1 files changed, 83 insertions, 114 deletions

diff --git a/drivers/infiniband/sw/rxe/rxe.c b/drivers/infiniband/sw/rxe/rxe.c
index 8e0f9c489cab..e891199cbdef 100644
--- a/drivers/infiniband/sw/rxe/rxe.c
+++ b/drivers/infiniband/sw/rxe/rxe.c
@@ -13,8 +13,6 @@ MODULE_AUTHOR("Bob Pearson, Frank Zago, John Groves, Kamal Heib");
 MODULE_DESCRIPTION("Soft RDMA transport");
 MODULE_LICENSE("Dual BSD/GPL");
 
-bool rxe_initialized;
-
 /* free resources for a rxe device all objects created for this device must
  * have been destroyed
  */
@@ -30,15 +28,18 @@ void rxe_dealloc(struct ib_device *ib_dev)
 	rxe_pool_cleanup(&rxe->cq_pool);
 	rxe_pool_cleanup(&rxe->mr_pool);
 	rxe_pool_cleanup(&rxe->mw_pool);
-	rxe_pool_cleanup(&rxe->mc_grp_pool);
-	rxe_pool_cleanup(&rxe->mc_elem_pool);
 
-	if (rxe->tfm)
-		crypto_free_shash(rxe->tfm);
+	WARN_ON(!RB_EMPTY_ROOT(&rxe->mcg_tree));
+
+	mutex_destroy(&rxe->usdev_lock);
 }
 
+static const struct ib_device_ops rxe_ib_dev_odp_ops = {
+	.advise_mr = rxe_ib_advise_mr,
+};
+
 /* initialize rxe device parameters */
-static void rxe_init_device_param(struct rxe_dev *rxe)
+static void rxe_init_device_param(struct rxe_dev *rxe, struct net_device *ndev)
 {
 	rxe->max_inline_data			= RXE_MAX_INLINE_DATA;
 
@@ -48,6 +49,7 @@ static void rxe_init_device_param(struct rxe_dev *rxe)
 	rxe->attr.max_qp			= RXE_MAX_QP;
 	rxe->attr.max_qp_wr			= RXE_MAX_QP_WR;
 	rxe->attr.device_cap_flags		= RXE_DEVICE_CAP_FLAGS;
+	rxe->attr.kernel_cap_flags		= IBK_ALLOW_USER_UNREG;
 	rxe->attr.max_send_sge			= RXE_MAX_SGE;
 	rxe->attr.max_recv_sge			= RXE_MAX_SGE;
 	rxe->attr.max_sge_rd			= RXE_MAX_SGE_RD;
@@ -70,10 +72,45 @@ static void rxe_init_device_param(struct rxe_dev *rxe)
 	rxe->attr.max_fast_reg_page_list_len	= RXE_MAX_FMR_PAGE_LIST_LEN;
 	rxe->attr.max_pkeys			= RXE_MAX_PKEYS;
 	rxe->attr.local_ca_ack_delay		= RXE_LOCAL_CA_ACK_DELAY;
+
+	if (ndev->addr_len) {
+		memcpy(rxe->raw_gid, ndev->dev_addr,
+			min_t(unsigned int, ndev->addr_len, ETH_ALEN));
+	} else {
+		/*
+		 * This device does not have a HW address, but
+		 * connection mangagement requires a unique gid.
+		 */
+		eth_random_addr(rxe->raw_gid);
+	}
+
 	addrconf_addr_eui48((unsigned char *)&rxe->attr.sys_image_guid,
-			rxe->ndev->dev_addr);
+			rxe->raw_gid);
 
 	rxe->max_ucontext			= RXE_MAX_UCONTEXT;
+
+	if (IS_ENABLED(CONFIG_INFINIBAND_ON_DEMAND_PAGING)) {
+		rxe->attr.kernel_cap_flags |= IBK_ON_DEMAND_PAGING;
+
+		/* IB_ODP_SUPPORT_IMPLICIT is not supported right now. */
+		rxe->attr.odp_caps.general_caps |= IB_ODP_SUPPORT;
+
+		rxe->attr.odp_caps.per_transport_caps.ud_odp_caps |= IB_ODP_SUPPORT_SEND;
+		rxe->attr.odp_caps.per_transport_caps.ud_odp_caps |= IB_ODP_SUPPORT_RECV;
+		rxe->attr.odp_caps.per_transport_caps.ud_odp_caps |= IB_ODP_SUPPORT_SRQ_RECV;
+
+		rxe->attr.odp_caps.per_transport_caps.rc_odp_caps |= IB_ODP_SUPPORT_SEND;
+		rxe->attr.odp_caps.per_transport_caps.rc_odp_caps |= IB_ODP_SUPPORT_RECV;
+		rxe->attr.odp_caps.per_transport_caps.rc_odp_caps |= IB_ODP_SUPPORT_WRITE;
+		rxe->attr.odp_caps.per_transport_caps.rc_odp_caps |= IB_ODP_SUPPORT_READ;
+		rxe->attr.odp_caps.per_transport_caps.rc_odp_caps |= IB_ODP_SUPPORT_ATOMIC;
+		rxe->attr.odp_caps.per_transport_caps.rc_odp_caps |= IB_ODP_SUPPORT_SRQ_RECV;
+		rxe->attr.odp_caps.per_transport_caps.rc_odp_caps |= IB_ODP_SUPPORT_FLUSH;
+		rxe->attr.odp_caps.per_transport_caps.rc_odp_caps |= IB_ODP_SUPPORT_ATOMIC_WRITE;
+
+		/* set handler for ODP prefetching API - ibv_advise_mr(3) */
+		ib_set_device_ops(&rxe->ib_dev, &rxe_ib_dev_odp_ops);
+	}
 }
 
