Commit f9debea2 authored by Chengchang Tang's avatar Chengchang Tang Committed by 岳国风
Browse files

RDMA/hns: Fix cpu stuck by printings during reset

driver inclusion
category: bugfix
bugzilla: https://gitee.com/openeuler/kernel/issues/I9SI44



----------------------------------------------------------------------

During the reset, issuing the cmdq command to destroy resources
such as qp, cq, and mr may fail, and the destruction failure
information is printed. When a large number of resources fail to
be destroyed, printk() causes multiple threads to compete for a
global log buffer spinlock.  As a result, the CPU performance
deteriorates and the CPU is stuck. To fix it, use a function like
printk_limit_rate() to limit the print frequency of printk().

Fixes: 9a443537 ("IB/hns: Add driver files for hns RoCE driver")
Fixes: c7bcb134 ("RDMA/hns: Add SRQ support for hip08 kernel mode")
Fixes: 626903e9 ("RDMA/hns: Add support for reporting wc as software mode")
Fixes: 6eef5242 ("RDMA/hns: Replace not intuitive function/macro names")
Fixes: 6f5f556d ("RDMA/hns: Use the reserved loopback QPs to free MR before destroying MPT")
Fixes: 357f3429 ("RDMA/hns: Simplify the state judgment code of qp")
Fixes: 926a01dc ("RDMA/hns: Add QP operations support for hip08 SoC")
Fixes: 0273952c ("RDMA/hns: Add method to detach WQE buffer")
Fixes: 9c9edf68 ("RDMA/hns: Remove redundant DFX file and DFX ops structure")
Signed-off-by: default avatarChengchang Tang <tangchengchang@huawei.com>
Signed-off-by: default avatarGuofeng Yue <yueguofeng@h-partners.com>
parent ef32fef1
Loading
Loading
Loading
Loading
+3 −2
Original line number Diff line number Diff line
@@ -179,8 +179,9 @@ static void free_cqc(struct hns_roce_dev *hr_dev, struct hns_roce_cq *hr_cq)
	ret = hns_roce_destroy_hw_ctx(hr_dev, HNS_ROCE_CMD_DESTROY_CQC,
				      hr_cq->cqn);
	if (ret)
		dev_err(dev, "DESTROY_CQ failed (%d) for CQN %06lx\n", ret,
			hr_cq->cqn);
		dev_err_ratelimited(dev,
				    "DESTROY_CQ failed (%d) for CQN %06lx\n",
				    ret, hr_cq->cqn);
	if (ret == -EBUSY)
		hr_cq->delayed_destroy_flag = true;

+3 −2
Original line number Diff line number Diff line
@@ -712,7 +712,8 @@ void hns_roce_table_put(struct hns_roce_dev *hr_dev,

	ret = hr_dev->hw->clear_hem(hr_dev, table, obj, HEM_HOP_STEP_DIRECT);
	if (ret)
		dev_warn(dev, "failed to clear HEM base address, ret = %d.\n",
		dev_warn_ratelimited(dev,
			"failed to clear HEM base address, ret = %d.\n",
			ret);

	hns_roce_free_hem(hr_dev, table->hem[i]);
+29 −21
Original line number Diff line number Diff line
@@ -451,11 +451,13 @@ static int check_send_valid(struct hns_roce_dev *hr_dev,
	if (unlikely(hr_qp->state == IB_QPS_RESET ||
		     hr_qp->state == IB_QPS_INIT ||
		     hr_qp->state == IB_QPS_RTR)) {
		ibdev_err(ibdev, "failed to post WQE, QP state %u!\n",
		ibdev_err_ratelimited(ibdev,
				      "failed to post WQE, QP state %u!\n",
				      hr_qp->state);
		return -EINVAL;
	} else if (unlikely(hr_dev->state >= HNS_ROCE_DEVICE_STATE_RST_DOWN)) {
		ibdev_err(ibdev, "failed to post WQE, dev state %d!\n",
		ibdev_err_ratelimited(ibdev,
				      "failed to post WQE, dev state %d!\n",
				      hr_dev->state);
		return -EIO;
	}
@@ -463,7 +465,7 @@ static int check_send_valid(struct hns_roce_dev *hr_dev,
	if (check_dca_attach_enable(hr_qp)) {
		ret = dca_attach_qp_buf(hr_dev, hr_qp);
		if (unlikely(ret)) {
			ibdev_err(ibdev,
			ibdev_err_ratelimited(ibdev,
				  "failed to attach DCA for QP-%ld send!\n",
				  hr_qp->qpn);
			return ret;
@@ -3818,7 +3820,8 @@ static int free_mr_post_send_lp_wqe(struct hns_roce_qp *hr_qp)

