Merge branch 'for-linus' of git://linux-nfs.org/~bfields/linux

* 'for-linus' of git://linux-nfs.org/~bfields/linux: (52 commits) knfsd: clear both setuid and setgid whenever a chown is done knfsd: get rid of imode variable in nfsd_setattr SUNRPC: Use unsigned loop and array index in svc_init_buffer() SUNRPC: Use unsigned index when looping over arrays SUNRPC: Update RPC server's TCP record marker decoder SUNRPC: RPC server still uses 2.4 method for disabling TCP Nagle NLM: don't let lockd exit on unexpected svc_recv errors (try #2) NFS: don't let nfs_callback_svc exit on unexpected svc_recv errors (try #2) Use a zero sized array for raw field in struct fid nfsd: use static memory for callback program and stats SUNRPC: remove svc_create_thread() nfsd: fix comment lockd: Fix stale nlmsvc_unlink_block comment NFSD: Strip __KERNEL__ testing from unexported header files. sunrpc: make token header values less confusing gss_krb5: consistently use unsigned for seqnum NFSD: Remove NFSv4 dependency on NFSv3 SUNRPC: Remove PROC_FS dependency NFSD: Use "depends on" for PROC_FS dependency nfsd: move most of fh_verify to separate function ...
2026-05-01 15:00:59 -07:00 · 2008-04-24 11:45:00 -07:00
parent c328d54cd4 ca456252db
commit 10c993a6b5
43 changed files with 877 additions and 515 deletions
@@ -0,0 +1,252 @@
+################################################################################
+#									       #
+#				NFS/RDMA README				       #
+#									       #
+################################################################################
+
+ Author: NetApp and Open Grid Computing
+ Date: February 25, 2008
+
+Table of Contents
+~~~~~~~~~~~~~~~~~
+ - Overview
+ - Getting Help
+ - Installation
+ - Check RDMA and NFS Setup
+ - NFS/RDMA Setup
+
+Overview
+~~~~~~~~
+
+  This document describes how to install and setup the Linux NFS/RDMA client
+  and server software.
+
+  The NFS/RDMA client was first included in Linux 2.6.24. The NFS/RDMA server
+  was first included in the following release, Linux 2.6.25.
+
+  In our testing, we have obtained excellent performance results (full 10Gbit
+  wire bandwidth at minimal client CPU) under many workloads. The code passes
+  the full Connectathon test suite and operates over both Infiniband and iWARP
+  RDMA adapters.
+
+Getting Help
+~~~~~~~~~~~~
+
+  If you get stuck, you can ask questions on the
+
+                nfs-rdma-devel@lists.sourceforge.net
+
+  mailing list.
+
+Installation
+~~~~~~~~~~~~
+
+  These instructions are a step by step guide to building a machine for
+  use with NFS/RDMA.
+
+  - Install an RDMA device
+
+    Any device supported by the drivers in drivers/infiniband/hw is acceptable.
+
+    Testing has been performed using several Mellanox-based IB cards, the
+    Ammasso AMS1100 iWARP adapter, and the Chelsio cxgb3 iWARP adapter.
+
+  - Install a Linux distribution and tools
+
+    The first kernel release to contain both the NFS/RDMA client and server was
+    Linux 2.6.25  Therefore, a distribution compatible with this and subsequent
+    Linux kernel release should be installed.
+
+    The procedures described in this document have been tested with
+    distributions from Red Hat's Fedora Project (http://fedora.redhat.com/).
+
+  - Install nfs-utils-1.1.1 or greater on the client
+
+    An NFS/RDMA mount point can only be obtained by using the mount.nfs
+    command in nfs-utils-1.1.1 or greater. To see which version of mount.nfs
+    you are using, type:
+
+    > /sbin/mount.nfs -V
+
+    If the version is less than 1.1.1 or the command does not exist,
+    then you will need to install the latest version of nfs-utils.
+
+    Download the latest package from:
+
+    http://www.kernel.org/pub/linux/utils/nfs
+
+    Uncompress the package and follow the installation instructions.
+
+    If you will not be using GSS and NFSv4, the installation process
+    can be simplified by disabling these features when running configure:
+
+    > ./configure --disable-gss --disable-nfsv4
+
+    For more information on this see the package's README and INSTALL files.
+
+    After building the nfs-utils package, there will be a mount.nfs binary in
+    the utils/mount directory. This binary can be used to initiate NFS v2, v3,
+    or v4 mounts. To initiate a v4 mount, the binary must be called mount.nfs4.
+    The standard technique is to create a symlink called mount.nfs4 to mount.nfs.
+
+    NOTE: mount.nfs and therefore nfs-utils-1.1.1 or greater is only needed
+    on the NFS client machine. You do not need this specific version of
+    nfs-utils on the server. Furthermore, only the mount.nfs command from
+    nfs-utils-1.1.1 is needed on the client.
+
+  - Install a Linux kernel with NFS/RDMA
+
+    The NFS/RDMA client and server are both included in the mainline Linux
+    kernel version 2.6.25 and later. This and other versions of the 2.6 Linux
+    kernel can be found at:
+
+    ftp://ftp.kernel.org/pub/linux/kernel/v2.6/
+
+    Download the sources and place them in an appropriate location.
+
+  - Configure the RDMA stack
+
+    Make sure your kernel configuration has RDMA support enabled. Under
+    Device Drivers -> InfiniBand support, update the kernel configuration
+    to enable InfiniBand support [NOTE: the option name is misleading. Enabling
+    InfiniBand support is required for all RDMA devices (IB, iWARP, etc.)].
+
+    Enable the appropriate IB HCA support (mlx4, mthca, ehca, ipath, etc.) or
+    iWARP adapter support (amso, cxgb3, etc.).
+
+    If you are using InfiniBand, be sure to enable IP-over-InfiniBand support.
+
+  - Configure the NFS client and server
+
+    Your kernel configuration must also have NFS file system support and/or
+    NFS server support enabled. These and other NFS related configuration
+    options can be found under File Systems -> Network File Systems.
+
+  - Build, install, reboot
+
+    The NFS/RDMA code will be enabled automatically if NFS and RDMA
+    are turned on. The NFS/RDMA client and server are configured via the hidden
+    SUNRPC_XPRT_RDMA config option that depends on SUNRPC and INFINIBAND. The
+    value of SUNRPC_XPRT_RDMA will be:
+
+     - N if either SUNRPC or INFINIBAND are N, in this case the NFS/RDMA client
+       and server will not be built
+     - M if both SUNRPC and INFINIBAND are on (M or Y) and at least one is M,
+       in this case the NFS/RDMA client and server will be built as modules
+     - Y if both SUNRPC and INFINIBAND are Y, in this case the NFS/RDMA client
+       and server will be built into the kernel
+
+    Therefore, if you have followed the steps above and turned no NFS and RDMA,
+    the NFS/RDMA client and server will be built.
+
+    Build a new kernel, install it, boot it.
+
+Check RDMA and NFS Setup
+~~~~~~~~~~~~~~~~~~~~~~~~
+
+    Before configuring the NFS/RDMA software, it is a good idea to test
+    your new kernel to ensure that the kernel is working correctly.
+    In particular, it is a good idea to verify that the RDMA stack
+    is functioning as expected and standard NFS over TCP/IP and/or UDP/IP
+    is working properly.
+
+  - Check RDMA Setup
+
+    If you built the RDMA components as modules, load them at
+    this time. For example, if you are using a Mellanox Tavor/Sinai/Arbel
+    card:
+
+    > modprobe ib_mthca
+    > modprobe ib_ipoib
+
+    If you are using InfiniBand, make sure there is a Subnet Manager (SM)
+    running on the network. If your IB switch has an embedded SM, you can
+    use it. Otherwise, you will need to run an SM, such as OpenSM, on one
+    of your end nodes.
+
+    If an SM is running on your network, you should see the following:
+
+    > cat /sys/class/infiniband/driverX/ports/1/state
+    4: ACTIVE
+
+    where driverX is mthca0, ipath5, ehca3, etc.
+
+    To further test the InfiniBand software stack, use IPoIB (this
+    assumes you have two IB hosts named host1 and host2):
+
+    host1> ifconfig ib0 a.b.c.x
+    host2> ifconfig ib0 a.b.c.y
+    host1> ping a.b.c.y
+    host2> ping a.b.c.x
+
+    For other device types, follow the appropriate procedures.
+
+  - Check NFS Setup
+
+    For the NFS components enabled above (client and/or server),
+    test their functionality over standard Ethernet using TCP/IP or UDP/IP.
+
+NFS/RDMA Setup
+~~~~~~~~~~~~~~
+
+  We recommend that you use two machines, one to act as the client and
+  one to act as the server.
+
+  One time configuration:
+
+  - On the server system, configure the /etc/exports file and
+    start the NFS/RDMA server.
+
+    Exports entries with the following format have been tested:
+
+    /vol0   10.97.103.47(rw,async) 192.168.0.47(rw,async,insecure,no_root_squash)
+
+    Here the first IP address is the client's Ethernet address and the second
+    IP address is the clients IPoIB address.
+
+ Each time a machine boots:
+
+  - Load and configure the RDMA drivers
+
+    For InfiniBand using a Mellanox adapter:
+
+    > modprobe ib_mthca
+    > modprobe ib_ipoib
+    > ifconfig ib0 a.b.c.d
+
+    NOTE: use unique addresses for the client and server
+
+  - Start the NFS server
+
+    If the NFS/RDMA server was built as a module (CONFIG_SUNRPC_XPRT_RDMA=m in kernel config),
+    load the RDMA transport module:
+
+    > modprobe svcrdma
+
+    Regardless of how the server was built (module or built-in), start the server:
+
+    > /etc/init.d/nfs start
+
+    or
+
+    > service nfs start
+
+    Instruct the server to listen on the RDMA transport:
+
+    > echo rdma 2050 > /proc/fs/nfsd/portlist
+
+  - On the client system
+
+    If the NFS/RDMA client was built as a module (CONFIG_SUNRPC_XPRT_RDMA=m in kernel config),
+    load the RDMA client module:
+
+    > modprobe xprtrdma.ko
+
+    Regardless of how the client was built (module or built-in), issue the mount.nfs command:
+
+    > /path/to/your/mount.nfs <IPoIB-server-name-or-address>:/<export> /mnt -i -o rdma,port=2050
+
+    To verify that the mount is using RDMA, run "cat /proc/mounts" and check the
+    "proto" field for the given mount.
+
+  Congratulations! You're using NFS/RDMA!
@@ -411,7 +411,7 @@ config JFS_STATISTICS
 	  to be made available to the user in the /proc/fs/jfs/ directory.

