From e3f20f02864f6da1509c523bfa1e928619e59095 Mon Sep 17 00:00:00 2001
From: Leon Romanovsky <leonro@mellanox.com>
Date: Thu, 19 May 2016 17:12:31 +0300
Subject: IB/core: Integrate IB address resolution module into core

IB address resolution is declared as a module (ib_addr.ko) which loads
itself before IB core module (ib_core.ko).

It causes to the scenario where IB netlink which is initialized by IB
core can't be used by ib_addr.ko.

In order to solve it, we are converting ib_addr.ko to be part of
IB core module.

Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Leon Romanovsky <leon@kernel.org>
Signed-off-by: Mark Bloch <markb@mellanox.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>
---
 drivers/infiniband/core/Makefile    |  6 ++----
 drivers/infiniband/core/addr.c      | 11 ++---------
 drivers/infiniband/core/core_priv.h |  3 +++
 drivers/infiniband/core/device.c    |  9 +++++++++
 4 files changed, 16 insertions(+), 13 deletions(-)

(limited to 'drivers/infiniband')

diff --git a/drivers/infiniband/core/Makefile b/drivers/infiniband/core/Makefile
index 26987d9d7e1c..209838d2114d 100644
--- a/drivers/infiniband/core/Makefile
+++ b/drivers/infiniband/core/Makefile
@@ -2,7 +2,7 @@ infiniband-$(CONFIG_INFINIBAND_ADDR_TRANS)	:= rdma_cm.o
 user_access-$(CONFIG_INFINIBAND_ADDR_TRANS)	:= rdma_ucm.o
 
 obj-$(CONFIG_INFINIBAND) +=		ib_core.o ib_mad.o ib_sa.o \
-					ib_cm.o iw_cm.o ib_addr.o \
+					ib_cm.o iw_cm.o \
 					$(infiniband-y)
 obj-$(CONFIG_INFINIBAND_USER_MAD) +=	ib_umad.o
 obj-$(CONFIG_INFINIBAND_USER_ACCESS) +=	ib_uverbs.o ib_ucm.o \
@@ -10,7 +10,7 @@ obj-$(CONFIG_INFINIBAND_USER_ACCESS) +=	ib_uverbs.o ib_ucm.o \
 
 ib_core-y :=			packer.o ud_header.o verbs.o cq.o rw.o sysfs.o \
 				device.o fmr_pool.o cache.o netlink.o \
-				roce_gid_mgmt.o mr_pool.o
+				roce_gid_mgmt.o mr_pool.o addr.o
 ib_core-$(CONFIG_INFINIBAND_USER_MEM) += umem.o
 ib_core-$(CONFIG_INFINIBAND_ON_DEMAND_PAGING) += umem_odp.o umem_rbtree.o
 
@@ -28,8 +28,6 @@ rdma_cm-$(CONFIG_INFINIBAND_ADDR_TRANS_CONFIGFS) += cma_configfs.o
 
 rdma_ucm-y :=			ucma.o
 
-ib_addr-y :=			addr.o
-
 ib_umad-y :=			user_mad.o
 
 ib_ucm-y :=			ucm.o
diff --git a/drivers/infiniband/core/addr.c b/drivers/infiniband/core/addr.c
index 337353d86cfa..3a203ee08ced 100644
--- a/drivers/infiniband/core/addr.c
+++ b/drivers/infiniband/core/addr.c
@@ -47,10 +47,6 @@
 #include <rdma/ib_addr.h>
 #include <rdma/ib.h>
 
-MODULE_AUTHOR("Sean Hefty");
-MODULE_DESCRIPTION("IB Address Translation");
-MODULE_LICENSE("Dual BSD/GPL");
-
 struct addr_req {
 	struct list_head list;
 	struct sockaddr_storage src_addr;
@@ -634,7 +630,7 @@ static struct notifier_block nb = {
 	.notifier_call = netevent_callback
 };
 
-static int __init addr_init(void)
+int addr_init(void)
 {
 	addr_wq = create_singlethread_workqueue("ib_addr");
 	if (!addr_wq)
@@ -645,12 +641,9 @@ static int __init addr_init(void)
 	return 0;
 }
 
-static void __exit addr_cleanup(void)
+void addr_cleanup(void)
 {
 	rdma_addr_unregister_client(&self);
 	unregister_netevent_notifier(&nb);
 	destroy_workqueue(addr_wq);
 }
-
-module_init(addr_init);
-module_exit(addr_cleanup);
diff --git a/drivers/infiniband/core/core_priv.h b/drivers/infiniband/core/core_priv.h
index eab32215756b..589f16ad7c72 100644
--- a/drivers/infiniband/core/core_priv.h
+++ b/drivers/infiniband/core/core_priv.h
@@ -137,4 +137,7 @@ static inline bool rdma_is_upper_dev_rcu(struct net_device *dev,
 	return _upper == upper;
 }
 
+int addr_init(void);
+void addr_cleanup(void);
+
 #endif /* _CORE_PRIV_H */
diff --git a/drivers/infiniband/core/device.c b/drivers/infiniband/core/device.c
index 10979844026a..805d72d67db1 100644
--- a/drivers/infiniband/core/device.c
+++ b/drivers/infiniband/core/device.c
@@ -983,10 +983,18 @@ static int __init ib_core_init(void)
 		goto err_sysfs;
 	}
 
+	ret = addr_init();
+	if (ret) {
+		pr_warn("Could't init IB address resolution\n");
+		goto err_ibnl;
+	}
+
 	ib_cache_setup();
 
 	return 0;
 
+err_ibnl:
+	ibnl_cleanup();
 err_sysfs:
 	class_unregister(&ib_class);
 err_comp:
@@ -999,6 +1007,7 @@ err:
 static void __exit ib_core_cleanup(void)
 {
 	ib_cache_cleanup();
+	addr_cleanup();
 	ibnl_cleanup();
 	class_unregister(&ib_class);
 	destroy_workqueue(ib_comp_wq);
-- 
cgit 1.4.1


From 4c2cb4220431cbf92233dc12733ee8962abb9081 Mon Sep 17 00:00:00 2001
From: Mark Bloch <markb@mellanox.com>
Date: Thu, 19 May 2016 17:12:32 +0300
Subject: IB/MAD: Integrate ib_mad module into ib_core module

Consolidate ib_mad into ib_core, this commit eliminates
ib_mad.ko and makes it part of ib_core.ko

Signed-off-by: Mark Bloch <markb@mellanox.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>
---
 drivers/infiniband/core/Makefile    |  7 +++----
 drivers/infiniband/core/core_priv.h |  3 +++
 drivers/infiniband/core/device.c    |  9 +++++++++
 drivers/infiniband/core/mad.c       | 13 +++----------
 4 files changed, 18 insertions(+), 14 deletions(-)

(limited to 'drivers/infiniband')

diff --git a/drivers/infiniband/core/Makefile b/drivers/infiniband/core/Makefile
index 209838d2114d..cc0a6042ccf4 100644
--- a/drivers/infiniband/core/Makefile
+++ b/drivers/infiniband/core/Makefile
@@ -1,7 +1,7 @@
 infiniband-$(CONFIG_INFINIBAND_ADDR_TRANS)	:= rdma_cm.o
 user_access-$(CONFIG_INFINIBAND_ADDR_TRANS)	:= rdma_ucm.o
 
-obj-$(CONFIG_INFINIBAND) +=		ib_core.o ib_mad.o ib_sa.o \
+obj-$(CONFIG_INFINIBAND) +=		ib_core.o ib_sa.o \
 					ib_cm.o iw_cm.o \
 					$(infiniband-y)
 obj-$(CONFIG_INFINIBAND_USER_MAD) +=	ib_umad.o
@@ -10,12 +10,11 @@ obj-$(CONFIG_INFINIBAND_USER_ACCESS) +=	ib_uverbs.o ib_ucm.o \
 
 ib_core-y :=			packer.o ud_header.o verbs.o cq.o rw.o sysfs.o \
 				device.o fmr_pool.o cache.o netlink.o \
-				roce_gid_mgmt.o mr_pool.o addr.o
+				roce_gid_mgmt.o mr_pool.o addr.o \
+				mad.o smi.o agent.o mad_rmpp.o
 ib_core-$(CONFIG_INFINIBAND_USER_MEM) += umem.o
 ib_core-$(CONFIG_INFINIBAND_ON_DEMAND_PAGING) += umem_odp.o umem_rbtree.o
 
-ib_mad-y :=			mad.o smi.o agent.o mad_rmpp.o
-
 ib_sa-y :=			sa_query.o multicast.o
 
 ib_cm-y :=			cm.o
diff --git a/drivers/infiniband/core/core_priv.h b/drivers/infiniband/core/core_priv.h
index 589f16ad7c72..d43b2fa01ee8 100644
--- a/drivers/infiniband/core/core_priv.h
+++ b/drivers/infiniband/core/core_priv.h
@@ -140,4 +140,7 @@ static inline bool rdma_is_upper_dev_rcu(struct net_device *dev,
 int addr_init(void);
 void addr_cleanup(void);
 
+int ib_mad_init(void);
+void ib_mad_cleanup(void);
+
 #endif /* _CORE_PRIV_H */
diff --git a/drivers/infiniband/core/device.c b/drivers/infiniband/core/device.c
index 805d72d67db1..f80549fbd6f5 100644
--- a/drivers/infiniband/core/device.c
+++ b/drivers/infiniband/core/device.c
@@ -989,10 +989,18 @@ static int __init ib_core_init(void)
 		goto err_ibnl;
 	}
 
+	ret = ib_mad_init();
+	if (ret) {
+		pr_warn("Couldn't init IB MAD\n");
+		goto err_addr;
+	}
+
 	ib_cache_setup();
 
 	return 0;
 
+err_addr:
+	addr_cleanup();
 err_ibnl:
 	ibnl_cleanup();
 err_sysfs:
@@ -1007,6 +1015,7 @@ err:
 static void __exit ib_core_cleanup(void)
 {
 	ib_cache_cleanup();
+	ib_mad_cleanup();
 	addr_cleanup();
 	ibnl_cleanup();
 	class_unregister(&ib_class);
diff --git a/drivers/infiniband/core/mad.c b/drivers/infiniband/core/mad.c
index 9fa5bf33f5a3..82fb511112da 100644
--- a/drivers/infiniband/core/mad.c
+++ b/drivers/infiniband/core/mad.c
@@ -47,11 +47,7 @@
 #include "smi.h"
 #include "opa_smi.h"
 #include "agent.h"
-
-MODULE_LICENSE("Dual BSD/GPL");
-MODULE_DESCRIPTION("kernel IB MAD API");
-MODULE_AUTHOR("Hal Rosenstock");
-MODULE_AUTHOR("Sean Hefty");
+#include "core_priv.h"
 
 static int mad_sendq_size = IB_MAD_QP_SEND_SIZE;
 static int mad_recvq_size = IB_MAD_QP_RECV_SIZE;
@@ -3316,7 +3312,7 @@ static struct ib_client mad_client = {
 	.remove = ib_mad_remove_device
 };
 
