Merge git://git.linux-nfs.org/projects/trondmy/nfs-2.6

* git://git.linux-nfs.org/projects/trondmy/nfs-2.6: (82 commits)
  NFSv4: Remove BKL from the nfsv4 state recovery
  SUNRPC: Remove the BKL from the callback functions
  NFS: Remove BKL from the readdir code
  NFS: Remove BKL from the symlink code
  NFS: Remove BKL from the sillydelete operations
  NFS: Remove the BKL from the rename, rmdir and unlink operations
  NFS: Remove BKL from NFS lookup code
  NFS: Remove the BKL from nfs_link()
  NFS: Remove the BKL from the inode creation operations
  NFS: Remove BKL usage from open()
  NFS: Remove BKL usage from the write path
  NFS: Remove the BKL from the permission checking code
  NFS: Remove attribute update related BKL references
  NFS: Remove BKL requirement from attribute updates
  NFS: Protect inode->i_nlink updates using inode->i_lock
  nfs: set correct fl_len in nlmclnt_test()
  SUNRPC: Support registering IPv6 interfaces with local rpcbind daemon
  SUNRPC: Refactor rpcb_register to make rpcbindv4 support easier
  SUNRPC: None of rpcb_create's callers wants a privileged source port
  SUNRPC: Introduce a specific rpcb_create for contacting localhost
  ...

fs/Kconfig

@@ -1544,10 +1544,6 @@ config UFS_FS
           The recently released UFS2 variant (used in FreeBSD 5.x) is
           READ-ONLY supported.
 
-	  If you only intend to mount files from some other Unix over the
-	  network using NFS, you don't need the UFS file system support (but
-	  you need NFS file system support obviously).
-
 	  Note that this option is generally not needed for floppies, since a
 	  good portable way to transport files and directories between unixes
 	  (and even other operating systems) is given by the tar program ("man
@@ -1587,6 +1583,7 @@ menuconfig NETWORK_FILESYSTEMS
 	  Say Y here to get to see options for network filesystems and
 	  filesystem-related networking code, such as NFS daemon and
 	  RPCSEC security modules.
+
 	  This option alone does not add any kernel code.
 
 	  If you say N, all options in this submenu will be skipped and
@@ -1595,76 +1592,92 @@ menuconfig NETWORK_FILESYSTEMS
 if NETWORK_FILESYSTEMS
 
 config NFS_FS
-	tristate "NFS file system support"
+	tristate "NFS client support"
 	depends on INET
 	select LOCKD
 	select SUNRPC
 	select NFS_ACL_SUPPORT if NFS_V3_ACL
 	help
-	  If you are connected to some other (usually local) Unix computer
-	  (using SLIP, PLIP, PPP or Ethernet) and want to mount files residing
-	  on that computer (the NFS server) using the Network File Sharing
-	  protocol, say Y. "Mounting files" means that the client can access
-	  the files with usual UNIX commands as if they were sitting on the
-	  client's hard disk. For this to work, the server must run the
-	  programs nfsd and mountd (but does not need to have NFS file system
-	  support enabled in its kernel). NFS is explained in the Network
-	  Administrator's Guide, available from
-	  <http://www.tldp.org/docs.html#guide>, on its man page: "man
-	  nfs", and in the NFS-HOWTO.
-
-	  A superior but less widely used alternative to NFS is provided by
-	  the Coda file system; see "Coda file system support" below.
+	  Choose Y here if you want to access files residing on other
+	  computers using Sun's Network File System protocol.  To compile
+	  this file system support as a module, choose M here: the module
+	  will be called nfs.
 
-	  If you say Y here, you should have said Y to TCP/IP networking also.
-	  This option would enlarge your kernel by about 27 KB.
+	  To mount file systems exported by NFS servers, you also need to
+	  install the user space mount.nfs command which can be found in
+	  the Linux nfs-utils package, available from http://linux-nfs.org/.
+	  Information about using the mount command is available in the
+	  mount(8) man page.  More detail about the Linux NFS client
+	  implementation is available via the nfs(5) man page.
 
-	  To compile this file system support as a module, choose M here: the
-	  module will be called nfs.
+	  Below you can choose which versions of the NFS protocol are
+	  available in the kernel to mount NFS servers.  Support for NFS
+	  version 2 (RFC 1094) is always available when NFS_FS is selected.
 
-	  If you are configuring a diskless machine which will mount its root
-	  file system over NFS at boot time, say Y here and to "Kernel
-	  level IP autoconfiguration" above and to "Root file system on NFS"
-	  below. You cannot compile this driver as a module in this case.
-	  There are two packages designed for booting diskless machines over
-	  the net: netboot, available from
-	  <http://ftp1.sourceforge.net/netboot/>, and Etherboot,
-	  available from <http://ftp1.sourceforge.net/etherboot/>.
+	  To configure a system which mounts its root file system via NFS
+	  at boot time, say Y here, select "Kernel level IP
+	  autoconfiguration" in the NETWORK menu, and select "Root file
+	  system on NFS" below.  You cannot compile this file system as a
+	  module in this case.
 
-	  If you don't know what all this is about, say N.
+	  If unsure, say N.
 
 config NFS_V3
-	bool "Provide NFSv3 client support"
+	bool "NFS client support for NFS version 3"
 	depends on NFS_FS
 	help
-	  Say Y here if you want your NFS client to be able to speak version
-	  3 of the NFS protocol.
+	  This option enables support for version 3 of the NFS protocol
+	  (RFC 1813) in the kernel's NFS client.
 
 	  If unsure, say Y.
 
 config NFS_V3_ACL
-	bool "Provide client support for the NFSv3 ACL protocol extension"
+	bool "NFS client support for the NFSv3 ACL protocol extension"
 	depends on NFS_V3
 	help
-	  Implement the NFSv3 ACL protocol extension for manipulating POSIX
-	  Access Control Lists.  The server should also be compiled with
-	  the NFSv3 ACL protocol extension; see the CONFIG_NFSD_V3_ACL option.
+	  Some NFS servers support an auxiliary NFSv3 ACL protocol that
+	  Sun added to Solaris but 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
+	  ACLs on local files whether this protocol is available or not.
+
+	  Choose Y here if your NFS server supports the Solaris NFSv3 ACL
+	  protocol extension and you want your NFS client to allow
+	  applications to access and modify ACLs on files on the server.
+
+	  Most NFS servers don't support the Solaris NFSv3 ACL protocol
+	  extension.  You can choose N here or specify the "noacl" mount
+	  option to prevent your NFS client from trying to use the NFSv3
+	  ACL protocol.
 
 	  If unsure, say N.
 
 config NFS_V4
-	bool "Provide NFSv4 client support (EXPERIMENTAL)"
+	bool "NFS client support for NFS version 4 (EXPERIMENTAL)"
 	depends on NFS_FS && EXPERIMENTAL
 	select RPCSEC_GSS_KRB5
 	help
-	  Say Y here if you want your NFS client to be able to speak the newer
-	  version 4 of the NFS protocol.
+	  This option enables support for version 4 of the NFS protocol
+	  (RFC 3530) in the kernel's NFS client.
 
-	  Note: Requires auxiliary userspace daemons which may be found on
-		http://www.citi.umich.edu/projects/nfsv4/
+	  To mount NFS servers using NFSv4, you also need to install 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"
+	depends on NFS_FS=y && IP_PNP
+	help
+	  If you want your system to mount its root file system via NFS,
+	  choose Y here.  This is common practice for managing systems
+	  without local permanent storage.  For details, read
+	  <file:Documentation/filesystems/nfsroot.txt>.
+
+	  Most people say N here.
+
 config NFSD
 	tristate "NFS server support"
 	depends on INET
@@ -1746,20 +1759,6 @@ config NFSD_V4
 
 	  If unsure, say N.
 
-config ROOT_NFS
-	bool "Root file system on NFS"
-	depends on NFS_FS=y && IP_PNP
-	help
-	  If you want your Linux box to mount its whole root file system (the
-	  one containing the directory /) from some other computer over the
-	  net via NFS (presumably because your box doesn't have a hard disk),
-	  say Y. Read <file:Documentation/filesystems/nfsroot.txt> for
-	  details. It is likely that in this case, you also want to say Y to
-	  "Kernel level IP autoconfiguration" so that your box can discover
-	  its network address at boot time.
-
-	  Most people say N here.
-
 config LOCKD
 	tristate
 
@@ -1800,27 +1799,6 @@ config SUNRPC_XPRT_RDMA
 
 	  If unsure, say N.
 
-config SUNRPC_BIND34
-	bool "Support for rpcbind versions 3 & 4 (EXPERIMENTAL)"
-	depends on SUNRPC && EXPERIMENTAL
-	default n
-	help
-	  RPC requests over IPv6 networks require support for larger
-	  addresses when performing an RPC bind.  Sun added support for
-	  IPv6 addressing by creating two new versions of the rpcbind
-	  protocol (RFC 1833).
-
-	  This option enables support in the kernel RPC client for
-	  querying rpcbind servers via versions 3 and 4 of the rpcbind
-	  protocol.  The kernel automatically falls back to version 2
-	  if a remote rpcbind service does not support versions 3 or 4.
-	  By themselves, these new versions do not provide support for
-	  RPC over IPv6, but the new protocol versions are necessary to
-	  support it.
-
-	  If unsure, say N to get traditional behavior (version 2 rpcbind
-	  requests only).
-
 config RPCSEC_GSS_KRB5
 	tristate "Secure RPC: Kerberos V mechanism (EXPERIMENTAL)"
 	depends on SUNRPC && EXPERIMENTAL

fs/lockd/clntproc.c

@@ -224,7 +224,9 @@ void nlm_release_call(struct nlm_rqst *call)
 
 static void nlmclnt_rpc_release(void *data)
 {
+	lock_kernel();
 	nlm_release_call(data);
+	unlock_kernel();
 }
 
 static int nlm_wait_on_grace(wait_queue_head_t *queue)
@@ -430,7 +432,7 @@ nlmclnt_test(struct nlm_rqst *req, struct file_lock *fl)
 			 * Report the conflicting lock back to the application.
 			 */
 			fl->fl_start = req->a_res.lock.fl.fl_start;
-			fl->fl_end = req->a_res.lock.fl.fl_start;
+			fl->fl_end = req->a_res.lock.fl.fl_end;
 			fl->fl_type = req->a_res.lock.fl.fl_type;
 			fl->fl_pid = 0;
 			break;
@@ -710,7 +712,9 @@ static void nlmclnt_unlock_callback(struct rpc_task *task, void *data)
 die:
 	return;
  retry_rebind:
+	lock_kernel();
 	nlm_rebind_host(req->a_host);
+	unlock_kernel();
  retry_unlock:
 	rpc_restart_call(task);
 }
@@ -788,7 +792,9 @@ retry_cancel:
 	/* Don't ever retry more than 3 times */
 	if (req->a_retries++ >= NLMCLNT_MAX_RETRIES)
 		goto die;
+	lock_kernel();
 	nlm_rebind_host(req->a_host);
+	unlock_kernel();
 	rpc_restart_call(task);
 	rpc_delay(task, 30 * HZ);
 }

fs/lockd/svc4proc.c

@@ -248,7 +248,9 @@ static void nlm4svc_callback_exit(struct rpc_task *task, void *data)
 
 static void nlm4svc_callback_release(void *data)
 {
+	lock_kernel();
 	nlm_release_call(data);
+	unlock_kernel();
 }
 
 static const struct rpc_call_ops nlm4svc_callback_ops = {

fs/lockd/svclock.c

@@ -795,6 +795,7 @@ static void nlmsvc_grant_callback(struct rpc_task *task, void *data)
 
 	dprintk("lockd: GRANT_MSG RPC callback\n");
 
+	lock_kernel();
 	/* if the block is not on a list at this point then it has
 	 * been invalidated. Don't try to requeue it.
 	 *
@@ -804,7 +805,7 @@ static void nlmsvc_grant_callback(struct rpc_task *task, void *data)
 	 * for nlm_blocked?
 	 */
 	if (list_empty(&block->b_list))
-		return;
+		goto out;
 
 	/* Technically, we should down the file semaphore here. Since we
 	 * move the block towards the head of the queue only, no harm
@@ -818,13 +819,17 @@ static void nlmsvc_grant_callback(struct rpc_task *task, void *data)
 	}
 	nlmsvc_insert_block(block, timeout);
 	svc_wake_up(block->b_daemon);
+out:
+	unlock_kernel();
 }
 
 static void nlmsvc_grant_release(void *data)
 {
 	struct nlm_rqst		*call = data;
 
+	lock_kernel();
 	nlmsvc_release_block(call->a_block);
+	unlock_kernel();
 }
 
 static const struct rpc_call_ops nlmsvc_grant_ops = {

fs/lockd/svcproc.c

@@ -278,7 +278,9 @@ static void nlmsvc_callback_exit(struct rpc_task *task, void *data)
 
 static void nlmsvc_callback_release(void *data)
 {
+	lock_kernel();
 	nlm_release_call(data);
+	unlock_kernel();
 }
 
 static const struct rpc_call_ops nlmsvc_callback_ops = {

fs/nfs/callback.c

@@ -27,7 +27,7 @@
 
 struct nfs_callback_data {
 	unsigned int users;
-	struct svc_serv *serv;
+	struct svc_rqst *rqst;
 	struct task_struct *task;
 };
 
@@ -91,21 +91,17 @@ nfs_callback_svc(void *vrqstp)
 		svc_process(rqstp);
 	}
 	unlock_kernel();
-	nfs_callback_info.task = NULL;
-	svc_exit_thread(rqstp);
 	return 0;
 }
 
 /*
- * Bring up the server process if it is not already up.
+ * Bring up the callback thread if it is not already up.
  */
 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.task != NULL)
 		goto out;
@@ -121,22 +117,23 @@ int nfs_callback_up(void)
 	nfs_callback_tcpport = ret;
 	dprintk("Callback port = 0x%x\n", nfs_callback_tcpport);
 
-	rqstp = svc_prepare_thread(serv, &serv->sv_pools[0]);
-	if (IS_ERR(rqstp)) {
-		ret = PTR_ERR(rqstp);
+	nfs_callback_info.rqst = svc_prepare_thread(serv, &serv->sv_pools[0]);
+	if (IS_ERR(nfs_callback_info.rqst)) {
+		ret = PTR_ERR(nfs_callback_info.rqst);
+		nfs_callback_info.rqst = NULL;
 		goto out_err;
 	}
 
 	svc_sock_update_bufs(serv);
-	nfs_callback_info.serv = serv;
 
-	nfs_callback_info.task = kthread_run(nfs_callback_svc, rqstp,
+	nfs_callback_info.task = kthread_run(nfs_callback_svc,
+					     nfs_callback_info.rqst,
 					     "nfsv4-svc");
 	if (IS_ERR(nfs_callback_info.task)) {
 		ret = PTR_ERR(nfs_callback_info.task);
-		nfs_callback_info.serv = NULL;
+		svc_exit_thread(nfs_callback_info.rqst);
+		nfs_callback_info.rqst = NULL;
 		nfs_callback_info.task = NULL;
-		svc_exit_thread(rqstp);
 		goto out_err;
 	}
 out:
@@ -149,7 +146,6 @@ out:
 	if (serv)
 		svc_destroy(serv);
 	mutex_unlock(&nfs_callback_mutex);
-	unlock_kernel();
 	return ret;
 out_err:
 	dprintk("Couldn't create callback socket or server thread; err = %d\n",
@@ -159,17 +155,19 @@ out_err:
 }
 
 /*
- * Kill the server process if it is not already down.
+ * Kill the callback thread if it's no longer being used.
  */
 void nfs_callback_down(void)
 {
-	lock_kernel();
 	mutex_lock(&nfs_callback_mutex);
 	nfs_callback_info.users--;
-	if (nfs_callback_info.users == 0 && nfs_callback_info.task != NULL)
+	if (nfs_callback_info.users == 0 && nfs_callback_info.task != NULL) {
 		kthread_stop(nfs_callback_info.task);
+		svc_exit_thread(nfs_callback_info.rqst);
+		nfs_callback_info.rqst = NULL;
+		nfs_callback_info.task = NULL;
+	}
 	mutex_unlock(&nfs_callback_mutex);
-	unlock_kernel();
 }
 
 static int nfs_callback_authenticate(struct svc_rqst *rqstp)

fs/nfs/client.c

@@ -431,14 +431,14 @@ static void nfs_init_timeout_values(struct rpc_timeout *to, int proto,
 {
 	to->to_initval = timeo * HZ / 10;
 	to->to_retries = retrans;
-	if (!to->to_retries)
-		to->to_retries = 2;
 
 	switch (proto) {
 	case XPRT_TRANSPORT_TCP:
 	case XPRT_TRANSPORT_RDMA:
+		if (to->to_retries == 0)
+			to->to_retries = NFS_DEF_TCP_RETRANS;
 		if (to->to_initval == 0)
-			to->to_initval = 60 * HZ;
+			to->to_initval = NFS_DEF_TCP_TIMEO * HZ / 10;
 		if (to->to_initval > NFS_MAX_TCP_TIMEOUT)
 			to->to_initval = NFS_MAX_TCP_TIMEOUT;
 		to->to_increment = to->to_initval;
@@ -450,14 +450,17 @@ static void nfs_init_timeout_values(struct rpc_timeout *to, int proto,
 		to->to_exponential = 0;
 		break;
 	case XPRT_TRANSPORT_UDP:
-	default:
+		if (to->to_retries == 0)
+			to->to_retries = NFS_DEF_UDP_RETRANS;
 		if (!to->to_initval)
-			to->to_initval = 11 * HZ / 10;
+			to->to_initval = NFS_DEF_UDP_TIMEO * HZ / 10;
 		if (to->to_initval > NFS_MAX_UDP_TIMEOUT)
 			to->to_initval = NFS_MAX_UDP_TIMEOUT;
 		to->to_maxval = NFS_MAX_UDP_TIMEOUT;
 		to->to_exponential = 1;
 		break;
+	default:
+		BUG();
 	}
 }
 

fs/nfs/dir.c

@@ -133,13 +133,14 @@ nfs_opendir(struct inode *inode, struct file *filp)
 {
 	int res;
 
-	dfprintk(VFS, "NFS: opendir(%s/%ld)\n",
-			inode->i_sb->s_id, inode->i_ino);
+	dfprintk(FILE, "NFS: open dir(%s/%s)\n",
+			filp->f_path.dentry->d_parent->d_name.name,
+			filp->f_path.dentry->d_name.name);
+
+	nfs_inc_stats(inode, NFSIOS_VFSOPEN);
 
-	lock_kernel();
 	/* Call generic open code in order to cache credentials */
 	res = nfs_open(inode, filp);
-	unlock_kernel();
 	return res;
 }
 
@@ -528,13 +529,11 @@ static int nfs_readdir(struct file *filp, void *dirent, filldir_t filldir)
 	struct nfs_fattr fattr;
 	long		res;
 
-	dfprintk(VFS, "NFS: readdir(%s/%s) starting at cookie %Lu\n",
+	dfprintk(FILE, "NFS: readdir(%s/%s) starting at cookie %llu\n",
 			dentry->d_parent->d_name.name, dentry->d_name.name,
 			(long long)filp->f_pos);
 	nfs_inc_stats(inode, NFSIOS_VFSGETDENTS);
 
-	lock_kernel();
-
 	/*
 	 * filp->f_pos points to the dirent entry number.
 	 * *desc->dir_cookie has the cookie for the next entry. We have
@@ -592,10 +591,9 @@ static int nfs_readdir(struct file *filp, void *dirent, filldir_t filldir)
 	}
 out:
 	nfs_unblock_sillyrename(dentry);
-	unlock_kernel();
 	if (res > 0)
 		res = 0;
-	dfprintk(VFS, "NFS: readdir(%s/%s) returns %ld\n",
+	dfprintk(FILE, "NFS: readdir(%s/%s) returns %ld\n",
 			dentry->d_parent->d_name.name, dentry->d_name.name,
 			res);
 	return res;
@@ -603,7 +601,15 @@ out:
 
 static loff_t nfs_llseek_dir(struct file *filp, loff_t offset, int origin)
 {
-	mutex_lock(&filp->f_path.dentry->d_inode->i_mutex);
+	struct dentry *dentry = filp->f_path.dentry;
+	struct inode *inode = dentry->d_inode;
+
+	dfprintk(FILE, "NFS: llseek dir(%s/%s, %lld, %d)\n",
+			dentry->d_parent->d_name.name,
+			dentry->d_name.name,
+			offset, origin);
+
+	mutex_lock(&inode->i_mutex);
 	switch (origin) {
 		case 1:
 			offset += filp->f_pos;
@@ -619,7 +625,7 @@ static loff_t nfs_llseek_dir(struct file *filp, loff_t offset, int origin)
 		nfs_file_open_context(filp)->dir_cookie = 0;
 	}
 out:
-	mutex_unlock(&filp->f_path.dentry->d_inode->i_mutex);
+	mutex_unlock(&inode->i_mutex);
 	return offset;
 }
 
@@ -629,10 +635,11 @@ out:
  */
 static int nfs_fsync_dir(struct file *filp, struct dentry *dentry, int datasync)
 {
-	dfprintk(VFS, "NFS: fsync_dir(%s/%s) datasync %d\n",
+	dfprintk(FILE, "NFS: fsync dir(%s/%s) datasync %d\n",
 			dentry->d_parent->d_name.name, dentry->d_name.name,
 			datasync);
 
+	nfs_inc_stats(dentry->d_inode, NFSIOS_VFSFSYNC);
 	return 0;
 }
 
@@ -767,7 +774,6 @@ static int nfs_lookup_revalidate(struct dentry * dentry, struct nameidata *nd)
 	struct nfs_fattr fattr;
 
 	parent = dget_parent(dentry);
-	lock_kernel();
 	dir = parent->d_inode;
 	nfs_inc_stats(dir, NFSIOS_DENTRYREVALIDATE);
 	inode = dentry->d_inode;
@@ -805,7 +811,6 @@ static int nfs_lookup_revalidate(struct dentry * dentry, struct nameidata *nd)
 
 	nfs_set_verifier(dentry, nfs_save_change_attribute(dir));
  out_valid:
-	unlock_kernel();
 	dput(parent);
 	dfprintk(LOOKUPCACHE, "NFS: %s(%s/%s) is valid\n",
 			__func__, dentry->d_parent->d_name.name,
@@ -824,7 +829,6 @@ out_zap_parent:
 		shrink_dcache_parent(dentry);
 	}
 	d_drop(dentry);
-	unlock_kernel();
 	dput(parent);
 	dfprintk(LOOKUPCACHE, "NFS: %s(%s/%s) is invalid\n",
 			__func__, dentry->d_parent->d_name.name,
@@ -858,6 +862,14 @@ static int nfs_dentry_delete(struct dentry *dentry)
 
 }
 
+static void nfs_drop_nlink(struct inode *inode)
+{
+	spin_lock(&inode->i_lock);
+	if (inode->i_nlink > 0)
+		drop_nlink(inode);
+	spin_unlock(&inode->i_lock);
+}
+
 /*
  * Called when the dentry loses inode.
  * We use it to clean up silly-renamed files.
@@ -869,10 +881,8 @@ static void nfs_dentry_iput(struct dentry *dentry, struct inode *inode)
 		NFS_I(inode)->cache_validity |= NFS_INO_INVALID_DATA;
 
 	if (dentry->d_flags & DCACHE_NFSFS_RENAMED) {
-		lock_kernel();
 		drop_nlink(inode);
 		nfs_complete_unlink(dentry, inode);
-		unlock_kernel();
 	}
 	iput(inode);
 }
@@ -903,8 +913,6 @@ static struct dentry *nfs_lookup(struct inode *dir, struct dentry * dentry, stru
 	res = ERR_PTR(-ENOMEM);
 	dentry->d_op = NFS_PROTO(dir)->dentry_ops;
 
-	lock_kernel();
-
 	/*
 	 * If we're doing an exclusive create, optimize away the lookup
 	 * but don't hash the dentry.
@@ -912,7 +920,7 @@ static struct dentry *nfs_lookup(struct inode *dir, struct dentry * dentry, stru
 	if (nfs_is_exclusive_create(dir, nd)) {
 		d_instantiate(dentry, NULL);
 		res = NULL;
-		goto out_unlock;
+		goto out;
 	}
 
 	parent = dentry->d_parent;
@@ -940,8 +948,6 @@ no_entry:
 	nfs_set_verifier(dentry, nfs_save_change_attribute(dir));
 out_unblock_sillyrename:
 	nfs_unblock_sillyrename(parent);
-out_unlock:
-	unlock_kernel();
 out:
 	return res;
 }
@@ -999,9 +1005,7 @@ static struct dentry *nfs_atomic_lookup(struct inode *dir, struct dentry *dentry
 	}
 
 	/* Open the file on the server */
-	lock_kernel();
 	res = nfs4_atomic_open(dir, dentry, nd);
-	unlock_kernel();
 	if (IS_ERR(res)) {
 		error = PTR_ERR(res);
 		switch (error) {
@@ -1063,9 +1067,7 @@ static int nfs_open_revalidate(struct dentry *dentry, struct nameidata *nd)
 	 * operations that change the directory. We therefore save the
 	 * change attribute *before* we do the RPC call.
 	 */
-	lock_kernel();
 	ret = nfs4_open_revalidate(dir, dentry, openflags, nd);
-	unlock_kernel();
 out:
 	dput(parent);
 	if (!ret)
@@ -1218,14 +1220,11 @@ static int nfs_create(struct inode *dir, struct dentry *dentry, int mode,
 	if ((nd->flags & LOOKUP_CREATE) != 0)
 		open_flags = nd->intent.open.flags;
 
-	lock_kernel();
 	error = NFS_PROTO(dir)->create(dir, dentry, &attr, open_flags, nd);
 	if (error != 0)
 		goto out_err;
-	unlock_kernel();
 	return 0;
 out_err:
-	unlock_kernel();
 	d_drop(dentry);
 	return error;
 }
@@ -1248,14 +1247,11 @@ nfs_mknod(struct inode *dir, struct dentry *dentry, int mode, dev_t rdev)
 	attr.ia_mode = mode;
 	attr.ia_valid = ATTR_MODE;
 
-	lock_kernel();
 	status = NFS_PROTO(dir)->mknod(dir, dentry, &attr, rdev);
 	if (status != 0)
 		goto out_err;
-	unlock_kernel();
 	return 0;
 out_err:
-	unlock_kernel();
 	d_drop(dentry);
 	return status;
 }
@@ -1274,15 +1270,12 @@ static int nfs_mkdir(struct inode *dir, struct dentry *dentry, int mode)
 	attr.ia_valid = ATTR_MODE;
 	attr.ia_mode = mode | S_IFDIR;
 
-	lock_kernel();
 	error = NFS_PROTO(dir)->mkdir(dir, dentry, &attr);
 	if (error != 0)
 		goto out_err;
-	unlock_kernel();
 	return 0;
 out_err:
 	d_drop(dentry);
-	unlock_kernel();
 	return error;
 }
 
@@ -1299,14 +1292,12 @@ static int nfs_rmdir(struct inode *dir, struct dentry *dentry)
 	dfprintk(VFS, "NFS: rmdir(%s/%ld), %s\n",
 			dir->i_sb->s_id, dir->i_ino, dentry->d_name.name);
 
-	lock_kernel();
 	error = NFS_PROTO(dir)->rmdir(dir, &dentry->d_name);
 	/* Ensure the VFS deletes this inode */
 	if (error == 0 && dentry->d_inode != NULL)
 		clear_nlink(dentry->d_inode);
 	else if (error == -ENOENT)
 		nfs_dentry_handle_enoent(dentry);
-	unlock_kernel();
 
 	return error;
 }
@@ -1408,7 +1399,7 @@ static int nfs_safe_remove(struct dentry *dentry)
 		error = NFS_PROTO(dir)->remove(dir, &dentry->d_name);
 		/* The VFS may want to delete this inode */
 		if (error == 0)
-			drop_nlink(inode);
+			nfs_drop_nlink(inode);
 		nfs_mark_for_revalidate(inode);
 	} else
 		error = NFS_PROTO(dir)->remove(dir, &dentry->d_name);
@@ -1431,7 +1422,6 @@ static int nfs_unlink(struct inode *dir, struct dentry *dentry)
 	dfprintk(VFS, "NFS: unlink(%s/%ld, %s)\n", dir->i_sb->s_id,
 		dir->i_ino, dentry->d_name.name);
 
