1 files changed, 226 insertions, 86 deletions

diff --git a/drivers/infiniband/hw/mlx5/qp.c b/drivers/infiniband/hw/mlx5/qp.c
index 768c7e81f688..2a97619ed603 100644
--- a/drivers/infiniband/hw/mlx5/qp.c
+++ b/drivers/infiniband/hw/mlx5/qp.c
@@ -34,6 +34,7 @@
 #include <rdma/ib_umem.h>
 #include <rdma/ib_cache.h>
 #include <rdma/ib_user_verbs.h>
+#include <rdma/rdma_counter.h>
 #include <linux/mlx5/fs.h>
 #include "mlx5_ib.h"
 #include "ib_rep.h"
@@ -442,9 +443,9 @@ static int calc_send_wqe(struct ib_qp_init_attr *attr)
 	}
 
 	size += attr->cap.max_send_sge * sizeof(struct mlx5_wqe_data_seg);
-	if (attr->create_flags & IB_QP_CREATE_SIGNATURE_EN &&
+	if (attr->create_flags & IB_QP_CREATE_INTEGRITY_EN &&
 	    ALIGN(max_t(int, inl_size, size), MLX5_SEND_WQE_BB) < MLX5_SIG_WQE_SIZE)
-			return MLX5_SIG_WQE_SIZE;
+		return MLX5_SIG_WQE_SIZE;
 	else
 		return ALIGN(max_t(int, inl_size, size), MLX5_SEND_WQE_BB);
 }
@@ -496,9 +497,6 @@ static int calc_sq_size(struct mlx5_ib_dev *dev, struct ib_qp_init_attr *attr,
 			      sizeof(struct mlx5_wqe_inline_seg);
 	attr->cap.max_inline_data = qp->max_inline_data;
 
-	if (attr->create_flags & IB_QP_CREATE_SIGNATURE_EN)
-		qp->signature_en = true;
-
 	wq_size = roundup_pow_of_two(attr->cap.max_send_wr * wqe_size);
 	qp->sq.wqe_cnt = wq_size / MLX5_SEND_WQE_BB;
 	if (qp->sq.wqe_cnt > (1 << MLX5_CAP_GEN(dev->mdev, log_max_qp_sz))) {
@@ -790,8 +788,7 @@ static void destroy_user_rq(struct mlx5_ib_dev *dev, struct ib_pd *pd,
 		atomic_dec(&dev->delay_drop.rqs_cnt);
 
 	mlx5_ib_db_unmap_user(context, &rwq->db);
-	if (rwq->umem)
-		ib_umem_release(rwq->umem);
+	ib_umem_release(rwq->umem);
 }
 
 static int create_user_rq(struct mlx5_ib_dev *dev, struct ib_pd *pd,
@@ -977,8 +974,7 @@ err_free:
 	kvfree(*in);
 
 err_umem:
-	if (ubuffer->umem)
-		ib_umem_release(ubuffer->umem);
+	ib_umem_release(ubuffer->umem);
 
 err_bfreg:
 	if (bfregn != MLX5_IB_INVALID_BFREG)
@@ -997,8 +993,7 @@ static void destroy_qp_user(struct mlx5_ib_dev *dev, struct ib_pd *pd,
 			ibucontext);
 
 	mlx5_ib_db_unmap_user(context, &qp->db);
-	if (base->ubuffer.umem)
-		ib_umem_release(base->ubuffer.umem);
+	ib_umem_release(base->ubuffer.umem);
 
 	/*
 	 * Free only the BFREGs which are handled by the kernel.
@@ -1042,7 +1037,7 @@ static int create_kernel_qp(struct mlx5_ib_dev *dev,
 	void *qpc;
 	int err;
 
-	if (init_attr->create_flags & ~(IB_QP_CREATE_SIGNATURE_EN |
+	if (init_attr->create_flags & ~(IB_QP_CREATE_INTEGRITY_EN |
 					IB_QP_CREATE_BLOCK_MULTICAST_LOOPBACK |
 					IB_QP_CREATE_IPOIB_UD_LSO |
 					IB_QP_CREATE_NETIF_QP |
@@ -3386,6 +3381,35 @@ static unsigned int get_tx_affinity(struct mlx5_ib_dev *dev,
 	return tx_port_affinity;
 }
 
