From: Roopa Prabhu <ro...@cumulusnetworks.com>
Adds support for both RTNH_F_DEAD and RTNH_F_LINKDOWN flags.
This resembles ipv4 fib code. I also picked fib_rebalance from
ipv4. Enabled weights support for nexthop, just because the
infrastructure is already there.
Signed-off-by: Roopa Prabhu <ro...@cumulusnetworks.com>
---
I want to get this in before net-next closes as promised.
I have tested it for the dead/linkdown flags. The multipath selection
and hash calculation in the face of dead routes needs some more
work. I am short on cycles this week and thought of getting some
early feedback. Hence sending this out as RFC. I will continue with some
more testing. Robert, I am using your hash algo but it needs some more
work with dead routes. If you already have any thoughts on this, i will
take them. thanks!.
net/mpls/af_mpls.c | 228 +++++++++++++++++++++++++++++++++++++++++++++-------
net/mpls/internal.h | 4 +
2 files changed, 202 insertions(+), 30 deletions(-)
diff --git a/net/mpls/af_mpls.c b/net/mpls/af_mpls.c
index c70d750..7db9678 100644
--- a/net/mpls/af_mpls.c
+++ b/net/mpls/af_mpls.c
@@ -27,6 +27,8 @@
*/
#define MAX_MP_SELECT_LABELS 4
+u32 mpls_multipath_secret __read_mostly;
+
static int zero = 0;
static int label_limit = (1 << 20) - 1;
@@ -96,22 +98,52 @@ bool mpls_pkt_too_big(const struct sk_buff *skb, unsigned
int mtu)
}
EXPORT_SYMBOL_GPL(mpls_pkt_too_big);
-static struct mpls_nh *mpls_select_multipath(struct mpls_route *rt,
- struct sk_buff *skb, bool bos)
+static void mpls_multipath_rebalance(struct mpls_route *rt)
+{
+ int total;
+ int w;
+
+ if (rt->rt_nhn < 2)
+ return;
+
+ total = 0;
+ for_nexthops(rt) {
+ if ((nh->nh_flags & RTNH_F_DEAD) ||
+ (nh->nh_flags & RTNH_F_LINKDOWN))
+ continue;
+
+ total += nh->nh_weight;
+ } endfor_nexthops(rt);
+
+ w = 0;
+ change_nexthops(rt) {
+ int upper_bound;
+
+ if ((nh->nh_flags & RTNH_F_DEAD) ||
+ (nh->nh_flags & RTNH_F_LINKDOWN)) {
+ upper_bound = -1;
+ } else {
+ w += nh->nh_weight;
+ upper_bound = DIV_ROUND_CLOSEST_ULL((u64)w << 31,
+ total) - 1;
+ }
+
+ atomic_set(&nh->nh_upper_bound, upper_bound);
+ } endfor_nexthops(rt);
+
+ net_get_random_once(&mpls_multipath_secret,
+ sizeof(mpls_multipath_secret));
+}
+
+static u32 mpls_multipath_hash(struct mpls_route *rt,
+ struct sk_buff *skb, bool bos)
{
struct mpls_entry_decoded dec;
struct mpls_shim_hdr *hdr;
bool eli_seen = false;
int label_index;
- int nh_index = 0;
u32 hash = 0;
- /* No need to look further into packet if there's only
- * one path
- */
- if (rt->rt_nhn == 1)
- goto out;
-
for (label_index = 0; label_index < MAX_MP_SELECT_LABELS && !bos;
label_index++) {
if (!pskb_may_pull(skb, sizeof(*hdr) * label_index))
@@ -165,9 +197,29 @@ static struct mpls_nh *mpls_select_multipath(struct
mpls_route *rt,
}
}
- nh_index = hash % rt->rt_nhn;
+ return hash;
+}
+
+static struct mpls_nh *mpls_select_multipath(struct mpls_route *rt,
+ struct sk_buff *skb, bool bos)
+{
+ u32 hash = 0;
+
+ /* No need to look further into packet if there's only
+ * one path
+ */
+ if (rt->rt_nhn == 1)
+ goto out;
+
+ hash = mpls_multipath_hash(rt, skb, bos);
+ for_nexthops(rt) {
+ if (hash > atomic_read(&nh->nh_upper_bound))
+ continue;
+ return nh;
+ } endfor_nexthops(rt);
+
out:
- return &rt->rt_nh[nh_index];
+ return &rt->rt_nh[0];
}
