switchdev: add offload_fwd_mark generator helper

skb->offload_fwd_mark and dev->offload_fwd_mark are 32-bit and should be
unique for device and may even be unique for a sub-set of ports within
device, so add switchdev helper function to generate unique marks based on
port's switch ID and group_ifindex.  group_ifindex would typically be the
container dev's ifindex, such as the bridge's ifindex.

The generator uses a global hash table to store offload_fwd_marks hashed by
{switch ID, group_ifindex} key.

Signed-off-by: Scott Feldman <sfeldma@gmail.com>
Acked-by: Jiri Pirko <jiri@resnulli.us>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/include/net/switchdev.h b/include/net/switchdev.h
index d5671f118bfc54566a34d48708e35b69af19b417..89da8934519bb720c4d5f1f479040a889e6079fd 100644 (file)
--- a/include/net/switchdev.h
+++ b/include/net/switchdev.h
@@ -157,6 +157,9 @@ int switchdev_port_fdb_del(struct ndmsg *ndm, struct nlattr *tb[],
 int switchdev_port_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb,
                            struct net_device *dev,
                            struct net_device *filter_dev, int idx);
+void switchdev_port_fwd_mark_set(struct net_device *dev,
+                                struct net_device *group_dev,
+                                bool joining);
 
 #else
 
@@ -271,6 +274,12 @@ static inline int switchdev_port_fdb_dump(struct sk_buff *skb,
        return -EOPNOTSUPP;
 }
 
+static inline void switchdev_port_fwd_mark_set(struct net_device *dev,
+                                              struct net_device *group_dev,
+                                              bool joining)
+{
+}
+
 #endif
 
 #endif /* _LINUX_SWITCHDEV_H_ */

diff --git a/net/switchdev/switchdev.c b/net/switchdev/switchdev.c
index 4e5bba50ccffaf1b7741876fcff5a12630094836..33bafa2e703e299f3b423d1f95b2a21cf177c634 100644 (file)
--- a/net/switchdev/switchdev.c
+++ b/net/switchdev/switchdev.c
@@ -1039,3 +1039,106 @@ void switchdev_fib_ipv4_abort(struct fib_info *fi)
        fi->fib_net->ipv4.fib_offload_disabled = true;
 }
 EXPORT_SYMBOL_GPL(switchdev_fib_ipv4_abort);
+
+static bool switchdev_port_same_parent_id(struct net_device *a,
+                                         struct net_device *b)
+{
+       struct switchdev_attr a_attr = {
+               .id = SWITCHDEV_ATTR_PORT_PARENT_ID,
+               .flags = SWITCHDEV_F_NO_RECURSE,
+       };
+       struct switchdev_attr b_attr = {
+               .id = SWITCHDEV_ATTR_PORT_PARENT_ID,
+               .flags = SWITCHDEV_F_NO_RECURSE,
+       };
+
+       if (switchdev_port_attr_get(a, &a_attr) ||
+           switchdev_port_attr_get(b, &b_attr))
+               return false;
+
+       return netdev_phys_item_id_same(&a_attr.u.ppid, &b_attr.u.ppid);
+}
+
+static u32 switchdev_port_fwd_mark_get(struct net_device *dev,
+                                      struct net_device *group_dev)
+{
+       struct net_device *lower_dev;
+       struct list_head *iter;
+
+       netdev_for_each_lower_dev(group_dev, lower_dev, iter) {
+               if (lower_dev == dev)
+                       continue;
+               if (switchdev_port_same_parent_id(dev, lower_dev))
+                       return lower_dev->offload_fwd_mark;
+               return switchdev_port_fwd_mark_get(dev, lower_dev);
+       }
+
+       return dev->ifindex;
+}
+
+static void switchdev_port_fwd_mark_reset(struct net_device *group_dev,
+                                         u32 old_mark, u32 *reset_mark)
+{
+       struct net_device *lower_dev;
+       struct list_head *iter;
+
+       netdev_for_each_lower_dev(group_dev, lower_dev, iter) {
+               if (lower_dev->offload_fwd_mark == old_mark) {
+                       if (!*reset_mark)
+                               *reset_mark = lower_dev->ifindex;
+                       lower_dev->offload_fwd_mark = *reset_mark;
+               }
+               switchdev_port_fwd_mark_reset(lower_dev, old_mark, reset_mark);
+       }
+}
+
+/**
+ *     switchdev_port_fwd_mark_set - Set port offload forwarding mark
+ *
+ *     @dev: port device
+ *     @group_dev: containing device
+ *     @joining: true if dev is joining group; false if leaving group
+ *
+ *     An ungrouped port's offload mark is just its ifindex.  A grouped
+ *     port's (member of a bridge, for example) offload mark is the ifindex
+ *     of one of the ports in the group with the same parent (switch) ID.
+ *     Ports on the same device in the same group will have the same mark.
+ *
+ *     Example:
+ *
+ *             br0             ifindex=9
+ *               sw1p1         ifindex=2       mark=2
+ *               sw1p2         ifindex=3       mark=2
+ *               sw2p1         ifindex=4       mark=5
+ *               sw2p2         ifindex=5       mark=5
+ *
+ *     If sw2p2 leaves the bridge, we'll have:
+ *
+ *             br0             ifindex=9
+ *               sw1p1         ifindex=2       mark=2
+ *               sw1p2         ifindex=3       mark=2
+ *               sw2p1         ifindex=4       mark=4
+ *             sw2p2           ifindex=5       mark=5
+ */
+void switchdev_port_fwd_mark_set(struct net_device *dev,
+                                struct net_device *group_dev,
+                                bool joining)
+{
+       u32 mark = dev->ifindex;
+       u32 reset_mark = 0;
+
+       if (group_dev && joining) {
+               mark = switchdev_port_fwd_mark_get(dev, group_dev);
+       } else if (group_dev && !joining) {
+               if (dev->offload_fwd_mark == mark)
+                       /* Ohoh, this port was the mark reference port,
+                        * but it's leaving the group, so reset the
+                        * mark for the remaining ports in the group.
+                        */
+                       switchdev_port_fwd_mark_reset(group_dev, mark,
+                                                     &reset_mark);
+       }
+
+       dev->offload_fwd_mark = mark;
+}
+EXPORT_SYMBOL_GPL(switchdev_port_fwd_mark_set);