 config FS_POSIX_ACL
-# Posix ACL utility routines (for now, only ext2/ext3/jfs/reiserfs)
+# Posix ACL utility routines (for now, only ext2/ext3/jfs/reiserfs/nfs4)
 #
 # NOTE: you can implement Posix ACLs without these helpers (XFS does).
 # 	Never use this symbol for ifdefs.
@@ -1694,75 +1694,80 @@ config NFSD
 	select LOCKD
 	select SUNRPC
 	select EXPORTFS
-	select NFSD_V2_ACL if NFSD_V3_ACL
 	select NFS_ACL_SUPPORT if NFSD_V2_ACL
-	select NFSD_TCP if NFSD_V4
-	select CRYPTO_MD5 if NFSD_V4
-	select CRYPTO if NFSD_V4
-	select FS_POSIX_ACL if NFSD_V4
-	select PROC_FS if NFSD_V4
-	select PROC_FS if SUNRPC_GSS
 	help
-	  If you want your Linux box to act as an NFS *server*, so that other
-	  computers on your local network which support NFS can access certain
-	  directories on your box transparently, you have two options: you can
-	  use the self-contained user space program nfsd, in which case you
-	  should say N here, or you can say Y and use the kernel based NFS
-	  server. The advantage of the kernel based solution is that it is
-	  faster.
+	  Choose Y here if you want to allow other computers to access
+	  files residing on this system using Sun's Network File System
+	  protocol.  To compile the NFS server support as a module,
+	  choose M here: the module will be called nfsd.

-	  In either case, you will need support software; the respective
-	  locations are given in the file <file:Documentation/Changes> in the
-	  NFS section.
+	  You may choose to use a user-space NFS server instead, in which
+	  case you can choose N here.

-	  If you say Y here, you will get support for version 2 of the NFS
-	  protocol (NFSv2). If you also want NFSv3, say Y to the next question
-	  as well.
+	  To export local file systems using NFS, you also need to install
+	  user space programs which can be found in the Linux nfs-utils
+	  package, available from http://linux-nfs.org/.  More detail about
+	  the Linux NFS server implementation is available via the
+	  exports(5) man page.

-	  Please read the NFS-HOWTO, available from
-	  <http://www.tldp.org/docs.html#howto>.
+	  Below you can choose which versions of the NFS protocol are
+	  available to clients mounting the NFS server on this system.
+	  Support for NFS version 2 (RFC 1094) is always available when
+	  CONFIG_NFSD is selected.

-	  To compile the NFS server support as a module, choose M here: the
-	  module will be called nfsd.  If unsure, say N.
+	  If unsure, say N.

 config NFSD_V2_ACL
 	bool
 	depends on NFSD

 config NFSD_V3
-	bool "Provide NFSv3 server support"
+	bool "NFS server support for NFS version 3"
 	depends on NFSD
 	help
-	  If you would like to include the NFSv3 server as well as the NFSv2
-	  server, say Y here.  If unsure, say Y.
+	  This option enables support in your system's NFS server for
+	  version 3 of the NFS protocol (RFC 1813).
+
+	  If unsure, say Y.

 config NFSD_V3_ACL
-	bool "Provide server support for the NFSv3 ACL protocol extension"
+	bool "NFS server support for the NFSv3 ACL protocol extension"
 	depends on NFSD_V3
+	select NFSD_V2_ACL
 	help
-	  Implement the NFSv3 ACL protocol extension for manipulating POSIX
-	  Access Control Lists on exported file systems. NFS clients should
-	  be compiled with the NFSv3 ACL protocol extension; see the
-	  CONFIG_NFS_V3_ACL option.  If unsure, say N.
+	  Solaris NFS servers support an auxiliary NFSv3 ACL protocol that
+	  never became an official part of the NFS version 3 protocol.
+	  This protocol extension allows applications on NFS clients to
+	  manipulate POSIX Access Control Lists on files residing on NFS
+	  servers.  NFS servers enforce POSIX ACLs on local files whether
+	  this protocol is available or not.
+
+	  This option enables support in your system's NFS server for the
+	  NFSv3 ACL protocol extension allowing NFS clients to manipulate
+	  POSIX ACLs on files exported by your system's NFS server.  NFS
+	  clients which support the Solaris NFSv3 ACL protocol can then
+	  access and modify ACLs on your NFS server.
+
+	  To store ACLs on your NFS server, you also need to enable ACL-
+	  related CONFIG options for your local file systems of choice.

-config NFSD_V4
-	bool "Provide NFSv4 server support (EXPERIMENTAL)"
-	depends on NFSD && NFSD_V3 && EXPERIMENTAL
-	select RPCSEC_GSS_KRB5
-	help
-	  If you would like to include the NFSv4 server as well as the NFSv2
-	  and NFSv3 servers, say Y here.  This feature is experimental, and
-	  should only be used if you are interested in helping to test NFSv4.
 	  If unsure, say N.

-config NFSD_TCP
-	bool "Provide NFS server over TCP support"
-	depends on NFSD
-	default y
+config NFSD_V4
+	bool "NFS server support for NFS version 4 (EXPERIMENTAL)"
+	depends on NFSD && PROC_FS && EXPERIMENTAL
+	select NFSD_V3
+	select FS_POSIX_ACL
+	select RPCSEC_GSS_KRB5
 	help
-	  If you want your NFS server to support TCP connections, say Y here.
-	  TCP connections usually perform better than the default UDP when
-	  the network is lossy or congested.  If unsure, say Y.
+	  This option enables support in your system's NFS server for
+	  version 4 of the NFS protocol (RFC 3530).
+
+	  To export files using NFSv4, you need to install additional user
+	  space programs which can be found in the Linux nfs-utils package,
+	  available from http://linux-nfs.org/.
+
+	  If unsure, say N.

 config ROOT_NFS
 	bool "Root file system on NFS"
@@ -19,12 +19,11 @@


 #define NLMDBG_FACILITY		NLMDBG_HOSTCACHE
-#define NLM_HOST_MAX		64
 #define NLM_HOST_NRHASH		32
 #define NLM_ADDRHASH(addr)	(ntohl(addr) & (NLM_HOST_NRHASH-1))
 #define NLM_HOST_REBIND		(60 * HZ)
-#define NLM_HOST_EXPIRE		((nrhosts > NLM_HOST_MAX)? 300 * HZ : 120 * HZ)
-#define NLM_HOST_COLLECT	((nrhosts > NLM_HOST_MAX)? 120 * HZ :  60 * HZ)
+#define NLM_HOST_EXPIRE		(300 * HZ)
+#define NLM_HOST_COLLECT	(120 * HZ)

 static struct hlist_head	nlm_hosts[NLM_HOST_NRHASH];
 static unsigned long		next_gc;
@@ -142,9 +141,7 @@ nlm_lookup_host(int server, const struct sockaddr_in *sin,
 	INIT_LIST_HEAD(&host->h_granted);
 	INIT_LIST_HEAD(&host->h_reclaim);

