Merge git://git.linux-nfs.org/pub/linux/nfs-2.6

* git://git.linux-nfs.org/pub/linux/nfs-2.6: (28 commits)
  NFS: Fix a compile glitch on 64-bit systems
  NFS: Clean up nfs_create_request comments
  spkm3: initialize hash
  spkm3: remove bad kfree, unnecessary export
  spkm3: fix spkm3's use of hmac
  NFS4: invalidate cached acl on setacl
  NFS: Fix directory caching problem - with test case and patch.
  NFS: Set meaningful value for fattr->time_start in readdirplus results.
  NFS: Added support to turn off the NFSv3 READDIRPLUS RPC.
  SUNRPC: RPC client should retry with different versions of rpcbind
  SUNRPC: remove old portmapper
  NFS: switch NFSROOT to use new rpcbind client
  SUNRPC: switch the RPC server to use the new rpcbind registration API
  SUNRPC: switch socket-based RPC transports to use rpcbind
  SUNRPC: introduce rpcbind: replacement for in-kernel portmapper
  SUNRPC: Eliminate side effects from rpc_malloc
  SUNRPC: RPC buffer size estimates are too large
  NLM: Shrink the maximum request size of NLM4 requests
  NFS: Use pgoff_t in structures and functions that pass page cache offsets
  NFS: Clean up nfs_sync_mapping_wait()
  ...

19 files changed, 349 insertions, 405 deletions

diff --git a/fs/Kconfig b/fs/Kconfig
index e33c0892457..8ea7b04c661 100644
--- a/fs/Kconfig
+++ b/fs/Kconfig
@@ -1734,6 +1734,18 @@ config SUNRPC
 config SUNRPC_GSS
 	tristate
 
+config SUNRPC_BIND34
+	bool "Support for rpcbind versions 3 & 4 (EXPERIMENTAL)"
+	depends on SUNRPC && EXPERIMENTAL
+	help
+	  Provides kernel support for querying rpcbind servers via versions 3
+	  and 4 of the rpcbind protocol.  The kernel automatically falls back
+	  to version 2 if a remote rpcbind service does not support versions
+	  3 or 4.
+
+	  If unsure, say N to get traditional behavior (version 2 rpcbind
+	  requests only).
+
 config RPCSEC_GSS_KRB5
 	tristate "Secure RPC: Kerberos V mechanism (EXPERIMENTAL)"
 	depends on SUNRPC && EXPERIMENTAL
diff --git a/fs/lockd/mon.c b/fs/lockd/mon.c
index eb243edf893..2102e2d0134 100644
--- a/fs/lockd/mon.c
+++ b/fs/lockd/mon.c
@@ -225,16 +225,13 @@ xdr_decode_stat(struct rpc_rqst *rqstp, __be32 *p, struct nsm_res *resp)
 #define SM_monres_sz	2
 #define SM_unmonres_sz	1
 
-#ifndef MAX
-# define MAX(a, b)	(((a) > (b))? (a) : (b))
-#endif
-
 static struct rpc_procinfo	nsm_procedures[] = {
 [SM_MON] = {
 		.p_proc		= SM_MON,
 		.p_encode	= (kxdrproc_t) xdr_encode_mon,
 		.p_decode	= (kxdrproc_t) xdr_decode_stat_res,
-		.p_bufsiz	= MAX(SM_mon_sz, SM_monres_sz) << 2,
+		.p_arglen	= SM_mon_sz,
+		.p_replen	= SM_monres_sz,
 		.p_statidx	= SM_MON,
 		.p_name		= "MONITOR",
 	},
@@ -242,7 +239,8 @@ static struct rpc_procinfo	nsm_procedures[] = {
 		.p_proc		= SM_UNMON,
 		.p_encode	= (kxdrproc_t) xdr_encode_unmon,
 		.p_decode	= (kxdrproc_t) xdr_decode_stat,
-		.p_bufsiz	= MAX(SM_mon_id_sz, SM_unmonres_sz) << 2,
+		.p_arglen	= SM_mon_id_sz,
+		.p_replen	= SM_unmonres_sz,
 		.p_statidx	= SM_UNMON,
 		.p_name		= "UNMONITOR",
 	},
diff --git a/fs/lockd/xdr.c b/fs/lockd/xdr.c
index 34dae5d7073..9702956d206 100644
--- a/fs/lockd/xdr.c
+++ b/fs/lockd/xdr.c
@@ -510,17 +510,20 @@ nlmclt_decode_res(struct rpc_rqst *req, __be32 *p, struct nlm_res *resp)
 	return 0;
 }
 
+#if (NLMCLNT_OHSIZE > XDR_MAX_NETOBJ)
+#  error "NLM host name cannot be larger than XDR_MAX_NETOBJ!"
+#endif
+
 /*
  * Buffer requirements for NLM
  */
 #define NLM_void_sz		0
 #define NLM_cookie_sz		1+XDR_QUADLEN(NLM_MAXCOOKIELEN)
-#define NLM_caller_sz		1+XDR_QUADLEN(sizeof(utsname()->nodename))
-#define NLM_netobj_sz		1+XDR_QUADLEN(XDR_MAX_NETOBJ)
-/* #define NLM_owner_sz		1+XDR_QUADLEN(NLM_MAXOWNER) */
+#define NLM_caller_sz		1+XDR_QUADLEN(NLMCLNT_OHSIZE)
+#define NLM_owner_sz		1+XDR_QUADLEN(NLMCLNT_OHSIZE)
 #define NLM_fhandle_sz		1+XDR_QUADLEN(NFS2_FHSIZE)
-#define NLM_lock_sz		3+NLM_caller_sz+NLM_netobj_sz+NLM_fhandle_sz
-#define NLM_holder_sz		4+NLM_netobj_sz
+#define NLM_lock_sz		3+NLM_caller_sz+NLM_owner_sz+NLM_fhandle_sz
+#define NLM_holder_sz		4+NLM_owner_sz
 
 #define NLM_testargs_sz		NLM_cookie_sz+1+NLM_lock_sz
 #define NLM_lockargs_sz		NLM_cookie_sz+4+NLM_lock_sz
@@ -531,10 +534,6 @@ nlmclt_decode_res(struct rpc_rqst *req, __be32 *p, struct nlm_res *resp)
 #define NLM_res_sz		NLM_cookie_sz+1
 #define NLM_norep_sz		0
 
-#ifndef MAX
-# define MAX(a, b)		(((a) > (b))? (a) : (b))
-#endif
-
 /*
  * For NLM, a void procedure really returns nothing
  */
@@ -545,7 +544,8 @@ nlmclt_decode_res(struct rpc_rqst *req, __be32 *p, struct nlm_res *resp)
 	.p_proc      = NLMPROC_##proc,					\
 	.p_encode    = (kxdrproc_t) nlmclt_encode_##argtype,		\
 	.p_decode    = (kxdrproc_t) nlmclt_decode_##restype,		\
-	.p_bufsiz    = MAX(NLM_##argtype##_sz, NLM_##restype##_sz) << 2,	\
+	.p_arglen    = NLM_##argtype##_sz,				\
+	.p_replen    = NLM_##restype##_sz,				\
 	.p_statidx   = NLMPROC_##proc,					\
 	.p_name      = #proc,						\
 	}
diff --git a/fs/lockd/xdr4.c b/fs/lockd/xdr4.c
index a7824055121..ce1efdbe1b3 100644
--- a/fs/lockd/xdr4.c
+++ b/fs/lockd/xdr4.c
@@ -516,17 +516,24 @@ nlm4clt_decode_res(struct rpc_rqst *req, __be32 *p, struct nlm_res *resp)
 	return 0;
 }
 
+#if (NLMCLNT_OHSIZE > XDR_MAX_NETOBJ)
+#  error "NLM host name cannot be larger than XDR_MAX_NETOBJ!"
+#endif
+
+#if (NLMCLNT_OHSIZE > NLM_MAXSTRLEN)
+#  error "NLM host name cannot be larger than NLM's maximum string length!"
+#endif
+
 /*
  * Buffer requirements for NLM
  */
 #define NLM4_void_sz		0
 #define NLM4_cookie_sz		1+XDR_QUADLEN(NLM_MAXCOOKIELEN)
-#define NLM4_caller_sz		1+XDR_QUADLEN(NLM_MAXSTRLEN)
-#define NLM4_netobj_sz		1+XDR_QUADLEN(XDR_MAX_NETOBJ)
-/* #define NLM4_owner_sz		1+XDR_QUADLEN(NLM4_MAXOWNER) */
+#define NLM4_caller_sz		1+XDR_QUADLEN(NLMCLNT_OHSIZE)
+#define NLM4_owner_sz		1+XDR_QUADLEN(NLMCLNT_OHSIZE)
 #define NLM4_fhandle_sz		1+XDR_QUADLEN(NFS3_FHSIZE)
-#define NLM4_lock_sz		5+NLM4_caller_sz+NLM4_netobj_sz+NLM4_fhandle_sz
-#define NLM4_holder_sz		6+NLM4_netobj_sz
+#define NLM4_lock_sz		5+NLM4_caller_sz+NLM4_owner_sz+NLM4_fhandle_sz
+#define NLM4_holder_sz		6+NLM4_owner_sz
 
