Merge branch 'nfs-for-2.6.40' of git://git.linux-nfs.org/projects/trondmy/nfs-2.6

* 'nfs-for-2.6.40' of git://git.linux-nfs.org/projects/trondmy/nfs-2.6:
  SUNRPC: Support for RPC over AF_LOCAL transports
  SUNRPC: Remove obsolete comment
  SUNRPC: Use AF_LOCAL for rpcbind upcalls
  SUNRPC: Clean up use of curly braces in switch cases
  NFS: Revert NFSROOT default mount options
  SUNRPC: Rename xs_encode_tcp_fragment_header()
  nfs,rcu: convert call_rcu(nfs_free_delegation_callback) to kfree_rcu()
  nfs41: Correct offset for LAYOUTCOMMIT
  NFS: nfs_update_inode: print current and new inode size in debug output
  NFSv4.1: Fix the handling of NFS4ERR_SEQ_MISORDERED errors
  NFSv4: Handle expired stateids when the lease is still valid
  SUNRPC: Deal with the lack of a SYN_SENT sk->sk_state_change callback...

fs/nfs/delegation.c

@@ -21,25 +21,13 @@
 #include "delegation.h"
 #include "internal.h"
 
-static void nfs_do_free_delegation(struct nfs_delegation *delegation)
-{
-	kfree(delegation);
-}
-
-static void nfs_free_delegation_callback(struct rcu_head *head)
-{
-	struct nfs_delegation *delegation = container_of(head, struct nfs_delegation, rcu);
-
-	nfs_do_free_delegation(delegation);
-}
-
 static void nfs_free_delegation(struct nfs_delegation *delegation)
 {
 	if (delegation->cred) {
 		put_rpccred(delegation->cred);
 		delegation->cred = NULL;
 	}
-	call_rcu(&delegation->rcu, nfs_free_delegation_callback);
+	kfree_rcu(delegation, rcu);
 }
 
 /**

fs/nfs/inode.c

@@ -1298,8 +1298,12 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
 				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",
-					inode->i_sb->s_id, inode->i_ino);
+			dprintk("NFS: isize change on server for file %s/%ld "
+					"(%Ld to %Ld)\n",
+					inode->i_sb->s_id,
+					inode->i_ino,
+					(long long)cur_isize,
+					(long long)new_isize);
 		}
 	} else
 		invalid |= save_cache_validity & (NFS_INO_INVALID_ATTR

fs/nfs/nfs4proc.c

@@ -267,9 +267,11 @@ static int nfs4_handle_exception(struct nfs_server *server, int errorcode, struc
 				break;
 			nfs4_schedule_stateid_recovery(server, state);
 			goto wait_on_recovery;
+		case -NFS4ERR_EXPIRED:
+			if (state != NULL)
+				nfs4_schedule_stateid_recovery(server, state);
 		case -NFS4ERR_STALE_STATEID:
 		case -NFS4ERR_STALE_CLIENTID:
-		case -NFS4ERR_EXPIRED:
 			nfs4_schedule_lease_recovery(clp);
 			goto wait_on_recovery;
 #if defined(CONFIG_NFS_V4_1)
@@ -3670,9 +3672,11 @@ nfs4_async_handle_error(struct rpc_task *task, const struct nfs_server *server,
 				break;
 			nfs4_schedule_stateid_recovery(server, state);
 			goto wait_on_recovery;
+		case -NFS4ERR_EXPIRED:
+			if (state != NULL)
+				nfs4_schedule_stateid_recovery(server, state);
 		case -NFS4ERR_STALE_STATEID:
 		case -NFS4ERR_STALE_CLIENTID:
-		case -NFS4ERR_EXPIRED:
 			nfs4_schedule_lease_recovery(clp);
 			goto wait_on_recovery;
 #if defined(CONFIG_NFS_V4_1)
@@ -4543,6 +4547,7 @@ int nfs4_lock_delegation_recall(struct nfs4_state *state, struct file_lock *fl)
 			case -ESTALE:
 				goto out;
 			case -NFS4ERR_EXPIRED:
+				nfs4_schedule_stateid_recovery(server, state);
 			case -NFS4ERR_STALE_CLIENTID:
 			case -NFS4ERR_STALE_STATEID:
 				nfs4_schedule_lease_recovery(server->nfs_client);

fs/nfs/nfs4state.c

@@ -1466,7 +1466,10 @@ static int nfs4_reclaim_lease(struct nfs_client *clp)
 #ifdef CONFIG_NFS_V4_1
 void nfs4_schedule_session_recovery(struct nfs4_session *session)
 {
-	nfs4_schedule_lease_recovery(session->clp);
+	struct nfs_client *clp = session->clp;
+
+	set_bit(NFS4CLNT_SESSION_RESET, &clp->cl_state);
+	nfs4_schedule_lease_recovery(clp);
 }
 EXPORT_SYMBOL_GPL(nfs4_schedule_session_recovery);
 
