Merge branches '32bit_lid' and 'irq_affinity' into k.o/merge-test

Conflicts:
	drivers/infiniband/hw/mlx5/main.c - Both add new code
	include/rdma/ib_verbs.h - Both add new code

Signed-off-by: Doug Ledford <dledford@redhat.com>

block/Kconfig

@@ -206,4 +206,9 @@ config BLK_MQ_VIRTIO
 	depends on BLOCK && VIRTIO
 	default y
 
+config BLK_MQ_RDMA
+	bool
+	depends on BLOCK && INFINIBAND
+	default y
+
 source block/Kconfig.iosched

block/Makefile

@@ -29,6 +29,7 @@ obj-$(CONFIG_BLK_CMDLINE_PARSER)	+= cmdline-parser.o
 obj-$(CONFIG_BLK_DEV_INTEGRITY) += bio-integrity.o blk-integrity.o t10-pi.o
 obj-$(CONFIG_BLK_MQ_PCI)	+= blk-mq-pci.o
 obj-$(CONFIG_BLK_MQ_VIRTIO)	+= blk-mq-virtio.o
+obj-$(CONFIG_BLK_MQ_RDMA)	+= blk-mq-rdma.o
 obj-$(CONFIG_BLK_DEV_ZONED)	+= blk-zoned.o
 obj-$(CONFIG_BLK_WBT)		+= blk-wbt.o
 obj-$(CONFIG_BLK_DEBUG_FS)	+= blk-mq-debugfs.o

block/blk-mq-rdma.c

@@ -0,0 +1,52 @@
+/*
+ * Copyright (c) 2017 Sagi Grimberg.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ */
+#include <linux/blk-mq.h>
+#include <linux/blk-mq-rdma.h>
+#include <rdma/ib_verbs.h>
+
+/**
+ * blk_mq_rdma_map_queues - provide a default queue mapping for rdma device
+ * @set:	tagset to provide the mapping for
+ * @dev:	rdma device associated with @set.
+ * @first_vec:	first interrupt vectors to use for queues (usually 0)
+ *
+ * This function assumes the rdma device @dev has at least as many available
+ * interrupt vetors as @set has queues.  It will then query it's affinity mask
+ * and built queue mapping that maps a queue to the CPUs that have irq affinity
+ * for the corresponding vector.
+ *
+ * In case either the driver passed a @dev with less vectors than
+ * @set->nr_hw_queues, or @dev does not provide an affinity mask for a
+ * vector, we fallback to the naive mapping.
+ */
+int blk_mq_rdma_map_queues(struct blk_mq_tag_set *set,
+		struct ib_device *dev, int first_vec)
+{
+	const struct cpumask *mask;
+	unsigned int queue, cpu;
+
+	for (queue = 0; queue < set->nr_hw_queues; queue++) {
+		mask = ib_get_vector_affinity(dev, first_vec + queue);
+		if (!mask)
+			goto fallback;
+
+		for_each_cpu(cpu, mask)
+			set->mq_map[cpu] = queue;
+	}
+
+	return 0;
+
+fallback:
+	return blk_mq_map_queues(set);
+}
+EXPORT_SYMBOL_GPL(blk_mq_rdma_map_queues);

drivers/infiniband/core/cm.c

@@ -1175,6 +1175,11 @@ static void cm_format_req(struct cm_req_msg *req_msg,
 {
 	struct sa_path_rec *pri_path = param->primary_path;
 	struct sa_path_rec *alt_path = param->alternate_path;
+	bool pri_ext = false;
+
+	if (pri_path->rec_type == SA_PATH_REC_TYPE_OPA)
+		pri_ext = opa_is_extended_lid(pri_path->opa.dlid,
+					      pri_path->opa.slid);
 
 	cm_format_mad_hdr(&req_msg->hdr, CM_REQ_ATTR_ID,
 			  cm_form_tid(cm_id_priv, CM_MSG_SEQUENCE_REQ));
@@ -1202,18 +1207,24 @@ static void cm_format_req(struct cm_req_msg *req_msg,
 		cm_req_set_srq(req_msg, param->srq);
 	}
 
+	req_msg->primary_local_gid = pri_path->sgid;
+	req_msg->primary_remote_gid = pri_path->dgid;
+	if (pri_ext) {
+		req_msg->primary_local_gid.global.interface_id
+			= OPA_MAKE_ID(be32_to_cpu(pri_path->opa.slid));
+		req_msg->primary_remote_gid.global.interface_id
+			= OPA_MAKE_ID(be32_to_cpu(pri_path->opa.dlid));
+	}
 	if (pri_path->hop_limit <= 1) {
-		req_msg->primary_local_lid =
+		req_msg->primary_local_lid = pri_ext ? 0 :
 			htons(ntohl(sa_path_get_slid(pri_path)));
-		req_msg->primary_remote_lid =
+		req_msg->primary_remote_lid = pri_ext ? 0 :
 			htons(ntohl(sa_path_get_dlid(pri_path)));
 	} else {
 		/* Work-around until there's a way to obtain remote LID info */
 		req_msg->primary_local_lid = IB_LID_PERMISSIVE;
 		req_msg->primary_remote_lid = IB_LID_PERMISSIVE;
 	}
-	req_msg->primary_local_gid = pri_path->sgid;
-	req_msg->primary_remote_gid = pri_path->dgid;
 	cm_req_set_primary_flow_label(req_msg, pri_path->flow_label);
 	cm_req_set_primary_packet_rate(req_msg, pri_path->rate);
 	req_msg->primary_traffic_class = pri_path->traffic_class;
@@ -1225,17 +1236,29 @@ static void cm_format_req(struct cm_req_msg *req_msg,
 			       pri_path->packet_life_time));
 
 	if (alt_path) {
+		bool alt_ext = false;
+
+		if (alt_path->rec_type == SA_PATH_REC_TYPE_OPA)
+			alt_ext = opa_is_extended_lid(alt_path->opa.dlid,
+						      alt_path->opa.slid);
+
+		req_msg->alt_local_gid = alt_path->sgid;
+		req_msg->alt_remote_gid = alt_path->dgid;
+		if (alt_ext) {
+			req_msg->alt_local_gid.global.interface_id
+				= OPA_MAKE_ID(be32_to_cpu(alt_path->opa.slid));
+			req_msg->alt_remote_gid.global.interface_id
+				= OPA_MAKE_ID(be32_to_cpu(alt_path->opa.dlid));
+		}
 		if (alt_path->hop_limit <= 1) {
-			req_msg->alt_local_lid =
+			req_msg->alt_local_lid = alt_ext ? 0 :
 				htons(ntohl(sa_path_get_slid(alt_path)));
-			req_msg->alt_remote_lid =
+			req_msg->alt_remote_lid = alt_ext ? 0 :
 				htons(ntohl(sa_path_get_dlid(alt_path)));
 		} else {
 			req_msg->alt_local_lid = IB_LID_PERMISSIVE;
 			req_msg->alt_remote_lid = IB_LID_PERMISSIVE;
 		}
-		req_msg->alt_local_gid = alt_path->sgid;
-		req_msg->alt_remote_gid = alt_path->dgid;
 		cm_req_set_alt_flow_label(req_msg,
 					  alt_path->flow_label);
 		cm_req_set_alt_packet_rate(req_msg, alt_path->rate);
@@ -1405,16 +1428,63 @@ static inline int cm_is_active_peer(__be64 local_ca_guid, __be64 remote_ca_guid,
 		 (be32_to_cpu(local_qpn) > be32_to_cpu(remote_qpn))));
 }
 
