[PATCH v6 0/4] Add network namespace support in the RDMA-CM

[PATCH v6 0/4] Add network namespace support in the RDMA-CM

[Haggai Eran]

Hi,

Now that the code for demuxing requests is inside rdma_cm, here are the patches
to add InfiniBand network namespace again.

Changes from v5:
- removed patches that got in as part of the cleanup series.

RDMA-CM uses IP based addressing and routing to setup RDMA connections between
hosts. Currently, all of the IP interfaces and addresses used by the RDMA-CM
must reside in the init_net namespace. This restricts the usage of containers
with RDMA to only work with host network namespace (aka the kernel init_net NS
instance).

This patchset allows using network namespaces with the RDMA-CM.

Each RDMA-CM id keeps a reference to a network namespace.

This reference is based on the process network namespace at the time of the
creation of the object or inherited from the listener.

This network namespace is used to perform all IP and network related
operations. Specifically, the local device lookup, as well as the remote GID
address resolution are done in the context of the RDMA-CM object's namespace.
This allows outgoing connections to reach the right target, even if the same
IP address exists in multiple network namespaces. This can happen if each
network namespace resides on a different P_Key.

Additionally, the network namespace is used to split the listener port space
tables. From the user point of view, each network namespace has a unique,
completely independent tables for its port spaces. This allows running multiple
instances of a single service on the same machine, using containers. 

The functionality introduced by this series would come into play when the
transport is InfiniBand and IPoIB interfaces are assigned to each namespace.
Multiple IPoIB interfaces can be created and assigned to different RDMA-CM
capable containers, for example using pipework [1].

The patches apply against Doug's to-be-rebased tree for v4.3.

The patchset is structured as follows:

Patch 1 is a relatively trivial API extension, requiring the callers
of certain ib_addr functions to provide a network namespace, as needed.

Patches 2-4 add proper namespace support to the RDMA-CM module. This
includes adding multiple port space tables, adding a network namespace
parameter, and finally retrieving the namespace from the creating process.

[1] https://github.com/jpetazzo/pipework/pull/108

Guy Shapiro (3):
  IB/addr: Pass network namespace as a parameter
  IB/cma: Add support for network namespaces
  IB/ucma: Take the network namespace from the process

Haggai Eran (1):
  IB/cma: Separate port allocation to network namespaces

 drivers/infiniband/core/addr.c                     |  17 +--
 drivers/infiniband/core/cma.c                      | 129 +++++++++++++++------
 drivers/infiniband/core/ucma.c                     |   4 +-
 drivers/infiniband/ulp/iser/iser_verbs.c           |   2 +-
 drivers/infiniband/ulp/isert/ib_isert.c            |   2 +-
 .../staging/lustre/lnet/klnds/o2iblnd/o2iblnd.h    |   4 +-
 include/rdma/ib_addr.h                             |  16 ++-
 include/rdma/rdma_cm.h                             |   6 +-
 net/9p/trans_rdma.c                                |   4 +-
 net/rds/ib.c                                       |   2 +-
 net/rds/ib_cm.c                                    |   2 +-
 net/rds/iw.c                                       |   2 +-
 net/rds/iw_cm.c                                    |   2 +-
 net/rds/rdma_transport.c                           |   4 +-
 net/sunrpc/xprtrdma/svc_rdma_transport.c           |   4 +-
 net/sunrpc/xprtrdma/verbs.c                        |   3 +-
 16 files changed, 142 insertions(+), 61 deletions(-)

-- 
1.7.11.2

--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

[PATCH v6 1/4] IB/addr: Pass network namespace as a parameter

[Haggai Eran]

From: Guy Shapiro <guysh-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>

Add network namespace support to the ib_addr module. For that, all the
address resolution and matching should be done using the appropriate
namespace instead of init_net.

This is achieved by:

1. Adding an explicit network namespace argument to exported function that
   require a namespace.
2. Saving the namespace in the rdma_addr_client structure.
3. Using it when calling networking functions.

In order to preserve the behavior of calling modules, &init_net is
passed as the parameter in calls from other modules. This is modified as
namespace support is added on more levels.

Signed-off-by: Haggai Eran <haggaie-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
Signed-off-by: Yotam Kenneth <yotamke-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
Signed-off-by: Shachar Raindel <raindel-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
Signed-off-by: Guy Shapiro <guysh-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
---
 drivers/infiniband/core/addr.c | 17 +++++++++--------
 drivers/infiniband/core/cma.c  |  1 +
 include/rdma/ib_addr.h         | 16 +++++++++++++++-
 3 files changed, 25 insertions(+), 9 deletions(-)

diff --git a/drivers/infiniband/core/addr.c b/drivers/infiniband/core/addr.c
index 746cdf56bc76..6ed9685efebd 100644
--- a/drivers/infiniband/core/addr.c
+++ b/drivers/infiniband/core/addr.c
@@ -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);
@@ -138,7 +138,7 @@ 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,
+		dev = ip_dev_find(dev_addr->net,
 			((struct sockaddr_in *) addr)->sin_addr.s_addr);
 