-	if (++nrhosts > NLM_HOST_MAX)
-		next_gc = 0;
-
+	nrhosts++;
 out:
 	mutex_unlock(&nlm_host_mutex);
 	return host;
@@ -460,7 +457,7 @@ nlm_gc_hosts(void)
 * Manage NSM handles
 */
 static LIST_HEAD(nsm_handles);
-static DEFINE_MUTEX(nsm_mutex);
+static DEFINE_SPINLOCK(nsm_lock);

 static struct nsm_handle *
 __nsm_find(const struct sockaddr_in *sin,
@@ -468,7 +465,7 @@ __nsm_find(const struct sockaddr_in *sin,
 		int create)
 {
 	struct nsm_handle *nsm = NULL;
-	struct list_head *pos;
+	struct nsm_handle *pos;

 	if (!sin)
 		return NULL;
@@ -482,38 +479,43 @@ __nsm_find(const struct sockaddr_in *sin,
 		return NULL;
 	}

-	mutex_lock(&nsm_mutex);
-	list_for_each(pos, &nsm_handles) {
-		nsm = list_entry(pos, struct nsm_handle, sm_link);
+retry:
+	spin_lock(&nsm_lock);
+	list_for_each_entry(pos, &nsm_handles, sm_link) {

 		if (hostname && nsm_use_hostnames) {
-			if (strlen(nsm->sm_name) != hostname_len
-			 || memcmp(nsm->sm_name, hostname, hostname_len))
+			if (strlen(pos->sm_name) != hostname_len
+			 || memcmp(pos->sm_name, hostname, hostname_len))
 				continue;
-		} else if (!nlm_cmp_addr(&nsm->sm_addr, sin))
+		} else if (!nlm_cmp_addr(&pos->sm_addr, sin))
 			continue;
-		atomic_inc(&nsm->sm_count);
-		goto out;
+		atomic_inc(&pos->sm_count);
+		kfree(nsm);
+		nsm = pos;
+		goto found;
 	}
+	if (nsm) {
+		list_add(&nsm->sm_link, &nsm_handles);
+		goto found;
+	}
+	spin_unlock(&nsm_lock);

-	if (!create) {
-		nsm = NULL;
-		goto out;
-	}
+	if (!create)
+		return NULL;

 	nsm = kzalloc(sizeof(*nsm) + hostname_len + 1, GFP_KERNEL);
-	if (nsm != NULL) {
-		nsm->sm_addr = *sin;
-		nsm->sm_name = (char *) (nsm + 1);
-		memcpy(nsm->sm_name, hostname, hostname_len);
-		nsm->sm_name[hostname_len] = '\0';
-		atomic_set(&nsm->sm_count, 1);
+	if (nsm == NULL)
+		return NULL;

-		list_add(&nsm->sm_link, &nsm_handles);
-	}
+	nsm->sm_addr = *sin;
+	nsm->sm_name = (char *) (nsm + 1);
+	memcpy(nsm->sm_name, hostname, hostname_len);
+	nsm->sm_name[hostname_len] = '\0';
+	atomic_set(&nsm->sm_count, 1);
+	goto retry;

-out:
-	mutex_unlock(&nsm_mutex);
+found:
+	spin_unlock(&nsm_lock);
 	return nsm;
 }

@@ -532,12 +534,9 @@ nsm_release(struct nsm_handle *nsm)
 {
 	if (!nsm)
 		return;
-	if (atomic_dec_and_test(&nsm->sm_count)) {
-		mutex_lock(&nsm_mutex);
-		if (atomic_read(&nsm->sm_count) == 0) {
-			list_del(&nsm->sm_link);
-			kfree(nsm);
-		}
-		mutex_unlock(&nsm_mutex);
+	if (atomic_dec_and_lock(&nsm->sm_count, &nsm_lock)) {
+		list_del(&nsm->sm_link);
+		spin_unlock(&nsm_lock);
+		kfree(nsm);
 	}
 }
@@ -25,6 +25,7 @@
 #include <linux/smp.h>
 #include <linux/smp_lock.h>
 #include <linux/mutex.h>
+#include <linux/kthread.h>
 #include <linux/freezer.h>

 #include <linux/sunrpc/types.h>
@@ -48,14 +49,11 @@ EXPORT_SYMBOL(nlmsvc_ops);

 static DEFINE_MUTEX(nlmsvc_mutex);
 static unsigned int		nlmsvc_users;
-static pid_t			nlmsvc_pid;
+static struct task_struct	*nlmsvc_task;
 static struct svc_serv		*nlmsvc_serv;
 int				nlmsvc_grace_period;
 unsigned long			nlmsvc_timeout;

-static DECLARE_COMPLETION(lockd_start_done);
-static DECLARE_WAIT_QUEUE_HEAD(lockd_exit);
-
 /*
 * These can be set at insmod time (useful for NFS as root filesystem),
 * and also changed through the sysctl interface.  -- Jamie Lokier, Aug 2003
@@ -111,35 +109,30 @@ static inline void clear_grace_period(void)
 /*
 * This is the lockd kernel thread
 */
-static void
-lockd(struct svc_rqst *rqstp)
+static int
+lockd(void *vrqstp)
 {
-	int		err = 0;
+	int		err = 0, preverr = 0;
+	struct svc_rqst *rqstp = vrqstp;
 	unsigned long grace_period_expire;

-	/* Lock module and set up kernel thread */
-	/* lockd_up is waiting for us to startup, so will
-	 * be holding a reference to this module, so it
-	 * is safe to just claim another reference
-	 */
-	__module_get(THIS_MODULE);
-	lock_kernel();
-
-	/*
-	 * Let our maker know we're running.
-	 */
-	nlmsvc_pid = current->pid;
-	nlmsvc_serv = rqstp->rq_server;
-	complete(&lockd_start_done);
-
-	daemonize("lockd");
+	/* try_to_freeze() is called from svc_recv() */
 	set_freezable();

-	/* Process request with signals blocked, but allow SIGKILL.  */
+	/* Allow SIGKILL to tell lockd to drop all of its locks */
 	allow_signal(SIGKILL);

 	dprintk("NFS locking service started (ver " LOCKD_VERSION ").\n");

+	/*
+	 * FIXME: it would be nice if lockd didn't spend its entire life
+	 * running under the BKL. At the very least, it would be good to
+	 * have someone clarify what it's intended to protect here. I've
+	 * seen some handwavy posts about posix locking needing to be
+	 * done under the BKL, but it's far from clear.
+	 */
+	lock_kernel();
+
 	if (!nlm_timeout)
 		nlm_timeout = LOCKD_DFLT_TIMEO;
 	nlmsvc_timeout = nlm_timeout * HZ;
@@ -148,10 +141,9 @@ lockd(struct svc_rqst *rqstp)

 	/*
 	 * The main request loop. We don't terminate until the last
-	 * NFS mount or NFS daemon has gone away, and we've been sent a
-	 * signal, or else another process has taken over our job.
+	 * NFS mount or NFS daemon has gone away.
 	 */
-	while ((nlmsvc_users || !signalled()) && nlmsvc_pid == current->pid) {
+	while (!kthread_should_stop()) {
 		long timeout = MAX_SCHEDULE_TIMEOUT;
 		RPC_IFDEBUG(char buf[RPC_MAX_ADDRBUFLEN]);

@@ -161,6 +153,7 @@ lockd(struct svc_rqst *rqstp)
 				nlmsvc_invalidate_all();
 				grace_period_expire = set_grace_period();
 			}
+			continue;
 		}

 		/*
@@ -179,14 +172,20 @@ lockd(struct svc_rqst *rqstp)
 		 * recvfrom routine.
 		 */
 		err = svc_recv(rqstp, timeout);
-		if (err == -EAGAIN || err == -EINTR)
+		if (err == -EAGAIN || err == -EINTR) {
+			preverr = err;
 			continue;
-		if (err < 0) {
-			printk(KERN_WARNING
-			       "lockd: terminating on error %d\n",
-			       -err);
-			break;
 		}
+		if (err < 0) {
+			if (err != preverr) {
+				printk(KERN_WARNING "%s: unexpected error "
+					"from svc_recv (%d)\n", __func__, err);
+				preverr = err;
+			}
+			schedule_timeout_interruptible(HZ);
+			continue;
+		}
+		preverr = err;

 		dprintk("lockd: request from %s\n",
 				svc_print_addr(rqstp, buf, sizeof(buf)));
@@ -195,28 +194,19 @@ lockd(struct svc_rqst *rqstp)
 	}

 	flush_signals(current);
+	if (nlmsvc_ops)
+		nlmsvc_invalidate_all();
+	nlm_shutdown_hosts();