+static int __mlx5_ib_qp_set_counter(struct ib_qp *qp,
+				    struct rdma_counter *counter)
+{
+	struct mlx5_ib_dev *dev = to_mdev(qp->device);
+	struct mlx5_ib_qp *mqp = to_mqp(qp);
+	struct mlx5_qp_context context = {};
+	struct mlx5_ib_port *mibport = NULL;
+	struct mlx5_ib_qp_base *base;
+	u32 set_id;
+
+	if (!MLX5_CAP_GEN(dev->mdev, rts2rts_qp_counters_set_id))
+		return 0;
+
+	if (counter) {
+		set_id = counter->id;
+	} else {
+		mibport = &dev->port[mqp->port - 1];
+		set_id = mibport->cnts.set_id;
+	}
+
+	base = &mqp->trans_qp.base;
+	context.qp_counter_set_usr_page &= cpu_to_be32(0xffffff);
+	context.qp_counter_set_usr_page |= cpu_to_be32(set_id << 24);
+	return mlx5_core_qp_modify(dev->mdev,
+				   MLX5_CMD_OP_RTS2RTS_QP,
+				   MLX5_QP_OPTPAR_COUNTER_SET_ID,
+				   &context, &base->mqp);
+}
+
 static int __mlx5_ib_modify_qp(struct ib_qp *ibqp,
 			       const struct ib_qp_attr *attr, int attr_mask,
 			       enum ib_qp_state cur_state,
@@ -3439,6 +3463,7 @@ static int __mlx5_ib_modify_qp(struct ib_qp *ibqp,
 	struct mlx5_ib_port *mibport = NULL;
 	enum mlx5_qp_state mlx5_cur, mlx5_new;
 	enum mlx5_qp_optpar optpar;
+	u32 set_id = 0;
 	int mlx5_st;
 	int err;
 	u16 op;
@@ -3601,8 +3626,12 @@ static int __mlx5_ib_modify_qp(struct ib_qp *ibqp,
 			port_num = 0;
 
 		mibport = &dev->port[port_num];
+		if (ibqp->counter)
+			set_id = ibqp->counter->id;
+		else
+			set_id = mibport->cnts.set_id;
 		context->qp_counter_set_usr_page |=
-			cpu_to_be32((u32)(mibport->cnts.set_id) << 24);
+			cpu_to_be32(set_id << 24);
 	}
 
 	if (!ibqp->uobject && cur_state == IB_QPS_RESET && new_state == IB_QPS_INIT)
@@ -3630,7 +3659,7 @@ static int __mlx5_ib_modify_qp(struct ib_qp *ibqp,
 
 		raw_qp_param.operation = op;
 		if (cur_state == IB_QPS_RESET && new_state == IB_QPS_INIT) {
-			raw_qp_param.rq_q_ctr_id = mibport->cnts.set_id;
+			raw_qp_param.rq_q_ctr_id = set_id;
 			raw_qp_param.set_mask |= MLX5_RAW_QP_MOD_SET_RQ_Q_CTR_ID;
 		}
 
@@ -3707,6 +3736,12 @@ static int __mlx5_ib_modify_qp(struct ib_qp *ibqp,
 		qp->db.db[MLX5_SND_DBR] = 0;
 	}
 
+	if ((new_state == IB_QPS_RTS) && qp->counter_pending) {
+		err = __mlx5_ib_qp_set_counter(ibqp, ibqp->counter);
+		if (!err)
+			qp->counter_pending = 0;
+	}
+
 out:
 	kfree(context);
 	return err;
@@ -4170,15 +4205,13 @@ static __be64 sig_mkey_mask(void)
 }
 
 static void set_reg_umr_seg(struct mlx5_wqe_umr_ctrl_seg *umr,
-			    struct mlx5_ib_mr *mr, bool umr_inline)
+			    struct mlx5_ib_mr *mr, u8 flags)
 {
-	int size = mr->ndescs * mr->desc_size;
+	int size = (mr->ndescs + mr->meta_ndescs) * mr->desc_size;
 
 	memset(umr, 0, sizeof(*umr));
 
