RDMA/cxgb4: Handle newer firmware changes

Move QP to TERMINATE instead to allow the peer to get the TERM
message. This bug wasn't detectable until newer FW that moves
connections out of RDMA mode as soon as an error is detected.

QP can exit RTS before the last AE arrives.  This was introduced by
changes in the FW to kick connections out of RDMA mode as soon as an
error is detected.  A side effect of this is that the driver can move
the QP out of RTS before the AE causing the connection to get kicked
out of RDMA mode is processed.  Fix for this is to always post async
errors even if the QP is out of RTS.

Signed-off-by: Steve Wise <swise@opengridcomputing.com>
Signed-off-by: Vipul Pandya <vipul@chelsio.com>
Signed-off-by: Roland Dreier <roland@purestorage.com>

diff --git a/drivers/infiniband/hw/cxgb4/cm.c b/drivers/infiniband/hw/cxgb4/cm.c
index 6ee5d84..8865a33 100644 (file)
--- a/drivers/infiniband/hw/cxgb4/cm.c
+++ b/drivers/infiniband/hw/cxgb4/cm.c
@@ -1572,10 +1572,9 @@ static int rx_data(struct c4iw_dev *dev, struct sk_buff *skb)
                               " qpid %u ep %p state %d tid %u status %d\n",
                               __func__, ep->com.qp->wq.sq.qid, ep,
                               state_read(&ep->com), ep->hwtid, status);
-               attrs.next_state = C4IW_QP_STATE_ERROR;
+               attrs.next_state = C4IW_QP_STATE_TERMINATE;
                c4iw_modify_qp(ep->com.qp->rhp, ep->com.qp,
-                              C4IW_QP_ATTR_NEXT_STATE, &attrs, 1);
-               c4iw_ep_disconnect(ep, 1, GFP_KERNEL);
+                              C4IW_QP_ATTR_NEXT_STATE, &attrs, 0);
                break;
        }
        default:

diff --git a/drivers/infiniband/hw/cxgb4/ev.c b/drivers/infiniband/hw/cxgb4/ev.c
index 1a840b2..d61d0a1 100644 (file)
--- a/drivers/infiniband/hw/cxgb4/ev.c
+++ b/drivers/infiniband/hw/cxgb4/ev.c
@@ -44,16 +44,6 @@ static void post_qp_event(struct c4iw_dev *dev, struct c4iw_cq *chp,
        struct c4iw_qp_attributes attrs;
        unsigned long flag;
 
-       if ((qhp->attr.state == C4IW_QP_STATE_ERROR) ||
-           (qhp->attr.state == C4IW_QP_STATE_TERMINATE)) {
-               pr_err("%s AE after RTS - qpid 0x%x opcode %d status 0x%x "\
-                      "type %d wrid.hi 0x%x wrid.lo 0x%x\n",
-                      __func__, CQE_QPID(err_cqe), CQE_OPCODE(err_cqe),
-                      CQE_STATUS(err_cqe), CQE_TYPE(err_cqe),
-                      CQE_WRID_HI(err_cqe), CQE_WRID_LOW(err_cqe));
-               return;
-       }
-
        printk(KERN_ERR MOD "AE qpid 0x%x opcode %d status 0x%x "
               "type %d wrid.hi 0x%x wrid.lo 0x%x\n",
               CQE_QPID(err_cqe), CQE_OPCODE(err_cqe),