 /* initialize port attributes */
@@ -105,117 +142,48 @@ static void rxe_init_port_param(struct rxe_port *port)
 /* initialize port state, note IB convention that HCA ports are always
  * numbered from 1
  */
-static void rxe_init_ports(struct rxe_dev *rxe)
+static void rxe_init_ports(struct rxe_dev *rxe, struct net_device *ndev)
 {
 	struct rxe_port *port = &rxe->port;
 
 	rxe_init_port_param(port);
 	addrconf_addr_eui48((unsigned char *)&port->port_guid,
-			    rxe->ndev->dev_addr);
+			    rxe->raw_gid);
 	spin_lock_init(&port->port_lock);
 }
 
 /* init pools of managed objects */
-static int rxe_init_pools(struct rxe_dev *rxe)
+static void rxe_init_pools(struct rxe_dev *rxe)
 {
-	int err;
-
-	err = rxe_pool_init(rxe, &rxe->uc_pool, RXE_TYPE_UC,
-			    rxe->max_ucontext);
-	if (err)
-		goto err1;
-
-	err = rxe_pool_init(rxe, &rxe->pd_pool, RXE_TYPE_PD,
-			    rxe->attr.max_pd);
-	if (err)
-		goto err2;
-
-	err = rxe_pool_init(rxe, &rxe->ah_pool, RXE_TYPE_AH,
-			    rxe->attr.max_ah);
-	if (err)
-		goto err3;
-
-	err = rxe_pool_init(rxe, &rxe->srq_pool, RXE_TYPE_SRQ,
-			    rxe->attr.max_srq);
-	if (err)
-		goto err4;
-
-	err = rxe_pool_init(rxe, &rxe->qp_pool, RXE_TYPE_QP,
-			    rxe->attr.max_qp);
-	if (err)
-		goto err5;
-
-	err = rxe_pool_init(rxe, &rxe->cq_pool, RXE_TYPE_CQ,
-			    rxe->attr.max_cq);
-	if (err)
-		goto err6;
-
-	err = rxe_pool_init(rxe, &rxe->mr_pool, RXE_TYPE_MR,
-			    rxe->attr.max_mr);
-	if (err)
-		goto err7;
-
-	err = rxe_pool_init(rxe, &rxe->mw_pool, RXE_TYPE_MW,
-			    rxe->attr.max_mw);
-	if (err)
-		goto err8;
-
-	err = rxe_pool_init(rxe, &rxe->mc_grp_pool, RXE_TYPE_MC_GRP,
-			    rxe->attr.max_mcast_grp);
-	if (err)
-		goto err9;
-
-	err = rxe_pool_init(rxe, &rxe->mc_elem_pool, RXE_TYPE_MC_ELEM,
-			    rxe->attr.max_total_mcast_qp_attach);
-	if (err)
-		goto err10;
-
-	return 0;
-
-err10:
-	rxe_pool_cleanup(&rxe->mc_grp_pool);
-err9:
-	rxe_pool_cleanup(&rxe->mw_pool);
-err8:
-	rxe_pool_cleanup(&rxe->mr_pool);
-err7:
-	rxe_pool_cleanup(&rxe->cq_pool);
-err6:
-	rxe_pool_cleanup(&rxe->qp_pool);
-err5:
-	rxe_pool_cleanup(&rxe->srq_pool);
-err4:
-	rxe_pool_cleanup(&rxe->ah_pool);
-err3:
-	rxe_pool_cleanup(&rxe->pd_pool);
-err2:
-	rxe_pool_cleanup(&rxe->uc_pool);
-err1:
-	return err;
+	rxe_pool_init(rxe, &rxe->uc_pool, RXE_TYPE_UC);
+	rxe_pool_init(rxe, &rxe->pd_pool, RXE_TYPE_PD);
+	rxe_pool_init(rxe, &rxe->ah_pool, RXE_TYPE_AH);
+	rxe_pool_init(rxe, &rxe->srq_pool, RXE_TYPE_SRQ);
+	rxe_pool_init(rxe, &rxe->qp_pool, RXE_TYPE_QP);
+	rxe_pool_init(rxe, &rxe->cq_pool, RXE_TYPE_CQ);
+	rxe_pool_init(rxe, &rxe->mr_pool, RXE_TYPE_MR);
+	rxe_pool_init(rxe, &rxe->mw_pool, RXE_TYPE_MW);
 }
 
