nfsd: give up on CB_LAYOUTRECALLs after two lease periods

Have the CB_LAYOUTRECALL code treat NFS4_OK and NFS4ERR_DELAY returns
equivalently. Change the code to periodically resend CB_LAYOUTRECALLS
until the ls_layouts list is empty or the client returns a different
error code.

If we go for two lease periods without the list being emptied or the
client sending a hard error, then we give up and clean out the list
anyway.

Signed-off-by: Jeff Layton <jeff.layton@primarydata.com>
Tested-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: J. Bruce Fields <bfields@redhat.com>

diff --git a/fs/nfsd/nfs4layouts.c b/fs/nfsd/nfs4layouts.c
index fec49fe..76c13b0 100644 (file)
--- a/fs/nfsd/nfs4layouts.c
+++ b/fs/nfsd/nfs4layouts.c
@@ -623,24 +623,39 @@ 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.