Merge git://git.linux-nfs.org/projects/trondmy/nfs-2.6

* git://git.linux-nfs.org/projects/trondmy/nfs-2.6: (87 commits)
  NFSv4: Disallow 'mount -t nfs4 -overs=2' and 'mount -t nfs4 -overs=3'
  NFS: Allow the "nfs" file system type to support NFSv4
  NFS: Move details of nfs4_get_sb() to a helper
  NFS: Refactor NFSv4 text-based mount option validation
  NFS: Mount option parser should detect missing "port="
  NFS: out of date comment regarding O_EXCL above nfs3_proc_create()
  NFS: Handle a zero-length auth flavor list
  SUNRPC: Ensure that sunrpc gets initialised before nfs, lockd, etc...
  nfs: fix compile error in rpc_pipefs.h
  nfs: Remove reference to generic_osync_inode from a comment
  SUNRPC: cache must take a reference to the cache detail's module on open()
  NFS: Use the DNS resolver in the mount code.
  NFS: Add a dns resolver for use with NFSv4 referrals and migration
  SUNRPC: Fix a typo in cache_pipefs_files
  nfs: nfs4xdr: optimize low level decoding
  nfs: nfs4xdr: get rid of READ_BUF
  nfs: nfs4xdr: simplify decode_exchange_id by reusing decode_opaque_inline
  nfs: nfs4xdr: get rid of COPYMEM
  nfs: nfs4xdr: introduce decode_sessionid helper
  nfs: nfs4xdr: introduce decode_verifier helper
  ...

Documentation/filesystems/nfs.txt

@@ -0,0 +1,98 @@
+
+The NFS client
+==============
+
+The NFS version 2 protocol was first documented in RFC1094 (March 1989).
+Since then two more major releases of NFS have been published, with NFSv3
+being documented in RFC1813 (June 1995), and NFSv4 in RFC3530 (April
+2003).
+
+The Linux NFS client currently supports all the above published versions,
+and work is in progress on adding support for minor version 1 of the NFSv4
+protocol.
+
+The purpose of this document is to provide information on some of the
+upcall interfaces that are used in order to provide the NFS client with
+some of the information that it requires in order to fully comply with
+the NFS spec.
+
+The DNS resolver
+================
+
+NFSv4 allows for one server to refer the NFS client to data that has been
+migrated onto another server by means of the special "fs_locations"
+attribute. See
+	http://tools.ietf.org/html/rfc3530#section-6
+and
+	http://tools.ietf.org/html/draft-ietf-nfsv4-referrals-00
+
+The fs_locations information can take the form of either an ip address and
+a path, or a DNS hostname and a path. The latter requires the NFS client to
+do a DNS lookup in order to mount the new volume, and hence the need for an
+upcall to allow userland to provide this service.
+
+Assuming that the user has the 'rpc_pipefs' filesystem mounted in the usual
+/var/lib/nfs/rpc_pipefs, the upcall consists of the following steps:
+
+   (1) The process checks the dns_resolve cache to see if it contains a
+       valid entry. If so, it returns that entry and exits.
+
+   (2) If no valid entry exists, the helper script '/sbin/nfs_cache_getent'
+       (may be changed using the 'nfs.cache_getent' kernel boot parameter)
+       is run, with two arguments:
+		- the cache name, "dns_resolve"
+		- the hostname to resolve
+
+   (3) After looking up the corresponding ip address, the helper script
+       writes the result into the rpc_pipefs pseudo-file
+       '/var/lib/nfs/rpc_pipefs/cache/dns_resolve/channel'
+       in the following (text) format:
+
+		"<ip address> <hostname> <ttl>\n"
+
+       Where <ip address> is in the usual IPv4 (123.456.78.90) or IPv6
+       (ffee:ddcc:bbaa:9988:7766:5544:3322:1100, ffee::1100, ...) format.
+       <hostname> is identical to the second argument of the helper
+       script, and <ttl> is the 'time to live' of this cache entry (in
+       units of seconds).
+
+       Note: If <ip address> is invalid, say the string "0", then a negative
+       entry is created, which will cause the kernel to treat the hostname
+       as having no valid DNS translation.
+
+
+
+
+A basic sample /sbin/nfs_cache_getent
+=====================================
+
+#!/bin/bash
+#
+ttl=600
+#
+cut=/usr/bin/cut
+getent=/usr/bin/getent
+rpc_pipefs=/var/lib/nfs/rpc_pipefs
+#
+die()
+{
+	echo "Usage: $0 cache_name entry_name"
+	exit 1
+}
+
+[ $# -lt 2 ] && die
+cachename="$1"
+cache_path=${rpc_pipefs}/cache/${cachename}/channel
+
+case "${cachename}" in
+	dns_resolve)
+		name="$2"
+		result="$(${getent} hosts ${name} | ${cut} -f1 -d\ )"
+		[ -z "${result}" ] && result="0"
+		;;
+	*)
+		die
+		;;
+esac
+echo "${result} ${name} ${ttl}" >${cache_path}
+

Documentation/kernel-parameters.txt

@@ -1503,6 +1503,14 @@ and is between 256 and 4096 characters. It is defined in the file
 			[NFS] set the TCP port on which the NFSv4 callback
 			channel should listen.
 
+	nfs.cache_getent=
+			[NFS] sets the pathname to the program which is used
+			to update the NFS client cache entries.
+
+	nfs.cache_getent_timeout=
+			[NFS] sets the timeout after which an attempt to
+			update a cache entry is deemed to have failed.
+
 	nfs.idmap_cache_timeout=
 			[NFS] set the maximum lifetime for idmapper cache
 			entries.
@@ -2395,6 +2403,18 @@ and is between 256 and 4096 characters. It is defined in the file
 	stifb=		[HW]
 			Format: bpp:<bpp1>[:<bpp2>[:<bpp3>...]]
 
+	sunrpc.min_resvport=
+	sunrpc.max_resvport=
+			[NFS,SUNRPC]
+			SunRPC servers often require that client requests
+			originate from a privileged port (i.e. a port in the
+			range 0 < portnr < 1024).
+			An administrator who wishes to reserve some of these
+			ports for other uses may adjust the range that the
+			kernel's sunrpc client considers to be privileged
+			using these two parameters to set the minimum and
+			maximum port values.
+
 	sunrpc.pool_mode=
 			[NFS]
 			Control how the NFS server code allocates CPUs to
@@ -2411,6 +2431,15 @@ and is between 256 and 4096 characters. It is defined in the file
 			pernode	    one pool for each NUMA node (equivalent
 				    to global on non-NUMA machines)
 
+	sunrpc.tcp_slot_table_entries=
+	sunrpc.udp_slot_table_entries=
+			[NFS,SUNRPC]
+			Sets the upper limit on the number of simultaneous
+			RPC calls that can be sent from the client to a
+			server. Increasing these values may allow you to
+			improve throughput, but will also increase the
+			amount of memory reserved for use by the client.
+
 	swiotlb=	[IA-64] Number of I/O TLB slabs
 
 	switches=	[HW,M68k]

fs/lockd/host.c

@@ -87,18 +87,6 @@ static unsigned int nlm_hash_address(const struct sockaddr *sap)
 	return hash & (NLM_HOST_NRHASH - 1);
 }
 
-static void nlm_clear_port(struct sockaddr *sap)
-{
-	switch (sap->sa_family) {
-	case AF_INET:
-		((struct sockaddr_in *)sap)->sin_port = 0;
-		break;
-	case AF_INET6:
-		((struct sockaddr_in6 *)sap)->sin6_port = 0;
-		break;
-	}
-}
-
 /*
  * Common host lookup routine for server & client
  */
@@ -177,7 +165,7 @@ static struct nlm_host *nlm_lookup_host(struct nlm_lookup_host_info *ni)
 	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));
+	rpc_set_port(nlm_addr(host), 0);
 	memcpy(nlm_srcaddr(host), ni->src_sap, ni->src_len);
 	host->h_version    = ni->version;
 	host->h_proto      = ni->protocol;

fs/lockd/mon.c

@@ -61,43 +61,6 @@ 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 = {
@@ -307,8 +270,11 @@ static struct nsm_handle *nsm_create_handle(const struct sockaddr *sap,
 	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));
+	if (rpc_ntop(nsm_addr(new), new->sm_addrbuf,
+					sizeof(new->sm_addrbuf)) == 0)
+		(void)snprintf(new->sm_addrbuf, sizeof(new->sm_addrbuf),
+				"unsupported address family");
 	memcpy(new->sm_name, hostname, hostname_len);
 	new->sm_name[hostname_len] = '\0';
 

fs/nfs/Makefile

@@ -6,7 +6,8 @@ obj-$(CONFIG_NFS_FS) += nfs.o
 
 nfs-y 			:= client.o dir.o file.o getroot.o inode.o super.o nfs2xdr.o \
 			   direct.o pagelist.o proc.o read.o symlink.o unlink.o \
-			   write.o namespace.o mount_clnt.o
+			   write.o namespace.o mount_clnt.o \
+			   dns_resolve.o cache_lib.o
 nfs-$(CONFIG_ROOT_NFS)	+= nfsroot.o
 nfs-$(CONFIG_NFS_V3)	+= nfs3proc.o nfs3xdr.o
 nfs-$(CONFIG_NFS_V3_ACL)	+= nfs3acl.o

fs/nfs/cache_lib.c

@@ -0,0 +1,140 @@
+/*
+ * linux/fs/nfs/cache_lib.c
+ *
+ * Helper routines for the NFS client caches
+ *
+ * Copyright (c) 2009 Trond Myklebust <Trond.Myklebust@netapp.com>
+ */
+#include <linux/kmod.h>
+#include <linux/module.h>
+#include <linux/moduleparam.h>
+#include <linux/mount.h>
+#include <linux/namei.h>
+#include <linux/sunrpc/cache.h>
+#include <linux/sunrpc/rpc_pipe_fs.h>
+
+#include "cache_lib.h"
+
+#define NFS_CACHE_UPCALL_PATHLEN 256
+#define NFS_CACHE_UPCALL_TIMEOUT 15
+
+static char nfs_cache_getent_prog[NFS_CACHE_UPCALL_PATHLEN] =
+				"/sbin/nfs_cache_getent";
+static unsigned long nfs_cache_getent_timeout = NFS_CACHE_UPCALL_TIMEOUT;
+
+module_param_string(cache_getent, nfs_cache_getent_prog,
+		sizeof(nfs_cache_getent_prog), 0600);
+MODULE_PARM_DESC(cache_getent, "Path to the client cache upcall program");
+module_param_named(cache_getent_timeout, nfs_cache_getent_timeout, ulong, 0600);
+MODULE_PARM_DESC(cache_getent_timeout, "Timeout (in seconds) after which "
+		"the cache upcall is assumed to have failed");
+
+int nfs_cache_upcall(struct cache_detail *cd, char *entry_name)
+{
+	static char *envp[] = { "HOME=/",
+		"TERM=linux",
+		"PATH=/sbin:/usr/sbin:/bin:/usr/bin",
+		NULL
+	};
+	char *argv[] = {
+		nfs_cache_getent_prog,
+		cd->name,
+		entry_name,
+		NULL
+	};
+	int ret = -EACCES;
+
+	if (nfs_cache_getent_prog[0] == '\0')
+		goto out;
+	ret = call_usermodehelper(argv[0], argv, envp, UMH_WAIT_EXEC);
+	/*
+	 * Disable the upcall mechanism if we're getting an ENOENT or
+	 * EACCES error. The admin can re-enable it on the fly by using
+	 * sysfs to set the 'cache_getent' parameter once the problem
+	 * has been fixed.
+	 */
+	if (ret == -ENOENT || ret == -EACCES)
+		nfs_cache_getent_prog[0] = '\0';
+out:
+	return ret > 0 ? 0 : ret;
+}
+
+/*
+ * Deferred request handling
+ */
+void nfs_cache_defer_req_put(struct nfs_cache_defer_req *dreq)
+{
+	if (atomic_dec_and_test(&dreq->count))
+		kfree(dreq);
+}
+
+static void nfs_dns_cache_revisit(struct cache_deferred_req *d, int toomany)
+{
+	struct nfs_cache_defer_req *dreq;
+
+	dreq = container_of(d, struct nfs_cache_defer_req, deferred_req);
+
+	complete_all(&dreq->completion);
+	nfs_cache_defer_req_put(dreq);
+}
+
+static struct cache_deferred_req *nfs_dns_cache_defer(struct cache_req *req)
+{
+	struct nfs_cache_defer_req *dreq;
+
+	dreq = container_of(req, struct nfs_cache_defer_req, req);
+	dreq->deferred_req.revisit = nfs_dns_cache_revisit;
+	atomic_inc(&dreq->count);
+
+	return &dreq->deferred_req;
+}
+
+struct nfs_cache_defer_req *nfs_cache_defer_req_alloc(void)
+{
+	struct nfs_cache_defer_req *dreq;
+
+	dreq = kzalloc(sizeof(*dreq), GFP_KERNEL);
+	if (dreq) {
+		init_completion(&dreq->completion);
+		atomic_set(&dreq->count, 1);
+		dreq->req.defer = nfs_dns_cache_defer;
+	}
+	return dreq;
+}
+
+int nfs_cache_wait_for_upcall(struct nfs_cache_defer_req *dreq)
+{
+	if (wait_for_completion_timeout(&dreq->completion,
+			nfs_cache_getent_timeout * HZ) == 0)
+		return -ETIMEDOUT;
+	return 0;
+}
+
+int nfs_cache_register(struct cache_detail *cd)
+{
+	struct nameidata nd;
+	struct vfsmount *mnt;
+	int ret;
+
+	mnt = rpc_get_mount();
+	if (IS_ERR(mnt))
+		return PTR_ERR(mnt);
+	ret = vfs_path_lookup(mnt->mnt_root, mnt, "/cache", 0, &nd);
+	if (ret)
+		goto err;
+	ret = sunrpc_cache_register_pipefs(nd.path.dentry,
+			cd->name, 0600, cd);
+	path_put(&nd.path);
+	if (!ret)
+		return ret;
+err:
+	rpc_put_mount();
+	return ret;
+}
+
+void nfs_cache_unregister(struct cache_detail *cd)
+{
+	sunrpc_cache_unregister_pipefs(cd);
+	rpc_put_mount();
+}
+

fs/nfs/cache_lib.h

@@ -0,0 +1,27 @@
+/*
+ * Helper routines for the NFS client caches
+ *
+ * Copyright (c) 2009 Trond Myklebust <Trond.Myklebust@netapp.com>
+ */
+
+#include <linux/completion.h>
+#include <linux/sunrpc/cache.h>
+#include <asm/atomic.h>
+
+/*
+ * Deferred request handling
+ */
+struct nfs_cache_defer_req {
+	struct cache_req req;
+	struct cache_deferred_req deferred_req;
+	struct completion completion;
+	atomic_t count;
+};
+
+extern int nfs_cache_upcall(struct cache_detail *cd, char *entry_name);
+extern struct nfs_cache_defer_req *nfs_cache_defer_req_alloc(void);
+extern void nfs_cache_defer_req_put(struct nfs_cache_defer_req *dreq);
+extern int nfs_cache_wait_for_upcall(struct nfs_cache_defer_req *dreq);
+
+extern int nfs_cache_register(struct cache_detail *cd);
+extern void nfs_cache_unregister(struct cache_detail *cd);

fs/nfs/callback.c

@@ -43,21 +43,29 @@ static struct svc_program nfs4_callback_program;
 unsigned int nfs_callback_set_tcpport;
 unsigned short nfs_callback_tcpport;
 unsigned short nfs_callback_tcpport6;
-static const int nfs_set_port_min = 0;
+#define NFS_CALLBACK_MAXPORTNR (65535U)
-static const int nfs_set_port_max = 65535;
 
-static int param_set_port(const char *val, struct kernel_param *kp)
+static int param_set_portnr(const char *val, struct kernel_param *kp)
 {
-	char *endp;
+	unsigned long num;
-	int num = simple_strtol(val, &endp, 0);
+	int ret;
-	if (endp == val || *endp || num < nfs_set_port_min || num > nfs_set_port_max)
+
+	if (!val)
 		return -EINVAL;
-	*((int *)kp->arg) = num;
+	ret = strict_strtoul(val, 0, &num);
+	if (ret == -EINVAL || num > NFS_CALLBACK_MAXPORTNR)
+		return -EINVAL;
+	*((unsigned int *)kp->arg) = num;
 	return 0;
 }
 
-module_param_call(callback_tcpport, param_set_port, param_get_int,
+static int param_get_portnr(char *buffer, struct kernel_param *kp)
-		 &nfs_callback_set_tcpport, 0644);
+{
+	return param_get_uint(buffer, kp);
+}
+#define param_check_portnr(name, p) __param_check(name, p, unsigned int);
+
+module_param_named(callback_tcpport, nfs_callback_set_tcpport, portnr, 0644);
 
 /*
  * This is the NFSv4 callback kernel thread.

fs/nfs/client.c

@@ -809,6 +809,9 @@ static int nfs_init_server(struct nfs_server *server,
 	/* Initialise the client representation from the mount data */
 	server->flags = data->flags;
 	server->options = data->options;
+	server->caps |= NFS_CAP_HARDLINKS|NFS_CAP_SYMLINKS|NFS_CAP_FILEID|
+		NFS_CAP_MODE|NFS_CAP_NLINK|NFS_CAP_OWNER|NFS_CAP_OWNER_GROUP|
+		NFS_CAP_ATIME|NFS_CAP_CTIME|NFS_CAP_MTIME;
 
 	if (data->rsize)
 		server->rsize = nfs_block_size(data->rsize, NULL);
@@ -1075,10 +1078,6 @@ struct nfs_server *nfs_create_server(const struct nfs_parsed_mount_data *data,
 		(unsigned long long) server->fsid.major,
 		(unsigned long long) server->fsid.minor);
 
-	BUG_ON(!server->nfs_client);
-	BUG_ON(!server->nfs_client->rpc_ops);
-	BUG_ON(!server->nfs_client->rpc_ops->file_inode_ops);
-
 	spin_lock(&nfs_client_lock);
 	list_add_tail(&server->client_link, &server->nfs_client->cl_superblocks);
 	list_add_tail(&server->master_link, &nfs_volume_list);
@@ -1275,7 +1274,7 @@ static int nfs4_init_server(struct nfs_server *server,
 
 	/* Initialise the client representation from the mount data */
 	server->flags = data->flags;
-	server->caps |= NFS_CAP_ATOMIC_OPEN;
+	server->caps |= NFS_CAP_ATOMIC_OPEN|NFS_CAP_CHANGE_ATTR;
 	server->options = data->options;
 
 	/* Get a client record */
@@ -1360,10 +1359,6 @@ struct nfs_server *nfs4_create_server(const struct nfs_parsed_mount_data *data,
 	if (server->namelen == 0 || server->namelen > NFS4_MAXNAMLEN)
 		server->namelen = NFS4_MAXNAMLEN;
 
-	BUG_ON(!server->nfs_client);
-	BUG_ON(!server->nfs_client->rpc_ops);
-	BUG_ON(!server->nfs_client->rpc_ops->file_inode_ops);
-
 	spin_lock(&nfs_client_lock);
 	list_add_tail(&server->client_link, &server->nfs_client->cl_superblocks);
 	list_add_tail(&server->master_link, &nfs_volume_list);
@@ -1401,7 +1396,7 @@ struct nfs_server *nfs4_create_referral_server(struct nfs_clone_mount *data,
 
 	/* Initialise the client representation from the parent server */
 	nfs_server_copy_userdata(server, parent_server);
-	server->caps |= NFS_CAP_ATOMIC_OPEN;
+	server->caps |= NFS_CAP_ATOMIC_OPEN|NFS_CAP_CHANGE_ATTR;
 
 	/* Get a client representation.
 	 * Note: NFSv4 always uses TCP, */

fs/nfs/direct.c

@@ -934,9 +934,6 @@ out:
  * back into its cache.  We let the server do generic write
  * parameter checking and report problems.
  *
- * We also avoid an unnecessary invocation of generic_osync_inode(),
- * as it is fairly meaningless to sync the metadata of an NFS file.
- *
  * We eliminate local atime updates, see direct read above.
  *
  * We avoid unnecessary page cache invalidations for normal cached

fs/nfs/dns_resolve.c

@@ -0,0 +1,335 @@
+/*
+ * linux/fs/nfs/dns_resolve.c
+ *
+ * Copyright (c) 2009 Trond Myklebust <Trond.Myklebust@netapp.com>
+ *
+ * Resolves DNS hostnames into valid ip addresses
+ */
+
+#include <linux/hash.h>
+#include <linux/string.h>
+#include <linux/kmod.h>
+#include <linux/module.h>
+#include <linux/socket.h>
+#include <linux/seq_file.h>
+#include <linux/inet.h>
+#include <linux/sunrpc/clnt.h>
+#include <linux/sunrpc/cache.h>
+#include <linux/sunrpc/svcauth.h>
+
+#include "dns_resolve.h"
+#include "cache_lib.h"
+
+#define NFS_DNS_HASHBITS 4
+#define NFS_DNS_HASHTBL_SIZE (1 << NFS_DNS_HASHBITS)
+
+static struct cache_head *nfs_dns_table[NFS_DNS_HASHTBL_SIZE];
+
+struct nfs_dns_ent {
+	struct cache_head h;
+
+	char *hostname;
+	size_t namelen;
+
+	struct sockaddr_storage addr;
+	size_t addrlen;
+};
+
+
+static void nfs_dns_ent_init(struct cache_head *cnew,
+		struct cache_head *ckey)
+{
+	struct nfs_dns_ent *new;
+	struct nfs_dns_ent *key;
+
+	new = container_of(cnew, struct nfs_dns_ent, h);
+	key = container_of(ckey, struct nfs_dns_ent, h);
+
+	kfree(new->hostname);
+	new->hostname = kstrndup(key->hostname, key->namelen, GFP_KERNEL);
+	if (new->hostname) {
+		new->namelen = key->namelen;
+		memcpy(&new->addr, &key->addr, key->addrlen);
+		new->addrlen = key->addrlen;
+	} else {
+		new->namelen = 0;
+		new->addrlen = 0;
+	}
+}
+
+static void nfs_dns_ent_put(struct kref *ref)
+{
+	struct nfs_dns_ent *item;
+
+	item = container_of(ref, struct nfs_dns_ent, h.ref);
+	kfree(item->hostname);
+	kfree(item);
+}
+
+static struct cache_head *nfs_dns_ent_alloc(void)
+{
+	struct nfs_dns_ent *item = kmalloc(sizeof(*item), GFP_KERNEL);
+
+	if (item != NULL) {
+		item->hostname = NULL;
+		item->namelen = 0;
+		item->addrlen = 0;
+		return &item->h;
+	}
+	return NULL;
+};
+
+static unsigned int nfs_dns_hash(const struct nfs_dns_ent *key)
+{
+	return hash_str(key->hostname, NFS_DNS_HASHBITS);
+}
+
+static void nfs_dns_request(struct cache_detail *cd,
+		struct cache_head *ch,
+		char **bpp, int *blen)
+{
+	struct nfs_dns_ent *key = container_of(ch, struct nfs_dns_ent, h);
+
+	qword_add(bpp, blen, key->hostname);
+	(*bpp)[-1] = '\n';
+}
+
+static int nfs_dns_upcall(struct cache_detail *cd,
+		struct cache_head *ch)
+{
+	struct nfs_dns_ent *key = container_of(ch, struct nfs_dns_ent, h);
+	int ret;
+
+	ret = nfs_cache_upcall(cd, key->hostname);
+	if (ret)
+		ret = sunrpc_cache_pipe_upcall(cd, ch, nfs_dns_request);
+	return ret;
+}
+
+static int nfs_dns_match(struct cache_head *ca,
+		struct cache_head *cb)
+{
+	struct nfs_dns_ent *a;
+	struct nfs_dns_ent *b;
+
+	a = container_of(ca, struct nfs_dns_ent, h);
+	b = container_of(cb, struct nfs_dns_ent, h);
+
+	if (a->namelen == 0 || a->namelen != b->namelen)
+		return 0;
+	return memcmp(a->hostname, b->hostname, a->namelen) == 0;
+}
+
+static int nfs_dns_show(struct seq_file *m, struct cache_detail *cd,
+		struct cache_head *h)
+{
+	struct nfs_dns_ent *item;
+	long ttl;
+
+	if (h == NULL) {
+		seq_puts(m, "# ip address      hostname        ttl\n");
+		return 0;
+	}
+	item = container_of(h, struct nfs_dns_ent, h);
+	ttl = (long)item->h.expiry_time - (long)get_seconds();
+	if (ttl < 0)
+		ttl = 0;
+
+	if (!test_bit(CACHE_NEGATIVE, &h->flags)) {
+		char buf[INET6_ADDRSTRLEN+IPV6_SCOPE_ID_LEN+1];
+
+		rpc_ntop((struct sockaddr *)&item->addr, buf, sizeof(buf));
+		seq_printf(m, "%15s ", buf);
+	} else
+		seq_puts(m, "<none>          ");
+	seq_printf(m, "%15s %ld\n", item->hostname, ttl);
+	return 0;
+}
+
+struct nfs_dns_ent *nfs_dns_lookup(struct cache_detail *cd,
+		struct nfs_dns_ent *key)
+{
+	struct cache_head *ch;
+
+	ch = sunrpc_cache_lookup(cd,
+			&key->h,
+			nfs_dns_hash(key));
+	if (!ch)
+		return NULL;
+	return container_of(ch, struct nfs_dns_ent, h);
+}
+
+struct nfs_dns_ent *nfs_dns_update(struct cache_detail *cd,
+		struct nfs_dns_ent *new,
+		struct nfs_dns_ent *key)
+{
+	struct cache_head *ch;
+
+	ch = sunrpc_cache_update(cd,
+			&new->h, &key->h,
+			nfs_dns_hash(key));
+	if (!ch)
+		return NULL;
+	return container_of(ch, struct nfs_dns_ent, h);
+}
+
+static int nfs_dns_parse(struct cache_detail *cd, char *buf, int buflen)
+{
+	char buf1[NFS_DNS_HOSTNAME_MAXLEN+1];
+	struct nfs_dns_ent key, *item;
+	unsigned long ttl;
+	ssize_t len;
+	int ret = -EINVAL;
+
+	if (buf[buflen-1] != '\n')
+		goto out;
+	buf[buflen-1] = '\0';
+
+	len = qword_get(&buf, buf1, sizeof(buf1));
+	if (len <= 0)
+		goto out;
+	key.addrlen = rpc_pton(buf1, len,
+			(struct sockaddr *)&key.addr,
+			sizeof(key.addr));
+
+	len = qword_get(&buf, buf1, sizeof(buf1));
+	if (len <= 0)
+		goto out;
+
+	key.hostname = buf1;
+	key.namelen = len;
+	memset(&key.h, 0, sizeof(key.h));
+
+	ttl = get_expiry(&buf);
+	if (ttl == 0)
+		goto out;
+	key.h.expiry_time = ttl + get_seconds();
+
+	ret = -ENOMEM;
+	item = nfs_dns_lookup(cd, &key);
+	if (item == NULL)
+		goto out;
+
+	if (key.addrlen == 0)
+		set_bit(CACHE_NEGATIVE, &key.h.flags);
+
+	item = nfs_dns_update(cd, &key, item);
+	if (item == NULL)
+		goto out;
+
+	ret = 0;
+	cache_put(&item->h, cd);
+out:
+	return ret;
+}
+
+static struct cache_detail nfs_dns_resolve = {
+	.owner = THIS_MODULE,
+	.hash_size = NFS_DNS_HASHTBL_SIZE,
+	.hash_table = nfs_dns_table,
+	.name = "dns_resolve",
+	.cache_put = nfs_dns_ent_put,
+	.cache_upcall = nfs_dns_upcall,
+	.cache_parse = nfs_dns_parse,
+	.cache_show = nfs_dns_show,
+	.match = nfs_dns_match,
+	.init = nfs_dns_ent_init,
+	.update = nfs_dns_ent_init,
+	.alloc = nfs_dns_ent_alloc,
+};
+
+static int do_cache_lookup(struct cache_detail *cd,
+		struct nfs_dns_ent *key,
+		struct nfs_dns_ent **item,
+		struct nfs_cache_defer_req *dreq)
+{
+	int ret = -ENOMEM;
+
+	*item = nfs_dns_lookup(cd, key);
+	if (*item) {
+		ret = cache_check(cd, &(*item)->h, &dreq->req);
+		if (ret)
+			*item = NULL;
+	}
+	return ret;
+}
+
+static int do_cache_lookup_nowait(struct cache_detail *cd,
+		struct nfs_dns_ent *key,
+		struct nfs_dns_ent **item)
+{
+	int ret = -ENOMEM;
+
+	*item = nfs_dns_lookup(cd, key);
+	if (!*item)
+		goto out_err;
+	ret = -ETIMEDOUT;
+	if (!test_bit(CACHE_VALID, &(*item)->h.flags)
+			|| (*item)->h.expiry_time < get_seconds()
+			|| cd->flush_time > (*item)->h.last_refresh)
+		goto out_put;
+	ret = -ENOENT;
+	if (test_bit(CACHE_NEGATIVE, &(*item)->h.flags))
+		goto out_put;
+	return 0;
+out_put:
+	cache_put(&(*item)->h, cd);
+out_err:
+	*item = NULL;
+	return ret;
+}
+
+static int do_cache_lookup_wait(struct cache_detail *cd,
+		struct nfs_dns_ent *key,
+		struct nfs_dns_ent **item)
+{
+	struct nfs_cache_defer_req *dreq;
+	int ret = -ENOMEM;
+
+	dreq = nfs_cache_defer_req_alloc();
+	if (!dreq)
+		goto out;
+	ret = do_cache_lookup(cd, key, item, dreq);
+	if (ret == -EAGAIN) {
+		ret = nfs_cache_wait_for_upcall(dreq);
+		if (!ret)
+			ret = do_cache_lookup_nowait(cd, key, item);
+	}
+	nfs_cache_defer_req_put(dreq);
+out:
+	return ret;
+}
+
+ssize_t nfs_dns_resolve_name(char *name, size_t namelen,
+		struct sockaddr *sa, size_t salen)
+{
+	struct nfs_dns_ent key = {
+		.hostname = name,
+		.namelen = namelen,
+	};
+	struct nfs_dns_ent *item = NULL;
+	ssize_t ret;
+
+	ret = do_cache_lookup_wait(&nfs_dns_resolve, &key, &item);
+	if (ret == 0) {
+		if (salen >= item->addrlen) {
+			memcpy(sa, &item->addr, item->addrlen);
+			ret = item->addrlen;
+		} else
+			ret = -EOVERFLOW;
+		cache_put(&item->h, &nfs_dns_resolve);
+	} else if (ret == -ENOENT)
+		ret = -ESRCH;
+	return ret;
+}
+
+int nfs_dns_resolver_init(void)
+{
+	return nfs_cache_register(&nfs_dns_resolve);
+}
+
+void nfs_dns_resolver_destroy(void)
+{
+	nfs_cache_unregister(&nfs_dns_resolve);
+}
+

fs/nfs/dns_resolve.h

@@ -0,0 +1,14 @@
+/*
+ * Resolve DNS hostnames into valid ip addresses
+ */
+#ifndef __LINUX_FS_NFS_DNS_RESOLVE_H
+#define __LINUX_FS_NFS_DNS_RESOLVE_H
+
+#define NFS_DNS_HOSTNAME_MAXLEN	(128)
+
+extern int nfs_dns_resolver_init(void);
+extern void nfs_dns_resolver_destroy(void);
+extern ssize_t nfs_dns_resolve_name(char *name, size_t namelen,
+		struct sockaddr *sa, size_t salen);
+
+#endif

fs/nfs/file.c

@@ -327,6 +327,42 @@ nfs_file_fsync(struct file *file, struct dentry *dentry, int datasync)
 	return nfs_do_fsync(ctx, inode);
 }
 