+static bool cm_req_has_alt_path(struct cm_req_msg *req_msg)
+{
+	return ((req_msg->alt_local_lid) ||
+		(ib_is_opa_gid(&req_msg->alt_local_gid)));
+}
+
+static void cm_path_set_rec_type(struct ib_device *ib_device, u8 port_num,
+				 struct sa_path_rec *path, union ib_gid *gid)
+{
+	if (ib_is_opa_gid(gid) && rdma_cap_opa_ah(ib_device, port_num))
+		path->rec_type = SA_PATH_REC_TYPE_OPA;
+	else
+		path->rec_type = SA_PATH_REC_TYPE_IB;
+}
+
+static void cm_format_path_lid_from_req(struct cm_req_msg *req_msg,
+					struct sa_path_rec *primary_path,
+					struct sa_path_rec *alt_path)
+{
+	u32 lid;
+
+	if (primary_path->rec_type != SA_PATH_REC_TYPE_OPA) {
+		sa_path_set_dlid(primary_path,
+				 htonl(ntohs(req_msg->primary_local_lid)));
+		sa_path_set_slid(primary_path,
+				 htonl(ntohs(req_msg->primary_remote_lid)));
+	} else {
+		lid = opa_get_lid_from_gid(&req_msg->primary_local_gid);
+		sa_path_set_dlid(primary_path, cpu_to_be32(lid));
+
+		lid = opa_get_lid_from_gid(&req_msg->primary_remote_gid);
+		sa_path_set_slid(primary_path, cpu_to_be32(lid));
+	}
+
+	if (!cm_req_has_alt_path(req_msg))
+		return;
+
+	if (alt_path->rec_type != SA_PATH_REC_TYPE_OPA) {
+		sa_path_set_dlid(alt_path,
+				 htonl(ntohs(req_msg->alt_local_lid)));
+		sa_path_set_slid(alt_path,
+				 htonl(ntohs(req_msg->alt_remote_lid)));
+	} else {
+		lid = opa_get_lid_from_gid(&req_msg->alt_local_gid);
+		sa_path_set_dlid(alt_path, cpu_to_be32(lid));
+
+		lid = opa_get_lid_from_gid(&req_msg->alt_remote_gid);
+		sa_path_set_slid(alt_path, cpu_to_be32(lid));
+	}
+}
+
 static void cm_format_paths_from_req(struct cm_req_msg *req_msg,
 				     struct sa_path_rec *primary_path,
 				     struct sa_path_rec *alt_path)
 {
 	primary_path->dgid = req_msg->primary_local_gid;
 	primary_path->sgid = req_msg->primary_remote_gid;
-	sa_path_set_dlid(primary_path,
-			 htonl(ntohs(req_msg->primary_local_lid)));
-	sa_path_set_slid(primary_path,
-			 htonl(ntohs(req_msg->primary_remote_lid)));
 	primary_path->flow_label = cm_req_get_primary_flow_label(req_msg);
 	primary_path->hop_limit = req_msg->primary_hop_limit;
 	primary_path->traffic_class = req_msg->primary_traffic_class;
@@ -1431,13 +1501,9 @@ static void cm_format_paths_from_req(struct cm_req_msg *req_msg,
 	primary_path->packet_life_time -= (primary_path->packet_life_time > 0);
 	primary_path->service_id = req_msg->service_id;
 
-	if (req_msg->alt_local_lid) {
+	if (cm_req_has_alt_path(req_msg)) {
 		alt_path->dgid = req_msg->alt_local_gid;
 		alt_path->sgid = req_msg->alt_remote_gid;
-		sa_path_set_dlid(alt_path,
-				 htonl(ntohs(req_msg->alt_local_lid)));
-		sa_path_set_slid(alt_path,
-				 htonl(ntohs(req_msg->alt_remote_lid)));
 		alt_path->flow_label = cm_req_get_alt_flow_label(req_msg);
 		alt_path->hop_limit = req_msg->alt_hop_limit;
 		alt_path->traffic_class = req_msg->alt_traffic_class;
@@ -1454,6 +1520,7 @@ static void cm_format_paths_from_req(struct cm_req_msg *req_msg,
 		alt_path->packet_life_time -= (alt_path->packet_life_time > 0);
 		alt_path->service_id = req_msg->service_id;
 	}
+	cm_format_path_lid_from_req(req_msg, primary_path, alt_path);
 }
 
 static u16 cm_get_bth_pkey(struct cm_work *work)
@@ -1703,7 +1770,7 @@ static void cm_process_routed_req(struct cm_req_msg *req_msg, struct ib_wc *wc)
 {
 	if (!cm_req_get_primary_subnet_local(req_msg)) {
 		if (req_msg->primary_local_lid == IB_LID_PERMISSIVE) {
-			req_msg->primary_local_lid = cpu_to_be16(wc->slid);
+			req_msg->primary_local_lid = ib_slid_be16(wc->slid);
 			cm_req_set_primary_sl(req_msg, wc->sl);
 		}
 
@@ -1713,7 +1780,7 @@ static void cm_process_routed_req(struct cm_req_msg *req_msg, struct ib_wc *wc)
 
 	if (!cm_req_get_alt_subnet_local(req_msg)) {
 		if (req_msg->alt_local_lid == IB_LID_PERMISSIVE) {
-			req_msg->alt_local_lid = cpu_to_be16(wc->slid);
+			req_msg->alt_local_lid = ib_slid_be16(wc->slid);
 			cm_req_set_alt_sl(req_msg, wc->sl);
 		}
 
@@ -1784,9 +1851,12 @@ static int cm_req_handler(struct cm_work *work)
 					 dev_net(gid_attr.ndev));
 			dev_put(gid_attr.ndev);
 		} else {
-			work->path[0].rec_type = SA_PATH_REC_TYPE_IB;
+			cm_path_set_rec_type(work->port->cm_dev->ib_device,
+					     work->port->port_num,
+					     &work->path[0],
+					     &req_msg->primary_local_gid);
 		}
-		if (req_msg->alt_local_lid)
+		if (cm_req_has_alt_path(req_msg))
 			work->path[1].rec_type = work->path[0].rec_type;
 		cm_format_paths_from_req(req_msg, &work->path[0],
 					 &work->path[1]);
@@ -1811,16 +1881,19 @@ static int cm_req_handler(struct cm_work *work)
 					 dev_net(gid_attr.ndev));
 			dev_put(gid_attr.ndev);
 		} else {
-			work->path[0].rec_type = SA_PATH_REC_TYPE_IB;
+			cm_path_set_rec_type(work->port->cm_dev->ib_device,
+					     work->port->port_num,
+					     &work->path[0],
+					     &req_msg->primary_local_gid);
 		}
-		if (req_msg->alt_local_lid)
+		if (cm_req_has_alt_path(req_msg))
 			work->path[1].rec_type = work->path[0].rec_type;
 		ib_send_cm_rej(cm_id, IB_CM_REJ_INVALID_GID,
 			       &work->path[0].sgid, sizeof work->path[0].sgid,
 			       NULL, 0);
 		goto rejected;
 	}
-	if (req_msg->alt_local_lid) {
+	if (cm_req_has_alt_path(req_msg)) {
 		ret = cm_init_av_by_path(&work->path[1], &cm_id_priv->alt_av,
 					 cm_id_priv);
 		if (ret) {
@@ -2843,6 +2916,11 @@ static void cm_format_lap(struct cm_lap_msg *lap_msg,
 			  const void *private_data,
 			  u8 private_data_len)
 {
+	bool alt_ext = false;
+
+	if (alternate_path->rec_type == SA_PATH_REC_TYPE_OPA)
+		alt_ext = opa_is_extended_lid(alternate_path->opa.dlid,
+					      alternate_path->opa.slid);
 	cm_format_mad_hdr(&lap_msg->hdr, CM_LAP_ATTR_ID,
 			  cm_form_tid(cm_id_priv, CM_MSG_SEQUENCE_LAP));
 	lap_msg->local_comm_id = cm_id_priv->id.local_id;
@@ -2856,6 +2934,12 @@ static void cm_format_lap(struct cm_lap_msg *lap_msg,
 		htons(ntohl(sa_path_get_dlid(alternate_path)));
 	lap_msg->alt_local_gid = alternate_path->sgid;
 	lap_msg->alt_remote_gid = alternate_path->dgid;
+	if (alt_ext) {
+		lap_msg->alt_local_gid.global.interface_id
+			= OPA_MAKE_ID(be32_to_cpu(alternate_path->opa.slid));
+		lap_msg->alt_remote_gid.global.interface_id
+			= OPA_MAKE_ID(be32_to_cpu(alternate_path->opa.dlid));
+	}
 	cm_lap_set_flow_label(lap_msg, alternate_path->flow_label);
 	cm_lap_set_traffic_class(lap_msg, alternate_path->traffic_class);
 	lap_msg->alt_hop_limit = alternate_path->hop_limit;
@@ -2924,16 +3008,29 @@ out:	spin_unlock_irqrestore(&cm_id_priv->lock, flags);
 }
 EXPORT_SYMBOL(ib_send_cm_lap);
 
