Merge branch 'for-2.6.29' of git://linux-nfs.org/~bfields/linux

* 'for-2.6.29' of git://linux-nfs.org/~bfields/linux: (67 commits)
  nfsd: get rid of NFSD_VERSION
  nfsd: last_byte_offset
  nfsd: delete wrong file comment from nfsd/nfs4xdr.c
  nfsd: git rid of nfs4_cb_null_ops declaration
  nfsd: dprint each op status in nfsd4_proc_compound
  nfsd: add etoosmall to nfserrno
  NFSD: FIDs need to take precedence over UUIDs
  SUNRPC: The sunrpc server code should not be used by out-of-tree modules
  svc: Clean up deferred requests on transport destruction
  nfsd: fix double-locks of directory mutex
  svc: Move kfree of deferral record to common code
  CRED: Fix NFSD regression
  NLM: Clean up flow of control in make_socks() function
  NLM: Refactor make_socks() function
  nfsd: Ensure nfsv4 calls the underlying filesystem on LOCKT
  SUNRPC: Ensure the server closes sockets in a timely fashion
  NFSD: Add documenting comments for nfsctl interface
  NFSD: Replace open-coded integer with macro
  NFSD: Fix a handful of coding style issues in write_filehandle()
  NFSD: clean up failover sysctl function naming
  ...

fs/lockd/clntproc.c

@@ -16,7 +16,6 @@
 #include <linux/sunrpc/clnt.h>
 #include <linux/sunrpc/svc.h>
 #include <linux/lockd/lockd.h>
-#include <linux/lockd/sm_inter.h>
 
 #define NLMDBG_FACILITY		NLMDBG_CLIENT
 #define NLMCLNT_GRACE_WAIT	(5*HZ)
@@ -518,11 +517,9 @@ nlmclnt_lock(struct nlm_rqst *req, struct file_lock *fl)
 	unsigned char fl_type;
 	int status = -ENOLCK;
 
-	if (nsm_monitor(host) < 0) {
-		printk(KERN_NOTICE "lockd: failed to monitor %s\n",
-					host->h_name);
+	if (nsm_monitor(host) < 0)
 		goto out;
-	}
+
 	fl->fl_flags |= FL_ACCESS;
 	status = do_vfs_lock(fl);
 	fl->fl_flags = fl_flags;

fs/lockd/host.c

@@ -15,7 +15,6 @@
 #include <linux/sunrpc/clnt.h>
 #include <linux/sunrpc/svc.h>
 #include <linux/lockd/lockd.h>
-#include <linux/lockd/sm_inter.h>
 #include <linux/mutex.h>
 
 #include <net/ipv6.h>
@@ -32,11 +31,6 @@ static int			nrhosts;
 static DEFINE_MUTEX(nlm_host_mutex);
 
 static void			nlm_gc_hosts(void);
-static struct nsm_handle	*nsm_find(const struct sockaddr *sap,
-						const size_t salen,
-						const char *hostname,
-						const size_t hostname_len,
-						const int create);
 
 struct nlm_lookup_host_info {
 	const int		server;		/* search for server|client */
@@ -105,32 +99,6 @@ static void nlm_clear_port(struct sockaddr *sap)
 	}
 }
 
-static void nlm_display_address(const struct sockaddr *sap,
-				char *buf, const size_t len)
-{
-	const struct sockaddr_in *sin = (struct sockaddr_in *)sap;
-	const struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *)sap;
-
-	switch (sap->sa_family) {
-	case AF_UNSPEC:
-		snprintf(buf, len, "unspecified");
-		break;
-	case AF_INET:
-		snprintf(buf, len, "%pI4", &sin->sin_addr.s_addr);
-		break;
-	case AF_INET6:
-		if (ipv6_addr_v4mapped(&sin6->sin6_addr))
-			snprintf(buf, len, "%pI4",
-				 &sin6->sin6_addr.s6_addr32[3]);
-		else
-			snprintf(buf, len, "%pI6", &sin6->sin6_addr);
-		break;
-	default:
-		snprintf(buf, len, "unsupported address family");
-		break;
-	}
-}
-
 /*
  * Common host lookup routine for server & client
  */
@@ -190,8 +158,8 @@ static struct nlm_host *nlm_lookup_host(struct nlm_lookup_host_info *ni)
 		atomic_inc(&nsm->sm_count);
 	else {
 		host = NULL;
-		nsm = nsm_find(ni->sap, ni->salen,
-				ni->hostname, ni->hostname_len, 1);
+		nsm = nsm_get_handle(ni->sap, ni->salen,
+					ni->hostname, ni->hostname_len);
 		if (!nsm) {
 			dprintk("lockd: nlm_lookup_host failed; "
 				"no nsm handle\n");
@@ -206,6 +174,7 @@ static struct nlm_host *nlm_lookup_host(struct nlm_lookup_host_info *ni)
 		goto out;
 	}
 	host->h_name	   = nsm->sm_name;
+	host->h_addrbuf    = nsm->sm_addrbuf;
 	memcpy(nlm_addr(host), ni->sap, ni->salen);
 	host->h_addrlen = ni->salen;
 	nlm_clear_port(nlm_addr(host));
@@ -232,11 +201,6 @@ static struct nlm_host *nlm_lookup_host(struct nlm_lookup_host_info *ni)
 
 	nrhosts++;
 
-	nlm_display_address((struct sockaddr *)&host->h_addr,
-				host->h_addrbuf, sizeof(host->h_addrbuf));
-	nlm_display_address((struct sockaddr *)&host->h_srcaddr,
-				host->h_srcaddrbuf, sizeof(host->h_srcaddrbuf));
-
 	dprintk("lockd: nlm_lookup_host created host %s\n",
 			host->h_name);
 
@@ -256,10 +220,8 @@ nlm_destroy_host(struct nlm_host *host)
 	BUG_ON(!list_empty(&host->h_lockowners));
 	BUG_ON(atomic_read(&host->h_count));
 
-	/*
-	 * Release NSM handle and unmonitor host.
-	 */
 	nsm_unmonitor(host);
+	nsm_release(host->h_nsmhandle);
 
 	clnt = host->h_rpcclnt;
 	if (clnt != NULL)
@@ -378,8 +340,8 @@ nlm_bind_host(struct nlm_host *host)
 {
 	struct rpc_clnt	*clnt;
 
-	dprintk("lockd: nlm_bind_host %s (%s), my addr=%s\n",
-			host->h_name, host->h_addrbuf, host->h_srcaddrbuf);
+	dprintk("lockd: nlm_bind_host %s (%s)\n",
+			host->h_name, host->h_addrbuf);
 
 	/* Lock host handle */
 	mutex_lock(&host->h_mutex);
@@ -481,35 +443,23 @@ void nlm_release_host(struct nlm_host *host)
 	}
 }
 
-/*
- * We were notified that the host indicated by address &sin
- * has rebooted.
- * Release all resources held by that peer.
+/**
+ * nlm_host_rebooted - Release all resources held by rebooted host
+ * @info: pointer to decoded results of NLM_SM_NOTIFY call
+ *
+ * We were notified that the specified host has rebooted.  Release
+ * all resources held by that peer.
  */
-void nlm_host_rebooted(const struct sockaddr_in *sin,
-				const char *hostname,
-				unsigned int hostname_len,
-				u32 new_state)
+void nlm_host_rebooted(const struct nlm_reboot *info)
 {
 	struct hlist_head *chain;
 	struct hlist_node *pos;
 	struct nsm_handle *nsm;
 	struct nlm_host	*host;
 
-	nsm = nsm_find((struct sockaddr *)sin, sizeof(*sin),
-			hostname, hostname_len, 0);
-	if (nsm == NULL) {
-		dprintk("lockd: never saw rebooted peer '%.*s' before\n",
-				hostname_len, hostname);
+	nsm = nsm_reboot_lookup(info);
+	if (unlikely(nsm == NULL))
 		return;
-	}
-
-	dprintk("lockd: nlm_host_rebooted(%.*s, %s)\n",
-			hostname_len, hostname, nsm->sm_addrbuf);
-
-	/* When reclaiming locks on this peer, make sure that
-	 * we set up a new notification */
-	nsm->sm_monitored = 0;
 
 	/* Mark all hosts tied to this NSM state as having rebooted.
 	 * We run the loop repeatedly, because we drop the host table
@@ -520,8 +470,8 @@ again:	mutex_lock(&nlm_host_mutex);
 	for (chain = nlm_hosts; chain < nlm_hosts + NLM_HOST_NRHASH; ++chain) {
 		hlist_for_each_entry(host, pos, chain, h_hash) {
 			if (host->h_nsmhandle == nsm
-			 && host->h_nsmstate != new_state) {
-				host->h_nsmstate = new_state;
+			 && host->h_nsmstate != info->state) {
+				host->h_nsmstate = info->state;
 				host->h_state++;
 
 				nlm_get_host(host);
@@ -629,89 +579,3 @@ nlm_gc_hosts(void)
 
 	next_gc = jiffies + NLM_HOST_COLLECT;
 }
-
-
-/*
- * Manage NSM handles
- */
-static LIST_HEAD(nsm_handles);
-static DEFINE_SPINLOCK(nsm_lock);
-
-static struct nsm_handle *nsm_find(const struct sockaddr *sap,
-				   const size_t salen,
-				   const char *hostname,
-				   const size_t hostname_len,
-				   const int create)
-{
-	struct nsm_handle *nsm = NULL;
-	struct nsm_handle *pos;
-
-	if (!sap)
-		return NULL;
-
-	if (hostname && memchr(hostname, '/', hostname_len) != NULL) {
-		if (printk_ratelimit()) {
-			printk(KERN_WARNING "Invalid hostname \"%.*s\" "
-					    "in NFS lock request\n",
-				(int)hostname_len, hostname);
-		}
-		return NULL;
-	}
-
-retry:
-	spin_lock(&nsm_lock);
-	list_for_each_entry(pos, &nsm_handles, sm_link) {
-
-		if (hostname && nsm_use_hostnames) {
-			if (strlen(pos->sm_name) != hostname_len
-			 || memcmp(pos->sm_name, hostname, hostname_len))
-				continue;
-		} else if (!nlm_cmp_addr(nsm_addr(pos), sap))
-			continue;
-		atomic_inc(&pos->sm_count);
-		kfree(nsm);
-		nsm = pos;
-		goto found;
-	}
-	if (nsm) {
-		list_add(&nsm->sm_link, &nsm_handles);
-		goto found;
-	}
-	spin_unlock(&nsm_lock);
-
-	if (!create)
-		return NULL;
-
-	nsm = kzalloc(sizeof(*nsm) + hostname_len + 1, GFP_KERNEL);
-	if (nsm == NULL)
-		return NULL;
-
-	memcpy(nsm_addr(nsm), sap, salen);
-	nsm->sm_addrlen = salen;
-	nsm->sm_name = (char *) (nsm + 1);
-	memcpy(nsm->sm_name, hostname, hostname_len);
-	nsm->sm_name[hostname_len] = '\0';
-	nlm_display_address((struct sockaddr *)&nsm->sm_addr,
-				nsm->sm_addrbuf, sizeof(nsm->sm_addrbuf));
-	atomic_set(&nsm->sm_count, 1);
-	goto retry;
-
-found:
-	spin_unlock(&nsm_lock);
-	return nsm;
-}
-
-/*
- * Release an NSM handle
- */
-void
-nsm_release(struct nsm_handle *nsm)
-{
-	if (!nsm)
-		return;
-	if (atomic_dec_and_lock(&nsm->sm_count, &nsm_lock)) {
-		list_del(&nsm->sm_link);
-		spin_unlock(&nsm_lock);
-		kfree(nsm);
-	}
-}

fs/lockd/mon.c

@@ -9,35 +9,123 @@
 #include <linux/types.h>
 #include <linux/utsname.h>
 #include <linux/kernel.h>
+#include <linux/ktime.h>
+
 #include <linux/sunrpc/clnt.h>
 #include <linux/sunrpc/xprtsock.h>
 #include <linux/sunrpc/svc.h>
 #include <linux/lockd/lockd.h>
-#include <linux/lockd/sm_inter.h>
-
 
 #define NLMDBG_FACILITY		NLMDBG_MONITOR
+#define NSM_PROGRAM		100024
+#define NSM_VERSION		1
+
+enum {
+	NSMPROC_NULL,
+	NSMPROC_STAT,
+	NSMPROC_MON,
+	NSMPROC_UNMON,
+	NSMPROC_UNMON_ALL,
+	NSMPROC_SIMU_CRASH,
+	NSMPROC_NOTIFY,
+};
+
+struct nsm_args {
+	struct nsm_private	*priv;
+	u32			prog;		/* RPC callback info */
+	u32			vers;
+	u32			proc;
 
-#define XDR_ADDRBUF_LEN		(20)
+	char			*mon_name;
+};
 
-static struct rpc_clnt *	nsm_create(void);
+struct nsm_res {
+	u32			status;
+	u32			state;
+};
 
 static struct rpc_program	nsm_program;
+static				LIST_HEAD(nsm_handles);
+static				DEFINE_SPINLOCK(nsm_lock);
 
 /*
  * Local NSM state
  */
-int				nsm_local_state;
+int	__read_mostly		nsm_local_state;
+int	__read_mostly		nsm_use_hostnames;
 
