IB/mthca: Fix posting lists of 256 receive requests for Tavor

If we post a list of length 256 exactly, nreq in doorbell gets set to
256 which is wrong: it should be encoded by 0.  This is because we
only zero it out on the next WR, which may not be there.  The solution
is to ring the doorbell after posting a WQE, not before posting the
next one.

Signed-off-by: Michael S. Tsirkin <mst@mellanox.co.il>
Signed-off-by: Roland Dreier <rolandd@cisco.com>

1 files changed, 18 insertions, 17 deletions

diff --git a/drivers/infiniband/hw/mthca/mthca_qp.c b/drivers/infiniband/hw/mthca/mthca_qp.c
index 19765f6f8d58..07c13be07a4a 100644
--- a/drivers/infiniband/hw/mthca/mthca_qp.c
+++ b/drivers/infiniband/hw/mthca/mthca_qp.c
@@ -1727,23 +1727,7 @@ int mthca_tavor_post_receive(struct ib_qp *ibqp, struct ib_recv_wr *wr,
 
         ind = qp->rq.next_ind;
 
-        for (nreq = 0; wr; ++nreq, wr = wr->next) {
-                if (unlikely(nreq == MTHCA_TAVOR_MAX_WQES_PER_RECV_DB)) {
-                        nreq = 0;
-
-                        doorbell[0] = cpu_to_be32((qp->rq.next_ind << qp->rq.wqe_shift) | size0);
-                        doorbell[1] = cpu_to_be32(qp->qpn << 8);
-
-                        wmb();
-
-                        mthca_write64(doorbell,
-                                      dev->kar + MTHCA_RECEIVE_DOORBELL,
-                                      MTHCA_GET_DOORBELL_LOCK(&dev->doorbell_lock));
-
-                        qp->rq.head += MTHCA_TAVOR_MAX_WQES_PER_RECV_DB;
-                        size0 = 0;
-                }
-
+        for (nreq = 0; wr; wr = wr->next) {
                 if (mthca_wq_overflow(&qp->rq, nreq, qp->ibqp.recv_cq)) {
                         mthca_err(dev, "RQ %06x full (%u head, %u tail,"
                                         " %d max, %d nreq)\n", qp->qpn,
@@ -1797,6 +1781,23 @@ int mthca_tavor_post_receive(struct ib_qp *ibqp, struct ib_recv_wr *wr,
                 ++ind;
                 if (unlikely(ind >= qp->rq.max))
                         ind -= qp->rq.max;
+
+                ++nreq;
+                if (unlikely(nreq == MTHCA_TAVOR_MAX_WQES_PER_RECV_DB)) {
+                        nreq = 0;
+
+                        doorbell[0] = cpu_to_be32((qp->rq.next_ind << qp->rq.wqe_shift) | size0);
+                        doorbell[1] = cpu_to_be32(qp->qpn << 8);
+
+                        wmb();
+
+                        mthca_write64(doorbell,
+                                      dev->kar + MTHCA_RECEIVE_DOORBELL,
+                                      MTHCA_GET_DOORBELL_LOCK(&dev->doorbell_lock));
+
+                        qp->rq.head += MTHCA_TAVOR_MAX_WQES_PER_RECV_DB;
+                        size0 = 0;
+                }
         }
 
 out: