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

Pull rdma updates from Jason Gunthorpe:
 "This is quite a small cycle, no major series stands out. The HNS and
  rxe drivers saw the most activity this cycle, with rxe being broken
  for a good chunk of time. The significant deleted line count is due to
  a SPDX cleanup series.

  Summary:

   - Various cleanup and small features for rtrs

   - kmap_local_page() conversions

   - Driver updates and fixes for: efa, rxe, mlx5, hfi1, qed, hns

   - Cache the IB subnet prefix

   - Rework how CRC is calcuated in rxe

   - Clean reference counting in iwpm's netlink

   - Pull object allocation and lifecycle for user QPs to the uverbs
     core code

   - Several small hns features and continued general code cleanups

   - Fix the scatterlist confusion of orig_nents/nents introduced in an
     earlier patch creating the append operation"

* tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdma: (90 commits)
  RDMA/mlx5: Relax DCS QP creation checks
  RDMA/hns: Delete unnecessary blank lines.
  RDMA/hns: Encapsulate the qp db as a function
  RDMA/hns: Adjust the order in which irq are requested and enabled
  RDMA/hns: Remove RST2RST error prints for hw v1
  RDMA/hns: Remove dqpn filling when modify qp from Init to Init
  RDMA/hns: Fix QP's resp incomplete assignment
  RDMA/hns: Fix query destination qpn
  RDMA/hfi1: Convert to SPDX identifier
  IB/rdmavt: Convert to SPDX identifier
  RDMA/hns: Bugfix for incorrect association between dip_idx and dgid
  RDMA/hns: Bugfix for the missing assignment for dip_idx
  RDMA/hns: Bugfix for data type of dip_idx
  RDMA/hns: Fix incorrect lsn field
  RDMA/irdma: Remove the repeated declaration
  RDMA/core/sa_query: Retry SA queries
  RDMA: Use the sg_table directly and remove the opencoded version from umem
  lib/scatterlist: Fix wrong update of orig_nents
  lib/scatterlist: Provide a dedicated function to support table append
  RDMA/hns: Delete unused hns bitmap interface
  ...

7 files changed, 156 insertions, 142 deletions

diff --git a/drivers/infiniband/ulp/rtrs/rtrs-clt-stats.c b/drivers/infiniband/ulp/rtrs/rtrs-clt-stats.c
index 26bbe5d6dff5..5e780bdd763d 100644
--- a/drivers/infiniband/ulp/rtrs/rtrs-clt-stats.c
+++ b/drivers/infiniband/ulp/rtrs/rtrs-clt-stats.c
@@ -20,7 +20,7 @@ void rtrs_clt_update_wc_stats(struct rtrs_clt_con *con)
 
 	cpu = raw_smp_processor_id();
 	s = this_cpu_ptr(stats->pcpu_stats);
-	if (unlikely(con->cpu != cpu)) {
+	if (con->cpu != cpu) {
 		s->cpu_migr.to++;
 
 		/* Careful here, override s pointer */
@@ -180,7 +180,7 @@ void rtrs_clt_update_all_stats(struct rtrs_clt_io_req *req, int dir)
 
 	len = req->usr_len + req->data_len;
 	rtrs_clt_update_rdma_stats(stats, len, dir);
-	if (sess->clt->mp_policy == MP_POLICY_MIN_INFLIGHT)
+	if (req->mp_policy == MP_POLICY_MIN_INFLIGHT)
 		atomic_inc(&stats->inflight);
 }
 
diff --git a/drivers/infiniband/ulp/rtrs/rtrs-clt.c b/drivers/infiniband/ulp/rtrs/rtrs-clt.c
index f2c40e50f25e..bc8824b4ee0d 100644
--- a/drivers/infiniband/ulp/rtrs/rtrs-clt.c
+++ b/drivers/infiniband/ulp/rtrs/rtrs-clt.c
@@ -75,9 +75,9 @@ __rtrs_get_permit(struct rtrs_clt *clt, enum rtrs_clt_con_type con_type)
 	 */
 	do {
 		bit = find_first_zero_bit(clt->permits_map, max_depth);
-		if (unlikely(bit >= max_depth))
+		if (bit >= max_depth)
 			return NULL;
-	} while (unlikely(test_and_set_bit_lock(bit, clt->permits_map)));
+	} while (test_and_set_bit_lock(bit, clt->permits_map));
 
 	permit = get_permit(clt, bit);
 	WARN_ON(permit->mem_id != bit);
@@ -115,14 +115,14 @@ struct rtrs_permit *rtrs_clt_get_permit(struct rtrs_clt *clt,
 	DEFINE_WAIT(wait);
 
 	permit = __rtrs_get_permit(clt, con_type);
-	if (likely(permit) || !can_wait)
+	if (permit || !can_wait)
 		return permit;
 
 	do {
 		prepare_to_wait(&clt->permits_wait, &wait,
 				TASK_UNINTERRUPTIBLE);
 		permit = __rtrs_get_permit(clt, con_type);
-		if (likely(permit))
+		if (permit)
 			break;
 
 		io_schedule();
@@ -175,7 +175,7 @@ struct rtrs_clt_con *rtrs_permit_to_clt_con(struct rtrs_clt_sess *sess,
 {
 	int id = 0;
 
-	if (likely(permit->con_type == RTRS_IO_CON))
+	if (permit->con_type == RTRS_IO_CON)
 		id = (permit->cpu_id % (sess->s.irq_con_num - 1)) + 1;
 
 	return to_clt_con(sess->s.con[id]);
@@ -329,7 +329,7 @@ static void rtrs_clt_fast_reg_done(struct ib_cq *cq, struct ib_wc *wc)
 {
 	struct rtrs_clt_con *con = to_clt_con(wc->qp->qp_context);
 
-	if (unlikely(wc->status != IB_WC_SUCCESS)) {
+	if (wc->status != IB_WC_SUCCESS) {
 		rtrs_err(con->c.sess, "Failed IB_WR_REG_MR: %s\n",
 			  ib_wc_status_msg(wc->status));
 		rtrs_rdma_error_recovery(con);
@@ -349,13 +349,13 @@ static void rtrs_clt_inv_rkey_done(struct ib_cq *cq, struct ib_wc *wc)
 		container_of(wc->wr_cqe, typeof(*req), inv_cqe);
 	struct rtrs_clt_con *con = to_clt_con(wc->qp->qp_context);
 
-	if (unlikely(wc->status != IB_WC_SUCCESS)) {
+	if (wc->status != IB_WC_SUCCESS) {
 		rtrs_err(con->c.sess, "Failed IB_WR_LOCAL_INV: %s\n",
 			  ib_wc_status_msg(wc->status));
 		rtrs_rdma_error_recovery(con);
 	}
 	req->need_inv = false;
-	if (likely(req->need_inv_comp))
+	if (req->need_inv_comp)
 		complete(&req->inv_comp);
 	else
 		/* Complete request from INV callback */
@@ -390,7 +390,7 @@ static void complete_rdma_req(struct rtrs_clt_io_req *req, int errno,
 	sess = to_clt_sess(con->c.sess);
 
 	if (req->sg_cnt) {
-		if (unlikely(req->dir == DMA_FROM_DEVICE && req->need_inv)) {
+		if (req->dir == DMA_FROM_DEVICE && req->need_inv) {
 			/*
 			 * We are here to invalidate read requests
 			 * ourselves.  In normal scenario server should
@@ -405,7 +405,7 @@ static void complete_rdma_req(struct rtrs_clt_io_req *req, int errno,
 			 *        should do that ourselves.
 			 */
 
