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
  ...

Documentation/filesystems/nfs/nfs-rdma.txt

@@ -138,9 +138,9 @@ Installation
   - Build, install, reboot
 
     The NFS/RDMA code will be enabled automatically if NFS and RDMA
-    are turned on. The NFS/RDMA client and server are configured via the
-    SUNRPC_XPRT_RDMA_CLIENT and SUNRPC_XPRT_RDMA_SERVER config options that both
-    depend on SUNRPC and INFINIBAND. The default value of both options will be:
+    are turned on. The NFS/RDMA client and server are configured via the hidden
+    SUNRPC_XPRT_RDMA config option that depends on SUNRPC and INFINIBAND. The
+    value of SUNRPC_XPRT_RDMA will be:
 
      - N if either SUNRPC or INFINIBAND are N, in this case the NFS/RDMA client
        and server will not be built
@@ -238,9 +238,8 @@ NFS/RDMA Setup
 
   - Start the NFS server
 
-    If the NFS/RDMA server was built as a module
-    (CONFIG_SUNRPC_XPRT_RDMA_SERVER=m in kernel config), load the RDMA
-    transport module:
+    If the NFS/RDMA server was built as a module (CONFIG_SUNRPC_XPRT_RDMA=m in
+    kernel config), load the RDMA transport module:
 
     $ modprobe svcrdma
 
@@ -259,9 +258,8 @@ NFS/RDMA Setup
 
   - On the client system
 
-    If the NFS/RDMA client was built as a module
-    (CONFIG_SUNRPC_XPRT_RDMA_CLIENT=m in kernel config), load the RDMA client
-    module:
+    If the NFS/RDMA client was built as a module (CONFIG_SUNRPC_XPRT_RDMA=m in
+    kernel config), load the RDMA client module:
 
     $ modprobe xprtrdma.ko
 

fs/lockd/svc.c

@@ -322,6 +322,11 @@ static int lockd_start_svc(struct svc_serv *serv)
 	return error;
 }
 
+static struct svc_serv_ops lockd_sv_ops = {
+	.svo_shutdown		= svc_rpcb_cleanup,
+	.svo_enqueue_xprt	= svc_xprt_do_enqueue,
+};
+
 static struct svc_serv *lockd_create_svc(void)
 {
 	struct svc_serv *serv;
@@ -350,7 +355,7 @@ static struct svc_serv *lockd_create_svc(void)
 		nlm_timeout = LOCKD_DFLT_TIMEO;
 	nlmsvc_timeout = nlm_timeout * HZ;
 
-	serv = svc_create(&nlmsvc_program, LOCKD_BUFSIZE, svc_rpcb_cleanup);
+	serv = svc_create(&nlmsvc_program, LOCKD_BUFSIZE, &lockd_sv_ops);
 	if (!serv) {
 		printk(KERN_WARNING "lockd_up: create service failed\n");
 		return ERR_PTR(-ENOMEM);
@@ -586,6 +591,7 @@ static int lockd_init_net(struct net *net)
 
 	INIT_DELAYED_WORK(&ln->grace_period_end, grace_ender);
 	INIT_LIST_HEAD(&ln->lockd_manager.list);
+	ln->lockd_manager.block_opens = false;
 	spin_lock_init(&ln->nsm_clnt_lock);
 	return 0;
 }

fs/locks.c

@@ -1568,6 +1568,7 @@ int fcntl_getlease(struct file *filp)
  * 			    desired lease.
  * @dentry:	dentry to check
  * @arg:	type of lease that we're trying to acquire
+ * @flags:	current lock flags
  *
  * Check to see if there's an existing open fd on this file that would
  * conflict with the lease we're trying to set.

fs/nfs/callback.c

@@ -308,6 +308,10 @@ static int nfs_callback_up_net(int minorversion, struct svc_serv *serv, struct n
 	return ret;
 }
 
+static struct svc_serv_ops nfs_cb_sv_ops = {
+	.svo_enqueue_xprt	= svc_xprt_do_enqueue,
+};
+
 static struct svc_serv *nfs_callback_create_svc(int minorversion)
 {
 	struct nfs_callback_data *cb_info = &nfs_callback_info[minorversion];
@@ -333,7 +337,7 @@ static struct svc_serv *nfs_callback_create_svc(int minorversion)
 		printk(KERN_WARNING "nfs_callback_create_svc: no kthread, %d users??\n",
 			cb_info->users);
 
-	serv = svc_create(&nfs4_callback_program, NFS4_CALLBACK_BUFSIZE, NULL);
+	serv = svc_create(&nfs4_callback_program, NFS4_CALLBACK_BUFSIZE, &nfs_cb_sv_ops);
 	if (!serv) {
 		printk(KERN_ERR "nfs_callback_create_svc: create service failed\n");
 		return ERR_PTR(-ENOMEM);

fs/nfs_common/grace.c

@@ -63,14 +63,33 @@ EXPORT_SYMBOL_GPL(locks_end_grace);
  * lock reclaims.
  */
 int
-locks_in_grace(struct net *net)
+__state_in_grace(struct net *net, bool open)
 {
 	struct list_head *grace_list = net_generic(net, grace_net_id);
+	struct lock_manager *lm;
 
-	return !list_empty(grace_list);
+	if (!open)
+		return !list_empty(grace_list);
+
+	list_for_each_entry(lm, grace_list, list) {
+		if (lm->block_opens)
+			return true;
+	}
+	return false;
+}
+
+int locks_in_grace(struct net *net)
+{
+	return __state_in_grace(net, 0);
 }
 EXPORT_SYMBOL_GPL(locks_in_grace);
 
+int opens_in_grace(struct net *net)
+{
+	return __state_in_grace(net, 1);
+}
+EXPORT_SYMBOL_GPL(opens_in_grace);
+
 static int __net_init
 grace_init_net(struct net *net)
 {

fs/nfsd/export.c

@@ -1075,73 +1075,6 @@ exp_pseudoroot(struct svc_rqst *rqstp, struct svc_fh *fhp)
 	return rv;
 }
 