-	umr->flags = MLX5_UMR_CHECK_NOT_FREE;
-	if (umr_inline)
-		umr->flags |= MLX5_UMR_INLINE;
+	umr->flags = flags;
 	umr->xlt_octowords = cpu_to_be16(get_xlt_octo(size));
 	umr->mkey_mask = frwr_mkey_mask();
 }
@@ -4305,7 +4338,7 @@ static void set_reg_mkey_seg(struct mlx5_mkey_seg *seg,
 			     struct mlx5_ib_mr *mr,
 			     u32 key, int access)
 {
-	int ndescs = ALIGN(mr->ndescs, 8) >> 1;
+	int ndescs = ALIGN(mr->ndescs + mr->meta_ndescs, 8) >> 1;
 
 	memset(seg, 0, sizeof(*seg));
 
@@ -4356,7 +4389,7 @@ static void set_reg_data_seg(struct mlx5_wqe_data_seg *dseg,
 			     struct mlx5_ib_mr *mr,
 			     struct mlx5_ib_pd *pd)
 {
-	int bcount = mr->desc_size * mr->ndescs;
+	int bcount = mr->desc_size * (mr->ndescs + mr->meta_ndescs);
 
 	dseg->addr = cpu_to_be64(mr->desc_map);
 	dseg->byte_count = cpu_to_be32(ALIGN(bcount, 64));
@@ -4549,23 +4582,37 @@ static int mlx5_set_bsf(struct ib_mr *sig_mr,
 	return 0;
 }
 
-static int set_sig_data_segment(const struct ib_sig_handover_wr *wr,
-				struct mlx5_ib_qp *qp, void **seg,
-				int *size, void **cur_edge)
+static int set_sig_data_segment(const struct ib_send_wr *send_wr,
+				struct ib_mr *sig_mr,
+				struct ib_sig_attrs *sig_attrs,
+				struct mlx5_ib_qp *qp, void **seg, int *size,
+				void **cur_edge)
 {
-	struct ib_sig_attrs *sig_attrs = wr->sig_attrs;
-	struct ib_mr *sig_mr = wr->sig_mr;
 	struct mlx5_bsf *bsf;
-	u32 data_len = wr->wr.sg_list->length;
-	u32 data_key = wr->wr.sg_list->lkey;
-	u64 data_va = wr->wr.sg_list->addr;
+	u32 data_len;
+	u32 data_key;
+	u64 data_va;
+	u32 prot_len = 0;
+	u32 prot_key = 0;
+	u64 prot_va = 0;
+	bool prot = false;
 	int ret;
 	int wqe_size;
+	struct mlx5_ib_mr *mr = to_mmr(sig_mr);
+	struct mlx5_ib_mr *pi_mr = mr->pi_mr;
+
+	data_len = pi_mr->data_length;
+	data_key = pi_mr->ibmr.lkey;
+	data_va = pi_mr->data_iova;
+	if (pi_mr->meta_ndescs) {
+		prot_len = pi_mr->meta_length;
+		prot_key = pi_mr->ibmr.lkey;
+		prot_va = pi_mr->pi_iova;
+		prot = true;
+	}
 
-	if (!wr->prot ||
-	    (data_key == wr->prot->lkey &&
-	     data_va == wr->prot->addr &&
-	     data_len == wr->prot->length)) {
+	if (!prot || (data_key == prot_key && data_va == prot_va &&
+		      data_len == prot_len)) {
 		/**
 		 * Source domain doesn't contain signature information
 		 * or data and protection are interleaved in memory.
@@ -4599,8 +4646,6 @@ static int set_sig_data_segment(const struct ib_sig_handover_wr *wr,
 		struct mlx5_stride_block_ctrl_seg *sblock_ctrl;
 		struct mlx5_stride_block_entry *data_sentry;
 		struct mlx5_stride_block_entry *prot_sentry;
-		u32 prot_key = wr->prot->lkey;
-		u64 prot_va = wr->prot->addr;
 		u16 block_size = sig_attrs->mem.sig.dif.pi_interval;
 		int prot_size;
 