-	lock_kernel();
 	spin_lock(&dcache_lock);
 	spin_lock(&dentry->d_lock);
 	if (atomic_read(&dentry->d_count) > 1) {
@@ -1440,7 +1430,6 @@ static int nfs_unlink(struct inode *dir, struct dentry *dentry)
 		/* Start asynchronous writeout of the inode */
 		write_inode_now(dentry->d_inode, 0);
 		error = nfs_sillyrename(dir, dentry);
-		unlock_kernel();
 		return error;
 	}
 	if (!d_unhashed(dentry)) {
@@ -1454,7 +1443,6 @@ static int nfs_unlink(struct inode *dir, struct dentry *dentry)
 		nfs_set_verifier(dentry, nfs_save_change_attribute(dir));
 	} else if (need_rehash)
 		d_rehash(dentry);
-	unlock_kernel();
 	return error;
 }
 
@@ -1491,13 +1479,9 @@ static int nfs_symlink(struct inode *dir, struct dentry *dentry, const char *sym
 	attr.ia_mode = S_IFLNK | S_IRWXUGO;
 	attr.ia_valid = ATTR_MODE;
 
-	lock_kernel();
-
 	page = alloc_page(GFP_HIGHUSER);
-	if (!page) {
-		unlock_kernel();
+	if (!page)
 		return -ENOMEM;
-	}
 
 	kaddr = kmap_atomic(page, KM_USER0);
 	memcpy(kaddr, symname, pathlen);
@@ -1512,7 +1496,6 @@ static int nfs_symlink(struct inode *dir, struct dentry *dentry, const char *sym
 			dentry->d_name.name, symname, error);
 		d_drop(dentry);
 		__free_page(page);
-		unlock_kernel();
 		return error;
 	}
 
@@ -1530,7 +1513,6 @@ static int nfs_symlink(struct inode *dir, struct dentry *dentry, const char *sym
 	} else
 		__free_page(page);
 
-	unlock_kernel();
 	return 0;
 }
 
@@ -1544,14 +1526,12 @@ nfs_link(struct dentry *old_dentry, struct inode *dir, struct dentry *dentry)
 		old_dentry->d_parent->d_name.name, old_dentry->d_name.name,
 		dentry->d_parent->d_name.name, dentry->d_name.name);
 
-	lock_kernel();
 	d_drop(dentry);
 	error = NFS_PROTO(dir)->link(inode, dir, &dentry->d_name);
 	if (error == 0) {
 		atomic_inc(&inode->i_count);
 		d_add(dentry, inode);
 	}
-	unlock_kernel();
 	return error;
 }
 
@@ -1591,7 +1571,6 @@ static int nfs_rename(struct inode *old_dir, struct dentry *old_dentry,
 	 * To prevent any new references to the target during the rename,
 	 * we unhash the dentry and free the inode in advance.
 	 */
-	lock_kernel();
 	if (!d_unhashed(new_dentry)) {
 		d_drop(new_dentry);
 		rehash = new_dentry;
@@ -1635,7 +1614,7 @@ static int nfs_rename(struct inode *old_dir, struct dentry *old_dentry,
 			/* dentry still busy? */
 			goto out;
 	} else
-		drop_nlink(new_inode);
+		nfs_drop_nlink(new_inode);
 
 go_ahead:
 	/*
@@ -1669,7 +1648,6 @@ out:
 	/* new dentry created? */
 	if (dentry)
 		dput(dentry);
-	unlock_kernel();
 	return error;
 }
 
@@ -1962,8 +1940,6 @@ int nfs_permission(struct inode *inode, int mask, struct nameidata *nd)
 	}
 
 force_lookup:
-	lock_kernel();
-
 	if (!NFS_PROTO(inode)->access)
 		goto out_notsup;
 
@@ -1973,7 +1949,6 @@ force_lookup:
 		put_rpccred(cred);
 	} else
 		res = PTR_ERR(cred);
-	unlock_kernel();
 out:
 	dfprintk(VFS, "NFS: permission(%s/%ld), mask=0x%x, res=%d\n",
 		inode->i_sb->s_id, inode->i_ino, mask, res);
@@ -1982,7 +1957,6 @@ out_notsup:
 	res = nfs_revalidate_inode(NFS_SERVER(inode), inode);
 	if (res == 0)
 		res = generic_permission(inode, mask, NULL);
-	unlock_kernel();
 	goto out;
 }
 

fs/nfs/direct.c

@@ -890,7 +890,7 @@ ssize_t nfs_file_direct_read(struct kiocb *iocb, const struct iovec *iov,
 	count = iov_length(iov, nr_segs);
 	nfs_add_stats(mapping->host, NFSIOS_DIRECTREADBYTES, count);
 
-	dprintk("nfs: direct read(%s/%s, %zd@%Ld)\n",
+	dfprintk(FILE, "NFS: direct read(%s/%s, %zd@%Ld)\n",
 		file->f_path.dentry->d_parent->d_name.name,
 		file->f_path.dentry->d_name.name,
 		count, (long long) pos);
@@ -947,7 +947,7 @@ ssize_t nfs_file_direct_write(struct kiocb *iocb, const struct iovec *iov,
 	count = iov_length(iov, nr_segs);
 	nfs_add_stats(mapping->host, NFSIOS_DIRECTWRITTENBYTES, count);
 
-	dfprintk(VFS, "nfs: direct write(%s/%s, %zd@%Ld)\n",
+	dfprintk(FILE, "NFS: direct write(%s/%s, %zd@%Ld)\n",
 		file->f_path.dentry->d_parent->d_name.name,
 		file->f_path.dentry->d_name.name,
 		count, (long long) pos);

fs/nfs/file.c

@@ -50,7 +50,7 @@ static ssize_t nfs_file_read(struct kiocb *, const struct iovec *iov,
 static ssize_t nfs_file_write(struct kiocb *, const struct iovec *iov,
 				unsigned long nr_segs, loff_t pos);
 static int  nfs_file_flush(struct file *, fl_owner_t id);
-static int  nfs_fsync(struct file *, struct dentry *dentry, int datasync);
+static int  nfs_file_fsync(struct file *, struct dentry *dentry, int datasync);
 static int nfs_check_flags(int flags);
 static int nfs_lock(struct file *filp, int cmd, struct file_lock *fl);
 static int nfs_flock(struct file *filp, int cmd, struct file_lock *fl);
@@ -72,7 +72,7 @@ const struct file_operations nfs_file_operations = {
 	.open		= nfs_file_open,
 	.flush		= nfs_file_flush,
 	.release	= nfs_file_release,
-	.fsync		= nfs_fsync,
+	.fsync		= nfs_file_fsync,
 	.lock		= nfs_lock,
 	.flock		= nfs_flock,
 	.splice_read	= nfs_file_splice_read,
@@ -119,25 +119,33 @@ nfs_file_open(struct inode *inode, struct file *filp)
 {
 	int res;
 
+	dprintk("NFS: open file(%s/%s)\n",
+			filp->f_path.dentry->d_parent->d_name.name,
+			filp->f_path.dentry->d_name.name);
+
 	res = nfs_check_flags(filp->f_flags);
 	if (res)
 		return res;
 
 	nfs_inc_stats(inode, NFSIOS_VFSOPEN);
-	lock_kernel();
-	res = NFS_PROTO(inode)->file_open(inode, filp);
-	unlock_kernel();
+	res = nfs_open(inode, filp);
 	return res;
 }
 
 static int
 nfs_file_release(struct inode *inode, struct file *filp)
 {
+	struct dentry *dentry = filp->f_path.dentry;
+
+	dprintk("NFS: release(%s/%s)\n",
+			dentry->d_parent->d_name.name,
+			dentry->d_name.name);
+
 	/* Ensure that dirty pages are flushed out with the right creds */
 	if (filp->f_mode & FMODE_WRITE)
-		nfs_wb_all(filp->f_path.dentry->d_inode);
+		nfs_wb_all(dentry->d_inode);
 	nfs_inc_stats(inode, NFSIOS_VFSRELEASE);
-	return NFS_PROTO(inode)->file_release(inode, filp);
+	return nfs_release(inode, filp);
 }
 
 /**
@@ -171,6 +179,12 @@ force_reval:
 static loff_t nfs_file_llseek(struct file *filp, loff_t offset, int origin)
 {
 	loff_t loff;
+
+	dprintk("NFS: llseek file(%s/%s, %lld, %d)\n",
+			filp->f_path.dentry->d_parent->d_name.name,
+			filp->f_path.dentry->d_name.name,
+			offset, origin);
+
 	/* origin == SEEK_END => we must revalidate the cached file length */
 	if (origin == SEEK_END) {
 		struct inode *inode = filp->f_mapping->host;
@@ -185,7 +199,7 @@ static loff_t nfs_file_llseek(struct file *filp, loff_t offset, int origin)
 }
 
 /*
- * Helper for nfs_file_flush() and nfs_fsync()
+ * Helper for nfs_file_flush() and nfs_file_fsync()
  *
  * Notice that it clears the NFS_CONTEXT_ERROR_WRITE before synching to
  * disk, but it retrieves and clears ctx->error after synching, despite
@@ -211,16 +225,18 @@ static int nfs_do_fsync(struct nfs_open_context *ctx, struct inode *inode)
 
 /*
  * Flush all dirty pages, and check for write errors.
- *
  */
 static int
 nfs_file_flush(struct file *file, fl_owner_t id)
 {
 	struct nfs_open_context *ctx = nfs_file_open_context(file);
-	struct inode	*inode = file->f_path.dentry->d_inode;
+	struct dentry	*dentry = file->f_path.dentry;
+	struct inode	*inode = dentry->d_inode;
 	int		status;
 
-	dfprintk(VFS, "nfs: flush(%s/%ld)\n", inode->i_sb->s_id, inode->i_ino);
+	dprintk("NFS: flush(%s/%s)\n",
+			dentry->d_parent->d_name.name,
+			dentry->d_name.name);
 
 	if ((file->f_mode & FMODE_WRITE) == 0)
 		return 0;
@@ -245,7 +261,7 @@ nfs_file_read(struct kiocb *iocb, const struct iovec *iov,
 	if (iocb->ki_filp->f_flags & O_DIRECT)
 		return nfs_file_direct_read(iocb, iov, nr_segs, pos);
 
-	dfprintk(VFS, "nfs: read(%s/%s, %lu@%lu)\n",
+	dprintk("NFS: read(%s/%s, %lu@%lu)\n",
 		dentry->d_parent->d_name.name, dentry->d_name.name,
 		(unsigned long) count, (unsigned long) pos);
 
@@ -265,7 +281,7 @@ nfs_file_splice_read(struct file *filp, loff_t *ppos,
 	struct inode *inode = dentry->d_inode;
 	ssize_t res;
 
-	dfprintk(VFS, "nfs: splice_read(%s/%s, %lu@%Lu)\n",
+	dprintk("NFS: splice_read(%s/%s, %lu@%Lu)\n",
 		dentry->d_parent->d_name.name, dentry->d_name.name,
 		(unsigned long) count, (unsigned long long) *ppos);
 
@@ -282,7 +298,7 @@ nfs_file_mmap(struct file * file, struct vm_area_struct * vma)
 	struct inode *inode = dentry->d_inode;
 	int	status;
 
-	dfprintk(VFS, "nfs: mmap(%s/%s)\n",
+	dprintk("NFS: mmap(%s/%s)\n",
 		dentry->d_parent->d_name.name, dentry->d_name.name);
 
 	status = nfs_revalidate_mapping(inode, file->f_mapping);
@@ -300,12 +316,14 @@ nfs_file_mmap(struct file * file, struct vm_area_struct * vma)
  * whether any write errors occurred for this process.
  */
 static int
-nfs_fsync(struct file *file, struct dentry *dentry, int datasync)
+nfs_file_fsync(struct file *file, struct dentry *dentry, int datasync)
 {
 	struct nfs_open_context *ctx = nfs_file_open_context(file);
 	struct inode *inode = dentry->d_inode;
 
-	dfprintk(VFS, "nfs: fsync(%s/%ld)\n", inode->i_sb->s_id, inode->i_ino);
+	dprintk("NFS: fsync file(%s/%s) datasync %d\n",
+			dentry->d_parent->d_name.name, dentry->d_name.name,
+			datasync);
 
 	nfs_inc_stats(inode, NFSIOS_VFSFSYNC);
 	return nfs_do_fsync(ctx, inode);
@@ -328,6 +346,11 @@ static int nfs_write_begin(struct file *file, struct address_space *mapping,
 	struct page *page;
 	index = pos >> PAGE_CACHE_SHIFT;
 
+	dfprintk(PAGECACHE, "NFS: write_begin(%s/%s(%ld), %u@%lld)\n",
+		file->f_path.dentry->d_parent->d_name.name,
+		file->f_path.dentry->d_name.name,
+		mapping->host->i_ino, len, (long long) pos);
+
 	page = __grab_cache_page(mapping, index);
 	if (!page)
 		return -ENOMEM;
@@ -348,9 +371,32 @@ static int nfs_write_end(struct file *file, struct address_space *mapping,
 	unsigned offset = pos & (PAGE_CACHE_SIZE - 1);
 	int status;
 
-	lock_kernel();
+	dfprintk(PAGECACHE, "NFS: write_end(%s/%s(%ld), %u@%lld)\n",
+		file->f_path.dentry->d_parent->d_name.name,
+		file->f_path.dentry->d_name.name,
+		mapping->host->i_ino, len, (long long) pos);
+
+	/*
+	 * Zero any uninitialised parts of the page, and then mark the page
+	 * as up to date if it turns out that we're extending the file.
+	 */
+	if (!PageUptodate(page)) {
+		unsigned pglen = nfs_page_length(page);
+		unsigned end = offset + len;
+
+		if (pglen == 0) {
+			zero_user_segments(page, 0, offset,
+					end, PAGE_CACHE_SIZE);
+			SetPageUptodate(page);
+		} else if (end >= pglen) {
+			zero_user_segment(page, end, PAGE_CACHE_SIZE);
+			if (offset == 0)
+				SetPageUptodate(page);
+		} else
+			zero_user_segment(page, pglen, PAGE_CACHE_SIZE);
+	}
+
 	status = nfs_updatepage(file, page, offset, copied);
-	unlock_kernel();
 
 	unlock_page(page);
 	page_cache_release(page);
@@ -362,6 +408,8 @@ static int nfs_write_end(struct file *file, struct address_space *mapping,
 
 static void nfs_invalidate_page(struct page *page, unsigned long offset)
 {
+	dfprintk(PAGECACHE, "NFS: invalidate_page(%p, %lu)\n", page, offset);
+
 	if (offset != 0)
 		return;
 	/* Cancel any unstarted writes on this page */
@@ -370,13 +418,20 @@ static void nfs_invalidate_page(struct page *page, unsigned long offset)
 
 static int nfs_release_page(struct page *page, gfp_t gfp)
 {
+	dfprintk(PAGECACHE, "NFS: release_page(%p)\n", page);
+
 	/* If PagePrivate() is set, then the page is not freeable */
 	return 0;
 }
 
 static int nfs_launder_page(struct page *page)
 {
-	return nfs_wb_page(page->mapping->host, page);
+	struct inode *inode = page->mapping->host;
+
+	dfprintk(PAGECACHE, "NFS: launder_page(%ld, %llu)\n",
+		inode->i_ino, (long long)page_offset(page));
+
+	return nfs_wb_page(inode, page);
 }
 
 const struct address_space_operations nfs_file_aops = {
@@ -396,13 +451,19 @@ const struct address_space_operations nfs_file_aops = {
 static int nfs_vm_page_mkwrite(struct vm_area_struct *vma, struct page *page)
 {
 	struct file *filp = vma->vm_file;
+	struct dentry *dentry = filp->f_path.dentry;
 	unsigned pagelen;
 	int ret = -EINVAL;
 	struct address_space *mapping;
 
+	dfprintk(PAGECACHE, "NFS: vm_page_mkwrite(%s/%s(%ld), offset %lld)\n",
+		dentry->d_parent->d_name.name, dentry->d_name.name,
+		filp->f_mapping->host->i_ino,
+		(long long)page_offset(page));
+
 	lock_page(page);
 	mapping = page->mapping;
-	if (mapping != vma->vm_file->f_path.dentry->d_inode->i_mapping)
+	if (mapping != dentry->d_inode->i_mapping)
 		goto out_unlock;
 
 	ret = 0;
@@ -450,9 +511,9 @@ static ssize_t nfs_file_write(struct kiocb *iocb, const struct iovec *iov,
 	if (iocb->ki_filp->f_flags & O_DIRECT)
 		return nfs_file_direct_write(iocb, iov, nr_segs, pos);
 
-	dfprintk(VFS, "nfs: write(%s/%s(%ld), %lu@%Ld)\n",
+	dprintk("NFS: write(%s/%s, %lu@%Ld)\n",
 		dentry->d_parent->d_name.name, dentry->d_name.name,
-		inode->i_ino, (unsigned long) count, (long long) pos);
+		(unsigned long) count, (long long) pos);
 
 	result = -EBUSY;
 	if (IS_SWAPFILE(inode))
@@ -586,7 +647,8 @@ static int do_setlk(struct file *filp, int cmd, struct file_lock *fl)
 	 * This makes locking act as a cache coherency point.
 	 */
 	nfs_sync_mapping(filp->f_mapping);
-	nfs_zap_caches(inode);
+	if (!nfs_have_delegation(inode, FMODE_READ))
+		nfs_zap_caches(inode);
 out:
 	return status;
 }
@@ -596,23 +658,35 @@ out:
  */
 static int nfs_lock(struct file *filp, int cmd, struct file_lock *fl)
 {
-	struct inode * inode = filp->f_mapping->host;
+	struct inode *inode = filp->f_mapping->host;
+	int ret = -ENOLCK;
 
-	dprintk("NFS: nfs_lock(f=%s/%ld, t=%x, fl=%x, r=%Ld:%Ld)\n",
-			inode->i_sb->s_id, inode->i_ino,
+	dprintk("NFS: lock(%s/%s, t=%x, fl=%x, r=%lld:%lld)\n",
+			filp->f_path.dentry->d_parent->d_name.name,
+			filp->f_path.dentry->d_name.name,
 			fl->fl_type, fl->fl_flags,
 			(long long)fl->fl_start, (long long)fl->fl_end);
+
 	nfs_inc_stats(inode, NFSIOS_VFSLOCK);
 
 	/* No mandatory locks over NFS */
 	if (__mandatory_lock(inode) && fl->fl_type != F_UNLCK)
-		return -ENOLCK;
+		goto out_err;
+
+	if (NFS_PROTO(inode)->lock_check_bounds != NULL) {
+		ret = NFS_PROTO(inode)->lock_check_bounds(fl);
+		if (ret < 0)
+			goto out_err;
+	}
 
 	if (IS_GETLK(cmd))
-		return do_getlk(filp, cmd, fl);
-	if (fl->fl_type == F_UNLCK)
-		return do_unlk(filp, cmd, fl);
-	return do_setlk(filp, cmd, fl);
+		ret = do_getlk(filp, cmd, fl);
+	else if (fl->fl_type == F_UNLCK)
+		ret = do_unlk(filp, cmd, fl);
+	else
+		ret = do_setlk(filp, cmd, fl);
+out_err:
+	return ret;
 }
 
 /*
@@ -620,9 +694,9 @@ static int nfs_lock(struct file *filp, int cmd, struct file_lock *fl)
  */
 static int nfs_flock(struct file *filp, int cmd, struct file_lock *fl)
 {
-	dprintk("NFS: nfs_flock(f=%s/%ld, t=%x, fl=%x)\n",
-			filp->f_path.dentry->d_inode->i_sb->s_id,
-			filp->f_path.dentry->d_inode->i_ino,
+	dprintk("NFS: flock(%s/%s, t=%x, fl=%x)\n",
+			filp->f_path.dentry->d_parent->d_name.name,
+			filp->f_path.dentry->d_name.name,
 			fl->fl_type, fl->fl_flags);
 
 	/*
@@ -645,12 +719,15 @@ static int nfs_flock(struct file *filp, int cmd, struct file_lock *fl)
 	return do_setlk(filp, cmd, fl);
 }
 
+/*
+ * There is no protocol support for leases, so we have no way to implement
+ * them correctly in the face of opens by other clients.
+ */
 static int nfs_setlease(struct file *file, long arg, struct file_lock **fl)
 {
-	/*
-	 * There is no protocol support for leases, so we have no way
-	 * to implement them correctly in the face of opens by other
-	 * clients.
-	 */
+	dprintk("NFS: setlease(%s/%s, arg=%ld)\n",
+			file->f_path.dentry->d_parent->d_name.name,
+			file->f_path.dentry->d_name.name, arg);
+
 	return -EINVAL;
 }

fs/nfs/inode.c

@@ -57,8 +57,6 @@ static int enable_ino64 = NFS_64_BIT_INODE_NUMBERS_ENABLED;
 static void nfs_invalidate_inode(struct inode *);
 static int nfs_update_inode(struct inode *, struct nfs_fattr *);
 
-static void nfs_zap_acl_cache(struct inode *);
-
 static struct kmem_cache * nfs_inode_cachep;
 
 static inline unsigned long
@@ -167,7 +165,7 @@ void nfs_zap_mapping(struct inode *inode, struct address_space *mapping)
 	}
 }
 
-static void nfs_zap_acl_cache(struct inode *inode)
+void nfs_zap_acl_cache(struct inode *inode)
 {
 	void (*clear_acl_cache)(struct inode *);
 
@@ -347,7 +345,7 @@ out_no_inode:
 	goto out;
 }
 
-#define NFS_VALID_ATTRS (ATTR_MODE|ATTR_UID|ATTR_GID|ATTR_SIZE|ATTR_ATIME|ATTR_ATIME_SET|ATTR_MTIME|ATTR_MTIME_SET)
+#define NFS_VALID_ATTRS (ATTR_MODE|ATTR_UID|ATTR_GID|ATTR_SIZE|ATTR_ATIME|ATTR_ATIME_SET|ATTR_MTIME|ATTR_MTIME_SET|ATTR_FILE)
 
 int
 nfs_setattr(struct dentry *dentry, struct iattr *attr)
@@ -369,10 +367,9 @@ nfs_setattr(struct dentry *dentry, struct iattr *attr)
 
 	/* Optimization: if the end result is no change, don't RPC */
 	attr->ia_valid &= NFS_VALID_ATTRS;
-	if (attr->ia_valid == 0)
+	if ((attr->ia_valid & ~ATTR_FILE) == 0)
 		return 0;
 
-	lock_kernel();
 	/* Write all dirty data */
 	if (S_ISREG(inode->i_mode)) {
 		filemap_write_and_wait(inode->i_mapping);
@@ -386,10 +383,65 @@ nfs_setattr(struct dentry *dentry, struct iattr *attr)
 	error = NFS_PROTO(inode)->setattr(dentry, &fattr, attr);
 	if (error == 0)
 		nfs_refresh_inode(inode, &fattr);
-	unlock_kernel();
 	return error;
 }
 
+/**
+ * nfs_vmtruncate - unmap mappings "freed" by truncate() syscall
+ * @inode: inode of the file used
+ * @offset: file offset to start truncating
+ *
+ * This is a copy of the common vmtruncate, but with the locking
+ * corrected to take into account the fact that NFS requires
+ * inode->i_size to be updated under the inode->i_lock.
+ */
+static int nfs_vmtruncate(struct inode * inode, loff_t offset)
+{
+	if (i_size_read(inode) < offset) {
+		unsigned long limit;
+
+		limit = current->signal->rlim[RLIMIT_FSIZE].rlim_cur;
+		if (limit != RLIM_INFINITY && offset > limit)
+			goto out_sig;
+		if (offset > inode->i_sb->s_maxbytes)
+			goto out_big;
+		spin_lock(&inode->i_lock);
+		i_size_write(inode, offset);
+		spin_unlock(&inode->i_lock);
+	} else {
+		struct address_space *mapping = inode->i_mapping;
+
+		/*
+		 * truncation of in-use swapfiles is disallowed - it would
+		 * cause subsequent swapout to scribble on the now-freed
+		 * blocks.
+		 */
+		if (IS_SWAPFILE(inode))
+			return -ETXTBSY;
+		spin_lock(&inode->i_lock);
+		i_size_write(inode, offset);
+		spin_unlock(&inode->i_lock);
+
+		/*
+		 * unmap_mapping_range is called twice, first simply for
+		 * efficiency so that truncate_inode_pages does fewer
+		 * single-page unmaps.  However after this first call, and
+		 * before truncate_inode_pages finishes, it is possible for
+		 * private pages to be COWed, which remain after
+		 * truncate_inode_pages finishes, hence the second
+		 * unmap_mapping_range call must be made for correctness.
+		 */
+		unmap_mapping_range(mapping, offset + PAGE_SIZE - 1, 0, 1);
+		truncate_inode_pages(mapping, offset);
+		unmap_mapping_range(mapping, offset + PAGE_SIZE - 1, 0, 1);
+	}
+	return 0;
+out_sig:
+	send_sig(SIGXFSZ, current, 0);
+out_big:
+	return -EFBIG;
+}
+
 /**
  * nfs_setattr_update_inode - Update inode metadata after a setattr call.
  * @inode: pointer to struct inode
@@ -416,8 +468,7 @@ void nfs_setattr_update_inode(struct inode *inode, struct iattr *attr)
 	}
 	if ((attr->ia_valid & ATTR_SIZE) != 0) {
 		nfs_inc_stats(inode, NFSIOS_SETATTRTRUNC);
-		inode->i_size = attr->ia_size;
-		vmtruncate(inode, attr->ia_size);
+		nfs_vmtruncate(inode, attr->ia_size);
 	}
 }
 
@@ -647,7 +698,6 @@ __nfs_revalidate_inode(struct nfs_server *server, struct inode *inode)
 		inode->i_sb->s_id, (long long)NFS_FILEID(inode));
 
 	nfs_inc_stats(inode, NFSIOS_INODEREVALIDATE);
-	lock_kernel();
 	if (is_bad_inode(inode))
  		goto out_nowait;
 	if (NFS_STALE(inode))
@@ -696,7 +746,6 @@ __nfs_revalidate_inode(struct nfs_server *server, struct inode *inode)
 	nfs_wake_up_inode(inode);
 
  out_nowait:
-	unlock_kernel();
 	return status;
 }
 
@@ -831,9 +880,9 @@ static void nfs_wcc_update_inode(struct inode *inode, struct nfs_fattr *fattr)
 			if (S_ISDIR(inode->i_mode))
 				nfsi->cache_validity |= NFS_INO_INVALID_DATA;
 		}
-		if (inode->i_size == nfs_size_to_loff_t(fattr->pre_size) &&
+		if (i_size_read(inode) == nfs_size_to_loff_t(fattr->pre_size) &&
 		    nfsi->npages == 0)
-			inode->i_size = nfs_size_to_loff_t(fattr->size);
+			i_size_write(inode, nfs_size_to_loff_t(fattr->size));
 	}
 }
 
