NFSv4.1: Deal effectively with interrupted RPC calls.

If an RPC call is interrupted, assume that the server hasn't processed
the RPC call so that the next time we use the slot, we know that if we
get a NFS4ERR_SEQ_MISORDERED or NFS4ERR_SEQ_FALSE_RETRY, we just have
to bump the sequence number.

Signed-off-by: Trond Myklebust <Trond.Myklebust@netapp.com>

3 files changed, 25 insertions, 9 deletions

diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index afb428e63b52..493f0f41c554 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -420,17 +420,9 @@ static int nfs41_sequence_done(struct rpc_task *task, struct nfs4_sequence_res *
         struct nfs4_session *session;
         struct nfs4_slot *slot;
         struct nfs_client *clp;
+        bool interrupted = false;
         int ret = 1;
 
-        /*
-         * sr_status remains 1 if an RPC level error occurred. The server
-         * may or may not have processed the sequence operation..
-         * Proceed as if the server received and processed the sequence
-         * operation.
-         */
-        if (res->sr_status == 1)
-                res->sr_status = NFS_OK;
-
         /* don't increment the sequence number if the task wasn't sent */
         if (!RPC_WAS_SENT(task))
                 goto out;
@@ -438,6 +430,11 @@ static int nfs41_sequence_done(struct rpc_task *task, struct nfs4_sequence_res *
         slot = res->sr_slot;
         session = slot->table->session;
 
+        if (slot->interrupted) {
+                slot->interrupted = 0;
+                interrupted = true;
+        }
+
         /* Check the SEQUENCE operation status */
         switch (res->sr_status) {
         case 0:
@@ -450,6 +447,15 @@ static int nfs41_sequence_done(struct rpc_task *task, struct nfs4_sequence_res *
                         nfs4_schedule_lease_recovery(clp);
                 nfs41_update_target_slotid(slot->table, slot, res);
                 break;
+        case 1:
+                /*
+                 * sr_status remains 1 if an RPC level error occurred.
+                 * The server may or may not have processed the sequence
+                 * operation..
+                 * Mark the slot as having hosted an interrupted RPC call.
+                 */
+                slot->interrupted = 1;
+                goto out;
         case -NFS4ERR_DELAY:
                 /* The server detected a resend of the RPC call and
                  * returned NFS4ERR_DELAY as per Section 2.10.6.2
@@ -468,6 +474,14 @@ static int nfs41_sequence_done(struct rpc_task *task, struct nfs4_sequence_res *
                 goto retry_nowait;
         case -NFS4ERR_SEQ_MISORDERED:
                 /*
+                 * Was the last operation on this sequence interrupted?
+                 * If so, retry after bumping the sequence number.
+                 */
+                if (interrupted) {
+                        ++slot->seq_nr;
+                        goto retry_nowait;
+                }
+                /*
                  * Could this slot have been previously retired?
                  * If so, then the server may be expecting seq_nr = 1!
                  */
diff --git a/fs/nfs/nfs4session.c b/fs/nfs/nfs4session.c
index 0e1cc1f4e51a..ebda5f4a031b 100644
--- a/fs/nfs/nfs4session.c
+++ b/fs/nfs/nfs4session.c
@@ -172,6 +172,7 @@ static void nfs4_reset_slot_table(struct nfs4_slot_table *tbl,
         p = &tbl->slots;
         while (*p) {
                 (*p)->seq_nr = ivalue;
+                (*p)->interrupted = 0;
                 p = &(*p)->next;
         }
         tbl->highest_used_slotid = NFS4_NO_SLOT;
diff --git a/fs/nfs/nfs4session.h b/fs/nfs/nfs4session.h
index d17b08091d4b..6f3cb39386d4 100644
--- a/fs/nfs/nfs4session.h
+++ b/fs/nfs/nfs4session.h
@@ -21,6 +21,7 @@ struct nfs4_slot {
         unsigned long           generation;
         u32                     slot_nr;
         u32                     seq_nr;
+        unsigned int            interrupted : 1;
 };
 
 /* Sessions */