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

* 'for-linus' of git://linux-nfs.org/~bfields/linux: (100 commits)
  SUNRPC: RPC program information is stored in unsigned integers
  SUNRPC: Move exported symbol definitions after function declaration part 2
  NLM: tear down RPC clients in nlm_shutdown_hosts
  SUNRPC: spin svc_rqst initialization to its own function
  nfsd: more careful input validation in nfsctl write methods
  lockd: minor log message fix
  knfsd: don't bother mapping putrootfh enoent to eperm
  rdma: makefile
  rdma: ONCRPC RDMA protocol marshalling
  rdma: SVCRDMA sendto
  rdma: SVCRDMA recvfrom
  rdma: SVCRDMA Core Transport Services
  rdma: SVCRDMA Transport Module
  rdma: SVCRMDA Header File
  svc: Add svc_xprt_names service to replace svc_sock_names
  knfsd: Support adding transports by writing portlist file
  svc: Add svc API that queries for a transport instance
  svc: Add /proc/sys/sunrpc/transport files
  svc: Add transport hdr size for defer/revisit
  svc: Move the xprt independent code to the svc_xprt.c file
  ...

18 files changed, 4530 insertions, 1206 deletions

diff --git a/net/sunrpc/Makefile b/net/sunrpc/Makefile
index 5c69a725e53..92e1dbe5094 100644
--- a/net/sunrpc/Makefile
+++ b/net/sunrpc/Makefile
@@ -11,6 +11,7 @@ sunrpc-y := clnt.o xprt.o socklib.o xprtsock.o sched.o \
 	    auth.o auth_null.o auth_unix.o \
 	    svc.o svcsock.o svcauth.o svcauth_unix.o \
 	    rpcb_clnt.o timer.o xdr.o \
-	    sunrpc_syms.o cache.o rpc_pipe.o
+	    sunrpc_syms.o cache.o rpc_pipe.o \
+	    svc_xprt.o
 sunrpc-$(CONFIG_PROC_FS) += stats.o
 sunrpc-$(CONFIG_SYSCTL) += sysctl.o
diff --git a/net/sunrpc/auth_gss/svcauth_gss.c b/net/sunrpc/auth_gss/svcauth_gss.c
index 73940df6c46..481f984e9a2 100644
--- a/net/sunrpc/auth_gss/svcauth_gss.c
+++ b/net/sunrpc/auth_gss/svcauth_gss.c
@@ -224,38 +224,34 @@ static int rsi_parse(struct cache_detail *cd,
 
 	/* major/minor */
 	len = qword_get(&mesg, buf, mlen);
-	if (len < 0)
+	if (len <= 0)
 		goto out;
-	if (len == 0) {
+	rsii.major_status = simple_strtoul(buf, &ep, 10);
+	if (*ep)
+		goto out;
+	len = qword_get(&mesg, buf, mlen);
+	if (len <= 0)
+		goto out;
+	rsii.minor_status = simple_strtoul(buf, &ep, 10);
+	if (*ep)
 		goto out;
-	} else {
-		rsii.major_status = simple_strtoul(buf, &ep, 10);
-		if (*ep)
-			goto out;
-		len = qword_get(&mesg, buf, mlen);
-		if (len <= 0)
-			goto out;
-		rsii.minor_status = simple_strtoul(buf, &ep, 10);
-		if (*ep)
-			goto out;
 
-		/* out_handle */
-		len = qword_get(&mesg, buf, mlen);
-		if (len < 0)
-			goto out;
-		status = -ENOMEM;
-		if (dup_to_netobj(&rsii.out_handle, buf, len))
-			goto out;
+	/* out_handle */
+	len = qword_get(&mesg, buf, mlen);
+	if (len < 0)
+		goto out;
+	status = -ENOMEM;
+	if (dup_to_netobj(&rsii.out_handle, buf, len))
+		goto out;
 
-		/* out_token */
-		len = qword_get(&mesg, buf, mlen);
-		status = -EINVAL;
-		if (len < 0)
-			goto out;
-		status = -ENOMEM;
-		if (dup_to_netobj(&rsii.out_token, buf, len))
-			goto out;
-	}
+	/* out_token */
+	len = qword_get(&mesg, buf, mlen);
+	status = -EINVAL;
+	if (len < 0)
+		goto out;
+	status = -ENOMEM;
+	if (dup_to_netobj(&rsii.out_token, buf, len))
+		goto out;
 	rsii.h.expiry_time = expiry;
 	rsip = rsi_update(&rsii, rsip);
 	status = 0;
@@ -975,6 +971,7 @@ static int svcauth_gss_handle_init(struct svc_rqst *rqstp,
 	struct kvec *resv = &rqstp->rq_res.head[0];
 	struct xdr_netobj tmpobj;
 	struct rsi *rsip, rsikey;
+	int ret;
 