-/* Iterator */
-
-static void *e_start(struct seq_file *m, loff_t *pos)
-	__acquires(((struct cache_detail *)m->private)->hash_lock)
-{
-	loff_t n = *pos;
-	unsigned hash, export;
-	struct cache_head *ch;
-	struct cache_detail *cd = m->private;
-	struct cache_head **export_table = cd->hash_table;
-
-	read_lock(&cd->hash_lock);
-	if (!n--)
-		return SEQ_START_TOKEN;
-	hash = n >> 32;
-	export = n & ((1LL<<32) - 1);
-
-	
-	for (ch=export_table[hash]; ch; ch=ch->next)
-		if (!export--)
-			return ch;
-	n &= ~((1LL<<32) - 1);
-	do {
-		hash++;
-		n += 1LL<<32;
-	} while(hash < EXPORT_HASHMAX && export_table[hash]==NULL);
-	if (hash >= EXPORT_HASHMAX)
-		return NULL;
-	*pos = n+1;
-	return export_table[hash];
-}
-
-static void *e_next(struct seq_file *m, void *p, loff_t *pos)
-{
-	struct cache_head *ch = p;
-	int hash = (*pos >> 32);
-	struct cache_detail *cd = m->private;
-	struct cache_head **export_table = cd->hash_table;
-
-	if (p == SEQ_START_TOKEN)
-		hash = 0;
-	else if (ch->next == NULL) {
-		hash++;
-		*pos += 1LL<<32;
-	} else {
-		++*pos;
-		return ch->next;
-	}
-	*pos &= ~((1LL<<32) - 1);
-	while (hash < EXPORT_HASHMAX && export_table[hash] == NULL) {
-		hash++;
-		*pos += 1LL<<32;
-	}
-	if (hash >= EXPORT_HASHMAX)
-		return NULL;
-	++*pos;
-	return export_table[hash];
-}
-
-static void e_stop(struct seq_file *m, void *p)
-	__releases(((struct cache_detail *)m->private)->hash_lock)
-{
-	struct cache_detail *cd = m->private;
-
-	read_unlock(&cd->hash_lock);
-}
-
 static struct flags {
 	int flag;
 	char *name[2];
@@ -1270,9 +1203,9 @@ static int e_show(struct seq_file *m, void *p)
 }
 
 const struct seq_operations nfs_exports_op = {
-	.start	= e_start,
-	.next	= e_next,
-	.stop	= e_stop,
+	.start	= cache_seq_start,
+	.next	= cache_seq_next,
+	.stop	= cache_seq_stop,
 	.show	= e_show,
 };
 

fs/nfsd/export.h

@@ -6,6 +6,7 @@
 
 #include <linux/sunrpc/cache.h>
 #include <uapi/linux/nfsd/export.h>
+#include <linux/nfs4.h>
 
 struct knfsd_fh;
 struct svc_fh;

fs/nfsd/idmap.h

@@ -37,9 +37,7 @@
 
 #include <linux/in.h>
 #include <linux/sunrpc/svc.h>
-
-/* XXX from linux/nfs_idmap.h */
-#define IDMAP_NAMESZ 128
+#include <linux/nfs_idmap.h>
 
 #ifdef CONFIG_NFSD_V4
 int nfsd_idmap_init(struct net *);

fs/nfsd/netns.h

@@ -110,6 +110,7 @@ struct nfsd_net {
 	unsigned int max_connections;
 
 	u32 clientid_counter;
+	u32 clverifier_counter;
 
 	struct svc_serv *nfsd_serv;
 };

fs/nfsd/nfs2acl.c

@@ -44,13 +44,13 @@ static __be32 nfsacld_proc_getacl(struct svc_rqst * rqstp,
 
 	inode = d_inode(fh->fh_dentry);
 
-	if (argp->mask & ~(NFS_ACL|NFS_ACLCNT|NFS_DFACL|NFS_DFACLCNT))
+	if (argp->mask & ~NFS_ACL_MASK)
 		RETURN_STATUS(nfserr_inval);
 	resp->mask = argp->mask;
 
 	nfserr = fh_getattr(fh, &resp->stat);
 	if (nfserr)
-		goto fail;
+		RETURN_STATUS(nfserr);
 
 	if (resp->mask & (NFS_ACL|NFS_ACLCNT)) {
 		acl = get_acl(inode, ACL_TYPE_ACCESS);
@@ -202,7 +202,7 @@ static int nfsaclsvc_decode_setaclargs(struct svc_rqst *rqstp, __be32 *p,
 	if (!p)
 		return 0;
 	argp->mask = ntohl(*p++);
-	if (argp->mask & ~(NFS_ACL|NFS_ACLCNT|NFS_DFACL|NFS_DFACLCNT) ||
+	if (argp->mask & ~NFS_ACL_MASK ||
 	    !xdr_argsize_check(rqstp, p))
 		return 0;
 
@@ -293,9 +293,7 @@ static int nfsaclsvc_encode_getaclres(struct svc_rqst *rqstp, __be32 *p,
 				  resp->acl_default,
 				  resp->mask & NFS_DFACL,
 				  NFS_ACL_DEFAULT);
-	if (n <= 0)
-		return 0;
-	return 1;
+	return (n > 0);
 }
 
 static int nfsaclsvc_encode_attrstatres(struct svc_rqst *rqstp, __be32 *p,

fs/nfsd/nfs3acl.c

@@ -41,7 +41,7 @@ static __be32 nfsd3_proc_getacl(struct svc_rqst * rqstp,
 
 	inode = d_inode(fh->fh_dentry);
 
-	if (argp->mask & ~(NFS_ACL|NFS_ACLCNT|NFS_DFACL|NFS_DFACLCNT))
+	if (argp->mask & ~NFS_ACL_MASK)
 		RETURN_STATUS(nfserr_inval);
 	resp->mask = argp->mask;
 
@@ -148,7 +148,7 @@ static int nfs3svc_decode_setaclargs(struct svc_rqst *rqstp, __be32 *p,
 	if (!p)
 		return 0;
 	args->mask = ntohl(*p++);
-	if (args->mask & ~(NFS_ACL|NFS_ACLCNT|NFS_DFACL|NFS_DFACLCNT) ||
+	if (args->mask & ~NFS_ACL_MASK ||
 	    !xdr_argsize_check(rqstp, p))
 		return 0;
 

fs/nfsd/nfs4acl.c

@@ -34,8 +34,10 @@
  *  SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
  */
 
+#include <linux/fs.h>
 #include <linux/slab.h>
-#include <linux/nfs_fs.h>
+#include <linux/posix_acl.h>
+
 #include "nfsfh.h"
 #include "nfsd.h"
 #include "acl.h"
@@ -100,7 +102,7 @@ deny_mask_from_posix(unsigned short perm, u32 flags)
 /* We only map from NFSv4 to POSIX ACLs when setting ACLs, when we err on the
  * side of being more restrictive, so the mode bit mapping below is
  * pessimistic.  An optimistic version would be needed to handle DENY's,
- * but we espect to coalesce all ALLOWs and DENYs before mapping to mode
+ * but we expect to coalesce all ALLOWs and DENYs before mapping to mode
  * bits. */
 
 static void
@@ -458,7 +460,7 @@ init_state(struct posix_acl_state *state, int cnt)
 	state->empty = 1;
 	/*
 	 * In the worst case, each individual acl could be for a distinct
-	 * named user or group, but we don't no which, so we allocate
+	 * named user or group, but we don't know which, so we allocate
 	 * enough space for either:
 	 */
 	alloc = sizeof(struct posix_ace_state_array)

fs/nfsd/nfs4callback.c

@@ -435,12 +435,12 @@ static int decode_cb_sequence4resok(struct xdr_stream *xdr,
 	 */
 	status = 0;
 out:
-	if (status)
-		nfsd4_mark_cb_fault(cb->cb_clp, status);
+	cb->cb_seq_status = status;
 	return status;
 out_overflow:
 	print_overflow_msg(__func__, xdr);
-	return -EIO;
+	status = -EIO;
+	goto out;
 }
 
 static int decode_cb_sequence4res(struct xdr_stream *xdr,
@@ -451,11 +451,10 @@ static int decode_cb_sequence4res(struct xdr_stream *xdr,
 	if (cb->cb_minorversion == 0)
 		return 0;
 
