Merge branch 'for-2.6.37' of git://linux-nfs.org/~bfields/linux

* 'for-2.6.37' of git://linux-nfs.org/~bfields/linux: (99 commits)
  svcrpc: svc_tcp_sendto XPT_DEAD check is redundant
  svcrpc: no need for XPT_DEAD check in svc_xprt_enqueue
  svcrpc: assume svc_delete_xprt() called only once
  svcrpc: never clear XPT_BUSY on dead xprt
  nfsd4: fix connection allocation in sequence()
  nfsd4: only require krb5 principal for NFSv4.0 callbacks
  nfsd4: move minorversion to client
  nfsd4: delay session removal till free_client
  nfsd4: separate callback change and callback probe
  nfsd4: callback program number is per-session
  nfsd4: track backchannel connections
  nfsd4: confirm only on succesful create_session
  nfsd4: make backchannel sequence number per-session
  nfsd4: use client pointer to backchannel session
  nfsd4: move callback setup into session init code
  nfsd4: don't cache seq_misordered replies
  SUNRPC: Properly initialize sock_xprt.srcaddr in all cases
  SUNRPC: Use conventional switch statement when reclassifying sockets
  sunrpc/xprtrdma: clean up workqueue usage
  sunrpc: Turn list_for_each-s into the ..._entry-s
  ...

Fix up trivial conflicts (two different deprecation notices added in
separate branches) in Documentation/feature-removal-schedule.txt

Documentation/feature-removal-schedule.txt

@@ -535,3 +535,13 @@ Why:	Hareware scan is the prefer method for iwlwifi devices for
 Who:	Wey-Yi Guy <wey-yi.w.guy@intel.com>
 
 ----------------------------
+
+What:   access to nfsd auth cache through sys_nfsservctl or '.' files
+        in the 'nfsd' filesystem.
+When:   2.6.40
+Why:    This is a legacy interface which have been replaced by a more
+        dynamic cache.  Continuing to maintain this interface is an
+        unnecessary burden.
+Who:    NeilBrown <neilb@suse.de>
+
+----------------------------

fs/Makefile

@@ -29,10 +29,7 @@ obj-$(CONFIG_EVENTFD)		+= eventfd.o
 obj-$(CONFIG_AIO)               += aio.o
 obj-$(CONFIG_FILE_LOCKING)      += locks.o
 obj-$(CONFIG_COMPAT)		+= compat.o compat_ioctl.o
-
-nfsd-$(CONFIG_NFSD)		:= nfsctl.o
-obj-y				+= $(nfsd-y) $(nfsd-m)
-
+obj-$(CONFIG_NFSD_DEPRECATED)	+= nfsctl.o
 obj-$(CONFIG_BINFMT_AOUT)	+= binfmt_aout.o
 obj-$(CONFIG_BINFMT_EM86)	+= binfmt_em86.o
 obj-$(CONFIG_BINFMT_MISC)	+= binfmt_misc.o

fs/compat.c

@@ -1963,7 +1963,7 @@ asmlinkage long compat_sys_ppoll(struct pollfd __user *ufds,
 }
 #endif /* HAVE_SET_RESTORE_SIGMASK */
 
-#if defined(CONFIG_NFSD) || defined(CONFIG_NFSD_MODULE)
+#if (defined(CONFIG_NFSD) || defined(CONFIG_NFSD_MODULE)) && !defined(CONFIG_NFSD_DEPRECATED)
 /* Stuff for NFS server syscalls... */
 struct compat_nfsctl_svc {
 	u16			svc32_port;

fs/lockd/host.c

@@ -353,6 +353,7 @@ nlm_bind_host(struct nlm_host *host)
 			.to_retries	= 5U,
 		};
 		struct rpc_create_args args = {
+			.net		= &init_net,
 			.protocol	= host->h_proto,
 			.address	= nlm_addr(host),
 			.addrsize	= host->h_addrlen,

fs/lockd/mon.c

@@ -69,6 +69,7 @@ static struct rpc_clnt *nsm_create(void)
 		.sin_addr.s_addr	= htonl(INADDR_LOOPBACK),
 	};
 	struct rpc_create_args args = {
+		.net			= &init_net,
 		.protocol		= XPRT_TRANSPORT_UDP,
 		.address		= (struct sockaddr *)&sin,
 		.addrsize		= sizeof(sin),

fs/lockd/svc.c

@@ -206,7 +206,7 @@ static int create_lockd_listener(struct svc_serv *serv, const char *name,
 
 	xprt = svc_find_xprt(serv, name, family, 0);
 	if (xprt == NULL)
-		return svc_create_xprt(serv, name, family, port,
+		return svc_create_xprt(serv, name, &init_net, family, port,
 						SVC_SOCK_DEFAULTS);
 	svc_xprt_put(xprt);
 	return 0;

fs/lockd/svc4proc.c

@@ -230,9 +230,7 @@ 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

@@ -52,12 +52,13 @@ static const struct rpc_call_ops nlmsvc_grant_ops;
  * The list of blocked locks to retry
  */
 static LIST_HEAD(nlm_blocked);
+static DEFINE_SPINLOCK(nlm_blocked_lock);
 
 /*
  * Insert a blocked lock into the global list
  */
 static void
-nlmsvc_insert_block(struct nlm_block *block, unsigned long when)
+nlmsvc_insert_block_locked(struct nlm_block *block, unsigned long when)
 {
 	struct nlm_block *b;
 	struct list_head *pos;
@@ -87,6 +88,13 @@ nlmsvc_insert_block(struct nlm_block *block, unsigned long when)
 	block->b_when = when;
 }
 
+static void nlmsvc_insert_block(struct nlm_block *block, unsigned long when)
+{
+	spin_lock(&nlm_blocked_lock);
+	nlmsvc_insert_block_locked(block, when);
+	spin_unlock(&nlm_blocked_lock);
+}
+
 /*
  * Remove a block from the global list
  */
@@ -94,7 +102,9 @@ static inline void
 nlmsvc_remove_block(struct nlm_block *block)
 {
 	if (!list_empty(&block->b_list)) {
+		spin_lock(&nlm_blocked_lock);
 		list_del_init(&block->b_list);
+		spin_unlock(&nlm_blocked_lock);
 		nlmsvc_release_block(block);
 	}
 }
@@ -651,7 +661,7 @@ static int nlmsvc_grant_deferred(struct file_lock *fl, struct file_lock *conf,
 	struct nlm_block *block;
 	int rc = -ENOENT;
 
-	lock_kernel();
+	spin_lock(&nlm_blocked_lock);
 	list_for_each_entry(block, &nlm_blocked, b_list) {
 		if (nlm_compare_locks(&block->b_call->a_args.lock.fl, fl)) {
 			dprintk("lockd: nlmsvc_notify_blocked block %p flags %d\n",
@@ -665,13 +675,13 @@ static int nlmsvc_grant_deferred(struct file_lock *fl, struct file_lock *conf,
 			} else if (result == 0)
 				block->b_granted = 1;
 
-			nlmsvc_insert_block(block, 0);
+			nlmsvc_insert_block_locked(block, 0);
 			svc_wake_up(block->b_daemon);
 			rc = 0;
 			break;
 		}
 	}
-	unlock_kernel();
+	spin_unlock(&nlm_blocked_lock);
 	if (rc == -ENOENT)
 		printk(KERN_WARNING "lockd: grant for unknown block\n");
 	return rc;
@@ -803,7 +813,7 @@ static void nlmsvc_grant_callback(struct rpc_task *task, void *data)
 
 	dprintk("lockd: GRANT_MSG RPC callback\n");
 
-	lock_kernel();
+	spin_lock(&nlm_blocked_lock);
 	/* if the block is not on a list at this point then it has
 	 * been invalidated. Don't try to requeue it.
 	 *
@@ -825,19 +835,20 @@ static void nlmsvc_grant_callback(struct rpc_task *task, void *data)
 		/* Call was successful, now wait for client callback */
 		timeout = 60 * HZ;
 	}
-	nlmsvc_insert_block(block, timeout);
+	nlmsvc_insert_block_locked(block, timeout);
 	svc_wake_up(block->b_daemon);
 out:
-	unlock_kernel();
+	spin_unlock(&nlm_blocked_lock);
 }
 
+/*
+ * FIXME: nlmsvc_release_block() grabs a mutex.  This is not allowed for an
+ * .rpc_release rpc_call_op
+ */
 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

@@ -260,9 +260,7 @@ 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

@@ -109,7 +109,7 @@ nfs4_callback_up(struct svc_serv *serv)
 {
 	int ret;
 
-	ret = svc_create_xprt(serv, "tcp", PF_INET,
+	ret = svc_create_xprt(serv, "tcp", &init_net, PF_INET,
 				nfs_callback_set_tcpport, SVC_SOCK_ANONYMOUS);
 	if (ret <= 0)
 		goto out_err;
@@ -117,7 +117,7 @@ nfs4_callback_up(struct svc_serv *serv)
 	dprintk("NFS: Callback listener port = %u (af %u)\n",
 			nfs_callback_tcpport, PF_INET);
 
-	ret = svc_create_xprt(serv, "tcp", PF_INET6,
+	ret = svc_create_xprt(serv, "tcp", &init_net, PF_INET6,
 				nfs_callback_set_tcpport, SVC_SOCK_ANONYMOUS);
 	if (ret > 0) {
 		nfs_callback_tcpport6 = ret;

fs/nfs/client.c

@@ -605,6 +605,7 @@ static int nfs_create_rpc_client(struct nfs_client *clp,
 {
 	struct rpc_clnt		*clnt = NULL;
 	struct rpc_create_args args = {
+		.net		= &init_net,
 		.protocol	= clp->cl_proto,
 		.address	= (struct sockaddr *)&clp->cl_addr,
 		.addrsize	= clp->cl_addrlen,

fs/nfs/dns_resolve.c

@@ -167,7 +167,7 @@ static int nfs_dns_show(struct seq_file *m, struct cache_detail *cd,
 		return 0;
 	}
 	item = container_of(h, struct nfs_dns_ent, h);
-	ttl = (long)item->h.expiry_time - (long)get_seconds();
+	ttl = item->h.expiry_time - seconds_since_boot();
 	if (ttl < 0)
 		ttl = 0;
 
@@ -239,7 +239,7 @@ static int nfs_dns_parse(struct cache_detail *cd, char *buf, int buflen)
 	ttl = get_expiry(&buf);
 	if (ttl == 0)
 		goto out;
-	key.h.expiry_time = ttl + get_seconds();
+	key.h.expiry_time = ttl + seconds_since_boot();
 
 	ret = -ENOMEM;
 	item = nfs_dns_lookup(cd, &key);
@@ -301,7 +301,7 @@ static int do_cache_lookup_nowait(struct cache_detail *cd,
 		goto out_err;
 	ret = -ETIMEDOUT;
 	if (!test_bit(CACHE_VALID, &(*item)->h.flags)
-			|| (*item)->h.expiry_time < get_seconds()
+			|| (*item)->h.expiry_time < seconds_since_boot()
 			|| cd->flush_time > (*item)->h.last_refresh)
 		goto out_put;
 	ret = -ENOENT;

fs/nfs/mount_clnt.c

@@ -153,6 +153,7 @@ int nfs_mount(struct nfs_mount_request *info)
 		.rpc_resp	= &result,
 	};
 	struct rpc_create_args args = {
+		.net		= &init_net,
 		.protocol	= info->protocol,
 		.address	= info->sap,
 		.addrsize	= info->salen,
@@ -224,6 +225,7 @@ void nfs_umount(const struct nfs_mount_request *info)
 		.to_retries = 2,
 	};
 	struct rpc_create_args args = {
+		.net		= &init_net,
 		.protocol	= IPPROTO_UDP,
 		.address	= info->sap,
 		.addrsize	= info->salen,

fs/nfsd/Kconfig

@@ -29,6 +29,18 @@ config NFSD
 
 	  If unsure, say N.
 
+config NFSD_DEPRECATED
+	bool "Include support for deprecated syscall interface to NFSD"
+	depends on NFSD
+	default y
+	help
+	  The syscall interface to nfsd was obsoleted in 2.6.0 by a new
+	  filesystem based interface.  The old interface is due for removal
+	  in 2.6.40.  If you wish to remove the interface before then
+	  say N.
+
+	  In unsure, say Y.
+
 config NFSD_V2_ACL
 	bool
 	depends on NFSD

fs/nfsd/export.c

@@ -28,9 +28,6 @@
 typedef struct auth_domain	svc_client;
 typedef struct svc_export	svc_export;
 
-static void		exp_do_unexport(svc_export *unexp);
-static int		exp_verify_string(char *cp, int max);
-
 /*
  * We have two caches.
  * One maps client+vfsmnt+dentry to export options - the export map
@@ -802,6 +799,7 @@ exp_find_key(svc_client *clp, int fsid_type, u32 *fsidv, struct cache_req *reqp)
 	return ek;
 }
 
+#ifdef CONFIG_NFSD_DEPRECATED
 static int exp_set_key(svc_client *clp, int fsid_type, u32 *fsidv,
 		       struct svc_export *exp)
 {
@@ -852,6 +850,7 @@ exp_get_fsid_key(svc_client *clp, int fsid)
 
 	return exp_find_key(clp, FSID_NUM, fsidv, NULL);
 }
+#endif
 
 static svc_export *exp_get_by_name(svc_client *clp, const struct path *path,
 				     struct cache_req *reqp)
@@ -893,6 +892,7 @@ static struct svc_export *exp_parent(svc_client *clp, struct path *path)
 	return exp;
 }
 
+#ifdef CONFIG_NFSD_DEPRECATED
 /*
  * Hashtable locking. Write locks are placed only by user processes
  * wanting to modify export information.
@@ -925,6 +925,19 @@ exp_writeunlock(void)
 {
 	up_write(&hash_sem);
 }
+#else
+
+/* hash_sem not needed once deprecated interface is removed */
+void exp_readlock(void) {}
+static inline void exp_writelock(void){}
+void exp_readunlock(void) {}
+static inline void exp_writeunlock(void){}
+
+#endif
+
+#ifdef CONFIG_NFSD_DEPRECATED
+static void		exp_do_unexport(svc_export *unexp);
+static int		exp_verify_string(char *cp, int max);
 
 static void exp_fsid_unhash(struct svc_export *exp)
 {
@@ -935,10 +948,9 @@ static void exp_fsid_unhash(struct svc_export *exp)
 
 	ek = exp_get_fsid_key(exp->ex_client, exp->ex_fsid);
 	if (!IS_ERR(ek)) {
-		ek->h.expiry_time = get_seconds()-1;
+		sunrpc_invalidate(&ek->h, &svc_expkey_cache);
 		cache_put(&ek->h, &svc_expkey_cache);
 	}
-	svc_expkey_cache.nextcheck = get_seconds();
 }
 
 static int exp_fsid_hash(svc_client *clp, struct svc_export *exp)
@@ -973,10 +985,9 @@ static void exp_unhash(struct svc_export *exp)
 
 	ek = exp_get_key(exp->ex_client, inode->i_sb->s_dev, inode->i_ino);
 	if (!IS_ERR(ek)) {
-		ek->h.expiry_time = get_seconds()-1;
+		sunrpc_invalidate(&ek->h, &svc_expkey_cache);
 		cache_put(&ek->h, &svc_expkey_cache);
 	}
-	svc_expkey_cache.nextcheck = get_seconds();
 }
 	