-			if (likely(can_wait)) {
+			if (can_wait) {
 				req->need_inv_comp = true;
 			} else {
 				/* This should be IO path, so always notify */
@@ -416,10 +416,10 @@ static void complete_rdma_req(struct rtrs_clt_io_req *req, int errno,
 
 			refcount_inc(&req->ref);
 			err = rtrs_inv_rkey(req);
-			if (unlikely(err)) {
+			if (err) {
 				rtrs_err(con->c.sess, "Send INV WR key=%#x: %d\n",
 					  req->mr->rkey, err);
-			} else if (likely(can_wait)) {
+			} else if (can_wait) {
 				wait_for_completion(&req->inv_comp);
 			} else {
 				/*
@@ -438,7 +438,7 @@ static void complete_rdma_req(struct rtrs_clt_io_req *req, int errno,
 	}
 	if (!refcount_dec_and_test(&req->ref))
 		return;
-	if (sess->clt->mp_policy == MP_POLICY_MIN_INFLIGHT)
+	if (req->mp_policy == MP_POLICY_MIN_INFLIGHT)
 		atomic_dec(&sess->stats->inflight);
 
 	req->in_use = false;
@@ -463,7 +463,7 @@ static int rtrs_post_send_rdma(struct rtrs_clt_con *con,
 	enum ib_send_flags flags;
 	struct ib_sge sge;
 
-	if (unlikely(!req->sg_size)) {
+	if (!req->sg_size) {
 		rtrs_wrn(con->c.sess,
 			 "Doing RDMA Write failed, no data supplied\n");
 		return -EINVAL;
@@ -478,7 +478,7 @@ static int rtrs_post_send_rdma(struct rtrs_clt_con *con,
 	 * From time to time we have to post signalled sends,
 	 * or send queue will fill up and only QP reset can help.
 	 */
-	flags = atomic_inc_return(&con->io_cnt) % sess->queue_depth ?
+	flags = atomic_inc_return(&con->c.wr_cnt) % sess->s.signal_interval ?
 			0 : IB_SEND_SIGNALED;
 
 	ib_dma_sync_single_for_device(sess->s.dev->ib_dev, req->iu->dma_addr,
@@ -513,7 +513,7 @@ static void rtrs_clt_recv_done(struct rtrs_clt_con *con, struct ib_wc *wc)
 	iu = container_of(wc->wr_cqe, struct rtrs_iu,
 			  cqe);
 	err = rtrs_iu_post_recv(&con->c, iu);
-	if (unlikely(err)) {
+	if (err) {
 		rtrs_err(con->c.sess, "post iu failed %d\n", err);
 		rtrs_rdma_error_recovery(con);
 	}
@@ -533,7 +533,7 @@ static void rtrs_clt_rkey_rsp_done(struct rtrs_clt_con *con, struct ib_wc *wc)
 
 	iu = container_of(wc->wr_cqe, struct rtrs_iu, cqe);
 
-	if (unlikely(wc->byte_len < sizeof(*msg))) {
+	if (wc->byte_len < sizeof(*msg)) {
 		rtrs_err(con->c.sess, "rkey response is malformed: size %d\n",
 			  wc->byte_len);
 		goto out;
@@ -541,7 +541,7 @@ static void rtrs_clt_rkey_rsp_done(struct rtrs_clt_con *con, struct ib_wc *wc)
 	ib_dma_sync_single_for_cpu(sess->s.dev->ib_dev, iu->dma_addr,
 				   iu->size, DMA_FROM_DEVICE);
 	msg = iu->buf;
-	if (unlikely(le16_to_cpu(msg->type) != RTRS_MSG_RKEY_RSP)) {
+	if (le16_to_cpu(msg->type) != RTRS_MSG_RKEY_RSP) {
 		rtrs_err(sess->clt, "rkey response is malformed: type %d\n",
 			  le16_to_cpu(msg->type));
 		goto out;
@@ -551,8 +551,8 @@ static void rtrs_clt_rkey_rsp_done(struct rtrs_clt_con *con, struct ib_wc *wc)
 		goto out;
 
 	rtrs_from_imm(be32_to_cpu(wc->ex.imm_data), &imm_type, &imm_payload);
-	if (likely(imm_type == RTRS_IO_RSP_IMM ||
-		   imm_type == RTRS_IO_RSP_W_INV_IMM)) {
+	if (imm_type == RTRS_IO_RSP_IMM ||
+	    imm_type == RTRS_IO_RSP_W_INV_IMM) {
 		u32 msg_id;
 
 		w_inval = (imm_type == RTRS_IO_RSP_W_INV_IMM);
@@ -605,7 +605,7 @@ static void rtrs_clt_rdma_done(struct ib_cq *cq, struct ib_wc *wc)
 	bool w_inval = false;
 	int err;
 
-	if (unlikely(wc->status != IB_WC_SUCCESS)) {
+	if (wc->status != IB_WC_SUCCESS) {
 		if (wc->status != IB_WC_WR_FLUSH_ERR) {
 			rtrs_err(sess->clt, "RDMA failed: %s\n",
 				  ib_wc_status_msg(wc->status));
@@ -625,8 +625,8 @@ static void rtrs_clt_rdma_done(struct ib_cq *cq, struct ib_wc *wc)
 			return;
 		rtrs_from_imm(be32_to_cpu(wc->ex.imm_data),
 			       &imm_type, &imm_payload);
-		if (likely(imm_type == RTRS_IO_RSP_IMM ||
-			   imm_type == RTRS_IO_RSP_W_INV_IMM)) {
+		if (imm_type == RTRS_IO_RSP_IMM ||
+		    imm_type == RTRS_IO_RSP_W_INV_IMM) {
 			u32 msg_id;
 
 			w_inval = (imm_type == RTRS_IO_RSP_W_INV_IMM);
@@ -657,7 +657,7 @@ static void rtrs_clt_rdma_done(struct ib_cq *cq, struct ib_wc *wc)
 			err = rtrs_post_recv_empty_x2(&con->c, &io_comp_cqe);
 		else
 			err = rtrs_post_recv_empty(&con->c, &io_comp_cqe);
-		if (unlikely(err)) {
+		if (err) {
 			rtrs_err(con->c.sess, "rtrs_post_recv_empty(): %d\n",
 				  err);
 			rtrs_rdma_error_recovery(con);
@@ -680,6 +680,7 @@ static void rtrs_clt_rdma_done(struct ib_cq *cq, struct ib_wc *wc)
 	case IB_WC_RDMA_WRITE:
 		/*
 		 * post_send() RDMA write completions of IO reqs (read/write)
+		 * and hb.
 		 */
 		break;
 
@@ -702,7 +703,7 @@ static int post_recv_io(struct rtrs_clt_con *con, size_t q_size)
 		} else {
 			err = rtrs_post_recv_empty(&con->c, &io_comp_cqe);
 		}
-		if (unlikely(err))
+		if (err)
 			return err;
 	}
 
@@ -727,7 +728,7 @@ static int post_recv_sess(struct rtrs_clt_sess *sess)
 		q_size *= 2;
 
 		err = post_recv_io(to_clt_con(sess->s.con[cid]), q_size);
-		if (unlikely(err)) {
+		if (err) {
 			rtrs_err(sess->clt, "post_recv_io(), err: %d\n", err);
 			return err;
 		}
@@ -788,7 +789,7 @@ static struct rtrs_clt_sess *get_next_path_rr(struct path_it *it)
 
 	ppcpu_path = this_cpu_ptr(clt->pcpu_path);
 	path = rcu_dereference(*ppcpu_path);
-	if (unlikely(!path))
+	if (!path)
 		path = list_first_or_null_rcu(&clt->paths_list,
 					      typeof(*path), s.entry);
 	else
@@ -819,10 +820,10 @@ static struct rtrs_clt_sess *get_next_path_min_inflight(struct path_it *it)
 	int inflight;
 
 	list_for_each_entry_rcu(sess, &clt->paths_list, s.entry) {
-		if (unlikely(READ_ONCE(sess->state) != RTRS_CLT_CONNECTED))
+		if (READ_ONCE(sess->state) != RTRS_CLT_CONNECTED)
 			continue;
 
-		if (unlikely(!list_empty(raw_cpu_ptr(sess->mp_skip_entry))))
+		if (!list_empty(raw_cpu_ptr(sess->mp_skip_entry)))
 			continue;
 
 		inflight = atomic_read(&sess->stats->inflight);
@@ -870,10 +871,10 @@ static struct rtrs_clt_sess *get_next_path_min_latency(struct path_it *it)
 	ktime_t latency;
 
 	list_for_each_entry_rcu(sess, &clt->paths_list, s.entry) {
-		if (unlikely(READ_ONCE(sess->state) != RTRS_CLT_CONNECTED))
+		if (READ_ONCE(sess->state) != RTRS_CLT_CONNECTED)
 			continue;
 
