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

Pull rdma updates from Jason Gunthorpe:
 "Usual size of updates, a new driver, and most of the bulk focusing on
  rxe:

   - Usual typos, style, and language updates

   - Driver updates for mlx5, irdma, siw, rts, srp, hfi1, hns, erdma,
     mlx4, srp

   - Lots of RXE updates:
      * Improve reply error handling for bad MR operations
      * Code tidying
      * Debug printing uses common loggers
      * Remove half implemented RD related stuff
      * Support IBA's recently defined Atomic Write and Flush operations

   - erdma support for atomic operations

   - New driver 'mana' for Ethernet HW available in Azure VMs. This
     driver only supports DPDK"

* tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdma: (122 commits)
  IB/IPoIB: Fix queue count inconsistency for PKEY child interfaces
  RDMA: Add missed netdev_put() for the netdevice_tracker
  RDMA/rxe: Enable RDMA FLUSH capability for rxe device
  RDMA/cm: Make QP FLUSHABLE for supported device
  RDMA/rxe: Implement flush completion
  RDMA/rxe: Implement flush execution in responder side
  RDMA/rxe: Implement RC RDMA FLUSH service in requester side
  RDMA/rxe: Extend rxe packet format to support flush
  RDMA/rxe: Allow registering persistent flag for pmem MR only
  RDMA/rxe: Extend rxe user ABI to support flush
  RDMA: Extend RDMA kernel verbs ABI to support flush
  RDMA: Extend RDMA user ABI to support flush
  RDMA/rxe: Fix incorrect responder length checking
  RDMA/rxe: Fix oops with zero length reads
  RDMA/mlx5: Remove not-used IB_FLOW_SPEC_IB define
  RDMA/hns: Fix XRC caps on HIP08
  RDMA/hns: Fix error code of CMD
  RDMA/hns: Fix page size cap from firmware
  RDMA/hns: Fix PBL page MTR find
  RDMA/hns: Fix AH attr queried by query_qp
  ...

1 files changed, 34 insertions, 111 deletions

diff --git a/drivers/infiniband/hw/irdma/verbs.c b/drivers/infiniband/hw/irdma/verbs.c
index a22afbb25bc5..f6973ea55eda 100644
--- a/drivers/infiniband/hw/irdma/verbs.c
+++ b/drivers/infiniband/hw/irdma/verbs.c
@@ -64,36 +64,6 @@ static int irdma_query_device(struct ib_device *ibdev,
 }
 
 /**
- * irdma_get_eth_speed_and_width - Get IB port speed and width from netdev speed
- * @link_speed: netdev phy link speed
- * @active_speed: IB port speed
- * @active_width: IB port width
- */
-static void irdma_get_eth_speed_and_width(u32 link_speed, u16 *active_speed,
-					  u8 *active_width)
-{
-	if (link_speed <= SPEED_1000) {
-		*active_width = IB_WIDTH_1X;
-		*active_speed = IB_SPEED_SDR;
-	} else if (link_speed <= SPEED_10000) {
-		*active_width = IB_WIDTH_1X;
-		*active_speed = IB_SPEED_FDR10;
-	} else if (link_speed <= SPEED_20000) {
-		*active_width = IB_WIDTH_4X;
-		*active_speed = IB_SPEED_DDR;
-	} else if (link_speed <= SPEED_25000) {
-		*active_width = IB_WIDTH_1X;
-		*active_speed = IB_SPEED_EDR;
-	} else if (link_speed <= SPEED_40000) {
-		*active_width = IB_WIDTH_4X;
-		*active_speed = IB_SPEED_FDR10;
-	} else {
-		*active_width = IB_WIDTH_4X;
-		*active_speed = IB_SPEED_EDR;
-	}
-}
-
-/**
  * irdma_query_port - get port attributes
  * @ibdev: device pointer from stack
  * @port: port number for query
@@ -120,8 +90,9 @@ static int irdma_query_port(struct ib_device *ibdev, u32 port,
 		props->state = IB_PORT_DOWN;
 		props->phys_state = IB_PORT_PHYS_STATE_DISABLED;
 	}
-	irdma_get_eth_speed_and_width(SPEED_100000, &props->active_speed,
-				      &props->active_width);
+
+	ib_get_eth_speed(ibdev, port, &props->active_speed,
+			 &props->active_width);
 
