Unverified Commit cc58681d authored by openeuler-ci-bot's avatar openeuler-ci-bot Committed by Gitee
Browse files

!427 Support the feature of querying stats 

Merge Pull Request from: @stinft 
 
Feature information:
1.RDMA/hns: Support hns HW stats
Support query hns HW stats to help debugging several issues.
2.RDMA/hns: Add dfx cnt stats
Add more dfx cnt to help diagnosis. And this stats could be got by
sysfs or rdmatool.
bugzilla：https://gitee.com/openeuler/kernel/issues/I6GSZL 
 
Link:https://gitee.com/openeuler/kernel/pulls/427

 

Reviewed-by: default avatarYue Haibing <yuehaibing@huawei.com>
Reviewed-by: default avatarZheng Zengkai <zhengzengkai@huawei.com>
Signed-off-by: default avatarZheng Zengkai <zhengzengkai@huawei.com>
parents 1c8d3dec d5a4ca75

drivers/infiniband/hw/hns/hns_roce_ah.c

+6 −2
Original line number Diff line number Diff line
@@ -85,7 +85,7 @@ int hns_roce_create_ah(struct ib_ah *ibah, struct rdma_ah_init_attr *init_attr, 
		ret = 0;



	if (ret && grh->sgid_attr->gid_type == IB_GID_TYPE_ROCE_UDP_ENCAP)

		return ret;

		goto err_out;



	if (tc_mode == HNAE3_TC_MAP_MODE_DSCP &&

	    grh->sgid_attr->gid_type == IB_GID_TYPE_ROCE_UDP_ENCAP)
@@ -101,7 +101,7 @@ int hns_roce_create_ah(struct ib_ah *ibah, struct rdma_ah_init_attr *init_attr, 
		ret = rdma_read_gid_l2_fields(ah_attr->grh.sgid_attr,

					      &ah->av.vlan_id, NULL);

		if (ret)

			return ret;

			goto err_out;



		ah->av.vlan_en = ah->av.vlan_id < VLAN_N_VID;

	}
@@ -113,6 +113,10 @@ int hns_roce_create_ah(struct ib_ah *ibah, struct rdma_ah_init_attr *init_attr, 
				       min(udata->outlen, sizeof(resp)));

	}



err_out:

	if (ret)

		atomic64_inc(&hr_dev->dfx_cnt[HNS_ROCE_DFX_AH_CREATE_ERR_CNT]);



	return ret;

}

drivers/infiniband/hw/hns/hns_roce_cmd.c

+15 −2
Original line number Diff line number Diff line
@@ -41,7 +41,14 @@ 
static int hns_roce_cmd_mbox_post_hw(struct hns_roce_dev *hr_dev,

				     struct hns_roce_mbox_msg *mbox_msg)

{

	return hr_dev->hw->post_mbox(hr_dev, mbox_msg);

	int ret;



	ret = hr_dev->hw->post_mbox(hr_dev, mbox_msg);

	if (ret)

		return ret;



	atomic64_inc(&hr_dev->dfx_cnt[HNS_ROCE_DFX_MBX_POSTED_CNT]);

	return 0;

}



/* this should be called with "poll_sem" */
@@ -58,7 +65,12 @@ static int __hns_roce_cmd_mbox_poll(struct hns_roce_dev *hr_dev, 
		return ret;

	}



	return hr_dev->hw->poll_mbox_done(hr_dev);

	ret = hr_dev->hw->poll_mbox_done(hr_dev);

	if (ret)

		return ret;



	atomic64_inc(&hr_dev->dfx_cnt[HNS_ROCE_DFX_MBX_POLLED_CNT]);

	return 0;

}



static int hns_roce_cmd_mbox_poll(struct hns_roce_dev *hr_dev,
@@ -89,6 +101,7 @@ void hns_roce_cmd_event(struct hns_roce_dev *hr_dev, u16 token, u8 status, 
	context->result = (status == HNS_ROCE_CMD_SUCCESS) ? 0 : (-EIO);

	context->out_param = out_param;

	complete(&context->done);

	atomic64_inc(&hr_dev->dfx_cnt[HNS_ROCE_DFX_MBX_EVENT_CNT]);

}



static int __hns_roce_cmd_mbox_wait(struct hns_roce_dev *hr_dev,

drivers/infiniband/hw/hns/hns_roce_cq.c

+11 −6
Original line number Diff line number Diff line
@@ -363,17 +363,19 @@ int hns_roce_create_cq(struct ib_cq *ib_cq, const struct ib_cq_init_attr *attr, 
	struct hns_roce_ib_create_cq ucmd = {};

	int ret;



	if (attr->flags)

		return -EOPNOTSUPP;

	if (attr->flags) {

		ret = -EOPNOTSUPP;

		goto err_out;

	}



	ret = verify_cq_create_attr(hr_dev, attr);

	if (ret)

		return ret;

		goto err_out;



	if (udata) {

		ret = get_cq_ucmd(hr_cq, udata, &ucmd);

		if (ret)

			return ret;

			goto err_out;