-		if (unlikely(!list_empty(raw_cpu_ptr(sess->mp_skip_entry))))
+		if (!list_empty(raw_cpu_ptr(sess->mp_skip_entry)))
 			continue;
 
 		latency = sess->s.hb_cur_latency;
@@ -963,6 +964,7 @@ static void rtrs_clt_init_req(struct rtrs_clt_io_req *req,
 	req->need_inv_comp = false;
 	req->inv_errno = 0;
 	refcount_set(&req->ref, 1);
+	req->mp_policy = sess->clt->mp_policy;
 
 	iov_iter_kvec(&iter, READ, vec, 1, usr_len);
 	len = _copy_from_iter(req->iu->buf, usr_len, &iter);
@@ -1043,7 +1045,7 @@ static int rtrs_post_rdma_write_sg(struct rtrs_clt_con *con,
 	 * From time to time we have to post signalled sends,
 	 * or send queue will fill up and only QP reset can help.
 	 */
-	flags = atomic_inc_return(&con->io_cnt) % sess->queue_depth ?
+	flags = atomic_inc_return(&con->c.wr_cnt) % sess->s.signal_interval ?
 			0 : IB_SEND_SIGNALED;
 
 	ib_dma_sync_single_for_device(sess->s.dev->ib_dev, req->iu->dma_addr,
@@ -1062,7 +1064,7 @@ static int rtrs_map_sg_fr(struct rtrs_clt_io_req *req, size_t count)
 	nr = ib_map_mr_sg(req->mr, req->sglist, count, NULL, SZ_4K);
 	if (nr < 0)
 		return nr;
-	if (unlikely(nr < req->sg_cnt))
+	if (nr < req->sg_cnt)
 		return -EINVAL;
 	ib_update_fast_reg_key(req->mr, ib_inc_rkey(req->mr->rkey));
 
@@ -1086,7 +1088,7 @@ static int rtrs_clt_write_req(struct rtrs_clt_io_req *req)
 
 	const size_t tsize = sizeof(*msg) + req->data_len + req->usr_len;
 
-	if (unlikely(tsize > sess->chunk_size)) {
+	if (tsize > sess->chunk_size) {
 		rtrs_wrn(s, "Write request failed, size too big %zu > %d\n",
 			  tsize, sess->chunk_size);
 		return -EMSGSIZE;
@@ -1094,7 +1096,7 @@ static int rtrs_clt_write_req(struct rtrs_clt_io_req *req)
 	if (req->sg_cnt) {
 		count = ib_dma_map_sg(sess->s.dev->ib_dev, req->sglist,
 				      req->sg_cnt, req->dir);
-		if (unlikely(!count)) {
+		if (!count) {
 			rtrs_wrn(s, "Write request failed, map failed\n");
 			return -EINVAL;
 		}
@@ -1148,12 +1150,12 @@ static int rtrs_clt_write_req(struct rtrs_clt_io_req *req)
 	ret = rtrs_post_rdma_write_sg(req->con, req, rbuf, fr_en,
 				      req->usr_len + sizeof(*msg),
 				      imm, wr, &inv_wr);
-	if (unlikely(ret)) {
+	if (ret) {
 		rtrs_err_rl(s,
 			    "Write request failed: error=%d path=%s [%s:%u]\n",
 			    ret, kobject_name(&sess->kobj), sess->hca_name,
 			    sess->hca_port);
-		if (sess->clt->mp_policy == MP_POLICY_MIN_INFLIGHT)
+		if (req->mp_policy == MP_POLICY_MIN_INFLIGHT)
 			atomic_dec(&sess->stats->inflight);
 		if (req->sg_cnt)
 			ib_dma_unmap_sg(sess->s.dev->ib_dev, req->sglist,
@@ -1179,7 +1181,7 @@ static int rtrs_clt_read_req(struct rtrs_clt_io_req *req)
 
 	const size_t tsize = sizeof(*msg) + req->data_len + req->usr_len;
 
-	if (unlikely(tsize > sess->chunk_size)) {
+	if (tsize > sess->chunk_size) {
 		rtrs_wrn(s,
 			  "Read request failed, message size is %zu, bigger than CHUNK_SIZE %d\n",
 			  tsize, sess->chunk_size);
@@ -1189,7 +1191,7 @@ static int rtrs_clt_read_req(struct rtrs_clt_io_req *req)
 	if (req->sg_cnt) {
 		count = ib_dma_map_sg(dev->ib_dev, req->sglist, req->sg_cnt,
 				      req->dir);
-		if (unlikely(!count)) {
+		if (!count) {
 			rtrs_wrn(s,
 				  "Read request failed, dma map failed\n");
 			return -EINVAL;
@@ -1254,12 +1256,12 @@ static int rtrs_clt_read_req(struct rtrs_clt_io_req *req)
 
 	ret = rtrs_post_send_rdma(req->con, req, &sess->rbufs[buf_id],
 				   req->data_len, imm, wr);
-	if (unlikely(ret)) {
+	if (ret) {
 		rtrs_err_rl(s,
 			    "Read request failed: error=%d path=%s [%s:%u]\n",
 			    ret, kobject_name(&sess->kobj), sess->hca_name,
 			    sess->hca_port);
-		if (sess->clt->mp_policy == MP_POLICY_MIN_INFLIGHT)
+		if (req->mp_policy == MP_POLICY_MIN_INFLIGHT)
 			atomic_dec(&sess->stats->inflight);
 		req->need_inv = false;
 		if (req->sg_cnt)
@@ -1287,15 +1289,14 @@ static int rtrs_clt_failover_req(struct rtrs_clt *clt,
 	for (path_it_init(&it, clt);
 	     (alive_sess = it.next_path(&it)) && it.i < it.clt->paths_num;
 	     it.i++) {
-		if (unlikely(READ_ONCE(alive_sess->state) !=
-			     RTRS_CLT_CONNECTED))
+		if (READ_ONCE(alive_sess->state) != RTRS_CLT_CONNECTED)
 			continue;
 		req = rtrs_clt_get_copy_req(alive_sess, fail_req);
 		if (req->dir == DMA_TO_DEVICE)
 			err = rtrs_clt_write_req(req);
 		else
 			err = rtrs_clt_read_req(req);
-		if (unlikely(err)) {
+		if (err) {
 			req->in_use = false;
 			continue;
 		}
@@ -1330,7 +1331,7 @@ static void fail_all_outstanding_reqs(struct rtrs_clt_sess *sess)
 		complete_rdma_req(req, -ECONNABORTED, false, true);
 
 		err = rtrs_clt_failover_req(clt, req);
-		if (unlikely(err))
+		if (err)
 			/* Failover failed, notify anyway */
 			req->conf(req->priv, err);
 	}
@@ -1601,7 +1602,8 @@ static int create_con(struct rtrs_clt_sess *sess, unsigned int cid)
 	con->cpu  = (cid ? cid - 1 : 0) % nr_cpu_ids;
 	con->c.cid = cid;
 	con->c.sess = &sess->s;
-	atomic_set(&con->io_cnt, 0);
+	/* Align with srv, init as 1 */
+	atomic_set(&con->c.wr_cnt, 1);
 	mutex_init(&con->con_mutex);
 
 	sess->s.con[cid] = &con->c;
@@ -1678,6 +1680,7 @@ static int create_con_cq_qp(struct rtrs_clt_con *con)
 			      sess->queue_depth * 3 + 1);
 		max_send_sge = 2;
 	}
+	atomic_set(&con->c.sq_wr_avail, max_send_wr);
 	cq_num = max_send_wr + max_recv_wr;
 	/* alloc iu to recv new rkey reply when server reports flags set */
 	if (sess->flags & RTRS_MSG_NEW_RKEY_F || con->c.cid == 0) {
@@ -1841,13 +1844,14 @@ static int rtrs_rdma_conn_established(struct rtrs_clt_con *con,
 		}
 
