net: replace hooks in __netif_receive_skb V5

What this patch does is it removes two receive frame hooks (for bridge and for
macvlan) from __netif_receive_skb. These are replaced them with a single
hook for both. It only supports one hook per device because it makes no
sense to do bridging and macvlan on the same device.

Then a network driver (of virtual netdev like macvlan or bridge) can register
an rx_handler for needed net device.

Signed-off-by: Jiri Pirko <jpirko@redhat.com>
Signed-off-by: Stephen Hemminger <shemminger@vyatta.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

9 files changed, 93 insertions, 83 deletions

diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c
index 87e8d4cb405..53422ce26f7 100644
--- a/drivers/net/macvlan.c
+++ b/drivers/net/macvlan.c
@@ -145,15 +145,16 @@ static void macvlan_broadcast(struct sk_buff *skb,
 }
 
 /* called under rcu_read_lock() from netif_receive_skb */
-static struct sk_buff *macvlan_handle_frame(struct macvlan_port *port,
-                                            struct sk_buff *skb)
+static struct sk_buff *macvlan_handle_frame(struct sk_buff *skb)
 {
+        struct macvlan_port *port;
         const struct ethhdr *eth = eth_hdr(skb);
         const struct macvlan_dev *vlan;
         const struct macvlan_dev *src;
         struct net_device *dev;
         unsigned int len;
 
+        port = rcu_dereference(skb->dev->macvlan_port);
         if (is_multicast_ether_addr(eth->h_dest)) {
                 src = macvlan_hash_lookup(port, eth->h_source);
                 if (!src)
@@ -515,6 +516,7 @@ static int macvlan_port_create(struct net_device *dev)
 {
         struct macvlan_port *port;
         unsigned int i;
+        int err;
 
         if (dev->type != ARPHRD_ETHER || dev->flags & IFF_LOOPBACK)
                 return -EINVAL;
@@ -528,13 +530,21 @@ static int macvlan_port_create(struct net_device *dev)
         for (i = 0; i < MACVLAN_HASH_SIZE; i++)
                 INIT_HLIST_HEAD(&port->vlan_hash[i]);
         rcu_assign_pointer(dev->macvlan_port, port);
-        return 0;
+
+        err = netdev_rx_handler_register(dev, macvlan_handle_frame);
+        if (err) {
+                rcu_assign_pointer(dev->macvlan_port, NULL);
+                kfree(port);
+        }
+
+        return err;
 }
 
 static void macvlan_port_destroy(struct net_device *dev)
 {
         struct macvlan_port *port = dev->macvlan_port;
 
+        netdev_rx_handler_unregister(dev);
         rcu_assign_pointer(dev->macvlan_port, NULL);
         synchronize_rcu();
         kfree(port);
@@ -767,14 +777,12 @@ static int __init macvlan_init_module(void)
         int err;
 
         register_netdevice_notifier(&macvlan_notifier_block);
-        macvlan_handle_frame_hook = macvlan_handle_frame;
 
         err = macvlan_link_register(&macvlan_link_ops);
         if (err < 0)
                 goto err1;
         return 0;
 err1:
-        macvlan_handle_frame_hook = NULL;
         unregister_netdevice_notifier(&macvlan_notifier_block);
         return err;
 }
@@ -782,7 +790,6 @@ err1:
 static void __exit macvlan_cleanup_module(void)
 {
         rtnl_link_unregister(&macvlan_link_ops);
-        macvlan_handle_frame_hook = NULL;
         unregister_netdevice_notifier(&macvlan_notifier_block);
 }
 
diff --git a/include/linux/if_bridge.h b/include/linux/if_bridge.h
index 938b7e81df9..0d241a5c490 100644
--- a/include/linux/if_bridge.h
+++ b/include/linux/if_bridge.h
@@ -102,8 +102,6 @@ struct __fdb_entry {
 #include <linux/netdevice.h>
 
 extern void brioctl_set(int (*ioctl_hook)(struct net *, unsigned int, void __user *));
-extern struct sk_buff *(*br_handle_frame_hook)(struct net_bridge_port *p,
-                                               struct sk_buff *skb);
 extern int (*br_should_route_hook)(struct sk_buff *skb);
 