 		if (!dev)
@@ -149,12 +149,11 @@ 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 +235,7 @@ 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 +277,12 @@ 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;
@@ -476,6 +475,7 @@ int rdma_addr_find_dmac_by_grh(const union ib_gid *sgid, const union ib_gid *dgi
 	rdma_gid2ip(&dgid_addr._sockaddr, dgid);
 
 	memset(&dev_addr, 0, sizeof(dev_addr));
+	dev_addr.net = &init_net;
 
 	ctx.addr = &dev_addr;
 	init_completion(&ctx.comp);
@@ -510,6 +510,7 @@ int rdma_addr_find_smac_by_sgid(union ib_gid *sgid, u8 *smac, u16 *vlan_id)
 	rdma_gid2ip(&gid_addr._sockaddr, sgid);
 
 	memset(&dev_addr, 0, sizeof(dev_addr));
+	dev_addr.net = &init_net;
 	ret = rdma_translate_ip(&gid_addr._sockaddr, &dev_addr, vlan_id);
 	if (ret)
 		return ret;
diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c
index b1ab13f3e182..0530c6188e75 100644
--- a/drivers/infiniband/core/cma.c
+++ b/drivers/infiniband/core/cma.c
@@ -601,6 +601,7 @@ 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;
 }
diff --git a/include/rdma/ib_addr.h b/include/rdma/ib_addr.h
index fde33ac6b58a..3d9afc3bc601 100644
--- a/include/rdma/ib_addr.h
+++ b/include/rdma/ib_addr.h
@@ -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.
-- 
1.7.11.2

--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

[PATCH v6 2/4] IB/cma: Separate port allocation to network namespaces

[Haggai Eran]

Keep a struct for each network namespace containing the IDRs for the RDMA
CM port spaces. The struct is created dynamically using the generic_net
mechanism.

This patch is internal infrastructure work for the following patches. In
this patch, init_net is statically used as the network namespace for
the new port-space API.

Signed-off-by: Haggai Eran <haggaie-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
Signed-off-by: Yotam Kenneth <yotamke-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
Signed-off-by: Shachar Raindel <raindel-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
Signed-off-by: Guy Shapiro <guysh-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
---
 drivers/infiniband/core/cma.c | 94 ++++++++++++++++++++++++++++++++-----------
 1 file changed, 70 insertions(+), 24 deletions(-)

diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c
index 0530c6188e75..f40ca053fa3e 100644
--- a/drivers/infiniband/core/cma.c
+++ b/drivers/infiniband/core/cma.c
@@ -44,6 +44,8 @@
 #include <linux/module.h>
 #include <net/route.h>
 
+#include <net/net_namespace.h>
+#include <net/netns/generic.h>
 #include <net/tcp.h>
 #include <net/ipv6.h>
 #include <net/ip_fib.h>
@@ -110,22 +112,33 @@ 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 int cma_pernet_id;
 
-static struct idr *cma_idr(enum rdma_port_space ps)
+struct cma_pernet {
+	struct idr tcp_ps;
+	struct idr udp_ps;
+	struct idr ipoib_ps;
+	struct idr ib_ps;
+};
+
+static struct cma_pernet *cma_pernet(struct net *net)
+{
+	return net_generic(net, cma_pernet_id);
+}
+
+static struct idr *cma_pernet_idr(struct net *net, enum rdma_port_space ps)
 {
+	struct cma_pernet *pernet = cma_pernet(net);
+
 	switch (ps) {
 	case RDMA_PS_TCP:
-		return &tcp_ps;
+		return &pernet->tcp_ps;
 	case RDMA_PS_UDP:
-		return &udp_ps;
+		return &pernet->udp_ps;
 	case RDMA_PS_IPOIB:
-		return &ipoib_ps;
+		return &pernet->ipoib_ps;
 	case RDMA_PS_IB:
-		return &ib_ps;
+		return &pernet->ib_ps;
 	default:
 		return NULL;
 	}
@@ -145,24 +158,25 @@ struct rdma_bind_list {
 	unsigned short		port;
 };
 
-static int cma_ps_alloc(enum rdma_port_space ps,
+static int cma_ps_alloc(struct net *net, enum rdma_port_space ps,
 			struct rdma_bind_list *bind_list, int snum)
 {
-	struct idr *idr = cma_idr(ps);
+	struct idr *idr = cma_pernet_idr(net, ps);
 
 	return idr_alloc(idr, bind_list, snum, snum + 1, GFP_KERNEL);
 }
 
-static struct rdma_bind_list *cma_ps_find(enum rdma_port_space ps, int snum)
+static struct rdma_bind_list *cma_ps_find(struct net *net,
+					  enum rdma_port_space ps, int snum)
 {
-	struct idr *idr = cma_idr(ps);
+	struct idr *idr = cma_pernet_idr(net, ps);
 
 	return idr_find(idr, snum);
 }
 
-static void cma_ps_remove(enum rdma_port_space ps, int snum)
+static void cma_ps_remove(struct net *net, enum rdma_port_space ps, int snum)
 {
-	struct idr *idr = cma_idr(ps);
+	struct idr *idr = cma_pernet_idr(net, ps);
 
 	idr_remove(idr, snum);
 }
@@ -1300,7 +1314,8 @@ static struct rdma_id_private *cma_id_from_event(struct ib_cm_id *cm_id,
 		}
 	}
 
