IB: Support netlink commands in non init_net net namespaces

PATCH RESEND Applied Leon Romanovsky 2 participants 2 messages Jul 23, 2019 – Jul 25, 2019 InfiniBand

lore

Share & tools

lore

Leon Romanovsky

author

2019-07-23 07:02 UTC #0 lore raw

PATCH RESEND 1/1 IB: Support netlink commands in non init_net net namespaces

From: Parav Pandit <[email protected]>

Now that IB core supports RDMA device binding with specific net namespace, enable IB core to accept netlink commands in non init_net namespaces.

This is done by having per net namespace netlink socket.

At present only netlink device handling client RDMA_NL_NLDEV supports device handling in multiple net namespaces.
Hence do not accept netlink messages for other clients in non init_net net namespaces.

Signed-off-by Parav Pandit <[email protected]>

Signed-off-by Leon Romanovsky <[email protected]>

---
Rebased on top v5.3-rc1

---
 drivers/infiniband/core/addr.c      |  2 +-
 drivers/infiniband/core/core_priv.h | 24 ++++++++++-
 drivers/infiniband/core/device.c    | 38 ++++++-----------
 drivers/infiniband/core/iwpm_msg.c  |  8 ++--
 drivers/infiniband/core/iwpm_util.c |  6 +--
 drivers/infiniband/core/netlink.c   | 63 ++++++++++++++++++++---------
 drivers/infiniband/core/nldev.c     | 20 ++++-----
 drivers/infiniband/core/sa_query.c  |  2 +-
 include/rdma/rdma_netlink.h         | 10 +++--
 9 files changed, 105 insertions(+), 68 deletions(-)

drivers/infiniband/core/addr.c +1 -1

index 9b76a8fcdd24..1dd467bed8fc 100644
@@ -183,7 +183,7 @@ static int ib_nl_ip_send_msg(struct rdma_dev_addr *dev_addr,
 
 	/* Repair the nlmsg header length */
 	nlmsg_end(skb, nlh);
-	rdma_nl_multicast(skb, RDMA_NL_GROUP_LS, GFP_KERNEL);
+	rdma_nl_multicast(&init_net, skb, RDMA_NL_GROUP_LS, GFP_KERNEL);
 
 	/* Make the request retry, so when we get the response from userspace
 	 * we will have something.

drivers/infiniband/core/core_priv.h +23 -1

index 888d89ce81df..589ed805e0ad 100644
@@ -36,6 +36,8 @@
 #include <linux/list.h>
 #include <linux/spinlock.h>
 #include <linux/cgroup_rdma.h>
+#include <net/net_namespace.h>
+#include <net/netns/generic.h>
 
 #include <rdma/ib_verbs.h>
 #include <rdma/opa_addr.h>

@@ -54,8 +56,26 @@ struct pkey_index_qp_list {
 	struct list_head    qp_list;
 };
 
+/**
+ * struct rdma_dev_net - rdma net namespace metadata for a net
+ * @nl_sock:	Pointer to netlink socket
+ * @net:	Pointer to owner net namespace
+ * @id:		xarray id to identify the net namespace.
+ */
+struct rdma_dev_net {
+	struct sock *nl_sock;
+	possible_net_t net;
+	u32 id;
+};
+
 extern const struct attribute_group ib_dev_attr_group;
 extern bool ib_devices_shared_netns;
+extern unsigned int rdma_dev_net_id;
+
+static inline struct rdma_dev_net *rdma_net_to_dev_net(struct net *net)
+{
+	return net_generic(net, rdma_dev_net_id);
+}
 
 int ib_device_register_sysfs(struct ib_device *device);
 void ib_device_unregister_sysfs(struct ib_device *device);

@@ -179,7 +199,6 @@ void ib_mad_cleanup(void);
 int ib_sa_init(void);
 void ib_sa_cleanup(void);
 