-	/*
-	 * Check whether there's a new lockd process before
-	 * shutting down the hosts and clearing the slot.
-	 */
-	if (!nlmsvc_pid || current->pid == nlmsvc_pid) {
-		if (nlmsvc_ops)
-			nlmsvc_invalidate_all();
-		nlm_shutdown_hosts();
-		nlmsvc_pid = 0;
-		nlmsvc_serv = NULL;
-	} else
-		printk(KERN_DEBUG
-			"lockd: new process, skipping host shutdown\n");
-	wake_up(&lockd_exit);
+	unlock_kernel();
+
+	nlmsvc_task = NULL;
+	nlmsvc_serv = NULL;

 	/* Exit the RPC thread */
 	svc_exit_thread(rqstp);

-	/* Release module */
-	unlock_kernel();
-	module_put_and_exit(0);
+	return 0;
 }

 /*
@@ -261,14 +251,15 @@ static int make_socks(struct svc_serv *serv, int proto)
 int
 lockd_up(int proto) /* Maybe add a 'family' option when IPv6 is supported ?? */
 {
-	struct svc_serv *	serv;
-	int			error = 0;
+	struct svc_serv *serv;
+	struct svc_rqst *rqstp;
+	int		error = 0;

 	mutex_lock(&nlmsvc_mutex);
 	/*
 	 * Check whether we're already up and running.
 	 */
-	if (nlmsvc_pid) {
+	if (nlmsvc_serv) {
 		if (proto)
 			error = make_socks(nlmsvc_serv, proto);
 		goto out;
@@ -295,13 +286,28 @@ lockd_up(int proto) /* Maybe add a 'family' option when IPv6 is supported ?? */
 	/*
 	 * Create the kernel thread and wait for it to start.
 	 */
-	error = svc_create_thread(lockd, serv);
-	if (error) {
+	rqstp = svc_prepare_thread(serv, &serv->sv_pools[0]);
+	if (IS_ERR(rqstp)) {
+		error = PTR_ERR(rqstp);
 		printk(KERN_WARNING
-			"lockd_up: create thread failed, error=%d\n", error);
+			"lockd_up: svc_rqst allocation failed, error=%d\n",
+			error);
+		goto destroy_and_out;
+	}
+
+	svc_sock_update_bufs(serv);
+	nlmsvc_serv = rqstp->rq_server;
+
+	nlmsvc_task = kthread_run(lockd, rqstp, serv->sv_name);
+	if (IS_ERR(nlmsvc_task)) {
+		error = PTR_ERR(nlmsvc_task);
+		nlmsvc_task = NULL;
+		nlmsvc_serv = NULL;
+		printk(KERN_WARNING
+			"lockd_up: kthread_run failed, error=%d\n", error);
+		svc_exit_thread(rqstp);
 		goto destroy_and_out;
 	}
-	wait_for_completion(&lockd_start_done);

 	/*
 	 * Note: svc_serv structures have an initial use count of 1,
@@ -323,37 +329,21 @@ EXPORT_SYMBOL(lockd_up);
 void
 lockd_down(void)
 {
-	static int warned;
-
 	mutex_lock(&nlmsvc_mutex);
 	if (nlmsvc_users) {
 		if (--nlmsvc_users)
 			goto out;
-	} else
-		printk(KERN_WARNING "lockd_down: no users! pid=%d\n", nlmsvc_pid);
-
-	if (!nlmsvc_pid) {
-		if (warned++ == 0)
-			printk(KERN_WARNING "lockd_down: no lockd running.\n"); 
-		goto out;
+	} else {
+		printk(KERN_ERR "lockd_down: no users! task=%p\n",
+			nlmsvc_task);
+		BUG();
 	}
-	warned = 0;

-	kill_proc(nlmsvc_pid, SIGKILL, 1);
-	/*
-	 * Wait for the lockd process to exit, but since we're holding
-	 * the lockd semaphore, we can't wait around forever ...
-	 */
-	clear_thread_flag(TIF_SIGPENDING);
-	interruptible_sleep_on_timeout(&lockd_exit, HZ);
-	if (nlmsvc_pid) {
-		printk(KERN_WARNING 
-			"lockd_down: lockd failed to exit, clearing pid\n");
-		nlmsvc_pid = 0;
+	if (!nlmsvc_task) {
+		printk(KERN_ERR "lockd_down: no lockd running.\n");
+		BUG();
 	}
-	spin_lock_irq(&current->sighand->siglock);
-	recalc_sigpending();
-	spin_unlock_irq(&current->sighand->siglock);
+	kthread_stop(nlmsvc_task);
 out:
 	mutex_unlock(&nlmsvc_mutex);
 }
@@ -29,6 +29,7 @@
 #include <linux/sunrpc/svc.h>
 #include <linux/lockd/nlm.h>
 #include <linux/lockd/lockd.h>
+#include <linux/kthread.h>

 #define NLMDBG_FACILITY		NLMDBG_SVCLOCK

@@ -226,8 +227,7 @@ failed:
 }

 /*
- * Delete a block. If the lock was cancelled or the grant callback
- * failed, unlock is set to 1.
+ * Delete a block.
 * It is the caller's responsibility to check whether the file
 * can be closed hereafter.
 */
@@ -887,7 +887,7 @@ nlmsvc_retry_blocked(void)
 	unsigned long	timeout = MAX_SCHEDULE_TIMEOUT;
 	struct nlm_block *block;

-	while (!list_empty(&nlm_blocked)) {
+	while (!list_empty(&nlm_blocked) && !kthread_should_stop()) {
 		block = list_entry(nlm_blocked.next, struct nlm_block, b_list);

 		if (block->b_when == NLM_NEVER)
@@ -71,7 +71,8 @@ nlmsvc_unshare_file(struct nlm_host *host, struct nlm_file *file,
 	struct nlm_share	*share, **shpp;
 	struct xdr_netobj	*oh = &argp->lock.oh;

-	for (shpp = &file->f_shares; (share = *shpp) != 0; shpp = &share->s_next) {
+	for (shpp = &file->f_shares; (share = *shpp) != NULL;
+					shpp = &share->s_next) {
 		if (share->s_host == host && nlm_cmp_owner(share, oh)) {
 			*shpp = share->s_next;
 			kfree(share);
@@ -15,6 +15,7 @@
 #include <linux/nfs_fs.h>
 #include <linux/mutex.h>
 #include <linux/freezer.h>
+#include <linux/kthread.h>

 #include <net/inet_sock.h>

@@ -27,9 +28,7 @@
 struct nfs_callback_data {
 	unsigned int users;
 	struct svc_serv *serv;
-	pid_t pid;
-	struct completion started;
-	struct completion stopped;
+	struct task_struct *task;
 };

 static struct nfs_callback_data nfs_callback_info;
@@ -57,48 +56,44 @@ module_param_call(callback_tcpport, param_set_port, param_get_int,
 /*
 * This is the callback kernel thread.
 */
-static void nfs_callback_svc(struct svc_rqst *rqstp)
+static int
+nfs_callback_svc(void *vrqstp)
 {
-	int err;
+	int err, preverr = 0;
+	struct svc_rqst *rqstp = vrqstp;

-	__module_get(THIS_MODULE);
-	lock_kernel();
-
-	nfs_callback_info.pid = current->pid;
-	daemonize("nfsv4-svc");
-	/* Process request with signals blocked, but allow SIGKILL.  */
-	allow_signal(SIGKILL);
 	set_freezable();

-	complete(&nfs_callback_info.started);
-
-	for(;;) {
-		if (signalled()) {
-			if (nfs_callback_info.users == 0)
-				break;
-			flush_signals(current);
-		}
+	/*
+	 * FIXME: do we really need to run this under the BKL? If so, please
+	 * add a comment about what it's intended to protect.
+	 */
+	lock_kernel();
+	while (!kthread_should_stop()) {
 		/*
 		 * Listen for a request on the socket
 		 */
 		err = svc_recv(rqstp, MAX_SCHEDULE_TIMEOUT);
-		if (err == -EAGAIN || err == -EINTR)
+		if (err == -EAGAIN || err == -EINTR) {
+			preverr = err;
 			continue;
-		if (err < 0) {
-			printk(KERN_WARNING
-					"%s: terminating on error %d\n",
-					__FUNCTION__, -err);
-			break;
 		}
+		if (err < 0) {
+			if (err != preverr) {
+				printk(KERN_WARNING "%s: unexpected error "
+					"from svc_recv (%d)\n", __func__, err);
+				preverr = err;
+			}
+			schedule_timeout_uninterruptible(HZ);
+			continue;
+		}
+		preverr = err;
 		svc_process(rqstp);
 	}
-
-	flush_signals(current);
-	svc_exit_thread(rqstp);
-	nfs_callback_info.pid = 0;
-	complete(&nfs_callback_info.stopped);
 	unlock_kernel();
-	module_put_and_exit(0);
+	nfs_callback_info.task = NULL;
+	svc_exit_thread(rqstp);
+	return 0;
 }

