Merge branch 'perf/urgent' into perf/core, to resolve conflicts

Conflicts:
	tools/perf/builtin-kmem.c

Signed-off-by: Ingo Molnar <mingo@kernel.org>

17 files changed, 229 insertions, 135 deletions

diff --git a/drivers/infiniband/hw/cxgb4/cm.c b/drivers/infiniband/hw/cxgb4/cm.c
index 57176dd..bb95a6c 100644
--- a/drivers/infiniband/hw/cxgb4/cm.c
+++ b/drivers/infiniband/hw/cxgb4/cm.c
@@ -583,6 +583,22 @@ static void c4iw_record_pm_msg(struct c4iw_ep *ep,
 		sizeof(ep->com.mapped_remote_addr));
 }
 
+static int get_remote_addr(struct c4iw_ep *ep)
+{
+	int ret;
+
+	print_addr(&ep->com, __func__, "get_remote_addr");
+
+	ret = iwpm_get_remote_info(&ep->com.mapped_local_addr,
+				   &ep->com.mapped_remote_addr,
+				   &ep->com.remote_addr, RDMA_NL_C4IW);
+	if (ret)
+		pr_info(MOD "Unable to find remote peer addr info - err %d\n",
+			ret);
+
+	return ret;
+}
+
 static void best_mtu(const unsigned short *mtus, unsigned short mtu,
 		     unsigned int *idx, int use_ts, int ipv6)
 {
@@ -675,7 +691,7 @@ static int send_connect(struct c4iw_ep *ep)
 	if (is_t5(ep->com.dev->rdev.lldi.adapter_type)) {
 		opt2 |= T5_OPT_2_VALID_F;
 		opt2 |= CONG_CNTRL_V(CONG_ALG_TAHOE);
-		opt2 |= CONG_CNTRL_VALID; /* OPT_2_ISS for T5 */
+		opt2 |= T5_ISS_F;
 	}
 	t4_set_arp_err_handler(skb, ep, act_open_req_arp_failure);
 
@@ -2042,9 +2058,12 @@ static int act_open_rpl(struct c4iw_dev *dev, struct sk_buff *skb)
 	     status, status2errno(status));
 
 	if (is_neg_adv(status)) {
-		dev_warn(&dev->rdev.lldi.pdev->dev,
-			 "Connection problems for atid %u status %u (%s)\n",
-			 atid, status, neg_adv_str(status));
+		PDBG("%s Connection problems for atid %u status %u (%s)\n",
+		     __func__, atid, status, neg_adv_str(status));
+		ep->stats.connect_neg_adv++;
+		mutex_lock(&dev->rdev.stats.lock);
+		dev->rdev.stats.neg_adv++;
+		mutex_unlock(&dev->rdev.stats.lock);
 		return 0;
 	}
 
@@ -2214,7 +2233,7 @@ static void accept_cr(struct c4iw_ep *ep, struct sk_buff *skb,
 		u32 isn = (prandom_u32() & ~7UL) - 1;
 		opt2 |= T5_OPT_2_VALID_F;
 		opt2 |= CONG_CNTRL_V(CONG_ALG_TAHOE);
-		opt2 |= CONG_CNTRL_VALID; /* OPT_2_ISS for T5 */
+		opt2 |= T5_ISS_F;
 		rpl5 = (void *)rpl;
 		memset(&rpl5->iss, 0, roundup(sizeof(*rpl5)-sizeof(*rpl), 16));
 		if (peer2peer)
@@ -2352,27 +2371,57 @@ static int pass_accept_req(struct c4iw_dev *dev, struct sk_buff *skb)
 	state_set(&child_ep->com, CONNECTING);
 	child_ep->com.dev = dev;
 	child_ep->com.cm_id = NULL;
+
+	/*
+	 * The mapped_local and mapped_remote addresses get setup with
+	 * the actual 4-tuple.  The local address will be based on the
+	 * actual local address of the connection, but on the port number
+	 * of the parent listening endpoint.  The remote address is
+	 * setup based on a query to the IWPM since we don't know what it
+	 * originally was before mapping.  If no mapping was done, then
+	 * mapped_remote == remote, and mapped_local == local.
+	 */
 	if (iptype == 4) {
 		struct sockaddr_in *sin = (struct sockaddr_in *)
-			&child_ep->com.local_addr;
+			&child_ep->com.mapped_local_addr;
+
 		sin->sin_family = PF_INET;
 		sin->sin_port = local_port;
 		sin->sin_addr.s_addr = *(__be32 *)local_ip;
-		sin = (struct sockaddr_in *)&child_ep->com.remote_addr;
+
+		sin = (struct sockaddr_in *)&child_ep->com.local_addr;
+		sin->sin_family = PF_INET;
+		sin->sin_port = ((struct sockaddr_in *)
+				 &parent_ep->com.local_addr)->sin_port;
+		sin->sin_addr.s_addr = *(__be32 *)local_ip;
+
+		sin = (struct sockaddr_in *)&child_ep->com.mapped_remote_addr;
 		sin->sin_family = PF_INET;
 		sin->sin_port = peer_port;
 		sin->sin_addr.s_addr = *(__be32 *)peer_ip;
 	} else {
 		struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *)
-			&child_ep->com.local_addr;
+			&child_ep->com.mapped_local_addr;
+
 		sin6->sin6_family = PF_INET6;
 		sin6->sin6_port = local_port;
 		memcpy(sin6->sin6_addr.s6_addr, local_ip, 16);
-		sin6 = (struct sockaddr_in6 *)&child_ep->com.remote_addr;
+
+		sin6 = (struct sockaddr_in6 *)&child_ep->com.local_addr;
+		sin6->sin6_family = PF_INET6;
+		sin6->sin6_port = ((struct sockaddr_in6 *)
+				   &parent_ep->com.local_addr)->sin6_port;
+		memcpy(sin6->sin6_addr.s6_addr, local_ip, 16);
+
+		sin6 = (struct sockaddr_in6 *)&child_ep->com.mapped_remote_addr;
 		sin6->sin6_family = PF_INET6;
 		sin6->sin6_port = peer_port;
 		memcpy(sin6->sin6_addr.s6_addr, peer_ip, 16);
 	}
+	memcpy(&child_ep->com.remote_addr, &child_ep->com.mapped_remote_addr,
+	       sizeof(child_ep->com.remote_addr));
+	get_remote_addr(child_ep);
+
 	c4iw_get_ep(&parent_ep->com);
 	child_ep->parent_ep = parent_ep;
 	child_ep->tos = PASS_OPEN_TOS_G(ntohl(req->tos_stid));
@@ -2520,9 +2569,13 @@ static int peer_abort(struct c4iw_dev *dev, struct sk_buff *skb)
 