 	/* Read the verifier; should be NULL: */
 	*authp = rpc_autherr_badverf;
@@ -1014,23 +1011,27 @@ static int svcauth_gss_handle_init(struct svc_rqst *rqstp,
 		/* No upcall result: */
 		return SVC_DROP;
 	case 0:
+		ret = SVC_DROP;
 		/* Got an answer to the upcall; use it: */
 		if (gss_write_init_verf(rqstp, rsip))
-			return SVC_DROP;
+			goto out;
 		if (resv->iov_len + 4 > PAGE_SIZE)
-			return SVC_DROP;
+			goto out;
 		svc_putnl(resv, RPC_SUCCESS);
 		if (svc_safe_putnetobj(resv, &rsip->out_handle))
-			return SVC_DROP;
+			goto out;
 		if (resv->iov_len + 3 * 4 > PAGE_SIZE)
-			return SVC_DROP;
+			goto out;
 		svc_putnl(resv, rsip->major_status);
 		svc_putnl(resv, rsip->minor_status);
 		svc_putnl(resv, GSS_SEQ_WIN);
 		if (svc_safe_putnetobj(resv, &rsip->out_token))
-			return SVC_DROP;
+			goto out;
 	}
-	return SVC_COMPLETE;
+	ret = SVC_COMPLETE;
+out:
+	cache_put(&rsip->h, &rsi_cache);
+	return ret;
 }
 
 /*
@@ -1125,6 +1126,7 @@ svcauth_gss_accept(struct svc_rqst *rqstp, __be32 *authp)
 	case RPC_GSS_PROC_DESTROY:
 		if (gss_write_verf(rqstp, rsci->mechctx, gc->gc_seq))
 			goto auth_err;
+		rsci->h.expiry_time = get_seconds();
 		set_bit(CACHE_NEGATIVE, &rsci->h.flags);
 		if (resv->iov_len + 4 > PAGE_SIZE)
 			goto drop;
@@ -1386,19 +1388,26 @@ int
 gss_svc_init(void)
 {
 	int rv = svc_auth_register(RPC_AUTH_GSS, &svcauthops_gss);
-	if (rv == 0) {
-		cache_register(&rsc_cache);
-		cache_register(&rsi_cache);
-	}
+	if (rv)
+		return rv;
+	rv = cache_register(&rsc_cache);
+	if (rv)
+		goto out1;
+	rv = cache_register(&rsi_cache);
+	if (rv)
+		goto out2;
+	return 0;
+out2:
+	cache_unregister(&rsc_cache);
+out1:
+	svc_auth_unregister(RPC_AUTH_GSS);
 	return rv;
 }
 
 void
 gss_svc_shutdown(void)
 {
-	if (cache_unregister(&rsc_cache))
-		printk(KERN_ERR "auth_rpcgss: failed to unregister rsc cache\n");
-	if (cache_unregister(&rsi_cache))
-		printk(KERN_ERR "auth_rpcgss: failed to unregister rsi cache\n");
+	cache_unregister(&rsc_cache);
+	cache_unregister(&rsi_cache);
 	svc_auth_unregister(RPC_AUTH_GSS);
 }
diff --git a/net/sunrpc/cache.c b/net/sunrpc/cache.c
index 73f053d0cc7..636c8e04e0b 100644
--- a/net/sunrpc/cache.c
+++ b/net/sunrpc/cache.c
@@ -245,6 +245,7 @@ int cache_check(struct cache_detail *detail,
 		cache_put(h, detail);
 	return rv;
 }
+EXPORT_SYMBOL(cache_check);
 
 /*
  * caches need to be periodically cleaned.
@@ -290,44 +291,78 @@ static const struct file_operations cache_flush_operations;
 static void do_cache_clean(struct work_struct *work);
 static DECLARE_DELAYED_WORK(cache_cleaner, do_cache_clean);
 
-void cache_register(struct cache_detail *cd)
+static void remove_cache_proc_entries(struct cache_detail *cd)
 {
-	cd->proc_ent = proc_mkdir(cd->name, proc_net_rpc);
-	if (cd->proc_ent) {
-		struct proc_dir_entry *p;
-		cd->proc_ent->owner = cd->owner;
-		cd->channel_ent = cd->content_ent = NULL;
+	if (cd->proc_ent == NULL)
+		return;
+	if (cd->flush_ent)
+		remove_proc_entry("flush", cd->proc_ent);
+	if (cd->channel_ent)
+		remove_proc_entry("channel", cd->proc_ent);
+	if (cd->content_ent)
+		remove_proc_entry("content", cd->proc_ent);
+	cd->proc_ent = NULL;
+	remove_proc_entry(cd->name, proc_net_rpc);
+}
 
-		p = create_proc_entry("flush", S_IFREG|S_IRUSR|S_IWUSR,
-				      cd->proc_ent);
-		cd->flush_ent =  p;
-		if (p) {
-			p->proc_fops = &cache_flush_operations;
-			p->owner = cd->owner;
-			p->data = cd;
-		}
+#ifdef CONFIG_PROC_FS
+static int create_cache_proc_entries(struct cache_detail *cd)
+{
+	struct proc_dir_entry *p;
 