+static void cm_format_path_lid_from_lap(struct cm_lap_msg *lap_msg,
+					struct sa_path_rec *path)
+{
+	u32 lid;
+
+	if (path->rec_type != SA_PATH_REC_TYPE_OPA) {
+		sa_path_set_dlid(path, htonl(ntohs(lap_msg->alt_local_lid)));
+		sa_path_set_slid(path, htonl(ntohs(lap_msg->alt_remote_lid)));
+	} else {
+		lid = opa_get_lid_from_gid(&lap_msg->alt_local_gid);
+		sa_path_set_dlid(path, cpu_to_be32(lid));
+
+		lid = opa_get_lid_from_gid(&lap_msg->alt_remote_gid);
+		sa_path_set_slid(path, cpu_to_be32(lid));
+	}
+}
+
 static void cm_format_path_from_lap(struct cm_id_private *cm_id_priv,
 				    struct sa_path_rec *path,
 				    struct cm_lap_msg *lap_msg)
 {
-	memset(path, 0, sizeof *path);
-	path->rec_type = SA_PATH_REC_TYPE_IB;
 	path->dgid = lap_msg->alt_local_gid;
 	path->sgid = lap_msg->alt_remote_gid;
-	sa_path_set_dlid(path, htonl(ntohs(lap_msg->alt_local_lid)));
-	sa_path_set_slid(path, htonl(ntohs(lap_msg->alt_remote_lid)));
 	path->flow_label = cm_lap_get_flow_label(lap_msg);
 	path->hop_limit = lap_msg->alt_hop_limit;
 	path->traffic_class = cm_lap_get_traffic_class(lap_msg);
@@ -2947,6 +3044,7 @@ static void cm_format_path_from_lap(struct cm_id_private *cm_id_priv,
 	path->packet_life_time_selector = IB_SA_EQ;
 	path->packet_life_time = cm_lap_get_local_ack_timeout(lap_msg);
 	path->packet_life_time -= (path->packet_life_time > 0);
+	cm_format_path_lid_from_lap(lap_msg, path);
 }
 
 static int cm_lap_handler(struct cm_work *work)
@@ -2965,6 +3063,11 @@ static int cm_lap_handler(struct cm_work *work)
 		return -EINVAL;
 
 	param = &work->cm_event.param.lap_rcvd;
+	memset(&work->path[0], 0, sizeof(work->path[1]));
+	cm_path_set_rec_type(work->port->cm_dev->ib_device,
+			     work->port->port_num,
+			     &work->path[0],
+			     &lap_msg->alt_local_gid);
 	param->alternate_path = &work->path[0];
 	cm_format_path_from_lap(cm_id_priv, param->alternate_path, lap_msg);
 	work->cm_event.private_data = &lap_msg->private_data;

drivers/infiniband/core/core_priv.h

@@ -38,6 +38,7 @@
 #include <linux/cgroup_rdma.h>
 
 #include <rdma/ib_verbs.h>
+#include <rdma/opa_addr.h>
 #include <rdma/ib_mad.h>
 #include "mad_priv.h"
 

drivers/infiniband/core/mad_rmpp.c

@@ -64,7 +64,7 @@ struct mad_rmpp_recv {
 
 	__be64 tid;
 	u32 src_qp;
-	u16 slid;
+	u32 slid;
 	u8 mgmt_class;
 	u8 class_version;
 	u8 method;

drivers/infiniband/core/ucm.c

@@ -618,7 +618,7 @@ static ssize_t ib_ucm_init_qp_attr(struct ib_ucm_file *file,
 	if (result)
 		goto out;
 
-	ib_copy_qp_attr_to_user(&resp, &qp_attr);
+	ib_copy_qp_attr_to_user(ctx->cm_id->device, &resp, &qp_attr);
 
 	if (copy_to_user((void __user *)(unsigned long)cmd.response,
 			 &resp, sizeof(resp)))

drivers/infiniband/core/ucma.c

@@ -248,14 +248,15 @@ static void ucma_copy_conn_event(struct rdma_ucm_conn_param *dst,
 	dst->qp_num = src->qp_num;
 }
 
-static void ucma_copy_ud_event(struct rdma_ucm_ud_param *dst,
+static void ucma_copy_ud_event(struct ib_device *device,
+			       struct rdma_ucm_ud_param *dst,
 			       struct rdma_ud_param *src)
 {
 	if (src->private_data_len)
 		memcpy(dst->private_data, src->private_data,
 		       src->private_data_len);
 	dst->private_data_len = src->private_data_len;
-	ib_copy_ah_attr_to_user(&dst->ah_attr, &src->ah_attr);
+	ib_copy_ah_attr_to_user(device, &dst->ah_attr, &src->ah_attr);
 	dst->qp_num = src->qp_num;
 	dst->qkey = src->qkey;
 }
@@ -335,7 +336,8 @@ static int ucma_event_handler(struct rdma_cm_id *cm_id,
 	uevent->resp.event = event->event;
 	uevent->resp.status = event->status;
 	if (cm_id->qp_type == IB_QPT_UD)
-		ucma_copy_ud_event(&uevent->resp.param.ud, &event->param.ud);
+		ucma_copy_ud_event(cm_id->device, &uevent->resp.param.ud,
+				   &event->param.ud);
 	else
 		ucma_copy_conn_event(&uevent->resp.param.conn,
 				     &event->param.conn);
@@ -1157,7 +1159,7 @@ static ssize_t ucma_init_qp_attr(struct ucma_file *file,
 	if (ret)
 		goto out;
 
-	ib_copy_qp_attr_to_user(&resp, &qp_attr);
+	ib_copy_qp_attr_to_user(ctx->cm_id->device, &resp, &qp_attr);
 	if (copy_to_user((void __user *)(unsigned long)cmd.response,
 			 &resp, sizeof(resp)))
 		ret = -EFAULT;

drivers/infiniband/core/user_mad.c

@@ -229,7 +229,7 @@ static void recv_handler(struct ib_mad_agent *agent,
 	packet->mad.hdr.status	   = 0;
 	packet->mad.hdr.length	   = hdr_size(file) + mad_recv_wc->mad_len;
 	packet->mad.hdr.qpn	   = cpu_to_be32(mad_recv_wc->wc->src_qp);
-	packet->mad.hdr.lid	   = cpu_to_be16(mad_recv_wc->wc->slid);
+	packet->mad.hdr.lid	   = ib_slid_be16(mad_recv_wc->wc->slid);
 	packet->mad.hdr.sl	   = mad_recv_wc->wc->sl;
 	packet->mad.hdr.path_bits  = mad_recv_wc->wc->dlid_path_bits;
 	packet->mad.hdr.pkey_index = mad_recv_wc->wc->pkey_index;

drivers/infiniband/core/uverbs_cmd.c

@@ -275,8 +275,13 @@ ssize_t ib_uverbs_query_port(struct ib_uverbs_file *file,
 	resp.bad_pkey_cntr   = attr.bad_pkey_cntr;
 	resp.qkey_viol_cntr  = attr.qkey_viol_cntr;
 	resp.pkey_tbl_len    = attr.pkey_tbl_len;
-	resp.lid 	     = attr.lid;
-	resp.sm_lid 	     = attr.sm_lid;
+	if (rdma_cap_opa_ah(ib_dev, cmd.port_num)) {
+		resp.lid  = OPA_TO_IB_UCAST_LID(attr.lid);
+		resp.sm_lid  = OPA_TO_IB_UCAST_LID(attr.sm_lid);
+	} else {
+		resp.lid     = (u16)attr.lid;
+		resp.sm_lid  = (u16)attr.sm_lid;
+	}
 	resp.lmc 	     = attr.lmc;
 	resp.max_vl_num      = attr.max_vl_num;
 	resp.sm_sl 	     = attr.sm_sl;
@@ -1185,7 +1190,8 @@ out:
 	return ret ? ret : in_len;
 }
 
-static int copy_wc_to_user(void __user *dest, struct ib_wc *wc)
+static int copy_wc_to_user(struct ib_device *ib_dev, void __user *dest,
+			   struct ib_wc *wc)
 {
 	struct ib_uverbs_wc tmp;
 
@@ -1199,7 +1205,10 @@ static int copy_wc_to_user(void __user *dest, struct ib_wc *wc)
 	tmp.src_qp		= wc->src_qp;
 	tmp.wc_flags		= wc->wc_flags;
 	tmp.pkey_index		= wc->pkey_index;
-	tmp.slid		= wc->slid;
+	if (rdma_cap_opa_ah(ib_dev, wc->port_num))
+		tmp.slid  = OPA_TO_IB_UCAST_LID(wc->slid);
+	else
+		tmp.slid  = ib_slid_cpu16(wc->slid);
 	tmp.sl			= wc->sl;
 	tmp.dlid_path_bits	= wc->dlid_path_bits;
 	tmp.port_num		= wc->port_num;
@@ -1243,7 +1252,7 @@ ssize_t ib_uverbs_poll_cq(struct ib_uverbs_file *file,
 		if (!ret)
 			break;
 