 	ep = lookup_tid(t, tid);
 	if (is_neg_adv(req->status)) {
-		dev_warn(&dev->rdev.lldi.pdev->dev,
-			 "Negative advice on abort - tid %u status %d (%s)\n",
-			 ep->hwtid, req->status, neg_adv_str(req->status));
+		PDBG("%s Negative advice on abort- tid %u status %d (%s)\n",
+		     __func__, ep->hwtid, req->status,
+		     neg_adv_str(req->status));
+		ep->stats.abort_neg_adv++;
+		mutex_lock(&dev->rdev.stats.lock);
+		dev->rdev.stats.neg_adv++;
+		mutex_unlock(&dev->rdev.stats.lock);
 		return 0;
 	}
 	PDBG("%s ep %p tid %u state %u\n", __func__, ep, ep->hwtid,
@@ -3571,7 +3624,7 @@ static void send_fw_pass_open_req(struct c4iw_dev *dev, struct sk_buff *skb,
 	 * TP will ignore any value > 0 for MSS index.
 	 */
 	req->tcb.opt0 = cpu_to_be64(MSS_IDX_V(0xF));
-	req->cookie = (unsigned long)skb;
+	req->cookie = (uintptr_t)skb;
 
 	set_wr_txq(req_skb, CPL_PRIORITY_CONTROL, port_id);
 	ret = cxgb4_ofld_send(dev->rdev.lldi.ports[0], req_skb);
@@ -3931,9 +3984,11 @@ static int peer_abort_intr(struct c4iw_dev *dev, struct sk_buff *skb)
 		return 0;
 	}
 	if (is_neg_adv(req->status)) {
-		dev_warn(&dev->rdev.lldi.pdev->dev,
-			 "Negative advice on abort - tid %u status %d (%s)\n",
-			 ep->hwtid, req->status, neg_adv_str(req->status));
+		PDBG("%s Negative advice on abort- tid %u status %d (%s)\n",
+		     __func__, ep->hwtid, req->status,
+		     neg_adv_str(req->status));
+		ep->stats.abort_neg_adv++;
+		dev->rdev.stats.neg_adv++;
 		kfree_skb(skb);
 		return 0;
 	}
diff --git a/drivers/infiniband/hw/cxgb4/cq.c b/drivers/infiniband/hw/cxgb4/cq.c
index ab7692a..68ddb37 100644
--- a/drivers/infiniband/hw/cxgb4/cq.c
+++ b/drivers/infiniband/hw/cxgb4/cq.c
@@ -55,7 +55,7 @@ static int destroy_cq(struct c4iw_rdev *rdev, struct t4_cq *cq,
 			FW_RI_RES_WR_NRES_V(1) |
 			FW_WR_COMPL_F);
 	res_wr->len16_pkd = cpu_to_be32(DIV_ROUND_UP(wr_len, 16));
-	res_wr->cookie = (unsigned long) &wr_wait;
+	res_wr->cookie = (uintptr_t)&wr_wait;
 	res = res_wr->res;
 	res->u.cq.restype = FW_RI_RES_TYPE_CQ;
 	res->u.cq.op = FW_RI_RES_OP_RESET;
@@ -125,7 +125,7 @@ static int create_cq(struct c4iw_rdev *rdev, struct t4_cq *cq,
 			FW_RI_RES_WR_NRES_V(1) |
 			FW_WR_COMPL_F);
 	res_wr->len16_pkd = cpu_to_be32(DIV_ROUND_UP(wr_len, 16));
-	res_wr->cookie = (unsigned long) &wr_wait;
+	res_wr->cookie = (uintptr_t)&wr_wait;
 	res = res_wr->res;
 	res->u.cq.restype = FW_RI_RES_TYPE_CQ;
 	res->u.cq.op = FW_RI_RES_OP_WRITE;
@@ -156,12 +156,19 @@ static int create_cq(struct c4iw_rdev *rdev, struct t4_cq *cq,
 		goto err4;
 