 /*
@@ -1097,8 +1108,7 @@ exp_export(struct nfsctl_export *nxp)
 static void
 exp_do_unexport(svc_export *unexp)
 {
-	unexp->h.expiry_time = get_seconds()-1;
-	svc_export_cache.nextcheck = get_seconds();
+	sunrpc_invalidate(&unexp->h, &svc_export_cache);
 	exp_unhash(unexp);
 	exp_fsid_unhash(unexp);
 }
@@ -1150,6 +1160,7 @@ exp_unexport(struct nfsctl_export *nxp)
 	exp_writeunlock();
 	return err;
 }
+#endif /* CONFIG_NFSD_DEPRECATED */
 
 /*
  * Obtain the root fh on behalf of a client.
@@ -1459,25 +1470,43 @@ static void show_secinfo_flags(struct seq_file *m, int flags)
 	show_expflags(m, flags, NFSEXP_SECINFO_FLAGS);
 }
 
+static bool secinfo_flags_equal(int f, int g)
+{
+	f &= NFSEXP_SECINFO_FLAGS;
+	g &= NFSEXP_SECINFO_FLAGS;
+	return f == g;
+}
+
+static int show_secinfo_run(struct seq_file *m, struct exp_flavor_info **fp, struct exp_flavor_info *end)
+{
+	int flags;
+
+	flags = (*fp)->flags;
+	seq_printf(m, ",sec=%d", (*fp)->pseudoflavor);
+	(*fp)++;
+	while (*fp != end && secinfo_flags_equal(flags, (*fp)->flags)) {
+		seq_printf(m, ":%d", (*fp)->pseudoflavor);
+		(*fp)++;
+	}
+	return flags;
+}
+
 static void show_secinfo(struct seq_file *m, struct svc_export *exp)
 {
 	struct exp_flavor_info *f;
 	struct exp_flavor_info *end = exp->ex_flavors + exp->ex_nflavors;
-	int lastflags = 0, first = 0;
+	int flags;
 
 	if (exp->ex_nflavors == 0)
 		return;
-	for (f = exp->ex_flavors; f < end; f++) {
-		if (first || f->flags != lastflags) {
-			if (!first)
-				show_secinfo_flags(m, lastflags);
-			seq_printf(m, ",sec=%d", f->pseudoflavor);
-			lastflags = f->flags;
-		} else {
-			seq_printf(m, ":%d", f->pseudoflavor);
-		}
+	f = exp->ex_flavors;
+	flags = show_secinfo_run(m, &f, end);
+	if (!secinfo_flags_equal(flags, exp->ex_flags))
+		show_secinfo_flags(m, flags);
+	while (f != end) {
+		flags = show_secinfo_run(m, &f, end);
+		show_secinfo_flags(m, flags);
 	}
-	show_secinfo_flags(m, lastflags);
 }
 
 static void exp_flags(struct seq_file *m, int flag, int fsid,
@@ -1532,6 +1561,7 @@ const struct seq_operations nfs_exports_op = {
 	.show	= e_show,
 };
 
+#ifdef CONFIG_NFSD_DEPRECATED
 /*
  * Add or modify a client.
  * Change requests may involve the list of host addresses. The list of
@@ -1563,7 +1593,7 @@ exp_addclient(struct nfsctl_client *ncp)
 	/* Insert client into hashtable. */
 	for (i = 0; i < ncp->cl_naddr; i++) {
 		ipv6_addr_set_v4mapped(ncp->cl_addrlist[i].s_addr, &addr6);
-		auth_unix_add_addr(&addr6, dom);
+		auth_unix_add_addr(&init_net, &addr6, dom);
 	}
 	auth_unix_forget_old(dom);
 	auth_domain_put(dom);
@@ -1621,6 +1651,7 @@ exp_verify_string(char *cp, int max)
 	printk(KERN_NOTICE "nfsd: couldn't validate string %s\n", cp);
 	return 0;
 }
+#endif /* CONFIG_NFSD_DEPRECATED */
 
 /*
  * Initialize the exports module.

fs/nfsd/nfs4idmap.c

@@ -482,109 +482,26 @@ nfsd_idmap_shutdown(void)
 	cache_unregister(&nametoid_cache);
 }
 
-/*
- * Deferred request handling
- */
-
-struct idmap_defer_req {
-       struct cache_req		req;
-       struct cache_deferred_req deferred_req;
-       wait_queue_head_t	waitq;
-       atomic_t			count;
-};
-
-static inline void
-put_mdr(struct idmap_defer_req *mdr)
-{
-	if (atomic_dec_and_test(&mdr->count))
-		kfree(mdr);
-}
-
-static inline void
-get_mdr(struct idmap_defer_req *mdr)
-{
-	atomic_inc(&mdr->count);
-}
-
-static void
-idmap_revisit(struct cache_deferred_req *dreq, int toomany)
-{
-	struct idmap_defer_req *mdr =
-		container_of(dreq, struct idmap_defer_req, deferred_req);
-
-	wake_up(&mdr->waitq);
-	put_mdr(mdr);
-}
-
-static struct cache_deferred_req *
-idmap_defer(struct cache_req *req)
-{
-	struct idmap_defer_req *mdr =
-		container_of(req, struct idmap_defer_req, req);
-
-	mdr->deferred_req.revisit = idmap_revisit;
-	get_mdr(mdr);
-	return (&mdr->deferred_req);
-}
-
-static inline int
-do_idmap_lookup(struct ent *(*lookup_fn)(struct ent *), struct ent *key,
-		struct cache_detail *detail, struct ent **item,
-		struct idmap_defer_req *mdr)
-{
-	*item = lookup_fn(key);
-	if (!*item)
-		return -ENOMEM;
-	return cache_check(detail, &(*item)->h, &mdr->req);
-}
-
-static inline int
-do_idmap_lookup_nowait(struct ent *(*lookup_fn)(struct ent *),
-			struct ent *key, struct cache_detail *detail,
-			struct ent **item)
-{
-	int ret = -ENOMEM;
-
-	*item = lookup_fn(key);
-	if (!*item)
-		goto out_err;
-	ret = -ETIMEDOUT;
-	if (!test_bit(CACHE_VALID, &(*item)->h.flags)
-			|| (*item)->h.expiry_time < get_seconds()
-			|| detail->flush_time > (*item)->h.last_refresh)
-		goto out_put;
-	ret = -ENOENT;
-	if (test_bit(CACHE_NEGATIVE, &(*item)->h.flags))
-		goto out_put;
-	return 0;
-out_put:
-	cache_put(&(*item)->h, detail);
-out_err:
-	*item = NULL;
-	return ret;
-}
-
 static int
 idmap_lookup(struct svc_rqst *rqstp,
 		struct ent *(*lookup_fn)(struct ent *), struct ent *key,
 		struct cache_detail *detail, struct ent **item)
 {
-	struct idmap_defer_req *mdr;
 	int ret;
 
-	mdr = kzalloc(sizeof(*mdr), GFP_KERNEL);
-	if (!mdr)
+	*item = lookup_fn(key);
+	if (!*item)
 		return -ENOMEM;
-	atomic_set(&mdr->count, 1);
-	init_waitqueue_head(&mdr->waitq);
-	mdr->req.defer = idmap_defer;
-	ret = do_idmap_lookup(lookup_fn, key, detail, item, mdr);
-	if (ret == -EAGAIN) {
-		wait_event_interruptible_timeout(mdr->waitq,
-			test_bit(CACHE_VALID, &(*item)->h.flags), 1 * HZ);
-		ret = do_idmap_lookup_nowait(lookup_fn, key, detail, item);
+ retry:
+	ret = cache_check(detail, &(*item)->h, &rqstp->rq_chandle);
+
+	if (ret == -ETIMEDOUT) {
+		struct ent *prev_item = *item;
+		*item = lookup_fn(key);
+		if (*item != prev_item)
+			goto retry;
+		cache_put(&(*item)->h, detail);
 	}
-	put_mdr(mdr);
 	return ret;
 }
 

fs/nfsd/nfs4proc.c

@@ -1031,8 +1031,11 @@ nfsd4_proc_compound(struct svc_rqst *rqstp,
 	resp->cstate.session = NULL;
 	fh_init(&resp->cstate.current_fh, NFS4_FHSIZE);
 	fh_init(&resp->cstate.save_fh, NFS4_FHSIZE);
-	/* Use the deferral mechanism only for NFSv4.0 compounds */
-	rqstp->rq_usedeferral = (args->minorversion == 0);
+	/*
+	 * Don't use the deferral mechanism for NFSv4; compounds make it
+	 * too hard to avoid non-idempotency problems.
+	 */
+	rqstp->rq_usedeferral = 0;
 
 	/*
 	 * According to RFC3010, this takes precedence over all other errors.

fs/nfsd/nfs4xdr.c

@@ -1805,19 +1805,23 @@ nfsd4_encode_fattr(struct svc_fh *fhp, struct svc_export *exp,
 				goto out_nfserr;
 		}
 	}
+
+	if (bmval2) {
 		if ((buflen -= 16) < 0)
 			goto out_resource;
-
-	if (unlikely(bmval2)) {
 		WRITE32(3);
 		WRITE32(bmval0);
 		WRITE32(bmval1);
 		WRITE32(bmval2);
-	} else if (likely(bmval1)) {
+	} else if (bmval1) {
+		if ((buflen -= 12) < 0)
+			goto out_resource;
 		WRITE32(2);
 		WRITE32(bmval0);
 		WRITE32(bmval1);
 	} else {
+		if ((buflen -= 8) < 0)
+			goto out_resource;
 		WRITE32(1);
 		WRITE32(bmval0);
 	}
@@ -1828,15 +1832,17 @@ nfsd4_encode_fattr(struct svc_fh *fhp, struct svc_export *exp,
 		u32 word1 = nfsd_suppattrs1(minorversion);
 		u32 word2 = nfsd_suppattrs2(minorversion);
 
-		if ((buflen -= 12) < 0)
-			goto out_resource;
 		if (!aclsupport)
 			word0 &= ~FATTR4_WORD0_ACL;
 		if (!word2) {
+			if ((buflen -= 12) < 0)
+				goto out_resource;
 			WRITE32(2);
 			WRITE32(word0);
 			WRITE32(word1);
 		} else {
+			if ((buflen -= 16) < 0)
+				goto out_resource;
 			WRITE32(3);
 			WRITE32(word0);
 			WRITE32(word1);

fs/nfsd/nfsctl.c

@@ -22,6 +22,7 @@
  */
 enum {
 	NFSD_Root = 1,
+#ifdef CONFIG_NFSD_DEPRECATED
 	NFSD_Svc,
 	NFSD_Add,
 	NFSD_Del,
@@ -29,6 +30,7 @@ enum {
 	NFSD_Unexport,
 	NFSD_Getfd,
 	NFSD_Getfs,
+#endif
 	NFSD_List,
 	NFSD_Export_features,
 	NFSD_Fh,
@@ -54,6 +56,7 @@ enum {
 /*
  * write() for these nodes.
  */
+#ifdef CONFIG_NFSD_DEPRECATED
 static ssize_t write_svc(struct file *file, char *buf, size_t size);
 static ssize_t write_add(struct file *file, char *buf, size_t size);
 static ssize_t write_del(struct file *file, char *buf, size_t size);
@@ -61,6 +64,7 @@ static ssize_t write_export(struct file *file, char *buf, size_t size);
 static ssize_t write_unexport(struct file *file, char *buf, size_t size);
 static ssize_t write_getfd(struct file *file, char *buf, size_t size);
 static ssize_t write_getfs(struct file *file, char *buf, size_t size);
+#endif
 static ssize_t write_filehandle(struct file *file, char *buf, size_t size);
 static ssize_t write_unlock_ip(struct file *file, char *buf, size_t size);
 static ssize_t write_unlock_fs(struct file *file, char *buf, size_t size);
@@ -76,6 +80,7 @@ static ssize_t write_recoverydir(struct file *file, char *buf, size_t size);
 #endif
 
 static ssize_t (*write_op[])(struct file *, char *, size_t) = {
+#ifdef CONFIG_NFSD_DEPRECATED
 	[NFSD_Svc] = write_svc,
 	[NFSD_Add] = write_add,
 	[NFSD_Del] = write_del,
@@ -83,6 +88,7 @@ static ssize_t (*write_op[])(struct file *, char *, size_t) = {
 	[NFSD_Unexport] = write_unexport,
 	[NFSD_Getfd] = write_getfd,
 	[NFSD_Getfs] = write_getfs,
+#endif
 	[NFSD_Fh] = write_filehandle,
 	[NFSD_FO_UnlockIP] = write_unlock_ip,
 	[NFSD_FO_UnlockFS] = write_unlock_fs,
@@ -121,6 +127,14 @@ static ssize_t nfsctl_transaction_write(struct file *file, const char __user *bu
 
 static ssize_t nfsctl_transaction_read(struct file *file, char __user *buf, size_t size, loff_t *pos)
 {
+	static int warned;
+	if (file->f_dentry->d_name.name[0] == '.' && !warned) {
+		printk(KERN_INFO
+		       "Warning: \"%s\" uses deprecated NFSD interface: %s."
+		       "  This will be removed in 2.6.40\n",
+		       current->comm, file->f_dentry->d_name.name);
+		warned = 1;
+	}
 	if (! file->private_data) {
 		/* An attempt to read a transaction file without writing
 		 * causes a 0-byte write so that the file can return
@@ -187,6 +201,7 @@ static const struct file_operations pool_stats_operations = {
  * payload - write methods
  */
 
+#ifdef CONFIG_NFSD_DEPRECATED
 /**
  * write_svc - Start kernel's NFSD server
  *
@@ -402,7 +417,7 @@ static ssize_t write_getfs(struct file *file, char *buf, size_t size)
 
 	ipv6_addr_set_v4mapped(sin->sin_addr.s_addr, &in6);
 
-	clp = auth_unix_lookup(&in6);
+	clp = auth_unix_lookup(&init_net, &in6);
 	if (!clp)
 		err = -EPERM;
 	else {
@@ -465,7 +480,7 @@ static ssize_t write_getfd(struct file *file, char *buf, size_t size)
 
 	ipv6_addr_set_v4mapped(sin->sin_addr.s_addr, &in6);
 
-	clp = auth_unix_lookup(&in6);
+	clp = auth_unix_lookup(&init_net, &in6);
 	if (!clp)
 		err = -EPERM;
 	else {
@@ -482,6 +497,7 @@ static ssize_t write_getfd(struct file *file, char *buf, size_t size)
  out:
 	return err;
 }
+#endif /* CONFIG_NFSD_DEPRECATED */
 
 /**
  * write_unlock_ip - Release all locks used by a client
@@ -1000,12 +1016,12 @@ static ssize_t __write_ports_addxprt(char *buf)
 	if (err != 0)
 		return err;
 
-	err = svc_create_xprt(nfsd_serv, transport,
+	err = svc_create_xprt(nfsd_serv, transport, &init_net,
 				PF_INET, port, SVC_SOCK_ANONYMOUS);
 	if (err < 0)
 		goto out_err;
 
