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  NFS: out of date comment regarding O_EXCL above nfs3_proc_create()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

+
+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

+/*
+ * 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

+/*
+ * 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;
-static const int nfs_set_port_max = 65535;
+#define NFS_CALLBACK_MAXPORTNR (65535U)
 
-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;
-	int num = simple_strtol(val, &endp, 0);
-	if (endp == val || *endp || num < nfs_set_port_min || num > nfs_set_port_max)
+	unsigned long num;
+	int ret;
+
+	if (!val)
+		return -EINVAL;
+	ret = strict_strtoul(val, 0, &num);
+	if (ret == -EINVAL || num > NFS_CALLBACK_MAXPORTNR)
 		return -EINVAL;
-	*((int *)kp->arg) = num;
+	*((unsigned int *)kp->arg) = num;
 	return 0;
 }
 
-module_param_call(callback_tcpport, param_set_port, param_get_int,
-		 &nfs_callback_set_tcpport, 0644);
+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(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 @@ ssize_t nfs_file_direct_read(struct kiocb *iocb, const struct iovec *iov,
  * 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

+/*
+ * 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

+/*
+ * 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_upcall_ops, 0);
+	idmap->idmap_dentry = rpc_mkpipe(clp->cl_rpcclient->cl_path.dentry,
+			"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 @@ static int __init init_nfs_fs(void)
 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 @@ int nfs_mount(struct nfs_mount_request *info)
 	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->addr, &mountdata->addrlen);
-		if (mountdata->addr->sa_family == AF_UNSPEC)
+		mountdata->addrlen = nfs_parse_server_name(buf->data,
+				buf->len,
+				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 @@ nfs4_find_slot(struct nfs4_slot_table *tbl, struct rpc_task *task)
 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/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,