 /*
@@ -107,14 +102,13 @@ static void nfs_callback_svc(struct svc_rqst *rqstp)
 int nfs_callback_up(void)
 {
 	struct svc_serv *serv = NULL;
+	struct svc_rqst *rqstp;
 	int ret = 0;

 	lock_kernel();
 	mutex_lock(&nfs_callback_mutex);
-	if (nfs_callback_info.users++ || nfs_callback_info.pid != 0)
+	if (nfs_callback_info.users++ || nfs_callback_info.task != NULL)
 		goto out;
-	init_completion(&nfs_callback_info.started);
-	init_completion(&nfs_callback_info.stopped);
 	serv = svc_create(&nfs4_callback_program, NFS4_CALLBACK_BUFSIZE, NULL);
 	ret = -ENOMEM;
 	if (!serv)
@@ -127,15 +121,28 @@ int nfs_callback_up(void)
 	nfs_callback_tcpport = ret;
 	dprintk("Callback port = 0x%x\n", nfs_callback_tcpport);

-	ret = svc_create_thread(nfs_callback_svc, serv);
-	if (ret < 0)
+	rqstp = svc_prepare_thread(serv, &serv->sv_pools[0]);
+	if (IS_ERR(rqstp)) {
+		ret = PTR_ERR(rqstp);
 		goto out_err;
+	}
+
+	svc_sock_update_bufs(serv);
 	nfs_callback_info.serv = serv;
-	wait_for_completion(&nfs_callback_info.started);
+
+	nfs_callback_info.task = kthread_run(nfs_callback_svc, rqstp,
+					     "nfsv4-svc");
+	if (IS_ERR(nfs_callback_info.task)) {
+		ret = PTR_ERR(nfs_callback_info.task);
+		nfs_callback_info.serv = NULL;
+		nfs_callback_info.task = NULL;
+		svc_exit_thread(rqstp);
+		goto out_err;
+	}
 out:
 	/*
 	 * svc_create creates the svc_serv with sv_nrthreads == 1, and then
-	 * svc_create_thread increments that. So we need to call svc_destroy
+	 * svc_prepare_thread increments that. So we need to call svc_destroy
 	 * on both success and failure so that the refcount is 1 when the
 	 * thread exits.
 	 */
@@ -152,19 +159,15 @@ out_err:
 }

 /*
- * Kill the server process if it is not already up.
+ * Kill the server process if it is not already down.
 */
 void nfs_callback_down(void)
 {
 	lock_kernel();
 	mutex_lock(&nfs_callback_mutex);
 	nfs_callback_info.users--;
-	do {
-		if (nfs_callback_info.users != 0 || nfs_callback_info.pid == 0)
-			break;
-		if (kill_proc(nfs_callback_info.pid, SIGKILL, 1) < 0)
-			break;
-	} while (wait_for_completion_timeout(&nfs_callback_info.stopped, 5*HZ) == 0);
+	if (nfs_callback_info.users == 0 && nfs_callback_info.task != NULL)
+		kthread_stop(nfs_callback_info.task);
 	mutex_unlock(&nfs_callback_mutex);
 	unlock_kernel();
 }
@@ -10,7 +10,6 @@
 *  nfs symlink handling code
 */

-#define NFS_NEED_XDR_TYPES
 #include <linux/time.h>
 #include <linux/errno.h>
 #include <linux/sunrpc/clnt.h>
@@ -10,6 +10,7 @@
 #include <linux/sunrpc/svcauth.h>
 #include <linux/nfsd/nfsd.h>
 #include <linux/nfsd/export.h>
+#include "auth.h"

 int nfsexp_flags(struct svc_rqst *rqstp, struct svc_export *exp)
 {
@@ -35,6 +35,7 @@
 #include <linux/lockd/bind.h>
 #include <linux/sunrpc/msg_prot.h>
 #include <linux/sunrpc/gss_api.h>
+#include <net/ipv6.h>

 #define NFSDDBG_FACILITY	NFSDDBG_EXPORT

@@ -1548,6 +1549,7 @@ exp_addclient(struct nfsctl_client *ncp)
 {
 	struct auth_domain	*dom;
 	int			i, err;
+	struct in6_addr addr6;

 	/* First, consistency check. */
 	err = -EINVAL;
@@ -1566,9 +1568,10 @@ exp_addclient(struct nfsctl_client *ncp)
 		goto out_unlock;

 	/* Insert client into hashtable. */
-	for (i = 0; i < ncp->cl_naddr; i++)
-		auth_unix_add_addr(ncp->cl_addrlist[i], dom);
-
+	for (i = 0; i < ncp->cl_naddr; i++) {
+		ipv6_addr_set_v4mapped(ncp->cl_addrlist[i].s_addr, &addr6);
+		auth_unix_add_addr(&addr6, dom);
+	}
 	auth_unix_forget_old(dom);
 	auth_domain_put(dom);

@@ -344,6 +344,21 @@ static struct rpc_version *	nfs_cb_version[] = {
 	&nfs_cb_version4,
 };

+static struct rpc_program cb_program;
+
+static struct rpc_stat cb_stats = {
+		.program	= &cb_program
+};
+
+#define NFS4_CALLBACK 0x40000000
+static struct rpc_program cb_program = {
+		.name 		= "nfs4_cb",
+		.number		= NFS4_CALLBACK,
+		.nrvers		= ARRAY_SIZE(nfs_cb_version),
+		.version	= nfs_cb_version,
+		.stats		= &cb_stats,
+};
+
 /* Reference counting, callback cleanup, etc., all look racy as heck.
 * And why is cb_set an atomic? */

@@ -358,13 +373,12 @@ static int do_probe_callback(void *data)
 		.to_maxval	= (NFSD_LEASE_TIME/2) * HZ,
 		.to_exponential	= 1,
 	};
-	struct rpc_program *	program = &cb->cb_program;
 	struct rpc_create_args args = {
 		.protocol	= IPPROTO_TCP,
 		.address	= (struct sockaddr *)&addr,
 		.addrsize	= sizeof(addr),
 		.timeout	= &timeparms,
-		.program	= program,
+		.program	= &cb_program,
 		.version	= nfs_cb_version[1]->number,
 		.authflavor	= RPC_AUTH_UNIX, /* XXX: need AUTH_GSS... */
 		.flags		= (RPC_CLNT_CREATE_NOPING),
@@ -382,16 +396,8 @@ static int do_probe_callback(void *data)
 	addr.sin_port = htons(cb->cb_port);
 	addr.sin_addr.s_addr = htonl(cb->cb_addr);

-	/* Initialize rpc_program */
-	program->name = "nfs4_cb";
-	program->number = cb->cb_prog;
-	program->nrvers = ARRAY_SIZE(nfs_cb_version);
-	program->version = nfs_cb_version;
-	program->stats = &cb->cb_stat;
-
 	/* Initialize rpc_stat */
-	memset(program->stats, 0, sizeof(cb->cb_stat));
-	program->stats->program = program;
+	memset(args.program->stats, 0, sizeof(struct rpc_stat));

 	/* Create RPC client */
 	client = rpc_create(&args);
@@ -202,7 +202,7 @@ static struct cache_detail idtoname_cache = {
 	.alloc		= ent_alloc,
 };

-int
+static int
 idtoname_parse(struct cache_detail *cd, char *buf, int buflen)
 {
 	struct ent ent, *res;
@@ -1639,6 +1639,7 @@ nfs4_open_delegation(struct svc_fh *fh, struct nfsd4_open *open, struct nfs4_sta
 	locks_init_lock(&fl);
 	fl.fl_lmops = &nfsd_lease_mng_ops;
 	fl.fl_flags = FL_LEASE;
+	fl.fl_type = flag == NFS4_OPEN_DELEGATE_READ? F_RDLCK: F_WRLCK;
 	fl.fl_end = OFFSET_MAX;
 	fl.fl_owner =  (fl_owner_t)dp;
 	fl.fl_file = stp->st_vfs_file;
@@ -1647,8 +1648,7 @@ nfs4_open_delegation(struct svc_fh *fh, struct nfsd4_open *open, struct nfs4_sta
 	/* vfs_setlease checks to see if delegation should be handed out.
 	 * the lock_manager callbacks fl_mylease and fl_change are used
 	 */
-	if ((status = vfs_setlease(stp->st_vfs_file,
-		flag == NFS4_OPEN_DELEGATE_READ? F_RDLCK: F_WRLCK, &flp))) {
+	if ((status = vfs_setlease(stp->st_vfs_file, fl.fl_type, &flp))) {
 		dprintk("NFSD: setlease failed [%d], no delegation\n", status);
 		unhash_delegation(dp);
 		flag = NFS4_OPEN_DELEGATE_NONE;
@@ -1763,10 +1763,6 @@ out:
 	return status;
 }