 		if (!sess->rbufs) {
-			kfree(sess->rbufs);
 			sess->rbufs = kcalloc(queue_depth, sizeof(*sess->rbufs),
 					      GFP_KERNEL);
 			if (!sess->rbufs)
 				return -ENOMEM;
 		}
 		sess->queue_depth = queue_depth;
+		sess->s.signal_interval = min_not_zero(queue_depth,
+						(unsigned short) SERVICE_CON_QUEUE_DEPTH);
 		sess->max_hdr_size = le32_to_cpu(msg->max_hdr_size);
 		sess->max_io_size = le32_to_cpu(msg->max_io_size);
 		sess->flags = le32_to_cpu(msg->flags);
@@ -1958,7 +1962,7 @@ static int rtrs_clt_rdma_cm_handler(struct rdma_cm_id *cm_id,
 		break;
 	case RDMA_CM_EVENT_ESTABLISHED:
 		cm_err = rtrs_rdma_conn_established(con, ev);
-		if (likely(!cm_err)) {
+		if (!cm_err) {
 			/*
 			 * Report success and wake up. Here we abuse state_wq,
 			 * i.e. wake up without state change, but we set cm_err.
@@ -2377,7 +2381,7 @@ static void rtrs_clt_info_req_done(struct ib_cq *cq, struct ib_wc *wc)
 	iu = container_of(wc->wr_cqe, struct rtrs_iu, cqe);
 	rtrs_iu_free(iu, sess->s.dev->ib_dev, 1);
 
-	if (unlikely(wc->status != IB_WC_SUCCESS)) {
+	if (wc->status != IB_WC_SUCCESS) {
 		rtrs_err(sess->clt, "Sess info request send failed: %s\n",
 			  ib_wc_status_msg(wc->status));
 		rtrs_clt_change_state_get_old(sess, RTRS_CLT_CONNECTING_ERR, NULL);
@@ -2394,7 +2398,7 @@ static int process_info_rsp(struct rtrs_clt_sess *sess,
 	int i, sgi;
 
 	sg_cnt = le16_to_cpu(msg->sg_cnt);
-	if (unlikely(!sg_cnt || (sess->queue_depth % sg_cnt))) {
+	if (!sg_cnt || (sess->queue_depth % sg_cnt)) {
 		rtrs_err(sess->clt, "Incorrect sg_cnt %d, is not multiple\n",
 			  sg_cnt);
 		return -EINVAL;
@@ -2404,9 +2408,8 @@ static int process_info_rsp(struct rtrs_clt_sess *sess,
 	 * Check if IB immediate data size is enough to hold the mem_id and
 	 * the offset inside the memory chunk.
 	 */
-	if (unlikely((ilog2(sg_cnt - 1) + 1) +
-		     (ilog2(sess->chunk_size - 1) + 1) >
-		     MAX_IMM_PAYL_BITS)) {
+	if ((ilog2(sg_cnt - 1) + 1) + (ilog2(sess->chunk_size - 1) + 1) >
+	    MAX_IMM_PAYL_BITS) {
 		rtrs_err(sess->clt,
 			  "RDMA immediate size (%db) not enough to encode %d buffers of size %dB\n",
 			  MAX_IMM_PAYL_BITS, sg_cnt, sess->chunk_size);
@@ -2424,7 +2427,7 @@ static int process_info_rsp(struct rtrs_clt_sess *sess,
 
 		total_len += len;
 
-		if (unlikely(!len || (len % sess->chunk_size))) {
+		if (!len || (len % sess->chunk_size)) {
 			rtrs_err(sess->clt, "Incorrect [%d].len %d\n", sgi,
 				  len);
 			return -EINVAL;
@@ -2438,11 +2441,11 @@ static int process_info_rsp(struct rtrs_clt_sess *sess,
 		}
 	}
 	/* Sanity check */
-	if (unlikely(sgi != sg_cnt || i != sess->queue_depth)) {
+	if (sgi != sg_cnt || i != sess->queue_depth) {
 		rtrs_err(sess->clt, "Incorrect sg vector, not fully mapped\n");
 		return -EINVAL;
 	}
-	if (unlikely(total_len != sess->chunk_size * sess->queue_depth)) {
+	if (total_len != sess->chunk_size * sess->queue_depth) {
 		rtrs_err(sess->clt, "Incorrect total_len %d\n", total_len);
 		return -EINVAL;
 	}
@@ -2464,14 +2467,14 @@ static void rtrs_clt_info_rsp_done(struct ib_cq *cq, struct ib_wc *wc)
 
 	WARN_ON(con->c.cid);
 	iu = container_of(wc->wr_cqe, struct rtrs_iu, cqe);
-	if (unlikely(wc->status != IB_WC_SUCCESS)) {
+	if (wc->status != IB_WC_SUCCESS) {
 		rtrs_err(sess->clt, "Sess info response recv failed: %s\n",
 			  ib_wc_status_msg(wc->status));
 		goto out;
 	}
 	WARN_ON(wc->opcode != IB_WC_RECV);
 
-	if (unlikely(wc->byte_len < sizeof(*msg))) {
+	if (wc->byte_len < sizeof(*msg)) {
 		rtrs_err(sess->clt, "Sess info response is malformed: size %d\n",
 			  wc->byte_len);
 		goto out;
@@ -2479,24 +2482,24 @@ static void rtrs_clt_info_rsp_done(struct ib_cq *cq, struct ib_wc *wc)
 	ib_dma_sync_single_for_cpu(sess->s.dev->ib_dev, iu->dma_addr,
 				   iu->size, DMA_FROM_DEVICE);
 	msg = iu->buf;
-	if (unlikely(le16_to_cpu(msg->type) != RTRS_MSG_INFO_RSP)) {
+	if (le16_to_cpu(msg->type) != RTRS_MSG_INFO_RSP) {
 		rtrs_err(sess->clt, "Sess info response is malformed: type %d\n",
 			  le16_to_cpu(msg->type));
 		goto out;
 	}
 	rx_sz  = sizeof(*msg);
 	rx_sz += sizeof(msg->desc[0]) * le16_to_cpu(msg->sg_cnt);
-	if (unlikely(wc->byte_len < rx_sz)) {
+	if (wc->byte_len < rx_sz) {
 		rtrs_err(sess->clt, "Sess info response is malformed: size %d\n",
 			  wc->byte_len);
 		goto out;
 	}
 	err = process_info_rsp(sess, msg);
-	if (unlikely(err))
+	if (err)
 		goto out;
 
 	err = post_recv_sess(sess);
-	if (unlikely(err))
+	if (err)
 		goto out;
 
 	state = RTRS_CLT_CONNECTED;
@@ -2523,13 +2526,13 @@ static int rtrs_send_sess_info(struct rtrs_clt_sess *sess)
 			       rtrs_clt_info_req_done);
 	rx_iu = rtrs_iu_alloc(1, rx_sz, GFP_KERNEL, sess->s.dev->ib_dev,
 			       DMA_FROM_DEVICE, rtrs_clt_info_rsp_done);
-	if (unlikely(!tx_iu || !rx_iu)) {
+	if (!tx_iu || !rx_iu) {
 		err = -ENOMEM;
 		goto out;
 	}
 	/* Prepare for getting info response */
 	err = rtrs_iu_post_recv(&usr_con->c, rx_iu);
-	if (unlikely(err)) {
+	if (err) {
 		rtrs_err(sess->clt, "rtrs_iu_post_recv(), err: %d\n", err);
 		goto out;
 	}
@@ -2544,7 +2547,7 @@ static int rtrs_send_sess_info(struct rtrs_clt_sess *sess)
 