-	err = svc_create_xprt(nfsd_serv, transport,
+	err = svc_create_xprt(nfsd_serv, transport, &init_net,
 				PF_INET6, port, SVC_SOCK_ANONYMOUS);
 	if (err < 0 && err != -EAFNOSUPPORT)
 		goto out_close;
@@ -1356,6 +1372,7 @@ static ssize_t write_recoverydir(struct file *file, char *buf, size_t size)
 static int nfsd_fill_super(struct super_block * sb, void * data, int silent)
 {
 	static struct tree_descr nfsd_files[] = {
+#ifdef CONFIG_NFSD_DEPRECATED
 		[NFSD_Svc] = {".svc", &transaction_ops, S_IWUSR},
 		[NFSD_Add] = {".add", &transaction_ops, S_IWUSR},
 		[NFSD_Del] = {".del", &transaction_ops, S_IWUSR},
@@ -1363,6 +1380,7 @@ static int nfsd_fill_super(struct super_block * sb, void * data, int silent)
 		[NFSD_Unexport] = {".unexport", &transaction_ops, S_IWUSR},
 		[NFSD_Getfd] = {".getfd", &transaction_ops, S_IWUSR|S_IRUSR},
 		[NFSD_Getfs] = {".getfs", &transaction_ops, S_IWUSR|S_IRUSR},
+#endif
 		[NFSD_List] = {"exports", &exports_operations, S_IRUGO},
 		[NFSD_Export_features] = {"export_features",
 					&export_features_operations, S_IRUGO},

fs/nfsd/nfsd.h

@@ -249,7 +249,7 @@ extern time_t nfsd4_grace;
 #define	COMPOUND_SLACK_SPACE		140    /* OP_GETFH */
 #define COMPOUND_ERR_SLACK_SPACE	12     /* OP_SETATTR */
 
-#define NFSD_LAUNDROMAT_MINTIMEOUT      10   /* seconds */
+#define NFSD_LAUNDROMAT_MINTIMEOUT      1   /* seconds */
 
 /*
  * The following attributes are currently not supported by the NFSv4 server:

fs/nfsd/nfssvc.c

@@ -16,6 +16,7 @@
 #include <linux/lockd/bind.h>
 #include <linux/nfsacl.h>
 #include <linux/seq_file.h>
+#include <net/net_namespace.h>
 #include "nfsd.h"
 #include "cache.h"
 #include "vfs.h"
@@ -186,12 +187,12 @@ static int nfsd_init_socks(int port)
 	if (!list_empty(&nfsd_serv->sv_permsocks))
 		return 0;
 
-	error = svc_create_xprt(nfsd_serv, "udp", PF_INET, port,
+	error = svc_create_xprt(nfsd_serv, "udp", &init_net, PF_INET, port,
 					SVC_SOCK_DEFAULTS);
 	if (error < 0)
 		return error;
 
-	error = svc_create_xprt(nfsd_serv, "tcp", PF_INET, port,
+	error = svc_create_xprt(nfsd_serv, "tcp", &init_net, PF_INET, port,
 					SVC_SOCK_DEFAULTS);
 	if (error < 0)
 		return error;

fs/nfsd/state.h

@@ -35,6 +35,7 @@
 #ifndef _NFSD4_STATE_H
 #define _NFSD4_STATE_H
 
+#include <linux/sunrpc/svc_xprt.h>
 #include <linux/nfsd/nfsfh.h>
 #include "nfsfh.h"
 
@@ -64,19 +65,12 @@ typedef struct {
 	(s)->si_fileid, \
 	(s)->si_generation
 
-struct nfsd4_cb_sequence {
-	/* args/res */
-	u32			cbs_minorversion;
-	struct nfs4_client	*cbs_clp;
-};
-
-struct nfs4_rpc_args {
-	void				*args_op;
-	struct nfsd4_cb_sequence	args_seq;
-};
-
 struct nfsd4_callback {
-	struct nfs4_rpc_args cb_args;
+	void *cb_op;
+	struct nfs4_client *cb_clp;
+	u32 cb_minorversion;
+	struct rpc_message cb_msg;
+	const struct rpc_call_ops *cb_ops;
 	struct work_struct cb_work;
 };
 
@@ -91,7 +85,6 @@ struct nfs4_delegation {
 	u32			dl_type;
 	time_t			dl_time;
 /* For recall: */
-	u32			dl_ident;
 	stateid_t		dl_stateid;
 	struct knfsd_fh		dl_fh;
 	int			dl_retries;
@@ -103,8 +96,8 @@ struct nfs4_cb_conn {
 	/* SETCLIENTID info */
 	struct sockaddr_storage	cb_addr;
 	size_t			cb_addrlen;
-	u32                     cb_prog;
-	u32			cb_minorversion;
+	u32                     cb_prog; /* used only in 4.0 case;
+					    per-session otherwise */
 	u32                     cb_ident;	/* minorversion 0 only */
 	struct svc_xprt		*cb_xprt;	/* minorversion 1 only */
 };
@@ -160,6 +153,15 @@ struct nfsd4_clid_slot {
 	struct nfsd4_create_session	sl_cr_ses;
 };
 
+struct nfsd4_conn {
+	struct list_head cn_persession;
+	struct svc_xprt *cn_xprt;
+	struct svc_xpt_user cn_xpt_user;
+	struct nfsd4_session *cn_session;
+/* CDFC4_FORE, CDFC4_BACK: */
+	unsigned char cn_flags;
+};
+
 struct nfsd4_session {
 	struct kref		se_ref;
 	struct list_head	se_hash;	/* hash by sessionid */
@@ -169,6 +171,9 @@ struct nfsd4_session {
 	struct nfs4_sessionid	se_sessionid;
 	struct nfsd4_channel_attrs se_fchannel;
 	struct nfsd4_channel_attrs se_bchannel;
+	struct list_head	se_conns;
+	u32			se_cb_prog;
+	u32			se_cb_seq_nr;
 	struct nfsd4_slot	*se_slots[];	/* forward channel slots */
 };
 
@@ -221,24 +226,32 @@ struct nfs4_client {
 	clientid_t		cl_clientid;	/* generated by server */
 	nfs4_verifier		cl_confirm;	/* generated by server */
 	u32			cl_firststate;	/* recovery dir creation */
+	u32			cl_minorversion;
 
 	/* for v4.0 and v4.1 callbacks: */
 	struct nfs4_cb_conn	cl_cb_conn;
+#define NFSD4_CLIENT_CB_UPDATE	1
+#define NFSD4_CLIENT_KILL	2
+	unsigned long		cl_cb_flags;
 	struct rpc_clnt		*cl_cb_client;
+	u32			cl_cb_ident;
 	atomic_t		cl_cb_set;
+	struct nfsd4_callback	cl_cb_null;
+	struct nfsd4_session	*cl_cb_session;
+
+	/* for all client information that callback code might need: */
+	spinlock_t		cl_lock;
 
 	/* for nfs41 */
 	struct list_head	cl_sessions;
 	struct nfsd4_clid_slot	cl_cs_slot;	/* create_session slot */
 	u32			cl_exchange_flags;
-	struct nfs4_sessionid	cl_sessionid;
 	/* number of rpc's in progress over an associated session: */
 	atomic_t		cl_refcount;
 
 	/* for nfs41 callbacks */
 	/* We currently support a single back channel with a single slot */
 	unsigned long		cl_cb_slot_busy;
-	u32			cl_cb_seq_nr;
 	struct rpc_wait_queue	cl_cb_waitq;	/* backchannel callers may */
 						/* wait here for slots */
 };
@@ -440,12 +453,13 @@ extern int nfs4_in_grace(void);
 extern __be32 nfs4_check_open_reclaim(clientid_t *clid);
 extern void nfs4_free_stateowner(struct kref *kref);
 extern int set_callback_cred(void);
-extern void nfsd4_probe_callback(struct nfs4_client *clp, struct nfs4_cb_conn *);
+extern void nfsd4_probe_callback(struct nfs4_client *clp);
+extern void nfsd4_change_callback(struct nfs4_client *clp, struct nfs4_cb_conn *);
 extern void nfsd4_do_callback_rpc(struct work_struct *);
 extern void nfsd4_cb_recall(struct nfs4_delegation *dp);
 extern int nfsd4_create_callback_queue(void);
 extern void nfsd4_destroy_callback_queue(void);
-extern void nfsd4_set_callback_client(struct nfs4_client *, struct rpc_clnt *);
+extern void nfsd4_shutdown_callback(struct nfs4_client *);
 extern void nfs4_put_delegation(struct nfs4_delegation *dp);
 extern __be32 nfs4_make_rec_clidname(char *clidname, struct xdr_netobj *clname);
 extern void nfsd4_init_recdir(char *recdir_name);

include/linux/net.h

@@ -229,6 +229,8 @@ enum {
 extern int	     sock_wake_async(struct socket *sk, int how, int band);
 extern int	     sock_register(const struct net_proto_family *fam);
 extern void	     sock_unregister(int family);
+extern int	     __sock_create(struct net *net, int family, int type, int proto,
+				 struct socket **res, int kern);
 extern int	     sock_create(int family, int type, int proto,
 				 struct socket **res);
 extern int	     sock_create_kern(int family, int type, int proto,

include/linux/nfs4.h

@@ -63,6 +63,9 @@
 #define NFS4_SHARE_SIGNAL_DELEG_WHEN_RESRC_AVAIL	0x10000
 #define NFS4_SHARE_PUSH_DELEG_WHEN_UNCONTENDED		0x20000
 
+#define NFS4_CDFC4_FORE	0x1
+#define NFS4_CDFC4_BACK 0x2
+
 #define NFS4_SET_TO_SERVER_TIME	0
 #define NFS4_SET_TO_CLIENT_TIME	1
 

include/linux/sunrpc/auth.h

@@ -122,8 +122,8 @@ extern const struct rpc_authops	authnull_ops;
 int __init		rpc_init_authunix(void);
 int __init		rpc_init_generic_auth(void);
 int __init		rpcauth_init_module(void);
-void __exit		rpcauth_remove_module(void);
-void __exit		rpc_destroy_generic_auth(void);
+void			rpcauth_remove_module(void);
+void			rpc_destroy_generic_auth(void);
 void 			rpc_destroy_authunix(void);
 
 struct rpc_cred *	rpc_lookup_cred(void);

include/linux/sunrpc/cache.h

@@ -125,12 +125,15 @@ struct cache_detail {
  */
 struct cache_req {
 	struct cache_deferred_req *(*defer)(struct cache_req *req);
+	int thread_wait;  /* How long (jiffies) we can block the
+			   * current thread to wait for updates.
+			   */
 };
 /* this must be embedded in a deferred_request that is being
  * delayed awaiting cache-fill
  */
 struct cache_deferred_req {
-	struct list_head	hash;	/* on hash chain */
+	struct hlist_node	hash;	/* on hash chain */
 	struct list_head	recent; /* on fifo */
 	struct cache_head	*item;  /* cache item we wait on */
 	void			*owner; /* we might need to discard all defered requests
@@ -194,7 +197,9 @@ extern void cache_purge(struct cache_detail *detail);
 #define NEVER (0x7FFFFFFF)
 extern void __init cache_initialize(void);
 extern int cache_register(struct cache_detail *cd);
+extern int cache_register_net(struct cache_detail *cd, struct net *net);
 extern void cache_unregister(struct cache_detail *cd);
+extern void cache_unregister_net(struct cache_detail *cd, struct net *net);
 
 extern int sunrpc_cache_register_pipefs(struct dentry *parent, const char *,
 					mode_t, struct cache_detail *);
@@ -218,14 +223,42 @@ static inline int get_int(char **bpp, int *anint)
 	return 0;
 }
 
+/*
+ * timestamps kept in the cache are expressed in seconds
+ * since boot.  This is the best for measuring differences in
+ * real time.
+ */
+static inline time_t seconds_since_boot(void)
+{
+	struct timespec boot;
+	getboottime(&boot);
+	return get_seconds() - boot.tv_sec;
+}
+
+static inline time_t convert_to_wallclock(time_t sinceboot)
+{
+	struct timespec boot;
+	getboottime(&boot);
+	return boot.tv_sec + sinceboot;
+}
+
 static inline time_t get_expiry(char **bpp)
 {
 	int rv;
+	struct timespec boot;
+
 	if (get_int(bpp, &rv))
 		return 0;
 	if (rv < 0)
 		return 0;
-	return rv;
+	getboottime(&boot);
+	return rv - boot.tv_sec;
 }
 
+static inline void sunrpc_invalidate(struct cache_head *h,
+				     struct cache_detail *detail)
+{
+	h->expiry_time = seconds_since_boot() - 1;
+	detail->nextcheck = seconds_since_boot();
+}
 #endif /*  _LINUX_SUNRPC_CACHE_H_ */

include/linux/sunrpc/clnt.h

@@ -102,6 +102,7 @@ struct rpc_procinfo {
 #ifdef __KERNEL__
 
 struct rpc_create_args {
+	struct net		*net;
 	int			protocol;
 	struct sockaddr		*address;
 	size_t			addrsize;

include/linux/sunrpc/gss_spkm3.h

-/*
- *  linux/include/linux/sunrpc/gss_spkm3.h
- *
- *  Copyright (c) 2000 The Regents of the University of Michigan.
- *  All rights reserved.
- *
- *  Andy Adamson   <andros@umich.edu>
- */
-
-#include <linux/sunrpc/auth_gss.h>
-#include <linux/sunrpc/gss_err.h>
-#include <linux/sunrpc/gss_asn1.h>
-
-struct spkm3_ctx {
-	struct xdr_netobj	ctx_id;  /* per message context id */
-	int			endtime; /* endtime of the context */
-	struct xdr_netobj	mech_used;
-	unsigned int		ret_flags ;
-	struct xdr_netobj	conf_alg;
-	struct xdr_netobj	derived_conf_key;
-	struct xdr_netobj	intg_alg;
-	struct xdr_netobj 	derived_integ_key;
-};
-
-/* OIDs declarations for K-ALG, I-ALG, C-ALG, and OWF-ALG */
-extern const struct xdr_netobj hmac_md5_oid;
-extern const struct xdr_netobj cast5_cbc_oid;
-
-/* SPKM InnerContext Token types */
-
-#define SPKM_ERROR_TOK	3
-#define SPKM_MIC_TOK	4
-#define SPKM_WRAP_TOK	5
-#define SPKM_DEL_TOK	6
-
-u32 spkm3_make_token(struct spkm3_ctx *ctx, struct xdr_buf * text, struct xdr_netobj * token, int toktype);
-
-u32 spkm3_read_token(struct spkm3_ctx *ctx, struct xdr_netobj *read_token, struct xdr_buf *message_buffer, int toktype);
-
-#define CKSUMTYPE_RSA_MD5            0x0007
-#define CKSUMTYPE_HMAC_MD5           0x0008
-
-s32 make_spkm3_checksum(s32 cksumtype, struct xdr_netobj *key, char *header,
-		unsigned int hdrlen, struct xdr_buf *body,
-		unsigned int body_offset, struct xdr_netobj *cksum);
-void 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);
-void spkm3_mic_header(unsigned char **hdrbuf, unsigned int *hdrlen, 
-                   unsigned char *ctxhdr, int elen, int zbit);
-void spkm3_make_mic_token(unsigned  char **tokp, int toklen, 
-                   struct xdr_netobj *mic_hdr,
-                   struct xdr_netobj *md5cksum, int md5elen, int md5zbit);
-u32 spkm3_verify_mic_token(unsigned char **tokp, int *mic_hdrlen, 
-                   unsigned char **cksum);

include/linux/sunrpc/stats.h

@@ -38,8 +38,21 @@ struct svc_stat {
 				rpcbadclnt;
 };
 
