Merge tag 'nfsd-4.5' of git://linux-nfs.org/~bfields/linux

Pull nfsd updates from Bruce Fields:
 "Smaller bugfixes and cleanup, including a fix for a failures of
  kerberized NFSv4.1 mounts, and Scott Mayhew's work addressing ACK
  storms that can affect some high-availability NFS setups"

* tag 'nfsd-4.5' of git://linux-nfs.org/~bfields/linux:
  nfsd: add new io class tracepoint
  nfsd: give up on CB_LAYOUTRECALLs after two lease periods
  nfsd: Fix nfsd leaks sunrpc module references
  lockd: constify nlmsvc_binding structure
  lockd: use to_delayed_work
  nfsd: use to_delayed_work
  Revert "svcrdma: Do not send XDR roundup bytes for a write chunk"
  lockd: Register callbacks on the inetaddr_chain and inet6addr_chain
  nfsd: Register callbacks on the inetaddr_chain and inet6addr_chain
  sunrpc: Add a function to close temporary transports immediately
  nfsd: don't base cl_cb_status on stale information
  nfsd4: fix gss-proxy 4.1 mounts for some AD principals
  nfsd: fix unlikely NULL deref in mach_creds_match
  nfsd: minor consolidation of mach_cred handling code
  nfsd: helper for dup of possibly NULL string
  svcrpc: move some initialization to common code
  nfsd: fix a warning message
  nfsd: constify nfsd4_callback_ops structure
  nfsd: recover: constify nfsd4_client_tracking_ops structures
  svcrdma: Do not send XDR roundup bytes for a write chunk

fs/nfsd/nfs4layouts.c

@@ -22,7 +22,7 @@ struct nfs4_layout {
 static struct kmem_cache *nfs4_layout_cache;
 static struct kmem_cache *nfs4_layout_stateid_cache;
 
-static struct nfsd4_callback_ops nfsd4_cb_layout_ops;
+static const struct nfsd4_callback_ops nfsd4_cb_layout_ops;
 static const struct lock_manager_operations nfsd4_layouts_lm_ops;
 
 const struct nfsd4_layout_ops *nfsd4_layout_ops[LAYOUT_TYPE_MAX] =  {
@@ -624,24 +624,39 @@ nfsd4_cb_layout_done(struct nfsd4_callback *cb, struct rpc_task *task)
 {
 	struct nfs4_layout_stateid *ls =
 		container_of(cb, struct nfs4_layout_stateid, ls_recall);
+	struct nfsd_net *nn;
+	ktime_t now, cutoff;
 	LIST_HEAD(reaplist);
 
+
 	switch (task->tk_status) {
 	case 0:
-		return 1;
+	case -NFS4ERR_DELAY:
+		/*
+		 * Anything left? If not, then call it done. Note that we don't
+		 * take the spinlock since this is an optimization and nothing
+		 * should get added until the cb counter goes to zero.
+		 */
+		if (list_empty(&ls->ls_layouts))
+			return 1;
+
+		/* Poll the client until it's done with the layout */
+		now = ktime_get();
+		nn = net_generic(ls->ls_stid.sc_client->net, nfsd_net_id);
+
+		/* Client gets 2 lease periods to return it */
+		cutoff = ktime_add_ns(task->tk_start,
+					 nn->nfsd4_lease * NSEC_PER_SEC * 2);
+
+		if (ktime_before(now, cutoff)) {
+			rpc_delay(task, HZ/100); /* 10 mili-seconds */
+			return 0;
+		}
+		/* Fallthrough */
 	case -NFS4ERR_NOMATCHING_LAYOUT:
 		trace_layout_recall_done(&ls->ls_stid.sc_stateid);
 		task->tk_status = 0;
 		return 1;
-	case -NFS4ERR_DELAY:
-		/* Poll the client until it's done with the layout */
-		/* FIXME: cap number of retries.
-		 * The pnfs standard states that we need to only expire
-		 * the client after at-least "lease time" .eg lease-time * 2
-		 * when failing to communicate a recall
-		 */
-		rpc_delay(task, HZ/100); /* 10 mili-seconds */
-		return 0;
 	default:
 		/*
 		 * Unknown error or non-responding client, we'll need to fence.
@@ -665,7 +680,7 @@ nfsd4_cb_layout_release(struct nfsd4_callback *cb)
 	nfs4_put_stid(&ls->ls_stid);
 }
 
-static struct nfsd4_callback_ops nfsd4_cb_layout_ops = {
+static const struct nfsd4_callback_ops nfsd4_cb_layout_ops = {
 	.prepare	= nfsd4_cb_layout_prepare,
 	.done		= nfsd4_cb_layout_done,
 	.release	= nfsd4_cb_layout_release,