-		ret = copy_wc_to_user(data_ptr, &wc);
+		ret = copy_wc_to_user(ib_dev, data_ptr, &wc);
 		if (ret)
 			goto out_put;
 

drivers/infiniband/core/uverbs_marshall.c

@@ -33,10 +33,47 @@
 #include <linux/export.h>
 #include <rdma/ib_marshall.h>
 
-void ib_copy_ah_attr_to_user(struct ib_uverbs_ah_attr *dst,
-			     struct rdma_ah_attr *src)
+#define OPA_DEFAULT_GID_PREFIX cpu_to_be64(0xfe80000000000000ULL)
+static int rdma_ah_conv_opa_to_ib(struct ib_device *dev,
+				  struct rdma_ah_attr *ib,
+				  struct rdma_ah_attr *opa)
 {
+	struct ib_port_attr port_attr;
+	int ret = 0;
+
+	/* Do structure copy and the over-write fields */
+	*ib = *opa;
+
+	ib->type = RDMA_AH_ATTR_TYPE_IB;
+	rdma_ah_set_grh(ib, NULL, 0, 0, 1, 0);
+
+	if (ib_query_port(dev, opa->port_num, &port_attr)) {
+		/* Set to default subnet to indicate error */
+		rdma_ah_set_subnet_prefix(ib, OPA_DEFAULT_GID_PREFIX);
+		ret = -EINVAL;
+	} else {
+		rdma_ah_set_subnet_prefix(ib,
+					  cpu_to_be64(port_attr.subnet_prefix));
+	}
+	rdma_ah_set_interface_id(ib, OPA_MAKE_ID(rdma_ah_get_dlid(opa)));
+	return ret;
+}
+
+void ib_copy_ah_attr_to_user(struct ib_device *device,
+			     struct ib_uverbs_ah_attr *dst,
+			     struct rdma_ah_attr *ah_attr)
+{
+	struct rdma_ah_attr *src = ah_attr;
+	struct rdma_ah_attr conv_ah;
+
 	memset(&dst->grh.reserved, 0, sizeof(dst->grh.reserved));
+
+	if ((ah_attr->type == RDMA_AH_ATTR_TYPE_OPA) &&
+	    (rdma_ah_get_dlid(ah_attr) >=
+	     be16_to_cpu(IB_MULTICAST_LID_BASE)) &&
+	    (!rdma_ah_conv_opa_to_ib(device, &conv_ah, ah_attr)))
+		src = &conv_ah;
+
 	dst->dlid		   = rdma_ah_get_dlid(src);
 	dst->sl			   = rdma_ah_get_sl(src);
 	dst->src_path_bits	   = rdma_ah_get_path_bits(src);
@@ -57,7 +94,8 @@ void ib_copy_ah_attr_to_user(struct ib_uverbs_ah_attr *dst,
 }
 EXPORT_SYMBOL(ib_copy_ah_attr_to_user);
 
-void ib_copy_qp_attr_to_user(struct ib_uverbs_qp_attr *dst,
+void ib_copy_qp_attr_to_user(struct ib_device *device,
+			     struct ib_uverbs_qp_attr *dst,
 			     struct ib_qp_attr *src)
 {
 	dst->qp_state	        = src->qp_state;
@@ -76,8 +114,8 @@ void ib_copy_qp_attr_to_user(struct ib_uverbs_qp_attr *dst,
 	dst->max_recv_sge	= src->cap.max_recv_sge;
 	dst->max_inline_data	= src->cap.max_inline_data;
 
-	ib_copy_ah_attr_to_user(&dst->ah_attr, &src->ah_attr);
-	ib_copy_ah_attr_to_user(&dst->alt_ah_attr, &src->alt_ah_attr);
+	ib_copy_ah_attr_to_user(device, &dst->ah_attr, &src->ah_attr);
+	ib_copy_ah_attr_to_user(device, &dst->alt_ah_attr, &src->alt_ah_attr);
 
 	dst->pkey_index		= src->pkey_index;
 	dst->alt_pkey_index	= src->alt_pkey_index;

drivers/infiniband/hw/hfi1/mad.c

@@ -4216,7 +4216,7 @@ static int opa_local_smp_check(struct hfi1_ibport *ibp,
 			       const struct ib_wc *in_wc)
 {
 	struct hfi1_pportdata *ppd = ppd_from_ibp(ibp);
-	u16 slid = in_wc->slid;
+	u16 slid = ib_slid_cpu16(in_wc->slid);
 	u16 pkey;
 
 	if (in_wc->pkey_index >= ARRAY_SIZE(ppd->pkeys))

drivers/infiniband/hw/mlx4/alias_GUID.c

@@ -528,7 +528,7 @@ static int set_guid_rec(struct ib_device *ibdev,
 
 	memset(&guid_info_rec, 0, sizeof (struct ib_sa_guidinfo_rec));
 
-	guid_info_rec.lid = cpu_to_be16(attr.lid);
+	guid_info_rec.lid = cpu_to_be16((u16)attr.lid);
 	guid_info_rec.block_num = index;
 
 	memcpy(guid_info_rec.guid_info_list, rec_det->all_recs,

drivers/infiniband/hw/mlx4/mad.c

@@ -169,7 +169,7 @@ int mlx4_MAD_IFC(struct mlx4_ib_dev *dev, int mad_ifc_flags,
 
 		op_modifier |= 0x4;
 
-		in_modifier |= in_wc->slid << 16;
+		in_modifier |= ib_slid_cpu16(in_wc->slid) << 16;
 	}
 
 	err = mlx4_cmd_box(dev->dev, inmailbox->dma, outmailbox->dma, in_modifier,
@@ -625,7 +625,7 @@ int mlx4_ib_send_to_slave(struct mlx4_ib_dev *dev, int slave, u8 port,
 		memcpy((char *)&tun_mad->hdr.slid_mac_47_32, &(wc->smac[4]), 2);
 	} else {
 		tun_mad->hdr.sl_vid = cpu_to_be16(((u16)(wc->sl)) << 12);
-		tun_mad->hdr.slid_mac_47_32 = cpu_to_be16(wc->slid);
+		tun_mad->hdr.slid_mac_47_32 = ib_slid_be16(wc->slid);
 	}
 
 	ib_dma_sync_single_for_device(&dev->ib_dev,
@@ -826,7 +826,7 @@ static int ib_process_mad(struct ib_device *ibdev, int mad_flags, u8 port_num,
 		}
 	}
 
-	slid = in_wc ? in_wc->slid : be16_to_cpu(IB_LID_PERMISSIVE);
+	slid = in_wc ? ib_slid_cpu16(in_wc->slid) : be16_to_cpu(IB_LID_PERMISSIVE);
 
 	if (in_mad->mad_hdr.method == IB_MGMT_METHOD_TRAP && slid == 0) {
 		forward_trap(to_mdev(ibdev), port_num, in_mad);
@@ -860,7 +860,7 @@ static int ib_process_mad(struct ib_device *ibdev, int mad_flags, u8 port_num,
 	    in_mad->mad_hdr.method == IB_MGMT_METHOD_SET &&
 	    in_mad->mad_hdr.attr_id == IB_SMP_ATTR_PORT_INFO &&
 	    !ib_query_port(ibdev, port_num, &pattr))
-		prev_lid = pattr.lid;
+		prev_lid = (u16)pattr.lid;
 
 	err = mlx4_MAD_IFC(to_mdev(ibdev),
 			   (mad_flags & IB_MAD_IGNORE_MKEY ? MLX4_MAD_IFC_IGNORE_MKEY : 0) |

drivers/infiniband/hw/mlx5/mad.c

@@ -78,7 +78,7 @@ static int process_mad(struct ib_device *ibdev, int mad_flags, u8 port_num,
 	u16 slid;
 	int err;
 
-	slid = in_wc ? in_wc->slid : be16_to_cpu(IB_LID_PERMISSIVE);
+	slid = in_wc ? ib_slid_cpu16(in_wc->slid) : be16_to_cpu(IB_LID_PERMISSIVE);
 
 	if (in_mad->mad_hdr.method == IB_MGMT_METHOD_TRAP && slid == 0)
 		return IB_MAD_RESULT_SUCCESS | IB_MAD_RESULT_CONSUMED;

drivers/infiniband/hw/mlx5/main.c

@@ -3816,6 +3816,14 @@ static void init_delay_drop(struct mlx5_ib_dev *dev)
 		mlx5_ib_warn(dev, "Failed to init delay drop debugfs\n");
 }
 
+const struct cpumask *mlx5_ib_get_vector_affinity(struct ib_device *ibdev,
+		int comp_vector)
+{
+	struct mlx5_ib_dev *dev = to_mdev(ibdev);
+
+	return mlx5_get_vector_affinity(dev->mdev, comp_vector);
+}
+
 static void *mlx5_ib_add(struct mlx5_core_dev *mdev)
 {
 	struct mlx5_ib_dev *dev;
@@ -3946,6 +3954,7 @@ static void *mlx5_ib_add(struct mlx5_core_dev *mdev)
 	dev->ib_dev.check_mr_status	= mlx5_ib_check_mr_status;
 	dev->ib_dev.get_port_immutable  = mlx5_port_immutable;
 	dev->ib_dev.get_dev_fw_str      = get_dev_fw_str;
+	dev->ib_dev.get_vector_affinity	= mlx5_ib_get_vector_affinity;
 	if (MLX5_CAP_GEN(mdev, ipoib_enhanced_offloads))
 		dev->ib_dev.alloc_rdma_netdev	= mlx5_ib_alloc_rdma_netdev;
 

drivers/infiniband/hw/mthca/mthca_cmd.c

@@ -1921,7 +1921,7 @@ int mthca_MAD_IFC(struct mthca_dev *dev, int ignore_mkey, int ignore_bkey,
 			(in_wc->wc_flags & IB_WC_GRH ? 0x80 : 0);
 		MTHCA_PUT(inbox, val,               MAD_IFC_G_PATH_OFFSET);
 