static bool mpls_egress(struct mpls_route *rt, struct sk_buff *skb,
@@ -577,7 +629,7 @@ errout:
}
static int mpls_nh_build(struct net *net, struct mpls_route *rt,
- struct mpls_nh *nh, int oif,
+ struct mpls_nh *nh, int oif, int hops,
struct nlattr *via, struct nlattr *newdst)
{
int err = -ENOMEM;
@@ -597,6 +649,7 @@ static int mpls_nh_build(struct net *net, struct mpls_route
*rt,
if (err)
goto errout;
+ nh->nh_weight = hops + 1;
err = mpls_nh_assign_dev(net, rt, nh, oif);
if (err)
goto errout;
@@ -663,10 +716,9 @@ static int mpls_nh_build_multi(struct mpls_route_config
*cfg,
if (!rtnh_ok(rtnh, remaining))
goto errout;
- /* neither weighted multipath nor any flags
- * are supported
+ /* flags are not supported
*/
- if (rtnh->rtnh_hops || rtnh->rtnh_flags)
+ if (rtnh->rtnh_flags)
goto errout;
attrlen = rtnh_attrlen(rtnh);
@@ -681,8 +733,8 @@ static int mpls_nh_build_multi(struct mpls_route_config
*cfg,
goto errout;
err = mpls_nh_build(cfg->rc_nlinfo.nl_net, rt, nh,
- rtnh->rtnh_ifindex, nla_via,
- nla_newdst);
+ rtnh->rtnh_ifindex, rtnh->rtnh_hops,
+ nla_via, nla_newdst);
if (err)
goto errout;
@@ -875,34 +927,111 @@ free:
return ERR_PTR(err);
}
-static void mpls_ifdown(struct net_device *dev)
+static void mpls_ifdown(struct net_device *dev, int event)
{
struct mpls_route __rcu **platform_label;
struct net *net = dev_net(dev);
- struct mpls_dev *mdev;
unsigned index;
+ int dead;
platform_label = rtnl_dereference(net->mpls.platform_label);
for (index = 0; index < net->mpls.platform_labels; index++) {
struct mpls_route *rt = rtnl_dereference(platform_label[index]);
+ int changed = 0;
+
if (!rt)
continue;
+ dead = 0;
for_nexthops(rt) {
+ if ((event == NETDEV_DOWN &&
+ (nh->nh_flags & RTNH_F_DEAD)) ||
+ (event == NETDEV_CHANGE &&
+ (nh->nh_flags & RTNH_F_LINKDOWN))) {
+ dead++;
+ continue;
+ }
+
if (rtnl_dereference(nh->nh_dev) != dev)
continue;
- nh->nh_dev = NULL;
+ switch (event) {
+ case NETDEV_DOWN:
+ case NETDEV_UNREGISTER:
+ nh->nh_flags |= RTNH_F_DEAD;
+ /* fall through */
+ case NETDEV_CHANGE:
+ nh->nh_flags |= RTNH_F_LINKDOWN;
+ changed = 1;
+ break;
+ }
+ if (event == NETDEV_UNREGISTER) {
+ nh->nh_dev = NULL;
+ dead = rt->rt_nhn;
+ changed = 1;
+ break;
+ }
+ dead++;
} endfor_nexthops(rt);
+
+ if (dead == rt->rt_nhn) {
+ switch (event) {
+ case NETDEV_DOWN:
+ case NETDEV_UNREGISTER:
+ rt->rt_flags |= RTNH_F_DEAD;
+ /* fall through */
+ case NETDEV_CHANGE:
+ rt->rt_flags |= RTNH_F_LINKDOWN;
+ changed = 1;
+ break;
+ }
+ }
+
+ if (changed)
+ mpls_multipath_rebalance(rt);
}
- mdev = mpls_dev_get(dev);
- if (!mdev)
- return;
+ return;
+}
+
+static void mpls_ifup(struct net_device *dev, unsigned int nh_flags)
+{
+ struct mpls_route __rcu **platform_label;
+ struct net *net = dev_net(dev);
+ unsigned index;
+ int alive;
+
+ platform_label = rtnl_dereference(net->mpls.platform_label);
+ for (index = 0; index < net->mpls.platform_labels; index++) {
+ struct mpls_route *rt = rtnl_dereference(platform_label[index]);
+ int changed = 0;
+
+ if (!rt)
+ continue;
+ alive = 0;
+ for_nexthops(rt) {
+ struct net_device *nh_dev =
+ rtnl_dereference(nh->nh_dev);
+
+ if (!(nh->nh_flags & nh_flags)) {
+ alive++;
+ continue;
+ }
+ if (nh_dev != dev)
+ continue;
+ alive++;
+ nh->nh_flags &= ~nh_flags;
+ changed = 1;
+ } endfor_nexthops(rt);
- mpls_dev_sysctl_unregister(mdev);