@@ -974,7 +1023,7 @@ int nfs_post_op_update_inode_force_wcc(struct inode *inode, struct nfs_fattr *fa
 			(fattr->valid & NFS_ATTR_WCC) == 0) {
 		memcpy(&fattr->pre_ctime, &inode->i_ctime, sizeof(fattr->pre_ctime));
 		memcpy(&fattr->pre_mtime, &inode->i_mtime, sizeof(fattr->pre_mtime));
-		fattr->pre_size = inode->i_size;
+		fattr->pre_size = i_size_read(inode);
 		fattr->valid |= NFS_ATTR_WCC;
 	}
 	return nfs_post_op_update_inode(inode, fattr);
@@ -1059,7 +1108,7 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
 		/* Do we perhaps have any outstanding writes, or has
 		 * the file grown beyond our last write? */
 		if (nfsi->npages == 0 || new_isize > cur_isize) {
-			inode->i_size = new_isize;
+			i_size_write(inode, new_isize);
 			invalid |= NFS_INO_INVALID_ATTR|NFS_INO_INVALID_DATA;
 		}
 		dprintk("NFS: isize change on server for file %s/%ld\n",

fs/nfs/internal.h

@@ -150,6 +150,7 @@ extern void nfs_clear_inode(struct inode *);
 #ifdef CONFIG_NFS_V4
 extern void nfs4_clear_inode(struct inode *);
 #endif
+void nfs_zap_acl_cache(struct inode *inode);
 
 /* super.c */
 extern struct file_system_type nfs_xdev_fs_type;

fs/nfs/iostat.h

@@ -5,135 +5,41 @@
  *
  *  Copyright (C) 2005, 2006 Chuck Lever <cel@netapp.com>
  *
- *  NFS client per-mount statistics provide information about the health of
- *  the NFS client and the health of each NFS mount point.  Generally these
- *  are not for detailed problem diagnosis, but simply to indicate that there
- *  is a problem.
- *
- *  These counters are not meant to be human-readable, but are meant to be
- *  integrated into system monitoring tools such as "sar" and "iostat".  As
- *  such, the counters are sampled by the tools over time, and are never
- *  zeroed after a file system is mounted.  Moving averages can be computed
- *  by the tools by taking the difference between two instantaneous samples
- *  and dividing that by the time between the samples.
  */
 
 #ifndef _NFS_IOSTAT
 #define _NFS_IOSTAT
 
-#define NFS_IOSTAT_VERS		"1.0"
-
-/*
- * NFS byte counters
- *
- * 1.  SERVER - the number of payload bytes read from or written to the
- *     server by the NFS client via an NFS READ or WRITE request.
- *
- * 2.  NORMAL - the number of bytes read or written by applications via
- *     the read(2) and write(2) system call interfaces.
- *
- * 3.  DIRECT - the number of bytes read or written from files opened
- *     with the O_DIRECT flag.
- *
- * These counters give a view of the data throughput into and out of the NFS
- * client.  Comparing the number of bytes requested by an application with the
- * number of bytes the client requests from the server can provide an
- * indication of client efficiency (per-op, cache hits, etc).
- *
- * These counters can also help characterize which access methods are in
- * use.  DIRECT by itself shows whether there is any O_DIRECT traffic.
- * NORMAL + DIRECT shows how much data is going through the system call
- * interface.  A large amount of SERVER traffic without much NORMAL or
- * DIRECT traffic shows that applications are using mapped files.
- *
- * NFS page counters
- *
- * These count the number of pages read or written via nfs_readpage(),
- * nfs_readpages(), or their write equivalents.
- */
-enum nfs_stat_bytecounters {
-	NFSIOS_NORMALREADBYTES = 0,
-	NFSIOS_NORMALWRITTENBYTES,
-	NFSIOS_DIRECTREADBYTES,
-	NFSIOS_DIRECTWRITTENBYTES,
-	NFSIOS_SERVERREADBYTES,
-	NFSIOS_SERVERWRITTENBYTES,
-	NFSIOS_READPAGES,
-	NFSIOS_WRITEPAGES,
-	__NFSIOS_BYTESMAX,
-};
-
-/*
- * NFS event counters
- *
- * These counters provide a low-overhead way of monitoring client activity
- * without enabling NFS trace debugging.  The counters show the rate at
- * which VFS requests are made, and how often the client invalidates its
- * data and attribute caches.  This allows system administrators to monitor
- * such things as how close-to-open is working, and answer questions such
- * as "why are there so many GETATTR requests on the wire?"
- *
- * They also count anamolous events such as short reads and writes, silly
- * renames due to close-after-delete, and operations that change the size
- * of a file (such operations can often be the source of data corruption
- * if applications aren't using file locking properly).
- */
-enum nfs_stat_eventcounters {
-	NFSIOS_INODEREVALIDATE = 0,
-	NFSIOS_DENTRYREVALIDATE,
-	NFSIOS_DATAINVALIDATE,
-	NFSIOS_ATTRINVALIDATE,
-	NFSIOS_VFSOPEN,
-	NFSIOS_VFSLOOKUP,
-	NFSIOS_VFSACCESS,
-	NFSIOS_VFSUPDATEPAGE,
-	NFSIOS_VFSREADPAGE,
-	NFSIOS_VFSREADPAGES,
-	NFSIOS_VFSWRITEPAGE,
-	NFSIOS_VFSWRITEPAGES,
-	NFSIOS_VFSGETDENTS,
-	NFSIOS_VFSSETATTR,
-	NFSIOS_VFSFLUSH,
-	NFSIOS_VFSFSYNC,
-	NFSIOS_VFSLOCK,
-	NFSIOS_VFSRELEASE,
-	NFSIOS_CONGESTIONWAIT,
-	NFSIOS_SETATTRTRUNC,
-	NFSIOS_EXTENDWRITE,
-	NFSIOS_SILLYRENAME,
-	NFSIOS_SHORTREAD,
-	NFSIOS_SHORTWRITE,
-	NFSIOS_DELAY,
-	__NFSIOS_COUNTSMAX,
-};
-
-#ifdef __KERNEL__
-
 #include <linux/percpu.h>
 #include <linux/cache.h>
+#include <linux/nfs_iostat.h>
 
 struct nfs_iostats {
 	unsigned long long	bytes[__NFSIOS_BYTESMAX];
 	unsigned long		events[__NFSIOS_COUNTSMAX];
 } ____cacheline_aligned;
 
-static inline void nfs_inc_server_stats(struct nfs_server *server, enum nfs_stat_eventcounters stat)
+static inline void nfs_inc_server_stats(const struct nfs_server *server,
+					enum nfs_stat_eventcounters stat)
 {
 	struct nfs_iostats *iostats;
 	int cpu;
 
 	cpu = get_cpu();
 	iostats = per_cpu_ptr(server->io_stats, cpu);
-	iostats->events[stat] ++;
+	iostats->events[stat]++;
 	put_cpu_no_resched();
 }
 
-static inline void nfs_inc_stats(struct inode *inode, enum nfs_stat_eventcounters stat)
+static inline void nfs_inc_stats(const struct inode *inode,
+				 enum nfs_stat_eventcounters stat)
 {
 	nfs_inc_server_stats(NFS_SERVER(inode), stat);
 }
 
-static inline void nfs_add_server_stats(struct nfs_server *server, enum nfs_stat_bytecounters stat, unsigned long addend)
+static inline void nfs_add_server_stats(const struct nfs_server *server,
+					enum nfs_stat_bytecounters stat,
+					unsigned long addend)
 {
 	struct nfs_iostats *iostats;
 	int cpu;
@@ -144,7 +50,9 @@ static inline void nfs_add_server_stats(struct nfs_server *server, enum nfs_stat
 	put_cpu_no_resched();
 }
 
-static inline void nfs_add_stats(struct inode *inode, enum nfs_stat_bytecounters stat, unsigned long addend)
+static inline void nfs_add_stats(const struct inode *inode,
+				 enum nfs_stat_bytecounters stat,
+				 unsigned long addend)
 {
 	nfs_add_server_stats(NFS_SERVER(inode), stat, addend);
 }
@@ -160,5 +68,4 @@ static inline void nfs_free_iostats(struct nfs_iostats *stats)
 		free_percpu(stats);
 }
 
-#endif
-#endif
+#endif /* _NFS_IOSTAT */

fs/nfs/nfs3acl.c

@@ -5,6 +5,8 @@
 #include <linux/posix_acl_xattr.h>
 #include <linux/nfsacl.h>
 
+#include "internal.h"
+
 #define NFSDBG_FACILITY	NFSDBG_PROC
 
 ssize_t nfs3_listxattr(struct dentry *dentry, char *buffer, size_t size)
@@ -205,6 +207,8 @@ struct posix_acl *nfs3_proc_getacl(struct inode *inode, int type)
 	status = nfs_revalidate_inode(server, inode);
 	if (status < 0)
 		return ERR_PTR(status);
+	if (NFS_I(inode)->cache_validity & NFS_INO_INVALID_ACL)
+		nfs_zap_acl_cache(inode);
 	acl = nfs3_get_cached_acl(inode, type);
 	if (acl != ERR_PTR(-EAGAIN))
 		return acl;
@@ -319,9 +323,8 @@ static int nfs3_proc_setacls(struct inode *inode, struct posix_acl *acl,
 	dprintk("NFS call setacl\n");
 	msg.rpc_proc = &server->client_acl->cl_procinfo[ACLPROC3_SETACL];
 	status = rpc_call_sync(server->client_acl, &msg, 0);
-	spin_lock(&inode->i_lock);
-	NFS_I(inode)->cache_validity |= NFS_INO_INVALID_ACCESS;
-	spin_unlock(&inode->i_lock);
+	nfs_access_zap_cache(inode);
+	nfs_zap_acl_cache(inode);
 	dprintk("NFS reply setacl: %d\n", status);
 
 	/* pages may have been allocated at the xdr layer. */

fs/nfs/nfs3proc.c

@@ -129,6 +129,8 @@ nfs3_proc_setattr(struct dentry *dentry, struct nfs_fattr *fattr,
 	int	status;
 
 	dprintk("NFS call  setattr\n");
+	if (sattr->ia_valid & ATTR_FILE)
+		msg.rpc_cred = nfs_file_cred(sattr->ia_file);
 	nfs_fattr_init(fattr);
 	status = rpc_call_sync(NFS_CLIENT(inode), &msg, 0);
 	if (status == 0)
@@ -248,6 +250,53 @@ static int nfs3_proc_readlink(struct inode *inode, struct page *page,
 	return status;
 }
 
+struct nfs3_createdata {
+	struct rpc_message msg;
+	union {
+		struct nfs3_createargs create;
+		struct nfs3_mkdirargs mkdir;
+		struct nfs3_symlinkargs symlink;
+		struct nfs3_mknodargs mknod;
+	} arg;
+	struct nfs3_diropres res;
+	struct nfs_fh fh;
+	struct nfs_fattr fattr;
+	struct nfs_fattr dir_attr;
+};
+
+static struct nfs3_createdata *nfs3_alloc_createdata(void)
+{
+	struct nfs3_createdata *data;
+
+	data = kzalloc(sizeof(*data), GFP_KERNEL);
+	if (data != NULL) {
+		data->msg.rpc_argp = &data->arg;
+		data->msg.rpc_resp = &data->res;
+		data->res.fh = &data->fh;
+		data->res.fattr = &data->fattr;
+		data->res.dir_attr = &data->dir_attr;
+		nfs_fattr_init(data->res.fattr);
+		nfs_fattr_init(data->res.dir_attr);
+	}
+	return data;
+}
+
+static int nfs3_do_create(struct inode *dir, struct dentry *dentry, struct nfs3_createdata *data)
+{
+	int status;
+
+	status = rpc_call_sync(NFS_CLIENT(dir), &data->msg, 0);
+	nfs_post_op_update_inode(dir, data->res.dir_attr);
+	if (status == 0)
+		status = nfs_instantiate(dentry, data->res.fh, data->res.fattr);
+	return status;
+}
+
+static void nfs3_free_createdata(struct nfs3_createdata *data)
+{
+	kfree(data);
+}
+
 /*
  * Create a regular file.
  * For now, we don't implement O_EXCL.
@@ -256,70 +305,60 @@ static int
 nfs3_proc_create(struct inode *dir, struct dentry *dentry, struct iattr *sattr,
 		 int flags, struct nameidata *nd)
 {
-	struct nfs_fh		fhandle;
-	struct nfs_fattr	fattr;
-	struct nfs_fattr	dir_attr;
-	struct nfs3_createargs	arg = {
-		.fh		= NFS_FH(dir),
-		.name		= dentry->d_name.name,
-		.len		= dentry->d_name.len,
-		.sattr		= sattr,
-	};
-	struct nfs3_diropres	res = {
-		.dir_attr	= &dir_attr,
-		.fh		= &fhandle,
-		.fattr		= &fattr
-	};
-	struct rpc_message msg = {
-		.rpc_proc	= &nfs3_procedures[NFS3PROC_CREATE],
-		.rpc_argp	= &arg,
-		.rpc_resp	= &res,
-	};
+	struct nfs3_createdata *data;
 	mode_t mode = sattr->ia_mode;
-	int status;
+	int status = -ENOMEM;
 
 	dprintk("NFS call  create %s\n", dentry->d_name.name);
-	arg.createmode = NFS3_CREATE_UNCHECKED;
+
+	data = nfs3_alloc_createdata();
+	if (data == NULL)
+		goto out;
+
+	data->msg.rpc_proc = &nfs3_procedures[NFS3PROC_CREATE];
+	data->arg.create.fh = NFS_FH(dir);
+	data->arg.create.name = dentry->d_name.name;
+	data->arg.create.len = dentry->d_name.len;
+	data->arg.create.sattr = sattr;
+
+	data->arg.create.createmode = NFS3_CREATE_UNCHECKED;
 	if (flags & O_EXCL) {
-		arg.createmode  = NFS3_CREATE_EXCLUSIVE;
-		arg.verifier[0] = jiffies;
-		arg.verifier[1] = current->pid;
+		data->arg.create.createmode  = NFS3_CREATE_EXCLUSIVE;
+		data->arg.create.verifier[0] = jiffies;
+		data->arg.create.verifier[1] = current->pid;
 	}
 
 	sattr->ia_mode &= ~current->fs->umask;
 
-again:
-	nfs_fattr_init(&dir_attr);
-	nfs_fattr_init(&fattr);
-	status = rpc_call_sync(NFS_CLIENT(dir), &msg, 0);
-	nfs_refresh_inode(dir, &dir_attr);
+	for (;;) {
+		status = nfs3_do_create(dir, dentry, data);
 
-	/* If the server doesn't support the exclusive creation semantics,
-	 * try again with simple 'guarded' mode. */
-	if (status == -ENOTSUPP) {
-		switch (arg.createmode) {
+		if (status != -ENOTSUPP)
+			break;
+		/* If the server doesn't support the exclusive creation
+		 * semantics, try again with simple 'guarded' mode. */
+		switch (data->arg.create.createmode) {
 			case NFS3_CREATE_EXCLUSIVE:
-				arg.createmode = NFS3_CREATE_GUARDED;
+				data->arg.create.createmode = NFS3_CREATE_GUARDED;
 				break;
 
 			case NFS3_CREATE_GUARDED:
-				arg.createmode = NFS3_CREATE_UNCHECKED;
+				data->arg.create.createmode = NFS3_CREATE_UNCHECKED;
 				break;
 
 			case NFS3_CREATE_UNCHECKED:
 				goto out;
 		}
-		goto again;
+		nfs_fattr_init(data->res.dir_attr);
+		nfs_fattr_init(data->res.fattr);
 	}
 
-	if (status == 0)
-		status = nfs_instantiate(dentry, &fhandle, &fattr);
 	if (status != 0)
 		goto out;
 
 	/* When we created the file with exclusive semantics, make
 	 * sure we set the attributes afterwards. */
-	if (arg.createmode == NFS3_CREATE_EXCLUSIVE) {
+	if (data->arg.create.createmode == NFS3_CREATE_EXCLUSIVE) {
 		dprintk("NFS call  setattr (post-create)\n");
 
 		if (!(sattr->ia_valid & ATTR_ATIME_SET))
@@ -330,14 +369,15 @@ again:
 		/* Note: we could use a guarded setattr here, but I'm
 		 * not sure this buys us anything (and I'd have
 		 * to revamp the NFSv3 XDR code) */
-		status = nfs3_proc_setattr(dentry, &fattr, sattr);
-		nfs_post_op_update_inode(dentry->d_inode, &fattr);
+		status = nfs3_proc_setattr(dentry, data->res.fattr, sattr);
+		nfs_post_op_update_inode(dentry->d_inode, data->res.fattr);
 		dprintk("NFS reply setattr (post-create): %d\n", status);
+		if (status != 0)
+			goto out;
 	}
-	if (status != 0)
-		goto out;
 	status = nfs3_proc_set_default_acl(dir, dentry->d_inode, mode);
 out:
+	nfs3_free_createdata(data);
 	dprintk("NFS reply create: %d\n", status);
 	return status;
 }
@@ -452,40 +492,28 @@ static int
 nfs3_proc_symlink(struct inode *dir, struct dentry *dentry, struct page *page,
 		  unsigned int len, struct iattr *sattr)
 {
-	struct nfs_fh fhandle;
-	struct nfs_fattr fattr, dir_attr;
-	struct nfs3_symlinkargs	arg = {
-		.fromfh		= NFS_FH(dir),
-		.fromname	= dentry->d_name.name,
-		.fromlen	= dentry->d_name.len,
-		.pages		= &page,
-		.pathlen	= len,
-		.sattr		= sattr
-	};
-	struct nfs3_diropres	res = {
-		.dir_attr	= &dir_attr,
-		.fh		= &fhandle,
-		.fattr		= &fattr
-	};
-	struct rpc_message msg = {
-		.rpc_proc	= &nfs3_procedures[NFS3PROC_SYMLINK],
-		.rpc_argp	= &arg,
-		.rpc_resp	= &res,
-	};
-	int			status;
+	struct nfs3_createdata *data;
+	int status = -ENOMEM;
 
 	if (len > NFS3_MAXPATHLEN)
 		return -ENAMETOOLONG;
 
 	dprintk("NFS call  symlink %s\n", dentry->d_name.name);
 
-	nfs_fattr_init(&dir_attr);
-	nfs_fattr_init(&fattr);
-	status = rpc_call_sync(NFS_CLIENT(dir), &msg, 0);
-	nfs_post_op_update_inode(dir, &dir_attr);
-	if (status != 0)
+	data = nfs3_alloc_createdata();
+	if (data == NULL)
 		goto out;
-	status = nfs_instantiate(dentry, &fhandle, &fattr);
+	data->msg.rpc_proc = &nfs3_procedures[NFS3PROC_SYMLINK];
+	data->arg.symlink.fromfh = NFS_FH(dir);
+	data->arg.symlink.fromname = dentry->d_name.name;
+	data->arg.symlink.fromlen = dentry->d_name.len;
+	data->arg.symlink.pages = &page;
+	data->arg.symlink.pathlen = len;
+	data->arg.symlink.sattr = sattr;
+
+	status = nfs3_do_create(dir, dentry, data);
+
+	nfs3_free_createdata(data);
 out:
 	dprintk("NFS reply symlink: %d\n", status);
 	return status;
@@ -494,42 +522,31 @@ out:
 static int
 nfs3_proc_mkdir(struct inode *dir, struct dentry *dentry, struct iattr *sattr)
 {
-	struct nfs_fh fhandle;
-	struct nfs_fattr fattr, dir_attr;
-	struct nfs3_mkdirargs	arg = {
-		.fh		= NFS_FH(dir),
-		.name		= dentry->d_name.name,
-		.len		= dentry->d_name.len,
-		.sattr		= sattr
-	};
-	struct nfs3_diropres	res = {
-		.dir_attr	= &dir_attr,
-		.fh		= &fhandle,
-		.fattr		= &fattr
-	};
-	struct rpc_message msg = {
-		.rpc_proc	= &nfs3_procedures[NFS3PROC_MKDIR],
-		.rpc_argp	= &arg,
-		.rpc_resp	= &res,
-	};
+	struct nfs3_createdata *data;
 	int mode = sattr->ia_mode;
-	int status;
+	int status = -ENOMEM;
 
 	dprintk("NFS call  mkdir %s\n", dentry->d_name.name);
 
 	sattr->ia_mode &= ~current->fs->umask;
 
-	nfs_fattr_init(&dir_attr);
-	nfs_fattr_init(&fattr);
-	status = rpc_call_sync(NFS_CLIENT(dir), &msg, 0);
-	nfs_post_op_update_inode(dir, &dir_attr);
-	if (status != 0)
+	data = nfs3_alloc_createdata();
+	if (data == NULL)
 		goto out;
-	status = nfs_instantiate(dentry, &fhandle, &fattr);
+
+	data->msg.rpc_proc = &nfs3_procedures[NFS3PROC_MKDIR];
+	data->arg.mkdir.fh = NFS_FH(dir);
+	data->arg.mkdir.name = dentry->d_name.name;
+	data->arg.mkdir.len = dentry->d_name.len;
+	data->arg.mkdir.sattr = sattr;
+
+	status = nfs3_do_create(dir, dentry, data);
 	if (status != 0)
 		goto out;
+
 	status = nfs3_proc_set_default_acl(dir, dentry->d_inode, mode);
 out:
+	nfs3_free_createdata(data);
 	dprintk("NFS reply mkdir: %d\n", status);
 	return status;
 }
@@ -615,52 +632,50 @@ static int
 nfs3_proc_mknod(struct inode *dir, struct dentry *dentry, struct iattr *sattr,
 		dev_t rdev)
 {
-	struct nfs_fh fh;
-	struct nfs_fattr fattr, dir_attr;
-	struct nfs3_mknodargs	arg = {
-		.fh		= NFS_FH(dir),
-		.name		= dentry->d_name.name,
-		.len		= dentry->d_name.len,
-		.sattr		= sattr,
-		.rdev		= rdev
-	};
-	struct nfs3_diropres	res = {
-		.dir_attr	= &dir_attr,
-		.fh		= &fh,
-		.fattr		= &fattr
-	};
-	struct rpc_message msg = {
-		.rpc_proc	= &nfs3_procedures[NFS3PROC_MKNOD],
-		.rpc_argp	= &arg,
-		.rpc_resp	= &res,
-	};
+	struct nfs3_createdata *data;
 	mode_t mode = sattr->ia_mode;
-	int status;
-
-	switch (sattr->ia_mode & S_IFMT) {
-	case S_IFBLK:	arg.type = NF3BLK;  break;
-	case S_IFCHR:	arg.type = NF3CHR;  break;
-	case S_IFIFO:	arg.type = NF3FIFO; break;
-	case S_IFSOCK:	arg.type = NF3SOCK; break;
-	default:	return -EINVAL;
-	}
+	int status = -ENOMEM;
 
 	dprintk("NFS call  mknod %s %u:%u\n", dentry->d_name.name,
 			MAJOR(rdev), MINOR(rdev));
 
 	sattr->ia_mode &= ~current->fs->umask;
 
-	nfs_fattr_init(&dir_attr);
-	nfs_fattr_init(&fattr);
-	status = rpc_call_sync(NFS_CLIENT(dir), &msg, 0);
-	nfs_post_op_update_inode(dir, &dir_attr);
-	if (status != 0)
+	data = nfs3_alloc_createdata();
+	if (data == NULL)
 		goto out;
-	status = nfs_instantiate(dentry, &fh, &fattr);
+
+	data->msg.rpc_proc = &nfs3_procedures[NFS3PROC_MKNOD];
+	data->arg.mknod.fh = NFS_FH(dir);
+	data->arg.mknod.name = dentry->d_name.name;
+	data->arg.mknod.len = dentry->d_name.len;
+	data->arg.mknod.sattr = sattr;
+	data->arg.mknod.rdev = rdev;
+
+	switch (sattr->ia_mode & S_IFMT) {
+	case S_IFBLK:
+		data->arg.mknod.type = NF3BLK;
+		break;
+	case S_IFCHR:
+		data->arg.mknod.type = NF3CHR;
+		break;
+	case S_IFIFO:
+		data->arg.mknod.type = NF3FIFO;
+		break;
+	case S_IFSOCK:
+		data->arg.mknod.type = NF3SOCK;
+		break;
+	default:
+		status = -EINVAL;
+		goto out;
+	}
+
+	status = nfs3_do_create(dir, dentry, data);
 	if (status != 0)
 		goto out;
 	status = nfs3_proc_set_default_acl(dir, dentry->d_inode, mode);
 out:
+	nfs3_free_createdata(data);
 	dprintk("NFS reply mknod: %d\n", status);
 	return status;
 }
@@ -801,8 +816,6 @@ const struct nfs_rpc_ops nfs_v3_clientops = {
 	.write_done	= nfs3_write_done,
 	.commit_setup	= nfs3_proc_commit_setup,
 	.commit_done	= nfs3_commit_done,
-	.file_open	= nfs_open,
-	.file_release	= nfs_release,
 	.lock		= nfs3_proc_lock,
 	.clear_acl_cache = nfs3_forget_cached_acls,
 };

fs/nfs/nfs4proc.c

@@ -451,9 +451,7 @@ static struct nfs4_state *nfs4_try_open_cached(struct nfs4_opendata *opendata)
 		/* Save the delegation */
 		memcpy(stateid.data, delegation->stateid.data, sizeof(stateid.data));
 		rcu_read_unlock();
-		lock_kernel();
 		ret = nfs_may_open(state->inode, state->owner->so_cred, open_mode);
-		unlock_kernel();
 		if (ret != 0)
 			goto out;
 		ret = -EAGAIN;
@@ -1139,8 +1137,9 @@ static struct nfs4_state *nfs4_do_open(struct inode *dir, struct path *path, int
 	return res;
 }
 
-static int _nfs4_do_setattr(struct inode *inode, struct nfs_fattr *fattr,
-                struct iattr *sattr, struct nfs4_state *state)
+static int _nfs4_do_setattr(struct inode *inode, struct rpc_cred *cred,
+			    struct nfs_fattr *fattr, struct iattr *sattr,
+			    struct nfs4_state *state)
 {
 	struct nfs_server *server = NFS_SERVER(inode);
         struct nfs_setattrargs  arg = {
@@ -1154,9 +1153,10 @@ static int _nfs4_do_setattr(struct inode *inode, struct nfs_fattr *fattr,
 		.server		= server,
         };
         struct rpc_message msg = {
-                .rpc_proc       = &nfs4_procedures[NFSPROC4_CLNT_SETATTR],
-                .rpc_argp       = &arg,
-                .rpc_resp       = &res,
+		.rpc_proc	= &nfs4_procedures[NFSPROC4_CLNT_SETATTR],
+		.rpc_argp	= &arg,
+		.rpc_resp	= &res,
+		.rpc_cred	= cred,
         };
 	unsigned long timestamp = jiffies;
 	int status;
@@ -1166,7 +1166,6 @@ static int _nfs4_do_setattr(struct inode *inode, struct nfs_fattr *fattr,
 	if (nfs4_copy_delegation_stateid(&arg.stateid, inode)) {
 		/* Use that stateid */
 	} else if (state != NULL) {
-		msg.rpc_cred = state->owner->so_cred;
 		nfs4_copy_stateid(&arg.stateid, state, current->files);
 	} else
 		memcpy(&arg.stateid, &zero_stateid, sizeof(arg.stateid));
@@ -1177,15 +1176,16 @@ static int _nfs4_do_setattr(struct inode *inode, struct nfs_fattr *fattr,
 	return status;
 }
 
-static int nfs4_do_setattr(struct inode *inode, struct nfs_fattr *fattr,
-                struct iattr *sattr, struct nfs4_state *state)
+static int nfs4_do_setattr(struct inode *inode, struct rpc_cred *cred,
+			   struct nfs_fattr *fattr, struct iattr *sattr,
+			   struct nfs4_state *state)
 {
 	struct nfs_server *server = NFS_SERVER(inode);
 	struct nfs4_exception exception = { };
 	int err;
 	do {
 		err = nfs4_handle_exception(server,
-				_nfs4_do_setattr(inode, fattr, sattr, state),
+				_nfs4_do_setattr(inode, cred, fattr, sattr, state),
 				&exception);
 	} while (exception.retry);
 	return err;
@@ -1647,29 +1647,25 @@ static int
 nfs4_proc_setattr(struct dentry *dentry, struct nfs_fattr *fattr,
 		  struct iattr *sattr)
 {
-	struct rpc_cred *cred;
 	struct inode *inode = dentry->d_inode;
-	struct nfs_open_context *ctx;
+	struct rpc_cred *cred = NULL;
 	struct nfs4_state *state = NULL;
 	int status;
 
 	nfs_fattr_init(fattr);
 	