 	/* Send info request */
 	err = rtrs_iu_post_send(&usr_con->c, tx_iu, sizeof(*msg), NULL);
-	if (unlikely(err)) {
+	if (err) {
 		rtrs_err(sess->clt, "rtrs_iu_post_send(), err: %d\n", err);
 		goto out;
 	}
@@ -2555,7 +2558,7 @@ static int rtrs_send_sess_info(struct rtrs_clt_sess *sess)
 					 sess->state != RTRS_CLT_CONNECTING,
 					 msecs_to_jiffies(
 						 RTRS_CONNECT_TIMEOUT_MS));
-	if (unlikely(READ_ONCE(sess->state) != RTRS_CLT_CONNECTED)) {
+	if (READ_ONCE(sess->state) != RTRS_CLT_CONNECTED) {
 		if (READ_ONCE(sess->state) == RTRS_CLT_CONNECTING_ERR)
 			err = -ECONNRESET;
 		else
@@ -2567,7 +2570,7 @@ out:
 		rtrs_iu_free(tx_iu, sess->s.dev->ib_dev, 1);
 	if (rx_iu)
 		rtrs_iu_free(rx_iu, sess->s.dev->ib_dev, 1);
-	if (unlikely(err))
+	if (err)
 		/* If we've never taken async path because of malloc problems */
 		rtrs_clt_change_state_get_old(sess, RTRS_CLT_CONNECTING_ERR, NULL);
 
@@ -2915,7 +2918,7 @@ int rtrs_clt_remove_path_from_sysfs(struct rtrs_clt_sess *sess,
 							&old_state);
 	} while (!changed && old_state != RTRS_CLT_DEAD);
 
-	if (likely(changed)) {
+	if (changed) {
 		rtrs_clt_remove_path_from_arr(sess);
 		rtrs_clt_destroy_sess_files(sess, sysfs_self);
 		kobject_put(&sess->kobj);
@@ -2987,10 +2990,10 @@ int rtrs_clt_request(int dir, struct rtrs_clt_req_ops *ops,
 	rcu_read_lock();
 	for (path_it_init(&it, clt);
 	     (sess = it.next_path(&it)) && it.i < it.clt->paths_num; it.i++) {
-		if (unlikely(READ_ONCE(sess->state) != RTRS_CLT_CONNECTED))
+		if (READ_ONCE(sess->state) != RTRS_CLT_CONNECTED)
 			continue;
 
-		if (unlikely(usr_len + hdr_len > sess->max_hdr_size)) {
+		if (usr_len + hdr_len > sess->max_hdr_size) {
 			rtrs_wrn_rl(sess->clt,
 				     "%s request failed, user message size is %zu and header length %zu, but max size is %u\n",
 				     dir == READ ? "Read" : "Write",
@@ -3005,7 +3008,7 @@ int rtrs_clt_request(int dir, struct rtrs_clt_req_ops *ops,
 			err = rtrs_clt_read_req(req);
 		else
 			err = rtrs_clt_write_req(req);
-		if (unlikely(err)) {
+		if (err) {
 			req->in_use = false;
 			continue;
 		}
@@ -3078,6 +3081,18 @@ int rtrs_clt_create_path_from_sysfs(struct rtrs_clt *clt,
 	if (IS_ERR(sess))
 		return PTR_ERR(sess);
 
+	mutex_lock(&clt->paths_mutex);
+	if (clt->paths_num == 0) {
+		/*
+		 * When all the paths are removed for a session,
+		 * the addition of the first path is like a new session for
+		 * the storage server
+		 */
+		sess->for_new_clt = 1;
+	}
+
+	mutex_unlock(&clt->paths_mutex);
+
 	/*
 	 * It is totally safe to add path in CONNECTING state: coming
 	 * IO will never grab it.  Also it is very important to add
diff --git a/drivers/infiniband/ulp/rtrs/rtrs-clt.h b/drivers/infiniband/ulp/rtrs/rtrs-clt.h
index e276a2dfcf7c..9dc819885ec7 100644
--- a/drivers/infiniband/ulp/rtrs/rtrs-clt.h
+++ b/drivers/infiniband/ulp/rtrs/rtrs-clt.h
@@ -74,7 +74,6 @@ struct rtrs_clt_con {
 	u32			queue_num;
 	unsigned int		cpu;
 	struct mutex		con_mutex;
-	atomic_t		io_cnt;
 	int			cm_err;
 };
 
@@ -102,6 +101,7 @@ struct rtrs_clt_io_req {
 	unsigned int		usr_len;
 	void			*priv;
 	bool			in_use;
+	enum rtrs_mp_policy     mp_policy;
 	struct rtrs_clt_con	*con;
 	struct rtrs_sg_desc	*desc;
 	struct ib_sge		*sge;
@@ -230,10 +230,7 @@ int rtrs_clt_stats_migration_cnt_to_str(struct rtrs_clt_stats *stats, char *buf,
 					 size_t len);
 int rtrs_clt_reset_reconnects_stat(struct rtrs_clt_stats *stats, bool enable);
 int rtrs_clt_stats_reconnects_to_str(struct rtrs_clt_stats *stats, char *buf,
-				      size_t len);
-int rtrs_clt_reset_wc_comp_stats(struct rtrs_clt_stats *stats, bool enable);
-int rtrs_clt_stats_wc_completion_to_str(struct rtrs_clt_stats *stats, char *buf,
-					 size_t len);
+				     size_t len);
 int rtrs_clt_reset_rdma_stats(struct rtrs_clt_stats *stats, bool enable);
 ssize_t rtrs_clt_stats_rdma_to_str(struct rtrs_clt_stats *stats,
 				    char *page, size_t len);
diff --git a/drivers/infiniband/ulp/rtrs/rtrs-pri.h b/drivers/infiniband/ulp/rtrs/rtrs-pri.h
index 36f184a3b676..d12ddfa50747 100644
--- a/drivers/infiniband/ulp/rtrs/rtrs-pri.h
+++ b/drivers/infiniband/ulp/rtrs/rtrs-pri.h
@@ -96,6 +96,8 @@ struct rtrs_con {
 	struct rdma_cm_id	*cm_id;
 	unsigned int		cid;
 	int                     nr_cqe;
+	atomic_t		wr_cnt;
+	atomic_t		sq_wr_avail;
 };
 
 struct rtrs_sess {
@@ -108,6 +110,7 @@ struct rtrs_sess {
 	unsigned int		con_num;
 	unsigned int		irq_con_num;
 	unsigned int		recon_cnt;
+	unsigned int		signal_interval;
 	struct rtrs_ib_dev	*dev;
 	int			dev_ref;
 	struct ib_cqe		*hb_cqe;
@@ -309,9 +312,6 @@ int rtrs_iu_post_rdma_write_imm(struct rtrs_con *con, struct rtrs_iu *iu,
 				struct ib_send_wr *tail);
 
 int rtrs_post_recv_empty(struct rtrs_con *con, struct ib_cqe *cqe);
-int rtrs_post_rdma_write_imm_empty(struct rtrs_con *con, struct ib_cqe *cqe,
-				   u32 imm_data, enum ib_send_flags flags,
-				   struct ib_send_wr *head);
 
 int rtrs_cq_qp_create(struct rtrs_sess *sess, struct rtrs_con *con,
 		      u32 max_send_sge, int cq_vector, int nr_cqe,
diff --git a/drivers/infiniband/ulp/rtrs/rtrs-srv.c b/drivers/infiniband/ulp/rtrs/rtrs-srv.c
index 3df290086169..716ef7b23558 100644
--- a/drivers/infiniband/ulp/rtrs/rtrs-srv.c
+++ b/drivers/infiniband/ulp/rtrs/rtrs-srv.c
@@ -183,7 +183,7 @@ static void rtrs_srv_reg_mr_done(struct ib_cq *cq, struct ib_wc *wc)
 	struct rtrs_sess *s = con->c.sess;
 	struct rtrs_srv_sess *sess = to_srv_sess(s);
 
