Merge tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdma

Pull rdma updates from Jason Gunthorpe:
 "Usual size of updates, a new driver, and most of the bulk focusing on
  rxe:

   - Usual typos, style, and language updates

   - Driver updates for mlx5, irdma, siw, rts, srp, hfi1, hns, erdma,
     mlx4, srp

   - Lots of RXE updates:
      * Improve reply error handling for bad MR operations
      * Code tidying
      * Debug printing uses common loggers
      * Remove half implemented RD related stuff
      * Support IBA's recently defined Atomic Write and Flush operations

   - erdma support for atomic operations

   - New driver 'mana' for Ethernet HW available in Azure VMs. This
     driver only supports DPDK"

* tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdma: (122 commits)
  IB/IPoIB: Fix queue count inconsistency for PKEY child interfaces
  RDMA: Add missed netdev_put() for the netdevice_tracker
  RDMA/rxe: Enable RDMA FLUSH capability for rxe device
  RDMA/cm: Make QP FLUSHABLE for supported device
  RDMA/rxe: Implement flush completion
  RDMA/rxe: Implement flush execution in responder side
  RDMA/rxe: Implement RC RDMA FLUSH service in requester side
  RDMA/rxe: Extend rxe packet format to support flush
  RDMA/rxe: Allow registering persistent flag for pmem MR only
  RDMA/rxe: Extend rxe user ABI to support flush
  RDMA: Extend RDMA kernel verbs ABI to support flush
  RDMA: Extend RDMA user ABI to support flush
  RDMA/rxe: Fix incorrect responder length checking
  RDMA/rxe: Fix oops with zero length reads
  RDMA/mlx5: Remove not-used IB_FLOW_SPEC_IB define
  RDMA/hns: Fix XRC caps on HIP08
  RDMA/hns: Fix error code of CMD
  RDMA/hns: Fix page size cap from firmware
  RDMA/hns: Fix PBL page MTR find
  RDMA/hns: Fix AH attr queried by query_qp
  ...

6 files changed, 289 insertions, 73 deletions

diff --git a/drivers/infiniband/hw/hns/hns_roce_device.h b/drivers/infiniband/hw/hns/hns_roce_device.h
index 723e55a7de8d..f701cc86896b 100644
--- a/drivers/infiniband/hw/hns/hns_roce_device.h
+++ b/drivers/infiniband/hw/hns/hns_roce_device.h
@@ -202,6 +202,7 @@ struct hns_roce_ucontext {
 	struct list_head	page_list;
 	struct mutex		page_mutex;
 	struct hns_user_mmap_entry *db_mmap_entry;
+	u32			config;
 };
 
 struct hns_roce_pd {
@@ -334,6 +335,7 @@ struct hns_roce_wq {
 	u32		head;
 	u32		tail;
 	void __iomem	*db_reg;
+	u32		ext_sge_cnt;
 };
 
 struct hns_roce_sge {
@@ -635,6 +637,7 @@ struct hns_roce_qp {
 	struct list_head	rq_node; /* all recv qps are on a list */
 	struct list_head	sq_node; /* all send qps are on a list */
 	struct hns_user_mmap_entry *dwqe_mmap_entry;
+	u32			config;
 };
 
 struct hns_roce_ib_iboe {
diff --git a/drivers/infiniband/hw/hns/hns_roce_hw_v2.c b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c
index 1435fe2ea176..b2421883993b 100644
--- a/drivers/infiniband/hw/hns/hns_roce_hw_v2.c
+++ b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c
@@ -192,7 +192,6 @@ static int fill_ext_sge_inl_data(struct hns_roce_qp *qp,
 				 unsigned int *sge_idx, u32 msg_len)
 {
 	struct ib_device *ibdev = &(to_hr_dev(qp->ibqp.device))->ib_dev;
-	unsigned int ext_sge_sz = qp->sq.max_gs * HNS_ROCE_SGE_SIZE;
 	unsigned int left_len_in_pg;
 	unsigned int idx = *sge_idx;
 	unsigned int i = 0;
@@ -200,7 +199,7 @@ static int fill_ext_sge_inl_data(struct hns_roce_qp *qp,
 	void *addr;
 	void *dseg;
 
-	if (msg_len > ext_sge_sz) {
+	if (msg_len > qp->sq.ext_sge_cnt * HNS_ROCE_SGE_SIZE) {
 		ibdev_err(ibdev,
 			  "no enough extended sge space for inline data.\n");
 		return -EINVAL;
@@ -1274,6 +1273,30 @@ static void update_cmdq_status(struct hns_roce_dev *hr_dev)
 		hr_dev->cmd.state = HNS_ROCE_CMDQ_STATE_FATAL_ERR;
 }
 
