Unverified Commit eee89848 authored by openeuler-ci-bot's avatar openeuler-ci-bot Committed by Gitee
Browse files

!13044 Some patches of RDMA/hns from Linux to OLK-6.6 

Merge Pull Request from: @ci-robot 
 
PR sync from: Chengchang Tang <tangchengchang@huawei.com>
https://mailweb.openeuler.org/hyperkitty/list/kernel@openeuler.org/message/33LMZO36ZOPABOQTZHSZYQQFBG3SAEIS/ 
From: Xinghai Cen <cenxinghai@h-partners.com>

Some patches of RDMA/hns from Linux to OLK-6.6

Junxian Huang (1):
  RDMA/hns: Use dev_* printings in hem code instead of ibdev_*

Xinghai Cen (2):
  Revert "RDMA/hns: Fix missing spin_lock_init() for qp flush lock"
  Revert "RDMA/hns: Fix flush cqe error when racing with destroy qp"

Yuyu Li (1):
  RDMA/hns: Modify debugfs name

wenglianfa (3):
  RDMA/hns: Fix an AEQE overflow error caused by untimely update of
    eq_db_ci
  RDMA/hns: Fix flush cqe error when racing with destroy qp
  RDMA/hns: Fix cpu stuck caused by printings during reset


-- 
2.33.0
 
https://gitee.com/openeuler/kernel/issues/IB1I99 
 
Link:https://gitee.com/openeuler/kernel/pulls/13044

 

Reviewed-by: default avatarChengchang Tang <tangchengchang@huawei.com>
Signed-off-by: default avatarZhang Peng <zhangpeng362@huawei.com>
parents be251396 a2393d42

drivers/infiniband/hw/hns/hns_roce_cq.c

+2 −2
Original line number Diff line number Diff line
@@ -179,9 +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_ratelimited(dev,

				    "DESTROY_CQ failed (%d) for CQN %06lx\n",

		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;

drivers/infiniband/hw/hns/hns_roce_debugfs.c

+2 −1
Original line number Diff line number Diff line
@@ -5,6 +5,7 @@ 


#include <linux/debugfs.h>

#include <linux/device.h>

#include <linux/pci.h>



#include "hns_roce_device.h"

#include "hns_roce_common.h"
@@ -489,7 +490,7 @@ void hns_roce_register_debugfs(struct hns_roce_dev *hr_dev) 
{

	struct hns_roce_dev_debugfs *dbgfs = &hr_dev->dbgfs;



	dbgfs->root = debugfs_create_dir(dev_name(&hr_dev->ib_dev.dev),

	dbgfs->root = debugfs_create_dir(pci_name(hr_dev->pci_dev),

					 hns_roce_dbgfs_root);



	if (hr_dev->caps.flags & HNS_ROCE_CAP_FLAG_DCA_MODE)

drivers/infiniband/hw/hns/hns_roce_device.h

+1 −0
Original line number Diff line number Diff line
@@ -1445,6 +1445,7 @@ void hns_roce_cq_completion(struct hns_roce_dev *hr_dev, u32 cqn); 
void hns_roce_cq_event(struct hns_roce_dev *hr_dev, u32 cqn, int event_type);

void flush_cqe(struct hns_roce_dev *dev, struct hns_roce_qp *qp);

void hns_roce_qp_event(struct hns_roce_dev *hr_dev, u32 qpn, int event_type);

void hns_roce_flush_cqe(struct hns_roce_dev *hr_dev, u32 qpn);

void hns_roce_srq_event(struct hns_roce_dev *hr_dev, u32 srqn, int event_type);

void hns_roce_handle_device_err(struct hns_roce_dev *hr_dev);

int hns_roce_init(struct hns_roce_dev *hr_dev);

drivers/infiniband/hw/hns/hns_roce_hem.c

+22 −22
Original line number Diff line number Diff line
@@ -300,7 +300,7 @@ static int calc_hem_config(struct hns_roce_dev *hr_dev, 
			   struct hns_roce_hem_mhop *mhop,

			   struct hns_roce_hem_index *index)

