[PATCH for-next 00/11] Add network namespace support in the RDMA-CM

@@ -38,6 +38,7 @@
 #include <linux/slab.h>
 #include <linux/init.h>
 #include <linux/mutex.h>
+#include <linux/netdevice.h>
 #include <rdma/rdma_netlink.h>
 
 #include "core_priv.h"

@@ -733,6 +734,62 @@ int ib_find_pkey(struct ib_device *device,
 }
 EXPORT_SYMBOL(ib_find_pkey);
 
+static struct net_device *ib_get_net_dev_by_port_pkey_ip(struct ib_device *dev,
+							 u8 port,
+							 u16 pkey,
+							 struct sockaddr *addr)
+{
+	struct net_device *ret = NULL;
+	struct ib_client *client;
+
+	mutex_lock(&device_mutex);
+	list_for_each_entry(client, &client_list, list)
+		if (client->get_net_device_by_port_pkey_ip) {
+			ret = client->get_net_device_by_port_pkey_ip(dev, port,
+								     pkey,
+								     addr);
+			if (ret)
+				break;
+		}
+
+	mutex_unlock(&device_mutex);
+	return ret;
+}
+
+struct net *ib_get_net_ns_by_port_pkey_ip(struct ib_device *dev,
+					  u8 port,
+					  u16 pkey,
+					  struct sockaddr *addr)
+{
+	struct net_device *ndev = NULL;
+	struct net *ns;
+
+	switch (rdma_port_get_link_layer(dev, port)) {
+	case IB_LINK_LAYER_INFINIBAND:
+		if (!addr)
+			goto not_found;
+		ndev = ib_get_net_dev_by_port_pkey_ip(dev, port, pkey, addr);
+		break;
+	default:
+		goto not_found;
+	}
+
+	if (!ndev)
+		goto not_found;
+
+	rcu_read_lock();
+	ns = maybe_get_net(dev_net(ndev));
+	dev_put(ndev);
+	rcu_read_unlock();
+	if (!ns)
+		goto not_found;
+	return ns;
+
+not_found:
+	return get_net(&init_net);
+}
+EXPORT_SYMBOL(ib_get_net_ns_by_port_pkey_ip);
+
 static int __init ib_core_init(void)
 {
 	int ret;

@@ -1683,6 +1683,21 @@ struct ib_client {
 	void (*add)   (struct ib_device *);
 	void (*remove)(struct ib_device *);
 
+	/* Returns the net_dev belonging to this ib_client and matching the
+	 * given parameters.
+	 * @dev:	An RDMA device that the net_dev use for communication.
+	 * @port:	A physical port number on the RDMA device.
+	 * @pkey:	P_Key that the net_dev uses if applicable.
+	 * @addr:	An IP address the net_dev is configured with.
+	 *
+	 * An ib_client that implements a net_dev on top of RDMA devices
+	 * (such as IP over IB) should implement this callback, allowing the
+	 * rdma_cm module to find the right net_dev for a given request. */
+	struct net_device *(*get_net_device_by_port_pkey_ip)(
+			struct ib_device *dev,
+			u8 port,
+			u16 pkey,
+			struct sockaddr *addr);
 	struct list_head list;
 };
 

@@ -2682,4 +2697,18 @@ static inline int ib_check_mr_access(int flags)
 int ib_check_mr_status(struct ib_mr *mr, u32 check_mask,
 		       struct ib_mr_status *mr_status);
 
+/**
+ * ib_get_net_ns_by_port_pkey_ip() - Return the appropriate net namespace
+ * for a received CM request
+ * @dev:	An RDMA device on which the request has been received.
+ * @port:	Port number on the RDMA device.
+ * @pkey:	The Pkey the request came on.
+ * @addr:	Contains the IP address that the request specified as its
+ *		destination.
+ */
+struct net *ib_get_net_ns_by_port_pkey_ip(struct ib_device *dev,
+					  u8 port,
+					  u16 pkey,
+					  struct sockaddr *addr);
+
 #endif /* IB_VERBS_H */

