RDMA/cxgb4: SQ flush fix

There is a race when moving a QP from RTS->CLOSING where a SQ work
request could be posted after the FW receives the RDMA_RI/FINI WR.
The SQ work request will never get processed, and should be completed
with FLUSHED status.  Function c4iw_flush_sq(), however was dropping
the oldest SQ work request when in CLOSING or IDLE states, instead of
completing the pending work request. If that oldest pending work
request was actually complete and has a CQE in the CQ, then when that
CQE is proceessed in poll_cq, we'll BUG_ON() due to the inconsistent
SQ/CQ state.

This is a very small timing hole and has only been hit once so far.

The fix is two-fold:

1) c4iw_flush_sq() MUST always flush all non-completed WRs with FLUSHED
   status regardless of the QP state.

2) In c4iw_modify_rc_qp(), always set the "in error" bit on the queue
   before moving the state out of RTS.  This ensures that the state
   transition will not happen while another thread is in
   post_rc_send(), because set_state() and post_rc_send() both aquire
   the qp spinlock.  Also, once we transition the state out of RTS,
   subsequent calls to post_rc_send() will fail because the "in error"
   bit is set.  I don't think this fully closes the race where the FW
   can get a FINI followed a SQ work request being posted (because
   they are posted to differente EQs), but the #1 fix will handle the
   issue by flushing the SQ work request.

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

diff --git a/drivers/infiniband/hw/cxgb4/cq.c b/drivers/infiniband/hw/cxgb4/cq.c
index ce468e54242881096ce1c2ce8691b44e43b0bab9..e17b155b3758c4b447a2ac96552a9d81a5fa63b8 100644 (file)
--- a/drivers/infiniband/hw/cxgb4/cq.c
+++ b/drivers/infiniband/hw/cxgb4/cq.c
@@ -235,27 +235,21 @@ int c4iw_flush_sq(struct c4iw_qp *qhp)
        struct t4_cq *cq = &chp->cq;
        int idx;
        struct t4_swsqe *swsqe;
-       int error = (qhp->attr.state != C4IW_QP_STATE_CLOSING &&
-                       qhp->attr.state != C4IW_QP_STATE_IDLE);
 
        if (wq->sq.flush_cidx == -1)
                wq->sq.flush_cidx = wq->sq.cidx;
        idx = wq->sq.flush_cidx;
        BUG_ON(idx >= wq->sq.size);
        while (idx != wq->sq.pidx) {
-               if (error) {
-                       swsqe = &wq->sq.sw_sq[idx];
-                       BUG_ON(swsqe->flushed);
-                       swsqe->flushed = 1;
-                       insert_sq_cqe(wq, cq, swsqe);
-                       if (wq->sq.oldest_read == swsqe) {
-                               BUG_ON(swsqe->opcode != FW_RI_READ_REQ);
-                               advance_oldest_read(wq);
-                       }
-                       flushed++;
-               } else {
-                       t4_sq_consume(wq);
+               swsqe = &wq->sq.sw_sq[idx];
+               BUG_ON(swsqe->flushed);
+               swsqe->flushed = 1;
+               insert_sq_cqe(wq, cq, swsqe);
+               if (wq->sq.oldest_read == swsqe) {
+                       BUG_ON(swsqe->opcode != FW_RI_READ_REQ);
+                       advance_oldest_read(wq);
                }
+               flushed++;
                if (++idx == wq->sq.size)
                        idx = 0;
        }

diff --git a/drivers/infiniband/hw/cxgb4/qp.c b/drivers/infiniband/hw/cxgb4/qp.c
index e2fcbf4814f27962367d9efead102e169c05c8ed..9b4a8b88908e512bcfc439505123525542403398 100644 (file)
--- a/drivers/infiniband/hw/cxgb4/qp.c
+++ b/drivers/infiniband/hw/cxgb4/qp.c
@@ -1367,6 +1367,7 @@ int c4iw_modify_qp(struct c4iw_dev *rhp, struct c4iw_qp *qhp,
                switch (attrs->next_state) {
                case C4IW_QP_STATE_CLOSING:
                        BUG_ON(atomic_read(&qhp->ep->com.kref.refcount) < 2);
+                       t4_set_wq_in_error(&qhp->wq);
                        set_state(qhp, C4IW_QP_STATE_CLOSING);
                        ep = qhp->ep;
                        if (!internal) {
@@ -1374,16 +1375,15 @@ int c4iw_modify_qp(struct c4iw_dev *rhp, struct c4iw_qp *qhp,
                                disconnect = 1;
                                c4iw_get_ep(&qhp->ep->com);
                        }
-                       t4_set_wq_in_error(&qhp->wq);
                        ret = rdma_fini(rhp, qhp, ep);
                        if (ret)
                                goto err;
                        break;
                case C4IW_QP_STATE_TERMINATE:
+                       t4_set_wq_in_error(&qhp->wq);
                        set_state(qhp, C4IW_QP_STATE_TERMINATE);
                        qhp->attr.layer_etype = attrs->layer_etype;
                        qhp->attr.ecode = attrs->ecode;
-                       t4_set_wq_in_error(&qhp->wq);
                        ep = qhp->ep;
                        disconnect = 1;
                        if (!internal)
@@ -1396,8 +1396,8 @@ int c4iw_modify_qp(struct c4iw_dev *rhp, struct c4iw_qp *qhp,
                        c4iw_get_ep(&qhp->ep->com);
                        break;
                case C4IW_QP_STATE_ERROR:
-                       set_state(qhp, C4IW_QP_STATE_ERROR);
                        t4_set_wq_in_error(&qhp->wq);
+                       set_state(qhp, C4IW_QP_STATE_ERROR);
                        if (!internal) {
                                abort = 1;
                                disconnect = 1;