-void			rpc_proc_init(void);
-void			rpc_proc_exit(void);
+struct net;
+#ifdef CONFIG_PROC_FS
+int			rpc_proc_init(struct net *);
+void			rpc_proc_exit(struct net *);
+#else
+static inline int rpc_proc_init(struct net *net)
+{
+	return 0;
+}
+
+static inline void rpc_proc_exit(struct net *net)
+{
+}
+#endif
+
 #ifdef MODULE
 void			rpc_modcount(struct inode *, int);
 #endif
@@ -54,9 +67,6 @@ void			svc_proc_unregister(const char *);
 
 void			svc_seq_show(struct seq_file *,
 				     const struct svc_stat *);
-
-extern struct proc_dir_entry	*proc_net_rpc;
-
 #else
 
 static inline struct proc_dir_entry *rpc_proc_register(struct rpc_stat *s) { return NULL; }
@@ -69,9 +79,6 @@ static inline void svc_proc_unregister(const char *p) {}
 
 static inline void svc_seq_show(struct seq_file *seq,
 				const struct svc_stat *st) {}
-
-#define proc_net_rpc NULL
-
 #endif
 
 #endif /* _LINUX_SUNRPC_STATS_H */

include/linux/sunrpc/svc_xprt.h

@@ -12,6 +12,7 @@
 
 struct svc_xprt_ops {
 	struct svc_xprt	*(*xpo_create)(struct svc_serv *,
+				       struct net *net,
 				       struct sockaddr *, int,
 				       int);
 	struct svc_xprt	*(*xpo_accept)(struct svc_xprt *);
@@ -32,6 +33,16 @@ struct svc_xprt_class {
 	u32			xcl_max_payload;
 };
 
+/*
+ * This is embedded in an object that wants a callback before deleting
+ * an xprt; intended for use by NFSv4.1, which needs to know when a
+ * client's tcp connection (and hence possibly a backchannel) goes away.
+ */
+struct svc_xpt_user {
+	struct list_head list;
+	void (*callback)(struct svc_xpt_user *);
+};
+
 struct svc_xprt {
 	struct svc_xprt_class	*xpt_class;
 	struct svc_xprt_ops	*xpt_ops;
@@ -66,14 +77,31 @@ struct svc_xprt {
 	struct sockaddr_storage	xpt_remote;	/* remote peer's address */
 	size_t			xpt_remotelen;	/* length of address */
 	struct rpc_wait_queue	xpt_bc_pending;	/* backchannel wait queue */
+	struct list_head	xpt_users;	/* callbacks on free */
+
+	struct net		*xpt_net;
 };
 
+static inline void register_xpt_user(struct svc_xprt *xpt, struct svc_xpt_user *u)
+{
+	spin_lock(&xpt->xpt_lock);
+	list_add(&u->list, &xpt->xpt_users);
+	spin_unlock(&xpt->xpt_lock);
+}
+
+static inline void unregister_xpt_user(struct svc_xprt *xpt, struct svc_xpt_user *u)
+{
+	spin_lock(&xpt->xpt_lock);
+	list_del_init(&u->list);
+	spin_unlock(&xpt->xpt_lock);
+}
+
 int	svc_reg_xprt_class(struct svc_xprt_class *);
 void	svc_unreg_xprt_class(struct svc_xprt_class *);
 void	svc_xprt_init(struct svc_xprt_class *, struct svc_xprt *,
 		      struct svc_serv *);
-int	svc_create_xprt(struct svc_serv *, const char *, const int,
-			const unsigned short, int);
+int	svc_create_xprt(struct svc_serv *, const char *, struct net *,
+			const int, const unsigned short, int);
 void	svc_xprt_enqueue(struct svc_xprt *xprt);
 void	svc_xprt_received(struct svc_xprt *);
 void	svc_xprt_put(struct svc_xprt *xprt);

include/linux/sunrpc/svcauth.h

@@ -108,10 +108,15 @@ struct auth_ops {
 #define	SVC_NEGATIVE	4
 #define	SVC_OK		5
 #define	SVC_DROP	6
-#define	SVC_DENIED	7
-#define	SVC_PENDING	8
-#define	SVC_COMPLETE	9
+#define	SVC_CLOSE	7	/* Like SVC_DROP, but request is definitely
+				 * lost so if there is a tcp connection, it
+				 * should be closed
+				 */
+#define	SVC_DENIED	8
+#define	SVC_PENDING	9
+#define	SVC_COMPLETE	10
 
+struct svc_xprt;
 
 extern int	svc_authenticate(struct svc_rqst *rqstp, __be32 *authp);
 extern int	svc_authorise(struct svc_rqst *rqstp);
@@ -121,13 +126,13 @@ extern void	svc_auth_unregister(rpc_authflavor_t flavor);
 
 extern struct auth_domain *unix_domain_find(char *name);
 extern void auth_domain_put(struct auth_domain *item);
-extern int auth_unix_add_addr(struct in6_addr *addr, struct auth_domain *dom);
+extern int auth_unix_add_addr(struct net *net, struct in6_addr *addr, struct auth_domain *dom);
 extern struct auth_domain *auth_domain_lookup(char *name, struct auth_domain *new);
 extern struct auth_domain *auth_domain_find(char *name);
-extern struct auth_domain *auth_unix_lookup(struct in6_addr *addr);
+extern struct auth_domain *auth_unix_lookup(struct net *net, struct in6_addr *addr);
 extern int auth_unix_forget_old(struct auth_domain *dom);
 extern void svcauth_unix_purge(void);
-extern void svcauth_unix_info_release(void *);
+extern void svcauth_unix_info_release(struct svc_xprt *xpt);
 extern int svcauth_unix_set_client(struct svc_rqst *rqstp);
 
 static inline unsigned long hash_str(char *name, int bits)

include/linux/sunrpc/xprt.h

@@ -224,6 +224,7 @@ struct rpc_xprt {
 					bklog_u;	/* backlog queue utilization */
 	} stat;
 
+	struct net		*xprt_net;
 	const char		*address_strings[RPC_DISPLAY_MAX];
 };
 
@@ -249,6 +250,7 @@ static inline int bc_prealloc(struct rpc_rqst *req)
 
 struct xprt_create {
 	int			ident;		/* XPRT_TRANSPORT identifier */
+	struct net *		net;
 	struct sockaddr *	srcaddr;	/* optional local address */
 	struct sockaddr *	dstaddr;	/* remote peer address */
 	size_t			addrlen;
@@ -280,6 +282,8 @@ void			xprt_release_xprt_cong(struct rpc_xprt *xprt, struct rpc_task *task);
 void			xprt_release(struct rpc_task *task);
 struct rpc_xprt *	xprt_get(struct rpc_xprt *xprt);
 void			xprt_put(struct rpc_xprt *xprt);
+struct rpc_xprt *	xprt_alloc(struct net *net, int size, int max_req);
+void			xprt_free(struct rpc_xprt *);
 
 static inline __be32 *xprt_skip_transport_header(struct rpc_xprt *xprt, __be32 *p)
 {

net/socket.c

@@ -1145,7 +1145,7 @@ int sock_wake_async(struct socket *sock, int how, int band)
 }
 EXPORT_SYMBOL(sock_wake_async);
 
-static int __sock_create(struct net *net, int family, int type, int protocol,
+int __sock_create(struct net *net, int family, int type, int protocol,
 			 struct socket **res, int kern)
 {
 	int err;
@@ -1257,6 +1257,7 @@ static int __sock_create(struct net *net, int family, int type, int protocol,
 	rcu_read_unlock();
 	goto out_sock_release;
 }
+EXPORT_SYMBOL(__sock_create);
 
 int sock_create(int family, int type, int protocol, struct socket **res)
 {

net/sunrpc/Kconfig

@@ -36,22 +36,3 @@ config RPCSEC_GSS_KRB5
 	  Kerberos support should be installed.
 
 	  If unsure, say Y.
-
-config RPCSEC_GSS_SPKM3
-	tristate "Secure RPC: SPKM3 mechanism (EXPERIMENTAL)"
-	depends on SUNRPC && EXPERIMENTAL
-	select SUNRPC_GSS
-	select CRYPTO
-	select CRYPTO_MD5
-	select CRYPTO_DES
-	select CRYPTO_CAST5
-	select CRYPTO_CBC
-	help
-	  Choose Y here to enable Secure RPC using the SPKM3 public key
-	  GSS-API mechanism (RFC 2025).
-
-	  Secure RPC calls with SPKM3 require an auxiliary userspace
-	  daemon which may be found in the Linux nfs-utils package
-	  available from http://linux-nfs.org/.
-
-	  If unsure, say N.

net/sunrpc/auth.c

@@ -658,7 +658,7 @@ int __init rpcauth_init_module(void)
 	return err;
 }
 
-void __exit rpcauth_remove_module(void)
+void rpcauth_remove_module(void)
 {
 	rpc_destroy_authunix();
 	rpc_destroy_generic_auth();

net/sunrpc/auth_generic.c

@@ -158,7 +158,7 @@ int __init rpc_init_generic_auth(void)
 	return rpcauth_init_credcache(&generic_auth);
 }
 
-void __exit rpc_destroy_generic_auth(void)
+void rpc_destroy_generic_auth(void)
 {
 	rpcauth_destroy_credcache(&generic_auth);
 }

net/sunrpc/auth_gss/Makefile

@@ -11,8 +11,3 @@ obj-$(CONFIG_RPCSEC_GSS_KRB5) += rpcsec_gss_krb5.o
 
 rpcsec_gss_krb5-objs := gss_krb5_mech.o gss_krb5_seal.o gss_krb5_unseal.o \
 	gss_krb5_seqnum.o gss_krb5_wrap.o gss_krb5_crypto.o gss_krb5_keys.o
-
-obj-$(CONFIG_RPCSEC_GSS_SPKM3) += rpcsec_gss_spkm3.o
-
-rpcsec_gss_spkm3-objs := gss_spkm3_mech.o gss_spkm3_seal.o gss_spkm3_unseal.o \
-	gss_spkm3_token.o

net/sunrpc/auth_gss/gss_spkm3_mech.c

-/*
- *  linux/net/sunrpc/gss_spkm3_mech.c
- *
- *  Copyright (c) 2003 The Regents of the University of Michigan.
- *  All rights reserved.
- *
- *  Andy Adamson <andros@umich.edu>
- *  J. Bruce Fields <bfields@umich.edu>
- *
- *  Redistribution and use in source and binary forms, with or without
- *  modification, are permitted provided that the following conditions
- *  are met:
- *
- *  1. Redistributions of source code must retain the above copyright
- *     notice, this list of conditions and the following disclaimer.
- *  2. Redistributions in binary form must reproduce the above copyright
- *     notice, this list of conditions and the following disclaimer in the
- *     documentation and/or other materials provided with the distribution.
- *  3. Neither the name of the University nor the names of its
- *     contributors may be used to endorse or promote products derived
- *     from this software without specific prior written permission.
- *
- *  THIS SOFTWARE IS PROVIDED ``AS IS'' AND ANY EXPRESS OR IMPLIED
- *  WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF
- *  MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
- *  DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
- *  FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- *  CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- *  SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR
- *  BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF
- *  LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING
- *  NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
- *  SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
- *
- */
-
-#include <linux/err.h>
-#include <linux/module.h>
-#include <linux/init.h>
-#include <linux/types.h>
-#include <linux/slab.h>
-#include <linux/sunrpc/auth.h>
-#include <linux/in.h>
-#include <linux/sunrpc/svcauth_gss.h>
-#include <linux/sunrpc/gss_spkm3.h>
-#include <linux/sunrpc/xdr.h>
-#include <linux/crypto.h>
-
-#ifdef RPC_DEBUG
-# define RPCDBG_FACILITY	RPCDBG_AUTH
-#endif
-
-static const void *
-simple_get_bytes(const void *p, const void *end, void *res, int len)
-{
-	const void *q = (const void *)((const char *)p + len);
-	if (unlikely(q > end || q < p))
-		return ERR_PTR(-EFAULT);
-	memcpy(res, p, len);
-	return q;
-}
-
-static const void *
-simple_get_netobj(const void *p, const void *end, struct xdr_netobj *res)
-{
-	const void *q;
-	unsigned int len;
-	p = simple_get_bytes(p, end, &len, sizeof(len));
-	if (IS_ERR(p))
-		return p;
-	res->len = len;
-	if (len == 0) {
-		res->data = NULL;
-		return p;
-	}
-	q = (const void *)((const char *)p + len);
-	if (unlikely(q > end || q < p))
-		return ERR_PTR(-EFAULT);
-	res->data = kmemdup(p, len, GFP_NOFS);
-	if (unlikely(res->data == NULL))
-		return ERR_PTR(-ENOMEM);
-	return q;
-}
-
-static int
-gss_import_sec_context_spkm3(const void *p, size_t len,
-				struct gss_ctx *ctx_id,
-				gfp_t gfp_mask)
-{
-	const void *end = (const void *)((const char *)p + len);
-	struct	spkm3_ctx *ctx;
-	int	version;
-
-	if (!(ctx = kzalloc(sizeof(*ctx), gfp_mask)))
-		goto out_err;
-
-	p = simple_get_bytes(p, end, &version, sizeof(version));
-	if (IS_ERR(p))
-		goto out_err_free_ctx;
-	if (version != 1) {
-		dprintk("RPC:       unknown spkm3 token format: "
-				"obsolete nfs-utils?\n");
-		p = ERR_PTR(-EINVAL);
-		goto out_err_free_ctx;
-	}
-
-	p = simple_get_netobj(p, end, &ctx->ctx_id);
-	if (IS_ERR(p))
-		goto out_err_free_ctx;
-
-	p = simple_get_bytes(p, end, &ctx->endtime, sizeof(ctx->endtime));
-	if (IS_ERR(p))
-		goto out_err_free_ctx_id;
-
-	p = simple_get_netobj(p, end, &ctx->mech_used);
-	if (IS_ERR(p))
-		goto out_err_free_ctx_id;
-
-	p = simple_get_bytes(p, end, &ctx->ret_flags, sizeof(ctx->ret_flags));
-	if (IS_ERR(p))
-		goto out_err_free_mech;
-
-	p = simple_get_netobj(p, end, &ctx->conf_alg);
-	if (IS_ERR(p))
-		goto out_err_free_mech;
-
-	p = simple_get_netobj(p, end, &ctx->derived_conf_key);
-	if (IS_ERR(p))
-		goto out_err_free_conf_alg;
-
-	p = simple_get_netobj(p, end, &ctx->intg_alg);
-	if (IS_ERR(p))
-		goto out_err_free_conf_key;
-
-	p = simple_get_netobj(p, end, &ctx->derived_integ_key);
-	if (IS_ERR(p))
-		goto out_err_free_intg_alg;
-
-	if (p != end) {
-		p = ERR_PTR(-EFAULT);
-		goto out_err_free_intg_key;
-	}
-
-	ctx_id->internal_ctx_id = ctx;
-
-	dprintk("RPC:       Successfully imported new spkm context.\n");
-	return 0;
-
-out_err_free_intg_key:
-	kfree(ctx->derived_integ_key.data);
-out_err_free_intg_alg:
-	kfree(ctx->intg_alg.data);
-out_err_free_conf_key:
-	kfree(ctx->derived_conf_key.data);
-out_err_free_conf_alg:
-	kfree(ctx->conf_alg.data);
-out_err_free_mech:
-	kfree(ctx->mech_used.data);
-out_err_free_ctx_id:
-	kfree(ctx->ctx_id.data);
-out_err_free_ctx:
-	kfree(ctx);
-out_err:
-	return PTR_ERR(p);
-}
-
-static void
-gss_delete_sec_context_spkm3(void *internal_ctx)
-{
-	struct spkm3_ctx *sctx = internal_ctx;
-
-	kfree(sctx->derived_integ_key.data);
-	kfree(sctx->intg_alg.data);
-	kfree(sctx->derived_conf_key.data);
-	kfree(sctx->conf_alg.data);
-	kfree(sctx->mech_used.data);
-	kfree(sctx->ctx_id.data);
-	kfree(sctx);
-}
-
-static u32
-gss_verify_mic_spkm3(struct gss_ctx		*ctx,
-			struct xdr_buf		*signbuf,
-			struct xdr_netobj	*checksum)
-{
-	u32 maj_stat = 0;
-	struct spkm3_ctx *sctx = ctx->internal_ctx_id;
-
-	maj_stat = spkm3_read_token(sctx, checksum, signbuf, SPKM_MIC_TOK);
-
-	dprintk("RPC:       gss_verify_mic_spkm3 returning %d\n", maj_stat);
-	return maj_stat;
-}
-
-static u32
-gss_get_mic_spkm3(struct gss_ctx	*ctx,
-		     struct xdr_buf	*message_buffer,
-		     struct xdr_netobj	*message_token)
-{
-	u32 err = 0;
-	struct spkm3_ctx *sctx = ctx->internal_ctx_id;
-
-	err = spkm3_make_token(sctx, message_buffer,
-				message_token, SPKM_MIC_TOK);
-	dprintk("RPC:       gss_get_mic_spkm3 returning %d\n", err);
-	return err;
-}
-
-static const struct gss_api_ops gss_spkm3_ops = {
-	.gss_import_sec_context	= gss_import_sec_context_spkm3,
-	.gss_get_mic		= gss_get_mic_spkm3,
-	.gss_verify_mic		= gss_verify_mic_spkm3,
-	.gss_delete_sec_context	= gss_delete_sec_context_spkm3,
-};
-
-static struct pf_desc gss_spkm3_pfs[] = {
-	{RPC_AUTH_GSS_SPKM, RPC_GSS_SVC_NONE, "spkm3"},
-	{RPC_AUTH_GSS_SPKMI, RPC_GSS_SVC_INTEGRITY, "spkm3i"},
-};
-
-static struct gss_api_mech gss_spkm3_mech = {
-	.gm_name	= "spkm3",
-	.gm_owner	= THIS_MODULE,
-	.gm_oid		= {7, "\053\006\001\005\005\001\003"},
-	.gm_ops		= &gss_spkm3_ops,
-	.gm_pf_num	= ARRAY_SIZE(gss_spkm3_pfs),
-	.gm_pfs		= gss_spkm3_pfs,
-};
-
-static int __init init_spkm3_module(void)
-{
-	int status;
-
-	status = gss_mech_register(&gss_spkm3_mech);
-	if (status)
-		printk("Failed to register spkm3 gss mechanism!\n");
-	return status;
-}
-
-static void __exit cleanup_spkm3_module(void)
-{
-	gss_mech_unregister(&gss_spkm3_mech);
-}
-
-MODULE_LICENSE("GPL");
-module_init(init_spkm3_module);
-module_exit(cleanup_spkm3_module);