-static int __init ib_mad_init_module(void)
+int ib_mad_init(void)
 {
 	mad_recvq_size = min(mad_recvq_size, IB_MAD_QP_MAX_SIZE);
 	mad_recvq_size = max(mad_recvq_size, IB_MAD_QP_MIN_SIZE);
@@ -3334,10 +3330,7 @@ static int __init ib_mad_init_module(void)
 	return 0;
 }
 
-static void __exit ib_mad_cleanup_module(void)
+void ib_mad_cleanup(void)
 {
 	ib_unregister_client(&mad_client);
 }
-
-module_init(ib_mad_init_module);
-module_exit(ib_mad_cleanup_module);
-- 
cgit 1.4.1


From c2e49c92326f9baaa490492c48bea5a7f49d3244 Mon Sep 17 00:00:00 2001
From: Mark Bloch <markb@mellanox.com>
Date: Thu, 19 May 2016 17:12:33 +0300
Subject: IB/SA: Integrate ib_sa module into ib_core module

Consolidate ib_sa into ib_core, this commit eliminates
ib_sa.ko and makes it part of ib_core.ko

Signed-off-by: Mark Bloch <markb@mellanox.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>
---
 drivers/infiniband/core/Makefile    |  9 +++------
 drivers/infiniband/core/core_priv.h |  3 +++
 drivers/infiniband/core/device.c    |  9 +++++++++
 drivers/infiniband/core/sa_query.c  | 11 ++---------
 4 files changed, 17 insertions(+), 15 deletions(-)

(limited to 'drivers/infiniband')

diff --git a/drivers/infiniband/core/Makefile b/drivers/infiniband/core/Makefile
index cc0a6042ccf4..edaae9f9853c 100644
--- a/drivers/infiniband/core/Makefile
+++ b/drivers/infiniband/core/Makefile
@@ -1,8 +1,7 @@
 infiniband-$(CONFIG_INFINIBAND_ADDR_TRANS)	:= rdma_cm.o
 user_access-$(CONFIG_INFINIBAND_ADDR_TRANS)	:= rdma_ucm.o
 
-obj-$(CONFIG_INFINIBAND) +=		ib_core.o ib_sa.o \
-					ib_cm.o iw_cm.o \
+obj-$(CONFIG_INFINIBAND) +=		ib_core.o ib_cm.o iw_cm.o \
 					$(infiniband-y)
 obj-$(CONFIG_INFINIBAND_USER_MAD) +=	ib_umad.o
 obj-$(CONFIG_INFINIBAND_USER_ACCESS) +=	ib_uverbs.o ib_ucm.o \
@@ -10,13 +9,11 @@ obj-$(CONFIG_INFINIBAND_USER_ACCESS) +=	ib_uverbs.o ib_ucm.o \
 
 ib_core-y :=			packer.o ud_header.o verbs.o cq.o rw.o sysfs.o \
 				device.o fmr_pool.o cache.o netlink.o \
-				roce_gid_mgmt.o mr_pool.o addr.o \
-				mad.o smi.o agent.o mad_rmpp.o
+				roce_gid_mgmt.o mr_pool.o addr.o sa_query.o \
+				multicast.o mad.o smi.o agent.o mad_rmpp.o
 ib_core-$(CONFIG_INFINIBAND_USER_MEM) += umem.o
 ib_core-$(CONFIG_INFINIBAND_ON_DEMAND_PAGING) += umem_odp.o umem_rbtree.o
 
-ib_sa-y :=			sa_query.o multicast.o
-
 ib_cm-y :=			cm.o
 
 iw_cm-y :=			iwcm.o iwpm_util.o iwpm_msg.o
diff --git a/drivers/infiniband/core/core_priv.h b/drivers/infiniband/core/core_priv.h
index d43b2fa01ee8..c78a7fa2c2bb 100644
--- a/drivers/infiniband/core/core_priv.h
+++ b/drivers/infiniband/core/core_priv.h
@@ -143,4 +143,7 @@ void addr_cleanup(void);
 int ib_mad_init(void);
 void ib_mad_cleanup(void);
 
+int ib_sa_init(void);
+void ib_sa_cleanup(void);
+
 #endif /* _CORE_PRIV_H */
diff --git a/drivers/infiniband/core/device.c b/drivers/infiniband/core/device.c
index f80549fbd6f5..2cd0956aef34 100644
--- a/drivers/infiniband/core/device.c
+++ b/drivers/infiniband/core/device.c
@@ -995,10 +995,18 @@ static int __init ib_core_init(void)
 		goto err_addr;
 	}
 
+	ret = ib_sa_init();
+	if (ret) {
+		pr_warn("Couldn't init SA\n");
+		goto err_mad;
+	}
+
 	ib_cache_setup();
 
 	return 0;
 
+err_mad:
+	ib_mad_cleanup();
 err_addr:
 	addr_cleanup();
 err_ibnl:
@@ -1015,6 +1023,7 @@ err:
 static void __exit ib_core_cleanup(void)
 {
 	ib_cache_cleanup();
+	ib_sa_cleanup();
 	ib_mad_cleanup();
 	addr_cleanup();
 	ibnl_cleanup();
diff --git a/drivers/infiniband/core/sa_query.c b/drivers/infiniband/core/sa_query.c
index 3ebd108bcc5f..db3c92d2b5ec 100644
--- a/drivers/infiniband/core/sa_query.c
+++ b/drivers/infiniband/core/sa_query.c
@@ -53,10 +53,6 @@
 #include "sa.h"
 #include "core_priv.h"
 
-MODULE_AUTHOR("Roland Dreier");
-MODULE_DESCRIPTION("InfiniBand subnet administration query support");
-MODULE_LICENSE("Dual BSD/GPL");
-
 #define IB_SA_LOCAL_SVC_TIMEOUT_MIN		100
 #define IB_SA_LOCAL_SVC_TIMEOUT_DEFAULT		2000
 #define IB_SA_LOCAL_SVC_TIMEOUT_MAX		200000
@@ -1794,7 +1790,7 @@ static void ib_sa_remove_one(struct ib_device *device, void *client_data)
 	kfree(sa_dev);
 }
 
-static int __init ib_sa_init(void)
+int ib_sa_init(void)
 {
 	int ret;
 
@@ -1839,7 +1835,7 @@ err1:
 	return ret;
 }
 
-static void __exit ib_sa_cleanup(void)
+void ib_sa_cleanup(void)
 {
 	ibnl_remove_client(RDMA_NL_LS);
 	cancel_delayed_work(&ib_nl_timed_work);
@@ -1849,6 +1845,3 @@ static void __exit ib_sa_cleanup(void)
 	ib_unregister_client(&sa_client);
 	idr_destroy(&query_idr);
 }
-
-module_init(ib_sa_init);
-module_exit(ib_sa_cleanup);
-- 
cgit 1.4.1


From 735c631ae99d4b6cffc9e2774258329c526daa65 Mon Sep 17 00:00:00 2001
From: Mark Bloch <markb@mellanox.com>
Date: Thu, 19 May 2016 17:12:35 +0300
Subject: IB/core: Register SA ibnl client during ib_core initialization

Move SA ibnl client registration to ib_core module init.
This will allow us to register a single client to handle
all RDMA_NL_LS operations and make it SA independent.

Signed-off-by: Mark Bloch <markb@mellanox.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>
---
 drivers/infiniband/core/core_priv.h |  5 +++++
 drivers/infiniband/core/device.c    | 28 ++++++++++++++++++++++++++++
 drivers/infiniband/core/sa_query.c  | 27 +++++----------------------
 3 files changed, 38 insertions(+), 22 deletions(-)

(limited to 'drivers/infiniband')

diff --git a/drivers/infiniband/core/core_priv.h b/drivers/infiniband/core/core_priv.h
index c78a7fa2c2bb..1ff334587e7b 100644
--- a/drivers/infiniband/core/core_priv.h
+++ b/drivers/infiniband/core/core_priv.h
@@ -146,4 +146,9 @@ void ib_mad_cleanup(void);
 int ib_sa_init(void);
 void ib_sa_cleanup(void);
 
+int ib_nl_handle_resolve_resp(struct sk_buff *skb,
+			      struct netlink_callback *cb);
+int ib_nl_handle_set_timeout(struct sk_buff *skb,
+			     struct netlink_callback *cb);
+
 #endif /* _CORE_PRIV_H */
diff --git a/drivers/infiniband/core/device.c b/drivers/infiniband/core/device.c
index 2cd0956aef34..8b4366b2e358 100644
--- a/drivers/infiniband/core/device.c
+++ b/drivers/infiniband/core/device.c
@@ -955,6 +955,26 @@ struct net_device *ib_get_net_dev_by_params(struct ib_device *dev,
 }
 EXPORT_SYMBOL(ib_get_net_dev_by_params);
 
+static struct ibnl_client_cbs ibnl_ls_cb_table[] = {
+	[RDMA_NL_LS_OP_RESOLVE] = {
+		.dump = ib_nl_handle_resolve_resp,
+		.module = THIS_MODULE },
+	[RDMA_NL_LS_OP_SET_TIMEOUT] = {
+		.dump = ib_nl_handle_set_timeout,
+		.module = THIS_MODULE },
+};
+
+static int ib_add_ibnl_clients(void)
+{
+	return ibnl_add_client(RDMA_NL_LS, ARRAY_SIZE(ibnl_ls_cb_table),
+			       ibnl_ls_cb_table);
+}
+
+static void ib_remove_ibnl_clients(void)
+{
+	ibnl_remove_client(RDMA_NL_LS);
+}
+
 static int __init ib_core_init(void)
 {
 	int ret;
@@ -1001,10 +1021,17 @@ static int __init ib_core_init(void)
 		goto err_mad;
 	}
 
+	if (ib_add_ibnl_clients()) {
+		pr_warn("Couldn't register ibnl clients\n");
+		goto err_sa;
+	}
+
 	ib_cache_setup();
 
 	return 0;
 
+err_sa:
+	ib_sa_cleanup();
 err_mad:
 	ib_mad_cleanup();
 err_addr:
@@ -1023,6 +1050,7 @@ err:
 static void __exit ib_core_cleanup(void)
 {
 	ib_cache_cleanup();
+	ib_remove_ibnl_clients();
 	ib_sa_cleanup();
 	ib_mad_cleanup();
 	addr_cleanup();
diff --git a/drivers/infiniband/core/sa_query.c b/drivers/infiniband/core/sa_query.c
index db3c92d2b5ec..8bd61a612001 100644
--- a/drivers/infiniband/core/sa_query.c
+++ b/drivers/infiniband/core/sa_query.c
@@ -701,8 +701,8 @@ static void ib_nl_request_timeout(struct work_struct *work)
 	spin_unlock_irqrestore(&ib_nl_request_lock, flags);
 }
 
