Merge tag 'nfsd-4.3' of git://linux-nfs.org/~bfields/linux

Pull nfsd updates from Bruce Fields:
 "Nothing major, but:

   - Add Jeff Layton as an nfsd co-maintainer: no change to existing
     practice, just an acknowledgement of the status quo.

   - Two patches ("nfsd: ensure that...") for a race overlooked by the
     state locking rewrite, causing a crash noticed by multiple users.

   - Lots of smaller bugfixes all over from Kinglong Mee.

   - From Jeff, some cleanup of server rpc code in preparation for
     possible shift of nfsd threads to workqueues"

* tag 'nfsd-4.3' of git://linux-nfs.org/~bfields/linux: (52 commits)
  nfsd: deal with DELEGRETURN racing with CB_RECALL
  nfsd: return CLID_INUSE for unexpected SETCLIENTID_CONFIRM case
  nfsd: ensure that delegation stateid hash references are only put once
  nfsd: ensure that the ol stateid hash reference is only put once
  net: sunrpc: fix tracepoint Warning: unknown op '->'
  nfsd: allow more than one laundry job to run at a time
  nfsd: don't WARN/backtrace for invalid container deployment.
  fs: fix fs/locks.c kernel-doc warning
  nfsd: Add Jeff Layton as co-maintainer
  NFSD: Return word2 bitmask if setting security label in OPEN/CREATE
  NFSD: Set the attributes used to store the verifier for EXCLUSIVE4_1
  nfsd: SUPPATTR_EXCLCREAT must be encoded before SECURITY_LABEL.
  nfsd: Fix an FS_LAYOUT_TYPES/LAYOUT_TYPES encode bug
  NFSD: Store parent's stat in a separate value
  nfsd: Fix two typos in comments
  lockd: NLM grace period shouldn't block NFSv4 opens
  nfsd: include linux/nfs4.h in export.h
  sunrpc: Switch to using hash list instead single list
  sunrpc/nfsd: Remove redundant code by exports seq_operations functions
  sunrpc: Store cache_detail in seq_file's private directly
  ...

6 files changed, 197 insertions, 150 deletions

diff --git a/net/sunrpc/cache.c b/net/sunrpc/cache.c
index 2928afffbb81..4a2340a54401 100644
--- a/net/sunrpc/cache.c
+++ b/net/sunrpc/cache.c
@@ -44,7 +44,7 @@ static void cache_revisit_request(struct cache_head *item);
 static void cache_init(struct cache_head *h)
 {
 	time_t now = seconds_since_boot();
-	h->next = NULL;
+	INIT_HLIST_NODE(&h->cache_list);
 	h->flags = 0;
 	kref_init(&h->ref);
 	h->expiry_time = now + CACHE_NEW_EXPIRY;
@@ -54,15 +54,14 @@ static void cache_init(struct cache_head *h)
 struct cache_head *sunrpc_cache_lookup(struct cache_detail *detail,
 				       struct cache_head *key, int hash)
 {
-	struct cache_head **head,  **hp;
-	struct cache_head *new = NULL, *freeme = NULL;
+	struct cache_head *new = NULL, *freeme = NULL, *tmp = NULL;
+	struct hlist_head *head;
 
 	head = &detail->hash_table[hash];
 
 	read_lock(&detail->hash_lock);
 
-	for (hp=head; *hp != NULL ; hp = &(*hp)->next) {
-		struct cache_head *tmp = *hp;
+	hlist_for_each_entry(tmp, head, cache_list) {
 		if (detail->match(tmp, key)) {
 			if (cache_is_expired(detail, tmp))
 				/* This entry is expired, we will discard it. */
@@ -88,12 +87,10 @@ struct cache_head *sunrpc_cache_lookup(struct cache_detail *detail,
 	write_lock(&detail->hash_lock);
 