+/*
+ * Decide whether a read/modify/write cycle may be more efficient
+ * then a modify/write/read cycle when writing to a page in the
+ * page cache.
+ *
+ * The modify/write/read cycle may occur if a page is read before
+ * being completely filled by the writer.  In this situation, the
+ * page must be completely written to stable storage on the server
+ * before it can be refilled by reading in the page from the server.
+ * This can lead to expensive, small, FILE_SYNC mode writes being
+ * done.
+ *
+ * It may be more efficient to read the page first if the file is
+ * open for reading in addition to writing, the page is not marked
+ * as Uptodate, it is not dirty or waiting to be committed,
+ * indicating that it was previously allocated and then modified,
+ * that there were valid bytes of data in that range of the file,
+ * and that the new data won't completely replace the old data in
+ * that range of the file.
+ */
+static int nfs_want_read_modify_write(struct file *file, struct page *page,
+			loff_t pos, unsigned len)
+{
+	unsigned int pglen = nfs_page_length(page);
+	unsigned int offset = pos & (PAGE_CACHE_SIZE - 1);
+	unsigned int end = offset + len;
+
+	if ((file->f_mode & FMODE_READ) &&	/* open for read? */
+	    !PageUptodate(page) &&		/* Uptodate? */
+	    !PagePrivate(page) &&		/* i/o request already? */
+	    pglen &&				/* valid bytes of file? */
+	    (end < pglen || offset))		/* replace all valid bytes? */
+		return 1;
+	return 0;
+}
+
 /*
  * This does the "real" work of the write. We must allocate and lock the
  * page to be sent back to the generic routine, which then copies the
@@ -340,15 +376,16 @@ static int nfs_write_begin(struct file *file, struct address_space *mapping,
 			struct page **pagep, void **fsdata)
 {
 	int ret;
-	pgoff_t index;
+	pgoff_t index = pos >> PAGE_CACHE_SHIFT;
 	struct page *page;
-	index = pos >> PAGE_CACHE_SHIFT;
+	int once_thru = 0;
 
 	dfprintk(PAGECACHE, "NFS: write_begin(%s/%s(%ld), %u@%lld)\n",
 		file->f_path.dentry->d_parent->d_name.name,
 		file->f_path.dentry->d_name.name,
 		mapping->host->i_ino, len, (long long) pos);
 
+start:
 	/*
 	 * Prevent starvation issues if someone is doing a consistency
 	 * sync-to-disk
@@ -367,6 +404,13 @@ static int nfs_write_begin(struct file *file, struct address_space *mapping,
 	if (ret) {
 		unlock_page(page);
 		page_cache_release(page);
+	} else if (!once_thru &&
+		   nfs_want_read_modify_write(file, page, pos, len)) {
+		once_thru = 1;
+		ret = nfs_readpage(file, page);
+		page_cache_release(page);
+		if (!ret)
+			goto start;
 	}
 	return ret;
 }
@@ -479,6 +523,7 @@ const struct address_space_operations nfs_file_aops = {
 	.invalidatepage = nfs_invalidate_page,
 	.releasepage = nfs_release_page,
 	.direct_IO = nfs_direct_IO,
+	.migratepage = nfs_migrate_page,
 	.launder_page = nfs_launder_page,
 };
 

fs/nfs/idmap.c

@@ -101,7 +101,7 @@ static void idmap_pipe_destroy_msg(struct rpc_pipe_msg *);
 
 static unsigned int fnvhash32(const void *, size_t);
 
-static struct rpc_pipe_ops idmap_upcall_ops = {
+static const struct rpc_pipe_ops idmap_upcall_ops = {
 	.upcall		= idmap_pipe_upcall,
 	.downcall	= idmap_pipe_downcall,
 	.destroy_msg	= idmap_pipe_destroy_msg,
@@ -119,8 +119,8 @@ nfs_idmap_new(struct nfs_client *clp)
 	if (idmap == NULL)
 		return -ENOMEM;
 
-	idmap->idmap_dentry = rpc_mkpipe(clp->cl_rpcclient->cl_dentry, "idmap",
+	idmap->idmap_dentry = rpc_mkpipe(clp->cl_rpcclient->cl_path.dentry,
-					 idmap, &idmap_upcall_ops, 0);
+			"idmap", idmap, &idmap_upcall_ops, 0);
 	if (IS_ERR(idmap->idmap_dentry)) {
 		error = PTR_ERR(idmap->idmap_dentry);
 		kfree(idmap);

fs/nfs/inode.c

@@ -46,6 +46,7 @@
 #include "iostat.h"
 #include "internal.h"
 #include "fscache.h"
+#include "dns_resolve.h"
 
 #define NFSDBG_FACILITY		NFSDBG_VFS
 
@@ -286,6 +287,11 @@ nfs_fhget(struct super_block *sb, struct nfs_fh *fh, struct nfs_fattr *fattr)
 		/* We can't support update_atime(), since the server will reset it */
 		inode->i_flags |= S_NOATIME|S_NOCMTIME;
 		inode->i_mode = fattr->mode;
+		if ((fattr->valid & NFS_ATTR_FATTR_MODE) == 0
+				&& nfs_server_capable(inode, NFS_CAP_MODE))
+			nfsi->cache_validity |= NFS_INO_INVALID_ATTR
+				| NFS_INO_INVALID_ACCESS
+				| NFS_INO_INVALID_ACL;
 		/* Why so? Because we want revalidate for devices/FIFOs, and
 		 * that's precisely what we have in nfs_file_inode_operations.
 		 */
@@ -330,20 +336,46 @@ nfs_fhget(struct super_block *sb, struct nfs_fh *fh, struct nfs_fattr *fattr)
 		nfsi->attr_gencount = fattr->gencount;
 		if (fattr->valid & NFS_ATTR_FATTR_ATIME)
 			inode->i_atime = fattr->atime;
+		else if (nfs_server_capable(inode, NFS_CAP_ATIME))
+			nfsi->cache_validity |= NFS_INO_INVALID_ATTR;
 		if (fattr->valid & NFS_ATTR_FATTR_MTIME)
 			inode->i_mtime = fattr->mtime;
+		else if (nfs_server_capable(inode, NFS_CAP_MTIME))
+			nfsi->cache_validity |= NFS_INO_INVALID_ATTR
+				| NFS_INO_INVALID_DATA;
 		if (fattr->valid & NFS_ATTR_FATTR_CTIME)
 			inode->i_ctime = fattr->ctime;
+		else if (nfs_server_capable(inode, NFS_CAP_CTIME))
+			nfsi->cache_validity |= NFS_INO_INVALID_ATTR
+				| NFS_INO_INVALID_ACCESS
+				| NFS_INO_INVALID_ACL;
 		if (fattr->valid & NFS_ATTR_FATTR_CHANGE)
 			nfsi->change_attr = fattr->change_attr;
+		else if (nfs_server_capable(inode, NFS_CAP_CHANGE_ATTR))
+			nfsi->cache_validity |= NFS_INO_INVALID_ATTR
+				| NFS_INO_INVALID_DATA;
 		if (fattr->valid & NFS_ATTR_FATTR_SIZE)
 			inode->i_size = nfs_size_to_loff_t(fattr->size);
+		else
+			nfsi->cache_validity |= NFS_INO_INVALID_ATTR
+				| NFS_INO_INVALID_DATA
+				| NFS_INO_REVAL_PAGECACHE;
 		if (fattr->valid & NFS_ATTR_FATTR_NLINK)
 			inode->i_nlink = fattr->nlink;
+		else if (nfs_server_capable(inode, NFS_CAP_NLINK))
+			nfsi->cache_validity |= NFS_INO_INVALID_ATTR;
 		if (fattr->valid & NFS_ATTR_FATTR_OWNER)
 			inode->i_uid = fattr->uid;
+		else if (nfs_server_capable(inode, NFS_CAP_OWNER))
+			nfsi->cache_validity |= NFS_INO_INVALID_ATTR
+				| NFS_INO_INVALID_ACCESS
+				| NFS_INO_INVALID_ACL;
 		if (fattr->valid & NFS_ATTR_FATTR_GROUP)
 			inode->i_gid = fattr->gid;
+		else if (nfs_server_capable(inode, NFS_CAP_OWNER_GROUP))
+			nfsi->cache_validity |= NFS_INO_INVALID_ATTR
+				| NFS_INO_INVALID_ACCESS
+				| NFS_INO_INVALID_ACL;
 		if (fattr->valid & NFS_ATTR_FATTR_BLOCKS_USED)
 			inode->i_blocks = fattr->du.nfs2.blocks;
 		if (fattr->valid & NFS_ATTR_FATTR_SPACE_USED) {
@@ -1145,6 +1177,7 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
 	loff_t cur_isize, new_isize;
 	unsigned long invalid = 0;
 	unsigned long now = jiffies;
+	unsigned long save_cache_validity;
 
 	dfprintk(VFS, "NFS: %s(%s/%ld ct=%d info=0x%x)\n",
 			__func__, inode->i_sb->s_id, inode->i_ino,
@@ -1171,9 +1204,10 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
 	 */
 	nfsi->read_cache_jiffies = fattr->time_start;
 
-	if ((fattr->valid & NFS_ATTR_FATTR_CHANGE) || (fattr->valid & (NFS_ATTR_FATTR_MTIME|NFS_ATTR_FATTR_CTIME)))
+	save_cache_validity = nfsi->cache_validity;
 	nfsi->cache_validity &= ~(NFS_INO_INVALID_ATTR
 			| NFS_INO_INVALID_ATIME
+			| NFS_INO_REVAL_FORCED
 			| NFS_INO_REVAL_PAGECACHE);
 
 	/* Do atomic weak cache consistency updates */
@@ -1189,7 +1223,8 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
 				nfs_force_lookup_revalidate(inode);
 			nfsi->change_attr = fattr->change_attr;
 		}
-	}
+	} else if (server->caps & NFS_CAP_CHANGE_ATTR)
+		invalid |= save_cache_validity;
 
 	if (fattr->valid & NFS_ATTR_FATTR_MTIME) {
 		/* NFSv2/v3: Check if the mtime agrees */
@@ -1201,7 +1236,12 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
 				nfs_force_lookup_revalidate(inode);
 			memcpy(&inode->i_mtime, &fattr->mtime, sizeof(inode->i_mtime));
 		}
-	}
+	} else if (server->caps & NFS_CAP_MTIME)
+		invalid |= save_cache_validity & (NFS_INO_INVALID_ATTR
+				| NFS_INO_INVALID_DATA
+				| NFS_INO_REVAL_PAGECACHE
+				| NFS_INO_REVAL_FORCED);
+
 	if (fattr->valid & NFS_ATTR_FATTR_CTIME) {
 		/* If ctime has changed we should definitely clear access+acl caches */
 		if (!timespec_equal(&inode->i_ctime, &fattr->ctime)) {
@@ -1215,7 +1255,11 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
 			}
 			memcpy(&inode->i_ctime, &fattr->ctime, sizeof(inode->i_ctime));
 		}
-	}
+	} else if (server->caps & NFS_CAP_CTIME)
+		invalid |= save_cache_validity & (NFS_INO_INVALID_ATTR
+				| NFS_INO_INVALID_ACCESS
+				| NFS_INO_INVALID_ACL
+				| NFS_INO_REVAL_FORCED);
 
 	/* Check if our cached file size is stale */
 	if (fattr->valid & NFS_ATTR_FATTR_SIZE) {
@@ -1231,30 +1275,50 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
 			dprintk("NFS: isize change on server for file %s/%ld\n",
 					inode->i_sb->s_id, inode->i_ino);
 		}
-	}
+	} else
+		invalid |= save_cache_validity & (NFS_INO_INVALID_ATTR
+				| NFS_INO_REVAL_PAGECACHE
+				| NFS_INO_REVAL_FORCED);
 
 
 	if (fattr->valid & NFS_ATTR_FATTR_ATIME)
 		memcpy(&inode->i_atime, &fattr->atime, sizeof(inode->i_atime));
+	else if (server->caps & NFS_CAP_ATIME)
+		invalid |= save_cache_validity & (NFS_INO_INVALID_ATIME
+				| NFS_INO_REVAL_FORCED);
 
 	if (fattr->valid & NFS_ATTR_FATTR_MODE) {
 		if ((inode->i_mode & S_IALLUGO) != (fattr->mode & S_IALLUGO)) {
 			invalid |= NFS_INO_INVALID_ATTR|NFS_INO_INVALID_ACCESS|NFS_INO_INVALID_ACL;
 			inode->i_mode = fattr->mode;
 		}
-	}
+	} else if (server->caps & NFS_CAP_MODE)
+		invalid |= save_cache_validity & (NFS_INO_INVALID_ATTR
+				| NFS_INO_INVALID_ACCESS
+				| NFS_INO_INVALID_ACL
+				| NFS_INO_REVAL_FORCED);
+
 	if (fattr->valid & NFS_ATTR_FATTR_OWNER) {
 		if (inode->i_uid != fattr->uid) {
 			invalid |= NFS_INO_INVALID_ATTR|NFS_INO_INVALID_ACCESS|NFS_INO_INVALID_ACL;
 			inode->i_uid = fattr->uid;
 		}
-	}
+	} else if (server->caps & NFS_CAP_OWNER)
+		invalid |= save_cache_validity & (NFS_INO_INVALID_ATTR
+				| NFS_INO_INVALID_ACCESS
+				| NFS_INO_INVALID_ACL
+				| NFS_INO_REVAL_FORCED);
+
 	if (fattr->valid & NFS_ATTR_FATTR_GROUP) {
 		if (inode->i_gid != fattr->gid) {
 			invalid |= NFS_INO_INVALID_ATTR|NFS_INO_INVALID_ACCESS|NFS_INO_INVALID_ACL;
 			inode->i_gid = fattr->gid;
 		}
-	}
+	} else if (server->caps & NFS_CAP_OWNER_GROUP)
+		invalid |= save_cache_validity & (NFS_INO_INVALID_ATTR
+				| NFS_INO_INVALID_ACCESS
+				| NFS_INO_INVALID_ACL
+				| NFS_INO_REVAL_FORCED);
 
 	if (fattr->valid & NFS_ATTR_FATTR_NLINK) {
 		if (inode->i_nlink != fattr->nlink) {
@@ -1263,7 +1327,9 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
 				invalid |= NFS_INO_INVALID_DATA;
 			inode->i_nlink = fattr->nlink;
 		}
-	}
+	} else if (server->caps & NFS_CAP_NLINK)
+		invalid |= save_cache_validity & (NFS_INO_INVALID_ATTR
+				| NFS_INO_REVAL_FORCED);
 
 	if (fattr->valid & NFS_ATTR_FATTR_SPACE_USED) {
 		/*
@@ -1293,9 +1359,8 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
 				|| S_ISLNK(inode->i_mode)))
 		invalid &= ~NFS_INO_INVALID_DATA;
 	if (!nfs_have_delegation(inode, FMODE_READ) ||
-			(nfsi->cache_validity & NFS_INO_REVAL_FORCED))
+			(save_cache_validity & NFS_INO_REVAL_FORCED))
 		nfsi->cache_validity |= invalid;
-	nfsi->cache_validity &= ~NFS_INO_REVAL_FORCED;
 
 	return 0;
  out_changed:
@@ -1442,6 +1507,10 @@ static int __init init_nfs_fs(void)
 {
 	int err;
 
+	err = nfs_dns_resolver_init();
+	if (err < 0)
+		goto out8;
+
 	err = nfs_fscache_register();
 	if (err < 0)
 		goto out7;
@@ -1500,6 +1569,8 @@ out5:
 out6:
 	nfs_fscache_unregister();
 out7:
+	nfs_dns_resolver_destroy();
+out8:
 	return err;
 }
 
@@ -1511,6 +1582,7 @@ static void __exit exit_nfs_fs(void)
 	nfs_destroy_inodecache();
 	nfs_destroy_nfspagecache();
 	nfs_fscache_unregister();
+	nfs_dns_resolver_destroy();
 #ifdef CONFIG_PROC_FS
 	rpc_proc_unregister("nfs");
 #endif

fs/nfs/internal.h

@@ -48,6 +48,11 @@ struct nfs_clone_mount {
  */
 #define NFS_MAX_SECFLAVORS	(12)
 
+/*
+ * Value used if the user did not specify a port value.
+ */
+#define NFS_UNSPEC_PORT		(-1)
+
 /*
  * In-kernel mount arguments
  */
@@ -63,6 +68,7 @@ struct nfs_parsed_mount_data {
 	unsigned int		auth_flavor_len;
 	rpc_authflavor_t	auth_flavors[1];
 	char			*client_address;
+	unsigned int		version;
 	unsigned int		minorversion;
 	char			*fscache_uniq;
 
@@ -71,7 +77,7 @@ struct nfs_parsed_mount_data {
 		size_t			addrlen;
 		char			*hostname;
 		u32			version;
-		unsigned short		port;
+		int			port;
 		unsigned short		protocol;
 	} mount_server;
 
@@ -80,7 +86,7 @@ struct nfs_parsed_mount_data {
 		size_t			addrlen;
 		char			*hostname;
 		char			*export_path;
-		unsigned short		port;
+		int			port;
 		unsigned short		protocol;
 	} nfs_server;
 
@@ -102,6 +108,7 @@ struct nfs_mount_request {
 };
 
 extern int nfs_mount(struct nfs_mount_request *info);
+extern void nfs_umount(const struct nfs_mount_request *info);
 
 /* client.c */
 extern struct rpc_program nfs_program;
@@ -213,7 +220,6 @@ void nfs_zap_acl_cache(struct inode *inode);
 extern int nfs_wait_bit_killable(void *word);
 
 /* super.c */
-void nfs_parse_ip_address(char *, size_t, struct sockaddr *, size_t *);
 extern struct file_system_type nfs_xdev_fs_type;
 #ifdef CONFIG_NFS_V4
 extern struct file_system_type nfs4_xdev_fs_type;
@@ -248,6 +254,12 @@ extern void nfs_read_prepare(struct rpc_task *task, void *calldata);
 
 /* write.c */
 extern void nfs_write_prepare(struct rpc_task *task, void *calldata);
+#ifdef CONFIG_MIGRATION
+extern int nfs_migrate_page(struct address_space *,
+		struct page *, struct page *);
+#else
+#define nfs_migrate_page NULL
+#endif
 
 /* nfs4proc.c */
 extern int _nfs4_call_sync(struct nfs_server *server,
@@ -368,24 +380,3 @@ unsigned int nfs_page_array_len(unsigned int base, size_t len)
 	return ((unsigned long)len + (unsigned long)base +
 		PAGE_SIZE - 1) >> PAGE_SHIFT;
 }
-
-#define IPV6_SCOPE_DELIMITER	'%'
-
-/*
- * Set the port number in an address.  Be agnostic about the address
- * family.
- */
-static inline void nfs_set_port(struct sockaddr *sap, unsigned short port)
-{
-	struct sockaddr_in *ap = (struct sockaddr_in *)sap;
-	struct sockaddr_in6 *ap6 = (struct sockaddr_in6 *)sap;
-
-	switch (sap->sa_family) {
-	case AF_INET:
-		ap->sin_port = htons(port);
-		break;
-	case AF_INET6:
-		ap6->sin6_port = htons(port);
-		break;
-	}
-}

fs/nfs/mount_clnt.c

@@ -209,6 +209,71 @@ out_mnt_err:
 	goto out;
 }
 
+/**
+ * nfs_umount - Notify a server that we have unmounted this export
+ * @info: pointer to umount request arguments
+ *
+ * MOUNTPROC_UMNT is advisory, so we set a short timeout, and always
+ * use UDP.
+ */
+void nfs_umount(const struct nfs_mount_request *info)
+{
+	static const struct rpc_timeout nfs_umnt_timeout = {
+		.to_initval = 1 * HZ,
+		.to_maxval = 3 * HZ,
+		.to_retries = 2,
+	};
+	struct rpc_create_args args = {
+		.protocol	= IPPROTO_UDP,
+		.address	= info->sap,
+		.addrsize	= info->salen,
+		.timeout	= &nfs_umnt_timeout,
+		.servername	= info->hostname,
+		.program	= &mnt_program,
+		.version	= info->version,
+		.authflavor	= RPC_AUTH_UNIX,
+		.flags		= RPC_CLNT_CREATE_NOPING,
+	};
+	struct mountres	result;
+	struct rpc_message msg	= {
+		.rpc_argp	= info->dirpath,
+		.rpc_resp	= &result,
+	};
+	struct rpc_clnt *clnt;
+	int status;
+
+	if (info->noresvport)
+		args.flags |= RPC_CLNT_CREATE_NONPRIVPORT;
+
+	clnt = rpc_create(&args);
+	if (unlikely(IS_ERR(clnt)))
+		goto out_clnt_err;
+
+	dprintk("NFS: sending UMNT request for %s:%s\n",
+		(info->hostname ? info->hostname : "server"), info->dirpath);
+
+	if (info->version == NFS_MNT3_VERSION)
+		msg.rpc_proc = &clnt->cl_procinfo[MOUNTPROC3_UMNT];
+	else
+		msg.rpc_proc = &clnt->cl_procinfo[MOUNTPROC_UMNT];
+
+	status = rpc_call_sync(clnt, &msg, 0);
+	rpc_shutdown_client(clnt);
+
+	if (unlikely(status < 0))
+		goto out_call_err;
+
+	return;
+
+out_clnt_err:
+	dprintk("NFS: failed to create UMNT RPC client, status=%ld\n",
+			PTR_ERR(clnt));
+	return;
+
+out_call_err:
+	dprintk("NFS: UMNT request failed, status=%d\n", status);
+}
+
 /*
  * XDR encode/decode functions for MOUNT
  */
@@ -258,7 +323,7 @@ static int decode_status(struct xdr_stream *xdr, struct mountres *res)
 		return -EIO;
 	status = ntohl(*p);
 
-	for (i = 0; i <= ARRAY_SIZE(mnt_errtbl); i++) {
+	for (i = 0; i < ARRAY_SIZE(mnt_errtbl); i++) {
 		if (mnt_errtbl[i].status == status) {
 			res->errno = mnt_errtbl[i].errno;
 			return 0;
@@ -309,7 +374,7 @@ static int decode_fhs_status(struct xdr_stream *xdr, struct mountres *res)
 		return -EIO;
 	status = ntohl(*p);
 
-	for (i = 0; i <= ARRAY_SIZE(mnt3_errtbl); i++) {
+	for (i = 0; i < ARRAY_SIZE(mnt3_errtbl); i++) {
 		if (mnt3_errtbl[i].status == status) {
 			res->errno = mnt3_errtbl[i].errno;
 			return 0;
@@ -407,6 +472,13 @@ static struct rpc_procinfo mnt_procedures[] = {
 		.p_statidx	= MOUNTPROC_MNT,
 		.p_name		= "MOUNT",
 	},
+	[MOUNTPROC_UMNT] = {
+		.p_proc		= MOUNTPROC_UMNT,
+		.p_encode	= (kxdrproc_t)mnt_enc_dirpath,
+		.p_arglen	= MNT_enc_dirpath_sz,
+		.p_statidx	= MOUNTPROC_UMNT,
+		.p_name		= "UMOUNT",
+	},
 };
 
 static struct rpc_procinfo mnt3_procedures[] = {
@@ -419,6 +491,13 @@ static struct rpc_procinfo mnt3_procedures[] = {
 		.p_statidx	= MOUNTPROC3_MNT,
 		.p_name		= "MOUNT",
 	},
+	[MOUNTPROC3_UMNT] = {
+		.p_proc		= MOUNTPROC3_UMNT,
+		.p_encode	= (kxdrproc_t)mnt_enc_dirpath,
+		.p_arglen	= MNT_enc_dirpath_sz,
+		.p_statidx	= MOUNTPROC3_UMNT,
+		.p_name		= "UMOUNT",
+	},
 };
 
 

fs/nfs/nfs3proc.c

@@ -299,7 +299,6 @@ static void nfs3_free_createdata(struct nfs3_createdata *data)
 
 /*
  * Create a regular file.
- * For now, we don't implement O_EXCL.
  */
 static int
 nfs3_proc_create(struct inode *dir, struct dentry *dentry, struct iattr *sattr,

fs/nfs/nfs4namespace.c

@@ -17,6 +17,7 @@
 #include <linux/inet.h>
 #include "internal.h"
 #include "nfs4_fs.h"
+#include "dns_resolve.h"
 
 #define NFSDBG_FACILITY		NFSDBG_VFS
 
@@ -95,6 +96,20 @@ static int nfs4_validate_fspath(const struct vfsmount *mnt_parent,
 	return 0;
 }
 
+static size_t nfs_parse_server_name(char *string, size_t len,
+		struct sockaddr *sa, size_t salen)
+{
+	ssize_t ret;
+
+	ret = rpc_pton(string, len, sa, salen);
+	if (ret == 0) {
+		ret = nfs_dns_resolve_name(string, len, sa, salen);
+		if (ret < 0)
+			ret = 0;
+	}
+	return ret;
+}
+
 static struct vfsmount *try_location(struct nfs_clone_mount *mountdata,
 				     char *page, char *page2,
 				     const struct nfs4_fs_location *location)
@@ -121,11 +136,12 @@ static struct vfsmount *try_location(struct nfs_clone_mount *mountdata,
 
 		if (memchr(buf->data, IPV6_SCOPE_DELIMITER, buf->len))
 			continue;
-		nfs_parse_ip_address(buf->data, buf->len,
+		mountdata->addrlen = nfs_parse_server_name(buf->data,
-				mountdata->addr, &mountdata->addrlen);
+				buf->len,
-		if (mountdata->addr->sa_family == AF_UNSPEC)
+				mountdata->addr, mountdata->addrlen);
+		if (mountdata->addrlen == 0)
 			continue;
-		nfs_set_port(mountdata->addr, NFS_PORT);
+		rpc_set_port(mountdata->addr, NFS_PORT);
 
 		memcpy(page2, buf->data, buf->len);
 		page2[buf->len] = '\0';

fs/nfs/nfs4proc.c

@@ -61,6 +61,8 @@
 #define NFS4_POLL_RETRY_MIN	(HZ/10)
 #define NFS4_POLL_RETRY_MAX	(15*HZ)
 
+#define NFS4_MAX_LOOP_ON_RECOVER (10)
+
 struct nfs4_opendata;
 static int _nfs4_proc_open(struct nfs4_opendata *data);
 static int nfs4_do_fsinfo(struct nfs_server *, struct nfs_fh *, struct nfs_fsinfo *);
@@ -426,17 +428,19 @@ out:
 static int nfs4_recover_session(struct nfs4_session *session)
 {
 	struct nfs_client *clp = session->clp;
+	unsigned int loop;
 	int ret;
 
-	for (;;) {
+	for (loop = NFS4_MAX_LOOP_ON_RECOVER; loop != 0; loop--) {
 		ret = nfs4_wait_clnt_recover(clp);
 		if (ret != 0)
-				return ret;
+			break;
 		if (!test_bit(NFS4CLNT_SESSION_SETUP, &clp->cl_state))
 			break;
 		nfs4_schedule_state_manager(clp);
+		ret = -EIO;
 	}
-	return 0;
+	return ret;
 }
 
 static int nfs41_setup_sequence(struct nfs4_session *session,
@@ -1444,18 +1448,20 @@ static int _nfs4_proc_open(struct nfs4_opendata *data)
 static int nfs4_recover_expired_lease(struct nfs_server *server)
 {
 	struct nfs_client *clp = server->nfs_client;
+	unsigned int loop;
 	int ret;
 
-	for (;;) {
+	for (loop = NFS4_MAX_LOOP_ON_RECOVER; loop != 0; loop--) {
 		ret = nfs4_wait_clnt_recover(clp);
 		if (ret != 0)
-			return ret;
+			break;
 		if (!test_bit(NFS4CLNT_LEASE_EXPIRED, &clp->cl_state) &&
 		    !test_bit(NFS4CLNT_CHECK_LEASE,&clp->cl_state))
 			break;
 		nfs4_schedule_state_recovery(clp);
+		ret = -EIO;
 	}
-	return 0;
+	return ret;
 }
 