-	bind_list = cma_ps_find(rdma_ps_from_service_id(req.service_id),
+	bind_list = cma_ps_find(&init_net,
+				rdma_ps_from_service_id(req.service_id),
 				cma_port_from_service_id(req.service_id));
 	id_priv = cma_find_listener(bind_list, cm_id, ib_event, &req, *net_dev);
 	if (IS_ERR(id_priv)) {
@@ -1378,7 +1393,7 @@ 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)) {
-		cma_ps_remove(bind_list->ps, bind_list->port);
+		cma_ps_remove(&init_net, bind_list->ps, bind_list->port);
 		kfree(bind_list);
 	}
 	mutex_unlock(&lock);
@@ -2663,7 +2678,7 @@ static int cma_alloc_port(enum rdma_port_space ps,
 	if (!bind_list)
 		return -ENOMEM;
 
-	ret = cma_ps_alloc(ps, bind_list, snum);
+	ret = cma_ps_alloc(&init_net, ps, bind_list, snum);
 	if (ret < 0)
 		goto err;
 
@@ -2688,7 +2703,7 @@ static int cma_alloc_any_port(enum rdma_port_space ps,
 	rover = prandom_u32() % remaining + low;
 retry:
 	if (last_used_port != rover &&
-	    !cma_ps_find(ps, (unsigned short)rover)) {
+	    !cma_ps_find(&init_net, ps, (unsigned short)rover)) {
 		int ret = cma_alloc_port(ps, id_priv, rover);
 		/*
 		 * Remember previously used port number in order to avoid
@@ -2754,7 +2769,7 @@ static int cma_use_port(enum rdma_port_space ps,
 	if (snum < PROT_SOCK && !capable(CAP_NET_BIND_SERVICE))
 		return -EACCES;
 
-	bind_list = cma_ps_find(ps, snum);
+	bind_list = cma_ps_find(&init_net, ps, snum);
 	if (!bind_list) {
 		ret = cma_alloc_port(ps, id_priv, snum);
 	} else {
@@ -3974,6 +3989,35 @@ static const struct ibnl_client_cbs cma_cb_table[] = {
 				       .module = THIS_MODULE },
 };
 
+static int cma_init_net(struct net *net)
+{
+	struct cma_pernet *pernet = cma_pernet(net);
+
+	idr_init(&pernet->tcp_ps);
+	idr_init(&pernet->udp_ps);
+	idr_init(&pernet->ipoib_ps);
+	idr_init(&pernet->ib_ps);
+
+	return 0;
+}
+
+static void cma_exit_net(struct net *net)
+{
+	struct cma_pernet *pernet = cma_pernet(net);
+
+	idr_destroy(&pernet->tcp_ps);
+	idr_destroy(&pernet->udp_ps);
+	idr_destroy(&pernet->ipoib_ps);
+	idr_destroy(&pernet->ib_ps);
+}
+
+static struct pernet_operations cma_pernet_operations = {
+	.init = cma_init_net,
+	.exit = cma_exit_net,
+	.id = &cma_pernet_id,
+	.size = sizeof(struct cma_pernet),
+};
+
 static int __init cma_init(void)
 {
 	int ret;
@@ -3982,6 +4026,10 @@ static int __init cma_init(void)
 	if (!cma_wq)
 		return -ENOMEM;
 
+	ret = register_pernet_subsys(&cma_pernet_operations);
+	if (ret)
+		goto err_wq;
+
 	ib_sa_register_client(&sa_client);
 	rdma_addr_register_client(&addr_client);
 	register_netdevice_notifier(&cma_nb);
@@ -3999,6 +4047,7 @@ err:
 	unregister_netdevice_notifier(&cma_nb);
 	rdma_addr_unregister_client(&addr_client);
 	ib_sa_unregister_client(&sa_client);
+err_wq:
 	destroy_workqueue(cma_wq);
 	return ret;
 }
@@ -4010,11 +4059,8 @@ static void __exit cma_cleanup(void)
 	unregister_netdevice_notifier(&cma_nb);
 	rdma_addr_unregister_client(&addr_client);
 	ib_sa_unregister_client(&sa_client);
+	unregister_pernet_subsys(&cma_pernet_operations);
 	destroy_workqueue(cma_wq);
-	idr_destroy(&tcp_ps);
-	idr_destroy(&udp_ps);
-	idr_destroy(&ipoib_ps);
-	idr_destroy(&ib_ps);
 }
 
 module_init(cma_init);
-- 
1.7.11.2

--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

[PATCH v6 3/4] IB/cma: Add support for network namespaces

[Haggai Eran]

From: Guy Shapiro <guysh-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>

Add support for network namespaces in the ib_cma module. This is
accomplished by:

1. Adding network namespace parameter for rdma_create_id. This parameter is
   used to populate the network namespace field in rdma_id_private.
   rdma_create_id keeps a reference on the network namespace.
2. Using the network namespace from the rdma_id instead of init_net inside
   of ib_cma, when listening on an ID and when looking for an ID for an
   incoming request.
3. Decrementing the reference count for the appropriate network namespace
   when calling rdma_destroy_id.