 	/* check if entry appeared while we slept */
-	for (hp=head; *hp != NULL ; hp = &(*hp)->next) {
-		struct cache_head *tmp = *hp;
+	hlist_for_each_entry(tmp, head, cache_list) {
 		if (detail->match(tmp, key)) {
 			if (cache_is_expired(detail, tmp)) {
-				*hp = tmp->next;
-				tmp->next = NULL;
+				hlist_del_init(&tmp->cache_list);
 				detail->entries --;
 				freeme = tmp;
 				break;
@@ -104,8 +101,8 @@ struct cache_head *sunrpc_cache_lookup(struct cache_detail *detail,
 			return tmp;
 		}
 	}
-	new->next = *head;
-	*head = new;
+
+	hlist_add_head(&new->cache_list, head);
 	detail->entries++;
 	cache_get(new);
 	write_unlock(&detail->hash_lock);
@@ -143,7 +140,6 @@ struct cache_head *sunrpc_cache_update(struct cache_detail *detail,
 	 * If 'old' is not VALID, we update it directly,
 	 * otherwise we need to replace it
 	 */
-	struct cache_head **head;
 	struct cache_head *tmp;
 
 	if (!test_bit(CACHE_VALID, &old->flags)) {
@@ -168,15 +164,13 @@ struct cache_head *sunrpc_cache_update(struct cache_detail *detail,
 	}
 	cache_init(tmp);
 	detail->init(tmp, old);
-	head = &detail->hash_table[hash];
 
 	write_lock(&detail->hash_lock);
 	if (test_bit(CACHE_NEGATIVE, &new->flags))
 		set_bit(CACHE_NEGATIVE, &tmp->flags);
 	else
 		detail->update(tmp, new);
-	tmp->next = *head;
-	*head = tmp;
+	hlist_add_head(&tmp->cache_list, &detail->hash_table[hash]);
 	detail->entries++;
 	cache_get(tmp);
 	cache_fresh_locked(tmp, new->expiry_time);
@@ -416,28 +410,29 @@ static int cache_clean(void)
 	/* find a non-empty bucket in the table */
 	while (current_detail &&
 	       current_index < current_detail->hash_size &&
-	       current_detail->hash_table[current_index] == NULL)
+	       hlist_empty(&current_detail->hash_table[current_index]))
 		current_index++;
 
 	/* find a cleanable entry in the bucket and clean it, or set to next bucket */
 
 	if (current_detail && current_index < current_detail->hash_size) {
-		struct cache_head *ch, **cp;
+		struct cache_head *ch = NULL;
 		struct cache_detail *d;
+		struct hlist_head *head;
+		struct hlist_node *tmp;
 
 		write_lock(&current_detail->hash_lock);
 
 		/* Ok, now to clean this strand */
 
-		cp = & current_detail->hash_table[current_index];
-		for (ch = *cp ; ch ; cp = & ch->next, ch = *cp) {
+		head = &current_detail->hash_table[current_index];
+		hlist_for_each_entry_safe(ch, tmp, head, cache_list) {
 			if (current_detail->nextcheck > ch->expiry_time)
 				current_detail->nextcheck = ch->expiry_time+1;
 			if (!cache_is_expired(current_detail, ch))
 				continue;
 
-			*cp = ch->next;
-			ch->next = NULL;
+			hlist_del_init(&ch->cache_list);
 			current_detail->entries--;
 			rv = 1;
 			break;
@@ -1270,18 +1265,13 @@ EXPORT_SYMBOL_GPL(qword_get);
  * get a header, then pass each real item in the cache
  */
 
-struct handle {
-	struct cache_detail *cd;
-};
-
-static void *c_start(struct seq_file *m, loff_t *pos)
+void *cache_seq_start(struct seq_file *m, loff_t *pos)
 	__acquires(cd->hash_lock)
 {
 	loff_t n = *pos;
 	unsigned int hash, entry;
 	struct cache_head *ch;
-	struct cache_detail *cd = ((struct handle*)m->private)->cd;
-
+	struct cache_detail *cd = m->private;
 
 	read_lock(&cd->hash_lock);
 	if (!n--)
@@ -1289,7 +1279,7 @@ static void *c_start(struct seq_file *m, loff_t *pos)
 	hash = n >> 32;
 	entry = n & ((1LL<<32) - 1);
 
-	for (ch=cd->hash_table[hash]; ch; ch=ch->next)
+	hlist_for_each_entry(ch, &cd->hash_table[hash], cache_list)
 		if (!entry--)
 			return ch;
 	n &= ~((1LL<<32) - 1);
@@ -1297,51 +1287,57 @@ static void *c_start(struct seq_file *m, loff_t *pos)
 		hash++;
 		n += 1LL<<32;
 	} while(hash < cd->hash_size &&
-		cd->hash_table[hash]==NULL);
+		hlist_empty(&cd->hash_table[hash]));
 	if (hash >= cd->hash_size)
 		return NULL;
 	*pos = n+1;
-	return cd->hash_table[hash];
+	return hlist_entry_safe(cd->hash_table[hash].first,
+				struct cache_head, cache_list);
 }
+EXPORT_SYMBOL_GPL(cache_seq_start);
 