-		if (cd->cache_request || cd->cache_parse) {
-			p = create_proc_entry("channel", S_IFREG|S_IRUSR|S_IWUSR,
-					      cd->proc_ent);
-			cd->channel_ent = p;
-			if (p) {
-				p->proc_fops = &cache_file_operations;
-				p->owner = cd->owner;
-				p->data = cd;
-			}
-		}
-		if (cd->cache_show) {
-			p = create_proc_entry("content", S_IFREG|S_IRUSR|S_IWUSR,
-					      cd->proc_ent);
-			cd->content_ent = p;
-			if (p) {
-				p->proc_fops = &content_file_operations;
-				p->owner = cd->owner;
-				p->data = cd;
-			}
-		}
+	cd->proc_ent = proc_mkdir(cd->name, proc_net_rpc);
+	if (cd->proc_ent == NULL)
+		goto out_nomem;
+	cd->proc_ent->owner = cd->owner;
+	cd->channel_ent = cd->content_ent = NULL;
+
+	p = create_proc_entry("flush", S_IFREG|S_IRUSR|S_IWUSR, cd->proc_ent);
+	cd->flush_ent = p;
+	if (p == NULL)
+		goto out_nomem;
+	p->proc_fops = &cache_flush_operations;
+	p->owner = cd->owner;
+	p->data = cd;
+
+	if (cd->cache_request || cd->cache_parse) {
+		p = create_proc_entry("channel", S_IFREG|S_IRUSR|S_IWUSR,
+				      cd->proc_ent);
+		cd->channel_ent = p;
+		if (p == NULL)
+			goto out_nomem;
+		p->proc_fops = &cache_file_operations;
+		p->owner = cd->owner;
+		p->data = cd;
 	}
+	if (cd->cache_show) {
+		p = create_proc_entry("content", S_IFREG|S_IRUSR|S_IWUSR,
+				      cd->proc_ent);
+		cd->content_ent = p;
+		if (p == NULL)
+			goto out_nomem;
+		p->proc_fops = &content_file_operations;
+		p->owner = cd->owner;
+		p->data = cd;
+	}
+	return 0;
+out_nomem:
+	remove_cache_proc_entries(cd);
+	return -ENOMEM;
+}
+#else /* CONFIG_PROC_FS */
+static int create_cache_proc_entries(struct cache_detail *cd)
+{
+	return 0;
+}
+#endif
+
+int cache_register(struct cache_detail *cd)
+{
+	int ret;
+
+	ret = create_cache_proc_entries(cd);
+	if (ret)
+		return ret;
 	rwlock_init(&cd->hash_lock);
 	INIT_LIST_HEAD(&cd->queue);
 	spin_lock(&cache_list_lock);
@@ -341,9 +376,11 @@ void cache_register(struct cache_detail *cd)
 
 	/* start the cleaning process */
 	schedule_delayed_work(&cache_cleaner, 0);
+	return 0;
 }
+EXPORT_SYMBOL(cache_register);
 
-int cache_unregister(struct cache_detail *cd)
+void cache_unregister(struct cache_detail *cd)
 {
 	cache_purge(cd);
 	spin_lock(&cache_list_lock);
@@ -351,30 +388,23 @@ int cache_unregister(struct cache_detail *cd)
 	if (cd->entries || atomic_read(&cd->inuse)) {
 		write_unlock(&cd->hash_lock);
 		spin_unlock(&cache_list_lock);
-		return -EBUSY;
+		goto out;
 	}
 	if (current_detail == cd)
 		current_detail = NULL;
 	list_del_init(&cd->others);
 	write_unlock(&cd->hash_lock);
 	spin_unlock(&cache_list_lock);
-	if (cd->proc_ent) {
-		if (cd->flush_ent)
-			remove_proc_entry("flush", cd->proc_ent);
-		if (cd->channel_ent)
-			remove_proc_entry("channel", cd->proc_ent);
-		if (cd->content_ent)
-			remove_proc_entry("content", cd->proc_ent);
-
-		cd->proc_ent = NULL;
-		remove_proc_entry(cd->name, proc_net_rpc);
-	}
+	remove_cache_proc_entries(cd);
 	if (list_empty(&cache_list)) {
 		/* module must be being unloaded so its safe to kill the worker */
 		cancel_delayed_work_sync(&cache_cleaner);
 	}
-	return 0;
+	return;
+out:
+	printk(KERN_ERR "nfsd: failed to unregister %s cache\n", cd->name);
 }
+EXPORT_SYMBOL(cache_unregister);
 
 /* clean cache tries to find something to clean
  * and cleans it.
@@ -489,6 +519,7 @@ void cache_flush(void)
 	while (cache_clean() != -1)
 		cond_resched();
 }
+EXPORT_SYMBOL(cache_flush);
 
 void cache_purge(struct cache_detail *detail)
 {
@@ -497,7 +528,7 @@ void cache_purge(struct cache_detail *detail)
 	cache_flush();
 	detail->flush_time = 1;
 }
-
+EXPORT_SYMBOL(cache_purge);
 
