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

Pull rdma updates from Jason Gunthorpe:
 "A quiet cycle after the larger 5.8 effort. Substantially cleanup and
  driver work with a few smaller features this time.

   - Driver updates for hfi1, rxe, mlx5, hns, qedr, usnic, bnxt_re

   - Removal of dead or redundant code across the drivers

   - RAW resource tracker dumps to include a device specific data blob
     for device objects to aide device debugging

   - Further advance the IOCTL interface, remove the ability to turn it
     off. Add QUERY_CONTEXT, QUERY_MR, and QUERY_PD commands

   - Remove stubs related to devices with no pkey table

   - A shared CQ scheme to allow multiple ULPs to share the CQ rings of
     a device to give higher performance

   - Several more static checker, syzkaller and rare crashers fixed"

* tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdma: (121 commits)
  RDMA/mlx5: Fix flow destination setting for RDMA TX flow table
  RDMA/rxe: Remove pkey table
  RDMA/umem: Add a schedule point in ib_umem_get()
  RDMA/hns: Fix the unneeded process when getting a general type of CQE error
  RDMA/hns: Fix error during modify qp RTS2RTS
  RDMA/hns: Delete unnecessary memset when allocating VF resource
  RDMA/hns: Remove redundant parameters in set_rc_wqe()
  RDMA/hns: Remove support for HIP08_A
  RDMA/hns: Refactor hns_roce_v2_set_hem()
  RDMA/hns: Remove redundant hardware opcode definitions
  RDMA/netlink: Remove CAP_NET_RAW check when dump a raw QP
  RDMA/include: Replace license text with SPDX tags
  RDMA/rtrs: remove WQ_MEM_RECLAIM for rtrs_wq
  RDMA/rtrs-clt: add an additional random 8 seconds before reconnecting
  RDMA/cma: Execute rdma_cm destruction from a handler properly
  RDMA/cma: Remove unneeded locking for req paths
  RDMA/cma: Using the standard locking pattern when delivering the removal event
  RDMA/cma: Simplify DEVICE_REMOVAL for internal_id
  RDMA/efa: Add EFA 0xefa1 PCI ID
  RDMA/efa: User/kernel compatibility handshake mechanism
  ...

1 files changed, 25 insertions, 20 deletions

diff --git a/drivers/infiniband/hw/qedr/verbs.c b/drivers/infiniband/hw/qedr/verbs.c
index f5aa85a5377c..4ce4e2eef6cc 100644
--- a/drivers/infiniband/hw/qedr/verbs.c
+++ b/drivers/infiniband/hw/qedr/verbs.c
@@ -239,7 +239,6 @@ int qedr_query_port(struct ib_device *ibdev, u8 port, struct ib_port_attr *attr)
 	attr->ip_gids = true;
 	if (rdma_protocol_iwarp(&dev->ibdev, 1)) {
 		attr->gid_tbl_len = 1;
-		attr->pkey_tbl_len = 1;
 	} else {
 		attr->gid_tbl_len = QEDR_MAX_SGID;
 		attr->pkey_tbl_len = QEDR_ROCE_PKEY_TABLE_LEN;
@@ -275,7 +274,8 @@ int qedr_alloc_ucontext(struct ib_ucontext *uctx, struct ib_udata *udata)
 			DP_ERR(dev, "Problem copying data from user space\n");
 			return -EFAULT;
 		}
-
+		ctx->edpm_mode = !!(ureq.context_flags &
+				    QEDR_ALLOC_UCTX_EDPM_MODE);
 		ctx->db_rec = !!(ureq.context_flags & QEDR_ALLOC_UCTX_DB_REC);
 	}
 
@@ -316,11 +316,15 @@ int qedr_alloc_ucontext(struct ib_ucontext *uctx, struct ib_udata *udata)
 		uresp.dpm_flags = QEDR_DPM_TYPE_IWARP_LEGACY;
 	else
 		uresp.dpm_flags = QEDR_DPM_TYPE_ROCE_ENHANCED |
-				  QEDR_DPM_TYPE_ROCE_LEGACY;
+				  QEDR_DPM_TYPE_ROCE_LEGACY |
+				  QEDR_DPM_TYPE_ROCE_EDPM_MODE;
 
-	uresp.dpm_flags |= QEDR_DPM_SIZES_SET;
-	uresp.ldpm_limit_size = QEDR_LDPM_MAX_SIZE;
-	uresp.edpm_trans_size = QEDR_EDPM_TRANS_SIZE;
+	if (ureq.context_flags & QEDR_SUPPORT_DPM_SIZES) {
+		uresp.dpm_flags |= QEDR_DPM_SIZES_SET;
+		uresp.ldpm_limit_size = QEDR_LDPM_MAX_SIZE;
+		uresp.edpm_trans_size = QEDR_EDPM_TRANS_SIZE;
+		uresp.edpm_limit_size = QEDR_EDPM_MAX_SIZE;
+	}
 
 	uresp.wids_enabled = 1;
 	uresp.wid_count = oparams.wid_count;
@@ -1754,7 +1758,7 @@ static int qedr_create_user_qp(struct qedr_dev *dev,
 	struct qed_rdma_create_qp_out_params out_params;
 	struct qedr_pd *pd = get_qedr_pd(ibpd);
 	struct qedr_create_qp_uresp uresp;
-	struct qedr_ucontext *ctx = NULL;
+	struct qedr_ucontext *ctx = pd ? pd->uctx : NULL;
 	struct qedr_create_qp_ureq ureq;
 	int alloc_and_init = rdma_protocol_roce(&dev->ibdev, 1);
 	int rc = -EINVAL;
@@ -1792,6 +1796,9 @@ static int qedr_create_user_qp(struct qedr_dev *dev,
 		in_params.rq_pbl_ptr = qp->urq.pbl_tbl->pa;
 	}
 
+	if (ctx)
+		SET_FIELD(in_params.flags, QED_ROCE_EDPM_MODE, ctx->edpm_mode);
+
 	qp->qed_qp = dev->ops->rdma_create_qp(dev->rdma_ctx,
 					      &in_params, &out_params);
 
@@ -3004,7 +3011,7 @@ err0:
 }
 
 struct ib_mr *qedr_alloc_mr(struct ib_pd *ibpd, enum ib_mr_type mr_type,
-			    u32 max_num_sg, struct ib_udata *udata)
+			    u32 max_num_sg)
 {
 	struct qedr_mr *mr;
 
@@ -3687,7 +3694,7 @@ 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;
 }
@@ -3702,7 +3709,6 @@ 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);
 
@@ -3715,7 +3721,8 @@ 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;
@@ -3749,22 +3756,20 @@ 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;
 	}
 
@@ -4183,7 +4188,7 @@ 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;
 }