net/sunrpc/auth_gss/gss_spkm3_seal.c

-/*
- *  linux/net/sunrpc/gss_spkm3_seal.c
- *
- *  Copyright (c) 2003 The Regents of the University of Michigan.
- *  All rights reserved.
- *
- *  Andy Adamson <andros@umich.edu>
- *
- *  Redistribution and use in source and binary forms, with or without
- *  modification, are permitted provided that the following conditions
- *  are met:
- *
- *  1. Redistributions of source code must retain the above copyright
- *     notice, this list of conditions and the following disclaimer.
- *  2. Redistributions in binary form must reproduce the above copyright
- *     notice, this list of conditions and the following disclaimer in the
- *     documentation and/or other materials provided with the distribution.
- *  3. Neither the name of the University nor the names of its
- *     contributors may be used to endorse or promote products derived
- *     from this software without specific prior written permission.
- *
- *  THIS SOFTWARE IS PROVIDED ``AS IS'' AND ANY EXPRESS OR IMPLIED
- *  WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF
- *  MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
- *  DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
- *  FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- *  CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- *  SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR
- *  BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF
- *  LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING
- *  NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
- *  SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
- *
- */
-
-#include <linux/types.h>
-#include <linux/jiffies.h>
-#include <linux/sunrpc/gss_spkm3.h>
-#include <linux/random.h>
-#include <linux/crypto.h>
-#include <linux/pagemap.h>
-#include <linux/scatterlist.h>
-#include <linux/sunrpc/xdr.h>
-
-#ifdef RPC_DEBUG
-# define RPCDBG_FACILITY        RPCDBG_AUTH
-#endif
-
-const struct xdr_netobj hmac_md5_oid = { 8, "\x2B\x06\x01\x05\x05\x08\x01\x01"};
-const struct xdr_netobj cast5_cbc_oid = {9, "\x2A\x86\x48\x86\xF6\x7D\x07\x42\x0A"};
-
-/*
- * spkm3_make_token()
- *
- * Only SPKM_MIC_TOK with md5 intg-alg is supported
- */
-
-u32
-spkm3_make_token(struct spkm3_ctx *ctx,
-		   struct xdr_buf * text, struct xdr_netobj * token,
-		   int toktype)
-{
-	s32			checksum_type;
-	char			tokhdrbuf[25];
-	char			cksumdata[16];
-	struct xdr_netobj	md5cksum = {.len = 0, .data = cksumdata};
-	struct xdr_netobj	mic_hdr = {.len = 0, .data = tokhdrbuf};
-	int			tokenlen = 0;
-	unsigned char		*ptr;
-	s32			now;
-	int			ctxelen = 0, ctxzbit = 0;
-	int			md5elen = 0, md5zbit = 0;
-
-	now = jiffies;
-
-	if (ctx->ctx_id.len != 16) {
-		dprintk("RPC:       spkm3_make_token BAD ctx_id.len %d\n",
-				ctx->ctx_id.len);
-		goto out_err;
-	}
-
-	if (!g_OID_equal(&ctx->intg_alg, &hmac_md5_oid)) {
-		dprintk("RPC:       gss_spkm3_seal: unsupported I-ALG "
-				"algorithm.  only support hmac-md5 I-ALG.\n");
-		goto out_err;
-	} else
-		checksum_type = CKSUMTYPE_HMAC_MD5;
-
-	if (!g_OID_equal(&ctx->conf_alg, &cast5_cbc_oid)) {
-		dprintk("RPC:       gss_spkm3_seal: unsupported C-ALG "
-				"algorithm\n");
-		goto out_err;
-	}
-
-	if (toktype == SPKM_MIC_TOK) {
-		/* Calculate checksum over the mic-header */
-		asn1_bitstring_len(&ctx->ctx_id, &ctxelen, &ctxzbit);
-		spkm3_mic_header(&mic_hdr.data, &mic_hdr.len, ctx->ctx_id.data,
-				ctxelen, ctxzbit);
-		if (make_spkm3_checksum(checksum_type, &ctx->derived_integ_key,
-					(char *)mic_hdr.data, mic_hdr.len,
-					text, 0, &md5cksum))
-			goto out_err;
-
-		asn1_bitstring_len(&md5cksum, &md5elen, &md5zbit);
-		tokenlen = 10 + ctxelen + 1 + md5elen + 1;
-
-		/* Create token header using generic routines */
-		token->len = g_token_size(&ctx->mech_used, tokenlen + 2);
-
-		ptr = token->data;
-		g_make_token_header(&ctx->mech_used, tokenlen + 2, &ptr);
-
-		spkm3_make_mic_token(&ptr, tokenlen, &mic_hdr, &md5cksum, md5elen, md5zbit);
-	} else if (toktype == SPKM_WRAP_TOK) { /* Not Supported */
-		dprintk("RPC:       gss_spkm3_seal: SPKM_WRAP_TOK "
-				"not supported\n");
-		goto out_err;
-	}
-
-	/* XXX need to implement sequence numbers, and ctx->expired */
-
-	return  GSS_S_COMPLETE;
-out_err:
-	token->data = NULL;
-	token->len = 0;
-	return GSS_S_FAILURE;
-}
-
-static int
-spkm3_checksummer(struct scatterlist *sg, void *data)
-{
-	struct hash_desc *desc = data;
-
-	return crypto_hash_update(desc, sg, sg->length);
-}
-
-/* checksum the plaintext data and hdrlen bytes of the token header */
-s32
-make_spkm3_checksum(s32 cksumtype, struct xdr_netobj *key, char *header,
-		    unsigned int hdrlen, struct xdr_buf *body,
-		    unsigned int body_offset, struct xdr_netobj *cksum)
-{
-	char				*cksumname;
-	struct hash_desc		desc; /* XXX add to ctx? */
-	struct scatterlist		sg[1];
-	int err;
-
-	switch (cksumtype) {
-		case CKSUMTYPE_HMAC_MD5:
-			cksumname = "hmac(md5)";
-			break;
-		default:
-			dprintk("RPC:       spkm3_make_checksum:"
-					" unsupported checksum %d", cksumtype);
-			return GSS_S_FAILURE;
-	}
-
-	if (key->data == NULL || key->len <= 0) return GSS_S_FAILURE;
-
-	desc.tfm = crypto_alloc_hash(cksumname, 0, CRYPTO_ALG_ASYNC);
-	if (IS_ERR(desc.tfm))
-		return GSS_S_FAILURE;
-	cksum->len = crypto_hash_digestsize(desc.tfm);
-	desc.flags = CRYPTO_TFM_REQ_MAY_SLEEP;
-
-	err = crypto_hash_setkey(desc.tfm, key->data, key->len);
-	if (err)
-		goto out;
-
-	err = crypto_hash_init(&desc);
-	if (err)
-		goto out;
-
-	sg_init_one(sg, header, hdrlen);
-	crypto_hash_update(&desc, sg, sg->length);
-
-	xdr_process_buf(body, body_offset, body->len - body_offset,
-			spkm3_checksummer, &desc);
-	crypto_hash_final(&desc, cksum->data);
-
-out:
-	crypto_free_hash(desc.tfm);
-
-	return err ? GSS_S_FAILURE : 0;
-}

net/sunrpc/auth_gss/gss_spkm3_token.c

-/*
- *  linux/net/sunrpc/gss_spkm3_token.c
- *
- *  Copyright (c) 2003 The Regents of the University of Michigan.
- *  All rights reserved.
- *
- *  Andy Adamson <andros@umich.edu>
- *
- *  Redistribution and use in source and binary forms, with or without
- *  modification, are permitted provided that the following conditions
- *  are met:
- *
- *  1. Redistributions of source code must retain the above copyright
- *     notice, this list of conditions and the following disclaimer.
- *  2. Redistributions in binary form must reproduce the above copyright
- *     notice, this list of conditions and the following disclaimer in the
- *     documentation and/or other materials provided with the distribution.
- *  3. Neither the name of the University nor the names of its
- *     contributors may be used to endorse or promote products derived
- *     from this software without specific prior written permission.
- *
- *  THIS SOFTWARE IS PROVIDED ``AS IS'' AND ANY EXPRESS OR IMPLIED
- *  WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF
- *  MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
- *  DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
- *  FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- *  CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- *  SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR
- *  BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF
- *  LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING
- *  NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
- *  SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
- *
- */
-
-#include <linux/types.h>
-#include <linux/slab.h>
-#include <linux/jiffies.h>
-#include <linux/sunrpc/gss_spkm3.h>
-#include <linux/random.h>
-#include <linux/crypto.h>
-
-#ifdef RPC_DEBUG
-# define RPCDBG_FACILITY        RPCDBG_AUTH
-#endif
-
-/*
- * asn1_bitstring_len()
- *
- * calculate the asn1 bitstring length of the xdr_netobject
- */
-void
-asn1_bitstring_len(struct xdr_netobj *in, int *enclen, int *zerobits)
-{
-	int i, zbit = 0,elen = in->len;
-	char *ptr;
-
-	ptr = &in->data[in->len -1];
-
-	/* count trailing 0's */
-	for(i = in->len; i > 0; i--) {
-		if (*ptr == 0) {
-			ptr--;
-			elen--;
-		} else
-			break;
-	}
-
-	/* count number of 0 bits in final octet */
-	ptr = &in->data[elen - 1];
-	for(i = 0; i < 8; i++) {
-		short mask = 0x01;
-
-		if (!((mask << i) & *ptr))
-			zbit++;
-		else
-			break;
-	}
-	*enclen = elen;
-	*zerobits = zbit;
-}
-
-/*
- * decode_asn1_bitstring()
- *
- * decode a bitstring into a buffer of the expected length.
- * enclen = bit string length
- * explen = expected length (define in rfc)
- */
-int
-decode_asn1_bitstring(struct xdr_netobj *out, char *in, int enclen, int explen)
-{
-	if (!(out->data = kzalloc(explen,GFP_NOFS)))
-		return 0;
-	out->len = explen;
-	memcpy(out->data, in, enclen);
-	return 1;
-}
-
-/*
- * SPKMInnerContextToken choice SPKM_MIC asn1 token layout
- *
- * contextid is always 16 bytes plain data. max asn1 bitstring len = 17.
- *
- * tokenlen = pos[0] to end of token (max pos[45] with MD5 cksum)
- *
- * pos  value
- * ----------
- * [0]	a4  SPKM-MIC tag
- * [1]	??  innertoken length  (max 44)
- *
- *
- * tok_hdr piece of checksum data starts here
- *
- * the maximum mic-header len = 9 + 17 = 26
- *	mic-header
- *	----------
- * [2]	30      SEQUENCE tag
- * [3]	??	mic-header length: (max 23) = TokenID + ContextID
- *
- *		TokenID  - all fields constant and can be hardcoded
- *		-------
- * [4]	  02	Type 2
- * [5]	  02	Length 2
- * [6][7] 01 01	TokenID (SPKM_MIC_TOK)
- *
- *		ContextID  - encoded length not constant, calculated
- *		---------
- * [8]	03	Type 3
- * [9]	??	encoded length
- * [10]	??	ctxzbit
- * [11]	 	contextid
- *
- * mic_header piece of checksum data ends here.
- *
- *	int-cksum - encoded length not constant, calculated
- *	---------
- * [??]	03	Type 3
- * [??]	??	encoded length
- * [??]	??	md5zbit
- * [??]	 	int-cksum (NID_md5 = 16)
- *
- * maximum SPKM-MIC innercontext token length =
- *	 10 + encoded contextid_size(17 max) + 2 + encoded
- *       cksum_size (17 maxfor NID_md5) = 46
- */
-
-/*
- * spkm3_mic_header()
- *
- * Prepare the SPKM_MIC_TOK mic-header for check-sum calculation
- * elen: 16 byte context id asn1 bitstring encoded length
- */
-void
-spkm3_mic_header(unsigned char **hdrbuf, unsigned int *hdrlen, unsigned char *ctxdata, int elen, int zbit)
-{
-	char *hptr = *hdrbuf;
-	char *top = *hdrbuf;
-
-	*(u8 *)hptr++ = 0x30;
-	*(u8 *)hptr++ = elen + 7;  /* on the wire header length */
-
-	/* tokenid */
-	*(u8 *)hptr++ = 0x02;
-	*(u8 *)hptr++ = 0x02;
-	*(u8 *)hptr++ = 0x01;
-	*(u8 *)hptr++ = 0x01;
-
-	/* coniextid */
-	*(u8 *)hptr++ = 0x03;
-	*(u8 *)hptr++ = elen + 1; /* add 1 to include zbit */
-	*(u8 *)hptr++ = zbit;
-	memcpy(hptr, ctxdata, elen);
-	hptr += elen;
-	*hdrlen = hptr - top;
-}
-
-/*
- * spkm3_mic_innercontext_token()
- *
- * *tokp points to the beginning of the SPKM_MIC token  described
- * in rfc 2025, section 3.2.1:
- *
- * toklen is the inner token length
- */
-void
-spkm3_make_mic_token(unsigned char **tokp, int toklen, struct xdr_netobj *mic_hdr, struct xdr_netobj *md5cksum, int md5elen, int md5zbit)
-{
-	unsigned char *ict = *tokp;
-
-	*(u8 *)ict++ = 0xa4;
-	*(u8 *)ict++ = toklen;
-	memcpy(ict, mic_hdr->data, mic_hdr->len);
-	ict += mic_hdr->len;
-
-	*(u8 *)ict++ = 0x03;
-	*(u8 *)ict++ = md5elen + 1; /* add 1 to include zbit */
-	*(u8 *)ict++ = md5zbit;
-	memcpy(ict, md5cksum->data, md5elen);
-}
-
-u32
-spkm3_verify_mic_token(unsigned char **tokp, int *mic_hdrlen, unsigned char **cksum)
-{
-	struct xdr_netobj       spkm3_ctx_id = {.len =0, .data = NULL};
-	unsigned char 		*ptr = *tokp;
-	int 			ctxelen;
-	u32     		ret = GSS_S_DEFECTIVE_TOKEN;
-
-	/* spkm3 innercontext token preamble */
-	if ((ptr[0] != 0xa4) || (ptr[2] != 0x30)) {
-		dprintk("RPC:       BAD SPKM ictoken preamble\n");
-		goto out;
-	}
-
-	*mic_hdrlen = ptr[3];
-
-	/* token type */
-	if ((ptr[4] != 0x02) || (ptr[5] != 0x02)) {
-		dprintk("RPC:       BAD asn1 SPKM3 token type\n");
-		goto out;
-	}
-
-	/* only support SPKM_MIC_TOK */
-	if((ptr[6] != 0x01) || (ptr[7] != 0x01)) {
-		dprintk("RPC:       ERROR unsupported SPKM3 token\n");
-		goto out;
-	}
-
-	/* contextid */
-	if (ptr[8] != 0x03) {
-		dprintk("RPC:       BAD SPKM3 asn1 context-id type\n");
-		goto out;
-	}
-
-	ctxelen = ptr[9];
-	if (ctxelen > 17) {  /* length includes asn1 zbit octet */
-		dprintk("RPC:       BAD SPKM3 contextid len %d\n", ctxelen);
-		goto out;
-	}
-
-	/* ignore ptr[10] */
-
-	if(!decode_asn1_bitstring(&spkm3_ctx_id, &ptr[11], ctxelen - 1, 16))
-		goto out;
-
-	/*
-	* in the current implementation: the optional int-alg is not present
-	* so the default int-alg (md5) is used the optional snd-seq field is
-	* also not present
-	*/
-
-	if (*mic_hdrlen != 6 + ctxelen) {
-		dprintk("RPC:       BAD SPKM_ MIC_TOK header len %d: we only "
-				"support default int-alg (should be absent) "
-				"and do not support snd-seq\n", *mic_hdrlen);
-		goto out;
-	}
-	/* checksum */
-	*cksum = (&ptr[10] + ctxelen); /* ctxelen includes ptr[10] */
-
-	ret = GSS_S_COMPLETE;
-out:
-	kfree(spkm3_ctx_id.data);
-	return ret;
-}
-