 #define NLM4_testargs_sz	NLM4_cookie_sz+1+NLM4_lock_sz
 #define NLM4_lockargs_sz	NLM4_cookie_sz+4+NLM4_lock_sz
@@ -537,10 +544,6 @@ nlm4clt_decode_res(struct rpc_rqst *req, __be32 *p, struct nlm_res *resp)
 #define NLM4_res_sz		NLM4_cookie_sz+1
 #define NLM4_norep_sz		0
 
-#ifndef MAX
-# define MAX(a,b)		(((a) > (b))? (a) : (b))
-#endif
-
 /*
  * For NLM, a void procedure really returns nothing
  */
@@ -551,7 +554,8 @@ nlm4clt_decode_res(struct rpc_rqst *req, __be32 *p, struct nlm_res *resp)
 	.p_proc      = NLMPROC_##proc,					\
 	.p_encode    = (kxdrproc_t) nlm4clt_encode_##argtype,		\
 	.p_decode    = (kxdrproc_t) nlm4clt_decode_##restype,		\
-	.p_bufsiz    = MAX(NLM4_##argtype##_sz, NLM4_##restype##_sz) << 2,	\
+	.p_arglen    = NLM4_##argtype##_sz,				\
+	.p_replen    = NLM4_##restype##_sz,				\
 	.p_statidx   = NLMPROC_##proc,					\
 	.p_name      = #proc,						\
 	}
diff --git a/fs/nfs/client.c b/fs/nfs/client.c
index 2190e6c2792..5bd03b97002 100644
--- a/fs/nfs/client.c
+++ b/fs/nfs/client.c
@@ -618,7 +618,8 @@ static int nfs_init_server(struct nfs_server *server, const struct nfs_mount_dat
 	if (clp->cl_nfsversion == 3) {
 		if (server->namelen == 0 || server->namelen > NFS3_MAXNAMLEN)
 			server->namelen = NFS3_MAXNAMLEN;
-		server->caps |= NFS_CAP_READDIRPLUS;
+		if (!(data->flags & NFS_MOUNT_NORDIRPLUS))
+			server->caps |= NFS_CAP_READDIRPLUS;
 	} else {
 		if (server->namelen == 0 || server->namelen > NFS2_MAXNAMLEN)
 			server->namelen = NFS2_MAXNAMLEN;
diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index cd3469720cb..e59fd31c9a2 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -154,6 +154,8 @@ typedef struct {
 	decode_dirent_t	decode;
 	int		plus;
 	int		error;
+	unsigned long	timestamp;
+	int		timestamp_valid;
 } nfs_readdir_descriptor_t;
 
 /* Now we cache directories properly, by stuffing the dirent
@@ -195,6 +197,8 @@ int nfs_readdir_filler(nfs_readdir_descriptor_t *desc, struct page *page)
 		}
 		goto error;
 	}
+	desc->timestamp = timestamp;
+	desc->timestamp_valid = 1;
 	SetPageUptodate(page);
 	spin_lock(&inode->i_lock);
 	NFS_I(inode)->cache_validity |= NFS_INO_INVALID_ATIME;
@@ -225,6 +229,10 @@ int dir_decode(nfs_readdir_descriptor_t *desc)
 	if (IS_ERR(p))
 		return PTR_ERR(p);
 	desc->ptr = p;
+	if (desc->timestamp_valid)
+		desc->entry->fattr->time_start = desc->timestamp;
+	else
+		desc->entry->fattr->valid &= ~NFS_ATTR_FATTR;
 	return 0;
 }
 
@@ -316,6 +324,10 @@ int find_dirent_page(nfs_readdir_descriptor_t *desc)
 			__FUNCTION__, desc->page_index,
 			(long long) *desc->dir_cookie);
 
+	/* If we find the page in the page_cache, we cannot be sure
+	 * how fresh the data is, so we will ignore readdir_plus attributes.
+	 */
+	desc->timestamp_valid = 0;
 	page = read_cache_page(inode->i_mapping, desc->page_index,
 			       (filler_t *)nfs_readdir_filler, desc);
 	if (IS_ERR(page)) {
@@ -468,6 +480,7 @@ int uncached_readdir(nfs_readdir_descriptor_t *desc, void *dirent,
 	struct rpc_cred	*cred = nfs_file_cred(file);
 	struct page	*page = NULL;
 	int		status;
+	unsigned long	timestamp;
 
 	dfprintk(DIRCACHE, "NFS: uncached_readdir() searching for cookie %Lu\n",
 			(unsigned long long)*desc->dir_cookie);
@@ -477,6 +490,7 @@ int uncached_readdir(nfs_readdir_descriptor_t *desc, void *dirent,
 		status = -ENOMEM;
 		goto out;
 	}
+	timestamp = jiffies;
 	desc->error = NFS_PROTO(inode)->readdir(file->f_path.dentry, cred, *desc->dir_cookie,
 						page,
 						NFS_SERVER(inode)->dtsize,
@@ -487,6 +501,8 @@ int uncached_readdir(nfs_readdir_descriptor_t *desc, void *dirent,
 	desc->page = page;
 	desc->ptr = kmap(page);		/* matching kunmap in nfs_do_filldir */
 	if (desc->error >= 0) {
+		desc->timestamp = timestamp;
+		desc->timestamp_valid = 1;
 		if ((status = dir_decode(desc)) == 0)
 			desc->entry->prev_cookie = *desc->dir_cookie;
 	} else
@@ -849,6 +865,10 @@ static int nfs_dentry_delete(struct dentry *dentry)
 static void nfs_dentry_iput(struct dentry *dentry, struct inode *inode)
 {
 	nfs_inode_return_delegation(inode);
+	if (S_ISDIR(inode->i_mode))
+		/* drop any readdir cache as it could easily be old */
+		NFS_I(inode)->cache_validity |= NFS_INO_INVALID_DATA;
+
 	if (dentry->d_flags & DCACHE_NFSFS_RENAMED) {
 		lock_kernel();
 		drop_nlink(inode);
diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c
index 2877744cb60..889de60f8a8 100644
--- a/fs/nfs/direct.c
+++ b/fs/nfs/direct.c
@@ -54,6 +54,7 @@
 #include <asm/uaccess.h>
 #include <asm/atomic.h>
 
+#include "internal.h"
 #include "iostat.h"
 
 #define NFSDBG_FACILITY		NFSDBG_VFS
@@ -271,7 +272,7 @@ static ssize_t nfs_direct_read_schedule(struct nfs_direct_req *dreq, unsigned lo
 		bytes = min(rsize,count);
 
 		result = -ENOMEM;
-		data = nfs_readdata_alloc(pgbase + bytes);
+		data = nfs_readdata_alloc(nfs_page_array_len(pgbase, bytes));
 		if (unlikely(!data))
 			break;
 
@@ -602,7 +603,7 @@ static ssize_t nfs_direct_write_schedule(struct nfs_direct_req *dreq, unsigned l
 		bytes = min(wsize,count);
 
 		result = -ENOMEM;
-		data = nfs_writedata_alloc(pgbase + bytes);
+		data = nfs_writedata_alloc(nfs_page_array_len(pgbase, bytes));
 		if (unlikely(!data))
 			break;
 
diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h
index 6610f2b0207..ad2b40db1e6 100644
--- a/fs/nfs/internal.h
+++ b/fs/nfs/internal.h
@@ -231,3 +231,15 @@ unsigned int nfs_page_length(struct page *page)
 	}
 	return 0;
 }
+
+/*
+ * Determine the number of pages in an array of length 'len' and
+ * with a base offset of 'base'
+ */
+static inline
+unsigned int nfs_page_array_len(unsigned int base, size_t len)
+{
+	return ((unsigned long)len + (unsigned long)base +
+		PAGE_SIZE - 1) >> PAGE_SHIFT;
+}
+
diff --git a/fs/nfs/mount_clnt.c b/fs/nfs/mount_clnt.c
index f75fe72b416..ca5a266a314 100644
--- a/fs/nfs/mount_clnt.c
+++ b/fs/nfs/mount_clnt.c
@@ -133,13 +133,15 @@ xdr_decode_fhstatus3(struct rpc_rqst *req, __be32 *p, struct mnt_fhstatus *res)
 