 	cq->gen = 1;
-	cq->gts = rdev->lldi.gts_reg;
 	cq->rdev = rdev;
 	if (user) {
-		cq->ugts = (u64)pci_resource_start(rdev->lldi.pdev, 2) +
-					(cq->cqid << rdev->cqshift);
-		cq->ugts &= PAGE_MASK;
+		u32 off = (cq->cqid << rdev->cqshift) & PAGE_MASK;
+
+		cq->ugts = (u64)rdev->bar2_pa + off;
+	} else if (is_t4(rdev->lldi.adapter_type)) {
+		cq->gts = rdev->lldi.gts_reg;
+		cq->qid_mask = -1U;
+	} else {
+		u32 off = ((cq->cqid << rdev->cqshift) & PAGE_MASK) + 12;
+
+		cq->gts = rdev->bar2_kva + off;
+		cq->qid_mask = rdev->qpmask;
 	}
 	return 0;
 err4:
@@ -970,8 +977,7 @@ struct ib_cq *c4iw_create_cq(struct ib_device *ibdev, int entries,
 	}
 	PDBG("%s cqid 0x%0x chp %p size %u memsize %zu, dma_addr 0x%0llx\n",
 	     __func__, chp->cq.cqid, chp, chp->cq.size,
-	     chp->cq.memsize,
-	     (unsigned long long) chp->cq.dma_addr);
+	     chp->cq.memsize, (unsigned long long) chp->cq.dma_addr);
 	return &chp->ibcq;
 err5:
 	kfree(mm2);
diff --git a/drivers/infiniband/hw/cxgb4/device.c b/drivers/infiniband/hw/cxgb4/device.c
index 8fb295e..cf54d69 100644
--- a/drivers/infiniband/hw/cxgb4/device.c
+++ b/drivers/infiniband/hw/cxgb4/device.c
@@ -93,6 +93,7 @@ static struct ibnl_client_cbs c4iw_nl_cb_table[] = {
 	[RDMA_NL_IWPM_ADD_MAPPING] = {.dump = iwpm_add_mapping_cb},
 	[RDMA_NL_IWPM_QUERY_MAPPING] = {.dump = iwpm_add_and_query_mapping_cb},
 	[RDMA_NL_IWPM_HANDLE_ERR] = {.dump = iwpm_mapping_error_cb},
+	[RDMA_NL_IWPM_REMOTE_INFO] = {.dump = iwpm_remote_info_cb},
 	[RDMA_NL_IWPM_MAPINFO] = {.dump = iwpm_mapping_info_cb},
 	[RDMA_NL_IWPM_MAPINFO_NUM] = {.dump = iwpm_ack_mapping_info_cb}
 };
@@ -151,7 +152,7 @@ static int wr_log_show(struct seq_file *seq, void *v)
 	int prev_ts_set = 0;
 	int idx, end;
 
-#define ts2ns(ts) div64_ul((ts) * dev->rdev.lldi.cclk_ps, 1000)
+#define ts2ns(ts) div64_u64((ts) * dev->rdev.lldi.cclk_ps, 1000)
 
 	idx = atomic_read(&dev->rdev.wr_log_idx) &
 		(dev->rdev.wr_log_size - 1);
@@ -489,6 +490,7 @@ static int stats_show(struct seq_file *seq, void *v)
 		   dev->rdev.stats.act_ofld_conn_fails);
 	seq_printf(seq, "PAS_OFLD_CONN_FAILS: %10llu\n",
 		   dev->rdev.stats.pas_ofld_conn_fails);
+	seq_printf(seq, "NEG_ADV_RCVD: %10llu\n", dev->rdev.stats.neg_adv);
 	seq_printf(seq, "AVAILABLE IRD: %10u\n", dev->avail_ird);
 	return 0;
 }
@@ -560,10 +562,13 @@ static int dump_ep(int id, void *p, void *data)
 		cc = snprintf(epd->buf + epd->pos, space,
 			      "ep %p cm_id %p qp %p state %d flags 0x%lx "
 			      "history 0x%lx hwtid %d atid %d "
+			      "conn_na %u abort_na %u "
 			      "%pI4:%d/%d <-> %pI4:%d/%d\n",
 			      ep, ep->com.cm_id, ep->com.qp,
 			      (int)ep->com.state, ep->com.flags,
 			      ep->com.history, ep->hwtid, ep->atid,
+			      ep->stats.connect_neg_adv,
+			      ep->stats.abort_neg_adv,
 			      &lsin->sin_addr, ntohs(lsin->sin_port),
 			      ntohs(mapped_lsin->sin_port),
 			      &rsin->sin_addr, ntohs(rsin->sin_port),
@@ -581,10 +586,13 @@ static int dump_ep(int id, void *p, void *data)
 		cc = snprintf(epd->buf + epd->pos, space,
 			      "ep %p cm_id %p qp %p state %d flags 0x%lx "
 			      "history 0x%lx hwtid %d atid %d "
+			      "conn_na %u abort_na %u "
 			      "%pI6:%d/%d <-> %pI6:%d/%d\n",
 			      ep, ep->com.cm_id, ep->com.qp,
 			      (int)ep->com.state, ep->com.flags,
 			      ep->com.history, ep->hwtid, ep->atid,
+			      ep->stats.connect_neg_adv,
+			      ep->stats.abort_neg_adv,
 			      &lsin6->sin6_addr, ntohs(lsin6->sin6_port),
 			      ntohs(mapped_lsin6->sin6_port),
 			      &rsin6->sin6_addr, ntohs(rsin6->sin6_port),
@@ -765,6 +773,29 @@ static int c4iw_rdev_open(struct c4iw_rdev *rdev)
 	c4iw_init_dev_ucontext(rdev, &rdev->uctx);
 