 #endif
diff --git a/include/linux/if_macvlan.h b/include/linux/if_macvlan.h
index 9ea047aca79..c26a0e4f0ce 100644
--- a/include/linux/if_macvlan.h
+++ b/include/linux/if_macvlan.h
@@ -84,8 +84,4 @@ extern int macvlan_link_register(struct rtnl_link_ops *ops);
 extern netdev_tx_t macvlan_start_xmit(struct sk_buff *skb,
                                       struct net_device *dev);
 
-
-extern struct sk_buff *(*macvlan_handle_frame_hook)(struct macvlan_port *,
-                                                    struct sk_buff *);
-
 #endif /* _LINUX_IF_MACVLAN_H */
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index bd6b75317d5..5156b806924 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -381,6 +381,8 @@ enum gro_result {
 };
 typedef enum gro_result gro_result_t;
 
+typedef struct sk_buff *rx_handler_func_t(struct sk_buff *skb);
+
 extern void __napi_schedule(struct napi_struct *n);
 
 static inline int napi_disable_pending(struct napi_struct *n)
@@ -957,6 +959,7 @@ struct net_device {
 #endif
 
         struct netdev_queue     rx_queue;
+        rx_handler_func_t       *rx_handler;
 
         struct netdev_queue     *_tx ____cacheline_aligned_in_smp;
 
@@ -1689,6 +1692,10 @@ static inline void napi_free_frags(struct napi_struct *napi)
         napi->skb = NULL;
 }
 
+extern int netdev_rx_handler_register(struct net_device *dev,
+                                      rx_handler_func_t *rx_handler);
+extern void netdev_rx_handler_unregister(struct net_device *dev);
+
 extern void             netif_nit_deliver(struct sk_buff *skb);
 extern int              dev_valid_name(const char *name);
 extern int              dev_ioctl(struct net *net, unsigned int cmd, void __user *);
diff --git a/net/bridge/br.c b/net/bridge/br.c
index 76357b54775..c8436fa3134 100644
--- a/net/bridge/br.c
+++ b/net/bridge/br.c
@@ -63,7 +63,6 @@ static int __init br_init(void)
                 goto err_out4;
 
         brioctl_set(br_ioctl_deviceless_stub);
-        br_handle_frame_hook = br_handle_frame;
 
 #if defined(CONFIG_ATM_LANE) || defined(CONFIG_ATM_LANE_MODULE)
         br_fdb_test_addr_hook = br_fdb_test_addr;
@@ -100,7 +99,6 @@ static void __exit br_deinit(void)
         br_fdb_test_addr_hook = NULL;
 #endif
 
-        br_handle_frame_hook = NULL;
         br_fdb_fini();
 }
 
diff --git a/net/bridge/br_if.c b/net/bridge/br_if.c
index 18b245e2c00..d9242342837 100644
--- a/net/bridge/br_if.c
+++ b/net/bridge/br_if.c
@@ -147,6 +147,7 @@ static void del_nbp(struct net_bridge_port *p)
 
         list_del_rcu(&p->list);
 
+        netdev_rx_handler_unregister(dev);
         rcu_assign_pointer(dev->br_port, NULL);
 
         br_multicast_del_port(p);
@@ -429,6 +430,11 @@ int br_add_if(struct net_bridge *br, struct net_device *dev)
                 goto err2;
 
         rcu_assign_pointer(dev->br_port, p);
+
+        err = netdev_rx_handler_register(dev, br_handle_frame);
+        if (err)
+                goto err3;
+
         dev_disable_lro(dev);
 
         list_add_rcu(&p->list, &br->port_list);
@@ -451,6 +457,8 @@ int br_add_if(struct net_bridge *br, struct net_device *dev)
         br_netpoll_enable(br, dev);
 
         return 0;
+err3:
+        rcu_assign_pointer(dev->br_port, NULL);
 err2:
         br_fdb_delete_by_port(br, p, 1);
 err1:
diff --git a/net/bridge/br_input.c b/net/bridge/br_input.c
index d36e700f7a2..99647d8f95c 100644
--- a/net/bridge/br_input.c
+++ b/net/bridge/br_input.c
@@ -131,15 +131,19 @@ static inline int is_link_local(const unsigned char *dest)
 }
 