-		MTHCA_PUT(inbox, in_wc->slid,       MAD_IFC_RLID_OFFSET);
+		MTHCA_PUT(inbox, ib_slid_cpu16(in_wc->slid), MAD_IFC_RLID_OFFSET);
 		MTHCA_PUT(inbox, in_wc->pkey_index, MAD_IFC_PKEY_OFFSET);
 
 		if (in_grh)
@@ -1929,7 +1929,7 @@ int mthca_MAD_IFC(struct mthca_dev *dev, int ignore_mkey, int ignore_bkey,
 
 		op_modifier |= 0x4;
 
-		in_modifier |= in_wc->slid << 16;
+		in_modifier |= ib_slid_cpu16(in_wc->slid) << 16;
 	}
 
 	err = mthca_cmd_box(dev, inmailbox->dma, outmailbox->dma,

drivers/infiniband/hw/mthca/mthca_mad.c

@@ -205,7 +205,7 @@ int mthca_process_mad(struct ib_device *ibdev,
 		      u16 *out_mad_pkey_index)
 {
 	int err;
-	u16 slid = in_wc ? in_wc->slid : be16_to_cpu(IB_LID_PERMISSIVE);
+	u16 slid = in_wc ? ib_slid_cpu16(in_wc->slid) : be16_to_cpu(IB_LID_PERMISSIVE);
 	u16 prev_lid = 0;
 	struct ib_port_attr pattr;
 	const struct ib_mad *in_mad = (const struct ib_mad *)in;
@@ -256,7 +256,7 @@ int mthca_process_mad(struct ib_device *ibdev,
 	    in_mad->mad_hdr.method == IB_MGMT_METHOD_SET &&
 	    in_mad->mad_hdr.attr_id == IB_SMP_ATTR_PORT_INFO &&
 	    !ib_query_port(ibdev, port_num, &pattr))
-		prev_lid = pattr.lid;
+		prev_lid = (u16)pattr.lid;
 
 	err = mthca_MAD_IFC(to_mdev(ibdev),
 			    mad_flags & IB_MAD_IGNORE_MKEY,

drivers/infiniband/sw/rdmavt/cq.c

@@ -107,7 +107,7 @@ void rvt_cq_enter(struct rvt_cq *cq, struct ib_wc *entry, bool solicited)
 		wc->uqueue[head].src_qp = entry->src_qp;
 		wc->uqueue[head].wc_flags = entry->wc_flags;
 		wc->uqueue[head].pkey_index = entry->pkey_index;
-		wc->uqueue[head].slid = entry->slid;
+		wc->uqueue[head].slid = ib_slid_cpu16(entry->slid);
 		wc->uqueue[head].sl = entry->sl;
 		wc->uqueue[head].dlid_path_bits = entry->dlid_path_bits;
 		wc->uqueue[head].port_num = entry->port_num;

drivers/infiniband/ulp/ipoib/ipoib.h

@@ -366,7 +366,7 @@ struct ipoib_dev_priv {
 	u32		  qkey;
 
 	union ib_gid local_gid;
-	u16	     local_lid;
+	u32	     local_lid;
 
 	unsigned int admin_mtu;
 	unsigned int mcast_mtu;

drivers/infiniband/ulp/srpt/ib_srpt.h

@@ -328,8 +328,8 @@ struct srpt_port {
 	u8			port_guid[24];
 	u8			port_gid[64];
 	u8			port;
-	u16			sm_lid;
-	u16			lid;
+	u32			sm_lid;
+	u32			lid;
 	union ib_gid		gid;
 	struct work_struct	work;
 	struct se_portal_group	port_guid_tpg;

drivers/net/ethernet/mellanox/mlx5/core/en.h

@@ -587,7 +587,6 @@ struct mlx5e_channel {
 	struct mlx5_core_dev      *mdev;
 	struct mlx5e_tstamp       *tstamp;
 	int                        ix;
-	int                        cpu;
 };
 
 struct mlx5e_channels {

drivers/net/ethernet/mellanox/mlx5/core/en_main.c

@@ -71,6 +71,11 @@ struct mlx5e_channel_param {
 	struct mlx5e_cq_param      icosq_cq;
 };
 
+static int mlx5e_get_node(struct mlx5e_priv *priv, int ix)
+{
+	return pci_irq_get_node(priv->mdev->pdev, MLX5_EQ_VEC_COMP_BASE + ix);
+}
+
 static bool mlx5e_check_fragmented_striding_rq_cap(struct mlx5_core_dev *mdev)
 {
 	return MLX5_CAP_GEN(mdev, striding_rq) &&
@@ -397,7 +402,7 @@ static void mlx5e_enable_async_events(struct mlx5e_priv *priv)
 static void mlx5e_disable_async_events(struct mlx5e_priv *priv)
 {
 	clear_bit(MLX5E_STATE_ASYNC_EVENTS_ENABLED, &priv->state);
-	synchronize_irq(mlx5_get_msix_vec(priv->mdev, MLX5_EQ_VEC_ASYNC));
+	synchronize_irq(pci_irq_vector(priv->mdev->pdev, MLX5_EQ_VEC_ASYNC));
 }
 
 static inline int mlx5e_get_wqe_mtt_sz(void)
@@ -444,16 +449,17 @@ static int mlx5e_rq_alloc_mpwqe_info(struct mlx5e_rq *rq,
 	int wq_sz = mlx5_wq_ll_get_size(&rq->wq);
 	int mtt_sz = mlx5e_get_wqe_mtt_sz();
 	int mtt_alloc = mtt_sz + MLX5_UMR_ALIGN - 1;
+	int node = mlx5e_get_node(c->priv, c->ix);
 	int i;
 
 	rq->mpwqe.info = kzalloc_node(wq_sz * sizeof(*rq->mpwqe.info),
-				      GFP_KERNEL, cpu_to_node(c->cpu));
+					GFP_KERNEL, node);
 	if (!rq->mpwqe.info)
 		goto err_out;
 
 	/* We allocate more than mtt_sz as we will align the pointer */
-	rq->mpwqe.mtt_no_align = kzalloc_node(mtt_alloc * wq_sz, GFP_KERNEL,
-					cpu_to_node(c->cpu));
+	rq->mpwqe.mtt_no_align = kzalloc_node(mtt_alloc * wq_sz,
+					GFP_KERNEL, node);
 	if (unlikely(!rq->mpwqe.mtt_no_align))
 		goto err_free_wqe_info;
 
@@ -561,7 +567,7 @@ static int mlx5e_alloc_rq(struct mlx5e_channel *c,
 	int err;
 	int i;
 
-	rqp->wq.db_numa_node = cpu_to_node(c->cpu);
+	rqp->wq.db_numa_node = mlx5e_get_node(c->priv, c->ix);
 
 	err = mlx5_wq_ll_create(mdev, &rqp->wq, rqc_wq, &rq->wq,
 				&rq->wq_ctrl);
@@ -628,7 +634,8 @@ static int mlx5e_alloc_rq(struct mlx5e_channel *c,
 	default: /* MLX5_WQ_TYPE_LINKED_LIST */
 		rq->wqe.frag_info =
 			kzalloc_node(wq_sz * sizeof(*rq->wqe.frag_info),
-				     GFP_KERNEL, cpu_to_node(c->cpu));
+				     GFP_KERNEL,
+				     mlx5e_get_node(c->priv, c->ix));
 		if (!rq->wqe.frag_info) {
 			err = -ENOMEM;
 			goto err_rq_wq_destroy;
@@ -993,13 +1000,13 @@ static int mlx5e_alloc_xdpsq(struct mlx5e_channel *c,
 	sq->uar_map   = mdev->mlx5e_res.bfreg.map;
 	sq->min_inline_mode = params->tx_min_inline_mode;
 
-	param->wq.db_numa_node = cpu_to_node(c->cpu);
+	param->wq.db_numa_node = mlx5e_get_node(c->priv, c->ix);
 	err = mlx5_wq_cyc_create(mdev, &param->wq, sqc_wq, &sq->wq, &sq->wq_ctrl);
 	if (err)
 		return err;
 	sq->wq.db = &sq->wq.db[MLX5_SND_DBR];
 
-	err = mlx5e_alloc_xdpsq_db(sq, cpu_to_node(c->cpu));
+	err = mlx5e_alloc_xdpsq_db(sq, mlx5e_get_node(c->priv, c->ix));
 	if (err)
 		goto err_sq_wq_destroy;
 
@@ -1047,13 +1054,13 @@ static int mlx5e_alloc_icosq(struct mlx5e_channel *c,
 	sq->channel   = c;
 	sq->uar_map   = mdev->mlx5e_res.bfreg.map;
 