 	/*
+	 * This implementation assumes udb_density == ucq_density!  Eventually
+	 * we might need to support this but for now fail the open. Also the
+	 * cqid and qpid range must match for now.
+	 */
+	if (rdev->lldi.udb_density != rdev->lldi.ucq_density) {
+		pr_err(MOD "%s: unsupported udb/ucq densities %u/%u\n",
+		       pci_name(rdev->lldi.pdev), rdev->lldi.udb_density,
+		       rdev->lldi.ucq_density);
+		err = -EINVAL;
+		goto err1;
+	}
+	if (rdev->lldi.vr->qp.start != rdev->lldi.vr->cq.start ||
+	    rdev->lldi.vr->qp.size != rdev->lldi.vr->cq.size) {
+		pr_err(MOD "%s: unsupported qp and cq id ranges "
+		       "qp start %u size %u cq start %u size %u\n",
+		       pci_name(rdev->lldi.pdev), rdev->lldi.vr->qp.start,
+		       rdev->lldi.vr->qp.size, rdev->lldi.vr->cq.size,
+		       rdev->lldi.vr->cq.size);
+		err = -EINVAL;
+		goto err1;
+	}
+
+	/*
 	 * qpshift is the number of bits to shift the qpid left in order
 	 * to get the correct address of the doorbell for that qp.
 	 */
@@ -784,10 +815,10 @@ static int c4iw_rdev_open(struct c4iw_rdev *rdev)
 	     rdev->lldi.vr->qp.size,
 	     rdev->lldi.vr->cq.start,
 	     rdev->lldi.vr->cq.size);
-	PDBG("udb len 0x%x udb base %llx db_reg %p gts_reg %p qpshift %lu "
+	PDBG("udb len 0x%x udb base %p db_reg %p gts_reg %p qpshift %lu "
 	     "qpmask 0x%x cqshift %lu cqmask 0x%x\n",
 	     (unsigned)pci_resource_len(rdev->lldi.pdev, 2),
-	     (u64)pci_resource_start(rdev->lldi.pdev, 2),
+	     (void *)pci_resource_start(rdev->lldi.pdev, 2),
 	     rdev->lldi.db_reg,
 	     rdev->lldi.gts_reg,
 	     rdev->qpshift, rdev->qpmask,
diff --git a/drivers/infiniband/hw/cxgb4/iw_cxgb4.h b/drivers/infiniband/hw/cxgb4/iw_cxgb4.h
index d87e165..97bb555 100644
--- a/drivers/infiniband/hw/cxgb4/iw_cxgb4.h
+++ b/drivers/infiniband/hw/cxgb4/iw_cxgb4.h
@@ -137,6 +137,7 @@ struct c4iw_stats {
 	u64  tcam_full;
 	u64  act_ofld_conn_fails;
 	u64  pas_ofld_conn_fails;
+	u64  neg_adv;
 };
 
 struct c4iw_hw_queue {
@@ -814,6 +815,11 @@ struct c4iw_listen_ep {
 	int backlog;
 };
 
+struct c4iw_ep_stats {
+	unsigned connect_neg_adv;
+	unsigned abort_neg_adv;
+};
+
 struct c4iw_ep {
 	struct c4iw_ep_common com;
 	struct c4iw_ep *parent_ep;
@@ -846,6 +852,7 @@ struct c4iw_ep {
 	unsigned int retry_count;
 	int snd_win;
 	int rcv_win;
+	struct c4iw_ep_stats stats;
 };
 
 static inline void print_addr(struct c4iw_ep_common *epc, const char *func,
diff --git a/drivers/infiniband/hw/cxgb4/mem.c b/drivers/infiniband/hw/cxgb4/mem.c
index 3ef0cf9..cff815b 100644
--- a/drivers/infiniband/hw/cxgb4/mem.c
+++ b/drivers/infiniband/hw/cxgb4/mem.c
@@ -144,7 +144,7 @@ static int _c4iw_write_mem_inline(struct c4iw_rdev *rdev, u32 addr, u32 len,
 		if (i == (num_wqe-1)) {
 			req->wr.wr_hi = cpu_to_be32(FW_WR_OP_V(FW_ULPTX_WR) |
 						    FW_WR_COMPL_F);
-			req->wr.wr_lo = (__force __be64)(unsigned long) &wr_wait;
+			req->wr.wr_lo = (__force __be64)&wr_wait;
 		} else
 			req->wr.wr_hi = cpu_to_be32(FW_WR_OP_V(FW_ULPTX_WR));
 		req->wr.wr_mid = cpu_to_be32(
@@ -676,12 +676,12 @@ struct ib_mr *c4iw_get_dma_mr(struct ib_pd *pd, int acc)
 	mhp->attr.zbva = 0;
 	mhp->attr.va_fbo = 0;
 	mhp->attr.page_size = 0;
-	mhp->attr.len = ~0UL;
+	mhp->attr.len = ~0ULL;
 	mhp->attr.pbl_size = 0;
 
 	ret = write_tpt_entry(&rhp->rdev, 0, &stag, 1, php->pdid,
 			      FW_RI_STAG_NSMR, mhp->attr.perms,
-			      mhp->attr.mw_bind_enable, 0, 0, ~0UL, 0, 0, 0);
+			      mhp->attr.mw_bind_enable, 0, 0, ~0ULL, 0, 0, 0);
 	if (ret)
 		goto err1;
 