 #define MNT_dirpath_sz		(1 + 256)
 #define MNT_fhstatus_sz		(1 + 8)
+#define MNT_fhstatus3_sz	(1 + 16)
 
 static struct rpc_procinfo	mnt_procedures[] = {
 [MNTPROC_MNT] = {
 	  .p_proc		= MNTPROC_MNT,
 	  .p_encode		= (kxdrproc_t) xdr_encode_dirpath,	
 	  .p_decode		= (kxdrproc_t) xdr_decode_fhstatus,
-	  .p_bufsiz		= MNT_dirpath_sz << 2,
+	  .p_arglen		= MNT_dirpath_sz,
+	  .p_replen		= MNT_fhstatus_sz,
 	  .p_statidx		= MNTPROC_MNT,
 	  .p_name		= "MOUNT",
 	},
@@ -150,7 +152,8 @@ static struct rpc_procinfo mnt3_procedures[] = {
 	  .p_proc		= MOUNTPROC3_MNT,
 	  .p_encode		= (kxdrproc_t) xdr_encode_dirpath,
 	  .p_decode		= (kxdrproc_t) xdr_decode_fhstatus3,
-	  .p_bufsiz		= MNT_dirpath_sz << 2,
+	  .p_arglen		= MNT_dirpath_sz,
+	  .p_replen		= MNT_fhstatus3_sz,
 	  .p_statidx		= MOUNTPROC3_MNT,
 	  .p_name		= "MOUNT",
 	},
diff --git a/fs/nfs/nfs2xdr.c b/fs/nfs/nfs2xdr.c
index 3be4e72a022..abd9f8b4894 100644
--- a/fs/nfs/nfs2xdr.c
+++ b/fs/nfs/nfs2xdr.c
@@ -687,16 +687,13 @@ nfs_stat_to_errno(int stat)
 	return nfs_errtbl[i].errno;
 }
 
-#ifndef MAX
-# define MAX(a, b)	(((a) > (b))? (a) : (b))
-#endif
-
 #define PROC(proc, argtype, restype, timer)				\
 [NFSPROC_##proc] = {							\
 	.p_proc	    =  NFSPROC_##proc,					\
 	.p_encode   =  (kxdrproc_t) nfs_xdr_##argtype,			\
 	.p_decode   =  (kxdrproc_t) nfs_xdr_##restype,			\
-	.p_bufsiz   =  MAX(NFS_##argtype##_sz,NFS_##restype##_sz) << 2,	\
+	.p_arglen   =  NFS_##argtype##_sz,				\
+	.p_replen   =  NFS_##restype##_sz,				\
 	.p_timer    =  timer,						\
 	.p_statidx  =  NFSPROC_##proc,					\
 	.p_name     =  #proc,						\
diff --git a/fs/nfs/nfs3xdr.c b/fs/nfs/nfs3xdr.c
index 0ace092d126..b51df8eb9f0 100644
--- a/fs/nfs/nfs3xdr.c
+++ b/fs/nfs/nfs3xdr.c
@@ -1102,16 +1102,13 @@ nfs3_xdr_setaclres(struct rpc_rqst *req, __be32 *p, struct nfs_fattr *fattr)
 }
 #endif  /* CONFIG_NFS_V3_ACL */
 
-#ifndef MAX
-# define MAX(a, b)	(((a) > (b))? (a) : (b))
-#endif
-
 #define PROC(proc, argtype, restype, timer)				\
 [NFS3PROC_##proc] = {							\
 	.p_proc      = NFS3PROC_##proc,					\
 	.p_encode    = (kxdrproc_t) nfs3_xdr_##argtype,			\
 	.p_decode    = (kxdrproc_t) nfs3_xdr_##restype,			\
-	.p_bufsiz    = MAX(NFS3_##argtype##_sz,NFS3_##restype##_sz) << 2,	\
+	.p_arglen    = NFS3_##argtype##_sz,				\
+	.p_replen    = NFS3_##restype##_sz,				\
 	.p_timer     = timer,						\
 	.p_statidx   = NFS3PROC_##proc,					\
 	.p_name      = #proc,						\
@@ -1153,7 +1150,8 @@ static struct rpc_procinfo	nfs3_acl_procedures[] = {
 		.p_proc = ACLPROC3_GETACL,
 		.p_encode = (kxdrproc_t) nfs3_xdr_getaclargs,
 		.p_decode = (kxdrproc_t) nfs3_xdr_getaclres,
-		.p_bufsiz = MAX(ACL3_getaclargs_sz, ACL3_getaclres_sz) << 2,
+		.p_arglen = ACL3_getaclargs_sz,
+		.p_replen = ACL3_getaclres_sz,
 		.p_timer = 1,
 		.p_name = "GETACL",
 	},
@@ -1161,7 +1159,8 @@ static struct rpc_procinfo	nfs3_acl_procedures[] = {
 		.p_proc = ACLPROC3_SETACL,
 		.p_encode = (kxdrproc_t) nfs3_xdr_setaclargs,
 		.p_decode = (kxdrproc_t) nfs3_xdr_setaclres,
-		.p_bufsiz = MAX(ACL3_setaclargs_sz, ACL3_setaclres_sz) << 2,
+		.p_arglen = ACL3_setaclargs_sz,
+		.p_replen = ACL3_setaclres_sz,
 		.p_timer = 0,
 		.p_name = "SETACL",
 	},
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index f52cf5c33c6..3b5ca1b15fe 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -2647,8 +2647,7 @@ static int __nfs4_proc_set_acl(struct inode *inode, const void *buf, size_t bufl
 	nfs_inode_return_delegation(inode);
 	buf_to_pages(buf, buflen, arg.acl_pages, &arg.acl_pgbase);
 	ret = rpc_call_sync(NFS_CLIENT(inode), &msg, 0);
-	if (ret == 0)
-		nfs4_write_cached_acl(inode, buf, buflen);
+	nfs_zap_caches(inode);
 	return ret;
 }
 
diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c
index f02d522fd78..b8c28f2380a 100644
--- a/fs/nfs/nfs4xdr.c
+++ b/fs/nfs/nfs4xdr.c
@@ -4546,16 +4546,13 @@ nfs4_stat_to_errno(int stat)
 	return stat;
 }
 
-#ifndef MAX
-# define MAX(a, b)	(((a) > (b))? (a) : (b))
-#endif
-
 #define PROC(proc, argtype, restype)				\
 [NFSPROC4_CLNT_##proc] = {					\
 	.p_proc   = NFSPROC4_COMPOUND,				\
 	.p_encode = (kxdrproc_t) nfs4_xdr_##argtype,		\
 	.p_decode = (kxdrproc_t) nfs4_xdr_##restype,		\
-	.p_bufsiz = MAX(NFS4_##argtype##_sz,NFS4_##restype##_sz) << 2,	\
+	.p_arglen = NFS4_##argtype##_sz,			\
+	.p_replen = NFS4_##restype##_sz,			\
 	.p_statidx = NFSPROC4_CLNT_##proc,			\
 	.p_name   = #proc,					\
     }
diff --git a/fs/nfs/nfsroot.c b/fs/nfs/nfsroot.c
index 75f819dc025..49d1008ce1d 100644
--- a/fs/nfs/nfsroot.c
+++ b/fs/nfs/nfsroot.c
@@ -428,7 +428,7 @@ static int __init root_nfs_getport(int program, int version, int proto)
 	printk(KERN_NOTICE "Looking up port of RPC %d/%d on %u.%u.%u.%u\n",
 		program, version, NIPQUAD(servaddr));
 	set_sockaddr(&sin, servaddr, 0);
-	return rpc_getport_external(&sin, program, version, proto);
+	return rpcb_getport_external(&sin, program, version, proto);
 }
 
 
diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c
index ca4b1d4ff42..388950118f5 100644
--- a/fs/nfs/pagelist.c
+++ b/fs/nfs/pagelist.c
@@ -17,7 +17,8 @@
 #include <linux/nfs_page.h>
 #include <linux/nfs_fs.h>
 #include <linux/nfs_mount.h>
-#include <linux/writeback.h>
+
+#include "internal.h"
 
 #define NFS_PARANOIA 1
 
@@ -50,9 +51,7 @@ nfs_page_free(struct nfs_page *p)
  * @count: number of bytes to read/write
  *
  * The page must be locked by the caller. This makes sure we never
- * create two different requests for the same page, and avoids
- * a possible deadlock when we reach the hard limit on the number
- * of dirty pages.
+ * create two different requests for the same page.
  * User should ensure it is safe to sleep in this function.
  */
 struct nfs_page *
@@ -63,16 +62,12 @@ nfs_create_request(struct nfs_open_context *ctx, struct inode *inode,
 	struct nfs_server *server = NFS_SERVER(inode);
 	struct nfs_page		*req;
 