-	status = decode_cb_op_status(xdr, OP_CB_SEQUENCE, &cb->cb_status);
-	if (unlikely(status || cb->cb_status))
+	status = decode_cb_op_status(xdr, OP_CB_SEQUENCE, &cb->cb_seq_status);
+	if (unlikely(status || cb->cb_seq_status))
 		return status;
 
-	cb->cb_update_seq_nr = true;
 	return decode_cb_sequence4resok(xdr, cb);
 }
 
@@ -527,7 +526,7 @@ static int nfs4_xdr_dec_cb_recall(struct rpc_rqst *rqstp,
 
 	if (cb != NULL) {
 		status = decode_cb_sequence4res(xdr, cb);
-		if (unlikely(status || cb->cb_status))
+		if (unlikely(status || cb->cb_seq_status))
 			return status;
 	}
 
@@ -617,7 +616,7 @@ static int nfs4_xdr_dec_cb_layout(struct rpc_rqst *rqstp,
 
 	if (cb) {
 		status = decode_cb_sequence4res(xdr, cb);
-		if (unlikely(status || cb->cb_status))
+		if (unlikely(status || cb->cb_seq_status))
 			return status;
 	}
 	return decode_cb_op_status(xdr, OP_CB_LAYOUTRECALL, &cb->cb_status);
@@ -876,7 +875,11 @@ static void nfsd4_cb_prepare(struct rpc_task *task, void *calldata)
 	u32 minorversion = clp->cl_minorversion;
 
 	cb->cb_minorversion = minorversion;
-	cb->cb_update_seq_nr = false;
+	/*
+	 * cb_seq_status is only set in decode_cb_sequence4res,
+	 * and so will remain 1 if an rpc level failure occurs.
+	 */
+	cb->cb_seq_status = 1;
 	cb->cb_status = 0;
 	if (minorversion) {
 		if (!nfsd41_cb_get_slot(clp, task))
@@ -885,15 +888,30 @@ static void nfsd4_cb_prepare(struct rpc_task *task, void *calldata)
 	rpc_call_start(task);
 }
 
-static void nfsd4_cb_done(struct rpc_task *task, void *calldata)
+static bool nfsd4_cb_sequence_done(struct rpc_task *task, struct nfsd4_callback *cb)
 {
-	struct nfsd4_callback *cb = calldata;
 	struct nfs4_client *clp = cb->cb_clp;
+	struct nfsd4_session *session = clp->cl_cb_session;
+	bool ret = true;
 
-	dprintk("%s: minorversion=%d\n", __func__,
-		clp->cl_minorversion);
+	if (!clp->cl_minorversion) {
+		/*
+		 * If the backchannel connection was shut down while this
+		 * task was queued, we need to resubmit it after setting up
+		 * a new backchannel connection.
+		 *
+		 * Note that if we lost our callback connection permanently
+		 * the submission code will error out, so we don't need to
+		 * handle that case here.
+		 */
+		if (task->tk_flags & RPC_TASK_KILLED)
+			goto need_restart;
+
+		return true;
+	}
 
-	if (clp->cl_minorversion) {
+	switch (cb->cb_seq_status) {
+	case 0:
 		/*
 		 * No need for lock, access serialized in nfsd4_cb_prepare
 		 *
@@ -901,29 +919,63 @@ static void nfsd4_cb_done(struct rpc_task *task, void *calldata)
 		 * If CB_SEQUENCE returns an error, then the state of the slot
 		 * (sequence ID, cached reply) MUST NOT change.
 		 */
-		if (cb->cb_update_seq_nr)
-			++clp->cl_cb_session->se_cb_seq_nr;
-
-		clear_bit(0, &clp->cl_cb_slot_busy);
-		rpc_wake_up_next(&clp->cl_cb_waitq);
-		dprintk("%s: freed slot, new seqid=%d\n", __func__,
-			clp->cl_cb_session->se_cb_seq_nr);
+		++session->se_cb_seq_nr;
+		break;
+	case -ESERVERFAULT:
+		++session->se_cb_seq_nr;
+	case 1:
+	case -NFS4ERR_BADSESSION:
+		nfsd4_mark_cb_fault(cb->cb_clp, cb->cb_seq_status);
+		ret = false;
+		break;
+	case -NFS4ERR_DELAY:
+		if (!rpc_restart_call(task))
+			goto out;
+
+		rpc_delay(task, 2 * HZ);
+		return false;
+	case -NFS4ERR_BADSLOT:
+		goto retry_nowait;
+	case -NFS4ERR_SEQ_MISORDERED:
+		if (session->se_cb_seq_nr != 1) {
+			session->se_cb_seq_nr = 1;
+			goto retry_nowait;
+		}
+		break;
+	default:
+		dprintk("%s: unprocessed error %d\n", __func__,
+			cb->cb_seq_status);
 	}
 
-	/*
-	 * If the backchannel connection was shut down while this
-	 * task was queued, we need to resubmit it after setting up
-	 * a new backchannel connection.
-	 *
-	 * Note that if we lost our callback connection permanently
-	 * the submission code will error out, so we don't need to
-	 * handle that case here.
-	 */
-	if (task->tk_flags & RPC_TASK_KILLED) {
-		task->tk_status = 0;
-		cb->cb_need_restart = true;
+	clear_bit(0, &clp->cl_cb_slot_busy);
+	rpc_wake_up_next(&clp->cl_cb_waitq);
+	dprintk("%s: freed slot, new seqid=%d\n", __func__,
+		clp->cl_cb_session->se_cb_seq_nr);
+
+	if (task->tk_flags & RPC_TASK_KILLED)
+		goto need_restart;
+out:
+	return ret;
+retry_nowait:
+	if (rpc_restart_call_prepare(task))
+		ret = false;
+	goto out;
+need_restart:
+	task->tk_status = 0;
+	cb->cb_need_restart = true;
+	return false;
+}
+
+static void nfsd4_cb_done(struct rpc_task *task, void *calldata)
+{
+	struct nfsd4_callback *cb = calldata;
+	struct nfs4_client *clp = cb->cb_clp;
+
+	dprintk("%s: minorversion=%d\n", __func__,
+		clp->cl_minorversion);
+
+	if (!nfsd4_cb_sequence_done(task, cb))
 		return;
-	}
 
 	if (cb->cb_status) {
 		WARN_ON_ONCE(task->tk_status);
@@ -1099,8 +1151,8 @@ void nfsd4_init_cb(struct nfsd4_callback *cb, struct nfs4_client *clp,
 	cb->cb_msg.rpc_resp = cb;
 	cb->cb_ops = ops;
 	INIT_WORK(&cb->cb_work, nfsd4_run_cb_work);
+	cb->cb_seq_status = 1;
 	cb->cb_status = 0;
-	cb->cb_update_seq_nr = false;
 	cb->cb_need_restart = false;
 }
 

fs/nfsd/nfs4idmap.c

@@ -59,9 +59,6 @@ MODULE_PARM_DESC(nfs4_disable_idmapping,
  * that.
  */
 
-#define IDMAP_TYPE_USER  0
-#define IDMAP_TYPE_GROUP 1
-
 struct ent {
 	struct cache_head h;
 	int               type;		       /* User / Group */

fs/nfsd/nfs4proc.c

@@ -276,13 +276,13 @@ do_open_lookup(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, stru
 			nfsd4_security_inode_setsecctx(*resfh, &open->op_label, open->op_bmval);
 