 	if (rdma_protocol_roce(ibdev, 1)) {
 		props->gid_tbl_len = 32;
@@ -1242,6 +1213,7 @@ int irdma_modify_qp_roce(struct ib_qp *ibqp, struct ib_qp_attr *attr,
 		av->attrs = attr->ah_attr;
 		rdma_gid2ip((struct sockaddr *)&av->sgid_addr, &sgid_attr->gid);
 		rdma_gid2ip((struct sockaddr *)&av->dgid_addr, &attr->ah_attr.grh.dgid);
+		av->net_type = rdma_gid_attr_network_type(sgid_attr);
 		if (av->net_type == RDMA_NETWORK_IPV6) {
 			__be32 *daddr =
 				av->dgid_addr.saddr_in6.sin6_addr.in6_u.u6_addr32;
@@ -2358,9 +2330,10 @@ static bool irdma_check_mr_contiguous(struct irdma_pble_alloc *palloc,
  * @rf: RDMA PCI function
  * @iwmr: mr pointer for this memory registration
  * @use_pbles: flag if to use pble's
+ * @lvl_1_only: request only level 1 pble if true
  */
 static int irdma_setup_pbles(struct irdma_pci_f *rf, struct irdma_mr *iwmr,
-			     bool use_pbles)
+			     bool use_pbles, bool lvl_1_only)
 {
 	struct irdma_pbl *iwpbl = &iwmr->iwpbl;
 	struct irdma_pble_alloc *palloc = &iwpbl->pble_alloc;
@@ -2371,7 +2344,7 @@ static int irdma_setup_pbles(struct irdma_pci_f *rf, struct irdma_mr *iwmr,
 
 	if (use_pbles) {
 		status = irdma_get_pble(rf->pble_rsrc, palloc, iwmr->page_cnt,
-					false);
+					lvl_1_only);
 		if (status)
 			return status;
 
@@ -2414,16 +2387,10 @@ static int irdma_handle_q_mem(struct irdma_device *iwdev,
 	bool ret = true;
 
 	pg_size = iwmr->page_size;
-	err = irdma_setup_pbles(iwdev->rf, iwmr, use_pbles);
+	err = irdma_setup_pbles(iwdev->rf, iwmr, use_pbles, true);
 	if (err)
 		return err;
 
-	if (use_pbles && palloc->level != PBLE_LEVEL_1) {
-		irdma_free_pble(iwdev->rf->pble_rsrc, palloc);
-		iwpbl->pbl_allocated = false;
-		return -ENOMEM;
-	}
-
 	if (use_pbles)
 		arr = palloc->level1.addr;
 
@@ -2899,7 +2866,7 @@ static struct ib_mr *irdma_reg_user_mr(struct ib_pd *pd, u64 start, u64 len,
 	case IRDMA_MEMREG_TYPE_MEM:
 		use_pbles = (iwmr->page_cnt != 1);
 
-		err = irdma_setup_pbles(iwdev->rf, iwmr, use_pbles);
+		err = irdma_setup_pbles(iwdev->rf, iwmr, use_pbles, false);
 		if (err)
 			goto error;
 
@@ -3165,30 +3132,20 @@ static int irdma_post_send(struct ib_qp *ibqp,
 				info.stag_to_inv = ib_wr->ex.invalidate_rkey;
 			}
 
-			if (ib_wr->send_flags & IB_SEND_INLINE) {
-				info.op.inline_send.data = (void *)(unsigned long)
-							   ib_wr->sg_list[0].addr;
-				info.op.inline_send.len = ib_wr->sg_list[0].length;
-				if (iwqp->ibqp.qp_type == IB_QPT_UD ||
-				    iwqp->ibqp.qp_type == IB_QPT_GSI) {
-					ah = to_iwah(ud_wr(ib_wr)->ah);
-					info.op.inline_send.ah_id = ah->sc_ah.ah_info.ah_idx;
-					info.op.inline_send.qkey = ud_wr(ib_wr)->remote_qkey;
-					info.op.inline_send.dest_qp = ud_wr(ib_wr)->remote_qpn;
-				}
+			info.op.send.num_sges = ib_wr->num_sge;
+			info.op.send.sg_list = ib_wr->sg_list;
+			if (iwqp->ibqp.qp_type == IB_QPT_UD ||
+			    iwqp->ibqp.qp_type == IB_QPT_GSI) {
+				ah = to_iwah(ud_wr(ib_wr)->ah);
+				info.op.send.ah_id = ah->sc_ah.ah_info.ah_idx;
+				info.op.send.qkey = ud_wr(ib_wr)->remote_qkey;
+				info.op.send.dest_qp = ud_wr(ib_wr)->remote_qpn;
+			}
+
+			if (ib_wr->send_flags & IB_SEND_INLINE)
 				err = irdma_uk_inline_send(ukqp, &info, false);
-			} else {
-				info.op.send.num_sges = ib_wr->num_sge;
-				info.op.send.sg_list = ib_wr->sg_list;
-				if (iwqp->ibqp.qp_type == IB_QPT_UD ||
-				    iwqp->ibqp.qp_type == IB_QPT_GSI) {
-					ah = to_iwah(ud_wr(ib_wr)->ah);
-					info.op.send.ah_id = ah->sc_ah.ah_info.ah_idx;
-					info.op.send.qkey = ud_wr(ib_wr)->remote_qkey;
-					info.op.send.dest_qp = ud_wr(ib_wr)->remote_qpn;
-				}
+			else
 				err = irdma_uk_send(ukqp, &info, false);
-			}
 			break;
 		case IB_WR_RDMA_WRITE_WITH_IMM:
 			if (ukqp->qp_caps & IRDMA_WRITE_WITH_IMM) {
@@ -3205,22 +3162,15 @@ static int irdma_post_send(struct ib_qp *ibqp,
 			else
 				info.op_type = IRDMA_OP_TYPE_RDMA_WRITE;
 