+static int hns_roce_cmd_err_convert_errno(u16 desc_ret)
+{
+	struct hns_roce_cmd_errcode errcode_table[] = {
+		{CMD_EXEC_SUCCESS, 0},
+		{CMD_NO_AUTH, -EPERM},
+		{CMD_NOT_EXIST, -EOPNOTSUPP},
+		{CMD_CRQ_FULL, -EXFULL},
+		{CMD_NEXT_ERR, -ENOSR},
+		{CMD_NOT_EXEC, -ENOTBLK},
+		{CMD_PARA_ERR, -EINVAL},
+		{CMD_RESULT_ERR, -ERANGE},
+		{CMD_TIMEOUT, -ETIME},
+		{CMD_HILINK_ERR, -ENOLINK},
+		{CMD_INFO_ILLEGAL, -ENXIO},
+		{CMD_INVALID, -EBADR},
+	};
+	u16 i;
+
+	for (i = 0; i < ARRAY_SIZE(errcode_table); i++)
+		if (desc_ret == errcode_table[i].return_status)
+			return errcode_table[i].errno;
+	return -EIO;
+}
+
 static int __hns_roce_cmq_send(struct hns_roce_dev *hr_dev,
 			       struct hns_roce_cmq_desc *desc, int num)
 {
@@ -1319,7 +1342,7 @@ static int __hns_roce_cmq_send(struct hns_roce_dev *hr_dev,
 			dev_err_ratelimited(hr_dev->dev,
 					    "Cmdq IO error, opcode = 0x%x, return = 0x%x.\n",
 					    desc->opcode, desc_ret);
-			ret = -EIO;
+			ret = hns_roce_cmd_err_convert_errno(desc_ret);
 		}
 	} else {
 		/* FW/HW reset or incorrect number of desc */
@@ -2024,13 +2047,14 @@ static void set_default_caps(struct hns_roce_dev *hr_dev)
 
 	caps->flags |= HNS_ROCE_CAP_FLAG_ATOMIC | HNS_ROCE_CAP_FLAG_MW |
 		       HNS_ROCE_CAP_FLAG_SRQ | HNS_ROCE_CAP_FLAG_FRMR |
-		       HNS_ROCE_CAP_FLAG_QP_FLOW_CTRL | HNS_ROCE_CAP_FLAG_XRC;
+		       HNS_ROCE_CAP_FLAG_QP_FLOW_CTRL;
 
 	caps->gid_table_len[0] = HNS_ROCE_V2_GID_INDEX_NUM;
 
 	if (hr_dev->pci_dev->revision >= PCI_REVISION_ID_HIP09) {
 		caps->flags |= HNS_ROCE_CAP_FLAG_STASH |
-			       HNS_ROCE_CAP_FLAG_DIRECT_WQE;
+			       HNS_ROCE_CAP_FLAG_DIRECT_WQE |
+			       HNS_ROCE_CAP_FLAG_XRC;
 		caps->max_sq_inline = HNS_ROCE_V3_MAX_SQ_INLINE;
 	} else {
 		caps->max_sq_inline = HNS_ROCE_V2_MAX_SQ_INLINE;
@@ -2342,6 +2366,9 @@ static int hns_roce_query_pf_caps(struct hns_roce_dev *hr_dev)
 	caps->wqe_sge_hop_num = hr_reg_read(resp_d, PF_CAPS_D_EX_SGE_HOP_NUM);
 	caps->wqe_rq_hop_num = hr_reg_read(resp_d, PF_CAPS_D_RQWQE_HOP_NUM);
 
+	if (!(caps->page_size_cap & PAGE_SIZE))
+		caps->page_size_cap = HNS_ROCE_V2_PAGE_SIZE_SUPPORTED;
+
 	return 0;
 }
 
@@ -2631,31 +2658,124 @@ static void free_dip_list(struct hns_roce_dev *hr_dev)
 	spin_unlock_irqrestore(&hr_dev->dip_list_lock, flags);
 }
 
