From 0b524123c93893391ec9e6c9b04998a45235f9c8 Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Sun, 9 Aug 2009 15:09:30 -0400
Subject: NFS: Add ability to send MOUNTPROC_UMNT to the kernel's mountd client

After certain failure modes of an NFS mount, an NFS client should send
a MOUNTPROC_UMNT request to remove the just-added mount entry from the
server's mount table.  While no-one should rely on the accuracy of the
server's mount table, sending a UMNT is simply being a good internet
neighbor.

Since NFS mount processing is handled in the kernel now, we will need
a function in the kernel's mountd client that can post a MOUNTRPC_UMNT
request, in order to handle these failure modes.

Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
---
 fs/nfs/internal.h | 1 +
 1 file changed, 1 insertion(+)

(limited to 'fs/nfs/internal.h')

diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h
index 7dd90a6769d0..8d2b71d57d29 100644
--- a/fs/nfs/internal.h
+++ b/fs/nfs/internal.h
@@ -102,6 +102,7 @@ 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;
-- 
cgit v1.2.3


From a02d692611348f11ee1bc37431a883c3ff2de23e Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Sun, 9 Aug 2009 15:09:34 -0400
Subject: SUNRPC: Provide functions for managing universal addresses

Introduce a set of functions in the kernel's RPC implementation for
converting between a socket address and either a standard
presentation address string or an RPC universal address.

The universal address functions will be used to encode and decode
RPCB_FOO and NFSv4 SETCLIENTID arguments.  The other functions are
part of a previous promise to deliver shared functions that can be
used by upper-layer protocols to display and manipulate IP
addresses.

The kernel's current address printf formatters were designed
specifically for kernel to user-space APIs that require a particular
string format for socket addresses, thus are somewhat limited for the
purposes of sunrpc.ko.  The formatter for IPv6 addresses, %pI6, does
not support short-handing or scope IDs.  Also, these printf formatters
are unique per address family, so a separate formatter string is
required for printing AF_INET and AF_INET6 addresses.

Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
---
 fs/nfs/internal.h           |   2 -
 include/linux/sunrpc/clnt.h |  38 +++++
 net/sunrpc/Makefile         |   2 +-
 net/sunrpc/addr.c           | 364 ++++++++++++++++++++++++++++++++++++++++++++
 4 files changed, 403 insertions(+), 3 deletions(-)
 create mode 100644 net/sunrpc/addr.c

(limited to 'fs/nfs/internal.h')

diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h
index 8d2b71d57d29..ff68397f9b19 100644
--- a/fs/nfs/internal.h
+++ b/fs/nfs/internal.h
@@ -370,8 +370,6 @@ unsigned int nfs_page_array_len(unsigned int base, size_t len)
 		PAGE_SIZE - 1) >> PAGE_SHIFT;
 }
 
-#define IPV6_SCOPE_DELIMITER	'%'
-
 /*
  * Set the port number in an address.  Be agnostic about the address
  * family.
diff --git a/include/linux/sunrpc/clnt.h b/include/linux/sunrpc/clnt.h
index 37881f1a0bd7..2636e8ad551c 100644
--- a/include/linux/sunrpc/clnt.h
+++ b/include/linux/sunrpc/clnt.h
@@ -9,6 +9,10 @@
 #ifndef _LINUX_SUNRPC_CLNT_H
 #define _LINUX_SUNRPC_CLNT_H
 
+#include <linux/socket.h>
+#include <linux/in.h>
+#include <linux/in6.h>
+
 #include <linux/sunrpc/msg_prot.h>
 #include <linux/sunrpc/sched.h>
 #include <linux/sunrpc/xprt.h>
@@ -151,5 +155,39 @@ void		rpc_force_rebind(struct rpc_clnt *);
 size_t		rpc_peeraddr(struct rpc_clnt *, struct sockaddr *, size_t);
 const char	*rpc_peeraddr2str(struct rpc_clnt *, enum rpc_display_format_t);
 