@@ -1549,6 +1552,7 @@ static int nfs4_reset_session(struct nfs_client *clp)
 		status = nfs4_recovery_handle_error(clp, status);
 		goto out;
 	}
+	clear_bit(NFS4CLNT_SESSION_RESET, &clp->cl_state);
 	/* create_session negotiated new slot table */
 	clear_bit(NFS4CLNT_RECALL_SLOT, &clp->cl_state);
 

fs/nfs/nfsroot.c

@@ -87,7 +87,7 @@
 #define NFS_ROOT		"/tftpboot/%s"
 
 /* Default NFSROOT mount options. */
-#define NFS_DEF_OPTIONS		"udp"
+#define NFS_DEF_OPTIONS		"vers=2,udp,rsize=4096,wsize=4096"
 
 /* Parameters passed from the kernel command line */
 static char nfs_root_parms[256] __initdata = "";

fs/nfs/pnfs.c

@@ -1009,7 +1009,7 @@ void
 pnfs_set_layoutcommit(struct nfs_write_data *wdata)
 {
 	struct nfs_inode *nfsi = NFS_I(wdata->inode);
-	loff_t end_pos = wdata->args.offset + wdata->res.count;
+	loff_t end_pos = wdata->mds_offset + wdata->res.count;
 	bool mark_as_dirty = false;
 
 	spin_lock(&nfsi->vfs_inode.i_lock);

include/linux/sunrpc/msg_prot.h

@@ -145,6 +145,7 @@ typedef __be32	rpc_fraghdr;
 #define RPCBIND_NETID_TCP	"tcp"
 #define RPCBIND_NETID_UDP6	"udp6"
 #define RPCBIND_NETID_TCP6	"tcp6"
+#define RPCBIND_NETID_LOCAL	"local"
 
 /*
  * Note that RFC 1833 does not put any size restrictions on the

include/linux/sunrpc/xprt.h

@@ -141,7 +141,8 @@ enum xprt_transports {
 	XPRT_TRANSPORT_UDP	= IPPROTO_UDP,
 	XPRT_TRANSPORT_TCP	= IPPROTO_TCP,
 	XPRT_TRANSPORT_BC_TCP	= IPPROTO_TCP | XPRT_TRANSPORT_BC,
-	XPRT_TRANSPORT_RDMA	= 256
+	XPRT_TRANSPORT_RDMA	= 256,
+	XPRT_TRANSPORT_LOCAL	= 257,
 };
 
 struct rpc_xprt {

net/sunrpc/clnt.c

@@ -13,10 +13,6 @@
  *	and need to be refreshed, or when a packet was damaged in transit.
  *	This may be have to be moved to the VFS layer.
  *
- *  NB: BSD uses a more intelligent approach to guessing when a request
- *  or reply has been lost by keeping the RTO estimate for each procedure.
- *  We currently make do with a constant timeout value.
- *
  *  Copyright (C) 1992,1993 Rick Sladkey <jrs@world.std.com>
  *  Copyright (C) 1995,1996 Olaf Kirch <okir@monad.swb.de>
  */
@@ -32,7 +28,9 @@
 #include <linux/slab.h>
 #include <linux/utsname.h>
 #include <linux/workqueue.h>
+#include <linux/in.h>
 #include <linux/in6.h>
+#include <linux/un.h>
 
 #include <linux/sunrpc/clnt.h>
 #include <linux/sunrpc/rpc_pipe_fs.h>
@@ -298,22 +296,27 @@ struct rpc_clnt *rpc_create(struct rpc_create_args *args)
 	 * up a string representation of the passed-in address.
 	 */
 	if (args->servername == NULL) {
+		struct sockaddr_un *sun =
+				(struct sockaddr_un *)args->address;
+		struct sockaddr_in *sin =
+				(struct sockaddr_in *)args->address;
+		struct sockaddr_in6 *sin6 =
+				(struct sockaddr_in6 *)args->address;
+
 		servername[0] = '\0';
 		switch (args->address->sa_family) {
-		case AF_INET: {
-			struct sockaddr_in *sin =
-					(struct sockaddr_in *)args->address;
+		case AF_LOCAL:
+			snprintf(servername, sizeof(servername), "%s",
+				 sun->sun_path);
+			break;
+		case AF_INET:
 			snprintf(servername, sizeof(servername), "%pI4",
 				 &sin->sin_addr.s_addr);
 			break;
-		}
-		case AF_INET6: {
-			struct sockaddr_in6 *sin =
-					(struct sockaddr_in6 *)args->address;
+		case AF_INET6:
 			snprintf(servername, sizeof(servername), "%pI6",
-				 &sin->sin6_addr);
+				 &sin6->sin6_addr);
 			break;
-		}
 		default:
 			/* caller wants default server name, but
 			 * address family isn't recognized. */

net/sunrpc/rpcb_clnt.c

@@ -16,6 +16,7 @@
 
 #include <linux/types.h>
 #include <linux/socket.h>
+#include <linux/un.h>
 #include <linux/in.h>
 #include <linux/in6.h>
 #include <linux/kernel.h>
@@ -32,6 +33,8 @@
 # define RPCDBG_FACILITY	RPCDBG_BIND
 #endif
 