-	cred = rpc_lookup_cred();
-	if (IS_ERR(cred))
-		return PTR_ERR(cred);
-
 	/* Search for an existing open(O_WRITE) file */
-	ctx = nfs_find_open_context(inode, cred, FMODE_WRITE);
-	if (ctx != NULL)
+	if (sattr->ia_valid & ATTR_FILE) {
+		struct nfs_open_context *ctx;
+
+		ctx = nfs_file_open_context(sattr->ia_file);
+		cred = ctx->cred;
 		state = ctx->state;
+	}
 
-	status = nfs4_do_setattr(inode, fattr, sattr, state);
+	status = nfs4_do_setattr(inode, cred, fattr, sattr, state);
 	if (status == 0)
 		nfs_setattr_update_inode(inode, sattr);
-	if (ctx != NULL)
-		put_nfs_open_context(ctx);
-	put_rpccred(cred);
 	return status;
 }
 
@@ -1897,17 +1893,16 @@ nfs4_proc_create(struct inode *dir, struct dentry *dentry, struct iattr *sattr,
 		goto out;
 	}
 	state = nfs4_do_open(dir, &path, flags, sattr, cred);
-	put_rpccred(cred);
 	d_drop(dentry);
 	if (IS_ERR(state)) {
 		status = PTR_ERR(state);
-		goto out;
+		goto out_putcred;
 	}
 	d_add(dentry, igrab(state->inode));
 	nfs_set_verifier(dentry, nfs_save_change_attribute(dir));
 	if (flags & O_EXCL) {
 		struct nfs_fattr fattr;
-		status = nfs4_do_setattr(state->inode, &fattr, sattr, state);
+		status = nfs4_do_setattr(state->inode, cred, &fattr, sattr, state);
 		if (status == 0)
 			nfs_setattr_update_inode(state->inode, sattr);
 		nfs_post_op_update_inode(state->inode, &fattr);
@@ -1916,6 +1911,8 @@ nfs4_proc_create(struct inode *dir, struct dentry *dentry, struct iattr *sattr,
 		status = nfs4_intent_set_file(nd, &path, state);
 	else
 		nfs4_close_sync(&path, state, flags);
+out_putcred:
+	put_rpccred(cred);
 out:
 	return status;
 }
@@ -2079,47 +2076,81 @@ static int nfs4_proc_link(struct inode *inode, struct inode *dir, struct qstr *n
 	return err;
 }
 
+struct nfs4_createdata {
+	struct rpc_message msg;
+	struct nfs4_create_arg arg;
+	struct nfs4_create_res res;
+	struct nfs_fh fh;
+	struct nfs_fattr fattr;
+	struct nfs_fattr dir_fattr;
+};
+
+static struct nfs4_createdata *nfs4_alloc_createdata(struct inode *dir,
+		struct qstr *name, struct iattr *sattr, u32 ftype)
+{
+	struct nfs4_createdata *data;
+
+	data = kzalloc(sizeof(*data), GFP_KERNEL);
+	if (data != NULL) {
+		struct nfs_server *server = NFS_SERVER(dir);
+
+		data->msg.rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_CREATE];
+		data->msg.rpc_argp = &data->arg;
+		data->msg.rpc_resp = &data->res;
+		data->arg.dir_fh = NFS_FH(dir);
+		data->arg.server = server;
+		data->arg.name = name;
+		data->arg.attrs = sattr;
+		data->arg.ftype = ftype;
+		data->arg.bitmask = server->attr_bitmask;
+		data->res.server = server;
+		data->res.fh = &data->fh;
+		data->res.fattr = &data->fattr;
+		data->res.dir_fattr = &data->dir_fattr;
+		nfs_fattr_init(data->res.fattr);
+		nfs_fattr_init(data->res.dir_fattr);
+	}
+	return data;
+}
+
+static int nfs4_do_create(struct inode *dir, struct dentry *dentry, struct nfs4_createdata *data)
+{
+	int status = rpc_call_sync(NFS_CLIENT(dir), &data->msg, 0);
+	if (status == 0) {
+		update_changeattr(dir, &data->res.dir_cinfo);
+		nfs_post_op_update_inode(dir, data->res.dir_fattr);
+		status = nfs_instantiate(dentry, data->res.fh, data->res.fattr);
+	}
+	return status;
+}
+
+static void nfs4_free_createdata(struct nfs4_createdata *data)
+{
+	kfree(data);
+}
+
 static int _nfs4_proc_symlink(struct inode *dir, struct dentry *dentry,
 		struct page *page, unsigned int len, struct iattr *sattr)
 {
-	struct nfs_server *server = NFS_SERVER(dir);
-	struct nfs_fh fhandle;
-	struct nfs_fattr fattr, dir_fattr;
-	struct nfs4_create_arg arg = {
-		.dir_fh = NFS_FH(dir),
-		.server = server,
-		.name = &dentry->d_name,
-		.attrs = sattr,
-		.ftype = NF4LNK,
-		.bitmask = server->attr_bitmask,
-	};
-	struct nfs4_create_res res = {
-		.server = server,
-		.fh = &fhandle,
-		.fattr = &fattr,
-		.dir_fattr = &dir_fattr,
-	};
-	struct rpc_message msg = {
-		.rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_SYMLINK],
-		.rpc_argp = &arg,
-		.rpc_resp = &res,
-	};
-	int			status;
+	struct nfs4_createdata *data;
+	int status = -ENAMETOOLONG;
 
 	if (len > NFS4_MAXPATHLEN)
-		return -ENAMETOOLONG;
+		goto out;
 
-	arg.u.symlink.pages = &page;
-	arg.u.symlink.len = len;
-	nfs_fattr_init(&fattr);
-	nfs_fattr_init(&dir_fattr);
+	status = -ENOMEM;
+	data = nfs4_alloc_createdata(dir, &dentry->d_name, sattr, NF4LNK);
+	if (data == NULL)
+		goto out;
+
+	data->msg.rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_SYMLINK];
+	data->arg.u.symlink.pages = &page;
+	data->arg.u.symlink.len = len;
 	
-	status = rpc_call_sync(NFS_CLIENT(dir), &msg, 0);
-	if (!status) {
-		update_changeattr(dir, &res.dir_cinfo);
-		nfs_post_op_update_inode(dir, res.dir_fattr);
-		status = nfs_instantiate(dentry, &fhandle, &fattr);
-	}
+	status = nfs4_do_create(dir, dentry, data);
+
+	nfs4_free_createdata(data);
+out:
 	return status;
 }
 
@@ -2140,39 +2171,17 @@ static int nfs4_proc_symlink(struct inode *dir, struct dentry *dentry,
 static int _nfs4_proc_mkdir(struct inode *dir, struct dentry *dentry,
 		struct iattr *sattr)
 {
-	struct nfs_server *server = NFS_SERVER(dir);
-	struct nfs_fh fhandle;
-	struct nfs_fattr fattr, dir_fattr;
-	struct nfs4_create_arg arg = {
-		.dir_fh = NFS_FH(dir),
-		.server = server,
-		.name = &dentry->d_name,
-		.attrs = sattr,
-		.ftype = NF4DIR,
-		.bitmask = server->attr_bitmask,
-	};
-	struct nfs4_create_res res = {
-		.server = server,
-		.fh = &fhandle,
-		.fattr = &fattr,
-		.dir_fattr = &dir_fattr,
-	};
-	struct rpc_message msg = {
-		.rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_CREATE],
-		.rpc_argp = &arg,
-		.rpc_resp = &res,
-	};
-	int			status;
+	struct nfs4_createdata *data;
+	int status = -ENOMEM;
 
-	nfs_fattr_init(&fattr);
-	nfs_fattr_init(&dir_fattr);
-	
-	status = rpc_call_sync(NFS_CLIENT(dir), &msg, 0);
-	if (!status) {
-		update_changeattr(dir, &res.dir_cinfo);
-		nfs_post_op_update_inode(dir, res.dir_fattr);
-		status = nfs_instantiate(dentry, &fhandle, &fattr);
-	}
+	data = nfs4_alloc_createdata(dir, &dentry->d_name, sattr, NF4DIR);
+	if (data == NULL)
+		goto out;
+
+	status = nfs4_do_create(dir, dentry, data);
+
+	nfs4_free_createdata(data);
+out:
 	return status;
 }
 
@@ -2242,56 +2251,34 @@ static int nfs4_proc_readdir(struct dentry *dentry, struct rpc_cred *cred,
 static int _nfs4_proc_mknod(struct inode *dir, struct dentry *dentry,
 		struct iattr *sattr, dev_t rdev)
 {
-	struct nfs_server *server = NFS_SERVER(dir);
-	struct nfs_fh fh;
-	struct nfs_fattr fattr, dir_fattr;
-	struct nfs4_create_arg arg = {
-		.dir_fh = NFS_FH(dir),
-		.server = server,
-		.name = &dentry->d_name,
-		.attrs = sattr,
-		.bitmask = server->attr_bitmask,
-	};
-	struct nfs4_create_res res = {
-		.server = server,
-		.fh = &fh,
-		.fattr = &fattr,
-		.dir_fattr = &dir_fattr,
-	};
-	struct rpc_message msg = {
-		.rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_CREATE],
-		.rpc_argp = &arg,
-		.rpc_resp = &res,
-	};
-	int			status;
-	int                     mode = sattr->ia_mode;
-
-	nfs_fattr_init(&fattr);
-	nfs_fattr_init(&dir_fattr);
+	struct nfs4_createdata *data;
+	int mode = sattr->ia_mode;
+	int status = -ENOMEM;
 
 	BUG_ON(!(sattr->ia_valid & ATTR_MODE));
 	BUG_ON(!S_ISFIFO(mode) && !S_ISBLK(mode) && !S_ISCHR(mode) && !S_ISSOCK(mode));
+
+	data = nfs4_alloc_createdata(dir, &dentry->d_name, sattr, NF4SOCK);
+	if (data == NULL)
+		goto out;
+
 	if (S_ISFIFO(mode))
-		arg.ftype = NF4FIFO;
+		data->arg.ftype = NF4FIFO;
 	else if (S_ISBLK(mode)) {
-		arg.ftype = NF4BLK;
-		arg.u.device.specdata1 = MAJOR(rdev);
-		arg.u.device.specdata2 = MINOR(rdev);
+		data->arg.ftype = NF4BLK;
+		data->arg.u.device.specdata1 = MAJOR(rdev);
+		data->arg.u.device.specdata2 = MINOR(rdev);
 	}
 	else if (S_ISCHR(mode)) {
-		arg.ftype = NF4CHR;
-		arg.u.device.specdata1 = MAJOR(rdev);
-		arg.u.device.specdata2 = MINOR(rdev);
+		data->arg.ftype = NF4CHR;
+		data->arg.u.device.specdata1 = MAJOR(rdev);
+		data->arg.u.device.specdata2 = MINOR(rdev);
 	}
-	else
-		arg.ftype = NF4SOCK;
 	
-	status = rpc_call_sync(NFS_CLIENT(dir), &msg, 0);
-	if (status == 0) {
-		update_changeattr(dir, &res.dir_cinfo);
-		nfs_post_op_update_inode(dir, res.dir_fattr);
-		status = nfs_instantiate(dentry, &fh, &fattr);
-	}
+	status = nfs4_do_create(dir, dentry, data);
+
+	nfs4_free_createdata(data);
+out:
 	return status;
 }
 
@@ -2706,6 +2693,8 @@ static ssize_t nfs4_proc_get_acl(struct inode *inode, void *buf, size_t buflen)
 	ret = nfs_revalidate_inode(server, inode);
 	if (ret < 0)
 		return ret;
+	if (NFS_I(inode)->cache_validity & NFS_INO_INVALID_ACL)
+		nfs_zap_acl_cache(inode);
 	ret = nfs4_read_cached_acl(inode, buf, buflen);
 	if (ret != -ENOENT)
 		return ret;
@@ -2733,7 +2722,8 @@ static int __nfs4_proc_set_acl(struct inode *inode, const void *buf, size_t bufl
 	nfs_inode_return_delegation(inode);
 	buf_to_pages(buf, buflen, arg.acl_pages, &arg.acl_pgbase);
 	ret = rpc_call_sync(NFS_CLIENT(inode), &msg, 0);
-	nfs_zap_caches(inode);
+	nfs_access_zap_cache(inode);
+	nfs_zap_acl_cache(inode);
 	return ret;
 }
 
@@ -2767,8 +2757,7 @@ nfs4_async_handle_error(struct rpc_task *task, const struct nfs_server *server)
 			task->tk_status = 0;
 			return -EAGAIN;
 		case -NFS4ERR_DELAY:
-			nfs_inc_server_stats((struct nfs_server *) server,
-						NFSIOS_DELAY);
+			nfs_inc_server_stats(server, NFSIOS_DELAY);
 		case -NFS4ERR_GRACE:
 			rpc_delay(task, NFS4_POLL_RETRY_MAX);
 			task->tk_status = 0;
@@ -2933,7 +2922,7 @@ static int _nfs4_proc_setclientid_confirm(struct nfs_client *clp, struct rpc_cre
 
 int nfs4_proc_setclientid_confirm(struct nfs_client *clp, struct rpc_cred *cred)
 {
-	long timeout;
+	long timeout = 0;
 	int err;
 	do {
 		err = _nfs4_proc_setclientid_confirm(clp, cred);
@@ -3725,8 +3714,6 @@ const struct nfs_rpc_ops nfs_v4_clientops = {
 	.write_done	= nfs4_write_done,
 	.commit_setup	= nfs4_proc_commit_setup,
 	.commit_done	= nfs4_commit_done,
-	.file_open      = nfs_open,
-	.file_release   = nfs_release,
 	.lock		= nfs4_proc_lock,
 	.clear_acl_cache = nfs4_zap_acl_attr,
 };

fs/nfs/nfs4state.c

@@ -940,7 +940,6 @@ static int reclaimer(void *ptr)
 	allow_signal(SIGKILL);
 
 	/* Ensure exclusive access to NFSv4 state */
-	lock_kernel();
 	down_write(&clp->cl_sem);
 	/* Are there any NFS mounts out there? */
 	if (list_empty(&clp->cl_superblocks))
@@ -1000,7 +999,6 @@ restart_loop:
 	nfs_delegation_reap_unclaimed(clp);
 out:
 	up_write(&clp->cl_sem);
-	unlock_kernel();
 	if (status == -NFS4ERR_CB_PATH_DOWN)
 		nfs_handle_cb_pathdown(clp);
 	nfs4_clear_recover_bit(clp);

fs/nfs/nfsroot.c

@@ -1,6 +1,4 @@
 /*
- *  $Id: nfsroot.c,v 1.45 1998/03/07 10:44:46 mj Exp $
- *
  *  Copyright (C) 1995, 1996  Gero Kuhlmann <gero@gkminix.han.de>
  *
  *  Allow an NFS filesystem to be mounted as root. The way this works is:
@@ -297,10 +295,10 @@ static int __init root_nfs_name(char *name)
 	nfs_data.flags    = NFS_MOUNT_NONLM;	/* No lockd in nfs root yet */
 	nfs_data.rsize    = NFS_DEF_FILE_IO_SIZE;
 	nfs_data.wsize    = NFS_DEF_FILE_IO_SIZE;
-	nfs_data.acregmin = 3;
-	nfs_data.acregmax = 60;
-	nfs_data.acdirmin = 30;
-	nfs_data.acdirmax = 60;
+	nfs_data.acregmin = NFS_DEF_ACREGMIN;
+	nfs_data.acregmax = NFS_DEF_ACREGMAX;
+	nfs_data.acdirmin = NFS_DEF_ACDIRMIN;
+	nfs_data.acdirmax = NFS_DEF_ACDIRMAX;
 	strcpy(buf, NFS_ROOT);
 
 	/* Process options received from the remote server */

fs/nfs/proc.c

@@ -129,6 +129,8 @@ nfs_proc_setattr(struct dentry *dentry, struct nfs_fattr *fattr,
 	sattr->ia_mode &= S_IALLUGO;
 
 	dprintk("NFS call  setattr\n");
+	if (sattr->ia_valid & ATTR_FILE)
+		msg.rpc_cred = nfs_file_cred(sattr->ia_file);
 	nfs_fattr_init(fattr);
 	status = rpc_call_sync(NFS_CLIENT(inode), &msg, 0);
 	if (status == 0)
@@ -598,6 +600,29 @@ nfs_proc_lock(struct file *filp, int cmd, struct file_lock *fl)
 	return nlmclnt_proc(NFS_SERVER(inode)->nlm_host, cmd, fl);
 }
 
+/* Helper functions for NFS lock bounds checking */
+#define NFS_LOCK32_OFFSET_MAX ((__s32)0x7fffffffUL)
+static int nfs_lock_check_bounds(const struct file_lock *fl)
+{
+	__s32 start, end;
+
+	start = (__s32)fl->fl_start;
+	if ((loff_t)start != fl->fl_start)
+		goto out_einval;
+
+	if (fl->fl_end != OFFSET_MAX) {
+		end = (__s32)fl->fl_end;
+		if ((loff_t)end != fl->fl_end)
+			goto out_einval;
+	} else
+		end = NFS_LOCK32_OFFSET_MAX;
+
+	if (start < 0 || start > end)
+		goto out_einval;
+	return 0;
+out_einval:
+	return -EINVAL;
+}
 
 const struct nfs_rpc_ops nfs_v2_clientops = {
 	.version	= 2,		       /* protocol version */
@@ -630,7 +655,6 @@ const struct nfs_rpc_ops nfs_v2_clientops = {
 	.write_setup	= nfs_proc_write_setup,
 	.write_done	= nfs_write_done,
 	.commit_setup	= nfs_proc_commit_setup,
-	.file_open	= nfs_open,
-	.file_release	= nfs_release,
 	.lock		= nfs_proc_lock,
+	.lock_check_bounds = nfs_lock_check_bounds,
 };

fs/nfs/super.c

@@ -47,6 +47,7 @@
 #include <linux/inet.h>
 #include <linux/in6.h>
 #include <net/ipv6.h>
+#include <linux/netdevice.h>
 #include <linux/nfs_xdr.h>
 #include <linux/magic.h>
 #include <linux/parser.h>
@@ -65,7 +66,6 @@
 enum {
 	/* Mount options that take no arguments */
 	Opt_soft, Opt_hard,
-	Opt_intr, Opt_nointr,
 	Opt_posix, Opt_noposix,
 	Opt_cto, Opt_nocto,
 	Opt_ac, Opt_noac,
@@ -92,8 +92,8 @@ enum {
 	Opt_sec, Opt_proto, Opt_mountproto, Opt_mounthost,
 	Opt_addr, Opt_mountaddr, Opt_clientaddr,
 
-	/* Mount options that are ignored */
-	Opt_userspace, Opt_deprecated,
+	/* Special mount options */
+	Opt_userspace, Opt_deprecated, Opt_sloppy,
 
 	Opt_err
 };
@@ -101,10 +101,14 @@ enum {
 static match_table_t nfs_mount_option_tokens = {
 	{ Opt_userspace, "bg" },
 	{ Opt_userspace, "fg" },
+	{ Opt_userspace, "retry=%s" },
+
+	{ Opt_sloppy, "sloppy" },
+
 	{ Opt_soft, "soft" },
 	{ Opt_hard, "hard" },
-	{ Opt_intr, "intr" },
-	{ Opt_nointr, "nointr" },
+	{ Opt_deprecated, "intr" },
+	{ Opt_deprecated, "nointr" },
 	{ Opt_posix, "posix" },
 	{ Opt_noposix, "noposix" },
 	{ Opt_cto, "cto" },
@@ -136,7 +140,6 @@ static match_table_t nfs_mount_option_tokens = {
 	{ Opt_acdirmin, "acdirmin=%u" },
 	{ Opt_acdirmax, "acdirmax=%u" },
 	{ Opt_actimeo, "actimeo=%u" },
-	{ Opt_userspace, "retry=%u" },
 	{ Opt_namelen, "namlen=%u" },
 	{ Opt_mountport, "mountport=%u" },
 	{ Opt_mountvers, "mountvers=%u" },
@@ -207,6 +210,7 @@ static int nfs_xdev_get_sb(struct file_system_type *fs_type,
 		int flags, const char *dev_name, void *raw_data, struct vfsmount *mnt);
 static void nfs_kill_super(struct super_block *);
 static void nfs_put_super(struct super_block *);
+static int nfs_remount(struct super_block *sb, int *flags, char *raw_data);
 
 static struct file_system_type nfs_fs_type = {
 	.owner		= THIS_MODULE,
@@ -234,6 +238,7 @@ static const struct super_operations nfs_sops = {
 	.umount_begin	= nfs_umount_begin,
 	.show_options	= nfs_show_options,
 	.show_stats	= nfs_show_stats,
+	.remount_fs	= nfs_remount,
 };
 
 #ifdef CONFIG_NFS_V4
@@ -278,6 +283,7 @@ static const struct super_operations nfs4_sops = {
 	.umount_begin	= nfs_umount_begin,
 	.show_options	= nfs_show_options,
 	.show_stats	= nfs_show_stats,
+	.remount_fs	= nfs_remount,
 };
 #endif
 
@@ -368,8 +374,6 @@ static int nfs_statfs(struct dentry *dentry, struct kstatfs *buf)
 	};
 	int error;
 
-	lock_kernel();
-
 	error = server->nfs_client->rpc_ops->statfs(server, fh, &res);
 	if (error < 0)
 		goto out_err;
@@ -401,12 +405,10 @@ static int nfs_statfs(struct dentry *dentry, struct kstatfs *buf)
 
 	buf->f_namelen = server->namelen;
 
-	unlock_kernel();
 	return 0;
 
  out_err:
 	dprintk("%s: statfs error = %d\n", __func__, -error);
-	unlock_kernel();
 	return error;
 }
 
@@ -514,13 +516,13 @@ static void nfs_show_mount_options(struct seq_file *m, struct nfs_server *nfss,
 	if (nfss->bsize != 0)
 		seq_printf(m, ",bsize=%u", nfss->bsize);
 	seq_printf(m, ",namlen=%u", nfss->namelen);
-	if (nfss->acregmin != 3*HZ || showdefaults)
+	if (nfss->acregmin != NFS_DEF_ACREGMIN*HZ || showdefaults)
 		seq_printf(m, ",acregmin=%u", nfss->acregmin/HZ);
-	if (nfss->acregmax != 60*HZ || showdefaults)
+	if (nfss->acregmax != NFS_DEF_ACREGMAX*HZ || showdefaults)
 		seq_printf(m, ",acregmax=%u", nfss->acregmax/HZ);
-	if (nfss->acdirmin != 30*HZ || showdefaults)
+	if (nfss->acdirmin != NFS_DEF_ACDIRMIN*HZ || showdefaults)
 		seq_printf(m, ",acdirmin=%u", nfss->acdirmin/HZ);
-	if (nfss->acdirmax != 60*HZ || showdefaults)
+	if (nfss->acdirmax != NFS_DEF_ACDIRMAX*HZ || showdefaults)
 		seq_printf(m, ",acdirmax=%u", nfss->acdirmax/HZ);
 	for (nfs_infop = nfs_info; nfs_infop->flag; nfs_infop++) {
 		if (nfss->flags & nfs_infop->flag)
@@ -702,49 +704,233 @@ static int nfs_verify_server_address(struct sockaddr *addr)
 	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;
+}
+
+#define IPV6_SCOPE_DELIMITER	'%'
+
+#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
+static void 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 (!(ipv6_addr_type(&sin6->sin6_addr) & IPV6_ADDR_LINKLOCAL))
+		return ;
+	if (*delim != IPV6_SCOPE_DELIMITER)
+		return;
+
+	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 {
+			/* scope_id is set to zero on error */
+			strict_strtoul(p, 10, &scope_id);
+		}
+
+		kfree(p);
+		sin6->sin6_scope_id = scope_id;
+		dfprintk(MOUNT, "NFS: IPv6 scope ID = %lu\n", scope_id);
+	}
+}
+
+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)) {
+			nfs_parse_ipv6_scope_id(string, str_len, delim, sin6);
+			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
+
 /*
- * Parse string addresses passed in via a mount option,
- * and construct a sockaddr based on the result.
+ * Construct a sockaddr based on the contents of a string that contains
+ * an IP address in presentation format.
  *
- * If address parsing fails, set the sockaddr's address
- * family to AF_UNSPEC to force nfs_verify_server_address()
- * to punt the mount.
+ * If there is a problem constructing the new sockaddr, set the address
+ * family to AF_UNSPEC.
  */
-static void nfs_parse_server_address(char *value,
-				     struct sockaddr *sap,
-				     size_t *len)
+static void nfs_parse_ip_address(char *string, size_t str_len,
+				 struct sockaddr *sap, size_t *addr_len)
 {
-	if (strchr(value, ':')) {
-		struct sockaddr_in6 *ap = (struct sockaddr_in6 *)sap;
-		u8 *addr = (u8 *)&ap->sin6_addr.in6_u;
+	unsigned int i, colons;
 
-		ap->sin6_family = AF_INET6;
-		*len = sizeof(*ap);
-		if (in6_pton(value, -1, addr, '\0', NULL))
-			return;
-	} else {
-		struct sockaddr_in *ap = (struct sockaddr_in *)sap;
-		u8 *addr = (u8 *)&ap->sin_addr.s_addr;
+	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.
+ *
+ */
+static void nfs_validate_transport_protocol(struct nfs_parsed_mount_data *mnt)
+{
+	switch (mnt->nfs_server.protocol) {
+	case XPRT_TRANSPORT_UDP:
+	case XPRT_TRANSPORT_TCP:
+	case XPRT_TRANSPORT_RDMA:
+		break;
+	default:
+		mnt->nfs_server.protocol = XPRT_TRANSPORT_TCP;
+	}
+}
+
+/*
+ * For text based NFSv2/v3 mounts, the mount protocol transport default
+ * settings should depend upon the specified NFS transport.
+ */
+static void nfs_set_mount_transport_protocol(struct nfs_parsed_mount_data *mnt)
+{
+	nfs_validate_transport_protocol(mnt);
 
-		ap->sin_family = AF_INET;
-		*len = sizeof(*ap);
-		if (in4_pton(value, -1, addr, '\0', NULL))
+	if (mnt->mount_server.protocol == XPRT_TRANSPORT_UDP ||
+	    mnt->mount_server.protocol == XPRT_TRANSPORT_TCP)
 			return;
+	switch (mnt->nfs_server.protocol) {
+	case XPRT_TRANSPORT_UDP:
+		mnt->mount_server.protocol = XPRT_TRANSPORT_UDP;
+		break;
+	case XPRT_TRANSPORT_TCP:
+	case XPRT_TRANSPORT_RDMA:
+		mnt->mount_server.protocol = XPRT_TRANSPORT_TCP;
 	}
+}
 