In order to preserve the current behavior init_net is passed when calling
from other modules.

Signed-off-by: Guy Shapiro <guysh-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
Signed-off-by: Haggai Eran <haggaie-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
Signed-off-by: Yotam Kenneth <yotamke-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
Signed-off-by: Shachar Raindel <raindel-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
---
 drivers/infiniband/core/cma.c                      | 46 +++++++++++++---------
 drivers/infiniband/core/ucma.c                     |  3 +-
 drivers/infiniband/ulp/iser/iser_verbs.c           |  2 +-
 drivers/infiniband/ulp/isert/ib_isert.c            |  2 +-
 .../staging/lustre/lnet/klnds/o2iblnd/o2iblnd.h    |  4 +-
 include/rdma/rdma_cm.h                             |  6 ++-
 net/9p/trans_rdma.c                                |  4 +-
 net/rds/ib.c                                       |  2 +-
 net/rds/ib_cm.c                                    |  2 +-
 net/rds/iw.c                                       |  2 +-
 net/rds/iw_cm.c                                    |  2 +-
 net/rds/rdma_transport.c                           |  4 +-
 net/sunrpc/xprtrdma/svc_rdma_transport.c           |  4 +-
 net/sunrpc/xprtrdma/verbs.c                        |  3 +-
 14 files changed, 52 insertions(+), 34 deletions(-)

diff --git a/drivers/infiniband/core/cma.c b/drivers/infiniband/core/cma.c
index f40ca053fa3e..debf25ccf930 100644
--- a/drivers/infiniband/core/cma.c
+++ b/drivers/infiniband/core/cma.c
@@ -591,7 +591,8 @@ static int cma_disable_callback(struct rdma_id_private *id_priv,
 	return 0;
 }
 
-struct rdma_cm_id *rdma_create_id(rdma_cm_event_handler event_handler,
+struct rdma_cm_id *rdma_create_id(struct net *net,
+				  rdma_cm_event_handler event_handler,
 				  void *context, enum rdma_port_space ps,
 				  enum ib_qp_type qp_type)
 {
@@ -615,7 +616,7 @@ 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;
+	id_priv->id.route.addr.dev_addr.net = get_net(net);
 
 	return &id_priv->id;
 }
@@ -1257,7 +1258,7 @@ static bool cma_match_net_dev(const struct rdma_id_private *id_priv,
 		return addr->src_addr.ss_family == AF_IB;
 
 	return !addr->dev_addr.bound_dev_if ||
-	       (net_eq(dev_net(net_dev), &init_net) &&
+	       (net_eq(dev_net(net_dev), addr->dev_addr.net) &&
 		addr->dev_addr.bound_dev_if == net_dev->ifindex);
 }
 
@@ -1314,7 +1315,7 @@ static struct rdma_id_private *cma_id_from_event(struct ib_cm_id *cm_id,
 		}
 	}
 
-	bind_list = cma_ps_find(&init_net,
+	bind_list = cma_ps_find(dev_net(*net_dev),
 				rdma_ps_from_service_id(req.service_id),
 				cma_port_from_service_id(req.service_id));
 	id_priv = cma_find_listener(bind_list, cm_id, ib_event, &req, *net_dev);
@@ -1386,6 +1387,7 @@ static void cma_cancel_operation(struct rdma_id_private *id_priv,
 static void cma_release_port(struct rdma_id_private *id_priv)
 {
 	struct rdma_bind_list *bind_list = id_priv->bind_list;
+	struct net *net = id_priv->id.route.addr.dev_addr.net;
 
 	if (!bind_list)
 		return;
@@ -1393,7 +1395,7 @@ 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)) {
-		cma_ps_remove(&init_net, bind_list->ps, bind_list->port);
+		cma_ps_remove(net, bind_list->ps, bind_list->port);
 		kfree(bind_list);
 	}
 	mutex_unlock(&lock);
@@ -1452,6 +1454,7 @@ void rdma_destroy_id(struct rdma_cm_id *id)
 		cma_deref_id(id_priv->id.context);
 
 	kfree(id_priv->id.route.path_rec);
+	put_net(id_priv->id.route.addr.dev_addr.net);
 	kfree(id_priv);
 }
 EXPORT_SYMBOL(rdma_destroy_id);
@@ -1582,7 +1585,8 @@ static struct rdma_id_private *cma_new_conn_id(struct rdma_cm_id *listen_id,
 		      ib_event->param.req_rcvd.primary_path->service_id;
 	int ret;
 