 /*
- * Called via br_handle_frame_hook.
  * Return NULL if skb is handled
- * note: already called with rcu_read_lock (preempt_disabled)
+ * note: already called with rcu_read_lock (preempt_disabled) from
+ * netif_receive_skb
  */
-struct sk_buff *br_handle_frame(struct net_bridge_port *p, struct sk_buff *skb)
+struct sk_buff *br_handle_frame(struct sk_buff *skb)
 {
+        struct net_bridge_port *p;
         const unsigned char *dest = eth_hdr(skb)->h_dest;
         int (*rhook)(struct sk_buff *skb);
 
+        if (skb->pkt_type == PACKET_LOOPBACK)
+                return skb;
+
         if (!is_valid_ether_addr(eth_hdr(skb)->h_source))
                 goto drop;
 
@@ -147,6 +151,8 @@ struct sk_buff *br_handle_frame(struct net_bridge_port *p, struct sk_buff *skb)
         if (!skb)
                 return NULL;
 
+        p = rcu_dereference(skb->dev->br_port);
+
         if (unlikely(is_link_local(dest))) {
                 /* Pause frames shouldn't be passed up by driver anyway */
                 if (skb->protocol == htons(ETH_P_PAUSE))
diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h
index 0f4a74bc6a9..c83519b555b 100644
--- a/net/bridge/br_private.h
+++ b/net/bridge/br_private.h
@@ -331,8 +331,7 @@ extern void br_features_recompute(struct net_bridge *br);
 
 /* br_input.c */
 extern int br_handle_frame_finish(struct sk_buff *skb);
-extern struct sk_buff *br_handle_frame(struct net_bridge_port *p,
-                                       struct sk_buff *skb);
+extern struct sk_buff *br_handle_frame(struct sk_buff *skb);
 
 /* br_ioctl.c */
 extern int br_dev_ioctl(struct net_device *dev, struct ifreq *rq, int cmd);
diff --git a/net/core/dev.c b/net/core/dev.c
index ffca5c1066f..ec01a5998d7 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -2604,70 +2604,14 @@ static inline int deliver_skb(struct sk_buff *skb,
         return pt_prev->func(skb, skb->dev, pt_prev, orig_dev);
 }
 
-#if defined(CONFIG_BRIDGE) || defined (CONFIG_BRIDGE_MODULE)
-
-#if defined(CONFIG_ATM_LANE) || defined(CONFIG_ATM_LANE_MODULE)
+#if (defined(CONFIG_BRIDGE) || defined(CONFIG_BRIDGE_MODULE)) && \
+    (defined(CONFIG_ATM_LANE) || defined(CONFIG_ATM_LANE_MODULE))
 /* This hook is defined here for ATM LANE */
 int (*br_fdb_test_addr_hook)(struct net_device *dev,
                              unsigned char *addr) __read_mostly;
 EXPORT_SYMBOL_GPL(br_fdb_test_addr_hook);
 #endif
 