{

	struct ib_device *ibdev = &hr_dev->ib_dev;

	struct device *dev = hr_dev->dev;

	unsigned long mhop_obj = obj;

	u32 l0_idx, l1_idx, l2_idx;

	u32 chunk_ba_num;
@@ -331,13 +331,13 @@ static int calc_hem_config(struct hns_roce_dev *hr_dev, 
		index->buf = l0_idx;

		break;

	default:

		ibdev_err(ibdev, "table %u not support mhop.hop_num = %u!\n",

		dev_err(dev, "table %u not support mhop.hop_num = %u!\n",

			table->type, mhop->hop_num);

		return -EINVAL;

	}



	if (unlikely(index->buf >= table->num_hem)) {

		ibdev_err(ibdev, "table %u exceed hem limt idx %llu, max %lu!\n",

		dev_err(dev, "table %u exceed hem limt idx %llu, max %lu!\n",

			table->type, index->buf, table->num_hem);

		return -EINVAL;

	}
@@ -448,14 +448,14 @@ static int set_mhop_hem(struct hns_roce_dev *hr_dev, 
			struct hns_roce_hem_mhop *mhop,

			struct hns_roce_hem_index *index)

{

	struct ib_device *ibdev = &hr_dev->ib_dev;

	struct device *dev = hr_dev->dev;

	u32 step_idx;

	int ret = 0;



	if (index->inited & HEM_INDEX_L0) {

		ret = hr_dev->hw->set_hem(hr_dev, table, obj, 0);

		if (ret) {

			ibdev_err(ibdev, "set HEM step 0 failed!\n");

			dev_err(dev, "set HEM step 0 failed!\n");

			goto out;

		}

	}
@@ -463,7 +463,7 @@ static int set_mhop_hem(struct hns_roce_dev *hr_dev, 
	if (index->inited & HEM_INDEX_L1) {

		ret = hr_dev->hw->set_hem(hr_dev, table, obj, 1);

		if (ret) {

			ibdev_err(ibdev, "set HEM step 1 failed!\n");

			dev_err(dev, "set HEM step 1 failed!\n");

			goto out;

		}

	}
@@ -475,7 +475,7 @@ static int set_mhop_hem(struct hns_roce_dev *hr_dev, 
			step_idx = mhop->hop_num;

		ret = hr_dev->hw->set_hem(hr_dev, table, obj, step_idx);

		if (ret)

			ibdev_err(ibdev, "set HEM step last failed!\n");

			dev_err(dev, "set HEM step last failed!\n");

	}

out:

	return ret;
@@ -485,14 +485,14 @@ static int hns_roce_table_mhop_get(struct hns_roce_dev *hr_dev, 
				   struct hns_roce_hem_table *table,

				   unsigned long obj)

{

	struct ib_device *ibdev = &hr_dev->ib_dev;

	struct hns_roce_hem_index index = {};

	struct hns_roce_hem_mhop mhop = {};

	struct device *dev = hr_dev->dev;

	int ret;



	ret = calc_hem_config(hr_dev, table, obj, &mhop, &index);

	if (ret) {

		ibdev_err(ibdev, "calc hem config failed!\n");

		dev_err(dev, "calc hem config failed!\n");

		return ret;

	}
@@ -504,7 +504,7 @@ static int hns_roce_table_mhop_get(struct hns_roce_dev *hr_dev, 


	ret = alloc_mhop_hem(hr_dev, table, &mhop, &index);

	if (ret) {

		ibdev_err(ibdev, "alloc mhop hem failed!\n");

		dev_err(dev, "alloc mhop hem failed!\n");

		goto out;

	}
@@ -512,7 +512,7 @@ static int hns_roce_table_mhop_get(struct hns_roce_dev *hr_dev, 
	if (table->type < HEM_TYPE_MTT) {

		ret = set_mhop_hem(hr_dev, table, obj, &mhop, &index);

		if (ret) {

			ibdev_err(ibdev, "set HEM address to HW failed!\n");

			dev_err(dev, "set HEM address to HW failed!\n");

			goto err_alloc;

		}

	}
@@ -575,7 +575,7 @@ static void clear_mhop_hem(struct hns_roce_dev *hr_dev, 
			   struct hns_roce_hem_mhop *mhop,

			   struct hns_roce_hem_index *index)