-static void *c_next(struct seq_file *m, void *p, loff_t *pos)
+void *cache_seq_next(struct seq_file *m, void *p, loff_t *pos)
 {
 	struct cache_head *ch = p;
 	int hash = (*pos >> 32);
-	struct cache_detail *cd = ((struct handle*)m->private)->cd;
+	struct cache_detail *cd = m->private;
 
 	if (p == SEQ_START_TOKEN)
 		hash = 0;
-	else if (ch->next == NULL) {
+	else if (ch->cache_list.next == NULL) {
 		hash++;
 		*pos += 1LL<<32;
 	} else {
 		++*pos;
-		return ch->next;
+		return hlist_entry_safe(ch->cache_list.next,
+					struct cache_head, cache_list);
 	}
 	*pos &= ~((1LL<<32) - 1);
 	while (hash < cd->hash_size &&
-	       cd->hash_table[hash] == NULL) {
+	       hlist_empty(&cd->hash_table[hash])) {
 		hash++;
 		*pos += 1LL<<32;
 	}
 	if (hash >= cd->hash_size)
 		return NULL;
 	++*pos;
-	return cd->hash_table[hash];
+	return hlist_entry_safe(cd->hash_table[hash].first,
+				struct cache_head, cache_list);
 }
+EXPORT_SYMBOL_GPL(cache_seq_next);
 
-static void c_stop(struct seq_file *m, void *p)
+void cache_seq_stop(struct seq_file *m, void *p)
 	__releases(cd->hash_lock)
 {
-	struct cache_detail *cd = ((struct handle*)m->private)->cd;
+	struct cache_detail *cd = m->private;
 	read_unlock(&cd->hash_lock);
 }
+EXPORT_SYMBOL_GPL(cache_seq_stop);
 
 static int c_show(struct seq_file *m, void *p)
 {
 	struct cache_head *cp = p;
-	struct cache_detail *cd = ((struct handle*)m->private)->cd;
+	struct cache_detail *cd = m->private;
 
 	if (p == SEQ_START_TOKEN)
 		return cd->cache_show(m, cd, NULL);
@@ -1364,33 +1360,36 @@ static int c_show(struct seq_file *m, void *p)
 }
 
 static const struct seq_operations cache_content_op = {
-	.start	= c_start,
-	.next	= c_next,
-	.stop	= c_stop,
+	.start	= cache_seq_start,
+	.next	= cache_seq_next,
+	.stop	= cache_seq_stop,
 	.show	= c_show,
 };
 
 static int content_open(struct inode *inode, struct file *file,
 			struct cache_detail *cd)
 {
-	struct handle *han;
+	struct seq_file *seq;
+	int err;
 
 	if (!cd || !try_module_get(cd->owner))
 		return -EACCES;
-	han = __seq_open_private(file, &cache_content_op, sizeof(*han));
-	if (han == NULL) {
+
+	err = seq_open(file, &cache_content_op);
+	if (err) {
 		module_put(cd->owner);
-		return -ENOMEM;
+		return err;
 	}
 
-	han->cd = cd;
+	seq = file->private_data;
+	seq->private = cd;
 	return 0;
 }
 
 static int content_release(struct inode *inode, struct file *file,
 		struct cache_detail *cd)
 {
-	int ret = seq_release_private(inode, file);
+	int ret = seq_release(inode, file);
 	module_put(cd->owner);
 	return ret;
 }
@@ -1665,17 +1664,21 @@ EXPORT_SYMBOL_GPL(cache_unregister_net);
 struct cache_detail *cache_create_net(struct cache_detail *tmpl, struct net *net)
 {
 	struct cache_detail *cd;
+	int i;
 
 	cd = kmemdup(tmpl, sizeof(struct cache_detail), GFP_KERNEL);
 	if (cd == NULL)
 		return ERR_PTR(-ENOMEM);
 