-static int ib_nl_handle_set_timeout(struct sk_buff *skb,
-				    struct netlink_callback *cb)
+int ib_nl_handle_set_timeout(struct sk_buff *skb,
+			     struct netlink_callback *cb)
 {
 	const struct nlmsghdr *nlh = (struct nlmsghdr *)cb->nlh;
 	int timeout, delta, abs_delta;
@@ -778,8 +778,8 @@ static inline int ib_nl_is_good_resolve_resp(const struct nlmsghdr *nlh)
 	return 1;
 }
 
-static int ib_nl_handle_resolve_resp(struct sk_buff *skb,
-				     struct netlink_callback *cb)
+int ib_nl_handle_resolve_resp(struct sk_buff *skb,
+			      struct netlink_callback *cb)
 {
 	const struct nlmsghdr *nlh = (struct nlmsghdr *)cb->nlh;
 	unsigned long flags;
@@ -834,15 +834,6 @@ resp_out:
 	return skb->len;
 }
 
-static struct ibnl_client_cbs ib_sa_cb_table[] = {
-	[RDMA_NL_LS_OP_RESOLVE] = {
-		.dump = ib_nl_handle_resolve_resp,
-		.module = THIS_MODULE },
-	[RDMA_NL_LS_OP_SET_TIMEOUT] = {
-		.dump = ib_nl_handle_set_timeout,
-		.module = THIS_MODULE },
-};
-
 static void free_sm_ah(struct kref *kref)
 {
 	struct ib_sa_sm_ah *sm_ah = container_of(kref, struct ib_sa_sm_ah, ref);
@@ -1816,17 +1807,10 @@ int ib_sa_init(void)
 		goto err3;
 	}
 
-	if (ibnl_add_client(RDMA_NL_LS, ARRAY_SIZE(ib_sa_cb_table),
-			    ib_sa_cb_table)) {
-		pr_err("Failed to add netlink callback\n");
-		ret = -EINVAL;
-		goto err4;
-	}
 	INIT_DELAYED_WORK(&ib_nl_timed_work, ib_nl_request_timeout);
 
 	return 0;
-err4:
-	destroy_workqueue(ib_nl_wq);
+
 err3:
 	mcast_cleanup();
 err2:
@@ -1837,7 +1821,6 @@ err1:
 
 void ib_sa_cleanup(void)
 {
-	ibnl_remove_client(RDMA_NL_LS);
 	cancel_delayed_work(&ib_nl_timed_work);
 	flush_workqueue(ib_nl_wq);
 	destroy_workqueue(ib_nl_wq);
-- 
cgit 1.4.1


From ae43f8286730d1f2d241c34601df59f6d2286ac4 Mon Sep 17 00:00:00 2001
From: Mark Bloch <markb@mellanox.com>
Date: Thu, 19 May 2016 17:12:36 +0300
Subject: IB/core: Add IP to GID netlink offload

There is an assumption that rdmacm is used only between nodes
in the same IB subnet, this why ARP resolution can be used to turn
IP to GID in rdmacm.

When dealing with IB communication between subnets this assumption
is no longer valid. ARP resolution will get us the next hop device
address and not the peer node's device address.

To solve this issue, we will check user space if it can provide the
GID of the peer node, and fail if not.

We add a sequence number to identify each request and fill in the GID
upon answer from userspace.

Signed-off-by: Mark Bloch <markb@mellanox.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>
---
 drivers/infiniband/core/addr.c      | 217 ++++++++++++++++++++++++++++++++----
 drivers/infiniband/core/core_priv.h |   2 +
 drivers/infiniband/core/device.c    |   3 +
 3 files changed, 198 insertions(+), 24 deletions(-)

(limited to 'drivers/infiniband')

diff --git a/drivers/infiniband/core/addr.c b/drivers/infiniband/core/addr.c
index 3a203ee08ced..1374541a4528 100644
--- a/drivers/infiniband/core/addr.c
+++ b/drivers/infiniband/core/addr.c
@@ -46,6 +46,10 @@
 #include <net/ip6_route.h>
 #include <rdma/ib_addr.h>
 #include <rdma/ib.h>
+#include <rdma/rdma_netlink.h>
+#include <net/netlink.h>
+
+#include "core_priv.h"
 
 struct addr_req {
 	struct list_head list;
@@ -58,8 +62,11 @@ struct addr_req {
 			 struct rdma_dev_addr *addr, void *context);
 	unsigned long timeout;
 	int status;
+	u32 seq;
 };
 
+static atomic_t ib_nl_addr_request_seq = ATOMIC_INIT(0);
+
 static void process_req(struct work_struct *work);
 
 static DEFINE_MUTEX(lock);
@@ -67,6 +74,126 @@ static LIST_HEAD(req_list);
 static DECLARE_DELAYED_WORK(work, process_req);
 static struct workqueue_struct *addr_wq;
 
+static const struct nla_policy ib_nl_addr_policy[LS_NLA_TYPE_MAX] = {
+	[LS_NLA_TYPE_DGID] = {.type = NLA_BINARY,
+		.len = sizeof(struct rdma_nla_ls_gid)},
+};
+
+static inline bool ib_nl_is_good_ip_resp(const struct nlmsghdr *nlh)
+{
+	struct nlattr *tb[LS_NLA_TYPE_MAX] = {};
+	int ret;
+
+	if (nlh->nlmsg_flags & RDMA_NL_LS_F_ERR)
+		return false;
+
+	ret = nla_parse(tb, LS_NLA_TYPE_MAX - 1, nlmsg_data(nlh),
+			nlmsg_len(nlh), ib_nl_addr_policy);
+	if (ret)
+		return false;
+
+	return true;
+}
+
+static void ib_nl_process_good_ip_rsep(const struct nlmsghdr *nlh)
+{
+	const struct nlattr *head, *curr;
+	union ib_gid gid;
+	struct addr_req *req;
+	int len, rem;
+	int found = 0;
+
+	head = (const struct nlattr *)nlmsg_data(nlh);
+	len = nlmsg_len(nlh);
+
+	nla_for_each_attr(curr, head, len, rem) {
+		if (curr->nla_type == LS_NLA_TYPE_DGID)
+			memcpy(&gid, nla_data(curr), nla_len(curr));
+	}
+
+	mutex_lock(&lock);
+	list_for_each_entry(req, &req_list, list) {
+		if (nlh->nlmsg_seq != req->seq)
+			continue;
+		/* We set the DGID part, the rest was set earlier */
+		rdma_addr_set_dgid(req->addr, &gid);
+		req->status = 0;
+		found = 1;
+		break;
+	}
+	mutex_unlock(&lock);
+
+	if (!found)
+		pr_info("Couldn't find request waiting for DGID: %pI6\n",
+			&gid);
+}
+
+int ib_nl_handle_ip_res_resp(struct sk_buff *skb,
+			     struct netlink_callback *cb)
+{
+	const struct nlmsghdr *nlh = (struct nlmsghdr *)cb->nlh;
+
+	if ((nlh->nlmsg_flags & NLM_F_REQUEST) ||
+	    !(NETLINK_CB(skb).sk) ||
+	    !netlink_capable(skb, CAP_NET_ADMIN))
+		return -EPERM;
+
+	if (ib_nl_is_good_ip_resp(nlh))
+		ib_nl_process_good_ip_rsep(nlh);
+
+	return skb->len;
+}
+
+static int ib_nl_ip_send_msg(struct rdma_dev_addr *dev_addr,
+			     const void *daddr,
+			     u32 seq, u16 family)
+{
+	struct sk_buff *skb = NULL;
+	struct nlmsghdr *nlh;
+	struct rdma_ls_ip_resolve_header *header;
+	void *data;
+	size_t size;
+	int attrtype;
+	int len;
+
+	if (family == AF_INET) {
+		size = sizeof(struct in_addr);
+		attrtype = RDMA_NLA_F_MANDATORY | LS_NLA_TYPE_IPV4;
+	} else {
+		size = sizeof(struct in6_addr);
+		attrtype = RDMA_NLA_F_MANDATORY | LS_NLA_TYPE_IPV6;
+	}
+
+	len = nla_total_size(sizeof(size));
+	len += NLMSG_ALIGN(sizeof(*header));
+
+	skb = nlmsg_new(len, GFP_KERNEL);
+	if (!skb)
+		return -ENOMEM;
+
+	data = ibnl_put_msg(skb, &nlh, seq, 0, RDMA_NL_LS,
+			    RDMA_NL_LS_OP_IP_RESOLVE, NLM_F_REQUEST);
+	if (!data) {
+		nlmsg_free(skb);
+		return -ENODATA;
+	}
+
+	/* Construct the family header first */
+	header = (struct rdma_ls_ip_resolve_header *)
+		skb_put(skb, NLMSG_ALIGN(sizeof(*header)));
+	header->ifindex = dev_addr->bound_dev_if;
+	nla_put(skb, attrtype, size, daddr);
+
+	/* Repair the nlmsg header length */
+	nlmsg_end(skb, nlh);
+	ibnl_multicast(skb, nlh, RDMA_NL_GROUP_LS, GFP_KERNEL);
+
+	/* Make the request retry, so when we get the response from userspace
+	 * we will have something.
+	 */
+	return -ENODATA;
+}
+
 int rdma_addr_size(struct sockaddr *addr)
 {
 	switch (addr->sa_family) {
@@ -195,6 +322,17 @@ static void queue_req(struct addr_req *req)
 	mutex_unlock(&lock);
 }
 
+static int ib_nl_fetch_ha(struct dst_entry *dst, struct rdma_dev_addr *dev_addr,
+			  const void *daddr, u32 seq, u16 family)
+{
+	if (ibnl_chk_listeners(RDMA_NL_GROUP_LS))
+		return -EADDRNOTAVAIL;
+
+	/* We fill in what we can, the response will fill the rest */
+	rdma_copy_addr(dev_addr, dst->dev, NULL);
+	return ib_nl_ip_send_msg(dev_addr, daddr, seq, family);
+}
+
 static int dst_fetch_ha(struct dst_entry *dst, struct rdma_dev_addr *dev_addr,
 			const void *daddr)
 {
@@ -219,6 +357,39 @@ static int dst_fetch_ha(struct dst_entry *dst, struct rdma_dev_addr *dev_addr,
 	return ret;
 }
 