@@ -128,7 +128,7 @@ int rdma_translate_ip(struct sockaddr *addr, struct rdma_dev_addr *dev_addr,
 	int ret = -EADDRNOTAVAIL;
 
 	if (dev_addr->bound_dev_if) {
-		dev = dev_get_by_index(&init_net, dev_addr->bound_dev_if);
+		dev = dev_get_by_index(dev_addr->net, dev_addr->bound_dev_if);
 		if (!dev)
 			return -ENODEV;
 		ret = rdma_copy_addr(dev_addr, dev, NULL);

@@ -137,9 +137,10 @@ int rdma_translate_ip(struct sockaddr *addr, struct rdma_dev_addr *dev_addr,
 	}
 
 	switch (addr->sa_family) {
-	case AF_INET:
-		dev = ip_dev_find(&init_net,
-			((struct sockaddr_in *) addr)->sin_addr.s_addr);
+	case AF_INET: {
+		struct sockaddr_in *addr_in = (struct sockaddr_in *)addr;
+
+		dev = ip_dev_find(dev_addr->net, addr_in->sin_addr.s_addr);
 
 		if (!dev)
 			return ret;

@@ -149,12 +150,12 @@ int rdma_translate_ip(struct sockaddr *addr, struct rdma_dev_addr *dev_addr,
 			*vlan_id = rdma_vlan_dev_vlan_id(dev);
 		dev_put(dev);
 		break;
-
+	}
 #if IS_ENABLED(CONFIG_IPV6)
 	case AF_INET6:
 		rcu_read_lock();
-		for_each_netdev_rcu(&init_net, dev) {
-			if (ipv6_chk_addr(&init_net,
+		for_each_netdev_rcu(dev_addr->net, dev) {
+			if (ipv6_chk_addr(dev_addr->net,
 					  &((struct sockaddr_in6 *) addr)->sin6_addr,
 					  dev, 1)) {
 				ret = rdma_copy_addr(dev_addr, dev, NULL);

@@ -236,7 +237,7 @@ static int addr4_resolve(struct sockaddr_in *src_in,
 	fl4.daddr = dst_ip;
 	fl4.saddr = src_ip;
 	fl4.flowi4_oif = addr->bound_dev_if;
-	rt = ip_route_output_key(&init_net, &fl4);
+	rt = ip_route_output_key(addr->net, &fl4);
 	if (IS_ERR(rt)) {
 		ret = PTR_ERR(rt);
 		goto out;

@@ -278,12 +279,13 @@ static int addr6_resolve(struct sockaddr_in6 *src_in,
 	fl6.saddr = src_in->sin6_addr;
 	fl6.flowi6_oif = addr->bound_dev_if;
 
-	dst = ip6_route_output(&init_net, NULL, &fl6);
+	dst = ip6_route_output(addr->net, NULL, &fl6);
 	if ((ret = dst->error))
 		goto put;
 
 	if (ipv6_addr_any(&fl6.saddr)) {
-		ret = ipv6_dev_get_saddr(&init_net, ip6_dst_idev(dst)->dev,
+		ret = ipv6_dev_get_saddr(addr->net,
+					 ip6_dst_idev(dst)->dev,
 					 &fl6.daddr, 0, &fl6.saddr);
 		if (ret)
 			goto put;

@@ -458,7 +460,7 @@ static void resolve_cb(int status, struct sockaddr *src_addr,
 }
 
 int rdma_addr_find_dmac_by_grh(union ib_gid *sgid, union ib_gid *dgid, u8 *dmac,
-			       u16 *vlan_id)
+			       u16 *vlan_id, struct net *net)
 {
 	int ret = 0;
 	struct rdma_dev_addr dev_addr;

@@ -481,6 +483,7 @@ int rdma_addr_find_dmac_by_grh(union ib_gid *sgid, union ib_gid *dgid, u8 *dmac,
 		return ret;
 
 	memset(&dev_addr, 0, sizeof(dev_addr));
+	dev_addr.net = net;
 
 	ctx.addr = &dev_addr;
 	init_completion(&ctx.comp);