 /*
@@ -1997,12 +2003,34 @@ static int _nfs4_server_capabilities(struct nfs_server *server, struct nfs_fh *f
 	status = nfs4_call_sync(server, &msg, &args, &res, 0);
 	if (status == 0) {
 		memcpy(server->attr_bitmask, res.attr_bitmask, sizeof(server->attr_bitmask));
+		server->caps &= ~(NFS_CAP_ACLS|NFS_CAP_HARDLINKS|
+				NFS_CAP_SYMLINKS|NFS_CAP_FILEID|
+				NFS_CAP_MODE|NFS_CAP_NLINK|NFS_CAP_OWNER|
+				NFS_CAP_OWNER_GROUP|NFS_CAP_ATIME|
+				NFS_CAP_CTIME|NFS_CAP_MTIME);
 		if (res.attr_bitmask[0] & FATTR4_WORD0_ACL)
 			server->caps |= NFS_CAP_ACLS;
 		if (res.has_links != 0)
 			server->caps |= NFS_CAP_HARDLINKS;
 		if (res.has_symlinks != 0)
 			server->caps |= NFS_CAP_SYMLINKS;
+		if (res.attr_bitmask[0] & FATTR4_WORD0_FILEID)
+			server->caps |= NFS_CAP_FILEID;
+		if (res.attr_bitmask[1] & FATTR4_WORD1_MODE)
+			server->caps |= NFS_CAP_MODE;
+		if (res.attr_bitmask[1] & FATTR4_WORD1_NUMLINKS)
+			server->caps |= NFS_CAP_NLINK;
+		if (res.attr_bitmask[1] & FATTR4_WORD1_OWNER)
+			server->caps |= NFS_CAP_OWNER;
+		if (res.attr_bitmask[1] & FATTR4_WORD1_OWNER_GROUP)
+			server->caps |= NFS_CAP_OWNER_GROUP;
+		if (res.attr_bitmask[1] & FATTR4_WORD1_TIME_ACCESS)
+			server->caps |= NFS_CAP_ATIME;
+		if (res.attr_bitmask[1] & FATTR4_WORD1_TIME_METADATA)
+			server->caps |= NFS_CAP_CTIME;
+		if (res.attr_bitmask[1] & FATTR4_WORD1_TIME_MODIFY)
+			server->caps |= NFS_CAP_MTIME;
+
 		memcpy(server->cache_consistency_bitmask, res.attr_bitmask, sizeof(server->cache_consistency_bitmask));
 		server->cache_consistency_bitmask[0] &= FATTR4_WORD0_CHANGE|FATTR4_WORD0_SIZE;
 		server->cache_consistency_bitmask[1] &= FATTR4_WORD1_TIME_METADATA|FATTR4_WORD1_TIME_MODIFY;

fs/nfs/super.c

@@ -73,7 +73,7 @@ enum {
 	Opt_cto, Opt_nocto,
 	Opt_ac, Opt_noac,
 	Opt_lock, Opt_nolock,
-	Opt_v2, Opt_v3,
+	Opt_v2, Opt_v3, Opt_v4,
 	Opt_udp, Opt_tcp, Opt_rdma,
 	Opt_acl, Opt_noacl,
 	Opt_rdirplus, Opt_nordirplus,
@@ -127,6 +127,7 @@ static const match_table_t nfs_mount_option_tokens = {
 	{ Opt_nolock, "nolock" },
 	{ Opt_v2, "v2" },
 	{ Opt_v3, "v3" },
+	{ Opt_v4, "v4" },
 	{ Opt_udp, "udp" },
 	{ Opt_tcp, "tcp" },
 	{ Opt_rdma, "rdma" },
@@ -158,7 +159,7 @@ static const match_table_t nfs_mount_option_tokens = {
 	{ Opt_mountvers, "mountvers=%s" },
 	{ Opt_nfsvers, "nfsvers=%s" },
 	{ Opt_nfsvers, "vers=%s" },
-	{ Opt_minorversion, "minorversion=%u" },
+	{ Opt_minorversion, "minorversion=%s" },
 
 	{ Opt_sec, "sec=%s" },
 	{ Opt_proto, "proto=%s" },
@@ -272,6 +273,10 @@ static const struct super_operations nfs_sops = {
 };
 
 #ifdef CONFIG_NFS_V4
+static int nfs4_validate_text_mount_data(void *options,
+	struct nfs_parsed_mount_data *args, const char *dev_name);
+static int nfs4_try_mount(int flags, const char *dev_name,
+	struct nfs_parsed_mount_data *data, struct vfsmount *mnt);
 static int nfs4_get_sb(struct file_system_type *fs_type,
 	int flags, const char *dev_name, void *raw_data, struct vfsmount *mnt);
 static int nfs4_remote_get_sb(struct file_system_type *fs_type,
@@ -742,127 +747,23 @@ static int nfs_verify_server_address(struct sockaddr *addr)
 	}
 	}
 
+	dfprintk(MOUNT, "NFS: Invalid IP address specified\n");
 	return 0;
 }
 
-static void nfs_parse_ipv4_address(char *string, size_t str_len,
-				   struct sockaddr *sap, size_t *addr_len)
-{
-	struct sockaddr_in *sin = (struct sockaddr_in *)sap;
-	u8 *addr = (u8 *)&sin->sin_addr.s_addr;
-
-	if (str_len <= INET_ADDRSTRLEN) {
-		dfprintk(MOUNT, "NFS: parsing IPv4 address %*s\n",
-				(int)str_len, string);
-
-		sin->sin_family = AF_INET;
-		*addr_len = sizeof(*sin);
-		if (in4_pton(string, str_len, addr, '\0', NULL))
-			return;
-	}
-
-	sap->sa_family = AF_UNSPEC;
-	*addr_len = 0;
-}
-
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
-static int nfs_parse_ipv6_scope_id(const char *string, const size_t str_len,
-				   const char *delim,
-				   struct sockaddr_in6 *sin6)
-{
-	char *p;
-	size_t len;
-
-	if ((string + str_len) == delim)
-		return 1;
-
-	if (*delim != IPV6_SCOPE_DELIMITER)
-		return 0;
-
-	if (!(ipv6_addr_type(&sin6->sin6_addr) & IPV6_ADDR_LINKLOCAL))
-		return 0;
-
-	len = (string + str_len) - delim - 1;
-	p = kstrndup(delim + 1, len, GFP_KERNEL);
-	if (p) {
-		unsigned long scope_id = 0;
-		struct net_device *dev;
-
-		dev = dev_get_by_name(&init_net, p);
-		if (dev != NULL) {
-			scope_id = dev->ifindex;
-			dev_put(dev);
-		} else {
-			if (strict_strtoul(p, 10, &scope_id) == 0) {
-				kfree(p);
-				return 0;
-			}
-		}
-
-		kfree(p);
-
-		sin6->sin6_scope_id = scope_id;
-		dfprintk(MOUNT, "NFS: IPv6 scope ID = %lu\n", scope_id);
-		return 1;
-	}
-
-	return 0;
-}
-
-static void nfs_parse_ipv6_address(char *string, size_t str_len,
-				   struct sockaddr *sap, size_t *addr_len)
-{
-	struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *)sap;
-	u8 *addr = (u8 *)&sin6->sin6_addr.in6_u;
-	const char *delim;
-
-	if (str_len <= INET6_ADDRSTRLEN) {
-		dfprintk(MOUNT, "NFS: parsing IPv6 address %*s\n",
-				(int)str_len, string);
-
-		sin6->sin6_family = AF_INET6;
-		*addr_len = sizeof(*sin6);
-		if (in6_pton(string, str_len, addr,
-					IPV6_SCOPE_DELIMITER, &delim) != 0) {
-			if (nfs_parse_ipv6_scope_id(string, str_len,
-							delim, sin6) != 0)
-				return;
-		}
-	}
-
-	sap->sa_family = AF_UNSPEC;
-	*addr_len = 0;
-}
-#else
-static void nfs_parse_ipv6_address(char *string, size_t str_len,
-				   struct sockaddr *sap, size_t *addr_len)
-{
-	sap->sa_family = AF_UNSPEC;
-	*addr_len = 0;
-}
-#endif
-
 /*
- * Construct a sockaddr based on the contents of a string that contains
+ * Select between a default port value and a user-specified port value.
- * an IP address in presentation format.
+ * If a zero value is set, then autobind will be used.
- *
- * If there is a problem constructing the new sockaddr, set the address
- * family to AF_UNSPEC.
  */
-void nfs_parse_ip_address(char *string, size_t str_len,
+static void nfs_set_default_port(struct sockaddr *sap, const int parsed_port,
-				 struct sockaddr *sap, size_t *addr_len)
+				 const unsigned short default_port)
 {
-	unsigned int i, colons;
+	unsigned short port = default_port;
 
-	colons = 0;
+	if (parsed_port != NFS_UNSPEC_PORT)
-	for (i = 0; i < str_len; i++)
+		port = parsed_port;
-		if (string[i] == ':')
-			colons++;
 
-	if (colons >= 2)
+	rpc_set_port(sap, port);
-		nfs_parse_ipv6_address(string, str_len, sap, addr_len);
-	else
-		nfs_parse_ipv4_address(string, str_len, sap, addr_len);
 }
 
 /*
@@ -904,8 +805,6 @@ static void nfs_set_mount_transport_protocol(struct nfs_parsed_mount_data *mnt)
 
 /*
  * Parse the value of the 'sec=' option.
- *
- * The flavor_len setting is for v4 mounts.
  */
 static int nfs_parse_security_flavors(char *value,
 				      struct nfs_parsed_mount_data *mnt)
@@ -916,53 +815,43 @@ static int nfs_parse_security_flavors(char *value,
 
 	switch (match_token(value, nfs_secflavor_tokens, args)) {
 	case Opt_sec_none:
-		mnt->auth_flavor_len = 0;
 		mnt->auth_flavors[0] = RPC_AUTH_NULL;
 		break;
 	case Opt_sec_sys:
-		mnt->auth_flavor_len = 0;
 		mnt->auth_flavors[0] = RPC_AUTH_UNIX;
 		break;
 	case Opt_sec_krb5:
-		mnt->auth_flavor_len = 1;
 		mnt->auth_flavors[0] = RPC_AUTH_GSS_KRB5;
 		break;
 	case Opt_sec_krb5i:
-		mnt->auth_flavor_len = 1;
 		mnt->auth_flavors[0] = RPC_AUTH_GSS_KRB5I;
 		break;
 	case Opt_sec_krb5p:
-		mnt->auth_flavor_len = 1;
 		mnt->auth_flavors[0] = RPC_AUTH_GSS_KRB5P;
 		break;
 	case Opt_sec_lkey:
-		mnt->auth_flavor_len = 1;
 		mnt->auth_flavors[0] = RPC_AUTH_GSS_LKEY;
 		break;
 	case Opt_sec_lkeyi:
-		mnt->auth_flavor_len = 1;
 		mnt->auth_flavors[0] = RPC_AUTH_GSS_LKEYI;
 		break;
 	case Opt_sec_lkeyp:
-		mnt->auth_flavor_len = 1;
 		mnt->auth_flavors[0] = RPC_AUTH_GSS_LKEYP;
 		break;
 	case Opt_sec_spkm:
-		mnt->auth_flavor_len = 1;
 		mnt->auth_flavors[0] = RPC_AUTH_GSS_SPKM;
 		break;
 	case Opt_sec_spkmi:
-		mnt->auth_flavor_len = 1;
 		mnt->auth_flavors[0] = RPC_AUTH_GSS_SPKMI;
 		break;
 	case Opt_sec_spkmp:
-		mnt->auth_flavor_len = 1;
 		mnt->auth_flavors[0] = RPC_AUTH_GSS_SPKMP;
 		break;
 	default:
 		return 0;
 	}
 
+	mnt->auth_flavor_len = 1;
 	return 1;
 }
 
@@ -1001,7 +890,6 @@ static int nfs_parse_mount_options(char *raw,
 	while ((p = strsep(&raw, ",")) != NULL) {
 		substring_t args[MAX_OPT_ARGS];
 		unsigned long option;
-		int int_option;
 		int token;
 
 		if (!*p)
@@ -1047,10 +935,18 @@ static int nfs_parse_mount_options(char *raw,
 			break;
 		case Opt_v2:
 			mnt->flags &= ~NFS_MOUNT_VER3;
+			mnt->version = 2;
 			break;
 		case Opt_v3:
 			mnt->flags |= NFS_MOUNT_VER3;
+			mnt->version = 3;
 			break;
+#ifdef CONFIG_NFS_V4
+		case Opt_v4:
+			mnt->flags &= ~NFS_MOUNT_VER3;
+			mnt->version = 4;
+			break;
+#endif
 		case Opt_udp:
 			mnt->flags &= ~NFS_MOUNT_TCP;
 			mnt->nfs_server.protocol = XPRT_TRANSPORT_UDP;
@@ -1264,20 +1160,33 @@ static int nfs_parse_mount_options(char *raw,
 			switch (option) {
 			case NFS2_VERSION:
 				mnt->flags &= ~NFS_MOUNT_VER3;
+				mnt->version = 2;
 				break;
 			case NFS3_VERSION:
 				mnt->flags |= NFS_MOUNT_VER3;
+				mnt->version = 3;
 				break;
+#ifdef CONFIG_NFS_V4
+			case NFS4_VERSION:
+				mnt->flags &= ~NFS_MOUNT_VER3;
+				mnt->version = 4;
+				break;
+#endif
 			default:
 				goto out_invalid_value;
 			}
 			break;
 		case Opt_minorversion:
-			if (match_int(args, &int_option))
+			string = match_strdup(args);
-				return 0;
+			if (string == NULL)
-			if (int_option < 0 || int_option > NFS4_MAX_MINOR_VERSION)
+				goto out_nomem;
-				return 0;
+			rc = strict_strtoul(string, 10, &option);
-			mnt->minorversion = int_option;
+			kfree(string);
+			if (rc != 0)
+				goto out_invalid_value;
+			if (option > NFS4_MAX_MINOR_VERSION)
+				goto out_invalid_value;
+			mnt->minorversion = option;
 			break;
 
 		/*
@@ -1352,11 +1261,14 @@ static int nfs_parse_mount_options(char *raw,
 			string = match_strdup(args);
 			if (string == NULL)
 				goto out_nomem;
-			nfs_parse_ip_address(string, strlen(string),
+			mnt->nfs_server.addrlen =
+				rpc_pton(string, strlen(string),
 					(struct sockaddr *)
 					&mnt->nfs_server.address,
-					     &mnt->nfs_server.addrlen);
+					sizeof(mnt->nfs_server.address));
 			kfree(string);
+			if (mnt->nfs_server.addrlen == 0)
+				goto out_invalid_address;
 			break;
 		case Opt_clientaddr:
 			string = match_strdup(args);
@@ -1376,11 +1288,14 @@ static int nfs_parse_mount_options(char *raw,
 			string = match_strdup(args);
 			if (string == NULL)
 				goto out_nomem;
-			nfs_parse_ip_address(string, strlen(string),
+			mnt->mount_server.addrlen =
+				rpc_pton(string, strlen(string),
 					(struct sockaddr *)
 					&mnt->mount_server.address,
-					     &mnt->mount_server.addrlen);
+					sizeof(mnt->mount_server.address));
 			kfree(string);
+			if (mnt->mount_server.addrlen == 0)
+				goto out_invalid_address;
 			break;
 		case Opt_lookupcache:
 			string = match_strdup(args);
@@ -1432,8 +1347,11 @@ static int nfs_parse_mount_options(char *raw,
 
 	return 1;
 
+out_invalid_address:
+	printk(KERN_INFO "NFS: bad IP address specified: %s\n", p);
+	return 0;
 out_invalid_value:
-	printk(KERN_INFO "NFS: bad mount option value specified: %s \n", p);
+	printk(KERN_INFO "NFS: bad mount option value specified: %s\n", p);
 	return 0;
 out_nomem:
 	printk(KERN_INFO "NFS: not enough memory to parse option\n");
@@ -1444,6 +1362,52 @@ out_security_failure:
 	return 0;
 }
 
+/*
+ * Match the requested auth flavors with the list returned by
+ * the server.  Returns zero and sets the mount's authentication
+ * flavor on success; returns -EACCES if server does not support
+ * the requested flavor.
+ */
+static int nfs_walk_authlist(struct nfs_parsed_mount_data *args,
+			     struct nfs_mount_request *request)
+{
+	unsigned int i, j, server_authlist_len = *(request->auth_flav_len);
+
+	/*
+	 * Certain releases of Linux's mountd return an empty
+	 * flavor list.  To prevent behavioral regression with
+	 * these servers (ie. rejecting mounts that used to
+	 * succeed), revert to pre-2.6.32 behavior (no checking)
+	 * if the returned flavor list is empty.
+	 */
+	if (server_authlist_len == 0)
+		return 0;
+
+	/*
+	 * We avoid sophisticated negotiating here, as there are
+	 * plenty of cases where we can get it wrong, providing
+	 * either too little or too much security.
+	 *
+	 * RFC 2623, section 2.7 suggests we SHOULD prefer the
+	 * flavor listed first.  However, some servers list
+	 * AUTH_NULL first.  Our caller plants AUTH_SYS, the
+	 * preferred default, in args->auth_flavors[0] if user
+	 * didn't specify sec= mount option.
+	 */
+	for (i = 0; i < args->auth_flavor_len; i++)
+		for (j = 0; j < server_authlist_len; j++)
+			if (args->auth_flavors[i] == request->auth_flavs[j]) {
+				dfprintk(MOUNT, "NFS: using auth flavor %d\n",
+					request->auth_flavs[j]);
+				args->auth_flavors[0] = request->auth_flavs[j];
+				return 0;
+			}
+
+	dfprintk(MOUNT, "NFS: server does not support requested auth flavor\n");
+	nfs_umount(request);
+	return -EACCES;
+}
+
 /*
  * Use the remote server's MOUNT service to request the NFS file handle
  * corresponding to the provided path.
@@ -1451,7 +1415,8 @@ out_security_failure:
 static int nfs_try_mount(struct nfs_parsed_mount_data *args,
 			 struct nfs_fh *root_fh)
 {
-	unsigned int auth_flavor_len = 0;
+	rpc_authflavor_t server_authlist[NFS_MAX_SECFLAVORS];
+	unsigned int server_authlist_len = ARRAY_SIZE(server_authlist);
 	struct nfs_mount_request request = {
 		.sap		= (struct sockaddr *)
 						&args->mount_server.address,
@@ -1459,7 +1424,8 @@ static int nfs_try_mount(struct nfs_parsed_mount_data *args,
 		.protocol	= args->mount_server.protocol,
 		.fh		= root_fh,
 		.noresvport	= args->flags & NFS_MOUNT_NORESVPORT,
-		.auth_flav_len	= &auth_flavor_len,
+		.auth_flav_len	= &server_authlist_len,
+		.auth_flavs	= server_authlist,
 	};
 	int status;
 
@@ -1485,23 +1451,25 @@ static int nfs_try_mount(struct nfs_parsed_mount_data *args,
 		args->mount_server.addrlen = args->nfs_server.addrlen;
 	}
 	request.salen = args->mount_server.addrlen;
-
+	nfs_set_default_port(request.sap, args->mount_server.port, 0);
-	/*
-	 * autobind will be used if mount_server.port == 0
-	 */
-	nfs_set_port(request.sap, args->mount_server.port);
 
 	/*
 	 * Now ask the mount server to map our export path
 	 * to a file handle.
 	 */
 	status = nfs_mount(&request);
-	if (status == 0)
+	if (status != 0) {
-		return 0;
-
 		dfprintk(MOUNT, "NFS: unable to mount server %s, error %d\n",
 				request.hostname, status);
 		return status;
+	}
+
+	/*
+	 * MNTv1 (NFSv2) does not support auth flavor negotiation.
+	 */
+	if (args->mount_server.version != NFS_MNT3_VERSION)
+		return 0;
+	return nfs_walk_authlist(args, &request);
 }
 
 static int nfs_parse_simple_hostname(const char *dev_name,
@@ -1661,6 +1629,7 @@ static int nfs_validate_mount_data(void *options,
 				   const char *dev_name)
 {
 	struct nfs_mount_data *data = (struct nfs_mount_data *)options;
+	struct sockaddr *sap = (struct sockaddr *)&args->nfs_server.address;
 
 	if (data == NULL)
 		goto out_no_data;
@@ -1672,10 +1641,12 @@ static int nfs_validate_mount_data(void *options,
 	args->acregmax		= NFS_DEF_ACREGMAX;
 	args->acdirmin		= NFS_DEF_ACDIRMIN;
 	args->acdirmax		= NFS_DEF_ACDIRMAX;
-	args->mount_server.port	= 0;	/* autobind unless user sets port */
+	args->mount_server.port	= NFS_UNSPEC_PORT;
-	args->nfs_server.port	= 0;	/* autobind unless user sets port */
+	args->nfs_server.port	= NFS_UNSPEC_PORT;
 	args->nfs_server.protocol = XPRT_TRANSPORT_TCP;
 	args->auth_flavors[0]	= RPC_AUTH_UNIX;
+	args->auth_flavor_len	= 1;
+	args->minorversion	= 0;
 
 	switch (data->version) {
 	case 1:
@@ -1697,8 +1668,11 @@ static int nfs_validate_mount_data(void *options,
 			if (data->root.size > NFS3_FHSIZE || data->root.size == 0)
 				goto out_invalid_fh;
 			mntfh->size = data->root.size;
-		} else
+			args->version = 3;
+		} else {
 			mntfh->size = NFS2_FHSIZE;
+			args->version = 2;
+		}
 
 
 		memcpy(mntfh->data, data->root.data, mntfh->size);
@@ -1720,11 +1694,9 @@ static int nfs_validate_mount_data(void *options,
 		args->acdirmin		= data->acdirmin;
 		args->acdirmax		= data->acdirmax;
 
-		memcpy(&args->nfs_server.address, &data->addr,
+		memcpy(sap, &data->addr, sizeof(data->addr));
-		       sizeof(data->addr));
 		args->nfs_server.addrlen = sizeof(data->addr);
-		if (!nfs_verify_server_address((struct sockaddr *)
+		if (!nfs_verify_server_address(sap))
-						&args->nfs_server.address))
 			goto out_no_address;
 
 		if (!(data->flags & NFS_MOUNT_TCP))
@@ -1772,12 +1744,18 @@ static int nfs_validate_mount_data(void *options,
 		if (nfs_parse_mount_options((char *)options, args) == 0)
 			return -EINVAL;
 
-		if (!nfs_verify_server_address((struct sockaddr *)
+		if (!nfs_verify_server_address(sap))
-						&args->nfs_server.address))
 			goto out_no_address;
 
-		nfs_set_port((struct sockaddr *)&args->nfs_server.address,
+		if (args->version == 4)
-				args->nfs_server.port);
+#ifdef CONFIG_NFS_V4
+			return nfs4_validate_text_mount_data(options,
+							     args, dev_name);
+#else
+			goto out_v4_not_compiled;
+#endif
+
+		nfs_set_default_port(sap, args->nfs_server.port, 0);
 
 		nfs_set_mount_transport_protocol(args);
 
@@ -1825,6 +1803,12 @@ out_v3_not_compiled:
 	return -EPROTONOSUPPORT;
 #endif /* !CONFIG_NFS_V3 */
 
+#ifndef CONFIG_NFS_V4
+out_v4_not_compiled:
+	dfprintk(MOUNT, "NFS: NFSv4 is not compiled into kernel\n");
+	return -EPROTONOSUPPORT;
+#endif /* !CONFIG_NFS_V4 */
+
 out_nomem:
 	dfprintk(MOUNT, "NFS: not enough memory to handle mount options\n");
 	return -ENOMEM;
@@ -2120,6 +2104,14 @@ static int nfs_get_sb(struct file_system_type *fs_type,
 	if (error < 0)
 		goto out;
 
+#ifdef CONFIG_NFS_V4
+	if (data->version == 4) {
+		error = nfs4_try_mount(flags, dev_name, data, mnt);
+		kfree(data->client_address);
+		goto out;
+	}
+#endif	/* CONFIG_NFS_V4 */
+
 	/* Get a volume representation */
 	server = nfs_create_server(data, mntfh);
 	if (IS_ERR(server)) {
@@ -2317,6 +2309,43 @@ static void nfs4_validate_mount_flags(struct nfs_parsed_mount_data *args)
 	args->flags &= ~(NFS_MOUNT_NONLM|NFS_MOUNT_NOACL|NFS_MOUNT_VER3);
 }
 
+static int nfs4_validate_text_mount_data(void *options,
+					 struct nfs_parsed_mount_data *args,
+					 const char *dev_name)
+{
+	struct sockaddr *sap = (struct sockaddr *)&args->nfs_server.address;
+
+	nfs_set_default_port(sap, args->nfs_server.port, NFS_PORT);
+
+	nfs_validate_transport_protocol(args);
+
+	nfs4_validate_mount_flags(args);
+
+	if (args->version != 4) {
+		dfprintk(MOUNT,
+			 "NFS4: Illegal mount version\n");
+		return -EINVAL;
+	}
+
+	if (args->auth_flavor_len > 1) {
+		dfprintk(MOUNT,
+			 "NFS4: Too many RPC auth flavours specified\n");
+		return -EINVAL;
+	}
+
+	if (args->client_address == NULL) {
+		dfprintk(MOUNT,
+			 "NFS4: mount program didn't pass callback address\n");
+		return -EINVAL;
+	}
+
+	return nfs_parse_devname(dev_name,
+				   &args->nfs_server.hostname,
+				   NFS4_MAXNAMLEN,
+				   &args->nfs_server.export_path,
+				   NFS4_MAXPATHLEN);
+}
+
 /*
  * Validate NFSv4 mount options
  */
@@ -2324,7 +2353,7 @@ static int nfs4_validate_mount_data(void *options,
 				    struct nfs_parsed_mount_data *args,
 				    const char *dev_name)
 {
-	struct sockaddr_in *ap;
+	struct sockaddr *sap = (struct sockaddr *)&args->nfs_server.address;
 	struct nfs4_mount_data *data = (struct nfs4_mount_data *)options;
 	char *c;
 
@@ -2337,23 +2366,22 @@ static int nfs4_validate_mount_data(void *options,
 	args->acregmax		= NFS_DEF_ACREGMAX;
 	args->acdirmin		= NFS_DEF_ACDIRMIN;
 	args->acdirmax		= NFS_DEF_ACDIRMAX;
-	args->nfs_server.port	= NFS_PORT; /* 2049 unless user set port= */
+	args->nfs_server.port	= NFS_UNSPEC_PORT;
 	args->auth_flavors[0]	= RPC_AUTH_UNIX;
-	args->auth_flavor_len	= 0;
+	args->auth_flavor_len	= 1;
+	args->version		= 4;
 	args->minorversion	= 0;
 
 	switch (data->version) {
 	case 1:
-		ap = (struct sockaddr_in *)&args->nfs_server.address;
 		if (data->host_addrlen > sizeof(args->nfs_server.address))
 			goto out_no_address;
 		if (data->host_addrlen == 0)
 			goto out_no_address;
 		args->nfs_server.addrlen = data->host_addrlen;
-		if (copy_from_user(ap, data->host_addr, data->host_addrlen))
+		if (copy_from_user(sap, data->host_addr, data->host_addrlen))
 			return -EFAULT;
-		if (!nfs_verify_server_address((struct sockaddr *)
+		if (!nfs_verify_server_address(sap))
-						&args->nfs_server.address))
 			goto out_no_address;
 
 		if (data->auth_flavourlen) {
@@ -2399,39 +2427,14 @@ static int nfs4_validate_mount_data(void *options,
 		nfs_validate_transport_protocol(args);
 
 		break;
-	default: {
+	default:
-		int status;
-
 		if (nfs_parse_mount_options((char *)options, args) == 0)
 			return -EINVAL;
 
-		if (!nfs_verify_server_address((struct sockaddr *)
+		if (!nfs_verify_server_address(sap))
-						&args->nfs_server.address))
 			return -EINVAL;
 
-		nfs_set_port((struct sockaddr *)&args->nfs_server.address,
+		return nfs4_validate_text_mount_data(options, args, dev_name);
-				args->nfs_server.port);
-
-		nfs_validate_transport_protocol(args);
-
-		nfs4_validate_mount_flags(args);
-
-		if (args->auth_flavor_len > 1)
-			goto out_inval_auth;
-
-		if (args->client_address == NULL)
-			goto out_no_client_address;
-
-		status = nfs_parse_devname(dev_name,
-					   &args->nfs_server.hostname,
-					   NFS4_MAXNAMLEN,
-					   &args->nfs_server.export_path,
-					   NFS4_MAXPATHLEN);
-		if (status < 0)
-			return status;
-
-		break;
-		}
 	}
 
 	return 0;
@@ -2448,10 +2451,6 @@ out_inval_auth:
 out_no_address:
 	dfprintk(MOUNT, "NFS4: mount program didn't pass remote address\n");
 	return -EINVAL;
-
-out_no_client_address:
-	dfprintk(MOUNT, "NFS4: mount program didn't pass callback address\n");
-	return -EINVAL;
 }
 
 /*
@@ -2618,25 +2617,15 @@ out_err:
 	return ret;
 }
 
-/*
+static int nfs4_try_mount(int flags, const char *dev_name,
- * Get the superblock for an NFS4 mountpoint
+			 struct nfs_parsed_mount_data *data,
- */
+			 struct vfsmount *mnt)
-static int nfs4_get_sb(struct file_system_type *fs_type,
-	int flags, const char *dev_name, void *raw_data, struct vfsmount *mnt)
 {
-	struct nfs_parsed_mount_data *data;
 	char *export_path;
 	struct vfsmount *root_mnt;
-	int error = -ENOMEM;
+	int error;
 
-	data = kzalloc(sizeof(*data), GFP_KERNEL);
+	dfprintk(MOUNT, "--> nfs4_try_mount()\n");
-	if (data == NULL)
-		goto out_free_data;
-
-	/* Validate the mount data */
-	error = nfs4_validate_mount_data(raw_data, data, dev_name);
-	if (error < 0)
-		goto out;
 
 	export_path = data->nfs_server.export_path;
 	data->nfs_server.export_path = "/";
@@ -2650,6 +2639,32 @@ static int nfs4_get_sb(struct file_system_type *fs_type,
 
 	error = nfs_follow_remote_path(root_mnt, export_path, mnt);
 
+out:
+	dfprintk(MOUNT, "<-- nfs4_try_mount() = %d%s\n", error,
+			error != 0 ? " [error]" : "");
+	return error;
+}
+
+/*
+ * Get the superblock for an NFS4 mountpoint
+ */
+static int nfs4_get_sb(struct file_system_type *fs_type,
+	int flags, const char *dev_name, void *raw_data, struct vfsmount *mnt)
+{
+	struct nfs_parsed_mount_data *data;
+	int error = -ENOMEM;
+
+	data = kzalloc(sizeof(*data), GFP_KERNEL);
+	if (data == NULL)
+		goto out_free_data;
+
+	/* Validate the mount data */
+	error = nfs4_validate_mount_data(raw_data, data, dev_name);
+	if (error < 0)
+		goto out;
+
+	error = nfs4_try_mount(flags, dev_name, data, mnt);
+
 out:
 	kfree(data->client_address);
 	kfree(data->nfs_server.export_path);

fs/nfs/write.c

@@ -13,6 +13,7 @@
 #include <linux/file.h>
 #include <linux/writeback.h>
 #include <linux/swap.h>
+#include <linux/migrate.h>
 
 #include <linux/sunrpc/clnt.h>
 #include <linux/nfs_fs.h>
@@ -26,6 +27,7 @@
 #include "internal.h"
 #include "iostat.h"
 #include "nfs4_fs.h"
+#include "fscache.h"
 
 #define NFSDBG_FACILITY		NFSDBG_PAGECACHE
 
@@ -218,24 +220,17 @@ static void nfs_end_page_writeback(struct page *page)
 		clear_bdi_congested(&nfss->backing_dev_info, BLK_RW_ASYNC);
 }
 