+static bool has_gateway(struct dst_entry *dst, sa_family_t family)
+{
+	struct rtable *rt;
+	struct rt6_info *rt6;
+
+	if (family == AF_INET) {
+		rt = container_of(dst, struct rtable, dst);
+		return rt->rt_uses_gateway;
+	}
+
+	rt6 = container_of(dst, struct rt6_info, dst);
+	return rt6->rt6i_flags & RTF_GATEWAY;
+}
+
+static int fetch_ha(struct dst_entry *dst, struct rdma_dev_addr *dev_addr,
+		    const struct sockaddr *dst_in, u32 seq)
+{
+	const struct sockaddr_in *dst_in4 =
+		(const struct sockaddr_in *)dst_in;
+	const struct sockaddr_in6 *dst_in6 =
+		(const struct sockaddr_in6 *)dst_in;
+	const void *daddr = (dst_in->sa_family == AF_INET) ?
+		(const void *)&dst_in4->sin_addr.s_addr :
+		(const void *)&dst_in6->sin6_addr;
+	sa_family_t family = dst_in->sa_family;
+
+	/* Gateway + ARPHRD_INFINIBAND -> IB router */
+	if (has_gateway(dst, family) && dst->dev->type == ARPHRD_INFINIBAND)
+		return ib_nl_fetch_ha(dst, dev_addr, daddr, seq, family);
+	else
+		return dst_fetch_ha(dst, dev_addr, daddr);
+}
+
 static int addr4_resolve(struct sockaddr_in *src_in,
 			 const struct sockaddr_in *dst_in,
 			 struct rdma_dev_addr *addr,
@@ -242,10 +413,11 @@ static int addr4_resolve(struct sockaddr_in *src_in,
 	src_in->sin_family = AF_INET;
 	src_in->sin_addr.s_addr = fl4.saddr;
 
-	/* If there's a gateway, we're definitely in RoCE v2 (as RoCE v1 isn't
-	 * routable) and we could set the network type accordingly.
+	/* If there's a gateway and type of device not ARPHRD_INFINIBAND, we're
+	 * definitely in RoCE v2 (as RoCE v1 isn't routable) set the network
+	 * type accordingly.
 	 */
-	if (rt->rt_uses_gateway)
+	if (rt->rt_uses_gateway && rt->dst.dev->type != ARPHRD_INFINIBAND)
 		addr->network = RDMA_NETWORK_IPV4;
 
 	addr->hoplimit = ip4_dst_hoplimit(&rt->dst);
@@ -287,10 +459,12 @@ static int addr6_resolve(struct sockaddr_in6 *src_in,
 		src_in->sin6_addr = fl6.saddr;
 	}
 
-	/* If there's a gateway, we're definitely in RoCE v2 (as RoCE v1 isn't
-	 * routable) and we could set the network type accordingly.
+	/* If there's a gateway and type of device not ARPHRD_INFINIBAND, we're
+	 * definitely in RoCE v2 (as RoCE v1 isn't routable) set the network
+	 * type accordingly.
 	 */
-	if (rt->rt6i_flags & RTF_GATEWAY)
+	if (rt->rt6i_flags & RTF_GATEWAY &&
+	    ip6_dst_idev(dst)->dev->type != ARPHRD_INFINIBAND)
 		addr->network = RDMA_NETWORK_IPV6;
 
 	addr->hoplimit = ip6_dst_hoplimit(dst);
@@ -313,7 +487,8 @@ static int addr6_resolve(struct sockaddr_in6 *src_in,
 
 static int addr_resolve_neigh(struct dst_entry *dst,
 			      const struct sockaddr *dst_in,
-			      struct rdma_dev_addr *addr)
+			      struct rdma_dev_addr *addr,
+			      u32 seq)
 {
 	if (dst->dev->flags & IFF_LOOPBACK) {
 		int ret;
@@ -327,17 +502,8 @@ static int addr_resolve_neigh(struct dst_entry *dst,
 	}
 
 	/* If the device doesn't do ARP internally */
-	if (!(dst->dev->flags & IFF_NOARP)) {
-		const struct sockaddr_in *dst_in4 =
-			(const struct sockaddr_in *)dst_in;
-		const struct sockaddr_in6 *dst_in6 =
-			(const struct sockaddr_in6 *)dst_in;
-
-		return dst_fetch_ha(dst, addr,
-				    dst_in->sa_family == AF_INET ?
-				    (const void *)&dst_in4->sin_addr.s_addr :
-				    (const void *)&dst_in6->sin6_addr);
-	}
+	if (!(dst->dev->flags & IFF_NOARP))
+		return fetch_ha(dst, addr, dst_in, seq);
 
 	return rdma_copy_addr(addr, dst->dev, NULL);
 }
@@ -345,7 +511,8 @@ static int addr_resolve_neigh(struct dst_entry *dst,
 static int addr_resolve(struct sockaddr *src_in,
 			const struct sockaddr *dst_in,
 			struct rdma_dev_addr *addr,
-			bool resolve_neigh)
+			bool resolve_neigh,
+			u32 seq)
 {
 	struct net_device *ndev;
 	struct dst_entry *dst;
@@ -362,7 +529,7 @@ static int addr_resolve(struct sockaddr *src_in,
 			return ret;
 
 		if (resolve_neigh)
-			ret = addr_resolve_neigh(&rt->dst, dst_in, addr);
+			ret = addr_resolve_neigh(&rt->dst, dst_in, addr, seq);
 
 		ndev = rt->dst.dev;
 		dev_hold(ndev);
@@ -379,7 +546,7 @@ static int addr_resolve(struct sockaddr *src_in,
 			return ret;
 
 		if (resolve_neigh)
-			ret = addr_resolve_neigh(dst, dst_in, addr);
+			ret = addr_resolve_neigh(dst, dst_in, addr, seq);
 
 		ndev = dst->dev;
 		dev_hold(ndev);
@@ -408,7 +575,7 @@ static void process_req(struct work_struct *work)
 			src_in = (struct sockaddr *) &req->src_addr;
 			dst_in = (struct sockaddr *) &req->dst_addr;
 			req->status = addr_resolve(src_in, dst_in, req->addr,
-						   true);
+						   true, req->seq);
 			if (req->status && time_after_eq(jiffies, req->timeout))
 				req->status = -ETIMEDOUT;
 			else if (req->status == -ENODATA)
@@ -467,8 +634,9 @@ int rdma_resolve_ip(struct rdma_addr_client *client,
 	req->context = context;
 	req->client = client;
 	atomic_inc(&client->refcount);
+	req->seq = (u32)atomic_inc_return(&ib_nl_addr_request_seq);
 
-	req->status = addr_resolve(src_in, dst_in, addr, true);
+	req->status = addr_resolve(src_in, dst_in, addr, true, req->seq);
 	switch (req->status) {
 	case 0:
 		req->timeout = jiffies;
@@ -506,7 +674,7 @@ int rdma_resolve_ip_route(struct sockaddr *src_addr,
 		src_in->sa_family = dst_addr->sa_family;
 	}
 
-	return addr_resolve(src_in, dst_addr, addr, false);
+	return addr_resolve(src_in, dst_addr, addr, false, 0);
 }
 EXPORT_SYMBOL(rdma_resolve_ip_route);
 
@@ -638,6 +806,7 @@ int addr_init(void)
 
 	register_netevent_notifier(&nb);
 	rdma_addr_register_client(&self);
+
 	return 0;
 }
 
diff --git a/drivers/infiniband/core/core_priv.h b/drivers/infiniband/core/core_priv.h
index 1ff334587e7b..19d499dcab76 100644
--- a/drivers/infiniband/core/core_priv.h
+++ b/drivers/infiniband/core/core_priv.h
@@ -150,5 +150,7 @@ int ib_nl_handle_resolve_resp(struct sk_buff *skb,
 			      struct netlink_callback *cb);
 int ib_nl_handle_set_timeout(struct sk_buff *skb,
 			     struct netlink_callback *cb);
+int ib_nl_handle_ip_res_resp(struct sk_buff *skb,
+			     struct netlink_callback *cb);
 
 #endif /* _CORE_PRIV_H */
diff --git a/drivers/infiniband/core/device.c b/drivers/infiniband/core/device.c
index 8b4366b2e358..5516fb070344 100644
--- a/drivers/infiniband/core/device.c
+++ b/drivers/infiniband/core/device.c
@@ -962,6 +962,9 @@ static struct ibnl_client_cbs ibnl_ls_cb_table[] = {
 	[RDMA_NL_LS_OP_SET_TIMEOUT] = {
 		.dump = ib_nl_handle_set_timeout,
 		.module = THIS_MODULE },
+	[RDMA_NL_LS_OP_IP_RESOLVE] = {
+		.dump = ib_nl_handle_ip_res_resp,
+		.module = THIS_MODULE },
 };
 
 static int ib_add_ibnl_clients(void)
-- 
cgit 1.4.1


From 507f6afa3ab6c9473d81c8091be0d1b859509a6d Mon Sep 17 00:00:00 2001
From: Erez Shitrit <erezsh@mellanox.com>
Date: Wed, 25 May 2016 22:02:04 +0300
Subject: IB/core: Introduce capabilitymask2 field in ClassPortInfo mad

Change struct ib_class_port_info to conform to IB Spec 1.3
That in order to get specific capability mask from ClassPortInfo mad.

>From the IB Spec, ClassPortInfo section:
        "CapabilityMask2 Bits 0-26: Additional class-specific capabilities...
         RespTimeValue the rest 5 bits"

The new struct now has one field for capabilitymask2 (previously was the
reserved field) and the resp_time field.