	ret = hns_roce_v2_post_send(&hr_qp->ibqp, send_wr, &bad_wr);
	if (ret) {
		ibdev_err(ibdev, "failed to post wqe for free mr, ret = %d.\n",
		ibdev_err_ratelimited(ibdev,
			"failed to post wqe for free mr, ret = %d.\n",
			ret);
		return ret;
	}
@@ -3858,7 +3861,7 @@ static void free_mr_send_cmd_to_hw(struct hns_roce_dev *hr_dev)

		ret = free_mr_post_send_lp_wqe(hr_qp);
		if (ret) {
			ibdev_err(ibdev,
			ibdev_err_ratelimited(ibdev,
				  "failed to send wqe (qp:0x%lx) for free mr, ret = %d.\n",
				  hr_qp->qpn, ret);
			break;
@@ -3871,14 +3874,14 @@ static void free_mr_send_cmd_to_hw(struct hns_roce_dev *hr_dev)
	while (cqe_cnt) {
		npolled = hns_roce_v2_poll_cq(&free_mr->rsv_cq->ib_cq, cqe_cnt, wc);
		if (npolled < 0) {
			ibdev_err(ibdev,
			ibdev_err_ratelimited(ibdev,
				  "failed to poll cqe for free mr, remain %d cqe.\n",
				  cqe_cnt);
			goto out;
		}

		if (time_after(jiffies, end)) {
			ibdev_err(ibdev,
			ibdev_err_ratelimited(ibdev,
				  "failed to poll cqe for free mr and timeout, remain %d cqe.\n",
				  cqe_cnt);
			goto out;
@@ -5541,7 +5544,8 @@ static int hns_roce_v2_set_abs_fields(struct ib_qp *ibqp,
	int ret = 0;

	if (!check_qp_state(cur_state, new_state)) {
		ibdev_err(&hr_dev->ib_dev, "Illegal state for QP!\n");
		ibdev_err_ratelimited(&hr_dev->ib_dev,
				      "Illegal state for QP!\n");
		return -EINVAL;
	}

@@ -5801,7 +5805,7 @@ static int hns_roce_v2_modify_qp(struct ib_qp *ibqp,
	/* SW pass context to HW */
	ret = hns_roce_v2_qp_modify(hr_dev, context, qpc_mask, hr_qp);
	if (ret) {
		ibdev_err(ibdev, "failed to modify QP, ret = %d.\n", ret);
		ibdev_err_ratelimited(ibdev, "failed to modify QP, ret = %d.\n", ret);
		goto out;
	}

@@ -5986,7 +5990,9 @@ static int hns_roce_v2_query_qp(struct ib_qp *ibqp, struct ib_qp_attr *qp_attr,

	ret = hns_roce_v2_query_qpc(hr_dev, hr_qp->qpn, &context);
	if (ret) {
		ibdev_err(ibdev, "failed to query QPC, ret = %d.\n", ret);
		ibdev_err_ratelimited(ibdev,
				      "failed to query QPC, ret = %d.\n",
				      ret);
		ret = -EINVAL;
		goto out;
	}
@@ -5994,7 +6000,7 @@ static int hns_roce_v2_query_qp(struct ib_qp *ibqp, struct ib_qp_attr *qp_attr,
	state = hr_reg_read(&context, QPC_QP_ST);
	tmp_qp_state = to_ib_qp_st((enum hns_roce_v2_qp_state)state);
	if (tmp_qp_state == -1) {
		ibdev_err(ibdev, "Illegal ib_qp_state\n");
		ibdev_err_ratelimited(ibdev, "Illegal ib_qp_state\n");
		ret = -EINVAL;
		goto out;
	}
@@ -6076,7 +6082,9 @@ static bool hns_roce_v2_chk_dca_buf_inactive(struct hns_roce_dev *hr_dev,