+size_t		rpc_ntop(const struct sockaddr *, char *, const size_t);
+size_t		rpc_pton(const char *, const size_t,
+			 struct sockaddr *, const size_t);
+char *		rpc_sockaddr2uaddr(const struct sockaddr *);
+size_t		rpc_uaddr2sockaddr(const char *, const size_t,
+				   struct sockaddr *, const size_t);
+
+static inline unsigned short rpc_get_port(const struct sockaddr *sap)
+{
+	switch (sap->sa_family) {
+	case AF_INET:
+		return ntohs(((struct sockaddr_in *)sap)->sin_port);
+	case AF_INET6:
+		return ntohs(((struct sockaddr_in6 *)sap)->sin6_port);
+	}
+	return 0;
+}
+
+static inline void rpc_set_port(struct sockaddr *sap,
+				const unsigned short port)
+{
+	switch (sap->sa_family) {
+	case AF_INET:
+		((struct sockaddr_in *)sap)->sin_port = htons(port);
+		break;
+	case AF_INET6:
+		((struct sockaddr_in6 *)sap)->sin6_port = htons(port);
+		break;
+	}
+}
+
+#define IPV6_SCOPE_DELIMITER		'%'
+#define IPV6_SCOPE_ID_LEN		sizeof("%nnnnnnnnnn")
+
 #endif /* __KERNEL__ */
 #endif /* _LINUX_SUNRPC_CLNT_H */
diff --git a/net/sunrpc/Makefile b/net/sunrpc/Makefile
index db73fd2a3f0e..9d2fca5ad14a 100644
--- a/net/sunrpc/Makefile
+++ b/net/sunrpc/Makefile
@@ -10,7 +10,7 @@ obj-$(CONFIG_SUNRPC_XPRT_RDMA) += xprtrdma/
 sunrpc-y := clnt.o xprt.o socklib.o xprtsock.o sched.o \
 	    auth.o auth_null.o auth_unix.o auth_generic.o \
 	    svc.o svcsock.o svcauth.o svcauth_unix.o \
-	    rpcb_clnt.o timer.o xdr.o \
+	    addr.o rpcb_clnt.o timer.o xdr.o \
 	    sunrpc_syms.o cache.o rpc_pipe.o \
 	    svc_xprt.o
 sunrpc-$(CONFIG_NFS_V4_1) += backchannel_rqst.o bc_svc.o
diff --git a/net/sunrpc/addr.c b/net/sunrpc/addr.c
new file mode 100644
index 000000000000..22e8fd89477f
--- /dev/null
+++ b/net/sunrpc/addr.c
@@ -0,0 +1,364 @@
+/*
+ * Copyright 2009, Oracle.  All rights reserved.
+ *
+ * Convert socket addresses to presentation addresses and universal
+ * addresses, and vice versa.
+ *
+ * Universal addresses are introduced by RFC 1833 and further refined by
+ * recent RFCs describing NFSv4.  The universal address format is part
+ * of the external (network) interface provided by rpcbind version 3
+ * and 4, and by NFSv4.  Such an address is a string containing a
+ * presentation format IP address followed by a port number in
+ * "hibyte.lobyte" format.
+ *
+ * IPv6 addresses can also include a scope ID, typically denoted by
+ * a '%' followed by a device name or a non-negative integer.  Refer to
+ * RFC 4291, Section 2.2 for details on IPv6 presentation formats.
+ */
+
+#include <net/ipv6.h>
+#include <linux/sunrpc/clnt.h>
+
+#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+
+static size_t rpc_ntop6_noscopeid(const struct sockaddr *sap,
+				  char *buf, const int buflen)
+{
+	const struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *)sap;
+	const struct in6_addr *addr = &sin6->sin6_addr;
+
+	/*
+	 * RFC 4291, Section 2.2.2
+	 *
+	 * Shorthanded ANY address
+	 */
+	if (ipv6_addr_any(addr))
+		return snprintf(buf, buflen, "::");
+
+	/*
+	 * RFC 4291, Section 2.2.2
+	 *
+	 * Shorthanded loopback address
+	 */
+	if (ipv6_addr_loopback(addr))
+		return snprintf(buf, buflen, "::1");
+
+	/*
+	 * RFC 4291, Section 2.2.3
+	 *
+	 * Special presentation address format for mapped v4
+	 * addresses.
+	 */
+	if (ipv6_addr_v4mapped(addr))
+		return snprintf(buf, buflen, "::ffff:%pI4",
+					&addr->s6_addr32[3]);
+
+	/*
+	 * RFC 4291, Section 2.2.1
+	 *
+	 * To keep the result as short as possible, especially
+	 * since we don't shorthand, we don't want leading zeros
+	 * in each halfword, so avoid %pI6.
+	 */
+	return snprintf(buf, buflen, "%x:%x:%x:%x:%x:%x:%x:%x",
+		ntohs(addr->s6_addr16[0]), ntohs(addr->s6_addr16[1]),
+		ntohs(addr->s6_addr16[2]), ntohs(addr->s6_addr16[3]),
+		ntohs(addr->s6_addr16[4]), ntohs(addr->s6_addr16[5]),
+		ntohs(addr->s6_addr16[6]), ntohs(addr->s6_addr16[7]));
+}
+
+static size_t rpc_ntop6(const struct sockaddr *sap,
+			char *buf, const size_t buflen)
+{
+	const struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *)sap;
+	char scopebuf[IPV6_SCOPE_ID_LEN];
+	size_t len;
+	int rc;
+
+	len = rpc_ntop6_noscopeid(sap, buf, buflen);
+	if (unlikely(len == 0))
+		return len;
+
+	if (!(ipv6_addr_type(&sin6->sin6_addr) & IPV6_ADDR_LINKLOCAL) &&
+	    !(ipv6_addr_type(&sin6->sin6_addr) & IPV6_ADDR_SITELOCAL))
+		return len;
+
+	rc = snprintf(scopebuf, sizeof(scopebuf), "%c%u",
+			IPV6_SCOPE_DELIMITER, sin6->sin6_scope_id);
+	if (unlikely((size_t)rc > sizeof(scopebuf)))
+		return 0;
+
+	len += rc;
+	if (unlikely(len > buflen))
+		return 0;
+
+	strcat(buf, scopebuf);
+	return len;
+}
+
+#else	/* !(defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)) */
+
+static size_t rpc_ntop6_noscopeid(const struct sockaddr *sap,
+				  char *buf, const int buflen)
+{
+	return 0;
+}
+
+static size_t rpc_ntop6(const struct sockaddr *sap,
+			char *buf, const size_t buflen)
+{
+	return 0;
+}
+
+#endif	/* !(defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)) */
+
+static int rpc_ntop4(const struct sockaddr *sap,
+		     char *buf, const size_t buflen)
+{
+	const struct sockaddr_in *sin = (struct sockaddr_in *)sap;
+
+	return snprintf(buf, buflen, "%pI4", &sin->sin_addr);
+}
+
+/**
+ * rpc_ntop - construct a presentation address in @buf
+ * @sap: socket address
+ * @buf: construction area
+ * @buflen: size of @buf, in bytes
+ *
+ * Plants a %NUL-terminated string in @buf and returns the length
+ * of the string, excluding the %NUL.  Otherwise zero is returned.
+ */
+size_t rpc_ntop(const struct sockaddr *sap, char *buf, const size_t buflen)
+{
+	switch (sap->sa_family) {
+	case AF_INET:
+		return rpc_ntop4(sap, buf, buflen);
+	case AF_INET6:
+		return rpc_ntop6(sap, buf, buflen);