-/*
+static struct nfs_page *nfs_find_and_lock_request(struct page *page)
- * Find an associated nfs write request, and prepare to flush it out
- * May return an error if the user signalled nfs_wait_on_request().
- */
-static int nfs_page_async_flush(struct nfs_pageio_descriptor *pgio,
-				struct page *page)
 {
 	struct inode *inode = page->mapping->host;
 	struct nfs_page *req;
 	int ret;
 
 	spin_lock(&inode->i_lock);
-	for(;;) {
+	for (;;) {
 		req = nfs_page_find_request_locked(page);
-		if (req == NULL) {
+		if (req == NULL)
-			spin_unlock(&inode->i_lock);
+			break;
-			return 0;
-		}
 		if (nfs_set_page_tag_locked(req))
 			break;
 		/* Note: If we hold the page lock, as is the case in nfs_writepage,
@@ -247,23 +242,40 @@ static int nfs_page_async_flush(struct nfs_pageio_descriptor *pgio,
 		ret = nfs_wait_on_request(req);
 		nfs_release_request(req);
 		if (ret != 0)
-			return ret;
+			return ERR_PTR(ret);
 		spin_lock(&inode->i_lock);
 	}
-	if (test_bit(PG_CLEAN, &req->wb_flags)) {
-		spin_unlock(&inode->i_lock);
-		BUG();
-	}
-	if (nfs_set_page_writeback(page) != 0) {
-		spin_unlock(&inode->i_lock);
-		BUG();
-	}
 	spin_unlock(&inode->i_lock);
+	return req;
+}
+
+/*
+ * Find an associated nfs write request, and prepare to flush it out
+ * May return an error if the user signalled nfs_wait_on_request().
+ */
+static int nfs_page_async_flush(struct nfs_pageio_descriptor *pgio,
+				struct page *page)
+{
+	struct nfs_page *req;
+	int ret = 0;
+
+	req = nfs_find_and_lock_request(page);
+	if (!req)
+		goto out;
+	ret = PTR_ERR(req);
+	if (IS_ERR(req))
+		goto out;
+
+	ret = nfs_set_page_writeback(page);
+	BUG_ON(ret != 0);
+	BUG_ON(test_bit(PG_CLEAN, &req->wb_flags));
+
 	if (!nfs_pageio_add_request(pgio, req)) {
 		nfs_redirty_request(req);
-		return pgio->pg_error;
+		ret = pgio->pg_error;
 	}
-	return 0;
+out:
+	return ret;
 }
 
 static int nfs_do_writepage(struct page *page, struct writeback_control *wbc, struct nfs_pageio_descriptor *pgio)
@@ -1580,6 +1592,41 @@ int nfs_wb_page(struct inode *inode, struct page* page)
 	return nfs_wb_page_priority(inode, page, FLUSH_STABLE);
 }
 
+#ifdef CONFIG_MIGRATION
+int nfs_migrate_page(struct address_space *mapping, struct page *newpage,
+		struct page *page)
+{
+	struct nfs_page *req;
+	int ret;
+
+	if (PageFsCache(page))
+		nfs_fscache_release_page(page, GFP_KERNEL);
+
+	req = nfs_find_and_lock_request(page);
+	ret = PTR_ERR(req);
+	if (IS_ERR(req))
+		goto out;
+
+	ret = migrate_page(mapping, newpage, page);
+	if (!req)
+		goto out;
+	if (ret)
+		goto out_unlock;
+	page_cache_get(newpage);
+	req->wb_page = newpage;
+	SetPagePrivate(newpage);
+	set_page_private(newpage, page_private(page));
+	ClearPagePrivate(page);
+	set_page_private(page, 0);
+	page_cache_release(page);
+out_unlock:
+	nfs_clear_page_tag_locked(req);
+	nfs_release_request(req);
+out:
+	return ret;
+}
+#endif
+
 int __init nfs_init_writepagecache(void)
 {
 	nfs_wdata_cachep = kmem_cache_create("nfs_write_data",

fs/nfsd/export.c

@@ -85,6 +85,11 @@ static void expkey_request(struct cache_detail *cd,
 	(*bpp)[-1] = '\n';
 }
 
+static int expkey_upcall(struct cache_detail *cd, struct cache_head *h)
+{
+	return sunrpc_cache_pipe_upcall(cd, h, expkey_request);
+}
+
 static struct svc_expkey *svc_expkey_update(struct svc_expkey *new, struct svc_expkey *old);
 static struct svc_expkey *svc_expkey_lookup(struct svc_expkey *);
 static struct cache_detail svc_expkey_cache;
@@ -259,7 +264,7 @@ static struct cache_detail svc_expkey_cache = {
 	.hash_table	= expkey_table,
 	.name		= "nfsd.fh",
 	.cache_put	= expkey_put,
-	.cache_request	= expkey_request,
+	.cache_upcall	= expkey_upcall,
 	.cache_parse	= expkey_parse,
 	.cache_show	= expkey_show,
 	.match		= expkey_match,
@@ -355,6 +360,11 @@ static void svc_export_request(struct cache_detail *cd,
 	(*bpp)[-1] = '\n';
 }
 
+static int svc_export_upcall(struct cache_detail *cd, struct cache_head *h)
+{
+	return sunrpc_cache_pipe_upcall(cd, h, svc_export_request);
+}
+
 static struct svc_export *svc_export_update(struct svc_export *new,
 					    struct svc_export *old);
 static struct svc_export *svc_export_lookup(struct svc_export *);
@@ -724,7 +734,7 @@ struct cache_detail svc_export_cache = {
 	.hash_table	= export_table,
 	.name		= "nfsd.export",
 	.cache_put	= svc_export_put,
-	.cache_request	= svc_export_request,
+	.cache_upcall	= svc_export_upcall,
 	.cache_parse	= svc_export_parse,
 	.cache_show	= svc_export_show,
 	.match		= svc_export_match,

fs/nfsd/nfs4idmap.c

@@ -145,6 +145,12 @@ idtoname_request(struct cache_detail *cd, struct cache_head *ch, char **bpp,
 	(*bpp)[-1] = '\n';
 }
 
+static int
+idtoname_upcall(struct cache_detail *cd, struct cache_head *ch)
+{
+	return sunrpc_cache_pipe_upcall(cd, ch, idtoname_request);
+}
+
 static int
 idtoname_match(struct cache_head *ca, struct cache_head *cb)
 {
@@ -175,10 +181,10 @@ idtoname_show(struct seq_file *m, struct cache_detail *cd, struct cache_head *h)
 }
 
 static void
-warn_no_idmapd(struct cache_detail *detail)
+warn_no_idmapd(struct cache_detail *detail, int has_died)
 {
 	printk("nfsd: nfsv4 idmapping failing: has idmapd %s?\n",
-			detail->last_close? "died" : "not been started");
+			has_died ? "died" : "not been started");
 }
 
 
@@ -192,7 +198,7 @@ static struct cache_detail idtoname_cache = {
 	.hash_table	= idtoname_table,
 	.name		= "nfs4.idtoname",
 	.cache_put	= ent_put,
-	.cache_request	= idtoname_request,
+	.cache_upcall	= idtoname_upcall,
 	.cache_parse	= idtoname_parse,
 	.cache_show	= idtoname_show,
 	.warn_no_listener = warn_no_idmapd,
@@ -324,6 +330,12 @@ nametoid_request(struct cache_detail *cd, struct cache_head *ch, char **bpp,
 	(*bpp)[-1] = '\n';
 }
 
+static int
+nametoid_upcall(struct cache_detail *cd, struct cache_head *ch)
+{
+	return sunrpc_cache_pipe_upcall(cd, ch, nametoid_request);
+}
+
 static int
 nametoid_match(struct cache_head *ca, struct cache_head *cb)
 {
@@ -363,7 +375,7 @@ static struct cache_detail nametoid_cache = {
 	.hash_table	= nametoid_table,
 	.name		= "nfs4.nametoid",
 	.cache_put	= ent_put,
-	.cache_request	= nametoid_request,
+	.cache_upcall	= nametoid_upcall,
 	.cache_parse	= nametoid_parse,
 	.cache_show	= nametoid_show,
 	.warn_no_listener = warn_no_idmapd,

fs/nfsd/nfsctl.c

@@ -37,6 +37,7 @@
 #include <linux/nfsd/xdr.h>
 #include <linux/nfsd/syscall.h>
 #include <linux/lockd/lockd.h>
+#include <linux/sunrpc/clnt.h>
 
 #include <asm/uaccess.h>
 #include <net/ipv6.h>
@@ -490,22 +491,18 @@ static ssize_t write_getfd(struct file *file, char *buf, size_t size)
  *
  * Input:
  *			buf:	'\n'-terminated C string containing a
- *				presentation format IPv4 address
+ *				presentation format IP 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 = {
+	struct sockaddr_storage address;
-		.sin_family	= AF_INET,
+	struct sockaddr *sap = (struct sockaddr *)&address;
-	};
+	size_t salen = sizeof(address);
-	int b1, b2, b3, b4;
-	char c;
 	char *fo_path;
 
 	/* sanity check */
@@ -519,14 +516,10 @@ static ssize_t write_unlock_ip(struct file *file, char *buf, size_t size)
 	if (qword_get(&buf, fo_path, size) < 0)
 		return -EINVAL;
 
-	/* get ipv4 address */
+	if (rpc_pton(fo_path, size, sap, salen) == 0)
-	if (sscanf(fo_path, "%u.%u.%u.%u%c", &b1, &b2, &b3, &b4, &c) != 4)
 		return -EINVAL;
-	if (b1 > 255 || b2 > 255 || b3 > 255 || b4 > 255)
-		return -EINVAL;
-	sin.sin_addr.s_addr = htonl((b1 << 24) | (b2 << 16) | (b3 << 8) | b4);
 
-	return nlmsvc_unlock_all_by_ip((struct sockaddr *)&sin);
+	return nlmsvc_unlock_all_by_ip(sap);
 }
 
 /**

include/linux/nfs4.h

@@ -472,6 +472,7 @@ enum lock_type4 {
 
 #define NFSPROC4_NULL 0
 #define NFSPROC4_COMPOUND 1
+#define NFS4_VERSION 4
 #define NFS4_MINOR_VERSION 0
 
 #if defined(CONFIG_NFS_V4_1)

include/linux/nfs_fs_sb.h

@@ -167,6 +167,15 @@ struct nfs_server {
 #define NFS_CAP_SYMLINKS	(1U << 2)
 #define NFS_CAP_ACLS		(1U << 3)
 #define NFS_CAP_ATOMIC_OPEN	(1U << 4)
+#define NFS_CAP_CHANGE_ATTR	(1U << 5)
+#define NFS_CAP_FILEID		(1U << 6)
+#define NFS_CAP_MODE		(1U << 7)
+#define NFS_CAP_NLINK		(1U << 8)
+#define NFS_CAP_OWNER		(1U << 9)
+#define NFS_CAP_OWNER_GROUP	(1U << 10)
+#define NFS_CAP_ATIME		(1U << 11)
+#define NFS_CAP_CTIME		(1U << 12)
+#define NFS_CAP_MTIME		(1U << 13)
 
 
 /* maximum number of slots to use */

include/linux/sunrpc/cache.h

@@ -59,6 +59,15 @@ struct cache_head {
 
 #define	CACHE_NEW_EXPIRY 120	/* keep new things pending confirmation for 120 seconds */
 
+struct cache_detail_procfs {
+	struct proc_dir_entry	*proc_ent;
+	struct proc_dir_entry   *flush_ent, *channel_ent, *content_ent;
+};
+
+struct cache_detail_pipefs {
+	struct dentry *dir;
+};
+
 struct cache_detail {
 	struct module *		owner;
 	int			hash_size;
@@ -70,15 +79,17 @@ struct cache_detail {
 	char			*name;
 	void			(*cache_put)(struct kref *);
 
-	void			(*cache_request)(struct cache_detail *cd,
+	int			(*cache_upcall)(struct cache_detail *,
-						 struct cache_head *h,
+						struct cache_head *);
-						 char **bpp, int *blen);
+
 	int			(*cache_parse)(struct cache_detail *,
 					       char *buf, int len);
 
 	int			(*cache_show)(struct seq_file *m,
 					      struct cache_detail *cd,
 					      struct cache_head *h);
+	void			(*warn_no_listener)(struct cache_detail *cd,
+					      int has_died);
 
 	struct cache_head *	(*alloc)(void);
 	int			(*match)(struct cache_head *orig, struct cache_head *new);
@@ -96,13 +107,15 @@ struct cache_detail {
 
 	/* fields for communication over channel */
 	struct list_head	queue;
-	struct proc_dir_entry	*proc_ent;
-	struct proc_dir_entry   *flush_ent, *channel_ent, *content_ent;
 
 	atomic_t		readers;		/* how many time is /chennel open */
 	time_t			last_close;		/* if no readers, when did last close */
 	time_t			last_warn;		/* when we last warned about no readers */
-	void			(*warn_no_listener)(struct cache_detail *cd);
+
+	union {
+		struct cache_detail_procfs procfs;
+		struct cache_detail_pipefs pipefs;
+	} u;
 };
 
 
@@ -127,6 +140,10 @@ struct cache_deferred_req {
 };
 
 
+extern const struct file_operations cache_file_operations_pipefs;
+extern const struct file_operations content_file_operations_pipefs;
+extern const struct file_operations cache_flush_operations_pipefs;
+
 extern struct cache_head *
 sunrpc_cache_lookup(struct cache_detail *detail,
 		    struct cache_head *key, int hash);
@@ -134,6 +151,13 @@ extern struct cache_head *
 sunrpc_cache_update(struct cache_detail *detail,
 		    struct cache_head *new, struct cache_head *old, int hash);
 
+extern int
+sunrpc_cache_pipe_upcall(struct cache_detail *detail, struct cache_head *h,
+		void (*cache_request)(struct cache_detail *,
+				      struct cache_head *,
+				      char **,
+				      int *));
+
 
 extern void cache_clean_deferred(void *owner);
 
@@ -171,6 +195,10 @@ extern void cache_purge(struct cache_detail *detail);
 extern int cache_register(struct cache_detail *cd);
 extern void cache_unregister(struct cache_detail *cd);
 
+extern int sunrpc_cache_register_pipefs(struct dentry *parent, const char *,
+					mode_t, struct cache_detail *);
+extern void sunrpc_cache_unregister_pipefs(struct cache_detail *);
+
 extern void qword_add(char **bpp, int *lp, char *str);
 extern void qword_addhex(char **bpp, int *lp, char *buf, int blen);
 extern int qword_get(char **bpp, char *dest, int bufsize);

include/linux/sunrpc/clnt.h

@@ -9,6 +9,10 @@
 #ifndef _LINUX_SUNRPC_CLNT_H
 #define _LINUX_SUNRPC_CLNT_H
 
+#include <linux/socket.h>
+#include <linux/in.h>
+#include <linux/in6.h>
+
 #include <linux/sunrpc/msg_prot.h>
 #include <linux/sunrpc/sched.h>
 #include <linux/sunrpc/xprt.h>
@@ -17,6 +21,7 @@
 #include <linux/sunrpc/xdr.h>
 #include <linux/sunrpc/timer.h>
 #include <asm/signal.h>
+#include <linux/path.h>
 
 struct rpc_inode;
 
@@ -50,9 +55,7 @@ struct rpc_clnt {
 
 	int			cl_nodelen;	/* nodename length */
 	char 			cl_nodename[UNX_MAXNODENAME];
-	char			cl_pathname[30];/* Path in rpc_pipe_fs */
+	struct path		cl_path;
-	struct vfsmount *	cl_vfsmnt;
-	struct dentry *		cl_dentry;	/* inode */
 	struct rpc_clnt *	cl_parent;	/* Points to parent of clones */
 	struct rpc_rtt		cl_rtt_default;
 	struct rpc_timeout	cl_timeout_default;
@@ -151,5 +154,39 @@ void		rpc_force_rebind(struct rpc_clnt *);
 size_t		rpc_peeraddr(struct rpc_clnt *, struct sockaddr *, size_t);
 const char	*rpc_peeraddr2str(struct rpc_clnt *, enum rpc_display_format_t);
 
+size_t		rpc_ntop(const struct sockaddr *, char *, const size_t);
+size_t		rpc_pton(const char *, const size_t,
+			 struct sockaddr *, const size_t);
+char *		rpc_sockaddr2uaddr(const struct sockaddr *);
+size_t		rpc_uaddr2sockaddr(const char *, const size_t,
+				   struct sockaddr *, const size_t);
+
+static inline unsigned short rpc_get_port(const struct sockaddr *sap)
+{
+	switch (sap->sa_family) {
+	case AF_INET:
+		return ntohs(((struct sockaddr_in *)sap)->sin_port);
+	case AF_INET6:
+		return ntohs(((struct sockaddr_in6 *)sap)->sin6_port);
+	}
+	return 0;
+}
+
+static inline void rpc_set_port(struct sockaddr *sap,
+				const unsigned short port)
+{
+	switch (sap->sa_family) {
+	case AF_INET:
+		((struct sockaddr_in *)sap)->sin_port = htons(port);
+		break;
+	case AF_INET6:
+		((struct sockaddr_in6 *)sap)->sin6_port = htons(port);
+		break;
+	}
+}
+
+#define IPV6_SCOPE_DELIMITER		'%'
+#define IPV6_SCOPE_ID_LEN		sizeof("%nnnnnnnnnn")
+
 #endif /* __KERNEL__ */
 #endif /* _LINUX_SUNRPC_CLNT_H */

include/linux/sunrpc/msg_prot.h

@@ -189,7 +189,22 @@ typedef __be32	rpc_fraghdr;
  * Additionally, the two alternative forms specified in Section 2.2 of
  * [RFC2373] are also acceptable.
  */
-#define RPCBIND_MAXUADDRLEN	(56u)
+
+#include <linux/inet.h>
+
+/* Maximum size of the port number part of a universal address */
+#define RPCBIND_MAXUADDRPLEN	sizeof(".255.255")
+
+/* Maximum size of an IPv4 universal address */
+#define RPCBIND_MAXUADDR4LEN	\
+		(INET_ADDRSTRLEN + RPCBIND_MAXUADDRPLEN)
+
+/* Maximum size of an IPv6 universal address */
+#define RPCBIND_MAXUADDR6LEN	\
+		(INET6_ADDRSTRLEN + RPCBIND_MAXUADDRPLEN)
+
+/* Assume INET6_ADDRSTRLEN will always be larger than INET_ADDRSTRLEN... */
+#define RPCBIND_MAXUADDRLEN	RPCBIND_MAXUADDR6LEN
 
 #endif /* __KERNEL__ */
 #endif /* _LINUX_SUNRPC_MSGPROT_H_ */

include/linux/sunrpc/rpc_pipe_fs.h

@@ -3,6 +3,8 @@
 
 #ifdef __KERNEL__
 
+#include <linux/workqueue.h>
+
 struct rpc_pipe_msg {
 	struct list_head list;
 	void *data;
@@ -32,8 +34,8 @@ struct rpc_inode {
 	wait_queue_head_t waitq;
 #define RPC_PIPE_WAIT_FOR_OPEN	1
 	int flags;
-	struct rpc_pipe_ops *ops;
 	struct delayed_work queue_timeout;
+	const struct rpc_pipe_ops *ops;
 };
 
 static inline struct rpc_inode *
@@ -44,9 +46,19 @@ RPC_I(struct inode *inode)
 
 extern int rpc_queue_upcall(struct inode *, struct rpc_pipe_msg *);
 
-extern struct dentry *rpc_mkdir(char *, struct rpc_clnt *);
+struct rpc_clnt;
-extern int rpc_rmdir(struct dentry *);
+extern struct dentry *rpc_create_client_dir(struct dentry *, struct qstr *, struct rpc_clnt *);
-extern struct dentry *rpc_mkpipe(struct dentry *, const char *, void *, struct rpc_pipe_ops *, int flags);
+extern int rpc_remove_client_dir(struct dentry *);
+
+struct cache_detail;
+extern struct dentry *rpc_create_cache_dir(struct dentry *,
+					   struct qstr *,
+					   mode_t umode,
+					   struct cache_detail *);
+extern void rpc_remove_cache_dir(struct dentry *);
+
+extern struct dentry *rpc_mkpipe(struct dentry *, const char *, void *,
+				 const struct rpc_pipe_ops *, int flags);
 extern int rpc_unlink(struct dentry *);
 extern struct vfsmount *rpc_get_mount(void);
 extern void rpc_put_mount(void);

include/linux/sunrpc/xdr.h

@@ -117,17 +117,15 @@ static inline __be32 *xdr_encode_array(__be32 *p, const void *s, unsigned int le
 static inline __be32 *
 xdr_encode_hyper(__be32 *p, __u64 val)
 {
-	*p++ = htonl(val >> 32);
+	*(__be64 *)p = cpu_to_be64(val);
-	*p++ = htonl(val & 0xFFFFFFFF);
+	return p + 2;
-	return p;
 }
 
 static inline __be32 *
 xdr_decode_hyper(__be32 *p, __u64 *valp)
 {
-	*valp  = ((__u64) ntohl(*p++)) << 32;
+	*valp = be64_to_cpup((__be64 *)p);
-	*valp |= ntohl(*p++);
+	return p + 2;
-	return p;
 }
 
 /*

include/linux/sunrpc/xprt.h

@@ -38,10 +38,8 @@ enum rpc_display_format_t {
 	RPC_DISPLAY_ADDR = 0,
 	RPC_DISPLAY_PORT,
 	RPC_DISPLAY_PROTO,
-	RPC_DISPLAY_ALL,
 	RPC_DISPLAY_HEX_ADDR,
 	RPC_DISPLAY_HEX_PORT,
-	RPC_DISPLAY_UNIVERSAL_ADDR,
 	RPC_DISPLAY_NETID,
 	RPC_DISPLAY_MAX,
 };

net/sunrpc/Makefile

@@ -10,7 +10,7 @@ obj-$(CONFIG_SUNRPC_XPRT_RDMA) += xprtrdma/
 sunrpc-y := clnt.o xprt.o socklib.o xprtsock.o sched.o \
 	    auth.o auth_null.o auth_unix.o auth_generic.o \
 	    svc.o svcsock.o svcauth.o svcauth_unix.o \
-	    rpcb_clnt.o timer.o xdr.o \
+	    addr.o rpcb_clnt.o timer.o xdr.o \
 	    sunrpc_syms.o cache.o rpc_pipe.o \
 	    svc_xprt.o
 sunrpc-$(CONFIG_NFS_V4_1) += backchannel_rqst.o bc_svc.o

net/sunrpc/addr.c

@@ -0,0 +1,364 @@
+/*
+ * Copyright 2009, Oracle.  All rights reserved.
+ *
+ * Convert socket addresses to presentation addresses and universal
+ * addresses, and vice versa.
+ *
+ * Universal addresses are introduced by RFC 1833 and further refined by
+ * recent RFCs describing NFSv4.  The universal address format is part
+ * of the external (network) interface provided by rpcbind version 3
+ * and 4, and by NFSv4.  Such an address is a string containing a
+ * presentation format IP address followed by a port number in
+ * "hibyte.lobyte" format.
+ *
+ * IPv6 addresses can also include a scope ID, typically denoted by
+ * a '%' followed by a device name or a non-negative integer.  Refer to
+ * RFC 4291, Section 2.2 for details on IPv6 presentation formats.
+ */
+
+#include <net/ipv6.h>
+#include <linux/sunrpc/clnt.h>
+
+#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+
+static size_t rpc_ntop6_noscopeid(const struct sockaddr *sap,
+				  char *buf, const int buflen)
+{
+	const struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *)sap;
+	const struct in6_addr *addr = &sin6->sin6_addr;
+
+	/*
+	 * RFC 4291, Section 2.2.2
+	 *
+	 * Shorthanded ANY address
+	 */
+	if (ipv6_addr_any(addr))
+		return snprintf(buf, buflen, "::");
+
+	/*
+	 * RFC 4291, Section 2.2.2
+	 *
+	 * Shorthanded loopback address
+	 */
+	if (ipv6_addr_loopback(addr))
+		return snprintf(buf, buflen, "::1");
+
+	/*
+	 * RFC 4291, Section 2.2.3
+	 *
+	 * Special presentation address format for mapped v4
+	 * addresses.
+	 */
+	if (ipv6_addr_v4mapped(addr))
+		return snprintf(buf, buflen, "::ffff:%pI4",
+					&addr->s6_addr32[3]);
+
+	/*
+	 * RFC 4291, Section 2.2.1
+	 *
+	 * To keep the result as short as possible, especially
+	 * since we don't shorthand, we don't want leading zeros
+	 * in each halfword, so avoid %pI6.
+	 */
+	return snprintf(buf, buflen, "%x:%x:%x:%x:%x:%x:%x:%x",
+		ntohs(addr->s6_addr16[0]), ntohs(addr->s6_addr16[1]),
+		ntohs(addr->s6_addr16[2]), ntohs(addr->s6_addr16[3]),
+		ntohs(addr->s6_addr16[4]), ntohs(addr->s6_addr16[5]),
+		ntohs(addr->s6_addr16[6]), ntohs(addr->s6_addr16[7]));
+}
+
+static size_t rpc_ntop6(const struct sockaddr *sap,
+			char *buf, const size_t buflen)
+{
+	const struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *)sap;
+	char scopebuf[IPV6_SCOPE_ID_LEN];
+	size_t len;
+	int rc;
+
+	len = rpc_ntop6_noscopeid(sap, buf, buflen);
+	if (unlikely(len == 0))
+		return len;
+
+	if (!(ipv6_addr_type(&sin6->sin6_addr) & IPV6_ADDR_LINKLOCAL) &&
+	    !(ipv6_addr_type(&sin6->sin6_addr) & IPV6_ADDR_SITELOCAL))
+		return len;
+
+	rc = snprintf(scopebuf, sizeof(scopebuf), "%c%u",
+			IPV6_SCOPE_DELIMITER, sin6->sin6_scope_id);
+	if (unlikely((size_t)rc > sizeof(scopebuf)))
+		return 0;
+
+	len += rc;
+	if (unlikely(len > buflen))
+		return 0;
+
+	strcat(buf, scopebuf);
+	return len;
+}
+
+#else	/* !(defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)) */
+
+static size_t rpc_ntop6_noscopeid(const struct sockaddr *sap,
+				  char *buf, const int buflen)
+{
+	return 0;
+}
+
+static size_t rpc_ntop6(const struct sockaddr *sap,
+			char *buf, const size_t buflen)
+{
+	return 0;
+}
+
+#endif	/* !(defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)) */
+
+static int rpc_ntop4(const struct sockaddr *sap,
+		     char *buf, const size_t buflen)
+{
+	const struct sockaddr_in *sin = (struct sockaddr_in *)sap;
+
+	return snprintf(buf, buflen, "%pI4", &sin->sin_addr);
+}
+
+/**
+ * rpc_ntop - construct a presentation address in @buf
+ * @sap: socket address
+ * @buf: construction area
+ * @buflen: size of @buf, in bytes
+ *
+ * Plants a %NUL-terminated string in @buf and returns the length
+ * of the string, excluding the %NUL.  Otherwise zero is returned.
+ */
+size_t rpc_ntop(const struct sockaddr *sap, char *buf, const size_t buflen)
+{
+	switch (sap->sa_family) {
+	case AF_INET:
+		return rpc_ntop4(sap, buf, buflen);
+	case AF_INET6:
+		return rpc_ntop6(sap, buf, buflen);
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(rpc_ntop);
+
+static size_t rpc_pton4(const char *buf, const size_t buflen,
+			struct sockaddr *sap, const size_t salen)
+{
+	struct sockaddr_in *sin = (struct sockaddr_in *)sap;
+	u8 *addr = (u8 *)&sin->sin_addr.s_addr;
+
+	if (buflen > INET_ADDRSTRLEN || salen < sizeof(struct sockaddr_in))
+		return 0;
+
+	memset(sap, 0, sizeof(struct sockaddr_in));
+
+	if (in4_pton(buf, buflen, addr, '\0', NULL) == 0)
+		return 0;
+
+	sin->sin_family = AF_INET;
+	return sizeof(struct sockaddr_in);;
+}
+
+#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+static int rpc_parse_scope_id(const char *buf, const size_t buflen,
+			      const char *delim, struct sockaddr_in6 *sin6)
+{
+	char *p;
+	size_t len;
+
+	if ((buf + buflen) == delim)
+		return 1;
+
+	if (*delim != IPV6_SCOPE_DELIMITER)
+		return 0;
+
+	if (!(ipv6_addr_type(&sin6->sin6_addr) & IPV6_ADDR_LINKLOCAL) &&
+	    !(ipv6_addr_type(&sin6->sin6_addr) & IPV6_ADDR_SITELOCAL))
+		return 0;
+
+	len = (buf + buflen) - delim - 1;
+	p = kstrndup(delim + 1, len, GFP_KERNEL);
+	if (p) {
+		unsigned long scope_id = 0;
+		struct net_device *dev;
+
+		dev = dev_get_by_name(&init_net, p);
+		if (dev != NULL) {
+			scope_id = dev->ifindex;
+			dev_put(dev);
+		} else {
+			if (strict_strtoul(p, 10, &scope_id) == 0) {
+				kfree(p);
+				return 0;
+			}
+		}
+
+		kfree(p);
+
+		sin6->sin6_scope_id = scope_id;
+		return 1;
+	}
+
+	return 0;
+}
+
+static size_t rpc_pton6(const char *buf, const size_t buflen,
+			struct sockaddr *sap, const size_t salen)
+{
+	struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *)sap;
+	u8 *addr = (u8 *)&sin6->sin6_addr.in6_u;
+	const char *delim;
+
+	if (buflen > (INET6_ADDRSTRLEN + IPV6_SCOPE_ID_LEN) ||
+	    salen < sizeof(struct sockaddr_in6))
+		return 0;
+
+	memset(sap, 0, sizeof(struct sockaddr_in6));
+
+	if (in6_pton(buf, buflen, addr, IPV6_SCOPE_DELIMITER, &delim) == 0)
+		return 0;
+
+	if (!rpc_parse_scope_id(buf, buflen, delim, sin6))
+		return 0;
+
+	sin6->sin6_family = AF_INET6;
+	return sizeof(struct sockaddr_in6);
+}
+#else
+static size_t rpc_pton6(const char *buf, const size_t buflen,
+			struct sockaddr *sap, const size_t salen)
+{
+	return 0;
+}
+#endif
+
+/**
+ * rpc_pton - Construct a sockaddr in @sap
+ * @buf: C string containing presentation format IP address
+ * @buflen: length of presentation address in bytes
+ * @sap: buffer into which to plant socket address
+ * @salen: size of buffer in bytes
+ *
+ * Returns the size of the socket address if successful; otherwise
+ * zero is returned.
+ *
+ * Plants a socket address in @sap and returns the size of the
+ * socket address, if successful.  Returns zero if an error
+ * occurred.
+ */
+size_t rpc_pton(const char *buf, const size_t buflen,
+		struct sockaddr *sap, const size_t salen)
+{
+	unsigned int i;
+
+	for (i = 0; i < buflen; i++)
+		if (buf[i] == ':')
+			return rpc_pton6(buf, buflen, sap, salen);
+	return rpc_pton4(buf, buflen, sap, salen);
+}
+EXPORT_SYMBOL_GPL(rpc_pton);
+
+/**
+ * rpc_sockaddr2uaddr - Construct a universal address string from @sap.
+ * @sap: socket address
+ *
+ * Returns a %NUL-terminated string in dynamically allocated memory;
+ * otherwise NULL is returned if an error occurred.  Caller must
+ * free the returned string.
+ */
+char *rpc_sockaddr2uaddr(const struct sockaddr *sap)
+{
+	char portbuf[RPCBIND_MAXUADDRPLEN];
+	char addrbuf[RPCBIND_MAXUADDRLEN];
+	unsigned short port;
+
+	switch (sap->sa_family) {
+	case AF_INET:
+		if (rpc_ntop4(sap, addrbuf, sizeof(addrbuf)) == 0)
+			return NULL;
+		port = ntohs(((struct sockaddr_in *)sap)->sin_port);
+		break;
+	case AF_INET6:
+		if (rpc_ntop6_noscopeid(sap, addrbuf, sizeof(addrbuf)) == 0)
+			return NULL;
+		port = ntohs(((struct sockaddr_in6 *)sap)->sin6_port);
+		break;
+	default:
+		return NULL;
+	}
+
+	if (snprintf(portbuf, sizeof(portbuf),
+		     ".%u.%u", port >> 8, port & 0xff) > (int)sizeof(portbuf))
+		return NULL;
+
+	if (strlcat(addrbuf, portbuf, sizeof(addrbuf)) > sizeof(addrbuf))
+		return NULL;
+
+	return kstrdup(addrbuf, GFP_KERNEL);
+}
+EXPORT_SYMBOL_GPL(rpc_sockaddr2uaddr);
+
+/**
+ * rpc_uaddr2sockaddr - convert a universal address to a socket address.
+ * @uaddr: C string containing universal address to convert
+ * @uaddr_len: length of universal address string
+ * @sap: buffer into which to plant socket address
+ * @salen: size of buffer
+ *
+ * Returns the size of the socket address if successful; otherwise
+ * zero is returned.
+ */
+size_t rpc_uaddr2sockaddr(const char *uaddr, const size_t uaddr_len,
+			  struct sockaddr *sap, const size_t salen)
+{
+	char *c, buf[RPCBIND_MAXUADDRLEN];
+	unsigned long portlo, porthi;
+	unsigned short port;
+
+	if (uaddr_len > sizeof(buf))
+		return 0;
+
+	memcpy(buf, uaddr, uaddr_len);
+
+	buf[uaddr_len] = '\n';
+	buf[uaddr_len + 1] = '\0';
+
+	c = strrchr(buf, '.');
+	if (unlikely(c == NULL))
+		return 0;
+	if (unlikely(strict_strtoul(c + 1, 10, &portlo) != 0))
+		return 0;
+	if (unlikely(portlo > 255))
+		return 0;
+
+	c[0] = '\n';
+	c[1] = '\0';
+
+	c = strrchr(buf, '.');
+	if (unlikely(c == NULL))
+		return 0;
+	if (unlikely(strict_strtoul(c + 1, 10, &porthi) != 0))
+		return 0;
+	if (unlikely(porthi > 255))
+		return 0;
+
+	port = (unsigned short)((porthi << 8) | portlo);
+
+	c[0] = '\0';
+
+	if (rpc_pton(buf, strlen(buf), sap, salen) == 0)
+		return 0;
+
+	switch (sap->sa_family) {
+	case AF_INET:
+		((struct sockaddr_in *)sap)->sin_port = htons(port);
+		return sizeof(struct sockaddr_in);
+	case AF_INET6:
+		((struct sockaddr_in6 *)sap)->sin6_port = htons(port);
+		return sizeof(struct sockaddr_in6);
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(rpc_uaddr2sockaddr);