-/*
- * Common procedure for SM_MON/SM_UNMON calls
- */
-static int
-nsm_mon_unmon(struct nsm_handle *nsm, u32 proc, struct nsm_res *res)
+static inline struct sockaddr *nsm_addr(const struct nsm_handle *nsm)
+{
+	return (struct sockaddr *)&nsm->sm_addr;
+}
+
+static void nsm_display_ipv4_address(const struct sockaddr *sap, char *buf,
+				     const size_t len)
+{
+	const struct sockaddr_in *sin = (struct sockaddr_in *)sap;
+	snprintf(buf, len, "%pI4", &sin->sin_addr.s_addr);
+}
+
+static void nsm_display_ipv6_address(const struct sockaddr *sap, char *buf,
+				     const size_t len)
+{
+	const struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *)sap;
+
+	if (ipv6_addr_v4mapped(&sin6->sin6_addr))
+		snprintf(buf, len, "%pI4", &sin6->sin6_addr.s6_addr32[3]);
+	else if (sin6->sin6_scope_id != 0)
+		snprintf(buf, len, "%pI6%%%u", &sin6->sin6_addr,
+				sin6->sin6_scope_id);
+	else
+		snprintf(buf, len, "%pI6", &sin6->sin6_addr);
+}
+
+static void nsm_display_address(const struct sockaddr *sap,
+				char *buf, const size_t len)
+{
+	switch (sap->sa_family) {
+	case AF_INET:
+		nsm_display_ipv4_address(sap, buf, len);
+		break;
+	case AF_INET6:
+		nsm_display_ipv6_address(sap, buf, len);
+		break;
+	default:
+		snprintf(buf, len, "unsupported address family");
+		break;
+	}
+}
+
+static struct rpc_clnt *nsm_create(void)
+{
+	struct sockaddr_in sin = {
+		.sin_family		= AF_INET,
+		.sin_addr.s_addr	= htonl(INADDR_LOOPBACK),
+	};
+	struct rpc_create_args args = {
+		.protocol		= XPRT_TRANSPORT_UDP,
+		.address		= (struct sockaddr *)&sin,
+		.addrsize		= sizeof(sin),
+		.servername		= "rpc.statd",
+		.program		= &nsm_program,
+		.version		= NSM_VERSION,
+		.authflavor		= RPC_AUTH_NULL,
+	};
+
+	return rpc_create(&args);
+}
+
+static int nsm_mon_unmon(struct nsm_handle *nsm, u32 proc, struct nsm_res *res)
 {
 	struct rpc_clnt	*clnt;
 	int		status;
-	struct nsm_args	args;
+	struct nsm_args args = {
+		.priv		= &nsm->sm_priv,
+		.prog		= NLM_PROGRAM,
+		.vers		= 3,
+		.proc		= NLMPROC_NSM_NOTIFY,
+		.mon_name	= nsm->sm_mon_name,
+	};
 	struct rpc_message msg = {
 		.rpc_argp	= &args,
 		.rpc_resp	= res,
@@ -46,22 +134,18 @@ nsm_mon_unmon(struct nsm_handle *nsm, u32 proc, struct nsm_res *res)
 	clnt = nsm_create();
 	if (IS_ERR(clnt)) {
 		status = PTR_ERR(clnt);
+		dprintk("lockd: failed to create NSM upcall transport, "
+				"status=%d\n", status);
 		goto out;
 	}
 
-	memset(&args, 0, sizeof(args));
-	args.mon_name = nsm->sm_name;
-	args.addr = nsm_addr_in(nsm)->sin_addr.s_addr;
-	args.prog = NLM_PROGRAM;
-	args.vers = 3;
-	args.proc = NLMPROC_NSM_NOTIFY;
 	memset(res, 0, sizeof(*res));
 
 	msg.rpc_proc = &clnt->cl_procinfo[proc];
 	status = rpc_call_sync(clnt, &msg, 0);
 	if (status < 0)
-		printk(KERN_DEBUG "nsm_mon_unmon: rpc failed, status=%d\n",
-			status);
+		dprintk("lockd: NSM upcall RPC failed, status=%d\n",
+				status);
 	else
 		status = 0;
 	rpc_shutdown_client(clnt);
@@ -69,82 +153,272 @@ nsm_mon_unmon(struct nsm_handle *nsm, u32 proc, struct nsm_res *res)
 	return status;
 }
 
-/*
- * Set up monitoring of a remote host
+/**
+ * nsm_monitor - Notify a peer in case we reboot
+ * @host: pointer to nlm_host of peer to notify
+ *
+ * If this peer is not already monitored, this function sends an
+ * upcall to the local rpc.statd to record the name/address of
+ * the peer to notify in case we reboot.
+ *
+ * Returns zero if the peer is monitored by the local rpc.statd;
+ * otherwise a negative errno value is returned.
  */
-int
-nsm_monitor(struct nlm_host *host)
+int nsm_monitor(const struct nlm_host *host)
 {
 	struct nsm_handle *nsm = host->h_nsmhandle;
 	struct nsm_res	res;
 	int		status;
 
-	dprintk("lockd: nsm_monitor(%s)\n", host->h_name);
-	BUG_ON(nsm == NULL);
+	dprintk("lockd: nsm_monitor(%s)\n", nsm->sm_name);
 
 	if (nsm->sm_monitored)
 		return 0;
 
-	status = nsm_mon_unmon(nsm, SM_MON, &res);
+	/*
+	 * Choose whether to record the caller_name or IP address of
+	 * this peer in the local rpc.statd's database.
+	 */
+	nsm->sm_mon_name = nsm_use_hostnames ? nsm->sm_name : nsm->sm_addrbuf;
 
-	if (status < 0 || res.status != 0)
-		printk(KERN_NOTICE "lockd: cannot monitor %s\n", host->h_name);
+	status = nsm_mon_unmon(nsm, NSMPROC_MON, &res);
+	if (res.status != 0)
+		status = -EIO;
+	if (status < 0)
+		printk(KERN_NOTICE "lockd: cannot monitor %s\n", nsm->sm_name);
 	else
 		nsm->sm_monitored = 1;
 	return status;
 }
 
-/*
- * Cease to monitor remote host
+/**
+ * nsm_unmonitor - Unregister peer notification
+ * @host: pointer to nlm_host of peer to stop monitoring
+ *
+ * If this peer is monitored, this function sends an upcall to
+ * tell the local rpc.statd not to send this peer a notification
+ * when we reboot.
  */
-int
-nsm_unmonitor(struct nlm_host *host)
+void nsm_unmonitor(const struct nlm_host *host)
 {
 	struct nsm_handle *nsm = host->h_nsmhandle;
 	struct nsm_res	res;
-	int		status = 0;
-
-	if (nsm == NULL)
-		return 0;
-	host->h_nsmhandle = NULL;
+	int status;
 
 	if (atomic_read(&nsm->sm_count) == 1
 	 && nsm->sm_monitored && !nsm->sm_sticky) {
-		dprintk("lockd: nsm_unmonitor(%s)\n", host->h_name);
+		dprintk("lockd: nsm_unmonitor(%s)\n", nsm->sm_name);
 
-		status = nsm_mon_unmon(nsm, SM_UNMON, &res);
+		status = nsm_mon_unmon(nsm, NSMPROC_UNMON, &res);
+		if (res.status != 0)
+			status = -EIO;
 		if (status < 0)
 			printk(KERN_NOTICE "lockd: cannot unmonitor %s\n",
-					host->h_name);
+					nsm->sm_name);
 		else
 			nsm->sm_monitored = 0;
 	}
-	nsm_release(nsm);
-	return status;
+}
+
+static struct nsm_handle *nsm_lookup_hostname(const char *hostname,
+					      const size_t len)
+{
+	struct nsm_handle *nsm;
+
+	list_for_each_entry(nsm, &nsm_handles, sm_link)
+		if (strlen(nsm->sm_name) == len &&
+		    memcmp(nsm->sm_name, hostname, len) == 0)
+			return nsm;
+	return NULL;
+}
+
+static struct nsm_handle *nsm_lookup_addr(const struct sockaddr *sap)
+{
+	struct nsm_handle *nsm;
+
+	list_for_each_entry(nsm, &nsm_handles, sm_link)
+		if (nlm_cmp_addr(nsm_addr(nsm), sap))
+			return nsm;
+	return NULL;
+}
+
+static struct nsm_handle *nsm_lookup_priv(const struct nsm_private *priv)
+{
+	struct nsm_handle *nsm;
+
+	list_for_each_entry(nsm, &nsm_handles, sm_link)
+		if (memcmp(nsm->sm_priv.data, priv->data,
+					sizeof(priv->data)) == 0)
+			return nsm;
+	return NULL;
 }
 
 /*
- * Create NSM client for the local host
+ * Construct a unique cookie to match this nsm_handle to this monitored
+ * host.  It is passed to the local rpc.statd via NSMPROC_MON, and
+ * returned via NLMPROC_SM_NOTIFY, in the "priv" field of these
+ * requests.
+ *
+ * The NSM protocol requires that these cookies be unique while the
+ * system is running.  We prefer a stronger requirement of making them
+ * unique across reboots.  If user space bugs cause a stale cookie to
+ * be sent to the kernel, it could cause the wrong host to lose its
+ * lock state if cookies were not unique across reboots.
+ *
+ * The cookies are exposed only to local user space via loopback.  They
+ * do not appear on the physical network.  If we want greater security
+ * for some reason, nsm_init_private() could perform a one-way hash to
+ * obscure the contents of the cookie.
  */
-static struct rpc_clnt *
-nsm_create(void)
+static void nsm_init_private(struct nsm_handle *nsm)
 {
-	struct sockaddr_in	sin = {
-		.sin_family	= AF_INET,
-		.sin_addr.s_addr = htonl(INADDR_LOOPBACK),
-		.sin_port	= 0,
-	};
-	struct rpc_create_args args = {
-		.protocol	= XPRT_TRANSPORT_UDP,
-		.address	= (struct sockaddr *)&sin,
-		.addrsize	= sizeof(sin),
-		.servername	= "localhost",
-		.program	= &nsm_program,
-		.version	= SM_VERSION,
-		.authflavor	= RPC_AUTH_NULL,
-	};
+	u64 *p = (u64 *)&nsm->sm_priv.data;
+	struct timespec ts;
 
-	return rpc_create(&args);
+	ktime_get_ts(&ts);
+	*p++ = timespec_to_ns(&ts);
+	*p = (unsigned long)nsm;
+}
+
+static struct nsm_handle *nsm_create_handle(const struct sockaddr *sap,
+					    const size_t salen,
+					    const char *hostname,
+					    const size_t hostname_len)
+{
+	struct nsm_handle *new;
+
+	new = kzalloc(sizeof(*new) + hostname_len + 1, GFP_KERNEL);
+	if (unlikely(new == NULL))
+		return NULL;
+
+	atomic_set(&new->sm_count, 1);
+	new->sm_name = (char *)(new + 1);
+	memcpy(nsm_addr(new), sap, salen);
+	new->sm_addrlen = salen;
+	nsm_init_private(new);
+	nsm_display_address((const struct sockaddr *)&new->sm_addr,
+				new->sm_addrbuf, sizeof(new->sm_addrbuf));
+	memcpy(new->sm_name, hostname, hostname_len);
+	new->sm_name[hostname_len] = '\0';
+
+	return new;
+}
+
+/**
+ * nsm_get_handle - Find or create a cached nsm_handle
+ * @sap: pointer to socket address of handle to find
+ * @salen: length of socket address
+ * @hostname: pointer to C string containing hostname to find
+ * @hostname_len: length of C string
+ *
+ * Behavior is modulated by the global nsm_use_hostnames variable.
+ *
+ * Returns a cached nsm_handle after bumping its ref count, or
+ * returns a fresh nsm_handle if a handle that matches @sap and/or
+ * @hostname cannot be found in the handle cache.  Returns NULL if
+ * an error occurs.
+ */
+struct nsm_handle *nsm_get_handle(const struct sockaddr *sap,
+				  const size_t salen, const char *hostname,
+				  const size_t hostname_len)
+{
+	struct nsm_handle *cached, *new = NULL;
+
+	if (hostname && memchr(hostname, '/', hostname_len) != NULL) {
+		if (printk_ratelimit()) {
+			printk(KERN_WARNING "Invalid hostname \"%.*s\" "
+					    "in NFS lock request\n",
+				(int)hostname_len, hostname);
+		}
+		return NULL;
+	}
+
+retry:
+	spin_lock(&nsm_lock);
+
+	if (nsm_use_hostnames && hostname != NULL)
+		cached = nsm_lookup_hostname(hostname, hostname_len);
+	else
+		cached = nsm_lookup_addr(sap);
+
+	if (cached != NULL) {
+		atomic_inc(&cached->sm_count);
+		spin_unlock(&nsm_lock);
+		kfree(new);
+		dprintk("lockd: found nsm_handle for %s (%s), "
+				"cnt %d\n", cached->sm_name,
+				cached->sm_addrbuf,
+				atomic_read(&cached->sm_count));
+		return cached;
+	}
+
+	if (new != NULL) {
+		list_add(&new->sm_link, &nsm_handles);
+		spin_unlock(&nsm_lock);
+		dprintk("lockd: created nsm_handle for %s (%s)\n",
+				new->sm_name, new->sm_addrbuf);
+		return new;
+	}
+
+	spin_unlock(&nsm_lock);
+
+	new = nsm_create_handle(sap, salen, hostname, hostname_len);
+	if (unlikely(new == NULL))
+		return NULL;
+	goto retry;
+}
+
+/**
+ * nsm_reboot_lookup - match NLMPROC_SM_NOTIFY arguments to an nsm_handle
+ * @info: pointer to NLMPROC_SM_NOTIFY arguments
+ *
+ * Returns a matching nsm_handle if found in the nsm cache; the returned
+ * nsm_handle's reference count is bumped and sm_monitored is cleared.
+ * Otherwise returns NULL if some error occurred.
+ */
+struct nsm_handle *nsm_reboot_lookup(const struct nlm_reboot *info)
+{
+	struct nsm_handle *cached;
+
+	spin_lock(&nsm_lock);
+
+	cached = nsm_lookup_priv(&info->priv);
+	if (unlikely(cached == NULL)) {
+		spin_unlock(&nsm_lock);
+		dprintk("lockd: never saw rebooted peer '%.*s' before\n",
+				info->len, info->mon);
+		return cached;
+	}
+
+	atomic_inc(&cached->sm_count);
+	spin_unlock(&nsm_lock);
+
+	/*
+	 * During subsequent lock activity, force a fresh
+	 * notification to be set up for this host.
+	 */
+	cached->sm_monitored = 0;
+
+	dprintk("lockd: host %s (%s) rebooted, cnt %d\n",
+			cached->sm_name, cached->sm_addrbuf,
+			atomic_read(&cached->sm_count));
+	return cached;
+}
+
+/**
+ * nsm_release - Release an NSM handle
+ * @nsm: pointer to handle to be released
+ *
+ */
+void nsm_release(struct nsm_handle *nsm)
+{
+	if (atomic_dec_and_lock(&nsm->sm_count, &nsm_lock)) {
+		list_del(&nsm->sm_link);
+		spin_unlock(&nsm_lock);
+		dprintk("lockd: destroyed nsm_handle for %s (%s)\n",
+				nsm->sm_name, nsm->sm_addrbuf);
+		kfree(nsm);
+	}
 }
 
 /*
@@ -154,127 +428,132 @@ nsm_create(void)
  * Status Monitor wire protocol.
  */
 
-static __be32 *xdr_encode_nsm_string(__be32 *p, char *string)
+static int encode_nsm_string(struct xdr_stream *xdr, const char *string)
 {
-	size_t len = strlen(string);
-
-	if (len > SM_MAXSTRLEN)
-		len = SM_MAXSTRLEN;
-	return xdr_encode_opaque(p, string, len);
+	const u32 len = strlen(string);
+	__be32 *p;
+
+	if (unlikely(len > SM_MAXSTRLEN))
+		return -EIO;
+	p = xdr_reserve_space(xdr, sizeof(u32) + len);
+	if (unlikely(p == NULL))
+		return -EIO;
+	xdr_encode_opaque(p, string, len);
+	return 0;
 }
 