-/*
- * If bridge module is loaded call bridging hook.
- *  returns NULL if packet was consumed.
- */
-struct sk_buff *(*br_handle_frame_hook)(struct net_bridge_port *p,
-                                        struct sk_buff *skb) __read_mostly;
-EXPORT_SYMBOL_GPL(br_handle_frame_hook);
-
-static inline struct sk_buff *handle_bridge(struct sk_buff *skb,
-                                            struct packet_type **pt_prev, int *ret,
-                                            struct net_device *orig_dev)
-{
-        struct net_bridge_port *port;
-
-        if (skb->pkt_type == PACKET_LOOPBACK ||
-            (port = rcu_dereference(skb->dev->br_port)) == NULL)
-                return skb;
-
-        if (*pt_prev) {
-                *ret = deliver_skb(skb, *pt_prev, orig_dev);
-                *pt_prev = NULL;
-        }
-
-        return br_handle_frame_hook(port, skb);
-}
-#else
-#define handle_bridge(skb, pt_prev, ret, orig_dev)      (skb)
-#endif
-
-#if defined(CONFIG_MACVLAN) || defined(CONFIG_MACVLAN_MODULE)
-struct sk_buff *(*macvlan_handle_frame_hook)(struct macvlan_port *p,
-                                             struct sk_buff *skb) __read_mostly;
-EXPORT_SYMBOL_GPL(macvlan_handle_frame_hook);
-
-static inline struct sk_buff *handle_macvlan(struct sk_buff *skb,
-                                             struct packet_type **pt_prev,
-                                             int *ret,
-                                             struct net_device *orig_dev)
-{
-        struct macvlan_port *port;
-
-        port = rcu_dereference(skb->dev->macvlan_port);
-        if (!port)
-                return skb;
-
-        if (*pt_prev) {
-                *ret = deliver_skb(skb, *pt_prev, orig_dev);
-                *pt_prev = NULL;
-        }
-        return macvlan_handle_frame_hook(port, skb);
-}
-#else
-#define handle_macvlan(skb, pt_prev, ret, orig_dev)     (skb)
-#endif
-
 #ifdef CONFIG_NET_CLS_ACT
 /* TODO: Maybe we should just force sch_ingress to be compiled in
  * when CONFIG_NET_CLS_ACT is? otherwise some useless instructions
@@ -2763,6 +2707,47 @@ void netif_nit_deliver(struct sk_buff *skb)
         rcu_read_unlock();
 }
 
+/**
+ *      netdev_rx_handler_register - register receive handler
+ *      @dev: device to register a handler for
+ *      @rx_handler: receive handler to register
+ *
+ *      Register a receive hander for a device. This handler will then be
+ *      called from __netif_receive_skb. A negative errno code is returned
+ *      on a failure.
+ *
+ *      The caller must hold the rtnl_mutex.
+ */
+int netdev_rx_handler_register(struct net_device *dev,
+                               rx_handler_func_t *rx_handler)
+{
+        ASSERT_RTNL();
+
+        if (dev->rx_handler)
+                return -EBUSY;
+
+        rcu_assign_pointer(dev->rx_handler, rx_handler);
+
+        return 0;
+}
+EXPORT_SYMBOL_GPL(netdev_rx_handler_register);
+
+/**
+ *      netdev_rx_handler_unregister - unregister receive handler
+ *      @dev: device to unregister a handler from
+ *
+ *      Unregister a receive hander from a device.
+ *
+ *      The caller must hold the rtnl_mutex.
+ */
+void netdev_rx_handler_unregister(struct net_device *dev)
+{
+
+        ASSERT_RTNL();
+        rcu_assign_pointer(dev->rx_handler, NULL);
+}
+EXPORT_SYMBOL_GPL(netdev_rx_handler_unregister);
+
 static inline void skb_bond_set_mac_by_master(struct sk_buff *skb,
                                               struct net_device *master)
 {
@@ -2815,6 +2800,7 @@ EXPORT_SYMBOL(__skb_bond_should_drop);
 static int __netif_receive_skb(struct sk_buff *skb)
 {
         struct packet_type *ptype, *pt_prev;
+        rx_handler_func_t *rx_handler;
         struct net_device *orig_dev;
         struct net_device *master;
         struct net_device *null_or_orig;
@@ -2877,12 +2863,17 @@ static int __netif_receive_skb(struct sk_buff *skb)
 ncls:
 #endif
 
-        skb = handle_bridge(skb, &pt_prev, &ret, orig_dev);
-        if (!skb)
-                goto out;
-        skb = handle_macvlan(skb, &pt_prev, &ret, orig_dev);
-        if (!skb)
-                goto out;
+        /* Handle special case of bridge or macvlan */
+        rx_handler = rcu_dereference(skb->dev->rx_handler);
+        if (rx_handler) {
+                if (pt_prev) {
+                        ret = deliver_skb(skb, pt_prev, orig_dev);
+                        pt_prev = NULL;
+                }
+                skb = rx_handler(skb);
+                if (!skb)
+                        goto out;
+        }
 
         /*
          * Make sure frames received on VLAN interfaces stacked on