@@ -4650,17 +4695,15 @@ static int set_sig_data_segment(const struct ib_sig_handover_wr *wr,
 }
 
 static void set_sig_mkey_segment(struct mlx5_mkey_seg *seg,
-				 const struct ib_sig_handover_wr *wr, u32 size,
-				 u32 length, u32 pdn)
+				 struct ib_mr *sig_mr, int access_flags,
+				 u32 size, u32 length, u32 pdn)
 {
-	struct ib_mr *sig_mr = wr->sig_mr;
 	u32 sig_key = sig_mr->rkey;
 	u8 sigerr = to_mmr(sig_mr)->sig->sigerr_count & 1;
 
 	memset(seg, 0, sizeof(*seg));
 
-	seg->flags = get_umr_flags(wr->access_flags) |
-				   MLX5_MKC_ACCESS_MODE_KLMS;
+	seg->flags = get_umr_flags(access_flags) | MLX5_MKC_ACCESS_MODE_KLMS;
 	seg->qpn_mkey7_0 = cpu_to_be32((sig_key & 0xff) | 0xffffff00);
 	seg->flags_pd = cpu_to_be32(MLX5_MKEY_REMOTE_INVAL | sigerr << 26 |
 				    MLX5_MKEY_BSF_EN | pdn);
@@ -4680,49 +4723,50 @@ static void set_sig_umr_segment(struct mlx5_wqe_umr_ctrl_seg *umr,
 	umr->mkey_mask = sig_mkey_mask();
 }
 
-
-static int set_sig_umr_wr(const struct ib_send_wr *send_wr,
-			  struct mlx5_ib_qp *qp, void **seg, int *size,
-			  void **cur_edge)
+static int set_pi_umr_wr(const struct ib_send_wr *send_wr,
+			 struct mlx5_ib_qp *qp, void **seg, int *size,
+			 void **cur_edge)
 {
-	const struct ib_sig_handover_wr *wr = sig_handover_wr(send_wr);
-	struct mlx5_ib_mr *sig_mr = to_mmr(wr->sig_mr);
+	const struct ib_reg_wr *wr = reg_wr(send_wr);
+	struct mlx5_ib_mr *sig_mr = to_mmr(wr->mr);
+	struct mlx5_ib_mr *pi_mr = sig_mr->pi_mr;
+	struct ib_sig_attrs *sig_attrs = sig_mr->ibmr.sig_attrs;
 	u32 pdn = get_pd(qp)->pdn;
 	u32 xlt_size;
 	int region_len, ret;
 
-	if (unlikely(wr->wr.num_sge != 1) ||
-	    unlikely(wr->access_flags & IB_ACCESS_REMOTE_ATOMIC) ||
-	    unlikely(!sig_mr->sig) || unlikely(!qp->signature_en) ||
+	if (unlikely(send_wr->num_sge != 0) ||
+	    unlikely(wr->access & IB_ACCESS_REMOTE_ATOMIC) ||
+	    unlikely(!sig_mr->sig) || unlikely(!qp->ibqp.integrity_en) ||
 	    unlikely(!sig_mr->sig->sig_status_checked))
 		return -EINVAL;
 
 	/* length of the protected region, data + protection */
-	region_len = wr->wr.sg_list->length;
-	if (wr->prot &&
-	    (wr->prot->lkey != wr->wr.sg_list->lkey  ||
-	     wr->prot->addr != wr->wr.sg_list->addr  ||
-	     wr->prot->length != wr->wr.sg_list->length))
-		region_len += wr->prot->length;
+	region_len = pi_mr->ibmr.length;
 
 	/**
 	 * KLM octoword size - if protection was provided
 	 * then we use strided block format (3 octowords),
 	 * else we use single KLM (1 octoword)
 	 **/
-	xlt_size = wr->prot ? 0x30 : sizeof(struct mlx5_klm);
+	if (sig_attrs->mem.sig_type != IB_SIG_TYPE_NONE)
+		xlt_size = 0x30;
+	else
+		xlt_size = sizeof(struct mlx5_klm);
 
 	set_sig_umr_segment(*seg, xlt_size);
 	*seg += sizeof(struct mlx5_wqe_umr_ctrl_seg);
 	*size += sizeof(struct mlx5_wqe_umr_ctrl_seg) / 16;
 	handle_post_send_edge(&qp->sq, seg, *size, cur_edge);
 