 		/*
-		 * Following rfc 3530 14.2.16, use the returned bitmask
-		 * to indicate which attributes we used to store the
-		 * verifier:
+		 * Following rfc 3530 14.2.16, and rfc 5661 18.16.4
+		 * use the returned bitmask to indicate which attributes
+		 * we used to store the verifier:
 		 */
-		if (open->op_createmode == NFS4_CREATE_EXCLUSIVE && status == 0)
-			open->op_bmval[1] = (FATTR4_WORD1_TIME_ACCESS |
-							FATTR4_WORD1_TIME_MODIFY);
+		if (nfsd_create_is_exclusive(open->op_createmode) && status == 0)
+			open->op_bmval[1] |= (FATTR4_WORD1_TIME_ACCESS |
+						FATTR4_WORD1_TIME_MODIFY);
 	} else
 		/*
 		 * Note this may exit with the parent still locked.
@@ -362,7 +362,6 @@ nfsd4_open(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 {
 	__be32 status;
 	struct svc_fh *resfh = NULL;
-	struct nfsd4_compoundres *resp;
 	struct net *net = SVC_NET(rqstp);
 	struct nfsd_net *nn = net_generic(net, nfsd_net_id);
 
@@ -389,8 +388,7 @@ nfsd4_open(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 		copy_clientid(&open->op_clientid, cstate->session);
 
 	/* check seqid for replay. set nfs4_owner */
-	resp = rqstp->rq_resp;
-	status = nfsd4_process_open1(&resp->cstate, open, nn);
+	status = nfsd4_process_open1(cstate, open, nn);
 	if (status == nfserr_replay_me) {
 		struct nfs4_replay *rp = &open->op_openowner->oo_owner.so_replay;
 		fh_put(&cstate->current_fh);
@@ -417,10 +415,10 @@ nfsd4_open(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 	/* Openowner is now set, so sequence id will get bumped.  Now we need
 	 * these checks before we do any creates: */
 	status = nfserr_grace;
-	if (locks_in_grace(net) && open->op_claim_type != NFS4_OPEN_CLAIM_PREVIOUS)
+	if (opens_in_grace(net) && open->op_claim_type != NFS4_OPEN_CLAIM_PREVIOUS)
 		goto out;
 	status = nfserr_no_grace;
-	if (!locks_in_grace(net) && open->op_claim_type == NFS4_OPEN_CLAIM_PREVIOUS)
+	if (!opens_in_grace(net) && open->op_claim_type == NFS4_OPEN_CLAIM_PREVIOUS)
 		goto out;
 
 	switch (open->op_claim_type) {
@@ -829,7 +827,7 @@ nfsd4_remove(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 {
 	__be32 status;
 
-	if (locks_in_grace(SVC_NET(rqstp)))
+	if (opens_in_grace(SVC_NET(rqstp)))
 		return nfserr_grace;
 	status = nfsd_unlink(rqstp, &cstate->current_fh, 0,
 			     remove->rm_name, remove->rm_namelen);
@@ -848,7 +846,7 @@ nfsd4_rename(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 
 	if (!cstate->save_fh.fh_dentry)
 		return status;
-	if (locks_in_grace(SVC_NET(rqstp)) &&
+	if (opens_in_grace(SVC_NET(rqstp)) &&
 		!(cstate->save_fh.fh_export->ex_flags & NFSEXP_NOSUBTREECHECK))
 		return nfserr_grace;
 	status = nfsd_rename(rqstp, &cstate->save_fh, rename->rn_sname,
@@ -1364,10 +1362,6 @@ nfsd4_layoutcommit(struct svc_rqst *rqstp,
 		goto out;
 	}
 
-	nfserr = ops->proc_layoutcommit(inode, lcp);
-	if (nfserr)
-		goto out_put_stid;
-
 	if (new_size > i_size_read(inode)) {
 		lcp->lc_size_chg = 1;
 		lcp->lc_newsize = new_size;
@@ -1375,7 +1369,7 @@ nfsd4_layoutcommit(struct svc_rqst *rqstp,
 		lcp->lc_size_chg = 0;
 	}
 
-out_put_stid:
+	nfserr = ops->proc_layoutcommit(inode, lcp);
 	nfs4_put_stid(&ls->ls_stid);
 out:
 	return nfserr;

fs/nfsd/nfs4recover.c

@@ -272,6 +272,7 @@ nfsd4_list_rec_dir(recdir_func *f, struct nfsd_net *nn)
 		.ctx.actor = nfsd4_build_namelist,
 		.names = LIST_HEAD_INIT(ctx.names)
 	};
+	struct name_list *entry, *tmp;
 	int status;
 
 	status = nfs4_save_creds(&original_cred);
@@ -286,9 +287,8 @@ nfsd4_list_rec_dir(recdir_func *f, struct nfsd_net *nn)
 
 	status = iterate_dir(nn->rec_file, &ctx.ctx);
 	mutex_lock_nested(&d_inode(dir)->i_mutex, I_MUTEX_PARENT);
-	while (!list_empty(&ctx.names)) {
-		struct name_list *entry;
-		entry = list_entry(ctx.names.next, struct name_list, list);
+
+	list_for_each_entry_safe(entry, tmp, &ctx.names, list) {
 		if (!status) {
 			struct dentry *dentry;
 			dentry = lookup_one_len(entry->name, dir, HEXDIR_LEN-1);
@@ -304,6 +304,12 @@ nfsd4_list_rec_dir(recdir_func *f, struct nfsd_net *nn)
 	}
 	mutex_unlock(&d_inode(dir)->i_mutex);
 	nfs4_reset_creds(original_cred);
+
+	list_for_each_entry_safe(entry, tmp, &ctx.names, list) {
+		dprintk("NFSD: %s. Left entry %s\n", __func__, entry->name);
+		list_del(&entry->list);
+		kfree(entry);
+	}
 	return status;
 }
 
@@ -541,8 +547,7 @@ nfsd4_legacy_tracking_init(struct net *net)
 
 	/* XXX: The legacy code won't work in a container */
 	if (net != &init_net) {
-		WARN(1, KERN_ERR "NFSD: attempt to initialize legacy client "
-			"tracking in a container!\n");
+		pr_warn("NFSD: attempt to initialize legacy client tracking in a container ignored.\n");
 		return -EINVAL;
 	}
 