-	id = rdma_create_id(listen_id->event_handler, listen_id->context,
+	id = rdma_create_id(listen_id->route.addr.dev_addr.net,
+			    listen_id->event_handler, listen_id->context,
 			    listen_id->ps, ib_event->param.req_rcvd.qp_type);
 	if (IS_ERR(id))
 		return NULL;
@@ -1632,9 +1636,10 @@ static struct rdma_id_private *cma_new_udp_id(struct rdma_cm_id *listen_id,
 	struct rdma_id_private *id_priv;
 	struct rdma_cm_id *id;
 	const sa_family_t ss_family = listen_id->route.addr.src_addr.ss_family;
+	struct net *net = listen_id->route.addr.dev_addr.net;
 	int ret;
 
-	id = rdma_create_id(listen_id->event_handler, listen_id->context,
+	id = rdma_create_id(net, listen_id->event_handler, listen_id->context,
 			    listen_id->ps, IB_QPT_UD);
 	if (IS_ERR(id))
 		return NULL;
@@ -1872,7 +1877,8 @@ static int iw_conn_req_handler(struct iw_cm_id *cm_id,
 		return -ECONNABORTED;
 
 	/* Create a new RDMA id for the new IW CM ID */
-	new_cm_id = rdma_create_id(listen_id->id.event_handler,
+	new_cm_id = rdma_create_id(listen_id->id.route.addr.dev_addr.net,
+				   listen_id->id.event_handler,
 				   listen_id->id.context,
 				   RDMA_PS_TCP, IB_QPT_RC);
 	if (IS_ERR(new_cm_id)) {
@@ -2000,12 +2006,13 @@ static void cma_listen_on_dev(struct rdma_id_private *id_priv,
 {
 	struct rdma_id_private *dev_id_priv;
 	struct rdma_cm_id *id;
+	struct net *net = id_priv->id.route.addr.dev_addr.net;
 	int ret;
 
 	if (cma_family(id_priv) == AF_IB && !rdma_cap_ib_cm(cma_dev->device, 1))
 		return;
 
-	id = rdma_create_id(cma_listen_handler, id_priv, id_priv->id.ps,
+	id = rdma_create_id(net, cma_listen_handler, id_priv, id_priv->id.ps,
 			    id_priv->id.qp_type);
 	if (IS_ERR(id))
 		return;
@@ -2678,7 +2685,8 @@ static int cma_alloc_port(enum rdma_port_space ps,
 	if (!bind_list)
 		return -ENOMEM;
 
-	ret = cma_ps_alloc(&init_net, ps, bind_list, snum);
+	ret = cma_ps_alloc(id_priv->id.route.addr.dev_addr.net, ps, bind_list,
+			   snum);
 	if (ret < 0)
 		goto err;
 
@@ -2697,13 +2705,14 @@ static int cma_alloc_any_port(enum rdma_port_space ps,
 	static unsigned int last_used_port;
 	int low, high, remaining;
 	unsigned int rover;
+	struct net *net = id_priv->id.route.addr.dev_addr.net;
 
-	inet_get_local_port_range(&init_net, &low, &high);
+	inet_get_local_port_range(net, &low, &high);
 	remaining = (high - low) + 1;
 	rover = prandom_u32() % remaining + low;
 retry:
 	if (last_used_port != rover &&
-	    !cma_ps_find(&init_net, ps, (unsigned short)rover)) {
+	    !cma_ps_find(net, ps, (unsigned short)rover)) {
 		int ret = cma_alloc_port(ps, id_priv, rover);
 		/*
 		 * Remember previously used port number in order to avoid
@@ -2769,7 +2778,7 @@ static int cma_use_port(enum rdma_port_space ps,
 	if (snum < PROT_SOCK && !capable(CAP_NET_BIND_SERVICE))
 		return -EACCES;
 
-	bind_list = cma_ps_find(&init_net, ps, snum);
+	bind_list = cma_ps_find(id_priv->id.route.addr.dev_addr.net, ps, snum);
 	if (!bind_list) {
 		ret = cma_alloc_port(ps, id_priv, snum);
 	} else {
@@ -2961,8 +2970,11 @@ int rdma_bind_addr(struct rdma_cm_id *id, struct sockaddr *addr)
 		if (addr->sa_family == AF_INET)
 			id_priv->afonly = 1;
 #if IS_ENABLED(CONFIG_IPV6)
-		else if (addr->sa_family == AF_INET6)
-			id_priv->afonly = init_net.ipv6.sysctl.bindv6only;
+		else if (addr->sa_family == AF_INET6) {
+			struct net *net = id_priv->id.route.addr.dev_addr.net;
+
+			id_priv->afonly = net->ipv6.sysctl.bindv6only;
+		}
 #endif
 	}
 	ret = cma_get_port(id_priv);
@@ -3767,6 +3779,7 @@ static int cma_netdev_change(struct net_device *ndev, struct rdma_id_private *id
 	dev_addr = &id_priv->id.route.addr.dev_addr;
 
 	if ((dev_addr->bound_dev_if == ndev->ifindex) &&
+	    (net_eq(dev_net(ndev), dev_addr->net)) &&
 	    memcmp(dev_addr->src_dev_addr, ndev->dev_addr, ndev->addr_len)) {
 		printk(KERN_INFO "RDMA CM addr change for ndev %s used by id %p\n",
 		       ndev->name, &id_priv->id);
@@ -3792,9 +3805,6 @@ static int cma_netdev_callback(struct notifier_block *self, unsigned long event,
 	struct rdma_id_private *id_priv;
 	int ret = NOTIFY_DONE;
 