-	cd->hash_table = kzalloc(cd->hash_size * sizeof(struct cache_head *),
+	cd->hash_table = kzalloc(cd->hash_size * sizeof(struct hlist_head),
 				 GFP_KERNEL);
 	if (cd->hash_table == NULL) {
 		kfree(cd);
 		return ERR_PTR(-ENOMEM);
 	}
+
+	for (i = 0; i < cd->hash_size; i++)
+		INIT_HLIST_HEAD(&cd->hash_table[i]);
 	cd->net = net;
 	return cd;
 }
diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c
index 5a16d8d8c831..a8f579df14d8 100644
--- a/net/sunrpc/svc.c
+++ b/net/sunrpc/svc.c
@@ -34,36 +34,19 @@
 
 static void svc_unregister(const struct svc_serv *serv, struct net *net);
 
-#define svc_serv_is_pooled(serv)    ((serv)->sv_function)
+#define svc_serv_is_pooled(serv)    ((serv)->sv_ops->svo_function)
 
-/*
- * Mode for mapping cpus to pools.
- */
-enum {
-	SVC_POOL_AUTO = -1,	/* choose one of the others */
-	SVC_POOL_GLOBAL,	/* no mapping, just a single global pool
-				 * (legacy & UP mode) */
-	SVC_POOL_PERCPU,	/* one pool per cpu */
-	SVC_POOL_PERNODE	/* one pool per numa node */
-};
 #define SVC_POOL_DEFAULT	SVC_POOL_GLOBAL
 
 /*
  * Structure for mapping cpus to pools and vice versa.
  * Setup once during sunrpc initialisation.
  */
-static struct svc_pool_map {
-	int count;			/* How many svc_servs use us */
-	int mode;			/* Note: int not enum to avoid
-					 * warnings about "enumeration value
-					 * not handled in switch" */
-	unsigned int npools;
-	unsigned int *pool_to;		/* maps pool id to cpu or node */
-	unsigned int *to_pool;		/* maps cpu or node to pool id */
-} svc_pool_map = {
-	.count = 0,
+struct svc_pool_map svc_pool_map = {
 	.mode = SVC_POOL_DEFAULT
 };
+EXPORT_SYMBOL_GPL(svc_pool_map);
+
 static DEFINE_MUTEX(svc_pool_map_mutex);/* protects svc_pool_map.count only */
 
 static int
@@ -236,7 +219,7 @@ svc_pool_map_init_pernode(struct svc_pool_map *m)
  * vice versa).  Initialise the map if we're the first user.
  * Returns the number of pools.
  */
-static unsigned int
+unsigned int
 svc_pool_map_get(void)
 {
 	struct svc_pool_map *m = &svc_pool_map;
@@ -271,7 +254,7 @@ svc_pool_map_get(void)
 	mutex_unlock(&svc_pool_map_mutex);
 	return m->npools;
 }
-
+EXPORT_SYMBOL_GPL(svc_pool_map_get);
 
 /*
  * Drop a reference to the global map of cpus to pools.
@@ -280,7 +263,7 @@ svc_pool_map_get(void)
  * mode using the pool_mode module option without
  * rebooting or re-loading sunrpc.ko.
  */
-static void
+void
 svc_pool_map_put(void)
 {
 	struct svc_pool_map *m = &svc_pool_map;
@@ -297,7 +280,7 @@ svc_pool_map_put(void)
 
 	mutex_unlock(&svc_pool_map_mutex);
 }
-
+EXPORT_SYMBOL_GPL(svc_pool_map_put);
 
 static int svc_pool_map_get_node(unsigned int pidx)
 {
@@ -423,7 +406,7 @@ EXPORT_SYMBOL_GPL(svc_bind);
  */
 static struct svc_serv *
 __svc_create(struct svc_program *prog, unsigned int bufsize, int npools,
-	     void (*shutdown)(struct svc_serv *serv, struct net *net))
+	     struct svc_serv_ops *ops)
 {
 	struct svc_serv	*serv;
 	unsigned int vers;
@@ -440,7 +423,7 @@ __svc_create(struct svc_program *prog, unsigned int bufsize, int npools,
 		bufsize = RPCSVC_MAXPAYLOAD;
 	serv->sv_max_payload = bufsize? bufsize : 4096;
 	serv->sv_max_mesg  = roundup(serv->sv_max_payload + PAGE_SIZE, PAGE_SIZE);
-	serv->sv_shutdown  = shutdown;
+	serv->sv_ops = ops;
 	xdrsize = 0;
 	while (prog) {
 		prog->pg_lovers = prog->pg_nvers-1;
@@ -486,26 +469,22 @@ __svc_create(struct svc_program *prog, unsigned int bufsize, int npools,
 
