RE: [PATCH for-next 08/10] IB/cma: Add support for network namespaces

-----Original Message-----
From: Yann Droneaud [mailto:ydroneaud@opteya.com]
Sent: Sunday, February 01, 2015 3:45 PM
To: Shachar Raindel
Cc: roland@kernel.org; sean.hefty@intel.com; linux-rdma@vger.kernel.org;
netdev@vger.kernel.org; Liran Liss; Guy Shapiro; Haggai Eran; Yotam
Kenneth
Subject: Re: [PATCH for-next 08/10] IB/cma: Add support for network
namespaces

Hi,

Le dimanche 01 février 2015 à 13:28 +0200, Shachar Raindel a écrit :

quoted

From: Guy Shapiro <redacted>

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

quoted

   to populate the network namespace field in rdma_id_private.

rdma_create_id

quoted

   keeps a reference on the network namespace.
2. Using the network namespace from the rdma_id instead of init_net

inside of

quoted

   ib_cma.
3. Decrementing the reference count for the appropriate network

namespace when

quoted

   calling rdma_destroy_id.

In order to preserve the current behavior init_net is passed when

calling from

quoted

other modules.

Signed-off-by: Guy Shapiro <redacted>
Signed-off-by: Haggai Eran <redacted>
Signed-off-by: Yotam Kenneth <redacted>
Signed-off-by: Shachar Raindel <redacted>

---
 drivers/infiniband/core/cma.c                      | 52

+++++++++++++---------

quoted

 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                                |  2 +-
 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                           |  2 +-
 net/sunrpc/xprtrdma/svc_rdma_transport.c           |  2 +-
 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

quoted

index 022b0d0a51cc..f6379b38b366 100644

--- a/drivers/infiniband/core/cma.c
+++ b/drivers/infiniband/core/cma.c

@@ -540,7 +540,8 @@ static int cma_disable_callback(struct

rdma_id_private *id_priv,

quoted

 struct rdma_cm_id *rdma_create_id(rdma_cm_event_handler

event_handler,

quoted

 				  void *context, enum rdma_port_space ps,
-				  enum ib_qp_type qp_type)
+				  enum ib_qp_type qp_type,
+				  struct net *net)
 {
 	struct rdma_id_private *id_priv;

@@ -562,7 +563,7 @@ struct rdma_cm_id

*rdma_create_id(rdma_cm_event_handler event_handler,

quoted

 	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;
 }

@@ -689,7 +690,7 @@ static int cma_modify_qp_rtr(struct

rdma_id_private *id_priv,

quoted

 	    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,
-						  &init_net);
+				id_priv->id.route.addr.dev_addr.net);

 		if (ret)
 			goto out;

@@ -953,6 +954,7 @@ static void cma_cancel_operation(struct

rdma_id_private *id_priv,

quoted

 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;

@@ -960,7 +962,7 @@ static void cma_release_port(struct

rdma_id_private *id_priv)

quoted

 	mutex_lock(&lock);
 	hlist_del(&id_priv->node);
 	if (hlist_empty(&bind_list->owners)) {
-		cma_ps_remove(bind_list->ps, &init_net, bind_list->port);
+		cma_ps_remove(bind_list->ps, net, bind_list->port);
 		kfree(bind_list);
 	}
 	mutex_unlock(&lock);

@@ -1029,6 +1031,7 @@ 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);

@@ -1156,7 +1159,8 @@ static struct rdma_id_private

*cma_new_conn_id(struct rdma_cm_id *listen_id,

quoted

 	int ret;

 	id = rdma_create_id(listen_id->event_handler, listen_id->context,
-			    listen_id->ps, ib_event->param.req_rcvd.qp_type);
+			    listen_id->ps, ib_event->param.req_rcvd.qp_type,
+			    listen_id->route.addr.dev_addr.net);
 	if (IS_ERR(id))
 		return NULL;

@@ -1201,10 +1205,11 @@ static struct rdma_id_private

*cma_new_udp_id(struct rdma_cm_id *listen_id,

quoted

 {
 	struct rdma_id_private *id_priv;
 	struct rdma_cm_id *id;
+	struct net *net = listen_id->route.addr.dev_addr.net;
 	int ret;

 	id = rdma_create_id(listen_id->event_handler, listen_id->context,
-			    listen_id->ps, IB_QPT_UD);
+			    listen_id->ps, IB_QPT_UD, net);
 	if (IS_ERR(id))
 		return NULL;