-static void free_mr_exit(struct hns_roce_dev *hr_dev)
+static struct ib_pd *free_mr_init_pd(struct hns_roce_dev *hr_dev)
+{
+	struct hns_roce_v2_priv *priv = hr_dev->priv;
+	struct hns_roce_v2_free_mr *free_mr = &priv->free_mr;
+	struct ib_device *ibdev = &hr_dev->ib_dev;
+	struct hns_roce_pd *hr_pd;
+	struct ib_pd *pd;
+
+	hr_pd = kzalloc(sizeof(*hr_pd), GFP_KERNEL);
+	if (ZERO_OR_NULL_PTR(hr_pd))
+		return NULL;
+	pd = &hr_pd->ibpd;
+	pd->device = ibdev;
+
+	if (hns_roce_alloc_pd(pd, NULL)) {
+		ibdev_err(ibdev, "failed to create pd for free mr.\n");
+		kfree(hr_pd);
+		return NULL;
+	}
+	free_mr->rsv_pd = to_hr_pd(pd);
+	free_mr->rsv_pd->ibpd.device = &hr_dev->ib_dev;
+	free_mr->rsv_pd->ibpd.uobject = NULL;
+	free_mr->rsv_pd->ibpd.__internal_mr = NULL;
+	atomic_set(&free_mr->rsv_pd->ibpd.usecnt, 0);
+
+	return pd;
+}
+
+static struct ib_cq *free_mr_init_cq(struct hns_roce_dev *hr_dev)
 {
 	struct hns_roce_v2_priv *priv = hr_dev->priv;
 	struct hns_roce_v2_free_mr *free_mr = &priv->free_mr;
+	struct ib_device *ibdev = &hr_dev->ib_dev;
+	struct ib_cq_init_attr cq_init_attr = {};
+	struct hns_roce_cq *hr_cq;
+	struct ib_cq *cq;
+
+	cq_init_attr.cqe = HNS_ROCE_FREE_MR_USED_CQE_NUM;
+
+	hr_cq = kzalloc(sizeof(*hr_cq), GFP_KERNEL);
+	if (ZERO_OR_NULL_PTR(hr_cq))
+		return NULL;
+
+	cq = &hr_cq->ib_cq;
+	cq->device = ibdev;
+
+	if (hns_roce_create_cq(cq, &cq_init_attr, NULL)) {
+		ibdev_err(ibdev, "failed to create cq for free mr.\n");
+		kfree(hr_cq);
+		return NULL;
+	}
+	free_mr->rsv_cq = to_hr_cq(cq);
+	free_mr->rsv_cq->ib_cq.device = &hr_dev->ib_dev;
+	free_mr->rsv_cq->ib_cq.uobject = NULL;
+	free_mr->rsv_cq->ib_cq.comp_handler = NULL;
+	free_mr->rsv_cq->ib_cq.event_handler = NULL;
+	free_mr->rsv_cq->ib_cq.cq_context = NULL;
+	atomic_set(&free_mr->rsv_cq->ib_cq.usecnt, 0);
+
+	return cq;
+}
+
+static int free_mr_init_qp(struct hns_roce_dev *hr_dev, struct ib_cq *cq,
+			   struct ib_qp_init_attr *init_attr, int i)
+{
+	struct hns_roce_v2_priv *priv = hr_dev->priv;
+	struct hns_roce_v2_free_mr *free_mr = &priv->free_mr;
+	struct ib_device *ibdev = &hr_dev->ib_dev;
+	struct hns_roce_qp *hr_qp;
+	struct ib_qp *qp;
 	int ret;
+
+	hr_qp = kzalloc(sizeof(*hr_qp), GFP_KERNEL);
+	if (ZERO_OR_NULL_PTR(hr_qp))
+		return -ENOMEM;
+
+	qp = &hr_qp->ibqp;
+	qp->device = ibdev;
+
+	ret = hns_roce_create_qp(qp, init_attr, NULL);
+	if (ret) {
+		ibdev_err(ibdev, "failed to create qp for free mr.\n");
+		kfree(hr_qp);
+		return ret;
+	}
+
+	free_mr->rsv_qp[i] = hr_qp;
+	free_mr->rsv_qp[i]->ibqp.recv_cq = cq;
+	free_mr->rsv_qp[i]->ibqp.send_cq = cq;
+
+	return 0;
+}
+
+static void free_mr_exit(struct hns_roce_dev *hr_dev)
+{
+	struct hns_roce_v2_priv *priv = hr_dev->priv;
+	struct hns_roce_v2_free_mr *free_mr = &priv->free_mr;
+	struct ib_qp *qp;
 	int i;
 
 	for (i = 0; i < ARRAY_SIZE(free_mr->rsv_qp); i++) {
 		if (free_mr->rsv_qp[i]) {
-			ret = ib_destroy_qp(free_mr->rsv_qp[i]);
-			if (ret)
-				ibdev_err(&hr_dev->ib_dev,
-					  "failed to destroy qp in free mr.\n");
-
+			qp = &free_mr->rsv_qp[i]->ibqp;
+			hns_roce_v2_destroy_qp(qp, NULL);
+			kfree(free_mr->rsv_qp[i]);
 			free_mr->rsv_qp[i] = NULL;
 		}
 	}
 
