[RTNETLINK 03/18]: Link creation API

[Patrick McHardy <kaber@trash.net>]

[RTNETLINK]: Link creation API

Add rtnetlink API for creating, changing and deleting software devices.

Signed-off-by: Patrick McHardy <kaber@trash.net>

---
commit 8a4171f86c516a43a7ed07f198c6cad2273ce2a7
tree 6bab9e96dd04c4ea13654fcda6a402a20a4f43c1
parent 806243b51e1f1607cec07f320dc9a8c3a70a8480
author Patrick McHardy <kaber@trash.net> Wed, 06 Jun 2007 14:45:57 +0200
committer Patrick McHardy <kaber@trash.net> Wed, 13 Jun 2007 18:10:29 +0200

 include/linux/if_link.h   |   13 ++
 include/linux/netdevice.h |    3 
 include/net/rtnetlink.h   |   58 ++++++++
 net/core/rtnetlink.c      |  342 ++++++++++++++++++++++++++++++++++++++++++++-
 4 files changed, 409 insertions(+), 7 deletions(-)

diff --git a/include/linux/if_link.h b/include/linux/if_link.h
index 604c243..3144bab 100644
--- a/include/linux/if_link.h
+++ b/include/linux/if_link.h
@@ -76,6 +76,8 @@ enum
 #define IFLA_WEIGHT IFLA_WEIGHT
 	IFLA_OPERSTATE,
 	IFLA_LINKMODE,
+	IFLA_LINKINFO,
+#define IFLA_LINKINFO IFLA_LINKINFO
 	__IFLA_MAX
 };
 
@@ -140,4 +142,15 @@ struct ifla_cacheinfo
 	__u32	retrans_time;
 };
 
+enum
+{
+	IFLA_INFO_UNSPEC,
+	IFLA_INFO_KIND,
+	IFLA_INFO_DATA,
+	IFLA_INFO_XSTATS,
+	__IFLA_INFO_MAX,
+};
+
+#define IFLA_INFO_MAX	(__IFLA_INFO_MAX - 1)
+
 #endif /* _LINUX_IF_LINK_H */
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 94cc77c..e7913ee 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -540,6 +540,9 @@ struct net_device
 	struct device		dev;
 	/* space for optional statistics and wireless sysfs groups */
 	struct attribute_group  *sysfs_groups[3];
+
+	/* rtnetlink link ops */
+	const struct rtnl_link_ops *rtnl_link_ops;
 };
 #define to_net_dev(d) container_of(d, struct net_device, dev)
 
diff --git a/include/net/rtnetlink.h b/include/net/rtnetlink.h
index 3b3d474..3861c05 100644
--- a/include/net/rtnetlink.h
+++ b/include/net/rtnetlink.h
@@ -22,4 +22,62 @@ static inline int rtnl_msg_family(struct nlmsghdr *nlh)
 		return AF_UNSPEC;
 }
 
+/**
+ *	struct rtnl_link_ops - rtnetlink link operations
+ *
+ *	@list: Used internally
+ *	@kind: Identifier
+ *	@maxtype: Highest device specific netlink attribute number
+ *	@policy: Netlink policy for device specific attribute validation
+ *	@validate: Optional validation function for netlink/changelink parameters
+ *	@priv_size: sizeof net_device private space
+ *	@setup: net_device setup function
+ *	@newlink: Function for configuring and registering a new device
+ *	@changelink: Function for changing parameters of an existing device
+ *	@dellink: Function to remove a device
+ *	@get_size: Function to calculate required room for dumping device
+ *		   specific netlink attributes
+ *	@fill_info: Function to dump device specific netlink attributes
+ *	@get_xstats_size: Function to calculate required room for dumping devic
+ *			  specific statistics
+ *	@fill_xstats: Function to dump device specific statistics
+ */
+struct rtnl_link_ops {
+	struct list_head	list;
+
+	const char		*kind;
+
+	size_t			priv_size;
+	void			(*setup)(struct net_device *dev);
+
+	int			maxtype;
+	const struct nla_policy	*policy;
+	int			(*validate)(struct nlattr *tb[],
+					    struct nlattr *data[]);
+
+	int			(*newlink)(struct net_device *dev,
+					   struct nlattr *tb[],
+					   struct nlattr *data[]);
+	int			(*changelink)(struct net_device *dev,
+					      struct nlattr *tb[],
+					      struct nlattr *data[]);
+	void			(*dellink)(struct net_device *dev);
+
+	size_t			(*get_size)(const struct net_device *dev);
+	int			(*fill_info)(struct sk_buff *skb,
+					     const struct net_device *dev);
+
+	size_t			(*get_xstats_size)(const struct net_device *dev);
+	int			(*fill_xstats)(struct sk_buff *skb,
+					       const struct net_device *dev);
+};
+
+extern int	__rtnl_link_register(struct rtnl_link_ops *ops);
+extern void	__rtnl_link_unregister(struct rtnl_link_ops *ops);
+
+extern int	rtnl_link_register(struct rtnl_link_ops *ops);
+extern void	rtnl_link_unregister(struct rtnl_link_ops *ops);
+
+#define MODULE_ALIAS_RTNL_LINK(kind) MODULE_ALIAS("rtnl-link-" kind)
+
 #endif
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 25ca219..06c0c5a 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -243,6 +243,143 @@ void rtnl_unregister_all(int protocol)
 
