ibmvnic: Properly dispose of all skbs during a failover.

During a reset, there may have been transmits in flight that are no
longer valid and cannot be fulfilled.  Resetting and clearing the
queues is insufficient; each skb also needs to be explicitly freed
so that upper levels are not left waiting for confirmation of a
transmit that will never happen.  If this happens frequently enough,
the apparent backlog will cause TCP to begin "congestion control"
unnecessarily, culminating in permanently decreased throughput.

Fixes: d7c0ef36bde03 ("ibmvnic: Free and re-allocate scrqs when tx/rx scrqs change")
Tested-by: Nick Child <nnac123@linux.ibm.com>
Reviewed-by: Brian King <brking@linux.vnet.ibm.com>
Signed-off-by: Rick Lindsley <ricklind@us.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 7e7fe5bdf1f8c4b6ccf3d810909fe2dae3c38a8c..5ab7c0f81e9afc9ec6230325cb9bac71ca33f34b 100644 (file)
--- a/drivers/net/ethernet/ibm/ibmvnic.c
+++ b/drivers/net/ethernet/ibm/ibmvnic.c
@@ -5981,6 +5981,15 @@ static int ibmvnic_reset_init(struct ibmvnic_adapter *adapter, bool reset)
                        release_sub_crqs(adapter, 0);
                        rc = init_sub_crqs(adapter);
                } else {
+                       /* no need to reinitialize completely, but we do
+                        * need to clean up transmits that were in flight
+                        * when we processed the reset.  Failure to do so
+                        * will confound the upper layer, usually TCP, by
+                        * creating the illusion of transmits that are
+                        * awaiting completion.
+                        */
+                       clean_tx_pools(adapter);
+
                        rc = reset_sub_crq_queues(adapter);
                }
        } else {