@@ -1455,7 +1460,8 @@ static int iw_conn_req_handler(struct iw_cm_id

*cm_id,

quoted

 	/* Create a new RDMA id for the new IW CM ID */
 	new_cm_id = rdma_create_id(listen_id->id.event_handler,
 				   listen_id->id.context,
-				   RDMA_PS_TCP, IB_QPT_RC);
+				   RDMA_PS_TCP, IB_QPT_RC,
+				   listen_id->id.route.addr.dev_addr.net);
 	if (IS_ERR(new_cm_id)) {
 		ret = -ENOMEM;
 		goto out;

@@ -1528,11 +1534,11 @@ static int cma_ib_listen(struct

rdma_id_private *id_priv)

quoted

 	struct ib_cm_compare_data compare_data;
 	struct sockaddr *addr;
 	struct ib_cm_id	*id;
+	struct net *net = id_priv->id.route.addr.dev_addr.net;
 	__be64 svc_id;
 	int ret;

-	id = ib_create_cm_id(id_priv->id.device, cma_req_handler, id_priv,
-			     &init_net);
+	id = ib_create_cm_id(id_priv->id.device, cma_req_handler, id_priv,

net);

quoted

 	if (IS_ERR(id))
 		return PTR_ERR(id);

@@ -1596,6 +1602,7 @@ static void cma_listen_on_dev(struct

rdma_id_private *id_priv,

quoted

 {
 	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 &&

@@ -1603,7 +1610,7 @@ static void cma_listen_on_dev(struct

rdma_id_private *id_priv,

quoted

 		return;

 	id = rdma_create_id(cma_listen_handler, id_priv, id_priv->id.ps,
-			    id_priv->id.qp_type);
+			    id_priv->id.qp_type, net);
 	if (IS_ERR(id))
 		return;

@@ -2283,7 +2290,8 @@ static int cma_alloc_port(struct radix_tree_root

*ps,

quoted

 	if (!bind_list)
 		return -ENOMEM;

-	ret = cma_ps_alloc(ps, &init_net, bind_list, snum);
+	ret = cma_ps_alloc(ps, id_priv->id.route.addr.dev_addr.net,

bind_list,

quoted

+			   snum);
 	if (ret < 0)
 		goto err;

@@ -2302,13 +2310,14 @@ static int cma_alloc_any_port(struct

radix_tree_root *ps,

quoted

 	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(ps, &init_net, (unsigned short)rover)) {
+	    !cma_ps_find(ps, net, (unsigned short)rover)) {
 		int ret = cma_alloc_port(ps, id_priv, rover);
 		/*
 		 * Remember previously used port number in order to avoid

@@ -2376,7 +2385,7 @@ static int cma_use_port(struct radix_tree_root

*ps,

quoted

 	if (snum < PROT_SOCK && !capable(CAP_NET_BIND_SERVICE))
 		return -EACCES;

-	bind_list = cma_ps_find(ps, &init_net, snum);
+	bind_list = cma_ps_find(ps, id_priv->id.route.addr.dev_addr.net,

snum);

quoted

 	if (!bind_list) {
 		ret = cma_alloc_port(ps, id_priv, snum);
 	} else {

@@ -2573,8 +2582,11 @@ int rdma_bind_addr(struct rdma_cm_id *id,

struct sockaddr *addr)

quoted

 		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);

@@ -2687,7 +2699,7 @@ static int cma_resolve_ib_udp(struct

rdma_id_private *id_priv,

quoted

 	}

 	id = ib_create_cm_id(id_priv->id.device, cma_sidr_rep_handler,
-			     id_priv, &init_net);
+			     id_priv, id_priv->id.route.addr.dev_addr.net);
 	if (IS_ERR(id)) {
 		ret = PTR_ERR(id);
 		goto out;

@@ -2737,7 +2749,7 @@ static int cma_connect_ib(struct rdma_id_private

*id_priv,

quoted

 		       conn_param->private_data_len);

 	id = ib_create_cm_id(id_priv->id.device, cma_ib_handler, id_priv,
-			     &init_net);
+			     id_priv->id.route.addr.dev_addr.net);
 	if (IS_ERR(id)) {
 		ret = PTR_ERR(id);
 		goto out;

@@ -3387,6 +3399,7 @@ static int cma_netdev_change(struct net_device

*ndev, struct rdma_id_private *id

quoted

 	dev_addr = &id_priv->id.route.addr.dev_addr;

 	if ((dev_addr->bound_dev_if == ndev->ifindex) &&
+	    (dev_net(ndev) == dev_addr->net) &&

net_eq() ?

