ibmvnic: retry reset if there are no other resets

Normally, if a reset fails due to failover or other communication error
there is another reset (eg: FAILOVER) in the queue and we would process
that reset. But if we are unable to communicate with PHYP or VIOS after
H_FREE_CRQ, there would be no other resets in the queue and the adapter
would be in an undefined state even though it was in the OPEN state
earlier. While starting the reset we set the carrier to off state so
we won't even get the timeout resets.

If the last queued reset fails, retry it as a hard reset (after the
usual 60 second settling time).

Signed-off-by: Sukadev Bhattiprolu <sukadev@linux.ibm.com>
Reviewed-by: Dany Madden <drt@linux.ibm.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/drivers/net/ethernet/ibm/ibmvnic.c b/drivers/net/ethernet/ibm/ibmvnic.c
index 374a75d4faeae241b9fc2faafc9877dd0aac2ca0..ed77191d19f44cb8228290a7c00c13777ae38d79 100644 (file)
--- a/drivers/net/ethernet/ibm/ibmvnic.c
+++ b/drivers/net/ethernet/ibm/ibmvnic.c
@@ -2420,9 +2420,10 @@ out:
 
 static void __ibmvnic_reset(struct work_struct *work)
 {
-       struct ibmvnic_rwi *rwi;
        struct ibmvnic_adapter *adapter;
        bool saved_state = false;
+       struct ibmvnic_rwi *tmprwi;
+       struct ibmvnic_rwi *rwi;
        unsigned long flags;
        u32 reset_state;
        int rc = 0;
@@ -2489,7 +2490,7 @@ static void __ibmvnic_reset(struct work_struct *work)
                } else {
                        rc = do_reset(adapter, rwi, reset_state);
                }
-               kfree(rwi);
+               tmprwi = rwi;
                adapter->last_reset_time = jiffies;
 
                if (rc)
@@ -2497,8 +2498,23 @@ static void __ibmvnic_reset(struct work_struct *work)
 
                rwi = get_next_rwi(adapter);
 
+               /*
+                * If there is another reset queued, free the previous rwi
+                * and process the new reset even if previous reset failed
+                * (the previous reset could have failed because of a fail
+                * over for instance, so process the fail over).
+                *
+                * If there are no resets queued and the previous reset failed,
+                * the adapter would be in an undefined state. So retry the
+                * previous reset as a hard reset.
+                */
+               if (rwi)
+                       kfree(tmprwi);
+               else if (rc)
+                       rwi = tmprwi;
+
                if (rwi && (rwi->reset_reason == VNIC_RESET_FAILOVER ||
-                           rwi->reset_reason == VNIC_RESET_MOBILITY))
+                           rwi->reset_reason == VNIC_RESET_MOBILITY || rc))
                        adapter->force_reset_recovery = true;
        }