-	/* Deal with hard limits.  */
 	for (;;) {
 		/* try to allocate the request struct */
 		req = nfs_page_alloc();
 		if (req != NULL)
 			break;
 
-		/* Try to free up at least one request in order to stay
-		 * below the hard limit
-		 */
 		if (signalled() && (server->flags & NFS_MOUNT_INTR))
 			return ERR_PTR(-ERESTARTSYS);
 		yield();
@@ -223,124 +218,151 @@ out:
 }
 
 /**
- * nfs_coalesce_requests - Split coalesced requests out from a list.
- * @head: source list
- * @dst: destination list
- * @nmax: maximum number of requests to coalesce
- *
- * Moves a maximum of 'nmax' elements from one list to another.
- * The elements are checked to ensure that they form a contiguous set
- * of pages, and that the RPC credentials are the same.
+ * nfs_pageio_init - initialise a page io descriptor
+ * @desc: pointer to descriptor
+ * @inode: pointer to inode
+ * @doio: pointer to io function
+ * @bsize: io block size
+ * @io_flags: extra parameters for the io function
  */
-int
-nfs_coalesce_requests(struct list_head *head, struct list_head *dst,
-		      unsigned int nmax)
+void nfs_pageio_init(struct nfs_pageio_descriptor *desc,
+		     struct inode *inode,
+		     int (*doio)(struct inode *, struct list_head *, unsigned int, size_t, int),
+		     size_t bsize,
+		     int io_flags)
 {
-	struct nfs_page		*req = NULL;
-	unsigned int		npages = 0;
-
-	while (!list_empty(head)) {
-		struct nfs_page	*prev = req;
-
-		req = nfs_list_entry(head->next);
-		if (prev) {
-			if (req->wb_context->cred != prev->wb_context->cred)
-				break;
-			if (req->wb_context->lockowner != prev->wb_context->lockowner)
-				break;
-			if (req->wb_context->state != prev->wb_context->state)
-				break;
-			if (req->wb_index != (prev->wb_index + 1))
-				break;
-
-			if (req->wb_pgbase != 0)
-				break;
-		}
-		nfs_list_remove_request(req);
-		nfs_list_add_request(req, dst);
-		npages++;
-		if (req->wb_pgbase + req->wb_bytes != PAGE_CACHE_SIZE)
-			break;
-		if (npages >= nmax)
-			break;
-	}
-	return npages;
+	INIT_LIST_HEAD(&desc->pg_list);
+	desc->pg_bytes_written = 0;
+	desc->pg_count = 0;
+	desc->pg_bsize = bsize;
+	desc->pg_base = 0;
+	desc->pg_inode = inode;
+	desc->pg_doio = doio;
+	desc->pg_ioflags = io_flags;
+	desc->pg_error = 0;
 }
 
-#define NFS_SCAN_MAXENTRIES 16
 /**
- * nfs_scan_dirty - Scan the radix tree for dirty requests
- * @mapping: pointer to address space
- * @wbc: writeback_control structure
- * @dst: Destination list
+ * nfs_can_coalesce_requests - test two requests for compatibility
+ * @prev: pointer to nfs_page
+ * @req: pointer to nfs_page
  *
- * Moves elements from one of the inode request lists.
- * If the number of requests is set to 0, the entire address_space
- * starting at index idx_start, is scanned.
- * The requests are *not* checked to ensure that they form a contiguous set.
- * You must be holding the inode's req_lock when calling this function
+ * The nfs_page structures 'prev' and 'req' are compared to ensure that the
+ * page data area they describe is contiguous, and that their RPC
+ * credentials, NFSv4 open state, and lockowners are the same.
+ *
+ * Return 'true' if this is the case, else return 'false'.
  */
-long nfs_scan_dirty(struct address_space *mapping,
-			struct writeback_control *wbc,
-			struct list_head *dst)
+static int nfs_can_coalesce_requests(struct nfs_page *prev,
+				     struct nfs_page *req)
 {
-	struct nfs_inode *nfsi = NFS_I(mapping->host);
-	struct nfs_page *pgvec[NFS_SCAN_MAXENTRIES];
-	struct nfs_page *req;
-	pgoff_t idx_start, idx_end;
-	long res = 0;
-	int found, i;
-
-	if (nfsi->ndirty == 0)
+	if (req->wb_context->cred != prev->wb_context->cred)
 		return 0;
-	if (wbc->range_cyclic) {
-		idx_start = 0;
-		idx_end = ULONG_MAX;
-	} else if (wbc->range_end == 0) {
-		idx_start = wbc->range_start >> PAGE_CACHE_SHIFT;
-		idx_end = ULONG_MAX;
-	} else {
-		idx_start = wbc->range_start >> PAGE_CACHE_SHIFT;
-		idx_end = wbc->range_end >> PAGE_CACHE_SHIFT;
-	}
+	if (req->wb_context->lockowner != prev->wb_context->lockowner)
+		return 0;
+	if (req->wb_context->state != prev->wb_context->state)
+		return 0;
+	if (req->wb_index != (prev->wb_index + 1))
+		return 0;
+	if (req->wb_pgbase != 0)
+		return 0;
+	if (prev->wb_pgbase + prev->wb_bytes != PAGE_CACHE_SIZE)
+		return 0;
+	return 1;
+}
 
-	for (;;) {
-		unsigned int toscan = NFS_SCAN_MAXENTRIES;
+/**
+ * nfs_pageio_do_add_request - Attempt to coalesce a request into a page list.
+ * @desc: destination io descriptor
+ * @req: request
+ *
+ * Returns true if the request 'req' was successfully coalesced into the
+ * existing list of pages 'desc'.
+ */
+static int nfs_pageio_do_add_request(struct nfs_pageio_descriptor *desc,
+				     struct nfs_page *req)
+{
+	size_t newlen = req->wb_bytes;
 
-		found = radix_tree_gang_lookup_tag(&nfsi->nfs_page_tree,
-				(void **)&pgvec[0], idx_start, toscan,
-				NFS_PAGE_TAG_DIRTY);
+	if (desc->pg_count != 0) {
+		struct nfs_page *prev;
 
-		/* Did we make progress? */
-		if (found <= 0)
-			break;
+		/*
+		 * FIXME: ideally we should be able to coalesce all requests
+		 * that are not block boundary aligned, but currently this
+		 * is problematic for the case of bsize < PAGE_CACHE_SIZE,
+		 * since nfs_flush_multi and nfs_pagein_multi assume you
+		 * can have only one struct nfs_page.
+		 */
+		if (desc->pg_bsize < PAGE_SIZE)
+			return 0;
+		newlen += desc->pg_count;
+		if (newlen > desc->pg_bsize)
+			return 0;
+		prev = nfs_list_entry(desc->pg_list.prev);
+		if (!nfs_can_coalesce_requests(prev, req))
+			return 0;
+	} else
+		desc->pg_base = req->wb_pgbase;
+	nfs_list_remove_request(req);
+	nfs_list_add_request(req, &desc->pg_list);
+	desc->pg_count = newlen;
+	return 1;
+}
 
-		for (i = 0; i < found; i++) {
-			req = pgvec[i];
-			if (!wbc->range_cyclic && req->wb_index > idx_end)
-				goto out;
+/*
+ * Helper for nfs_pageio_add_request and nfs_pageio_complete
+ */
+static void nfs_pageio_doio(struct nfs_pageio_descriptor *desc)
+{
+	if (!list_empty(&desc->pg_list)) {
+		int error = desc->pg_doio(desc->pg_inode,
+					  &desc->pg_list,
+					  nfs_page_array_len(desc->pg_base,
+							     desc->pg_count),
+					  desc->pg_count,
+					  desc->pg_ioflags);
+		if (error < 0)
+			desc->pg_error = error;
+		else
+			desc->pg_bytes_written += desc->pg_count;
+	}
+	if (list_empty(&desc->pg_list)) {
+		desc->pg_count = 0;
+		desc->pg_base = 0;
+	}
+}
 
-			/* Try to lock request and mark it for writeback */
-			if (!nfs_set_page_writeback_locked(req))
-				goto next;
-			radix_tree_tag_clear(&nfsi->nfs_page_tree,
-					req->wb_index, NFS_PAGE_TAG_DIRTY);
-			nfsi->ndirty--;
-			nfs_list_remove_request(req);
-			nfs_list_add_request(req, dst);
-			res++;
-			if (res == LONG_MAX)
-				goto out;
-next:
-			idx_start = req->wb_index + 1;
-		}
+/**
+ * nfs_pageio_add_request - Attempt to coalesce a request into a page list.
+ * @desc: destination io descriptor
+ * @req: request
+ *
+ * Returns true if the request 'req' was successfully coalesced into the
+ * existing list of pages 'desc'.
+ */
+int nfs_pageio_add_request(struct nfs_pageio_descriptor *desc,
+			   struct nfs_page *req)
+{
+	while (!nfs_pageio_do_add_request(desc, req)) {
+		nfs_pageio_doio(desc);
+		if (desc->pg_error < 0)
+			return 0;
 	}
-out:
-	WARN_ON ((nfsi->ndirty == 0) != list_empty(&nfsi->dirty));
-	return res;
+	return 1;
 }
 