-int rdma_nl_init(void);
 void rdma_nl_exit(void);
 
 int ib_nl_handle_resolve_resp(struct sk_buff *skb,

@@ -362,4 +381,7 @@ void ib_port_unregister_module_stat(struct kobject *kobj);
 
 int ib_device_set_netns_put(struct sk_buff *skb,
 			    struct ib_device *dev, u32 ns_fd);
+
+int rdma_nl_net_init(struct rdma_dev_net *rnet);
+void rdma_nl_net_exit(struct rdma_dev_net *rnet);
 #endif /* _CORE_PRIV_H */

drivers/infiniband/core/device.c +13 ~~-25~~

index 9773145dee09..c56993e5e5ea 100644
@@ -39,7 +39,6 @@
 #include <linux/init.h>
 #include <linux/netdevice.h>
 #include <net/net_namespace.h>
-#include <net/netns/generic.h>
 #include <linux/security.h>
 #include <linux/notifier.h>
 #include <linux/hashtable.h>

@@ -105,17 +104,7 @@ static DECLARE_RWSEM(clients_rwsem);
  */
 #define CLIENT_DATA_REGISTERED XA_MARK_1
 
-/**
- * struct rdma_dev_net - rdma net namespace metadata for a net
- * @net:	Pointer to owner net namespace
- * @id:		xarray id to identify the net namespace.
- */
-struct rdma_dev_net {
-	possible_net_t net;
-	u32 id;
-};
-
-static unsigned int rdma_dev_net_id;
+unsigned int rdma_dev_net_id;
 
 /*
  * A list of net namespaces is maintained in an xarray. This is necessary

@@ -1047,7 +1036,7 @@ int rdma_compatdev_set(u8 enable)
 
 static void rdma_dev_exit_net(struct net *net)
 {
-	struct rdma_dev_net *rnet = net_generic(net, rdma_dev_net_id);
+	struct rdma_dev_net *rnet = rdma_net_to_dev_net(net);
 	struct ib_device *dev;
 	unsigned long index;
 	int ret;

@@ -1081,25 +1070,32 @@ static void rdma_dev_exit_net(struct net *net)
 	}
 	up_read(&devices_rwsem);
 
+	rdma_nl_net_exit(rnet);
 	xa_erase(&rdma_nets, rnet->id);
 }
 
 static __net_init int rdma_dev_init_net(struct net *net)
 {
-	struct rdma_dev_net *rnet = net_generic(net, rdma_dev_net_id);
+	struct rdma_dev_net *rnet = rdma_net_to_dev_net(net);
 	unsigned long index;
 	struct ib_device *dev;
 	int ret;
 
+	write_pnet(&rnet->net, net);
+
+	ret = rdma_nl_net_init(rnet);
+	if (ret)
+		return ret;
+
 	/* No need to create any compat devices in default init_net. */
 	if (net_eq(net, &init_net))
 		return 0;
 
-	write_pnet(&rnet->net, net);
-
 	ret = xa_alloc(&rdma_nets, &rnet->id, rnet, xa_limit_32b, GFP_KERNEL);
-	if (ret)
+	if (ret) {
+		rdma_nl_net_exit(rnet);
 		return ret;
+	}
 
 	down_read(&devices_rwsem);
 	xa_for_each_marked (&devices, index, dev, DEVICE_REGISTERED) {

@@ -2626,12 +2622,6 @@ static int __init ib_core_init(void)
 		goto err_comp_unbound;
 	}
 
-	ret = rdma_nl_init();
-	if (ret) {
-		pr_warn("Couldn't init IB netlink interface: err %d\n", ret);
-		goto err_sysfs;
-	}
-
 	ret = addr_init();
 	if (ret) {
 		pr_warn("Could't init IB address resolution\n");

@@ -2677,8 +2667,6 @@ static int __init ib_core_init(void)
 err_addr:
 	addr_cleanup();
 err_ibnl:
-	rdma_nl_exit();
-err_sysfs:
 	class_unregister(&ib_class);
 err_comp_unbound:
 	destroy_workqueue(ib_comp_unbound_wq);

drivers/infiniband/core/iwpm_msg.c +4 -4

index 2452b0ddcf0d..f1a873d4e842 100644
@@ -112,7 +112,7 @@ int iwpm_register_pid(struct iwpm_dev_data *pm_msg, u8 nl_client)
 	pr_debug("%s: Multicasting a nlmsg (dev = %s ifname = %s iwpm = %s)\n",
 		__func__, pm_msg->dev_name, pm_msg->if_name, iwpm_ulib_name);
 