{

	struct ib_device *ibdev = &hr_dev->ib_dev;

	struct device *dev = hr_dev->dev;

	u32 hop_num = mhop->hop_num;

	u32 chunk_ba_num;

	u32 step_idx;
@@ -605,20 +605,20 @@ static void clear_mhop_hem(struct hns_roce_dev *hr_dev, 


		ret = hr_dev->hw->clear_hem(hr_dev, table, obj, step_idx);

		if (ret)

			ibdev_warn(ibdev, "failed to clear hop%u HEM, ret = %d.\n",

			dev_warn(dev, "failed to clear hop%u HEM, ret = %d.\n",

				 hop_num, ret);



		if (index->inited & HEM_INDEX_L1) {

			ret = hr_dev->hw->clear_hem(hr_dev, table, obj, 1);

			if (ret)

				ibdev_warn(ibdev, "failed to clear HEM step 1, ret = %d.\n",

				dev_warn(dev, "failed to clear HEM step 1, ret = %d.\n",

					 ret);

		}



		if (index->inited & HEM_INDEX_L0) {

			ret = hr_dev->hw->clear_hem(hr_dev, table, obj, 0);

			if (ret)

				ibdev_warn(ibdev, "failed to clear HEM step 0, ret = %d.\n",

				dev_warn(dev, "failed to clear HEM step 0, ret = %d.\n",

					 ret);

		}

	}
@@ -629,14 +629,14 @@ static void hns_roce_table_mhop_put(struct hns_roce_dev *hr_dev, 
				    unsigned long obj,

				    int check_refcount)

{

	struct ib_device *ibdev = &hr_dev->ib_dev;

	struct hns_roce_hem_index index = {};

	struct hns_roce_hem_mhop mhop = {};

	struct device *dev = hr_dev->dev;

	int ret;



	ret = calc_hem_config(hr_dev, table, obj, &mhop, &index);

	if (ret) {

		ibdev_err(ibdev, "calc hem config failed!\n");

		dev_err(dev, "calc hem config failed!\n");

		return;

	}

drivers/infiniband/hw/hns/hns_roce_hw_v2.c

+57 −43
Original line number Diff line number Diff line
@@ -451,17 +451,10 @@ 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_ratelimited(ibdev,

				      "failed to post WQE, QP state %u!\n",

				      hr_qp->state);

		     hr_qp->state == IB_QPS_RTR))

		return -EINVAL;

	} else if (unlikely(hr_dev->state >= HNS_ROCE_DEVICE_STATE_RST_DOWN)) {

		ibdev_err_ratelimited(ibdev,

				      "failed to post WQE, dev state %d!\n",

				      hr_dev->state);

	else if (unlikely(hr_dev->state >= HNS_ROCE_DEVICE_STATE_RST_DOWN))

		return -EIO;

	}



	if (check_dca_attach_enable(hr_qp)) {

		ret = dca_attach_qp_buf(hr_dev, hr_qp);
@@ -2972,7 +2965,7 @@ static int free_mr_modify_rsv_qp(struct hns_roce_dev *hr_dev, 
	ret = hr_dev->hw->modify_qp(&hr_qp->ibqp, attr, mask, IB_QPS_INIT,

				    IB_QPS_INIT, NULL);

	if (ret) {

		ibdev_err(ibdev, "failed to modify qp to init, ret = %d.\n",

		ibdev_err_ratelimited(ibdev, "failed to modify qp to init, ret = %d.\n",

				      ret);

		return ret;

	}
@@ -3658,8 +3651,7 @@ 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_ratelimited(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;

	}
@@ -5398,11 +5390,8 @@ static int hns_roce_v2_set_abs_fields(struct ib_qp *ibqp, 
	struct hns_roce_dev *hr_dev = to_hr_dev(ibqp->device);

	int ret = 0;



	if (!check_qp_state(cur_state, new_state)) {

		ibdev_err_ratelimited(&hr_dev->ib_dev,

				      "Illegal state for QP!\n");

	if (!check_qp_state(cur_state, new_state))

		return -EINVAL;