And it fixes up qib and srpt, use of the field repurposed to be used as
capabilitymask2:
IB/qib: Change pma_get_classportinfo
IB/srpt: Adjust the use of ib_class_port_info

Signed-off-by: Erez Shitrit <erezsh@mellanox.com>
Reviewed-by: Leon Romanovsky <leonro@mellanox.com>
Reviewed-by: Hal Rosenstock <hal@mellanox.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>
---
 drivers/infiniband/hw/qib/qib_mad.c   |  6 ++--
 drivers/infiniband/ulp/srpt/ib_srpt.c |  2 +-
 include/rdma/ib_mad.h                 | 60 +++++++++++++++++++++++++++++++++--
 3 files changed, 63 insertions(+), 5 deletions(-)

(limited to 'drivers/infiniband')

diff --git a/drivers/infiniband/hw/qib/qib_mad.c b/drivers/infiniband/hw/qib/qib_mad.c
index 0bd18375d7df..d2ac29861af5 100644
--- a/drivers/infiniband/hw/qib/qib_mad.c
+++ b/drivers/infiniband/hw/qib/qib_mad.c
@@ -1172,11 +1172,13 @@ static int pma_get_classportinfo(struct ib_pma_mad *pmp,
 	 * Set the most significant bit of CM2 to indicate support for
 	 * congestion statistics
 	 */
-	p->reserved[0] = dd->psxmitwait_supported << 7;
+	ib_set_cpi_capmask2(p,
+			    dd->psxmitwait_supported <<
+			    (31 - IB_CLASS_PORT_INFO_RESP_TIME_FIELD_SIZE));
 	/*
 	 * Expected response time is 4.096 usec. * 2^18 == 1.073741824 sec.
 	 */
-	p->resp_time_value = 18;
+	ib_set_cpi_resp_time(p, 18);
 
 	return reply((struct ib_smp *) pmp);
 }
diff --git a/drivers/infiniband/ulp/srpt/ib_srpt.c b/drivers/infiniband/ulp/srpt/ib_srpt.c
index 2843f1ae75bd..887ebadd4774 100644
--- a/drivers/infiniband/ulp/srpt/ib_srpt.c
+++ b/drivers/infiniband/ulp/srpt/ib_srpt.c
@@ -254,8 +254,8 @@ static void srpt_get_class_port_info(struct ib_dm_mad *mad)
 	memset(cif, 0, sizeof(*cif));
 	cif->base_version = 1;
 	cif->class_version = 1;
-	cif->resp_time_value = 20;
 
+	ib_set_cpi_resp_time(cif, 20);
 	mad->mad_hdr.status = 0;
 }
 
diff --git a/include/rdma/ib_mad.h b/include/rdma/ib_mad.h
index 37dd534cbeab..c8a773ffe23b 100644
--- a/include/rdma/ib_mad.h
+++ b/include/rdma/ib_mad.h
@@ -239,12 +239,15 @@ struct ib_vendor_mad {
 
 #define IB_MGMT_CLASSPORTINFO_ATTR_ID	cpu_to_be16(0x0001)
 
+#define IB_CLASS_PORT_INFO_RESP_TIME_MASK	0x1F
+#define IB_CLASS_PORT_INFO_RESP_TIME_FIELD_SIZE 5
+
 struct ib_class_port_info {
 	u8			base_version;
 	u8			class_version;
 	__be16			capability_mask;
-	u8			reserved[3];
-	u8			resp_time_value;
+	  /* 27 bits for cap_mask2, 5 bits for resp_time */
+	__be32			cap_mask2_resp_time;
 	u8			redirect_gid[16];
 	__be32			redirect_tcslfl;
 	__be16			redirect_lid;
@@ -259,6 +262,59 @@ struct ib_class_port_info {
 	__be32			trap_qkey;
 };
 
+/**
+ * ib_get_cpi_resp_time - Returns the resp_time value from
+ * cap_mask2_resp_time in ib_class_port_info.
+ * @cpi: A struct ib_class_port_info mad.
+ */
+static inline u8 ib_get_cpi_resp_time(struct ib_class_port_info *cpi)
+{
+	return (u8)(be32_to_cpu(cpi->cap_mask2_resp_time) &
+		    IB_CLASS_PORT_INFO_RESP_TIME_MASK);
+}
+
+/**
+ * ib_set_cpi_resptime - Sets the response time in an
+ * ib_class_port_info mad.
+ * @cpi: A struct ib_class_port_info.
+ * @rtime: The response time to set.
+ */
+static inline void ib_set_cpi_resp_time(struct ib_class_port_info *cpi,
+					u8 rtime)
+{
+	cpi->cap_mask2_resp_time =
+		(cpi->cap_mask2_resp_time &
+		 cpu_to_be32(~IB_CLASS_PORT_INFO_RESP_TIME_MASK)) |
+		cpu_to_be32(rtime & IB_CLASS_PORT_INFO_RESP_TIME_MASK);
+}
+
+/**
+ * ib_get_cpi_capmask2 - Returns the capmask2 value from
+ * cap_mask2_resp_time in ib_class_port_info.
+ * @cpi: A struct ib_class_port_info mad.
+ */
+static inline u32 ib_get_cpi_capmask2(struct ib_class_port_info *cpi)
+{
+	return (be32_to_cpu(cpi->cap_mask2_resp_time) >>
+		IB_CLASS_PORT_INFO_RESP_TIME_FIELD_SIZE);
+}
+
+/**
+ * ib_set_cpi_capmask2 - Sets the capmask2 in an
+ * ib_class_port_info mad.
+ * @cpi: A struct ib_class_port_info.
+ * @capmask2: The capmask2 to set.
+ */
+static inline void ib_set_cpi_capmask2(struct ib_class_port_info *cpi,
+				       u32 capmask2)
+{
+	cpi->cap_mask2_resp_time =
+		(cpi->cap_mask2_resp_time &
+		 cpu_to_be32(IB_CLASS_PORT_INFO_RESP_TIME_MASK)) |
+		cpu_to_be32(capmask2 <<
+			    IB_CLASS_PORT_INFO_RESP_TIME_FIELD_SIZE);
+}
+
 struct ib_mad_notice_attr {
 	u8 generic_type;
 	u8 prod_type_msb;
-- 
cgit 1.4.1


From 628e6f75156eac6979eacc2e9383e41f6432beb4 Mon Sep 17 00:00:00 2001
From: Erez Shitrit <erezsh@mellanox.com>
Date: Wed, 25 May 2016 22:02:05 +0300
Subject: IB/SA Agent: Add support for SA agent get ClassPortInfo

New SA query function to return the ClassPortInfo struct from the SA.
If the SM supports FullMemberSendOnly mode for MCG's, it sets a
capability bit in the capability_mask2 field of the response.

Signed-off-by: Erez Shitrit <erezsh@mellanox.com>
Reviewed-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>
---
 drivers/infiniband/core/sa_query.c | 173 +++++++++++++++++++++++++++++++++++++
 include/rdma/ib_sa.h               |  12 +++
 2 files changed, 185 insertions(+)

(limited to 'drivers/infiniband')

diff --git a/drivers/infiniband/core/sa_query.c b/drivers/infiniband/core/sa_query.c
index 3ebd108bcc5f..5c37f2f56d3f 100644
--- a/drivers/infiniband/core/sa_query.c
+++ b/drivers/infiniband/core/sa_query.c
@@ -119,6 +119,12 @@ struct ib_sa_guidinfo_query {
 	struct ib_sa_query sa_query;
 };
 
+struct ib_sa_classport_info_query {
+	void (*callback)(int, struct ib_class_port_info *, void *);
+	void *context;
+	struct ib_sa_query sa_query;
+};
+
 struct ib_sa_mcmember_query {
 	void (*callback)(int, struct ib_sa_mcmember_rec *, void *);
 	void *context;
@@ -392,6 +398,82 @@ static const struct ib_field service_rec_table[] = {
 	  .size_bits    = 2*64 },
 };
 
+#define CLASSPORTINFO_REC_FIELD(field) \
+	.struct_offset_bytes = offsetof(struct ib_class_port_info, field),	\
+	.struct_size_bytes   = sizeof((struct ib_class_port_info *)0)->field,	\
+	.field_name          = "ib_class_port_info:" #field
+
+static const struct ib_field classport_info_rec_table[] = {
+	{ CLASSPORTINFO_REC_FIELD(base_version),
+	  .offset_words = 0,
+	  .offset_bits  = 0,
+	  .size_bits    = 8 },
+	{ CLASSPORTINFO_REC_FIELD(class_version),
+	  .offset_words = 0,
+	  .offset_bits  = 8,
+	  .size_bits    = 8 },
+	{ CLASSPORTINFO_REC_FIELD(capability_mask),
+	  .offset_words = 0,
+	  .offset_bits  = 16,
+	  .size_bits    = 16 },
+	{ CLASSPORTINFO_REC_FIELD(cap_mask2_resp_time),
+	  .offset_words = 1,
+	  .offset_bits  = 0,
+	  .size_bits    = 32 },
+	{ CLASSPORTINFO_REC_FIELD(redirect_gid),
+	  .offset_words = 2,
+	  .offset_bits  = 0,
+	  .size_bits    = 128 },
+	{ CLASSPORTINFO_REC_FIELD(redirect_tcslfl),
+	  .offset_words = 6,
+	  .offset_bits  = 0,
+	  .size_bits    = 32 },
+	{ CLASSPORTINFO_REC_FIELD(redirect_lid),
+	  .offset_words = 7,
+	  .offset_bits  = 0,
+	  .size_bits    = 16 },
+	{ CLASSPORTINFO_REC_FIELD(redirect_pkey),
+	  .offset_words = 7,
+	  .offset_bits  = 16,
+	  .size_bits    = 16 },
+
+	{ CLASSPORTINFO_REC_FIELD(redirect_qp),
+	  .offset_words = 8,
+	  .offset_bits  = 0,
+	  .size_bits    = 32 },
+	{ CLASSPORTINFO_REC_FIELD(redirect_qkey),
+	  .offset_words = 9,
+	  .offset_bits  = 0,
+	  .size_bits    = 32 },
+
+	{ CLASSPORTINFO_REC_FIELD(trap_gid),
+	  .offset_words = 10,
+	  .offset_bits  = 0,
+	  .size_bits    = 128 },
+	{ CLASSPORTINFO_REC_FIELD(trap_tcslfl),
+	  .offset_words = 14,
+	  .offset_bits  = 0,
+	  .size_bits    = 32 },
+
+	{ CLASSPORTINFO_REC_FIELD(trap_lid),
+	  .offset_words = 15,
+	  .offset_bits  = 0,
+	  .size_bits    = 16 },
+	{ CLASSPORTINFO_REC_FIELD(trap_pkey),
+	  .offset_words = 15,
+	  .offset_bits  = 16,
+	  .size_bits    = 16 },
+
+	{ CLASSPORTINFO_REC_FIELD(trap_hlqp),
+	  .offset_words = 16,
+	  .offset_bits  = 0,
+	  .size_bits    = 32 },
+	{ CLASSPORTINFO_REC_FIELD(trap_qkey),
+	  .offset_words = 17,
+	  .offset_bits  = 0,
+	  .size_bits    = 32 },
+};
+
 #define GUIDINFO_REC_FIELD(field) \
 	.struct_offset_bytes = offsetof(struct ib_sa_guidinfo_rec, field),	\
 	.struct_size_bytes   = sizeof((struct ib_sa_guidinfo_rec *) 0)->field,	\
@@ -1645,6 +1727,97 @@ err1:
 }
 EXPORT_SYMBOL(ib_sa_guid_info_rec_query);
 