-	set_sig_mkey_segment(*seg, wr, xlt_size, region_len, pdn);
+	set_sig_mkey_segment(*seg, wr->mr, wr->access, xlt_size, region_len,
+			     pdn);
 	*seg += sizeof(struct mlx5_mkey_seg);
 	*size += sizeof(struct mlx5_mkey_seg) / 16;
 	handle_post_send_edge(&qp->sq, seg, *size, cur_edge);
 
-	ret = set_sig_data_segment(wr, qp, seg, size, cur_edge);
+	ret = set_sig_data_segment(send_wr, wr->mr, sig_attrs, qp, seg, size,
+				   cur_edge);
 	if (ret)
 		return ret;
 
@@ -4759,12 +4803,14 @@ static int set_psv_wr(struct ib_sig_domain *domain,
 
 static int set_reg_wr(struct mlx5_ib_qp *qp,
 		      const struct ib_reg_wr *wr,
-		      void **seg, int *size, void **cur_edge)
+		      void **seg, int *size, void **cur_edge,
+		      bool check_not_free)
 {
 	struct mlx5_ib_mr *mr = to_mmr(wr->mr);
 	struct mlx5_ib_pd *pd = to_mpd(qp->ibqp.pd);
-	size_t mr_list_size = mr->ndescs * mr->desc_size;
+	int mr_list_size = (mr->ndescs + mr->meta_ndescs) * mr->desc_size;
 	bool umr_inline = mr_list_size <= MLX5_IB_SQ_UMR_INLINE_THRESHOLD;
+	u8 flags = 0;
 
 	if (unlikely(wr->wr.send_flags & IB_SEND_INLINE)) {
 		mlx5_ib_warn(to_mdev(qp->ibqp.device),
@@ -4772,7 +4818,12 @@ static int set_reg_wr(struct mlx5_ib_qp *qp,
 		return -EINVAL;
 	}
 
-	set_reg_umr_seg(*seg, mr, umr_inline);
+	if (check_not_free)
+		flags |= MLX5_UMR_CHECK_NOT_FREE;
+	if (umr_inline)
+		flags |= MLX5_UMR_INLINE;
+
+	set_reg_umr_seg(*seg, mr, flags);
 	*seg += sizeof(struct mlx5_wqe_umr_ctrl_seg);
 	*size += sizeof(struct mlx5_wqe_umr_ctrl_seg) / 16;
 	handle_post_send_edge(&qp->sq, seg, *size, cur_edge);
@@ -4898,8 +4949,12 @@ static int _mlx5_ib_post_send(struct ib_qp *ibqp, const struct ib_send_wr *wr,
 	struct mlx5_wqe_ctrl_seg *ctrl = NULL;  /* compiler warning */
 	struct mlx5_ib_dev *dev = to_mdev(ibqp->device);
 	struct mlx5_core_dev *mdev = dev->mdev;
+	struct ib_reg_wr reg_pi_wr;
 	struct mlx5_ib_qp *qp;
 	struct mlx5_ib_mr *mr;
+	struct mlx5_ib_mr *pi_mr;
+	struct mlx5_ib_mr pa_pi_mr;
+	struct ib_sig_attrs *sig_attrs;
 	struct mlx5_wqe_xrc_seg *xrc;
 	struct mlx5_bf *bf;
 	void *cur_edge;
@@ -4953,7 +5008,8 @@ static int _mlx5_ib_post_send(struct ib_qp *ibqp, const struct ib_send_wr *wr,
 			goto out;
 		}
 