 /*
  * "mon_name" specifies the host to be monitored.
- *
- * Linux uses a text version of the IP address of the remote
- * host as the host identifier (the "mon_name" argument).
- *
- * Linux statd always looks up the canonical hostname first for
- * whatever remote hostname it receives, so this works alright.
  */
-static __be32 *xdr_encode_mon_name(__be32 *p, struct nsm_args *argp)
+static int encode_mon_name(struct xdr_stream *xdr, const struct nsm_args *argp)
 {
-	char	buffer[XDR_ADDRBUF_LEN + 1];
-	char	*name = argp->mon_name;
-
-	if (!nsm_use_hostnames) {
-		snprintf(buffer, XDR_ADDRBUF_LEN,
-			 "%pI4", &argp->addr);
-		name = buffer;
-	}
-
-	return xdr_encode_nsm_string(p, name);
+	return encode_nsm_string(xdr, argp->mon_name);
 }
 
 /*
  * The "my_id" argument specifies the hostname and RPC procedure
  * to be called when the status manager receives notification
- * (via the SM_NOTIFY call) that the state of host "mon_name"
+ * (via the NLMPROC_SM_NOTIFY call) that the state of host "mon_name"
  * has changed.
  */
-static __be32 *xdr_encode_my_id(__be32 *p, struct nsm_args *argp)
+static int encode_my_id(struct xdr_stream *xdr, const struct nsm_args *argp)
 {
-	p = xdr_encode_nsm_string(p, utsname()->nodename);
-	if (!p)
-		return ERR_PTR(-EIO);
-
+	int status;
+	__be32 *p;
+
+	status = encode_nsm_string(xdr, utsname()->nodename);
+	if (unlikely(status != 0))
+		return status;
+	p = xdr_reserve_space(xdr, 3 * sizeof(u32));
+	if (unlikely(p == NULL))
+		return -EIO;
 	*p++ = htonl(argp->prog);
 	*p++ = htonl(argp->vers);
 	*p++ = htonl(argp->proc);
-
-	return p;
+	return 0;
 }
 
 /*
  * The "mon_id" argument specifies the non-private arguments
- * of an SM_MON or SM_UNMON call.
+ * of an NSMPROC_MON or NSMPROC_UNMON call.
  */
-static __be32 *xdr_encode_mon_id(__be32 *p, struct nsm_args *argp)
+static int encode_mon_id(struct xdr_stream *xdr, const struct nsm_args *argp)
 {
-	p = xdr_encode_mon_name(p, argp);
-	if (!p)
-		return ERR_PTR(-EIO);
+	int status;
 
-	return xdr_encode_my_id(p, argp);
+	status = encode_mon_name(xdr, argp);
+	if (unlikely(status != 0))
+		return status;
+	return encode_my_id(xdr, argp);
 }
 
 /*
  * The "priv" argument may contain private information required
- * by the SM_MON call. This information will be supplied in the
- * SM_NOTIFY call.
- *
- * Linux provides the raw IP address of the monitored host,
- * left in network byte order.
+ * by the NSMPROC_MON call. This information will be supplied in the
+ * NLMPROC_SM_NOTIFY call.
  */
-static __be32 *xdr_encode_priv(__be32 *p, struct nsm_args *argp)
+static int encode_priv(struct xdr_stream *xdr, const struct nsm_args *argp)
 {
-	*p++ = argp->addr;
-	*p++ = 0;
-	*p++ = 0;
-	*p++ = 0;
+	__be32 *p;
 
-	return p;
+	p = xdr_reserve_space(xdr, SM_PRIV_SIZE);
+	if (unlikely(p == NULL))
+		return -EIO;
+	xdr_encode_opaque_fixed(p, argp->priv->data, SM_PRIV_SIZE);
+	return 0;
 }
 
-static int
-xdr_encode_mon(struct rpc_rqst *rqstp, __be32 *p, struct nsm_args *argp)
+static int xdr_enc_mon(struct rpc_rqst *req, __be32 *p,
+		       const struct nsm_args *argp)
 {
-	p = xdr_encode_mon_id(p, argp);
-	if (IS_ERR(p))
-		return PTR_ERR(p);
-
-	p = xdr_encode_priv(p, argp);
-	if (IS_ERR(p))
-		return PTR_ERR(p);
-
-	rqstp->rq_slen = xdr_adjust_iovec(rqstp->rq_svec, p);
-	return 0;
+	struct xdr_stream xdr;
+	int status;
+
+	xdr_init_encode(&xdr, &req->rq_snd_buf, p);
+	status = encode_mon_id(&xdr, argp);
+	if (unlikely(status))
+		return status;
+	return encode_priv(&xdr, argp);
 }
 
-static int
-xdr_encode_unmon(struct rpc_rqst *rqstp, __be32 *p, struct nsm_args *argp)
+static int xdr_enc_unmon(struct rpc_rqst *req, __be32 *p,
+			 const struct nsm_args *argp)
 {
-	p = xdr_encode_mon_id(p, argp);
-	if (IS_ERR(p))
-		return PTR_ERR(p);
-	rqstp->rq_slen = xdr_adjust_iovec(rqstp->rq_svec, p);
-	return 0;
+	struct xdr_stream xdr;
+
+	xdr_init_encode(&xdr, &req->rq_snd_buf, p);
+	return encode_mon_id(&xdr, argp);
 }
 
-static int
-xdr_decode_stat_res(struct rpc_rqst *rqstp, __be32 *p, struct nsm_res *resp)
+static int xdr_dec_stat_res(struct rpc_rqst *rqstp, __be32 *p,
+			    struct nsm_res *resp)
 {
+	struct xdr_stream xdr;
+
+	xdr_init_decode(&xdr, &rqstp->rq_rcv_buf, p);
+	p = xdr_inline_decode(&xdr, 2 * sizeof(u32));
+	if (unlikely(p == NULL))
+		return -EIO;
 	resp->status = ntohl(*p++);
-	resp->state = ntohl(*p++);
-	dprintk("nsm: xdr_decode_stat_res status %d state %d\n",
+	resp->state = ntohl(*p);
+
+	dprintk("lockd: xdr_dec_stat_res status %d state %d\n",
 			resp->status, resp->state);
 	return 0;
 }
 
-static int
-xdr_decode_stat(struct rpc_rqst *rqstp, __be32 *p, struct nsm_res *resp)
+static int xdr_dec_stat(struct rpc_rqst *rqstp, __be32 *p,
+			struct nsm_res *resp)
 {
-	resp->state = ntohl(*p++);
+	struct xdr_stream xdr;
+
+	xdr_init_decode(&xdr, &rqstp->rq_rcv_buf, p);
+	p = xdr_inline_decode(&xdr, sizeof(u32));
+	if (unlikely(p == NULL))
+		return -EIO;
+	resp->state = ntohl(*p);
+
+	dprintk("lockd: xdr_dec_stat state %d\n", resp->state);
 	return 0;
 }
 
@@ -288,22 +567,22 @@ xdr_decode_stat(struct rpc_rqst *rqstp, __be32 *p, struct nsm_res *resp)
 #define SM_unmonres_sz	1
 
 static struct rpc_procinfo	nsm_procedures[] = {
-[SM_MON] = {
-		.p_proc		= SM_MON,
-		.p_encode	= (kxdrproc_t) xdr_encode_mon,
-		.p_decode	= (kxdrproc_t) xdr_decode_stat_res,
+[NSMPROC_MON] = {
+		.p_proc		= NSMPROC_MON,
+		.p_encode	= (kxdrproc_t)xdr_enc_mon,
+		.p_decode	= (kxdrproc_t)xdr_dec_stat_res,
 		.p_arglen	= SM_mon_sz,
 		.p_replen	= SM_monres_sz,
-		.p_statidx	= SM_MON,
+		.p_statidx	= NSMPROC_MON,
 		.p_name		= "MONITOR",
 	},
-[SM_UNMON] = {
-		.p_proc		= SM_UNMON,
-		.p_encode	= (kxdrproc_t) xdr_encode_unmon,
-		.p_decode	= (kxdrproc_t) xdr_decode_stat,
+[NSMPROC_UNMON] = {
+		.p_proc		= NSMPROC_UNMON,
+		.p_encode	= (kxdrproc_t)xdr_enc_unmon,
+		.p_decode	= (kxdrproc_t)xdr_dec_stat,
 		.p_arglen	= SM_mon_id_sz,
 		.p_replen	= SM_unmonres_sz,
-		.p_statidx	= SM_UNMON,
+		.p_statidx	= NSMPROC_UNMON,
 		.p_name		= "UNMONITOR",
 	},
 };
@@ -322,7 +601,7 @@ static struct rpc_stat		nsm_stats;
 
 static struct rpc_program	nsm_program = {
 		.name		= "statd",
-		.number		= SM_PROGRAM,
+		.number		= NSM_PROGRAM,
 		.nrvers		= ARRAY_SIZE(nsm_version),
 		.version	= nsm_version,
 		.stats		= &nsm_stats

fs/lockd/svc.c

@@ -35,7 +35,6 @@
 #include <linux/sunrpc/svcsock.h>
 #include <net/ip.h>
 #include <linux/lockd/lockd.h>
-#include <linux/lockd/sm_inter.h>
 #include <linux/nfs.h>
 
 #define NLMDBG_FACILITY		NLMDBG_SVC
@@ -53,6 +52,17 @@ static struct task_struct	*nlmsvc_task;
 static struct svc_rqst		*nlmsvc_rqst;
 unsigned long			nlmsvc_timeout;
 
+/*
+ * If the kernel has IPv6 support available, always listen for
+ * both AF_INET and AF_INET6 requests.
+ */
+#if (defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)) && \
+	defined(CONFIG_SUNRPC_REGISTER_V4)
+static const sa_family_t	nlmsvc_family = AF_INET6;
+#else	/* (CONFIG_IPV6 || CONFIG_IPV6_MODULE) && CONFIG_SUNRPC_REGISTER_V4 */
+static const sa_family_t	nlmsvc_family = AF_INET;
+#endif	/* (CONFIG_IPV6 || CONFIG_IPV6_MODULE) && CONFIG_SUNRPC_REGISTER_V4 */
+
 /*
  * These can be set at insmod time (useful for NFS as root filesystem),
  * and also changed through the sysctl interface.  -- Jamie Lokier, Aug 2003
@@ -60,7 +70,9 @@ unsigned long			nlmsvc_timeout;
 static unsigned long		nlm_grace_period;
 static unsigned long		nlm_timeout = LOCKD_DFLT_TIMEO;
 static int			nlm_udpport, nlm_tcpport;
-int				nsm_use_hostnames = 0;
+
+/* RLIM_NOFILE defaults to 1024. That seems like a reasonable default here. */
+static unsigned int		nlm_max_connections = 1024;
 
 /*
  * Constants needed for the sysctl interface.
@@ -143,6 +155,9 @@ lockd(void *vrqstp)
 		long timeout = MAX_SCHEDULE_TIMEOUT;
 		RPC_IFDEBUG(char buf[RPC_MAX_ADDRBUFLEN]);
 
+		/* update sv_maxconn if it has changed */
+		rqstp->rq_server->sv_maxconn = nlm_max_connections;
+
 		if (signalled()) {
 			flush_signals(current);
 			if (nlmsvc_ops) {
@@ -189,6 +204,19 @@ lockd(void *vrqstp)
 	return 0;
 }
 
+static int create_lockd_listener(struct svc_serv *serv, char *name,
+				 unsigned short port)
+{
+	struct svc_xprt *xprt;
+
+	xprt = svc_find_xprt(serv, name, 0, 0);
+	if (xprt == NULL)
+		return svc_create_xprt(serv, name, port, SVC_SOCK_DEFAULTS);
+
+	svc_xprt_put(xprt);
+	return 0;
+}
+
 /*
  * Ensure there are active UDP and TCP listeners for lockd.
  *
@@ -202,29 +230,23 @@ lockd(void *vrqstp)
 static int make_socks(struct svc_serv *serv)
 {
 	static int warned;
-	struct svc_xprt *xprt;
-	int err = 0;
+	int err;
 
-	xprt = svc_find_xprt(serv, "udp", 0, 0);
-	if (!xprt)
-		err = svc_create_xprt(serv, "udp", nlm_udpport,
-				      SVC_SOCK_DEFAULTS);
-	else
-		svc_xprt_put(xprt);
-	if (err >= 0) {
-		xprt = svc_find_xprt(serv, "tcp", 0, 0);
-		if (!xprt)
-			err = svc_create_xprt(serv, "tcp", nlm_tcpport,
-					      SVC_SOCK_DEFAULTS);
-		else
-			svc_xprt_put(xprt);
-	}
-	if (err >= 0) {
-		warned = 0;
-		err = 0;
-	} else if (warned++ == 0)
+	err = create_lockd_listener(serv, "udp", nlm_udpport);
+	if (err < 0)
+		goto out_err;
+
+	err = create_lockd_listener(serv, "tcp", nlm_tcpport);
+	if (err < 0)
+		goto out_err;
+
+	warned = 0;
+	return 0;
+
+out_err:
+	if (warned++ == 0)
 		printk(KERN_WARNING
-		       "lockd_up: makesock failed, error=%d\n", err);
+			"lockd_up: makesock failed, error=%d\n", err);
 	return err;
 }
 
@@ -252,7 +274,7 @@ int lockd_up(void)
 			"lockd_up: no pid, %d users??\n", nlmsvc_users);
 
 	error = -ENOMEM;
-	serv = svc_create(&nlmsvc_program, LOCKD_BUFSIZE, AF_INET, NULL);
+	serv = svc_create(&nlmsvc_program, LOCKD_BUFSIZE, nlmsvc_family, NULL);
 	if (!serv) {
 		printk(KERN_WARNING "lockd_up: create service failed\n");
 		goto out;
@@ -276,6 +298,7 @@ int lockd_up(void)
 	}
 
 	svc_sock_update_bufs(serv);
+	serv->sv_maxconn = nlm_max_connections;
 
 	nlmsvc_task = kthread_run(lockd, nlmsvc_rqst, serv->sv_name);
 	if (IS_ERR(nlmsvc_task)) {
@@ -485,6 +508,7 @@ module_param_call(nlm_udpport, param_set_port, param_get_int,
 module_param_call(nlm_tcpport, param_set_port, param_get_int,
 		  &nlm_tcpport, 0644);
 module_param(nsm_use_hostnames, bool, 0644);
+module_param(nlm_max_connections, uint, 0644);
 
 /*
  * Initialising and terminating the module.

fs/lockd/svc4proc.c

@@ -16,8 +16,6 @@
 #include <linux/nfsd/nfsd.h>
 #include <linux/lockd/lockd.h>
 #include <linux/lockd/share.h>
-#include <linux/lockd/sm_inter.h>
-
 