 /**
+ * nfs_pageio_complete - Complete I/O on an nfs_pageio_descriptor
+ * @desc: pointer to io descriptor
+ */
+void nfs_pageio_complete(struct nfs_pageio_descriptor *desc)
+{
+	nfs_pageio_doio(desc);
+}
+
+#define NFS_SCAN_MAXENTRIES 16
+/**
  * nfs_scan_list - Scan a list for matching requests
  * @nfsi: NFS inode
  * @head: One of the NFS inode request lists
@@ -355,12 +377,12 @@ out:
  * You must be holding the inode's req_lock when calling this function
  */
 int nfs_scan_list(struct nfs_inode *nfsi, struct list_head *head,
-		struct list_head *dst, unsigned long idx_start,
+		struct list_head *dst, pgoff_t idx_start,
 		unsigned int npages)
 {
 	struct nfs_page *pgvec[NFS_SCAN_MAXENTRIES];
 	struct nfs_page *req;
-	unsigned long idx_end;
+	pgoff_t idx_end;
 	int found, i;
 	int res;
 
diff --git a/fs/nfs/read.c b/fs/nfs/read.c
index 6ab4d5a9edf..9a55807b2a7 100644
--- a/fs/nfs/read.c
+++ b/fs/nfs/read.c
@@ -27,7 +27,8 @@
 
 #define NFSDBG_FACILITY		NFSDBG_PAGECACHE
 
-static int nfs_pagein_one(struct list_head *, struct inode *);
+static int nfs_pagein_multi(struct inode *, struct list_head *, unsigned int, size_t, int);
+static int nfs_pagein_one(struct inode *, struct list_head *, unsigned int, size_t, int);
 static const struct rpc_call_ops nfs_read_partial_ops;
 static const struct rpc_call_ops nfs_read_full_ops;
 
@@ -36,9 +37,8 @@ static mempool_t *nfs_rdata_mempool;
 
 #define MIN_POOL_READ	(32)
 
-struct nfs_read_data *nfs_readdata_alloc(size_t len)
+struct nfs_read_data *nfs_readdata_alloc(unsigned int pagecount)
 {
-	unsigned int pagecount = (len + PAGE_SIZE - 1) >> PAGE_SHIFT;
 	struct nfs_read_data *p = mempool_alloc(nfs_rdata_mempool, GFP_NOFS);
 
 	if (p) {
@@ -133,7 +133,10 @@ static int nfs_readpage_async(struct nfs_open_context *ctx, struct inode *inode,
 		memclear_highpage_flush(page, len, PAGE_CACHE_SIZE - len);
 
 	nfs_list_add_request(new, &one_request);
-	nfs_pagein_one(&one_request, inode);
+	if (NFS_SERVER(inode)->rsize < PAGE_CACHE_SIZE)
+		nfs_pagein_multi(inode, &one_request, 1, len, 0);
+	else
+		nfs_pagein_one(inode, &one_request, 1, len, 0);
 	return 0;
 }
 
@@ -230,7 +233,7 @@ static void nfs_execute_read(struct nfs_read_data *data)
  * won't see the new data until our attribute cache is updated.  This is more
  * or less conventional NFS client behavior.
  */
-static int nfs_pagein_multi(struct list_head *head, struct inode *inode)
+static int nfs_pagein_multi(struct inode *inode, struct list_head *head, unsigned int npages, size_t count, int flags)
 {
 	struct nfs_page *req = nfs_list_entry(head->next);
 	struct page *page = req->wb_page;
@@ -242,11 +245,11 @@ static int nfs_pagein_multi(struct list_head *head, struct inode *inode)
 
 	nfs_list_remove_request(req);
 
-	nbytes = req->wb_bytes;
+	nbytes = count;
 	do {
 		size_t len = min(nbytes,rsize);
 
-		data = nfs_readdata_alloc(len);
+		data = nfs_readdata_alloc(1);
 		if (!data)
 			goto out_bad;
 		INIT_LIST_HEAD(&data->pages);
@@ -258,23 +261,19 @@ static int nfs_pagein_multi(struct list_head *head, struct inode *inode)
 
 	ClearPageError(page);
 	offset = 0;
-	nbytes = req->wb_bytes;
+	nbytes = count;
 	do {
 		data = list_entry(list.next, struct nfs_read_data, pages);
 		list_del_init(&data->pages);
 
 		data->pagevec[0] = page;
 
-		if (nbytes > rsize) {
-			nfs_read_rpcsetup(req, data, &nfs_read_partial_ops,
-					rsize, offset);
-			offset += rsize;
-			nbytes -= rsize;
-		} else {
-			nfs_read_rpcsetup(req, data, &nfs_read_partial_ops,
-					nbytes, offset);
-			nbytes = 0;
-		}
+		if (nbytes < rsize)
+			rsize = nbytes;
+		nfs_read_rpcsetup(req, data, &nfs_read_partial_ops,
+				  rsize, offset);
+		offset += rsize;
+		nbytes -= rsize;
 		nfs_execute_read(data);
 	} while (nbytes != 0);
 
@@ -291,30 +290,24 @@ out_bad:
 	return -ENOMEM;
 }
 
-static int nfs_pagein_one(struct list_head *head, struct inode *inode)
+static int nfs_pagein_one(struct inode *inode, struct list_head *head, unsigned int npages, size_t count, int flags)
 {
 	struct nfs_page		*req;
 	struct page		**pages;
 	struct nfs_read_data	*data;
-	unsigned int		count;
 
-	if (NFS_SERVER(inode)->rsize < PAGE_CACHE_SIZE)
-		return nfs_pagein_multi(head, inode);
-
-	data = nfs_readdata_alloc(NFS_SERVER(inode)->rsize);
+	data = nfs_readdata_alloc(npages);
 	if (!data)
 		goto out_bad;
 
 	INIT_LIST_HEAD(&data->pages);
 	pages = data->pagevec;
-	count = 0;
 	while (!list_empty(head)) {
 		req = nfs_list_entry(head->next);
 		nfs_list_remove_request(req);
 		nfs_list_add_request(req, &data->pages);
 		ClearPageError(req->wb_page);
 		*pages++ = req->wb_page;
-		count += req->wb_bytes;
 	}
 	req = nfs_list_entry(data->pages.next);
 
@@ -327,28 +320,6 @@ out_bad:
 	return -ENOMEM;
 }
 
-static int
-nfs_pagein_list(struct list_head *head, int rpages)
-{
-	LIST_HEAD(one_request);
-	struct nfs_page		*req;
-	int			error = 0;
-	unsigned int		pages = 0;
-
-	while (!list_empty(head)) {
-		pages += nfs_coalesce_requests(head, &one_request, rpages);
-		req = nfs_list_entry(one_request.next);
-		error = nfs_pagein_one(&one_request, req->wb_context->dentry->d_inode);
-		if (error < 0)
-			break;
-	}
-	if (error >= 0)
-		return pages;
-
-	nfs_async_read_error(head);
-	return error;
-}
-
 /*
  * This is the callback from RPC telling us whether a reply was
  * received or some error occurred (timeout or socket shutdown).
@@ -538,7 +509,7 @@ out_error:
 }
 
 struct nfs_readdesc {
-	struct list_head *head;
+	struct nfs_pageio_descriptor *pgio;
 	struct nfs_open_context *ctx;
 };
 