 
 /*
@@ -634,13 +665,13 @@ void cache_clean_deferred(void *owner)
 /*
  * communicate with user-space
  *
- * We have a magic /proc file - /proc/sunrpc/cache
- * On read, you get a full request, or block
- * On write, an update request is processed
- * Poll works if anything to read, and always allows write
+ * We have a magic /proc file - /proc/sunrpc/<cachename>/channel.
+ * On read, you get a full request, or block.
+ * On write, an update request is processed.
+ * Poll works if anything to read, and always allows write.
  *
  * Implemented by linked list of requests.  Each open file has
- * a ->private that also exists in this list.  New request are added
+ * a ->private that also exists in this list.  New requests are added
  * to the end and may wakeup and preceding readers.
  * New readers are added to the head.  If, on read, an item is found with
  * CACHE_UPCALLING clear, we free it from the list.
@@ -963,6 +994,7 @@ void qword_add(char **bpp, int *lp, char *str)
 	*bpp = bp;
 	*lp = len;
 }
+EXPORT_SYMBOL(qword_add);
 
 void qword_addhex(char **bpp, int *lp, char *buf, int blen)
 {
@@ -991,6 +1023,7 @@ void qword_addhex(char **bpp, int *lp, char *buf, int blen)
 	*bpp = bp;
 	*lp = len;
 }
+EXPORT_SYMBOL(qword_addhex);
 
 static void warn_no_listener(struct cache_detail *detail)
 {
@@ -1113,6 +1146,7 @@ int qword_get(char **bpp, char *dest, int bufsize)
 	*dest = '\0';
 	return len;
 }
+EXPORT_SYMBOL(qword_get);
 
 
 /*
@@ -1244,18 +1278,18 @@ static ssize_t read_flush(struct file *file, char __user *buf,
 	struct cache_detail *cd = PDE(file->f_path.dentry->d_inode)->data;
 	char tbuf[20];
 	unsigned long p = *ppos;
-	int len;
+	size_t len;
 
 	sprintf(tbuf, "%lu\n", cd->flush_time);
 	len = strlen(tbuf);
 	if (p >= len)
 		return 0;
 	len -= p;
-	if (len > count) len = count;
+	if (len > count)
+		len = count;
 	if (copy_to_user(buf, (void*)(tbuf+p), len))
-		len = -EFAULT;
-	else
-		*ppos += len;
+		return -EFAULT;
+	*ppos += len;
 	return len;
 }
 
diff --git a/net/sunrpc/stats.c b/net/sunrpc/stats.c
index 74df2d358e6..5a16875f5ac 100644
--- a/net/sunrpc/stats.c
+++ b/net/sunrpc/stats.c
@@ -33,7 +33,7 @@ struct proc_dir_entry	*proc_net_rpc = NULL;
 static int rpc_proc_show(struct seq_file *seq, void *v) {
 	const struct rpc_stat	*statp = seq->private;
 	const struct rpc_program *prog = statp->program;
-	int		i, j;
+	unsigned int i, j;
 
 	seq_printf(seq,
 		"net %u %u %u %u\n",
@@ -81,7 +81,7 @@ void svc_seq_show(struct seq_file *seq, const struct svc_stat *statp) {
 	const struct svc_program *prog = statp->program;
 	const struct svc_procedure *proc;
 	const struct svc_version *vers;
-	int		i, j;
+	unsigned int i, j;
 
 	seq_printf(seq,
 		"net %u %u %u %u\n",
@@ -106,6 +106,7 @@ void svc_seq_show(struct seq_file *seq, const struct svc_stat *statp) {
 		seq_putc(seq, '\n');
 	}
 }
+EXPORT_SYMBOL(svc_seq_show);
 
 /**
  * rpc_alloc_iostats - allocate an rpc_iostats structure
@@ -255,12 +256,14 @@ svc_proc_register(struct svc_stat *statp, const struct file_operations *fops)
 {
 	return do_register(statp->program->pg_name, statp, fops);
 }
+EXPORT_SYMBOL(svc_proc_register);
 
 void
 svc_proc_unregister(const char *name)
 {
 	remove_proc_entry(name, proc_net_rpc);
 }
+EXPORT_SYMBOL(svc_proc_unregister);
 
 void
 rpc_proc_init(void)
diff --git a/net/sunrpc/sunrpc_syms.c b/net/sunrpc/sunrpc_syms.c
index 1a7e309d008..843629f5576 100644
--- a/net/sunrpc/sunrpc_syms.c
+++ b/net/sunrpc/sunrpc_syms.c
@@ -22,48 +22,6 @@
 #include <linux/sunrpc/rpc_pipe_fs.h>
 #include <linux/sunrpc/xprtsock.h>
 