-	param->wq.db_numa_node = cpu_to_node(c->cpu);
+	param->wq.db_numa_node = mlx5e_get_node(c->priv, c->ix);
 	err = mlx5_wq_cyc_create(mdev, &param->wq, sqc_wq, &sq->wq, &sq->wq_ctrl);
 	if (err)
 		return err;
 	sq->wq.db = &sq->wq.db[MLX5_SND_DBR];
 
-	err = mlx5e_alloc_icosq_db(sq, cpu_to_node(c->cpu));
+	err = mlx5e_alloc_icosq_db(sq, mlx5e_get_node(c->priv, c->ix));
 	if (err)
 		goto err_sq_wq_destroy;
 
@@ -1119,13 +1126,13 @@ static int mlx5e_alloc_txqsq(struct mlx5e_channel *c,
 	if (MLX5_IPSEC_DEV(c->priv->mdev))
 		set_bit(MLX5E_SQ_STATE_IPSEC, &sq->state);
 
-	param->wq.db_numa_node = cpu_to_node(c->cpu);
+	param->wq.db_numa_node = mlx5e_get_node(c->priv, c->ix);
 	err = mlx5_wq_cyc_create(mdev, &param->wq, sqc_wq, &sq->wq, &sq->wq_ctrl);
 	if (err)
 		return err;
 	sq->wq.db    = &sq->wq.db[MLX5_SND_DBR];
 
-	err = mlx5e_alloc_txqsq_db(sq, cpu_to_node(c->cpu));
+	err = mlx5e_alloc_txqsq_db(sq, mlx5e_get_node(c->priv, c->ix));
 	if (err)
 		goto err_sq_wq_destroy;
 
@@ -1497,8 +1504,8 @@ static int mlx5e_alloc_cq(struct mlx5e_channel *c,
 	struct mlx5_core_dev *mdev = c->priv->mdev;
 	int err;
 
-	param->wq.buf_numa_node = cpu_to_node(c->cpu);
-	param->wq.db_numa_node  = cpu_to_node(c->cpu);
+	param->wq.buf_numa_node = mlx5e_get_node(c->priv, c->ix);
+	param->wq.db_numa_node  = mlx5e_get_node(c->priv, c->ix);
 	param->eq_ix   = c->ix;
 
 	err = mlx5e_alloc_cq_common(mdev, param, cq);
@@ -1597,11 +1604,6 @@ static void mlx5e_close_cq(struct mlx5e_cq *cq)
 	mlx5e_free_cq(cq);
 }
 
-static int mlx5e_get_cpu(struct mlx5e_priv *priv, int ix)
-{
-	return cpumask_first(priv->mdev->priv.irq_info[ix].mask);
-}
-
 static int mlx5e_open_tx_cqs(struct mlx5e_channel *c,
 			     struct mlx5e_params *params,
 			     struct mlx5e_channel_param *cparam)
@@ -1750,11 +1752,10 @@ static int mlx5e_open_channel(struct mlx5e_priv *priv, int ix,
 {
 	struct mlx5e_cq_moder icocq_moder = {0, 0};
 	struct net_device *netdev = priv->netdev;
-	int cpu = mlx5e_get_cpu(priv, ix);
 	struct mlx5e_channel *c;
 	int err;
 
-	c = kzalloc_node(sizeof(*c), GFP_KERNEL, cpu_to_node(cpu));
+	c = kzalloc_node(sizeof(*c), GFP_KERNEL, mlx5e_get_node(priv, ix));
 	if (!c)
 		return -ENOMEM;
 
@@ -1762,7 +1763,6 @@ static int mlx5e_open_channel(struct mlx5e_priv *priv, int ix,
 	c->mdev     = priv->mdev;
 	c->tstamp   = &priv->tstamp;
 	c->ix       = ix;
-	c->cpu      = cpu;
 	c->pdev     = &priv->mdev->pdev->dev;
 	c->netdev   = priv->netdev;
 	c->mkey_be  = cpu_to_be32(priv->mdev->mlx5e_res.mkey.key);
@@ -1848,7 +1848,8 @@ static void mlx5e_activate_channel(struct mlx5e_channel *c)
 	for (tc = 0; tc < c->num_tc; tc++)
 		mlx5e_activate_txqsq(&c->sq[tc]);
 	mlx5e_activate_rq(&c->rq);
-	netif_set_xps_queue(c->netdev, get_cpu_mask(c->cpu), c->ix);
+	netif_set_xps_queue(c->netdev,
+		mlx5_get_vector_affinity(c->priv->mdev, c->ix), c->ix);
 }
 
 static void mlx5e_deactivate_channel(struct mlx5e_channel *c)
@@ -3793,18 +3794,8 @@ void mlx5e_build_default_indir_rqt(struct mlx5_core_dev *mdev,
 				   u32 *indirection_rqt, int len,
 				   int num_channels)
 {
-	int node = mdev->priv.numa_node;
-	int node_num_of_cores;
 	int i;
 
-	if (node == -1)
-		node = first_online_node;
-
-	node_num_of_cores = cpumask_weight(cpumask_of_node(node));
-
-	if (node_num_of_cores)
-		num_channels = min_t(int, num_channels, node_num_of_cores);
-
 	for (i = 0; i < len; i++)
 		indirection_rqt[i] = i % num_channels;
 }

drivers/net/ethernet/mellanox/mlx5/core/eq.c

@@ -604,7 +604,7 @@ int mlx5_create_map_eq(struct mlx5_core_dev *dev, struct mlx5_eq *eq, u8 vecidx,
 		 name, pci_name(dev->pdev));
 
 	eq->eqn = MLX5_GET(create_eq_out, out, eq_number);
-	eq->irqn = priv->msix_arr[vecidx].vector;
+	eq->irqn = pci_irq_vector(dev->pdev, vecidx);
 	eq->dev = dev;
 	eq->doorbell = priv->uar->map + MLX5_EQ_DOORBEL_OFFSET;
 	err = request_irq(eq->irqn, handler, 0,
@@ -639,7 +639,7 @@ int mlx5_create_map_eq(struct mlx5_core_dev *dev, struct mlx5_eq *eq, u8 vecidx,
 	return 0;
 
 err_irq:
-	free_irq(priv->msix_arr[vecidx].vector, eq);
+	free_irq(eq->irqn, eq);
 
 err_eq:
 	mlx5_cmd_destroy_eq(dev, eq->eqn);
@@ -680,11 +680,6 @@ int mlx5_destroy_unmap_eq(struct mlx5_core_dev *dev, struct mlx5_eq *eq)
 }
 EXPORT_SYMBOL_GPL(mlx5_destroy_unmap_eq);
 
-u32 mlx5_get_msix_vec(struct mlx5_core_dev *dev, int vecidx)
-{
-	return dev->priv.msix_arr[MLX5_EQ_VEC_ASYNC].vector;
-}
-
 int mlx5_eq_init(struct mlx5_core_dev *dev)
 {
 	int err;

drivers/net/ethernet/mellanox/mlx5/core/eswitch.c

@@ -1585,7 +1585,7 @@ static void esw_disable_vport(struct mlx5_eswitch *esw, int vport_num)
 	/* Mark this vport as disabled to discard new events */
 	vport->enabled = false;
 
-	synchronize_irq(mlx5_get_msix_vec(esw->dev, MLX5_EQ_VEC_ASYNC));
+	synchronize_irq(pci_irq_vector(esw->dev->pdev, MLX5_EQ_VEC_ASYNC));
 	/* Wait for current already scheduled events to complete */
 	flush_workqueue(esw->work_queue);
 	/* Disable events from this vport */

drivers/net/ethernet/mellanox/mlx5/core/health.c

@@ -81,7 +81,7 @@ static void trigger_cmd_completions(struct mlx5_core_dev *dev)
 	u64 vector;
 
 	/* wait for pending handlers to complete */
-	synchronize_irq(dev->priv.msix_arr[MLX5_EQ_VEC_CMD].vector);
+	synchronize_irq(pci_irq_vector(dev->pdev, MLX5_EQ_VEC_CMD));
 	spin_lock_irqsave(&dev->cmd.alloc_lock, flags);
 	vector = ~dev->cmd.bitmask & ((1ul << (1 << dev->cmd.log_sz)) - 1);
 	if (!vector)

drivers/net/ethernet/mellanox/mlx5/core/main.c

@@ -313,13 +313,15 @@ static void release_bar(struct pci_dev *pdev)
 	pci_release_regions(pdev);
 }
 