 #define NLMDBG_FACILITY		NLMDBG_CLIENT
 
@@ -419,8 +417,6 @@ static __be32
 nlm4svc_proc_sm_notify(struct svc_rqst *rqstp, struct nlm_reboot *argp,
 					      void	        *resp)
 {
-	struct sockaddr_in	saddr;
-
 	dprintk("lockd: SM_NOTIFY     called\n");
 
 	if (!nlm_privileged_requester(rqstp)) {
@@ -430,14 +426,7 @@ nlm4svc_proc_sm_notify(struct svc_rqst *rqstp, struct nlm_reboot *argp,
 		return rpc_system_err;
 	}
 
-	/* Obtain the host pointer for this NFS server and try to
-	 * reclaim all locks we hold on this server.
-	 */
-	memset(&saddr, 0, sizeof(saddr));
-	saddr.sin_family = AF_INET;
-	saddr.sin_addr.s_addr = argp->addr;
-	nlm_host_rebooted(&saddr, argp->mon, argp->len, argp->state);
-
+	nlm_host_rebooted(argp);
 	return rpc_success;
 }
 

fs/lockd/svcproc.c

@@ -16,8 +16,6 @@
 #include <linux/nfsd/nfsd.h>
 #include <linux/lockd/lockd.h>
 #include <linux/lockd/share.h>
-#include <linux/lockd/sm_inter.h>
-
 
 #define NLMDBG_FACILITY		NLMDBG_CLIENT
 
@@ -451,8 +449,6 @@ static __be32
 nlmsvc_proc_sm_notify(struct svc_rqst *rqstp, struct nlm_reboot *argp,
 					      void	        *resp)
 {
-	struct sockaddr_in	saddr;
-
 	dprintk("lockd: SM_NOTIFY     called\n");
 
 	if (!nlm_privileged_requester(rqstp)) {
@@ -462,14 +458,7 @@ nlmsvc_proc_sm_notify(struct svc_rqst *rqstp, struct nlm_reboot *argp,
 		return rpc_system_err;
 	}
 
-	/* Obtain the host pointer for this NFS server and try to
-	 * reclaim all locks we hold on this server.
-	 */
-	memset(&saddr, 0, sizeof(saddr));
-	saddr.sin_family = AF_INET;
-	saddr.sin_addr.s_addr = argp->addr;
-	nlm_host_rebooted(&saddr, argp->mon, argp->len, argp->state);
-
+	nlm_host_rebooted(argp);
 	return rpc_success;
 }
 

fs/lockd/svcsubs.c

@@ -17,7 +17,6 @@
 #include <linux/nfsd/export.h>
 #include <linux/lockd/lockd.h>
 #include <linux/lockd/share.h>
-#include <linux/lockd/sm_inter.h>
 #include <linux/module.h>
 #include <linux/mount.h>
 

fs/lockd/xdr.c

@@ -16,7 +16,6 @@
 #include <linux/sunrpc/svc.h>
 #include <linux/sunrpc/stats.h>
 #include <linux/lockd/lockd.h>
-#include <linux/lockd/sm_inter.h>
 
 #define NLMDBG_FACILITY		NLMDBG_XDR
 
@@ -349,8 +348,8 @@ nlmsvc_decode_reboot(struct svc_rqst *rqstp, __be32 *p, struct nlm_reboot *argp)
 	if (!(p = xdr_decode_string_inplace(p, &argp->mon, &argp->len, SM_MAXSTRLEN)))
 		return 0;
 	argp->state = ntohl(*p++);
-	/* Preserve the address in network byte order */
-	argp->addr = *p++;
+	memcpy(&argp->priv.data, p, sizeof(argp->priv.data));
+	p += XDR_QUADLEN(SM_PRIV_SIZE);
 	return xdr_argsize_check(rqstp, p);
 }
 

fs/lockd/xdr4.c

@@ -17,7 +17,6 @@
 #include <linux/sunrpc/svc.h>
 #include <linux/sunrpc/stats.h>
 #include <linux/lockd/lockd.h>
-#include <linux/lockd/sm_inter.h>
 
 #define NLMDBG_FACILITY		NLMDBG_XDR
 
@@ -356,8 +355,8 @@ nlm4svc_decode_reboot(struct svc_rqst *rqstp, __be32 *p, struct nlm_reboot *argp
 	if (!(p = xdr_decode_string_inplace(p, &argp->mon, &argp->len, SM_MAXSTRLEN)))
 		return 0;
 	argp->state = ntohl(*p++);
-	/* Preserve the address in network byte order */
-	argp->addr  = *p++;
+	memcpy(&argp->priv.data, p, sizeof(argp->priv.data));
+	p += XDR_QUADLEN(SM_PRIV_SIZE);
 	return xdr_argsize_check(rqstp, p);
 }
 

fs/nfsd/auth.c

@@ -76,10 +76,10 @@ int nfsd_setuser(struct svc_rqst *rqstp, struct svc_export *exp)
 
 	ret = set_groups(new, gi);
 	put_group_info(gi);
-	if (!ret)
+	if (ret < 0)
 		goto error;
 
-	if (new->uid)
+	if (new->fsuid)
 		new->cap_effective = cap_drop_nfsd_set(new->cap_effective);
 	else
 		new->cap_effective = cap_raise_nfsd_set(new->cap_effective,

fs/nfsd/nfs4callback.c

@@ -53,9 +53,6 @@
 #define NFSPROC4_CB_NULL 0
 #define NFSPROC4_CB_COMPOUND 1
 
-/* declarations */
-static const struct rpc_call_ops nfs4_cb_null_ops;
-
 /* Index of predefined Linux callback client operations */
 
 enum {

fs/nfsd/nfs4proc.c

@@ -946,6 +946,11 @@ encode_op:
 			nfsd4_encode_operation(resp, op);
 			status = op->status;
 		}
+
+		dprintk("nfsv4 compound op %p opcnt %d #%d: %d: status %d\n",
+			args->ops, args->opcnt, resp->opcnt, op->opnum,
+			be32_to_cpu(status));
+
 		if (cstate->replay_owner) {
 			nfs4_put_stateowner(cstate->replay_owner);
 			cstate->replay_owner = NULL;

fs/nfsd/nfs4recover.c

@@ -116,9 +116,9 @@ nfs4_make_rec_clidname(char *dname, struct xdr_netobj *clname)
 
 	md5_to_hex(dname, cksum.data);
 
-	kfree(cksum.data);
 	status = nfs_ok;
 out:
+	kfree(cksum.data);
 	crypto_free_hash(desc.tfm);
 out_no_tfm:
 	return status;

fs/nfsd/nfs4state.c

@@ -2416,6 +2416,26 @@ out:
 #define LOCK_HASH_SIZE             (1 << LOCK_HASH_BITS)
 #define LOCK_HASH_MASK             (LOCK_HASH_SIZE - 1)
 
+static inline u64
+end_offset(u64 start, u64 len)
+{
+	u64 end;
+
+	end = start + len;
+	return end >= start ? end: NFS4_MAX_UINT64;
+}
+
+/* last octet in a range */
+static inline u64
+last_byte_offset(u64 start, u64 len)
+{
+	u64 end;
+
+	BUG_ON(!len);
+	end = start + len;
+	return end > start ? end - 1: NFS4_MAX_UINT64;
+}
+
 #define lockownerid_hashval(id) \
         ((id) & LOCK_HASH_MASK)
 
@@ -2435,13 +2455,13 @@ static struct list_head lockstateid_hashtbl[STATEID_HASH_SIZE];
 static struct nfs4_stateid *
 find_stateid(stateid_t *stid, int flags)
 {
-	struct nfs4_stateid *local = NULL;
+	struct nfs4_stateid *local;
 	u32 st_id = stid->si_stateownerid;
 	u32 f_id = stid->si_fileid;
 	unsigned int hashval;
 
 	dprintk("NFSD: find_stateid flags 0x%x\n",flags);
-	if ((flags & LOCK_STATE) || (flags & RD_STATE) || (flags & WR_STATE)) {
+	if (flags & (LOCK_STATE | RD_STATE | WR_STATE)) {
 		hashval = stateid_hashval(st_id, f_id);
 		list_for_each_entry(local, &lockstateid_hashtbl[hashval], st_hash) {
 			if ((local->st_stateid.si_stateownerid == st_id) &&
@@ -2449,7 +2469,8 @@ find_stateid(stateid_t *stid, int flags)
 				return local;
 		}
 	} 
-	if ((flags & OPEN_STATE) || (flags & RD_STATE) || (flags & WR_STATE)) {
+
+	if (flags & (OPEN_STATE | RD_STATE | WR_STATE)) {
 		hashval = stateid_hashval(st_id, f_id);
 		list_for_each_entry(local, &stateid_hashtbl[hashval], st_hash) {
 			if ((local->st_stateid.si_stateownerid == st_id) &&
@@ -2518,8 +2539,8 @@ nfs4_set_lock_denied(struct file_lock *fl, struct nfsd4_lock_denied *deny)
 		deny->ld_clientid.cl_id = 0;
 	}
 	deny->ld_start = fl->fl_start;
-	deny->ld_length = ~(u64)0;
-	if (fl->fl_end != ~(u64)0)
+	deny->ld_length = NFS4_MAX_UINT64;
+	if (fl->fl_end != NFS4_MAX_UINT64)
 		deny->ld_length = fl->fl_end - fl->fl_start + 1;        
 	deny->ld_type = NFS4_READ_LT;
 	if (fl->fl_type != F_RDLCK)
@@ -2616,7 +2637,7 @@ out:
 static int
 check_lock_length(u64 offset, u64 length)
 {
-	return ((length == 0)  || ((length != ~(u64)0) &&
+	return ((length == 0)  || ((length != NFS4_MAX_UINT64) &&
 	     LOFF_OVERFLOW(offset, length)));
 }
 
@@ -2736,11 +2757,7 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	file_lock.fl_lmops = &nfsd_posix_mng_ops;
 
 	file_lock.fl_start = lock->lk_offset;
-	if ((lock->lk_length == ~(u64)0) || 
-			LOFF_OVERFLOW(lock->lk_offset, lock->lk_length))
-		file_lock.fl_end = ~(u64)0;
-	else
-		file_lock.fl_end = lock->lk_offset + lock->lk_length - 1;
+	file_lock.fl_end = last_byte_offset(lock->lk_offset, lock->lk_length);
 	nfs4_transform_lock_offset(&file_lock);
 
 	/*
@@ -2780,6 +2797,25 @@ out:
 	return status;
 }
 
+/*
+ * The NFSv4 spec allows a client to do a LOCKT without holding an OPEN,
+ * so we do a temporary open here just to get an open file to pass to
+ * vfs_test_lock.  (Arguably perhaps test_lock should be done with an
+ * inode operation.)
+ */
+static int nfsd_test_lock(struct svc_rqst *rqstp, struct svc_fh *fhp, struct file_lock *lock)
+{
+	struct file *file;
+	int err;
+
+	err = nfsd_open(rqstp, fhp, S_IFREG, NFSD_MAY_READ, &file);
+	if (err)
+		return err;
+	err = vfs_test_lock(file, lock);
+	nfsd_close(file);
+	return err;
+}
+
 /*
  * LOCKT operation
  */
@@ -2788,7 +2824,6 @@ nfsd4_lockt(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	    struct nfsd4_lockt *lockt)
 {
 	struct inode *inode;
-	struct file file;
 	struct file_lock file_lock;
 	int error;
 	__be32 status;
@@ -2839,23 +2874,12 @@ nfsd4_lockt(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	file_lock.fl_lmops = &nfsd_posix_mng_ops;
 
 	file_lock.fl_start = lockt->lt_offset;
-	if ((lockt->lt_length == ~(u64)0) || LOFF_OVERFLOW(lockt->lt_offset, lockt->lt_length))
-		file_lock.fl_end = ~(u64)0;
-	else
-		file_lock.fl_end = lockt->lt_offset + lockt->lt_length - 1;
+	file_lock.fl_end = last_byte_offset(lockt->lt_offset, lockt->lt_length);
 
 	nfs4_transform_lock_offset(&file_lock);
 
-	/* vfs_test_lock uses the struct file _only_ to resolve the inode.
-	 * since LOCKT doesn't require an OPEN, and therefore a struct
-	 * file may not exist, pass vfs_test_lock a struct file with
-	 * only the dentry:inode set.
-	 */
-	memset(&file, 0, sizeof (struct file));
-	file.f_path.dentry = cstate->current_fh.fh_dentry;
-
 	status = nfs_ok;
-	error = vfs_test_lock(&file, &file_lock);
+	error = nfsd_test_lock(rqstp, &cstate->current_fh, &file_lock);
 	if (error) {
 		status = nfserrno(error);
 		goto out;
@@ -2906,10 +2930,7 @@ nfsd4_locku(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	file_lock.fl_lmops = &nfsd_posix_mng_ops;
 	file_lock.fl_start = locku->lu_offset;
 
-	if ((locku->lu_length == ~(u64)0) || LOFF_OVERFLOW(locku->lu_offset, locku->lu_length))
-		file_lock.fl_end = ~(u64)0;
-	else
-		file_lock.fl_end = locku->lu_offset + locku->lu_length - 1;
+	file_lock.fl_end = last_byte_offset(locku->lu_offset, locku->lu_length);
 	nfs4_transform_lock_offset(&file_lock);
 
 	/*

fs/nfsd/nfs4xdr.c

@@ -1,6 +1,4 @@
 /*
- *  fs/nfs/nfs4xdr.c
- *
  *  Server-side XDR for NFSv4
  *
  *  Copyright (c) 2002 The Regents of the University of Michigan.

fs/nfsd/nfsctl.c

@@ -84,6 +84,8 @@ static ssize_t write_unexport(struct file *file, char *buf, size_t size);
 static ssize_t write_getfd(struct file *file, char *buf, size_t size);
 static ssize_t write_getfs(struct file *file, char *buf, size_t size);
 static ssize_t write_filehandle(struct file *file, char *buf, size_t size);
+static ssize_t write_unlock_ip(struct file *file, char *buf, size_t size);
+static ssize_t write_unlock_fs(struct file *file, char *buf, size_t size);
 static ssize_t write_threads(struct file *file, char *buf, size_t size);
 static ssize_t write_pool_threads(struct file *file, char *buf, size_t size);
 static ssize_t write_versions(struct file *file, char *buf, size_t size);
@@ -94,9 +96,6 @@ static ssize_t write_leasetime(struct file *file, char *buf, size_t size);
 static ssize_t write_recoverydir(struct file *file, char *buf, size_t size);
 #endif
 