-	ret = rdma_nl_multicast(skb, RDMA_NL_GROUP_IWPM, GFP_KERNEL);
+	ret = rdma_nl_multicast(&init_net, skb, RDMA_NL_GROUP_IWPM, GFP_KERNEL);
 	if (ret) {
 		skb = NULL; /* skb is freed in the netlink send-op handling */
 		iwpm_user_pid = IWPM_PID_UNAVAILABLE;

@@ -202,7 +202,7 @@ int iwpm_add_mapping(struct iwpm_sa_data *pm_msg, u8 nl_client)
 	nlmsg_end(skb, nlh);
 	nlmsg_request->req_buffer = pm_msg;
 
-	ret = rdma_nl_unicast_wait(skb, iwpm_user_pid);
+	ret = rdma_nl_unicast_wait(&init_net, skb, iwpm_user_pid);
 	if (ret) {
 		skb = NULL; /* skb is freed in the netlink send-op handling */
 		iwpm_user_pid = IWPM_PID_UNDEFINED;

@@ -297,7 +297,7 @@ int iwpm_add_and_query_mapping(struct iwpm_sa_data *pm_msg, u8 nl_client)
 	nlmsg_end(skb, nlh);
 	nlmsg_request->req_buffer = pm_msg;
 
-	ret = rdma_nl_unicast_wait(skb, iwpm_user_pid);
+	ret = rdma_nl_unicast_wait(&init_net, skb, iwpm_user_pid);
 	if (ret) {
 		skb = NULL; /* skb is freed in the netlink send-op handling */
 		err_str = "Unable to send a nlmsg";

@@ -364,7 +364,7 @@ int iwpm_remove_mapping(struct sockaddr_storage *local_addr, u8 nl_client)
 
 	nlmsg_end(skb, nlh);
 
-	ret = rdma_nl_unicast_wait(skb, iwpm_user_pid);
+	ret = rdma_nl_unicast_wait(&init_net, skb, iwpm_user_pid);
 	if (ret) {
 		skb = NULL; /* skb is freed in the netlink send-op handling */
 		iwpm_user_pid = IWPM_PID_UNDEFINED;

drivers/infiniband/core/iwpm_util.c +3 -3

index 41929bb83739..c7ad3499228c 100644
@@ -645,7 +645,7 @@ static int send_mapinfo_num(u32 mapping_num, u8 nl_client, int iwpm_pid)
 
 	nlmsg_end(skb, nlh);
 
-	ret = rdma_nl_unicast(skb, iwpm_pid);
+	ret = rdma_nl_unicast(&init_net, skb, iwpm_pid);
 	if (ret) {
 		skb = NULL;
 		err_str = "Unable to send a nlmsg";

@@ -674,7 +674,7 @@ static int send_nlmsg_done(struct sk_buff *skb, u8 nl_client, int iwpm_pid)
 		return -ENOMEM;
 	}
 	nlh->nlmsg_type = NLMSG_DONE;
-	ret = rdma_nl_unicast(skb, iwpm_pid);
+	ret = rdma_nl_unicast(&init_net, skb, iwpm_pid);
 	if (ret)
 		pr_warn("%s Unable to send a nlmsg\n", __func__);
 	return ret;

@@ -824,7 +824,7 @@ int iwpm_send_hello(u8 nl_client, int iwpm_pid, u16 abi_version)
 		goto hello_num_error;
 	nlmsg_end(skb, nlh);
 
-	ret = rdma_nl_unicast(skb, iwpm_pid);
+	ret = rdma_nl_unicast(&init_net, skb, iwpm_pid);
 	if (ret) {
 		skb = NULL;
 		err_str = "Unable to send a nlmsg";

drivers/infiniband/core/netlink.c +43 ~~-20~~

142 lines not on this page · raw message

drivers/infiniband/core/nldev.c +10 ~~-10~~

index 783e465e7c41..e287b71a1cfd 100644
@@ -832,7 +832,7 @@ static int nldev_get_doit(struct sk_buff *skb, struct nlmsghdr *nlh,
 	nlmsg_end(msg, nlh);
 
 	ib_device_put(device);
-	return rdma_nl_unicast(msg, NETLINK_CB(skb).portid);
+	return rdma_nl_unicast(sock_net(skb->sk), msg, NETLINK_CB(skb).portid);
 
 err_free:
 	nlmsg_free(msg);