-	sap->sa_family = AF_UNSPEC;
-	*len = 0;
+/*
+ * Parse the value of the 'sec=' option.
+ *
+ * The flavor_len setting is for v4 mounts.
+ */
+static int nfs_parse_security_flavors(char *value,
+				      struct nfs_parsed_mount_data *mnt)
+{
+	substring_t args[MAX_OPT_ARGS];
+
+	dfprintk(MOUNT, "NFS: parsing sec=%s option\n", value);
+
+	switch (match_token(value, nfs_secflavor_tokens, args)) {
+	case Opt_sec_none:
+		mnt->auth_flavor_len = 0;
+		mnt->auth_flavors[0] = RPC_AUTH_NULL;
+		break;
+	case Opt_sec_sys:
+		mnt->auth_flavor_len = 0;
+		mnt->auth_flavors[0] = RPC_AUTH_UNIX;
+		break;
+	case Opt_sec_krb5:
+		mnt->auth_flavor_len = 1;
+		mnt->auth_flavors[0] = RPC_AUTH_GSS_KRB5;
+		break;
+	case Opt_sec_krb5i:
+		mnt->auth_flavor_len = 1;
+		mnt->auth_flavors[0] = RPC_AUTH_GSS_KRB5I;
+		break;
+	case Opt_sec_krb5p:
+		mnt->auth_flavor_len = 1;
+		mnt->auth_flavors[0] = RPC_AUTH_GSS_KRB5P;
+		break;
+	case Opt_sec_lkey:
+		mnt->auth_flavor_len = 1;
+		mnt->auth_flavors[0] = RPC_AUTH_GSS_LKEY;
+		break;
+	case Opt_sec_lkeyi:
+		mnt->auth_flavor_len = 1;
+		mnt->auth_flavors[0] = RPC_AUTH_GSS_LKEYI;
+		break;
+	case Opt_sec_lkeyp:
+		mnt->auth_flavor_len = 1;
+		mnt->auth_flavors[0] = RPC_AUTH_GSS_LKEYP;
+		break;
+	case Opt_sec_spkm:
+		mnt->auth_flavor_len = 1;
+		mnt->auth_flavors[0] = RPC_AUTH_GSS_SPKM;
+		break;
+	case Opt_sec_spkmi:
+		mnt->auth_flavor_len = 1;
+		mnt->auth_flavors[0] = RPC_AUTH_GSS_SPKMI;
+		break;
+	case Opt_sec_spkmp:
+		mnt->auth_flavor_len = 1;
+		mnt->auth_flavors[0] = RPC_AUTH_GSS_SPKMP;
+		break;
+	default:
+		return 0;
+	}
+
+	return 1;
+}
+
+static void nfs_parse_invalid_value(const char *option)
+{
+	dfprintk(MOUNT, "NFS:   bad value specified for %s option\n", option);
 }
 
 /*
  * Error-check and convert a string of mount options from user space into
- * a data structure
+ * a data structure.  The whole mount string is processed; bad options are
+ * skipped as they are encountered.  If there were no errors, return 1;
+ * otherwise return 0 (zero).
  */
 static int nfs_parse_mount_options(char *raw,
 				   struct nfs_parsed_mount_data *mnt)
 {
 	char *p, *string, *secdata;
-	int rc;
+	int rc, sloppy = 0, errors = 0;
 
 	if (!raw) {
 		dfprintk(MOUNT, "NFS: mount options string was NULL.\n");
@@ -777,15 +963,16 @@ static int nfs_parse_mount_options(char *raw,
 
 		token = match_token(p, nfs_mount_option_tokens, args);
 		switch (token) {
+
+		/*
+		 * boolean options:  foo/nofoo
+		 */
 		case Opt_soft:
 			mnt->flags |= NFS_MOUNT_SOFT;
 			break;
 		case Opt_hard:
 			mnt->flags &= ~NFS_MOUNT_SOFT;
 			break;
-		case Opt_intr:
-		case Opt_nointr:
-			break;
 		case Opt_posix:
 			mnt->flags |= NFS_MOUNT_POSIX;
 			break;
@@ -819,20 +1006,14 @@ static int nfs_parse_mount_options(char *raw,
 		case Opt_udp:
 			mnt->flags &= ~NFS_MOUNT_TCP;
 			mnt->nfs_server.protocol = XPRT_TRANSPORT_UDP;
-			mnt->timeo = 7;
-			mnt->retrans = 5;
 			break;
 		case Opt_tcp:
 			mnt->flags |= NFS_MOUNT_TCP;
 			mnt->nfs_server.protocol = XPRT_TRANSPORT_TCP;
-			mnt->timeo = 600;
-			mnt->retrans = 2;
 			break;
 		case Opt_rdma:
 			mnt->flags |= NFS_MOUNT_TCP; /* for side protocols */
 			mnt->nfs_server.protocol = XPRT_TRANSPORT_RDMA;
-			mnt->timeo = 600;
-			mnt->retrans = 2;
 			break;
 		case Opt_acl:
 			mnt->flags &= ~NFS_MOUNT_NOACL;
@@ -853,165 +1034,144 @@ static int nfs_parse_mount_options(char *raw,
 			mnt->flags |= NFS_MOUNT_UNSHARED;
 			break;
 
+		/*
+		 * options that take numeric values
+		 */
 		case Opt_port:
-			if (match_int(args, &option))
-				return 0;
-			if (option < 0 || option > 65535)
-				return 0;
-			mnt->nfs_server.port = option;
+			if (match_int(args, &option) ||
+			    option < 0 || option > USHORT_MAX) {
+				errors++;
+				nfs_parse_invalid_value("port");
+			} else
+				mnt->nfs_server.port = option;
 			break;
 		case Opt_rsize:
-			if (match_int(args, &mnt->rsize))
-				return 0;
+			if (match_int(args, &option) || option < 0) {
+				errors++;
+				nfs_parse_invalid_value("rsize");
+			} else
+				mnt->rsize = option;
 			break;
 		case Opt_wsize:
-			if (match_int(args, &mnt->wsize))
-				return 0;
+			if (match_int(args, &option) || option < 0) {
+				errors++;
+				nfs_parse_invalid_value("wsize");
+			} else
+				mnt->wsize = option;
 			break;
 		case Opt_bsize:
-			if (match_int(args, &option))
-				return 0;
-			if (option < 0)
-				return 0;
-			mnt->bsize = option;
+			if (match_int(args, &option) || option < 0) {
+				errors++;
+				nfs_parse_invalid_value("bsize");
+			} else
+				mnt->bsize = option;
 			break;
 		case Opt_timeo:
-			if (match_int(args, &mnt->timeo))
-				return 0;
+			if (match_int(args, &option) || option <= 0) {
+				errors++;
+				nfs_parse_invalid_value("timeo");
+			} else
+				mnt->timeo = option;
 			break;
 		case Opt_retrans:
-			if (match_int(args, &mnt->retrans))
-				return 0;
+			if (match_int(args, &option) || option <= 0) {
+				errors++;
+				nfs_parse_invalid_value("retrans");
+			} else
+				mnt->retrans = option;
 			break;
 		case Opt_acregmin:
-			if (match_int(args, &mnt->acregmin))
-				return 0;
+			if (match_int(args, &option) || option < 0) {
+				errors++;
+				nfs_parse_invalid_value("acregmin");
+			} else
+				mnt->acregmin = option;
 			break;
 		case Opt_acregmax:
-			if (match_int(args, &mnt->acregmax))
-				return 0;
+			if (match_int(args, &option) || option < 0) {
+				errors++;
+				nfs_parse_invalid_value("acregmax");
+			} else
+				mnt->acregmax = option;
 			break;
 		case Opt_acdirmin:
-			if (match_int(args, &mnt->acdirmin))
-				return 0;
+			if (match_int(args, &option) || option < 0) {
+				errors++;
+				nfs_parse_invalid_value("acdirmin");
+			} else
+				mnt->acdirmin = option;
 			break;
 		case Opt_acdirmax:
-			if (match_int(args, &mnt->acdirmax))
-				return 0;
+			if (match_int(args, &option) || option < 0) {
+				errors++;
+				nfs_parse_invalid_value("acdirmax");
+			} else
+				mnt->acdirmax = option;
 			break;
 		case Opt_actimeo:
-			if (match_int(args, &option))
-				return 0;
-			if (option < 0)
-				return 0;
-			mnt->acregmin =
-			mnt->acregmax =
-			mnt->acdirmin =
-			mnt->acdirmax = option;
+			if (match_int(args, &option) || option < 0) {
+				errors++;
+				nfs_parse_invalid_value("actimeo");
+			} else
+				mnt->acregmin = mnt->acregmax =
+				mnt->acdirmin = mnt->acdirmax = option;
 			break;
 		case Opt_namelen:
-			if (match_int(args, &mnt->namlen))
-				return 0;
+			if (match_int(args, &option) || option < 0) {
+				errors++;
+				nfs_parse_invalid_value("namlen");
+			} else
+				mnt->namlen = option;
 			break;
 		case Opt_mountport:
-			if (match_int(args, &option))
-				return 0;
-			if (option < 0 || option > 65535)
-				return 0;
-			mnt->mount_server.port = option;
+			if (match_int(args, &option) ||
+			    option < 0 || option > USHORT_MAX) {
+				errors++;
+				nfs_parse_invalid_value("mountport");
+			} else
+				mnt->mount_server.port = option;
 			break;
 		case Opt_mountvers:
-			if (match_int(args, &option))
-				return 0;
-			if (option < 0)
-				return 0;
-			mnt->mount_server.version = option;
+			if (match_int(args, &option) ||
+			    option < NFS_MNT_VERSION ||
+			    option > NFS_MNT3_VERSION) {
+				errors++;
+				nfs_parse_invalid_value("mountvers");
+			} else
+				mnt->mount_server.version = option;
 			break;
 		case Opt_nfsvers:
-			if (match_int(args, &option))
-				return 0;
+			if (match_int(args, &option)) {
+				errors++;
+				nfs_parse_invalid_value("nfsvers");
+				break;
+			}
 			switch (option) {
-			case 2:
+			case NFS2_VERSION:
 				mnt->flags &= ~NFS_MOUNT_VER3;
 				break;
-			case 3:
+			case NFS3_VERSION:
 				mnt->flags |= NFS_MOUNT_VER3;
 				break;
 			default:
-				goto out_unrec_vers;
+				errors++;
+				nfs_parse_invalid_value("nfsvers");
 			}
 			break;
 
+		/*
+		 * options that take text values
+		 */
 		case Opt_sec:
 			string = match_strdup(args);
 			if (string == NULL)
 				goto out_nomem;
-			token = match_token(string, nfs_secflavor_tokens, args);
+			rc = nfs_parse_security_flavors(string, mnt);
 			kfree(string);
-
-			/*
-			 * The flags setting is for v2/v3.  The flavor_len
-			 * setting is for v4.  v2/v3 also need to know the
-			 * difference between NULL and UNIX.
-			 */
-			switch (token) {
-			case Opt_sec_none:
-				mnt->flags &= ~NFS_MOUNT_SECFLAVOUR;
-				mnt->auth_flavor_len = 0;
-				mnt->auth_flavors[0] = RPC_AUTH_NULL;
-				break;
-			case Opt_sec_sys:
-				mnt->flags &= ~NFS_MOUNT_SECFLAVOUR;
-				mnt->auth_flavor_len = 0;
-				mnt->auth_flavors[0] = RPC_AUTH_UNIX;
-				break;
-			case Opt_sec_krb5:
-				mnt->flags |= NFS_MOUNT_SECFLAVOUR;
-				mnt->auth_flavor_len = 1;
-				mnt->auth_flavors[0] = RPC_AUTH_GSS_KRB5;
-				break;
-			case Opt_sec_krb5i:
-				mnt->flags |= NFS_MOUNT_SECFLAVOUR;
-				mnt->auth_flavor_len = 1;
-				mnt->auth_flavors[0] = RPC_AUTH_GSS_KRB5I;
-				break;
-			case Opt_sec_krb5p:
-				mnt->flags |= NFS_MOUNT_SECFLAVOUR;
-				mnt->auth_flavor_len = 1;
-				mnt->auth_flavors[0] = RPC_AUTH_GSS_KRB5P;
-				break;
-			case Opt_sec_lkey:
-				mnt->flags |= NFS_MOUNT_SECFLAVOUR;
-				mnt->auth_flavor_len = 1;
-				mnt->auth_flavors[0] = RPC_AUTH_GSS_LKEY;
-				break;
-			case Opt_sec_lkeyi:
-				mnt->flags |= NFS_MOUNT_SECFLAVOUR;
-				mnt->auth_flavor_len = 1;
-				mnt->auth_flavors[0] = RPC_AUTH_GSS_LKEYI;
-				break;
-			case Opt_sec_lkeyp:
-				mnt->flags |= NFS_MOUNT_SECFLAVOUR;
-				mnt->auth_flavor_len = 1;
-				mnt->auth_flavors[0] = RPC_AUTH_GSS_LKEYP;
-				break;
-			case Opt_sec_spkm:
-				mnt->flags |= NFS_MOUNT_SECFLAVOUR;
-				mnt->auth_flavor_len = 1;
-				mnt->auth_flavors[0] = RPC_AUTH_GSS_SPKM;
-				break;
-			case Opt_sec_spkmi:
-				mnt->flags |= NFS_MOUNT_SECFLAVOUR;
-				mnt->auth_flavor_len = 1;
-				mnt->auth_flavors[0] = RPC_AUTH_GSS_SPKMI;
-				break;
-			case Opt_sec_spkmp:
-				mnt->flags |= NFS_MOUNT_SECFLAVOUR;
-				mnt->auth_flavor_len = 1;
-				mnt->auth_flavors[0] = RPC_AUTH_GSS_SPKMP;
-				break;
-			default:
-				goto out_unrec_sec;
+			if (!rc) {
+				errors++;
+				dfprintk(MOUNT, "NFS:   unrecognized "
+						"security flavor\n");
 			}
 			break;
 		case Opt_proto:
@@ -1026,24 +1186,20 @@ static int nfs_parse_mount_options(char *raw,
 			case Opt_xprt_udp:
 				mnt->flags &= ~NFS_MOUNT_TCP;
 				mnt->nfs_server.protocol = XPRT_TRANSPORT_UDP;
-				mnt->timeo = 7;
-				mnt->retrans = 5;
 				break;
 			case Opt_xprt_tcp:
 				mnt->flags |= NFS_MOUNT_TCP;
 				mnt->nfs_server.protocol = XPRT_TRANSPORT_TCP;
-				mnt->timeo = 600;
-				mnt->retrans = 2;
 				break;
 			case Opt_xprt_rdma:
 				/* vector side protocols to TCP */
 				mnt->flags |= NFS_MOUNT_TCP;
 				mnt->nfs_server.protocol = XPRT_TRANSPORT_RDMA;
-				mnt->timeo = 600;
-				mnt->retrans = 2;
 				break;
 			default:
-				goto out_unrec_xprt;
+				errors++;
+				dfprintk(MOUNT, "NFS:   unrecognized "
+						"transport protocol\n");
 			}
 			break;
 		case Opt_mountproto:
@@ -1063,16 +1219,19 @@ static int nfs_parse_mount_options(char *raw,
 				break;
 			case Opt_xprt_rdma: /* not used for side protocols */
 			default:
-				goto out_unrec_xprt;
+				errors++;
+				dfprintk(MOUNT, "NFS:   unrecognized "
+						"transport protocol\n");
 			}
 			break;
 		case Opt_addr:
 			string = match_strdup(args);
 			if (string == NULL)
 				goto out_nomem;
-			nfs_parse_server_address(string, (struct sockaddr *)
-						 &mnt->nfs_server.address,
-						 &mnt->nfs_server.addrlen);
+			nfs_parse_ip_address(string, strlen(string),
+					     (struct sockaddr *)
+						&mnt->nfs_server.address,
+					     &mnt->nfs_server.addrlen);
 			kfree(string);
 			break;
 		case Opt_clientaddr:
@@ -1093,24 +1252,33 @@ static int nfs_parse_mount_options(char *raw,
 			string = match_strdup(args);
 			if (string == NULL)
 				goto out_nomem;
-			nfs_parse_server_address(string, (struct sockaddr *)
-						 &mnt->mount_server.address,
-						 &mnt->mount_server.addrlen);
+			nfs_parse_ip_address(string, strlen(string),
+					     (struct sockaddr *)
+						&mnt->mount_server.address,
+					     &mnt->mount_server.addrlen);
 			kfree(string);
 			break;
 
+		/*
+		 * Special options
+		 */
+		case Opt_sloppy:
+			sloppy = 1;
+			dfprintk(MOUNT, "NFS:   relaxing parsing rules\n");
+			break;
 		case Opt_userspace:
 		case Opt_deprecated:
+			dfprintk(MOUNT, "NFS:   ignoring mount option "
+					"'%s'\n", p);
 			break;
 
 		default:
-			goto out_unknown;
+			errors++;
+			dfprintk(MOUNT, "NFS:   unrecognized mount option "
+					"'%s'\n", p);
 		}
 	}
 
-	nfs_set_port((struct sockaddr *)&mnt->nfs_server.address,
-				mnt->nfs_server.port);
-
 	return 1;
 
 out_nomem:
@@ -1120,21 +1288,6 @@ out_security_failure:
 	free_secdata(secdata);
 	printk(KERN_INFO "NFS: security options invalid: %d\n", rc);
 	return 0;
-out_unrec_vers:
-	printk(KERN_INFO "NFS: unrecognized NFS version number\n");
-	return 0;
-
-out_unrec_xprt:
-	printk(KERN_INFO "NFS: unrecognized transport protocol\n");
-	return 0;
-
-out_unrec_sec:
-	printk(KERN_INFO "NFS: unrecognized security flavor\n");
-	return 0;
-
-out_unknown:
-	printk(KERN_INFO "NFS: unknown mount option: %s\n", p);
-	return 0;
 }
 
 /*
@@ -1188,11 +1341,146 @@ static int nfs_try_mount(struct nfs_parsed_mount_data *args,
 	if (status == 0)
 		return 0;
 
-	dfprintk(MOUNT, "NFS: unable to mount server %s, error %d",
+	dfprintk(MOUNT, "NFS: unable to mount server %s, error %d\n",
 			hostname, status);
 	return status;
 }
 
+static int nfs_parse_simple_hostname(const char *dev_name,
+				     char **hostname, size_t maxnamlen,
+				     char **export_path, size_t maxpathlen)
+{
+	size_t len;
+	char *colon, *comma;
+
+	colon = strchr(dev_name, ':');
+	if (colon == NULL)
+		goto out_bad_devname;
+
+	len = colon - dev_name;
+	if (len > maxnamlen)
+		goto out_hostname;
+
+	/* N.B. caller will free nfs_server.hostname in all cases */
+	*hostname = kstrndup(dev_name, len, GFP_KERNEL);
+	if (!*hostname)
+		goto out_nomem;
+
+	/* kill possible hostname list: not supported */
+	comma = strchr(*hostname, ',');
+	if (comma != NULL) {
+		if (comma == *hostname)
+			goto out_bad_devname;
+		*comma = '\0';
+	}
+
+	colon++;
+	len = strlen(colon);
+	if (len > maxpathlen)
+		goto out_path;
+	*export_path = kstrndup(colon, len, GFP_KERNEL);
+	if (!*export_path)
+		goto out_nomem;
+
+	dfprintk(MOUNT, "NFS: MNTPATH: '%s'\n", *export_path);
+	return 0;
+
+out_bad_devname:
+	dfprintk(MOUNT, "NFS: device name not in host:path format\n");
+	return -EINVAL;
+
+out_nomem:
+	dfprintk(MOUNT, "NFS: not enough memory to parse device name\n");
+	return -ENOMEM;
+
+out_hostname:
+	dfprintk(MOUNT, "NFS: server hostname too long\n");
+	return -ENAMETOOLONG;
+
+out_path:
+	dfprintk(MOUNT, "NFS: export pathname too long\n");
+	return -ENAMETOOLONG;
+}
+
+/*
+ * Hostname has square brackets around it because it contains one or
+ * more colons.  We look for the first closing square bracket, and a
+ * colon must follow it.
+ */
+static int nfs_parse_protected_hostname(const char *dev_name,
+					char **hostname, size_t maxnamlen,
+					char **export_path, size_t maxpathlen)
+{
+	size_t len;
+	char *start, *end;
+
+	start = (char *)(dev_name + 1);
+
+	end = strchr(start, ']');
+	if (end == NULL)
+		goto out_bad_devname;
+	if (*(end + 1) != ':')
+		goto out_bad_devname;
+
+	len = end - start;
+	if (len > maxnamlen)
+		goto out_hostname;
+
+	/* N.B. caller will free nfs_server.hostname in all cases */
+	*hostname = kstrndup(start, len, GFP_KERNEL);
+	if (*hostname == NULL)
+		goto out_nomem;
+
+	end += 2;
+	len = strlen(end);
+	if (len > maxpathlen)
+		goto out_path;
+	*export_path = kstrndup(end, len, GFP_KERNEL);
+	if (!*export_path)
+		goto out_nomem;
+
+	return 0;
+
+out_bad_devname:
+	dfprintk(MOUNT, "NFS: device name not in host:path format\n");
+	return -EINVAL;
+
+out_nomem:
+	dfprintk(MOUNT, "NFS: not enough memory to parse device name\n");
+	return -ENOMEM;
+
+out_hostname:
+	dfprintk(MOUNT, "NFS: server hostname too long\n");
+	return -ENAMETOOLONG;
+
+out_path:
+	dfprintk(MOUNT, "NFS: export pathname too long\n");
+	return -ENAMETOOLONG;
+}
+
+/*
+ * Split "dev_name" into "hostname:export_path".
+ *
+ * The leftmost colon demarks the split between the server's hostname
+ * and the export path.  If the hostname starts with a left square
+ * bracket, then it may contain colons.
+ *
+ * Note: caller frees hostname and export path, even on error.
+ */
+static int nfs_parse_devname(const char *dev_name,
+			     char **hostname, size_t maxnamlen,
+			     char **export_path, size_t maxpathlen)
+{
+	if (*dev_name == '[')
+		return nfs_parse_protected_hostname(dev_name,
+						    hostname, maxnamlen,
+						    export_path, maxpathlen);
+
+	return nfs_parse_simple_hostname(dev_name,
+					 hostname, maxnamlen,
+					 export_path, maxpathlen);
+}
+
 /*
  * Validate the NFS2/NFS3 mount data
  * - fills in the mount root filehandle
@@ -1222,16 +1510,14 @@ static int nfs_validate_mount_data(void *options,
 	args->flags		= (NFS_MOUNT_VER3 | NFS_MOUNT_TCP);
 	args->rsize		= NFS_MAX_FILE_IO_SIZE;
 	args->wsize		= NFS_MAX_FILE_IO_SIZE;
-	args->timeo		= 600;
-	args->retrans		= 2;
-	args->acregmin		= 3;
-	args->acregmax		= 60;
-	args->acdirmin		= 30;
-	args->acdirmax		= 60;
+	args->acregmin		= NFS_DEF_ACREGMIN;
+	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->mount_server.protocol = XPRT_TRANSPORT_UDP;
 	args->nfs_server.port	= 0;	/* autobind unless user sets port */
 	args->nfs_server.protocol = XPRT_TRANSPORT_TCP;
+	args->auth_flavors[0]	= RPC_AUTH_UNIX;
 
 	switch (data->version) {
 	case 1:
@@ -1289,7 +1575,9 @@ static int nfs_validate_mount_data(void *options,
 		args->nfs_server.hostname = kstrdup(data->hostname, GFP_KERNEL);
 		args->namlen		= data->namlen;
 		args->bsize		= data->bsize;
-		args->auth_flavors[0]	= data->pseudoflavor;
+
+		if (data->flags & NFS_MOUNT_SECFLAVOUR)
+			args->auth_flavors[0] = data->pseudoflavor;
 		if (!args->nfs_server.hostname)
 			goto out_nomem;
 
@@ -1321,8 +1609,6 @@ static int nfs_validate_mount_data(void *options,
 
 		break;
 	default: {
-		unsigned int len;
-		char *c;
 		int status;
 
 		if (nfs_parse_mount_options((char *)options, args) == 0)
@@ -1332,21 +1618,22 @@ static int nfs_validate_mount_data(void *options,
 						&args->nfs_server.address))
 			goto out_no_address;
 
-		c = strchr(dev_name, ':');
-		if (c == NULL)
-			return -EINVAL;
-		len = c - dev_name;
-		/* N.B. caller will free nfs_server.hostname in all cases */
-		args->nfs_server.hostname = kstrndup(dev_name, len, GFP_KERNEL);
-		if (!args->nfs_server.hostname)
-			goto out_nomem;
+		nfs_set_port((struct sockaddr *)&args->nfs_server.address,
+				args->nfs_server.port);
 
-		c++;
-		if (strlen(c) > NFS_MAXPATHLEN)
-			return -ENAMETOOLONG;
-		args->nfs_server.export_path = c;
+		nfs_set_mount_transport_protocol(args);
+
+		status = nfs_parse_devname(dev_name,
+					   &args->nfs_server.hostname,
+					   PAGE_SIZE,
+					   &args->nfs_server.export_path,
+					   NFS_MAXPATHLEN);
+		if (!status)
+			status = nfs_try_mount(args, mntfh);
+
+		kfree(args->nfs_server.export_path);
+		args->nfs_server.export_path = NULL;
 
-		status = nfs_try_mount(args, mntfh);
 		if (status)
 			return status;
 
@@ -1354,9 +1641,6 @@ static int nfs_validate_mount_data(void *options,
 		}
 	}
 
-	if (!(args->flags & NFS_MOUNT_SECFLAVOUR))
-		args->auth_flavors[0] = RPC_AUTH_UNIX;
-
 #ifndef CONFIG_NFS_V3
 	if (args->flags & NFS_MOUNT_VER3)
 		goto out_v3_not_compiled;
@@ -1396,6 +1680,80 @@ out_invalid_fh:
 	return -EINVAL;
 }
 
+static int
+nfs_compare_remount_data(struct nfs_server *nfss,
+			 struct nfs_parsed_mount_data *data)
+{
+	if (data->flags != nfss->flags ||
+	    data->rsize != nfss->rsize ||
+	    data->wsize != nfss->wsize ||
+	    data->retrans != nfss->client->cl_timeout->to_retries ||
+	    data->auth_flavors[0] != nfss->client->cl_auth->au_flavor ||
+	    data->acregmin != nfss->acregmin / HZ ||
+	    data->acregmax != nfss->acregmax / HZ ||
+	    data->acdirmin != nfss->acdirmin / HZ ||
+	    data->acdirmax != nfss->acdirmax / HZ ||
+	    data->timeo != (10U * nfss->client->cl_timeout->to_initval / HZ) ||
+	    data->nfs_server.addrlen != nfss->nfs_client->cl_addrlen ||
+	    memcmp(&data->nfs_server.address, &nfss->nfs_client->cl_addr,
+		   data->nfs_server.addrlen) != 0)
+		return -EINVAL;
+
+	return 0;
+}
+
+static int
+nfs_remount(struct super_block *sb, int *flags, char *raw_data)
+{
+	int error;
+	struct nfs_server *nfss = sb->s_fs_info;
+	struct nfs_parsed_mount_data *data;
+	struct nfs_mount_data *options = (struct nfs_mount_data *)raw_data;
+	struct nfs4_mount_data *options4 = (struct nfs4_mount_data *)raw_data;
+	u32 nfsvers = nfss->nfs_client->rpc_ops->version;
+
+	/*
+	 * Userspace mount programs that send binary options generally send
+	 * them populated with default values. We have no way to know which
+	 * ones were explicitly specified. Fall back to legacy behavior and
+	 * just return success.
+	 */
+	if ((nfsvers == 4 && options4->version == 1) ||
+	    (nfsvers <= 3 && options->version >= 1 &&
+	     options->version <= 6))
+		return 0;
+
+	data = kzalloc(sizeof(*data), GFP_KERNEL);
+	if (data == NULL)
+		return -ENOMEM;
+
+	/* fill out struct with values from existing mount */
+	data->flags = nfss->flags;
+	data->rsize = nfss->rsize;
+	data->wsize = nfss->wsize;
+	data->retrans = nfss->client->cl_timeout->to_retries;
+	data->auth_flavors[0] = nfss->client->cl_auth->au_flavor;
+	data->acregmin = nfss->acregmin / HZ;
+	data->acregmax = nfss->acregmax / HZ;
+	data->acdirmin = nfss->acdirmin / HZ;
+	data->acdirmax = nfss->acdirmax / HZ;
+	data->timeo = 10U * nfss->client->cl_timeout->to_initval / HZ;
+	data->nfs_server.addrlen = nfss->nfs_client->cl_addrlen;
+	memcpy(&data->nfs_server.address, &nfss->nfs_client->cl_addr,
+		data->nfs_server.addrlen);
+
+	/* overwrite those values with any that were specified */
+	error = nfs_parse_mount_options((char *)options, data);
+	if (error < 0)
+		goto out;
+
+	/* compare new mount options with old ones */
+	error = nfs_compare_remount_data(nfss, data);
+out:
+	kfree(data);
+	return error;
+}
+
 /*
  * Initialise the common bits of the superblock
  */
@@ -1811,14 +2169,13 @@ static int nfs4_validate_mount_data(void *options,
 
 	args->rsize		= NFS_MAX_FILE_IO_SIZE;
 	args->wsize		= NFS_MAX_FILE_IO_SIZE;
-	args->timeo		= 600;
-	args->retrans		= 2;
-	args->acregmin		= 3;
-	args->acregmax		= 60;
-	args->acdirmin		= 30;
-	args->acdirmax		= 60;
+	args->acregmin		= NFS_DEF_ACREGMIN;
+	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.protocol = XPRT_TRANSPORT_TCP;
+	args->auth_flavors[0]	= RPC_AUTH_UNIX;
+	args->auth_flavor_len	= 0;
 
 	switch (data->version) {
 	case 1:
@@ -1834,18 +2191,13 @@ static int nfs4_validate_mount_data(void *options,
 						&args->nfs_server.address))
 			goto out_no_address;
 