-	if (dev_net(ndev) != &init_net)
-		return NOTIFY_DONE;
-
 	if (event != NETDEV_BONDING_FAILOVER)
 		return NOTIFY_DONE;
 
diff --git a/drivers/infiniband/core/ucma.c b/drivers/infiniband/core/ucma.c
index a53fc9b01c69..82a17a7b7e6d 100644
--- a/drivers/infiniband/core/ucma.c
+++ b/drivers/infiniband/core/ucma.c
@@ -472,7 +472,8 @@ static ssize_t ucma_create_id(struct ucma_file *file, const char __user *inbuf,
 		return -ENOMEM;
 
 	ctx->uid = cmd.uid;
-	ctx->cm_id = rdma_create_id(ucma_event_handler, ctx, cmd.ps, qp_type);
+	ctx->cm_id = rdma_create_id(&init_net, ucma_event_handler, ctx, cmd.ps,
+				    qp_type);
 	if (IS_ERR(ctx->cm_id)) {
 		ret = PTR_ERR(ctx->cm_id);
 		goto err1;
diff --git a/drivers/infiniband/ulp/iser/iser_verbs.c b/drivers/infiniband/ulp/iser/iser_verbs.c
index ae70cc1463ac..2896ed64da73 100644
--- a/drivers/infiniband/ulp/iser/iser_verbs.c
+++ b/drivers/infiniband/ulp/iser/iser_verbs.c
@@ -1012,7 +1012,7 @@ int iser_connect(struct iser_conn   *iser_conn,
 	ib_conn->beacon.wr_id = ISER_BEACON_WRID;
 	ib_conn->beacon.opcode = IB_WR_SEND;
 
-	ib_conn->cma_id = rdma_create_id(iser_cma_handler,
+	ib_conn->cma_id = rdma_create_id(&init_net, iser_cma_handler,
 					 (void *)iser_conn,
 					 RDMA_PS_TCP, IB_QPT_RC);
 	if (IS_ERR(ib_conn->cma_id)) {
diff --git a/drivers/infiniband/ulp/isert/ib_isert.c b/drivers/infiniband/ulp/isert/ib_isert.c
index dc439a40da3f..797fc398c266 100644
--- a/drivers/infiniband/ulp/isert/ib_isert.c
+++ b/drivers/infiniband/ulp/isert/ib_isert.c
@@ -3065,7 +3065,7 @@ isert_setup_id(struct isert_np *isert_np)
 	sa = (struct sockaddr *)&np->np_sockaddr;
 	isert_dbg("ksockaddr: %p, sa: %p\n", &np->np_sockaddr, sa);
 
-	id = rdma_create_id(isert_cma_handler, isert_np,
+	id = rdma_create_id(&init_net, isert_cma_handler, isert_np,
 			    RDMA_PS_TCP, IB_QPT_RC);
 	if (IS_ERR(id)) {
 		isert_err("rdma_create_id() failed: %ld\n", PTR_ERR(id));
diff --git a/drivers/staging/lustre/lnet/klnds/o2iblnd/o2iblnd.h b/drivers/staging/lustre/lnet/klnds/o2iblnd/o2iblnd.h
index f5d1d9f8f1ed..eb1a3abdb153 100644
--- a/drivers/staging/lustre/lnet/klnds/o2iblnd/o2iblnd.h
+++ b/drivers/staging/lustre/lnet/klnds/o2iblnd/o2iblnd.h
@@ -129,7 +129,9 @@ extern kib_tunables_t  kiblnd_tunables;
 				     IBLND_CREDIT_HIGHWATER_V1 : \
 				     *kiblnd_tunables.kib_peercredits_hiw) /* when eagerly to return credits */
 
-#define kiblnd_rdma_create_id(cb, dev, ps, qpt) rdma_create_id(cb, dev, ps, qpt)
+#define kiblnd_rdma_create_id(cb, dev, ps, qpt) rdma_create_id(&init_net, \
+							       cb, dev, \
+							       ps, qpt)
 
 static inline int
 kiblnd_concurrent_sends_v1(void)
diff --git a/include/rdma/rdma_cm.h b/include/rdma/rdma_cm.h
index c92522c192d2..463ec0ccbe51 100644
--- a/include/rdma/rdma_cm.h
+++ b/include/rdma/rdma_cm.h
@@ -160,13 +160,17 @@ struct rdma_cm_id {
 /**
  * rdma_create_id - Create an RDMA identifier.
  *
+ * @net: The network namespace in which to create the new id.
  * @event_handler: User callback invoked to report events associated with the
  *   returned rdma_id.
  * @context: User specified context associated with the id.
  * @ps: RDMA port space.
  * @qp_type: type of queue pair associated with the id.
+ *
+ * The id holds a reference on the network namespace until it is destroyed.
  */
-struct rdma_cm_id *rdma_create_id(rdma_cm_event_handler event_handler,
+struct rdma_cm_id *rdma_create_id(struct net *net,
+				  rdma_cm_event_handler event_handler,
 				  void *context, enum rdma_port_space ps,
 				  enum ib_qp_type qp_type);
 
diff --git a/net/9p/trans_rdma.c b/net/9p/trans_rdma.c
index ba1210253f5e..52b4a2f993f2 100644
--- a/net/9p/trans_rdma.c
+++ b/net/9p/trans_rdma.c
@@ -655,8 +655,8 @@ rdma_create_trans(struct p9_client *client, const char *addr, char *args)
 		return -ENOMEM;
 