-static struct workqueue_struct *laundry_wq;
-static void laundromat_main(struct work_struct *);
-static DECLARE_DELAYED_WORK(laundromat_work, laundromat_main);
-
 __be32
 nfsd4_renew(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	    clientid_t *clid)
@@ -1874,7 +1870,11 @@ nfs4_laundromat(void)
 	return clientid_val;
 }

-void
+static struct workqueue_struct *laundry_wq;
+static void laundromat_main(struct work_struct *);
+static DECLARE_DELAYED_WORK(laundromat_work, laundromat_main);
+
+static void
 laundromat_main(struct work_struct *not_used)
 {
 	time_t t;
@@ -1975,6 +1975,26 @@ io_during_grace_disallowed(struct inode *inode, int flags)
 		&& mandatory_lock(inode);
 }

+static int check_stateid_generation(stateid_t *in, stateid_t *ref)
+{
+	/* If the client sends us a stateid from the future, it's buggy: */
+	if (in->si_generation > ref->si_generation)
+		return nfserr_bad_stateid;
+	/*
+	 * The following, however, can happen.  For example, if the
+	 * client sends an open and some IO at the same time, the open
+	 * may bump si_generation while the IO is still in flight.
+	 * Thanks to hard links and renames, the client never knows what
+	 * file an open will affect.  So it could avoid that situation
+	 * only by serializing all opens and IO from the same open
+	 * owner.  To recover from the old_stateid error, the client
+	 * will just have to retry the IO:
+	 */
+	if (in->si_generation < ref->si_generation)
+		return nfserr_old_stateid;
+	return nfs_ok;
+}
+
 /*
 * Checks for stateid operations
 */
@@ -2023,12 +2043,8 @@ nfs4_preprocess_stateid_op(struct svc_fh *current_fh, stateid_t *stateid, int fl
 			goto out;
 		stidp = &stp->st_stateid;
 	}
-	if (stateid->si_generation > stidp->si_generation)
-		goto out;
-
-	/* OLD STATEID */
-	status = nfserr_old_stateid;
-	if (stateid->si_generation < stidp->si_generation)
+	status = check_stateid_generation(stateid, stidp);
+	if (status)
 		goto out;
 	if (stp) {
 		if ((status = nfs4_check_openmode(stp,flags)))
@@ -2036,7 +2052,7 @@ nfs4_preprocess_stateid_op(struct svc_fh *current_fh, stateid_t *stateid, int fl
 		renew_client(stp->st_stateowner->so_client);
 		if (filpp)
 			*filpp = stp->st_vfs_file;
-	} else if (dp) {
+	} else {
 		if ((status = nfs4_check_delegmode(dp, flags)))
 			goto out;
 		renew_client(dp->dl_client);
@@ -2065,6 +2081,7 @@ nfs4_preprocess_seqid_op(struct svc_fh *current_fh, u32 seqid, stateid_t *statei
 {
 	struct nfs4_stateid *stp;
 	struct nfs4_stateowner *sop;
+	__be32 status;

 	dprintk("NFSD: preprocess_seqid_op: seqid=%d " 
 			"stateid = (%08x/%08x/%08x/%08x)\n", seqid,
@@ -2127,7 +2144,7 @@ nfs4_preprocess_seqid_op(struct svc_fh *current_fh, u32 seqid, stateid_t *statei
               }
 	}

-	if ((flags & CHECK_FH) && nfs4_check_fh(current_fh, stp)) {
+	if (nfs4_check_fh(current_fh, stp)) {
 		dprintk("NFSD: preprocess_seqid_op: fh-stateid mismatch!\n");
 		return nfserr_bad_stateid;
 	}
@@ -2150,15 +2167,9 @@ nfs4_preprocess_seqid_op(struct svc_fh *current_fh, u32 seqid, stateid_t *statei
 				" confirmed yet!\n");
 		return nfserr_bad_stateid;
 	}
-	if (stateid->si_generation > stp->st_stateid.si_generation) {
-		dprintk("NFSD: preprocess_seqid_op: future stateid?!\n");
-		return nfserr_bad_stateid;
-	}
-
-	if (stateid->si_generation < stp->st_stateid.si_generation) {
-		dprintk("NFSD: preprocess_seqid_op: old stateid!\n");
-		return nfserr_old_stateid;
-	}
+	status = check_stateid_generation(stateid, &stp->st_stateid);
+	if (status)
+		return status;
 	renew_client(sop->so_client);
 	return nfs_ok;

@@ -2194,7 +2205,7 @@ nfsd4_open_confirm(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,

 	if ((status = nfs4_preprocess_seqid_op(&cstate->current_fh,
 					oc->oc_seqid, &oc->oc_req_stateid,
-					CHECK_FH | CONFIRM | OPEN_STATE,
+					CONFIRM | OPEN_STATE,
 					&oc->oc_stateowner, &stp, NULL)))
 		goto out; 

@@ -2265,7 +2276,7 @@ nfsd4_open_downgrade(struct svc_rqst *rqstp,
 	if ((status = nfs4_preprocess_seqid_op(&cstate->current_fh,
 					od->od_seqid,
 					&od->od_stateid, 
-					CHECK_FH | OPEN_STATE, 
+					OPEN_STATE,
 					&od->od_stateowner, &stp, NULL)))
 		goto out; 

@@ -2318,7 +2329,7 @@ nfsd4_close(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	if ((status = nfs4_preprocess_seqid_op(&cstate->current_fh,
 					close->cl_seqid,
 					&close->cl_stateid, 
-					CHECK_FH | OPEN_STATE | CLOSE_STATE,
+					OPEN_STATE | CLOSE_STATE,
 					&close->cl_stateowner, &stp, NULL)))
 		goto out; 
 	status = nfs_ok;
@@ -2623,7 +2634,7 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 		status = nfs4_preprocess_seqid_op(&cstate->current_fh,
 				        lock->lk_new_open_seqid,
 		                        &lock->lk_new_open_stateid,
-		                        CHECK_FH | OPEN_STATE,
+					OPEN_STATE,
 		                        &lock->lk_replay_owner, &open_stp,
 					lock);
 		if (status)
@@ -2650,7 +2661,7 @@ nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 		status = nfs4_preprocess_seqid_op(&cstate->current_fh,
 				       lock->lk_old_lock_seqid, 
 				       &lock->lk_old_lock_stateid, 
-				       CHECK_FH | LOCK_STATE, 
+				       LOCK_STATE,
 				       &lock->lk_replay_owner, &lock_stp, lock);
 		if (status)
 			goto out;
@@ -2847,7 +2858,7 @@ nfsd4_locku(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	if ((status = nfs4_preprocess_seqid_op(&cstate->current_fh,
 					locku->lu_seqid, 
 					&locku->lu_stateid, 
-					CHECK_FH | LOCK_STATE, 
+					LOCK_STATE,
 					&locku->lu_stateowner, &stp, NULL)))
 		goto out;

@@ -1867,6 +1867,15 @@ out_serverfault:
 	goto out;
 }

+static inline int attributes_need_mount(u32 *bmval)
+{
+	if (bmval[0] & ~(FATTR4_WORD0_RDATTR_ERROR | FATTR4_WORD0_LEASE_TIME))
+		return 1;
+	if (bmval[1] & ~FATTR4_WORD1_MOUNTED_ON_FILEID)
+		return 1;
+	return 0;
+}
+
 static __be32
 nfsd4_encode_dirent_fattr(struct nfsd4_readdir *cd,
 		const char *name, int namlen, __be32 *p, int *buflen)
@@ -1888,9 +1897,7 @@ nfsd4_encode_dirent_fattr(struct nfsd4_readdir *cd,
 	 * we will not follow the cross mount and will fill the attribtutes
 	 * directly from the mountpoint dentry.
 	 */
-	if (d_mountpoint(dentry) &&
-	    (cd->rd_bmval[0] & ~FATTR4_WORD0_RDATTR_ERROR) == 0 &&
-	    (cd->rd_bmval[1] & ~FATTR4_WORD1_MOUNTED_ON_FILEID) == 0)
+	if (d_mountpoint(dentry) && !attributes_need_mount(cd->rd_bmval))
 		ignore_crossmnt = 1;
 	else if (d_mountpoint(dentry)) {
 		int err;
@@ -37,6 +37,7 @@
 #include <linux/nfsd/syscall.h>

 #include <asm/uaccess.h>
+#include <net/ipv6.h>

 /*
 *	We have a single directory with 9 nodes in it.
@@ -149,7 +150,6 @@ static const struct file_operations transaction_ops = {
 	.release	= simple_transaction_release,
 };