+/* Support get SA ClassPortInfo */
+static void ib_sa_classport_info_rec_callback(struct ib_sa_query *sa_query,
+					      int status,
+					      struct ib_sa_mad *mad)
+{
+	struct ib_sa_classport_info_query *query =
+		container_of(sa_query, struct ib_sa_classport_info_query, sa_query);
+
+	if (mad) {
+		struct ib_class_port_info rec;
+
+		ib_unpack(classport_info_rec_table,
+			  ARRAY_SIZE(classport_info_rec_table),
+			  mad->data, &rec);
+		query->callback(status, &rec, query->context);
+	} else {
+		query->callback(status, NULL, query->context);
+	}
+}
+
+static void ib_sa_portclass_info_rec_release(struct ib_sa_query *sa_query)
+{
+	kfree(container_of(sa_query, struct ib_sa_classport_info_query,
+			   sa_query));
+}
+
+int ib_sa_classport_info_rec_query(struct ib_sa_client *client,
+				   struct ib_device *device, u8 port_num,
+				   int timeout_ms, gfp_t gfp_mask,
+				   void (*callback)(int status,
+						    struct ib_class_port_info *resp,
+						    void *context),
+				   void *context,
+				   struct ib_sa_query **sa_query)
+{
+	struct ib_sa_classport_info_query *query;
+	struct ib_sa_device *sa_dev = ib_get_client_data(device, &sa_client);
+	struct ib_sa_port *port;
+	struct ib_mad_agent *agent;
+	struct ib_sa_mad *mad;
+	int ret;
+
+	if (!sa_dev)
+		return -ENODEV;
+
+	port  = &sa_dev->port[port_num - sa_dev->start_port];
+	agent = port->agent;
+
+	query = kzalloc(sizeof(*query), gfp_mask);
+	if (!query)
+		return -ENOMEM;
+
+	query->sa_query.port = port;
+	ret = alloc_mad(&query->sa_query, gfp_mask);
+	if (ret)
+		goto err1;
+
+	ib_sa_client_get(client);
+	query->sa_query.client = client;
+	query->callback        = callback;
+	query->context         = context;
+
+	mad = query->sa_query.mad_buf->mad;
+	init_mad(mad, agent);
+
+	query->sa_query.callback = callback ? ib_sa_classport_info_rec_callback : NULL;
+
+	query->sa_query.release  = ib_sa_portclass_info_rec_release;
+	/* support GET only */
+	mad->mad_hdr.method	 = IB_MGMT_METHOD_GET;
+	mad->mad_hdr.attr_id	 = cpu_to_be16(IB_SA_ATTR_CLASS_PORTINFO);
+	mad->sa_hdr.comp_mask	 = 0;
+	*sa_query = &query->sa_query;
+
+	ret = send_mad(&query->sa_query, timeout_ms, gfp_mask);
+	if (ret < 0)
+		goto err2;
+
+	return ret;
+
+err2:
+	*sa_query = NULL;
+	ib_sa_client_put(query->sa_query.client);
+	free_mad(&query->sa_query);
+
+err1:
+	kfree(query);
+	return ret;
+}
+EXPORT_SYMBOL(ib_sa_classport_info_rec_query);
+
 static void send_handler(struct ib_mad_agent *agent,
 			 struct ib_mad_send_wc *mad_send_wc)
 {
diff --git a/include/rdma/ib_sa.h b/include/rdma/ib_sa.h
index cdc1c81aa275..384041669489 100644
--- a/include/rdma/ib_sa.h
+++ b/include/rdma/ib_sa.h
@@ -94,6 +94,8 @@ enum ib_sa_selector {
 	IB_SA_BEST = 3
 };
 
+#define IB_SA_CAP_MASK2_SENDONLY_FULL_MEM_SUPPORT	BIT(12)
+
 /*
  * Structures for SA records are named "struct ib_sa_xxx_rec."  No
  * attempt is made to pack structures to match the physical layout of
@@ -439,4 +441,14 @@ int ib_sa_guid_info_rec_query(struct ib_sa_client *client,
 			      void *context,
 			      struct ib_sa_query **sa_query);
 
+/* Support get SA ClassPortInfo */
+int ib_sa_classport_info_rec_query(struct ib_sa_client *client,
+				   struct ib_device *device, u8 port_num,
+				   int timeout_ms, gfp_t gfp_mask,
+				   void (*callback)(int status,
+						    struct ib_class_port_info *resp,
+						    void *context),
+				   void *context,
+				   struct ib_sa_query **sa_query);
+
 #endif /* IB_SA_H */
-- 
cgit 1.4.1


From cd6e9b7ef90515cb90962059ffb03b679de27f99 Mon Sep 17 00:00:00 2001
From: Erez Shitrit <erezsh@mellanox.com>
Date: Wed, 25 May 2016 22:02:06 +0300
Subject: IB/core: Support new type of join-state for multicast

There are four types for MCG, FullMember, NonMember, SendOnlyNonMember,
and the new added type: SendOnlyFullMember.
Add support for the new SendOnlyFullMember join state.

The new type allows host to send join request as sendonly, it will cause the
group to be created but without getting packets from this multicast back to the
host.

Signed-off-by: Erez Shitrit <erezsh@mellanox.com>
Reviewed-by: Leon Romanovsky <leonro@mellanox.com>
Reviewed-by: Christoph Lameter <cl@linux.com>
Reviewed-by: Ira Weiny <ira.weiny@intel.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>
---
 drivers/infiniband/core/multicast.c | 23 ++++++++++++++++++-----
 1 file changed, 18 insertions(+), 5 deletions(-)

(limited to 'drivers/infiniband')

diff --git a/drivers/infiniband/core/multicast.c b/drivers/infiniband/core/multicast.c
index 250937cb9a1a..a83ec28a147b 100644
--- a/drivers/infiniband/core/multicast.c
+++ b/drivers/infiniband/core/multicast.c
@@ -93,6 +93,18 @@ enum {
 
 struct mcast_member;
 
+/*
+* There are 4 types of join states:
+* FullMember, NonMember, SendOnlyNonMember, SendOnlyFullMember.
+*/
+enum {
+	FULLMEMBER_JOIN,
+	NONMEMBER_JOIN,
+	SENDONLY_NONMEBER_JOIN,
+	SENDONLY_FULLMEMBER_JOIN,
+	NUM_JOIN_MEMBERSHIP_TYPES,
+};
+
 struct mcast_group {
 	struct ib_sa_mcmember_rec rec;
 	struct rb_node		node;
@@ -102,7 +114,7 @@ struct mcast_group {
 	struct list_head	pending_list;
 	struct list_head	active_list;
 	struct mcast_member	*last_join;
-	int			members[3];
+	int			members[NUM_JOIN_MEMBERSHIP_TYPES];
 	atomic_t		refcount;
 	enum mcast_group_state	state;
 	struct ib_sa_query	*query;
@@ -220,8 +232,9 @@ static void queue_join(struct mcast_member *member)
 }
 
 /*
- * A multicast group has three types of members: full member, non member, and
- * send only member.  We need to keep track of the number of members of each
+ * A multicast group has four types of members: full member, non member,
+ * sendonly non member and sendonly full member.
+ * We need to keep track of the number of members of each
  * type based on their join state.  Adjust the number of members the belong to
  * the specified join states.
  */
@@ -229,7 +242,7 @@ static void adjust_membership(struct mcast_group *group, u8 join_state, int inc)
 {
 	int i;
 
-	for (i = 0; i < 3; i++, join_state >>= 1)
+	for (i = 0; i < NUM_JOIN_MEMBERSHIP_TYPES; i++, join_state >>= 1)
 		if (join_state & 0x1)
 			group->members[i] += inc;
 }
@@ -245,7 +258,7 @@ static u8 get_leave_state(struct mcast_group *group)
 	u8 leave_state = 0;
 	int i;
 
-	for (i = 0; i < 3; i++)
+	for (i = 0; i < NUM_JOIN_MEMBERSHIP_TYPES; i++)
 		if (!group->members[i])
 			leave_state |= (0x1 << i);
 
-- 
cgit 1.4.1


From 3b56113016400a4e2b9870c368ebb8080cb5739b Mon Sep 17 00:00:00 2001
From: Erez Shitrit <erezsh@mellanox.com>
Date: Wed, 25 May 2016 22:02:07 +0300
Subject: IB/ipoib: Support SendOnlyFullMember MCG for SendOnly join

Check (via an SA query) if the SM supports the new option for SendOnly
multicast joins.
If the SM supports that option it will use the new join state to create
such multicast group.
If SendOnlyFullMember is supported, we wouldn't use faked FullMember state
join for SendOnly MCG, use the correct state if supported.

This check is performed at every invocation of mcast_restart task, to be
sure that the driver stays in sync with the current state of the SM.

Signed-off-by: Erez Shitrit <erezsh@mellanox.com>
Reviewed-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>
---
 drivers/infiniband/ulp/ipoib/ipoib.h           |  2 +
 drivers/infiniband/ulp/ipoib/ipoib_main.c      | 73 ++++++++++++++++++++++++++
 drivers/infiniband/ulp/ipoib/ipoib_multicast.c | 38 +++++++++-----
 3 files changed, 100 insertions(+), 13 deletions(-)

(limited to 'drivers/infiniband')

diff --git a/drivers/infiniband/ulp/ipoib/ipoib.h b/drivers/infiniband/ulp/ipoib/ipoib.h
index caec8e9c4666..c51f618f6120 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib.h
+++ b/drivers/infiniband/ulp/ipoib/ipoib.h
@@ -392,6 +392,7 @@ struct ipoib_dev_priv {
 	struct ipoib_ethtool_st ethtool;
 	struct timer_list poll_timer;
 	unsigned max_send_sge;
+	bool sm_fullmember_sendonly_support;
 };
 
 struct ipoib_ah {
@@ -476,6 +477,7 @@ void ipoib_reap_ah(struct work_struct *work);
 
 void ipoib_mark_paths_invalid(struct net_device *dev);
 void ipoib_flush_paths(struct net_device *dev);
+int ipoib_check_sm_sendonly_fullmember_support(struct ipoib_dev_priv *priv);
 struct ipoib_dev_priv *ipoib_intf_alloc(const char *format);
 
 int ipoib_ib_dev_init(struct net_device *dev, struct ib_device *ca, int port);
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_main.c b/drivers/infiniband/ulp/ipoib/ipoib_main.c
index 80807d6e5c4c..8bf1859ebed4 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_main.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_main.c
@@ -117,6 +117,8 @@ int ipoib_open(struct net_device *dev)
 
 	set_bit(IPOIB_FLAG_ADMIN_UP, &priv->flags);
 
+	priv->sm_fullmember_sendonly_support = false;
+
 	if (ipoib_ib_dev_open(dev)) {
 		if (!test_bit(IPOIB_PKEY_ASSIGNED, &priv->flags))
 			return 0;
@@ -629,6 +631,77 @@ void ipoib_mark_paths_invalid(struct net_device *dev)
 	spin_unlock_irq(&priv->lock);
 }
 