diff --git a/drivers/infiniband/hw/cxgb4/qp.c b/drivers/infiniband/hw/cxgb4/qp.c
index 15cae5a..389ced3 100644
--- a/drivers/infiniband/hw/cxgb4/qp.c
+++ b/drivers/infiniband/hw/cxgb4/qp.c
@@ -275,7 +275,7 @@ static int create_qp(struct c4iw_rdev *rdev, struct t4_wq *wq,
 			FW_RI_RES_WR_NRES_V(2) |
 			FW_WR_COMPL_F);
 	res_wr->len16_pkd = cpu_to_be32(DIV_ROUND_UP(wr_len, 16));
-	res_wr->cookie = (unsigned long) &wr_wait;
+	res_wr->cookie = (uintptr_t)&wr_wait;
 	res = res_wr->res;
 	res->u.sqrq.restype = FW_RI_RES_TYPE_SQ;
 	res->u.sqrq.op = FW_RI_RES_OP_WRITE;
@@ -1209,7 +1209,7 @@ static int rdma_fini(struct c4iw_dev *rhp, struct c4iw_qp *qhp,
 	wqe->flowid_len16 = cpu_to_be32(
 		FW_WR_FLOWID_V(ep->hwtid) |
 		FW_WR_LEN16_V(DIV_ROUND_UP(sizeof(*wqe), 16)));
-	wqe->cookie = (unsigned long) &ep->com.wr_wait;
+	wqe->cookie = (uintptr_t)&ep->com.wr_wait;
 
 	wqe->u.fini.type = FW_RI_TYPE_FINI;
 	ret = c4iw_ofld_send(&rhp->rdev, skb);
@@ -1279,7 +1279,7 @@ static int rdma_init(struct c4iw_dev *rhp, struct c4iw_qp *qhp)
 		FW_WR_FLOWID_V(qhp->ep->hwtid) |
 		FW_WR_LEN16_V(DIV_ROUND_UP(sizeof(*wqe), 16)));
 
-	wqe->cookie = (unsigned long) &qhp->ep->com.wr_wait;
+	wqe->cookie = (uintptr_t)&qhp->ep->com.wr_wait;
 
 	wqe->u.init.type = FW_RI_TYPE_INIT;
 	wqe->u.init.mpareqbit_p2ptype =
@@ -1766,11 +1766,11 @@ struct ib_qp *c4iw_create_qp(struct ib_pd *pd, struct ib_qp_init_attr *attrs,
 		mm2->len = PAGE_ALIGN(qhp->wq.rq.memsize);
 		insert_mmap(ucontext, mm2);
 		mm3->key = uresp.sq_db_gts_key;
-		mm3->addr = (__force unsigned long) qhp->wq.sq.udb;
+		mm3->addr = (__force unsigned long)qhp->wq.sq.udb;
 		mm3->len = PAGE_SIZE;
 		insert_mmap(ucontext, mm3);
 		mm4->key = uresp.rq_db_gts_key;
-		mm4->addr = (__force unsigned long) qhp->wq.rq.udb;
+		mm4->addr = (__force unsigned long)qhp->wq.rq.udb;
 		mm4->len = PAGE_SIZE;
 		insert_mmap(ucontext, mm4);
 		if (mm5) {
diff --git a/drivers/infiniband/hw/cxgb4/t4.h b/drivers/infiniband/hw/cxgb4/t4.h
index 871cdca..7f2a6c2 100644
--- a/drivers/infiniband/hw/cxgb4/t4.h
+++ b/drivers/infiniband/hw/cxgb4/t4.h
@@ -539,6 +539,7 @@ struct t4_cq {
 	size_t memsize;
 	__be64 bits_type_ts;
 	u32 cqid;
+	u32 qid_mask;
 	int vector;
 	u16 size; /* including status page */
 	u16 cidx;
@@ -563,12 +564,12 @@ static inline int t4_arm_cq(struct t4_cq *cq, int se)
 	set_bit(CQ_ARMED, &cq->flags);
 	while (cq->cidx_inc > CIDXINC_M) {
 		val = SEINTARM_V(0) | CIDXINC_V(CIDXINC_M) | TIMERREG_V(7) |
-		      INGRESSQID_V(cq->cqid);
+		      INGRESSQID_V(cq->cqid & cq->qid_mask);
 		writel(val, cq->gts);
 		cq->cidx_inc -= CIDXINC_M;
 	}
 	val = SEINTARM_V(se) | CIDXINC_V(cq->cidx_inc) | TIMERREG_V(6) |
-	      INGRESSQID_V(cq->cqid);
+	      INGRESSQID_V(cq->cqid & cq->qid_mask);
 	writel(val, cq->gts);
 	cq->cidx_inc = 0;
 	return 0;
@@ -601,7 +602,7 @@ static inline void t4_hwcq_consume(struct t4_cq *cq)
 		u32 val;
 
 		val = SEINTARM_V(0) | CIDXINC_V(cq->cidx_inc) | TIMERREG_V(7) |
-		      INGRESSQID_V(cq->cqid);
+		      INGRESSQID_V(cq->cqid & cq->qid_mask);
 		writel(val, cq->gts);
 		cq->cidx_inc = 0;
 	}
diff --git a/drivers/infiniband/hw/cxgb4/t4fw_ri_api.h b/drivers/infiniband/hw/cxgb4/t4fw_ri_api.h
index 5e53327..343e8daf 100644
--- a/drivers/infiniband/hw/cxgb4/t4fw_ri_api.h
+++ b/drivers/infiniband/hw/cxgb4/t4fw_ri_api.h
@@ -848,6 +848,8 @@ enum {                     /* TCP congestion control algorithms */
 #define CONG_CNTRL_V(x) ((x) << CONG_CNTRL_S)
 #define CONG_CNTRL_G(x) (((x) >> CONG_CNTRL_S) & CONG_CNTRL_M)
 