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(rpc_ntop);
+
+static size_t rpc_pton4(const char *buf, const size_t buflen,
+			struct sockaddr *sap, const size_t salen)
+{
+	struct sockaddr_in *sin = (struct sockaddr_in *)sap;
+	u8 *addr = (u8 *)&sin->sin_addr.s_addr;
+
+	if (buflen > INET_ADDRSTRLEN || salen < sizeof(struct sockaddr_in))
+		return 0;
+
+	memset(sap, 0, sizeof(struct sockaddr_in));
+
+	if (in4_pton(buf, buflen, addr, '\0', NULL) == 0)
+		return 0;
+
+	sin->sin_family = AF_INET;
+	return sizeof(struct sockaddr_in);;
+}
+
+#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+static int rpc_parse_scope_id(const char *buf, const size_t buflen,
+			      const char *delim, struct sockaddr_in6 *sin6)
+{
+	char *p;
+	size_t len;
+
+	if ((buf + buflen) == delim)
+		return 1;
+
+	if (*delim != IPV6_SCOPE_DELIMITER)
+		return 0;
+
+	if (!(ipv6_addr_type(&sin6->sin6_addr) & IPV6_ADDR_LINKLOCAL) &&
+	    !(ipv6_addr_type(&sin6->sin6_addr) & IPV6_ADDR_SITELOCAL))
+		return 0;
+
+	len = (buf + buflen) - delim - 1;
+	p = kstrndup(delim + 1, len, GFP_KERNEL);
+	if (p) {
+		unsigned long scope_id = 0;
+		struct net_device *dev;
+
+		dev = dev_get_by_name(&init_net, p);
+		if (dev != NULL) {
+			scope_id = dev->ifindex;
+			dev_put(dev);
+		} else {
+			if (strict_strtoul(p, 10, &scope_id) == 0) {
+				kfree(p);
+				return 0;
+			}
+		}
+
+		kfree(p);
+
+		sin6->sin6_scope_id = scope_id;
+		return 1;
+	}
+
+	return 0;
+}
+
+static size_t rpc_pton6(const char *buf, const size_t buflen,
+			struct sockaddr *sap, const size_t salen)
+{
+	struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *)sap;
+	u8 *addr = (u8 *)&sin6->sin6_addr.in6_u;
+	const char *delim;
+
+	if (buflen > (INET6_ADDRSTRLEN + IPV6_SCOPE_ID_LEN) ||
+	    salen < sizeof(struct sockaddr_in6))
+		return 0;
+
+	memset(sap, 0, sizeof(struct sockaddr_in6));
+
+	if (in6_pton(buf, buflen, addr, IPV6_SCOPE_DELIMITER, &delim) == 0)
+		return 0;
+
+	if (!rpc_parse_scope_id(buf, buflen, delim, sin6))
+		return 0;
+
+	sin6->sin6_family = AF_INET6;
+	return sizeof(struct sockaddr_in6);
+}
+#else
+static size_t rpc_pton6(const char *buf, const size_t buflen,
+			struct sockaddr *sap, const size_t salen)
+{
+	return 0;
+}
+#endif
+
+/**
+ * rpc_pton - Construct a sockaddr in @sap
+ * @buf: C string containing presentation format IP address
+ * @buflen: length of presentation address in bytes
+ * @sap: buffer into which to plant socket address
+ * @salen: size of buffer in bytes
+ *
+ * Returns the size of the socket address if successful; otherwise
+ * zero is returned.
+ *
+ * Plants a socket address in @sap and returns the size of the
+ * socket address, if successful.  Returns zero if an error
+ * occurred.
+ */
+size_t rpc_pton(const char *buf, const size_t buflen,
+		struct sockaddr *sap, const size_t salen)
+{
+	unsigned int i;
+
+	for (i = 0; i < buflen; i++)
+		if (buf[i] == ':')
+			return rpc_pton6(buf, buflen, sap, salen);
+	return rpc_pton4(buf, buflen, sap, salen);
+}
+EXPORT_SYMBOL_GPL(rpc_pton);
+
+/**
+ * rpc_sockaddr2uaddr - Construct a universal address string from @sap.
+ * @sap: socket address
+ *
+ * Returns a %NUL-terminated string in dynamically allocated memory;
+ * otherwise NULL is returned if an error occurred.  Caller must
+ * free the returned string.
+ */
+char *rpc_sockaddr2uaddr(const struct sockaddr *sap)
+{
+	char portbuf[RPCBIND_MAXUADDRPLEN];
+	char addrbuf[RPCBIND_MAXUADDRLEN];
+	unsigned short port;
+
+	switch (sap->sa_family) {
+	case AF_INET:
+		if (rpc_ntop4(sap, addrbuf, sizeof(addrbuf)) == 0)
+			return NULL;
+		port = ntohs(((struct sockaddr_in *)sap)->sin_port);
+		break;
+	case AF_INET6:
+		if (rpc_ntop6_noscopeid(sap, addrbuf, sizeof(addrbuf)) == 0)
+			return NULL;
+		port = ntohs(((struct sockaddr_in6 *)sap)->sin6_port);
+		break;
+	default:
+		return NULL;
+	}
+
+	if (snprintf(portbuf, sizeof(portbuf),
+		     ".%u.%u", port >> 8, port & 0xff) > (int)sizeof(portbuf))
+		return NULL;
+
+	if (strlcat(addrbuf, portbuf, sizeof(addrbuf)) > sizeof(addrbuf))
+		return NULL;
+
+	return kstrdup(addrbuf, GFP_KERNEL);
+}
+EXPORT_SYMBOL_GPL(rpc_sockaddr2uaddr);
+
+/**
+ * rpc_uaddr2sockaddr - convert a universal address to a socket address.
+ * @uaddr: C string containing universal address to convert
+ * @uaddr_len: length of universal address string
+ * @sap: buffer into which to plant socket address
+ * @salen: size of buffer
+ *
+ * Returns the size of the socket address if successful; otherwise
+ * zero is returned.
+ */
+size_t rpc_uaddr2sockaddr(const char *uaddr, const size_t uaddr_len,
+			  struct sockaddr *sap, const size_t salen)
+{
+	char *c, buf[RPCBIND_MAXUADDRLEN];
+	unsigned long portlo, porthi;
+	unsigned short port;
+
+	if (uaddr_len > sizeof(buf))
+		return 0;
+
+	memcpy(buf, uaddr, uaddr_len);
+
+	buf[uaddr_len] = '\n';
+	buf[uaddr_len + 1] = '\0';
+
+	c = strrchr(buf, '.');
+	if (unlikely(c == NULL))
+		return 0;
+	if (unlikely(strict_strtoul(c + 1, 10, &portlo) != 0))
+		return 0;
+	if (unlikely(portlo > 255))
+		return 0;
+
+	c[0] = '\n';
+	c[1] = '\0';
+
+	c = strrchr(buf, '.');
+	if (unlikely(c == NULL))
+		return 0;
+	if (unlikely(strict_strtoul(c + 1, 10, &porthi) != 0))
+		return 0;
+	if (unlikely(porthi > 255))
+		return 0;
+
+	port = (unsigned short)((porthi << 8) | portlo);
+
+	c[0] = '\0';
+
+	if (rpc_pton(buf, strlen(buf), sap, salen) == 0)
+		return 0;
+
+	switch (sap->sa_family) {
+	case AF_INET:
+		((struct sockaddr_in *)sap)->sin_port = htons(port);
+		return sizeof(struct sockaddr_in);
+	case AF_INET6:
+		((struct sockaddr_in6 *)sap)->sin6_port = htons(port);
+		return sizeof(struct sockaddr_in6);
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(rpc_uaddr2sockaddr);
-- 
cgit v1.2.3