-		if (wr->opcode == IB_WR_REG_MR) {
+		if (wr->opcode == IB_WR_REG_MR ||
+		    wr->opcode == IB_WR_REG_MR_INTEGRITY) {
 			fence = dev->umr_fence;
 			next_fence = MLX5_FENCE_MODE_INITIATOR_SMALL;
 		} else  {
@@ -5003,7 +5059,7 @@ static int _mlx5_ib_post_send(struct ib_qp *ibqp, const struct ib_send_wr *wr,
 				qp->sq.wr_data[idx] = IB_WR_REG_MR;
 				ctrl->imm = cpu_to_be32(reg_wr(wr)->key);
 				err = set_reg_wr(qp, reg_wr(wr), &seg, &size,
-						 &cur_edge);
+						 &cur_edge, true);
 				if (err) {
 					*bad_wr = wr;
 					goto out;
@@ -5011,26 +5067,82 @@ static int _mlx5_ib_post_send(struct ib_qp *ibqp, const struct ib_send_wr *wr,
 				num_sge = 0;
 				break;
 
-			case IB_WR_REG_SIG_MR:
-				qp->sq.wr_data[idx] = IB_WR_REG_SIG_MR;
-				mr = to_mmr(sig_handover_wr(wr)->sig_mr);
-
+			case IB_WR_REG_MR_INTEGRITY:
+				qp->sq.wr_data[idx] = IB_WR_REG_MR_INTEGRITY;
+
+				mr = to_mmr(reg_wr(wr)->mr);
+				pi_mr = mr->pi_mr;
+
+				if (pi_mr) {
+					memset(&reg_pi_wr, 0,
+					       sizeof(struct ib_reg_wr));
+
+					reg_pi_wr.mr = &pi_mr->ibmr;
+					reg_pi_wr.access = reg_wr(wr)->access;
+					reg_pi_wr.key = pi_mr->ibmr.rkey;
+
+					ctrl->imm = cpu_to_be32(reg_pi_wr.key);
+					/* UMR for data + prot registration */
+					err = set_reg_wr(qp, &reg_pi_wr, &seg,
+							 &size, &cur_edge,
+							 false);
+					if (err) {
+						*bad_wr = wr;
+						goto out;
+					}
+					finish_wqe(qp, ctrl, seg, size,
+						   cur_edge, idx, wr->wr_id,
+						   nreq, fence,
+						   MLX5_OPCODE_UMR);
+
+					err = begin_wqe(qp, &seg, &ctrl, wr,
+							&idx, &size, &cur_edge,
+							nreq);
+					if (err) {
+						mlx5_ib_warn(dev, "\n");
+						err = -ENOMEM;
+						*bad_wr = wr;
+						goto out;
+					}
+				} else {
+					memset(&pa_pi_mr, 0,
+					       sizeof(struct mlx5_ib_mr));
+					/* No UMR, use local_dma_lkey */
+					pa_pi_mr.ibmr.lkey =
+						mr->ibmr.pd->local_dma_lkey;
+
+					pa_pi_mr.ndescs = mr->ndescs;
+					pa_pi_mr.data_length = mr->data_length;
+					pa_pi_mr.data_iova = mr->data_iova;
+					if (mr->meta_ndescs) {
+						pa_pi_mr.meta_ndescs =
+							mr->meta_ndescs;
+						pa_pi_mr.meta_length =
+							mr->meta_length;
+						pa_pi_mr.pi_iova = mr->pi_iova;
+					}
+
+					pa_pi_mr.ibmr.length = mr->ibmr.length;
+					mr->pi_mr = &pa_pi_mr;
+				}
 				ctrl->imm = cpu_to_be32(mr->ibmr.rkey);
-				err = set_sig_umr_wr(wr, qp, &seg, &size,
-						     &cur_edge);
+				/* UMR for sig MR */
+				err = set_pi_umr_wr(wr, qp, &seg, &size,
+						    &cur_edge);
 				if (err) {
 					mlx5_ib_warn(dev, "\n");
 					*bad_wr = wr;
 					goto out;
 				}
-
 				finish_wqe(qp, ctrl, seg, size, cur_edge, idx,
 					   wr->wr_id, nreq, fence,
 					   MLX5_OPCODE_UMR);
+
 				/*
 				 * SET_PSV WQEs are not signaled and solicited
 				 * on error
 				 */
+				sig_attrs = mr->ibmr.sig_attrs;
 				err = __begin_wqe(qp, &seg, &ctrl, wr, &idx,
 						  &size, &cur_edge, nreq, false,
 						  true);
@@ -5040,19 +5152,18 @@ static int _mlx5_ib_post_send(struct ib_qp *ibqp, const struct ib_send_wr *wr,
 					*bad_wr = wr;
 					goto out;
 				}
-
-				err = set_psv_wr(&sig_handover_wr(wr)->sig_attrs->mem,
-						 mr->sig->psv_memory.psv_idx, &seg,
-						 &size);
+				err = set_psv_wr(&sig_attrs->mem,
+						 mr->sig->psv_memory.psv_idx,
+						 &seg, &size);
 				if (err) {
 					mlx5_ib_warn(dev, "\n");
 					*bad_wr = wr;
 					goto out;
 				}
-
 				finish_wqe(qp, ctrl, seg, size, cur_edge, idx,
-					   wr->wr_id, nreq, fence,
+					   wr->wr_id, nreq, next_fence,
 					   MLX5_OPCODE_SET_PSV);
+
 				err = __begin_wqe(qp, &seg, &ctrl, wr, &idx,
 						  &size, &cur_edge, nreq, false,
 						  true);
@@ -5062,20 +5173,20 @@ static int _mlx5_ib_post_send(struct ib_qp *ibqp, const struct ib_send_wr *wr,
 					*bad_wr = wr;
 					goto out;
 				}
-
-				err = set_psv_wr(&sig_handover_wr(wr)->sig_attrs->wire,
-						 mr->sig->psv_wire.psv_idx, &seg,
-						 &size);
+				err = set_psv_wr(&sig_attrs->wire,
+						 mr->sig->psv_wire.psv_idx,
+						 &seg, &size);
 				if (err) {
 					mlx5_ib_warn(dev, "\n");
 					*bad_wr = wr;
 					goto out;
 				}
-
 				finish_wqe(qp, ctrl, seg, size, cur_edge, idx,
-					   wr->wr_id, nreq, fence,
+					   wr->wr_id, nreq, next_fence,
 					   MLX5_OPCODE_SET_PSV);
-				qp->next_fence = MLX5_FENCE_MODE_INITIATOR_SMALL;
+
+				qp->next_fence =
+					MLX5_FENCE_MODE_INITIATOR_SMALL;
 				num_sge = 0;
 				goto skip_psv;
 