net/sunrpc/auth_gss/auth_gss.c

@@ -89,8 +89,8 @@ static struct rpc_wait_queue pipe_version_rpc_waitqueue;
 static DECLARE_WAIT_QUEUE_HEAD(pipe_version_waitqueue);
 
 static void gss_free_ctx(struct gss_cl_ctx *);
-static struct rpc_pipe_ops gss_upcall_ops_v0;
+static const struct rpc_pipe_ops gss_upcall_ops_v0;
-static struct rpc_pipe_ops gss_upcall_ops_v1;
+static const struct rpc_pipe_ops gss_upcall_ops_v1;
 
 static inline struct gss_cl_ctx *
 gss_get_ctx(struct gss_cl_ctx *ctx)
@@ -777,7 +777,7 @@ gss_create(struct rpc_clnt *clnt, rpc_authflavor_t flavor)
 	 * that we supported only the old pipe.  So we instead create
 	 * the new pipe first.
 	 */
-	gss_auth->dentry[1] = rpc_mkpipe(clnt->cl_dentry,
+	gss_auth->dentry[1] = rpc_mkpipe(clnt->cl_path.dentry,
 					 "gssd",
 					 clnt, &gss_upcall_ops_v1,
 					 RPC_PIPE_WAIT_FOR_OPEN);
@@ -786,7 +786,7 @@ gss_create(struct rpc_clnt *clnt, rpc_authflavor_t flavor)
 		goto err_put_mech;
 	}
 
-	gss_auth->dentry[0] = rpc_mkpipe(clnt->cl_dentry,
+	gss_auth->dentry[0] = rpc_mkpipe(clnt->cl_path.dentry,
 					 gss_auth->mech->gm_name,
 					 clnt, &gss_upcall_ops_v0,
 					 RPC_PIPE_WAIT_FOR_OPEN);
@@ -1507,7 +1507,7 @@ static const struct rpc_credops gss_nullops = {
 	.crunwrap_resp	= gss_unwrap_resp,
 };
 
-static struct rpc_pipe_ops gss_upcall_ops_v0 = {
+static const struct rpc_pipe_ops gss_upcall_ops_v0 = {
 	.upcall		= gss_pipe_upcall,
 	.downcall	= gss_pipe_downcall,
 	.destroy_msg	= gss_pipe_destroy_msg,
@@ -1515,7 +1515,7 @@ static struct rpc_pipe_ops gss_upcall_ops_v0 = {
 	.release_pipe	= gss_pipe_release,
 };
 
-static struct rpc_pipe_ops gss_upcall_ops_v1 = {
+static const struct rpc_pipe_ops gss_upcall_ops_v1 = {
 	.upcall		= gss_pipe_upcall,
 	.downcall	= gss_pipe_downcall,
 	.destroy_msg	= gss_pipe_destroy_msg,

net/sunrpc/auth_gss/svcauth_gss.c

@@ -181,6 +181,11 @@ static void rsi_request(struct cache_detail *cd,
 	(*bpp)[-1] = '\n';
 }
 
+static int rsi_upcall(struct cache_detail *cd, struct cache_head *h)
+{
+	return sunrpc_cache_pipe_upcall(cd, h, rsi_request);
+}
+
 
 static int rsi_parse(struct cache_detail *cd,
 		    char *mesg, int mlen)
@@ -270,7 +275,7 @@ static struct cache_detail rsi_cache = {
 	.hash_table     = rsi_table,
 	.name           = "auth.rpcsec.init",
 	.cache_put      = rsi_put,
-	.cache_request  = rsi_request,
+	.cache_upcall   = rsi_upcall,
 	.cache_parse    = rsi_parse,
 	.match		= rsi_match,
 	.init		= rsi_init,

net/sunrpc/cache.c

@@ -27,10 +27,12 @@
 #include <linux/net.h>
 #include <linux/workqueue.h>
 #include <linux/mutex.h>
+#include <linux/pagemap.h>
 #include <asm/ioctls.h>
 #include <linux/sunrpc/types.h>
 #include <linux/sunrpc/cache.h>
 #include <linux/sunrpc/stats.h>
+#include <linux/sunrpc/rpc_pipe_fs.h>
 
 #define	 RPCDBG_FACILITY RPCDBG_CACHE
 
@@ -175,7 +177,13 @@ struct cache_head *sunrpc_cache_update(struct cache_detail *detail,
 }
 EXPORT_SYMBOL_GPL(sunrpc_cache_update);
 
-static int cache_make_upcall(struct cache_detail *detail, struct cache_head *h);
+static int cache_make_upcall(struct cache_detail *cd, struct cache_head *h)
+{
+	if (!cd->cache_upcall)
+		return -EINVAL;
+	return cd->cache_upcall(cd, h);
+}
+
 /*
  * This is the generic cache management routine for all
  * the authentication caches.
@@ -284,76 +292,11 @@ static DEFINE_SPINLOCK(cache_list_lock);
 static struct cache_detail *current_detail;
 static int current_index;
 
-static const struct file_operations cache_file_operations;
-static const struct file_operations content_file_operations;
-static const struct file_operations cache_flush_operations;
-
 static void do_cache_clean(struct work_struct *work);
 static DECLARE_DELAYED_WORK(cache_cleaner, do_cache_clean);
 
-static void remove_cache_proc_entries(struct cache_detail *cd)
+static void sunrpc_init_cache_detail(struct cache_detail *cd)
 {
-	if (cd->proc_ent == NULL)
-		return;
-	if (cd->flush_ent)
-		remove_proc_entry("flush", cd->proc_ent);
-	if (cd->channel_ent)
-		remove_proc_entry("channel", cd->proc_ent);
-	if (cd->content_ent)
-		remove_proc_entry("content", cd->proc_ent);
-	cd->proc_ent = NULL;
-	remove_proc_entry(cd->name, proc_net_rpc);
-}
-
-#ifdef CONFIG_PROC_FS
-static int create_cache_proc_entries(struct cache_detail *cd)
-{
-	struct proc_dir_entry *p;
-
-	cd->proc_ent = proc_mkdir(cd->name, proc_net_rpc);
-	if (cd->proc_ent == NULL)
-		goto out_nomem;
-	cd->channel_ent = cd->content_ent = NULL;
-
-	p = proc_create_data("flush", S_IFREG|S_IRUSR|S_IWUSR,
-			     cd->proc_ent, &cache_flush_operations, cd);
-	cd->flush_ent = p;
-	if (p == NULL)
-		goto out_nomem;
-
-	if (cd->cache_request || cd->cache_parse) {
-		p = proc_create_data("channel", S_IFREG|S_IRUSR|S_IWUSR,
-				     cd->proc_ent, &cache_file_operations, cd);
-		cd->channel_ent = p;
-		if (p == NULL)
-			goto out_nomem;
-	}
-	if (cd->cache_show) {
-		p = proc_create_data("content", S_IFREG|S_IRUSR|S_IWUSR,
-				cd->proc_ent, &content_file_operations, cd);
-		cd->content_ent = p;
-		if (p == NULL)
-			goto out_nomem;
-	}
-	return 0;
-out_nomem:
-	remove_cache_proc_entries(cd);
-	return -ENOMEM;
-}
-#else /* CONFIG_PROC_FS */
-static int create_cache_proc_entries(struct cache_detail *cd)
-{
-	return 0;
-}
-#endif
-
-int cache_register(struct cache_detail *cd)
-{
-	int ret;
-
-	ret = create_cache_proc_entries(cd);
-	if (ret)
-		return ret;
 	rwlock_init(&cd->hash_lock);
 	INIT_LIST_HEAD(&cd->queue);
 	spin_lock(&cache_list_lock);
@@ -367,11 +310,9 @@ int cache_register(struct cache_detail *cd)
 
 	/* start the cleaning process */
 	schedule_delayed_work(&cache_cleaner, 0);
-	return 0;
 }
-EXPORT_SYMBOL_GPL(cache_register);
 
-void cache_unregister(struct cache_detail *cd)
+static void sunrpc_destroy_cache_detail(struct cache_detail *cd)
 {
 	cache_purge(cd);
 	spin_lock(&cache_list_lock);
@@ -386,7 +327,6 @@ void cache_unregister(struct cache_detail *cd)
 	list_del_init(&cd->others);
 	write_unlock(&cd->hash_lock);
 	spin_unlock(&cache_list_lock);
-	remove_cache_proc_entries(cd);
 	if (list_empty(&cache_list)) {
 		/* module must be being unloaded so its safe to kill the worker */
 		cancel_delayed_work_sync(&cache_cleaner);
@@ -395,7 +335,6 @@ void cache_unregister(struct cache_detail *cd)
 out:
 	printk(KERN_ERR "nfsd: failed to unregister %s cache\n", cd->name);
 }
-EXPORT_SYMBOL_GPL(cache_unregister);
 
 /* clean cache tries to find something to clean
  * and cleans it.
@@ -687,18 +626,18 @@ struct cache_reader {
 	int			offset;	/* if non-0, we have a refcnt on next request */
 };
 
-static ssize_t
+static ssize_t cache_read(struct file *filp, char __user *buf, size_t count,
-cache_read(struct file *filp, char __user *buf, size_t count, loff_t *ppos)
+			  loff_t *ppos, struct cache_detail *cd)
 {
 	struct cache_reader *rp = filp->private_data;
 	struct cache_request *rq;
-	struct cache_detail *cd = PDE(filp->f_path.dentry->d_inode)->data;
+	struct inode *inode = filp->f_path.dentry->d_inode;
 	int err;
 
 	if (count == 0)
 		return 0;
 
-	mutex_lock(&queue_io_mutex); /* protect against multiple concurrent
+	mutex_lock(&inode->i_mutex); /* protect against multiple concurrent
 			      * readers on this file */
  again:
 	spin_lock(&queue_lock);
@@ -711,7 +650,7 @@ cache_read(struct file *filp, char __user *buf, size_t count, loff_t *ppos)
 	}
 	if (rp->q.list.next == &cd->queue) {
 		spin_unlock(&queue_lock);
-		mutex_unlock(&queue_io_mutex);
+		mutex_unlock(&inode->i_mutex);
 		BUG_ON(rp->offset);
 		return 0;
 	}
@@ -758,49 +697,90 @@ cache_read(struct file *filp, char __user *buf, size_t count, loff_t *ppos)
 	}
 	if (err == -EAGAIN)
 		goto again;
-	mutex_unlock(&queue_io_mutex);
+	mutex_unlock(&inode->i_mutex);
 	return err ? err :  count;
 }
 
-static char write_buf[8192]; /* protected by queue_io_mutex */
+static ssize_t cache_do_downcall(char *kaddr, const char __user *buf,
-
+				 size_t count, struct cache_detail *cd)
-static ssize_t
-cache_write(struct file *filp, const char __user *buf, size_t count,
-	    loff_t *ppos)
 {
-	int err;
+	ssize_t ret;
-	struct cache_detail *cd = PDE(filp->f_path.dentry->d_inode)->data;
 
-	if (count == 0)
+	if (copy_from_user(kaddr, buf, count))
-		return 0;
-	if (count >= sizeof(write_buf))
-		return -EINVAL;
-
-	mutex_lock(&queue_io_mutex);
-
-	if (copy_from_user(write_buf, buf, count)) {
-		mutex_unlock(&queue_io_mutex);
 		return -EFAULT;
-	}
+	kaddr[count] = '\0';
-	write_buf[count] = '\0';
+	ret = cd->cache_parse(cd, kaddr, count);
-	if (cd->cache_parse)
+	if (!ret)
-		err = cd->cache_parse(cd, write_buf, count);
+		ret = count;
-	else
+	return ret;
-		err = -EINVAL;
+}
 
+static ssize_t cache_slow_downcall(const char __user *buf,
+				   size_t count, struct cache_detail *cd)
+{
+	static char write_buf[8192]; /* protected by queue_io_mutex */
+	ssize_t ret = -EINVAL;
+
+	if (count >= sizeof(write_buf))
+		goto out;
+	mutex_lock(&queue_io_mutex);
+	ret = cache_do_downcall(write_buf, buf, count, cd);
 	mutex_unlock(&queue_io_mutex);
-	return err ? err : count;
+out:
+	return ret;
+}
+
+static ssize_t cache_downcall(struct address_space *mapping,
+			      const char __user *buf,
+			      size_t count, struct cache_detail *cd)
+{
+	struct page *page;
+	char *kaddr;
+	ssize_t ret = -ENOMEM;
+
+	if (count >= PAGE_CACHE_SIZE)
+		goto out_slow;
+
+	page = find_or_create_page(mapping, 0, GFP_KERNEL);
+	if (!page)
+		goto out_slow;
+
+	kaddr = kmap(page);
+	ret = cache_do_downcall(kaddr, buf, count, cd);
+	kunmap(page);
+	unlock_page(page);
+	page_cache_release(page);
+	return ret;
+out_slow:
+	return cache_slow_downcall(buf, count, cd);
+}
+
+static ssize_t cache_write(struct file *filp, const char __user *buf,
+			   size_t count, loff_t *ppos,
+			   struct cache_detail *cd)
+{
+	struct address_space *mapping = filp->f_mapping;
+	struct inode *inode = filp->f_path.dentry->d_inode;
+	ssize_t ret = -EINVAL;
+
+	if (!cd->cache_parse)
+		goto out;
+
+	mutex_lock(&inode->i_mutex);
+	ret = cache_downcall(mapping, buf, count, cd);
+	mutex_unlock(&inode->i_mutex);
+out:
+	return ret;
 }
 
 static DECLARE_WAIT_QUEUE_HEAD(queue_wait);
 
-static unsigned int
+static unsigned int cache_poll(struct file *filp, poll_table *wait,
-cache_poll(struct file *filp, poll_table *wait)
+			       struct cache_detail *cd)
 {
 	unsigned int mask;
 	struct cache_reader *rp = filp->private_data;
 	struct cache_queue *cq;
-	struct cache_detail *cd = PDE(filp->f_path.dentry->d_inode)->data;
 
 	poll_wait(filp, &queue_wait, wait);
 
@@ -822,14 +802,13 @@ cache_poll(struct file *filp, poll_table *wait)
 	return mask;
 }
 
-static int
+static int cache_ioctl(struct inode *ino, struct file *filp,
-cache_ioctl(struct inode *ino, struct file *filp,
+		       unsigned int cmd, unsigned long arg,
-	    unsigned int cmd, unsigned long arg)
+		       struct cache_detail *cd)
 {
 	int len = 0;
 	struct cache_reader *rp = filp->private_data;
 	struct cache_queue *cq;
-	struct cache_detail *cd = PDE(ino)->data;
 
 	if (cmd != FIONREAD || !rp)
 		return -EINVAL;
@@ -852,15 +831,15 @@ cache_ioctl(struct inode *ino, struct file *filp,
 	return put_user(len, (int __user *)arg);
 }
 
-static int
+static int cache_open(struct inode *inode, struct file *filp,
-cache_open(struct inode *inode, struct file *filp)
+		      struct cache_detail *cd)
 {
 	struct cache_reader *rp = NULL;
 
+	if (!cd || !try_module_get(cd->owner))
+		return -EACCES;
 	nonseekable_open(inode, filp);
 	if (filp->f_mode & FMODE_READ) {
-		struct cache_detail *cd = PDE(inode)->data;
-
 		rp = kmalloc(sizeof(*rp), GFP_KERNEL);
 		if (!rp)
 			return -ENOMEM;
@@ -875,11 +854,10 @@ cache_open(struct inode *inode, struct file *filp)
 	return 0;
 }
 
-static int
+static int cache_release(struct inode *inode, struct file *filp,
-cache_release(struct inode *inode, struct file *filp)
+			 struct cache_detail *cd)
 {
 	struct cache_reader *rp = filp->private_data;
-	struct cache_detail *cd = PDE(inode)->data;
 
 	if (rp) {
 		spin_lock(&queue_lock);
@@ -903,23 +881,12 @@ cache_release(struct inode *inode, struct file *filp)
 		cd->last_close = get_seconds();
 		atomic_dec(&cd->readers);
 	}
+	module_put(cd->owner);
 	return 0;
 }
 
 
 
-static const struct file_operations cache_file_operations = {
-	.owner		= THIS_MODULE,
-	.llseek		= no_llseek,
-	.read		= cache_read,
-	.write		= cache_write,
-	.poll		= cache_poll,
-	.ioctl		= cache_ioctl, /* for FIONREAD */
-	.open		= cache_open,
-	.release	= cache_release,
-};
-
-
 static void queue_loose(struct cache_detail *detail, struct cache_head *ch)
 {
 	struct cache_queue *cq;
@@ -1020,15 +987,21 @@ static void warn_no_listener(struct cache_detail *detail)
 	if (detail->last_warn != detail->last_close) {
 		detail->last_warn = detail->last_close;
 		if (detail->warn_no_listener)
-			detail->warn_no_listener(detail);
+			detail->warn_no_listener(detail, detail->last_close != 0);
 	}
 }
 
 /*
- * register an upcall request to user-space.
+ * register an upcall request to user-space and queue it up for read() by the
+ * upcall daemon.
+ *
  * Each request is at most one page long.
  */
-static int cache_make_upcall(struct cache_detail *detail, struct cache_head *h)
+int sunrpc_cache_pipe_upcall(struct cache_detail *detail, struct cache_head *h,
+		void (*cache_request)(struct cache_detail *,
+				      struct cache_head *,
+				      char **,
+				      int *))
 {
 
 	char *buf;
@@ -1036,9 +1009,6 @@ static int cache_make_upcall(struct cache_detail *detail, struct cache_head *h)
 	char *bp;
 	int len;
 
-	if (detail->cache_request == NULL)
-		return -EINVAL;
-
 	if (atomic_read(&detail->readers) == 0 &&
 	    detail->last_close < get_seconds() - 30) {
 			warn_no_listener(detail);
@@ -1057,7 +1027,7 @@ static int cache_make_upcall(struct cache_detail *detail, struct cache_head *h)
 
 	bp = buf; len = PAGE_SIZE;
 
-	detail->cache_request(detail, h, &bp, &len);
+	cache_request(detail, h, &bp, &len);
 
 	if (len < 0) {
 		kfree(buf);
@@ -1075,6 +1045,7 @@ static int cache_make_upcall(struct cache_detail *detail, struct cache_head *h)
 	wake_up(&queue_wait);
 	return 0;
 }
+EXPORT_SYMBOL_GPL(sunrpc_cache_pipe_upcall);
 
 /*
  * parse a message from user-space and pass it
@@ -1242,11 +1213,13 @@ static const struct seq_operations cache_content_op = {
 	.show	= c_show,
 };
 
-static int content_open(struct inode *inode, struct file *file)
+static int content_open(struct inode *inode, struct file *file,
+			struct cache_detail *cd)
 {
 	struct handle *han;
-	struct cache_detail *cd = PDE(inode)->data;
 
+	if (!cd || !try_module_get(cd->owner))
+		return -EACCES;
 	han = __seq_open_private(file, &cache_content_op, sizeof(*han));
 	if (han == NULL)
 		return -ENOMEM;
@@ -1255,17 +1228,33 @@ static int content_open(struct inode *inode, struct file *file)
 	return 0;
 }
 
-static const struct file_operations content_file_operations = {
+static int content_release(struct inode *inode, struct file *file,
-	.open		= content_open,
+		struct cache_detail *cd)
-	.read		= seq_read,
+{
-	.llseek		= seq_lseek,
+	int ret = seq_release_private(inode, file);
-	.release	= seq_release_private,
+	module_put(cd->owner);
-};
+	return ret;
+}
+
+static int open_flush(struct inode *inode, struct file *file,
+			struct cache_detail *cd)
+{
+	if (!cd || !try_module_get(cd->owner))
+		return -EACCES;
+	return nonseekable_open(inode, file);
+}
+
+static int release_flush(struct inode *inode, struct file *file,
+			struct cache_detail *cd)
+{
+	module_put(cd->owner);
+	return 0;
+}
 
 static ssize_t read_flush(struct file *file, char __user *buf,
-			    size_t count, loff_t *ppos)
+			  size_t count, loff_t *ppos,
+			  struct cache_detail *cd)
 {
-	struct cache_detail *cd = PDE(file->f_path.dentry->d_inode)->data;
 	char tbuf[20];
 	unsigned long p = *ppos;
 	size_t len;
@@ -1283,10 +1272,10 @@ static ssize_t read_flush(struct file *file, char __user *buf,
 	return len;
 }
 
-static ssize_t write_flush(struct file * file, const char __user * buf,
+static ssize_t write_flush(struct file *file, const char __user *buf,
-			     size_t count, loff_t *ppos)
+			   size_t count, loff_t *ppos,
+			   struct cache_detail *cd)
 {
-	struct cache_detail *cd = PDE(file->f_path.dentry->d_inode)->data;
 	char tbuf[20];
 	char *ep;
 	long flushtime;
@@ -1307,8 +1296,343 @@ static ssize_t write_flush(struct file * file, const char __user * buf,
 	return count;
 }
 
-static const struct file_operations cache_flush_operations = {
+static ssize_t cache_read_procfs(struct file *filp, char __user *buf,
-	.open		= nonseekable_open,
+				 size_t count, loff_t *ppos)
-	.read		= read_flush,
+{
-	.write		= write_flush,
+	struct cache_detail *cd = PDE(filp->f_path.dentry->d_inode)->data;
+
+	return cache_read(filp, buf, count, ppos, cd);
+}
+
+static ssize_t cache_write_procfs(struct file *filp, const char __user *buf,
+				  size_t count, loff_t *ppos)
+{
+	struct cache_detail *cd = PDE(filp->f_path.dentry->d_inode)->data;
+
+	return cache_write(filp, buf, count, ppos, cd);
+}
+
+static unsigned int cache_poll_procfs(struct file *filp, poll_table *wait)
+{
+	struct cache_detail *cd = PDE(filp->f_path.dentry->d_inode)->data;
+
+	return cache_poll(filp, wait, cd);
+}
+
+static int cache_ioctl_procfs(struct inode *inode, struct file *filp,
+			      unsigned int cmd, unsigned long arg)
+{
+	struct cache_detail *cd = PDE(inode)->data;
+
+	return cache_ioctl(inode, filp, cmd, arg, cd);
+}
+
+static int cache_open_procfs(struct inode *inode, struct file *filp)
+{
+	struct cache_detail *cd = PDE(inode)->data;
+
+	return cache_open(inode, filp, cd);
+}
+
+static int cache_release_procfs(struct inode *inode, struct file *filp)
+{
+	struct cache_detail *cd = PDE(inode)->data;
+
+	return cache_release(inode, filp, cd);
+}
+
+static const struct file_operations cache_file_operations_procfs = {
+	.owner		= THIS_MODULE,
+	.llseek		= no_llseek,
+	.read		= cache_read_procfs,
+	.write		= cache_write_procfs,
+	.poll		= cache_poll_procfs,
+	.ioctl		= cache_ioctl_procfs, /* for FIONREAD */
+	.open		= cache_open_procfs,
+	.release	= cache_release_procfs,
 };
+
+static int content_open_procfs(struct inode *inode, struct file *filp)
+{
+	struct cache_detail *cd = PDE(inode)->data;
+
+	return content_open(inode, filp, cd);
+}
+
+static int content_release_procfs(struct inode *inode, struct file *filp)
+{
+	struct cache_detail *cd = PDE(inode)->data;
+
+	return content_release(inode, filp, cd);
+}
+
+static const struct file_operations content_file_operations_procfs = {
+	.open		= content_open_procfs,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= content_release_procfs,
+};
+
+static int open_flush_procfs(struct inode *inode, struct file *filp)
+{
+	struct cache_detail *cd = PDE(inode)->data;
+
+	return open_flush(inode, filp, cd);
+}
+
+static int release_flush_procfs(struct inode *inode, struct file *filp)
+{
+	struct cache_detail *cd = PDE(inode)->data;
+
+	return release_flush(inode, filp, cd);
+}
+
+static ssize_t read_flush_procfs(struct file *filp, char __user *buf,
+			    size_t count, loff_t *ppos)
+{
+	struct cache_detail *cd = PDE(filp->f_path.dentry->d_inode)->data;
+
+	return read_flush(filp, buf, count, ppos, cd);
+}
+
+static ssize_t write_flush_procfs(struct file *filp,
+				  const char __user *buf,
+				  size_t count, loff_t *ppos)
+{
+	struct cache_detail *cd = PDE(filp->f_path.dentry->d_inode)->data;
+
+	return write_flush(filp, buf, count, ppos, cd);
+}
+
+static const struct file_operations cache_flush_operations_procfs = {
+	.open		= open_flush_procfs,
+	.read		= read_flush_procfs,
+	.write		= write_flush_procfs,
+	.release	= release_flush_procfs,
+};
+
+static void remove_cache_proc_entries(struct cache_detail *cd)
+{
+	if (cd->u.procfs.proc_ent == NULL)
+		return;
+	if (cd->u.procfs.flush_ent)
+		remove_proc_entry("flush", cd->u.procfs.proc_ent);
+	if (cd->u.procfs.channel_ent)
+		remove_proc_entry("channel", cd->u.procfs.proc_ent);
+	if (cd->u.procfs.content_ent)
+		remove_proc_entry("content", cd->u.procfs.proc_ent);
+	cd->u.procfs.proc_ent = NULL;
+	remove_proc_entry(cd->name, proc_net_rpc);
+}
+
+#ifdef CONFIG_PROC_FS
+static int create_cache_proc_entries(struct cache_detail *cd)
+{
+	struct proc_dir_entry *p;
+
+	cd->u.procfs.proc_ent = proc_mkdir(cd->name, proc_net_rpc);
+	if (cd->u.procfs.proc_ent == NULL)
+		goto out_nomem;
+	cd->u.procfs.channel_ent = NULL;
+	cd->u.procfs.content_ent = NULL;
+
+	p = proc_create_data("flush", S_IFREG|S_IRUSR|S_IWUSR,
+			     cd->u.procfs.proc_ent,
+			     &cache_flush_operations_procfs, cd);
+	cd->u.procfs.flush_ent = p;
+	if (p == NULL)
+		goto out_nomem;
+
+	if (cd->cache_upcall || cd->cache_parse) {
+		p = proc_create_data("channel", S_IFREG|S_IRUSR|S_IWUSR,
+				     cd->u.procfs.proc_ent,
+				     &cache_file_operations_procfs, cd);
+		cd->u.procfs.channel_ent = p;
+		if (p == NULL)
+			goto out_nomem;
+	}
+	if (cd->cache_show) {
+		p = proc_create_data("content", S_IFREG|S_IRUSR|S_IWUSR,
+				cd->u.procfs.proc_ent,
+				&content_file_operations_procfs, cd);
+		cd->u.procfs.content_ent = p;
+		if (p == NULL)
+			goto out_nomem;
+	}
+	return 0;
+out_nomem:
+	remove_cache_proc_entries(cd);
+	return -ENOMEM;
+}
+#else /* CONFIG_PROC_FS */
+static int create_cache_proc_entries(struct cache_detail *cd)
+{
+	return 0;
+}
+#endif
+
+int cache_register(struct cache_detail *cd)
+{
+	int ret;
+
+	sunrpc_init_cache_detail(cd);
+	ret = create_cache_proc_entries(cd);
+	if (ret)
+		sunrpc_destroy_cache_detail(cd);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(cache_register);
+
+void cache_unregister(struct cache_detail *cd)
+{
+	remove_cache_proc_entries(cd);
+	sunrpc_destroy_cache_detail(cd);
+}
+EXPORT_SYMBOL_GPL(cache_unregister);
+
+static ssize_t cache_read_pipefs(struct file *filp, char __user *buf,
+				 size_t count, loff_t *ppos)
+{
+	struct cache_detail *cd = RPC_I(filp->f_path.dentry->d_inode)->private;
+
+	return cache_read(filp, buf, count, ppos, cd);
+}
+
+static ssize_t cache_write_pipefs(struct file *filp, const char __user *buf,
+				  size_t count, loff_t *ppos)
+{
+	struct cache_detail *cd = RPC_I(filp->f_path.dentry->d_inode)->private;
+
+	return cache_write(filp, buf, count, ppos, cd);
+}
+
+static unsigned int cache_poll_pipefs(struct file *filp, poll_table *wait)
+{
+	struct cache_detail *cd = RPC_I(filp->f_path.dentry->d_inode)->private;
+
+	return cache_poll(filp, wait, cd);
+}
+
+static int cache_ioctl_pipefs(struct inode *inode, struct file *filp,
+			      unsigned int cmd, unsigned long arg)
+{
+	struct cache_detail *cd = RPC_I(inode)->private;
+
+	return cache_ioctl(inode, filp, cmd, arg, cd);
+}
+
+static int cache_open_pipefs(struct inode *inode, struct file *filp)
+{
+	struct cache_detail *cd = RPC_I(inode)->private;
+
+	return cache_open(inode, filp, cd);
+}
+
+static int cache_release_pipefs(struct inode *inode, struct file *filp)
+{
+	struct cache_detail *cd = RPC_I(inode)->private;
+
+	return cache_release(inode, filp, cd);
+}
+
+const struct file_operations cache_file_operations_pipefs = {
+	.owner		= THIS_MODULE,
+	.llseek		= no_llseek,
+	.read		= cache_read_pipefs,
+	.write		= cache_write_pipefs,
+	.poll		= cache_poll_pipefs,
+	.ioctl		= cache_ioctl_pipefs, /* for FIONREAD */
+	.open		= cache_open_pipefs,
+	.release	= cache_release_pipefs,
+};
+
+static int content_open_pipefs(struct inode *inode, struct file *filp)
+{
+	struct cache_detail *cd = RPC_I(inode)->private;
+
+	return content_open(inode, filp, cd);
+}
+
+static int content_release_pipefs(struct inode *inode, struct file *filp)
+{
+	struct cache_detail *cd = RPC_I(inode)->private;
+
+	return content_release(inode, filp, cd);
+}
+
+const struct file_operations content_file_operations_pipefs = {
+	.open		= content_open_pipefs,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= content_release_pipefs,
+};
+
+static int open_flush_pipefs(struct inode *inode, struct file *filp)
+{
+	struct cache_detail *cd = RPC_I(inode)->private;
+
+	return open_flush(inode, filp, cd);
+}
+
+static int release_flush_pipefs(struct inode *inode, struct file *filp)
+{
+	struct cache_detail *cd = RPC_I(inode)->private;
+
+	return release_flush(inode, filp, cd);
+}
+
+static ssize_t read_flush_pipefs(struct file *filp, char __user *buf,
+			    size_t count, loff_t *ppos)
+{
+	struct cache_detail *cd = RPC_I(filp->f_path.dentry->d_inode)->private;
+
+	return read_flush(filp, buf, count, ppos, cd);
+}
+
+static ssize_t write_flush_pipefs(struct file *filp,
+				  const char __user *buf,
+				  size_t count, loff_t *ppos)
+{
+	struct cache_detail *cd = RPC_I(filp->f_path.dentry->d_inode)->private;
+
+	return write_flush(filp, buf, count, ppos, cd);
+}
+
+const struct file_operations cache_flush_operations_pipefs = {
+	.open		= open_flush_pipefs,
+	.read		= read_flush_pipefs,
+	.write		= write_flush_pipefs,
+	.release	= release_flush_pipefs,
+};
+
+int sunrpc_cache_register_pipefs(struct dentry *parent,
+				 const char *name, mode_t umode,
+				 struct cache_detail *cd)
+{
+	struct qstr q;
+	struct dentry *dir;
+	int ret = 0;
+
+	sunrpc_init_cache_detail(cd);
+	q.name = name;
+	q.len = strlen(name);
+	q.hash = full_name_hash(q.name, q.len);
+	dir = rpc_create_cache_dir(parent, &q, umode, cd);
+	if (!IS_ERR(dir))
+		cd->u.pipefs.dir = dir;
+	else {
+		sunrpc_destroy_cache_detail(cd);
+		ret = PTR_ERR(dir);
+	}
+	return ret;
+}
+EXPORT_SYMBOL_GPL(sunrpc_cache_register_pipefs);
+
+void sunrpc_cache_unregister_pipefs(struct cache_detail *cd)
+{
+	rpc_remove_cache_dir(cd->u.pipefs.dir);
+	cd->u.pipefs.dir = NULL;
+	sunrpc_destroy_cache_detail(cd);
+}
+EXPORT_SYMBOL_GPL(sunrpc_cache_unregister_pipefs);
+