	}



	if (cur_state == IB_QPS_RESET && new_state == IB_QPS_INIT) {

		memset(qpc_mask, 0, hr_dev->caps.qpc_sz);
@@ -6023,7 +6012,7 @@ int hns_roce_v2_destroy_qp(struct ib_qp *ibqp, struct ib_udata *udata) 
	unsigned long flags;

	int ret;



	/* Make sure flush_cqe() is complete */

	/* Make sure flush_cqe() is completed */

	spin_lock_irqsave(&hr_qp->flush_lock, flags);

	set_bit(HNS_ROCE_STOP_FLUSH_FLAG, &hr_qp->flush_flag);

	spin_unlock_irqrestore(&hr_qp->flush_lock, flags);
@@ -6399,11 +6388,10 @@ static int hns_roce_v2_query_mpt(struct hns_roce_dev *hr_dev, u32 key, 
	return ret;

}



static void hns_roce_irq_work_handle(struct work_struct *work)

static void dump_aeqe_log(struct hns_roce_work *irq_work)

{

	struct hns_roce_work *irq_work =

				container_of(work, struct hns_roce_work, work);

	struct ib_device *ibdev = &irq_work->hr_dev->ib_dev;

	struct hns_roce_dev *hr_dev = irq_work->hr_dev;

	struct ib_device *ibdev = &hr_dev->ib_dev;



	switch (irq_work->event_type) {

	case HNS_ROCE_EVENT_TYPE_PATH_MIG:
@@ -6447,6 +6435,8 @@ static void hns_roce_irq_work_handle(struct work_struct *work) 
	case HNS_ROCE_EVENT_TYPE_DB_OVERFLOW:

		ibdev_warn(ibdev, "DB overflow.\n");

		break;

	case HNS_ROCE_EVENT_TYPE_MB:

		break;

	case HNS_ROCE_EVENT_TYPE_FLR:

		ibdev_warn(ibdev, "function level reset.\n");

		break;
@@ -6456,10 +6446,48 @@ static void hns_roce_irq_work_handle(struct work_struct *work) 
	case HNS_ROCE_EVENT_TYPE_INVALID_XRCETH:

		ibdev_err(ibdev, "invalid xrceth error.\n");

		break;

	default:

		ibdev_info(ibdev, "Undefined event %d.\n",

			   irq_work->event_type);

		break;

	}

}



static void hns_roce_irq_work_handle(struct work_struct *work)

{

	struct hns_roce_work *irq_work =

				container_of(work, struct hns_roce_work, work);

	struct hns_roce_dev *hr_dev = irq_work->hr_dev;

	int event_type = irq_work->event_type;

	u32 queue_num = irq_work->queue_num;



	switch (event_type) {

	case HNS_ROCE_EVENT_TYPE_PATH_MIG:

	case HNS_ROCE_EVENT_TYPE_PATH_MIG_FAILED:

	case HNS_ROCE_EVENT_TYPE_COMM_EST:

	case HNS_ROCE_EVENT_TYPE_SQ_DRAINED:

	case HNS_ROCE_EVENT_TYPE_WQ_CATAS_ERROR:

	case HNS_ROCE_EVENT_TYPE_SRQ_LAST_WQE_REACH:

	case HNS_ROCE_EVENT_TYPE_INV_REQ_LOCAL_WQ_ERROR:

	case HNS_ROCE_EVENT_TYPE_LOCAL_WQ_ACCESS_ERROR:

	case HNS_ROCE_EVENT_TYPE_XRCD_VIOLATION:

	case HNS_ROCE_EVENT_TYPE_INVALID_XRCETH:

		hns_roce_qp_event(hr_dev, queue_num, event_type);

		break;

	case HNS_ROCE_EVENT_TYPE_SRQ_LIMIT_REACH:

	case HNS_ROCE_EVENT_TYPE_SRQ_CATAS_ERROR:

		hns_roce_srq_event(hr_dev, queue_num, event_type);

		break;

	case HNS_ROCE_EVENT_TYPE_CQ_ACCESS_ERROR:

	case HNS_ROCE_EVENT_TYPE_CQ_OVERFLOW:

		hns_roce_cq_event(hr_dev, queue_num, event_type);

		break;

	default:

		break;

	}



	dump_aeqe_log(irq_work);



	kfree(irq_work);