 	if (free_mr->rsv_cq) {
-		ib_destroy_cq(free_mr->rsv_cq);
+		hns_roce_destroy_cq(&free_mr->rsv_cq->ib_cq, NULL);
+		kfree(free_mr->rsv_cq);
 		free_mr->rsv_cq = NULL;
 	}
 
 	if (free_mr->rsv_pd) {
-		ib_dealloc_pd(free_mr->rsv_pd);
+		hns_roce_dealloc_pd(&free_mr->rsv_pd->ibpd, NULL);
+		kfree(free_mr->rsv_pd);
 		free_mr->rsv_pd = NULL;
 	}
 }
@@ -2664,55 +2784,46 @@ static int free_mr_alloc_res(struct hns_roce_dev *hr_dev)
 {
 	struct hns_roce_v2_priv *priv = hr_dev->priv;
 	struct hns_roce_v2_free_mr *free_mr = &priv->free_mr;
-	struct ib_device *ibdev = &hr_dev->ib_dev;
-	struct ib_cq_init_attr cq_init_attr = {};
 	struct ib_qp_init_attr qp_init_attr = {};
 	struct ib_pd *pd;
 	struct ib_cq *cq;
-	struct ib_qp *qp;
 	int ret;
 	int i;
 
-	pd = ib_alloc_pd(ibdev, 0);
-	if (IS_ERR(pd)) {
-		ibdev_err(ibdev, "failed to create pd for free mr.\n");
-		return PTR_ERR(pd);
-	}
-	free_mr->rsv_pd = pd;
+	pd = free_mr_init_pd(hr_dev);
+	if (!pd)
+		return -ENOMEM;
 
-	cq_init_attr.cqe = HNS_ROCE_FREE_MR_USED_CQE_NUM;
-	cq = ib_create_cq(ibdev, NULL, NULL, NULL, &cq_init_attr);
-	if (IS_ERR(cq)) {
-		ibdev_err(ibdev, "failed to create cq for free mr.\n");
-		ret = PTR_ERR(cq);
-		goto create_failed;
+	cq = free_mr_init_cq(hr_dev);
+	if (!cq) {
+		ret = -ENOMEM;
+		goto create_failed_cq;
 	}
-	free_mr->rsv_cq = cq;
 
 	qp_init_attr.qp_type = IB_QPT_RC;
 	qp_init_attr.sq_sig_type = IB_SIGNAL_ALL_WR;
-	qp_init_attr.send_cq = free_mr->rsv_cq;
-	qp_init_attr.recv_cq = free_mr->rsv_cq;
+	qp_init_attr.send_cq = cq;
+	qp_init_attr.recv_cq = cq;
 	for (i = 0; i < ARRAY_SIZE(free_mr->rsv_qp); i++) {
 		qp_init_attr.cap.max_send_wr = HNS_ROCE_FREE_MR_USED_SQWQE_NUM;
 		qp_init_attr.cap.max_send_sge = HNS_ROCE_FREE_MR_USED_SQSGE_NUM;
 		qp_init_attr.cap.max_recv_wr = HNS_ROCE_FREE_MR_USED_RQWQE_NUM;
 		qp_init_attr.cap.max_recv_sge = HNS_ROCE_FREE_MR_USED_RQSGE_NUM;
 
-		qp = ib_create_qp(free_mr->rsv_pd, &qp_init_attr);
-		if (IS_ERR(qp)) {
-			ibdev_err(ibdev, "failed to create qp for free mr.\n");
-			ret = PTR_ERR(qp);
-			goto create_failed;
-		}
-
-		free_mr->rsv_qp[i] = qp;
+		ret = free_mr_init_qp(hr_dev, cq, &qp_init_attr, i);
+		if (ret)
+			goto create_failed_qp;
 	}
 
 	return 0;
 
-create_failed:
-	free_mr_exit(hr_dev);
+create_failed_qp:
+	hns_roce_destroy_cq(cq, NULL);
+	kfree(cq);
+
+create_failed_cq:
+	hns_roce_dealloc_pd(pd, NULL);
+	kfree(pd);
 
 	return ret;
 }
@@ -2728,14 +2839,17 @@ static int free_mr_modify_rsv_qp(struct hns_roce_dev *hr_dev,
 	int mask;
 	int ret;
 
