOUT;
+
+	spin_lock(&nn->client_lock);
+	for (idhashval = 0; idhashval < CLIENT_HASH_SIZE; idhashval++) {
+		struct list_head *head = &nn->conf_id_hashtbl[idhashval];
+		struct nfs4_client *clp;
+	retry:
+		list_for_each_entry(clp, head, cl_idhash) {
+			struct nfs4_stid *stid = find_one_export_stid(
+							clp, path,
+							sc_types);
+			if (stid) {
+				spin_unlock(&nn->client_lock);
+				revoke_one_stid(nn, clp, stid);
+				nfs4_put_stid(stid);
+				spin_lock(&nn->client_lock);
+				if (clp->cl_minorversion == 0)
+					nn->nfs40_last_revoke =
+						ktime_get_boottime_seconds();
+				goto retry;
+			}
+		}
+	}
+	spin_unlock(&nn->client_lock);
+}
+
 static inline int
 hash_sessionid(struct nfs4_sessionid *sessionid)
 {

fs/nfsd/nfsctl.c

@@ -2354,6 +2354,51 @@ int nfsd_nl_unlock_filesystem_doit(struct sk_buff *skb,
 	return error;
 }
 
+/**
+ * nfsd_nl_unlock_export_doit - revoke NFSv4 state for an export path
+ * @skb: reply buffer
+ * @info: netlink metadata and command arguments
+ *
+ * Revokes all NFSv4 state (opens, locks, delegations, layouts) acquired
+ * through any export of the given path, regardless of which client holds
+ * the state.  Userspace (exportfs -u) sends this after removing the last
+ * client for a path so the underlying filesystem can be unmounted.
+ *
+ * Unlike NFSD_CMD_UNLOCK_FILESYSTEM, which operates at superblock
+ * granularity, this command revokes only the state associated with
+ * exports of a specific path.
+ *
+ * Return: 0 on success or a negative errno.
+ */
+int nfsd_nl_unlock_export_doit(struct sk_buff *skb, struct genl_info *info)
+{
+	struct net *net = genl_info_net(info);
+	struct nfsd_net *nn = net_generic(net, nfsd_net_id);
+	struct path path;
+	int error;
+
+	if (GENL_REQ_ATTR_CHECK(info, NFSD_A_UNLOCK_EXPORT_PATH))
+		return -EINVAL;
+
+	trace_nfsd_ctl_unlock_export(net,
+			nla_data(info->attrs[NFSD_A_UNLOCK_EXPORT_PATH]));
+	error = kern_path(
+			nla_data(info->attrs[NFSD_A_UNLOCK_EXPORT_PATH]),
+			0, &path);
+	if (error)
+		return error;
+
+	mutex_lock(&nfsd_mutex);
+	if (nn->nfsd_serv)
+		nfsd4_revoke_export_states(nn, &path);
+	else
+		error = -EINVAL;
+	mutex_unlock(&nfsd_mutex);
+
+	path_put(&path);
+	return error;
+}
+
 /**
  * nfsd_net_init - Prepare the nfsd_net portion of a new net namespace
  * @net: a freshly-created network namespace

fs/nfsd/state.h

@@ -863,6 +863,7 @@ struct nfsd_file *find_any_file(struct nfs4_file *f);
 
 #ifdef CONFIG_NFSD_V4
 void nfsd4_revoke_states(struct nfsd_net *nn, struct super_block *sb);
+void nfsd4_revoke_export_states(struct nfsd_net *nn, const struct path *path);
 void nfsd4_cancel_copy_by_sb(struct net *net, struct super_block *sb);
 int nfsd_net_cb_init(struct nfsd_net *nn);
 void nfsd_net_cb_shutdown(struct nfsd_net *nn);
@@ -870,6 +871,10 @@ void nfsd_net_cb_shutdown(struct nfsd_net *nn);
 static inline void nfsd4_revoke_states(struct nfsd_net *nn, struct super_block *sb)
 {
 }
+static inline void nfsd4_revoke_export_states(struct nfsd_net *nn,
+					      const struct path *path)
+{
+}
 static inline void nfsd4_cancel_copy_by_sb(struct net *net, struct super_block *sb)
 {
 }

fs/nfsd/trace.h

@@ -2021,6 +2021,25 @@ TRACE_EVENT(nfsd_ctl_unlock_fs,
 	)
 );
 
+TRACE_EVENT(nfsd_ctl_unlock_export,
+	TP_PROTO(
+		const struct net *net,
+		const char *path
+	),
+	TP_ARGS(net, path),
+	TP_STRUCT__entry(
+		__field(unsigned int, netns_ino)
+		__string(path, path)
+	),
+	TP_fast_assign(
+		__entry->netns_ino = net->ns.inum;
+		__assign_str(path);
+	),
+	TP_printk("path=%s",
+		__get_str(path)
+	)
+);
+
 TRACE_EVENT(nfsd_ctl_filehandle,
 	TP_PROTO(
 		const struct net *net,

include/uapi/linux/nfsd_netlink.h

@@ -218,6 +218,13 @@ enum {
 	NFSD_A_UNLOCK_FILESYSTEM_MAX = (__NFSD_A_UNLOCK_FILESYSTEM_MAX - 1)
 };
 
+enum {
+	NFSD_A_UNLOCK_EXPORT_PATH = 1,
+
+	__NFSD_A_UNLOCK_EXPORT_MAX,
+	NFSD_A_UNLOCK_EXPORT_MAX = (__NFSD_A_UNLOCK_EXPORT_MAX - 1)
+};
+
 enum {
 	NFSD_CMD_RPC_STATUS_GET = 1,
 	NFSD_CMD_THREADS_SET,
@@ -236,6 +243,7 @@ enum {
 	NFSD_CMD_CACHE_FLUSH,
 	NFSD_CMD_UNLOCK_IP,
 	NFSD_CMD_UNLOCK_FILESYSTEM,
+	NFSD_CMD_UNLOCK_EXPORT,
 
 	__NFSD_CMD_MAX,
 	NFSD_CMD_MAX = (__NFSD_CMD_MAX - 1)