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

Pull rdma updates from Jason Gunthorpe:
 "Many small changes across the subystem, some highlights:

   - Usual driver cleanups in qedr, siw, erdma, hfi1, mlx4/5, irdma,
     mthca, hns, and bnxt_re

   - siw now works over tunnel and other netdevs with a MAC address by
     removing assumptions about a MAC/GID from the connection manager

   - "Doorbell Pacing" for bnxt_re - this is a best effort scheme to
     allow userspace to slow down the doorbell rings if the HW gets full

   - irdma egress VLAN priority, better QP/WQ sizing

   - rxe bug fixes in queue draining and srq resizing

   - Support more ethernet speed options in the core layer

   - DMABUF support for bnxt_re

   - Multi-stage MTT support for erdma to allow much bigger MR
     registrations

   - A irdma fix with a CVE that came in too late to go to -rc, missing
     bounds checking for 0 length MRs"

* tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdma: (87 commits)
  IB/hfi1: Reduce printing of errors during driver shut down
  RDMA/hfi1: Move user SDMA system memory pinning code to its own file
  RDMA/hfi1: Use list_for_each_entry() helper
  RDMA/mlx5: Fix trailing */ formatting in block comment
  RDMA/rxe: Fix redundant break statement in switch-case.
  RDMA/efa: Fix wrong resources deallocation order
  RDMA/siw: Call llist_reverse_order in siw_run_sq
  RDMA/siw: Correct wrong debug message
  RDMA/siw: Balance the reference of cep->kref in the error path
  Revert "IB/isert: Fix incorrect release of isert connection"
  RDMA/bnxt_re: Fix kernel doc errors
  RDMA/irdma: Prevent zero-length STAG registration
  RDMA/erdma: Implement hierarchical MTT
  RDMA/erdma: Refactor the storage structure of MTT entries
  RDMA/erdma: Renaming variable names and field names of struct erdma_mem
  RDMA/hns: Support hns HW stats
  RDMA/hns: Dump whole QP/CQ/MR resource in raw
  RDMA/irdma: Add missing kernel-doc in irdma_setup_umode_qp()
  RDMA/mlx4: Copy union directly
  RDMA/irdma: Drop unused kernel push code
  ...

1 files changed, 25 insertions, 20 deletions

diff --git a/drivers/infiniband/sw/rxe/rxe_req.c b/drivers/infiniband/sw/rxe/rxe_req.c
index 2171f19494bc..d8c41fd626a9 100644
--- a/drivers/infiniband/sw/rxe/rxe_req.c
+++ b/drivers/infiniband/sw/rxe/rxe_req.c
@@ -578,10 +578,11 @@ static void save_state(struct rxe_send_wqe *wqe,
 		       struct rxe_send_wqe *rollback_wqe,
 		       u32 *rollback_psn)
 {
-	rollback_wqe->state     = wqe->state;
+	rollback_wqe->state = wqe->state;
 	rollback_wqe->first_psn = wqe->first_psn;
-	rollback_wqe->last_psn  = wqe->last_psn;
-	*rollback_psn		= qp->req.psn;
+	rollback_wqe->last_psn = wqe->last_psn;
+	rollback_wqe->dma = wqe->dma;
+	*rollback_psn = qp->req.psn;
 }
 
 static void rollback_state(struct rxe_send_wqe *wqe,
@@ -589,10 +590,11 @@ static void rollback_state(struct rxe_send_wqe *wqe,
 			   struct rxe_send_wqe *rollback_wqe,
 			   u32 rollback_psn)
 {
-	wqe->state     = rollback_wqe->state;
+	wqe->state = rollback_wqe->state;
 	wqe->first_psn = rollback_wqe->first_psn;
-	wqe->last_psn  = rollback_wqe->last_psn;
-	qp->req.psn    = rollback_psn;
+	wqe->last_psn = rollback_wqe->last_psn;
+	wqe->dma = rollback_wqe->dma;
+	qp->req.psn = rollback_psn;
 }
 
 static void update_state(struct rxe_qp *qp, struct rxe_pkt_info *pkt)
@@ -797,6 +799,9 @@ int rxe_requester(struct rxe_qp *qp)
 	pkt.mask = rxe_opcode[opcode].mask;
 	pkt.wqe = wqe;
 
+	/* save wqe state before we build and send packet */
+	save_state(wqe, qp, &rollback_wqe, &rollback_psn);
+
 	av = rxe_get_av(&pkt, &ah);
 	if (unlikely(!av)) {
 		rxe_dbg_qp(qp, "Failed no address vector\n");
@@ -829,29 +834,29 @@ int rxe_requester(struct rxe_qp *qp)
 	if (ah)
 		rxe_put(ah);
 
-	/*
-	 * To prevent a race on wqe access between requester and completer,
-	 * wqe members state and psn need to be set before calling
-	 * rxe_xmit_packet().
-	 * Otherwise, completer might initiate an unjustified retry flow.
-	 */
-	save_state(wqe, qp, &rollback_wqe, &rollback_psn);
+	/* update wqe state as though we had sent it */
 	update_wqe_state(qp, wqe, &pkt);
 	update_wqe_psn(qp, wqe, &pkt, payload);
 
 	err = rxe_xmit_packet(qp, &pkt, skb);
 	if (err) {
-		qp->need_req_skb = 1;
+		if (err != -EAGAIN) {
+			wqe->status = IB_WC_LOC_QP_OP_ERR;
+			goto err;
+		}
 
+		/* the packet was dropped so reset wqe to the state
+		 * before we sent it so we can try to resend
+		 */
 		rollback_state(wqe, qp, &rollback_wqe, rollback_psn);
 
-		if (err == -EAGAIN) {
-			rxe_sched_task(&qp->req.task);
-			goto exit;
-		}
+		/* force a delay until the dropped packet is freed and
+		 * the send queue is drained below the low water mark
+		 */
+		qp->need_req_skb = 1;
 
-		wqe->status = IB_WC_LOC_QP_OP_ERR;
-		goto err;
+		rxe_sched_task(&qp->req.task);
+		goto exit;
 	}
 
 	update_state(qp, &pkt);