From 53a0b9c4c99ab0085a06421f71592722e5b3fd5f Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Sun, 9 Aug 2009 15:09:36 -0400
Subject: NFS: Replace nfs_parse_ip_address() with rpc_pton()

Clean up: Use the common routine now provided in sunrpc.ko for parsing mount
addresses.

Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
---
 fs/nfs/internal.h      |   1 -
 fs/nfs/nfs4namespace.c |   6 +-
 fs/nfs/super.c         | 148 +++++++------------------------------------------
 3 files changed, 22 insertions(+), 133 deletions(-)

(limited to 'fs/nfs/internal.h')

diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h
index ff68397f9b19..cf1da3e22004 100644
--- a/fs/nfs/internal.h
+++ b/fs/nfs/internal.h
@@ -214,7 +214,6 @@ 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;
diff --git a/fs/nfs/nfs4namespace.c b/fs/nfs/nfs4namespace.c
index 2a2a0a7143ad..43c86b7556e1 100644
--- a/fs/nfs/nfs4namespace.c
+++ b/fs/nfs/nfs4namespace.c
@@ -121,9 +121,9 @@ 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 = rpc_pton(buf->data, buf->len,
+				mountdata->addr, mountdata->addrlen);
+		if (mountdata->addrlen == 0)
 			continue;
 		nfs_set_port(mountdata->addr, NFS_PORT);
 
diff --git a/fs/nfs/super.c b/fs/nfs/super.c
index 8526008eba72..1eeba8e53802 100644
--- a/fs/nfs/super.c
+++ b/fs/nfs/super.c
@@ -742,129 +742,10 @@ static int nfs_verify_server_address(struct sockaddr *addr)
 	}
 	}
 
+	dfprintk(MOUNT, "NFS: Invalid IP address specified\n");
 	return 0;
 }
 
-static void nfs_parse_ipv4_address(char *string, size_t str_len,
-				   struct sockaddr *sap, size_t *addr_len)
-{
-	struct sockaddr_in *sin = (struct sockaddr_in *)sap;
-	u8 *addr = (u8 *)&sin->sin_addr.s_addr;
-
-	if (str_len <= INET_ADDRSTRLEN) {
-		dfprintk(MOUNT, "NFS: parsing IPv4 address %*s\n",
-				(int)str_len, string);
-
-		sin->sin_family = AF_INET;
-		*addr_len = sizeof(*sin);
-		if (in4_pton(string, str_len, addr, '\0', NULL))
-			return;
-	}
-
-	sap->sa_family = AF_UNSPEC;
-	*addr_len = 0;
-}
-
-#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
-static int nfs_parse_ipv6_scope_id(const char *string, const size_t str_len,
-				   const char *delim,
-				   struct sockaddr_in6 *sin6)
-{
-	char *p;
-	size_t len;
-
-	if ((string + str_len) == delim)
-		return 1;
-
-	if (*delim != IPV6_SCOPE_DELIMITER)
-		return 0;
-
-	if (!(ipv6_addr_type(&sin6->sin6_addr) & IPV6_ADDR_LINKLOCAL))
-		return 0;
-
-	len = (string + str_len) - delim - 1;
-	p = kstrndup(delim + 1, len, GFP_KERNEL);
-	if (p) {
-		unsigned long scope_id = 0;
-		struct net_device *dev;
-
-		dev = dev_get_by_name(&init_net, p);
-		if (dev != NULL) {
-			scope_id = dev->ifindex;
-			dev_put(dev);
-		} else {
-			if (strict_strtoul(p, 10, &scope_id) == 0) {
-				kfree(p);
-				return 0;
-			}
-		}
-
-		kfree(p);
-
-		sin6->sin6_scope_id = scope_id;
-		dfprintk(MOUNT, "NFS: IPv6 scope ID = %lu\n", scope_id);
-		return 1;
-	}
-
-	return 0;
-}
-
-static void nfs_parse_ipv6_address(char *string, size_t str_len,
-				   struct sockaddr *sap, size_t *addr_len)
-{
-	struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *)sap;
-	u8 *addr = (u8 *)&sin6->sin6_addr.in6_u;
-	const char *delim;
-
-	if (str_len <= INET6_ADDRSTRLEN) {
-		dfprintk(MOUNT, "NFS: parsing IPv6 address %*s\n",
-				(int)str_len, string);
-
-		sin6->sin6_family = AF_INET6;
-		*addr_len = sizeof(*sin6);
-		if (in6_pton(string, str_len, addr,
-					IPV6_SCOPE_DELIMITER, &delim) != 0) {
-			if (nfs_parse_ipv6_scope_id(string, str_len,
-							delim, sin6) != 0)
-				return;
-		}
-	}
-
-	sap->sa_family = AF_UNSPEC;
-	*addr_len = 0;
-}
-#else
-static void nfs_parse_ipv6_address(char *string, size_t str_len,
-				   struct sockaddr *sap, size_t *addr_len)
-{
-	sap->sa_family = AF_UNSPEC;
-	*addr_len = 0;
-}
-#endif
-
-/*
- * Construct a sockaddr based on the contents of a string that contains
- * an IP address in presentation format.
- *
- * If there is a problem constructing the new sockaddr, set the address
- * family to AF_UNSPEC.
- */
-void nfs_parse_ip_address(char *string, size_t str_len,
-				 struct sockaddr *sap, size_t *addr_len)
-{
-	unsigned int i, colons;
-
-	colons = 0;
-	for (i = 0; i < str_len; i++)
-		if (string[i] == ':')
-			colons++;
-
-	if (colons >= 2)
-		nfs_parse_ipv6_address(string, str_len, sap, addr_len);
-	else
-		nfs_parse_ipv4_address(string, str_len, sap, addr_len);
-}
-
 /*
  * Sanity check the NFS transport protocol.
  *
@@ -1344,11 +1225,14 @@ static int nfs_parse_mount_options(char *raw,
 			string = match_strdup(args);
 			if (string == NULL)
 				goto out_nomem;
-			nfs_parse_ip_address(string, strlen(string),
-					     (struct sockaddr *)
-						&mnt->nfs_server.address,
-					     &mnt->nfs_server.addrlen);
+			mnt->nfs_server.addrlen =
+				rpc_pton(string, strlen(string),
+					(struct sockaddr *)
+					&mnt->nfs_server.address,
+					sizeof(mnt->nfs_server.address));
 			kfree(string);
+			if (mnt->nfs_server.addrlen == 0)
+				goto out_invalid_address;
 			break;
 		case Opt_clientaddr:
 			string = match_strdup(args);
@@ -1368,11 +1252,14 @@ static int nfs_parse_mount_options(char *raw,
 			string = match_strdup(args);
 			if (string == NULL)
 				goto out_nomem;
-			nfs_parse_ip_address(string, strlen(string),
-					     (struct sockaddr *)
-						&mnt->mount_server.address,
-					     &mnt->mount_server.addrlen);
+			mnt->mount_server.addrlen =
+				rpc_pton(string, strlen(string),
+					(struct sockaddr *)
+					&mnt->mount_server.address,
+					sizeof(mnt->mount_server.address));
 			kfree(string);
+			if (mnt->mount_server.addrlen == 0)
+				goto out_invalid_address;
 			break;
 		case Opt_lookupcache:
 			string = match_strdup(args);
@@ -1424,8 +1311,11 @@ static int nfs_parse_mount_options(char *raw,
 