 	/* Create the RDMA CM ID */
-	rdma->cm_id = rdma_create_id(p9_cm_event_handler, client, RDMA_PS_TCP,
-				     IB_QPT_RC);
+	rdma->cm_id = rdma_create_id(&init_net, p9_cm_event_handler, client,
+				     RDMA_PS_TCP, IB_QPT_RC);
 	if (IS_ERR(rdma->cm_id))
 		goto error;
 
diff --git a/net/rds/ib.c b/net/rds/ib.c
index c6f95b9494ae..3f87a93e38bb 100644
--- a/net/rds/ib.c
+++ b/net/rds/ib.c
@@ -317,7 +317,7 @@ static int rds_ib_laddr_check(__be32 addr)
 	/* Create a CMA ID and try to bind it. This catches both
 	 * IB and iWARP capable NICs.
 	 */
-	cm_id = rdma_create_id(NULL, NULL, RDMA_PS_TCP, IB_QPT_RC);
+	cm_id = rdma_create_id(&init_net, NULL, NULL, RDMA_PS_TCP, IB_QPT_RC);
 	if (IS_ERR(cm_id))
 		return PTR_ERR(cm_id);
 
diff --git a/net/rds/ib_cm.c b/net/rds/ib_cm.c
index a75e8832bc23..79126a190842 100644
--- a/net/rds/ib_cm.c
+++ b/net/rds/ib_cm.c
@@ -564,7 +564,7 @@ int rds_ib_conn_connect(struct rds_connection *conn)
 
 	/* XXX I wonder what affect the port space has */
 	/* delegate cm event handler to rdma_transport */
-	ic->i_cm_id = rdma_create_id(rds_rdma_cm_event_handler, conn,
+	ic->i_cm_id = rdma_create_id(&init_net, rds_rdma_cm_event_handler, conn,
 				     RDMA_PS_TCP, IB_QPT_RC);
 	if (IS_ERR(ic->i_cm_id)) {
 		ret = PTR_ERR(ic->i_cm_id);
diff --git a/net/rds/iw.c b/net/rds/iw.c
index c7dcddbf17cb..e32221eb1a6c 100644
--- a/net/rds/iw.c
+++ b/net/rds/iw.c
@@ -223,7 +223,7 @@ static int rds_iw_laddr_check(__be32 addr)
 	/* Create a CMA ID and try to bind it. This catches both
 	 * IB and iWARP capable NICs.
 	 */
-	cm_id = rdma_create_id(NULL, NULL, RDMA_PS_TCP, IB_QPT_RC);
+	cm_id = rdma_create_id(&init_net, NULL, NULL, RDMA_PS_TCP, IB_QPT_RC);
 	if (IS_ERR(cm_id))
 		return PTR_ERR(cm_id);
 
diff --git a/net/rds/iw_cm.c b/net/rds/iw_cm.c
index 8f486fa32079..6068da58701f 100644
--- a/net/rds/iw_cm.c
+++ b/net/rds/iw_cm.c
@@ -523,7 +523,7 @@ int rds_iw_conn_connect(struct rds_connection *conn)
 
 	/* XXX I wonder what affect the port space has */
 	/* delegate cm event handler to rdma_transport */
-	ic->i_cm_id = rdma_create_id(rds_rdma_cm_event_handler, conn,
+	ic->i_cm_id = rdma_create_id(&init_net, rds_rdma_cm_event_handler, conn,
 				     RDMA_PS_TCP, IB_QPT_RC);
 	if (IS_ERR(ic->i_cm_id)) {
 		ret = PTR_ERR(ic->i_cm_id);
diff --git a/net/rds/rdma_transport.c b/net/rds/rdma_transport.c
index 208240836043..7deaa617e821 100644
--- a/net/rds/rdma_transport.c
+++ b/net/rds/rdma_transport.c
@@ -131,8 +131,8 @@ static int rds_rdma_listen_init(void)
 	struct rdma_cm_id *cm_id;
 	int ret;
 
-	cm_id = rdma_create_id(rds_rdma_cm_event_handler, NULL, RDMA_PS_TCP,
-			       IB_QPT_RC);
+	cm_id = rdma_create_id(&init_net, rds_rdma_cm_event_handler, NULL,
+			       RDMA_PS_TCP, IB_QPT_RC);
 	if (IS_ERR(cm_id)) {
 		ret = PTR_ERR(cm_id);
 		printk(KERN_ERR "RDS/RDMA: failed to setup listener, "
diff --git a/net/sunrpc/xprtrdma/svc_rdma_transport.c b/net/sunrpc/xprtrdma/svc_rdma_transport.c
index 11d5133c3f38..4e220e6716d4 100644
--- a/net/sunrpc/xprtrdma/svc_rdma_transport.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_transport.c
@@ -691,8 +691,8 @@ static struct svc_xprt *svc_rdma_create(struct svc_serv *serv,
 	if (!cma_xprt)
 		return ERR_PTR(-ENOMEM);
 