net/sunrpc/auth_gss/gss_spkm3_unseal.c

-/*
- *  linux/net/sunrpc/gss_spkm3_unseal.c
- *
- *  Copyright (c) 2003 The Regents of the University of Michigan.
- *  All rights reserved.
- *
- *  Andy Adamson <andros@umich.edu>
- *
- *  Redistribution and use in source and binary forms, with or without
- *  modification, are permitted provided that the following conditions
- *  are met:
- *
- *  1. Redistributions of source code must retain the above copyright
- *     notice, this list of conditions and the following disclaimer.
- *  2. Redistributions in binary form must reproduce the above copyright
- *     notice, this list of conditions and the following disclaimer in the
- *     documentation and/or other materials provided with the distribution.
- *  3. Neither the name of the University nor the names of its
- *     contributors may be used to endorse or promote products derived
- *     from this software without specific prior written permission.
- *
- *  THIS SOFTWARE IS PROVIDED ``AS IS'' AND ANY EXPRESS OR IMPLIED
- *  WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF
- *  MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
- *  DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
- *  FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- *  CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- *  SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR
- *  BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF
- *  LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING
- *  NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
- *  SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
- *
- */
-
-#include <linux/types.h>
-#include <linux/slab.h>
-#include <linux/jiffies.h>
-#include <linux/sunrpc/gss_spkm3.h>
-#include <linux/crypto.h>
-
-#ifdef RPC_DEBUG
-# define RPCDBG_FACILITY        RPCDBG_AUTH
-#endif
-
-/*
- * spkm3_read_token()
- *
- * only SPKM_MIC_TOK with md5 intg-alg is supported
- */
-u32
-spkm3_read_token(struct spkm3_ctx *ctx,
-		struct xdr_netobj *read_token,    /* checksum */
-		struct xdr_buf *message_buffer, /* signbuf */
-		int toktype)
-{
-	s32			checksum_type;
-	s32			code;
-	struct xdr_netobj	wire_cksum = {.len =0, .data = NULL};
-	char			cksumdata[16];
-	struct xdr_netobj	md5cksum = {.len = 0, .data = cksumdata};
-	unsigned char		*ptr = (unsigned char *)read_token->data;
-	unsigned char		*cksum;
-	int			bodysize, md5elen;
-	int			mic_hdrlen;
-	u32			ret = GSS_S_DEFECTIVE_TOKEN;
-
-	if (g_verify_token_header((struct xdr_netobj *) &ctx->mech_used,
-					&bodysize, &ptr, read_token->len))
-		goto out;
-
-	/* decode the token */
-
-	if (toktype != SPKM_MIC_TOK) {
-		dprintk("RPC:       BAD SPKM3 token type: %d\n", toktype);
-		goto out;
-	}
-
-	if ((ret = spkm3_verify_mic_token(&ptr, &mic_hdrlen, &cksum)))
-		goto out;
-
-	if (*cksum++ != 0x03) {
-		dprintk("RPC:       spkm3_read_token BAD checksum type\n");
-		goto out;
-	}
-	md5elen = *cksum++;
-	cksum++; 	/* move past the zbit */
-
-	if (!decode_asn1_bitstring(&wire_cksum, cksum, md5elen - 1, 16))
-		goto out;
-
-	/* HARD CODED FOR MD5 */
-
-	/* compute the checksum of the message.
-	 * ptr + 2 = start of header piece of checksum
-	 * mic_hdrlen + 2 = length of header piece of checksum
-	 */
-	ret = GSS_S_DEFECTIVE_TOKEN;
-	if (!g_OID_equal(&ctx->intg_alg, &hmac_md5_oid)) {
-		dprintk("RPC:       gss_spkm3_seal: unsupported I-ALG "
-				"algorithm\n");
-		goto out;
-	}
-
-	checksum_type = CKSUMTYPE_HMAC_MD5;
-
-	code = make_spkm3_checksum(checksum_type,
-		&ctx->derived_integ_key, ptr + 2, mic_hdrlen + 2,
-		message_buffer, 0, &md5cksum);
-
-	if (code)
-		goto out;
-
-	ret = GSS_S_BAD_SIG;
-	code = memcmp(md5cksum.data, wire_cksum.data, wire_cksum.len);
-	if (code) {
-		dprintk("RPC:       bad MIC checksum\n");
-		goto out;
-	}
-
-
-	/* XXX: need to add expiration and sequencing */
-	ret = GSS_S_COMPLETE;
-out:
-	kfree(wire_cksum.data);
-	return ret;
-}

net/sunrpc/auth_gss/svcauth_gss.c

@@ -964,7 +964,7 @@ svcauth_gss_set_client(struct svc_rqst *rqstp)
 	if (rqstp->rq_gssclient == NULL)
 		return SVC_DENIED;
 	stat = svcauth_unix_set_client(rqstp);
-	if (stat == SVC_DROP)
+	if (stat == SVC_DROP || stat == SVC_CLOSE)
 		return stat;
 	return SVC_OK;
 }
@@ -1018,7 +1018,7 @@ static int svcauth_gss_handle_init(struct svc_rqst *rqstp,
 		return SVC_DENIED;
 	memset(&rsikey, 0, sizeof(rsikey));
 	if (dup_netobj(&rsikey.in_handle, &gc->gc_ctx))
-		return SVC_DROP;
+		return SVC_CLOSE;
 	*authp = rpc_autherr_badverf;
 	if (svc_safe_getnetobj(argv, &tmpobj)) {
 		kfree(rsikey.in_handle.data);
@@ -1026,22 +1026,19 @@ static int svcauth_gss_handle_init(struct svc_rqst *rqstp,
 	}
 	if (dup_netobj(&rsikey.in_token, &tmpobj)) {
 		kfree(rsikey.in_handle.data);
-		return SVC_DROP;
+		return SVC_CLOSE;
 	}
 
 	/* Perform upcall, or find upcall result: */
 	rsip = rsi_lookup(&rsikey);
 	rsi_free(&rsikey);
 	if (!rsip)
-		return SVC_DROP;
-	switch (cache_check(&rsi_cache, &rsip->h, &rqstp->rq_chandle)) {
-	case -EAGAIN:
-	case -ETIMEDOUT:
-	case -ENOENT:
+		return SVC_CLOSE;
+	if (cache_check(&rsi_cache, &rsip->h, &rqstp->rq_chandle) < 0)
 		/* No upcall result: */
-		return SVC_DROP;
-	case 0:
-		ret = SVC_DROP;
+		return SVC_CLOSE;
+
+	ret = SVC_CLOSE;
 	/* Got an answer to the upcall; use it: */
 	if (gss_write_init_verf(rqstp, rsip))
 		goto out;
@@ -1057,7 +1054,7 @@ static int svcauth_gss_handle_init(struct svc_rqst *rqstp,
 	svc_putnl(resv, GSS_SEQ_WIN);
 	if (svc_safe_putnetobj(resv, &rsip->out_token))
 		goto out;
-	}
+
 	ret = SVC_COMPLETE;
 out:
 	cache_put(&rsip->h, &rsi_cache);

net/sunrpc/clnt.c

@@ -284,6 +284,7 @@ struct rpc_clnt *rpc_create(struct rpc_create_args *args)
 	struct rpc_xprt *xprt;
 	struct rpc_clnt *clnt;
 	struct xprt_create xprtargs = {
+		.net = args->net,
 		.ident = args->protocol,
 		.srcaddr = args->saddress,
 		.dstaddr = args->address,

net/sunrpc/netns.h

+#ifndef __SUNRPC_NETNS_H__
+#define __SUNRPC_NETNS_H__
+
+#include <net/net_namespace.h>
+#include <net/netns/generic.h>
+
+struct cache_detail;
+
+struct sunrpc_net {
+	struct proc_dir_entry *proc_net_rpc;
+	struct cache_detail *ip_map_cache;
+};
+
+extern int sunrpc_net_id;
+
+int ip_map_cache_create(struct net *);
+void ip_map_cache_destroy(struct net *);
+
+#endif

net/sunrpc/rpcb_clnt.c

@@ -177,6 +177,7 @@ static DEFINE_MUTEX(rpcb_create_local_mutex);
 static int rpcb_create_local(void)
 {
 	struct rpc_create_args args = {
+		.net		= &init_net,
 		.protocol	= XPRT_TRANSPORT_TCP,
 		.address	= (struct sockaddr *)&rpcb_inaddr_loopback,
 		.addrsize	= sizeof(rpcb_inaddr_loopback),
@@ -229,6 +230,7 @@ static struct rpc_clnt *rpcb_create(char *hostname, struct sockaddr *srvaddr,
 				    size_t salen, int proto, u32 version)
 {
 	struct rpc_create_args args = {
+		.net		= &init_net,
 		.protocol	= proto,
 		.address	= srvaddr,
 		.addrsize	= salen,
@@ -248,7 +250,7 @@ static struct rpc_clnt *rpcb_create(char *hostname, struct sockaddr *srvaddr,
 		((struct sockaddr_in6 *)srvaddr)->sin6_port = htons(RPCBIND_PORT);
 		break;
 	default:
-		return NULL;
+		return ERR_PTR(-EAFNOSUPPORT);
 	}
 
 	return rpc_create(&args);

net/sunrpc/stats.c

@@ -22,11 +22,10 @@
 #include <linux/sunrpc/clnt.h>
 #include <linux/sunrpc/svcsock.h>
 #include <linux/sunrpc/metrics.h>
-#include <net/net_namespace.h>
 
-#define RPCDBG_FACILITY	RPCDBG_MISC
+#include "netns.h"
 
-struct proc_dir_entry	*proc_net_rpc = NULL;
+#define RPCDBG_FACILITY	RPCDBG_MISC
 
 /*
  * Get RPC client stats
@@ -218,10 +217,11 @@ EXPORT_SYMBOL_GPL(rpc_print_iostats);
 static inline struct proc_dir_entry *
 do_register(const char *name, void *data, const struct file_operations *fops)
 {
-	rpc_proc_init();
-	dprintk("RPC:       registering /proc/net/rpc/%s\n", name);
+	struct sunrpc_net *sn;
 
-	return proc_create_data(name, 0, proc_net_rpc, fops, data);
+	dprintk("RPC:       registering /proc/net/rpc/%s\n", name);
+	sn = net_generic(&init_net, sunrpc_net_id);
+	return proc_create_data(name, 0, sn->proc_net_rpc, fops, data);
 }
 
 struct proc_dir_entry *
@@ -234,7 +234,10 @@ EXPORT_SYMBOL_GPL(rpc_proc_register);
 void
 rpc_proc_unregister(const char *name)
 {
-	remove_proc_entry(name, proc_net_rpc);
+	struct sunrpc_net *sn;
+
+	sn = net_generic(&init_net, sunrpc_net_id);
+	remove_proc_entry(name, sn->proc_net_rpc);
 }
 EXPORT_SYMBOL_GPL(rpc_proc_unregister);
 
@@ -248,25 +251,29 @@ EXPORT_SYMBOL_GPL(svc_proc_register);
 void
 svc_proc_unregister(const char *name)
 {
-	remove_proc_entry(name, proc_net_rpc);
+	struct sunrpc_net *sn;
+
+	sn = net_generic(&init_net, sunrpc_net_id);
+	remove_proc_entry(name, sn->proc_net_rpc);
 }
 EXPORT_SYMBOL_GPL(svc_proc_unregister);
 
-void
-rpc_proc_init(void)
+int rpc_proc_init(struct net *net)
 {
+	struct sunrpc_net *sn;
+
 	dprintk("RPC:       registering /proc/net/rpc\n");
-	if (!proc_net_rpc)
-		proc_net_rpc = proc_mkdir("rpc", init_net.proc_net);
+	sn = net_generic(net, sunrpc_net_id);
+	sn->proc_net_rpc = proc_mkdir("rpc", net->proc_net);
+	if (sn->proc_net_rpc == NULL)
+		return -ENOMEM;
+
+	return 0;
 }
 
-void
-rpc_proc_exit(void)
+void rpc_proc_exit(struct net *net)
 {
 	dprintk("RPC:       unregistering /proc/net/rpc\n");
-	if (proc_net_rpc) {
-		proc_net_rpc = NULL;
-		remove_proc_entry("rpc", init_net.proc_net);
-	}
+	remove_proc_entry("rpc", net->proc_net);
 }
 

net/sunrpc/sunrpc_syms.c

@@ -22,7 +22,44 @@
 #include <linux/sunrpc/rpc_pipe_fs.h>
 #include <linux/sunrpc/xprtsock.h>
 