net/sunrpc/clnt.c

@@ -27,6 +27,8 @@
 #include <linux/types.h>
 #include <linux/kallsyms.h>
 #include <linux/mm.h>
+#include <linux/namei.h>
+#include <linux/mount.h>
 #include <linux/slab.h>
 #include <linux/utsname.h>
 #include <linux/workqueue.h>
@@ -97,33 +99,49 @@ static int
 rpc_setup_pipedir(struct rpc_clnt *clnt, char *dir_name)
 {
 	static uint32_t clntid;
+	struct nameidata nd;
+	struct path path;
+	char name[15];
+	struct qstr q = {
+		.name = name,
+	};
 	int error;
 
-	clnt->cl_vfsmnt = ERR_PTR(-ENOENT);
+	clnt->cl_path.mnt = ERR_PTR(-ENOENT);
-	clnt->cl_dentry = ERR_PTR(-ENOENT);
+	clnt->cl_path.dentry = ERR_PTR(-ENOENT);
 	if (dir_name == NULL)
 		return 0;
 
-	clnt->cl_vfsmnt = rpc_get_mount();
+	path.mnt = rpc_get_mount();
-	if (IS_ERR(clnt->cl_vfsmnt))
+	if (IS_ERR(path.mnt))
-		return PTR_ERR(clnt->cl_vfsmnt);
+		return PTR_ERR(path.mnt);
+	error = vfs_path_lookup(path.mnt->mnt_root, path.mnt, dir_name, 0, &nd);
+	if (error)
+		goto err;
 
 	for (;;) {
-		snprintf(clnt->cl_pathname, sizeof(clnt->cl_pathname),
+		q.len = snprintf(name, sizeof(name), "clnt%x", (unsigned int)clntid++);
-				"%s/clnt%x", dir_name,
+		name[sizeof(name) - 1] = '\0';
-				(unsigned int)clntid++);
+		q.hash = full_name_hash(q.name, q.len);
-		clnt->cl_pathname[sizeof(clnt->cl_pathname) - 1] = '\0';
+		path.dentry = rpc_create_client_dir(nd.path.dentry, &q, clnt);
-		clnt->cl_dentry = rpc_mkdir(clnt->cl_pathname, clnt);
+		if (!IS_ERR(path.dentry))
-		if (!IS_ERR(clnt->cl_dentry))
+			break;
-			return 0;
+		error = PTR_ERR(path.dentry);
-		error = PTR_ERR(clnt->cl_dentry);
 		if (error != -EEXIST) {
-			printk(KERN_INFO "RPC: Couldn't create pipefs entry %s, error %d\n",
+			printk(KERN_INFO "RPC: Couldn't create pipefs entry"
-					clnt->cl_pathname, error);
+					" %s/%s, error %d\n",
+					dir_name, name, error);
+			goto err_path_put;
+		}
+	}
+	path_put(&nd.path);
+	clnt->cl_path = path;
+	return 0;
+err_path_put:
+	path_put(&nd.path);
+err:
 	rpc_put_mount();
 	return error;
-		}
-	}
 }
 
 static struct rpc_clnt * rpc_new_client(const struct rpc_create_args *args, struct rpc_xprt *xprt)
@@ -231,8 +249,8 @@ static struct rpc_clnt * rpc_new_client(const struct rpc_create_args *args, stru
 	return clnt;
 
 out_no_auth:
-	if (!IS_ERR(clnt->cl_dentry)) {
+	if (!IS_ERR(clnt->cl_path.dentry)) {
-		rpc_rmdir(clnt->cl_dentry);
+		rpc_remove_client_dir(clnt->cl_path.dentry);
 		rpc_put_mount();
 	}
 out_no_path:
@@ -423,8 +441,8 @@ rpc_free_client(struct kref *kref)
 
 	dprintk("RPC:       destroying %s client for %s\n",
 			clnt->cl_protname, clnt->cl_server);
-	if (!IS_ERR(clnt->cl_dentry)) {
+	if (!IS_ERR(clnt->cl_path.dentry)) {
-		rpc_rmdir(clnt->cl_dentry);
+		rpc_remove_client_dir(clnt->cl_path.dentry);
 		rpc_put_mount();
 	}
 	if (clnt->cl_parent != clnt) {

net/sunrpc/rpc_pipe.c

@@ -26,6 +26,7 @@
 #include <linux/sunrpc/clnt.h>
 #include <linux/workqueue.h>
 #include <linux/sunrpc/rpc_pipe_fs.h>
+#include <linux/sunrpc/cache.h>
 
 static struct vfsmount *rpc_mount __read_mostly;
 static int rpc_mount_count;
@@ -125,7 +126,7 @@ static void
 rpc_close_pipes(struct inode *inode)
 {
 	struct rpc_inode *rpci = RPC_I(inode);
-	struct rpc_pipe_ops *ops;
+	const struct rpc_pipe_ops *ops;
 	int need_release;
 
 	mutex_lock(&inode->i_mutex);
@@ -397,67 +398,13 @@ static const struct file_operations rpc_info_operations = {
 };
 
 
-/*
- * We have a single directory with 1 node in it.
- */
-enum {
-	RPCAUTH_Root = 1,
-	RPCAUTH_lockd,
-	RPCAUTH_mount,
-	RPCAUTH_nfs,
-	RPCAUTH_portmap,
-	RPCAUTH_statd,
-	RPCAUTH_nfsd4_cb,
-	RPCAUTH_RootEOF
-};
-
 /*
  * Description of fs contents.
  */
 struct rpc_filelist {
-	char *name;
+	const char *name;
 	const struct file_operations *i_fop;
-	int mode;
+	umode_t mode;
-};
-
-static struct rpc_filelist files[] = {
-	[RPCAUTH_lockd] = {
-		.name = "lockd",
-		.mode = S_IFDIR | S_IRUGO | S_IXUGO,
-	},
-	[RPCAUTH_mount] = {
-		.name = "mount",
-		.mode = S_IFDIR | S_IRUGO | S_IXUGO,
-	},
-	[RPCAUTH_nfs] = {
-		.name = "nfs",
-		.mode = S_IFDIR | S_IRUGO | S_IXUGO,
-	},
-	[RPCAUTH_portmap] = {
-		.name = "portmap",
-		.mode = S_IFDIR | S_IRUGO | S_IXUGO,
-	},
-	[RPCAUTH_statd] = {
-		.name = "statd",
-		.mode = S_IFDIR | S_IRUGO | S_IXUGO,
-	},
-	[RPCAUTH_nfsd4_cb] = {
-		.name = "nfsd4_cb",
-		.mode = S_IFDIR | S_IRUGO | S_IXUGO,
-	},
-};
-
-enum {
-	RPCAUTH_info = 2,
-	RPCAUTH_EOF
-};
-
-static struct rpc_filelist authfiles[] = {
-	[RPCAUTH_info] = {
-		.name = "info",
-		.i_fop = &rpc_info_operations,
-		.mode = S_IFREG | S_IRUSR,
-	},
 };
 
 struct vfsmount *rpc_get_mount(void)
@@ -469,11 +416,13 @@ struct vfsmount *rpc_get_mount(void)
 		return ERR_PTR(err);
 	return rpc_mount;
 }
+EXPORT_SYMBOL_GPL(rpc_get_mount);
 
 void rpc_put_mount(void)
 {
 	simple_release_fs(&rpc_mount, &rpc_mount_count);
 }
+EXPORT_SYMBOL_GPL(rpc_put_mount);
 
 static int rpc_delete_dentry(struct dentry *dentry)
 {
@@ -484,39 +433,8 @@ static const struct dentry_operations rpc_dentry_operations = {
 	.d_delete = rpc_delete_dentry,
 };
 
-static int
-rpc_lookup_parent(char *path, struct nameidata *nd)
-{
-	struct vfsmount *mnt;
-
-	if (path[0] == '\0')
-		return -ENOENT;
-
-	mnt = rpc_get_mount();
-	if (IS_ERR(mnt)) {
-		printk(KERN_WARNING "%s: %s failed to mount "
-			       "pseudofilesystem \n", __FILE__, __func__);
-		return PTR_ERR(mnt);
-	}
-
-	if (vfs_path_lookup(mnt->mnt_root, mnt, path, LOOKUP_PARENT, nd)) {
-		printk(KERN_WARNING "%s: %s failed to find path %s\n",
-				__FILE__, __func__, path);
-		rpc_put_mount();
-		return -ENOENT;
-	}
-	return 0;
-}
-
-static void
-rpc_release_path(struct nameidata *nd)
-{
-	path_put(&nd->path);
-	rpc_put_mount();
-}
-
 static struct inode *
-rpc_get_inode(struct super_block *sb, int mode)
+rpc_get_inode(struct super_block *sb, umode_t mode)
 {
 	struct inode *inode = new_inode(sb);
 	if (!inode)
@@ -534,212 +452,274 @@ rpc_get_inode(struct super_block *sb, int mode)
 	return inode;
 }
 
-/*
+static int __rpc_create_common(struct inode *dir, struct dentry *dentry,
- * FIXME: This probably has races.
+			       umode_t mode,
- */
+			       const struct file_operations *i_fop,
-static void rpc_depopulate(struct dentry *parent,
+			       void *private)
-			   unsigned long start, unsigned long eof)
-{
-	struct inode *dir = parent->d_inode;
-	struct list_head *pos, *next;
-	struct dentry *dentry, *dvec[10];
-	int n = 0;
-
-	mutex_lock_nested(&dir->i_mutex, I_MUTEX_CHILD);
-repeat:
-	spin_lock(&dcache_lock);
-	list_for_each_safe(pos, next, &parent->d_subdirs) {
-		dentry = list_entry(pos, struct dentry, d_u.d_child);
-		if (!dentry->d_inode ||
-				dentry->d_inode->i_ino < start ||
-				dentry->d_inode->i_ino >= eof)
-			continue;
-		spin_lock(&dentry->d_lock);
-		if (!d_unhashed(dentry)) {
-			dget_locked(dentry);
-			__d_drop(dentry);
-			spin_unlock(&dentry->d_lock);
-			dvec[n++] = dentry;
-			if (n == ARRAY_SIZE(dvec))
-				break;
-		} else
-			spin_unlock(&dentry->d_lock);
-	}
-	spin_unlock(&dcache_lock);
-	if (n) {
-		do {
-			dentry = dvec[--n];
-			if (S_ISREG(dentry->d_inode->i_mode))
-				simple_unlink(dir, dentry);
-			else if (S_ISDIR(dentry->d_inode->i_mode))
-				simple_rmdir(dir, dentry);
-			d_delete(dentry);
-			dput(dentry);
-		} while (n);
-		goto repeat;
-	}
-	mutex_unlock(&dir->i_mutex);
-}
-
-static int
-rpc_populate(struct dentry *parent,
-		struct rpc_filelist *files,
-		int start, int eof)
-{
-	struct inode *inode, *dir = parent->d_inode;
-	void *private = RPC_I(dir)->private;
-	struct dentry *dentry;
-	int mode, i;
-
-	mutex_lock(&dir->i_mutex);
-	for (i = start; i < eof; i++) {
-		dentry = d_alloc_name(parent, files[i].name);
-		if (!dentry)
-			goto out_bad;
-		dentry->d_op = &rpc_dentry_operations;
-		mode = files[i].mode;
-		inode = rpc_get_inode(dir->i_sb, mode);
-		if (!inode) {
-			dput(dentry);
-			goto out_bad;
-		}
-		inode->i_ino = i;
-		if (files[i].i_fop)
-			inode->i_fop = files[i].i_fop;
-		if (private)
-			rpc_inode_setowner(inode, private);
-		if (S_ISDIR(mode))
-			inc_nlink(dir);
-		d_add(dentry, inode);
-		fsnotify_create(dir, dentry);
-	}
-	mutex_unlock(&dir->i_mutex);
-	return 0;
-out_bad:
-	mutex_unlock(&dir->i_mutex);
-	printk(KERN_WARNING "%s: %s failed to populate directory %s\n",
-			__FILE__, __func__, parent->d_name.name);
-	return -ENOMEM;
-}
-
-static int
-__rpc_mkdir(struct inode *dir, struct dentry *dentry)
 {
 	struct inode *inode;
 
-	inode = rpc_get_inode(dir->i_sb, S_IFDIR | S_IRUGO | S_IXUGO);
+	BUG_ON(!d_unhashed(dentry));
+	inode = rpc_get_inode(dir->i_sb, mode);
 	if (!inode)
 		goto out_err;
 	inode->i_ino = iunique(dir->i_sb, 100);
-	d_instantiate(dentry, inode);
+	if (i_fop)
-	inc_nlink(dir);
+		inode->i_fop = i_fop;
-	fsnotify_mkdir(dir, dentry);
+	if (private)
+		rpc_inode_setowner(inode, private);
+	d_add(dentry, inode);
 	return 0;
 out_err:
 	printk(KERN_WARNING "%s: %s failed to allocate inode for dentry %s\n",
 			__FILE__, __func__, dentry->d_name.name);
+	dput(dentry);
 	return -ENOMEM;
 }
 
-static int
+static int __rpc_create(struct inode *dir, struct dentry *dentry,
-__rpc_rmdir(struct inode *dir, struct dentry *dentry)
+			umode_t mode,
+			const struct file_operations *i_fop,
+			void *private)
 {
-	int error;
+	int err;
-	error = simple_rmdir(dir, dentry);
+
-	if (!error)
+	err = __rpc_create_common(dir, dentry, S_IFREG | mode, i_fop, private);
-		d_delete(dentry);
+	if (err)
-	return error;
+		return err;
+	fsnotify_create(dir, dentry);
+	return 0;
 }
 
-static struct dentry *
+static int __rpc_mkdir(struct inode *dir, struct dentry *dentry,
-rpc_lookup_create(struct dentry *parent, const char *name, int len, int exclusive)
+		       umode_t mode,
+		       const struct file_operations *i_fop,
+		       void *private)
+{
+	int err;
+
+	err = __rpc_create_common(dir, dentry, S_IFDIR | mode, i_fop, private);
+	if (err)
+		return err;
+	inc_nlink(dir);
+	fsnotify_mkdir(dir, dentry);
+	return 0;
+}
+
+static int __rpc_mkpipe(struct inode *dir, struct dentry *dentry,
+			umode_t mode,
+			const struct file_operations *i_fop,
+			void *private,
+			const struct rpc_pipe_ops *ops,
+			int flags)
+{
+	struct rpc_inode *rpci;
+	int err;
+
+	err = __rpc_create_common(dir, dentry, S_IFIFO | mode, i_fop, private);
+	if (err)
+		return err;
+	rpci = RPC_I(dentry->d_inode);
+	rpci->nkern_readwriters = 1;
+	rpci->private = private;
+	rpci->flags = flags;
+	rpci->ops = ops;
+	fsnotify_create(dir, dentry);
+	return 0;
+}
+
+static int __rpc_rmdir(struct inode *dir, struct dentry *dentry)
+{
+	int ret;
+
+	dget(dentry);
+	ret = simple_rmdir(dir, dentry);
+	d_delete(dentry);
+	dput(dentry);
+	return ret;
+}
+
+static int __rpc_unlink(struct inode *dir, struct dentry *dentry)
+{
+	int ret;
+
+	dget(dentry);
+	ret = simple_unlink(dir, dentry);
+	d_delete(dentry);
+	dput(dentry);
+	return ret;
+}
+
+static int __rpc_rmpipe(struct inode *dir, struct dentry *dentry)
+{
+	struct inode *inode = dentry->d_inode;
+	struct rpc_inode *rpci = RPC_I(inode);
+
+	rpci->nkern_readwriters--;
+	if (rpci->nkern_readwriters != 0)
+		return 0;
+	rpc_close_pipes(inode);
+	return __rpc_unlink(dir, dentry);
+}
+
+static struct dentry *__rpc_lookup_create(struct dentry *parent,
+					  struct qstr *name)
+{
+	struct dentry *dentry;
+
+	dentry = d_lookup(parent, name);
+	if (!dentry) {
+		dentry = d_alloc(parent, name);
+		if (!dentry) {
+			dentry = ERR_PTR(-ENOMEM);
+			goto out_err;
+		}
+	}
+	if (!dentry->d_inode)
+		dentry->d_op = &rpc_dentry_operations;
+out_err:
+	return dentry;
+}
+
+static struct dentry *__rpc_lookup_create_exclusive(struct dentry *parent,
+					  struct qstr *name)
+{
+	struct dentry *dentry;
+
+	dentry = __rpc_lookup_create(parent, name);
+	if (dentry->d_inode == NULL)
+		return dentry;
+	dput(dentry);
+	return ERR_PTR(-EEXIST);
+}
+
+/*
+ * FIXME: This probably has races.
+ */
+static void __rpc_depopulate(struct dentry *parent,
+			     const struct rpc_filelist *files,
+			     int start, int eof)
 {
 	struct inode *dir = parent->d_inode;
 	struct dentry *dentry;
+	struct qstr name;
+	int i;
+
+	for (i = start; i < eof; i++) {
+		name.name = files[i].name;
+		name.len = strlen(files[i].name);
+		name.hash = full_name_hash(name.name, name.len);
+		dentry = d_lookup(parent, &name);
+
+		if (dentry == NULL)
+			continue;
+		if (dentry->d_inode == NULL)
+			goto next;
+		switch (dentry->d_inode->i_mode & S_IFMT) {
+			default:
+				BUG();
+			case S_IFREG:
+				__rpc_unlink(dir, dentry);
+				break;
+			case S_IFDIR:
+				__rpc_rmdir(dir, dentry);
+		}
+next:
+		dput(dentry);
+	}
+}
+
+static void rpc_depopulate(struct dentry *parent,
+			   const struct rpc_filelist *files,
+			   int start, int eof)
+{
+	struct inode *dir = parent->d_inode;
+
+	mutex_lock_nested(&dir->i_mutex, I_MUTEX_CHILD);
+	__rpc_depopulate(parent, files, start, eof);
+	mutex_unlock(&dir->i_mutex);
+}
+
+static int rpc_populate(struct dentry *parent,
+			const struct rpc_filelist *files,
+			int start, int eof,
+			void *private)
+{
+	struct inode *dir = parent->d_inode;
+	struct dentry *dentry;
+	int i, err;
+
+	mutex_lock(&dir->i_mutex);
+	for (i = start; i < eof; i++) {
+		struct qstr q;
+
+		q.name = files[i].name;
+		q.len = strlen(files[i].name);
+		q.hash = full_name_hash(q.name, q.len);
+		dentry = __rpc_lookup_create_exclusive(parent, &q);
+		err = PTR_ERR(dentry);
+		if (IS_ERR(dentry))
+			goto out_bad;
+		switch (files[i].mode & S_IFMT) {
+			default:
+				BUG();
+			case S_IFREG:
+				err = __rpc_create(dir, dentry,
+						files[i].mode,
+						files[i].i_fop,
+						private);
+				break;
+			case S_IFDIR:
+				err = __rpc_mkdir(dir, dentry,
+						files[i].mode,
+						NULL,
+						private);
+		}
+		if (err != 0)
+			goto out_bad;
+	}
+	mutex_unlock(&dir->i_mutex);
+	return 0;
+out_bad:
+	__rpc_depopulate(parent, files, start, eof);
+	mutex_unlock(&dir->i_mutex);
+	printk(KERN_WARNING "%s: %s failed to populate directory %s\n",
+			__FILE__, __func__, parent->d_name.name);
+	return err;
+}
+
+static struct dentry *rpc_mkdir_populate(struct dentry *parent,
+		struct qstr *name, umode_t mode, void *private,
+		int (*populate)(struct dentry *, void *), void *args_populate)
+{
+	struct dentry *dentry;
+	struct inode *dir = parent->d_inode;
+	int error;
 
 	mutex_lock_nested(&dir->i_mutex, I_MUTEX_PARENT);
-	dentry = lookup_one_len(name, parent, len);
+	dentry = __rpc_lookup_create_exclusive(parent, name);
 	if (IS_ERR(dentry))
+		goto out;
+	error = __rpc_mkdir(dir, dentry, mode, NULL, private);
+	if (error != 0)
 		goto out_err;
-	if (!dentry->d_inode)
+	if (populate != NULL) {
-		dentry->d_op = &rpc_dentry_operations;
+		error = populate(dentry, args_populate);
-	else if (exclusive) {
-		dput(dentry);
-		dentry = ERR_PTR(-EEXIST);
-		goto out_err;
-	}
-	return dentry;
-out_err:
-	mutex_unlock(&dir->i_mutex);
-	return dentry;
-}
-
-static struct dentry *
-rpc_lookup_negative(char *path, struct nameidata *nd)
-{
-	struct dentry *dentry;
-	int error;
-
-	if ((error = rpc_lookup_parent(path, nd)) != 0)
-		return ERR_PTR(error);
-	dentry = rpc_lookup_create(nd->path.dentry, nd->last.name, nd->last.len,
-				   1);
-	if (IS_ERR(dentry))
-		rpc_release_path(nd);
-	return dentry;
-}
-
-/**
- * rpc_mkdir - Create a new directory in rpc_pipefs
- * @path: path from the rpc_pipefs root to the new directory
- * @rpc_client: rpc client to associate with this directory
- *
- * This creates a directory at the given @path associated with
- * @rpc_clnt, which will contain a file named "info" with some basic
- * information about the client, together with any "pipes" that may
- * later be created using rpc_mkpipe().
- */
-struct dentry *
-rpc_mkdir(char *path, struct rpc_clnt *rpc_client)
-{
-	struct nameidata nd;
-	struct dentry *dentry;
-	struct inode *dir;
-	int error;
-
-	dentry = rpc_lookup_negative(path, &nd);
-	if (IS_ERR(dentry))
-		return dentry;
-	dir = nd.path.dentry->d_inode;
-	if ((error = __rpc_mkdir(dir, dentry)) != 0)
-		goto err_dput;
-	RPC_I(dentry->d_inode)->private = rpc_client;
-	error = rpc_populate(dentry, authfiles,
-			RPCAUTH_info, RPCAUTH_EOF);
 		if (error)
-		goto err_depopulate;
+			goto err_rmdir;
-	dget(dentry);
+	}
 out:
 	mutex_unlock(&dir->i_mutex);
-	rpc_release_path(&nd);
 	return dentry;
-err_depopulate:
+err_rmdir:
-	rpc_depopulate(dentry, RPCAUTH_info, RPCAUTH_EOF);
 	__rpc_rmdir(dir, dentry);
-err_dput:
+out_err:
-	dput(dentry);
-	printk(KERN_WARNING "%s: %s() failed to create directory %s (errno = %d)\n",
-			__FILE__, __func__, path, error);
 	dentry = ERR_PTR(error);
 	goto out;
 }
 
-/**
+static int rpc_rmdir_depopulate(struct dentry *dentry,
- * rpc_rmdir - Remove a directory created with rpc_mkdir()
+		void (*depopulate)(struct dentry *))
- * @dentry: directory to remove
- */
-int
-rpc_rmdir(struct dentry *dentry)
 {
 	struct dentry *parent;
 	struct inode *dir;
@@ -748,9 +728,9 @@ rpc_rmdir(struct dentry *dentry)
 	parent = dget_parent(dentry);
 	dir = parent->d_inode;
 	mutex_lock_nested(&dir->i_mutex, I_MUTEX_PARENT);
-	rpc_depopulate(dentry, RPCAUTH_info, RPCAUTH_EOF);
+	if (depopulate != NULL)
+		depopulate(dentry);
 	error = __rpc_rmdir(dir, dentry);
-	dput(dentry);
 	mutex_unlock(&dir->i_mutex);
 	dput(parent);
 	return error;
@@ -776,50 +756,54 @@ rpc_rmdir(struct dentry *dentry)
  * The @private argument passed here will be available to all these methods
  * from the file pointer, via RPC_I(file->f_dentry->d_inode)->private.
  */
-struct dentry *
+struct dentry *rpc_mkpipe(struct dentry *parent, const char *name,
-rpc_mkpipe(struct dentry *parent, const char *name, void *private, struct rpc_pipe_ops *ops, int flags)
+			  void *private, const struct rpc_pipe_ops *ops,
+			  int flags)
 {
 	struct dentry *dentry;
-	struct inode *dir, *inode;
+	struct inode *dir = parent->d_inode;
-	struct rpc_inode *rpci;
+	umode_t umode = S_IFIFO | S_IRUSR | S_IWUSR;
+	struct qstr q;
+	int err;
 