@@ -1254,8 +1259,7 @@ nfsd4_umh_cltrack_init(struct net *net)
 
 	/* XXX: The usermode helper s not working in container yet. */
 	if (net != &init_net) {
-		WARN(1, KERN_ERR "NFSD: attempt to initialize umh client "
-			"tracking in a container!\n");
+		pr_warn("NFSD: attempt to initialize umh client tracking in a container ignored.\n");
 		return -EINVAL;
 	}
 

fs/nfsd/nfs4xdr.c

@@ -2140,6 +2140,27 @@ nfsd4_encode_aclname(struct xdr_stream *xdr, struct svc_rqst *rqstp,
 		return nfsd4_encode_user(xdr, rqstp, ace->who_uid);
 }
 
+static inline __be32
+nfsd4_encode_layout_type(struct xdr_stream *xdr, enum pnfs_layouttype layout_type)
+{
+	__be32 *p;
+
+	if (layout_type) {
+		p = xdr_reserve_space(xdr, 8);
+		if (!p)
+			return nfserr_resource;
+		*p++ = cpu_to_be32(1);
+		*p++ = cpu_to_be32(layout_type);
+	} else {
+		p = xdr_reserve_space(xdr, 4);
+		if (!p)
+			return nfserr_resource;
+		*p++ = cpu_to_be32(0);
+	}
+
+	return 0;
+}
+
 #define WORD0_ABSENT_FS_ATTRS (FATTR4_WORD0_FS_LOCATIONS | FATTR4_WORD0_FSID | \
 			      FATTR4_WORD0_RDATTR_ERROR)
 #define WORD1_ABSENT_FS_ATTRS FATTR4_WORD1_MOUNTED_ON_FILEID
@@ -2205,6 +2226,39 @@ static int get_parent_attributes(struct svc_export *exp, struct kstat *stat)
 	return err;
 }
 
+static __be32
+nfsd4_encode_bitmap(struct xdr_stream *xdr, u32 bmval0, u32 bmval1, u32 bmval2)
+{
+	__be32 *p;
+
+	if (bmval2) {
+		p = xdr_reserve_space(xdr, 16);
+		if (!p)
+			goto out_resource;
+		*p++ = cpu_to_be32(3);
+		*p++ = cpu_to_be32(bmval0);
+		*p++ = cpu_to_be32(bmval1);
+		*p++ = cpu_to_be32(bmval2);
+	} else if (bmval1) {
+		p = xdr_reserve_space(xdr, 12);
+		if (!p)
+			goto out_resource;
+		*p++ = cpu_to_be32(2);
+		*p++ = cpu_to_be32(bmval0);
+		*p++ = cpu_to_be32(bmval1);
+	} else {
+		p = xdr_reserve_space(xdr, 8);
+		if (!p)
+			goto out_resource;
+		*p++ = cpu_to_be32(1);
+		*p++ = cpu_to_be32(bmval0);
+	}
+
+	return 0;
+out_resource:
+	return nfserr_resource;
+}
+
 /*
  * Note: @fhp can be NULL; in this case, we might have to compose the filehandle
  * ourselves.
@@ -2301,28 +2355,9 @@ nfsd4_encode_fattr(struct xdr_stream *xdr, struct svc_fh *fhp,
 	}
 #endif /* CONFIG_NFSD_V4_SECURITY_LABEL */
 
-	if (bmval2) {
-		p = xdr_reserve_space(xdr, 16);
-		if (!p)
-			goto out_resource;
-		*p++ = cpu_to_be32(3);
-		*p++ = cpu_to_be32(bmval0);
-		*p++ = cpu_to_be32(bmval1);
-		*p++ = cpu_to_be32(bmval2);
-	} else if (bmval1) {
-		p = xdr_reserve_space(xdr, 12);
-		if (!p)
-			goto out_resource;
-		*p++ = cpu_to_be32(2);
-		*p++ = cpu_to_be32(bmval0);
-		*p++ = cpu_to_be32(bmval1);
-	} else {
-		p = xdr_reserve_space(xdr, 8);
-		if (!p)
-			goto out_resource;
-		*p++ = cpu_to_be32(1);
-		*p++ = cpu_to_be32(bmval0);
-	}
+	status = nfsd4_encode_bitmap(xdr, bmval0, bmval1, bmval2);
+	if (status)
+		goto out;
 
 	attrlen_offset = xdr->buf->len;
 	p = xdr_reserve_space(xdr, 4);
@@ -2675,6 +2710,9 @@ nfsd4_encode_fattr(struct xdr_stream *xdr, struct svc_fh *fhp,
 		*p++ = cpu_to_be32(stat.mtime.tv_nsec);
 	}
 	if (bmval1 & FATTR4_WORD1_MOUNTED_ON_FILEID) {
+		struct kstat parent_stat;
+		u64 ino = stat.ino;
+
 		p = xdr_reserve_space(xdr, 8);
 		if (!p)
                 	goto out_resource;
@@ -2683,25 +2721,25 @@ nfsd4_encode_fattr(struct xdr_stream *xdr, struct svc_fh *fhp,
 		 * and this is the root of a cross-mounted filesystem.
 		 */
 		if (ignore_crossmnt == 0 &&
-		    dentry == exp->ex_path.mnt->mnt_root)
-			get_parent_attributes(exp, &stat);
-		p = xdr_encode_hyper(p, stat.ino);
+		    dentry == exp->ex_path.mnt->mnt_root) {
+			err = get_parent_attributes(exp, &parent_stat);
+			if (err)
+				goto out_nfserr;
+			ino = parent_stat.ino;
+		}
+		p = xdr_encode_hyper(p, ino);
 	}
 #ifdef CONFIG_NFSD_PNFS
-	if ((bmval1 & FATTR4_WORD1_FS_LAYOUT_TYPES) ||
-	    (bmval2 & FATTR4_WORD2_LAYOUT_TYPES)) {
-		if (exp->ex_layout_type) {
-			p = xdr_reserve_space(xdr, 8);
-			if (!p)
-				goto out_resource;
-			*p++ = cpu_to_be32(1);
-			*p++ = cpu_to_be32(exp->ex_layout_type);
-		} else {
-			p = xdr_reserve_space(xdr, 4);
-			if (!p)
-				goto out_resource;
-			*p++ = cpu_to_be32(0);
-		}
+	if (bmval1 & FATTR4_WORD1_FS_LAYOUT_TYPES) {
+		status = nfsd4_encode_layout_type(xdr, exp->ex_layout_type);
+		if (status)
+			goto out;
+	}
+
+	if (bmval2 & FATTR4_WORD2_LAYOUT_TYPES) {
+		status = nfsd4_encode_layout_type(xdr, exp->ex_layout_type);
+		if (status)
+			goto out;
 	}
 
