RDMA/qedr: SRQ's bug fixes

QP's with the same SRQ, working on different CQs and running in parallel
on different CPUs could lead to a race when maintaining the SRQ consumer
count, and leads to FW running out of SRQs. Update the consumer
atomically.  Make sure the wqe_prod is updated after the sge_prod due to
FW requirements.

Fixes: 3491c9e ("qedr: Add support for kernel mode SRQ's")
Link: https://lore.kernel.org/r/20200708195526.31040-1-ybason@marvell.com
Signed-off-by: Michal Kalderon <mkalderon@marvell.com>
Signed-off-by: Yuval Basson <ybason@marvell.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>

drivers/infiniband/hw/qedr/qedr.h

@@ -344,10 +344,10 @@ struct qedr_srq_hwq_info {
 	u32 wqe_prod;
 	u32 sge_prod;
 	u32 wr_prod_cnt;
-	u32 wr_cons_cnt;
+	atomic_t wr_cons_cnt;
 	u32 num_elems;
 
-	u32 *virt_prod_pair_addr;
+	struct rdma_srq_producers *virt_prod_pair_addr;
 	dma_addr_t phy_prod_pair_addr;
 };
 

drivers/infiniband/hw/qedr/verbs.c

@@ -3686,7 +3686,7 @@ static u32 qedr_srq_elem_left(struct qedr_srq_hwq_info *hw_srq)
 	 * count and consumer count and subtract it from max
 	 * work request supported so that we get elements left.
 	 */
-	used = hw_srq->wr_prod_cnt - hw_srq->wr_cons_cnt;
+	used = hw_srq->wr_prod_cnt - (u32)atomic_read(&hw_srq->wr_cons_cnt);
 
 	return hw_srq->max_wr - used;
 }
@@ -3701,7 +3701,6 @@ int qedr_post_srq_recv(struct ib_srq *ibsrq, const struct ib_recv_wr *wr,
 	unsigned long flags;
 	int status = 0;
 	u32 num_sge;
-	u32 offset;
 
 	spin_lock_irqsave(&srq->lock, flags);
 
@@ -3714,7 +3713,8 @@ int qedr_post_srq_recv(struct ib_srq *ibsrq, const struct ib_recv_wr *wr,
 		if (!qedr_srq_elem_left(hw_srq) ||
 		    wr->num_sge > srq->hw_srq.max_sges) {
 			DP_ERR(dev, "Can't post WR  (%d,%d) || (%d > %d)\n",
-			       hw_srq->wr_prod_cnt, hw_srq->wr_cons_cnt,
+			       hw_srq->wr_prod_cnt,
+			       atomic_read(&hw_srq->wr_cons_cnt),
 			       wr->num_sge, srq->hw_srq.max_sges);
 			status = -ENOMEM;
 			*bad_wr = wr;
@@ -3748,22 +3748,20 @@ int qedr_post_srq_recv(struct ib_srq *ibsrq, const struct ib_recv_wr *wr,
 			hw_srq->sge_prod++;
 		}
 
-		/* Flush WQE and SGE information before
+		/* Update WQE and SGE information before
 		 * updating producer.
 		 */
-		wmb();
+		dma_wmb();
 
 		/* SRQ producer is 8 bytes. Need to update SGE producer index
 		 * in first 4 bytes and need to update WQE producer in
 		 * next 4 bytes.
 		 */
-		*srq->hw_srq.virt_prod_pair_addr = hw_srq->sge_prod;
-		offset = offsetof(struct rdma_srq_producers, wqe_prod);
-		*((u8 *)srq->hw_srq.virt_prod_pair_addr + offset) =
-			hw_srq->wqe_prod;
+		srq->hw_srq.virt_prod_pair_addr->sge_prod = hw_srq->sge_prod;
+		/* Make sure sge producer is updated first */
+		dma_wmb();
+		srq->hw_srq.virt_prod_pair_addr->wqe_prod = hw_srq->wqe_prod;
 
-		/* Flush producer after updating it. */
-		wmb();
 		wr = wr->next;
 	}
 
@@ -4182,7 +4180,7 @@ static int process_resp_one_srq(struct qedr_dev *dev, struct qedr_qp *qp,
 	} else {
 		__process_resp_one(dev, qp, cq, wc, resp, wr_id);
 	}
-	srq->hw_srq.wr_cons_cnt++;
+	atomic_inc(&srq->hw_srq.wr_cons_cnt);
 
 	return 1;
 }