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

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/roland/infiniband:
  IB/mlx4: Make sure inline data segments don't cross a 64 byte boundary
  IB/mlx4: Handle FW command interface rev 3
  IB/mlx4: Handle buffer wraparound in __mlx4_ib_cq_clean()
  IB/mlx4: Get rid of max_inline_data calculation
  IB/mlx4: Handle new FW requirement for send request prefetching
  IB/mlx4: Fix warning in rounding up queue sizes
  IB/mlx4: Fix handling of wq->tail for send completions

1 files changed, 12 insertions, 7 deletions

diff --git a/drivers/infiniband/hw/mlx4/cq.c b/drivers/infiniband/hw/mlx4/cq.c
index b2a290c6703a..660b27aecae5 100644
--- a/drivers/infiniband/hw/mlx4/cq.c
+++ b/drivers/infiniband/hw/mlx4/cq.c
@@ -354,8 +354,8 @@ static int mlx4_ib_poll_one(struct mlx4_ib_cq *cq,
         if (is_send) {
                 wq = &(*cur_qp)->sq;
                 wqe_ctr = be16_to_cpu(cqe->wqe_index);
-                wq->tail += wqe_ctr - (u16) wq->tail;
-                wc->wr_id = wq->wrid[wq->tail & (wq->max - 1)];
+                wq->tail += (u16) (wqe_ctr - (u16) wq->tail);
+                wc->wr_id = wq->wrid[wq->tail & (wq->wqe_cnt - 1)];
                 ++wq->tail;
         } else if ((*cur_qp)->ibqp.srq) {
                 srq = to_msrq((*cur_qp)->ibqp.srq);
@@ -364,7 +364,7 @@ static int mlx4_ib_poll_one(struct mlx4_ib_cq *cq,
                 mlx4_ib_free_srq_wqe(srq, wqe_ctr);
         } else {
                 wq        = &(*cur_qp)->rq;
-                wc->wr_id = wq->wrid[wq->tail & (wq->max - 1)];
+                wc->wr_id = wq->wrid[wq->tail & (wq->wqe_cnt - 1)];
                 ++wq->tail;
         }
 
@@ -478,7 +478,8 @@ void __mlx4_ib_cq_clean(struct mlx4_ib_cq *cq, u32 qpn, struct mlx4_ib_srq *srq)
 {
         u32 prod_index;
         int nfreed = 0;
-        struct mlx4_cqe *cqe;
+        struct mlx4_cqe *cqe, *dest;
+        u8 owner_bit;
 
         /*
          * First we need to find the current producer index, so we
@@ -501,9 +502,13 @@ void __mlx4_ib_cq_clean(struct mlx4_ib_cq *cq, u32 qpn, struct mlx4_ib_srq *srq)
                         if (srq && !(cqe->owner_sr_opcode & MLX4_CQE_IS_SEND_MASK))
                                 mlx4_ib_free_srq_wqe(srq, be16_to_cpu(cqe->wqe_index));
                         ++nfreed;
-                } else if (nfreed)
-                        memcpy(get_cqe(cq, (prod_index + nfreed) & cq->ibcq.cqe),
-                               cqe, sizeof *cqe);
+                } else if (nfreed) {
+                        dest = get_cqe(cq, (prod_index + nfreed) & cq->ibcq.cqe);
+                        owner_bit = dest->owner_sr_opcode & MLX4_CQE_OWNER_MASK;
+                        memcpy(dest, cqe, sizeof *cqe);
+                        dest->owner_sr_opcode = owner_bit |
+                                (dest->owner_sr_opcode & ~MLX4_CQE_OWNER_MASK);
+                }
         }
 
         if (nfreed) {