 	if (bmval2 & FATTR4_WORD2_LAYOUT_BLKSIZE) {
@@ -2711,21 +2749,20 @@ nfsd4_encode_fattr(struct xdr_stream *xdr, struct svc_fh *fhp,
 		*p++ = cpu_to_be32(stat.blksize);
 	}
 #endif /* CONFIG_NFSD_PNFS */
+	if (bmval2 & FATTR4_WORD2_SUPPATTR_EXCLCREAT) {
+		status = nfsd4_encode_bitmap(xdr, NFSD_SUPPATTR_EXCLCREAT_WORD0,
+						  NFSD_SUPPATTR_EXCLCREAT_WORD1,
+						  NFSD_SUPPATTR_EXCLCREAT_WORD2);
+		if (status)
+			goto out;
+	}
+
 	if (bmval2 & FATTR4_WORD2_SECURITY_LABEL) {
 		status = nfsd4_encode_security_label(xdr, rqstp, context,
 								contextlen);
 		if (status)
 			goto out;
 	}
-	if (bmval2 & FATTR4_WORD2_SUPPATTR_EXCLCREAT) {
-		p = xdr_reserve_space(xdr, 16);
-		if (!p)
-			goto out_resource;
-		*p++ = cpu_to_be32(3);
-		*p++ = cpu_to_be32(NFSD_SUPPATTR_EXCLCREAT_WORD0);
-		*p++ = cpu_to_be32(NFSD_SUPPATTR_EXCLCREAT_WORD1);
-		*p++ = cpu_to_be32(NFSD_SUPPATTR_EXCLCREAT_WORD2);
-	}
 
 	attrlen = htonl(xdr->buf->len - attrlen_offset - 4);
 	write_bytes_to_xdr_buf(xdr->buf, attrlen_offset, &attrlen, 4);
@@ -3044,13 +3081,12 @@ nfsd4_encode_create(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_
 	__be32 *p;
 
 	if (!nfserr) {
-		p = xdr_reserve_space(xdr, 32);
+		p = xdr_reserve_space(xdr, 20);
 		if (!p)
 			return nfserr_resource;
-		p = encode_cinfo(p, &create->cr_cinfo);
-		*p++ = cpu_to_be32(2);
-		*p++ = cpu_to_be32(create->cr_bmval[0]);
-		*p++ = cpu_to_be32(create->cr_bmval[1]);
+		encode_cinfo(p, &create->cr_cinfo);
+		nfserr = nfsd4_encode_bitmap(xdr, create->cr_bmval[0],
+				create->cr_bmval[1], create->cr_bmval[2]);
 	}
 	return nfserr;
 }
@@ -3190,16 +3226,22 @@ nfsd4_encode_open(struct nfsd4_compoundres *resp, __be32 nfserr, struct nfsd4_op
 	nfserr = nfsd4_encode_stateid(xdr, &open->op_stateid);
 	if (nfserr)
 		goto out;
-	p = xdr_reserve_space(xdr, 40);
+	p = xdr_reserve_space(xdr, 24);
 	if (!p)
 		return nfserr_resource;
 	p = encode_cinfo(p, &open->op_cinfo);
 	*p++ = cpu_to_be32(open->op_rflags);
-	*p++ = cpu_to_be32(2);
-	*p++ = cpu_to_be32(open->op_bmval[0]);
-	*p++ = cpu_to_be32(open->op_bmval[1]);
-	*p++ = cpu_to_be32(open->op_delegate_type);
 
+	nfserr = nfsd4_encode_bitmap(xdr, open->op_bmval[0], open->op_bmval[1],
+					open->op_bmval[2]);
+	if (nfserr)
+		goto out;
+
+	p = xdr_reserve_space(xdr, 4);
+	if (!p)
+		return nfserr_resource;
+
+	*p++ = cpu_to_be32(open->op_delegate_type);
 	switch (open->op_delegate_type) {
 	case NFS4_OPEN_DELEGATE_NONE:
 		break;

fs/nfsd/nfssvc.c

@@ -391,6 +391,14 @@ static int nfsd_get_default_max_blksize(void)
 	return ret;
 }
 
+static struct svc_serv_ops nfsd_thread_sv_ops = {
+	.svo_shutdown		= nfsd_last_thread,
+	.svo_function		= nfsd,
+	.svo_enqueue_xprt	= svc_xprt_do_enqueue,
+	.svo_setup		= svc_set_num_threads,
+	.svo_module		= THIS_MODULE,
+};
+
 int nfsd_create_serv(struct net *net)
 {
 	int error;
@@ -405,7 +413,7 @@ int nfsd_create_serv(struct net *net)
 		nfsd_max_blksize = nfsd_get_default_max_blksize();
 	nfsd_reset_versions();
 	nn->nfsd_serv = svc_create_pooled(&nfsd_program, nfsd_max_blksize,
-				      nfsd_last_thread, nfsd, THIS_MODULE);
+						&nfsd_thread_sv_ops);
 	if (nn->nfsd_serv == NULL)
 		return -ENOMEM;
 
@@ -500,8 +508,8 @@ int nfsd_set_nrthreads(int n, int *nthreads, struct net *net)
 	/* apply the new numbers */
 	svc_get(nn->nfsd_serv);
 	for (i = 0; i < n; i++) {
-		err = svc_set_num_threads(nn->nfsd_serv, &nn->nfsd_serv->sv_pools[i],
-				    	  nthreads[i]);
+		err = nn->nfsd_serv->sv_ops->svo_setup(nn->nfsd_serv,
+				&nn->nfsd_serv->sv_pools[i], nthreads[i]);
 		if (err)
 			break;
 	}
@@ -540,7 +548,8 @@ nfsd_svc(int nrservs, struct net *net)
 	error = nfsd_startup_net(nrservs, net);
 	if (error)
 		goto out_destroy;
-	error = svc_set_num_threads(nn->nfsd_serv, NULL, nrservs);
+	error = nn->nfsd_serv->sv_ops->svo_setup(nn->nfsd_serv,
+			NULL, nrservs);
 	if (error)
 		goto out_shutdown;
 	/* We are holding a reference to nn->nfsd_serv which

fs/nfsd/state.h

@@ -67,8 +67,8 @@ struct nfsd4_callback {
 	struct rpc_message cb_msg;
 	struct nfsd4_callback_ops *cb_ops;
 	struct work_struct cb_work;
+	int cb_seq_status;
 	int cb_status;
-	bool cb_update_seq_nr;
 	bool cb_need_restart;
 };
 

fs/nfsd/vfs.c

@@ -1249,12 +1249,6 @@ nfsd_create(struct svc_rqst *rqstp, struct svc_fh *fhp,
 
 #ifdef CONFIG_NFSD_V3
 
-static inline int nfsd_create_is_exclusive(int createmode)
-{
-	return createmode == NFS3_CREATE_EXCLUSIVE
-	       || createmode == NFS4_CREATE_EXCLUSIVE4_1;
-}
-
 /*
  * NFSv3 and NFSv4 version of nfsd_create
  */

fs/nfsd/vfs.h

@@ -131,4 +131,10 @@ static inline __be32 fh_getattr(struct svc_fh *fh, struct kstat *stat)
 	return nfserrno(vfs_getattr(&p, stat));
 }
 