@@ -6047,7 +6158,7 @@ err:
 	return ERR_PTR(err);
 }
 
-int mlx5_ib_destroy_wq(struct ib_wq *wq, struct ib_udata *udata)
+void mlx5_ib_destroy_wq(struct ib_wq *wq, struct ib_udata *udata)
 {
 	struct mlx5_ib_dev *dev = to_mdev(wq->device);
 	struct mlx5_ib_rwq *rwq = to_mrwq(wq);
@@ -6055,8 +6166,6 @@ int mlx5_ib_destroy_wq(struct ib_wq *wq, struct ib_udata *udata)
 	mlx5_core_destroy_rq_tracked(dev->mdev, &rwq->core_qp);
 	destroy_user_rq(dev, wq->pd, rwq, udata);
 	kfree(rwq);
-
-	return 0;
 }
 
 struct ib_rwq_ind_table *mlx5_ib_create_rwq_ind_table(struct ib_device *device,
@@ -6367,3 +6476,34 @@ void mlx5_ib_drain_rq(struct ib_qp *qp)
 
 	handle_drain_completion(cq, &rdrain, dev);
 }
+
+/**
+ * Bind a qp to a counter. If @counter is NULL then bind the qp to
+ * the default counter
+ */
+int mlx5_ib_qp_set_counter(struct ib_qp *qp, struct rdma_counter *counter)
+{
+	struct mlx5_ib_qp *mqp = to_mqp(qp);
+	int err = 0;
+
+	mutex_lock(&mqp->mutex);
+	if (mqp->state == IB_QPS_RESET) {
+		qp->counter = counter;
+		goto out;
+	}
+
+	if (mqp->state == IB_QPS_RTS) {
+		err = __mlx5_ib_qp_set_counter(qp, counter);
+		if (!err)
+			qp->counter = counter;
+
+		goto out;
+	}
+
+	mqp->counter_pending = 1;
+	qp->counter = counter;
+
+out:
+	mutex_unlock(&mqp->mutex);
+	return err;
+}