 	return 1;
 
+out_invalid_address:
+	printk(KERN_INFO "NFS: bad IP address specified: %s\n", p);
+	return 0;
 out_invalid_value:
-	printk(KERN_INFO "NFS: bad mount option value specified: %s \n", p);
+	printk(KERN_INFO "NFS: bad mount option value specified: %s\n", p);
 	return 0;
 out_nomem:
 	printk(KERN_INFO "NFS: not enough memory to parse option\n");
-- 
cgit v1.2.3


From ec6ee61250acfccbc5578dd4014735fb2cbe53b5 Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Sun, 9 Aug 2009 15:09:37 -0400
Subject: NFS: Replace nfs_set_port() with rpc_set_port()

Clean up.

Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
---
 fs/nfs/internal.h      | 19 -------------------
 fs/nfs/nfs4namespace.c |  2 +-
 fs/nfs/super.c         |  6 +++---
 3 files changed, 4 insertions(+), 23 deletions(-)

(limited to 'fs/nfs/internal.h')

diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h
index cf1da3e22004..c2f171a3d70e 100644
--- a/fs/nfs/internal.h
+++ b/fs/nfs/internal.h
@@ -368,22 +368,3 @@ unsigned int nfs_page_array_len(unsigned int base, size_t len)
 	return ((unsigned long)len + (unsigned long)base +
 		PAGE_SIZE - 1) >> PAGE_SHIFT;
 }
-
-/*
- * 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;
-	}
-}
diff --git a/fs/nfs/nfs4namespace.c b/fs/nfs/nfs4namespace.c
index 43c86b7556e1..ef22ee89aa77 100644
--- a/fs/nfs/nfs4namespace.c
+++ b/fs/nfs/nfs4namespace.c
@@ -125,7 +125,7 @@ static struct vfsmount *try_location(struct nfs_clone_mount *mountdata,
 				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';
diff --git a/fs/nfs/super.c b/fs/nfs/super.c
index 1eeba8e53802..9c85cdb353aa 100644
--- a/fs/nfs/super.c
+++ b/fs/nfs/super.c
@@ -1409,7 +1409,7 @@ static int nfs_try_mount(struct nfs_parsed_mount_data *args,
 	/*
 	 * autobind will be used if mount_server.port == 0
 	 */
-	nfs_set_port(request.sap, args->mount_server.port);
+	rpc_set_port(request.sap, args->mount_server.port);
 
 	/*
 	 * Now ask the mount server to map our export path
@@ -1703,7 +1703,7 @@ static int nfs_validate_mount_data(void *options,
 						&args->nfs_server.address))
 			goto out_no_address;
 
-		nfs_set_port((struct sockaddr *)&args->nfs_server.address,
+		rpc_set_port((struct sockaddr *)&args->nfs_server.address,
 				args->nfs_server.port);
 
 		nfs_set_mount_transport_protocol(args);
@@ -2336,7 +2336,7 @@ static int nfs4_validate_mount_data(void *options,
 						&args->nfs_server.address))
 			return -EINVAL;
 
-		nfs_set_port((struct sockaddr *)&args->nfs_server.address,
+		rpc_set_port((struct sockaddr *)&args->nfs_server.address,
 				args->nfs_server.port);
 
 		nfs_validate_transport_protocol(args);
-- 
cgit v1.2.3


From 074cc1deec5dee63fcd5d966b36fa4f3765b50fc Mon Sep 17 00:00:00 2001
From: Trond Myklebust <Trond.Myklebust@netapp.com>
Date: Mon, 10 Aug 2009 08:54:13 -0400
Subject: NFS: Add a ->migratepage() aop for NFS

Make NFS a bit more friendly to NUMA and memory hot removal...

Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
---
 fs/nfs/file.c     |  1 +
 fs/nfs/internal.h |  6 ++++
 fs/nfs/write.c    | 91 +++++++++++++++++++++++++++++++++++++++++--------------
 3 files changed, 76 insertions(+), 22 deletions(-)

(limited to 'fs/nfs/internal.h')

diff --git a/fs/nfs/file.c b/fs/nfs/file.c
index 05062329b678..dfc89671dc94 100644
--- a/fs/nfs/file.c
+++ b/fs/nfs/file.c
@@ -479,6 +479,7 @@ 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,
 };
 
diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h
index 7dd90a6769d0..e2ccb4a4398a 100644
--- a/fs/nfs/internal.h
+++ b/fs/nfs/internal.h
@@ -248,6 +248,12 @@ 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,
diff --git a/fs/nfs/write.c b/fs/nfs/write.c
index 0a0a2ff767c3..6240e644f249 100644
--- a/fs/nfs/write.c
+++ b/fs/nfs/write.c
@@ -13,6 +13,7 @@
 #include <linux/file.h>
 #include <linux/writeback.h>
 #include <linux/swap.h>
+#include <linux/migrate.h>
 
 #include <linux/sunrpc/clnt.h>
 #include <linux/nfs_fs.h>
@@ -26,6 +27,7 @@
 #include "internal.h"
 #include "iostat.h"
 #include "nfs4_fs.h"
+#include "fscache.h"
 
