diff mbox

[net-next,v2,2/2] net: vrf: Add l3mdev rules on first device create

Message ID 1464916959-4029-3-git-send-email-dsa@cumulusnetworks.com
State Superseded, archived
Delegated to: David Miller
Headers show

Commit Message

David Ahern June 3, 2016, 1:22 a.m. UTC
Add l3mdev rule per address family when the first VRF device is
created. Remove them when the last is deleted.

Signed-off-by: David Ahern <dsa@cumulusnetworks.com>
---
v2
- added EXCL flag and EEXISTS check. Appropriate once the exclude fib rule
  patch is accepted
- changed 3rd arg to vrf_fib_rule from 0/1 to false/true per Dave's comment

 drivers/net/vrf.c | 119 +++++++++++++++++++++++++++++++++++++++++++++++++++++-
 1 file changed, 118 insertions(+), 1 deletion(-)

Comments

Nikolay Aleksandrov June 3, 2016, 11:05 a.m. UTC | #1
> On Jun 3, 2016, at 4:22 AM, David Ahern <dsa@cumulusnetworks.com> wrote:
> 
> Add l3mdev rule per address family when the first VRF device is
> created. Remove them when the last is deleted.
> 
> Signed-off-by: David Ahern <dsa@cumulusnetworks.com>
> ---
> v2
> - added EXCL flag and EEXISTS check. Appropriate once the exclude fib rule
>  patch is accepted
> - changed 3rd arg to vrf_fib_rule from 0/1 to false/true per Dave's comment
> 
> drivers/net/vrf.c | 119 +++++++++++++++++++++++++++++++++++++++++++++++++++++-
> 1 file changed, 118 insertions(+), 1 deletion(-)
> 
> diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c
> index d356f5d0f7b0..1d13c95cab97 100644
> --- a/drivers/net/vrf.c
> +++ b/drivers/net/vrf.c
> @@ -35,6 +35,7 @@
> #include <net/route.h>
> #include <net/addrconf.h>
> #include <net/l3mdev.h>
> +#include <net/fib_rules.h>
> 
> #define RT_FL_TOS(oldflp4) \
> 	((oldflp4)->flowi4_tos & (IPTOS_RT_MASK | RTO_ONLINK))
> @@ -42,6 +43,11 @@
> #define DRV_NAME	"vrf"
> #define DRV_VERSION	"1.0"
> 
> +static atomic_t num_vrfs;

num_vrfs seems to be used only with rtnl held, so it seems you can avoid the atomic ops altogether.

> +
> +static u32 rule_pref = 1000;
> +module_param(rule_pref, uint,  S_IRUGO);
> +
> struct net_vrf {
> 	struct rtable __rcu	*rth;
> 	struct rt6_info	__rcu	*rt6;
> @@ -729,6 +735,98 @@ static const struct ethtool_ops vrf_ethtool_ops = {
> 	.get_drvinfo	= vrf_get_drvinfo,
> };
[snip]
> static void vrf_setup(struct net_device *dev)
> {
> 	ether_setup(dev);
> @@ -763,12 +861,17 @@ static int vrf_validate(struct nlattr *tb[], struct nlattr *data[])
> static void vrf_dellink(struct net_device *dev, struct list_head *head)
> {
> 	unregister_netdevice_queue(dev, head);
> +
> +	atomic_dec(&num_vrfs);
> +	if (!atomic_read(&num_vrfs))

If you’re sticking with atomics, this looks like atomic_dec_and_test().

> +		vrf_del_fib_rules(dev);
> }
> 
> static int vrf_newlink(struct net *src_net, struct net_device *dev,
> 		       struct nlattr *tb[], struct nlattr *data[])
> {
> 	struct net_vrf *vrf = netdev_priv(dev);
> +	int err;
> 
> 	if (!data || !data[IFLA_VRF_TABLE])
> 		return -EINVAL;

Cheers,
 Nik
diff mbox

Patch

diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c
index d356f5d0f7b0..1d13c95cab97 100644
--- a/drivers/net/vrf.c
+++ b/drivers/net/vrf.c
@@ -35,6 +35,7 @@ 
 #include <net/route.h>
 #include <net/addrconf.h>
 #include <net/l3mdev.h>
+#include <net/fib_rules.h>
 
 #define RT_FL_TOS(oldflp4) \
 	((oldflp4)->flowi4_tos & (IPTOS_RT_MASK | RTO_ONLINK))
@@ -42,6 +43,11 @@ 
 #define DRV_NAME	"vrf"
 #define DRV_VERSION	"1.0"
 