}
@@ -6519,14 +6547,14 @@ static struct hns_roce_aeqe *next_aeqe_sw_v2(struct hns_roce_eq *eq) 
static irqreturn_t hns_roce_v2_aeq_int(struct hns_roce_dev *hr_dev,

				       struct hns_roce_eq *eq)

{

	struct device *dev = hr_dev->dev;

	struct hns_roce_aeqe *aeqe = next_aeqe_sw_v2(eq);

	irqreturn_t aeqe_found = IRQ_NONE;

	int num_aeqes = 0;

	int event_type;

	u32 queue_num;

	int sub_type;



	while (aeqe) {

	while (aeqe && num_aeqes < HNS_AEQ_POLLING_BUDGET) {

		/* Make sure we read AEQ entry after we have checked the

		 * ownership bit

		 */
@@ -6537,25 +6565,12 @@ static irqreturn_t hns_roce_v2_aeq_int(struct hns_roce_dev *hr_dev, 
		queue_num = hr_reg_read(aeqe, AEQE_EVENT_QUEUE_NUM);



		switch (event_type) {

		case HNS_ROCE_EVENT_TYPE_PATH_MIG:

		case HNS_ROCE_EVENT_TYPE_PATH_MIG_FAILED:

		case HNS_ROCE_EVENT_TYPE_COMM_EST:

		case HNS_ROCE_EVENT_TYPE_SQ_DRAINED:

		case HNS_ROCE_EVENT_TYPE_WQ_CATAS_ERROR:

		case HNS_ROCE_EVENT_TYPE_SRQ_LAST_WQE_REACH:

		case HNS_ROCE_EVENT_TYPE_INV_REQ_LOCAL_WQ_ERROR:

		case HNS_ROCE_EVENT_TYPE_LOCAL_WQ_ACCESS_ERROR:

		case HNS_ROCE_EVENT_TYPE_XRCD_VIOLATION:

		case HNS_ROCE_EVENT_TYPE_INVALID_XRCETH:

			hns_roce_qp_event(hr_dev, queue_num, event_type);

			break;

		case HNS_ROCE_EVENT_TYPE_SRQ_LIMIT_REACH:

		case HNS_ROCE_EVENT_TYPE_SRQ_CATAS_ERROR:

			hns_roce_srq_event(hr_dev, queue_num, event_type);

			break;

		case HNS_ROCE_EVENT_TYPE_CQ_ACCESS_ERROR:

		case HNS_ROCE_EVENT_TYPE_CQ_OVERFLOW:

			hns_roce_cq_event(hr_dev, queue_num, event_type);

			hns_roce_flush_cqe(hr_dev, queue_num);

			break;

		case HNS_ROCE_EVENT_TYPE_MB:

			hns_roce_cmd_event(hr_dev,
@@ -6563,12 +6578,7 @@ static irqreturn_t hns_roce_v2_aeq_int(struct hns_roce_dev *hr_dev, 
					aeqe->event.cmd.status,

					le64_to_cpu(aeqe->event.cmd.out_param));

			break;

		case HNS_ROCE_EVENT_TYPE_DB_OVERFLOW:

		case HNS_ROCE_EVENT_TYPE_FLR:

			break;

		default:

			dev_err(dev, "unhandled event %d on EQ %d at idx %u.\n",

				event_type, eq->eqn, eq->cons_index);

			break;

		}
@@ -6582,6 +6592,7 @@ static irqreturn_t hns_roce_v2_aeq_int(struct hns_roce_dev *hr_dev, 
		hns_roce_v2_init_irq_work(hr_dev, eq, queue_num);



		aeqe = next_aeqe_sw_v2(eq);

		++num_aeqes;

	}



	update_eq_db(eq);
@@ -7129,6 +7140,9 @@ static int hns_roce_v2_init_eq_table(struct hns_roce_dev *hr_dev) 
	int ret;

	int i;



	if (hr_dev->caps.aeqe_depth < HNS_AEQ_POLLING_BUDGET)

		return -EINVAL;



	other_num = hr_dev->caps.num_other_vectors;

	comp_num = hr_dev->caps.num_comp_vectors;

	aeq_num = hr_dev->caps.num_aeq_vectors;