 struct svc_serv *
 svc_create(struct svc_program *prog, unsigned int bufsize,
-	   void (*shutdown)(struct svc_serv *serv, struct net *net))
+	   struct svc_serv_ops *ops)
 {
-	return __svc_create(prog, bufsize, /*npools*/1, shutdown);
+	return __svc_create(prog, bufsize, /*npools*/1, ops);
 }
 EXPORT_SYMBOL_GPL(svc_create);
 
 struct svc_serv *
 svc_create_pooled(struct svc_program *prog, unsigned int bufsize,
-		  void (*shutdown)(struct svc_serv *serv, struct net *net),
-		  svc_thread_fn func, struct module *mod)
+		  struct svc_serv_ops *ops)
 {
 	struct svc_serv *serv;
 	unsigned int npools = svc_pool_map_get();
 
-	serv = __svc_create(prog, bufsize, npools, shutdown);
+	serv = __svc_create(prog, bufsize, npools, ops);
 	if (!serv)
 		goto out_err;
-
-	serv->sv_function = func;
-	serv->sv_module = mod;
 	return serv;
 out_err:
 	svc_pool_map_put();
@@ -517,8 +496,8 @@ void svc_shutdown_net(struct svc_serv *serv, struct net *net)
 {
 	svc_close_net(serv, net);
 
-	if (serv->sv_shutdown)
-		serv->sv_shutdown(serv, net);
+	if (serv->sv_ops->svo_shutdown)
+		serv->sv_ops->svo_shutdown(serv, net);
 }
 EXPORT_SYMBOL_GPL(svc_shutdown_net);
 
@@ -604,40 +583,52 @@ svc_release_buffer(struct svc_rqst *rqstp)
 }
 
 struct svc_rqst *
-svc_prepare_thread(struct svc_serv *serv, struct svc_pool *pool, int node)
+svc_rqst_alloc(struct svc_serv *serv, struct svc_pool *pool, int node)
 {
 	struct svc_rqst	*rqstp;
 
 	rqstp = kzalloc_node(sizeof(*rqstp), GFP_KERNEL, node);
 	if (!rqstp)
-		goto out_enomem;
+		return rqstp;
 
-	serv->sv_nrthreads++;
 	__set_bit(RQ_BUSY, &rqstp->rq_flags);
 	spin_lock_init(&rqstp->rq_lock);
 	rqstp->rq_server = serv;
 	rqstp->rq_pool = pool;
-	spin_lock_bh(&pool->sp_lock);
-	pool->sp_nrthreads++;
-	list_add_rcu(&rqstp->rq_all, &pool->sp_all_threads);
-	spin_unlock_bh(&pool->sp_lock);
 
 	rqstp->rq_argp = kmalloc_node(serv->sv_xdrsize, GFP_KERNEL, node);
 	if (!rqstp->rq_argp)
-		goto out_thread;
+		goto out_enomem;
 
 	rqstp->rq_resp = kmalloc_node(serv->sv_xdrsize, GFP_KERNEL, node);
 	if (!rqstp->rq_resp)
-		goto out_thread;
+		goto out_enomem;
 
 	if (!svc_init_buffer(rqstp, serv->sv_max_mesg, node))
-		goto out_thread;
+		goto out_enomem;
 
 	return rqstp;
-out_thread:
-	svc_exit_thread(rqstp);
 out_enomem:
-	return ERR_PTR(-ENOMEM);
+	svc_rqst_free(rqstp);
+	return NULL;
+}
+EXPORT_SYMBOL_GPL(svc_rqst_alloc);
+
+struct svc_rqst *
+svc_prepare_thread(struct svc_serv *serv, struct svc_pool *pool, int node)
+{
+	struct svc_rqst	*rqstp;
+
+	rqstp = svc_rqst_alloc(serv, pool, node);
+	if (!rqstp)
+		return ERR_PTR(-ENOMEM);
+
+	serv->sv_nrthreads++;
+	spin_lock_bh(&pool->sp_lock);
+	pool->sp_nrthreads++;
+	list_add_rcu(&rqstp->rq_all, &pool->sp_all_threads);
+	spin_unlock_bh(&pool->sp_lock);
+	return rqstp;
 }
 EXPORT_SYMBOL_GPL(svc_prepare_thread);
 