 EXPORT_SYMBOL_GPL(rtnl_unregister_all);
 
+static LIST_HEAD(link_ops);
+
+/**
+ * __rtnl_link_register - Register rtnl_link_ops with rtnetlink.
+ * @ops: struct rtnl_link_ops * to register
+ *
+ * The caller must hold the rtnl_mutex. This function should be used
+ * by drivers that create devices during module initialization. It
+ * must be called before registering the devices.
+ *
+ * Returns 0 on success or a negative error code.
+ */
+int __rtnl_link_register(struct rtnl_link_ops *ops)
+{
+	list_add_tail(&ops->list, &link_ops);
+	return 0;
+}
+
+EXPORT_SYMBOL_GPL(__rtnl_link_register);
+
+/**
+ * rtnl_link_register - Register rtnl_link_ops with rtnetlink.
+ * @ops: struct rtnl_link_ops * to register
+ *
+ * Returns 0 on success or a negative error code.
+ */
+int rtnl_link_register(struct rtnl_link_ops *ops)
+{
+	int err;
+
+	rtnl_lock();
+	err = __rtnl_link_register(ops);
+	rtnl_unlock();
+	return err;
+}
+
+EXPORT_SYMBOL_GPL(rtnl_link_register);
+
+/**
+ * __rtnl_link_unregister - Unregister rtnl_link_ops from rtnetlink.
+ * @ops: struct rtnl_link_ops * to unregister
+ *
+ * The caller must hold the rtnl_mutex. This function should be used
+ * by drivers that unregister devices during module unloading. It must
+ * be called after unregistering the devices.
+ */
+void __rtnl_link_unregister(struct rtnl_link_ops *ops)
+{
+	list_del(&ops->list);
+}
+
+EXPORT_SYMBOL_GPL(__rtnl_link_unregister);
+
+/**
+ * rtnl_link_unregister - Unregister rtnl_link_ops from rtnetlink.
+ * @ops: struct rtnl_link_ops * to unregister
+ */
+void rtnl_link_unregister(struct rtnl_link_ops *ops)
+{
+	rtnl_lock();
+	__rtnl_link_unregister(ops);
+	rtnl_unlock();
+}
+
+EXPORT_SYMBOL_GPL(rtnl_link_unregister);
+
+static const struct rtnl_link_ops *rtnl_link_ops_get(const char *kind)
+{
+	const struct rtnl_link_ops *ops;
+
+	list_for_each_entry(ops, &link_ops, list) {
+		if (!strcmp(ops->kind, kind))
+			return ops;
+	}
+	return NULL;
+}
+
+static size_t rtnl_link_get_size(const struct net_device *dev)
+{
+	const struct rtnl_link_ops *ops = dev->rtnl_link_ops;
+	size_t size;
+
+	if (!ops)
+		return 0;
+
+	size = nlmsg_total_size(sizeof(struct nlattr)) + /* IFLA_LINKINFO */
+	       nlmsg_total_size(strlen(ops->kind) + 1);	 /* IFLA_INFO_KIND */
+
+	if (ops->get_size)
+		/* IFLA_INFO_DATA + nested data */
+		size += nlmsg_total_size(sizeof(struct nlattr)) +
+			ops->get_size(dev);
+
+	if (ops->get_xstats_size)
+		size += ops->get_xstats_size(dev);	/* IFLA_INFO_XSTATS */
+
+	return size;
+}
+
+static int rtnl_link_fill(struct sk_buff *skb, const struct net_device *dev)
+{
+	const struct rtnl_link_ops *ops = dev->rtnl_link_ops;
+	struct nlattr *linkinfo, *data;
+	int err = -EMSGSIZE;
+
+	linkinfo = nla_nest_start(skb, IFLA_LINKINFO);
+	if (linkinfo == NULL)
+		goto out;
+
+	if (nla_put_string(skb, IFLA_INFO_KIND, ops->kind) < 0)
+		goto err_cancel_link;
+	if (ops->fill_xstats) {
+		err = ops->fill_xstats(skb, dev);
+		if (err < 0)
+			goto err_cancel_link;
+	}
+	if (ops->fill_info) {
+		data = nla_nest_start(skb, IFLA_INFO_DATA);
+		if (data == NULL)
+			goto err_cancel_link;
+		err = ops->fill_info(skb, dev);
+		if (err < 0)
+			goto err_cancel_data;
+		nla_nest_end(skb, data);
+	}
+
+	nla_nest_end(skb, linkinfo);
+	return 0;
+
+err_cancel_data:
+	nla_nest_cancel(skb, data);
+err_cancel_link:
+	nla_nest_cancel(skb, linkinfo);
+out:
+	return err;
+}
+
 static const int rtm_min[RTM_NR_FAMILIES] =
 {
 	[RTM_FAM(RTM_NEWLINK)]      = NLMSG_LENGTH(sizeof(struct ifinfomsg)),
@@ -437,7 +574,7 @@ static void copy_rtnl_link_stats(struct rtnl_link_stats *a,
 	a->tx_compressed = b->tx_compressed;
 };
 