-extern struct cache_detail ip_map_cache, unix_gid_cache;
+#include "netns.h"
+
+int sunrpc_net_id;
+
+static __net_init int sunrpc_init_net(struct net *net)
+{
+	int err;
+
+	err = rpc_proc_init(net);
+	if (err)
+		goto err_proc;
+
+	err = ip_map_cache_create(net);
+	if (err)
+		goto err_ipmap;
+
+	return 0;
+
+err_ipmap:
+	rpc_proc_exit(net);
+err_proc:
+	return err;
+}
+
+static __net_exit void sunrpc_exit_net(struct net *net)
+{
+	ip_map_cache_destroy(net);
+	rpc_proc_exit(net);
+}
+
+static struct pernet_operations sunrpc_net_ops = {
+	.init = sunrpc_init_net,
+	.exit = sunrpc_exit_net,
+	.id = &sunrpc_net_id,
+	.size = sizeof(struct sunrpc_net),
+};
+
+extern struct cache_detail unix_gid_cache;
 
 extern void cleanup_rpcb_clnt(void);
 
@@ -38,18 +75,22 @@ init_sunrpc(void)
 	err = rpcauth_init_module();
 	if (err)
 		goto out3;
+
+	cache_initialize();
+
+	err = register_pernet_subsys(&sunrpc_net_ops);
+	if (err)
+		goto out4;
 #ifdef RPC_DEBUG
 	rpc_register_sysctl();
 #endif
-#ifdef CONFIG_PROC_FS
-	rpc_proc_init();
-#endif
-	cache_initialize();
-	cache_register(&ip_map_cache);
 	cache_register(&unix_gid_cache);
 	svc_init_xprt_sock();	/* svc sock transport */
 	init_socket_xprt();	/* clnt sock transport */
 	return 0;
+
+out4:
+	rpcauth_remove_module();
 out3:
 	rpc_destroy_mempool();
 out2:
@@ -67,13 +108,10 @@ cleanup_sunrpc(void)
 	svc_cleanup_xprt_sock();
 	unregister_rpc_pipefs();
 	rpc_destroy_mempool();
-	cache_unregister(&ip_map_cache);
 	cache_unregister(&unix_gid_cache);
+	unregister_pernet_subsys(&sunrpc_net_ops);
 #ifdef RPC_DEBUG
 	rpc_unregister_sysctl();
-#endif
-#ifdef CONFIG_PROC_FS
-	rpc_proc_exit();
 #endif
 	rcu_barrier(); /* Wait for completion of call_rcu()'s */
 }

net/sunrpc/svc.c

@@ -1055,6 +1055,9 @@ svc_process_common(struct svc_rqst *rqstp, struct kvec *argv, struct kvec *resv)
 		goto err_bad;
 	case SVC_DENIED:
 		goto err_bad_auth;
+	case SVC_CLOSE:
+		if (test_bit(XPT_TEMP, &rqstp->rq_xprt->xpt_flags))
+			svc_close_xprt(rqstp->rq_xprt);
 	case SVC_DROP:
 		goto dropit;
 	case SVC_COMPLETE:

net/sunrpc/svc_xprt.c

@@ -100,16 +100,14 @@ EXPORT_SYMBOL_GPL(svc_unreg_xprt_class);
  */
 int svc_print_xprts(char *buf, int maxlen)
 {
-	struct list_head *le;
+	struct svc_xprt_class *xcl;
 	char tmpstr[80];
 	int len = 0;
 	buf[0] = '\0';
 
 	spin_lock(&svc_xprt_class_lock);
-	list_for_each(le, &svc_xprt_class_list) {
+	list_for_each_entry(xcl, &svc_xprt_class_list, xcl_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);
@@ -128,9 +126,9 @@ 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);
+	if (test_bit(XPT_CACHE_AUTH, &xprt->xpt_flags))
+		svcauth_unix_info_release(xprt);
+	put_net(xprt->xpt_net);
 	xprt->xpt_ops->xpo_free(xprt);
 	module_put(owner);
 }
@@ -156,15 +154,18 @@ void svc_xprt_init(struct svc_xprt_class *xcl, struct svc_xprt *xprt,
 	INIT_LIST_HEAD(&xprt->xpt_list);
 	INIT_LIST_HEAD(&xprt->xpt_ready);
 	INIT_LIST_HEAD(&xprt->xpt_deferred);
+	INIT_LIST_HEAD(&xprt->xpt_users);
 	mutex_init(&xprt->xpt_mutex);
 	spin_lock_init(&xprt->xpt_lock);
 	set_bit(XPT_BUSY, &xprt->xpt_flags);
 	rpc_init_wait_queue(&xprt->xpt_bc_pending, "xpt_bc_pending");
+	xprt->xpt_net = get_net(&init_net);
 }
 EXPORT_SYMBOL_GPL(svc_xprt_init);
 
 static struct svc_xprt *__svc_xpo_create(struct svc_xprt_class *xcl,
 					 struct svc_serv *serv,
+					 struct net *net,
 					 const int family,
 					 const unsigned short port,
 					 int flags)
@@ -199,12 +200,12 @@ static struct svc_xprt *__svc_xpo_create(struct svc_xprt_class *xcl,
 		return ERR_PTR(-EAFNOSUPPORT);
 	}
 
-	return xcl->xcl_ops->xpo_create(serv, sap, len, flags);
+	return xcl->xcl_ops->xpo_create(serv, net, sap, len, flags);
 }
 
 int svc_create_xprt(struct svc_serv *serv, const char *xprt_name,
-		    const int family, const unsigned short port,
-		    int flags)
+		    struct net *net, const int family,
+		    const unsigned short port, int flags)
 {
 	struct svc_xprt_class *xcl;
 
@@ -220,7 +221,7 @@ int svc_create_xprt(struct svc_serv *serv, const char *xprt_name,
 			goto err;
 
 		spin_unlock(&svc_xprt_class_lock);
-		newxprt = __svc_xpo_create(xcl, serv, family, port, flags);
+		newxprt = __svc_xpo_create(xcl, serv, net, family, port, flags);
 		if (IS_ERR(newxprt)) {
 			module_put(xcl->xcl_owner);
 			return PTR_ERR(newxprt);
@@ -329,12 +330,6 @@ void svc_xprt_enqueue(struct svc_xprt *xprt)
 		       "svc_xprt_enqueue: "
 		       "threads and transports both waiting??\n");
 
-	if (test_bit(XPT_DEAD, &xprt->xpt_flags)) {
-		/* Don't enqueue dead transports */
-		dprintk("svc: transport %p is dead, not enqueued\n", xprt);
-		goto out_unlock;
-	}
-
 	pool->sp_stats.packets++;
 
 	/* Mark transport as busy. It will remain in this state until
@@ -651,6 +646,11 @@ int svc_recv(struct svc_rqst *rqstp, long timeout)
 	if (signalled() || kthread_should_stop())
 		return -EINTR;
 
+	/* Normally we will wait up to 5 seconds for any required
+	 * cache information to be provided.
+	 */
+	rqstp->rq_chandle.thread_wait = 5*HZ;
+
 	spin_lock_bh(&pool->sp_lock);
 	xprt = svc_xprt_dequeue(pool);
 	if (xprt) {
@@ -658,6 +658,12 @@ int svc_recv(struct svc_rqst *rqstp, long timeout)
 		svc_xprt_get(xprt);
 		rqstp->rq_reserved = serv->sv_max_mesg;
 		atomic_add(rqstp->rq_reserved, &xprt->xpt_reserved);
+
+		/* As there is a shortage of threads and this request
+		 * had to be queued, don't allow the thread to wait so
+		 * long for cache updates.
+		 */
+		rqstp->rq_chandle.thread_wait = 1*HZ;
 	} else {
 		/* No data pending. Go to sleep */
 		svc_thread_enqueue(pool, rqstp);
@@ -868,6 +874,19 @@ static void svc_age_temp_xprts(unsigned long closure)
 	mod_timer(&serv->sv_temptimer, jiffies + svc_conn_age_period * HZ);
 }
 
+static void call_xpt_users(struct svc_xprt *xprt)
+{
+	struct svc_xpt_user *u;
+
+	spin_lock(&xprt->xpt_lock);
+	while (!list_empty(&xprt->xpt_users)) {
+		u = list_first_entry(&xprt->xpt_users, struct svc_xpt_user, list);
+		list_del(&u->list);
+		u->callback(u);
+	}
+	spin_unlock(&xprt->xpt_lock);
+}
+
 /*
  * Remove a dead transport
  */
@@ -878,7 +897,7 @@ void svc_delete_xprt(struct svc_xprt *xprt)
 
 	/* Only do this once */
 	if (test_and_set_bit(XPT_DEAD, &xprt->xpt_flags))
-		return;
+		BUG();
 
 	dprintk("svc: svc_delete_xprt(%p)\n", xprt);
 	xprt->xpt_ops->xpo_detach(xprt);
@@ -900,6 +919,7 @@ void svc_delete_xprt(struct svc_xprt *xprt)
 	while ((dr = svc_deferred_dequeue(xprt)) != NULL)
 		kfree(dr);
 
+	call_xpt_users(xprt);
 	svc_xprt_put(xprt);
 }
 
@@ -910,10 +930,7 @@ void svc_close_xprt(struct svc_xprt *xprt)
 		/* someone else will have to effect the close */
 		return;
 
-	svc_xprt_get(xprt);
 	svc_delete_xprt(xprt);
-	clear_bit(XPT_BUSY, &xprt->xpt_flags);
-	svc_xprt_put(xprt);
 }
 EXPORT_SYMBOL_GPL(svc_close_xprt);
 

net/sunrpc/svcsock.c

@@ -64,7 +64,8 @@ static void		svc_tcp_sock_detach(struct svc_xprt *);
 static void		svc_sock_free(struct svc_xprt *);
 
 static struct svc_xprt *svc_create_socket(struct svc_serv *, int,
-					  struct sockaddr *, int, int);
+					  struct net *, struct sockaddr *,
+					  int, int);
 #ifdef CONFIG_DEBUG_LOCK_ALLOC
 static struct lock_class_key svc_key[2];
 static struct lock_class_key svc_slock_key[2];
@@ -657,10 +658,11 @@ static struct svc_xprt *svc_udp_accept(struct svc_xprt *xprt)
 }
 
 static struct svc_xprt *svc_udp_create(struct svc_serv *serv,
+				       struct net *net,
 				       struct sockaddr *sa, int salen,
 				       int flags)
 {
-	return svc_create_socket(serv, IPPROTO_UDP, sa, salen, flags);
+	return svc_create_socket(serv, IPPROTO_UDP, net, sa, salen, flags);
 }
 
 static struct svc_xprt_ops svc_udp_ops = {
@@ -1133,9 +1135,6 @@ static int svc_tcp_sendto(struct svc_rqst *rqstp)
 	reclen = htonl(0x80000000|((xbufp->len ) - 4));
 	memcpy(xbufp->head[0].iov_base, &reclen, 4);
 
-	if (test_bit(XPT_DEAD, &rqstp->rq_xprt->xpt_flags))
-		return -ENOTCONN;
-
 	sent = svc_sendto(rqstp, &rqstp->rq_res);
 	if (sent != xbufp->len) {
 		printk(KERN_NOTICE
@@ -1178,10 +1177,11 @@ static int svc_tcp_has_wspace(struct svc_xprt *xprt)
 }
 
 static struct svc_xprt *svc_tcp_create(struct svc_serv *serv,
+				       struct net *net,
 				       struct sockaddr *sa, int salen,
 				       int flags)
 {
-	return svc_create_socket(serv, IPPROTO_TCP, sa, salen, flags);
+	return svc_create_socket(serv, IPPROTO_TCP, net, sa, salen, flags);
 }
 
 static struct svc_xprt_ops svc_tcp_ops = {
@@ -1258,19 +1258,13 @@ void svc_sock_update_bufs(struct svc_serv *serv)
 	 * The number of server threads has changed. Update
 	 * rcvbuf and sndbuf accordingly on all sockets
 	 */
-	struct list_head *le;
+	struct svc_sock *svsk;
 
 	spin_lock_bh(&serv->sv_lock);
-	list_for_each(le, &serv->sv_permsocks) {
-		struct svc_sock *svsk =
-			list_entry(le, struct svc_sock, sk_xprt.xpt_list);
+	list_for_each_entry(svsk, &serv->sv_permsocks, sk_xprt.xpt_list)
 		set_bit(XPT_CHNGBUF, &svsk->sk_xprt.xpt_flags);
-	}
-	list_for_each(le, &serv->sv_tempsocks) {
-		struct svc_sock *svsk =
-			list_entry(le, struct svc_sock, sk_xprt.xpt_list);
+	list_for_each_entry(svsk, &serv->sv_tempsocks, sk_xprt.xpt_list)
 		set_bit(XPT_CHNGBUF, &svsk->sk_xprt.xpt_flags);
-	}
 	spin_unlock_bh(&serv->sv_lock);
 }
 EXPORT_SYMBOL_GPL(svc_sock_update_bufs);
@@ -1385,6 +1379,7 @@ EXPORT_SYMBOL_GPL(svc_addsock);
  */
 static struct svc_xprt *svc_create_socket(struct svc_serv *serv,
 					  int protocol,
+					  struct net *net,
 					  struct sockaddr *sin, int len,
 					  int flags)
 {
@@ -1421,7 +1416,7 @@ static struct svc_xprt *svc_create_socket(struct svc_serv *serv,
 		return ERR_PTR(-EINVAL);
 	}
 
-	error = sock_create_kern(family, type, protocol, &sock);
+	error = __sock_create(net, family, type, protocol, &sock, 1);
 	if (error < 0)
 		return ERR_PTR(error);
 

net/sunrpc/xprt.c

@@ -199,8 +199,6 @@ int xprt_reserve_xprt(struct rpc_task *task)
 	if (test_and_set_bit(XPRT_LOCKED, &xprt->state)) {
 		if (task == xprt->snd_task)
 			return 1;
-		if (task == NULL)
-			return 0;
 		goto out_sleep;
 	}
 	xprt->snd_task = task;
@@ -757,13 +755,11 @@ static void xprt_connect_status(struct rpc_task *task)
  */
 struct rpc_rqst *xprt_lookup_rqst(struct rpc_xprt *xprt, __be32 xid)
 {
-	struct list_head *pos;
+	struct rpc_rqst *entry;
 
-	list_for_each(pos, &xprt->recv) {
-		struct rpc_rqst *entry = list_entry(pos, struct rpc_rqst, rq_list);
+	list_for_each_entry(entry, &xprt->recv, rq_list)
 		if (entry->rq_xid == xid)
 			return entry;
-	}
 
 	dprintk("RPC:       xprt_lookup_rqst did not find xid %08x\n",
 			ntohl(xid));
@@ -962,6 +958,37 @@ static void xprt_free_slot(struct rpc_xprt *xprt, struct rpc_rqst *req)
 	spin_unlock(&xprt->reserve_lock);
 }
 