-	listen_id = rdma_create_id(rdma_listen_handler, cma_xprt, RDMA_PS_TCP,
-				   IB_QPT_RC);
+	listen_id = rdma_create_id(&init_net, rdma_listen_handler, cma_xprt,
+				   RDMA_PS_TCP, IB_QPT_RC);
 	if (IS_ERR(listen_id)) {
 		ret = PTR_ERR(listen_id);
 		dprintk("svcrdma: rdma_create_id failed = %d\n", ret);
diff --git a/net/sunrpc/xprtrdma/verbs.c b/net/sunrpc/xprtrdma/verbs.c
index afd504375a9a..2c605d22a3f6 100644
--- a/net/sunrpc/xprtrdma/verbs.c
+++ b/net/sunrpc/xprtrdma/verbs.c
@@ -423,7 +423,8 @@ rpcrdma_create_id(struct rpcrdma_xprt *xprt,
 
 	init_completion(&ia->ri_done);
 
-	id = rdma_create_id(rpcrdma_conn_upcall, xprt, RDMA_PS_TCP, IB_QPT_RC);
+	id = rdma_create_id(&init_net, rpcrdma_conn_upcall, xprt, RDMA_PS_TCP,
+			    IB_QPT_RC);
 	if (IS_ERR(id)) {
 		rc = PTR_ERR(id);
 		dprintk("RPC:       %s: rdma_create_id() failed %i\n",
-- 
1.7.11.2

--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

[PATCH v6 4/4] IB/ucma: Take the network namespace from the process

[Haggai Eran]

From: Guy Shapiro <guysh-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>

Add support for network namespaces from user space. This is done by passing
the network namespace of the process instead of init_net.

Signed-off-by: Haggai Eran <haggaie-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
Signed-off-by: Yotam Kenneth <yotamke-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
Signed-off-by: Shachar Raindel <raindel-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
Signed-off-by: Guy Shapiro <guysh-VPRAkNaXOzVWk0Htik3J/w@public.gmane.org>
---
 drivers/infiniband/core/ucma.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/drivers/infiniband/core/ucma.c b/drivers/infiniband/core/ucma.c
index 82a17a7b7e6d..00402e6d505a 100644
--- a/drivers/infiniband/core/ucma.c
+++ b/drivers/infiniband/core/ucma.c
@@ -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>
@@ -472,8 +473,8 @@ static ssize_t ucma_create_id(struct ucma_file *file, const char __user *inbuf,
 		return -ENOMEM;
 
 	ctx->uid = cmd.uid;
-	ctx->cm_id = rdma_create_id(&init_net, ucma_event_handler, ctx, cmd.ps,
-				    qp_type);
+	ctx->cm_id = rdma_create_id(current->nsproxy->net_ns,
+				    ucma_event_handler, ctx, cmd.ps, qp_type);
 	if (IS_ERR(ctx->cm_id)) {
 		ret = PTR_ERR(ctx->cm_id);
 		goto err1;
-- 
1.7.11.2

--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

RE: [PATCH v6 0/4] Add network namespace support in the RDMA-CM

[Hefty, Sean]

This series looks reasonable to me
--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html

Re: [PATCH v6 0/4] Add network namespace support in the RDMA-CM

[Doug Ledford]

[-- Attachment #1: Type: text/plain, Size: 527 bytes --]

On 08/27/2015 10:29 AM, Haggai Eran wrote:
> Hi,
> 
> Now that the code for demuxing requests is inside rdma_cm, here are the patches
> to add InfiniBand network namespace again.
> 
> Changes from v5:
> - removed patches that got in as part of the cleanup series.

Hi Haggai,

This series no longer applies cleanly after all of the cm changes that
made it into 4.3.  Can you please rebase and resend?


-- 
Doug Ledford <dledford-H+wXaHxf7aLQT0dZR+AlfA@public.gmane.org>
              GPG KeyID: 0E572FDD



[-- Attachment #2: OpenPGP digital signature --]
[-- Type: application/pgp-signature, Size: 884 bytes --]

Re: [PATCH v6 0/4] Add network namespace support in the RDMA-CM

[Haggai Eran]

On 22/10/2015 06:37, Doug Ledford wrote:
> On 08/27/2015 10:29 AM, Haggai Eran wrote:
>> Hi,
>>
>> Now that the code for demuxing requests is inside rdma_cm, here are the patches
>> to add InfiniBand network namespace again.
>>
>> Changes from v5:
>> - removed patches that got in as part of the cleanup series.
> 
> Hi Haggai,
> 
> This series no longer applies cleanly after all of the cm changes that
> made it into 4.3.  Can you please rebase and resend?

Sure, I'll do that.

--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html