Merge branch 'nfs-for-2.6.32'

The NFS client

==============

The NFS version 2 protocol was first documented in RFC1094 (March 1989).

Since then two more major releases of NFS have been published, with NFSv3

being documented in RFC1813 (June 1995), and NFSv4 in RFC3530 (April

2003).

The Linux NFS client currently supports all the above published versions,

and work is in progress on adding support for minor version 1 of the NFSv4

protocol.

The purpose of this document is to provide information on some of the

upcall interfaces that are used in order to provide the NFS client with

some of the information that it requires in order to fully comply with

the NFS spec.

The DNS resolver

================

NFSv4 allows for one server to refer the NFS client to data that has been

migrated onto another server by means of the special "fs_locations"

attribute. See

	http://tools.ietf.org/html/rfc3530#section-6

and

	http://tools.ietf.org/html/draft-ietf-nfsv4-referrals-00

The fs_locations information can take the form of either an ip address and

a path, or a DNS hostname and a path. The latter requires the NFS client to

do a DNS lookup in order to mount the new volume, and hence the need for an

upcall to allow userland to provide this service.

Assuming that the user has the 'rpc_pipefs' filesystem mounted in the usual

/var/lib/nfs/rpc_pipefs, the upcall consists of the following steps:

   (1) The process checks the dns_resolve cache to see if it contains a

       valid entry. If so, it returns that entry and exits.

   (2) If no valid entry exists, the helper script '/sbin/nfs_cache_getent'

       (may be changed using the 'nfs.cache_getent' kernel boot parameter)

       is run, with two arguments:

		- the cache name, "dns_resolve"

		- the hostname to resolve

   (3) After looking up the corresponding ip address, the helper script

       writes the result into the rpc_pipefs pseudo-file

       '/var/lib/nfs/rpc_pipefs/cache/dns_resolve/channel'

       in the following (text) format:

		"<ip address> <hostname> <ttl>\n"

       Where <ip address> is in the usual IPv4 (123.456.78.90) or IPv6

       (ffee:ddcc:bbaa:9988:7766:5544:3322:1100, ffee::1100, ...) format.

       <hostname> is identical to the second argument of the helper

       script, and <ttl> is the 'time to live' of this cache entry (in

       units of seconds).

       Note: If <ip address> is invalid, say the string "0", then a negative

       entry is created, which will cause the kernel to treat the hostname

       as having no valid DNS translation.

A basic sample /sbin/nfs_cache_getent

=====================================

#!/bin/bash

#

ttl=600

#

cut=/usr/bin/cut

getent=/usr/bin/getent

rpc_pipefs=/var/lib/nfs/rpc_pipefs

#

die()

{

	echo "Usage: $0 cache_name entry_name"

	exit 1

}

[ $# -lt 2 ] && die

cachename="$1"

cache_path=${rpc_pipefs}/cache/${cachename}/channel

case "${cachename}" in

	dns_resolve)

		name="$2"

		result="$(${getent} hosts ${name} | ${cut} -f1 -d\ )"

		[ -z "${result}" ] && result="0"

		;;

	*)

		die

		;;

esac

echo "${result} ${name} ${ttl}" >${cache_path}

			[NFS] set the TCP port on which the NFSv4 callback

			channel should listen.

	nfs.cache_getent=

			[NFS] sets the pathname to the program which is used

			to update the NFS client cache entries.

	nfs.cache_getent_timeout=

			[NFS] sets the timeout after which an attempt to

			update a cache entry is deemed to have failed.

	nfs.idmap_cache_timeout=

			[NFS] set the maximum lifetime for idmapper cache

			entries.

	stifb=		[HW]

			Format: bpp:<bpp1>[:<bpp2>[:<bpp3>...]]

	sunrpc.min_resvport=

	sunrpc.max_resvport=

			[NFS,SUNRPC]

			SunRPC servers often require that client requests

			originate from a privileged port (i.e. a port in the

			range 0 < portnr < 1024).