-	hr_qp = to_hr_qp(free_mr->rsv_qp[sl_num]);
+	hr_qp = to_hr_qp(&free_mr->rsv_qp[sl_num]->ibqp);
 	hr_qp->free_mr_en = 1;
+	hr_qp->ibqp.device = ibdev;
+	hr_qp->ibqp.qp_type = IB_QPT_RC;
 
 	mask = IB_QP_STATE | IB_QP_PKEY_INDEX | IB_QP_PORT | IB_QP_ACCESS_FLAGS;
 	attr->qp_state = IB_QPS_INIT;
 	attr->port_num = 1;
 	attr->qp_access_flags = IB_ACCESS_REMOTE_WRITE;
-	ret = ib_modify_qp(&hr_qp->ibqp, attr, mask);
+	ret = hr_dev->hw->modify_qp(&hr_qp->ibqp, attr, mask, IB_QPS_INIT,
+				    IB_QPS_INIT);
 	if (ret) {
 		ibdev_err(ibdev, "failed to modify qp to init, ret = %d.\n",
 			  ret);
@@ -2756,7 +2870,8 @@ static int free_mr_modify_rsv_qp(struct hns_roce_dev *hr_dev,
 
 	rdma_ah_set_sl(&attr->ah_attr, (u8)sl_num);
 
-	ret = ib_modify_qp(&hr_qp->ibqp, attr, mask);
+	ret = hr_dev->hw->modify_qp(&hr_qp->ibqp, attr, mask, IB_QPS_INIT,
+				    IB_QPS_RTR);
 	hr_dev->loop_idc = loopback;
 	if (ret) {
 		ibdev_err(ibdev, "failed to modify qp to rtr, ret = %d.\n",
@@ -2770,7 +2885,8 @@ static int free_mr_modify_rsv_qp(struct hns_roce_dev *hr_dev,
 	attr->sq_psn = HNS_ROCE_FREE_MR_USED_PSN;
 	attr->retry_cnt = HNS_ROCE_FREE_MR_USED_QP_RETRY_CNT;
 	attr->timeout = HNS_ROCE_FREE_MR_USED_QP_TIMEOUT;
-	ret = ib_modify_qp(&hr_qp->ibqp, attr, mask);
+	ret = hr_dev->hw->modify_qp(&hr_qp->ibqp, attr, mask, IB_QPS_RTR,
+				    IB_QPS_RTS);
 	if (ret)
 		ibdev_err(ibdev, "failed to modify qp to rts, ret = %d.\n",
 			  ret);
@@ -3186,7 +3302,8 @@ static int set_mtpt_pbl(struct hns_roce_dev *hr_dev,
 	int i, count;
 
 	count = hns_roce_mtr_find(hr_dev, &mr->pbl_mtr, 0, pages,
-				  ARRAY_SIZE(pages), &pbl_ba);
+				  min_t(int, ARRAY_SIZE(pages), mr->npages),
+				  &pbl_ba);
 	if (count < 1) {
 		ibdev_err(ibdev, "failed to find PBL mtr, count = %d.\n",
 			  count);
@@ -3414,7 +3531,7 @@ static void free_mr_send_cmd_to_hw(struct hns_roce_dev *hr_dev)
 	mutex_lock(&free_mr->mutex);
 
 	for (i = 0; i < ARRAY_SIZE(free_mr->rsv_qp); i++) {
-		hr_qp = to_hr_qp(free_mr->rsv_qp[i]);
+		hr_qp = free_mr->rsv_qp[i];
 
 		ret = free_mr_post_send_lp_wqe(hr_qp);
 		if (ret) {
@@ -3429,7 +3546,7 @@ static void free_mr_send_cmd_to_hw(struct hns_roce_dev *hr_dev)
 
 	end = msecs_to_jiffies(HNS_ROCE_V2_FREE_MR_TIMEOUT) + jiffies;
 	while (cqe_cnt) {
-		npolled = hns_roce_v2_poll_cq(free_mr->rsv_cq, cqe_cnt, wc);
+		npolled = hns_roce_v2_poll_cq(&free_mr->rsv_cq->ib_cq, cqe_cnt, wc);
 		if (npolled < 0) {
 			ibdev_err(ibdev,
 				  "failed to poll cqe for free mr, remain %d cqe.\n",
@@ -5375,6 +5492,8 @@ static int hns_roce_v2_query_qp(struct ib_qp *ibqp, struct ib_qp_attr *qp_attr,
 
 		rdma_ah_set_sl(&qp_attr->ah_attr,
 			       hr_reg_read(&context, QPC_SL));
+		rdma_ah_set_port_num(&qp_attr->ah_attr, hr_qp->port + 1);
+		rdma_ah_set_ah_flags(&qp_attr->ah_attr, IB_AH_GRH);
 		grh->flow_label = hr_reg_read(&context, QPC_FL);
 		grh->sgid_index = hr_reg_read(&context, QPC_GMV_IDX);
 		grh->hop_limit = hr_reg_read(&context, QPC_HOPLIMIT);
@@ -5468,7 +5587,7 @@ static int hns_roce_v2_destroy_qp_common(struct hns_roce_dev *hr_dev,
 	return ret;
 }
 