+ if (alive > 0) {
+ rt->rt_flags &= ~nh_flags;
+ changed = 1;
+ }
- RCU_INIT_POINTER(dev->mpls_ptr, NULL);
+ if (changed)
+ mpls_multipath_rebalance(rt);
+ }
- kfree_rcu(mdev, rcu);
+ return;
}
static int mpls_dev_notify(struct notifier_block *this, unsigned long event,
@@ -910,9 +1039,9 @@ static int mpls_dev_notify(struct notifier_block *this,
unsigned long event,
{
struct net_device *dev = netdev_notifier_info_to_dev(ptr);
struct mpls_dev *mdev;
+ unsigned int flags;
- switch(event) {
- case NETDEV_REGISTER:
+ if (event == NETDEV_REGISTER) {
/* For now just support ethernet devices */
if ((dev->type == ARPHRD_ETHER) ||
(dev->type == ARPHRD_LOOPBACK)) {
@@ -920,10 +1049,39 @@ static int mpls_dev_notify(struct notifier_block *this,
unsigned long event,
if (IS_ERR(mdev))
return notifier_from_errno(PTR_ERR(mdev));
}
- break;
+ return NOTIFY_OK;
+ }
+ mdev = mpls_dev_get(dev);
+ if (!mdev)
+ return NOTIFY_OK;
+
+ switch (event) {
+ case NETDEV_DOWN:
+ mpls_ifdown(dev, event);
+ break;
+ case NETDEV_UP:
+ flags = dev_get_flags(dev);
+ if (flags & (IFF_RUNNING | IFF_LOWER_UP))
+ mpls_ifup(dev, RTNH_F_DEAD | RTNH_F_LINKDOWN);
+ else
+ mpls_ifup(dev, RTNH_F_DEAD);
+ break;
+ case NETDEV_CHANGE:
+ flags = dev_get_flags(dev);
+ if (flags & (IFF_RUNNING | IFF_LOWER_UP))
+ mpls_ifup(dev, RTNH_F_DEAD | RTNH_F_LINKDOWN);
+ else
+ mpls_ifdown(dev, event);
+ break;
case NETDEV_UNREGISTER:
- mpls_ifdown(dev);
+ mpls_ifdown(dev, event);
+ mdev = mpls_dev_get(dev);
+ if (mdev) {
+ mpls_dev_sysctl_unregister(mdev);
+ RCU_INIT_POINTER(dev->mpls_ptr, NULL);
+ kfree_rcu(mdev, rcu);
+ }
break;
case NETDEV_CHANGENAME:
mdev = mpls_dev_get(dev);
@@ -1237,6 +1395,10 @@ static int mpls_dump_route(struct sk_buff *skb, u32
portid, u32 seq, int event,
dev = rtnl_dereference(nh->nh_dev);
if (dev && nla_put_u32(skb, RTA_OIF, dev->ifindex))
goto nla_put_failure;
+ if (nh->nh_flags & RTNH_F_LINKDOWN)
+ rtm->rtm_flags |= RTNH_F_LINKDOWN;
+ if (nh->nh_flags & RTNH_F_DEAD)
+ rtm->rtm_flags |= RTNH_F_DEAD;
} else {
struct rtnexthop *rtnh;
struct nlattr *mp;
@@ -1253,6 +1415,12 @@ static int mpls_dump_route(struct sk_buff *skb, u32
portid, u32 seq, int event,
dev = rtnl_dereference(nh->nh_dev);
if (dev)
rtnh->rtnh_ifindex = dev->ifindex;
+ if (nh->nh_flags & RTNH_F_LINKDOWN)
+ rtnh->rtnh_flags |= RTNH_F_LINKDOWN;
+ if (nh->nh_flags & RTNH_F_DEAD)
+ rtnh->rtnh_flags |= RTNH_F_DEAD;
+
+ rtnh->rtnh_hops = nh->nh_weight - 1;
if (nh->nh_labels && nla_put_labels(skb, RTA_NEWDST,
nh->nh_labels,
nh->nh_label))
diff --git a/net/mpls/internal.h b/net/mpls/internal.h
index bde52ce..7014032 100644
--- a/net/mpls/internal.h
+++ b/net/mpls/internal.h
@@ -41,6 +41,9 @@ enum mpls_payload_type {
struct mpls_nh { /* next hop label forwarding entry */
struct net_device __rcu *nh_dev;
+ unsigned int nh_flags;
+ int nh_weight;
+ atomic_t nh_upper_bound;
u32 nh_label[MAX_NEW_LABELS];
u8 nh_labels;
u8 nh_via_alen;
@@ -70,6 +73,7 @@ struct mpls_nh { /* next hop label forwarding entry */
*/
struct mpls_route { /* next hop label forwarding entry */
struct rcu_head rt_rcu;
+ unsigned int rt_flags;
u8 rt_protocol;
u8 rt_payload_type;
u8 rt_max_alen;
--
1.9.1
--
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to majord...@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