	ret = hns_roce_v2_query_qpc(hr_dev, hr_qp->qpn, &context);
	if (ret) {
		ibdev_err(ibdev, "failed to query DCA QPC, ret = %d.\n", ret);
		ibdev_err_ratelimited(ibdev,
				      "failed to query DCA QPC, ret = %d.\n",
				      ret);
		return false;
	}

@@ -6120,7 +6128,7 @@ int hns_roce_v2_destroy_qp_common(struct hns_roce_dev *hr_dev,
		ret = hns_roce_v2_modify_qp(&hr_qp->ibqp, NULL, 0,
					    hr_qp->state, IB_QPS_RESET, udata);
		if (ret)
			ibdev_err(ibdev,
			ibdev_err_ratelimited(ibdev,
				  "failed to modify QP to RST, ret = %d.\n",
				  ret);
	}
@@ -6158,7 +6166,7 @@ int hns_roce_v2_destroy_qp(struct ib_qp *ibqp, struct ib_udata *udata)

	ret = hns_roce_v2_destroy_qp_common(hr_dev, hr_qp, udata);
	if (ret)
		ibdev_err(&hr_dev->ib_dev,
		ibdev_err_ratelimited(&hr_dev->ib_dev,
			  "failed to destroy QP, QPN = 0x%06lx, ret = %d.\n",
			  hr_qp->qpn, ret);

@@ -6457,7 +6465,7 @@ static int hns_roce_v2_modify_cq(struct ib_cq *cq, u16 cq_count, u16 cq_period)
				HNS_ROCE_CMD_MODIFY_CQC, hr_cq->cqn);
	hns_roce_free_cmd_mailbox(hr_dev, mailbox);
	if (ret)
		ibdev_err(&hr_dev->ib_dev,
		ibdev_err_ratelimited(&hr_dev->ib_dev,
			  "failed to process cmd when modifying CQ, ret = %d.\n",
			  ret);

@@ -6483,7 +6491,7 @@ static int hns_roce_v2_query_cqc(struct hns_roce_dev *hr_dev, u32 cqn,
	ret = hns_roce_cmd_mbox(hr_dev, 0, mailbox->dma,
				HNS_ROCE_CMD_QUERY_CQC, cqn);
	if (ret) {
		ibdev_err(&hr_dev->ib_dev,
		ibdev_err_ratelimited(&hr_dev->ib_dev,
			"failed to process cmd when querying CQ, ret = %d.\n",
			ret);
		goto err_mailbox;
+1 −1
Original line number Diff line number Diff line
@@ -151,7 +151,7 @@ static void hns_roce_mr_free(struct hns_roce_dev *hr_dev, struct hns_roce_mr *mr
					      key_to_hw_index(mr->key) &
					      (hr_dev->caps.num_mtpts - 1));
		if (ret)
			ibdev_warn(ibdev, "failed to destroy mpt, ret = %d.\n",
			ibdev_warn_ratelimited(ibdev, "failed to destroy mpt, ret = %d.\n",
				   ret);
		if (ret == -EBUSY)
			mr->delayed_destroy_flag = true;
+3 −2
Original line number Diff line number Diff line
@@ -162,7 +162,8 @@ static void free_srqc(struct hns_roce_dev *hr_dev, struct hns_roce_srq *srq)
	ret = hns_roce_destroy_hw_ctx(hr_dev, HNS_ROCE_CMD_DESTROY_SRQ,
				      srq->srqn);
	if (ret)
		dev_err(hr_dev->dev, "DESTROY_SRQ failed (%d) for SRQN %06lx\n",
		dev_err_ratelimited(hr_dev->dev,
				    "DESTROY_SRQ failed (%d) for SRQN %06lx\n",
				    ret, srq->srqn);
	if (ret == -EBUSY)
		srq->delayed_destroy_flag = true;