+static inline int nfsd_create_is_exclusive(int createmode)
+{
+	return createmode == NFS3_CREATE_EXCLUSIVE
+	       || createmode == NFS4_CREATE_EXCLUSIVE4_1;
+}
+
 #endif /* LINUX_NFSD_VFS_H */

include/linux/fs.h

@@ -943,12 +943,18 @@ struct lock_manager_operations {
 
 struct lock_manager {
 	struct list_head list;
+	/*
+	 * NFSv4 and up also want opens blocked during the grace period;
+	 * NLM doesn't care:
+	 */
+	bool block_opens;
 };
 
 struct net;
 void locks_start_grace(struct net *, struct lock_manager *);
 void locks_end_grace(struct lock_manager *);
 int locks_in_grace(struct net *);
+int opens_in_grace(struct net *);
 
 /* that will die - we need it for nfs_lock_info */
 #include <linux/nfs_fs_i.h>

include/linux/sunrpc/cache.h

@@ -46,7 +46,7 @@
  * 
  */
 struct cache_head {
-	struct cache_head * next;
+	struct hlist_node	cache_list;
 	time_t		expiry_time;	/* After time time, don't use the data */
 	time_t		last_refresh;   /* If CACHE_PENDING, this is when upcall 
 					 * was sent, else this is when update was received
@@ -73,7 +73,7 @@ struct cache_detail_pipefs {
 struct cache_detail {
 	struct module *		owner;
 	int			hash_size;
-	struct cache_head **	hash_table;
+	struct hlist_head *	hash_table;
 	rwlock_t		hash_lock;
 
 	atomic_t		inuse; /* active user-space update or lookup */
@@ -224,6 +224,11 @@ extern int sunrpc_cache_register_pipefs(struct dentry *parent, const char *,
 					umode_t, struct cache_detail *);
 extern void sunrpc_cache_unregister_pipefs(struct cache_detail *);
 
+/* Must store cache_detail in seq_file->private if using next three functions */
+extern void *cache_seq_start(struct seq_file *file, loff_t *pos);
+extern void *cache_seq_next(struct seq_file *file, void *p, loff_t *pos);
+extern void cache_seq_stop(struct seq_file *file, void *p);
+
 extern void qword_add(char **bpp, int *lp, char *str);
 extern void qword_addhex(char **bpp, int *lp, char *buf, int blen);
 extern int qword_get(char **bpp, char *dest, int bufsize);

include/linux/sunrpc/svc.h

@@ -19,11 +19,6 @@
 #include <linux/wait.h>
 #include <linux/mm.h>
 
-/*
- * This is the RPC server thread function prototype
- */
-typedef int		(*svc_thread_fn)(void *);
-
 /* statistics for svc_pool structures */
 struct svc_pool_stats {
 	atomic_long_t	packets;
@@ -54,6 +49,25 @@ struct svc_pool {
 	unsigned long		sp_flags;
 } ____cacheline_aligned_in_smp;
 
+struct svc_serv;
+
+struct svc_serv_ops {
+	/* Callback to use when last thread exits. */
+	void		(*svo_shutdown)(struct svc_serv *, struct net *);
+
+	/* function for service threads to run */
+	int		(*svo_function)(void *);
+
+	/* queue up a transport for servicing */
+	void		(*svo_enqueue_xprt)(struct svc_xprt *);
+
+	/* set up thread (or whatever) execution context */
+	int		(*svo_setup)(struct svc_serv *, struct svc_pool *, int);
+
+	/* optional module to count when adding threads (pooled svcs only) */
+	struct module	*svo_module;
+};
+
 /*
  * RPC service.
  *
@@ -85,16 +99,7 @@ struct svc_serv {
 
 	unsigned int		sv_nrpools;	/* number of thread pools */
 	struct svc_pool *	sv_pools;	/* array of thread pools */
-
-	void			(*sv_shutdown)(struct svc_serv *serv,
-					       struct net *net);
-						/* Callback to use when last thread
-						 * exits.
-						 */
-
-	struct module *		sv_module;	/* optional module to count when
-						 * adding threads */
-	svc_thread_fn		sv_function;	/* main function for threads */
+	struct svc_serv_ops	*sv_ops;	/* server operations */
 #if defined(CONFIG_SUNRPC_BACKCHANNEL)
 	struct list_head	sv_cb_list;	/* queue for callback requests
 						 * that arrive over the same
@@ -422,6 +427,29 @@ struct svc_procedure {
 	unsigned int		pc_xdrressize;	/* maximum size of XDR reply */
 };
 
+/*
+ * 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 */
+};
+
+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 */
+};
+
+extern struct svc_pool_map svc_pool_map;
+
 /*
  * Function prototypes.
  */
@@ -429,13 +457,17 @@ int svc_rpcb_setup(struct svc_serv *serv, struct net *net);
 void svc_rpcb_cleanup(struct svc_serv *serv, struct net *net);
 int svc_bind(struct svc_serv *serv, struct net *net);
 struct svc_serv *svc_create(struct svc_program *, unsigned int,
-			    void (*shutdown)(struct svc_serv *, struct net *net));
+			    struct svc_serv_ops *);
+struct svc_rqst *svc_rqst_alloc(struct svc_serv *serv,
+					struct svc_pool *pool, int node);
 struct svc_rqst *svc_prepare_thread(struct svc_serv *serv,
 					struct svc_pool *pool, int node);
+void		   svc_rqst_free(struct svc_rqst *);
 void		   svc_exit_thread(struct svc_rqst *);
+unsigned int	   svc_pool_map_get(void);
+void		   svc_pool_map_put(void);
 struct svc_serv *  svc_create_pooled(struct svc_program *, unsigned int,
-			void (*shutdown)(struct svc_serv *, struct net *net),
-			svc_thread_fn, struct module *);
+			struct svc_serv_ops *);
 int		   svc_set_num_threads(struct svc_serv *, struct svc_pool *, int);
 int		   svc_pool_stats_open(struct svc_serv *serv, struct file *file);
 void		   svc_destroy(struct svc_serv *);

include/linux/sunrpc/svc_rdma.h

@@ -172,13 +172,6 @@ struct svcxprt_rdma {
 #define RDMAXPRT_SQ_PENDING	2
 #define RDMAXPRT_CONN_PENDING	3
 
-#define RPCRDMA_MAX_SVC_SEGS	(64)	/* server max scatter/gather */
-#if RPCSVC_MAXPAYLOAD < (RPCRDMA_MAX_SVC_SEGS << PAGE_SHIFT)
-#define RPCRDMA_MAXPAYLOAD	RPCSVC_MAXPAYLOAD
-#else
-#define RPCRDMA_MAXPAYLOAD	(RPCRDMA_MAX_SVC_SEGS << PAGE_SHIFT)
-#endif
-
 #define RPCRDMA_LISTEN_BACKLOG  10
 /* The default ORD value is based on two outstanding full-size writes with a
  * page size of 4k, or 32k * 2 ops / 4k = 16 outstanding RDMA_READ.  */
@@ -187,6 +180,8 @@ struct svcxprt_rdma {
 #define RPCRDMA_MAX_REQUESTS    32
 #define RPCRDMA_MAX_REQ_SIZE    4096
 