	}
@@ -381,12 +383,12 @@ int hns_roce_create_cq(struct ib_cq *ib_cq, const struct ib_cq_init_attr *attr, 


	ret = set_cqe_size(hr_cq, udata, &ucmd);

	if (ret)

		return ret;

		goto err_out;



	ret = alloc_cq_buf(hr_dev, hr_cq, udata, ucmd.buf_addr);

	if (ret) {

		ibdev_err(ibdev, "failed to alloc CQ buf, ret = %d.\n", ret);

		return ret;

		goto err_out;

	}



	ret = alloc_cq_db(hr_dev, hr_cq, udata, ucmd.db_addr, &resp);
@@ -431,6 +433,9 @@ int hns_roce_create_cq(struct ib_cq *ib_cq, const struct ib_cq_init_attr *attr, 
	free_cq_db(hr_dev, hr_cq, udata);

err_cq_buf:

	free_cq_buf(hr_dev, hr_cq);

err_out:

	atomic64_inc(&hr_dev->dfx_cnt[HNS_ROCE_DFX_CQ_CREATE_ERR_CNT]);



	return ret;

}

drivers/infiniband/hw/hns/hns_roce_device.h

+50 −0
Original line number Diff line number Diff line
@@ -914,6 +914,53 @@ enum hns_roce_device_state { 
	HNS_ROCE_DEVICE_STATE_UNINIT,

};



enum hns_roce_hw_pkt_stat_index {

	HNS_ROCE_HW_RX_RC_PKT_CNT,

	HNS_ROCE_HW_RX_UC_PKT_CNT,

	HNS_ROCE_HW_RX_UD_PKT_CNT,

	HNS_ROCE_HW_RX_XRC_PKT_CNT,

	HNS_ROCE_HW_RX_PKT_CNT,

	HNS_ROCE_HW_RX_ERR_PKT_CNT,

	HNS_ROCE_HW_RX_CNP_PKT_CNT,

	HNS_ROCE_HW_TX_RC_PKT_CNT,

	HNS_ROCE_HW_TX_UC_PKT_CNT,

	HNS_ROCE_HW_TX_UD_PKT_CNT,

	HNS_ROCE_HW_TX_XRC_PKT_CNT,

	HNS_ROCE_HW_TX_PKT_CNT,

	HNS_ROCE_HW_TX_ERR_PKT_CNT,

	HNS_ROCE_HW_TX_CNP_PKT_CNT,

	HNS_ROCE_HW_TRP_GET_MPT_ERR_PKT_CNT,

	HNS_ROCE_HW_TRP_GET_IRRL_ERR_PKT_CNT,

	HNS_ROCE_HW_ECN_DB_CNT,

	HNS_ROCE_HW_RX_BUF_CNT,

	HNS_ROCE_HW_TRP_RX_SOF_CNT,

	HNS_ROCE_HW_CQ_CQE_CNT,

	HNS_ROCE_HW_CQ_POE_CNT,

	HNS_ROCE_HW_CQ_NOTIFY_CNT,

	HNS_ROCE_HW_CNT_TOTAL,

};



enum hns_roce_hw_dfx_stat_index {

	HNS_ROCE_DFX_AEQE_CNT,

	HNS_ROCE_DFX_CEQE_CNT,

	HNS_ROCE_DFX_CMDS_CNT,

	HNS_ROCE_DFX_CMDS_ERR_CNT,

	HNS_ROCE_DFX_MBX_POSTED_CNT,

	HNS_ROCE_DFX_MBX_POLLED_CNT,

	HNS_ROCE_DFX_MBX_EVENT_CNT,

	HNS_ROCE_DFX_QP_CREATE_ERR_CNT,

	HNS_ROCE_DFX_QP_MODIFY_ERR_CNT,

	HNS_ROCE_DFX_CQ_CREATE_ERR_CNT,

	HNS_ROCE_DFX_SRQ_CREATE_ERR_CNT,

	HNS_ROCE_DFX_XRCD_ALLOC_ERR_CNT,

	HNS_ROCE_DFX_MR_REG_ERR_CNT,

	HNS_ROCE_DFX_MR_REREG_ERR_CNT,

	HNS_ROCE_DFX_AH_CREATE_ERR_CNT,

	HNS_ROCE_DFX_MMAP_ERR_CNT,

	HNS_ROCE_DFX_UCTX_ALLOC_ERR_CNT,

	HNS_ROCE_DFX_CNT_TOTAL

};



struct hns_roce_hw {

	int (*cmq_init)(struct hns_roce_dev *hr_dev);

	void (*cmq_exit)(struct hns_roce_dev *hr_dev);
@@ -962,6 +1009,8 @@ struct hns_roce_hw { 
	int (*query_mpt)(struct hns_roce_dev *hr_dev, u32 key, void *buffer);

	int (*get_dscp)(struct hns_roce_dev *hr_dev, u8 dscp,

			u8 *tc_mode, u8 *priority);

	int (*query_hw_counter)(struct hns_roce_dev *hr_dev,

				u64 *stats, u32 port, int *hw_counters);

	const struct ib_device_ops *hns_roce_dev_ops;

	const struct ib_device_ops *hns_roce_dev_srq_ops;

	int (*bond_init)(struct hns_roce_dev *hr_dev);
@@ -1045,6 +1094,7 @@ struct hns_roce_dev { 
	struct delayed_work bond_work;

	struct hns_roce_bond_group *bond_grp;

	struct netdev_lag_lower_state_info slave_state;

	atomic64_t *dfx_cnt;