 #define NFSDBG_FACILITY		NFSDBG_PAGECACHE
 
@@ -220,24 +222,17 @@ static void nfs_end_page_writeback(struct page *page)
 		clear_bdi_congested(&nfss->backing_dev_info, BLK_RW_ASYNC);
 }
 
-/*
- * Find an associated nfs write request, and prepare to flush it out
- * May return an error if the user signalled nfs_wait_on_request().
- */
-static int nfs_page_async_flush(struct nfs_pageio_descriptor *pgio,
-				struct page *page)
+static struct nfs_page *nfs_find_and_lock_request(struct page *page)
 {
 	struct inode *inode = page->mapping->host;
 	struct nfs_page *req;
 	int ret;
 
 	spin_lock(&inode->i_lock);
-	for(;;) {
+	for (;;) {
 		req = nfs_page_find_request_locked(page);
-		if (req == NULL) {
-			spin_unlock(&inode->i_lock);
-			return 0;
-		}
+		if (req == NULL)
+			break;
 		if (nfs_set_page_tag_locked(req))
 			break;
 		/* Note: If we hold the page lock, as is the case in nfs_writepage,
@@ -249,23 +244,40 @@ static int nfs_page_async_flush(struct nfs_pageio_descriptor *pgio,
 		ret = nfs_wait_on_request(req);
 		nfs_release_request(req);
 		if (ret != 0)
-			return ret;
+			return ERR_PTR(ret);
 		spin_lock(&inode->i_lock);
 	}
-	if (test_bit(PG_CLEAN, &req->wb_flags)) {
-		spin_unlock(&inode->i_lock);
-		BUG();
-	}
-	if (nfs_set_page_writeback(page) != 0) {
-		spin_unlock(&inode->i_lock);
-		BUG();
-	}
 	spin_unlock(&inode->i_lock);
+	return req;
+}
+
+/*
+ * Find an associated nfs write request, and prepare to flush it out
+ * May return an error if the user signalled nfs_wait_on_request().
+ */
+static int nfs_page_async_flush(struct nfs_pageio_descriptor *pgio,
+				struct page *page)
+{
+	struct nfs_page *req;
+	int ret = 0;
+
+	req = nfs_find_and_lock_request(page);
+	if (!req)
+		goto out;
+	ret = PTR_ERR(req);
+	if (IS_ERR(req))
+		goto out;
+
+	ret = nfs_set_page_writeback(page);
+	BUG_ON(ret != 0);
+	BUG_ON(test_bit(PG_CLEAN, &req->wb_flags));
+
 	if (!nfs_pageio_add_request(pgio, req)) {
 		nfs_redirty_request(req);
-		return pgio->pg_error;
+		ret = pgio->pg_error;
 	}
-	return 0;
+out:
+	return ret;
 }
 
 static int nfs_do_writepage(struct page *page, struct writeback_control *wbc, struct nfs_pageio_descriptor *pgio)
@@ -1582,6 +1594,41 @@ int nfs_wb_page(struct inode *inode, struct page* page)
 	return nfs_wb_page_priority(inode, page, FLUSH_STABLE);
 }
 
+#ifdef CONFIG_MIGRATION
+int nfs_migrate_page(struct address_space *mapping, struct page *newpage,
+		struct page *page)
+{
+	struct nfs_page *req;
+	int ret;
+
+	if (PageFsCache(page))
+		nfs_fscache_release_page(page, GFP_KERNEL);
+
+	req = nfs_find_and_lock_request(page);
+	ret = PTR_ERR(req);
+	if (IS_ERR(req))
+		goto out;
+
+	ret = migrate_page(mapping, newpage, page);
+	if (!req)
+		goto out;
+	if (ret)
+		goto out_unlock;
+	page_cache_get(newpage);
+	req->wb_page = newpage;
+	SetPagePrivate(newpage);
+	set_page_private(newpage, page_private(page));
+	ClearPagePrivate(page);
+	set_page_private(page, 0);
+	page_cache_release(page);
+out_unlock:
+	nfs_clear_page_tag_locked(req);
+	nfs_release_request(req);
+out:
+	return ret;
+}
+#endif
+
 int __init nfs_init_writepagecache(void)
 {
 	nfs_wdata_cachep = kmem_cache_create("nfs_write_data",
-- 
cgit v1.2.3


From 4cfd74fc99a41fdc161f243e1c16199656d33ab1 Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Tue, 8 Sep 2009 19:49:47 -0400
Subject: NFS: Mount option parser should detect missing "port="

The meaning of not specifying the "port=" mount option is different
for "-t nfs" and "-t nfs4" mounts.  The default port value for
NFSv2/v3 mounts is 0, but the default for NFSv4 mounts is 2049.

To support "-t nfs -o vers=4", the mount option parser must detect
when "port=" is missing so that the correct default port value can be
set depending on which NFS version is requested.

Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
---
 fs/nfs/internal.h |  9 +++++++--
 fs/nfs/super.c    | 55 +++++++++++++++++++++++++++++--------------------------
 2 files changed, 36 insertions(+), 28 deletions(-)

(limited to 'fs/nfs/internal.h')

diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h
index 2e485677019c..5e686a4d744e 100644
--- a/fs/nfs/internal.h
+++ b/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
  */
@@ -71,7 +76,7 @@ struct nfs_parsed_mount_data {
 		size_t			addrlen;
 		char			*hostname;
 		u32			version;
-		unsigned short		port;
+		int			port;
 		unsigned short		protocol;
 	} mount_server;
 
@@ -80,7 +85,7 @@ struct nfs_parsed_mount_data {
 		size_t			addrlen;
 		char			*hostname;
 		char			*export_path;
-		unsigned short		port;
+		int			port;
 		unsigned short		protocol;
 	} nfs_server;
 
diff --git a/fs/nfs/super.c b/fs/nfs/super.c
index f3a95df4b95f..05544336f7de 100644
--- a/fs/nfs/super.c
+++ b/fs/nfs/super.c
@@ -746,6 +746,21 @@ static int nfs_verify_server_address(struct sockaddr *addr)
 	return 0;
 }
 