The original code (below) contained the same comparison style.
Will fix in next iteration to use net_eq.

quoted

 	    memcmp(dev_addr->src_dev_addr, ndev->dev_addr, ndev->addr_len))

{

quoted

 		printk(KERN_INFO "RDMA CM addr change for ndev %s used by id

%p\n",

quoted

 		       ndev->name, &id_priv->id);

@@ -3412,9 +3425,6 @@ static int cma_netdev_callback(struct

notifier_block *self, unsigned long event,

quoted

 	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

quoted

index 56a4b7ca7ee3..de755f2c6166 100644

--- a/drivers/infiniband/core/ucma.c
+++ b/drivers/infiniband/core/ucma.c

@@ -391,7 +391,8 @@ static ssize_t ucma_create_id(struct ucma_file

*file, const char __user *inbuf,

quoted

 		return -ENOMEM;

 	ctx->uid = cmd.uid;
-	ctx->cm_id = rdma_create_id(ucma_event_handler, ctx, cmd.ps,

qp_type);

quoted

+	ctx->cm_id = rdma_create_id(ucma_event_handler, ctx, cmd.ps,

qp_type,

quoted

+				    &init_net);
 	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

quoted

index 695a2704bd43..d4e9c639ad2f 100644

--- a/drivers/infiniband/ulp/iser/iser_verbs.c
+++ b/drivers/infiniband/ulp/iser/iser_verbs.c

@@ -949,7 +949,7 @@ int iser_connect(struct iser_conn   *iser_conn,

 	ib_conn->cma_id = rdma_create_id(iser_cma_handler,
 					 (void *)iser_conn,
-					 RDMA_PS_TCP, IB_QPT_RC);
+					 RDMA_PS_TCP, IB_QPT_RC, &init_net);
 	if (IS_ERR(ib_conn->cma_id)) {
 		err = PTR_ERR(ib_conn->cma_id);
 		iser_err("rdma_create_id failed: %d\n", err);

diff --git a/drivers/infiniband/ulp/isert/ib_isert.c

b/drivers/infiniband/ulp/isert/ib_isert.c

quoted

index dafb3c531f96..44a6fff8dc79 100644

--- a/drivers/infiniband/ulp/isert/ib_isert.c
+++ b/drivers/infiniband/ulp/isert/ib_isert.c

@@ -2960,7 +2960,7 @@ isert_setup_id(struct isert_np *isert_np)
 	isert_dbg("ksockaddr: %p, sa: %p\n", &np->np_sockaddr, sa);

 	id = rdma_create_id(isert_cma_handler, isert_np,
-			    RDMA_PS_TCP, IB_QPT_RC);
+			    RDMA_PS_TCP, IB_QPT_RC, &init_net);
 	if (IS_ERR(id)) {
 		isert_err("rdma_create_id() failed: %ld\n", PTR_ERR(id));
 		ret = PTR_ERR(id);

diff --git a/drivers/staging/lustre/lnet/klnds/o2iblnd/o2iblnd.h

b/drivers/staging/lustre/lnet/klnds/o2iblnd/o2iblnd.h

quoted

index b02b4ec1e29d..128de4eb0959 100644

--- a/drivers/staging/lustre/lnet/klnds/o2iblnd/o2iblnd.h
+++ b/drivers/staging/lustre/lnet/klnds/o2iblnd/o2iblnd.h

@@ -125,7 +125,9 @@ extern kib_tunables_t  kiblnd_tunables;
 				     IBLND_CREDIT_HIGHWATER_V1 : \
 				     *kiblnd_tunables.kib_peercredits_hiw) /* when

eagerly to return credits */

quoted

-#define kiblnd_rdma_create_id(cb, dev, ps, qpt) rdma_create_id(cb,

dev, ps, qpt)

quoted

+#define kiblnd_rdma_create_id(cb, dev, ps, qpt) rdma_create_id(cb,

dev, \

quoted

+							       ps, qpt, \
+							       &init_net)

 static inline int
 kiblnd_concurrent_sends_v1(void)

diff --git a/include/rdma/rdma_cm.h b/include/rdma/rdma_cm.h
index 1ed2088dc9f5..3953e9c8bc94 100644
--- a/include/rdma/rdma_cm.h
+++ b/include/rdma/rdma_cm.h

@@ -163,10 +163,14 @@ struct rdma_cm_id {
  * @context: User specified context associated with the id.
  * @ps: RDMA port space.
  * @qp_type: type of queue pair associated with the id.
+ * @net: The network namespace in which to create the new id.
+ *
+ * The id holds a reference on the network namespace until it is

destroyed.

quoted

  */
 struct rdma_cm_id *rdma_create_id(rdma_cm_event_handler

event_handler,

quoted

 				  void *context, enum rdma_port_space ps,
-				  enum ib_qp_type qp_type);
+				  enum ib_qp_type qp_type,
+				  struct net *net);