			An administrator who wishes to reserve some of these

			ports for other uses may adjust the range that the

			kernel's sunrpc client considers to be privileged

			using these two parameters to set the minimum and

			maximum port values.

	sunrpc.pool_mode=

			[NFS]

			Control how the NFS server code allocates CPUs to

			pernode	    one pool for each NUMA node (equivalent

				    to global on non-NUMA machines)

	sunrpc.tcp_slot_table_entries=

	sunrpc.udp_slot_table_entries=

			[NFS,SUNRPC]

			Sets the upper limit on the number of simultaneous

			RPC calls that can be sent from the client to a

			server. Increasing these values may allow you to

			improve throughput, but will also increase the

			amount of memory reserved for use by the client.

	swiotlb=	[IA-64] Number of I/O TLB slabs

	switches=	[HW,M68k]

	return hash & (NLM_HOST_NRHASH - 1);

}

static void nlm_clear_port(struct sockaddr *sap)

{

	switch (sap->sa_family) {

	case AF_INET:

		((struct sockaddr_in *)sap)->sin_port = 0;

		break;

	case AF_INET6:

		((struct sockaddr_in6 *)sap)->sin6_port = 0;

		break;

	}

}

/*

 * Common host lookup routine for server & client

 */

	host->h_addrbuf    = nsm->sm_addrbuf;

	memcpy(nlm_addr(host), ni->sap, ni->salen);

	host->h_addrlen = ni->salen;

	nlm_clear_port(nlm_addr(host));

	rpc_set_port(nlm_addr(host), 0);

	memcpy(nlm_srcaddr(host), ni->src_sap, ni->src_len);

	host->h_version    = ni->version;

	host->h_proto      = ni->protocol;

	return (struct sockaddr *)&nsm->sm_addr;

}

static void nsm_display_ipv4_address(const struct sockaddr *sap, char *buf,

				     const size_t len)

{

	const struct sockaddr_in *sin = (struct sockaddr_in *)sap;

	snprintf(buf, len, "%pI4", &sin->sin_addr.s_addr);

}

static void nsm_display_ipv6_address(const struct sockaddr *sap, char *buf,

				     const size_t len)

{

	const struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *)sap;

	if (ipv6_addr_v4mapped(&sin6->sin6_addr))

		snprintf(buf, len, "%pI4", &sin6->sin6_addr.s6_addr32[3]);

	else if (sin6->sin6_scope_id != 0)

		snprintf(buf, len, "%pI6%%%u", &sin6->sin6_addr,

				sin6->sin6_scope_id);

	else

		snprintf(buf, len, "%pI6", &sin6->sin6_addr);

}

static void nsm_display_address(const struct sockaddr *sap,

				char *buf, const size_t len)

{

	switch (sap->sa_family) {

	case AF_INET:

		nsm_display_ipv4_address(sap, buf, len);

		break;

	case AF_INET6:

		nsm_display_ipv6_address(sap, buf, len);

		break;

	default:

		snprintf(buf, len, "unsupported address family");

		break;

	}

}

static struct rpc_clnt *nsm_create(void)

{

	struct sockaddr_in sin = {

	memcpy(nsm_addr(new), sap, salen);

	new->sm_addrlen = salen;

	nsm_init_private(new);

	nsm_display_address((const struct sockaddr *)&new->sm_addr,

				new->sm_addrbuf, sizeof(new->sm_addrbuf));

	if (rpc_ntop(nsm_addr(new), new->sm_addrbuf,

					sizeof(new->sm_addrbuf)) == 0)

		(void)snprintf(new->sm_addrbuf, sizeof(new->sm_addrbuf),

				"unsupported address family");

	memcpy(new->sm_name, hostname, hostname_len);

	new->sm_name[hostname_len] = '\0';

nfs-y 			:= client.o dir.o file.o getroot.o inode.o super.o nfs2xdr.o \

			   direct.o pagelist.o proc.o read.o symlink.o unlink.o \

			   write.o namespace.o mount_clnt.o

			   write.o namespace.o mount_clnt.o \

			   dns_resolve.o cache_lib.o

nfs-$(CONFIG_ROOT_NFS)	+= nfsroot.o

nfs-$(CONFIG_NFS_V3)	+= nfs3proc.o nfs3xdr.o

nfs-$(CONFIG_NFS_V3_ACL)	+= nfs3acl.o