@@ -492,7 +495,7 @@ int rdma_addr_find_dmac_by_grh(union ib_gid *sgid, union ib_gid *dgid, u8 *dmac,
 	wait_for_completion(&ctx.comp);
 
 	memcpy(dmac, dev_addr.dst_dev_addr, ETH_ALEN);
-	dev = dev_get_by_index(&init_net, dev_addr.bound_dev_if);
+	dev = dev_get_by_index(net, dev_addr.bound_dev_if);
 	if (!dev)
 		return -ENODEV;
 	if (vlan_id)

@@ -502,7 +505,8 @@ int rdma_addr_find_dmac_by_grh(union ib_gid *sgid, union ib_gid *dgid, u8 *dmac,
 }
 EXPORT_SYMBOL(rdma_addr_find_dmac_by_grh);
 
-int rdma_addr_find_smac_by_sgid(union ib_gid *sgid, u8 *smac, u16 *vlan_id)
+int rdma_addr_find_smac_by_sgid(union ib_gid *sgid, u8 *smac, u16 *vlan_id,
+				struct net *net)
 {
 	int ret = 0;
 	struct rdma_dev_addr dev_addr;

@@ -517,6 +521,7 @@ int rdma_addr_find_smac_by_sgid(union ib_gid *sgid, u8 *smac, u16 *vlan_id)
 	if (ret)
 		return ret;
 	memset(&dev_addr, 0, sizeof(dev_addr));
+	dev_addr.net = net;
 	ret = rdma_translate_ip(&gid_addr._sockaddr, &dev_addr, vlan_id);
 	if (ret)
 		return ret;

@@ -512,6 +512,7 @@ struct rdma_cm_id *rdma_create_id(rdma_cm_event_handler event_handler,
 	INIT_LIST_HEAD(&id_priv->listen_list);
 	INIT_LIST_HEAD(&id_priv->mc_list);
 	get_random_bytes(&id_priv->seq_num, sizeof id_priv->seq_num);
+	id_priv->id.route.addr.dev_addr.net = &init_net;
 
 	return &id_priv->id;
 }

@@ -637,7 +638,8 @@ static int cma_modify_qp_rtr(struct rdma_id_private *id_priv,
 	    == RDMA_TRANSPORT_IB &&
 	    rdma_port_get_link_layer(id_priv->id.device, id_priv->id.port_num)
 	    == IB_LINK_LAYER_ETHERNET) {
-		ret = rdma_addr_find_smac_by_sgid(&sgid, qp_attr.smac, NULL);
+		ret = rdma_addr_find_smac_by_sgid(&sgid, qp_attr.smac, NULL,
+						  &init_net);
 
 		if (ret)
 			goto out;

@@ -212,7 +212,9 @@ int ib_init_ah_from_wc(struct ib_device *device, u8 port_num, struct ib_wc *wc,
 			ah_attr->vlan_id = wc->vlan_id;
 		} else {
 			ret = rdma_addr_find_dmac_by_grh(&grh->dgid, &grh->sgid,
-					ah_attr->dmac, &ah_attr->vlan_id);
+							 ah_attr->dmac,
+							 &ah_attr->vlan_id,
+							 &init_net);
 			if (ret)
 				return ret;
 		}

@@ -882,11 +884,15 @@ int ib_resolve_eth_l2_attrs(struct ib_qp *qp,
 			if (!(*qp_attr_mask & IB_QP_VID))
 				qp_attr->vlan_id = rdma_get_vlan_id(&sgid);
 		} else {
-			ret = rdma_addr_find_dmac_by_grh(&sgid, &qp_attr->ah_attr.grh.dgid,
-					qp_attr->ah_attr.dmac, &qp_attr->vlan_id);
+			ret = rdma_addr_find_dmac_by_grh(
+				&sgid,
+				&qp_attr->ah_attr.grh.dgid,
+				qp_attr->ah_attr.dmac, &qp_attr->vlan_id,
+				&init_net);
 			if (ret)
 				goto out;
-			ret = rdma_addr_find_smac_by_sgid(&sgid, qp_attr->smac, NULL);
+			ret = rdma_addr_find_smac_by_sgid(&sgid, qp_attr->smac,
+							  NULL, &init_net);
 			if (ret)
 				goto out;
 		}