-extern struct seq_operations nfs_exports_op;
 static int exports_open(struct inode *inode, struct file *file)
 {
 	return seq_open(file, &nfs_exports_op);
@@ -222,6 +222,7 @@ static ssize_t write_getfs(struct file *file, char *buf, size_t size)
 	struct auth_domain *clp;
 	int err = 0;
 	struct knfsd_fh *res;
+	struct in6_addr in6;

 	if (size < sizeof(*data))
 		return -EINVAL;
@@ -236,7 +237,11 @@ static ssize_t write_getfs(struct file *file, char *buf, size_t size)
 	res = (struct knfsd_fh*)buf;

 	exp_readlock();
-	if (!(clp = auth_unix_lookup(sin->sin_addr)))
+
+	ipv6_addr_set_v4mapped(sin->sin_addr.s_addr, &in6);
+
+	clp = auth_unix_lookup(&in6);
+	if (!clp)
 		err = -EPERM;
 	else {
 		err = exp_rootfh(clp, data->gd_path, res, data->gd_maxlen);
@@ -257,6 +262,7 @@ static ssize_t write_getfd(struct file *file, char *buf, size_t size)
 	int err = 0;
 	struct knfsd_fh fh;
 	char *res;
+	struct in6_addr in6;

 	if (size < sizeof(*data))
 		return -EINVAL;
@@ -271,7 +277,11 @@ static ssize_t write_getfd(struct file *file, char *buf, size_t size)
 	res = buf;
 	sin = (struct sockaddr_in *)&data->gd_addr;
 	exp_readlock();
-	if (!(clp = auth_unix_lookup(sin->sin_addr)))
+
+	ipv6_addr_set_v4mapped(sin->sin_addr.s_addr, &in6);
+
+	clp = auth_unix_lookup(&in6);
+	if (!clp)
 		err = -EPERM;
 	else {
 		err = exp_rootfh(clp, data->gd_path, &fh, NFS_FHSIZE);
@@ -347,8 +357,6 @@ static ssize_t write_filehandle(struct file *file, char *buf, size_t size)
 	return mesg - buf;	
 }

-extern int nfsd_nrthreads(void);
-
 static ssize_t write_threads(struct file *file, char *buf, size_t size)
 {
 	/* if size > 0, look for a number of threads and call nfsd_svc
@@ -371,10 +379,6 @@ static ssize_t write_threads(struct file *file, char *buf, size_t size)
 	return strlen(buf);
 }

-extern int nfsd_nrpools(void);
-extern int nfsd_get_nrthreads(int n, int *);
-extern int nfsd_set_nrthreads(int n, int *);
-
 static ssize_t write_pool_threads(struct file *file, char *buf, size_t size)
 {
 	/* if size > 0, look for an array of number of threads per node
@@ -112,6 +112,124 @@ static __be32 nfsd_setuser_and_check_port(struct svc_rqst *rqstp,
 	return nfserrno(nfsd_setuser(rqstp, exp));
 }

+/*
+ * Use the given filehandle to look up the corresponding export and
+ * dentry.  On success, the results are used to set fh_export and
+ * fh_dentry.
+ */
+static __be32 nfsd_set_fh_dentry(struct svc_rqst *rqstp, struct svc_fh *fhp)
+{
+	struct knfsd_fh	*fh = &fhp->fh_handle;
+	struct fid *fid = NULL, sfid;
+	struct svc_export *exp;
+	struct dentry *dentry;
+	int fileid_type;
+	int data_left = fh->fh_size/4;
+	__be32 error;
+
+	error = nfserr_stale;
+	if (rqstp->rq_vers > 2)
+		error = nfserr_badhandle;
+	if (rqstp->rq_vers == 4 && fh->fh_size == 0)
+		return nfserr_nofilehandle;
+
+	if (fh->fh_version == 1) {
+		int len;
+
+		if (--data_left < 0)
+			return error;
+		if (fh->fh_auth_type != 0)
+			return error;
+		len = key_len(fh->fh_fsid_type) / 4;
+		if (len == 0)
+			return error;
+		if  (fh->fh_fsid_type == FSID_MAJOR_MINOR) {
+			/* deprecated, convert to type 3 */
+			len = key_len(FSID_ENCODE_DEV)/4;
+			fh->fh_fsid_type = FSID_ENCODE_DEV;
+			fh->fh_fsid[0] = new_encode_dev(MKDEV(ntohl(fh->fh_fsid[0]), ntohl(fh->fh_fsid[1])));
+			fh->fh_fsid[1] = fh->fh_fsid[2];
+		}
+		data_left -= len;
+		if (data_left < 0)
+			return error;
+		exp = rqst_exp_find(rqstp, fh->fh_fsid_type, fh->fh_auth);
+		fid = (struct fid *)(fh->fh_auth + len);
+	} else {
+		__u32 tfh[2];
+		dev_t xdev;
+		ino_t xino;
+
+		if (fh->fh_size != NFS_FHSIZE)
+			return error;
+		/* assume old filehandle format */
+		xdev = old_decode_dev(fh->ofh_xdev);
+		xino = u32_to_ino_t(fh->ofh_xino);
+		mk_fsid(FSID_DEV, tfh, xdev, xino, 0, NULL);
+		exp = rqst_exp_find(rqstp, FSID_DEV, tfh);
+	}
+
+	error = nfserr_stale;
+	if (PTR_ERR(exp) == -ENOENT)
+		return error;
+
+	if (IS_ERR(exp))
+		return nfserrno(PTR_ERR(exp));
+
+	error = nfsd_setuser_and_check_port(rqstp, exp);
+	if (error)
+		goto out;
+
+	/*
+	 * Look up the dentry using the NFS file handle.
+	 */
+	error = nfserr_stale;
+	if (rqstp->rq_vers > 2)
+		error = nfserr_badhandle;
+
+	if (fh->fh_version != 1) {
+		sfid.i32.ino = fh->ofh_ino;
+		sfid.i32.gen = fh->ofh_generation;
+		sfid.i32.parent_ino = fh->ofh_dirino;
+		fid = &sfid;
+		data_left = 3;
+		if (fh->ofh_dirino == 0)
+			fileid_type = FILEID_INO32_GEN;
+		else
+			fileid_type = FILEID_INO32_GEN_PARENT;
+	} else
+		fileid_type = fh->fh_fileid_type;
+
+	if (fileid_type == FILEID_ROOT)
+		dentry = dget(exp->ex_path.dentry);
+	else {
+		dentry = exportfs_decode_fh(exp->ex_path.mnt, fid,
+				data_left, fileid_type,
+				nfsd_acceptable, exp);
+	}
+	if (dentry == NULL)
+		goto out;
+	if (IS_ERR(dentry)) {
+		if (PTR_ERR(dentry) != -EINVAL)
+			error = nfserrno(PTR_ERR(dentry));
+		goto out;
+	}
+
+	if (S_ISDIR(dentry->d_inode->i_mode) &&
+			(dentry->d_flags & DCACHE_DISCONNECTED)) {
+		printk("nfsd: find_fh_dentry returned a DISCONNECTED directory: %s/%s\n",
+				dentry->d_parent->d_name.name, dentry->d_name.name);
+	}
+
+	fhp->fh_dentry = dentry;
+	fhp->fh_export = exp;
+	nfsd_nr_verified++;
+	return 0;
+out:
+	exp_put(exp);
+	return error;
+}
+
 /*
 * Perform sanity checks on the dentry in a client's file handle.
 *
@@ -124,115 +242,18 @@ static __be32 nfsd_setuser_and_check_port(struct svc_rqst *rqstp,
 __be32
 fh_verify(struct svc_rqst *rqstp, struct svc_fh *fhp, int type, int access)
 {
-	struct knfsd_fh	*fh = &fhp->fh_handle;
-	struct svc_export *exp = NULL;
+	struct svc_export *exp;
 	struct dentry	*dentry;
-	__be32		error = 0;
+	__be32		error;

 	dprintk("nfsd: fh_verify(%s)\n", SVCFH_fmt(fhp));