+#define RPCSVC_MAXPAYLOAD_RDMA	RPCSVC_MAXPAYLOAD
+
 /* svc_rdma_marshal.c */
 extern int svc_rdma_xdr_decode_req(struct rpcrdma_msg **, struct svc_rqst *);
 extern int svc_rdma_xdr_encode_error(struct svcxprt_rdma *,
@@ -213,6 +208,8 @@ extern int rdma_read_chunk_frmr(struct svcxprt_rdma *, struct svc_rqst *,
 
 /* svc_rdma_sendto.c */
 extern int svc_rdma_sendto(struct svc_rqst *);
+extern struct rpcrdma_read_chunk *
+	svc_rdma_get_read_chunk(struct rpcrdma_msg *);
 
 /* svc_rdma_transport.c */
 extern int svc_rdma_send(struct svcxprt_rdma *, struct ib_send_wr *);
@@ -225,7 +222,6 @@ extern void svc_rdma_put_context(struct svc_rdma_op_ctxt *, int);
 extern void svc_rdma_unmap_dma(struct svc_rdma_op_ctxt *ctxt);
 extern struct svc_rdma_req_map *svc_rdma_get_req_map(void);
 extern void svc_rdma_put_req_map(struct svc_rdma_req_map *);
-extern int svc_rdma_fastreg(struct svcxprt_rdma *, struct svc_rdma_fastreg_mr *);
 extern struct svc_rdma_fastreg_mr *svc_rdma_get_frmr(struct svcxprt_rdma *);
 extern void svc_rdma_put_frmr(struct svcxprt_rdma *,
 			      struct svc_rdma_fastreg_mr *);
@@ -238,83 +234,4 @@ extern void svc_rdma_prep_reply_hdr(struct svc_rqst *);
 extern int svc_rdma_init(void);
 extern void svc_rdma_cleanup(void);
 
-/*
- * Returns the address of the first read chunk or <nul> if no read chunk is
- * present
- */
-static inline 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 == 0)
-		return NULL;
-
-	return ch;
-}
-
-/*
- * Returns the address of the first read write array element or <nul> if no
- * write array list is present
- */
-static inline struct rpcrdma_write_array *
-svc_rdma_get_write_array(struct rpcrdma_msg *rmsgp)
-{
-	if (rmsgp->rm_body.rm_chunks[0] != 0
-	    || rmsgp->rm_body.rm_chunks[1] == 0)
-		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 inline 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 list may occur with read-list and/or
-	 * write list */
-	if (rmsgp->rm_body.rm_chunks[0] != 0 ||
-	    rmsgp->rm_body.rm_chunks[1] != 0)
-		return NULL;
-
-	rch = svc_rdma_get_read_chunk(rmsgp);
-	if (rch) {
-		while (rch->rc_discrim)
-			rch++;
-
-		/* The reply list 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) {
-		rp_ary = (struct rpcrdma_write_array *)
-			&wr_ary->
-			wc_array[ntohl(wr_ary->wc_nchunks)].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 == 0)
-		return NULL;
-
-	return rp_ary;
-}
 #endif

include/linux/sunrpc/svc_xprt.h

@@ -116,6 +116,7 @@ void	svc_xprt_init(struct net *, struct svc_xprt_class *, struct svc_xprt *,
 		      struct svc_serv *);
 int	svc_create_xprt(struct svc_serv *, const char *, struct net *,
 			const int, const unsigned short, int);
+void	svc_xprt_do_enqueue(struct svc_xprt *xprt);
 void	svc_xprt_enqueue(struct svc_xprt *xprt);
 void	svc_xprt_put(struct svc_xprt *xprt);
 void	svc_xprt_copy_addrs(struct svc_rqst *rqstp, struct svc_xprt *xprt);

include/trace/events/sunrpc.h

@@ -529,18 +529,21 @@ TRACE_EVENT(svc_xprt_do_enqueue,
 
 	TP_STRUCT__entry(
 		__field(struct svc_xprt *, xprt)
-		__field(struct svc_rqst *, rqst)
+		__field_struct(struct sockaddr_storage, ss)
+		__field(int, pid)
+		__field(unsigned long, flags)
 	),
 
 	TP_fast_assign(
 		__entry->xprt = xprt;
-		__entry->rqst = rqst;
+		xprt ? memcpy(&__entry->ss, &xprt->xpt_remote, sizeof(__entry->ss)) : memset(&__entry->ss, 0, sizeof(__entry->ss));
+		__entry->pid = rqst? rqst->rq_task->pid : 0;
+		__entry->flags = xprt ? xprt->xpt_flags : 0;
 	),
 
 	TP_printk("xprt=0x%p addr=%pIScp pid=%d flags=%s", __entry->xprt,
-		(struct sockaddr *)&__entry->xprt->xpt_remote,
-		__entry->rqst ? __entry->rqst->rq_task->pid : 0,
-		show_svc_xprt_flags(__entry->xprt->xpt_flags))
+		(struct sockaddr *)&__entry->ss,
+		__entry->pid, show_svc_xprt_flags(__entry->flags))
 );
 
 TRACE_EVENT(svc_xprt_dequeue,
@@ -589,16 +592,20 @@ TRACE_EVENT(svc_handle_xprt,
 	TP_STRUCT__entry(
 		__field(struct svc_xprt *, xprt)
 		__field(int, len)
+		__field_struct(struct sockaddr_storage, ss)
+		__field(unsigned long, flags)
 	),
 
 	TP_fast_assign(
 		__entry->xprt = xprt;
+		xprt ? memcpy(&__entry->ss, &xprt->xpt_remote, sizeof(__entry->ss)) : memset(&__entry->ss, 0, sizeof(__entry->ss));
 		__entry->len = len;
+		__entry->flags = xprt ? xprt->xpt_flags : 0;
 	),
 
 	TP_printk("xprt=0x%p addr=%pIScp len=%d flags=%s", __entry->xprt,
-		(struct sockaddr *)&__entry->xprt->xpt_remote, __entry->len,
-		show_svc_xprt_flags(__entry->xprt->xpt_flags))
+		(struct sockaddr *)&__entry->ss,
+		__entry->len, show_svc_xprt_flags(__entry->flags))
 );
 #endif /* _TRACE_SUNRPC_H */
 

include/uapi/linux/nfsacl.h

@@ -22,6 +22,7 @@
 #define NFS_ACLCNT		0x0002
 #define NFS_DFACL		0x0004
 #define NFS_DFACLCNT		0x0008
+#define NFS_ACL_MASK		0x000f
 
 /* Flag for Default ACL entries */
 #define NFS_ACL_DEFAULT		0x1000

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;
 }

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)

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 @@ static void svc_xprt_do_enqueue(struct svc_xprt *xprt)
 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);
 

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;

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;

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 */