@@ -119,7 +119,8 @@ struct ib_ah *ocrdma_create_ah(struct ib_pd *ibpd, struct ib_ah_attr *attr)
 
 	if (pd->uctx) {
 		status = rdma_addr_find_dmac_by_grh(&sgid, &attr->grh.dgid,
-                                        attr->dmac, &attr->vlan_id);
+						    attr->dmac, &attr->vlan_id,
+						    &init_net);
 		if (status) {
 			pr_err("%s(): Failed to resolve dmac from gid." 
 				"status = %d\n", __func__, status);

@@ -47,6 +47,7 @@
 #include <rdma/ib_verbs.h>
 #include <rdma/ib_pack.h>
 #include <net/ipv6.h>
+#include <net/net_namespace.h>
 
 struct rdma_addr_client {
 	atomic_t refcount;

@@ -64,6 +65,16 @@ void rdma_addr_register_client(struct rdma_addr_client *client);
  */
 void rdma_addr_unregister_client(struct rdma_addr_client *client);
 
+/**
+ * struct rdma_dev_addr - Contains resolved RDMA hardware addresses
+ * @src_dev_addr:	Source MAC address.
+ * @dst_dev_addr:	Destination MAC address.
+ * @broadcast:		Broadcast address of the device.
+ * @dev_type:		The interface hardware type of the device.
+ * @bound_dev_if:	An optional device interface index.
+ * @transport:		The transport type used.
+ * @net:		Network namespace containing the bound_dev_if net_dev.
+ */
 struct rdma_dev_addr {
 	unsigned char src_dev_addr[MAX_ADDR_LEN];
 	unsigned char dst_dev_addr[MAX_ADDR_LEN];

@@ -71,11 +82,14 @@ struct rdma_dev_addr {
 	unsigned short dev_type;
 	int bound_dev_if;
 	enum rdma_transport_type transport;
+	struct net *net;
 };
 
 /**
  * rdma_translate_ip - Translate a local IP address to an RDMA hardware
  *   address.
+ *
+ * The dev_addr->net field must be initialized.
  */
 int rdma_translate_ip(struct sockaddr *addr, struct rdma_dev_addr *dev_addr,
 		      u16 *vlan_id);

@@ -90,7 +104,7 @@ int rdma_translate_ip(struct sockaddr *addr, struct rdma_dev_addr *dev_addr,
  * @dst_addr: The destination address to resolve.
  * @addr: A reference to a data location that will receive the resolved
  *   addresses.  The data location must remain valid until the callback has
- *   been invoked.
+ *   been invoked. The net field of the addr struct must be valid.
  * @timeout_ms: Amount of time to wait for the address resolution to complete.
  * @callback: Call invoked once address resolution has completed, timed out,
  *   or been canceled.  A status of 0 indicates success.

@@ -110,9 +124,29 @@ int rdma_copy_addr(struct rdma_dev_addr *dev_addr, struct net_device *dev,
 
 int rdma_addr_size(struct sockaddr *addr);
 
-int rdma_addr_find_smac_by_sgid(union ib_gid *sgid, u8 *smac, u16 *vlan_id);
-int rdma_addr_find_dmac_by_grh(union ib_gid *sgid, union ib_gid *dgid, u8 *smac,
-			       u16 *vlan_id);
+/** rdma_addr_find_smac_by_sgid() - Find the src MAC and VLAN ID for a src GID
+ * @sgid:	Source GID to find the MAC and VLAN for.
+ * @smac:	A buffer to contain the resulting MAC address.
+ * @vlan_id:	Will contain the resulting VLAN ID.
+ * @net:	Network namespace to use for the address resolution.
+ *
+ * It is the caller's responsibility to keep the network namespace alive until
+ * the function returns.
+ */
+int rdma_addr_find_smac_by_sgid(union ib_gid *sgid, u8 *smac, u16 *vlan_id,
+				struct net *net);
+/** rdma_addr_find_dmac_by_grh() - Find the dst MAC and VLAN ID for a GID pair
+ * @sgid:	Source GID to use for the search.
+ * @dgid:	Destination GID to find the details for.
+ * @dmac:	Contains the resulting destination MAC address.
+ * @vlan_id:	Contains the resulting VLAN ID.
+ * @net:	Network namespace to use for the address resolution.
+ *
+ * It is the caller's responsibility to keep the network namespace alive until
+ * the function returns.
+ */
+int rdma_addr_find_dmac_by_grh(union ib_gid *sgid, union ib_gid *dgid, u8 *dmac,
+			       u16 *vlan_id, struct net *net);
 