-static int hns_roce_v2_destroy_qp(struct ib_qp *ibqp, struct ib_udata *udata)
+int hns_roce_v2_destroy_qp(struct ib_qp *ibqp, struct ib_udata *udata)
 {
 	struct hns_roce_dev *hr_dev = to_hr_dev(ibqp->device);
 	struct hns_roce_qp *hr_qp = to_hr_qp(ibqp);
diff --git a/drivers/infiniband/hw/hns/hns_roce_hw_v2.h b/drivers/infiniband/hw/hns/hns_roce_hw_v2.h
index c7bf2d52c1cd..b1b3e1e0b84e 100644
--- a/drivers/infiniband/hw/hns/hns_roce_hw_v2.h
+++ b/drivers/infiniband/hw/hns/hns_roce_hw_v2.h
@@ -272,6 +272,11 @@ enum hns_roce_cmd_return_status {
 	CMD_OTHER_ERR = 0xff
 };
 
+struct hns_roce_cmd_errcode {
+	enum hns_roce_cmd_return_status return_status;
+	int errno;
+};
+
 enum hns_roce_sgid_type {
 	GID_TYPE_FLAG_ROCE_V1 = 0,
 	GID_TYPE_FLAG_ROCE_V2_IPV4,
@@ -1327,9 +1332,9 @@ struct hns_roce_link_table {
 #define HNS_ROCE_EXT_LLM_MIN_PAGES(que_num) ((que_num) * 4 + 2)
 
 struct hns_roce_v2_free_mr {
-	struct ib_qp *rsv_qp[HNS_ROCE_FREE_MR_USED_QP_NUM];
-	struct ib_cq *rsv_cq;
-	struct ib_pd *rsv_pd;
+	struct hns_roce_qp *rsv_qp[HNS_ROCE_FREE_MR_USED_QP_NUM];
+	struct hns_roce_cq *rsv_cq;
+	struct hns_roce_pd *rsv_pd;
 	struct mutex mutex;
 };
 
@@ -1459,6 +1464,8 @@ struct hns_roce_sccc_clr_done {
 	__le32 rsv[5];
 };
 
+int hns_roce_v2_destroy_qp(struct ib_qp *ibqp, struct ib_udata *udata);
+
 static inline void hns_roce_write64(struct hns_roce_dev *hr_dev, __le32 val[2],
 				    void __iomem *dest)
 {
diff --git a/drivers/infiniband/hw/hns/hns_roce_main.c b/drivers/infiniband/hw/hns/hns_roce_main.c
index dcf89689a4c6..8ba68ac12388 100644
--- a/drivers/infiniband/hw/hns/hns_roce_main.c
+++ b/drivers/infiniband/hw/hns/hns_roce_main.c
@@ -354,10 +354,11 @@ static int hns_roce_alloc_uar_entry(struct ib_ucontext *uctx)
 static int hns_roce_alloc_ucontext(struct ib_ucontext *uctx,
 				   struct ib_udata *udata)
 {
-	int ret;
 	struct hns_roce_ucontext *context = to_hr_ucontext(uctx);
-	struct hns_roce_ib_alloc_ucontext_resp resp = {};
 	struct hns_roce_dev *hr_dev = to_hr_dev(uctx->device);
+	struct hns_roce_ib_alloc_ucontext_resp resp = {};
+	struct hns_roce_ib_alloc_ucontext ucmd = {};
+	int ret;
 
 	if (!hr_dev->active)
 		return -EAGAIN;
@@ -365,6 +366,19 @@ static int hns_roce_alloc_ucontext(struct ib_ucontext *uctx,
 	resp.qp_tab_size = hr_dev->caps.num_qps;
 	resp.srq_tab_size = hr_dev->caps.num_srqs;
 
+	ret = ib_copy_from_udata(&ucmd, udata,
+				 min(udata->inlen, sizeof(ucmd)));
+	if (ret)
+		return ret;
+
+	if (hr_dev->pci_dev->revision >= PCI_REVISION_ID_HIP09)
+		context->config = ucmd.config & HNS_ROCE_EXSGE_FLAGS;
+
+	if (context->config & HNS_ROCE_EXSGE_FLAGS) {
+		resp.config |= HNS_ROCE_RSP_EXSGE_FLAGS;
+		resp.max_inline_data = hr_dev->caps.max_sq_inline;
+	}
+
 	ret = hns_roce_uar_alloc(hr_dev, &context->uar);
 	if (ret)
 		goto error_fail_uar_alloc;
diff --git a/drivers/infiniband/hw/hns/hns_roce_mr.c b/drivers/infiniband/hw/hns/hns_roce_mr.c
index 845ac7d3831f..37a5cf62f88b 100644
--- a/drivers/infiniband/hw/hns/hns_roce_mr.c
+++ b/drivers/infiniband/hw/hns/hns_roce_mr.c
@@ -392,10 +392,10 @@ struct ib_mr *hns_roce_alloc_mr(struct ib_pd *pd, enum ib_mr_type mr_type,
 
 	return &mr->ibmr;
 