};



static inline struct hns_roce_dev *to_hr_dev(struct ib_device *ib_dev)

drivers/infiniband/hw/hns/hns_roce_hw_v2.c

+58 −0
Original line number Diff line number Diff line
@@ -1396,6 +1396,8 @@ static int __hns_roce_cmq_send(struct hns_roce_dev *hr_dev, 
	/* Write to hardware */

	roce_write(hr_dev, ROCEE_TX_CMQ_PI_REG, csq->head);



	atomic64_inc(&hr_dev->dfx_cnt[HNS_ROCE_DFX_CMDS_CNT]);



	do {

		if (hns_roce_cmq_csq_done(hr_dev))

			break;
@@ -1433,6 +1435,9 @@ static int __hns_roce_cmq_send(struct hns_roce_dev *hr_dev, 


	spin_unlock_bh(&csq->lock);



	if (ret)

		atomic64_inc(&hr_dev->dfx_cnt[HNS_ROCE_DFX_CMDS_ERR_CNT]);



	return ret;

}
@@ -1772,6 +1777,56 @@ static int hns_roce_query_func_info(struct hns_roce_dev *hr_dev) 
	return 0;

}



static int hns_roce_hw_v2_query_counter(struct hns_roce_dev *hr_dev,

					u64 *stats, u32 port, int *num_counters)

{

#define CNT_PER_DESC 3

	struct hns_roce_cmq_desc *desc;

	int bd_idx, cnt_idx;

	__le64 *cnt_data;

	int desc_num;

	int ret;

	int i;



	if (port > hr_dev->caps.num_ports)

		return -EINVAL;



	desc_num = DIV_ROUND_UP(HNS_ROCE_HW_CNT_TOTAL, CNT_PER_DESC);

	desc = kcalloc(desc_num, sizeof(*desc), GFP_KERNEL);

	if (!desc)

		return -ENOMEM;



	for (i = 0; i < desc_num; i++) {

		hns_roce_cmq_setup_basic_desc(&desc[i],

					      HNS_ROCE_OPC_QUERY_COUNTER, true);

		if (i != desc_num - 1)

			desc[i].flag |= cpu_to_le16(HNS_ROCE_CMD_FLAG_NEXT);

	}



	ret = hns_roce_cmq_send(hr_dev, desc, desc_num);

	if (ret) {

		ibdev_err(&hr_dev->ib_dev,

			  "failed to get counter, ret = %d.\n", ret);

		goto err_out;

	}



	for (i = 0; i < HNS_ROCE_HW_CNT_TOTAL && i < *num_counters; i++) {

		bd_idx = i / CNT_PER_DESC;

		if (!(desc[bd_idx].flag & HNS_ROCE_CMD_FLAG_NEXT) &&

		    bd_idx != HNS_ROCE_HW_CNT_TOTAL / CNT_PER_DESC)

			break;



		cnt_data = (__le64 *)&desc[bd_idx].data[0];

		cnt_idx = i % CNT_PER_DESC;

		stats[i] = le64_to_cpu(cnt_data[cnt_idx]);

	}

	*num_counters = i;



err_out:

	kfree(desc);

	return ret;

}



static int hns_roce_config_global_param(struct hns_roce_dev *hr_dev)

{

	struct hns_roce_cmq_desc desc;
@@ -6465,6 +6520,7 @@ static irqreturn_t hns_roce_v2_aeq_int(struct hns_roce_dev *hr_dev, 
		eq->sub_type = sub_type;

		++eq->cons_index;

		aeqe_found = IRQ_HANDLED;

		atomic64_inc(&hr_dev->dfx_cnt[HNS_ROCE_DFX_AEQE_CNT]);



		hns_roce_v2_init_irq_work(hr_dev, eq, queue_num);
@@ -6507,6 +6563,7 @@ static irqreturn_t hns_roce_v2_ceq_int(struct hns_roce_dev *hr_dev, 


		++eq->cons_index;

		ceqe_found = IRQ_HANDLED;

		atomic64_inc(&hr_dev->dfx_cnt[HNS_ROCE_DFX_CEQE_CNT]);



		ceqe = next_ceqe_sw_v2(eq);

	}
@@ -7140,6 +7197,7 @@ static const struct hns_roce_hw hns_roce_hw_v2 = { 
	.bond_init = hns_roce_bond_init,

	.bond_is_active = hns_roce_bond_is_active,

	.get_bond_netdev = hns_roce_get_bond_netdev,

	.query_hw_counter = hns_roce_hw_v2_query_counter,

};



static const struct pci_device_id hns_roce_hw_v2_pci_tbl[] = {