-static inline size_t if_nlmsg_size(void)
+static inline size_t if_nlmsg_size(const struct net_device *dev)
 {
 	return NLMSG_ALIGN(sizeof(struct ifinfomsg))
 	       + nla_total_size(IFNAMSIZ) /* IFLA_IFNAME */
@@ -452,7 +589,8 @@ static inline size_t if_nlmsg_size(void)
 	       + nla_total_size(4) /* IFLA_LINK */
 	       + nla_total_size(4) /* IFLA_MASTER */
 	       + nla_total_size(1) /* IFLA_OPERSTATE */
-	       + nla_total_size(1); /* IFLA_LINKMODE */
+	       + nla_total_size(1) /* IFLA_LINKMODE */
+	       + rtnl_link_get_size(dev); /* IFLA_LINKINFO */
 }
 
 static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev,
@@ -522,6 +660,11 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev,
 		}
 	}
 
+	if (dev->rtnl_link_ops) {
+		if (rtnl_link_fill(skb, dev) < 0)
+			goto nla_put_failure;
+	}
+
 	return nlmsg_end(skb, nlh);
 
 nla_put_failure:
@@ -553,6 +696,8 @@ cont:
 
 static const struct nla_policy ifla_policy[IFLA_MAX+1] = {
 	[IFLA_IFNAME]		= { .type = NLA_STRING, .len = IFNAMSIZ-1 },
+	[IFLA_ADDRESS]		= { .type = NLA_BINARY, .len = MAX_ADDR_LEN },
+	[IFLA_BROADCAST]	= { .type = NLA_BINARY, .len = MAX_ADDR_LEN },
 	[IFLA_MAP]		= { .len = sizeof(struct rtnl_link_ifmap) },
 	[IFLA_MTU]		= { .type = NLA_U32 },
 	[IFLA_TXQLEN]		= { .type = NLA_U32 },
@@ -561,10 +706,15 @@ static const struct nla_policy ifla_policy[IFLA_MAX+1] = {
 	[IFLA_LINKMODE]		= { .type = NLA_U8 },
 };
 
+static const struct nla_policy ifla_info_policy[IFLA_INFO_MAX+1] = {
+	[IFLA_INFO_KIND]	= { .type = NLA_STRING },
+	[IFLA_INFO_DATA]	= { .type = NLA_NESTED },
+};
+
 static int do_setlink(struct net_device *dev, struct ifinfomsg *ifm,
-		      struct nlattr **tb, char *ifname)
+		      struct nlattr **tb, char *ifname, int modified)
 {
-	int modified = 0, send_addr_notify = 0;
+	int send_addr_notify = 0;
 	int err;
 
 	if (tb[IFLA_MAP]) {
@@ -729,13 +879,189 @@ static int rtnl_setlink(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg)
 	    nla_len(tb[IFLA_BROADCAST]) < dev->addr_len)
 		goto errout_dev;
 