-err_key:
-	free_mr_key(hr_dev, mr);
 err_pbl:
 	free_mr_pbl(hr_dev, mr);
+err_key:
+	free_mr_key(hr_dev, mr);
 err_free:
 	kfree(mr);
 	return ERR_PTR(ret);
diff --git a/drivers/infiniband/hw/hns/hns_roce_qp.c b/drivers/infiniband/hw/hns/hns_roce_qp.c
index f0bd82a18069..0ae335fb205c 100644
--- a/drivers/infiniband/hw/hns/hns_roce_qp.c
+++ b/drivers/infiniband/hw/hns/hns_roce_qp.c
@@ -476,38 +476,109 @@ static int set_rq_size(struct hns_roce_dev *hr_dev, struct ib_qp_cap *cap,
 	return 0;
 }
 
-static u32 get_wqe_ext_sge_cnt(struct hns_roce_qp *qp)
+static u32 get_max_inline_data(struct hns_roce_dev *hr_dev,
+			       struct ib_qp_cap *cap)
 {
-	/* GSI/UD QP only has extended sge */
-	if (qp->ibqp.qp_type == IB_QPT_GSI || qp->ibqp.qp_type == IB_QPT_UD)
-		return qp->sq.max_gs;
-
-	if (qp->sq.max_gs > HNS_ROCE_SGE_IN_WQE)
-		return qp->sq.max_gs - HNS_ROCE_SGE_IN_WQE;
+	if (cap->max_inline_data) {
+		cap->max_inline_data = roundup_pow_of_two(cap->max_inline_data);
+		return min(cap->max_inline_data,
+			   hr_dev->caps.max_sq_inline);
+	}
 
 	return 0;
 }
 
+static void update_inline_data(struct hns_roce_qp *hr_qp,
+			       struct ib_qp_cap *cap)
+{
+	u32 sge_num = hr_qp->sq.ext_sge_cnt;
+
+	if (hr_qp->config & HNS_ROCE_EXSGE_FLAGS) {
+		if (!(hr_qp->ibqp.qp_type == IB_QPT_GSI ||
+		      hr_qp->ibqp.qp_type == IB_QPT_UD))
+			sge_num = max((u32)HNS_ROCE_SGE_IN_WQE, sge_num);
+
+		cap->max_inline_data = max(cap->max_inline_data,
+					   sge_num * HNS_ROCE_SGE_SIZE);
+	}
+
+	hr_qp->max_inline_data = cap->max_inline_data;
+}
+
+static u32 get_sge_num_from_max_send_sge(bool is_ud_or_gsi,
+					 u32 max_send_sge)
+{
+	unsigned int std_sge_num;
+	unsigned int min_sge;
+
+	std_sge_num = is_ud_or_gsi ? 0 : HNS_ROCE_SGE_IN_WQE;
+	min_sge = is_ud_or_gsi ? 1 : 0;
+	return max_send_sge > std_sge_num ? (max_send_sge - std_sge_num) :
+				min_sge;
+}
+
+static unsigned int get_sge_num_from_max_inl_data(bool is_ud_or_gsi,
+						  u32 max_inline_data)
+{
+	unsigned int inline_sge;
+
+	inline_sge = roundup_pow_of_two(max_inline_data) / HNS_ROCE_SGE_SIZE;
+
+	/*
+	 * if max_inline_data less than
+	 * HNS_ROCE_SGE_IN_WQE * HNS_ROCE_SGE_SIZE,
+	 * In addition to ud's mode, no need to extend sge.
+	 */
+	if (!is_ud_or_gsi && inline_sge <= HNS_ROCE_SGE_IN_WQE)
+		inline_sge = 0;
+
+	return inline_sge;
+}
+
 static void set_ext_sge_param(struct hns_roce_dev *hr_dev, u32 sq_wqe_cnt,
 			      struct hns_roce_qp *hr_qp, struct ib_qp_cap *cap)
 {
+	bool is_ud_or_gsi = (hr_qp->ibqp.qp_type == IB_QPT_GSI ||
+				hr_qp->ibqp.qp_type == IB_QPT_UD);
+	unsigned int std_sge_num;
+	u32 inline_ext_sge = 0;
+	u32 ext_wqe_sge_cnt;
 	u32 total_sge_cnt;
-	u32 wqe_sge_cnt;
+
+	cap->max_inline_data = get_max_inline_data(hr_dev, cap);
 
 	hr_qp->sge.sge_shift = HNS_ROCE_SGE_SHIFT;
+	std_sge_num = is_ud_or_gsi ? 0 : HNS_ROCE_SGE_IN_WQE;
+	ext_wqe_sge_cnt = get_sge_num_from_max_send_sge(is_ud_or_gsi,
+							cap->max_send_sge);
 