 static inline u16 ib_addr_get_pkey(struct rdma_dev_addr *dev_addr)
 {

@@ -182,7 +216,7 @@ static inline void iboe_addr_get_sgid(struct rdma_dev_addr *dev_addr,
 	struct net_device *dev;
 	struct in_device *ip4;
 
-	dev = dev_get_by_index(&init_net, dev_addr->bound_dev_if);
+	dev = dev_get_by_index(dev_addr->net, dev_addr->bound_dev_if);
 	if (dev) {
 		ip4 = (struct in_device *)dev->ip_ptr;
 		if (ip4 && ip4->ifa_list && ip4->ifa_list->ifa_address)

@@ -39,11 +39,13 @@
 #include <linux/mutex.h>
 #include <linux/random.h>
 #include <linux/idr.h>
+#include <linux/radix-tree.h>
 #include <linux/inetdevice.h>
 #include <linux/slab.h>
 #include <linux/module.h>
 #include <net/route.h>
 
+#include <net/netns/hash.h>
 #include <net/tcp.h>
 #include <net/ipv6.h>
 

@@ -80,10 +82,83 @@ static LIST_HEAD(dev_list);
 static LIST_HEAD(listen_any_list);
 static DEFINE_MUTEX(lock);
 static struct workqueue_struct *cma_wq;
-static DEFINE_IDR(tcp_ps);
-static DEFINE_IDR(udp_ps);
-static DEFINE_IDR(ipoib_ps);
-static DEFINE_IDR(ib_ps);
+static RADIX_TREE(tcp_ps, GFP_KERNEL);
+static RADIX_TREE(udp_ps, GFP_KERNEL);
+static RADIX_TREE(ipoib_ps, GFP_KERNEL);
+static RADIX_TREE(ib_ps, GFP_KERNEL);
+
+static LIST_HEAD(idrs_list);
+
+struct idr_ll {
+	unsigned net_val;
+	struct net *net;
+	struct radix_tree_root *ps;
+	struct idr idr;
+};
+
+static void zap_ps_idr(struct idr_ll *idr_ll)
+{
+	radix_tree_delete(idr_ll->ps, idr_ll->net_val);
+	idr_destroy(&idr_ll->idr);
+	kfree(idr_ll);
+}
+
+static int cma_ps_alloc(struct radix_tree_root *ps, struct net *net, void *ptr,
+			int snum)
+{
+	struct idr_ll *idr_ll;
+	int err;
+	int res;
+
+	idr_ll = radix_tree_lookup(ps, net_hash_mix(net));
+	if (!idr_ll) {
+		idr_ll = kmalloc(sizeof(*idr_ll), GFP_KERNEL);
+		if (!idr_ll)
+			return -ENOMEM;
+		idr_init(&idr_ll->idr);
+		idr_ll->net_val = net_hash_mix(net);
+		idr_ll->net = net;
+		idr_ll->ps = ps;
+		err = radix_tree_insert(ps, idr_ll->net_val, idr_ll);
+		if (err) {
+			idr_destroy(&idr_ll->idr);
+			kfree(idr_ll);
+			return err;
+		}
+	}
+	res = idr_alloc(&idr_ll->idr, ptr, snum, snum + 1, GFP_KERNEL);
+	if (unlikely((res < 0) && idr_is_empty(&idr_ll->idr))) {
+		zap_ps_idr(idr_ll);
+		return res;
+	}
+	return res;
+}
+
+static void *cma_ps_find(struct radix_tree_root *ps, struct net *net, int snum)
+{
+	struct idr_ll *idr_ll;
+
+	idr_ll = radix_tree_lookup(ps, net_hash_mix(net));
+	if (!idr_ll)
+		return NULL;
+	return idr_find(&idr_ll->idr, snum);
+}
+
+static void cma_ps_remove(struct radix_tree_root *ps, struct net *net, int snum)
+{
+	struct idr_ll *idr_ll;
+
+	idr_ll = radix_tree_lookup(ps, net_hash_mix(net));
+	if (unlikely(!idr_ll)) {
+		WARN(1, "cma_ps_removed can't find expected net ns 0x%lx\n",
+		     (unsigned long)net);
+		return;
+	}
+	idr_remove(&idr_ll->idr, snum);
+	if (idr_is_empty(&idr_ll->idr)) {
+		zap_ps_idr(idr_ll);
+	}
+}
 