-/* RPC server stuff */
-EXPORT_SYMBOL(svc_create);
-EXPORT_SYMBOL(svc_create_thread);
-EXPORT_SYMBOL(svc_create_pooled);
-EXPORT_SYMBOL(svc_set_num_threads);
-EXPORT_SYMBOL(svc_exit_thread);
-EXPORT_SYMBOL(svc_destroy);
-EXPORT_SYMBOL(svc_drop);
-EXPORT_SYMBOL(svc_process);
-EXPORT_SYMBOL(svc_recv);
-EXPORT_SYMBOL(svc_wake_up);
-EXPORT_SYMBOL(svc_makesock);
-EXPORT_SYMBOL(svc_reserve);
-EXPORT_SYMBOL(svc_auth_register);
-EXPORT_SYMBOL(auth_domain_lookup);
-EXPORT_SYMBOL(svc_authenticate);
-EXPORT_SYMBOL(svc_set_client);
-
-/* RPC statistics */
-#ifdef CONFIG_PROC_FS
-EXPORT_SYMBOL(svc_proc_register);
-EXPORT_SYMBOL(svc_proc_unregister);
-EXPORT_SYMBOL(svc_seq_show);
-#endif
-
-/* caching... */
-EXPORT_SYMBOL(auth_domain_find);
-EXPORT_SYMBOL(auth_domain_put);
-EXPORT_SYMBOL(auth_unix_add_addr);
-EXPORT_SYMBOL(auth_unix_forget_old);
-EXPORT_SYMBOL(auth_unix_lookup);
-EXPORT_SYMBOL(cache_check);
-EXPORT_SYMBOL(cache_flush);
-EXPORT_SYMBOL(cache_purge);
-EXPORT_SYMBOL(cache_register);
-EXPORT_SYMBOL(cache_unregister);
-EXPORT_SYMBOL(qword_add);
-EXPORT_SYMBOL(qword_addhex);
-EXPORT_SYMBOL(qword_get);
-EXPORT_SYMBOL(svcauth_unix_purge);
-EXPORT_SYMBOL(unix_domain_find);
-
 extern struct cache_detail ip_map_cache, unix_gid_cache;
 
 static int __init
@@ -85,7 +43,8 @@ init_sunrpc(void)
 #endif
 	cache_register(&ip_map_cache);
 	cache_register(&unix_gid_cache);
-	init_socket_xprt();
+	svc_init_xprt_sock();	/* svc sock transport */
+	init_socket_xprt();	/* clnt sock transport */
 	rpcauth_init_module();
 out:
 	return err;
@@ -96,12 +55,11 @@ cleanup_sunrpc(void)
 {
 	rpcauth_remove_module();
 	cleanup_socket_xprt();
+	svc_cleanup_xprt_sock();
 	unregister_rpc_pipefs();
 	rpc_destroy_mempool();
-	if (cache_unregister(&ip_map_cache))
-		printk(KERN_ERR "sunrpc: failed to unregister ip_map cache\n");
-	if (cache_unregister(&unix_gid_cache))
-	      printk(KERN_ERR "sunrpc: failed to unregister unix_gid cache\n");
+	cache_unregister(&ip_map_cache);
+	cache_unregister(&unix_gid_cache);
 #ifdef RPC_DEBUG
 	rpc_unregister_sysctl();
 #endif
diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c
index 4ad5fbbb18b..a290e152329 100644
--- a/net/sunrpc/svc.c
+++ b/net/sunrpc/svc.c
@@ -364,7 +364,7 @@ __svc_create(struct svc_program *prog, unsigned int bufsize, int npools,
 	   void (*shutdown)(struct svc_serv *serv))
 {
 	struct svc_serv	*serv;
-	int vers;
+	unsigned int vers;
 	unsigned int xdrsize;
 	unsigned int i;
 
@@ -433,6 +433,7 @@ svc_create(struct svc_program *prog, unsigned int bufsize,
 {
 	return __svc_create(prog, bufsize, /*npools*/1, shutdown);
 }
+EXPORT_SYMBOL(svc_create);
 
 struct svc_serv *
 svc_create_pooled(struct svc_program *prog, unsigned int bufsize,
@@ -452,6 +453,7 @@ svc_create_pooled(struct svc_program *prog, unsigned int bufsize,
 
 	return serv;
 }
+EXPORT_SYMBOL(svc_create_pooled);
 
 /*
  * Destroy an RPC service.  Should be called with the BKL held
@@ -459,9 +461,6 @@ svc_create_pooled(struct svc_program *prog, unsigned int bufsize,
 void
 svc_destroy(struct svc_serv *serv)
 {
-	struct svc_sock	*svsk;
-	struct svc_sock *tmp;
-
 	dprintk("svc: svc_destroy(%s, %d)\n",
 				serv->sv_program->pg_name,
 				serv->sv_nrthreads);
@@ -476,14 +475,12 @@ svc_destroy(struct svc_serv *serv)
 
 	del_timer_sync(&serv->sv_temptimer);
 
-	list_for_each_entry_safe(svsk, tmp, &serv->sv_tempsocks, sk_list)
-		svc_force_close_socket(svsk);
+	svc_close_all(&serv->sv_tempsocks);
 
 	if (serv->sv_shutdown)
 		serv->sv_shutdown(serv);
 