-	dentry = rpc_lookup_create(parent, name, strlen(name), 0);
+	if (ops->upcall == NULL)
+		umode &= ~S_IRUGO;
+	if (ops->downcall == NULL)
+		umode &= ~S_IWUGO;
+
+	q.name = name;
+	q.len = strlen(name);
+	q.hash = full_name_hash(q.name, q.len),
+
+	mutex_lock_nested(&dir->i_mutex, I_MUTEX_PARENT);
+	dentry = __rpc_lookup_create(parent, &q);
 	if (IS_ERR(dentry))
-		return dentry;
+		goto out;
-	dir = parent->d_inode;
 	if (dentry->d_inode) {
-		rpci = RPC_I(dentry->d_inode);
+		struct rpc_inode *rpci = RPC_I(dentry->d_inode);
 		if (rpci->private != private ||
 				rpci->ops != ops ||
 				rpci->flags != flags) {
 			dput (dentry);
-			dentry = ERR_PTR(-EBUSY);
+			err = -EBUSY;
+			goto out_err;
 		}
 		rpci->nkern_readwriters++;
 		goto out;
 	}
-	inode = rpc_get_inode(dir->i_sb, S_IFIFO | S_IRUSR | S_IWUSR);
+
-	if (!inode)
+	err = __rpc_mkpipe(dir, dentry, umode, &rpc_pipe_fops,
-		goto err_dput;
+			   private, ops, flags);
-	inode->i_ino = iunique(dir->i_sb, 100);
+	if (err)
-	inode->i_fop = &rpc_pipe_fops;
+		goto out_err;
-	d_instantiate(dentry, inode);
-	rpci = RPC_I(inode);
-	rpci->private = private;
-	rpci->flags = flags;
-	rpci->ops = ops;
-	rpci->nkern_readwriters = 1;
-	fsnotify_create(dir, dentry);
-	dget(dentry);
 out:
 	mutex_unlock(&dir->i_mutex);
 	return dentry;
-err_dput:
+out_err:
-	dput(dentry);
+	dentry = ERR_PTR(err);
-	dentry = ERR_PTR(-ENOMEM);
 	printk(KERN_WARNING "%s: %s() failed to create pipe %s/%s (errno = %d)\n",
 			__FILE__, __func__, parent->d_name.name, name,
-			-ENOMEM);
+			err);
 	goto out;
 }
 EXPORT_SYMBOL_GPL(rpc_mkpipe);
@@ -842,19 +826,107 @@ rpc_unlink(struct dentry *dentry)
 	parent = dget_parent(dentry);
 	dir = parent->d_inode;
 	mutex_lock_nested(&dir->i_mutex, I_MUTEX_PARENT);
-	if (--RPC_I(dentry->d_inode)->nkern_readwriters == 0) {
+	error = __rpc_rmpipe(dir, dentry);
-		rpc_close_pipes(dentry->d_inode);
-		error = simple_unlink(dir, dentry);
-		if (!error)
-			d_delete(dentry);
-	}
-	dput(dentry);
 	mutex_unlock(&dir->i_mutex);
 	dput(parent);
 	return error;
 }
 EXPORT_SYMBOL_GPL(rpc_unlink);
 
+enum {
+	RPCAUTH_info,
+	RPCAUTH_EOF
+};
+
+static const struct rpc_filelist authfiles[] = {
+	[RPCAUTH_info] = {
+		.name = "info",
+		.i_fop = &rpc_info_operations,
+		.mode = S_IFREG | S_IRUSR,
+	},
+};
+
+static int rpc_clntdir_populate(struct dentry *dentry, void *private)
+{
+	return rpc_populate(dentry,
+			    authfiles, RPCAUTH_info, RPCAUTH_EOF,
+			    private);
+}
+
+static void rpc_clntdir_depopulate(struct dentry *dentry)
+{
+	rpc_depopulate(dentry, authfiles, RPCAUTH_info, RPCAUTH_EOF);
+}
+
+/**
+ * rpc_create_client_dir - Create a new rpc_client directory in rpc_pipefs
+ * @path: path from the rpc_pipefs root to the new directory
+ * @rpc_client: rpc client to associate with this directory
+ *
+ * This creates a directory at the given @path associated with
+ * @rpc_clnt, which will contain a file named "info" with some basic
+ * information about the client, together with any "pipes" that may
+ * later be created using rpc_mkpipe().
+ */
+struct dentry *rpc_create_client_dir(struct dentry *dentry,
+				   struct qstr *name,
+				   struct rpc_clnt *rpc_client)
+{
+	return rpc_mkdir_populate(dentry, name, S_IRUGO | S_IXUGO, NULL,
+			rpc_clntdir_populate, rpc_client);
+}
+
+/**
+ * rpc_remove_client_dir - Remove a directory created with rpc_create_client_dir()
+ * @dentry: directory to remove
+ */
+int rpc_remove_client_dir(struct dentry *dentry)
+{
+	return rpc_rmdir_depopulate(dentry, rpc_clntdir_depopulate);
+}
+
+static const struct rpc_filelist cache_pipefs_files[3] = {
+	[0] = {
+		.name = "channel",
+		.i_fop = &cache_file_operations_pipefs,
+		.mode = S_IFREG|S_IRUSR|S_IWUSR,
+	},
+	[1] = {
+		.name = "content",
+		.i_fop = &content_file_operations_pipefs,
+		.mode = S_IFREG|S_IRUSR,
+	},
+	[2] = {
+		.name = "flush",
+		.i_fop = &cache_flush_operations_pipefs,
+		.mode = S_IFREG|S_IRUSR|S_IWUSR,
+	},
+};
+
+static int rpc_cachedir_populate(struct dentry *dentry, void *private)
+{
+	return rpc_populate(dentry,
+			    cache_pipefs_files, 0, 3,
+			    private);
+}
+
+static void rpc_cachedir_depopulate(struct dentry *dentry)
+{
+	rpc_depopulate(dentry, cache_pipefs_files, 0, 3);
+}
+
+struct dentry *rpc_create_cache_dir(struct dentry *parent, struct qstr *name,
+				    mode_t umode, struct cache_detail *cd)
+{
+	return rpc_mkdir_populate(parent, name, umode, NULL,
+			rpc_cachedir_populate, cd);
+}
+
+void rpc_remove_cache_dir(struct dentry *dentry)
+{
+	rpc_rmdir_depopulate(dentry, rpc_cachedir_depopulate);
+}
+
 /*
  * populate the filesystem
  */
@@ -866,6 +938,51 @@ static struct super_operations s_ops = {
 
 #define RPCAUTH_GSSMAGIC 0x67596969
 
+/*
+ * We have a single directory with 1 node in it.
+ */
+enum {
+	RPCAUTH_lockd,
+	RPCAUTH_mount,
+	RPCAUTH_nfs,
+	RPCAUTH_portmap,
+	RPCAUTH_statd,
+	RPCAUTH_nfsd4_cb,
+	RPCAUTH_cache,
+	RPCAUTH_RootEOF
+};
+
+static const struct rpc_filelist files[] = {
+	[RPCAUTH_lockd] = {
+		.name = "lockd",
+		.mode = S_IFDIR | S_IRUGO | S_IXUGO,
+	},
+	[RPCAUTH_mount] = {
+		.name = "mount",
+		.mode = S_IFDIR | S_IRUGO | S_IXUGO,
+	},
+	[RPCAUTH_nfs] = {
+		.name = "nfs",
+		.mode = S_IFDIR | S_IRUGO | S_IXUGO,
+	},
+	[RPCAUTH_portmap] = {
+		.name = "portmap",
+		.mode = S_IFDIR | S_IRUGO | S_IXUGO,
+	},
+	[RPCAUTH_statd] = {
+		.name = "statd",
+		.mode = S_IFDIR | S_IRUGO | S_IXUGO,
+	},
+	[RPCAUTH_nfsd4_cb] = {
+		.name = "nfsd4_cb",
+		.mode = S_IFDIR | S_IRUGO | S_IXUGO,
+	},
+	[RPCAUTH_cache] = {
+		.name = "cache",
+		.mode = S_IFDIR | S_IRUGO | S_IXUGO,
+	},
+};
+
 static int
 rpc_fill_super(struct super_block *sb, void *data, int silent)
 {
@@ -886,7 +1003,7 @@ rpc_fill_super(struct super_block *sb, void *data, int silent)
 		iput(inode);
 		return -ENOMEM;
 	}
-	if (rpc_populate(root, files, RPCAUTH_Root + 1, RPCAUTH_RootEOF))
+	if (rpc_populate(root, files, RPCAUTH_lockd, RPCAUTH_RootEOF, NULL))
 		goto out;
 	sb->s_root = root;
 	return 0;

net/sunrpc/rpcb_clnt.c

@@ -75,6 +75,37 @@ enum {
 #define RPCB_OWNER_STRING	"0"
 #define RPCB_MAXOWNERLEN	sizeof(RPCB_OWNER_STRING)
 
+/*
+ * XDR data type sizes
+ */
+#define RPCB_program_sz		(1)
+#define RPCB_version_sz		(1)
+#define RPCB_protocol_sz	(1)
+#define RPCB_port_sz		(1)
+#define RPCB_boolean_sz		(1)
+
+#define RPCB_netid_sz		(1 + XDR_QUADLEN(RPCBIND_MAXNETIDLEN))
+#define RPCB_addr_sz		(1 + XDR_QUADLEN(RPCBIND_MAXUADDRLEN))
+#define RPCB_ownerstring_sz	(1 + XDR_QUADLEN(RPCB_MAXOWNERLEN))
+
+/*
+ * XDR argument and result sizes
+ */
+#define RPCB_mappingargs_sz	(RPCB_program_sz + RPCB_version_sz + \
+				RPCB_protocol_sz + RPCB_port_sz)
+#define RPCB_getaddrargs_sz	(RPCB_program_sz + RPCB_version_sz + \
+				RPCB_netid_sz + RPCB_addr_sz + \
+				RPCB_ownerstring_sz)
+
+#define RPCB_getportres_sz	RPCB_port_sz
+#define RPCB_setres_sz		RPCB_boolean_sz
+
+/*
+ * Note that RFC 1833 does not put any size restrictions on the
+ * address string returned by the remote rpcbind database.
+ */
+#define RPCB_getaddrres_sz	RPCB_addr_sz
+
 static void			rpcb_getport_done(struct rpc_task *, void *);
 static void			rpcb_map_release(void *data);
 static struct rpc_program	rpcb_program;
@@ -122,6 +153,7 @@ static void rpcb_map_release(void *data)
 
 	rpcb_wake_rpcbind_waiters(map->r_xprt, map->r_status);
 	xprt_put(map->r_xprt);
+	kfree(map->r_addr);
 	kfree(map);
 }
 
@@ -268,12 +300,9 @@ static int rpcb_register_inet4(const struct sockaddr *sap,
 	const struct sockaddr_in *sin = (const struct sockaddr_in *)sap;
 	struct rpcbind_args *map = msg->rpc_argp;
 	unsigned short port = ntohs(sin->sin_port);
-	char buf[32];
+	int result;
 
-	/* Construct AF_INET universal address */
+	map->r_addr = rpc_sockaddr2uaddr(sap);
-	snprintf(buf, sizeof(buf), "%pI4.%u.%u",
-		 &sin->sin_addr.s_addr, port >> 8, port & 0xff);
-	map->r_addr = buf;
 
 	dprintk("RPC:       %sregistering [%u, %u, %s, '%s'] with "
 		"local rpcbind\n", (port ? "" : "un"),
@@ -284,7 +313,9 @@ static int rpcb_register_inet4(const struct sockaddr *sap,
 	if (port)
 		msg->rpc_proc = &rpcb_procedures4[RPCBPROC_SET];
 
-	return rpcb_register_call(RPCBVERS_4, msg);
+	result = rpcb_register_call(RPCBVERS_4, msg);
+	kfree(map->r_addr);
+	return result;
 }
 
 /*
@@ -296,16 +327,9 @@ static int rpcb_register_inet6(const struct sockaddr *sap,
 	const struct sockaddr_in6 *sin6 = (const struct sockaddr_in6 *)sap;
 	struct rpcbind_args *map = msg->rpc_argp;
 	unsigned short port = ntohs(sin6->sin6_port);
-	char buf[64];
+	int result;
 
-	/* Construct AF_INET6 universal address */
+	map->r_addr = rpc_sockaddr2uaddr(sap);
-	if (ipv6_addr_any(&sin6->sin6_addr))
-		snprintf(buf, sizeof(buf), "::.%u.%u",
-				port >> 8, port & 0xff);
-	else
-		snprintf(buf, sizeof(buf), "%pI6.%u.%u",
-			 &sin6->sin6_addr, port >> 8, port & 0xff);
-	map->r_addr = buf;
 
 	dprintk("RPC:       %sregistering [%u, %u, %s, '%s'] with "
 		"local rpcbind\n", (port ? "" : "un"),
@@ -316,7 +340,9 @@ static int rpcb_register_inet6(const struct sockaddr *sap,
 	if (port)
 		msg->rpc_proc = &rpcb_procedures4[RPCBPROC_SET];
 
-	return rpcb_register_call(RPCBVERS_4, msg);
+	result = rpcb_register_call(RPCBVERS_4, msg);
+	kfree(map->r_addr);
+	return result;
 }
 
 static int rpcb_unregister_all_protofamilies(struct rpc_message *msg)
@@ -428,7 +454,7 @@ int rpcb_getport_sync(struct sockaddr_in *sin, u32 prog, u32 vers, int prot)
 	struct rpc_message msg = {
 		.rpc_proc	= &rpcb_procedures2[RPCBPROC_GETPORT],
 		.rpc_argp	= &map,
-		.rpc_resp	= &map.r_port,
+		.rpc_resp	= &map,
 	};
 	struct rpc_clnt	*rpcb_clnt;
 	int status;
@@ -458,7 +484,7 @@ static struct rpc_task *rpcb_call_async(struct rpc_clnt *rpcb_clnt, struct rpcbi
 	struct rpc_message msg = {
 		.rpc_proc = proc,
 		.rpc_argp = map,
-		.rpc_resp = &map->r_port,
+		.rpc_resp = map,
 	};
 	struct rpc_task_setup task_setup_data = {
 		.rpc_client = rpcb_clnt,
@@ -539,6 +565,7 @@ void rpcb_getport_async(struct rpc_task *task)
 		goto bailout_nofree;
 	}
 
+	/* Parent transport's destination address */
 	salen = rpc_peeraddr(clnt, sap, sizeof(addr));
 
 	/* Don't ever use rpcbind v2 for AF_INET6 requests */
@@ -589,11 +616,22 @@ void rpcb_getport_async(struct rpc_task *task)
 	map->r_prot = xprt->prot;
 	map->r_port = 0;
 	map->r_xprt = xprt_get(xprt);
-	map->r_netid = rpc_peeraddr2str(clnt, RPC_DISPLAY_NETID);
-	map->r_addr = rpc_peeraddr2str(rpcb_clnt, RPC_DISPLAY_UNIVERSAL_ADDR);
-	map->r_owner = "";
 	map->r_status = -EIO;
 
+	switch (bind_version) {
+	case RPCBVERS_4:
+	case RPCBVERS_3:
+		map->r_netid = rpc_peeraddr2str(clnt, RPC_DISPLAY_NETID);
+		map->r_addr = rpc_sockaddr2uaddr(sap);
+		map->r_owner = "";
+		break;
+	case RPCBVERS_2:
+		map->r_addr = NULL;
+		break;
+	default:
+		BUG();
+	}
+
 	child = rpcb_call_async(rpcb_clnt, map, proc);
 	rpc_release_client(rpcb_clnt);
 	if (IS_ERR(child)) {
@@ -656,176 +694,278 @@ static void rpcb_getport_done(struct rpc_task *child, void *data)
  * XDR functions for rpcbind
  */
 
-static int rpcb_encode_mapping(struct rpc_rqst *req, __be32 *p,
+static int rpcb_enc_mapping(struct rpc_rqst *req, __be32 *p,
-			       struct rpcbind_args *rpcb)
+			    const struct rpcbind_args *rpcb)
 {
-	dprintk("RPC:       encoding rpcb request (%u, %u, %d, %u)\n",
+	struct rpc_task *task = req->rq_task;
+	struct xdr_stream xdr;
+
+	dprintk("RPC: %5u encoding PMAP_%s call (%u, %u, %d, %u)\n",
+			task->tk_pid, task->tk_msg.rpc_proc->p_name,
 			rpcb->r_prog, rpcb->r_vers, rpcb->r_prot, rpcb->r_port);
+
+	xdr_init_encode(&xdr, &req->rq_snd_buf, p);
+
+	p = xdr_reserve_space(&xdr, sizeof(__be32) * RPCB_mappingargs_sz);
+	if (unlikely(p == NULL))
+		return -EIO;
+
 	*p++ = htonl(rpcb->r_prog);
 	*p++ = htonl(rpcb->r_vers);
 	*p++ = htonl(rpcb->r_prot);
-	*p++ = htonl(rpcb->r_port);
+	*p   = htonl(rpcb->r_port);
 
-	req->rq_slen = xdr_adjust_iovec(req->rq_svec, p);
 	return 0;
 }
 
-static int rpcb_decode_getport(struct rpc_rqst *req, __be32 *p,
+static int rpcb_dec_getport(struct rpc_rqst *req, __be32 *p,
-			       unsigned short *portp)
+			    struct rpcbind_args *rpcb)
 {
-	*portp = (unsigned short) ntohl(*p++);
+	struct rpc_task *task = req->rq_task;
-	dprintk("RPC:       rpcb getport result: %u\n",
+	struct xdr_stream xdr;
-			*portp);
+	unsigned long port;
+
+	xdr_init_decode(&xdr, &req->rq_rcv_buf, p);
+
+	rpcb->r_port = 0;
+
+	p = xdr_inline_decode(&xdr, sizeof(__be32));
+	if (unlikely(p == NULL))
+		return -EIO;
+
+	port = ntohl(*p);
+	dprintk("RPC: %5u PMAP_%s result: %lu\n", task->tk_pid,
+			task->tk_msg.rpc_proc->p_name, port);
+	if (unlikely(port > USHORT_MAX))
+		return -EIO;
+
+	rpcb->r_port = port;
 	return 0;
 }
 
-static int rpcb_decode_set(struct rpc_rqst *req, __be32 *p,
+static int rpcb_dec_set(struct rpc_rqst *req, __be32 *p,
 			unsigned int *boolp)
 {
-	*boolp = (unsigned int) ntohl(*p++);
+	struct rpc_task *task = req->rq_task;
-	dprintk("RPC:       rpcb set/unset call %s\n",
+	struct xdr_stream xdr;
+
+	xdr_init_decode(&xdr, &req->rq_rcv_buf, p);
+
+	p = xdr_inline_decode(&xdr, sizeof(__be32));
+	if (unlikely(p == NULL))
+		return -EIO;
+
+	*boolp = 0;
+	if (*p)
+		*boolp = 1;
+
+	dprintk("RPC: %5u RPCB_%s call %s\n",
+			task->tk_pid, task->tk_msg.rpc_proc->p_name,
 			(*boolp ? "succeeded" : "failed"));
 	return 0;
 }
 
-static int rpcb_encode_getaddr(struct rpc_rqst *req, __be32 *p,
+static int encode_rpcb_string(struct xdr_stream *xdr, const char *string,
+				const u32 maxstrlen)
+{
+	u32 len;
+	__be32 *p;
+
+	if (unlikely(string == NULL))
+		return -EIO;
+	len = strlen(string);
+	if (unlikely(len > maxstrlen))
+		return -EIO;
+
+	p = xdr_reserve_space(xdr, sizeof(__be32) + len);
+	if (unlikely(p == NULL))
+		return -EIO;
+	xdr_encode_opaque(p, string, len);
+
+	return 0;
+}
+
+static int rpcb_enc_getaddr(struct rpc_rqst *req, __be32 *p,
+			    const struct rpcbind_args *rpcb)
+{
+	struct rpc_task *task = req->rq_task;
+	struct xdr_stream xdr;
+
+	dprintk("RPC: %5u encoding RPCB_%s call (%u, %u, '%s', '%s')\n",
+			task->tk_pid, task->tk_msg.rpc_proc->p_name,
+			rpcb->r_prog, rpcb->r_vers,
+			rpcb->r_netid, rpcb->r_addr);
+
+	xdr_init_encode(&xdr, &req->rq_snd_buf, p);
+
+	p = xdr_reserve_space(&xdr,
+			sizeof(__be32) * (RPCB_program_sz + RPCB_version_sz));
+	if (unlikely(p == NULL))
+		return -EIO;
+	*p++ = htonl(rpcb->r_prog);
+	*p = htonl(rpcb->r_vers);
+
+	if (encode_rpcb_string(&xdr, rpcb->r_netid, RPCBIND_MAXNETIDLEN))
+		return -EIO;
+	if (encode_rpcb_string(&xdr, rpcb->r_addr, RPCBIND_MAXUADDRLEN))
+		return -EIO;
+	if (encode_rpcb_string(&xdr, rpcb->r_owner, RPCB_MAXOWNERLEN))
+		return -EIO;
+
+	return 0;
+}
+
+static int rpcb_dec_getaddr(struct rpc_rqst *req, __be32 *p,
 			    struct rpcbind_args *rpcb)
 {
-	dprintk("RPC:       encoding rpcb request (%u, %u, %s)\n",
+	struct sockaddr_storage address;
-			rpcb->r_prog, rpcb->r_vers, rpcb->r_addr);
+	struct sockaddr *sap = (struct sockaddr *)&address;
-	*p++ = htonl(rpcb->r_prog);
+	struct rpc_task *task = req->rq_task;
-	*p++ = htonl(rpcb->r_vers);
+	struct xdr_stream xdr;
+	u32 len;
 
-	p = xdr_encode_string(p, rpcb->r_netid);
+	rpcb->r_port = 0;
-	p = xdr_encode_string(p, rpcb->r_addr);
-	p = xdr_encode_string(p, rpcb->r_owner);
 
-	req->rq_slen = xdr_adjust_iovec(req->rq_svec, p);
+	xdr_init_decode(&xdr, &req->rq_rcv_buf, p);
 
-	return 0;
+	p = xdr_inline_decode(&xdr, sizeof(__be32));
-}
+	if (unlikely(p == NULL))
+		goto out_fail;
+	len = ntohl(*p);
 
-static int rpcb_decode_getaddr(struct rpc_rqst *req, __be32 *p,
+	/*
-			       unsigned short *portp)
+	 * If the returned universal address is a null string,
-{
+	 * the requested RPC service was not registered.
-	char *addr;
+	 */
-	u32 addr_len;
+	if (len == 0) {
-	int c, i, f, first, val;
+		dprintk("RPC: %5u RPCB reply: program not registered\n",
-
+				task->tk_pid);
-	*portp = 0;
-	addr_len = ntohl(*p++);
-
-	if (addr_len == 0) {
-		dprintk("RPC:       rpcb_decode_getaddr: "
-					"service is not registered\n");
 		return 0;
 	}
 
-	/*
+	if (unlikely(len > RPCBIND_MAXUADDRLEN))
-	 * Simple sanity check.
+		goto out_fail;
-	 */
-	if (addr_len > RPCBIND_MAXUADDRLEN)
-		goto out_err;
 
-	/*
+	p = xdr_inline_decode(&xdr, len);
-	 * Start at the end and walk backwards until the first dot
+	if (unlikely(p == NULL))
-	 * is encountered.  When the second dot is found, we have
+		goto out_fail;
-	 * both parts of the port number.
+	dprintk("RPC: %5u RPCB_%s reply: %s\n", task->tk_pid,
-	 */
+			task->tk_msg.rpc_proc->p_name, (char *)p);
-	addr = (char *)p;
-	val = 0;
-	first = 1;
-	f = 1;
-	for (i = addr_len - 1; i > 0; i--) {
-		c = addr[i];
-		if (c >= '0' && c <= '9') {
-			val += (c - '0') * f;
-			f *= 10;
-		} else if (c == '.') {
-			if (first) {
-				*portp = val;
-				val = first = 0;
-				f = 1;
-			} else {
-				*portp |= (val << 8);
-				break;
-			}
-		}
-	}
 
-	/*
+	if (rpc_uaddr2sockaddr((char *)p, len, sap, sizeof(address)) == 0)
-	 * Simple sanity check.  If we never saw a dot in the reply,
+		goto out_fail;
-	 * then this was probably just garbage.
+	rpcb->r_port = rpc_get_port(sap);
-	 */
-	if (first)
-		goto out_err;
 
-	dprintk("RPC:       rpcb_decode_getaddr port=%u\n", *portp);
 	return 0;
 
-out_err:
+out_fail:
-	dprintk("RPC:       rpcbind server returned malformed reply\n");
+	dprintk("RPC: %5u malformed RPCB_%s reply\n",
+			task->tk_pid, task->tk_msg.rpc_proc->p_name);
 	return -EIO;
 }
 
-#define RPCB_program_sz		(1u)
-#define RPCB_version_sz		(1u)
-#define RPCB_protocol_sz	(1u)
-#define RPCB_port_sz		(1u)
-#define RPCB_boolean_sz		(1u)
-
-#define RPCB_netid_sz		(1+XDR_QUADLEN(RPCBIND_MAXNETIDLEN))
-#define RPCB_addr_sz		(1+XDR_QUADLEN(RPCBIND_MAXUADDRLEN))
-#define RPCB_ownerstring_sz	(1+XDR_QUADLEN(RPCB_MAXOWNERLEN))
-
-#define RPCB_mappingargs_sz	RPCB_program_sz+RPCB_version_sz+	\
-				RPCB_protocol_sz+RPCB_port_sz
-#define RPCB_getaddrargs_sz	RPCB_program_sz+RPCB_version_sz+	\
-				RPCB_netid_sz+RPCB_addr_sz+		\
-				RPCB_ownerstring_sz
-
-#define RPCB_setres_sz		RPCB_boolean_sz
-#define RPCB_getportres_sz	RPCB_port_sz
-
-/*
- * Note that RFC 1833 does not put any size restrictions on the
- * address string returned by the remote rpcbind database.
- */
-#define RPCB_getaddrres_sz	RPCB_addr_sz
-
-#define PROC(proc, argtype, restype)					\
-	[RPCBPROC_##proc] = {						\
-		.p_proc		= RPCBPROC_##proc,			\
-		.p_encode	= (kxdrproc_t) rpcb_encode_##argtype,	\
-		.p_decode	= (kxdrproc_t) rpcb_decode_##restype,	\
-		.p_arglen	= RPCB_##argtype##args_sz,		\
-		.p_replen	= RPCB_##restype##res_sz,		\
-		.p_statidx	= RPCBPROC_##proc,			\
-		.p_timer	= 0,					\
-		.p_name		= #proc,				\
-	}
-
 /*
  * Not all rpcbind procedures described in RFC 1833 are implemented
  * since the Linux kernel RPC code requires only these.
  */
+
 static struct rpc_procinfo rpcb_procedures2[] = {
-	PROC(SET,		mapping,	set),
+	[RPCBPROC_SET] = {
-	PROC(UNSET,		mapping,	set),
+		.p_proc		= RPCBPROC_SET,
-	PROC(GETPORT,		mapping,	getport),
+		.p_encode	= (kxdrproc_t)rpcb_enc_mapping,
+		.p_decode	= (kxdrproc_t)rpcb_dec_set,
+		.p_arglen	= RPCB_mappingargs_sz,
+		.p_replen	= RPCB_setres_sz,
+		.p_statidx	= RPCBPROC_SET,
+		.p_timer	= 0,
+		.p_name		= "SET",
+	},
+	[RPCBPROC_UNSET] = {
+		.p_proc		= RPCBPROC_UNSET,
+		.p_encode	= (kxdrproc_t)rpcb_enc_mapping,
+		.p_decode	= (kxdrproc_t)rpcb_dec_set,
+		.p_arglen	= RPCB_mappingargs_sz,
+		.p_replen	= RPCB_setres_sz,
+		.p_statidx	= RPCBPROC_UNSET,
+		.p_timer	= 0,
+		.p_name		= "UNSET",
+	},
+	[RPCBPROC_GETPORT] = {
+		.p_proc		= RPCBPROC_GETPORT,
+		.p_encode	= (kxdrproc_t)rpcb_enc_mapping,
+		.p_decode	= (kxdrproc_t)rpcb_dec_getport,
+		.p_arglen	= RPCB_mappingargs_sz,
+		.p_replen	= RPCB_getportres_sz,
+		.p_statidx	= RPCBPROC_GETPORT,
+		.p_timer	= 0,
+		.p_name		= "GETPORT",
+	},
 };
 
 static struct rpc_procinfo rpcb_procedures3[] = {
-	PROC(SET,		getaddr,	set),
+	[RPCBPROC_SET] = {
-	PROC(UNSET,		getaddr,	set),
+		.p_proc		= RPCBPROC_SET,
-	PROC(GETADDR,		getaddr,	getaddr),
+		.p_encode	= (kxdrproc_t)rpcb_enc_getaddr,
+		.p_decode	= (kxdrproc_t)rpcb_dec_set,
+		.p_arglen	= RPCB_getaddrargs_sz,
+		.p_replen	= RPCB_setres_sz,
+		.p_statidx	= RPCBPROC_SET,
+		.p_timer	= 0,
+		.p_name		= "SET",
+	},
+	[RPCBPROC_UNSET] = {
+		.p_proc		= RPCBPROC_UNSET,
+		.p_encode	= (kxdrproc_t)rpcb_enc_getaddr,
+		.p_decode	= (kxdrproc_t)rpcb_dec_set,
+		.p_arglen	= RPCB_getaddrargs_sz,
+		.p_replen	= RPCB_setres_sz,
+		.p_statidx	= RPCBPROC_UNSET,
+		.p_timer	= 0,
+		.p_name		= "UNSET",
+	},
+	[RPCBPROC_GETADDR] = {
+		.p_proc		= RPCBPROC_GETADDR,
+		.p_encode	= (kxdrproc_t)rpcb_enc_getaddr,
+		.p_decode	= (kxdrproc_t)rpcb_dec_getaddr,
+		.p_arglen	= RPCB_getaddrargs_sz,
+		.p_replen	= RPCB_getaddrres_sz,
+		.p_statidx	= RPCBPROC_GETADDR,
+		.p_timer	= 0,
+		.p_name		= "GETADDR",
+	},
 };
 
 static struct rpc_procinfo rpcb_procedures4[] = {
-	PROC(SET,		getaddr,	set),
+	[RPCBPROC_SET] = {
-	PROC(UNSET,		getaddr,	set),
+		.p_proc		= RPCBPROC_SET,
-	PROC(GETADDR,		getaddr,	getaddr),
+		.p_encode	= (kxdrproc_t)rpcb_enc_getaddr,
-	PROC(GETVERSADDR,	getaddr,	getaddr),
+		.p_decode	= (kxdrproc_t)rpcb_dec_set,
+		.p_arglen	= RPCB_getaddrargs_sz,
+		.p_replen	= RPCB_setres_sz,
+		.p_statidx	= RPCBPROC_SET,
+		.p_timer	= 0,
+		.p_name		= "SET",
+	},
+	[RPCBPROC_UNSET] = {
+		.p_proc		= RPCBPROC_UNSET,
+		.p_encode	= (kxdrproc_t)rpcb_enc_getaddr,
+		.p_decode	= (kxdrproc_t)rpcb_dec_set,
+		.p_arglen	= RPCB_getaddrargs_sz,
+		.p_replen	= RPCB_setres_sz,
+		.p_statidx	= RPCBPROC_UNSET,
+		.p_timer	= 0,
+		.p_name		= "UNSET",
+	},
+	[RPCBPROC_GETADDR] = {
+		.p_proc		= RPCBPROC_GETADDR,
+		.p_encode	= (kxdrproc_t)rpcb_enc_getaddr,
+		.p_decode	= (kxdrproc_t)rpcb_dec_getaddr,
+		.p_arglen	= RPCB_getaddrargs_sz,
+		.p_replen	= RPCB_getaddrres_sz,
+		.p_statidx	= RPCBPROC_GETADDR,
+		.p_timer	= 0,
+		.p_name		= "GETADDR",
+	},
 };
 
 static struct rpcb_info rpcb_next_version[] = {

net/sunrpc/sunrpc_syms.c

@@ -69,5 +69,5 @@ cleanup_sunrpc(void)
 	rcu_barrier(); /* Wait for completion of call_rcu()'s */
 }
 MODULE_LICENSE("GPL");
-module_init(init_sunrpc);
+fs_initcall(init_sunrpc); /* Ensure we're initialised before nfs */
 module_exit(cleanup_sunrpc);

net/sunrpc/svcauth_unix.c

@@ -171,6 +171,11 @@ static void ip_map_request(struct cache_detail *cd,
 	(*bpp)[-1] = '\n';
 }
 