-#define CONG_CNTRL_VALID   (1 << 18)
+#define T5_ISS_S    18
+#define T5_ISS_V(x) ((x) << T5_ISS_S)
+#define T5_ISS_F    T5_ISS_V(1U)
 
 #endif /* _T4FW_RI_API_H_ */
diff --git a/drivers/infiniband/hw/nes/nes.c b/drivers/infiniband/hw/nes/nes.c
index 3b2a6dc..9f9d5c5 100644
--- a/drivers/infiniband/hw/nes/nes.c
+++ b/drivers/infiniband/hw/nes/nes.c
@@ -116,6 +116,7 @@ static struct ibnl_client_cbs nes_nl_cb_table[] = {
 	[RDMA_NL_IWPM_REG_PID] = {.dump = iwpm_register_pid_cb},
 	[RDMA_NL_IWPM_ADD_MAPPING] = {.dump = iwpm_add_mapping_cb},
 	[RDMA_NL_IWPM_QUERY_MAPPING] = {.dump = iwpm_add_and_query_mapping_cb},
+	[RDMA_NL_IWPM_REMOTE_INFO] = {.dump = iwpm_remote_info_cb},
 	[RDMA_NL_IWPM_HANDLE_ERR] = {.dump = iwpm_mapping_error_cb},
 	[RDMA_NL_IWPM_MAPINFO] = {.dump = iwpm_mapping_info_cb},
 	[RDMA_NL_IWPM_MAPINFO_NUM] = {.dump = iwpm_ack_mapping_info_cb}
diff --git a/drivers/infiniband/hw/nes/nes_cm.c b/drivers/infiniband/hw/nes/nes_cm.c
index 6f09a72..72b4341 100644
--- a/drivers/infiniband/hw/nes/nes_cm.c
+++ b/drivers/infiniband/hw/nes/nes_cm.c
@@ -596,27 +596,52 @@ static void nes_form_reg_msg(struct nes_vnic *nesvnic,
 	memcpy(pm_msg->if_name, nesvnic->netdev->name, IWPM_IFNAME_SIZE);
 }
 
+static void record_sockaddr_info(struct sockaddr_storage *addr_info,
+					nes_addr_t *ip_addr, u16 *port_num)
+{
+	struct sockaddr_in *in_addr = (struct sockaddr_in *)addr_info;
+
+	if (in_addr->sin_family == AF_INET) {
+		*ip_addr = ntohl(in_addr->sin_addr.s_addr);
+		*port_num = ntohs(in_addr->sin_port);
+	}
+}
+
 /*
  * nes_record_pm_msg - Save the received mapping info
  */
 static void nes_record_pm_msg(struct nes_cm_info *cm_info,
 			struct iwpm_sa_data *pm_msg)
 {
-	struct sockaddr_in *mapped_loc_addr =
-			(struct sockaddr_in *)&pm_msg->mapped_loc_addr;
-	struct sockaddr_in *mapped_rem_addr =
-			(struct sockaddr_in *)&pm_msg->mapped_rem_addr;
-
-	if (mapped_loc_addr->sin_family == AF_INET) {
-		cm_info->mapped_loc_addr =
-			ntohl(mapped_loc_addr->sin_addr.s_addr);
-		cm_info->mapped_loc_port = ntohs(mapped_loc_addr->sin_port);
-	}
-	if (mapped_rem_addr->sin_family == AF_INET) {
-		cm_info->mapped_rem_addr =
-			ntohl(mapped_rem_addr->sin_addr.s_addr);
-		cm_info->mapped_rem_port = ntohs(mapped_rem_addr->sin_port);
-	}
+	record_sockaddr_info(&pm_msg->mapped_loc_addr,
+		&cm_info->mapped_loc_addr, &cm_info->mapped_loc_port);
+
+	record_sockaddr_info(&pm_msg->mapped_rem_addr,
+		&cm_info->mapped_rem_addr, &cm_info->mapped_rem_port);
+}
+
+/*
+ * nes_get_reminfo - Get the address info of the remote connecting peer
+ */
+static int nes_get_remote_addr(struct nes_cm_node *cm_node)
+{
+	struct sockaddr_storage mapped_loc_addr, mapped_rem_addr;
+	struct sockaddr_storage remote_addr;
+	int ret;
+
+	nes_create_sockaddr(htonl(cm_node->mapped_loc_addr),
+			htons(cm_node->mapped_loc_port), &mapped_loc_addr);
+	nes_create_sockaddr(htonl(cm_node->mapped_rem_addr),
+			htons(cm_node->mapped_rem_port), &mapped_rem_addr);
+
+	ret = iwpm_get_remote_info(&mapped_loc_addr, &mapped_rem_addr,
+				&remote_addr, RDMA_NL_NES);
+	if (ret)
+		nes_debug(NES_DBG_CM, "Unable to find remote peer address info\n");
+	else
+		record_sockaddr_info(&remote_addr, &cm_node->rem_addr,
+				&cm_node->rem_port);
+	return ret;
 }
 
 /**
@@ -1566,9 +1591,14 @@ static struct nes_cm_node *make_cm_node(struct nes_cm_core *cm_core,
 		return NULL;
 