 struct cma_device {
 	struct list_head	list;

@@ -94,9 +169,9 @@ struct cma_device {
 };
 
 struct rdma_bind_list {
-	struct idr		*ps;
-	struct hlist_head	owners;
-	unsigned short		port;
+	struct radix_tree_root	*ps;
+	struct hlist_head		owners;
+	unsigned short			port;
 };
 
 enum {

@@ -885,7 +960,7 @@ static void cma_release_port(struct rdma_id_private *id_priv)
 	mutex_lock(&lock);
 	hlist_del(&id_priv->node);
 	if (hlist_empty(&bind_list->owners)) {
-		idr_remove(bind_list->ps, bind_list->port);
+		cma_ps_remove(bind_list->ps, &init_net, bind_list->port);
 		kfree(bind_list);
 	}
 	mutex_unlock(&lock);

@@ -2198,8 +2273,8 @@ static void cma_bind_port(struct rdma_bind_list *bind_list,
 	hlist_add_head(&id_priv->node, &bind_list->owners);
 }
 
-static int cma_alloc_port(struct idr *ps, struct rdma_id_private *id_priv,
-			  unsigned short snum)
+static int cma_alloc_port(struct radix_tree_root *ps,
+			  struct rdma_id_private *id_priv, unsigned short snum)
 {
 	struct rdma_bind_list *bind_list;
 	int ret;

@@ -2208,7 +2283,7 @@ static int cma_alloc_port(struct idr *ps, struct rdma_id_private *id_priv,
 	if (!bind_list)
 		return -ENOMEM;
 
-	ret = idr_alloc(ps, bind_list, snum, snum + 1, GFP_KERNEL);
+	ret = cma_ps_alloc(ps, &init_net, bind_list, snum);
 	if (ret < 0)
 		goto err;
 

@@ -2221,7 +2296,8 @@ err:
 	return ret == -ENOSPC ? -EADDRNOTAVAIL : ret;
 }
 
-static int cma_alloc_any_port(struct idr *ps, struct rdma_id_private *id_priv)
+static int cma_alloc_any_port(struct radix_tree_root *ps,
+			      struct rdma_id_private *id_priv)
 {
 	static unsigned int last_used_port;
 	int low, high, remaining;

@@ -2232,7 +2308,7 @@ static int cma_alloc_any_port(struct idr *ps, struct rdma_id_private *id_priv)
 	rover = prandom_u32() % remaining + low;
 retry:
 	if (last_used_port != rover &&
-	    !idr_find(ps, (unsigned short) rover)) {
+	    !cma_ps_find(ps, &init_net, (unsigned short)rover)) {
 		int ret = cma_alloc_port(ps, id_priv, rover);
 		/*
 		 * Remember previously used port number in order to avoid

@@ -2257,6 +2333,8 @@ retry:
  * bind to a specific port, or when trying to listen on a bound port.  In
  * the latter case, the provided id_priv may already be on the bind_list, but
  * we still need to check that it's okay to start listening.
+ *
+ * Assume the bind_list contains only services from the correct name space.
  */
 static int cma_check_port(struct rdma_bind_list *bind_list,
 			  struct rdma_id_private *id_priv, uint8_t reuseaddr)