@@ -739,12 +730,12 @@ svc_set_num_threads(struct svc_serv *serv, struct svc_pool *pool, int nrservs)
 			break;
 		}
 
-		__module_get(serv->sv_module);
-		task = kthread_create_on_node(serv->sv_function, rqstp,
+		__module_get(serv->sv_ops->svo_module);
+		task = kthread_create_on_node(serv->sv_ops->svo_function, rqstp,
 					      node, "%s", serv->sv_name);
 		if (IS_ERR(task)) {
 			error = PTR_ERR(task);
-			module_put(serv->sv_module);
+			module_put(serv->sv_ops->svo_module);
 			svc_exit_thread(rqstp);
 			break;
 		}
@@ -772,15 +763,21 @@ EXPORT_SYMBOL_GPL(svc_set_num_threads);
  * mutex" for the service.
  */
 void
-svc_exit_thread(struct svc_rqst *rqstp)
+svc_rqst_free(struct svc_rqst *rqstp)
 {
-	struct svc_serv	*serv = rqstp->rq_server;
-	struct svc_pool	*pool = rqstp->rq_pool;
-
 	svc_release_buffer(rqstp);
 	kfree(rqstp->rq_resp);
 	kfree(rqstp->rq_argp);
 	kfree(rqstp->rq_auth_data);
+	kfree_rcu(rqstp, rq_rcu_head);
+}
+EXPORT_SYMBOL_GPL(svc_rqst_free);
+
+void
+svc_exit_thread(struct svc_rqst *rqstp)
+{
+	struct svc_serv	*serv = rqstp->rq_server;
+	struct svc_pool	*pool = rqstp->rq_pool;
 
 	spin_lock_bh(&pool->sp_lock);
 	pool->sp_nrthreads--;
@@ -788,7 +785,7 @@ svc_exit_thread(struct svc_rqst *rqstp)
 		list_del_rcu(&rqstp->rq_all);
 	spin_unlock_bh(&pool->sp_lock);
 
-	kfree_rcu(rqstp, rq_rcu_head);
+	svc_rqst_free(rqstp);
 
 	/* Release the server */
 	if (serv)
diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c
index 163ac45c3639..a6cbb2104667 100644
--- a/net/sunrpc/svc_xprt.c
+++ b/net/sunrpc/svc_xprt.c
@@ -24,7 +24,6 @@ static int svc_deferred_recv(struct svc_rqst *rqstp);
 static struct cache_deferred_req *svc_defer(struct cache_req *req);
 static void svc_age_temp_xprts(unsigned long closure);
 static void svc_delete_xprt(struct svc_xprt *xprt);
-static void svc_xprt_do_enqueue(struct svc_xprt *xprt);
 
 /* apparently the "standard" is that clients close
  * idle connections after 5 minutes, servers after
@@ -225,12 +224,12 @@ static void svc_xprt_received(struct svc_xprt *xprt)
 	}
 
 	/* As soon as we clear busy, the xprt could be closed and
-	 * 'put', so we need a reference to call svc_xprt_do_enqueue with:
+	 * 'put', so we need a reference to call svc_enqueue_xprt with:
 	 */
 	svc_xprt_get(xprt);
 	smp_mb__before_atomic();
 	clear_bit(XPT_BUSY, &xprt->xpt_flags);
-	svc_xprt_do_enqueue(xprt);
+	xprt->xpt_server->sv_ops->svo_enqueue_xprt(xprt);
 	svc_xprt_put(xprt);
 }
 
@@ -320,7 +319,7 @@ static bool svc_xprt_has_something_to_do(struct svc_xprt *xprt)
 	return false;
 }
 
-static void svc_xprt_do_enqueue(struct svc_xprt *xprt)
+void svc_xprt_do_enqueue(struct svc_xprt *xprt)
 {
 	struct svc_pool *pool;
 	struct svc_rqst	*rqstp = NULL;
@@ -402,6 +401,7 @@ redo_search:
 out:
 	trace_svc_xprt_do_enqueue(xprt, rqstp);
 }
+EXPORT_SYMBOL_GPL(svc_xprt_do_enqueue);
 