+static atomic_t num_vrfs;
+
+static u32 rule_pref = 1000;
+module_param(rule_pref, uint,  S_IRUGO);
+
 struct net_vrf {
 	struct rtable __rcu	*rth;
 	struct rt6_info	__rcu	*rt6;
@@ -729,6 +735,98 @@  static const struct ethtool_ops vrf_ethtool_ops = {
 	.get_drvinfo	= vrf_get_drvinfo,
 };
 
+static inline size_t vrf_fib_rule_nl_size(void)
+{
+	size_t sz;
+
+	sz  = NLMSG_ALIGN(sizeof(struct fib_rule_hdr));
+	sz += nla_total_size(sizeof(u8));	/* FRA_L3MDEV */
+	sz += nla_total_size(sizeof(u32));	/* FRA_PRIORITY */
+
+	return sz;
+}
+
+static int vrf_fib_rule(const struct net_device *dev, __u8 family, bool add_it)
+{
+	struct fib_rule_hdr *frh;
+	struct nlmsghdr *nlh;
+	struct sk_buff *skb;
+	int err;
+
+	skb = nlmsg_new(vrf_fib_rule_nl_size(), GFP_KERNEL);
+	if (!skb)
+		return -ENOMEM;
+
+	nlh = nlmsg_put(skb, 0, 0, 0, sizeof(*frh), 0);
+	if (!nlh)
+		goto nla_put_failure;
+
+	/* rule only needs to appear once */
+	nlh->nlmsg_flags &= NLM_F_EXCL;
+
+	frh = nlmsg_data(nlh);
+	memset(frh, 0, sizeof(*frh));
+	frh->family = family;
+	frh->action = FR_ACT_TO_TBL;
+
+	if (nla_put_u32(skb, FRA_L3MDEV, 1))
+		goto nla_put_failure;
+
+	if (nla_put_u32(skb, FRA_PRIORITY, rule_pref))
+		goto nla_put_failure;
+
+	nlmsg_end(skb, nlh);
+
+	/* fib_nl_{new,del}rule handling looks for net from skb->sk */
+	skb->sk = dev_net(dev)->rtnl;
+	if (add_it) {
+		err = fib_nl_newrule(skb, nlh);
+		if (err == -EEXIST)
+			err = 0;
+	} else {
+		err = fib_nl_delrule(skb, nlh);
+		if (err == -ENOENT)
+			err = 0;
+	}
+	nlmsg_free(skb);
+
+	return err;
+
+nla_put_failure:
+	nlmsg_free(skb);
+
+	return -EMSGSIZE;
+}
+
+static void vrf_del_fib_rules(const struct net_device *dev)
+{
+	if (vrf_fib_rule(dev, AF_INET,  false) ||
+	    vrf_fib_rule(dev, AF_INET6, false)) {
+		netdev_err(dev, "Failed to delete FIB rules.\n");
+	}
+}
+
+static int vrf_add_fib_rules(const struct net_device *dev)
+{
+	int err;
+
+	err = vrf_fib_rule(dev, AF_INET,  true);
+	if (err < 0)
+		goto out_err;
+
+	err = vrf_fib_rule(dev, AF_INET6, true);
+	if (err < 0)
+		goto out_err;
+
+	return 0;
+
+out_err:
+	netdev_err(dev, "Failed to add FIB rules.\n");
+	vrf_del_fib_rules(dev);
+
+	return err;
+}
+
 static void vrf_setup(struct net_device *dev)
 {
 	ether_setup(dev);
@@ -763,12 +861,17 @@  static int vrf_validate(struct nlattr *tb[], struct nlattr *data[])
 static void vrf_dellink(struct net_device *dev, struct list_head *head)
 {
 	unregister_netdevice_queue(dev, head);
+
+	atomic_dec(&num_vrfs);
+	if (!atomic_read(&num_vrfs))
+		vrf_del_fib_rules(dev);
 }
 
 static int vrf_newlink(struct net *src_net, struct net_device *dev,
 		       struct nlattr *tb[], struct nlattr *data[])
 {
 	struct net_vrf *vrf = netdev_priv(dev);
+	int err;
 
 	if (!data || !data[IFLA_VRF_TABLE])
 		return -EINVAL;
@@ -777,7 +880,21 @@  static int vrf_newlink(struct net *src_net, struct net_device *dev,
 
 	dev->priv_flags |= IFF_L3MDEV_MASTER;
 
-	return register_netdevice(dev);
+	err = register_netdevice(dev);
+	if (err)
+		goto out;
+
+	if (!atomic_read(&num_vrfs)) {
+		err = vrf_add_fib_rules(dev);
+		if (err) {
+			unregister_netdevice(dev);
+			goto out;
+		}
+	}
+
+	atomic_inc(&num_vrfs);
+out:
+	return err;
 }
 
 static size_t vrf_nl_getsize(const struct net_device *dev)