@@ -562,19 +533,21 @@ readpage_async_filler(void *data, struct page *page)
 	}
 	if (len < PAGE_CACHE_SIZE)
 		memclear_highpage_flush(page, len, PAGE_CACHE_SIZE - len);
-	nfs_list_add_request(new, desc->head);
+	nfs_pageio_add_request(desc->pgio, new);
 	return 0;
 }
 
 int nfs_readpages(struct file *filp, struct address_space *mapping,
 		struct list_head *pages, unsigned nr_pages)
 {
-	LIST_HEAD(head);
+	struct nfs_pageio_descriptor pgio;
 	struct nfs_readdesc desc = {
-		.head		= &head,
+		.pgio = &pgio,
 	};
 	struct inode *inode = mapping->host;
 	struct nfs_server *server = NFS_SERVER(inode);
+	size_t rsize = server->rsize;
+	unsigned long npages;
 	int ret = -ESTALE;
 
 	dprintk("NFS: nfs_readpages (%s/%Ld %d)\n",
@@ -593,13 +566,16 @@ int nfs_readpages(struct file *filp, struct address_space *mapping,
 	} else
 		desc.ctx = get_nfs_open_context((struct nfs_open_context *)
 				filp->private_data);
+	if (rsize < PAGE_CACHE_SIZE)
+		nfs_pageio_init(&pgio, inode, nfs_pagein_multi, rsize, 0);
+	else
+		nfs_pageio_init(&pgio, inode, nfs_pagein_one, rsize, 0);
+
 	ret = read_cache_pages(mapping, pages, readpage_async_filler, &desc);
-	if (!list_empty(&head)) {
-		int err = nfs_pagein_list(&head, server->rpages);
-		if (!ret)
-			nfs_add_stats(inode, NFSIOS_READPAGES, err);
-			ret = err;
-	}
+
+	nfs_pageio_complete(&pgio);
+	npages = (pgio.pg_bytes_written + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
+	nfs_add_stats(inode, NFSIOS_READPAGES, npages);
 	put_nfs_open_context(desc.ctx);
 out:
 	return ret;
diff --git a/fs/nfs/super.c b/fs/nfs/super.c
index f1eae44b9a1..ca20d3cc260 100644
--- a/fs/nfs/super.c
+++ b/fs/nfs/super.c
@@ -204,9 +204,9 @@ static int nfs_statfs(struct dentry *dentry, struct kstatfs *buf)
 	lock_kernel();
 
 	error = server->nfs_client->rpc_ops->statfs(server, fh, &res);
-	buf->f_type = NFS_SUPER_MAGIC;
 	if (error < 0)
 		goto out_err;
+	buf->f_type = NFS_SUPER_MAGIC;
 
 	/*
 	 * Current versions of glibc do not correctly handle the
@@ -233,15 +233,14 @@ static int nfs_statfs(struct dentry *dentry, struct kstatfs *buf)
 	buf->f_ffree = res.afiles;
 
 	buf->f_namelen = server->namelen;
- out:
+
 	unlock_kernel();
 	return 0;
 
  out_err:
 	dprintk("%s: statfs error = %d\n", __FUNCTION__, -error);
-	buf->f_bsize = buf->f_blocks = buf->f_bfree = buf->f_bavail = -1;
-	goto out;
-
+	unlock_kernel();
+	return error;
 }
 
 /*
@@ -291,6 +290,7 @@ static void nfs_show_mount_options(struct seq_file *m, struct nfs_server *nfss,
 		{ NFS_MOUNT_NOAC, ",noac", "" },
 		{ NFS_MOUNT_NONLM, ",nolock", "" },
 		{ NFS_MOUNT_NOACL, ",noacl", "" },
+		{ NFS_MOUNT_NORDIRPLUS, ",nordirplus", "" },
 		{ 0, NULL, NULL }
 	};
 	const struct proc_nfs_info *nfs_infop;
diff --git a/fs/nfs/write.c b/fs/nfs/write.c
index 79755894174..5d44b8bd107 100644
--- a/fs/nfs/write.c
+++ b/fs/nfs/write.c
@@ -38,7 +38,8 @@
 static struct nfs_page * nfs_update_request(struct nfs_open_context*,
 					    struct page *,
 					    unsigned int, unsigned int);
-static long nfs_flush_mapping(struct address_space *mapping, struct writeback_control *wbc, int how);
+static void nfs_pageio_init_write(struct nfs_pageio_descriptor *desc,
+				  struct inode *inode, int ioflags);
 static const struct rpc_call_ops nfs_write_partial_ops;
 static const struct rpc_call_ops nfs_write_full_ops;
 static const struct rpc_call_ops nfs_commit_ops;
@@ -71,9 +72,8 @@ void nfs_commit_free(struct nfs_write_data *wdata)
 	call_rcu_bh(&wdata->task.u.tk_rcu, nfs_commit_rcu_free);
 }
 
-struct nfs_write_data *nfs_writedata_alloc(size_t len)
+struct nfs_write_data *nfs_writedata_alloc(unsigned int pagecount)
 {
-	unsigned int pagecount = (len + PAGE_SIZE - 1) >> PAGE_SHIFT;
 	struct nfs_write_data *p = mempool_alloc(nfs_wdata_mempool, GFP_NOFS);
 
 	if (p) {
@@ -139,7 +139,7 @@ static void nfs_grow_file(struct page *page, unsigned int offset, unsigned int c
 {
 	struct inode *inode = page->mapping->host;
 	loff_t end, i_size = i_size_read(inode);
-	unsigned long end_index = (i_size - 1) >> PAGE_CACHE_SHIFT;
+	pgoff_t end_index = (i_size - 1) >> PAGE_CACHE_SHIFT;
 
 	if (i_size > 0 && page->index < end_index)
 		return;
@@ -201,7 +201,7 @@ static int nfs_writepage_setup(struct nfs_open_context *ctx, struct page *page,
 static int wb_priority(struct writeback_control *wbc)
 {
 	if (wbc->for_reclaim)
-		return FLUSH_HIGHPRI;
+		return FLUSH_HIGHPRI | FLUSH_STABLE;
 	if (wbc->for_kupdate)
 		return FLUSH_LOWPRI;
 	return 0;
@@ -251,7 +251,8 @@ static void nfs_end_page_writeback(struct page *page)
  * was not tagged.
  * May also return an error if the user signalled nfs_wait_on_request().
  */
-static int nfs_page_mark_flush(struct page *page)
+static int nfs_page_async_flush(struct nfs_pageio_descriptor *pgio,
+				struct page *page)
 {
 	struct nfs_page *req;
 	struct nfs_inode *nfsi = NFS_I(page->mapping->host);
@@ -273,6 +274,8 @@ static int nfs_page_mark_flush(struct page *page)
 		 *	 request as dirty (in which case we don't care).
 		 */
 		spin_unlock(req_lock);
+		/* Prevent deadlock! */
+		nfs_pageio_complete(pgio);
 		ret = nfs_wait_on_request(req);
 		nfs_release_request(req);
 		if (ret != 0)
@@ -283,21 +286,18 @@ static int nfs_page_mark_flush(struct page *page)
 		/* This request is marked for commit */
 		spin_unlock(req_lock);
 		nfs_unlock_request(req);
+		nfs_pageio_complete(pgio);
 		return 1;
 	}
-	if (nfs_set_page_writeback(page) == 0) {
-		nfs_list_remove_request(req);
-		/* add the request to the inode's dirty list. */
-		radix_tree_tag_set(&nfsi->nfs_page_tree,
-				req->wb_index, NFS_PAGE_TAG_DIRTY);
-		nfs_list_add_request(req, &nfsi->dirty);
-		nfsi->ndirty++;
-		spin_unlock(req_lock);
-		__mark_inode_dirty(page->mapping->host, I_DIRTY_PAGES);
-	} else
+	if (nfs_set_page_writeback(page) != 0) {
 		spin_unlock(req_lock);
+		BUG();
+	}
+	radix_tree_tag_set(&nfsi->nfs_page_tree, req->wb_index,
+			NFS_PAGE_TAG_WRITEBACK);
 	ret = test_bit(PG_NEED_FLUSH, &req->wb_flags);
-	nfs_unlock_request(req);
+	spin_unlock(req_lock);
+	nfs_pageio_add_request(pgio, req);
 	return ret;
 }
 
@@ -306,6 +306,7 @@ static int nfs_page_mark_flush(struct page *page)
  */
 static int nfs_writepage_locked(struct page *page, struct writeback_control *wbc)
 {
+	struct nfs_pageio_descriptor mypgio, *pgio;
 	struct nfs_open_context *ctx;
 	struct inode *inode = page->mapping->host;
 	unsigned offset;
@@ -314,7 +315,14 @@ static int nfs_writepage_locked(struct page *page, struct writeback_control *wbc
 	nfs_inc_stats(inode, NFSIOS_VFSWRITEPAGE);
 	nfs_add_stats(inode, NFSIOS_WRITEPAGES, 1);
 
-	err = nfs_page_mark_flush(page);
+	if (wbc->for_writepages)
+		pgio = wbc->fs_private;
+	else {
+		nfs_pageio_init_write(&mypgio, inode, wb_priority(wbc));
+		pgio = &mypgio;
+	}
+
+	err = nfs_page_async_flush(pgio, page);
 	if (err <= 0)
 		goto out;
 	err = 0;
@@ -331,12 +339,12 @@ static int nfs_writepage_locked(struct page *page, struct writeback_control *wbc
 	put_nfs_open_context(ctx);
 	if (err != 0)
 		goto out;
-	err = nfs_page_mark_flush(page);
+	err = nfs_page_async_flush(pgio, page);
 	if (err > 0)
 		err = 0;
 out:
 	if (!wbc->for_writepages)
-		nfs_flush_mapping(page->mapping, wbc, FLUSH_STABLE|wb_priority(wbc));
+		nfs_pageio_complete(pgio);
 	return err;
 }
 
