RDMA/bnxt_re: Fix error recovery sequence

JIRA: https://issues.redhat.com/browse/RHEL-74367

commit e6178bf
Author: Kalesh AP <kalesh-anakkur.purayil@broadcom.com>
Date:   Tue Dec 31 08:20:08 2024 +0530

    RDMA/bnxt_re: Fix error recovery sequence

    Fixed to return ENXIO from __send_message_basic_sanity()
    to indicate that device is in error state. In the case of
    ERR_DEVICE_DETACHED state, the driver should not post the
    commands to the firmware as it will time out eventually.

    Removed bnxt_re_modify_qp() call from bnxt_re_dev_stop()
    as it is a no-op.

    Fixes: cc5b9b4 ("RDMA/bnxt_re: Recover the device when FW error is detected")
    Signed-off-by: Kalesh AP <kalesh-anakkur.purayil@broadcom.com>
    Signed-off-by: Kashyap Desai <kashyap.desai@broadcom.com>
    Link: https://patch.msgid.link/20241231025008.2267162-1-kalesh-anakkur.purayil@broadcom.com
    Reviewed-by: Selvin Xavier <selvin.xavier@broadcom.com>
    Signed-off-by: Leon Romanovsky <leon@kernel.org>

Signed-off-by: Mohammad Heib <mheib@redhat.com>

Author: mohammadheib

drivers/infiniband/hw/bnxt_re/main.c

@@ -1435,24 +1435,18 @@ static bool bnxt_re_is_qp1_or_shadow_qp(struct bnxt_re_dev *rdev,
 
 static void bnxt_re_dev_stop(struct bnxt_re_dev *rdev)
 {
-	int mask = IB_QP_STATE;
-	struct ib_qp_attr qp_attr;
 	struct bnxt_re_qp *qp;
 
-	qp_attr.qp_state = IB_QPS_ERR;
 	mutex_lock(&rdev->qp_lock);
 	list_for_each_entry(qp, &rdev->qp_list, list) {
 		/* Modify the state of all QPs except QP1/Shadow QP */
 		if (!bnxt_re_is_qp1_or_shadow_qp(rdev, qp)) {
 			if (qp->qplib_qp.state !=
 			    CMDQ_MODIFY_QP_NEW_STATE_RESET &&
 			    qp->qplib_qp.state !=
-			    CMDQ_MODIFY_QP_NEW_STATE_ERR) {
+			    CMDQ_MODIFY_QP_NEW_STATE_ERR)
 				bnxt_re_dispatch_event(&rdev->ibdev, &qp->ib_qp,
 						       1, IB_EVENT_QP_FATAL);
-				bnxt_re_modify_qp(&qp->ib_qp, &qp_attr, mask,
-						  NULL);
-			}
 		}
 	}
 	mutex_unlock(&rdev->qp_lock);

drivers/infiniband/hw/bnxt_re/qplib_rcfw.c

@@ -424,7 +424,8 @@ static int __send_message_basic_sanity(struct bnxt_qplib_rcfw *rcfw,
 
 	/* Prevent posting if f/w is not in a state to process */
 	if (test_bit(ERR_DEVICE_DETACHED, &rcfw->cmdq.flags))
-		return bnxt_qplib_map_rc(opcode);
+		return -ENXIO;
+
 	if (test_bit(FIRMWARE_STALL_DETECTED, &cmdq->flags))
 		return -ETIMEDOUT;
 
@@ -493,7 +494,7 @@ static int __bnxt_qplib_rcfw_send_message(struct bnxt_qplib_rcfw *rcfw,
 
 	rc = __send_message_basic_sanity(rcfw, msg, opcode);
 	if (rc)
-		return rc;
+		return rc == -ENXIO ? bnxt_qplib_map_rc(opcode) : rc;
 
 	rc = __send_message(rcfw, msg, opcode);
 	if (rc)