-			if (ib_wr->send_flags & IB_SEND_INLINE) {
-				info.op.inline_rdma_write.data = (void *)(uintptr_t)ib_wr->sg_list[0].addr;
-				info.op.inline_rdma_write.len =
-						ib_wr->sg_list[0].length;
-				info.op.inline_rdma_write.rem_addr.addr =
-						rdma_wr(ib_wr)->remote_addr;
-				info.op.inline_rdma_write.rem_addr.lkey =
-						rdma_wr(ib_wr)->rkey;
+			info.op.rdma_write.num_lo_sges = ib_wr->num_sge;
+			info.op.rdma_write.lo_sg_list = ib_wr->sg_list;
+			info.op.rdma_write.rem_addr.addr =
+				rdma_wr(ib_wr)->remote_addr;
+			info.op.rdma_write.rem_addr.lkey = rdma_wr(ib_wr)->rkey;
+			if (ib_wr->send_flags & IB_SEND_INLINE)
 				err = irdma_uk_inline_rdma_write(ukqp, &info, false);
-			} else {
-				info.op.rdma_write.lo_sg_list = (void *)ib_wr->sg_list;
-				info.op.rdma_write.num_lo_sges = ib_wr->num_sge;
-				info.op.rdma_write.rem_addr.addr = rdma_wr(ib_wr)->remote_addr;
-				info.op.rdma_write.rem_addr.lkey = rdma_wr(ib_wr)->rkey;
+			else
 				err = irdma_uk_rdma_write(ukqp, &info, false);
-			}
 			break;
 		case IB_WR_RDMA_READ_WITH_INV:
 			inv_stag = true;
@@ -3380,7 +3330,6 @@ static enum ib_wc_status irdma_flush_err_to_ib_wc_status(enum irdma_flush_opcode
 static void irdma_process_cqe(struct ib_wc *entry,
 			      struct irdma_cq_poll_info *cq_poll_info)
 {
-	struct irdma_qp *iwqp;
 	struct irdma_sc_qp *qp;
 
 	entry->wc_flags = 0;
@@ -3388,7 +3337,6 @@ static void irdma_process_cqe(struct ib_wc *entry,
 	entry->wr_id = cq_poll_info->wr_id;
 
 	qp = cq_poll_info->qp_handle;
-	iwqp = qp->qp_uk.back_qp;
 	entry->qp = qp->qp_uk.back_qp;
 
 	if (cq_poll_info->error) {
@@ -3421,42 +3369,17 @@ static void irdma_process_cqe(struct ib_wc *entry,
 		}
 	}
 
-	switch (cq_poll_info->op_type) {
-	case IRDMA_OP_TYPE_RDMA_WRITE:
-	case IRDMA_OP_TYPE_RDMA_WRITE_SOL:
-		entry->opcode = IB_WC_RDMA_WRITE;
-		break;
-	case IRDMA_OP_TYPE_RDMA_READ_INV_STAG:
-	case IRDMA_OP_TYPE_RDMA_READ:
-		entry->opcode = IB_WC_RDMA_READ;
-		break;
-	case IRDMA_OP_TYPE_SEND_INV:
-	case IRDMA_OP_TYPE_SEND_SOL:
-	case IRDMA_OP_TYPE_SEND_SOL_INV:
-	case IRDMA_OP_TYPE_SEND:
-		entry->opcode = IB_WC_SEND;
-		break;
-	case IRDMA_OP_TYPE_FAST_REG_NSMR:
-		entry->opcode = IB_WC_REG_MR;
-		break;
-	case IRDMA_OP_TYPE_INV_STAG:
-		entry->opcode = IB_WC_LOCAL_INV;
-		break;
-	case IRDMA_OP_TYPE_REC_IMM:
-	case IRDMA_OP_TYPE_REC:
-		entry->opcode = cq_poll_info->op_type == IRDMA_OP_TYPE_REC_IMM ?
-			IB_WC_RECV_RDMA_WITH_IMM : IB_WC_RECV;
+	if (cq_poll_info->q_type == IRDMA_CQE_QTYPE_SQ) {
+		set_ib_wc_op_sq(cq_poll_info, entry);
+	} else {
+		set_ib_wc_op_rq(cq_poll_info, entry,
+				qp->qp_uk.qp_caps & IRDMA_SEND_WITH_IMM ?
+				true : false);
 		if (qp->qp_uk.qp_type != IRDMA_QP_TYPE_ROCE_UD &&
 		    cq_poll_info->stag_invalid_set) {
 			entry->ex.invalidate_rkey = cq_poll_info->inv_stag;
 			entry->wc_flags |= IB_WC_WITH_INVALIDATE;
 		}
-		break;
-	default:
-		ibdev_err(&iwqp->iwdev->ibdev,
-			  "Invalid opcode = %d in CQE\n", cq_poll_info->op_type);
-		entry->status = IB_WC_GENERAL_ERR;
-		return;
 	}
 
 	if (qp->qp_uk.qp_type == IRDMA_QP_TYPE_ROCE_UD) {