+static int ip_map_upcall(struct cache_detail *cd, struct cache_head *h)
+{
+	return sunrpc_cache_pipe_upcall(cd, h, ip_map_request);
+}
+
 static struct ip_map *ip_map_lookup(char *class, struct in6_addr *addr);
 static int ip_map_update(struct ip_map *ipm, struct unix_domain *udom, time_t expiry);
 
@@ -289,7 +294,7 @@ struct cache_detail ip_map_cache = {
 	.hash_table	= ip_table,
 	.name		= "auth.unix.ip",
 	.cache_put	= ip_map_put,
-	.cache_request	= ip_map_request,
+	.cache_upcall	= ip_map_upcall,
 	.cache_parse	= ip_map_parse,
 	.cache_show	= ip_map_show,
 	.match		= ip_map_match,
@@ -523,6 +528,11 @@ static void unix_gid_request(struct cache_detail *cd,
 	(*bpp)[-1] = '\n';
 }
 
+static int unix_gid_upcall(struct cache_detail *cd, struct cache_head *h)
+{
+	return sunrpc_cache_pipe_upcall(cd, h, unix_gid_request);
+}
+
 static struct unix_gid *unix_gid_lookup(uid_t uid);
 extern struct cache_detail unix_gid_cache;
 
@@ -622,7 +632,7 @@ struct cache_detail unix_gid_cache = {
 	.hash_table	= gid_table,
 	.name		= "auth.unix.gid",
 	.cache_put	= unix_gid_put,
-	.cache_request	= unix_gid_request,
+	.cache_upcall	= unix_gid_upcall,
 	.cache_parse	= unix_gid_parse,
 	.cache_show	= unix_gid_show,
 	.match		= unix_gid_match,

net/sunrpc/timer.c

@@ -25,8 +25,13 @@
 #define RPC_RTO_INIT (HZ/5)
 #define RPC_RTO_MIN (HZ/10)
 
-void
+/**
-rpc_init_rtt(struct rpc_rtt *rt, unsigned long timeo)
+ * rpc_init_rtt - Initialize an RPC RTT estimator context
+ * @rt: context to initialize
+ * @timeo: initial timeout value, in jiffies
+ *
+ */
+void rpc_init_rtt(struct rpc_rtt *rt, unsigned long timeo)
 {
 	unsigned long init = 0;
 	unsigned i;
@@ -43,12 +48,16 @@ rpc_init_rtt(struct rpc_rtt *rt, unsigned long timeo)
 }
 EXPORT_SYMBOL_GPL(rpc_init_rtt);
 
-/*
+/**
+ * rpc_update_rtt - Update an RPC RTT estimator context
+ * @rt: context to update
+ * @timer: timer array index (request type)
+ * @m: recent actual RTT, in jiffies
+ *
  * NB: When computing the smoothed RTT and standard deviation,
  *     be careful not to produce negative intermediate results.
  */
-void
+void rpc_update_rtt(struct rpc_rtt *rt, unsigned timer, long m)
-rpc_update_rtt(struct rpc_rtt *rt, unsigned timer, long m)
 {
 	long *srtt, *sdrtt;
 
@@ -79,21 +88,25 @@ rpc_update_rtt(struct rpc_rtt *rt, unsigned timer, long m)
 }
 EXPORT_SYMBOL_GPL(rpc_update_rtt);
 
-/*
+/**
- * Estimate rto for an nfs rpc sent via. an unreliable datagram.
+ * rpc_calc_rto - Provide an estimated timeout value
- * Use the mean and mean deviation of rtt for the appropriate type of rpc
+ * @rt: context to use for calculation
- * for the frequent rpcs and a default for the others.
+ * @timer: timer array index (request type)
- * The justification for doing "other" this way is that these rpcs
+ *
- * happen so infrequently that timer est. would probably be stale.
+ * Estimate RTO for an NFS RPC sent via an unreliable datagram.  Use
- * Also, since many of these rpcs are
+ * the mean and mean deviation of RTT for the appropriate type of RPC
- * non-idempotent, a conservative timeout is desired.
+ * for frequently issued RPCs, and a fixed default for the others.
+ *
+ * The justification for doing "other" this way is that these RPCs
+ * happen so infrequently that timer estimation would probably be
+ * stale.  Also, since many of these RPCs are non-idempotent, a
+ * conservative timeout is desired.
+ *
  * getattr, lookup,
  * read, write, commit     - A+4D
  * other                   - timeo
  */
-
+unsigned long rpc_calc_rto(struct rpc_rtt *rt, unsigned timer)
-unsigned long
-rpc_calc_rto(struct rpc_rtt *rt, unsigned timer)
 {
 	unsigned long res;
 

net/sunrpc/xdr.c

@@ -24,7 +24,7 @@ xdr_encode_netobj(__be32 *p, const struct xdr_netobj *obj)
 	unsigned int	quadlen = XDR_QUADLEN(obj->len);
 
 	p[quadlen] = 0;		/* zero trailing bytes */
-	*p++ = htonl(obj->len);
+	*p++ = cpu_to_be32(obj->len);
 	memcpy(p, obj->data, obj->len);
 	return p + XDR_QUADLEN(obj->len);
 }
@@ -35,7 +35,7 @@ xdr_decode_netobj(__be32 *p, struct xdr_netobj *obj)
 {
 	unsigned int	len;
 
-	if ((len = ntohl(*p++)) > XDR_MAX_NETOBJ)
+	if ((len = be32_to_cpu(*p++)) > XDR_MAX_NETOBJ)
 		return NULL;
 	obj->len  = len;
 	obj->data = (u8 *) p;
@@ -83,7 +83,7 @@ EXPORT_SYMBOL_GPL(xdr_encode_opaque_fixed);
  */
 __be32 *xdr_encode_opaque(__be32 *p, const void *ptr, unsigned int nbytes)
 {
-	*p++ = htonl(nbytes);
+	*p++ = cpu_to_be32(nbytes);
 	return xdr_encode_opaque_fixed(p, ptr, nbytes);
 }
 EXPORT_SYMBOL_GPL(xdr_encode_opaque);
@@ -101,7 +101,7 @@ xdr_decode_string_inplace(__be32 *p, char **sp,
 {
 	u32 len;
 
-	len = ntohl(*p++);
+	len = be32_to_cpu(*p++);
 	if (len > maxlen)
 		return NULL;
 	*lenp = len;
@@ -771,7 +771,7 @@ xdr_decode_word(struct xdr_buf *buf, unsigned int base, u32 *obj)
 	status = read_bytes_from_xdr_buf(buf, base, &raw, sizeof(*obj));
 	if (status)
 		return status;
-	*obj = ntohl(raw);
+	*obj = be32_to_cpu(raw);
 	return 0;
 }
 EXPORT_SYMBOL_GPL(xdr_decode_word);
@@ -779,7 +779,7 @@ EXPORT_SYMBOL_GPL(xdr_decode_word);
 int
 xdr_encode_word(struct xdr_buf *buf, unsigned int base, u32 obj)
 {
-	__be32	raw = htonl(obj);
+	__be32	raw = cpu_to_be32(obj);
 
 	return write_bytes_to_xdr_buf(buf, base, &raw, sizeof(obj));
 }

net/sunrpc/xprtrdma/transport.c

@@ -168,47 +168,25 @@ static struct rpc_xprt_ops xprt_rdma_procs;	/* forward reference */
 static void
 xprt_rdma_format_addresses(struct rpc_xprt *xprt)
 {
-	struct sockaddr_in *addr = (struct sockaddr_in *)
+	struct sockaddr *sap = (struct sockaddr *)
 					&rpcx_to_rdmad(xprt).addr;
-	char *buf;
+	struct sockaddr_in *sin = (struct sockaddr_in *)sap;
+	char buf[64];
 
-	buf = kzalloc(20, GFP_KERNEL);
+	(void)rpc_ntop(sap, buf, sizeof(buf));
-	if (buf)
+	xprt->address_strings[RPC_DISPLAY_ADDR] = kstrdup(buf, GFP_KERNEL);
-		snprintf(buf, 20, "%pI4", &addr->sin_addr.s_addr);
-	xprt->address_strings[RPC_DISPLAY_ADDR] = buf;
 
-	buf = kzalloc(8, GFP_KERNEL);
+	(void)snprintf(buf, sizeof(buf), "%u", rpc_get_port(sap));
-	if (buf)
+	xprt->address_strings[RPC_DISPLAY_PORT] = kstrdup(buf, GFP_KERNEL);
-		snprintf(buf, 8, "%u", ntohs(addr->sin_port));
-	xprt->address_strings[RPC_DISPLAY_PORT] = buf;
 
 	xprt->address_strings[RPC_DISPLAY_PROTO] = "rdma";
 
-	buf = kzalloc(48, GFP_KERNEL);
+	(void)snprintf(buf, sizeof(buf), "%02x%02x%02x%02x",
-	if (buf)
+				NIPQUAD(sin->sin_addr.s_addr));
-		snprintf(buf, 48, "addr=%pI4 port=%u proto=%s",
+	xprt->address_strings[RPC_DISPLAY_HEX_ADDR] = kstrdup(buf, GFP_KERNEL);
-			&addr->sin_addr.s_addr,
-			ntohs(addr->sin_port), "rdma");
-	xprt->address_strings[RPC_DISPLAY_ALL] = buf;
 
-	buf = kzalloc(10, GFP_KERNEL);
+	(void)snprintf(buf, sizeof(buf), "%4hx", rpc_get_port(sap));
-	if (buf)
+	xprt->address_strings[RPC_DISPLAY_HEX_PORT] = kstrdup(buf, GFP_KERNEL);
-		snprintf(buf, 10, "%02x%02x%02x%02x",
-			NIPQUAD(addr->sin_addr.s_addr));
-	xprt->address_strings[RPC_DISPLAY_HEX_ADDR] = buf;
-
-	buf = kzalloc(8, GFP_KERNEL);
-	if (buf)
-		snprintf(buf, 8, "%4hx", ntohs(addr->sin_port));
-	xprt->address_strings[RPC_DISPLAY_HEX_PORT] = buf;
-
-	buf = kzalloc(30, GFP_KERNEL);
-	if (buf)
-		snprintf(buf, 30, "%pI4.%u.%u",
-			&addr->sin_addr.s_addr,
-			ntohs(addr->sin_port) >> 8,
-			ntohs(addr->sin_port) & 0xff);
-	xprt->address_strings[RPC_DISPLAY_UNIVERSAL_ADDR] = buf;
 
 	/* netid */
 	xprt->address_strings[RPC_DISPLAY_NETID] = "rdma";

net/sunrpc/xprtsock.c

@@ -248,8 +248,8 @@ struct sock_xprt {
 	 * Connection of transports
 	 */
 	struct delayed_work	connect_worker;
-	struct sockaddr_storage	addr;
+	struct sockaddr_storage	srcaddr;
-	unsigned short		port;
+	unsigned short		srcport;
 
 	/*
 	 * UDP socket buffer size parameters
@@ -296,117 +296,60 @@ static inline struct sockaddr_in6 *xs_addr_in6(struct rpc_xprt *xprt)
 	return (struct sockaddr_in6 *) &xprt->addr;
 }
 
-static void xs_format_ipv4_peer_addresses(struct rpc_xprt *xprt,
+static void xs_format_common_peer_addresses(struct rpc_xprt *xprt)
-					  const char *protocol,
-					  const char *netid)
 {
-	struct sockaddr_in *addr = xs_addr_in(xprt);
+	struct sockaddr *sap = xs_addr(xprt);
-	char *buf;
+	struct sockaddr_in6 *sin6;
+	struct sockaddr_in *sin;
+	char buf[128];
 
-	buf = kzalloc(20, GFP_KERNEL);
+	(void)rpc_ntop(sap, buf, sizeof(buf));
-	if (buf) {
+	xprt->address_strings[RPC_DISPLAY_ADDR] = kstrdup(buf, GFP_KERNEL);
-		snprintf(buf, 20, "%pI4", &addr->sin_addr.s_addr);
+
+	switch (sap->sa_family) {
+	case AF_INET:
+		sin = xs_addr_in(xprt);
+		(void)snprintf(buf, sizeof(buf), "%02x%02x%02x%02x",
+					NIPQUAD(sin->sin_addr.s_addr));
+		break;
+	case AF_INET6:
+		sin6 = xs_addr_in6(xprt);
+		(void)snprintf(buf, sizeof(buf), "%pi6", &sin6->sin6_addr);
+		break;
+	default:
+		BUG();
 	}
-	xprt->address_strings[RPC_DISPLAY_ADDR] = buf;
+	xprt->address_strings[RPC_DISPLAY_HEX_ADDR] = kstrdup(buf, GFP_KERNEL);
-
-	buf = kzalloc(8, GFP_KERNEL);
-	if (buf) {
-		snprintf(buf, 8, "%u",
-				ntohs(addr->sin_port));
-	}
-	xprt->address_strings[RPC_DISPLAY_PORT] = buf;
-
-	xprt->address_strings[RPC_DISPLAY_PROTO] = protocol;
-
-	buf = kzalloc(48, GFP_KERNEL);
-	if (buf) {
-		snprintf(buf, 48, "addr=%pI4 port=%u proto=%s",
-			&addr->sin_addr.s_addr,
-			ntohs(addr->sin_port),
-			protocol);
-	}
-	xprt->address_strings[RPC_DISPLAY_ALL] = buf;
-
-	buf = kzalloc(10, GFP_KERNEL);
-	if (buf) {
-		snprintf(buf, 10, "%02x%02x%02x%02x",
-				NIPQUAD(addr->sin_addr.s_addr));
-	}
-	xprt->address_strings[RPC_DISPLAY_HEX_ADDR] = buf;
-
-	buf = kzalloc(8, GFP_KERNEL);
-	if (buf) {
-		snprintf(buf, 8, "%4hx",
-				ntohs(addr->sin_port));
-	}
-	xprt->address_strings[RPC_DISPLAY_HEX_PORT] = buf;
-
-	buf = kzalloc(30, GFP_KERNEL);
-	if (buf) {
-		snprintf(buf, 30, "%pI4.%u.%u",
-				&addr->sin_addr.s_addr,
-				ntohs(addr->sin_port) >> 8,
-				ntohs(addr->sin_port) & 0xff);
-	}
-	xprt->address_strings[RPC_DISPLAY_UNIVERSAL_ADDR] = buf;
-
-	xprt->address_strings[RPC_DISPLAY_NETID] = netid;
 }
 
-static void xs_format_ipv6_peer_addresses(struct rpc_xprt *xprt,
+static void xs_format_common_peer_ports(struct rpc_xprt *xprt)
+{
+	struct sockaddr *sap = xs_addr(xprt);
+	char buf[128];
+
+	(void)snprintf(buf, sizeof(buf), "%u", rpc_get_port(sap));
+	xprt->address_strings[RPC_DISPLAY_PORT] = kstrdup(buf, GFP_KERNEL);
+
+	(void)snprintf(buf, sizeof(buf), "%4hx", rpc_get_port(sap));
+	xprt->address_strings[RPC_DISPLAY_HEX_PORT] = kstrdup(buf, GFP_KERNEL);
+}
+
+static void xs_format_peer_addresses(struct rpc_xprt *xprt,
 				     const char *protocol,
 				     const char *netid)
 {
-	struct sockaddr_in6 *addr = xs_addr_in6(xprt);
-	char *buf;
-
-	buf = kzalloc(40, GFP_KERNEL);
-	if (buf) {
-		snprintf(buf, 40, "%pI6",&addr->sin6_addr);
-	}
-	xprt->address_strings[RPC_DISPLAY_ADDR] = buf;
-
-	buf = kzalloc(8, GFP_KERNEL);
-	if (buf) {
-		snprintf(buf, 8, "%u",
-				ntohs(addr->sin6_port));
-	}
-	xprt->address_strings[RPC_DISPLAY_PORT] = buf;
-
 	xprt->address_strings[RPC_DISPLAY_PROTO] = protocol;
-
-	buf = kzalloc(64, GFP_KERNEL);
-	if (buf) {
-		snprintf(buf, 64, "addr=%pI6 port=%u proto=%s",
-				&addr->sin6_addr,
-				ntohs(addr->sin6_port),
-				protocol);
-	}
-	xprt->address_strings[RPC_DISPLAY_ALL] = buf;
-
-	buf = kzalloc(36, GFP_KERNEL);
-	if (buf)
-		snprintf(buf, 36, "%pi6", &addr->sin6_addr);
-
-	xprt->address_strings[RPC_DISPLAY_HEX_ADDR] = buf;
-
-	buf = kzalloc(8, GFP_KERNEL);
-	if (buf) {
-		snprintf(buf, 8, "%4hx",
-				ntohs(addr->sin6_port));
-	}
-	xprt->address_strings[RPC_DISPLAY_HEX_PORT] = buf;
-
-	buf = kzalloc(50, GFP_KERNEL);
-	if (buf) {
-		snprintf(buf, 50, "%pI6.%u.%u",
-			 &addr->sin6_addr,
-			 ntohs(addr->sin6_port) >> 8,
-			 ntohs(addr->sin6_port) & 0xff);
-	}
-	xprt->address_strings[RPC_DISPLAY_UNIVERSAL_ADDR] = buf;
-
 	xprt->address_strings[RPC_DISPLAY_NETID] = netid;
+	xs_format_common_peer_addresses(xprt);
+	xs_format_common_peer_ports(xprt);
+}
+
+static void xs_update_peer_port(struct rpc_xprt *xprt)
+{
+	kfree(xprt->address_strings[RPC_DISPLAY_HEX_PORT]);
+	kfree(xprt->address_strings[RPC_DISPLAY_PORT]);
+
+	xs_format_common_peer_ports(xprt);
 }
 
 static void xs_free_peer_addresses(struct rpc_xprt *xprt)
@@ -1587,25 +1530,15 @@ static unsigned short xs_get_random_port(void)
  */
 static void xs_set_port(struct rpc_xprt *xprt, unsigned short port)
 {
-	struct sockaddr *addr = xs_addr(xprt);
-
 	dprintk("RPC:       setting port for xprt %p to %u\n", xprt, port);
 
-	switch (addr->sa_family) {
+	rpc_set_port(xs_addr(xprt), port);
-	case AF_INET:
+	xs_update_peer_port(xprt);
-		((struct sockaddr_in *)addr)->sin_port = htons(port);
-		break;
-	case AF_INET6:
-		((struct sockaddr_in6 *)addr)->sin6_port = htons(port);
-		break;
-	default:
-		BUG();
-	}
 }
 
 static unsigned short xs_get_srcport(struct sock_xprt *transport, struct socket *sock)
 {
-	unsigned short port = transport->port;
+	unsigned short port = transport->srcport;
 
 	if (port == 0 && transport->xprt.resvport)
 		port = xs_get_random_port();
@@ -1614,8 +1547,8 @@ static unsigned short xs_get_srcport(struct sock_xprt *transport, struct socket
 
 static unsigned short xs_next_srcport(struct sock_xprt *transport, struct socket *sock, unsigned short port)
 {
-	if (transport->port != 0)
+	if (transport->srcport != 0)
-		transport->port = 0;
+		transport->srcport = 0;
 	if (!transport->xprt.resvport)
 		return 0;
 	if (port <= xprt_min_resvport || port > xprt_max_resvport)
@@ -1633,7 +1566,7 @@ static int xs_bind4(struct sock_xprt *transport, struct socket *sock)
 	unsigned short port = xs_get_srcport(transport, sock);
 	unsigned short last;
 
-	sa = (struct sockaddr_in *)&transport->addr;
+	sa = (struct sockaddr_in *)&transport->srcaddr;
 	myaddr.sin_addr = sa->sin_addr;
 	do {
 		myaddr.sin_port = htons(port);
@@ -1642,7 +1575,7 @@ static int xs_bind4(struct sock_xprt *transport, struct socket *sock)
 		if (port == 0)
 			break;
 		if (err == 0) {
-			transport->port = port;
+			transport->srcport = port;
 			break;
 		}
 		last = port;
@@ -1666,7 +1599,7 @@ static int xs_bind6(struct sock_xprt *transport, struct socket *sock)
 	unsigned short port = xs_get_srcport(transport, sock);
 	unsigned short last;
 
-	sa = (struct sockaddr_in6 *)&transport->addr;
+	sa = (struct sockaddr_in6 *)&transport->srcaddr;
 	myaddr.sin6_addr = sa->sin6_addr;
 	do {
 		myaddr.sin6_port = htons(port);
@@ -1675,7 +1608,7 @@ static int xs_bind6(struct sock_xprt *transport, struct socket *sock)
 		if (port == 0)
 			break;
 		if (err == 0) {
-			transport->port = port;
+			transport->srcport = port;
 			break;
 		}
 		last = port;
@@ -1780,8 +1713,11 @@ static void xs_udp_connect_worker4(struct work_struct *work)
 		goto out;
 	}
 
-	dprintk("RPC:       worker connecting xprt %p to address: %s\n",
+	dprintk("RPC:       worker connecting xprt %p via %s to "
-			xprt, xprt->address_strings[RPC_DISPLAY_ALL]);
+				"%s (port %s)\n", xprt,
+			xprt->address_strings[RPC_DISPLAY_PROTO],
+			xprt->address_strings[RPC_DISPLAY_ADDR],
+			xprt->address_strings[RPC_DISPLAY_PORT]);
 
 	xs_udp_finish_connecting(xprt, sock);
 	status = 0;
@@ -1822,8 +1758,11 @@ static void xs_udp_connect_worker6(struct work_struct *work)
 		goto out;
 	}
 
-	dprintk("RPC:       worker connecting xprt %p to address: %s\n",
+	dprintk("RPC:       worker connecting xprt %p via %s to "
-			xprt, xprt->address_strings[RPC_DISPLAY_ALL]);
+				"%s (port %s)\n", xprt,
+			xprt->address_strings[RPC_DISPLAY_PROTO],
+			xprt->address_strings[RPC_DISPLAY_ADDR],
+			xprt->address_strings[RPC_DISPLAY_PORT]);
 
 	xs_udp_finish_connecting(xprt, sock);
 	status = 0;
@@ -1948,8 +1887,11 @@ static void xs_tcp_setup_socket(struct rpc_xprt *xprt,
 			goto out_eagain;
 	}
 
-	dprintk("RPC:       worker connecting xprt %p to address: %s\n",
+	dprintk("RPC:       worker connecting xprt %p via %s to "
-			xprt, xprt->address_strings[RPC_DISPLAY_ALL]);
+				"%s (port %s)\n", xprt,
+			xprt->address_strings[RPC_DISPLAY_PROTO],
+			xprt->address_strings[RPC_DISPLAY_ADDR],
+			xprt->address_strings[RPC_DISPLAY_PORT]);
 
 	status = xs_tcp_finish_connecting(xprt, sock);
 	dprintk("RPC:       %p connect status %d connected %d sock state %d\n",
@@ -2120,7 +2062,7 @@ static void xs_udp_print_stats(struct rpc_xprt *xprt, struct seq_file *seq)
 	struct sock_xprt *transport = container_of(xprt, struct sock_xprt, xprt);
 
 	seq_printf(seq, "\txprt:\tudp %u %lu %lu %lu %lu %Lu %Lu\n",
-			transport->port,
+			transport->srcport,
 			xprt->stat.bind_count,
 			xprt->stat.sends,
 			xprt->stat.recvs,
@@ -2144,7 +2086,7 @@ static void xs_tcp_print_stats(struct rpc_xprt *xprt, struct seq_file *seq)
 		idle_time = (long)(jiffies - xprt->last_used) / HZ;
 
 	seq_printf(seq, "\txprt:\ttcp %u %lu %lu %lu %ld %lu %lu %lu %Lu %Lu\n",
-			transport->port,
+			transport->srcport,
 			xprt->stat.bind_count,
 			xprt->stat.connect_count,
 			xprt->stat.connect_time,
@@ -2223,7 +2165,7 @@ static struct rpc_xprt *xs_setup_xprt(struct xprt_create *args,
 	memcpy(&xprt->addr, args->dstaddr, args->addrlen);
 	xprt->addrlen = args->addrlen;
 	if (args->srcaddr)
-		memcpy(&new->addr, args->srcaddr, args->addrlen);
+		memcpy(&new->srcaddr, args->srcaddr, args->addrlen);
 
 	return xprt;
 }
@@ -2272,7 +2214,7 @@ static struct rpc_xprt *xs_setup_udp(struct xprt_create *args)
 
 		INIT_DELAYED_WORK(&transport->connect_worker,
 					xs_udp_connect_worker4);
-		xs_format_ipv4_peer_addresses(xprt, "udp", RPCBIND_NETID_UDP);
+		xs_format_peer_addresses(xprt, "udp", RPCBIND_NETID_UDP);
 		break;
 	case AF_INET6:
 		if (((struct sockaddr_in6 *)addr)->sin6_port != htons(0))
@@ -2280,15 +2222,22 @@ static struct rpc_xprt *xs_setup_udp(struct xprt_create *args)
 
 		INIT_DELAYED_WORK(&transport->connect_worker,
 					xs_udp_connect_worker6);
-		xs_format_ipv6_peer_addresses(xprt, "udp", RPCBIND_NETID_UDP6);
+		xs_format_peer_addresses(xprt, "udp", RPCBIND_NETID_UDP6);
 		break;
 	default:
 		kfree(xprt);
 		return ERR_PTR(-EAFNOSUPPORT);
 	}
 
-	dprintk("RPC:       set up transport to address %s\n",
+	if (xprt_bound(xprt))
-			xprt->address_strings[RPC_DISPLAY_ALL]);
+		dprintk("RPC:       set up xprt to %s (port %s) via %s\n",
+				xprt->address_strings[RPC_DISPLAY_ADDR],
+				xprt->address_strings[RPC_DISPLAY_PORT],
+				xprt->address_strings[RPC_DISPLAY_PROTO]);
+	else
+		dprintk("RPC:       set up xprt to %s (autobind) via %s\n",
+				xprt->address_strings[RPC_DISPLAY_ADDR],
+				xprt->address_strings[RPC_DISPLAY_PROTO]);
 
 	if (try_module_get(THIS_MODULE))
 		return xprt;
@@ -2337,23 +2286,33 @@ static struct rpc_xprt *xs_setup_tcp(struct xprt_create *args)
 		if (((struct sockaddr_in *)addr)->sin_port != htons(0))
 			xprt_set_bound(xprt);
 
-		INIT_DELAYED_WORK(&transport->connect_worker, xs_tcp_connect_worker4);
+		INIT_DELAYED_WORK(&transport->connect_worker,
-		xs_format_ipv4_peer_addresses(xprt, "tcp", RPCBIND_NETID_TCP);
+					xs_tcp_connect_worker4);
+		xs_format_peer_addresses(xprt, "tcp", RPCBIND_NETID_TCP);
 		break;
 	case AF_INET6:
 		if (((struct sockaddr_in6 *)addr)->sin6_port != htons(0))
 			xprt_set_bound(xprt);
 
-		INIT_DELAYED_WORK(&transport->connect_worker, xs_tcp_connect_worker6);
+		INIT_DELAYED_WORK(&transport->connect_worker,
-		xs_format_ipv6_peer_addresses(xprt, "tcp", RPCBIND_NETID_TCP6);
+					xs_tcp_connect_worker6);
+		xs_format_peer_addresses(xprt, "tcp", RPCBIND_NETID_TCP6);
 		break;
 	default:
 		kfree(xprt);
 		return ERR_PTR(-EAFNOSUPPORT);
 	}
 
-	dprintk("RPC:       set up transport to address %s\n",
+	if (xprt_bound(xprt))
-			xprt->address_strings[RPC_DISPLAY_ALL]);
+		dprintk("RPC:       set up xprt to %s (port %s) via %s\n",
+				xprt->address_strings[RPC_DISPLAY_ADDR],
+				xprt->address_strings[RPC_DISPLAY_PORT],
+				xprt->address_strings[RPC_DISPLAY_PROTO]);
+	else
+		dprintk("RPC:       set up xprt to %s (autobind) via %s\n",
+				xprt->address_strings[RPC_DISPLAY_ADDR],
+				xprt->address_strings[RPC_DISPLAY_PROTO]);
+
 
 	if (try_module_get(THIS_MODULE))
 		return xprt;
@@ -2412,3 +2371,55 @@ void cleanup_socket_xprt(void)
 	xprt_unregister_transport(&xs_udp_transport);
 	xprt_unregister_transport(&xs_tcp_transport);
 }
+
+static int param_set_uint_minmax(const char *val, struct kernel_param *kp,
+		unsigned int min, unsigned int max)
+{
+	unsigned long num;
+	int ret;
+
+	if (!val)
+		return -EINVAL;
+	ret = strict_strtoul(val, 0, &num);
+	if (ret == -EINVAL || num < min || num > max)
+		return -EINVAL;
+	*((unsigned int *)kp->arg) = num;
+	return 0;
+}
+
+static int param_set_portnr(const char *val, struct kernel_param *kp)
+{
+	return param_set_uint_minmax(val, kp,
+			RPC_MIN_RESVPORT,
+			RPC_MAX_RESVPORT);
+}
+
+static int param_get_portnr(char *buffer, struct kernel_param *kp)
+{
+	return param_get_uint(buffer, kp);
+}
+#define param_check_portnr(name, p) \
+	__param_check(name, p, unsigned int);
+
+module_param_named(min_resvport, xprt_min_resvport, portnr, 0644);
+module_param_named(max_resvport, xprt_max_resvport, portnr, 0644);
+
+static int param_set_slot_table_size(const char *val, struct kernel_param *kp)
+{
+	return param_set_uint_minmax(val, kp,
+			RPC_MIN_SLOT_TABLE,
+			RPC_MAX_SLOT_TABLE);
+}
+
+static int param_get_slot_table_size(char *buffer, struct kernel_param *kp)
+{
+	return param_get_uint(buffer, kp);
+}
+#define param_check_slot_table_size(name, p) \
+	__param_check(name, p, unsigned int);
+
+module_param_named(tcp_slot_table_entries, xprt_tcp_slot_table_entries,
+		   slot_table_size, 0644);
+module_param_named(udp_slot_table_entries, xprt_udp_slot_table_entries,
+		   slot_table_size, 0644);
+