-static ssize_t failover_unlock_ip(struct file *file, char *buf, size_t size);
-static ssize_t failover_unlock_fs(struct file *file, char *buf, size_t size);
-
 static ssize_t (*write_op[])(struct file *, char *, size_t) = {
 	[NFSD_Svc] = write_svc,
 	[NFSD_Add] = write_add,
@@ -106,8 +105,8 @@ static ssize_t (*write_op[])(struct file *, char *, size_t) = {
 	[NFSD_Getfd] = write_getfd,
 	[NFSD_Getfs] = write_getfs,
 	[NFSD_Fh] = write_filehandle,
-	[NFSD_FO_UnlockIP] = failover_unlock_ip,
-	[NFSD_FO_UnlockFS] = failover_unlock_fs,
+	[NFSD_FO_UnlockIP] = write_unlock_ip,
+	[NFSD_FO_UnlockFS] = write_unlock_fs,
 	[NFSD_Threads] = write_threads,
 	[NFSD_Pool_Threads] = write_pool_threads,
 	[NFSD_Versions] = write_versions,
@@ -176,10 +175,24 @@ static const struct file_operations exports_operations = {
 /*----------------------------------------------------------------------------*/
 /*
  * payload - write methods
- * If the method has a response, the response should be put in buf,
- * and the length returned.  Otherwise return 0 or and -error.
  */
 
+/**
+ * write_svc - Start kernel's NFSD server
+ *
+ * Deprecated.  /proc/fs/nfsd/threads is preferred.
+ * Function remains to support old versions of nfs-utils.
+ *
+ * Input:
+ *			buf:	struct nfsctl_svc
+ *				svc_port:	port number of this
+ *						server's listener
+ *				svc_nthreads:	number of threads to start
+ *			size:	size in bytes of passed in nfsctl_svc
+ * Output:
+ *	On success:	returns zero
+ *	On error:	return code is negative errno value
+ */
 static ssize_t write_svc(struct file *file, char *buf, size_t size)
 {
 	struct nfsctl_svc *data;
@@ -189,6 +202,30 @@ static ssize_t write_svc(struct file *file, char *buf, size_t size)
 	return nfsd_svc(data->svc_port, data->svc_nthreads);
 }
 
+/**
+ * write_add - Add or modify client entry in auth unix cache
+ *
+ * Deprecated.  /proc/net/rpc/auth.unix.ip is preferred.
+ * Function remains to support old versions of nfs-utils.
+ *
+ * Input:
+ *			buf:	struct nfsctl_client
+ *				cl_ident:	'\0'-terminated C string
+ *						containing domain name
+ *						of client
+ *				cl_naddr:	no. of items in cl_addrlist
+ *				cl_addrlist:	array of client addresses
+ *				cl_fhkeytype:	ignored
+ *				cl_fhkeylen:	ignored
+ *				cl_fhkey:	ignored
+ *			size:	size in bytes of passed in nfsctl_client
+ * Output:
+ *	On success:	returns zero
+ *	On error:	return code is negative errno value
+ *
+ * Note: Only AF_INET client addresses are passed in, since
+ * nfsctl_client.cl_addrlist contains only in_addr fields for addresses.
+ */
 static ssize_t write_add(struct file *file, char *buf, size_t size)
 {
 	struct nfsctl_client *data;
@@ -198,6 +235,30 @@ static ssize_t write_add(struct file *file, char *buf, size_t size)
 	return exp_addclient(data);
 }
 
+/**
+ * write_del - Remove client from auth unix cache
+ *
+ * Deprecated.  /proc/net/rpc/auth.unix.ip is preferred.
+ * Function remains to support old versions of nfs-utils.
+ *
+ * Input:
+ *			buf:	struct nfsctl_client
+ *				cl_ident:	'\0'-terminated C string
+ *						containing domain name
+ *						of client
+ *				cl_naddr:	ignored
+ *				cl_addrlist:	ignored
+ *				cl_fhkeytype:	ignored
+ *				cl_fhkeylen:	ignored
+ *				cl_fhkey:	ignored
+ *			size:	size in bytes of passed in nfsctl_client
+ * Output:
+ *	On success:	returns zero
+ *	On error:	return code is negative errno value
+ *
+ * Note: Only AF_INET client addresses are passed in, since
+ * nfsctl_client.cl_addrlist contains only in_addr fields for addresses.
+ */
 static ssize_t write_del(struct file *file, char *buf, size_t size)
 {
 	struct nfsctl_client *data;
@@ -207,6 +268,33 @@ static ssize_t write_del(struct file *file, char *buf, size_t size)
 	return exp_delclient(data);
 }
 
+/**
+ * write_export - Export part or all of a local file system
+ *
+ * Deprecated.  /proc/net/rpc/{nfsd.export,nfsd.fh} are preferred.
+ * Function remains to support old versions of nfs-utils.
+ *
+ * Input:
+ *			buf:	struct nfsctl_export
+ *				ex_client:	'\0'-terminated C string
+ *						containing domain name
+ *						of client allowed to access
+ *						this export
+ *				ex_path:	'\0'-terminated C string
+ *						containing pathname of
+ *						directory in local file system
+ *				ex_dev:		fsid to use for this export
+ *				ex_ino:		ignored
+ *				ex_flags:	export flags for this export
+ *				ex_anon_uid:	UID to use for anonymous
+ *						requests
+ *				ex_anon_gid:	GID to use for anonymous
+ *						requests
+ *			size:	size in bytes of passed in nfsctl_export
+ * Output:
+ *	On success:	returns zero
+ *	On error:	return code is negative errno value
+ */
 static ssize_t write_export(struct file *file, char *buf, size_t size)
 {
 	struct nfsctl_export *data;
@@ -216,6 +304,31 @@ static ssize_t write_export(struct file *file, char *buf, size_t size)
 	return exp_export(data);
 }
 
+/**
+ * write_unexport - Unexport a previously exported file system
+ *
+ * Deprecated.  /proc/net/rpc/{nfsd.export,nfsd.fh} are preferred.
+ * Function remains to support old versions of nfs-utils.
+ *
+ * Input:
+ *			buf:	struct nfsctl_export
+ *				ex_client:	'\0'-terminated C string
+ *						containing domain name
+ *						of client no longer allowed
+ *						to access this export
+ *				ex_path:	'\0'-terminated C string
+ *						containing pathname of
+ *						directory in local file system
+ *				ex_dev:		ignored
+ *				ex_ino:		ignored
+ *				ex_flags:	ignored
+ *				ex_anon_uid:	ignored
+ *				ex_anon_gid:	ignored
+ *			size:	size in bytes of passed in nfsctl_export
+ * Output:
+ *	On success:	returns zero
+ *	On error:	return code is negative errno value
+ */
 static ssize_t write_unexport(struct file *file, char *buf, size_t size)
 {
 	struct nfsctl_export *data;
@@ -226,6 +339,30 @@ static ssize_t write_unexport(struct file *file, char *buf, size_t size)
 	return exp_unexport(data);
 }
 
+/**
+ * write_getfs - Get a variable-length NFS file handle by path
+ *
+ * Deprecated.  /proc/fs/nfsd/filehandle is preferred.
+ * Function remains to support old versions of nfs-utils.
+ *
+ * Input:
+ *			buf:	struct nfsctl_fsparm
+ *				gd_addr:	socket address of client
+ *				gd_path:	'\0'-terminated C string
+ *						containing pathname of
+ *						directory in local file system
+ *				gd_maxlen:	maximum size of returned file
+ *						handle
+ *			size:	size in bytes of passed in nfsctl_fsparm
+ * Output:
+ *	On success:	passed-in buffer filled with a knfsd_fh structure
+ *			(a variable-length raw NFS file handle);
+ *			return code is the size in bytes of the file handle
+ *	On error:	return code is negative errno value
+ *
+ * Note: Only AF_INET client addresses are passed in, since gd_addr
+ * is the same size as a struct sockaddr_in.
+ */
 static ssize_t write_getfs(struct file *file, char *buf, size_t size)
 {
 	struct nfsctl_fsparm *data;
@@ -265,6 +402,29 @@ static ssize_t write_getfs(struct file *file, char *buf, size_t size)
 	return err;
 }
 
+/**
+ * write_getfd - Get a fixed-length NFS file handle by path (used by mountd)
+ *
+ * Deprecated.  /proc/fs/nfsd/filehandle is preferred.
+ * Function remains to support old versions of nfs-utils.
+ *
+ * Input:
+ *			buf:	struct nfsctl_fdparm
+ *				gd_addr:	socket address of client
+ *				gd_path:	'\0'-terminated C string
+ *						containing pathname of
+ *						directory in local file system
+ *				gd_version:	fdparm structure version
+ *			size:	size in bytes of passed in nfsctl_fdparm
+ * Output:
+ *	On success:	passed-in buffer filled with nfsctl_res
+ *			(a fixed-length raw NFS file handle);
+ *			return code is the size in bytes of the file handle
+ *	On error:	return code is negative errno value
+ *
+ * Note: Only AF_INET client addresses are passed in, since gd_addr
+ * is the same size as a struct sockaddr_in.
+ */
 static ssize_t write_getfd(struct file *file, char *buf, size_t size)
 {
 	struct nfsctl_fdparm *data;
@@ -309,7 +469,23 @@ static ssize_t write_getfd(struct file *file, char *buf, size_t size)
 	return err;
 }
 
-static ssize_t failover_unlock_ip(struct file *file, char *buf, size_t size)
+/**
+ * write_unlock_ip - Release all locks used by a client
+ *
+ * Experimental.
+ *
+ * Input:
+ *			buf:	'\n'-terminated C string containing a
+ *				presentation format IPv4 address
+ *			size:	length of C string in @buf
+ * Output:
+ *	On success:	returns zero if all specified locks were released;
+ *			returns one if one or more locks were not released
+ *	On error:	return code is negative errno value
+ *
+ * Note: Only AF_INET client addresses are passed in
+ */
+static ssize_t write_unlock_ip(struct file *file, char *buf, size_t size)
 {
 	struct sockaddr_in sin = {
 		.sin_family	= AF_INET,
@@ -339,7 +515,21 @@ static ssize_t failover_unlock_ip(struct file *file, char *buf, size_t size)
 	return nlmsvc_unlock_all_by_ip((struct sockaddr *)&sin);
 }
 
-static ssize_t failover_unlock_fs(struct file *file, char *buf, size_t size)
+/**
+ * write_unlock_fs - Release all locks on a local file system
+ *
+ * Experimental.
+ *
+ * Input:
+ *			buf:	'\n'-terminated C string containing the
+ *				absolute pathname of a local file system
+ *			size:	length of C string in @buf
+ * Output:
+ *	On success:	returns zero if all specified locks were released;
+ *			returns one if one or more locks were not released
+ *	On error:	return code is negative errno value
+ */
+static ssize_t write_unlock_fs(struct file *file, char *buf, size_t size)
 {
 	struct path path;
 	char *fo_path;
@@ -360,21 +550,44 @@ static ssize_t failover_unlock_fs(struct file *file, char *buf, size_t size)
 	if (error)
 		return error;
 
+	/*
+	 * XXX: Needs better sanity checking.  Otherwise we could end up
+	 * releasing locks on the wrong file system.
+	 *
+	 * For example:
+	 * 1.  Does the path refer to a directory?
+	 * 2.  Is that directory a mount point, or
+	 * 3.  Is that directory the root of an exported file system?
+	 */
 	error = nlmsvc_unlock_all_by_sb(path.mnt->mnt_sb);
 
 	path_put(&path);
 	return error;
 }
 
+/**
+ * write_filehandle - Get a variable-length NFS file handle by path
+ *
+ * On input, the buffer contains a '\n'-terminated C string comprised of
+ * three alphanumeric words separated by whitespace.  The string may
+ * contain escape sequences.
+ *
+ * Input:
+ *			buf:
+ *				domain:		client domain name
+ *				path:		export pathname
+ *				maxsize:	numeric maximum size of
+ *						@buf
+ *			size:	length of C string in @buf
+ * Output:
+ *	On success:	passed-in buffer filled with '\n'-terminated C
+ *			string containing a ASCII hex text version
+ *			of the NFS file handle;
+ *			return code is the size in bytes of the string
+ *	On error:	return code is negative errno value
+ */
 static ssize_t write_filehandle(struct file *file, char *buf, size_t size)
 {
-	/* request is:
-	 *   domain path maxsize
-	 * response is
-	 *   filehandle
-	 *
-	 * qword quoting is used, so filehandle will be \x....
-	 */
 	char *dname, *path;
 	int uninitialized_var(maxsize);
 	char *mesg = buf;
@@ -391,11 +604,13 @@ static ssize_t write_filehandle(struct file *file, char *buf, size_t size)
 
 	dname = mesg;
 	len = qword_get(&mesg, dname, size);
-	if (len <= 0) return -EINVAL;
+	if (len <= 0)
+		return -EINVAL;
 	
 	path = dname+len+1;
 	len = qword_get(&mesg, path, size);
-	if (len <= 0) return -EINVAL;
+	if (len <= 0)
+		return -EINVAL;
 
 	len = get_int(&mesg, &maxsize);
 	if (len)
@@ -419,17 +634,43 @@ static ssize_t write_filehandle(struct file *file, char *buf, size_t size)
 	if (len)
 		return len;
 	
-	mesg = buf; len = SIMPLE_TRANSACTION_LIMIT;
+	mesg = buf;
+	len = SIMPLE_TRANSACTION_LIMIT;
 	qword_addhex(&mesg, &len, (char*)&fh.fh_base, fh.fh_size);
 	mesg[-1] = '\n';
 	return mesg - buf;	
 }
 
+/**
+ * write_threads - Start NFSD, or report the current number of running threads
+ *
+ * Input:
+ *			buf:		ignored
+ *			size:		zero
+ * Output:
+ *	On success:	passed-in buffer filled with '\n'-terminated C
+ *			string numeric value representing the number of
+ *			running NFSD threads;
+ *			return code is the size in bytes of the string
+ *	On error:	return code is zero
+ *
+ * OR
+ *
+ * Input:
+ *			buf:		C string containing an unsigned
+ *					integer value representing the
+ *					number of NFSD threads to start
+ *			size:		non-zero length of C string in @buf
+ * Output:
+ *	On success:	NFS service is started;
+ *			passed-in buffer filled with '\n'-terminated C
+ *			string numeric value representing the number of
+ *			running NFSD threads;
+ *			return code is the size in bytes of the string
+ *	On error:	return code is zero or a negative errno value
+ */
 static ssize_t write_threads(struct file *file, char *buf, size_t size)
 {
-	/* if size > 0, look for a number of threads and call nfsd_svc
-	 * then write out number of threads as reply
-	 */
 	char *mesg = buf;
 	int rv;
 	if (size > 0) {
@@ -437,9 +678,9 @@ static ssize_t write_threads(struct file *file, char *buf, size_t size)
 		rv = get_int(&mesg, &newthreads);
 		if (rv)
 			return rv;
-		if (newthreads <0)
+		if (newthreads < 0)
 			return -EINVAL;
-		rv = nfsd_svc(2049, newthreads);
+		rv = nfsd_svc(NFS_PORT, newthreads);
 		if (rv)
 			return rv;
 	}
@@ -447,6 +688,28 @@ static ssize_t write_threads(struct file *file, char *buf, size_t size)
 	return strlen(buf);
 }
 