 /*
  * Queue up a transport with data pending. If there are idle nfsd
@@ -412,7 +412,7 @@ void svc_xprt_enqueue(struct svc_xprt *xprt)
 {
 	if (test_bit(XPT_BUSY, &xprt->xpt_flags))
 		return;
-	svc_xprt_do_enqueue(xprt);
+	xprt->xpt_server->sv_ops->svo_enqueue_xprt(xprt);
 }
 EXPORT_SYMBOL_GPL(svc_xprt_enqueue);
 
diff --git a/net/sunrpc/xprtrdma/svc_rdma_sendto.c b/net/sunrpc/xprtrdma/svc_rdma_sendto.c
index d25cd430f9ff..1dfae8317065 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_sendto.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_sendto.c
@@ -136,6 +136,79 @@ static dma_addr_t dma_map_xdr(struct svcxprt_rdma *xprt,
 	return dma_addr;
 }
 
+/* Returns the address of the first read chunk or <nul> if no read chunk
+ * is present
+ */
+struct rpcrdma_read_chunk *
+svc_rdma_get_read_chunk(struct rpcrdma_msg *rmsgp)
+{
+	struct rpcrdma_read_chunk *ch =
+		(struct rpcrdma_read_chunk *)&rmsgp->rm_body.rm_chunks[0];
+
+	if (ch->rc_discrim == xdr_zero)
+		return NULL;
+	return ch;
+}
+
+/* Returns the address of the first read write array element or <nul>
+ * if no write array list is present
+ */
+static struct rpcrdma_write_array *
+svc_rdma_get_write_array(struct rpcrdma_msg *rmsgp)
+{
+	if (rmsgp->rm_body.rm_chunks[0] != xdr_zero ||
+	    rmsgp->rm_body.rm_chunks[1] == xdr_zero)
+		return NULL;
+	return (struct rpcrdma_write_array *)&rmsgp->rm_body.rm_chunks[1];
+}
+
+/* Returns the address of the first reply array element or <nul> if no
+ * reply array is present
+ */
+static struct rpcrdma_write_array *
+svc_rdma_get_reply_array(struct rpcrdma_msg *rmsgp)
+{
+	struct rpcrdma_read_chunk *rch;
+	struct rpcrdma_write_array *wr_ary;
+	struct rpcrdma_write_array *rp_ary;
+
+	/* XXX: Need to fix when reply chunk may occur with read list
+	 *	and/or write list.
+	 */
+	if (rmsgp->rm_body.rm_chunks[0] != xdr_zero ||
+	    rmsgp->rm_body.rm_chunks[1] != xdr_zero)
+		return NULL;
+
+	rch = svc_rdma_get_read_chunk(rmsgp);
+	if (rch) {
+		while (rch->rc_discrim != xdr_zero)
+			rch++;
+
+		/* The reply chunk follows an empty write array located
+		 * at 'rc_position' here. The reply array is at rc_target.
+		 */
+		rp_ary = (struct rpcrdma_write_array *)&rch->rc_target;
+		goto found_it;
+	}
+
+	wr_ary = svc_rdma_get_write_array(rmsgp);
+	if (wr_ary) {
+		int chunk = be32_to_cpu(wr_ary->wc_nchunks);
+
+		rp_ary = (struct rpcrdma_write_array *)
+			 &wr_ary->wc_array[chunk].wc_target.rs_length;
+		goto found_it;
+	}
+
+	/* No read list, no write list */
+	rp_ary = (struct rpcrdma_write_array *)&rmsgp->rm_body.rm_chunks[2];
+
+ found_it:
+	if (rp_ary->wc_discrim == xdr_zero)
+		return NULL;
+	return rp_ary;
+}
+
 /* Assumptions:
  * - The specified write_len can be represented in sc_max_sge * PAGE_SIZE
  */
@@ -384,6 +457,7 @@ static int send_reply(struct svcxprt_rdma *rdma,
 		      int byte_count)
 {
 	struct ib_send_wr send_wr;
+	u32 xdr_off;
 	int sge_no;
 	int sge_bytes;
 	int page_no;
@@ -418,8 +492,8 @@ static int send_reply(struct svcxprt_rdma *rdma,
 	ctxt->direction = DMA_TO_DEVICE;
 
 	/* Map the payload indicated by 'byte_count' */
+	xdr_off = 0;
 	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;
 		ctxt->sge[sge_no].addr =
@@ -457,6 +531,13 @@ static int send_reply(struct svcxprt_rdma *rdma,
 	}
 	rqstp->rq_next_page = rqstp->rq_respages + 1;
 