-	list_for_each_entry_safe(svsk, tmp, &serv->sv_permsocks, sk_list)
-		svc_force_close_socket(svsk);
+	svc_close_all(&serv->sv_permsocks);
 
 	BUG_ON(!list_empty(&serv->sv_permsocks));
 	BUG_ON(!list_empty(&serv->sv_tempsocks));
@@ -498,6 +495,7 @@ svc_destroy(struct svc_serv *serv)
 	kfree(serv->sv_pools);
 	kfree(serv);
 }
+EXPORT_SYMBOL(svc_destroy);
 
 /*
  * Allocate an RPC server's buffer space.
@@ -536,31 +534,17 @@ svc_release_buffer(struct svc_rqst *rqstp)
 			put_page(rqstp->rq_pages[i]);
 }
 
-/*
- * Create a thread in the given pool.  Caller must hold BKL.
- * On a NUMA or SMP machine, with a multi-pool serv, the thread
- * will be restricted to run on the cpus belonging to the pool.
- */
-static int
-__svc_create_thread(svc_thread_fn func, struct svc_serv *serv,
-		    struct svc_pool *pool)
+struct svc_rqst *
+svc_prepare_thread(struct svc_serv *serv, struct svc_pool *pool)
 {
 	struct svc_rqst	*rqstp;
-	int		error = -ENOMEM;
-	int		have_oldmask = 0;
-	cpumask_t	oldmask;
 
 	rqstp = kzalloc(sizeof(*rqstp), GFP_KERNEL);
 	if (!rqstp)
-		goto out;
+		goto out_enomem;
 
 	init_waitqueue_head(&rqstp->rq_wait);
 
-	if (!(rqstp->rq_argp = kmalloc(serv->sv_xdrsize, GFP_KERNEL))
-	 || !(rqstp->rq_resp = kmalloc(serv->sv_xdrsize, GFP_KERNEL))
-	 || !svc_init_buffer(rqstp, serv->sv_max_mesg))
-		goto out_thread;
-
 	serv->sv_nrthreads++;
 	spin_lock_bh(&pool->sp_lock);
 	pool->sp_nrthreads++;
@@ -569,6 +553,45 @@ __svc_create_thread(svc_thread_fn func, struct svc_serv *serv,
 	rqstp->rq_server = serv;
 	rqstp->rq_pool = pool;
 
+	rqstp->rq_argp = kmalloc(serv->sv_xdrsize, GFP_KERNEL);
+	if (!rqstp->rq_argp)
+		goto out_thread;
+
+	rqstp->rq_resp = kmalloc(serv->sv_xdrsize, GFP_KERNEL);
+	if (!rqstp->rq_resp)
+		goto out_thread;
+
+	if (!svc_init_buffer(rqstp, serv->sv_max_mesg))
+		goto out_thread;
+
+	return rqstp;
+out_thread:
+	svc_exit_thread(rqstp);
+out_enomem:
+	return ERR_PTR(-ENOMEM);
+}
+EXPORT_SYMBOL(svc_prepare_thread);
+
+/*
+ * Create a thread in the given pool.  Caller must hold BKL.
+ * On a NUMA or SMP machine, with a multi-pool serv, the thread
+ * will be restricted to run on the cpus belonging to the pool.
+ */
+static int
+__svc_create_thread(svc_thread_fn func, struct svc_serv *serv,
+		    struct svc_pool *pool)
+{
+	struct svc_rqst	*rqstp;
+	int		error = -ENOMEM;
+	int		have_oldmask = 0;
+	cpumask_t	oldmask;
+
+	rqstp = svc_prepare_thread(serv, pool);
+	if (IS_ERR(rqstp)) {
+		error = PTR_ERR(rqstp);
+		goto out;
+	}
+
 	if (serv->sv_nrpools > 1)
 		have_oldmask = svc_pool_map_set_cpumask(pool->sp_id, &oldmask);
 
@@ -597,6 +620,7 @@ svc_create_thread(svc_thread_fn func, struct svc_serv *serv)
 {
 	return __svc_create_thread(func, serv, &serv->sv_pools[0]);
 }
+EXPORT_SYMBOL(svc_create_thread);
 
 /*
  * Choose a pool in which to create a new thread, for svc_set_num_threads
@@ -700,6 +724,7 @@ svc_set_num_threads(struct svc_serv *serv, struct svc_pool *pool, int nrservs)
 
 	return error;
 }
+EXPORT_SYMBOL(svc_set_num_threads);
 
 /*
  * Called from a server thread as it's exiting.  Caller must hold BKL.
@@ -726,6 +751,7 @@ svc_exit_thread(struct svc_rqst *rqstp)
 	if (serv)
 		svc_destroy(serv);
 }
+EXPORT_SYMBOL(svc_exit_thread);
 