@@ -972,7 +972,7 @@ static int nldev_port_get_doit(struct sk_buff *skb, struct nlmsghdr *nlh,
 	nlmsg_end(msg, nlh);
 	ib_device_put(device);
 
-	return rdma_nl_unicast(msg, NETLINK_CB(skb).portid);
+	return rdma_nl_unicast(sock_net(skb->sk), msg, NETLINK_CB(skb).portid);
 
 err_free:
 	nlmsg_free(msg);

@@ -1074,7 +1074,7 @@ static int nldev_res_get_doit(struct sk_buff *skb, struct nlmsghdr *nlh,
 
 	nlmsg_end(msg, nlh);
 	ib_device_put(device);
-	return rdma_nl_unicast(msg, NETLINK_CB(skb).portid);
+	return rdma_nl_unicast(sock_net(skb->sk), msg, NETLINK_CB(skb).portid);
 
 err_free:
 	nlmsg_free(msg);

@@ -1251,7 +1251,7 @@ static int res_get_common_doit(struct sk_buff *skb, struct nlmsghdr *nlh,
 
 	nlmsg_end(msg, nlh);
 	ib_device_put(device);
-	return rdma_nl_unicast(msg, NETLINK_CB(skb).portid);
+	return rdma_nl_unicast(sock_net(skb->sk), msg, NETLINK_CB(skb).portid);
 
 err_free:
 	nlmsg_free(msg);

@@ -1596,7 +1596,7 @@ static int nldev_get_chardev(struct sk_buff *skb, struct nlmsghdr *nlh,
 	put_device(data.cdev);
 	if (ibdev)
 		ib_device_put(ibdev);
-	return rdma_nl_unicast(msg, NETLINK_CB(skb).portid);
+	return rdma_nl_unicast(sock_net(skb->sk), msg, NETLINK_CB(skb).portid);
 
 out_data:
 	put_device(data.cdev);

@@ -1636,7 +1636,7 @@ static int nldev_sys_get_doit(struct sk_buff *skb, struct nlmsghdr *nlh,
 		return err;
 	}
 	nlmsg_end(msg, nlh);
-	return rdma_nl_unicast(msg, NETLINK_CB(skb).portid);
+	return rdma_nl_unicast(sock_net(skb->sk), msg, NETLINK_CB(skb).portid);
 }
 
 static int nldev_set_sys_set_doit(struct sk_buff *skb, struct nlmsghdr *nlh,

@@ -1734,7 +1734,7 @@ static int nldev_stat_set_doit(struct sk_buff *skb, struct nlmsghdr *nlh,
 
 	nlmsg_end(msg, nlh);
 	ib_device_put(device);
-	return rdma_nl_unicast(msg, NETLINK_CB(skb).portid);
+	return rdma_nl_unicast(sock_net(skb->sk), msg, NETLINK_CB(skb).portid);
 
 err_fill:
 	rdma_counter_unbind_qpn(device, port, qpn, cntn);

@@ -1802,7 +1802,7 @@ static int nldev_stat_del_doit(struct sk_buff *skb, struct nlmsghdr *nlh,
 
 	nlmsg_end(msg, nlh);
 	ib_device_put(device);
-	return rdma_nl_unicast(msg, NETLINK_CB(skb).portid);
+	return rdma_nl_unicast(sock_net(skb->sk), msg, NETLINK_CB(skb).portid);
 
 err_fill:
 	rdma_counter_bind_qpn(device, port, qpn, cntn);

@@ -1893,7 +1893,7 @@ static int stat_get_doit_default_counter(struct sk_buff *skb,
 	mutex_unlock(&stats->lock);
 	nlmsg_end(msg, nlh);
 	ib_device_put(device);
-	return rdma_nl_unicast(msg, NETLINK_CB(skb).portid);
+	return rdma_nl_unicast(sock_net(skb->sk), msg, NETLINK_CB(skb).portid);
 
 err_table:
 	nla_nest_cancel(msg, table_attr);