 	/* set our node specific transport info */
-	cm_node->loc_addr = cm_info->loc_addr;
+	if (listener) {
+		cm_node->loc_addr = listener->loc_addr;
+		cm_node->loc_port = listener->loc_port;
+	} else {
+		cm_node->loc_addr = cm_info->loc_addr;
+		cm_node->loc_port = cm_info->loc_port;
+	}
 	cm_node->rem_addr = cm_info->rem_addr;
-	cm_node->loc_port = cm_info->loc_port;
 	cm_node->rem_port = cm_info->rem_port;
 
 	cm_node->mapped_loc_addr = cm_info->mapped_loc_addr;
@@ -2151,6 +2181,7 @@ static int handle_ack_pkt(struct nes_cm_node *cm_node, struct sk_buff *skb,
 		cm_node->state = NES_CM_STATE_ESTABLISHED;
 		if (datasize) {
 			cm_node->tcp_cntxt.rcv_nxt = inc_sequence + datasize;
+			nes_get_remote_addr(cm_node);
 			handle_rcv_mpa(cm_node, skb);
 		} else { /* rcvd ACK only */
 			dev_kfree_skb_any(skb);
diff --git a/drivers/infiniband/hw/qib/qib.h b/drivers/infiniband/hw/qib/qib.h
index ffd48bf..ba5173e2 100644
--- a/drivers/infiniband/hw/qib/qib.h
+++ b/drivers/infiniband/hw/qib/qib.h
@@ -1136,7 +1136,6 @@ extern struct qib_devdata *qib_lookup(int unit);
 extern u32 qib_cpulist_count;
 extern unsigned long *qib_cpulist;
 
-extern unsigned qib_wc_pat;
 extern unsigned qib_cc_table_size;
 int qib_init(struct qib_devdata *, int);
 int init_chip_wc_pat(struct qib_devdata *dd, u32);
diff --git a/drivers/infiniband/hw/qib/qib_file_ops.c b/drivers/infiniband/hw/qib/qib_file_ops.c
index 9ea6c44..7258818 100644
--- a/drivers/infiniband/hw/qib/qib_file_ops.c
+++ b/drivers/infiniband/hw/qib/qib_file_ops.c
@@ -835,7 +835,8 @@ static int mmap_piobufs(struct vm_area_struct *vma,
 	vma->vm_flags &= ~VM_MAYREAD;
 	vma->vm_flags |= VM_DONTCOPY | VM_DONTEXPAND;
 
-	if (qib_wc_pat)
+	/* We used PAT if wc_cookie == 0 */
+	if (!dd->wc_cookie)
 		vma->vm_page_prot = pgprot_writecombine(vma->vm_page_prot);
 
 	ret = io_remap_pfn_range(vma, vma->vm_start, phys >> PAGE_SHIFT,
diff --git a/drivers/infiniband/hw/qib/qib_iba6120.c b/drivers/infiniband/hw/qib/qib_iba6120.c
index 0d2ba59..4b927809 100644
--- a/drivers/infiniband/hw/qib/qib_iba6120.c
+++ b/drivers/infiniband/hw/qib/qib_iba6120.c
@@ -3315,11 +3315,9 @@ static int init_6120_variables(struct qib_devdata *dd)
 	qib_6120_config_ctxts(dd);
 	qib_set_ctxtcnt(dd);
 
-	if (qib_wc_pat) {
-		ret = init_chip_wc_pat(dd, 0);
-		if (ret)
-			goto bail;
-	}
+	ret = init_chip_wc_pat(dd, 0);
+	if (ret)
+		goto bail;
 	set_6120_baseaddrs(dd); /* set chip access pointers now */
 
 	ret = 0;
diff --git a/drivers/infiniband/hw/qib/qib_iba7220.c b/drivers/infiniband/hw/qib/qib_iba7220.c
index 22affda..00b2af2 100644
--- a/drivers/infiniband/hw/qib/qib_iba7220.c
+++ b/drivers/infiniband/hw/qib/qib_iba7220.c
@@ -4126,11 +4126,9 @@ static int qib_init_7220_variables(struct qib_devdata *dd)
 	qib_7220_config_ctxts(dd);
 	qib_set_ctxtcnt(dd);  /* needed for PAT setup */
 
-	if (qib_wc_pat) {
-		ret = init_chip_wc_pat(dd, 0);
-		if (ret)
-			goto bail;
-	}
+	ret = init_chip_wc_pat(dd, 0);
+	if (ret)
+		goto bail;
 	set_7220_baseaddrs(dd); /* set chip access pointers now */
 
 	ret = 0;
diff --git a/drivers/infiniband/hw/qib/qib_iba7322.c b/drivers/infiniband/hw/qib/qib_iba7322.c
index ef97b71..f32b462 100644
--- a/drivers/infiniband/hw/qib/qib_iba7322.c
+++ b/drivers/infiniband/hw/qib/qib_iba7322.c
@@ -6429,6 +6429,7 @@ static int qib_init_7322_variables(struct qib_devdata *dd)
 	unsigned features, pidx, sbufcnt;
 	int ret, mtu;
 	u32 sbufs, updthresh;
+	resource_size_t vl15off;
 
 	/* pport structs are contiguous, allocated after devdata */
 	ppd = (struct qib_pportdata *)(dd + 1);
@@ -6677,29 +6678,27 @@ static int qib_init_7322_variables(struct qib_devdata *dd)
 	qib_7322_config_ctxts(dd);
 	qib_set_ctxtcnt(dd);
 
-	if (qib_wc_pat) {
-		resource_size_t vl15off;
-		/*
-		 * We do not set WC on the VL15 buffers to avoid
-		 * a rare problem with unaligned writes from
-		 * interrupt-flushed store buffers, so we need
-		 * to map those separately here.  We can't solve
-		 * this for the rarely used mtrr case.
-		 */
-		ret = init_chip_wc_pat(dd, 0);
-		if (ret)
-			goto bail;
+	/*
+	 * We do not set WC on the VL15 buffers to avoid
+	 * a rare problem with unaligned writes from
+	 * interrupt-flushed store buffers, so we need
+	 * to map those separately here.  We can't solve
+	 * this for the rarely used mtrr case.
+	 */
+	ret = init_chip_wc_pat(dd, 0);
+	if (ret)
+		goto bail;
 