-	if (unlikely(wc->status != IB_WC_SUCCESS)) {
+	if (wc->status != IB_WC_SUCCESS) {
 		rtrs_err(s, "REG MR failed: %s\n",
 			  ib_wc_status_msg(wc->status));
 		close_sess(sess);
@@ -201,7 +201,6 @@ static int rdma_write_sg(struct rtrs_srv_op *id)
 	struct rtrs_srv_sess *sess = to_srv_sess(s);
 	dma_addr_t dma_addr = sess->dma_addr[id->msg_id];
 	struct rtrs_srv_mr *srv_mr;
-	struct rtrs_srv *srv = sess->srv;
 	struct ib_send_wr inv_wr;
 	struct ib_rdma_wr imm_wr;
 	struct ib_rdma_wr *wr = NULL;
@@ -216,7 +215,7 @@ static int rdma_write_sg(struct rtrs_srv_op *id)
 
 	sg_cnt = le16_to_cpu(id->rd_msg->sg_cnt);
 	need_inval = le16_to_cpu(id->rd_msg->flags) & RTRS_MSG_NEED_INVAL_F;
-	if (unlikely(sg_cnt != 1))
+	if (sg_cnt != 1)
 		return -EINVAL;
 
 	offset = 0;
@@ -229,7 +228,7 @@ static int rdma_write_sg(struct rtrs_srv_op *id)
 	/* WR will fail with length error
 	 * if this is 0
 	 */
-	if (unlikely(plist->length == 0)) {
+	if (plist->length == 0) {
 		rtrs_err(s, "Invalid RDMA-Write sg list length 0\n");
 		return -EINVAL;
 	}
@@ -269,7 +268,7 @@ static int rdma_write_sg(struct rtrs_srv_op *id)
 	 * From time to time we have to post signaled sends,
 	 * or send queue will fill up and only QP reset can help.
 	 */
-	flags = (atomic_inc_return(&id->con->wr_cnt) % srv->queue_depth) ?
+	flags = (atomic_inc_return(&id->con->c.wr_cnt) % s->signal_interval) ?
 		0 : IB_SEND_SIGNALED;
 
 	if (need_inval) {
@@ -322,7 +321,7 @@ static int rdma_write_sg(struct rtrs_srv_op *id)
 				      offset, DMA_BIDIRECTIONAL);
 
 	err = ib_post_send(id->con->c.qp, &id->tx_wr.wr, NULL);
-	if (unlikely(err))
+	if (err)
 		rtrs_err(s,
 			  "Posting RDMA-Write-Request to QP failed, err: %d\n",
 			  err);
@@ -347,7 +346,6 @@ static int send_io_resp_imm(struct rtrs_srv_con *con, struct rtrs_srv_op *id,
 	struct ib_send_wr inv_wr, *wr = NULL;
 	struct ib_rdma_wr imm_wr;
 	struct ib_reg_wr rwr;
-	struct rtrs_srv *srv = sess->srv;
 	struct rtrs_srv_mr *srv_mr;
 	bool need_inval = false;
 	enum ib_send_flags flags;
@@ -363,7 +361,7 @@ static int send_io_resp_imm(struct rtrs_srv_con *con, struct rtrs_srv_op *id,
 		sg_cnt = le16_to_cpu(rd_msg->sg_cnt);
 
 		if (need_inval) {
-			if (likely(sg_cnt)) {
+			if (sg_cnt) {
 				inv_wr.wr_cqe   = &io_comp_cqe;
 				inv_wr.sg_list = NULL;
 				inv_wr.num_sge = 0;
@@ -396,7 +394,7 @@ static int send_io_resp_imm(struct rtrs_srv_con *con, struct rtrs_srv_op *id,
 	 * From time to time we have to post signalled sends,
 	 * or send queue will fill up and only QP reset can help.
 	 */
-	flags = (atomic_inc_return(&con->wr_cnt) % srv->queue_depth) ?
+	flags = (atomic_inc_return(&con->c.wr_cnt) % s->signal_interval) ?
 		0 : IB_SEND_SIGNALED;
 	imm = rtrs_to_io_rsp_imm(id->msg_id, errno, need_inval);
 	imm_wr.wr.next = NULL;
@@ -439,7 +437,7 @@ static int send_io_resp_imm(struct rtrs_srv_con *con, struct rtrs_srv_op *id,
 	imm_wr.wr.ex.imm_data = cpu_to_be32(imm);
 
 	err = ib_post_send(id->con->c.qp, wr, NULL);
-	if (unlikely(err))
+	if (err)
 		rtrs_err_rl(s, "Posting RDMA-Reply to QP failed, err: %d\n",
 			     err);
 
@@ -496,7 +494,7 @@ bool rtrs_srv_resp_rdma(struct rtrs_srv_op *id, int status)
 
 	id->status = status;
 
-	if (unlikely(sess->state != RTRS_SRV_CONNECTED)) {
+	if (sess->state != RTRS_SRV_CONNECTED) {
 		rtrs_err_rl(s,
 			    "Sending I/O response failed,  session %s is disconnected, sess state %s\n",
 			    kobject_name(&sess->kobj),
@@ -508,12 +506,11 @@ bool rtrs_srv_resp_rdma(struct rtrs_srv_op *id, int status)
 
 		ib_update_fast_reg_key(mr->mr, ib_inc_rkey(mr->mr->rkey));
 	}
-	if (unlikely(atomic_sub_return(1,
-				       &con->sq_wr_avail) < 0)) {
+	if (atomic_sub_return(1, &con->c.sq_wr_avail) < 0) {
 		rtrs_err(s, "IB send queue full: sess=%s cid=%d\n",
 			 kobject_name(&sess->kobj),
 			 con->c.cid);
-		atomic_add(1, &con->sq_wr_avail);
+		atomic_add(1, &con->c.sq_wr_avail);
 		spin_lock(&con->rsp_wr_wait_lock);
 		list_add_tail(&id->wait_list, &con->rsp_wr_wait_list);
 		spin_unlock(&con->rsp_wr_wait_lock);
@@ -525,7 +522,7 @@ bool rtrs_srv_resp_rdma(struct rtrs_srv_op *id, int status)
 	else
 		err = rdma_write_sg(id);
 
-	if (unlikely(err)) {
+	if (err) {
 		rtrs_err_rl(s, "IO response failed: %d: sess=%s\n", err,
 			    kobject_name(&sess->kobj));
 		close_sess(sess);
@@ -712,7 +709,7 @@ static void rtrs_srv_info_rsp_done(struct ib_cq *cq, struct ib_wc *wc)
 	iu = container_of(wc->wr_cqe, struct rtrs_iu, cqe);
 	rtrs_iu_free(iu, sess->s.dev->ib_dev, 1);
 
-	if (unlikely(wc->status != IB_WC_SUCCESS)) {
+	if (wc->status != IB_WC_SUCCESS) {
 		rtrs_err(s, "Sess info response send failed: %s\n",
 			  ib_wc_status_msg(wc->status));
 		close_sess(sess);
@@ -801,7 +798,7 @@ static int process_info_req(struct rtrs_srv_con *con,
 	size_t tx_sz;
 
 	err = post_recv_sess(sess);
-	if (unlikely(err)) {
+	if (err) {
 		rtrs_err(s, "post_recv_sess(), err: %d\n", err);
 		return err;
 	}
@@ -814,14 +811,14 @@ static int process_info_req(struct rtrs_srv_con *con,
 	strscpy(sess->s.sessname, msg->sessname, sizeof(sess->s.sessname));
 
 	rwr = kcalloc(sess->mrs_num, sizeof(*rwr), GFP_KERNEL);
-	if (unlikely(!rwr))
+	if (!rwr)
 		return -ENOMEM;
 
 	tx_sz  = sizeof(*rsp);
 	tx_sz += sizeof(rsp->desc[0]) * sess->mrs_num;
 	tx_iu = rtrs_iu_alloc(1, tx_sz, GFP_KERNEL, sess->s.dev->ib_dev,
 			       DMA_TO_DEVICE, rtrs_srv_info_rsp_done);
-	if (unlikely(!tx_iu)) {
+	if (!tx_iu) {
 		err = -ENOMEM;
 		goto rwr_free;
 	}
@@ -853,7 +850,7 @@ static int process_info_req(struct rtrs_srv_con *con,
 	}
 
 	err = rtrs_srv_create_sess_files(sess);
-	if (unlikely(err))
+	if (err)
 		goto iu_free;
 	kobject_get(&sess->kobj);
 	get_device(&sess->srv->dev);
@@ -873,7 +870,7 @@ static int process_info_req(struct rtrs_srv_con *con,
 