@@ -2287,7 +2365,8 @@ static int cma_check_port(struct rdma_bind_list *bind_list,
 	return 0;
 }
 
-static int cma_use_port(struct idr *ps, struct rdma_id_private *id_priv)
+static int cma_use_port(struct radix_tree_root *ps,
+			struct rdma_id_private *id_priv)
 {
 	struct rdma_bind_list *bind_list;
 	unsigned short snum;

@@ -2297,7 +2376,7 @@ static int cma_use_port(struct idr *ps, struct rdma_id_private *id_priv)
 	if (snum < PROT_SOCK && !capable(CAP_NET_BIND_SERVICE))
 		return -EACCES;
 
-	bind_list = idr_find(ps, snum);
+	bind_list = cma_ps_find(ps, &init_net, snum);
 	if (!bind_list) {
 		ret = cma_alloc_port(ps, id_priv, snum);
 	} else {

@@ -2320,7 +2399,8 @@ static int cma_bind_listen(struct rdma_id_private *id_priv)
 	return ret;
 }
 
-static struct idr *cma_select_inet_ps(struct rdma_id_private *id_priv)
+static struct radix_tree_root *cma_select_inet_ps(
+		struct rdma_id_private *id_priv)
 {
 	switch (id_priv->id.ps) {
 	case RDMA_PS_TCP:

@@ -2336,9 +2416,9 @@ static struct idr *cma_select_inet_ps(struct rdma_id_private *id_priv)
 	}
 }
 
-static struct idr *cma_select_ib_ps(struct rdma_id_private *id_priv)
+static struct radix_tree_root *cma_select_ib_ps(struct rdma_id_private *id_priv)
 {
-	struct idr *ps = NULL;
+	struct radix_tree_root *ps = NULL;
 	struct sockaddr_ib *sib;
 	u64 sid_ps, mask, sid;
 

@@ -2369,7 +2449,7 @@ static struct idr *cma_select_ib_ps(struct rdma_id_private *id_priv)
 
 static int cma_get_port(struct rdma_id_private *id_priv)
 {
-	struct idr *ps;
+	struct radix_tree_root *ps;
 	int ret;
 
 	if (cma_family(id_priv) != AF_IB)

@@ -3567,10 +3647,6 @@ static void __exit cma_cleanup(void)
 	rdma_addr_unregister_client(&addr_client);
 	ib_sa_unregister_client(&sa_client);
 	destroy_workqueue(cma_wq);
-	idr_destroy(&tcp_ps);
-	idr_destroy(&udp_ps);
-	idr_destroy(&ipoib_ps);
-	idr_destroy(&ib_ps);
 }
 
 module_init(cma_init);

@@ -45,6 +45,7 @@
 #include <linux/idr.h>
 #include <linux/mutex.h>
 #include <linux/slab.h>
+#include <linux/nsproxy.h>
 
 #include <asm/uaccess.h>
 

@@ -490,7 +491,7 @@ static ssize_t ib_ucm_create_id(struct ib_ucm_file *file,
 	ctx->uid = cmd.uid;
 	ctx->cm_id = ib_create_cm_id(file->device->ib_dev,
 				     ib_ucm_event_handler, ctx,
-				     &init_net);
+				     current->nsproxy->net_ns);
 	if (IS_ERR(ctx->cm_id)) {
 		result = PTR_ERR(ctx->cm_id);
 		goto err1;

@@ -42,6 +42,7 @@
 #include <linux/slab.h>
 #include <linux/sysctl.h>
 #include <linux/module.h>
+#include <linux/nsproxy.h>
 
 #include <rdma/rdma_user_cm.h>
 #include <rdma/ib_marshall.h>

@@ -392,7 +393,7 @@ static ssize_t ucma_create_id(struct ucma_file *file, const char __user *inbuf,
 
 	ctx->uid = cmd.uid;
 	ctx->cm_id = rdma_create_id(ucma_event_handler, ctx, cmd.ps, qp_type,
-				    &init_net);
+				    current->nsproxy->net_ns);
 	if (IS_ERR(ctx->cm_id)) {
 		ret = PTR_ERR(ctx->cm_id);
 		goto err1;