-	err = do_setlink(dev, ifm, tb, ifname);
+	err = do_setlink(dev, ifm, tb, ifname, 0);
 errout_dev:
 	dev_put(dev);
 errout:
 	return err;
 }
 
+static int rtnl_dellink(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg)
+{
+	const struct rtnl_link_ops *ops;
+	struct net_device *dev;
+	struct ifinfomsg *ifm;
+	char ifname[IFNAMSIZ];
+	struct nlattr *tb[IFLA_MAX+1];
+	int err;
+
+	err = nlmsg_parse(nlh, sizeof(*ifm), tb, IFLA_MAX, ifla_policy);
+	if (err < 0)
+		return err;
+
+	if (tb[IFLA_IFNAME])
+		nla_strlcpy(ifname, tb[IFLA_IFNAME], IFNAMSIZ);
+
+	ifm = nlmsg_data(nlh);
+	if (ifm->ifi_index > 0)
+		dev = __dev_get_by_index(ifm->ifi_index);
+	else if (tb[IFLA_IFNAME])
+		dev = __dev_get_by_name(ifname);
+	else
+		return -EINVAL;
+
+	if (!dev)
+		return -ENODEV;
+
+	ops = dev->rtnl_link_ops;
+	if (!ops)
+		return -EOPNOTSUPP;
+
+	ops->dellink(dev);
+	return 0;
+}
+
+static int rtnl_newlink(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg)
+{
+	const struct rtnl_link_ops *ops;
+	struct net_device *dev;
+	struct ifinfomsg *ifm;
+	char kind[MODULE_NAME_LEN];
+	char ifname[IFNAMSIZ];
+	struct nlattr *tb[IFLA_MAX+1];
+	struct nlattr *linkinfo[IFLA_INFO_MAX+1];
+	int err;
+
+replay:
+	err = nlmsg_parse(nlh, sizeof(*ifm), tb, IFLA_MAX, ifla_policy);
+	if (err < 0)
+		return err;
+
+	if (tb[IFLA_IFNAME])
+		nla_strlcpy(ifname, tb[IFLA_IFNAME], IFNAMSIZ);
+	else
+		ifname[0] = '\0';
+
+	ifm = nlmsg_data(nlh);
+	if (ifm->ifi_index > 0)
+		dev = __dev_get_by_index(ifm->ifi_index);
+	else if (ifname[0])
+		dev = __dev_get_by_name(ifname);
+	else
+		dev = NULL;
+
+	if (tb[IFLA_LINKINFO]) {
+		err = nla_parse_nested(linkinfo, IFLA_INFO_MAX,
+				       tb[IFLA_LINKINFO], ifla_info_policy);
+		if (err < 0)
+			return err;
+	} else
+		memset(linkinfo, 0, sizeof(linkinfo));
+
+	if (linkinfo[IFLA_INFO_KIND]) {
+		nla_strlcpy(kind, linkinfo[IFLA_INFO_KIND], sizeof(kind));
+		ops = rtnl_link_ops_get(kind);
+	} else {
+		kind[0] = '\0';
+		ops = NULL;
+	}
+
+	if (1) {
+		struct nlattr *attr[ops ? ops->maxtype + 1 : 0], **data = NULL;
+
+		if (ops) {
+			if (ops->maxtype && linkinfo[IFLA_INFO_DATA]) {
+				err = nla_parse_nested(attr, ops->maxtype,
+						       linkinfo[IFLA_INFO_DATA],
+						       ops->policy);
+				if (err < 0)
+					return err;
+				data = attr;
+			}
+			if (ops->validate) {
+				err = ops->validate(tb, data);
+				if (err < 0)
+					return err;
+			}
+		}
+
+		if (dev) {
+			int modified = 0;
+
+			if (nlh->nlmsg_flags & NLM_F_EXCL)
+				return -EEXIST;
+			if (nlh->nlmsg_flags & NLM_F_REPLACE)
+				return -EOPNOTSUPP;
+
+			if (linkinfo[IFLA_INFO_DATA]) {
+				if (!ops || ops != dev->rtnl_link_ops ||
+				    !ops->changelink)
+					return -EOPNOTSUPP;
+
+				err = ops->changelink(dev, tb, data);
+				if (err < 0)
+					return err;
+				modified = 1;
+			}
+
+			return do_setlink(dev, ifm, tb, ifname, modified);
+		}
+
+		if (!(nlh->nlmsg_flags & NLM_F_CREATE))
+			return -ENODEV;
+
+		if (ifm->ifi_index || ifm->ifi_flags || ifm->ifi_change)
+			return -EOPNOTSUPP;
+		if (tb[IFLA_ADDRESS] || tb[IFLA_BROADCAST] || tb[IFLA_MAP] ||
+		    tb[IFLA_MASTER] || tb[IFLA_PROTINFO])
+			return -EOPNOTSUPP;
+
+		if (!ops) {
+#ifdef CONFIG_KMOD
+			if (kind[0]) {
+				__rtnl_unlock();
+				request_module("rtnl-link-%s", kind);
+				rtnl_lock();
+				ops = rtnl_link_ops_get(kind);
+				if (ops)
+					goto replay;
+			}
+#endif
+			return -EOPNOTSUPP;
+		}
+
+		if (!ifname[0])
+			snprintf(ifname, IFNAMSIZ, "%s%%d", ops->kind);
+		dev = alloc_netdev(ops->priv_size, ifname, ops->setup);
+		if (!dev)
+			return -ENOMEM;
+
+		if (strchr(dev->name, '%')) {
+			err = dev_alloc_name(dev, dev->name);
+			if (err < 0)
+				goto err_free;
+		}
+		dev->rtnl_link_ops = ops;
+
+		if (tb[IFLA_MTU])
+			dev->mtu = nla_get_u32(tb[IFLA_MTU]);
+		if (tb[IFLA_TXQLEN])
+			dev->tx_queue_len = nla_get_u32(tb[IFLA_TXQLEN]);
+		if (tb[IFLA_WEIGHT])
+			dev->weight = nla_get_u32(tb[IFLA_WEIGHT]);
+		if (tb[IFLA_OPERSTATE])
+			set_operstate(dev, nla_get_u8(tb[IFLA_OPERSTATE]));
+		if (tb[IFLA_LINKMODE])
+			dev->link_mode = nla_get_u8(tb[IFLA_LINKMODE]);
+
+		err = ops->newlink(dev, tb, data);
+err_free:
+		if (err < 0)
+			free_netdev(dev);
+		return err;
+	}
+}
+
 static int rtnl_getlink(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg)
 {
 	struct ifinfomsg *ifm;
@@ -756,7 +1082,7 @@ static int rtnl_getlink(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg)
 	} else
 		return -EINVAL;
 