-static int mlx5_enable_msix(struct mlx5_core_dev *dev)
+static int mlx5_alloc_irq_vectors(struct mlx5_core_dev *dev)
 {
 	struct mlx5_priv *priv = &dev->priv;
 	struct mlx5_eq_table *table = &priv->eq_table;
+	struct irq_affinity irqdesc = {
+		.pre_vectors = MLX5_EQ_VEC_COMP_BASE,
+	};
 	int num_eqs = 1 << MLX5_CAP_GEN(dev, log_max_eq);
 	int nvec;
-	int i;
 
 	nvec = MLX5_CAP_GEN(dev, num_ports) * num_online_cpus() +
 	       MLX5_EQ_VEC_COMP_BASE;
@@ -327,17 +329,14 @@ static int mlx5_enable_msix(struct mlx5_core_dev *dev)
 	if (nvec <= MLX5_EQ_VEC_COMP_BASE)
 		return -ENOMEM;
 
-	priv->msix_arr = kcalloc(nvec, sizeof(*priv->msix_arr), GFP_KERNEL);
-
 	priv->irq_info = kcalloc(nvec, sizeof(*priv->irq_info), GFP_KERNEL);
-	if (!priv->msix_arr || !priv->irq_info)
+	if (!priv->irq_info)
 		goto err_free_msix;
 
-	for (i = 0; i < nvec; i++)
-		priv->msix_arr[i].entry = i;
-
-	nvec = pci_enable_msix_range(dev->pdev, priv->msix_arr,
-				     MLX5_EQ_VEC_COMP_BASE + 1, nvec);
+	nvec = pci_alloc_irq_vectors_affinity(dev->pdev,
+			MLX5_EQ_VEC_COMP_BASE + 1, nvec,
+			PCI_IRQ_MSIX | PCI_IRQ_AFFINITY,
+			&irqdesc);
 	if (nvec < 0)
 		return nvec;
 
@@ -347,17 +346,15 @@ static int mlx5_enable_msix(struct mlx5_core_dev *dev)
 
 err_free_msix:
 	kfree(priv->irq_info);
-	kfree(priv->msix_arr);
 	return -ENOMEM;
 }
 
-static void mlx5_disable_msix(struct mlx5_core_dev *dev)
+static void mlx5_free_irq_vectors(struct mlx5_core_dev *dev)
 {
 	struct mlx5_priv *priv = &dev->priv;
 
-	pci_disable_msix(dev->pdev);
+	pci_free_irq_vectors(dev->pdev);
 	kfree(priv->irq_info);
-	kfree(priv->msix_arr);
 }
 
 struct mlx5_reg_host_endianness {
@@ -625,65 +622,6 @@ u64 mlx5_read_internal_timer(struct mlx5_core_dev *dev)
 	return (u64)timer_l | (u64)timer_h1 << 32;
 }
 
-static int mlx5_irq_set_affinity_hint(struct mlx5_core_dev *mdev, int i)
-{
-	struct mlx5_priv *priv  = &mdev->priv;
-	struct msix_entry *msix = priv->msix_arr;
-	int irq                 = msix[i + MLX5_EQ_VEC_COMP_BASE].vector;
-
-	if (!zalloc_cpumask_var(&priv->irq_info[i].mask, GFP_KERNEL)) {
-		mlx5_core_warn(mdev, "zalloc_cpumask_var failed");
-		return -ENOMEM;
-	}
-
-	cpumask_set_cpu(cpumask_local_spread(i, priv->numa_node),
-			priv->irq_info[i].mask);
-
-	if (IS_ENABLED(CONFIG_SMP) &&
-	    irq_set_affinity_hint(irq, priv->irq_info[i].mask))
-		mlx5_core_warn(mdev, "irq_set_affinity_hint failed, irq 0x%.4x", irq);
-
-	return 0;
-}
-
-static void mlx5_irq_clear_affinity_hint(struct mlx5_core_dev *mdev, int i)
-{
-	struct mlx5_priv *priv  = &mdev->priv;
-	struct msix_entry *msix = priv->msix_arr;
-	int irq                 = msix[i + MLX5_EQ_VEC_COMP_BASE].vector;
-
-	irq_set_affinity_hint(irq, NULL);
-	free_cpumask_var(priv->irq_info[i].mask);
-}
-
-static int mlx5_irq_set_affinity_hints(struct mlx5_core_dev *mdev)
-{
-	int err;
-	int i;
-
-	for (i = 0; i < mdev->priv.eq_table.num_comp_vectors; i++) {
-		err = mlx5_irq_set_affinity_hint(mdev, i);
-		if (err)
-			goto err_out;
-	}
-
-	return 0;
-
-err_out:
-	for (i--; i >= 0; i--)
-		mlx5_irq_clear_affinity_hint(mdev, i);
-
-	return err;
-}
-
-static void mlx5_irq_clear_affinity_hints(struct mlx5_core_dev *mdev)
-{
-	int i;
-
-	for (i = 0; i < mdev->priv.eq_table.num_comp_vectors; i++)
-		mlx5_irq_clear_affinity_hint(mdev, i);
-}
-
 int mlx5_vector2eqn(struct mlx5_core_dev *dev, int vector, int *eqn,
 		    unsigned int *irqn)
 {
@@ -773,8 +711,8 @@ static int alloc_comp_eqs(struct mlx5_core_dev *dev)
 		}
 
 #ifdef CONFIG_RFS_ACCEL
-		irq_cpu_rmap_add(dev->rmap,
-				 dev->priv.msix_arr[i + MLX5_EQ_VEC_COMP_BASE].vector);
+		irq_cpu_rmap_add(dev->rmap, pci_irq_vector(dev->pdev,
+				 MLX5_EQ_VEC_COMP_BASE + i));
 #endif
 		snprintf(name, MLX5_MAX_IRQ_NAME, "mlx5_comp%d", i);
 		err = mlx5_create_map_eq(dev, eq,
@@ -1132,9 +1070,9 @@ static int mlx5_load_one(struct mlx5_core_dev *dev, struct mlx5_priv *priv,
 		goto err_stop_poll;
 	}
 
-	err = mlx5_enable_msix(dev);
+	err = mlx5_alloc_irq_vectors(dev);
 	if (err) {
-		dev_err(&pdev->dev, "enable msix failed\n");
+		dev_err(&pdev->dev, "alloc irq vectors failed\n");
 		goto err_cleanup_once;
 	}
 
@@ -1156,12 +1094,6 @@ static int mlx5_load_one(struct mlx5_core_dev *dev, struct mlx5_priv *priv,
 		goto err_stop_eqs;
 	}
 
-	err = mlx5_irq_set_affinity_hints(dev);
-	if (err) {
-		dev_err(&pdev->dev, "Failed to alloc affinity hint cpumask\n");
-		goto err_affinity_hints;
-	}
-
 	err = mlx5_init_fs(dev);
 	if (err) {
 		dev_err(&pdev->dev, "Failed to init flow steering\n");
@@ -1227,9 +1159,6 @@ err_sriov:
 	mlx5_cleanup_fs(dev);
 
 err_fs:
-	mlx5_irq_clear_affinity_hints(dev);
-
-err_affinity_hints:
 	free_comp_eqs(dev);
 
 err_stop_eqs:
@@ -1239,7 +1168,7 @@ err_put_uars:
 	mlx5_put_uars_page(dev, priv->uar);
 
 err_disable_msix:
-	mlx5_disable_msix(dev);
+	mlx5_free_irq_vectors(dev);
 
 err_cleanup_once:
 	if (boot)
@@ -1302,11 +1231,10 @@ static int mlx5_unload_one(struct mlx5_core_dev *dev, struct mlx5_priv *priv,
 	mlx5_eswitch_detach(dev->priv.eswitch);
 #endif
 	mlx5_cleanup_fs(dev);
-	mlx5_irq_clear_affinity_hints(dev);
 	free_comp_eqs(dev);
 	mlx5_stop_eqs(dev);
 	mlx5_put_uars_page(dev, priv->uar);
-	mlx5_disable_msix(dev);
+	mlx5_free_irq_vectors(dev);
 	if (cleanup)
 		mlx5_cleanup_once(dev);
 	mlx5_stop_health_poll(dev);

drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h

@@ -110,7 +110,6 @@ int mlx5_destroy_scheduling_element_cmd(struct mlx5_core_dev *dev, u8 hierarchy,
 					u32 element_id);
 int mlx5_wait_for_vf_pages(struct mlx5_core_dev *dev);
 u64 mlx5_read_internal_timer(struct mlx5_core_dev *dev);
-u32 mlx5_get_msix_vec(struct mlx5_core_dev *dev, int vecidx);
 struct mlx5_eq *mlx5_eqn2eq(struct mlx5_core_dev *dev, int eqn);
 void mlx5_cq_tasklet_cb(unsigned long data);
 

drivers/nvme/host/rdma.c

@@ -19,6 +19,7 @@
 #include <linux/string.h>
 #include <linux/atomic.h>
 #include <linux/blk-mq.h>
+#include <linux/blk-mq-rdma.h>
 #include <linux/types.h>
 #include <linux/list.h>
 #include <linux/mutex.h>
@@ -463,14 +464,10 @@ static int nvme_rdma_create_queue_ib(struct nvme_rdma_queue *queue)
 	ibdev = queue->device->dev;
 