+/**
+ * write_pool_threads - Set or report the current number of threads per pool
+ *
+ * Input:
+ *			buf:		ignored
+ *			size:		zero
+ *
+ * OR
+ *
+ * Input:
+ * 			buf:		C string containing whitespace-
+ * 					separated unsigned integer values
+ *					representing the number of NFSD
+ *					threads to start in each pool
+ *			size:		non-zero length of C string in @buf
+ * Output:
+ *	On success:	passed-in buffer filled with '\n'-terminated C
+ *			string containing integer values representing the
+ *			number of NFSD threads in each pool;
+ *			return code is the size in bytes of the string
+ *	On error:	return code is zero or a negative errno value
+ */
 static ssize_t write_pool_threads(struct file *file, char *buf, size_t size)
 {
 	/* if size > 0, look for an array of number of threads per node
@@ -517,10 +780,6 @@ out_free:
 
 static ssize_t __write_versions(struct file *file, char *buf, size_t size)
 {
-	/*
-	 * Format:
-	 *   [-/+]vers [-/+]vers ...
-	 */
 	char *mesg = buf;
 	char *vers, sign;
 	int len, num;
@@ -578,6 +837,38 @@ static ssize_t __write_versions(struct file *file, char *buf, size_t size)
 	return len;
 }
 
+/**
+ * write_versions - Set or report the available NFS protocol versions
+ *
+ * Input:
+ *			buf:		ignored
+ *			size:		zero
+ * Output:
+ *	On success:	passed-in buffer filled with '\n'-terminated C
+ *			string containing positive or negative integer
+ *			values representing the current status of each
+ *			protocol version;
+ *			return code is the size in bytes of the string
+ *	On error:	return code is zero or a negative errno value
+ *
+ * OR
+ *
+ * Input:
+ * 			buf:		C string containing whitespace-
+ * 					separated positive or negative
+ * 					integer values representing NFS
+ * 					protocol versions to enable ("+n")
+ * 					or disable ("-n")
+ *			size:		non-zero length of C string in @buf
+ * Output:
+ *	On success:	status of zero or more protocol versions has
+ *			been updated; passed-in buffer filled with
+ *			'\n'-terminated C string containing positive
+ *			or negative integer values representing the
+ *			current status of each protocol version;
+ *			return code is the size in bytes of the string
+ *	On error:	return code is zero or a negative errno value
+ */
 static ssize_t write_versions(struct file *file, char *buf, size_t size)
 {
 	ssize_t rv;
@@ -687,6 +978,75 @@ static ssize_t __write_ports(struct file *file, char *buf, size_t size)
 	return -EINVAL;
 }
 
+/**
+ * write_ports - Pass a socket file descriptor or transport name to listen on
+ *
+ * Input:
+ *			buf:		ignored
+ *			size:		zero
+ * Output:
+ *	On success:	passed-in buffer filled with a '\n'-terminated C
+ *			string containing a whitespace-separated list of
+ *			named NFSD listeners;
+ *			return code is the size in bytes of the string
+ *	On error:	return code is zero or a negative errno value
+ *
+ * OR
+ *
+ * Input:
+ *			buf:		C string containing an unsigned
+ *					integer value representing a bound
+ *					but unconnected socket that is to be
+ *					used as an NFSD listener
+ *			size:		non-zero length of C string in @buf
+ * Output:
+ *	On success:	NFS service is started;
+ *			passed-in buffer filled with a '\n'-terminated C
+ *			string containing a unique alphanumeric name of
+ *			the listener;
+ *			return code is the size in bytes of the string
+ *	On error:	return code is a negative errno value
+ *
+ * OR
+ *
+ * Input:
+ *			buf:		C string containing a "-" followed
+ *					by an integer value representing a
+ *					previously passed in socket file
+ *					descriptor
+ *			size:		non-zero length of C string in @buf
+ * Output:
+ *	On success:	NFS service no longer listens on that socket;
+ *			passed-in buffer filled with a '\n'-terminated C
+ *			string containing a unique name of the listener;
+ *			return code is the size in bytes of the string
+ *	On error:	return code is a negative errno value
+ *
+ * OR
+ *
+ * Input:
+ *			buf:		C string containing a transport
+ *					name and an unsigned integer value
+ *					representing the port to listen on,
+ *					separated by whitespace
+ *			size:		non-zero length of C string in @buf
+ * Output:
+ *	On success:	returns zero; NFS service is started
+ *	On error:	return code is a negative errno value
+ *
+ * OR
+ *
+ * Input:
+ *			buf:		C string containing a "-" followed
+ *					by a transport name and an unsigned
+ *					integer value representing the port
+ *					to listen on, separated by whitespace
+ *			size:		non-zero length of C string in @buf
+ * Output:
+ *	On success:	returns zero; NFS service no longer listens
+ *			on that transport
+ *	On error:	return code is a negative errno value
+ */
 static ssize_t write_ports(struct file *file, char *buf, size_t size)
 {
 	ssize_t rv;
@@ -700,6 +1060,27 @@ static ssize_t write_ports(struct file *file, char *buf, size_t size)
 
 int nfsd_max_blksize;
 
+/**
+ * write_maxblksize - Set or report the current NFS blksize
+ *
+ * Input:
+ *			buf:		ignored
+ *			size:		zero
+ *
+ * OR
+ *
+ * Input:
+ * 			buf:		C string containing an unsigned
+ * 					integer value representing the new
+ * 					NFS blksize
+ *			size:		non-zero length of C string in @buf
+ * Output:
+ *	On success:	passed-in buffer filled with '\n'-terminated C string
+ *			containing numeric value of the current NFS blksize
+ *			setting;
+ *			return code is the size in bytes of the string
+ *	On error:	return code is zero or a negative errno value
+ */
 static ssize_t write_maxblksize(struct file *file, char *buf, size_t size)
 {
 	char *mesg = buf;
@@ -752,6 +1133,27 @@ static ssize_t __write_leasetime(struct file *file, char *buf, size_t size)
 	return strlen(buf);
 }
 
+/**
+ * write_leasetime - Set or report the current NFSv4 lease time
+ *
+ * Input:
+ *			buf:		ignored
+ *			size:		zero
+ *
+ * OR
+ *
+ * Input:
+ *			buf:		C string containing an unsigned
+ *					integer value representing the new
+ *					NFSv4 lease expiry time
+ *			size:		non-zero length of C string in @buf
+ * Output:
+ *	On success:	passed-in buffer filled with '\n'-terminated C
+ *			string containing unsigned integer value of the
+ *			current lease expiry time;
+ *			return code is the size in bytes of the string
+ *	On error:	return code is zero or a negative errno value
+ */
 static ssize_t write_leasetime(struct file *file, char *buf, size_t size)
 {
 	ssize_t rv;
@@ -788,6 +1190,27 @@ static ssize_t __write_recoverydir(struct file *file, char *buf, size_t size)
 	return strlen(buf);
 }
 
+/**
+ * write_recoverydir - Set or report the pathname of the recovery directory
+ *
+ * Input:
+ *			buf:		ignored
+ *			size:		zero
+ *
+ * OR
+ *
+ * Input:
+ *			buf:		C string containing the pathname
+ *					of the directory on a local file
+ *					system containing permanent NFSv4
+ *					recovery data
+ *			size:		non-zero length of C string in @buf
+ * Output:
+ *	On success:	passed-in buffer filled with '\n'-terminated C string
+ *			containing the current recovery pathname setting;
+ *			return code is the size in bytes of the string
+ *	On error:	return code is zero or a negative errno value
+ */
 static ssize_t write_recoverydir(struct file *file, char *buf, size_t size)
 {
 	ssize_t rv;

fs/nfsd/nfsfh.c

@@ -258,14 +258,32 @@ out:
 	return error;
 }
 
-/*
- * Perform sanity checks on the dentry in a client's file handle.
+/**
+ * fh_verify - filehandle lookup and access checking
+ * @rqstp: pointer to current rpc request
+ * @fhp: filehandle to be verified
+ * @type: expected type of object pointed to by filehandle
+ * @access: type of access needed to object
+ *
+ * Look up a dentry from the on-the-wire filehandle, check the client's
+ * access to the export, and set the current task's credentials.
+ *
+ * Regardless of success or failure of fh_verify(), fh_put() should be
+ * called on @fhp when the caller is finished with the filehandle.
  *
- * Note that the file handle dentry may need to be freed even after
- * an error return.
+ * fh_verify() may be called multiple times on a given filehandle, for
+ * example, when processing an NFSv4 compound.  The first call will look
+ * up a dentry using the on-the-wire filehandle.  Subsequent calls will
+ * skip the lookup and just perform the other checks and possibly change
+ * the current task's credentials.
  *
- * This is only called at the start of an nfsproc call, so fhp points to
- * a svc_fh which is all 0 except for the over-the-wire file handle.
+ * @type specifies the type of object expected using one of the S_IF*
+ * constants defined in include/linux/stat.h.  The caller may use zero
+ * to indicate that it doesn't care, or a negative integer to indicate
+ * that it expects something not of the given type.
+ *
+ * @access is formed from the NFSD_MAY_* constants defined in
+ * include/linux/nfsd/nfsd.h.
  */
 __be32
 fh_verify(struct svc_rqst *rqstp, struct svc_fh *fhp, int type, int access)
@@ -466,6 +484,8 @@ fh_compose(struct svc_fh *fhp, struct svc_export *exp, struct dentry *dentry,
 				goto retry;
 			break;
 		}
+	} else if (exp->ex_flags & NFSEXP_FSID) {
+		fsid_type = FSID_NUM;
 	} else if (exp->ex_uuid) {
 		if (fhp->fh_maxsize >= 64) {
 			if (root_export)
@@ -478,9 +498,7 @@ fh_compose(struct svc_fh *fhp, struct svc_export *exp, struct dentry *dentry,
 			else
 				fsid_type = FSID_UUID4_INUM;
 		}
-	} else if (exp->ex_flags & NFSEXP_FSID)
-		fsid_type = FSID_NUM;
-	else if (!old_valid_dev(ex_dev))
+	} else if (!old_valid_dev(ex_dev))
 		/* for newer device numbers, we must use a newer fsid format */
 		fsid_type = FSID_ENCODE_DEV;
 	else

fs/nfsd/nfsproc.c

@@ -622,6 +622,7 @@ nfserrno (int errno)
 		{ nfserr_badname, -ESRCH },
 		{ nfserr_io, -ETXTBSY },
 		{ nfserr_notsupp, -EOPNOTSUPP },
+		{ nfserr_toosmall, -ETOOSMALL },
 	};
 	int	i;
 

fs/nfsd/vfs.c

@@ -744,16 +744,44 @@ nfsd_close(struct file *filp)
 	fput(filp);
 }
 
+/*
+ * Sync a file
+ * As this calls fsync (not fdatasync) there is no need for a write_inode
+ * after it.
+ */
+static inline int nfsd_dosync(struct file *filp, struct dentry *dp,
+			      const struct file_operations *fop)
+{
+	struct inode *inode = dp->d_inode;
+	int (*fsync) (struct file *, struct dentry *, int);
+	int err;
+
+	err = filemap_fdatawrite(inode->i_mapping);
+	if (err == 0 && fop && (fsync = fop->fsync))
+		err = fsync(filp, dp, 0);
+	if (err == 0)
+		err = filemap_fdatawait(inode->i_mapping);
+
+	return err;
+}
+
 static int
 nfsd_sync(struct file *filp)
 {
-	return vfs_fsync(filp, filp->f_path.dentry, 0);
+        int err;
+	struct inode *inode = filp->f_path.dentry->d_inode;
+	dprintk("nfsd: sync file %s\n", filp->f_path.dentry->d_name.name);
+	mutex_lock(&inode->i_mutex);
+	err=nfsd_dosync(filp, filp->f_path.dentry, filp->f_op);
+	mutex_unlock(&inode->i_mutex);
+
+	return err;
 }
 
 int
-nfsd_sync_dir(struct dentry *dentry)
+nfsd_sync_dir(struct dentry *dp)
 {
-	return vfs_fsync(NULL, dentry, 0);
+	return nfsd_dosync(NULL, dp, dp->d_inode->i_fop);
 }
 
 /*

include/linux/lockd/lockd.h

@@ -43,8 +43,8 @@ struct nlm_host {
 	struct sockaddr_storage	h_addr;		/* peer address */
 	size_t			h_addrlen;
 	struct sockaddr_storage	h_srcaddr;	/* our address (optional) */
-	struct rpc_clnt	*	h_rpcclnt;	/* RPC client to talk to peer */
-	char *			h_name;		/* remote hostname */
+	struct rpc_clnt		*h_rpcclnt;	/* RPC client to talk to peer */
+	char			*h_name;		/* remote hostname */
 	u32			h_version;	/* interface version */
 	unsigned short		h_proto;	/* transport proto */
 	unsigned short		h_reclaiming : 1,
@@ -64,21 +64,29 @@ struct nlm_host {
 	spinlock_t		h_lock;
 	struct list_head	h_granted;	/* Locks in GRANTED state */
 	struct list_head	h_reclaim;	/* Locks in RECLAIM state */
-	struct nsm_handle *	h_nsmhandle;	/* NSM status handle */
-
-	char			h_addrbuf[48],	/* address eyecatchers */
-				h_srcaddrbuf[48];
+	struct nsm_handle	*h_nsmhandle;	/* NSM status handle */
+	char			*h_addrbuf;	/* address eyecatcher */
 };
 
+/*
+ * The largest string sm_addrbuf should hold is a full-size IPv6 address
+ * (no "::" anywhere) with a scope ID.  The buffer size is computed to
+ * hold eight groups of colon-separated four-hex-digit numbers, a
+ * percent sign, a scope id (at most 32 bits, in decimal), and NUL.
+ */
+#define NSM_ADDRBUF		((8 * 4 + 7) + (1 + 10) + 1)
+
 struct nsm_handle {
 	struct list_head	sm_link;
 	atomic_t		sm_count;
-	char *			sm_name;
+	char			*sm_mon_name;
+	char			*sm_name;
 	struct sockaddr_storage	sm_addr;
 	size_t			sm_addrlen;
 	unsigned int		sm_monitored : 1,
 				sm_sticky : 1;	/* don't unmonitor */
-	char			sm_addrbuf[48];	/* address eyecatcher */
+	struct nsm_private	sm_priv;
+	char			sm_addrbuf[NSM_ADDRBUF];
 };
 