 /*
  * Register an RPC service with the local portmapper.
@@ -737,7 +763,8 @@ svc_register(struct svc_serv *serv, int proto, unsigned short port)
 {
 	struct svc_program	*progp;
 	unsigned long		flags;
-	int			i, error = 0, dummy;
+	unsigned int		i;
+	int			error = 0, dummy;
 
 	if (!port)
 		clear_thread_flag(TIF_SIGPENDING);
@@ -840,9 +867,9 @@ svc_process(struct svc_rqst *rqstp)
 	rqstp->rq_res.tail[0].iov_len = 0;
 	/* Will be turned off only in gss privacy case: */
 	rqstp->rq_splice_ok = 1;
-	/* tcp needs a space for the record length... */
-	if (rqstp->rq_prot == IPPROTO_TCP)
-		svc_putnl(resv, 0);
+
+	/* Setup reply header */
+	rqstp->rq_xprt->xpt_ops->xpo_prep_reply_hdr(rqstp);
 
 	rqstp->rq_xid = svc_getu32(argv);
 	svc_putu32(resv, rqstp->rq_xid);
@@ -1049,16 +1076,15 @@ err_bad:
 	svc_putnl(resv, ntohl(rpc_stat));
 	goto sendit;
 }
+EXPORT_SYMBOL(svc_process);
 
 /*
  * Return (transport-specific) limit on the rpc payload.
  */
 u32 svc_max_payload(const struct svc_rqst *rqstp)
 {
-	int max = RPCSVC_MAXPAYLOAD_TCP;
+	u32 max = rqstp->rq_xprt->xpt_class->xcl_max_payload;
 