 	if (!fhp->fh_dentry) {
-		struct fid *fid = NULL, sfid;
-		int fileid_type;
-		int data_left = fh->fh_size/4;
-
-		error = nfserr_stale;
-		if (rqstp->rq_vers > 2)
-			error = nfserr_badhandle;
-		if (rqstp->rq_vers == 4 && fh->fh_size == 0)
-			return nfserr_nofilehandle;
-
-		if (fh->fh_version == 1) {
-			int len;
-			if (--data_left<0) goto out;
-			switch (fh->fh_auth_type) {
-			case 0: break;
-			default: goto out;
-			}
-			len = key_len(fh->fh_fsid_type) / 4;
-			if (len == 0) goto out;
-			if  (fh->fh_fsid_type == FSID_MAJOR_MINOR) {
-				/* deprecated, convert to type 3 */
-				len = key_len(FSID_ENCODE_DEV)/4;
-				fh->fh_fsid_type = FSID_ENCODE_DEV;
-				fh->fh_fsid[0] = new_encode_dev(MKDEV(ntohl(fh->fh_fsid[0]), ntohl(fh->fh_fsid[1])));
-				fh->fh_fsid[1] = fh->fh_fsid[2];
-			}
-			if ((data_left -= len)<0) goto out;
-			exp = rqst_exp_find(rqstp, fh->fh_fsid_type,
-					    fh->fh_auth);
-			fid = (struct fid *)(fh->fh_auth + len);
-		} else {
-			__u32 tfh[2];
-			dev_t xdev;
-			ino_t xino;
-			if (fh->fh_size != NFS_FHSIZE)
-				goto out;
-			/* assume old filehandle format */
-			xdev = old_decode_dev(fh->ofh_xdev);
-			xino = u32_to_ino_t(fh->ofh_xino);
-			mk_fsid(FSID_DEV, tfh, xdev, xino, 0, NULL);
-			exp = rqst_exp_find(rqstp, FSID_DEV, tfh);
-		}
-
-		error = nfserr_stale;
-		if (PTR_ERR(exp) == -ENOENT)
-			goto out;
-
-		if (IS_ERR(exp)) {
-			error = nfserrno(PTR_ERR(exp));
-			goto out;
-		}
-
-		error = nfsd_setuser_and_check_port(rqstp, exp);
+		error = nfsd_set_fh_dentry(rqstp, fhp);
 		if (error)
 			goto out;
-
-		/*
-		 * Look up the dentry using the NFS file handle.
-		 */
-		error = nfserr_stale;
-		if (rqstp->rq_vers > 2)
-			error = nfserr_badhandle;
-
-		if (fh->fh_version != 1) {
-			sfid.i32.ino = fh->ofh_ino;
-			sfid.i32.gen = fh->ofh_generation;
-			sfid.i32.parent_ino = fh->ofh_dirino;
-			fid = &sfid;
-			data_left = 3;
-			if (fh->ofh_dirino == 0)
-				fileid_type = FILEID_INO32_GEN;
-			else
-				fileid_type = FILEID_INO32_GEN_PARENT;
-		} else
-			fileid_type = fh->fh_fileid_type;
-
-		if (fileid_type == FILEID_ROOT)
-			dentry = dget(exp->ex_path.dentry);
-		else {
-			dentry = exportfs_decode_fh(exp->ex_path.mnt, fid,
-					data_left, fileid_type,
-					nfsd_acceptable, exp);
-		}
-		if (dentry == NULL)
-			goto out;
-		if (IS_ERR(dentry)) {
-			if (PTR_ERR(dentry) != -EINVAL)
-				error = nfserrno(PTR_ERR(dentry));
-			goto out;
-		}
-
-		if (S_ISDIR(dentry->d_inode->i_mode) &&
-		    (dentry->d_flags & DCACHE_DISCONNECTED)) {
-			printk("nfsd: find_fh_dentry returned a DISCONNECTED directory: %s/%s\n",
-			       dentry->d_parent->d_name.name, dentry->d_name.name);
-		}
-
-		fhp->fh_dentry = dentry;
-		fhp->fh_export = exp;
-		nfsd_nr_verified++;
-		cache_get(&exp->h);
+		dentry = fhp->fh_dentry;
+		exp = fhp->fh_export;
 	} else {
 		/*
 		 * just rechecking permissions
@@ -242,7 +263,6 @@ fh_verify(struct svc_rqst *rqstp, struct svc_fh *fhp, int type, int access)
 		dprintk("nfsd: fh_verify - just checking\n");
 		dentry = fhp->fh_dentry;
 		exp = fhp->fh_export;
-		cache_get(&exp->h);
 		/*
 		 * Set user creds for this exportpoint; necessary even
 		 * in the "just checking" case because this may be a
@@ -281,8 +301,6 @@ fh_verify(struct svc_rqst *rqstp, struct svc_fh *fhp, int type, int access)
 			access, ntohl(error));
 	}
 out:
-	if (exp && !IS_ERR(exp))
-		exp_put(exp);
 	if (error == nfserr_stale)
 		nfsdstats.fh_stale++;
 	return error;
@@ -244,7 +244,6 @@ static int nfsd_init_socks(int port)
 	if (error < 0)
 		return error;

-#ifdef CONFIG_NFSD_TCP
 	error = lockd_up(IPPROTO_TCP);
 	if (error >= 0) {
 		error = svc_create_xprt(nfsd_serv, "tcp", port,
@@ -254,7 +253,6 @@ static int nfsd_init_socks(int port)
 	}
 	if (error < 0)
 		return error;
-#endif
 	return 0;
 }

@@ -264,7 +264,6 @@ nfsd_setattr(struct svc_rqst *rqstp, struct svc_fh *fhp, struct iattr *iap,
 	struct inode	*inode;
 	int		accmode = MAY_SATTR;
 	int		ftype = 0;
-	int		imode;
 	__be32		err;
 	int		host_err;
 	int		size_change = 0;
@@ -360,25 +359,25 @@ nfsd_setattr(struct svc_rqst *rqstp, struct svc_fh *fhp, struct iattr *iap,
 		DQUOT_INIT(inode);
 	}

-	imode = inode->i_mode;
+	/* sanitize the mode change */
 	if (iap->ia_valid & ATTR_MODE) {
 		iap->ia_mode &= S_IALLUGO;
-		imode = iap->ia_mode |= (imode & ~S_IALLUGO);
-		/* if changing uid/gid revoke setuid/setgid in mode */
-		if ((iap->ia_valid & ATTR_UID) && iap->ia_uid != inode->i_uid) {
-			iap->ia_valid |= ATTR_KILL_PRIV;
+		iap->ia_mode |= (inode->i_mode & ~S_IALLUGO);
+	}
+
+	/* Revoke setuid/setgid on chown */
+	if (((iap->ia_valid & ATTR_UID) && iap->ia_uid != inode->i_uid) ||
+	    ((iap->ia_valid & ATTR_GID) && iap->ia_gid != inode->i_gid)) {
+		iap->ia_valid |= ATTR_KILL_PRIV;
+		if (iap->ia_valid & ATTR_MODE) {
+			/* we're setting mode too, just clear the s*id bits */
 			iap->ia_mode &= ~S_ISUID;
+			if (iap->ia_mode & S_IXGRP)
+				iap->ia_mode &= ~S_ISGID;
+		} else {
+			/* set ATTR_KILL_* bits and let VFS handle it */
+			iap->ia_valid |= (ATTR_KILL_SUID | ATTR_KILL_SGID);
 		}
-		if ((iap->ia_valid & ATTR_GID) && iap->ia_gid != inode->i_gid)
-			iap->ia_mode &= ~S_ISGID;
-	} else {
-		/*
-		 * Revoke setuid/setgid bit on chown/chgrp
-		 */
-		if ((iap->ia_valid & ATTR_UID) && iap->ia_uid != inode->i_uid)
-			iap->ia_valid |= ATTR_KILL_SUID | ATTR_KILL_PRIV;
-		if ((iap->ia_valid & ATTR_GID) && iap->ia_gid != inode->i_gid)
-			iap->ia_valid |= ATTR_KILL_SGID;
 	}

 	/* Change the attributes. */
@@ -988,7 +987,7 @@ nfsd_vfs_write(struct svc_rqst *rqstp, struct svc_fh *fhp, struct file *file,
 	 * flushing the data to disk is handled separately below.
 	 */

-	if (file->f_op->fsync == 0) {/* COMMIT3 cannot work */
+	if (!file->f_op->fsync) {/* COMMIT3 cannot work */
 	       stable = 2;
 	       *stablep = 2; /* FILE_SYNC */
 	}
@@ -1152,7 +1151,7 @@ nfsd_commit(struct svc_rqst *rqstp, struct svc_fh *fhp,
 }
 #endif /* CONFIG_NFSD_V3 */

-__be32
+static __be32
 nfsd_create_setattr(struct svc_rqst *rqstp, struct svc_fh *resfhp,
 			struct iattr *iap)
 {
@@ -43,7 +43,7 @@ struct fid {
 			u32 parent_ino;
 			u32 parent_gen;
 		} i32;
-		__u32 raw[6];
+		__u32 raw[0];
 	};
 };

@@ -96,7 +96,7 @@ struct nfs3_fh {
 #define MOUNTPROC3_UMNTALL	4
 

-#if defined(__KERNEL__) || defined(NFS_NEED_KERNEL_TYPES)
+#if defined(__KERNEL__)

 /* Number of 32bit words in post_op_attr */
 #define NFS3_POST_OP_ATTR_WORDS		22
--- a/Show More
+++ b/Show More