+struct rpc_xprt *xprt_alloc(struct net *net, int size, int max_req)
+{
+	struct rpc_xprt *xprt;
+
+	xprt = kzalloc(size, GFP_KERNEL);
+	if (xprt == NULL)
+		goto out;
+
+	xprt->max_reqs = max_req;
+	xprt->slot = kcalloc(max_req, sizeof(struct rpc_rqst), GFP_KERNEL);
+	if (xprt->slot == NULL)
+		goto out_free;
+
+	xprt->xprt_net = get_net(net);
+	return xprt;
+
+out_free:
+	kfree(xprt);
+out:
+	return NULL;
+}
+EXPORT_SYMBOL_GPL(xprt_alloc);
+
+void xprt_free(struct rpc_xprt *xprt)
+{
+	put_net(xprt->xprt_net);
+	kfree(xprt->slot);
+	kfree(xprt);
+}
+EXPORT_SYMBOL_GPL(xprt_free);
+
 /**
  * xprt_reserve - allocate an RPC request slot
  * @task: RPC task requesting a slot allocation

net/sunrpc/xprtrdma/svc_rdma.c

@@ -43,6 +43,7 @@
 #include <linux/slab.h>
 #include <linux/fs.h>
 #include <linux/sysctl.h>
+#include <linux/workqueue.h>
 #include <linux/sunrpc/clnt.h>
 #include <linux/sunrpc/sched.h>
 #include <linux/sunrpc/svc_rdma.h>
@@ -74,6 +75,8 @@ atomic_t rdma_stat_sq_prod;
 struct kmem_cache *svc_rdma_map_cachep;
 struct kmem_cache *svc_rdma_ctxt_cachep;
 
+struct workqueue_struct *svc_rdma_wq;
+
 /*
  * This function implements reading and resetting an atomic_t stat
  * variable through read/write to a proc file. Any write to the file
@@ -231,7 +234,7 @@ static ctl_table svcrdma_root_table[] = {
 void svc_rdma_cleanup(void)
 {
 	dprintk("SVCRDMA Module Removed, deregister RPC RDMA transport\n");
-	flush_scheduled_work();
+	destroy_workqueue(svc_rdma_wq);
 	if (svcrdma_table_header) {
 		unregister_sysctl_table(svcrdma_table_header);
 		svcrdma_table_header = NULL;
@@ -249,6 +252,11 @@ int svc_rdma_init(void)
 	dprintk("\tsq_depth         : %d\n",
 		svcrdma_max_requests * RPCRDMA_SQ_DEPTH_MULT);
 	dprintk("\tmax_inline       : %d\n", svcrdma_max_req_size);
+
+	svc_rdma_wq = alloc_workqueue("svc_rdma", 0, 0);
+	if (!svc_rdma_wq)
+		return -ENOMEM;
+
 	if (!svcrdma_table_header)
 		svcrdma_table_header =
 			register_sysctl_table(svcrdma_root_table);
@@ -283,6 +291,7 @@ int svc_rdma_init(void)
 	kmem_cache_destroy(svc_rdma_map_cachep);
  err0:
 	unregister_sysctl_table(svcrdma_table_header);
+	destroy_workqueue(svc_rdma_wq);
 	return -ENOMEM;
 }
 MODULE_AUTHOR("Tom Tucker <tom@opengridcomputing.com>");

net/sunrpc/xprtrdma/svc_rdma_recvfrom.c

@@ -263,8 +263,8 @@ static int fast_reg_read_chunks(struct svcxprt_rdma *xprt,
 	frmr->page_list_len = PAGE_ALIGN(byte_count) >> PAGE_SHIFT;
 	for (page_no = 0; page_no < frmr->page_list_len; page_no++) {
 		frmr->page_list->page_list[page_no] =
-			ib_dma_map_single(xprt->sc_cm_id->device,
-					  page_address(rqstp->rq_arg.pages[page_no]),
+			ib_dma_map_page(xprt->sc_cm_id->device,
+					rqstp->rq_arg.pages[page_no], 0,
 					PAGE_SIZE, DMA_FROM_DEVICE);
 		if (ib_dma_mapping_error(xprt->sc_cm_id->device,
 					 frmr->page_list->page_list[page_no]))
@@ -309,15 +309,19 @@ static int rdma_set_ctxt_sge(struct svcxprt_rdma *xprt,
 			     int count)
 {
 	int i;
+	unsigned long off;
 
 	ctxt->count = count;
 	ctxt->direction = DMA_FROM_DEVICE;
 	for (i = 0; i < count; i++) {
 		ctxt->sge[i].length = 0; /* in case map fails */
 		if (!frmr) {
+			BUG_ON(0 == virt_to_page(vec[i].iov_base));
+			off = (unsigned long)vec[i].iov_base & ~PAGE_MASK;
 			ctxt->sge[i].addr =
-				ib_dma_map_single(xprt->sc_cm_id->device,
-						  vec[i].iov_base,
+				ib_dma_map_page(xprt->sc_cm_id->device,
+						virt_to_page(vec[i].iov_base),
+						off,
 						vec[i].iov_len,
 						DMA_FROM_DEVICE);
 			if (ib_dma_mapping_error(xprt->sc_cm_id->device,
@@ -491,6 +495,7 @@ static int rdma_read_xdr(struct svcxprt_rdma *xprt,
 			printk(KERN_ERR "svcrdma: Error %d posting RDMA_READ\n",
 			       err);
 			set_bit(XPT_CLOSE, &xprt->sc_xprt.xpt_flags);
+			svc_rdma_unmap_dma(ctxt);
 			svc_rdma_put_context(ctxt, 0);
 			goto out;
 		}

net/sunrpc/xprtrdma/svc_rdma_sendto.c

@@ -96,21 +96,25 @@ static int fast_reg_xdr(struct svcxprt_rdma *xprt,
 	vec->count = 2;
 	sge_no++;
 
-	/* Build the FRMR */
+	/* Map the XDR head */
 	frmr->kva = frva;
 	frmr->direction = DMA_TO_DEVICE;
 	frmr->access_flags = 0;
 	frmr->map_len = PAGE_SIZE;
 	frmr->page_list_len = 1;
+	page_off = (unsigned long)xdr->head[0].iov_base & ~PAGE_MASK;
 	frmr->page_list->page_list[page_no] =
-		ib_dma_map_single(xprt->sc_cm_id->device,
-				  (void *)xdr->head[0].iov_base,
-				  PAGE_SIZE, DMA_TO_DEVICE);
+		ib_dma_map_page(xprt->sc_cm_id->device,
+				virt_to_page(xdr->head[0].iov_base),
+				page_off,
+				PAGE_SIZE - page_off,
+				DMA_TO_DEVICE);
 	if (ib_dma_mapping_error(xprt->sc_cm_id->device,
 				 frmr->page_list->page_list[page_no]))
 		goto fatal_err;
 	atomic_inc(&xprt->sc_dma_used);
 
+	/* Map the XDR page list */
 	page_off = xdr->page_base;
 	page_bytes = xdr->page_len + page_off;
 	if (!page_bytes)
@@ -128,9 +132,9 @@ static int fast_reg_xdr(struct svcxprt_rdma *xprt,
 		page_bytes -= sge_bytes;
 
 		frmr->page_list->page_list[page_no] =
-			ib_dma_map_single(xprt->sc_cm_id->device,
-					  page_address(page),
-					  PAGE_SIZE, DMA_TO_DEVICE);
+			ib_dma_map_page(xprt->sc_cm_id->device,
+					page, page_off,
+					sge_bytes, DMA_TO_DEVICE);
 		if (ib_dma_mapping_error(xprt->sc_cm_id->device,
 					 frmr->page_list->page_list[page_no]))
 			goto fatal_err;
@@ -166,7 +170,9 @@ static int fast_reg_xdr(struct svcxprt_rdma *xprt,
 		vec->sge[sge_no].iov_base = frva + frmr->map_len + page_off;
 
 		frmr->page_list->page_list[page_no] =
-			ib_dma_map_single(xprt->sc_cm_id->device, va, PAGE_SIZE,
+		    ib_dma_map_page(xprt->sc_cm_id->device, virt_to_page(va),
+				    page_off,
+				    PAGE_SIZE,
 				    DMA_TO_DEVICE);
 		if (ib_dma_mapping_error(xprt->sc_cm_id->device,
 					 frmr->page_list->page_list[page_no]))
@@ -245,6 +251,35 @@ static int map_xdr(struct svcxprt_rdma *xprt,
 	return 0;
 }
 
+static dma_addr_t dma_map_xdr(struct svcxprt_rdma *xprt,
+			      struct xdr_buf *xdr,
+			      u32 xdr_off, size_t len, int dir)
+{
+	struct page *page;
+	dma_addr_t dma_addr;
+	if (xdr_off < xdr->head[0].iov_len) {
+		/* This offset is in the head */
+		xdr_off += (unsigned long)xdr->head[0].iov_base & ~PAGE_MASK;
+		page = virt_to_page(xdr->head[0].iov_base);
+	} else {
+		xdr_off -= xdr->head[0].iov_len;
+		if (xdr_off < xdr->page_len) {
+			/* This offset is in the page list */
+			page = xdr->pages[xdr_off >> PAGE_SHIFT];
+			xdr_off &= ~PAGE_MASK;
+		} else {
+			/* This offset is in the tail */
+			xdr_off -= xdr->page_len;
+			xdr_off += (unsigned long)
+				xdr->tail[0].iov_base & ~PAGE_MASK;
+			page = virt_to_page(xdr->tail[0].iov_base);
+		}
+	}
+	dma_addr = ib_dma_map_page(xprt->sc_cm_id->device, page, xdr_off,
+				   min_t(size_t, PAGE_SIZE, len), dir);
+	return dma_addr;
+}
+
 /* Assumptions:
  * - We are using FRMR
  *     - or -
@@ -293,10 +328,9 @@ static int send_write(struct svcxprt_rdma *xprt, struct svc_rqst *rqstp,
 		sge[sge_no].length = sge_bytes;
 		if (!vec->frmr) {
 			sge[sge_no].addr =
-				ib_dma_map_single(xprt->sc_cm_id->device,
-						  (void *)
-						  vec->sge[xdr_sge_no].iov_base + sge_off,
+				dma_map_xdr(xprt, &rqstp->rq_res, xdr_off,
 					    sge_bytes, DMA_TO_DEVICE);
+			xdr_off += sge_bytes;
 			if (ib_dma_mapping_error(xprt->sc_cm_id->device,
 						 sge[sge_no].addr))
 				goto err;
@@ -333,6 +367,8 @@ static int send_write(struct svcxprt_rdma *xprt, struct svc_rqst *rqstp,
 		goto err;
 	return 0;
  err:
+	svc_rdma_unmap_dma(ctxt);
+	svc_rdma_put_frmr(xprt, vec->frmr);
 	svc_rdma_put_context(ctxt, 0);
 	/* Fatal error, close transport */
 	return -EIO;
@@ -494,7 +530,8 @@ static int send_reply_chunks(struct svcxprt_rdma *xprt,
  * In all three cases, this function prepares the RPCRDMA header in
  * sge[0], the 'type' parameter indicates the type to place in the
  * RPCRDMA header, and the 'byte_count' field indicates how much of
- * the XDR to include in this RDMA_SEND.
+ * the XDR to include in this RDMA_SEND. NB: The offset of the payload
+ * to send is zero in the XDR.
  */
 static int send_reply(struct svcxprt_rdma *rdma,
 		      struct svc_rqst *rqstp,
@@ -536,7 +573,7 @@ static int send_reply(struct svcxprt_rdma *rdma,
 	ctxt->sge[0].lkey = rdma->sc_dma_lkey;
 	ctxt->sge[0].length = svc_rdma_xdr_get_reply_hdr_len(rdma_resp);
 	ctxt->sge[0].addr =
-		ib_dma_map_single(rdma->sc_cm_id->device, page_address(page),
+	    ib_dma_map_page(rdma->sc_cm_id->device, page, 0,
 			    ctxt->sge[0].length, DMA_TO_DEVICE);
 	if (ib_dma_mapping_error(rdma->sc_cm_id->device, ctxt->sge[0].addr))
 		goto err;
@@ -544,15 +581,16 @@ static int send_reply(struct svcxprt_rdma *rdma,
 
 	ctxt->direction = DMA_TO_DEVICE;
 
-	/* Determine how many of our SGE are to be transmitted */
+	/* Map the payload indicated by 'byte_count' */
 	for (sge_no = 1; byte_count && sge_no < vec->count; sge_no++) {
+		int xdr_off = 0;
 		sge_bytes = min_t(size_t, vec->sge[sge_no].iov_len, byte_count);
 		byte_count -= sge_bytes;
 		if (!vec->frmr) {
 			ctxt->sge[sge_no].addr =
-				ib_dma_map_single(rdma->sc_cm_id->device,
-						  vec->sge[sge_no].iov_base,
+				dma_map_xdr(rdma, &rqstp->rq_res, xdr_off,
 					    sge_bytes, DMA_TO_DEVICE);
+			xdr_off += sge_bytes;
 			if (ib_dma_mapping_error(rdma->sc_cm_id->device,
 						 ctxt->sge[sge_no].addr))
 				goto err;

net/sunrpc/xprtrdma/transport.c

@@ -237,8 +237,7 @@ xprt_rdma_destroy(struct rpc_xprt *xprt)
 
 	dprintk("RPC:       %s: called\n", __func__);
 
-	cancel_delayed_work(&r_xprt->rdma_connect);
-	flush_scheduled_work();
+	cancel_delayed_work_sync(&r_xprt->rdma_connect);
 
 	xprt_clear_connected(xprt);
 
@@ -251,9 +250,7 @@ xprt_rdma_destroy(struct rpc_xprt *xprt)
 
 	xprt_rdma_free_addresses(xprt);
 
-	kfree(xprt->slot);
-	xprt->slot = NULL;
-	kfree(xprt);
+	xprt_free(xprt);
 
 	dprintk("RPC:       %s: returning\n", __func__);
 
@@ -285,23 +282,14 @@ xprt_setup_rdma(struct xprt_create *args)
 		return ERR_PTR(-EBADF);
 	}
 
-	xprt = kzalloc(sizeof(struct rpcrdma_xprt), GFP_KERNEL);
+	xprt = xprt_alloc(args->net, sizeof(struct rpcrdma_xprt),
+			xprt_rdma_slot_table_entries);
 	if (xprt == NULL) {
 		dprintk("RPC:       %s: couldn't allocate rpcrdma_xprt\n",
 			__func__);
 		return ERR_PTR(-ENOMEM);
 	}
 
-	xprt->max_reqs = xprt_rdma_slot_table_entries;
-	xprt->slot = kcalloc(xprt->max_reqs,
-				sizeof(struct rpc_rqst), GFP_KERNEL);
-	if (xprt->slot == NULL) {
-		dprintk("RPC:       %s: couldn't allocate %d slots\n",
-			__func__, xprt->max_reqs);
-		kfree(xprt);
-		return ERR_PTR(-ENOMEM);
-	}
-
 	/* 60 second timeout, no retries */
 	xprt->timeout = &xprt_rdma_default_timeout;
 	xprt->bind_timeout = (60U * HZ);
@@ -410,8 +398,7 @@ xprt_setup_rdma(struct xprt_create *args)
 out2:
 	rpcrdma_ia_close(&new_xprt->rx_ia);
 out1:
-	kfree(xprt->slot);
-	kfree(xprt);
+	xprt_free(xprt);
 	return ERR_PTR(rc);
 }
 
@@ -460,7 +447,7 @@ xprt_rdma_connect(struct rpc_task *task)
 	} else {
 		schedule_delayed_work(&r_xprt->rdma_connect, 0);
 		if (!RPC_IS_ASYNC(task))
-			flush_scheduled_work();
+			flush_delayed_work(&r_xprt->rdma_connect);
 	}
 }