@@ -833,6 +833,27 @@ typedef u16 (*select_queue_fallback_t)(struct net_device *dev,
struct sk_buff *skb,
struct net_device *sb_dev);
+enum net_device_path_type {
+ DEV_PATH_ETHERNET = 0,
+};
+
+struct net_device_path {
+ enum net_device_path_type type;
+ const struct net_device *dev;
+};
+
+#define NET_DEVICE_PATH_STACK_MAX 5
+
+struct net_device_path_stack {
+ int num_paths;
+ struct net_device_path path[NET_DEVICE_PATH_STACK_MAX];
+};
+
+struct net_device_path_ctx {
+ const struct net_device *dev;
+ const u8 *daddr;
+};
+
enum tc_setup_type {
TC_SETUP_QDISC_MQPRIO,
TC_SETUP_CLSU32,
@@ -1279,6 +1300,8 @@ struct netdev_net_notifier {
* struct net_device *(*ndo_get_peer_dev)(struct net_device *dev);
* If a device is paired with a peer device, return the peer instance.
* The caller must be under RCU read context.
+ * int (*ndo_fill_forward_path)(struct net_device_path_ctx *ctx, struct net_device_path *path);
+ * Get the forwarding path to reach the real device from the HW destination address
*/
struct net_device_ops {
int (*ndo_init)(struct net_device *dev);
@@ -1487,6 +1510,8 @@ struct net_device_ops {
int (*ndo_tunnel_ctl)(struct net_device *dev,
struct ip_tunnel_parm *p, int cmd);
struct net_device * (*ndo_get_peer_dev)(struct net_device *dev);
+ int (*ndo_fill_forward_path)(struct net_device_path_ctx *ctx,
+ struct net_device_path *path);
};
/**
@@ -2824,6 +2849,8 @@ void dev_remove_offload(struct packet_offload *po);
int dev_get_iflink(const struct net_device *dev);
int dev_fill_metadata_dst(struct net_device *dev, struct sk_buff *skb);
+int dev_fill_forward_path(const struct net_device *dev, const u8 *daddr,
+ struct net_device_path_stack *stack);
struct net_device *__dev_get_by_flags(struct net *net, unsigned short flags,
unsigned short mask);
struct net_device *dev_get_by_name(struct net *net, const char *name);
@@ -846,6 +846,42 @@ int dev_fill_metadata_dst(struct net_device *dev, struct sk_buff *skb)
}
EXPORT_SYMBOL_GPL(dev_fill_metadata_dst);
+int dev_fill_forward_path(const struct net_device *dev, const u8 *daddr,
+ struct net_device_path_stack *stack)
+{
+ const struct net_device *last_dev;
+ struct net_device_path_ctx ctx = {
+ .dev = dev,
+ .daddr = daddr,
+ };
+ struct net_device_path *path;
+ int ret = 0, k;
+
+ stack->num_paths = 0;
+ while (ctx.dev && ctx.dev->netdev_ops->ndo_fill_forward_path) {
+ last_dev = ctx.dev;
+ k = stack->num_paths++;
+ if (WARN_ON_ONCE(k >= NET_DEVICE_PATH_STACK_MAX))
+ return -1;
+
+ path = &stack->path[k];
+ memset(path, 0, sizeof(struct net_device_path));
+
+ ret = ctx.dev->netdev_ops->ndo_fill_forward_path(&ctx, path);
+ if (ret < 0)
+ return -1;
+
+ if (WARN_ON_ONCE(last_dev == ctx.dev))
+ return -1;
+ }
+ path = &stack->path[stack->num_paths++];
+ path->type = DEV_PATH_ETHERNET;
+ path->dev = ctx.dev;
+
+ return ret;
+}
+EXPORT_SYMBOL_GPL(dev_fill_forward_path);
+
/**
* __dev_get_by_name - find a device by its name
* @net: the applicable net namespace
This patch adds dev_fill_forward_path() which resolves the path to reach the real netdevice from the IP forwarding side. This function takes as input the netdevice and the destination hardware address and it walks down the devices calling .ndo_fill_forward_path() for each device until the real device is found. For instance, assuming the following topology: IP forwarding / \ br0 eth0 / \ eth1 eth2 . . . ethX ab:cd:ef:ab:cd:ef where eth1 and eth2 are bridge ports and eth0 provides WAN connectivity. ethX is the interface in another box which is connected to the eth1 bridge port. For packets going through IP forwarding to br0 whose destination MAC address is ab:cd:ef:ab:cd:ef, dev_fill_forward_path() provides the following path: br0 -> eth1 .ndo_fill_forward_path for br0 looks up at the FDB for the bridge port from the destination MAC address to get the bridge port eth1. This information allows to create a fast path that bypasses the classic bridge and IP forwarding paths, so packets go directly from the bridge port eth1 to eth0 (wan interface) and vice versa. fast path .------------------------. / \ | IP forwarding | | / \ \/ | br0 eth0 . / \ -> eth1 eth2 . . . ethX ab:cd:ef:ab:cd:ef Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org> --- v4: - Check for possible device stack overflow in dev_fill_forward_path(), per Jakub Kicinski. - Remove memset for the net_device_path_ctx structure in dev_fill_forward_path() and avoid full memset of struct net_device_path_stack. include/linux/netdevice.h | 27 +++++++++++++++++++++++++++ net/core/dev.c | 36 ++++++++++++++++++++++++++++++++++++ 2 files changed, 63 insertions(+)