Merge tag 'rdma-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/roland/infiniband

Pull infiniband/rdma updates from Roland Dreier:
 "Main set of InfiniBand/RDMA updates for 3.17 merge window:

   - MR reregistration support
   - MAD support for RMPP in userspace
   - iSER and SRP initiator updates
   - ocrdma hardware driver updates
   - other fixes..."

* tag 'rdma-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/roland/infiniband: (52 commits)
  IB/srp: Fix return value check in srp_init_module()
  RDMA/ocrdma: report asic-id in query device
  RDMA/ocrdma: Update sli data structure for endianness
  RDMA/ocrdma: Obtain SL from device structure
  RDMA/uapi: Include socket.h in rdma_user_cm.h
  IB/srpt: Handle GID change events
  IB/mlx5: Use ARRAY_SIZE instead of sizeof/sizeof[0]
  IB/mlx4: Use ARRAY_SIZE instead of sizeof/sizeof[0]
  RDMA/amso1100: Check for integer overflow in c2_alloc_cq_buf()
  IPoIB: Remove unnecessary test for NULL before debugfs_remove()
  IB/mad: Add user space RMPP support
  IB/mad: add new ioctl to ABI to support new registration options
  IB/mad: Add dev_notice messages for various umad/mad registration failures
  IB/mad: Update module to [pr|dev]_* style print messages
  IB/ipoib: Avoid multicast join attempts with invalid P_key
  IB/umad: Update module to [pr|dev]_* style print messages
  IB/ipoib: Avoid flushing the workqueue from worker context
  IB/ipoib: Use P_Key change event instead of P_Key polling mechanism
  IB/ipath: Add P_Key change event support
  mlx4_core: Add support for secure-host and SMP firewall
  ...

3 files changed, 37 insertions, 12 deletions

diff --git a/drivers/infiniband/hw/cxgb4/ev.c b/drivers/infiniband/hw/cxgb4/ev.c
index fbe6051af254..c9df0549f51d 100644
--- a/drivers/infiniband/hw/cxgb4/ev.c
+++ b/drivers/infiniband/hw/cxgb4/ev.c
@@ -227,6 +227,7 @@ int c4iw_ev_handler(struct c4iw_dev *dev, u32 qid)
 
         chp = get_chp(dev, qid);
         if (chp) {
+                t4_clear_cq_armed(&chp->cq);
                 spin_lock_irqsave(&chp->comp_handler_lock, flag);
                 (*chp->ibcq.comp_handler)(&chp->ibcq, chp->ibcq.cq_context);
                 spin_unlock_irqrestore(&chp->comp_handler_lock, flag);
diff --git a/drivers/infiniband/hw/cxgb4/qp.c b/drivers/infiniband/hw/cxgb4/qp.c
index c158fcc02bca..41cd6882b648 100644
--- a/drivers/infiniband/hw/cxgb4/qp.c
+++ b/drivers/infiniband/hw/cxgb4/qp.c
@@ -1105,7 +1105,7 @@ static void __flush_qp(struct c4iw_qp *qhp, struct c4iw_cq *rchp,
                        struct c4iw_cq *schp)
 {
         int count;
-        int flushed;
+        int rq_flushed, sq_flushed;
         unsigned long flag;
 
         PDBG("%s qhp %p rchp %p schp %p\n", __func__, qhp, rchp, schp);
@@ -1123,27 +1123,40 @@ static void __flush_qp(struct c4iw_qp *qhp, struct c4iw_cq *rchp,
 
         c4iw_flush_hw_cq(rchp);
         c4iw_count_rcqes(&rchp->cq, &qhp->wq, &count);
-        flushed = c4iw_flush_rq(&qhp->wq, &rchp->cq, count);
+        rq_flushed = c4iw_flush_rq(&qhp->wq, &rchp->cq, count);
         spin_unlock(&qhp->lock);
         spin_unlock_irqrestore(&rchp->lock, flag);
-        if (flushed) {
-                spin_lock_irqsave(&rchp->comp_handler_lock, flag);
-                (*rchp->ibcq.comp_handler)(&rchp->ibcq, rchp->ibcq.cq_context);
-                spin_unlock_irqrestore(&rchp->comp_handler_lock, flag);
-        }
 
         /* locking hierarchy: cq lock first, then qp lock. */
         spin_lock_irqsave(&schp->lock, flag);
         spin_lock(&qhp->lock);
         if (schp != rchp)
                 c4iw_flush_hw_cq(schp);
-        flushed = c4iw_flush_sq(qhp);
+        sq_flushed = c4iw_flush_sq(qhp);
         spin_unlock(&qhp->lock);
         spin_unlock_irqrestore(&schp->lock, flag);
-        if (flushed) {
-                spin_lock_irqsave(&schp->comp_handler_lock, flag);
-                (*schp->ibcq.comp_handler)(&schp->ibcq, schp->ibcq.cq_context);
-                spin_unlock_irqrestore(&schp->comp_handler_lock, flag);
+
+        if (schp == rchp) {
+                if (t4_clear_cq_armed(&rchp->cq) &&
+                    (rq_flushed || sq_flushed)) {
+                        spin_lock_irqsave(&rchp->comp_handler_lock, flag);
+                        (*rchp->ibcq.comp_handler)(&rchp->ibcq,
+                                                   rchp->ibcq.cq_context);
+                        spin_unlock_irqrestore(&rchp->comp_handler_lock, flag);
+                }
+        } else {
+                if (t4_clear_cq_armed(&rchp->cq) && rq_flushed) {
+                        spin_lock_irqsave(&rchp->comp_handler_lock, flag);
+                        (*rchp->ibcq.comp_handler)(&rchp->ibcq,
+                                                   rchp->ibcq.cq_context);
+                        spin_unlock_irqrestore(&rchp->comp_handler_lock, flag);
+                }
+                if (t4_clear_cq_armed(&schp->cq) && sq_flushed) {
+                        spin_lock_irqsave(&schp->comp_handler_lock, flag);
+                        (*schp->ibcq.comp_handler)(&schp->ibcq,
+                                                   schp->ibcq.cq_context);
+                        spin_unlock_irqrestore(&schp->comp_handler_lock, flag);
+                }
         }
 }
 
diff --git a/drivers/infiniband/hw/cxgb4/t4.h b/drivers/infiniband/hw/cxgb4/t4.h
index df5edfa31a8f..c04e5134b30c 100644
--- a/drivers/infiniband/hw/cxgb4/t4.h
+++ b/drivers/infiniband/hw/cxgb4/t4.h
@@ -524,6 +524,10 @@ static inline int t4_wq_db_enabled(struct t4_wq *wq)
         return !wq->rq.queue[wq->rq.size].status.db_off;
 }
 
+enum t4_cq_flags {
+        CQ_ARMED        = 1,
+};
+
 struct t4_cq {
         struct t4_cqe *queue;
         dma_addr_t dma_addr;
@@ -544,12 +548,19 @@ struct t4_cq {
         u16 cidx_inc;
         u8 gen;
         u8 error;
+        unsigned long flags;
 };
 
+static inline int t4_clear_cq_armed(struct t4_cq *cq)
+{
+        return test_and_clear_bit(CQ_ARMED, &cq->flags);
+}
+
 static inline int t4_arm_cq(struct t4_cq *cq, int se)
 {
         u32 val;
 
+        set_bit(CQ_ARMED, &cq->flags);
         while (cq->cidx_inc > CIDXINC_MASK) {
                 val = SEINTARM(0) | CIDXINC(CIDXINC_MASK) | TIMERREG(7) |
                       INGRESSQID(cq->cqid);