-		switch (data->auth_flavourlen) {
-		case 0:
-			args->auth_flavors[0] = RPC_AUTH_UNIX;
-			break;
-		case 1:
+		if (data->auth_flavourlen) {
+			if (data->auth_flavourlen > 1)
+				goto out_inval_auth;
 			if (copy_from_user(&args->auth_flavors[0],
 					   data->auth_flavours,
 					   sizeof(args->auth_flavors[0])))
 				return -EFAULT;
-			break;
-		default:
-			goto out_inval_auth;
 		}
 
 		c = strndup_user(data->hostname.data, NFS4_MAXNAMLEN);
@@ -1879,10 +2231,11 @@ static int nfs4_validate_mount_data(void *options,
 		args->acdirmin	= data->acdirmin;
 		args->acdirmax	= data->acdirmax;
 		args->nfs_server.protocol = data->proto;
+		nfs_validate_transport_protocol(args);
 
 		break;
 	default: {
-		unsigned int len;
+		int status;
 
 		if (nfs_parse_mount_options((char *)options, args) == 0)
 			return -EINVAL;
@@ -1891,44 +2244,25 @@ static int nfs4_validate_mount_data(void *options,
 						&args->nfs_server.address))
 			return -EINVAL;
 
-		switch (args->auth_flavor_len) {
-		case 0:
-			args->auth_flavors[0] = RPC_AUTH_UNIX;
-			break;
-		case 1:
-			break;
-		default:
-			goto out_inval_auth;
-		}
+		nfs_set_port((struct sockaddr *)&args->nfs_server.address,
+				args->nfs_server.port);
 
-		/*
-		 * Split "dev_name" into "hostname:mntpath".
-		 */
-		c = strchr(dev_name, ':');
-		if (c == NULL)
-			return -EINVAL;
-		/* while calculating len, pretend ':' is '\0' */
-		len = c - dev_name;
-		if (len > NFS4_MAXNAMLEN)
-			return -ENAMETOOLONG;
-		/* N.B. caller will free nfs_server.hostname in all cases */
-		args->nfs_server.hostname = kstrndup(dev_name, len, GFP_KERNEL);
-		if (!args->nfs_server.hostname)
-			goto out_nomem;
-
-		c++;			/* step over the ':' */
-		len = strlen(c);
-		if (len > NFS4_MAXPATHLEN)
-			return -ENAMETOOLONG;
-		args->nfs_server.export_path = kstrndup(c, len, GFP_KERNEL);
-		if (!args->nfs_server.export_path)
-			goto out_nomem;
+		nfs_validate_transport_protocol(args);
 
-		dprintk("NFS: MNTPATH: '%s'\n", args->nfs_server.export_path);
+		if (args->auth_flavor_len > 1)
+			goto out_inval_auth;
 
 		if (args->client_address == NULL)
 			goto out_no_client_address;
 
+		status = nfs_parse_devname(dev_name,
+					   &args->nfs_server.hostname,
+					   NFS4_MAXNAMLEN,
+					   &args->nfs_server.export_path,
+					   NFS4_MAXPATHLEN);
+		if (status < 0)
+			return status;
+
 		break;
 		}
 	}
@@ -1944,10 +2278,6 @@ out_inval_auth:
 		 data->auth_flavourlen);
 	return -EINVAL;
 
-out_nomem:
-	dfprintk(MOUNT, "NFS4: not enough memory to handle mount options\n");
-	return -ENOMEM;
-
 out_no_address:
 	dfprintk(MOUNT, "NFS4: mount program didn't pass remote address\n");
 	return -EINVAL;

fs/nfs/write.c

@@ -34,9 +34,6 @@
 /*
  * Local function declarations
  */
-static struct nfs_page * nfs_update_request(struct nfs_open_context*,
-					    struct page *,
-					    unsigned int, unsigned int);
 static void nfs_pageio_init_write(struct nfs_pageio_descriptor *desc,
 				  struct inode *inode, int ioflags);
 static void nfs_redirty_request(struct nfs_page *req);
@@ -136,16 +133,21 @@ static struct nfs_page *nfs_page_find_request(struct page *page)
 static void nfs_grow_file(struct page *page, unsigned int offset, unsigned int count)
 {
 	struct inode *inode = page->mapping->host;
-	loff_t end, i_size = i_size_read(inode);
-	pgoff_t end_index = (i_size - 1) >> PAGE_CACHE_SHIFT;
+	loff_t end, i_size;
+	pgoff_t end_index;
 
+	spin_lock(&inode->i_lock);
+	i_size = i_size_read(inode);
+	end_index = (i_size - 1) >> PAGE_CACHE_SHIFT;
 	if (i_size > 0 && page->index < end_index)
-		return;
+		goto out;
 	end = ((loff_t)page->index << PAGE_CACHE_SHIFT) + ((loff_t)offset+count);
 	if (i_size >= end)
-		return;
-	nfs_inc_stats(inode, NFSIOS_EXTENDWRITE);
+		goto out;
 	i_size_write(inode, end);
+	nfs_inc_stats(inode, NFSIOS_EXTENDWRITE);
+out:
+	spin_unlock(&inode->i_lock);
 }
 
 /* A writeback failed: mark the page as bad, and invalidate the page cache */
@@ -169,29 +171,6 @@ static void nfs_mark_uptodate(struct page *page, unsigned int base, unsigned int
 	SetPageUptodate(page);
 }
 
-static int nfs_writepage_setup(struct nfs_open_context *ctx, struct page *page,
-		unsigned int offset, unsigned int count)
-{
-	struct nfs_page	*req;
-	int ret;
-
-	for (;;) {
-		req = nfs_update_request(ctx, page, offset, count);
-		if (!IS_ERR(req))
-			break;
-		ret = PTR_ERR(req);
-		if (ret != -EBUSY)
-			return ret;
-		ret = nfs_wb_page(page->mapping->host, page);
-		if (ret != 0)
-			return ret;
-	}
-	/* Update file length */
-	nfs_grow_file(page, offset, count);
-	nfs_clear_page_tag_locked(req);
-	return 0;
-}
-
 static int wb_priority(struct writeback_control *wbc)
 {
 	if (wbc->for_reclaim)
@@ -268,12 +247,9 @@ static int nfs_page_async_flush(struct nfs_pageio_descriptor *pgio,
 			return ret;
 		spin_lock(&inode->i_lock);
 	}
-	if (test_bit(PG_NEED_COMMIT, &req->wb_flags)) {
-		/* This request is marked for commit */
+	if (test_bit(PG_CLEAN, &req->wb_flags)) {
 		spin_unlock(&inode->i_lock);
-		nfs_clear_page_tag_locked(req);
-		nfs_pageio_complete(pgio);
-		return 0;
+		BUG();
 	}
 	if (nfs_set_page_writeback(page) != 0) {
 		spin_unlock(&inode->i_lock);
@@ -355,11 +331,19 @@ int nfs_writepages(struct address_space *mapping, struct writeback_control *wbc)
 /*
  * Insert a write request into an inode
  */
-static void nfs_inode_add_request(struct inode *inode, struct nfs_page *req)
+static int nfs_inode_add_request(struct inode *inode, struct nfs_page *req)
 {
 	struct nfs_inode *nfsi = NFS_I(inode);
 	int error;
 
+	error = radix_tree_preload(GFP_NOFS);
+	if (error != 0)
+		goto out;
+
+	/* Lock the request! */
+	nfs_lock_request_dontget(req);
+
+	spin_lock(&inode->i_lock);
 	error = radix_tree_insert(&nfsi->nfs_page_tree, req->wb_index, req);
 	BUG_ON(error);
 	if (!nfsi->npages) {
@@ -373,6 +357,10 @@ static void nfs_inode_add_request(struct inode *inode, struct nfs_page *req)
 	kref_get(&req->wb_kref);
 	radix_tree_tag_set(&nfsi->nfs_page_tree, req->wb_index,
 				NFS_PAGE_TAG_LOCKED);
+	spin_unlock(&inode->i_lock);
+	radix_tree_preload_end();
+out:
+	return error;
 }
 
 /*
@@ -405,19 +393,6 @@ nfs_mark_request_dirty(struct nfs_page *req)
 	__set_page_dirty_nobuffers(req->wb_page);
 }
 
-/*
- * Check if a request is dirty
- */
-static inline int
-nfs_dirty_request(struct nfs_page *req)
-{
-	struct page *page = req->wb_page;
-
-	if (page == NULL || test_bit(PG_NEED_COMMIT, &req->wb_flags))
-		return 0;
-	return !PageWriteback(page);
-}
-
 #if defined(CONFIG_NFS_V3) || defined(CONFIG_NFS_V4)
 /*
  * Add a request to the inode's commit list.
@@ -430,7 +405,7 @@ nfs_mark_request_commit(struct nfs_page *req)
 
 	spin_lock(&inode->i_lock);
 	nfsi->ncommit++;
-	set_bit(PG_NEED_COMMIT, &(req)->wb_flags);
+	set_bit(PG_CLEAN, &(req)->wb_flags);
 	radix_tree_tag_set(&nfsi->nfs_page_tree,
 			req->wb_index,
 			NFS_PAGE_TAG_COMMIT);
@@ -440,6 +415,19 @@ nfs_mark_request_commit(struct nfs_page *req)
 	__mark_inode_dirty(inode, I_DIRTY_DATASYNC);
 }
 
+static int
+nfs_clear_request_commit(struct nfs_page *req)
+{
+	struct page *page = req->wb_page;
+
+	if (test_and_clear_bit(PG_CLEAN, &(req)->wb_flags)) {
+		dec_zone_page_state(page, NR_UNSTABLE_NFS);
+		dec_bdi_stat(page->mapping->backing_dev_info, BDI_RECLAIMABLE);
+		return 1;
+	}
+	return 0;
+}
+
 static inline
 int nfs_write_need_commit(struct nfs_write_data *data)
 {
@@ -449,7 +437,7 @@ int nfs_write_need_commit(struct nfs_write_data *data)
 static inline
 int nfs_reschedule_unstable_write(struct nfs_page *req)
 {
-	if (test_bit(PG_NEED_COMMIT, &req->wb_flags)) {
+	if (test_and_clear_bit(PG_NEED_COMMIT, &req->wb_flags)) {
 		nfs_mark_request_commit(req);
 		return 1;
 	}
@@ -465,6 +453,12 @@ nfs_mark_request_commit(struct nfs_page *req)
 {
 }
 
+static inline int
+nfs_clear_request_commit(struct nfs_page *req)
+{
+	return 0;
+}
+
 static inline
 int nfs_write_need_commit(struct nfs_write_data *data)
 {
@@ -522,11 +516,8 @@ static void nfs_cancel_commit_list(struct list_head *head)
 
 	while(!list_empty(head)) {
 		req = nfs_list_entry(head->next);
-		dec_zone_page_state(req->wb_page, NR_UNSTABLE_NFS);
-		dec_bdi_stat(req->wb_page->mapping->backing_dev_info,
-				BDI_RECLAIMABLE);
 		nfs_list_remove_request(req);
-		clear_bit(PG_NEED_COMMIT, &(req)->wb_flags);
+		nfs_clear_request_commit(req);
 		nfs_inode_remove_request(req);
 		nfs_unlock_request(req);
 	}
@@ -564,110 +555,124 @@ static inline int nfs_scan_commit(struct inode *inode, struct list_head *dst, pg
 #endif
 
 /*
- * Try to update any existing write request, or create one if there is none.
- * In order to match, the request's credentials must match those of
- * the calling process.
+ * Search for an existing write request, and attempt to update
+ * it to reflect a new dirty region on a given page.
  *
- * Note: Should always be called with the Page Lock held!
+ * If the attempt fails, then the existing request is flushed out
+ * to disk.
  */
-static struct nfs_page * nfs_update_request(struct nfs_open_context* ctx,
-		struct page *page, unsigned int offset, unsigned int bytes)
+static struct nfs_page *nfs_try_to_update_request(struct inode *inode,
+		struct page *page,
+		unsigned int offset,
+		unsigned int bytes)
 {
-	struct address_space *mapping = page->mapping;
-	struct inode *inode = mapping->host;
-	struct nfs_page		*req, *new = NULL;
-	pgoff_t		rqend, end;
+	struct nfs_page *req;
+	unsigned int rqend;
+	unsigned int end;
+	int error;
+
+	if (!PagePrivate(page))
+		return NULL;
 
 	end = offset + bytes;
+	spin_lock(&inode->i_lock);
 
 	for (;;) {
-		/* Loop over all inode entries and see if we find
-		 * A request for the page we wish to update
+		req = nfs_page_find_request_locked(page);
+		if (req == NULL)
+			goto out_unlock;
+
+		rqend = req->wb_offset + req->wb_bytes;
+		/*
+		 * Tell the caller to flush out the request if
+		 * the offsets are non-contiguous.
+		 * Note: nfs_flush_incompatible() will already
+		 * have flushed out requests having wrong owners.
 		 */
-		if (new) {
-			if (radix_tree_preload(GFP_NOFS)) {
-				nfs_release_request(new);
-				return ERR_PTR(-ENOMEM);
-			}
-		}
+		if (offset > rqend
+		    || end < req->wb_offset)
+			goto out_flushme;
 
-		spin_lock(&inode->i_lock);
-		req = nfs_page_find_request_locked(page);
-		if (req) {
-			if (!nfs_set_page_tag_locked(req)) {
-				int error;
-
-				spin_unlock(&inode->i_lock);
-				error = nfs_wait_on_request(req);
-				nfs_release_request(req);
-				if (error < 0) {
-					if (new) {
-						radix_tree_preload_end();
-						nfs_release_request(new);
-					}
-					return ERR_PTR(error);
-				}
-				continue;
-			}
-			spin_unlock(&inode->i_lock);
-			if (new) {
-				radix_tree_preload_end();
-				nfs_release_request(new);
-			}
+		if (nfs_set_page_tag_locked(req))
 			break;
-		}
 
-		if (new) {
-			nfs_lock_request_dontget(new);
-			nfs_inode_add_request(inode, new);
-			spin_unlock(&inode->i_lock);
-			radix_tree_preload_end();
-			req = new;
-			goto zero_page;
-		}
+		/* The request is locked, so wait and then retry */
 		spin_unlock(&inode->i_lock);
-
-		new = nfs_create_request(ctx, inode, page, offset, bytes);
-		if (IS_ERR(new))
-			return new;
+		error = nfs_wait_on_request(req);
+		nfs_release_request(req);
+		if (error != 0)
+			goto out_err;
+		spin_lock(&inode->i_lock);
 	}
 
-	/* We have a request for our page.
-	 * If the creds don't match, or the
-	 * page addresses don't match,
-	 * tell the caller to wait on the conflicting
-	 * request.
-	 */
-	rqend = req->wb_offset + req->wb_bytes;
-	if (req->wb_context != ctx
-	    || req->wb_page != page
-	    || !nfs_dirty_request(req)
-	    || offset > rqend || end < req->wb_offset) {
-		nfs_clear_page_tag_locked(req);
-		return ERR_PTR(-EBUSY);
-	}
+	if (nfs_clear_request_commit(req))
+		radix_tree_tag_clear(&NFS_I(inode)->nfs_page_tree,
+				req->wb_index, NFS_PAGE_TAG_COMMIT);
 
 	/* Okay, the request matches. Update the region */
 	if (offset < req->wb_offset) {
 		req->wb_offset = offset;
 		req->wb_pgbase = offset;
-		req->wb_bytes = max(end, rqend) - req->wb_offset;
-		goto zero_page;
 	}
-
 	if (end > rqend)
 		req->wb_bytes = end - req->wb_offset;
-
+	else
+		req->wb_bytes = rqend - req->wb_offset;
+out_unlock:
+	spin_unlock(&inode->i_lock);
 	return req;
-zero_page:
-	/* If this page might potentially be marked as up to date,
-	 * then we need to zero any uninitalised data. */
-	if (req->wb_pgbase == 0 && req->wb_bytes != PAGE_CACHE_SIZE
-			&& !PageUptodate(req->wb_page))
-		zero_user_segment(req->wb_page, req->wb_bytes, PAGE_CACHE_SIZE);
+out_flushme:
+	spin_unlock(&inode->i_lock);
+	nfs_release_request(req);
+	error = nfs_wb_page(inode, page);
+out_err:
+	return ERR_PTR(error);
+}
+
+/*
+ * Try to update an existing write request, or create one if there is none.
+ *
+ * Note: Should always be called with the Page Lock held to prevent races
+ * if we have to add a new request. Also assumes that the caller has
+ * already called nfs_flush_incompatible() if necessary.
+ */
+static struct nfs_page * nfs_setup_write_request(struct nfs_open_context* ctx,
+		struct page *page, unsigned int offset, unsigned int bytes)
+{
+	struct inode *inode = page->mapping->host;
+	struct nfs_page	*req;
+	int error;
+
+	req = nfs_try_to_update_request(inode, page, offset, bytes);
+	if (req != NULL)
+		goto out;
+	req = nfs_create_request(ctx, inode, page, offset, bytes);
+	if (IS_ERR(req))
+		goto out;
+	error = nfs_inode_add_request(inode, req);
+	if (error != 0) {
+		nfs_release_request(req);
+		req = ERR_PTR(error);
+	}
+out:
 	return req;
 }
 
+static int nfs_writepage_setup(struct nfs_open_context *ctx, struct page *page,
+		unsigned int offset, unsigned int count)
+{
+	struct nfs_page	*req;
+
+	req = nfs_setup_write_request(ctx, page, offset, count);
+	if (IS_ERR(req))
+		return PTR_ERR(req);
+	/* Update file length */
+	nfs_grow_file(page, offset, count);
+	nfs_mark_uptodate(page, req->wb_pgbase, req->wb_bytes);
+	nfs_clear_page_tag_locked(req);
+	return 0;
+}
+
 int nfs_flush_incompatible(struct file *file, struct page *page)
 {
 	struct nfs_open_context *ctx = nfs_file_open_context(file);
@@ -685,8 +690,7 @@ int nfs_flush_incompatible(struct file *file, struct page *page)
 		req = nfs_page_find_request(page);
 		if (req == NULL)
 			return 0;
-		do_flush = req->wb_page != page || req->wb_context != ctx
-			|| !nfs_dirty_request(req);
+		do_flush = req->wb_page != page || req->wb_context != ctx;
 		nfs_release_request(req);
 		if (!do_flush)
 			return 0;
@@ -721,10 +725,10 @@ int nfs_updatepage(struct file *file, struct page *page,
 
 	nfs_inc_stats(inode, NFSIOS_VFSUPDATEPAGE);
 
-	dprintk("NFS:      nfs_updatepage(%s/%s %d@%Ld)\n",
+	dprintk("NFS:       nfs_updatepage(%s/%s %d@%lld)\n",
 		file->f_path.dentry->d_parent->d_name.name,
 		file->f_path.dentry->d_name.name, count,
-		(long long)(page_offset(page) +offset));
+		(long long)(page_offset(page) + offset));
 
 	/* If we're not using byte range locks, and we know the page
 	 * is up to date, it may be more efficient to extend the write
@@ -744,7 +748,7 @@ int nfs_updatepage(struct file *file, struct page *page,
 	else
 		__set_page_dirty_nobuffers(page);
 
-        dprintk("NFS:      nfs_updatepage returns %d (isize %Ld)\n",
+	dprintk("NFS:       nfs_updatepage returns %d (isize %lld)\n",
 			status, (long long)i_size_read(inode));
 	return status;
 }
@@ -752,12 +756,7 @@ int nfs_updatepage(struct file *file, struct page *page,
 static void nfs_writepage_release(struct nfs_page *req)
 {
 
-	if (PageError(req->wb_page)) {
-		nfs_end_page_writeback(req->wb_page);
-		nfs_inode_remove_request(req);
-	} else if (!nfs_reschedule_unstable_write(req)) {
-		/* Set the PG_uptodate flag */
-		nfs_mark_uptodate(req->wb_page, req->wb_pgbase, req->wb_bytes);
+	if (PageError(req->wb_page) || !nfs_reschedule_unstable_write(req)) {
 		nfs_end_page_writeback(req->wb_page);
 		nfs_inode_remove_request(req);
 	} else
@@ -834,7 +833,7 @@ static int nfs_write_rpcsetup(struct nfs_page *req,
 	NFS_PROTO(inode)->write_setup(data, &msg);
 
 	dprintk("NFS: %5u initiated write call "
-		"(req %s/%Ld, %u bytes @ offset %Lu)\n",
+		"(req %s/%lld, %u bytes @ offset %llu)\n",
 		data->task.tk_pid,
 		inode->i_sb->s_id,
 		(long long)NFS_FILEID(inode),
@@ -978,13 +977,13 @@ static void nfs_pageio_init_write(struct nfs_pageio_descriptor *pgio,
 static void nfs_writeback_done_partial(struct rpc_task *task, void *calldata)
 {
 	struct nfs_write_data	*data = calldata;
-	struct nfs_page		*req = data->req;
 
-	dprintk("NFS: write (%s/%Ld %d@%Ld)",
-		req->wb_context->path.dentry->d_inode->i_sb->s_id,
-		(long long)NFS_FILEID(req->wb_context->path.dentry->d_inode),
-		req->wb_bytes,
-		(long long)req_offset(req));
+	dprintk("NFS: %5u write(%s/%lld %d@%lld)",
+		task->tk_pid,
+		data->req->wb_context->path.dentry->d_inode->i_sb->s_id,
+		(long long)
+		  NFS_FILEID(data->req->wb_context->path.dentry->d_inode),
+		data->req->wb_bytes, (long long)req_offset(data->req));
 
 	nfs_writeback_done(task, data);
 }
@@ -1058,7 +1057,8 @@ static void nfs_writeback_release_full(void *calldata)
 
 		nfs_list_remove_request(req);
 
-		dprintk("NFS: write (%s/%Ld %d@%Ld)",
+		dprintk("NFS: %5u write (%s/%lld %d@%lld)",
+			data->task.tk_pid,
 			req->wb_context->path.dentry->d_inode->i_sb->s_id,
 			(long long)NFS_FILEID(req->wb_context->path.dentry->d_inode),
 			req->wb_bytes,
@@ -1078,8 +1078,6 @@ static void nfs_writeback_release_full(void *calldata)
 			dprintk(" marked for commit\n");
 			goto next;
 		}
-		/* Set the PG_uptodate flag? */
-		nfs_mark_uptodate(page, req->wb_pgbase, req->wb_bytes);
 		dprintk(" OK\n");
 remove_request:
 		nfs_end_page_writeback(page);
@@ -1133,7 +1131,7 @@ int nfs_writeback_done(struct rpc_task *task, struct nfs_write_data *data)
 		static unsigned long    complain;
 
 		if (time_before(complain, jiffies)) {
-			dprintk("NFS: faulty NFS server %s:"
+			dprintk("NFS:       faulty NFS server %s:"
 				" (committed = %d) != (stable = %d)\n",
 				NFS_SERVER(data->inode)->nfs_client->cl_hostname,
 				resp->verf->committed, argp->stable);
@@ -1297,12 +1295,9 @@ static void nfs_commit_release(void *calldata)
 	while (!list_empty(&data->pages)) {
 		req = nfs_list_entry(data->pages.next);
 		nfs_list_remove_request(req);
-		clear_bit(PG_NEED_COMMIT, &(req)->wb_flags);
-		dec_zone_page_state(req->wb_page, NR_UNSTABLE_NFS);
-		dec_bdi_stat(req->wb_page->mapping->backing_dev_info,
-				BDI_RECLAIMABLE);
+		nfs_clear_request_commit(req);
 
-		dprintk("NFS: commit (%s/%Ld %d@%Ld)",
+		dprintk("NFS:       commit (%s/%lld %d@%lld)",
 			req->wb_context->path.dentry->d_inode->i_sb->s_id,
 			(long long)NFS_FILEID(req->wb_context->path.dentry->d_inode),
 			req->wb_bytes,
@@ -1318,9 +1313,6 @@ static void nfs_commit_release(void *calldata)
 		 * returned by the server against all stored verfs. */
 		if (!memcmp(req->wb_verf.verifier, data->verf.verifier, sizeof(data->verf.verifier))) {
 			/* We have a match */
-			/* Set the PG_uptodate flag */
-			nfs_mark_uptodate(req->wb_page, req->wb_pgbase,
-					req->wb_bytes);
 			nfs_inode_remove_request(req);
 			dprintk(" OK\n");
 			goto next;
@@ -1479,7 +1471,7 @@ int nfs_wb_page_cancel(struct inode *inode, struct page *page)
 		req = nfs_page_find_request(page);
 		if (req == NULL)
 			goto out;
-		if (test_bit(PG_NEED_COMMIT, &req->wb_flags)) {
+		if (test_bit(PG_CLEAN, &req->wb_flags)) {
 			nfs_release_request(req);
 			break;
 		}

fs/nfsd/nfs4callback.c

@@ -381,7 +381,7 @@ static int do_probe_callback(void *data)
 		.program	= &cb_program,
 		.version	= nfs_cb_version[1]->number,
 		.authflavor	= RPC_AUTH_UNIX, /* XXX: need AUTH_GSS... */
-		.flags		= (RPC_CLNT_CREATE_NOPING),
+		.flags		= (RPC_CLNT_CREATE_NOPING | RPC_CLNT_CREATE_QUIET),
 	};
 	struct rpc_message msg = {
 		.rpc_proc       = &nfs4_cb_procedures[NFSPROC4_CLNT_CB_NULL],

include/linux/inet.h

@@ -44,6 +44,13 @@
 
 #include <linux/types.h>
 
+/*
+ * These mimic similar macros defined in user-space for inet_ntop(3).
+ * See /usr/include/netinet/in.h .
+ */
+#define INET_ADDRSTRLEN		(16)
+#define INET6_ADDRSTRLEN	(48)
+
 extern __be32 in_aton(const char *str);
 extern int in4_pton(const char *src, int srclen, u8 *dst, int delim, const char **end);
 extern int in6_pton(const char *src, int srclen, u8 *dst, int delim, const char **end);

include/linux/nfs_fs.h

@@ -12,9 +12,19 @@
 #include <linux/magic.h>
 
 /* Default timeout values */
+#define NFS_DEF_UDP_TIMEO	(11)
+#define NFS_DEF_UDP_RETRANS	(3)
+#define NFS_DEF_TCP_TIMEO	(600)
+#define NFS_DEF_TCP_RETRANS	(2)
+
 #define NFS_MAX_UDP_TIMEOUT	(60*HZ)
 #define NFS_MAX_TCP_TIMEOUT	(600*HZ)
 
+#define NFS_DEF_ACREGMIN	(3)
+#define NFS_DEF_ACREGMAX	(60)
+#define NFS_DEF_ACDIRMIN	(30)
+#define NFS_DEF_ACDIRMAX	(60)
+
 /*
  * When flushing a cluster of dirty pages, there can be different
  * strategies:

include/linux/nfs_iostat.h

@@ -0,0 +1,119 @@
+/*
+ *  User-space visible declarations for NFS client per-mount
+ *  point statistics
+ *
+ *  Copyright (C) 2005, 2006 Chuck Lever <cel@netapp.com>
+ *
+ *  NFS client per-mount statistics provide information about the
+ *  health of the NFS client and the health of each NFS mount point.
+ *  Generally these are not for detailed problem diagnosis, but
+ *  simply to indicate that there is a problem.
+ *
+ *  These counters are not meant to be human-readable, but are meant
+ *  to be integrated into system monitoring tools such as "sar" and
+ *  "iostat".  As such, the counters are sampled by the tools over
+ *  time, and are never zeroed after a file system is mounted.
+ *  Moving averages can be computed by the tools by taking the
+ *  difference between two instantaneous samples  and dividing that
+ *  by the time between the samples.
+ */
+
+#ifndef _LINUX_NFS_IOSTAT
+#define _LINUX_NFS_IOSTAT
+
+#define NFS_IOSTAT_VERS		"1.0"
+
+/*
+ * NFS byte counters
+ *
+ * 1.  SERVER - the number of payload bytes read from or written
+ *     to the server by the NFS client via an NFS READ or WRITE
+ *     request.
+ *
+ * 2.  NORMAL - the number of bytes read or written by applications
+ *     via the read(2) and write(2) system call interfaces.
+ *
+ * 3.  DIRECT - the number of bytes read or written from files
+ *     opened with the O_DIRECT flag.
+ *
+ * These counters give a view of the data throughput into and out
+ * of the NFS client.  Comparing the number of bytes requested by
+ * an application with the number of bytes the client requests from
+ * the server can provide an indication of client efficiency
+ * (per-op, cache hits, etc).
+ *
+ * These counters can also help characterize which access methods
+ * are in use.  DIRECT by itself shows whether there is any O_DIRECT
+ * traffic.  NORMAL + DIRECT shows how much data is going through
+ * the system call interface.  A large amount of SERVER traffic
+ * without much NORMAL or DIRECT traffic shows that applications
+ * are using mapped files.
+ *
+ * NFS page counters
+ *
+ * These count the number of pages read or written via nfs_readpage(),
+ * nfs_readpages(), or their write equivalents.
+ *
+ * NB: When adding new byte counters, please include the measured
+ * units in the name of each byte counter to help users of this
+ * interface determine what exactly is being counted.
+ */
+enum nfs_stat_bytecounters {
+	NFSIOS_NORMALREADBYTES = 0,
+	NFSIOS_NORMALWRITTENBYTES,
+	NFSIOS_DIRECTREADBYTES,
+	NFSIOS_DIRECTWRITTENBYTES,
+	NFSIOS_SERVERREADBYTES,
+	NFSIOS_SERVERWRITTENBYTES,
+	NFSIOS_READPAGES,
+	NFSIOS_WRITEPAGES,
+	__NFSIOS_BYTESMAX,
+};
+
+/*
+ * NFS event counters
+ *
+ * These counters provide a low-overhead way of monitoring client
+ * activity without enabling NFS trace debugging.  The counters
+ * show the rate at which VFS requests are made, and how often the
+ * client invalidates its data and attribute caches.  This allows
+ * system administrators to monitor such things as how close-to-open
+ * is working, and answer questions such as "why are there so many
+ * GETATTR requests on the wire?"
+ *
+ * They also count anamolous events such as short reads and writes,
+ * silly renames due to close-after-delete, and operations that
+ * change the size of a file (such operations can often be the
+ * source of data corruption if applications aren't using file
+ * locking properly).
+ */
+enum nfs_stat_eventcounters {
+	NFSIOS_INODEREVALIDATE = 0,
+	NFSIOS_DENTRYREVALIDATE,
+	NFSIOS_DATAINVALIDATE,
+	NFSIOS_ATTRINVALIDATE,
+	NFSIOS_VFSOPEN,
+	NFSIOS_VFSLOOKUP,
+	NFSIOS_VFSACCESS,
+	NFSIOS_VFSUPDATEPAGE,
+	NFSIOS_VFSREADPAGE,
+	NFSIOS_VFSREADPAGES,
+	NFSIOS_VFSWRITEPAGE,
+	NFSIOS_VFSWRITEPAGES,
+	NFSIOS_VFSGETDENTS,
+	NFSIOS_VFSSETATTR,
+	NFSIOS_VFSFLUSH,
+	NFSIOS_VFSFSYNC,
+	NFSIOS_VFSLOCK,
+	NFSIOS_VFSRELEASE,
+	NFSIOS_CONGESTIONWAIT,
+	NFSIOS_SETATTRTRUNC,
+	NFSIOS_EXTENDWRITE,
+	NFSIOS_SILLYRENAME,
+	NFSIOS_SHORTREAD,
+	NFSIOS_SHORTWRITE,
+	NFSIOS_DELAY,
+	__NFSIOS_COUNTSMAX,
+};
+
+#endif	/* _LINUX_NFS_IOSTAT */

include/linux/nfs_page.h

@@ -27,9 +27,12 @@
 /*
  * Valid flags for a dirty buffer
  */
-#define PG_BUSY			0
-#define PG_NEED_COMMIT		1
-#define PG_NEED_RESCHED		2
+enum {
+	PG_BUSY = 0,
+	PG_CLEAN,
+	PG_NEED_COMMIT,
+	PG_NEED_RESCHED,
+};
 
 struct nfs_inode;
 struct nfs_page {

include/linux/nfs_xdr.h

@@ -829,9 +829,8 @@ struct nfs_rpc_ops {
 	int	(*write_done)  (struct rpc_task *, struct nfs_write_data *);
 	void	(*commit_setup) (struct nfs_write_data *, struct rpc_message *);
 	int	(*commit_done) (struct rpc_task *, struct nfs_write_data *);
-	int	(*file_open)   (struct inode *, struct file *);
-	int	(*file_release) (struct inode *, struct file *);
 	int	(*lock)(struct file *, int, struct file_lock *);
+	int	(*lock_check_bounds)(const struct file_lock *);
 	void	(*clear_acl_cache)(struct inode *);
 };
 

include/linux/sunrpc/clnt.h

@@ -42,7 +42,8 @@ struct rpc_clnt {
 
 	unsigned int		cl_softrtry : 1,/* soft timeouts */
 				cl_discrtry : 1,/* disconnect before retry */
-				cl_autobind : 1;/* use getport() */
+				cl_autobind : 1,/* use getport() */
+				cl_chatty   : 1;/* be verbose */
 
 	struct rpc_rtt *	cl_rtt;		/* RTO estimator data */
 	const struct rpc_timeout *cl_timeout;	/* Timeout strategy */
@@ -114,6 +115,7 @@ struct rpc_create_args {
 #define RPC_CLNT_CREATE_NONPRIVPORT	(1UL << 3)
 #define RPC_CLNT_CREATE_NOPING		(1UL << 4)
 #define RPC_CLNT_CREATE_DISCRTRY	(1UL << 5)
+#define RPC_CLNT_CREATE_QUIET		(1UL << 6)
 
 struct rpc_clnt *rpc_create(struct rpc_create_args *args);
 struct rpc_clnt	*rpc_bind_new_program(struct rpc_clnt *,
@@ -123,6 +125,9 @@ void		rpc_shutdown_client(struct rpc_clnt *);
 void		rpc_release_client(struct rpc_clnt *);
 
 int		rpcb_register(u32, u32, int, unsigned short, int *);
+int		rpcb_v4_register(const u32 program, const u32 version,
+				 const struct sockaddr *address,
+				 const char *netid, int *result);
 int		rpcb_getport_sync(struct sockaddr_in *, u32, u32, int);
 void		rpcb_getport_async(struct rpc_task *);
 

include/linux/sunrpc/sched.h

@@ -135,7 +135,6 @@ struct rpc_task_setup {
 #define RPC_IS_SWAPPER(t)	((t)->tk_flags & RPC_TASK_SWAPPER)
 #define RPC_DO_ROOTOVERRIDE(t)	((t)->tk_flags & RPC_TASK_ROOTCREDS)
 #define RPC_ASSASSINATED(t)	((t)->tk_flags & RPC_TASK_KILLED)
-#define RPC_DO_CALLBACK(t)	((t)->tk_callback != NULL)
 #define RPC_IS_SOFT(t)		((t)->tk_flags & RPC_TASK_SOFT)
 
 #define RPC_TASK_RUNNING	0

net/sunrpc/auth_gss/auth_gss.c

@@ -63,22 +63,11 @@ static const struct rpc_credops gss_nullops;
 # define RPCDBG_FACILITY	RPCDBG_AUTH
 #endif
 
-#define NFS_NGROUPS	16
-
-#define GSS_CRED_SLACK		1024		/* XXX: unused */
+#define GSS_CRED_SLACK		1024
 /* length of a krb5 verifier (48), plus data added before arguments when
  * using integrity (two 4-byte integers): */
 #define GSS_VERF_SLACK		100
 
-/* XXX this define must match the gssd define
-* as it is passed to gssd to signal the use of
-* machine creds should be part of the shared rpc interface */
-
-#define CA_RUN_AS_MACHINE  0x00000200
-
-/* dump the buffer in `emacs-hexl' style */
-#define isprint(c)      ((c > 0x1f) && (c < 0x7f))
-
 struct gss_auth {
 	struct kref kref;
 	struct rpc_auth rpc_auth;
@@ -146,7 +135,7 @@ simple_get_netobj(const void *p, const void *end, struct xdr_netobj *dest)
 	q = (const void *)((const char *)p + len);
 	if (unlikely(q > end || q < p))
 		return ERR_PTR(-EFAULT);
-	dest->data = kmemdup(p, len, GFP_KERNEL);
+	dest->data = kmemdup(p, len, GFP_NOFS);
 	if (unlikely(dest->data == NULL))
 		return ERR_PTR(-ENOMEM);
 	dest->len = len;
@@ -171,7 +160,7 @@ gss_alloc_context(void)
 {
 	struct gss_cl_ctx *ctx;
 
-	ctx = kzalloc(sizeof(*ctx), GFP_KERNEL);
+	ctx = kzalloc(sizeof(*ctx), GFP_NOFS);
 	if (ctx != NULL) {
 		ctx->gc_proc = RPC_GSS_PROC_DATA;
 		ctx->gc_seq = 1;	/* NetApp 6.4R1 doesn't accept seq. no. 0 */
@@ -272,7 +261,7 @@ __gss_find_upcall(struct rpc_inode *rpci, uid_t uid)
 	return NULL;
 }
 
-/* Try to add a upcall to the pipefs queue.
+/* Try to add an upcall to the pipefs queue.
  * If an upcall owned by our uid already exists, then we return a reference
  * to that upcall instead of adding the new upcall.
  */
@@ -341,7 +330,7 @@ gss_alloc_msg(struct gss_auth *gss_auth, uid_t uid)
 {
 	struct gss_upcall_msg *gss_msg;
 
-	gss_msg = kzalloc(sizeof(*gss_msg), GFP_KERNEL);
+	gss_msg = kzalloc(sizeof(*gss_msg), GFP_NOFS);
 	if (gss_msg != NULL) {
 		INIT_LIST_HEAD(&gss_msg->list);
 		rpc_init_wait_queue(&gss_msg->rpc_waitqueue, "RPCSEC_GSS upcall waitq");
@@ -493,7 +482,6 @@ gss_pipe_downcall(struct file *filp, const char __user *src, size_t mlen)
 {
 	const void *p, *end;
 	void *buf;
-	struct rpc_clnt *clnt;
 	struct gss_upcall_msg *gss_msg;
 	struct inode *inode = filp->f_path.dentry->d_inode;
 	struct gss_cl_ctx *ctx;
@@ -503,11 +491,10 @@ gss_pipe_downcall(struct file *filp, const char __user *src, size_t mlen)
 	if (mlen > MSG_BUF_MAXSIZE)
 		goto out;
 	err = -ENOMEM;
-	buf = kmalloc(mlen, GFP_KERNEL);
+	buf = kmalloc(mlen, GFP_NOFS);
 	if (!buf)
 		goto out;
 
-	clnt = RPC_I(inode)->private;
 	err = -EFAULT;
 	if (copy_from_user(buf, src, mlen))
 		goto err;
@@ -806,7 +793,7 @@ gss_create_cred(struct rpc_auth *auth, struct auth_cred *acred, int flags)
 	dprintk("RPC:       gss_create_cred for uid %d, flavor %d\n",
 		acred->uid, auth->au_flavor);
 
-	if (!(cred = kzalloc(sizeof(*cred), GFP_KERNEL)))
+	if (!(cred = kzalloc(sizeof(*cred), GFP_NOFS)))
 		goto out_err;
 
 	rpcauth_init_cred(&cred->gc_base, acred, auth, &gss_credops);

net/sunrpc/auth_gss/gss_krb5_mech.c

@@ -70,7 +70,7 @@ simple_get_netobj(const void *p, const void *end, struct xdr_netobj *res)
 	q = (const void *)((const char *)p + len);
 	if (unlikely(q > end || q < p))
 		return ERR_PTR(-EFAULT);
-	res->data = kmemdup(p, len, GFP_KERNEL);
+	res->data = kmemdup(p, len, GFP_NOFS);
 	if (unlikely(res->data == NULL))
 		return ERR_PTR(-ENOMEM);
 	res->len = len;
@@ -131,7 +131,7 @@ gss_import_sec_context_kerberos(const void *p,
 	struct	krb5_ctx *ctx;
 	int tmp;
 
-	if (!(ctx = kzalloc(sizeof(*ctx), GFP_KERNEL)))
+	if (!(ctx = kzalloc(sizeof(*ctx), GFP_NOFS)))
 		goto out_err;
 
 	p = simple_get_bytes(p, end, &ctx->initiate, sizeof(ctx->initiate));

net/sunrpc/auth_gss/gss_spkm3_mech.c

@@ -76,7 +76,7 @@ simple_get_netobj(const void *p, const void *end, struct xdr_netobj *res)
 	q = (const void *)((const char *)p + len);
 	if (unlikely(q > end || q < p))
 		return ERR_PTR(-EFAULT);
-	res->data = kmemdup(p, len, GFP_KERNEL);
+	res->data = kmemdup(p, len, GFP_NOFS);
 	if (unlikely(res->data == NULL))
 		return ERR_PTR(-ENOMEM);
 	return q;
@@ -90,7 +90,7 @@ gss_import_sec_context_spkm3(const void *p, size_t len,
 	struct	spkm3_ctx *ctx;
 	int	version;
 
-	if (!(ctx = kzalloc(sizeof(*ctx), GFP_KERNEL)))
+	if (!(ctx = kzalloc(sizeof(*ctx), GFP_NOFS)))
 		goto out_err;
 
 	p = simple_get_bytes(p, end, &version, sizeof(version));

net/sunrpc/auth_gss/gss_spkm3_token.c

@@ -90,7 +90,7 @@ asn1_bitstring_len(struct xdr_netobj *in, int *enclen, int *zerobits)
 int
 decode_asn1_bitstring(struct xdr_netobj *out, char *in, int enclen, int explen)
 {
-	if (!(out->data = kzalloc(explen,GFP_KERNEL)))
+	if (!(out->data = kzalloc(explen,GFP_NOFS)))
 		return 0;
 	out->len = explen;
 	memcpy(out->data, in, enclen);

net/sunrpc/auth_unix.c

@@ -66,7 +66,7 @@ unx_create_cred(struct rpc_auth *auth, struct auth_cred *acred, int flags)
 	dprintk("RPC:       allocating UNIX cred for uid %d gid %d\n",
 			acred->uid, acred->gid);
 
-	if (!(cred = kmalloc(sizeof(*cred), GFP_KERNEL)))
+	if (!(cred = kmalloc(sizeof(*cred), GFP_NOFS)))
 		return ERR_PTR(-ENOMEM);
 
 	rpcauth_init_cred(&cred->uc_base, acred, auth, &unix_credops);

net/sunrpc/clnt.c

@@ -25,6 +25,7 @@
 
 #include <linux/module.h>
 #include <linux/types.h>
+#include <linux/kallsyms.h>
 #include <linux/mm.h>
 #include <linux/slab.h>
 #include <linux/smp_lock.h>
@@ -58,7 +59,6 @@ static void	call_start(struct rpc_task *task);
 static void	call_reserve(struct rpc_task *task);
 static void	call_reserveresult(struct rpc_task *task);
 static void	call_allocate(struct rpc_task *task);
-static void	call_encode(struct rpc_task *task);
 static void	call_decode(struct rpc_task *task);
 static void	call_bind(struct rpc_task *task);
 static void	call_bind_status(struct rpc_task *task);
@@ -70,9 +70,9 @@ static void	call_refreshresult(struct rpc_task *task);
 static void	call_timeout(struct rpc_task *task);
 static void	call_connect(struct rpc_task *task);
 static void	call_connect_status(struct rpc_task *task);
-static __be32 *	call_header(struct rpc_task *task);
-static __be32 *	call_verify(struct rpc_task *task);
 
+static __be32	*rpc_encode_header(struct rpc_task *task);
+static __be32	*rpc_verify_header(struct rpc_task *task);
 static int	rpc_ping(struct rpc_clnt *clnt, int flags);
 
 static void rpc_register_client(struct rpc_clnt *clnt)
@@ -324,6 +324,8 @@ struct rpc_clnt *rpc_create(struct rpc_create_args *args)
 		clnt->cl_autobind = 1;
 	if (args->flags & RPC_CLNT_CREATE_DISCRTRY)
 		clnt->cl_discrtry = 1;
+	if (!(args->flags & RPC_CLNT_CREATE_QUIET))
+		clnt->cl_chatty = 1;
 
 	return clnt;
 }
@@ -690,6 +692,21 @@ rpc_restart_call(struct rpc_task *task)
 }
 EXPORT_SYMBOL_GPL(rpc_restart_call);
 
+#ifdef RPC_DEBUG
+static const char *rpc_proc_name(const struct rpc_task *task)
+{
+	const struct rpc_procinfo *proc = task->tk_msg.rpc_proc;
+
+	if (proc) {
+		if (proc->p_name)
+			return proc->p_name;
+		else
+			return "NULL";
+	} else
+		return "no proc";
+}
+#endif
+
 /*
  * 0.  Initial state
  *
@@ -701,9 +718,9 @@ call_start(struct rpc_task *task)
 {
 	struct rpc_clnt	*clnt = task->tk_client;
 
-	dprintk("RPC: %5u call_start %s%d proc %d (%s)\n", task->tk_pid,
+	dprintk("RPC: %5u call_start %s%d proc %s (%s)\n", task->tk_pid,
 			clnt->cl_protname, clnt->cl_vers,
-			task->tk_msg.rpc_proc->p_proc,
+			rpc_proc_name(task),
 			(RPC_IS_ASYNC(task) ? "async" : "sync"));
 
 	/* Increment call count */
@@ -861,7 +878,7 @@ rpc_xdr_buf_init(struct xdr_buf *buf, void *start, size_t len)
  * 3.	Encode arguments of an RPC call
  */
 static void
-call_encode(struct rpc_task *task)
+rpc_xdr_encode(struct rpc_task *task)
 {
 	struct rpc_rqst	*req = task->tk_rqstp;
 	kxdrproc_t	encode;
@@ -876,23 +893,19 @@ call_encode(struct rpc_task *task)
 			 (char *)req->rq_buffer + req->rq_callsize,
 			 req->rq_rcvsize);
 
-	/* Encode header and provided arguments */
-	encode = task->tk_msg.rpc_proc->p_encode;
-	if (!(p = call_header(task))) {
-		printk(KERN_INFO "RPC: call_header failed, exit EIO\n");
+	p = rpc_encode_header(task);
+	if (p == NULL) {
+		printk(KERN_INFO "RPC: couldn't encode RPC header, exit EIO\n");
 		rpc_exit(task, -EIO);
 		return;
 	}
+
+	encode = task->tk_msg.rpc_proc->p_encode;
 	if (encode == NULL)
 		return;
 
 	task->tk_status = rpcauth_wrap_req(task, encode, req, p,
 			task->tk_msg.rpc_argp);
-	if (task->tk_status == -ENOMEM) {
-		/* XXX: Is this sane? */
-		rpc_delay(task, 3*HZ);
-		task->tk_status = -EAGAIN;
-	}
 }
 
 /*
@@ -929,11 +942,9 @@ call_bind_status(struct rpc_task *task)
 	}
 
 	switch (task->tk_status) {
-	case -EAGAIN:
-		dprintk("RPC: %5u rpcbind waiting for another request "
-				"to finish\n", task->tk_pid);
-		/* avoid busy-waiting here -- could be a network outage. */
-		rpc_delay(task, 5*HZ);
+	case -ENOMEM:
+		dprintk("RPC: %5u rpcbind out of memory\n", task->tk_pid);
+		rpc_delay(task, HZ >> 2);
 		goto retry_timeout;
 	case -EACCES:
 		dprintk("RPC: %5u remote rpcbind: RPC program/version "
@@ -1046,10 +1057,16 @@ call_transmit(struct rpc_task *task)
 	/* Encode here so that rpcsec_gss can use correct sequence number. */
 	if (rpc_task_need_encode(task)) {
 		BUG_ON(task->tk_rqstp->rq_bytes_sent != 0);
-		call_encode(task);
+		rpc_xdr_encode(task);
 		/* Did the encode result in an error condition? */
-		if (task->tk_status != 0)
+		if (task->tk_status != 0) {
+			/* Was the error nonfatal? */
+			if (task->tk_status == -EAGAIN)
+				rpc_delay(task, HZ >> 4);
+			else
+				rpc_exit(task, task->tk_status);
 			return;
+		}
 	}
 	xprt_transmit(task);
 	if (task->tk_status < 0)
@@ -1132,7 +1149,8 @@ call_status(struct rpc_task *task)
 		rpc_exit(task, status);
 		break;
 	default:
-		printk("%s: RPC call returned error %d\n",
+		if (clnt->cl_chatty)
+			printk("%s: RPC call returned error %d\n",
 			       clnt->cl_protname, -status);
 		rpc_exit(task, status);
 	}
@@ -1157,7 +1175,8 @@ call_timeout(struct rpc_task *task)
 	task->tk_timeouts++;
 
 	if (RPC_IS_SOFT(task)) {
-		printk(KERN_NOTICE "%s: server %s not responding, timed out\n",
+		if (clnt->cl_chatty)
+			printk(KERN_NOTICE "%s: server %s not responding, timed out\n",
 				clnt->cl_protname, clnt->cl_server);
 		rpc_exit(task, -EIO);
 		return;
@@ -1165,7 +1184,8 @@ call_timeout(struct rpc_task *task)
 
 	if (!(task->tk_flags & RPC_CALL_MAJORSEEN)) {
 		task->tk_flags |= RPC_CALL_MAJORSEEN;
-		printk(KERN_NOTICE "%s: server %s not responding, still trying\n",
+		if (clnt->cl_chatty)
+			printk(KERN_NOTICE "%s: server %s not responding, still trying\n",
 			clnt->cl_protname, clnt->cl_server);
 	}
 	rpc_force_rebind(clnt);
@@ -1196,8 +1216,9 @@ call_decode(struct rpc_task *task)
 			task->tk_pid, task->tk_status);
 
 	if (task->tk_flags & RPC_CALL_MAJORSEEN) {
-		printk(KERN_NOTICE "%s: server %s OK\n",
-			clnt->cl_protname, clnt->cl_server);
+		if (clnt->cl_chatty)
+			printk(KERN_NOTICE "%s: server %s OK\n",
+				clnt->cl_protname, clnt->cl_server);
 		task->tk_flags &= ~RPC_CALL_MAJORSEEN;
 	}
 
@@ -1224,8 +1245,7 @@ call_decode(struct rpc_task *task)
 		goto out_retry;
 	}
 
-	/* Verify the RPC header */
-	p = call_verify(task);
+	p = rpc_verify_header(task);
 	if (IS_ERR(p)) {
 		if (p == ERR_PTR(-EAGAIN))
 			goto out_retry;
@@ -1243,7 +1263,7 @@ call_decode(struct rpc_task *task)
 	return;
 out_retry:
 	task->tk_status = 0;
-	/* Note: call_verify() may have freed the RPC slot */
+	/* Note: rpc_verify_header() may have freed the RPC slot */
 	if (task->tk_rqstp == req) {
 		req->rq_received = req->rq_rcv_buf.len = 0;
 		if (task->tk_client->cl_discrtry)
@@ -1290,11 +1310,8 @@ call_refreshresult(struct rpc_task *task)
 	return;
 }
 
-/*
- * Call header serialization
- */
 static __be32 *
-call_header(struct rpc_task *task)
+rpc_encode_header(struct rpc_task *task)
 {
 	struct rpc_clnt *clnt = task->tk_client;
 	struct rpc_rqst	*req = task->tk_rqstp;
@@ -1314,11 +1331,8 @@ call_header(struct rpc_task *task)
 	return p;
 }
 
-/*
- * Reply header verification
- */
 static __be32 *
-call_verify(struct rpc_task *task)
+rpc_verify_header(struct rpc_task *task)
 {
 	struct kvec *iov = &task->tk_rqstp->rq_rcv_buf.head[0];
 	int len = task->tk_rqstp->rq_rcv_buf.len >> 2;
@@ -1392,7 +1406,7 @@ call_verify(struct rpc_task *task)
 			task->tk_action = call_bind;
 			goto out_retry;
 		case RPC_AUTH_TOOWEAK:
-			printk(KERN_NOTICE "call_verify: server %s requires stronger "
+			printk(KERN_NOTICE "RPC: server %s requires stronger "
 			       "authentication.\n", task->tk_client->cl_server);
 			break;
 		default:
@@ -1431,10 +1445,10 @@ call_verify(struct rpc_task *task)
 		error = -EPROTONOSUPPORT;
 		goto out_err;
 	case RPC_PROC_UNAVAIL:
-		dprintk("RPC: %5u %s: proc %p unsupported by program %u, "
+		dprintk("RPC: %5u %s: proc %s unsupported by program %u, "
 				"version %u on server %s\n",
 				task->tk_pid, __func__,
-				task->tk_msg.rpc_proc,
+				rpc_proc_name(task),
 				task->tk_client->cl_prog,
 				task->tk_client->cl_vers,
 				task->tk_client->cl_server);
@@ -1517,44 +1531,53 @@ struct rpc_task *rpc_call_null(struct rpc_clnt *clnt, struct rpc_cred *cred, int
 EXPORT_SYMBOL_GPL(rpc_call_null);
 