-	if (rqstp->rq_sock->sk_sock->type == SOCK_DGRAM)
-		max = RPCSVC_MAXPAYLOAD_UDP;
 	if (rqstp->rq_server->sv_max_payload < max)
 		max = rqstp->rq_server->sv_max_payload;
 	return max;
diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c
new file mode 100644
index 00000000000..ea377e06afa
--- /dev/null
+++ b/net/sunrpc/svc_xprt.c
@@ -0,0 +1,1055 @@
+/*
+ * linux/net/sunrpc/svc_xprt.c
+ *
+ * Author: Tom Tucker <tom@opengridcomputing.com>
+ */
+
+#include <linux/sched.h>
+#include <linux/errno.h>
+#include <linux/fcntl.h>
+#include <linux/net.h>
+#include <linux/in.h>
+#include <linux/inet.h>
+#include <linux/udp.h>
+#include <linux/tcp.h>
+#include <linux/unistd.h>
+#include <linux/slab.h>
+#include <linux/netdevice.h>
+#include <linux/skbuff.h>
+#include <linux/file.h>
+#include <linux/freezer.h>
+#include <net/sock.h>
+#include <net/checksum.h>
+#include <net/ip.h>
+#include <net/ipv6.h>
+#include <net/tcp_states.h>
+#include <linux/uaccess.h>
+#include <asm/ioctls.h>
+
+#include <linux/sunrpc/types.h>
+#include <linux/sunrpc/clnt.h>
+#include <linux/sunrpc/xdr.h>
+#include <linux/sunrpc/stats.h>
+#include <linux/sunrpc/svc_xprt.h>
+
+#define RPCDBG_FACILITY	RPCDBG_SVCXPRT
+
+static struct svc_deferred_req *svc_deferred_dequeue(struct svc_xprt *xprt);
+static int svc_deferred_recv(struct svc_rqst *rqstp);
+static struct cache_deferred_req *svc_defer(struct cache_req *req);
+static void svc_age_temp_xprts(unsigned long closure);
+
+/* apparently the "standard" is that clients close
+ * idle connections after 5 minutes, servers after
+ * 6 minutes
+ *   http://www.connectathon.org/talks96/nfstcp.pdf
+ */
+static int svc_conn_age_period = 6*60;
+
+/* List of registered transport classes */
+static DEFINE_SPINLOCK(svc_xprt_class_lock);
+static LIST_HEAD(svc_xprt_class_list);
+
+/* SMP locking strategy:
+ *
+ *	svc_pool->sp_lock protects most of the fields of that pool.
+ *	svc_serv->sv_lock protects sv_tempsocks, sv_permsocks, sv_tmpcnt.
+ *	when both need to be taken (rare), svc_serv->sv_lock is first.
+ *	BKL protects svc_serv->sv_nrthread.
+ *	svc_sock->sk_lock protects the svc_sock->sk_deferred list
+ *             and the ->sk_info_authunix cache.
+ *
+ *	The XPT_BUSY bit in xprt->xpt_flags prevents a transport being
+ *	enqueued multiply. During normal transport processing this bit
+ *	is set by svc_xprt_enqueue and cleared by svc_xprt_received.
+ *	Providers should not manipulate this bit directly.
+ *
+ *	Some flags can be set to certain values at any time
+ *	providing that certain rules are followed:
+ *
+ *	XPT_CONN, XPT_DATA:
+ *		- Can be set or cleared at any time.
+ *		- After a set, svc_xprt_enqueue must be called to enqueue
+ *		  the transport for processing.
+ *		- After a clear, the transport must be read/accepted.
+ *		  If this succeeds, it must be set again.
+ *	XPT_CLOSE:
+ *		- Can set at any time. It is never cleared.
+ *      XPT_DEAD:
+ *		- Can only be set while XPT_BUSY is held which ensures
+ *		  that no other thread will be using the transport or will
+ *		  try to set XPT_DEAD.
+ */
+
+int svc_reg_xprt_class(struct svc_xprt_class *xcl)
+{
+	struct svc_xprt_class *cl;
+	int res = -EEXIST;
+
+	dprintk("svc: Adding svc transport class '%s'\n", xcl->xcl_name);
+
+	INIT_LIST_HEAD(&xcl->xcl_list);
+	spin_lock(&svc_xprt_class_lock);
+	/* Make sure there isn't already a class with the same name */
+	list_for_each_entry(cl, &svc_xprt_class_list, xcl_list) {
+		if (strcmp(xcl->xcl_name, cl->xcl_name) == 0)
+			goto out;
+	}
+	list_add_tail(&xcl->xcl_list, &svc_xprt_class_list);
+	res = 0;
+out:
+	spin_unlock(&svc_xprt_class_lock);
+	return res;
+}
+EXPORT_SYMBOL_GPL(svc_reg_xprt_class);
+
+void svc_unreg_xprt_class(struct svc_xprt_class *xcl)
+{
+	dprintk("svc: Removing svc transport class '%s'\n", xcl->xcl_name);
+	spin_lock(&svc_xprt_class_lock);
+	list_del_init(&xcl->xcl_list);
+	spin_unlock(&svc_xprt_class_lock);
+}
+EXPORT_SYMBOL_GPL(svc_unreg_xprt_class);
+
+/*
+ * Format the transport list for printing
+ */
+int svc_print_xprts(char *buf, int maxlen)
+{
+	struct list_head *le;
+	char tmpstr[80];
+	int len = 0;
+	buf[0] = '\0';
+
+	spin_lock(&svc_xprt_class_lock);
+	list_for_each(le, &svc_xprt_class_list) {
+		int slen;
+		struct svc_xprt_class *xcl =
+			list_entry(le, struct svc_xprt_class, xcl_list);
+
+		sprintf(tmpstr, "%s %d\n", xcl->xcl_name, xcl->xcl_max_payload);
+		slen = strlen(tmpstr);
+		if (len + slen > maxlen)
+			break;
+		len += slen;
+		strcat(buf, tmpstr);
+	}
+	spin_unlock(&svc_xprt_class_lock);
+
+	return len;
+}
+
+static void svc_xprt_free(struct kref *kref)
+{
+	struct svc_xprt *xprt =
+		container_of(kref, struct svc_xprt, xpt_ref);
+	struct module *owner = xprt->xpt_class->xcl_owner;
+	if (test_bit(XPT_CACHE_AUTH, &xprt->xpt_flags)
+	    && xprt->xpt_auth_cache != NULL)
+		svcauth_unix_info_release(xprt->xpt_auth_cache);
+	xprt->xpt_ops->xpo_free(xprt);
+	module_put(owner);
+}
+
+void svc_xprt_put(struct svc_xprt *xprt)
+{
+	kref_put(&xprt->xpt_ref, svc_xprt_free);
+}
+EXPORT_SYMBOL_GPL(svc_xprt_put);
+
+/*
+ * Called by transport drivers to initialize the transport independent
+ * portion of the transport instance.
+ */
+void svc_xprt_init(struct svc_xprt_class *xcl, struct svc_xprt *xprt,
+		   struct svc_serv *serv)
+{
+	memset(xprt, 0, sizeof(*xprt));
+	xprt->xpt_class = xcl;
+	xprt->xpt_ops = xcl->xcl_ops;
+	kref_init(&xprt->xpt_ref);
+	xprt->xpt_server = serv;
+	INIT_LIST_HEAD(&xprt->xpt_list);
+	INIT_LIST_HEAD(&xprt->xpt_ready);
+	INIT_LIST_HEAD(&xprt->xpt_deferred);
+	mutex_init(&xprt->xpt_mutex);
+	spin_lock_init(&xprt->xpt_lock);
+	set_bit(XPT_BUSY, &xprt->xpt_flags);
+}
+EXPORT_SYMBOL_GPL(svc_xprt_init);
+
+int svc_create_xprt(struct svc_serv *serv, char *xprt_name, unsigned short port,
+		    int flags)
+{
+	struct svc_xprt_class *xcl;
+	struct sockaddr_in sin = {
+		.sin_family		= AF_INET,
+		.sin_addr.s_addr	= INADDR_ANY,
+		.sin_port		= htons(port),
+	};
+	dprintk("svc: creating transport %s[%d]\n", xprt_name, port);
+	spin_lock(&svc_xprt_class_lock);
+	list_for_each_entry(xcl, &svc_xprt_class_list, xcl_list) {
+		struct svc_xprt *newxprt;
+
+		if (strcmp(xprt_name, xcl->xcl_name))
+			continue;
+
+		if (!try_module_get(xcl->xcl_owner))
+			goto err;
+
+		spin_unlock(&svc_xprt_class_lock);
+		newxprt = xcl->xcl_ops-><