+	/* The loop above bumps sc_dma_used for each sge. The
+	 * xdr_buf.tail gets a separate sge, but resides in the
+	 * same page as xdr_buf.head. Don't count it twice.
+	 */
+	if (sge_no > ctxt->count)
+		atomic_dec(&rdma->sc_dma_used);
+
 	if (sge_no > rdma->sc_max_sge) {
 		pr_err("svcrdma: Too many sges (%d)\n", sge_no);
 		goto err;
diff --git a/net/sunrpc/xprtrdma/svc_rdma_transport.c b/net/sunrpc/xprtrdma/svc_rdma_transport.c
index 6b36279e4288..21e40365042c 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_transport.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_transport.c
@@ -91,7 +91,7 @@ struct svc_xprt_class svc_rdma_class = {
 	.xcl_name = "rdma",
 	.xcl_owner = THIS_MODULE,
 	.xcl_ops = &svc_rdma_ops,
-	.xcl_max_payload = RPCRDMA_MAXPAYLOAD,
+	.xcl_max_payload = RPCSVC_MAXPAYLOAD_RDMA,
 	.xcl_ident = XPRT_TRANSPORT_RDMA,
 };
 
@@ -659,6 +659,7 @@ static int rdma_cma_handler(struct rdma_cm_id *cma_id,
 		if (xprt) {
 			set_bit(XPT_CLOSE, &xprt->xpt_flags);
 			svc_xprt_enqueue(xprt);
+			svc_xprt_put(xprt);
 		}
 		break;
 	default:
@@ -1201,40 +1202,6 @@ static int svc_rdma_secure_port(struct svc_rqst *rqstp)
 	return 1;
 }
 
-/*
- * Attempt to register the kvec representing the RPC memory with the
- * device.
- *
- * Returns:
- *  NULL : The device does not support fastreg or there were no more
- *         fastreg mr.
- *  frmr : The kvec register request was successfully posted.
- *    <0 : An error was encountered attempting to register the kvec.
- */
-int svc_rdma_fastreg(struct svcxprt_rdma *xprt,
-		     struct svc_rdma_fastreg_mr *frmr)
-{
-	struct ib_send_wr fastreg_wr;
-	u8 key;
-
-	/* Bump the key */
-	key = (u8)(frmr->mr->lkey & 0x000000FF);
-	ib_update_fast_reg_key(frmr->mr, ++key);
-
-	/* Prepare FASTREG WR */
-	memset(&fastreg_wr, 0, sizeof fastreg_wr);
-	fastreg_wr.opcode = IB_WR_FAST_REG_MR;
-	fastreg_wr.send_flags = IB_SEND_SIGNALED;
-	fastreg_wr.wr.fast_reg.iova_start = (unsigned long)frmr->kva;
-	fastreg_wr.wr.fast_reg.page_list = frmr->page_list;
-	fastreg_wr.wr.fast_reg.page_list_len = frmr->page_list_len;
-	fastreg_wr.wr.fast_reg.page_shift = PAGE_SHIFT;
-	fastreg_wr.wr.fast_reg.length = frmr->map_len;
-	fastreg_wr.wr.fast_reg.access_flags = frmr->access_flags;
-	fastreg_wr.wr.fast_reg.rkey = frmr->mr->lkey;
-	return svc_rdma_send(xprt, &fastreg_wr);
-}
-
 int svc_rdma_send(struct svcxprt_rdma *xprt, struct ib_send_wr *wr)
 {
 	struct ib_send_wr *bad_wr, *n_wr;
diff --git a/net/sunrpc/xprtrdma/xprt_rdma.h b/net/sunrpc/xprtrdma/xprt_rdma.h
index f49dd8b38122..e718d0959af3 100644
--- a/net/sunrpc/xprtrdma/xprt_rdma.h
+++ b/net/sunrpc/xprtrdma/xprt_rdma.h
@@ -51,7 +51,6 @@
 #include <linux/sunrpc/clnt.h> 		/* rpc_xprt */
 #include <linux/sunrpc/rpc_rdma.h> 	/* RPC/RDMA protocol */
 #include <linux/sunrpc/xprtrdma.h> 	/* xprt parameters */
-#include <linux/sunrpc/svc.h>		/* RPCSVC_MAXPAYLOAD */
 
 #define RDMA_RESOLVE_TIMEOUT	(5000)	/* 5 seconds */
 #define RDMA_CONNECT_RETRY_MAX	(2)	/* retries if no listener backlog */