 /*
@@ -104,16 +112,6 @@ static inline struct sockaddr *nlm_srcaddr(const struct nlm_host *host)
 	return (struct sockaddr *)&host->h_srcaddr;
 }
 
-static inline struct sockaddr_in *nsm_addr_in(const struct nsm_handle *handle)
-{
-	return (struct sockaddr_in *)&handle->sm_addr;
-}
-
-static inline struct sockaddr *nsm_addr(const struct nsm_handle *handle)
-{
-	return (struct sockaddr *)&handle->sm_addr;
-}
-
 /*
  * Map an fl_owner_t into a unique 32-bit "pid"
  */
@@ -197,6 +195,7 @@ extern struct svc_procedure	nlmsvc_procedures4[];
 extern int			nlmsvc_grace_period;
 extern unsigned long		nlmsvc_timeout;
 extern int			nsm_use_hostnames;
+extern int			nsm_local_state;
 
 /*
  * Lockd client functions
@@ -231,10 +230,20 @@ void		  nlm_rebind_host(struct nlm_host *);
 struct nlm_host * nlm_get_host(struct nlm_host *);
 void		  nlm_release_host(struct nlm_host *);
 void		  nlm_shutdown_hosts(void);
-extern void	  nlm_host_rebooted(const struct sockaddr_in *, const char *,
-					unsigned int, u32);
-void		  nsm_release(struct nsm_handle *);
+void		  nlm_host_rebooted(const struct nlm_reboot *);
 
+/*
+ * Host monitoring
+ */
+int		  nsm_monitor(const struct nlm_host *host);
+void		  nsm_unmonitor(const struct nlm_host *host);
+
+struct nsm_handle *nsm_get_handle(const struct sockaddr *sap,
+					const size_t salen,
+					const char *hostname,
+					const size_t hostname_len);
+struct nsm_handle *nsm_reboot_lookup(const struct nlm_reboot *info);
+void		  nsm_release(struct nsm_handle *nsm);
 
 /*
  * This is used in garbage collection and resource reclaim
@@ -282,16 +291,25 @@ static inline struct inode *nlmsvc_file_inode(struct nlm_file *file)
 static inline int __nlm_privileged_request4(const struct sockaddr *sap)
 {
 	const struct sockaddr_in *sin = (struct sockaddr_in *)sap;
-	return (sin->sin_addr.s_addr == htonl(INADDR_LOOPBACK)) &&
-			(ntohs(sin->sin_port) < 1024);
+
+	if (ntohs(sin->sin_port) > 1023)
+		return 0;
+
+	return ipv4_is_loopback(sin->sin_addr.s_addr);
 }
 
 #if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
 static inline int __nlm_privileged_request6(const struct sockaddr *sap)
 {
 	const struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *)sap;
-	return (ipv6_addr_type(&sin6->sin6_addr) & IPV6_ADDR_LOOPBACK) &&
-			(ntohs(sin6->sin6_port) < 1024);
+
+	if (ntohs(sin6->sin6_port) > 1023)
+		return 0;
+
+	if (ipv6_addr_type(&sin6->sin6_addr) & IPV6_ADDR_MAPPED)
+		return ipv4_is_loopback(sin6->sin6_addr.s6_addr32[3]);
+
+	return ipv6_addr_type(&sin6->sin6_addr) & IPV6_ADDR_LOOPBACK;
 }
 #else	/* defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) */
 static inline int __nlm_privileged_request6(const struct sockaddr *sap)

include/linux/lockd/sm_inter.h

@@ -1,48 +0,0 @@
-/*
- * linux/include/linux/lockd/sm_inter.h
- *
- * Declarations for the kernel statd client.
- *
- * Copyright (C) 1996, Olaf Kirch <okir@monad.swb.de>
- */
-
-#ifndef LINUX_LOCKD_SM_INTER_H
-#define LINUX_LOCKD_SM_INTER_H
-
-#define SM_PROGRAM	100024
-#define SM_VERSION	1
-#define SM_STAT		1
-#define SM_MON		2
-#define SM_UNMON	3
-#define SM_UNMON_ALL	4
-#define SM_SIMU_CRASH	5
-#define SM_NOTIFY	6
-
-#define SM_MAXSTRLEN	1024
-#define SM_PRIV_SIZE	16
-
-/*
- * Arguments for all calls to statd
- */
-struct nsm_args {
-	__be32		addr;		/* remote address */
-	u32		prog;		/* RPC callback info */
-	u32		vers;
-	u32		proc;
-
-	char *		mon_name;
-};
-
-/*
- * Result returned by statd
- */
-struct nsm_res {
-	u32		status;
-	u32		state;
-};
-
-int		nsm_monitor(struct nlm_host *);
-int		nsm_unmonitor(struct nlm_host *);
-extern int	nsm_local_state;
-
-#endif /* LINUX_LOCKD_SM_INTER_H */

include/linux/lockd/xdr.h

@@ -13,6 +13,13 @@
 #include <linux/nfs.h>
 #include <linux/sunrpc/xdr.h>
 
+#define SM_MAXSTRLEN		1024
+#define SM_PRIV_SIZE		16
+
+struct nsm_private {
+	unsigned char		data[SM_PRIV_SIZE];
+};
+
 struct svc_rqst;
 
 #define NLM_MAXCOOKIELEN    	32
@@ -77,10 +84,10 @@ struct nlm_res {
  * statd callback when client has rebooted
  */
 struct nlm_reboot {
-	char *		mon;
-	unsigned int	len;
-	u32		state;
-	__be32		addr;
+	char			*mon;
+	unsigned int		len;
+	u32			state;
+	struct nsm_private	priv;
 };
 
 /*

include/linux/nfs4.h

@@ -88,6 +88,8 @@
 #define NFS4_ACE_GENERIC_EXECUTE              0x001200A0
 #define NFS4_ACE_MASK_ALL                     0x001F01FF
 
+#define NFS4_MAX_UINT64	(~(u64)0)
+
 enum nfs4_acl_whotype {
 	NFS4_ACL_WHO_NAMED = 0,
 	NFS4_ACL_WHO_OWNER,

include/linux/nfsd/nfsd.h

@@ -23,7 +23,6 @@
 /*
  * nfsd version
  */
-#define NFSD_VERSION		"0.5"
 #define NFSD_SUPPORTED_MINOR_VERSION	0
 
 /*

include/linux/nfsd/nfsfh.h

@@ -68,6 +68,10 @@ struct nfs_fhbase_old {
  *     1  - 4 byte user specified identifier
  *     2  - 4 byte major, 4 byte minor, 4 byte inode number - DEPRECATED
  *     3  - 4 byte device id, encoded for user-space, 4 byte inode number
+ *     4  - 4 byte inode number and 4 byte uuid
+ *     5  - 8 byte uuid
+ *     6  - 16 byte uuid
+ *     7  - 8 byte inode number and 16 byte uuid
  *
  * The fileid_type identified how the file within the filesystem is encoded.
  * This is (will be) passed to, and set by, the underlying filesystem if it supports

include/linux/sunrpc/svc.h

@@ -58,10 +58,13 @@ struct svc_serv {
 	struct svc_stat *	sv_stats;	/* RPC statistics */
 	spinlock_t		sv_lock;
 	unsigned int		sv_nrthreads;	/* # of server threads */
+	unsigned int		sv_maxconn;	/* max connections allowed or
+						 * '0' causing max to be based
+						 * on number of threads. */
+
 	unsigned int		sv_max_payload;	/* datagram payload size */
 	unsigned int		sv_max_mesg;	/* max_payload + 1 page for overheads */
 	unsigned int		sv_xdrsize;	/* XDR buffer size */
-
 	struct list_head	sv_permsocks;	/* all permanent sockets */
 	struct list_head	sv_tempsocks;	/* all temporary sockets */
 	int			sv_tmpcnt;	/* count of temporary sockets */

net/sunrpc/cache.c

@@ -98,7 +98,7 @@ struct cache_head *sunrpc_cache_lookup(struct cache_detail *detail,
 
 	return new;
 }
-EXPORT_SYMBOL(sunrpc_cache_lookup);
+EXPORT_SYMBOL_GPL(sunrpc_cache_lookup);
 
 
 static void queue_loose(struct cache_detail *detail, struct cache_head *ch);
@@ -173,7 +173,7 @@ struct cache_head *sunrpc_cache_update(struct cache_detail *detail,
 	cache_put(old, detail);
 	return tmp;
 }
-EXPORT_SYMBOL(sunrpc_cache_update);
+EXPORT_SYMBOL_GPL(sunrpc_cache_update);
 
 static int cache_make_upcall(struct cache_detail *detail, struct cache_head *h);
 /*
@@ -245,7 +245,7 @@ int cache_check(struct cache_detail *detail,
 		cache_put(h, detail);
 	return rv;
 }
-EXPORT_SYMBOL(cache_check);
+EXPORT_SYMBOL_GPL(cache_check);
 
 /*
  * caches need to be periodically cleaned.
@@ -373,7 +373,7 @@ int cache_register(struct cache_detail *cd)
 	schedule_delayed_work(&cache_cleaner, 0);
 	return 0;
 }
-EXPORT_SYMBOL(cache_register);
+EXPORT_SYMBOL_GPL(cache_register);
 
 void cache_unregister(struct cache_detail *cd)
 {
@@ -399,7 +399,7 @@ void cache_unregister(struct cache_detail *cd)
 out:
 	printk(KERN_ERR "nfsd: failed to unregister %s cache\n", cd->name);
 }
-EXPORT_SYMBOL(cache_unregister);
+EXPORT_SYMBOL_GPL(cache_unregister);
 
 /* clean cache tries to find something to clean
  * and cleans it.
@@ -514,7 +514,7 @@ void cache_flush(void)
 	while (cache_clean() != -1)
 		cond_resched();
 }
-EXPORT_SYMBOL(cache_flush);
+EXPORT_SYMBOL_GPL(cache_flush);
 
 void cache_purge(struct cache_detail *detail)
 {
@@ -523,7 +523,7 @@ void cache_purge(struct cache_detail *detail)
 	cache_flush();
 	detail->flush_time = 1;
 }
-EXPORT_SYMBOL(cache_purge);
+EXPORT_SYMBOL_GPL(cache_purge);
 
 
 /*
@@ -988,7 +988,7 @@ void qword_add(char **bpp, int *lp, char *str)
 	*bpp = bp;
 	*lp = len;
 }
-EXPORT_SYMBOL(qword_add);
+EXPORT_SYMBOL_GPL(qword_add);
 
 void qword_addhex(char **bpp, int *lp, char *buf, int blen)
 {
@@ -1017,7 +1017,7 @@ void qword_addhex(char **bpp, int *lp, char *buf, int blen)
 	*bpp = bp;
 	*lp = len;
 }
-EXPORT_SYMBOL(qword_addhex);
+EXPORT_SYMBOL_GPL(qword_addhex);
 
 static void warn_no_listener(struct cache_detail *detail)
 {
@@ -1140,7 +1140,7 @@ int qword_get(char **bpp, char *dest, int bufsize)
 	*dest = '\0';
 	return len;
 }
-EXPORT_SYMBOL(qword_get);
+EXPORT_SYMBOL_GPL(qword_get);
 
 
 /*

net/sunrpc/stats.c

@@ -106,7 +106,7 @@ void svc_seq_show(struct seq_file *seq, const struct svc_stat *statp) {
 		seq_putc(seq, '\n');
 	}
 }
-EXPORT_SYMBOL(svc_seq_show);
+EXPORT_SYMBOL_GPL(svc_seq_show);
 
 /**
  * rpc_alloc_iostats - allocate an rpc_iostats structure
@@ -249,14 +249,14 @@ svc_proc_register(struct svc_stat *statp, const struct file_operations *fops)
 {
 	return do_register(statp->program->pg_name, statp, fops);
 }
-EXPORT_SYMBOL(svc_proc_register);
+EXPORT_SYMBOL_GPL(svc_proc_register);
 
 void
 svc_proc_unregister(const char *name)
 {
 	remove_proc_entry(name, proc_net_rpc);
 }
-EXPORT_SYMBOL(svc_proc_unregister);
+EXPORT_SYMBOL_GPL(svc_proc_unregister);
 
 void
 rpc_proc_init(void)

net/sunrpc/svc.c

@@ -431,7 +431,7 @@ svc_create(struct svc_program *prog, unsigned int bufsize,
 {
 	return __svc_create(prog, bufsize, /*npools*/1, family, shutdown);
 }
-EXPORT_SYMBOL(svc_create);
+EXPORT_SYMBOL_GPL(svc_create);
 
 struct svc_serv *
 svc_create_pooled(struct svc_program *prog, unsigned int bufsize,
@@ -450,7 +450,7 @@ svc_create_pooled(struct svc_program *prog, unsigned int bufsize,
 
 	return serv;
 }
-EXPORT_SYMBOL(svc_create_pooled);
+EXPORT_SYMBOL_GPL(svc_create_pooled);
 
 /*
  * Destroy an RPC service. Should be called with appropriate locking to
@@ -492,7 +492,7 @@ svc_destroy(struct svc_serv *serv)
 	kfree(serv->sv_pools);
 	kfree(serv);
 }
-EXPORT_SYMBOL(svc_destroy);
+EXPORT_SYMBOL_GPL(svc_destroy);
 
 /*
  * Allocate an RPC server's buffer space.
@@ -567,7 +567,7 @@ out_thread:
 out_enomem:
 	return ERR_PTR(-ENOMEM);
 }
-EXPORT_SYMBOL(svc_prepare_thread);
+EXPORT_SYMBOL_GPL(svc_prepare_thread);
 
 /*
  * Choose a pool in which to create a new thread, for svc_set_num_threads
@@ -689,7 +689,7 @@ svc_set_num_threads(struct svc_serv *serv, struct svc_pool *pool, int nrservs)
 
 	return error;
 }
-EXPORT_SYMBOL(svc_set_num_threads);
+EXPORT_SYMBOL_GPL(svc_set_num_threads);
 
 /*
  * Called from a server thread as it's exiting. Caller must hold the BKL or
@@ -717,7 +717,7 @@ svc_exit_thread(struct svc_rqst *rqstp)
 	if (serv)
 		svc_destroy(serv);
 }
-EXPORT_SYMBOL(svc_exit_thread);
+EXPORT_SYMBOL_GPL(svc_exit_thread);
 
 #ifdef CONFIG_SUNRPC_REGISTER_V4
 
@@ -1231,7 +1231,7 @@ err_bad:
 	svc_putnl(resv, ntohl(rpc_stat));
 	goto sendit;
 }
-EXPORT_SYMBOL(svc_process);
+EXPORT_SYMBOL_GPL(svc_process);
 