@@ -352,20 +360,20 @@ int nfs_writepage(struct page *page, struct writeback_control *wbc)
 int nfs_writepages(struct address_space *mapping, struct writeback_control *wbc)
 {
 	struct inode *inode = mapping->host;
+	struct nfs_pageio_descriptor pgio;
 	int err;
 
 	nfs_inc_stats(inode, NFSIOS_VFSWRITEPAGES);
 
+	nfs_pageio_init_write(&pgio, inode, wb_priority(wbc));
+	wbc->fs_private = &pgio;
 	err = generic_writepages(mapping, wbc);
+	nfs_pageio_complete(&pgio);
 	if (err)
 		return err;
-	err = nfs_flush_mapping(mapping, wbc, wb_priority(wbc));
-	if (err < 0)
-		goto out;
-	nfs_add_stats(inode, NFSIOS_WRITEPAGES, err);
-	err = 0;
-out:
-	return err;
+	if (pgio.pg_error)
+		return pgio.pg_error;
+	return 0;
 }
 
 /*
@@ -503,11 +511,11 @@ int nfs_reschedule_unstable_write(struct nfs_page *req)
  *
  * Interruptible by signals only if mounted with intr flag.
  */
-static int nfs_wait_on_requests_locked(struct inode *inode, unsigned long idx_start, unsigned int npages)
+static int nfs_wait_on_requests_locked(struct inode *inode, pgoff_t idx_start, unsigned int npages)
 {
 	struct nfs_inode *nfsi = NFS_I(inode);
 	struct nfs_page *req;
-	unsigned long		idx_end, next;
+	pgoff_t idx_end, next;
 	unsigned int		res = 0;
 	int			error;
 
@@ -536,18 +544,6 @@ static int nfs_wait_on_requests_locked(struct inode *inode, unsigned long idx_st
 	return res;
 }
 
-static void nfs_cancel_dirty_list(struct list_head *head)
-{
-	struct nfs_page *req;
-	while(!list_empty(head)) {
-		req = nfs_list_entry(head->next);
-		nfs_list_remove_request(req);
-		nfs_end_page_writeback(req->wb_page);
-		nfs_inode_remove_request(req);
-		nfs_clear_page_writeback(req);
-	}
-}
-
 static void nfs_cancel_commit_list(struct list_head *head)
 {
 	struct nfs_page *req;
@@ -574,7 +570,7 @@ static void nfs_cancel_commit_list(struct list_head *head)
  * The requests are *not* checked to ensure that they form a contiguous set.
  */
 static int
-nfs_scan_commit(struct inode *inode, struct list_head *dst, unsigned long idx_start, unsigned int npages)
+nfs_scan_commit(struct inode *inode, struct list_head *dst, pgoff_t idx_start, unsigned int npages)
 {
 	struct nfs_inode *nfsi = NFS_I(inode);
 	int res = 0;
@@ -588,40 +584,12 @@ nfs_scan_commit(struct inode *inode, struct list_head *dst, unsigned long idx_st
 	return res;
 }
 #else
-static inline int nfs_scan_commit(struct inode *inode, struct list_head *dst, unsigned long idx_start, unsigned int npages)
+static inline int nfs_scan_commit(struct inode *inode, struct list_head *dst, pgoff_t idx_start, unsigned int npages)
 {
 	return 0;
 }
 #endif
 
-static int nfs_wait_on_write_congestion(struct address_space *mapping)
-{
-	struct inode *inode = mapping->host;
-	struct backing_dev_info *bdi = mapping->backing_dev_info;
-	int ret = 0;
-
-	might_sleep();
-
-	if (!bdi_write_congested(bdi))
-		return 0;
-
-	nfs_inc_stats(inode, NFSIOS_CONGESTIONWAIT);
-
-	do {
-		struct rpc_clnt *clnt = NFS_CLIENT(inode);
-		sigset_t oldset;
-
-		rpc_clnt_sigmask(clnt, &oldset);
-		ret = congestion_wait_interruptible(WRITE, HZ/10);
-		rpc_clnt_sigunmask(clnt, &oldset);
-		if (ret == -ERESTARTSYS)
-			break;
-		ret = 0;
-	} while (bdi_write_congested(bdi));
-
-	return ret;
-}
-
 /*
  * Try to update any existing write request, or create one if there is none.
  * In order to match, the request's credentials must match those of
@@ -636,12 +604,10 @@ static struct nfs_page * nfs_update_request(struct nfs_open_context* ctx,
 	struct inode *inode = mapping->host;
 	struct nfs_inode *nfsi = NFS_I(inode);
 	struct nfs_page		*req, *new = NULL;
-	unsigned long		rqend, end;
+	pgoff_t		rqend, end;
 
 	end = offset + bytes;
 
-	if (nfs_wait_on_write_congestion(mapping))
-		return ERR_PTR(-ERESTARTSYS);
 	for (;;) {
 		/* Loop over all inode entries and see if we find
 		 * A request for the page we wish to update
@@ -865,7 +831,7 @@ static void nfs_execute_write(struct nfs_write_data *data)
  * Generate multiple small requests to write out a single
  * contiguous dirty area on one page.
  */
-static int nfs_flush_multi(struct inode *inode, struct list_head *head, int how)
+static int nfs_flush_multi(struct inode *inode, struct list_head *head, unsigned int npages, size_t count, int how)
 {
 	struct nfs_page *req = nfs_list_entry(head->next);
 	struct page *page = req->wb_page;
@@ -877,11 +843,11 @@ static int nfs_flush_multi(struct inode *inode, struct list_head *head, int how)
 
 	nfs_list_remove_request(req);
 
-	nbytes = req->wb_bytes;
+	nbytes = count;
 	do {
 		size_t len = min(nbytes, wsize);
 
-		data = nfs_writedata_alloc(len);
+		data = nfs_writedata_alloc(1);
 		if (!data)
 			goto out_bad;
 		list_add(&data->pages, &list);
@@ -892,23 +858,19 @@ static int nfs_flush_multi(struct inode *inode, struct list_head *head, int how)
 
 	ClearPageError(page);
 	offset = 0;
-	nbytes = req->wb_bytes;
+	nbytes = count;
 	do {
 		data = list_entry(list.next, struct nfs_write_data, pages);
 		list_del_init(&data->pages);
 
 		data->pagevec[0] = page;
 
-		if (nbytes > wsize) {
-			nfs_write_rpcsetup(req, data, &nfs_write_partial_ops,
-					wsize, offset, how);
-			offset += wsize;
-			nbytes -= wsize;
-		} else {
-			nfs_write_rpcsetup(req, data, &nfs_write_partial_ops,
-					nbytes, offset, how);
-			nbytes = 0;
-		}
+		if (nbytes < wsize)
+			wsize = nbytes;
+		nfs_write_rpcsetup(req, data, &nfs_write_partial_ops,
+				   wsize, offset, how);
+		offset += wsize;
+		nbytes -= wsize;
 		nfs_execute_write(data);
 	} while (nbytes != 0);
 
@@ -934,26 +896,23 @@ out_bad:
  * This is the case if nfs_updatepage detects a conflicting request
  * that has been written but not committed.
  */
-static int nfs_flush_one(struct inode *inode, struct list_head *head, int how)
+static int nfs_flush_one(struct inode *inode, struct list_head *head, unsigned int npages, size_t count, int how)
 {
 	struct nfs_page		*req;
 	struct page		**pages;
 	struct nfs_write_data	*data;
-	unsigned int		count;
 
-	data = nfs_writedata_alloc(NFS_SERVER(inode)->wsize);
+	data = nfs_writedata_alloc(npages);
 	if (!data)
 		goto out_bad;
 
 	pages = data->pagevec;
-	count = 0;
 	while (!list_empty(head)) {
 		req = nfs_list_entry(head->next);
 		nfs_list_remove_request(req);
 		nfs_list_add_request(req, &data->pages);
 		ClearPageError(req->wb_page);
 		*pages++ = req->wb_page;
-		count += req->wb_bytes;
 	}
 	req = nfs_list_entry(data->pages.next);
 
@@ -973,40 +932,15 @@ static int nfs_flush_one(struct inode *inode, struct list_head *head, int how)
 	return -ENOMEM;
 }
 
-static int nfs_flush_list(struct inode *inode, struct list_head *head, int npages, int how)
+static void nfs_pageio_init_write(struct nfs_pageio_descriptor *pgio,
+				  struct inode *inode, int ioflags)
 {
-	LIST_HEAD(one_request);
-	int (*flush_one)(struct inode *, struct list_head *, int);
-	struct nfs_page	*req;
-	int wpages = NFS_SERVER(inode)->wpages;
 	int wsize = NFS_SERVER(inode)->wsize;
-	int error;
 