@@ -1961,7 +1961,7 @@ static int stat_get_doit_qp(struct sk_buff *skb, struct nlmsghdr *nlh,
 
 	nlmsg_end(msg, nlh);
 	ib_device_put(device);
-	return rdma_nl_unicast(msg, NETLINK_CB(skb).portid);
+	return rdma_nl_unicast(sock_net(skb->sk), msg, NETLINK_CB(skb).portid);
 
 err_msg:
 	nlmsg_free(msg);

drivers/infiniband/core/sa_query.c +1 -1

index 7d8071c7e564..17fc2936c077 100644
@@ -860,7 +860,7 @@ static int ib_nl_send_msg(struct ib_sa_query *query, gfp_t gfp_mask)
 	/* Repair the nlmsg header length */
 	nlmsg_end(skb, nlh);
 
-	return rdma_nl_multicast(skb, RDMA_NL_GROUP_LS, gfp_mask);
+	return rdma_nl_multicast(&init_net, skb, RDMA_NL_GROUP_LS, gfp_mask);
 }
 
 static int ib_nl_make_request(struct ib_sa_query *query, gfp_t gfp_mask)

include/rdma/rdma_netlink.h +7 -3

index 6631624e4d7c..ab22759de7ea 100644
@@ -76,28 +76,32 @@ int ibnl_put_attr(struct sk_buff *skb, struct nlmsghdr *nlh,
 
 /**
  * Send the supplied skb to a specific userspace PID.
+ * @net: Net namespace in which to send the skb
  * @skb: The netlink skb
  * @pid: Userspace netlink process ID
  * Returns 0 on success or a negative error code.
  */
-int rdma_nl_unicast(struct sk_buff *skb, u32 pid);
+int rdma_nl_unicast(struct net *net, struct sk_buff *skb, u32 pid);
 
 /**
  * Send, with wait/1 retry, the supplied skb to a specific userspace PID.
+ * @net: Net namespace in which to send the skb
  * @skb: The netlink skb
  * @pid: Userspace netlink process ID
  * Returns 0 on success or a negative error code.
  */
-int rdma_nl_unicast_wait(struct sk_buff *skb, __u32 pid);
+int rdma_nl_unicast_wait(struct net *net, struct sk_buff *skb, __u32 pid);
 
 /**
  * Send the supplied skb to a netlink group.
+ * @net: Net namespace in which to send the skb
  * @skb: The netlink skb
  * @group: Netlink group ID
  * @flags: allocation flags
  * Returns 0 on success or a negative error code.
  */
-int rdma_nl_multicast(struct sk_buff *skb, unsigned int group, gfp_t flags);
+int rdma_nl_multicast(struct net *net, struct sk_buff *skb,
+		      unsigned int group, gfp_t flags);
 
 /**
  * Check if there are any listeners to the netlink group

--
2.20.1

Jason Gunthorpe

Applied

2019-07-25 17:21 UTC #1 lore raw

Quoted 17 lines · Leon Romanovsky

From: Parav Pandit <[email protected]>
Now that IB core supports RDMA device binding with specific net namespace, enable IB core to accept netlink commands in non init_net namespaces.
This is done by having per net namespace netlink socket.
At present only netlink device handling client RDMA_NL_NLDEV supports device handling in multiple net namespaces.
Hence do not accept netlink messages for other clients in non init_net net namespaces.
Signed-off-by Parav Pandit <[email protected]>
Signed-off-by Leon Romanovsky <[email protected]>
---
Rebased on top v5.3-rc1

Quoted 11 lines

---
 drivers/infiniband/core/addr.c      |  2 +-
 drivers/infiniband/core/core_priv.h | 24 ++++++++++-
 drivers/infiniband/core/device.c    | 38 ++++++-----------
 drivers/infiniband/core/iwpm_msg.c  |  8 ++--
 drivers/infiniband/core/iwpm_util.c |  6 +--
 drivers/infiniband/core/netlink.c   | 63 ++++++++++++++++++++---------
 drivers/infiniband/core/nldev.c     | 20 ++++-----
 drivers/infiniband/core/sa_query.c  |  2 +-
 include/rdma/rdma_netlink.h         | 10 +++--
 9 files changed, 105 insertions(+), 68 deletions(-)

Applied to for-next, thanks

But for future I would have prefered to see the 'add net * arguments' part as a 2nd patch

Jason