 	/*
-	 * The admin queue is barely used once the controller is live, so don't
-	 * bother to spread it out.
+	 * Spread I/O queues completion vectors according their queue index.
+	 * Admin queues can always go on completion vector 0.
 	 */
-	if (idx == 0)
-		comp_vector = 0;
-	else
-		comp_vector = idx % ibdev->num_comp_vectors;
-
+	comp_vector = idx == 0 ? idx : idx - 1;
 
 	/* +1 for ib_stop_cq */
 	queue->ib_cq = ib_alloc_cq(ibdev, queue,
@@ -611,10 +608,20 @@ out_free_queues:
 static int nvme_rdma_init_io_queues(struct nvme_rdma_ctrl *ctrl)
 {
 	struct nvmf_ctrl_options *opts = ctrl->ctrl.opts;
+	struct ib_device *ibdev = ctrl->device->dev;
 	unsigned int nr_io_queues;
 	int i, ret;
 
 	nr_io_queues = min(opts->nr_io_queues, num_online_cpus());
+
+	/*
+	 * we map queues according to the device irq vectors for
+	 * optimal locality so we don't need more queues than
+	 * completion vectors.
+	 */
+	nr_io_queues = min_t(unsigned int, nr_io_queues,
+				ibdev->num_comp_vectors);
+
 	ret = nvme_set_queue_count(&ctrl->ctrl, &nr_io_queues);
 	if (ret)
 		return ret;
@@ -1498,6 +1505,13 @@ static void nvme_rdma_complete_rq(struct request *rq)
 	nvme_complete_rq(rq);
 }
 
+static int nvme_rdma_map_queues(struct blk_mq_tag_set *set)
+{
+	struct nvme_rdma_ctrl *ctrl = set->driver_data;
+
+	return blk_mq_rdma_map_queues(set, ctrl->device->dev, 0);
+}
+
 static const struct blk_mq_ops nvme_rdma_mq_ops = {
 	.queue_rq	= nvme_rdma_queue_rq,
 	.complete	= nvme_rdma_complete_rq,
@@ -1507,6 +1521,7 @@ static const struct blk_mq_ops nvme_rdma_mq_ops = {
 	.init_hctx	= nvme_rdma_init_hctx,
 	.poll		= nvme_rdma_poll,
 	.timeout	= nvme_rdma_timeout,
+	.map_queues	= nvme_rdma_map_queues,
 };
 
 static const struct blk_mq_ops nvme_rdma_admin_mq_ops = {

include/linux/blk-mq-rdma.h

@@ -0,0 +1,10 @@
+#ifndef _LINUX_BLK_MQ_RDMA_H
+#define _LINUX_BLK_MQ_RDMA_H
+
+struct blk_mq_tag_set;
+struct ib_device;
+
+int blk_mq_rdma_map_queues(struct blk_mq_tag_set *set,
+		struct ib_device *dev, int first_vec);
+
+#endif /* _LINUX_BLK_MQ_RDMA_H */

include/linux/mlx5/driver.h

@@ -545,7 +545,6 @@ struct mlx5_core_sriov {
 };
 
 struct mlx5_irq_info {
-	cpumask_var_t mask;
 	char name[MLX5_MAX_IRQ_NAME];
 };
 
@@ -608,7 +607,6 @@ struct mlx5_port_module_event_stats {
 struct mlx5_priv {
 	char			name[MLX5_MAX_NAME_LEN];
 	struct mlx5_eq_table	eq_table;
-	struct msix_entry	*msix_arr;
 	struct mlx5_irq_info	*irq_info;
 
 	/* pages stuff */
@@ -1189,4 +1187,10 @@ enum {
 	MLX5_TRIGGERED_CMD_COMP = (u64)1 << 32,
 };
 
+static inline const struct cpumask *
+mlx5_get_vector_affinity(struct mlx5_core_dev *dev, int vector)
+{
+	return pci_irq_get_affinity(dev->pdev, MLX5_EQ_VEC_COMP_BASE + vector);
+}
+
 #endif /* MLX5_DRIVER_H */

include/rdma/ib_marshall.h

@@ -38,10 +38,12 @@
 #include <rdma/ib_user_verbs.h>
 #include <rdma/ib_user_sa.h>
 
-void ib_copy_qp_attr_to_user(struct ib_uverbs_qp_attr *dst,
+void ib_copy_qp_attr_to_user(struct ib_device *device,
+			     struct ib_uverbs_qp_attr *dst,
 			     struct ib_qp_attr *src);
 
-void ib_copy_ah_attr_to_user(struct ib_uverbs_ah_attr *dst,
+void ib_copy_ah_attr_to_user(struct ib_device *device,
+			     struct ib_uverbs_ah_attr *dst,
 			     struct rdma_ah_attr *src);
 
 void ib_copy_path_rec_to_user(struct ib_user_path_rec *dst,

include/rdma/ib_verbs.h

@@ -549,8 +549,8 @@ struct ib_port_attr {
 	u32			bad_pkey_cntr;
 	u32			qkey_viol_cntr;
 	u16			pkey_tbl_len;
-	u16			lid;
-	u16			sm_lid;
+	u32			sm_lid;
+	u32			lid;
 	u8			lmc;
 	u8			max_vl_num;
 	u8			sm_sl;
@@ -951,7 +951,7 @@ struct ib_wc {
 	u32			src_qp;
 	int			wc_flags;
 	u16			pkey_index;
-	u16			slid;
+	u32			slid;
 	u8			sl;
 	u8			dlid_path_bits;
 	u8			port_num;	/* valid only for DR SMPs on switches */
@@ -2306,6 +2306,8 @@ struct ib_device {
 	 */
 	int (*get_port_immutable)(struct ib_device *, u8, struct ib_port_immutable *);
 	void (*get_dev_fw_str)(struct ib_device *, char *str, size_t str_len);
+	const struct cpumask *(*get_vector_affinity)(struct ib_device *ibdev,
+						     int comp_vector);
 };
 
 struct ib_client {
@@ -3717,4 +3719,38 @@ static inline enum rdma_ah_attr_type rdma_ah_find_type(struct ib_device *dev,
 	else
 		return RDMA_AH_ATTR_TYPE_IB;
 }
+
+/* Return slid in 16bit CPU encoding */
+static inline u16 ib_slid_cpu16(u32 slid)
+{
+	return (u16)slid;
+}
+
+/* Return slid in 16bit BE encoding */
+static inline u16 ib_slid_be16(u32 slid)
+{
+	return cpu_to_be16((u16)slid);
+}
+
+/**
+ * ib_get_vector_affinity - Get the affinity mappings of a given completion
+ *   vector
+ * @device:         the rdma device
+ * @comp_vector:    index of completion vector
+ *
+ * Returns NULL on failure, otherwise a corresponding cpu map of the
+ * completion vector (returns all-cpus map if the device driver doesn't
+ * implement get_vector_affinity).
+ */
+static inline const struct cpumask *
+ib_get_vector_affinity(struct ib_device *device, int comp_vector)
+{
+	if (comp_vector < 0 || comp_vector >= device->num_comp_vectors ||
+	    !device->get_vector_affinity)
+		return NULL;
+
+	return device->get_vector_affinity(device, comp_vector);
+
+}
+
 #endif /* IB_VERBS_H */

include/rdma/opa_addr.h

@@ -50,7 +50,8 @@
 
 #define	OPA_SPECIAL_OUI		(0x00066AULL)
 #define OPA_MAKE_ID(x)          (cpu_to_be64(OPA_SPECIAL_OUI << 40 | (x)))
-
+#define OPA_TO_IB_UCAST_LID(x) (((x) >= be16_to_cpu(IB_MULTICAST_LID_BASE)) \
+				? 0 : x)
 /**
  * ib_is_opa_gid: Returns true if the top 24 bits of the gid
  * contains the OPA_STL_OUI identifier. This identifies that
@@ -76,4 +77,22 @@ static inline u32 opa_get_lid_from_gid(union ib_gid *gid)
 {
 	return be64_to_cpu(gid->global.interface_id) & 0xFFFFFFFF;
 }
+
+/**
+ * opa_is_extended_lid: Returns true if dlid or slid are
+ * extended.
+ *
+ * @dlid: The DLID
+ * @slid: The SLID
+ */
+static inline bool opa_is_extended_lid(u32 dlid, u32 slid)
+{
+	if ((be32_to_cpu(dlid) >=
+	     be16_to_cpu(IB_MULTICAST_LID_BASE)) ||
+	    (be32_to_cpu(slid) >=
+	     be16_to_cpu(IB_MULTICAST_LID_BASE)))
+		return true;
+	else
+		return false;
+}
 #endif /* OPA_ADDR_H */