 	/* Send info response */
 	err = rtrs_iu_post_send(&con->c, tx_iu, tx_sz, reg_wr);
-	if (unlikely(err)) {
+	if (err) {
 		rtrs_err(s, "rtrs_iu_post_send(), err: %d\n", err);
 iu_free:
 		rtrs_iu_free(tx_iu, sess->s.dev->ib_dev, 1);
@@ -896,14 +893,14 @@ static void rtrs_srv_info_req_done(struct ib_cq *cq, struct ib_wc *wc)
 	WARN_ON(con->c.cid);
 
 	iu = container_of(wc->wr_cqe, struct rtrs_iu, cqe);
-	if (unlikely(wc->status != IB_WC_SUCCESS)) {
+	if (wc->status != IB_WC_SUCCESS) {
 		rtrs_err(s, "Sess info request receive failed: %s\n",
 			  ib_wc_status_msg(wc->status));
 		goto close;
 	}
 	WARN_ON(wc->opcode != IB_WC_RECV);
 
-	if (unlikely(wc->byte_len < sizeof(*msg))) {
+	if (wc->byte_len < sizeof(*msg)) {
 		rtrs_err(s, "Sess info request is malformed: size %d\n",
 			  wc->byte_len);
 		goto close;
@@ -911,13 +908,13 @@ static void rtrs_srv_info_req_done(struct ib_cq *cq, struct ib_wc *wc)
 	ib_dma_sync_single_for_cpu(sess->s.dev->ib_dev, iu->dma_addr,
 				   iu->size, DMA_FROM_DEVICE);
 	msg = iu->buf;
-	if (unlikely(le16_to_cpu(msg->type) != RTRS_MSG_INFO_REQ)) {
+	if (le16_to_cpu(msg->type) != RTRS_MSG_INFO_REQ) {
 		rtrs_err(s, "Sess info request is malformed: type %d\n",
 			  le16_to_cpu(msg->type));
 		goto close;
 	}
 	err = process_info_req(con, msg);
-	if (unlikely(err))
+	if (err)
 		goto close;
 
 out:
@@ -938,11 +935,11 @@ static int post_recv_info_req(struct rtrs_srv_con *con)
 	rx_iu = rtrs_iu_alloc(1, sizeof(struct rtrs_msg_info_req),
 			       GFP_KERNEL, sess->s.dev->ib_dev,
 			       DMA_FROM_DEVICE, rtrs_srv_info_req_done);
-	if (unlikely(!rx_iu))
+	if (!rx_iu)
 		return -ENOMEM;
 	/* Prepare for getting info response */
 	err = rtrs_iu_post_recv(&con->c, rx_iu);
-	if (unlikely(err)) {
+	if (err) {
 		rtrs_err(s, "rtrs_iu_post_recv(), err: %d\n", err);
 		rtrs_iu_free(rx_iu, sess->s.dev->ib_dev, 1);
 		return err;
@@ -957,7 +954,7 @@ static int post_recv_io(struct rtrs_srv_con *con, size_t q_size)
 
 	for (i = 0; i < q_size; i++) {
 		err = rtrs_post_recv_empty(&con->c, &io_comp_cqe);
-		if (unlikely(err))
+		if (err)
 			return err;
 	}
 
@@ -978,7 +975,7 @@ static int post_recv_sess(struct rtrs_srv_sess *sess)
 			q_size = srv->queue_depth;
 
 		err = post_recv_io(to_srv_con(sess->s.con[cid]), q_size);
-		if (unlikely(err)) {
+		if (err) {
 			rtrs_err(s, "post_recv_io(), err: %d\n", err);
 			return err;
 		}
@@ -1001,13 +998,13 @@ static void process_read(struct rtrs_srv_con *con,
 	void *data;
 	int ret;
 
-	if (unlikely(sess->state != RTRS_SRV_CONNECTED)) {
+	if (sess->state != RTRS_SRV_CONNECTED) {
 		rtrs_err_rl(s,
 			     "Processing read request failed,  session is disconnected, sess state %s\n",
 			     rtrs_srv_state_str(sess->state));
 		return;
 	}
-	if (unlikely(msg->sg_cnt != 1 && msg->sg_cnt != 0)) {
+	if (msg->sg_cnt != 1 && msg->sg_cnt != 0) {
 		rtrs_err_rl(s,
 			    "Processing read request failed, invalid message\n");
 		return;
@@ -1025,7 +1022,7 @@ static void process_read(struct rtrs_srv_con *con,
 	ret = ctx->ops.rdma_ev(srv->priv, id, READ, data, data_len,
 			   data + data_len, usr_len);
 
-	if (unlikely(ret)) {
+	if (ret) {
 		rtrs_err_rl(s,
 			     "Processing read request failed, user module cb reported for msg_id %d, err: %d\n",
 			     buf_id, ret);
@@ -1059,7 +1056,7 @@ static void process_write(struct rtrs_srv_con *con,
 	void *data;
 	int ret;
 
-	if (unlikely(sess->state != RTRS_SRV_CONNECTED)) {
+	if (sess->state != RTRS_SRV_CONNECTED) {
 		rtrs_err_rl(s,
 			     "Processing write request failed,  session is disconnected, sess state %s\n",
 			     rtrs_srv_state_str(sess->state));
@@ -1076,8 +1073,8 @@ static void process_write(struct rtrs_srv_con *con,
 	data_len = off - usr_len;
 	data = page_address(srv->chunks[buf_id]);
 	ret = ctx->ops.rdma_ev(srv->priv, id, WRITE, data, data_len,
-			   data + data_len, usr_len);
-	if (unlikely(ret)) {
+			       data + data_len, usr_len);
+	if (ret) {
 		rtrs_err_rl(s,
 			     "Processing write request failed, user module callback reports err: %d\n",
 			     ret);
@@ -1141,7 +1138,7 @@ static void rtrs_srv_inv_rkey_done(struct ib_cq *cq, struct ib_wc *wc)
 	u32 msg_id, off;
 	void *data;
 
-	if (unlikely(wc->status != IB_WC_SUCCESS)) {
+	if (wc->status != IB_WC_SUCCESS) {
 		rtrs_err(s, "Failed IB_WR_LOCAL_INV: %s\n",
 			  ib_wc_status_msg(wc->status));
 		close_sess(sess);
@@ -1198,7 +1195,7 @@ static void rtrs_srv_rdma_done(struct ib_cq *cq, struct ib_wc *wc)
 	u32 imm_type, imm_payload;
 	int err;
 
-	if (unlikely(wc->status != IB_WC_SUCCESS)) {
+	if (wc->status != IB_WC_SUCCESS) {
 		if (wc->status != IB_WC_WR_FLUSH_ERR) {
 			rtrs_err(s,
 				  "%s (wr_cqe: %p, type: %d, vendor_err: 0x%x, len: %u)\n",
@@ -1218,21 +1215,20 @@ static void rtrs_srv_rdma_done(struct ib_cq *cq, struct ib_wc *wc)
 		if (WARN_ON(wc->wr_cqe != &io_comp_cqe))
 			return;
 		err = rtrs_post_recv_empty(&con->c, &io_comp_cqe);
-		if (unlikely(err)) {
+		if (err) {
 			rtrs_err(s, "rtrs_post_recv(), err: %d\n", err);
 			close_sess(sess);
 			break;
 		}
 		rtrs_from_imm(be32_to_cpu(wc->ex.imm_data),
 			       &imm_type, &imm_payload);
-		if (likely(imm_type == RTRS_IO_REQ_IMM)) {
+		if (imm_type == RTRS_IO_REQ_IMM) {
 			u32 msg_id, off;
 			void *data;
 
 			msg_id = imm_payload >> sess->mem_bits;
 			off = imm_payload & ((1 << sess->mem_bits) - 1);
-			if (unlikely(msg_id >= srv->queue_depth ||
-				     off >= max_chunk_size)) {
+			if (msg_id >= srv->queue_depth || off >= max_chunk_size) {
 				rtrs_err(s, "Wrong msg_id %u, off %u\n",
 					  msg_id, off);
 				close_sess(sess);
@@ -1244,7 +1240,7 @@ static void rtrs_srv_rdma_done(struct ib_cq *cq, struct ib_wc *wc)
 				mr->msg_off = off;
 				mr->msg_id = msg_id;
 				err = rtrs_srv_inv_rkey(con, mr);
-				if (unlikely(err)) {
+				if (err) {
 					rtrs_err(s, "rtrs_post_recv(), err: %d\n",
 						  err);
 					close_sess(sess);
@@ -1268,10 +1264,11 @@ static void rtrs_srv_rdma_done(struct ib_cq *cq, struct ib_wc *wc)
 	case IB_WC_SEND:
 		/*
 		 * post_send() RDMA write completions of IO reqs (read/write)
+		 * and hb.
 		 */
-		atomic_add(srv->queue_depth, &con->sq_wr_avail);
+		atomic_add(s->signal_interval, &con->c.sq_wr_avail);
 