 /**
   * rdma_destroy_id - Destroys an RDMA identifier.

diff --git a/net/9p/trans_rdma.c b/net/9p/trans_rdma.c
index 14ad43b5cf89..577fd3129bcf 100644
--- a/net/9p/trans_rdma.c
+++ b/net/9p/trans_rdma.c

@@ -635,7 +635,7 @@ rdma_create_trans(struct p9_client *client, const

char *addr, char *args)

quoted

 	/* Create the RDMA CM ID */
 	rdma->cm_id = rdma_create_id(p9_cm_event_handler, client,

RDMA_PS_TCP,

quoted

-				     IB_QPT_RC);
+				     IB_QPT_RC, &init_net);
 	if (IS_ERR(rdma->cm_id))
 		goto error;

diff --git a/net/rds/ib.c b/net/rds/ib.c
index ba2dffeff608..cc137f523248 100644
--- a/net/rds/ib.c
+++ b/net/rds/ib.c

@@ -326,7 +326,7 @@ 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(NULL, NULL, RDMA_PS_TCP, IB_QPT_RC,

&init_net);

quoted

 	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 31b74f5e61ad..d19b91296ddc 100644
--- a/net/rds/ib_cm.c
+++ b/net/rds/ib_cm.c

@@ -584,7 +584,7 @@ int rds_ib_conn_connect(struct rds_connection

*conn)

quoted

 	/* 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,
-				     RDMA_PS_TCP, IB_QPT_RC);
+				     RDMA_PS_TCP, IB_QPT_RC, &init_net);
 	if (IS_ERR(ic->i_cm_id)) {
 		ret = PTR_ERR(ic->i_cm_id);
 		ic->i_cm_id = NULL;

diff --git a/net/rds/iw.c b/net/rds/iw.c
index 589935661d66..8501b73ed12f 100644
--- a/net/rds/iw.c
+++ b/net/rds/iw.c

@@ -227,7 +227,7 @@ 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(NULL, NULL, RDMA_PS_TCP, IB_QPT_RC,

&init_net);

quoted

 	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 a91e1db62ee6..e5ee2d562a60 100644
--- a/net/rds/iw_cm.c
+++ b/net/rds/iw_cm.c

@@ -521,7 +521,7 @@ int rds_iw_conn_connect(struct rds_connection

*conn)

quoted

 	/* 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,
-				     RDMA_PS_TCP, IB_QPT_RC);
+				     RDMA_PS_TCP, IB_QPT_RC, &init_net);
 	if (IS_ERR(ic->i_cm_id)) {
 		ret = PTR_ERR(ic->i_cm_id);
 		ic->i_cm_id = NULL;

diff --git a/net/rds/rdma_transport.c b/net/rds/rdma_transport.c
index 6cd9d1deafc3..066b60b27b12 100644
--- a/net/rds/rdma_transport.c
+++ b/net/rds/rdma_transport.c

@@ -160,7 +160,7 @@ static int rds_rdma_listen_init(void)
 	int ret;

 	cm_id = rdma_create_id(rds_rdma_cm_event_handler, NULL,

RDMA_PS_TCP,

quoted

-			       IB_QPT_RC);
+			       IB_QPT_RC, &init_net);
 	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

quoted

index 4e618808bc98..e3b246e305f9 100644

--- a/net/sunrpc/xprtrdma/svc_rdma_transport.c
+++ b/net/sunrpc/xprtrdma/svc_rdma_transport.c

@@ -701,7 +701,7 @@ static struct svc_xprt *svc_rdma_create(struct

svc_serv *serv,

quoted

 	xprt = &cma_xprt->sc_xprt;

 	listen_id = rdma_create_id(rdma_listen_handler, cma_xprt,

RDMA_PS_TCP,

quoted

-				   IB_QPT_RC);
+				   IB_QPT_RC, &init_net);
 	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 c98e40643910..f574e77165f4 100644
--- a/net/sunrpc/xprtrdma/verbs.c
+++ b/net/sunrpc/xprtrdma/verbs.c

@@ -483,7 +483,8 @@ 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);

quoted

+	id = rdma_create_id(rpcrdma_conn_upcall, xprt, RDMA_PS_TCP,

IB_QPT_RC,

quoted

+			    &init_net);
 	if (IS_ERR(id)) {
 		rc = PTR_ERR(id);
 		dprintk("RPC:       %s: rdma_create_id() failed %i\n",

Thanks,
--Shachar

N�����r��y���b�X��ǧv�^�)޺{.n�+����{��ٚ�{ay�
ʇڙ�,j��f���h�����/oSc��ڳ9�u�����&jw��(�階�ݢj"���m�����z�ޖ���f���h���~�m