-	hr_qp->sq.max_gs = max(1U, cap->max_send_sge);
+	if (hr_qp->config & HNS_ROCE_EXSGE_FLAGS) {
+		inline_ext_sge = max(ext_wqe_sge_cnt,
+				     get_sge_num_from_max_inl_data(is_ud_or_gsi,
+							 cap->max_inline_data));
+		hr_qp->sq.ext_sge_cnt = inline_ext_sge ?
+					roundup_pow_of_two(inline_ext_sge) : 0;
 
-	wqe_sge_cnt = get_wqe_ext_sge_cnt(hr_qp);
+		hr_qp->sq.max_gs = max(1U, (hr_qp->sq.ext_sge_cnt + std_sge_num));
+		hr_qp->sq.max_gs = min(hr_qp->sq.max_gs, hr_dev->caps.max_sq_sg);
+
+		ext_wqe_sge_cnt = hr_qp->sq.ext_sge_cnt;
+	} else {
+		hr_qp->sq.max_gs = max(1U, cap->max_send_sge);
+		hr_qp->sq.max_gs = min(hr_qp->sq.max_gs, hr_dev->caps.max_sq_sg);
+		hr_qp->sq.ext_sge_cnt = hr_qp->sq.max_gs;
+	}
 
 	/* If the number of extended sge is not zero, they MUST use the
 	 * space of HNS_HW_PAGE_SIZE at least.
 	 */
-	if (wqe_sge_cnt) {
-		total_sge_cnt = roundup_pow_of_two(sq_wqe_cnt * wqe_sge_cnt);
+	if (ext_wqe_sge_cnt) {
+		total_sge_cnt = roundup_pow_of_two(sq_wqe_cnt * ext_wqe_sge_cnt);
 		hr_qp->sge.sge_cnt = max(total_sge_cnt,
 				(u32)HNS_HW_PAGE_SIZE / HNS_ROCE_SGE_SIZE);
 	}
+
+	update_inline_data(hr_qp, cap);
 }
 
 static int check_sq_size_with_integrity(struct hns_roce_dev *hr_dev,
@@ -556,6 +627,7 @@ static int set_user_sq_size(struct hns_roce_dev *hr_dev,
 
 	hr_qp->sq.wqe_shift = ucmd->log_sq_stride;
 	hr_qp->sq.wqe_cnt = cnt;
+	cap->max_send_sge = hr_qp->sq.max_gs;
 
 	return 0;
 }
@@ -986,13 +1058,9 @@ static int set_qp_param(struct hns_roce_dev *hr_dev, struct hns_roce_qp *hr_qp,
 			struct hns_roce_ib_create_qp *ucmd)
 {
 	struct ib_device *ibdev = &hr_dev->ib_dev;
+	struct hns_roce_ucontext *uctx;
 	int ret;
 
-	if (init_attr->cap.max_inline_data > hr_dev->caps.max_sq_inline)
-		init_attr->cap.max_inline_data = hr_dev->caps.max_sq_inline;
-
-	hr_qp->max_inline_data = init_attr->cap.max_inline_data;
-
 	if (init_attr->sq_sig_type == IB_SIGNAL_ALL_WR)
 		hr_qp->sq_signal_bits = IB_SIGNAL_ALL_WR;
 	else
@@ -1015,12 +1083,17 @@ static int set_qp_param(struct hns_roce_dev *hr_dev, struct hns_roce_qp *hr_qp,
 			return ret;
 		}
 
+		uctx = rdma_udata_to_drv_context(udata, struct hns_roce_ucontext,
+						 ibucontext);
+		hr_qp->config = uctx->config;
 		ret = set_user_sq_size(hr_dev, &init_attr->cap, hr_qp, ucmd);
 		if (ret)
 			ibdev_err(ibdev,
 				  "failed to set user SQ size, ret = %d.\n",
 				  ret);
 	} else {
+		if (hr_dev->pci_dev->revision >= PCI_REVISION_ID_HIP09)
+			hr_qp->config = HNS_ROCE_EXSGE_FLAGS;
 		ret = set_kernel_sq_size(hr_dev, &init_attr->cap, hr_qp);
 		if (ret)
 			ibdev_err(ibdev,