-		if (unlikely(!list_empty_careful(&con->rsp_wr_wait_list)))
+		if (!list_empty_careful(&con->rsp_wr_wait_list))
 			rtrs_rdma_process_wr_wait_list(con);
 
 		break;
@@ -1648,7 +1645,7 @@ static int create_con(struct rtrs_srv_sess *sess,
 	con->c.cm_id = cm_id;
 	con->c.sess = &sess->s;
 	con->c.cid = cid;
-	atomic_set(&con->wr_cnt, 1);
+	atomic_set(&con->c.wr_cnt, 1);
 	wr_limit = sess->s.dev->ib_dev->attrs.max_qp_wr;
 
 	if (con->c.cid == 0) {
@@ -1659,6 +1656,8 @@ static int create_con(struct rtrs_srv_sess *sess,
 		max_send_wr = min_t(int, wr_limit,
 				    SERVICE_CON_QUEUE_DEPTH * 2 + 2);
 		max_recv_wr = max_send_wr;
+		s->signal_interval = min_not_zero(srv->queue_depth,
+						  (size_t)SERVICE_CON_QUEUE_DEPTH);
 	} else {
 		/* when always_invlaidate enalbed, we need linv+rinv+mr+imm */
 		if (always_invalidate)
@@ -1679,7 +1678,7 @@ static int create_con(struct rtrs_srv_sess *sess,
 		 */
 	}
 	cq_num = max_send_wr + max_recv_wr;
-	atomic_set(&con->sq_wr_avail, max_send_wr);
+	atomic_set(&con->c.sq_wr_avail, max_send_wr);
 	cq_vector = rtrs_srv_get_next_cq_vector(sess);
 
 	/* TODO: SOFTIRQ can be faster, but be careful with softirq context */
@@ -1894,7 +1893,7 @@ static int rtrs_rdma_connect(struct rdma_cm_id *cm_id,
 	err = create_con(sess, cm_id, cid);
 	if (err) {
 		rtrs_err((&sess->s), "create_con(), error %d\n", err);
-		(void)rtrs_rdma_do_reject(cm_id, err);
+		rtrs_rdma_do_reject(cm_id, err);
 		/*
 		 * Since session has other connections we follow normal way
 		 * through workqueue, but still return an error to tell cma.c
@@ -1905,7 +1904,7 @@ static int rtrs_rdma_connect(struct rdma_cm_id *cm_id,
 	err = rtrs_rdma_do_accept(sess, cm_id);
 	if (err) {
 		rtrs_err((&sess->s), "rtrs_rdma_do_accept(), error %d\n", err);
-		(void)rtrs_rdma_do_reject(cm_id, err);
+		rtrs_rdma_do_reject(cm_id, err);
 		/*
 		 * Since current connection was successfully added to the
 		 * session we follow normal way through workqueue to close the
diff --git a/drivers/infiniband/ulp/rtrs/rtrs-srv.h b/drivers/infiniband/ulp/rtrs/rtrs-srv.h
index f8da2e3f0bda..9d8d2a91a235 100644
--- a/drivers/infiniband/ulp/rtrs/rtrs-srv.h
+++ b/drivers/infiniband/ulp/rtrs/rtrs-srv.h
@@ -42,8 +42,6 @@ struct rtrs_srv_stats {
 
 struct rtrs_srv_con {
 	struct rtrs_con		c;
-	atomic_t		wr_cnt;
-	atomic_t		sq_wr_avail;
 	struct list_head	rsp_wr_wait_list;
 	spinlock_t		rsp_wr_wait_lock;
 };
@@ -140,10 +138,6 @@ static inline void rtrs_srv_update_rdma_stats(struct rtrs_srv_stats *s,
 int rtrs_srv_reset_rdma_stats(struct rtrs_srv_stats *stats, bool enable);
 ssize_t rtrs_srv_stats_rdma_to_str(struct rtrs_srv_stats *stats,
 				    char *page, size_t len);
-int rtrs_srv_reset_wc_completion_stats(struct rtrs_srv_stats *stats,
-					bool enable);
-int rtrs_srv_stats_wc_completion_to_str(struct rtrs_srv_stats *stats, char *buf,
-					 size_t len);
 int rtrs_srv_reset_all_stats(struct rtrs_srv_stats *stats, bool enable);
 ssize_t rtrs_srv_reset_all_help(struct rtrs_srv_stats *stats,
 				 char *page, size_t len);
diff --git a/drivers/infiniband/ulp/rtrs/rtrs.c b/drivers/infiniband/ulp/rtrs/rtrs.c
index 61919ebd92b2..ca542e477d38 100644
--- a/drivers/infiniband/ulp/rtrs/rtrs.c
+++ b/drivers/infiniband/ulp/rtrs/rtrs.c
@@ -182,22 +182,28 @@ int rtrs_iu_post_rdma_write_imm(struct rtrs_con *con, struct rtrs_iu *iu,
 }
 EXPORT_SYMBOL_GPL(rtrs_iu_post_rdma_write_imm);
 
-int rtrs_post_rdma_write_imm_empty(struct rtrs_con *con, struct ib_cqe *cqe,
-				    u32 imm_data, enum ib_send_flags flags,
-				    struct ib_send_wr *head)
+static int rtrs_post_rdma_write_imm_empty(struct rtrs_con *con,
+					  struct ib_cqe *cqe,
+					  u32 imm_data,
+					  struct ib_send_wr *head)
 {
 	struct ib_rdma_wr wr;
+	struct rtrs_sess *sess = con->sess;
+	enum ib_send_flags sflags;
+
+	atomic_dec_if_positive(&con->sq_wr_avail);
+	sflags = (atomic_inc_return(&con->wr_cnt) % sess->signal_interval) ?
+		0 : IB_SEND_SIGNALED;
 
 	wr = (struct ib_rdma_wr) {
 		.wr.wr_cqe	= cqe,
-		.wr.send_flags	= flags,
+		.wr.send_flags	= sflags,
 		.wr.opcode	= IB_WR_RDMA_WRITE_WITH_IMM,
 		.wr.ex.imm_data	= cpu_to_be32(imm_data),
 	};
 
 	return rtrs_post_send(con->qp, head, &wr.wr, NULL);
 }
-EXPORT_SYMBOL_GPL(rtrs_post_rdma_write_imm_empty);
 
 static void qp_event_handler(struct ib_event *ev, void *ctx)
 {
@@ -314,8 +320,9 @@ void rtrs_send_hb_ack(struct rtrs_sess *sess)
 
 	imm = rtrs_to_imm(RTRS_HB_ACK_IMM, 0);
 	err = rtrs_post_rdma_write_imm_empty(usr_con, sess->hb_cqe, imm,
-					     0, NULL);
+					     NULL);
 	if (err) {
+		rtrs_err(sess, "send HB ACK failed, errno: %d\n", err);
 		sess->hb_err_handler(usr_con);
 		return;
 	}
@@ -333,6 +340,7 @@ static void hb_work(struct work_struct *work)
 	usr_con = sess->con[0];
 
 	if (sess->hb_missed_cnt > sess->hb_missed_max) {
+		rtrs_err(sess, "HB missed max reached.\n");
 		sess->hb_err_handler(usr_con);
 		return;
 	}
@@ -346,8 +354,9 @@ static void hb_work(struct work_struct *work)
 
 	imm = rtrs_to_imm(RTRS_HB_MSG_IMM, 0);
 	err = rtrs_post_rdma_write_imm_empty(usr_con, sess->hb_cqe, imm,
-					     0, NULL);
+					     NULL);
 	if (err) {
+		rtrs_err(sess, "HB send failed, errno: %d\n", err);
 		sess->hb_err_handler(usr_con);
 		return;
 	}