+/*
+ * Select between a default port value and a user-specified port value.
+ * If a zero value is set, then autobind will be used.
+ */
+static void nfs_set_default_port(struct sockaddr *sap, const int parsed_port,
+				 const unsigned short default_port)
+{
+	unsigned short port = default_port;
+
+	if (parsed_port != NFS_UNSPEC_PORT)
+		port = parsed_port;
+
+	rpc_set_port(sap, port);
+}
+
 /*
  * Sanity check the NFS transport protocol.
  *
@@ -1415,11 +1430,7 @@ static int nfs_try_mount(struct nfs_parsed_mount_data *args,
 		args->mount_server.addrlen = args->nfs_server.addrlen;
 	}
 	request.salen = args->mount_server.addrlen;
-
-	/*
-	 * autobind will be used if mount_server.port == 0
-	 */
-	rpc_set_port(request.sap, args->mount_server.port);
+	nfs_set_default_port(request.sap, args->mount_server.port, 0);
 
 	/*
 	 * Now ask the mount server to map our export path
@@ -1597,6 +1608,7 @@ static int nfs_validate_mount_data(void *options,
 				   const char *dev_name)
 {
 	struct nfs_mount_data *data = (struct nfs_mount_data *)options;
+	struct sockaddr *sap = (struct sockaddr *)&args->nfs_server.address;
 
 	if (data == NULL)
 		goto out_no_data;
@@ -1608,8 +1620,8 @@ static int nfs_validate_mount_data(void *options,
 	args->acregmax		= NFS_DEF_ACREGMAX;
 	args->acdirmin		= NFS_DEF_ACDIRMIN;
 	args->acdirmax		= NFS_DEF_ACDIRMAX;
-	args->mount_server.port	= 0;	/* autobind unless user sets port */
-	args->nfs_server.port	= 0;	/* autobind unless user sets port */
+	args->mount_server.port	= NFS_UNSPEC_PORT;
+	args->nfs_server.port	= NFS_UNSPEC_PORT;
 	args->nfs_server.protocol = XPRT_TRANSPORT_TCP;
 	args->auth_flavors[0]	= RPC_AUTH_UNIX;
 	args->auth_flavor_len	= 1;
@@ -1657,11 +1669,9 @@ static int nfs_validate_mount_data(void *options,
 		args->acdirmin		= data->acdirmin;
 		args->acdirmax		= data->acdirmax;
 
-		memcpy(&args->nfs_server.address, &data->addr,
-		       sizeof(data->addr));
+		memcpy(sap, &data->addr, sizeof(data->addr));
 		args->nfs_server.addrlen = sizeof(data->addr);
-		if (!nfs_verify_server_address((struct sockaddr *)
-						&args->nfs_server.address))
+		if (!nfs_verify_server_address(sap))
 			goto out_no_address;
 
 		if (!(data->flags & NFS_MOUNT_TCP))
@@ -1709,12 +1719,10 @@ static int nfs_validate_mount_data(void *options,
 		if (nfs_parse_mount_options((char *)options, args) == 0)
 			return -EINVAL;
 
-		if (!nfs_verify_server_address((struct sockaddr *)
-						&args->nfs_server.address))
+		if (!nfs_verify_server_address(sap))
 			goto out_no_address;
 
-		rpc_set_port((struct sockaddr *)&args->nfs_server.address,
-				args->nfs_server.port);
+		nfs_set_default_port(sap, args->nfs_server.port, 0);
 
 		nfs_set_mount_transport_protocol(args);
 
@@ -2261,7 +2269,7 @@ static int nfs4_validate_mount_data(void *options,
 				    struct nfs_parsed_mount_data *args,
 				    const char *dev_name)
 {
-	struct sockaddr_in *ap;
+	struct sockaddr *sap = (struct sockaddr *)&args->nfs_server.address;
 	struct nfs4_mount_data *data = (struct nfs4_mount_data *)options;
 	char *c;
 
@@ -2274,23 +2282,21 @@ static int nfs4_validate_mount_data(void *options,
 	args->acregmax		= NFS_DEF_ACREGMAX;
 	args->acdirmin		= NFS_DEF_ACDIRMIN;
 	args->acdirmax		= NFS_DEF_ACDIRMAX;
-	args->nfs_server.port	= NFS_PORT; /* 2049 unless user set port= */
+	args->nfs_server.port	= NFS_UNSPEC_PORT;
 	args->auth_flavors[0]	= RPC_AUTH_UNIX;
 	args->auth_flavor_len	= 1;
 	args->minorversion	= 0;
 
 	switch (data->version) {
 	case 1:
-		ap = (struct sockaddr_in *)&args->nfs_server.address;
 		if (data->host_addrlen > sizeof(args->nfs_server.address))
 			goto out_no_address;
 		if (data->host_addrlen == 0)
 			goto out_no_address;
 		args->nfs_server.addrlen = data->host_addrlen;
-		if (copy_from_user(ap, data->host_addr, data->host_addrlen))
+		if (copy_from_user(sap, data->host_addr, data->host_addrlen))
 			return -EFAULT;
-		if (!nfs_verify_server_address((struct sockaddr *)
-						&args->nfs_server.address))
+		if (!nfs_verify_server_address(sap))
 			goto out_no_address;
 
 		if (data->auth_flavourlen) {
@@ -2342,12 +2348,9 @@ static int nfs4_validate_mount_data(void *options,
 		if (nfs_parse_mount_options((char *)options, args) == 0)
 			return -EINVAL;
 
-		if (!nfs_verify_server_address((struct sockaddr *)
-						&args->nfs_server.address))
+		if (!nfs_verify_server_address(sap))
 			return -EINVAL;
-
-		rpc_set_port((struct sockaddr *)&args->nfs_server.address,
-				args->nfs_server.port);
+		nfs_set_default_port(sap, args->nfs_server.port, NFS_PORT);
 
 		nfs_validate_transport_protocol(args);
 
-- 
cgit v1.2.3


From 764302ccb88dd0df062eccd507b6c6de24f1c560 Mon Sep 17 00:00:00 2001
From: Chuck Lever <chuck.lever@oracle.com>
Date: Tue, 8 Sep 2009 19:50:03 -0400
Subject: NFS: Allow the "nfs" file system type to support NFSv4

When mounting an "nfs" type file system, recognize "v4," "vers=4," or
"nfsvers=4" mount options, and convert the file system to "nfs4" under
the covers.

Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
[trondmy: fixed up binary mount code so it sets the 'version' field too]
Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>
---
 fs/nfs/internal.h    |  1 +
 fs/nfs/super.c       | 48 ++++++++++++++++++++++++++++++++++++++++++++++--
 include/linux/nfs4.h |  1 +
 3 files changed, 48 insertions(+), 2 deletions(-)

(limited to 'fs/nfs/internal.h')

diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h
index 5e686a4d744e..e21b1bb9972f 100644
--- a/fs/nfs/internal.h
+++ b/fs/nfs/internal.h
@@ -68,6 +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;
 
diff --git a/fs/nfs/super.c b/fs/nfs/super.c
index c105e12197c2..34b1ccf51adf 100644
--- a/fs/nfs/super.c
+++ b/fs/nfs/super.c
@@ -73,7 +73,7 @@ enum {
 	Opt_cto, Opt_nocto,
 	Opt_ac, Opt_noac,
 	Opt_lock, Opt_nolock,
-	Opt_v2, Opt_v3,
+	Opt_v2, Opt_v3, Opt_v4,
 	Opt_udp, Opt_tcp, Opt_rdma,
 	Opt_acl, Opt_noacl,
 	Opt_rdirplus, Opt_nordirplus,
@@ -127,6 +127,7 @@ static const match_table_t nfs_mount_option_tokens = {
 	{ Opt_nolock, "nolock" },
 	{ Opt_v2, "v2" },
 	{ Opt_v3, "v3" },
+	{ Opt_v4, "v4" },
 	{ Opt_udp, "udp" },
 	{ Opt_tcp, "tcp" },
 	{ Opt_rdma, "rdma" },
@@ -934,10 +935,18 @@ static int nfs_parse_mount_options(char *raw,
 			break;
 		case Opt_v2:
 			mnt->flags &= ~NFS_MOUNT_VER3;
+			mnt->version = 2;
 			break;
 		case Opt_v3:
 			mnt->flags |= NFS_MOUNT_VER3;
+			mnt->version = 3;
 			break;
+#ifdef CONFIG_NFS_V4
+		case Opt_v4:
+			mnt->flags &= ~NFS_MOUNT_VER3;
+			mnt->version = 4;
+			break;
+#endif
 		case Opt_udp:
 			mnt->flags &= ~NFS_MOUNT_TCP;
 			mnt->nfs_server.protocol = XPRT_TRANSPORT_UDP;
@@ -1151,10 +1160,18 @@ static int nfs_parse_mount_options(char *raw,
 			switch (option) {
 			case NFS2_VERSION:
 				mnt->flags &= ~NFS_MOUNT_VER3;
+				mnt->version = 2;
 				break;
 			case NFS3_VERSION:
 				mnt->flags |= NFS_MOUNT_VER3;
+				mnt->version = 3;
+				break;
+#ifdef CONFIG_NFS_V4
+			case NFS4_VERSION:
+				mnt->flags &= ~NFS_MOUNT_VER3;
+				mnt->version = 4;
 				break;
+#endif
 			default:
 				goto out_invalid_value;
 			}
@@ -1629,6 +1646,7 @@ static int nfs_validate_mount_data(void *options,
 	args->nfs_server.protocol = XPRT_TRANSPORT_TCP;
 	args->auth_flavors[0]	= RPC_AUTH_UNIX;
 	args->auth_flavor_len	= 1;
+	args->minorversion	= 0;
 
 	switch (data->version) {
 	case 1:
@@ -1650,8 +1668,11 @@ static int nfs_validate_mount_data(void *options,
 			if (data->root.size > NFS3_FHSIZE || data->root.size == 0)
 				goto out_invalid_fh;
 			mntfh->size = data->root.size;
-		} else
+			args->version = 3;
+		} else {
 			mntfh->size = NFS2_FHSIZE;
+			args->version = 2;
+		}
 
 
 		memcpy(mntfh->data, data->root.data, mntfh->size);
@@ -1726,6 +1747,14 @@ static int nfs_validate_mount_data(void *options,
 		if (!nfs_verify_server_address(sap))
 			goto out_no_address;
 
+		if (args->version == 4)
+#ifdef CONFIG_NFS_V4
+			return nfs4_validate_text_mount_data(options,
+							     args, dev_name);
+#else
+			goto out_v4_not_compiled;
+#endif
+
 		nfs_set_default_port(sap, args->nfs_server.port, 0);
 
 		nfs_set_mount_transport_protocol(args);
@@ -1774,6 +1803,12 @@ out_v3_not_compiled:
 	return -EPROTONOSUPPORT;
 #endif /* !CONFIG_NFS_V3 */
 
+#ifndef CONFIG_NFS_V4
+out_v4_not_compiled:
+	dfprintk(MOUNT, "NFS: NFSv4 is not compiled into kernel\n");
+	return -EPROTONOSUPPORT;
+#endif /* !CONFIG_NFS_V4 */
+
 out_nomem:
 	dfprintk(MOUNT, "NFS: not enough memory to handle mount options\n");
 	return -ENOMEM;
@@ -2069,6 +2104,14 @@ static int nfs_get_sb(struct file_system_type *fs_type,
 	if (error < 0)
 		goto out;
 
+#ifdef CONFIG_NFS_V4
+	if (data->version == 4) {
+		error = nfs4_try_mount(flags, dev_name, data, mnt);
+		kfree(data->client_address);
+		goto out;
+	}
+#endif	/* CONFIG_NFS_V4 */
+
 	/* Get a volume representation */
 	server = nfs_create_server(data, mntfh);
 	if (IS_ERR(server)) {
@@ -2320,6 +2363,7 @@ static int nfs4_validate_mount_data(void *options,
 	args->nfs_server.port	= NFS_UNSPEC_PORT;
 	args->auth_flavors[0]	= RPC_AUTH_UNIX;
 	args->auth_flavor_len	= 1;
+	args->version		= 4;
 	args->minorversion	= 0;
 
 	switch (data->version) {
diff --git a/include/linux/nfs4.h b/include/linux/nfs4.h
index bd2eba530667..33b283601f62 100644
--- a/include/linux/nfs4.h
+++ b/include/linux/nfs4.h
@@ -472,6 +472,7 @@ enum lock_type4 {
 
 #define NFSPROC4_NULL 0
 #define NFSPROC4_COMPOUND 1
+#define NFS4_VERSION 4
 #define NFS4_MINOR_VERSION 0
 
 #if defined(CONFIG_NFS_V4_1)
-- 
cgit v1.2.3