hinic: fix out-of-order excution in arm cpu

add read barrier in driver code to keep from reading other fileds
in dma memory which is writable for hw until we have verified the
memory is valid for driver
Signed-off-by: Luo bin <luobin9@huawei.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

drivers/net/ethernet/huawei/hinic/hinic_hw_cmdq.c

@@ -623,6 +623,8 @@ static int cmdq_cmd_ceq_handler(struct hinic_cmdq *cmdq, u16 ci,
 	if (!CMDQ_WQE_COMPLETED(be32_to_cpu(ctrl->ctrl_info)))
 		return -EBUSY;
 
+	dma_rmb();
+
 	errcode = CMDQ_WQE_ERRCODE_GET(be32_to_cpu(status->status_info), VAL);
 
 	cmdq_sync_cmd_handler(cmdq, ci, errcode);

drivers/net/ethernet/huawei/hinic/hinic_hw_eqs.c

@@ -235,6 +235,8 @@ static void aeq_irq_handler(struct hinic_eq *eq)
 		if (HINIC_EQ_ELEM_DESC_GET(aeqe_desc, WRAPPED) == eq->wrapped)
 			break;
 
+		dma_rmb();
+
 		event = HINIC_EQ_ELEM_DESC_GET(aeqe_desc, TYPE);
 		if (event >= HINIC_MAX_AEQ_EVENTS) {
 			dev_err(&pdev->dev, "Unknown AEQ Event %d\n", event);

drivers/net/ethernet/huawei/hinic/hinic_rx.c

@@ -350,6 +350,9 @@ static int rxq_recv(struct hinic_rxq *rxq, int budget)
 		if (!rq_wqe)
 			break;
 
+		/* make sure we read rx_done before packet length */
+		dma_rmb();
+
 		cqe = rq->cqe[ci];
 		status =  be32_to_cpu(cqe->status);
 		hinic_rq_get_sge(rxq->rq, rq_wqe, ci, &sge);

drivers/net/ethernet/huawei/hinic/hinic_tx.c

@@ -622,6 +622,8 @@ static int free_tx_poll(struct napi_struct *napi, int budget)
 	do {
 		hw_ci = HW_CONS_IDX(sq) & wq->mask;
 
+		dma_rmb();
+
 		/* Reading a WQEBB to get real WQE size and consumer index. */
 		sq_wqe = hinic_sq_read_wqebb(sq, &skb, &wqe_size, &sw_ci);
 		if ((!sq_wqe) ||