+#define RPCBIND_SOCK_PATHNAME	"/var/run/rpcbind.sock"
+
 #define RPCBIND_PROGRAM		(100000u)
 #define RPCBIND_PORT		(111u)
 
@@ -158,20 +161,69 @@ static void rpcb_map_release(void *data)
 	kfree(map);
 }
 
-static const struct sockaddr_in rpcb_inaddr_loopback = {
-	.sin_family		= AF_INET,
-	.sin_addr.s_addr	= htonl(INADDR_LOOPBACK),
-	.sin_port		= htons(RPCBIND_PORT),
-};
+/*
+ * Returns zero on success, otherwise a negative errno value
+ * is returned.
+ */
+static int rpcb_create_local_unix(void)
+{
+	static const struct sockaddr_un rpcb_localaddr_rpcbind = {
+		.sun_family		= AF_LOCAL,
+		.sun_path		= RPCBIND_SOCK_PATHNAME,
+	};
+	struct rpc_create_args args = {
+		.net		= &init_net,
+		.protocol	= XPRT_TRANSPORT_LOCAL,
+		.address	= (struct sockaddr *)&rpcb_localaddr_rpcbind,
+		.addrsize	= sizeof(rpcb_localaddr_rpcbind),
+		.servername	= "localhost",
+		.program	= &rpcb_program,
+		.version	= RPCBVERS_2,
+		.authflavor	= RPC_AUTH_NULL,
+	};
+	struct rpc_clnt *clnt, *clnt4;
+	int result = 0;
+
+	/*
+	 * Because we requested an RPC PING at transport creation time,
+	 * this works only if the user space portmapper is rpcbind, and
+	 * it's listening on AF_LOCAL on the named socket.
+	 */
+	clnt = rpc_create(&args);
+	if (IS_ERR(clnt)) {
+		dprintk("RPC:       failed to create AF_LOCAL rpcbind "
+				"client (errno %ld).\n", PTR_ERR(clnt));
+		result = -PTR_ERR(clnt);
+		goto out;
+	}
+
+	clnt4 = rpc_bind_new_program(clnt, &rpcb_program, RPCBVERS_4);
+	if (IS_ERR(clnt4)) {
+		dprintk("RPC:       failed to bind second program to "
+				"rpcbind v4 client (errno %ld).\n",
+				PTR_ERR(clnt4));
+		clnt4 = NULL;
+	}
+
+	/* Protected by rpcb_create_local_mutex */
+	rpcb_local_clnt = clnt;
+	rpcb_local_clnt4 = clnt4;
 
-static DEFINE_MUTEX(rpcb_create_local_mutex);
+out:
+	return result;
+}
 
 /*
  * Returns zero on success, otherwise a negative errno value
  * is returned.
  */
-static int rpcb_create_local(void)
+static int rpcb_create_local_net(void)
 {
+	static const struct sockaddr_in rpcb_inaddr_loopback = {
+		.sin_family		= AF_INET,
+		.sin_addr.s_addr	= htonl(INADDR_LOOPBACK),
+		.sin_port		= htons(RPCBIND_PORT),
+	};
 	struct rpc_create_args args = {
 		.net		= &init_net,
 		.protocol	= XPRT_TRANSPORT_TCP,
@@ -186,13 +238,6 @@ static int rpcb_create_local(void)
 	struct rpc_clnt *clnt, *clnt4;
 	int result = 0;
 
-	if (rpcb_local_clnt)
-		return result;
-
-	mutex_lock(&rpcb_create_local_mutex);
-	if (rpcb_local_clnt)
-		goto out;
-
 	clnt = rpc_create(&args);
 	if (IS_ERR(clnt)) {
 		dprintk("RPC:       failed to create local rpcbind "
@@ -214,9 +259,33 @@ static int rpcb_create_local(void)
 		clnt4 = NULL;
 	}
 
+	/* Protected by rpcb_create_local_mutex */
 	rpcb_local_clnt = clnt;
 	rpcb_local_clnt4 = clnt4;
 
+out:
+	return result;
+}
+
+/*
+ * Returns zero on success, otherwise a negative errno value
+ * is returned.
+ */
+static int rpcb_create_local(void)
+{
+	static DEFINE_MUTEX(rpcb_create_local_mutex);
+	int result = 0;
+
+	if (rpcb_local_clnt)
+		return result;
+
+	mutex_lock(&rpcb_create_local_mutex);
+	if (rpcb_local_clnt)
+		goto out;
+
+	if (rpcb_create_local_unix() != 0)
+		result = rpcb_create_local_net();
+
 out:
 	mutex_unlock(&rpcb_create_local_mutex);
 	return result;

net/sunrpc/svc.c

@@ -942,6 +942,8 @@ static void svc_unregister(const struct svc_serv *serv)
 			if (progp->pg_vers[i]->vs_hidden)
 				continue;
 
+			dprintk("svc: attempting to unregister %sv%u\n",
+				progp->pg_name, i);
 			__svc_unregister(progp->pg_prog, i, progp->pg_name);
 		}
 	}