 /*
  * Return (transport-specific) limit on the rpc payload.

net/sunrpc/svc_xprt.c

@@ -440,7 +440,7 @@ void svc_reserve(struct svc_rqst *rqstp, int space)
 		svc_xprt_enqueue(xprt);
 	}
 }
-EXPORT_SYMBOL(svc_reserve);
+EXPORT_SYMBOL_GPL(svc_reserve);
 
 static void svc_xprt_release(struct svc_rqst *rqstp)
 {
@@ -448,6 +448,9 @@ static void svc_xprt_release(struct svc_rqst *rqstp)
 
 	rqstp->rq_xprt->xpt_ops->xpo_release_rqst(rqstp);
 
+	kfree(rqstp->rq_deferred);
+	rqstp->rq_deferred = NULL;
+
 	svc_free_res_pages(rqstp);
 	rqstp->rq_res.page_len = 0;
 	rqstp->rq_res.page_base = 0;
@@ -498,7 +501,7 @@ void svc_wake_up(struct svc_serv *serv)
 		spin_unlock_bh(&pool->sp_lock);
 	}
 }
-EXPORT_SYMBOL(svc_wake_up);
+EXPORT_SYMBOL_GPL(svc_wake_up);
 
 int svc_port_is_privileged(struct sockaddr *sin)
 {
@@ -515,8 +518,10 @@ int svc_port_is_privileged(struct sockaddr *sin)
 }
 
 /*
- * Make sure that we don't have too many active connections.  If we
- * have, something must be dropped.
+ * Make sure that we don't have too many active connections. If we have,
+ * something must be dropped. It's not clear what will happen if we allow
+ * "too many" connections, but when dealing with network-facing software,
+ * we have to code defensively. Here we do that by imposing hard limits.
  *
  * There's no point in trying to do random drop here for DoS
  * prevention. The NFS clients does 1 reconnect in 15 seconds. An
@@ -525,19 +530,27 @@ int svc_port_is_privileged(struct sockaddr *sin)
  * The only somewhat efficient mechanism would be if drop old
  * connections from the same IP first. But right now we don't even
  * record the client IP in svc_sock.
+ *
+ * single-threaded services that expect a lot of clients will probably
+ * need to set sv_maxconn to override the default value which is based
+ * on the number of threads
  */
 static void svc_check_conn_limits(struct svc_serv *serv)
 {
-	if (serv->sv_tmpcnt > (serv->sv_nrthreads+3)*20) {
+	unsigned int limit = serv->sv_maxconn ? serv->sv_maxconn :
+				(serv->sv_nrthreads+3) * 20;
+
+	if (serv->sv_tmpcnt > limit) {
 		struct svc_xprt *xprt = NULL;
 		spin_lock_bh(&serv->sv_lock);
 		if (!list_empty(&serv->sv_tempsocks)) {
 			if (net_ratelimit()) {
 				/* Try to help the admin */
 				printk(KERN_NOTICE "%s: too many open  "
-				       "connections, consider increasing the "
-				       "number of nfsd threads\n",
-				       serv->sv_name);
+				       "connections, consider increasing %s\n",
+				       serv->sv_name, serv->sv_maxconn ?
+				       "the max number of connections." :
+				       "the number of threads.");
 			}
 			/*
 			 * Always select the oldest connection. It's not fair,
@@ -730,7 +743,7 @@ int svc_recv(struct svc_rqst *rqstp, long timeout)
 		serv->sv_stats->netcnt++;
 	return len;
 }
-EXPORT_SYMBOL(svc_recv);
+EXPORT_SYMBOL_GPL(svc_recv);
 
 /*
  * Drop request
@@ -740,7 +753,7 @@ void svc_drop(struct svc_rqst *rqstp)
 	dprintk("svc: xprt %p dropped request\n", rqstp->rq_xprt);
 	svc_xprt_release(rqstp);
 }
-EXPORT_SYMBOL(svc_drop);
+EXPORT_SYMBOL_GPL(svc_drop);
 
 /*
  * Return reply to client.
@@ -837,6 +850,11 @@ static void svc_age_temp_xprts(unsigned long closure)
 void svc_delete_xprt(struct svc_xprt *xprt)
 {
 	struct svc_serv	*serv = xprt->xpt_server;
+	struct svc_deferred_req *dr;
+
+	/* Only do this once */
+	if (test_and_set_bit(XPT_DEAD, &xprt->xpt_flags))
+		return;
 
 	dprintk("svc: svc_delete_xprt(%p)\n", xprt);
 	xprt->xpt_ops->xpo_detach(xprt);
@@ -851,12 +869,16 @@ void svc_delete_xprt(struct svc_xprt *xprt)
 	 * while still attached to a queue, the queue itself
 	 * is about to be destroyed (in svc_destroy).
 	 */
-	if (!test_and_set_bit(XPT_DEAD, &xprt->xpt_flags)) {
-		BUG_ON(atomic_read(&xprt->xpt_ref.refcount) < 2);
-		if (test_bit(XPT_TEMP, &xprt->xpt_flags))
-			serv->sv_tmpcnt--;
+	if (test_bit(XPT_TEMP, &xprt->xpt_flags))
+		serv->sv_tmpcnt--;
+
+	for (dr = svc_deferred_dequeue(xprt); dr;
+	     dr = svc_deferred_dequeue(xprt)) {
 		svc_xprt_put(xprt);
+		kfree(dr);
 	}
+
+	svc_xprt_put(xprt);
 	spin_unlock_bh(&serv->sv_lock);
 }
 
@@ -902,17 +924,19 @@ static void svc_revisit(struct cache_deferred_req *dreq, int too_many)
 		container_of(dreq, struct svc_deferred_req, handle);
 	struct svc_xprt *xprt = dr->xprt;
 
-	if (too_many) {
+	spin_lock(&xprt->xpt_lock);
+	set_bit(XPT_DEFERRED, &xprt->xpt_flags);
+	if (too_many || test_bit(XPT_DEAD, &xprt->xpt_flags)) {
+		spin_unlock(&xprt->xpt_lock);
+		dprintk("revisit canceled\n");
 		svc_xprt_put(xprt);
 		kfree(dr);
 		return;
 	}
 	dprintk("revisit queued\n");
 	dr->xprt = NULL;
-	spin_lock(&xprt->xpt_lock);
 	list_add(&dr->handle.recent, &xprt->xpt_deferred);
 	spin_unlock(&xprt->xpt_lock);
-	set_bit(XPT_DEFERRED, &xprt->xpt_flags);
 	svc_xprt_enqueue(xprt);
 	svc_xprt_put(xprt);
 }

net/sunrpc/svcauth.c

@@ -57,13 +57,13 @@ svc_authenticate(struct svc_rqst *rqstp, __be32 *authp)
 	rqstp->rq_authop = aops;
 	return aops->accept(rqstp, authp);
 }
-EXPORT_SYMBOL(svc_authenticate);
+EXPORT_SYMBOL_GPL(svc_authenticate);
 
 int svc_set_client(struct svc_rqst *rqstp)
 {
 	return rqstp->rq_authop->set_client(rqstp);
 }
-EXPORT_SYMBOL(svc_set_client);
+EXPORT_SYMBOL_GPL(svc_set_client);
 
 /* A request, which was authenticated, has now executed.
  * Time to finalise the credentials and verifier
@@ -95,7 +95,7 @@ svc_auth_register(rpc_authflavor_t flavor, struct auth_ops *aops)
 	spin_unlock(&authtab_lock);
 	return rv;
 }
-EXPORT_SYMBOL(svc_auth_register);
+EXPORT_SYMBOL_GPL(svc_auth_register);
 
 void
 svc_auth_unregister(rpc_authflavor_t flavor)
@@ -105,7 +105,7 @@ svc_auth_unregister(rpc_authflavor_t flavor)
 		authtab[flavor] = NULL;
 	spin_unlock(&authtab_lock);
 }
-EXPORT_SYMBOL(svc_auth_unregister);
+EXPORT_SYMBOL_GPL(svc_auth_unregister);
 
 /**************************************************
  * 'auth_domains' are stored in a hash table indexed by name.
@@ -132,7 +132,7 @@ void auth_domain_put(struct auth_domain *dom)
 		spin_unlock(&auth_domain_lock);
 	}
 }
-EXPORT_SYMBOL(auth_domain_put);
+EXPORT_SYMBOL_GPL(auth_domain_put);
 
 struct auth_domain *
 auth_domain_lookup(char *name, struct auth_domain *new)
@@ -157,10 +157,10 @@ auth_domain_lookup(char *name, struct auth_domain *new)
 	spin_unlock(&auth_domain_lock);
 	return new;
 }
-EXPORT_SYMBOL(auth_domain_lookup);
+EXPORT_SYMBOL_GPL(auth_domain_lookup);
 
 struct auth_domain *auth_domain_find(char *name)
 {
 	return auth_domain_lookup(name, NULL);
 }
-EXPORT_SYMBOL(auth_domain_find);
+EXPORT_SYMBOL_GPL(auth_domain_find);

net/sunrpc/svcauth_unix.c

@@ -64,7 +64,7 @@ struct auth_domain *unix_domain_find(char *name)
 		rv = auth_domain_lookup(name, &new->h);
 	}
 }
-EXPORT_SYMBOL(unix_domain_find);
+EXPORT_SYMBOL_GPL(unix_domain_find);
 
 static void svcauth_unix_domain_release(struct auth_domain *dom)
 {
@@ -358,7 +358,7 @@ int auth_unix_add_addr(struct in6_addr *addr, struct auth_domain *dom)
 	else
 		return -ENOMEM;
 }
-EXPORT_SYMBOL(auth_unix_add_addr);
+EXPORT_SYMBOL_GPL(auth_unix_add_addr);
 
 int auth_unix_forget_old(struct auth_domain *dom)
 {
@@ -370,7 +370,7 @@ int auth_unix_forget_old(struct auth_domain *dom)
 	udom->addr_changes++;
 	return 0;
 }
-EXPORT_SYMBOL(auth_unix_forget_old);
+EXPORT_SYMBOL_GPL(auth_unix_forget_old);
 
 struct auth_domain *auth_unix_lookup(struct in6_addr *addr)
 {
@@ -395,13 +395,13 @@ struct auth_domain *auth_unix_lookup(struct in6_addr *addr)
 	cache_put(&ipm->h, &ip_map_cache);
 	return rv;
 }
-EXPORT_SYMBOL(auth_unix_lookup);
+EXPORT_SYMBOL_GPL(auth_unix_lookup);
 
 void svcauth_unix_purge(void)
 {
 	cache_purge(&ip_map_cache);
 }
-EXPORT_SYMBOL(svcauth_unix_purge);
+EXPORT_SYMBOL_GPL(svcauth_unix_purge);
 
 static inline struct ip_map *
 ip_map_cached_get(struct svc_rqst *rqstp)
@@ -714,7 +714,7 @@ svcauth_unix_set_client(struct svc_rqst *rqstp)
 	return SVC_OK;
 }
 
-EXPORT_SYMBOL(svcauth_unix_set_client);
+EXPORT_SYMBOL_GPL(svcauth_unix_set_client);
 
 static int
 svcauth_null_accept(struct svc_rqst *rqstp, __be32 *authp)

net/sunrpc/svcsock.c

@@ -59,6 +59,7 @@ static void		svc_udp_data_ready(struct sock *, int);
 static int		svc_udp_recvfrom(struct svc_rqst *);
 static int		svc_udp_sendto(struct svc_rqst *);
 static void		svc_sock_detach(struct svc_xprt *);
+static void		svc_tcp_sock_detach(struct svc_xprt *);
 static void		svc_sock_free(struct svc_xprt *);
 
 static struct svc_xprt *svc_create_socket(struct svc_serv *, int,
@@ -102,7 +103,6 @@ static void svc_reclassify_socket(struct socket *sock)
 static void svc_release_skb(struct svc_rqst *rqstp)
 {
 	struct sk_buff *skb = rqstp->rq_xprt_ctxt;
-	struct svc_deferred_req *dr = rqstp->rq_deferred;
 
 	if (skb) {
 		struct svc_sock *svsk =
@@ -112,10 +112,6 @@ static void svc_release_skb(struct svc_rqst *rqstp)
 		dprintk("svc: service %p, releasing skb %p\n", rqstp, skb);
 		skb_free_datagram(svsk->sk_sk, skb);
 	}
-	if (dr) {
-		rqstp->rq_deferred = NULL;
-		kfree(dr);
-	}
 }
 
 union svc_pktinfo_u {
@@ -289,7 +285,7 @@ svc_sock_names(char *buf, struct svc_serv *serv, char *toclose)
 		return -ENOENT;
 	return len;
 }
-EXPORT_SYMBOL(svc_sock_names);
+EXPORT_SYMBOL_GPL(svc_sock_names);
 
 /*
  * Check input queue length
@@ -1017,7 +1013,7 @@ static struct svc_xprt_ops svc_tcp_ops = {
 	.xpo_recvfrom = svc_tcp_recvfrom,
 	.xpo_sendto = svc_tcp_sendto,
 	.xpo_release_rqst = svc_release_skb,
-	.xpo_detach = svc_sock_detach,
+	.xpo_detach = svc_tcp_sock_detach,
 	.xpo_free = svc_sock_free,
 	.xpo_prep_reply_hdr = svc_tcp_prep_reply_hdr,
 	.xpo_has_wspace = svc_tcp_has_wspace,
@@ -1101,7 +1097,7 @@ void svc_sock_update_bufs(struct svc_serv *serv)
 	}
 	spin_unlock_bh(&serv->sv_lock);
 }
-EXPORT_SYMBOL(svc_sock_update_bufs);
+EXPORT_SYMBOL_GPL(svc_sock_update_bufs);
 
 /*
  * Initialize socket for RPC use and create svc_sock struct
@@ -1287,6 +1283,24 @@ static void svc_sock_detach(struct svc_xprt *xprt)
 	sk->sk_state_change = svsk->sk_ostate;
 	sk->sk_data_ready = svsk->sk_odata;
 	sk->sk_write_space = svsk->sk_owspace;
+
+	if (sk->sk_sleep && waitqueue_active(sk->sk_sleep))
+		wake_up_interruptible(sk->sk_sleep);
+}
+
+/*
+ * Disconnect the socket, and reset the callbacks
+ */
+static void svc_tcp_sock_detach(struct svc_xprt *xprt)
+{
+	struct svc_sock *svsk = container_of(xprt, struct svc_sock, sk_xprt);
+
+	dprintk("svc: svc_tcp_sock_detach(%p)\n", svsk);
+
+	svc_sock_detach(xprt);
+
+	if (!test_bit(XPT_LISTENER, &xprt->xpt_flags))
+		kernel_sock_shutdown(svsk->sk_sock, SHUT_RDWR);
 }
 
 /*