 /* initialize rxe device state */
-static int rxe_init(struct rxe_dev *rxe)
+static void rxe_init(struct rxe_dev *rxe, struct net_device *ndev)
 {
-	int err;
-
 	/* init default device parameters */
-	rxe_init_device_param(rxe);
-
-	rxe_init_ports(rxe);
+	rxe_init_device_param(rxe, ndev);
 
-	err = rxe_init_pools(rxe);
-	if (err)
-		return err;
+	rxe_init_ports(rxe, ndev);
+	rxe_init_pools(rxe);
 
 	/* init pending mmap list */
 	spin_lock_init(&rxe->mmap_offset_lock);
 	spin_lock_init(&rxe->pending_lock);
 	INIT_LIST_HEAD(&rxe->pending_mmaps);
 
-	mutex_init(&rxe->usdev_lock);
+	/* init multicast support */
+	spin_lock_init(&rxe->mcg_lock);
+	rxe->mcg_tree = RB_ROOT;
 
-	return 0;
+	mutex_init(&rxe->usdev_lock);
 }
 
 void rxe_set_mtu(struct rxe_dev *rxe, unsigned int ndev_mtu)
@@ -235,41 +203,37 @@ void rxe_set_mtu(struct rxe_dev *rxe, unsigned int ndev_mtu)
 /* called by ifc layer to create new rxe device.
  * The caller should allocate memory for rxe by calling ib_alloc_device.
  */
-int rxe_add(struct rxe_dev *rxe, unsigned int mtu, const char *ibdev_name)
+int rxe_add(struct rxe_dev *rxe, unsigned int mtu, const char *ibdev_name,
+			struct net_device *ndev)
 {
-	int err;
-
-	err = rxe_init(rxe);
-	if (err)
-		return err;
-
+	rxe_init(rxe, ndev);
 	rxe_set_mtu(rxe, mtu);
 
-	return rxe_register_device(rxe, ibdev_name);
+	return rxe_register_device(rxe, ibdev_name, ndev);
 }
 
 static int rxe_newlink(const char *ibdev_name, struct net_device *ndev)
 {
-	struct rxe_dev *exists;
+	struct rxe_dev *rxe;
 	int err = 0;
 
 	if (is_vlan_dev(ndev)) {
-		pr_err("rxe creation allowed on top of a real device only\n");
+		rxe_err("rxe creation allowed on top of a real device only\n");
 		err = -EPERM;
 		goto err;
 	}
 
-	exists = rxe_get_dev_from_net(ndev);
-	if (exists) {
-		ib_device_put(&exists->ib_dev);
-		pr_err("already configured on %s\n", ndev->name);
+	rxe = rxe_get_dev_from_net(ndev);
+	if (rxe) {
+		ib_device_put(&rxe->ib_dev);
+		rxe_err_dev(rxe, "already configured on %s\n", ndev->name);
 		err = -EEXIST;
 		goto err;
 	}
 
 	err = rxe_net_add(ibdev_name, ndev);
 	if (err) {
-		pr_err("failed to add %s\n", ndev->name);
+		rxe_err("failed to add %s\n", ndev->name);
 		goto err;
 	}
 err:
@@ -285,12 +249,17 @@ static int __init rxe_module_init(void)
 {
 	int err;
 
-	err = rxe_net_init();
+	err = rxe_alloc_wq();
 	if (err)
 		return err;
 
+	err = rxe_net_init();
+	if (err) {
+		rxe_destroy_wq();
+		return err;
+	}
+
 	rdma_link_register(&rxe_link_ops);
-	rxe_initialized = true;
 	pr_info("loaded\n");
 	return 0;
 }
@@ -300,8 +269,8 @@ static void __exit rxe_module_exit(void)
 	rdma_link_unregister(&rxe_link_ops);
 	ib_unregister_driver(RDMA_DRIVER_RXE);
 	rxe_net_exit();
+	rxe_destroy_wq();
 
-	rxe_initialized = false;
 	pr_info("unloaded\n");
 }