+struct classport_info_context {
+	struct ipoib_dev_priv	*priv;
+	struct completion	done;
+	struct ib_sa_query	*sa_query;
+};
+
+static void classport_info_query_cb(int status, struct ib_class_port_info *rec,
+				    void *context)
+{
+	struct classport_info_context *cb_ctx = context;
+	struct ipoib_dev_priv *priv;
+
+	WARN_ON(!context);
+
+	priv = cb_ctx->priv;
+
+	if (status || !rec) {
+		pr_debug("device: %s failed query classport_info status: %d\n",
+			 priv->dev->name, status);
+		/* keeps the default, will try next mcast_restart */
+		priv->sm_fullmember_sendonly_support = false;
+		goto out;
+	}
+
+	if (ib_get_cpi_capmask2(rec) &
+	    IB_SA_CAP_MASK2_SENDONLY_FULL_MEM_SUPPORT) {
+		pr_debug("device: %s enabled fullmember-sendonly for sendonly MCG\n",
+			 priv->dev->name);
+		priv->sm_fullmember_sendonly_support = true;
+	} else {
+		pr_debug("device: %s disabled fullmember-sendonly for sendonly MCG\n",
+			 priv->dev->name);
+		priv->sm_fullmember_sendonly_support = false;
+	}
+
+out:
+	complete(&cb_ctx->done);
+}
+
+int ipoib_check_sm_sendonly_fullmember_support(struct ipoib_dev_priv *priv)
+{
+	struct classport_info_context *callback_context;
+	int ret;
+
+	callback_context = kmalloc(sizeof(*callback_context), GFP_KERNEL);
+	if (!callback_context)
+		return -ENOMEM;
+
+	callback_context->priv = priv;
+	init_completion(&callback_context->done);
+
+	ret = ib_sa_classport_info_rec_query(&ipoib_sa_client,
+					     priv->ca, priv->port, 3000,
+					     GFP_KERNEL,
+					     classport_info_query_cb,
+					     callback_context,
+					     &callback_context->sa_query);
+	if (ret < 0) {
+		pr_info("%s failed to send ib_sa_classport_info query, ret: %d\n",
+			priv->dev->name, ret);
+		kfree(callback_context);
+		return ret;
+	}
+
+	/* waiting for the callback to finish before returnning */
+	wait_for_completion(&callback_context->done);
+	kfree(callback_context);
+
+	return ret;
+}
+
 void ipoib_flush_paths(struct net_device *dev)
 {
 	struct ipoib_dev_priv *priv = netdev_priv(dev);
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_multicast.c b/drivers/infiniband/ulp/ipoib/ipoib_multicast.c
index 25889311b1e9..fc3e50e8e391 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_multicast.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_multicast.c
@@ -64,6 +64,9 @@ struct ipoib_mcast_iter {
 	unsigned int       send_only;
 };
 
+/* join state that allows creating mcg with sendonly member request */
+#define SENDONLY_FULLMEMBER_JOIN	8
+
 /*
  * This should be called with the priv->lock held
  */
@@ -326,12 +329,23 @@ void ipoib_mcast_carrier_on_task(struct work_struct *work)
 	struct ipoib_dev_priv *priv = container_of(work, struct ipoib_dev_priv,
 						   carrier_on_task);
 	struct ib_port_attr attr;
+	int ret;
 
 	if (ib_query_port(priv->ca, priv->port, &attr) ||
 	    attr.state != IB_PORT_ACTIVE) {
 		ipoib_dbg(priv, "Keeping carrier off until IB port is active\n");
 		return;
 	}
+	/*
+	 * Check if can send sendonly MCG's with sendonly-fullmember join state.
+	 * It done here after the successfully join to the broadcast group,
+	 * because the broadcast group must always be joined first and is always
+	 * re-joined if the SM changes substantially.
+	 */
+	ret = ipoib_check_sm_sendonly_fullmember_support(priv);
+	if (ret < 0)
+		pr_debug("%s failed query sm support for sendonly-fullmember (ret: %d)\n",
+			 priv->dev->name, ret);
 
 	/*
 	 * Take rtnl_lock to avoid racing with ipoib_stop() and
@@ -515,22 +529,20 @@ static int ipoib_mcast_join(struct net_device *dev, struct ipoib_mcast *mcast)
 		rec.hop_limit	  = priv->broadcast->mcmember.hop_limit;
 
 		/*
-		 * Send-only IB Multicast joins do not work at the core
-		 * IB layer yet, so we can't use them here.  However,
-		 * we are emulating an Ethernet multicast send, which
-		 * does not require a multicast subscription and will
-		 * still send properly.  The most appropriate thing to
+		 * Send-only IB Multicast joins work at the core IB layer but
+		 * require specific SM support.
+		 * We can use such joins here only if the current SM supports that feature.
+		 * However, if not, we emulate an Ethernet multicast send,
+		 * which does not require a multicast subscription and will
+		 * still send properly. The most appropriate thing to
 		 * do is to create the group if it doesn't exist as that
 		 * most closely emulates the behavior, from a user space
-		 * application perspecitive, of Ethernet multicast
-		 * operation.  For now, we do a full join, maybe later
-		 * when the core IB layers support send only joins we
-		 * will use them.
+		 * application perspective, of Ethernet multicast operation.
 		 */
-#if 0
-		if (test_bit(IPOIB_MCAST_FLAG_SENDONLY, &mcast->flags))
-			rec.join_state = 4;
-#endif
+		if (test_bit(IPOIB_MCAST_FLAG_SENDONLY, &mcast->flags) &&
+		    priv->sm_fullmember_sendonly_support)
+			/* SM supports sendonly-fullmember, otherwise fallback to full-member */
+			rec.join_state = SENDONLY_FULLMEMBER_JOIN;
 	}
 	spin_unlock_irq(&priv->lock);
 
-- 
cgit 1.4.1


From 492a7e67ff83fc59adb768de25ccaecd33d46beb Mon Sep 17 00:00:00 2001
From: Mark Bloch <markb@mellanox.com>
Date: Wed, 18 May 2016 16:42:43 +0300
Subject: IB/IPoIB: Allow setting the device address

In IB networks, and specifically in IPoIB/rdmacm traffic, the device
address of an IPoIB interface is used as a means to exchange information
between nodes needed for communication.

Currently an IPoIB interface will always be created with a device
address based on its node GUID without a way to change that.

This change adds the ability to set the device address of an IPoIB
interface by value. We use the set mac address ndo to do that.

The flow should be broken down to two:
1) The GID value is already in the GID table,
   in this case the interface will be able to set carrier up.

2) The GID value is not yet in the GID table,
   in this case the interface won't try to join the multicast group
   and will wait (listen on GID_CHANGE event) until the GID is inserted.

In order to track those changes, we add a new flag:
* IPOIB_FLAG_DEV_ADDR_SET.

When set, it means the dev_addr is a based on a value in the gid
table. this bit will be cleared upon a dev_addr change triggered
by the user and set after validation.

Per IB spec the port GUID can't change if the module is loaded.
port GUID is the basis for GID at index 0 which is the basis for
the default device address of a ipoib interface.

The issue is that there are devices that don't follow the spec,
they change the port GUID while HCA is powered on, so in order
not to break userspace applications. We need to check if the
user wanted to control the device address and we assume that
if he sets the device address back to be based on GID index 0,
he no longer wishs to control it.

In order to track this, we add an additional flag:
* IPOIB_FLAG_DEV_ADDR_CTRL

When setting the device address, there is no validation of the upper
twelve bytes of the device address (flags, qpn, subnet prefix) as those
bytes are not under the control of the user.

Signed-off-by: Mark Bloch <markb@mellanox.com>
Reviewed-by: Leon Romanovsky <leonro@mellanox.com>
Signed-off-by: Leon Romanovsky <leon@kernel.org>
Signed-off-by: Doug Ledford <dledford@redhat.com>
---
 drivers/infiniband/ulp/ipoib/ipoib.h           |   2 +
 drivers/infiniband/ulp/ipoib/ipoib_ib.c        | 109 ++++++++++++++++++++++++-
 drivers/infiniband/ulp/ipoib/ipoib_main.c      |  67 +++++++++++++++
 drivers/infiniband/ulp/ipoib/ipoib_multicast.c |  10 ++-
 drivers/infiniband/ulp/ipoib/ipoib_verbs.c     |   3 +
 drivers/infiniband/ulp/ipoib/ipoib_vlan.c      |   2 +
 6 files changed, 187 insertions(+), 6 deletions(-)

(limited to 'drivers/infiniband')

diff --git a/drivers/infiniband/ulp/ipoib/ipoib.h b/drivers/infiniband/ulp/ipoib/ipoib.h
index c51f618f6120..bab7db6fa9ab 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib.h
+++ b/drivers/infiniband/ulp/ipoib/ipoib.h
@@ -92,6 +92,8 @@ enum {
 	IPOIB_FLAG_UMCAST	  = 10,
 	IPOIB_STOP_NEIGH_GC	  = 11,
 	IPOIB_NEIGH_TBL_FLUSH	  = 12,
+	IPOIB_FLAG_DEV_ADDR_SET	  = 13,
+	IPOIB_FLAG_DEV_ADDR_CTRL  = 14,
 
 	IPOIB_MAX_BACKOFF_SECONDS = 16,
 
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_ib.c b/drivers/infiniband/ulp/ipoib/ipoib_ib.c
index da5f28c892ca..7e9a77040a24 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_ib.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_ib.c
@@ -997,6 +997,106 @@ static inline int update_child_pkey(struct ipoib_dev_priv *priv)
 	return 0;
 }
 