 #ifdef RPC_DEBUG
+static void rpc_show_header(void)
+{
+	printk(KERN_INFO "-pid- flgs status -client- --rqstp- "
+		"-timeout ---ops--\n");
+}
+
+static void rpc_show_task(const struct rpc_clnt *clnt,
+			  const struct rpc_task *task)
+{
+	const char *rpc_waitq = "none";
+	char *p, action[KSYM_SYMBOL_LEN];
+
+	if (RPC_IS_QUEUED(task))
+		rpc_waitq = rpc_qname(task->tk_waitqueue);
+
+	/* map tk_action pointer to a function name; then trim off
+	 * the "+0x0 [sunrpc]" */
+	sprint_symbol(action, (unsigned long)task->tk_action);
+	p = strchr(action, '+');
+	if (p)
+		*p = '\0';
+
+	printk(KERN_INFO "%5u %04x %6d %8p %8p %8ld %8p %sv%u %s a:%s q:%s\n",
+		task->tk_pid, task->tk_flags, task->tk_status,
+		clnt, task->tk_rqstp, task->tk_timeout, task->tk_ops,
+		clnt->cl_protname, clnt->cl_vers, rpc_proc_name(task),
+		action, rpc_waitq);
+}
+
 void rpc_show_tasks(void)
 {
 	struct rpc_clnt *clnt;
-	struct rpc_task *t;
+	struct rpc_task *task;
+	int header = 0;
 
 	spin_lock(&rpc_client_lock);
-	if (list_empty(&all_clients))
-		goto out;
-	printk("-pid- proc flgs status -client- -prog- --rqstp- -timeout "
-		"-rpcwait -action- ---ops--\n");
 	list_for_each_entry(clnt, &all_clients, cl_clients) {
-		if (list_empty(&clnt->cl_tasks))
-			continue;
 		spin_lock(&clnt->cl_lock);
-		list_for_each_entry(t, &clnt->cl_tasks, tk_task) {
-			const char *rpc_waitq = "none";
-			int proc;
-
-			if (t->tk_msg.rpc_proc)
-				proc = t->tk_msg.rpc_proc->p_proc;
-			else
-				proc = -1;
-
-			if (RPC_IS_QUEUED(t))
-				rpc_waitq = rpc_qname(t->tk_waitqueue);
-
-			printk("%5u %04d %04x %6d %8p %6d %8p %8ld %8s %8p %8p\n",
-				t->tk_pid, proc,
-				t->tk_flags, t->tk_status,
-				t->tk_client,
-				(t->tk_client ? t->tk_client->cl_prog : 0),
-				t->tk_rqstp, t->tk_timeout,
-				rpc_waitq,
-				t->tk_action, t->tk_ops);
+		list_for_each_entry(task, &clnt->cl_tasks, tk_task) {
+			if (!header) {
+				rpc_show_header();
+				header++;
+			}
+			rpc_show_task(clnt, task);
 		}
 		spin_unlock(&clnt->cl_lock);
 	}
-out:
 	spin_unlock(&rpc_client_lock);
 }
 #endif

net/sunrpc/rpcb_clnt.c

@@ -32,6 +32,10 @@
 #define RPCBIND_PROGRAM		(100000u)
 #define RPCBIND_PORT		(111u)
 
+#define RPCBVERS_2		(2u)
+#define RPCBVERS_3		(3u)
+#define RPCBVERS_4		(4u)
+
 enum {
 	RPCBPROC_NULL,
 	RPCBPROC_SET,
@@ -64,6 +68,7 @@ enum {
 #define RPCB_MAXOWNERLEN	sizeof(RPCB_OWNER_STRING)
 
 static void			rpcb_getport_done(struct rpc_task *, void *);
+static void			rpcb_map_release(void *data);
 static struct rpc_program	rpcb_program;
 
 struct rpcbind_args {
@@ -76,41 +81,73 @@ struct rpcbind_args {
 	const char *		r_netid;
 	const char *		r_addr;
 	const char *		r_owner;
+
+	int			r_status;
 };
 
 static struct rpc_procinfo rpcb_procedures2[];
 static struct rpc_procinfo rpcb_procedures3[];
+static struct rpc_procinfo rpcb_procedures4[];
 
 struct rpcb_info {
-	int			rpc_vers;
+	u32			rpc_vers;
 	struct rpc_procinfo *	rpc_proc;
 };
 
 static struct rpcb_info rpcb_next_version[];
 static struct rpcb_info rpcb_next_version6[];
 
+static const struct rpc_call_ops rpcb_getport_ops = {
+	.rpc_call_done		= rpcb_getport_done,
+	.rpc_release		= rpcb_map_release,
+};
+
+static void rpcb_wake_rpcbind_waiters(struct rpc_xprt *xprt, int status)
+{
+	xprt_clear_binding(xprt);
+	rpc_wake_up_status(&xprt->binding, status);
+}
+
 static void rpcb_map_release(void *data)
 {
 	struct rpcbind_args *map = data;
 
+	rpcb_wake_rpcbind_waiters(map->r_xprt, map->r_status);
 	xprt_put(map->r_xprt);
 	kfree(map);
 }
 
-static const struct rpc_call_ops rpcb_getport_ops = {
-	.rpc_call_done		= rpcb_getport_done,
-	.rpc_release		= rpcb_map_release,
+static const struct sockaddr_in rpcb_inaddr_loopback = {
+	.sin_family		= AF_INET,
+	.sin_addr.s_addr	= htonl(INADDR_LOOPBACK),
+	.sin_port		= htons(RPCBIND_PORT),
 };
 
-static void rpcb_wake_rpcbind_waiters(struct rpc_xprt *xprt, int status)
+static const struct sockaddr_in6 rpcb_in6addr_loopback = {
+	.sin6_family		= AF_INET6,
+	.sin6_addr		= IN6ADDR_LOOPBACK_INIT,
+	.sin6_port		= htons(RPCBIND_PORT),
+};
+
+static struct rpc_clnt *rpcb_create_local(struct sockaddr *addr,
+					  size_t addrlen, u32 version)
 {
-	xprt_clear_binding(xprt);
-	rpc_wake_up_status(&xprt->binding, status);
+	struct rpc_create_args args = {
+		.protocol	= XPRT_TRANSPORT_UDP,
+		.address	= addr,
+		.addrsize	= addrlen,
+		.servername	= "localhost",
+		.program	= &rpcb_program,
+		.version	= version,
+		.authflavor	= RPC_AUTH_UNIX,
+		.flags		= RPC_CLNT_CREATE_NOPING,
+	};
+
+	return rpc_create(&args);
 }
 
 static struct rpc_clnt *rpcb_create(char *hostname, struct sockaddr *srvaddr,
-				    size_t salen, int proto, u32 version,
-				    int privileged)
+				    size_t salen, int proto, u32 version)
 {
 	struct rpc_create_args args = {
 		.protocol	= proto,
@@ -120,7 +157,8 @@ static struct rpc_clnt *rpcb_create(char *hostname, struct sockaddr *srvaddr,
 		.program	= &rpcb_program,
 		.version	= version,
 		.authflavor	= RPC_AUTH_UNIX,
-		.flags		= RPC_CLNT_CREATE_NOPING,
+		.flags		= (RPC_CLNT_CREATE_NOPING |
+					RPC_CLNT_CREATE_NONPRIVPORT),
 	};
 
 	switch (srvaddr->sa_family) {
@@ -134,29 +172,72 @@ static struct rpc_clnt *rpcb_create(char *hostname, struct sockaddr *srvaddr,
 		return NULL;
 	}
 
-	if (!privileged)
-		args.flags |= RPC_CLNT_CREATE_NONPRIVPORT;
 	return rpc_create(&args);
 }
 
+static int rpcb_register_call(struct sockaddr *addr, size_t addrlen,
+			      u32 version, struct rpc_message *msg,
+			      int *result)
+{
+	struct rpc_clnt *rpcb_clnt;
+	int error = 0;
+
+	*result = 0;
+
+	rpcb_clnt = rpcb_create_local(addr, addrlen, version);
+	if (!IS_ERR(rpcb_clnt)) {
+		error = rpc_call_sync(rpcb_clnt, msg, 0);
+		rpc_shutdown_client(rpcb_clnt);
+	} else
+		error = PTR_ERR(rpcb_clnt);
+
+	if (error < 0)
+		printk(KERN_WARNING "RPC: failed to contact local rpcbind "
+				"server (errno %d).\n", -error);
+	dprintk("RPC:       registration status %d/%d\n", error, *result);
+
+	return error;
+}
+
 /**
  * rpcb_register - set or unset a port registration with the local rpcbind svc
  * @prog: RPC program number to bind
  * @vers: RPC version number to bind
- * @prot: transport protocol to use to make this request
+ * @prot: transport protocol to register
  * @port: port value to register
- * @okay: result code
+ * @okay: OUT: result code
+ *
+ * RPC services invoke this function to advertise their contact
+ * information via the system's rpcbind daemon.  RPC services
+ * invoke this function once for each [program, version, transport]
+ * tuple they wish to advertise.
+ *
+ * Callers may also unregister RPC services that are no longer
+ * available by setting the passed-in port to zero.  This removes
+ * all registered transports for [program, version] from the local
+ * rpcbind database.
+ *
+ * Returns zero if the registration request was dispatched
+ * successfully and a reply was received.  The rpcbind daemon's
+ * boolean result code is stored in *okay.
+ *
+ * Returns an errno value and sets *result to zero if there was
+ * some problem that prevented the rpcbind request from being
+ * dispatched, or if the rpcbind daemon did not respond within
+ * the timeout.
  *
- * port == 0 means unregister, port != 0 means register.
+ * This function uses rpcbind protocol version 2 to contact the
+ * local rpcbind daemon.
  *
- * This routine supports only rpcbind version 2.
+ * Registration works over both AF_INET and AF_INET6, and services
+ * registered via this function are advertised as available for any
+ * address.  If the local rpcbind daemon is listening on AF_INET6,
+ * services registered via this function will be advertised on
+ * IN6ADDR_ANY (ie available for all AF_INET and AF_INET6
+ * addresses).
  */
 int rpcb_register(u32 prog, u32 vers, int prot, unsigned short port, int *okay)
 {
-	struct sockaddr_in sin = {
-		.sin_family		= AF_INET,
-		.sin_addr.s_addr	= htonl(INADDR_LOOPBACK),
-	};
 	struct rpcbind_args map = {
 		.r_prog		= prog,
 		.r_vers		= vers,
@@ -164,32 +245,159 @@ int rpcb_register(u32 prog, u32 vers, int prot, unsigned short port, int *okay)
 		.r_port		= port,
 	};
 	struct rpc_message msg = {
-		.rpc_proc	= &rpcb_procedures2[port ?
-					RPCBPROC_SET : RPCBPROC_UNSET],
 		.rpc_argp	= &map,
 		.rpc_resp	= okay,
 	};
-	struct rpc_clnt *rpcb_clnt;
-	int error = 0;
 
 	dprintk("RPC:       %sregistering (%u, %u, %d, %u) with local "
 			"rpcbind\n", (port ? "" : "un"),
 			prog, vers, prot, port);
 
-	rpcb_clnt = rpcb_create("localhost", (struct sockaddr *) &sin,
-				sizeof(sin), XPRT_TRANSPORT_UDP, 2, 1);
-	if (IS_ERR(rpcb_clnt))
-		return PTR_ERR(rpcb_clnt);
+	msg.rpc_proc = &rpcb_procedures2[RPCBPROC_UNSET];
+	if (port)
+		msg.rpc_proc = &rpcb_procedures2[RPCBPROC_SET];
 
-	error = rpc_call_sync(rpcb_clnt, &msg, 0);
+	return rpcb_register_call((struct sockaddr *)&rpcb_inaddr_loopback,
+					sizeof(rpcb_inaddr_loopback),
+					RPCBVERS_2, &msg, okay);
+}
 
-	rpc_shutdown_client(rpcb_clnt);
-	if (error < 0)
-		printk(KERN_WARNING "RPC: failed to contact local rpcbind "
-				"server (errno %d).\n", -error);
-	dprintk("RPC:       registration status %d/%d\n", error, *okay);
+/*
+ * Fill in AF_INET family-specific arguments to register
+ */
+static int rpcb_register_netid4(struct sockaddr_in *address_to_register,
+				struct rpc_message *msg)
+{
+	struct rpcbind_args *map = msg->rpc_argp;
+	unsigned short port = ntohs(address_to_register->sin_port);
+	char buf[32];
+
+	/* Construct AF_INET universal address */
+	snprintf(buf, sizeof(buf),
+			NIPQUAD_FMT".%u.%u",
+			NIPQUAD(address_to_register->sin_addr.s_addr),
+			port >> 8, port & 0xff);
+	map->r_addr = buf;
+
+	dprintk("RPC:       %sregistering [%u, %u, %s, '%s'] with "
+		"local rpcbind\n", (port ? "" : "un"),
+			map->r_prog, map->r_vers,
+			map->r_addr, map->r_netid);
+
+	msg->rpc_proc = &rpcb_procedures4[RPCBPROC_UNSET];
+	if (port)
+		msg->rpc_proc = &rpcb_procedures4[RPCBPROC_SET];
+
+	return rpcb_register_call((struct sockaddr *)&rpcb_inaddr_loopback,
+					sizeof(rpcb_inaddr_loopback),
+					RPCBVERS_4, msg, msg->rpc_resp);
+}
 
-	return error;
+/*
+ * Fill in AF_INET6 family-specific arguments to register
+ */
+static int rpcb_register_netid6(struct sockaddr_in6 *address_to_register,
+				struct rpc_message *msg)
+{
+	struct rpcbind_args *map = msg->rpc_argp;
+	unsigned short port = ntohs(address_to_register->sin6_port);
+	char buf[64];
+
+	/* Construct AF_INET6 universal address */
+	snprintf(buf, sizeof(buf),
+			NIP6_FMT".%u.%u",
+			NIP6(address_to_register->sin6_addr),
+			port >> 8, port & 0xff);
+	map->r_addr = buf;
+
+	dprintk("RPC:       %sregistering [%u, %u, %s, '%s'] with "
+		"local rpcbind\n", (port ? "" : "un"),
+			map->r_prog, map->r_vers,
+			map->r_addr, map->r_netid);
+
+	msg->rpc_proc = &rpcb_procedures4[RPCBPROC_UNSET];
+	if (port)
+		msg->rpc_proc = &rpcb_procedures4[RPCBPROC_SET];
+
+	return rpcb_register_call((struct sockaddr *)&rpcb_in6addr_loopback,
+					sizeof(rpcb_in6addr_loopback),
+					RPCBVERS_4, msg, msg->rpc_resp);
+}
+
+/**
+ * rpcb_v4_register - set or unset a port registration with the local rpcbind
+ * @program: RPC program number of service to (un)register
+ * @version: RPC version number of service to (un)register
+ * @address: address family, IP address, and port to (un)register
+ * @netid: netid of transport protocol to (un)register
+ * @result: result code from rpcbind RPC call
+ *
+ * RPC services invoke this function to advertise their contact
+ * information via the system's rpcbind daemon.  RPC services
+ * invoke this function once for each [program, version, address,
+ * netid] tuple they wish to advertise.
+ *
+ * Callers may also unregister RPC services that are no longer
+ * available by setting the port number in the passed-in address
+ * to zero.  Callers pass a netid of "" to unregister all
+ * transport netids associated with [program, version, address].
+ *
+ * Returns zero if the registration request was dispatched
+ * successfully and a reply was received.  The rpcbind daemon's
+ * result code is stored in *result.
+ *
+ * Returns an errno value and sets *result to zero if there was
+ * some problem that prevented the rpcbind request from being
+ * dispatched, or if the rpcbind daemon did not respond within
+ * the timeout.
+ *
+ * This function uses rpcbind protocol version 4 to contact the
+ * local rpcbind daemon.  The local rpcbind daemon must support
+ * version 4 of the rpcbind protocol in order for these functions
+ * to register a service successfully.
+ *
+ * Supported netids include "udp" and "tcp" for UDP and TCP over
+ * IPv4, and "udp6" and "tcp6" for UDP and TCP over IPv6,
+ * respectively.
+ *
+ * The contents of @address determine the address family and the
+ * port to be registered.  The usual practice is to pass INADDR_ANY
+ * as the raw address, but specifying a non-zero address is also
+ * supported by this API if the caller wishes to advertise an RPC
+ * service on a specific network interface.
+ *
+ * Note that passing in INADDR_ANY does not create the same service
+ * registration as IN6ADDR_ANY.  The former advertises an RPC
+ * service on any IPv4 address, but not on IPv6.  The latter
+ * advertises the service on all IPv4 and IPv6 addresses.
+ */
+int rpcb_v4_register(const u32 program, const u32 version,
+		     const struct sockaddr *address, const char *netid,
+		     int *result)
+{
+	struct rpcbind_args map = {
+		.r_prog		= program,
+		.r_vers		= version,
+		.r_netid	= netid,
+		.r_owner	= RPCB_OWNER_STRING,
+	};
+	struct rpc_message msg = {
+		.rpc_argp	= &map,
+		.rpc_resp	= result,
+	};
+
+	*result = 0;
+
+	switch (address->sa_family) {
+	case AF_INET:
+		return rpcb_register_netid4((struct sockaddr_in *)address,
+					    &msg);
+	case AF_INET6:
+		return rpcb_register_netid6((struct sockaddr_in6 *)address,
+					    &msg);
+	}
+
+	return -EAFNOSUPPORT;
 }
 
 /**
@@ -227,7 +435,7 @@ int rpcb_getport_sync(struct sockaddr_in *sin, u32 prog, u32 vers, int prot)
 		__func__, NIPQUAD(sin->sin_addr.s_addr), prog, vers, prot);
 
 	rpcb_clnt = rpcb_create(NULL, (struct sockaddr *)sin,
-				sizeof(*sin), prot, 2, 0);
+				sizeof(*sin), prot, RPCBVERS_2);
 	if (IS_ERR(rpcb_clnt))
 		return PTR_ERR(rpcb_clnt);
 
@@ -289,17 +497,16 @@ void rpcb_getport_async(struct rpc_task *task)
 	/* Autobind on cloned rpc clients is discouraged */
 	BUG_ON(clnt->cl_parent != clnt);
 
+	/* Put self on the wait queue to ensure we get notified if
+	 * some other task is already attempting to bind the port */
+	rpc_sleep_on(&xprt->binding, task, NULL);
+
 	if (xprt_test_and_set_binding(xprt)) {
-		status = -EAGAIN;	/* tell caller to check again */
 		dprintk("RPC: %5u %s: waiting for another binder\n",
 			task->tk_pid, __func__);
-		goto bailout_nowake;
+		return;
 	}
 
-	/* Put self on queue before sending rpcbind request, in case
-	 * rpcb_getport_done completes before we return from rpc_run_task */
-	rpc_sleep_on(&xprt->binding, task, NULL);
-
 	/* Someone else may have bound if we slept */
 	if (xprt_bound(xprt)) {
 		status = 0;
@@ -338,7 +545,7 @@ void rpcb_getport_async(struct rpc_task *task)
 		task->tk_pid, __func__, bind_version);
 
 	rpcb_clnt = rpcb_create(clnt->cl_server, sap, salen, xprt->prot,
-				bind_version, 0);
+				bind_version);
 	if (IS_ERR(rpcb_clnt)) {
 		status = PTR_ERR(rpcb_clnt);
 		dprintk("RPC: %5u %s: rpcb_create failed, error %ld\n",
@@ -361,15 +568,15 @@ void rpcb_getport_async(struct rpc_task *task)
 	map->r_netid = rpc_peeraddr2str(clnt, RPC_DISPLAY_NETID);
 	map->r_addr = rpc_peeraddr2str(rpcb_clnt, RPC_DISPLAY_UNIVERSAL_ADDR);
 	map->r_owner = RPCB_OWNER_STRING;	/* ignored for GETADDR */
+	map->r_status = -EIO;
 
 	child = rpcb_call_async(rpcb_clnt, map, proc);
 	rpc_release_client(rpcb_clnt);
 	if (IS_ERR(child)) {
-		status = -EIO;
 		/* rpcb_map_release() has freed the arguments */
 		dprintk("RPC: %5u %s: rpc_run_task failed\n",
 			task->tk_pid, __func__);
-		goto bailout_nofree;
+		return;
 	}
 	rpc_put_task(child);
 
@@ -378,7 +585,6 @@ void rpcb_getport_async(struct rpc_task *task)
 
 bailout_nofree:
 	rpcb_wake_rpcbind_waiters(xprt, status);
-bailout_nowake:
 	task->tk_status = status;
 }
 EXPORT_SYMBOL_GPL(rpcb_getport_async);
@@ -417,9 +623,13 @@ static void rpcb_getport_done(struct rpc_task *child, void *data)
 	dprintk("RPC: %5u rpcb_getport_done(status %d, port %u)\n",
 			child->tk_pid, status, map->r_port);
 
-	rpcb_wake_rpcbind_waiters(xprt, status);
+	map->r_status = status;
 }
 
+/*
+ * XDR functions for rpcbind
+ */
+
 static int rpcb_encode_mapping(struct rpc_rqst *req, __be32 *p,
 			       struct rpcbind_args *rpcb)
 {
@@ -438,7 +648,7 @@ static int rpcb_decode_getport(struct rpc_rqst *req, __be32 *p,
 			       unsigned short *portp)
 {
 	*portp = (unsigned short) ntohl(*p++);
-	dprintk("RPC:      rpcb_decode_getport result %u\n",
+	dprintk("RPC:       rpcb_decode_getport result %u\n",
 			*portp);
 	return 0;
 }
@@ -447,8 +657,8 @@ static int rpcb_decode_set(struct rpc_rqst *req, __be32 *p,
 			   unsigned int *boolp)
 {
 	*boolp = (unsigned int) ntohl(*p++);
-	dprintk("RPC:      rpcb_decode_set result %u\n",
-			*boolp);
+	dprintk("RPC:       rpcb_decode_set: call %s\n",
+			(*boolp ? "succeeded" : "failed"));
 	return 0;
 }
 
@@ -571,52 +781,60 @@ out_err:
 static struct rpc_procinfo rpcb_procedures2[] = {
 	PROC(SET,		mapping,	set),
 	PROC(UNSET,		mapping,	set),
-	PROC(GETADDR,		mapping,	getport),
+	PROC(GETPORT,		mapping,	getport),
 };
 
 static struct rpc_procinfo rpcb_procedures3[] = {
-	PROC(SET,		mapping,	set),
-	PROC(UNSET,		mapping,	set),
+	PROC(SET,		getaddr,	set),
+	PROC(UNSET,		getaddr,	set),
 	PROC(GETADDR,		getaddr,	getaddr),
 };
 
 static struct rpc_procinfo rpcb_procedures4[] = {
-	PROC(SET,		mapping,	set),
-	PROC(UNSET,		mapping,	set),
+	PROC(SET,		getaddr,	set),
+	PROC(UNSET,		getaddr,	set),
+	PROC(GETADDR,		getaddr,	getaddr),
 	PROC(GETVERSADDR,	getaddr,	getaddr),
 };
 
 static struct rpcb_info rpcb_next_version[] = {
-#ifdef CONFIG_SUNRPC_BIND34
-	{ 4, &rpcb_procedures4[RPCBPROC_GETVERSADDR] },
-	{ 3, &rpcb_procedures3[RPCBPROC_GETADDR] },
-#endif
-	{ 2, &rpcb_procedures2[RPCBPROC_GETPORT] },
-	{ 0, NULL },
+	{
+		.rpc_vers	= RPCBVERS_2,
+		.rpc_proc	= &rpcb_procedures2[RPCBPROC_GETPORT],
+	},
+	{
+		.rpc_proc	= NULL,
+	},
 };
 
 static struct rpcb_info rpcb_next_version6[] = {
-#ifdef CONFIG_SUNRPC_BIND34
-	{ 4, &rpcb_procedures4[RPCBPROC_GETVERSADDR] },
-	{ 3, &rpcb_procedures3[RPCBPROC_GETADDR] },
-#endif
-	{ 0, NULL },
+	{
+		.rpc_vers	= RPCBVERS_4,
+		.rpc_proc	= &rpcb_procedures4[RPCBPROC_GETADDR],
+	},
+	{
+		.rpc_vers	= RPCBVERS_3,
+		.rpc_proc	= &rpcb_procedures3[RPCBPROC_GETADDR],
+	},
+	{
+		.rpc_proc	= NULL,
+	},
 };
 
 static struct rpc_version rpcb_version2 = {
-	.number		= 2,
+	.number		= RPCBVERS_2,
 	.nrprocs	= RPCB_HIGHPROC_2,
 	.procs		= rpcb_procedures2
 };
 
 static struct rpc_version rpcb_version3 = {
-	.number		= 3,
+	.number		= RPCBVERS_3,
 	.nrprocs	= RPCB_HIGHPROC_3,
 	.procs		= rpcb_procedures3
 };
 
 static struct rpc_version rpcb_version4 = {
-	.number		= 4,
+	.number		= RPCBVERS_4,
 	.nrprocs	= RPCB_HIGHPROC_4,
 	.procs		= rpcb_procedures4
 };

net/sunrpc/sched.c

@@ -576,9 +576,7 @@ EXPORT_SYMBOL_GPL(rpc_delay);
  */
 static void rpc_prepare_task(struct rpc_task *task)
 {
-	lock_kernel();
 	task->tk_ops->rpc_call_prepare(task, task->tk_calldata);
-	unlock_kernel();
 }
 
 /*
@@ -588,9 +586,7 @@ void rpc_exit_task(struct rpc_task *task)
 {
 	task->tk_action = NULL;
 	if (task->tk_ops->rpc_call_done != NULL) {
-		lock_kernel();
 		task->tk_ops->rpc_call_done(task, task->tk_calldata);
-		unlock_kernel();
 		if (task->tk_action != NULL) {
 			WARN_ON(RPC_ASSASSINATED(task));
 			/* Always release the RPC slot and buffer memory */
@@ -602,11 +598,8 @@ EXPORT_SYMBOL_GPL(rpc_exit_task);
 
 void rpc_release_calldata(const struct rpc_call_ops *ops, void *calldata)
 {
-	if (ops->rpc_release != NULL) {
-		lock_kernel();
+	if (ops->rpc_release != NULL)
 		ops->rpc_release(calldata);
-		unlock_kernel();
-	}
 }
 
 /*
@@ -626,19 +619,15 @@ static void __rpc_execute(struct rpc_task *task)
 		/*
 		 * Execute any pending callback.
 		 */
-		if (RPC_DO_CALLBACK(task)) {
-			/* Define a callback save pointer */
+		if (task->tk_callback) {
 			void (*save_callback)(struct rpc_task *);
 
 			/*
-			 * If a callback exists, save it, reset it,
-			 * call it.
-			 * The save is needed to stop from resetting
-			 * another callback set within the callback handler
-			 * - Dave
+			 * We set tk_callback to NULL before calling it,
+			 * in case it sets the tk_callback field itself:
 			 */
-			save_callback=task->tk_callback;
-			task->tk_callback=NULL;
+			save_callback = task->tk_callback;
+			task->tk_callback = NULL;
 			save_callback(task);
 		}
 

net/sunrpc/xprt.c

@@ -690,7 +690,7 @@ static void xprt_connect_status(struct rpc_task *task)
 {
 	struct rpc_xprt	*xprt = task->tk_xprt;
 
-	if (task->tk_status >= 0) {
+	if (task->tk_status == 0) {
 		xprt->stat.connect_count++;
 		xprt->stat.connect_time += (long)jiffies - xprt->stat.connect_start;
 		dprintk("RPC: %5u xprt_connect_status: connection established\n",
@@ -699,12 +699,6 @@ static void xprt_connect_status(struct rpc_task *task)
 	}
 
 	switch (task->tk_status) {
-	case -ECONNREFUSED:
-	case -ECONNRESET:
-		dprintk("RPC: %5u xprt_connect_status: server %s refused "
-				"connection\n", task->tk_pid,
-				task->tk_client->cl_server);
-		break;
 	case -ENOTCONN:
 		dprintk("RPC: %5u xprt_connect_status: connection broken\n",
 				task->tk_pid);
@@ -878,6 +872,7 @@ void xprt_transmit(struct rpc_task *task)
 		return;
 
 	req->rq_connect_cookie = xprt->connect_cookie;
+	req->rq_xtime = jiffies;
 	status = xprt->ops->send_request(task);
 	if (status == 0) {
 		dprintk("RPC: %5u xmit complete\n", task->tk_pid);

net/sunrpc/xprtsock.c

@@ -579,7 +579,6 @@ static int xs_udp_send_request(struct rpc_task *task)
 				req->rq_svec->iov_base,
 				req->rq_svec->iov_len);
 
-	req->rq_xtime = jiffies;
 	status = xs_sendpages(transport->sock,
 			      xs_addr(xprt),
 			      xprt->addrlen, xdr,
@@ -671,7 +670,6 @@ static int xs_tcp_send_request(struct rpc_task *task)
 	 * to cope with writespace callbacks arriving _after_ we have
 	 * called sendmsg(). */
 	while (1) {
-		req->rq_xtime = jiffies;
 		status = xs_sendpages(transport->sock,
 					NULL, 0, xdr, req->rq_bytes_sent);