-	nskb = nlmsg_new(if_nlmsg_size(), GFP_KERNEL);
+	nskb = nlmsg_new(if_nlmsg_size(dev), GFP_KERNEL);
 	if (nskb == NULL) {
 		err = -ENOBUFS;
 		goto errout;
@@ -806,7 +1132,7 @@ void rtmsg_ifinfo(int type, struct net_device *dev, unsigned change)
 	struct sk_buff *skb;
 	int err = -ENOBUFS;
 
-	skb = nlmsg_new(if_nlmsg_size(), GFP_KERNEL);
+	skb = nlmsg_new(if_nlmsg_size(dev), GFP_KERNEL);
 	if (skb == NULL)
 		goto errout;
 
@@ -961,6 +1287,8 @@ void __init rtnetlink_init(void)
 
 	rtnl_register(PF_UNSPEC, RTM_GETLINK, rtnl_getlink, rtnl_dump_ifinfo);
 	rtnl_register(PF_UNSPEC, RTM_SETLINK, rtnl_setlink, NULL);
+	rtnl_register(PF_UNSPEC, RTM_NEWLINK, rtnl_newlink, NULL);
+	rtnl_register(PF_UNSPEC, RTM_DELLINK, rtnl_dellink, NULL);
 
 	rtnl_register(PF_UNSPEC, RTM_GETADDR, NULL, rtnl_dump_all);
 	rtnl_register(PF_UNSPEC, RTM_GETROUTE, NULL, rtnl_dump_all);