+/*
+ * returns true if the device address of the ipoib interface has changed and the
+ * new address is a valid one (i.e in the gid table), return false otherwise.
+ */
+static bool ipoib_dev_addr_changed_valid(struct ipoib_dev_priv *priv)
+{
+	union ib_gid search_gid;
+	union ib_gid gid0;
+	union ib_gid *netdev_gid;
+	int err;
+	u16 index;
+	u8 port;
+	bool ret = false;
+
+	netdev_gid = (union ib_gid *)(priv->dev->dev_addr + 4);
+	if (ib_query_gid(priv->ca, priv->port, 0, &gid0, NULL))
+		return false;
+
+	netif_addr_lock(priv->dev);
+
+	/* The subnet prefix may have changed, update it now so we won't have
+	 * to do it later
+	 */
+	priv->local_gid.global.subnet_prefix = gid0.global.subnet_prefix;
+	netdev_gid->global.subnet_prefix = gid0.global.subnet_prefix;
+	search_gid.global.subnet_prefix = gid0.global.subnet_prefix;
+
+	search_gid.global.interface_id = priv->local_gid.global.interface_id;
+
+	netif_addr_unlock(priv->dev);
+
+	err = ib_find_gid(priv->ca, &search_gid, IB_GID_TYPE_IB,
+			  priv->dev, &port, &index);
+
+	netif_addr_lock(priv->dev);
+
+	if (search_gid.global.interface_id !=
+	    priv->local_gid.global.interface_id)
+		/* There was a change while we were looking up the gid, bail
+		 * here and let the next work sort this out
+		 */
+		goto out;
+
+	/* The next section of code needs some background:
+	 * Per IB spec the port GUID can't change if the HCA is powered on.
+	 * port GUID is the basis for GID at index 0 which is the basis for
+	 * the default device address of a ipoib interface.
+	 *
+	 * so it seems the flow should be:
+	 * if user_changed_dev_addr && gid in gid tbl
+	 *	set bit dev_addr_set
+	 *	return true
+	 * else
+	 *	return false
+	 *
+	 * The issue is that there are devices that don't follow the spec,
+	 * they change the port GUID when the HCA is powered, so in order
+	 * not to break userspace applications, We need to check if the
+	 * user wanted to control the device address and we assume that
+	 * if he sets the device address back to be based on GID index 0,
+	 * he no longer wishs to control it.
+	 *
+	 * If the user doesn't control the the device address,
+	 * IPOIB_FLAG_DEV_ADDR_SET is set and ib_find_gid failed it means
+	 * the port GUID has changed and GID at index 0 has changed
+	 * so we need to change priv->local_gid and priv->dev->dev_addr
+	 * to reflect the new GID.
+	 */
+	if (!test_bit(IPOIB_FLAG_DEV_ADDR_SET, &priv->flags)) {
+		if (!err && port == priv->port) {
+			set_bit(IPOIB_FLAG_DEV_ADDR_SET, &priv->flags);
+			if (index == 0)
+				clear_bit(IPOIB_FLAG_DEV_ADDR_CTRL,
+					  &priv->flags);
+			else
+				set_bit(IPOIB_FLAG_DEV_ADDR_CTRL, &priv->flags);
+			ret = true;
+		} else {
+			ret = false;
+		}
+	} else {
+		if (!err && port == priv->port) {
+			ret = true;
+		} else {
+			if (!test_bit(IPOIB_FLAG_DEV_ADDR_CTRL, &priv->flags)) {
+				memcpy(&priv->local_gid, &gid0,
+				       sizeof(priv->local_gid));
+				memcpy(priv->dev->dev_addr + 4, &gid0,
+				       sizeof(priv->local_gid));
+				ret = true;
+			}
+		}
+	}
+
+out:
+	netif_addr_unlock(priv->dev);
+
+	return ret;
+}
+
 static void __ipoib_ib_dev_flush(struct ipoib_dev_priv *priv,
 				enum ipoib_flush_level level,
 				int nesting)
@@ -1018,6 +1118,9 @@ static void __ipoib_ib_dev_flush(struct ipoib_dev_priv *priv,
 
 	if (!test_bit(IPOIB_FLAG_INITIALIZED, &priv->flags) &&
 	    level != IPOIB_FLUSH_HEAVY) {
+		/* Make sure the dev_addr is set even if not flushing */
+		if (level == IPOIB_FLUSH_LIGHT)
+			ipoib_dev_addr_changed_valid(priv);
 		ipoib_dbg(priv, "Not flushing - IPOIB_FLAG_INITIALIZED not set.\n");
 		return;
 	}
@@ -1029,7 +1132,8 @@ static void __ipoib_ib_dev_flush(struct ipoib_dev_priv *priv,
 				update_parent_pkey(priv);
 			else
 				update_child_pkey(priv);
-		}
+		} else if (level == IPOIB_FLUSH_LIGHT)
+			ipoib_dev_addr_changed_valid(priv);
 		ipoib_dbg(priv, "Not flushing - IPOIB_FLAG_ADMIN_UP not set.\n");
 		return;
 	}
@@ -1081,7 +1185,8 @@ static void __ipoib_ib_dev_flush(struct ipoib_dev_priv *priv,
 	if (test_bit(IPOIB_FLAG_ADMIN_UP, &priv->flags)) {
 		if (level >= IPOIB_FLUSH_NORMAL)
 			ipoib_ib_dev_up(dev);
-		ipoib_mcast_restart_task(&priv->restart_task);
+		if (ipoib_dev_addr_changed_valid(priv))
+			ipoib_mcast_restart_task(&priv->restart_task);
 	}
 }
 
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_main.c b/drivers/infiniband/ulp/ipoib/ipoib_main.c
index 8bf1859ebed4..2c3fb5337bc1 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_main.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_main.c
@@ -99,6 +99,7 @@ static struct net_device *ipoib_get_net_dev_by_params(
 		struct ib_device *dev, u8 port, u16 pkey,
 		const union ib_gid *gid, const struct sockaddr *addr,
 		void *client_data);
+static int ipoib_set_mac(struct net_device *dev, void *addr);
 
 static struct ib_client ipoib_client = {
 	.name   = "ipoib",
@@ -1722,6 +1723,7 @@ static const struct net_device_ops ipoib_netdev_ops_pf = {
 	.ndo_get_vf_config	 = ipoib_get_vf_config,
 	.ndo_get_vf_stats	 = ipoib_get_vf_stats,
 	.ndo_set_vf_guid	 = ipoib_set_vf_guid,
+	.ndo_set_mac_address	 = ipoib_set_mac,
 };
 
 static const struct net_device_ops ipoib_netdev_ops_vf = {
@@ -1844,6 +1846,70 @@ int ipoib_add_umcast_attr(struct net_device *dev)
 	return device_create_file(&dev->dev, &dev_attr_umcast);
 }
 
+static void set_base_guid(struct ipoib_dev_priv *priv, union ib_gid *gid)
+{
+	struct ipoib_dev_priv *child_priv;
+	struct net_device *netdev = priv->dev;
+
+	netif_addr_lock(netdev);
+
+	memcpy(&priv->local_gid.global.interface_id,
+	       &gid->global.interface_id,
+	       sizeof(gid->global.interface_id));
+	memcpy(netdev->dev_addr + 4, &priv->local_gid, sizeof(priv->local_gid));
+	clear_bit(IPOIB_FLAG_DEV_ADDR_SET, &priv->flags);
+
+	netif_addr_unlock(netdev);
+
+	if (!test_bit(IPOIB_FLAG_SUBINTERFACE, &priv->flags)) {
+		down_read(&priv->vlan_rwsem);
+		list_for_each_entry(child_priv, &priv->child_intfs, list)
+			set_base_guid(child_priv, gid);
+		up_read(&priv->vlan_rwsem);
+	}
+}
+
+static int ipoib_check_lladdr(struct net_device *dev,
+			      struct sockaddr_storage *ss)
+{
+	union ib_gid *gid = (union ib_gid *)(ss->__data + 4);
+	int ret = 0;
+
+	netif_addr_lock(dev);
+
+	/* Make sure the QPN, reserved and subnet prefix match the current
+	 * lladdr, it also makes sure the lladdr is unicast.
+	 */
+	if (memcmp(dev->dev_addr, ss->__data,
+		   4 + sizeof(gid->global.subnet_prefix)) ||
+	    gid->global.interface_id == 0)
+		ret = -EINVAL;
+
+	netif_addr_unlock(dev);
+
+	return ret;
+}
+
+static int ipoib_set_mac(struct net_device *dev, void *addr)
+{
+	struct ipoib_dev_priv *priv = netdev_priv(dev);
+	struct sockaddr_storage *ss = addr;
+	int ret;
+
+	if (!(dev->priv_flags & IFF_LIVE_ADDR_CHANGE) && netif_running(dev))
+		return -EBUSY;
+
+	ret = ipoib_check_lladdr(dev, ss);
+	if (ret)
+		return ret;
+
+	set_base_guid(priv, (union ib_gid *)(ss->__data + 4));
+
+	queue_work(ipoib_workqueue, &priv->flush_light);
+
+	return 0;
+}
+
 static ssize_t create_child(struct device *dev,
 			    struct device_attribute *attr,
 			    const char *buf, size_t count)
@@ -1967,6 +2033,7 @@ static struct net_device *ipoib_add_port(const char *format,
 		goto device_init_failed;
 	} else
 		memcpy(priv->dev->dev_addr + 4, priv->local_gid.raw, sizeof (union ib_gid));
+	set_bit(IPOIB_FLAG_DEV_ADDR_SET, &priv->flags);
 
 	result = ipoib_dev_init(priv->dev, hca, port);
 	if (result < 0) {
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_multicast.c b/drivers/infiniband/ulp/ipoib/ipoib_multicast.c
index fc3e50e8e391..82fbc9442608 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_multicast.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_multicast.c
@@ -582,11 +582,13 @@ void ipoib_mcast_join_task(struct work_struct *work)
 		return;
 	}
 	priv->local_lid = port_attr.lid;
+	netif_addr_lock(dev);
 
-	if (ib_query_gid(priv->ca, priv->port, 0, &priv->local_gid, NULL))
-		ipoib_warn(priv, "ib_query_gid() failed\n");
-	else
-		memcpy(priv->dev->dev_addr + 4, priv->local_gid.raw, sizeof (union ib_gid));
+	if (!test_bit(IPOIB_FLAG_DEV_ADDR_SET, &priv->flags)) {
+		netif_addr_unlock(dev);
+		return;
+	}
+	netif_addr_unlock(dev);
 
 	spin_lock_irq(&priv->lock);
 	if (!test_bit(IPOIB_FLAG_OPER_UP, &priv->flags))
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_verbs.c b/drivers/infiniband/ulp/ipoib/ipoib_verbs.c
index b809c373e40e..1e7cbbaa15bd 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_verbs.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_verbs.c
@@ -307,5 +307,8 @@ void ipoib_event(struct ib_event_handler *handler,
 		queue_work(ipoib_workqueue, &priv->flush_normal);
 	} else if (record->event == IB_EVENT_PKEY_CHANGE) {
 		queue_work(ipoib_workqueue, &priv->flush_heavy);
+	} else if (record->event == IB_EVENT_GID_CHANGE &&
+		   !test_bit(IPOIB_FLAG_DEV_ADDR_SET, &priv->flags)) {
+		queue_work(ipoib_workqueue, &priv->flush_light);
 	}
 }
diff --git a/drivers/infiniband/ulp/ipoib/ipoib_vlan.c b/drivers/infiniband/ulp/ipoib/ipoib_vlan.c
index fca1a882de27..64a35595eab8 100644
--- a/drivers/infiniband/ulp/ipoib/ipoib_vlan.c
+++ b/drivers/infiniband/ulp/ipoib/ipoib_vlan.c
@@ -68,6 +68,8 @@ int __ipoib_vlan_add(struct ipoib_dev_priv *ppriv, struct ipoib_dev_priv *priv,
 	priv->pkey = pkey;
 
 	memcpy(priv->dev->dev_addr, ppriv->dev->dev_addr, INFINIBAND_ALEN);
+	memcpy(&priv->local_gid, &ppriv->local_gid, sizeof(priv->local_gid));
+	set_bit(IPOIB_FLAG_DEV_ADDR_SET, &priv->flags);
 	priv->dev->broadcast[8] = pkey >> 8;
 	priv->dev->broadcast[9] = pkey & 0xff;
 
-- 
cgit 1.4.1