-	flush_one = nfs_flush_one;
 	if (wsize < PAGE_CACHE_SIZE)
-		flush_one = nfs_flush_multi;
-	/* For single writes, FLUSH_STABLE is more efficient */
-	if (npages <= wpages && npages == NFS_I(inode)->npages
-			&& nfs_list_entry(head->next)->wb_bytes <= wsize)
-		how |= FLUSH_STABLE;
-
-	do {
-		nfs_coalesce_requests(head, &one_request, wpages);
-		req = nfs_list_entry(one_request.next);
-		error = flush_one(inode, &one_request, how);
-		if (error < 0)
-			goto out_err;
-	} while (!list_empty(head));
-	return 0;
-out_err:
-	while (!list_empty(head)) {
-		req = nfs_list_entry(head->next);
-		nfs_list_remove_request(req);
-		nfs_redirty_request(req);
-		nfs_end_page_writeback(req->wb_page);
-		nfs_clear_page_writeback(req);
-	}
-	return error;
+		nfs_pageio_init(pgio, inode, nfs_flush_multi, wsize, ioflags);
+	else
+		nfs_pageio_init(pgio, inode, nfs_flush_one, wsize, ioflags);
 }
 
 /*
@@ -1330,31 +1264,7 @@ static const struct rpc_call_ops nfs_commit_ops = {
 	.rpc_call_done = nfs_commit_done,
 	.rpc_release = nfs_commit_release,
 };
-#else
-static inline int nfs_commit_list(struct inode *inode, struct list_head *head, int how)
-{
-	return 0;
-}
-#endif
-
-static long nfs_flush_mapping(struct address_space *mapping, struct writeback_control *wbc, int how)
-{
-	struct nfs_inode *nfsi = NFS_I(mapping->host);
-	LIST_HEAD(head);
-	long res;
-
-	spin_lock(&nfsi->req_lock);
-	res = nfs_scan_dirty(mapping, wbc, &head);
-	spin_unlock(&nfsi->req_lock);
-	if (res) {
-		int error = nfs_flush_list(mapping->host, &head, res, how);
-		if (error < 0)
-			return error;
-	}
-	return res;
-}
 
-#if defined(CONFIG_NFS_V3) || defined(CONFIG_NFS_V4)
 int nfs_commit_inode(struct inode *inode, int how)
 {
 	struct nfs_inode *nfsi = NFS_I(inode);
@@ -1371,13 +1281,18 @@ int nfs_commit_inode(struct inode *inode, int how)
 	}
 	return res;
 }
+#else
+static inline int nfs_commit_list(struct inode *inode, struct list_head *head, int how)
+{
+	return 0;
+}
 #endif
 
 long nfs_sync_mapping_wait(struct address_space *mapping, struct writeback_control *wbc, int how)
 {
 	struct inode *inode = mapping->host;
 	struct nfs_inode *nfsi = NFS_I(inode);
-	unsigned long idx_start, idx_end;
+	pgoff_t idx_start, idx_end;
 	unsigned int npages = 0;
 	LIST_HEAD(head);
 	int nocommit = how & FLUSH_NOCOMMIT;
@@ -1390,41 +1305,24 @@ long nfs_sync_mapping_wait(struct address_space *mapping, struct writeback_contr
 		idx_start = wbc->range_start >> PAGE_CACHE_SHIFT;
 		idx_end = wbc->range_end >> PAGE_CACHE_SHIFT;
 		if (idx_end > idx_start) {
-			unsigned long l_npages = 1 + idx_end - idx_start;
+			pgoff_t l_npages = 1 + idx_end - idx_start;
 			npages = l_npages;
 			if (sizeof(npages) != sizeof(l_npages) &&
-					(unsigned long)npages != l_npages)
+					(pgoff_t)npages != l_npages)
 				npages = 0;
 		}
 	}
 	how &= ~FLUSH_NOCOMMIT;
 	spin_lock(&nfsi->req_lock);
 	do {
-		wbc->pages_skipped = 0;
 		ret = nfs_wait_on_requests_locked(inode, idx_start, npages);
 		if (ret != 0)
 			continue;
-		pages = nfs_scan_dirty(mapping, wbc, &head);
-		if (pages != 0) {
-			spin_unlock(&nfsi->req_lock);
-			if (how & FLUSH_INVALIDATE) {
-				nfs_cancel_dirty_list(&head);
-				ret = pages;
-			} else
-				ret = nfs_flush_list(inode, &head, pages, how);
-			spin_lock(&nfsi->req_lock);
-			continue;
-		}
-		if (wbc->pages_skipped != 0)
-			continue;
 		if (nocommit)
 			break;
 		pages = nfs_scan_commit(inode, &head, idx_start, npages);
-		if (pages == 0) {
-			if (wbc->pages_skipped != 0)
-				continue;
+		if (pages == 0)
 			break;
-		}
 		if (how & FLUSH_INVALIDATE) {
 			spin_unlock(&nfsi->req_lock);
 			nfs_cancel_commit_list(&head);
@@ -1456,7 +1354,7 @@ int nfs_wb_all(struct inode *inode)
 	};
 	int ret;
 
-	ret = generic_writepages(mapping, &wbc);
+	ret = nfs_writepages(mapping, &wbc);
 	if (ret < 0)
 		goto out;
 	ret = nfs_sync_mapping_wait(mapping, &wbc, 0);
@@ -1479,11 +1377,9 @@ int nfs_sync_mapping_range(struct address_space *mapping, loff_t range_start, lo
 	};
 	int ret;
 
-	if (!(how & FLUSH_NOWRITEPAGE)) {
-		ret = generic_writepages(mapping, &wbc);
-		if (ret < 0)
-			goto out;
-	}
+	ret = nfs_writepages(mapping, &wbc);
+	if (ret < 0)
+		goto out;
 	ret = nfs_sync_mapping_wait(mapping, &wbc, how);
 	if (ret >= 0)
 		return 0;
@@ -1506,7 +1402,7 @@ int nfs_wb_page_priority(struct inode *inode, struct page *page, int how)
 	int ret;
 
 	BUG_ON(!PageLocked(page));
-	if (!(how & FLUSH_NOWRITEPAGE) && clear_page_dirty_for_io(page)) {
+	if (clear_page_dirty_for_io(page)) {
 		ret = nfs_writepage_locked(page, &wbc);
 		if (ret < 0)
 			goto out;
@@ -1531,10 +1427,18 @@ int nfs_wb_page(struct inode *inode, struct page* page)
 
 int nfs_set_page_dirty(struct page *page)
 {
-	spinlock_t *req_lock = &NFS_I(page->mapping->host)->req_lock;
+	struct address_space *mapping = page->mapping;
+	struct inode *inode;
+	spinlock_t *req_lock;
 	struct nfs_page *req;
 	int ret;
 
+	if (!mapping)
+		goto out_raced;
+	inode = mapping->host;
+	if (!inode)
+		goto out_raced;
+	req_lock = &NFS_I(inode)->req_lock;
 	spin_lock(req_lock);
 	req = nfs_page_find_request_locked(page);
 	if (req != NULL) {
@@ -1547,6 +1451,8 @@ int nfs_set_page_dirty(struct page *page)
 	ret = __set_page_dirty_nobuffers(page);
 	spin_unlock(req_lock);
 	return ret;
+out_raced:
+	return !TestSetPageDirty(page);
 }
 
 
diff --git a/fs/nfsd/nfs4callback.c b/fs/nfsd/nfs4callback.c
index fb14d68eaca..32ffea033c7 100644
--- a/fs/nfsd/nfs4callback.c
+++ b/fs/nfsd/nfs4callback.c
@@ -315,16 +315,13 @@ out:
 /*
  * RPC procedure tables
  */
-#ifndef MAX
-# define MAX(a, b)      (((a) > (b))? (a) : (b))
-#endif
-
 #define PROC(proc, call, argtype, restype)                              \
 [NFSPROC4_CLNT_##proc] = {                                      	\
         .p_proc   = NFSPROC4_CB_##call,					\
         .p_encode = (kxdrproc_t) nfs4_xdr_##argtype,                    \
         .p_decode = (kxdrproc_t) nfs4_xdr_##restype,                    \
-        .p_bufsiz = MAX(NFS4_##argtype##_sz,NFS4_##restype##_sz) << 2,  \
+        .p_arglen = NFS4_##argtype##_sz,                                \
+        .p_replen = NFS4_##restype##_sz,                                \
         .p_statidx = NFSPROC4_CB_##call,				\
 	.p_name   = #proc,                                              \
 }