-		/* vl15 buffers start just after the 4k buffers */
-		vl15off = dd->physaddr + (dd->piobufbase >> 32) +
-			dd->piobcnt4k * dd->align4k;
-		dd->piovl15base	= ioremap_nocache(vl15off,
-						  NUM_VL15_BUFS * dd->align4k);
-		if (!dd->piovl15base) {
-			ret = -ENOMEM;
-			goto bail;
-		}
+	/* vl15 buffers start just after the 4k buffers */
+	vl15off = dd->physaddr + (dd->piobufbase >> 32) +
+		  dd->piobcnt4k * dd->align4k;
+	dd->piovl15base	= ioremap_nocache(vl15off,
+					  NUM_VL15_BUFS * dd->align4k);
+	if (!dd->piovl15base) {
+		ret = -ENOMEM;
+		goto bail;
 	}
+
 	qib_7322_set_baseaddrs(dd); /* set chip access pointers now */
 
 	ret = 0;
diff --git a/drivers/infiniband/hw/qib/qib_init.c b/drivers/infiniband/hw/qib/qib_init.c
index 2ee3695..7e00470 100644
--- a/drivers/infiniband/hw/qib/qib_init.c
+++ b/drivers/infiniband/hw/qib/qib_init.c
@@ -91,15 +91,6 @@ MODULE_PARM_DESC(krcvqs, "number of kernel receive queues per IB port");
 unsigned qib_cc_table_size;
 module_param_named(cc_table_size, qib_cc_table_size, uint, S_IRUGO);
 MODULE_PARM_DESC(cc_table_size, "Congestion control table entries 0 (CCA disabled - default), min = 128, max = 1984");
-/*
- * qib_wc_pat parameter:
- *      0 is WC via MTRR
- *      1 is WC via PAT
- *      If PAT initialization fails, code reverts back to MTRR
- */
-unsigned qib_wc_pat = 1; /* default (1) is to use PAT, not MTRR */
-module_param_named(wc_pat, qib_wc_pat, uint, S_IRUGO);
-MODULE_PARM_DESC(wc_pat, "enable write-combining via PAT mechanism");
 
 static void verify_interrupt(unsigned long);
 
@@ -1377,8 +1368,7 @@ static void cleanup_device_data(struct qib_devdata *dd)
 		spin_unlock(&dd->pport[pidx].cc_shadow_lock);
 	}
 
-	if (!qib_wc_pat)
-		qib_disable_wc(dd);
+	qib_disable_wc(dd);
 
 	if (dd->pioavailregs_dma) {
 		dma_free_coherent(&dd->pcidev->dev, PAGE_SIZE,
@@ -1547,14 +1537,12 @@ static int qib_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 		goto bail;
 	}
 
-	if (!qib_wc_pat) {
-		ret = qib_enable_wc(dd);
-		if (ret) {
-			qib_dev_err(dd,
-				"Write combining not enabled (err %d): performance may be poor\n",
-				-ret);
-			ret = 0;
-		}
+	ret = qib_enable_wc(dd);
+	if (ret) {
+		qib_dev_err(dd,
+			"Write combining not enabled (err %d): performance may be poor\n",
+			-ret);
+		ret = 0;
 	}
 
 	qib_verify_pioperf(dd);
diff --git a/drivers/infiniband/hw/qib/qib_wc_x86_64.c b/drivers/infiniband/hw/qib/qib_wc_x86_64.c
index 81b225f..6d61ef9 100644
--- a/drivers/infiniband/hw/qib/qib_wc_x86_64.c
+++ b/drivers/infiniband/hw/qib/qib_wc_x86_64.c
@@ -116,21 +116,9 @@ int qib_enable_wc(struct qib_devdata *dd)
 	}
 
 	if (!ret) {
-		int cookie;
-
-		cookie = mtrr_add(pioaddr, piolen, MTRR_TYPE_WRCOMB, 0);
-		if (cookie < 0) {
-			{
-				qib_devinfo(dd->pcidev,
-					 "mtrr_add()  WC for PIO bufs failed (%d)\n",
-					 cookie);
-				ret = -EINVAL;
-			}
-		} else {
-			dd->wc_cookie = cookie;
-			dd->wc_base = (unsigned long) pioaddr;
-			dd->wc_len = (unsigned long) piolen;
-		}
+		dd->wc_cookie = arch_phys_wc_add(pioaddr, piolen);
+		if (dd->wc_cookie < 0)
+			ret = -EINVAL;
 	}
 
 	return ret;
@@ -142,18 +130,7 @@ int qib_enable_wc(struct qib_devdata *dd)
  */
 void qib_disable_wc(struct qib_devdata *dd)
 {
-	if (dd->wc_cookie) {
-		int r;
-
-		r = mtrr_del(dd->wc_cookie, dd->wc_base,
-			     dd->wc_len);
-		if (r < 0)
-			qib_devinfo(dd->pcidev,
-				 "mtrr_del(%lx, %lx, %lx) failed: %d\n",
-				 dd->wc_cookie, dd->wc_base,
-				 dd->wc_len, r);
-		dd->wc_cookie = 0; /* even on failure */
-	}
+	arch_phys_wc_del(dd->wc_cookie);
 }
 
 /**