The current rx_handler approach was introduced for bonding, bridging, etc.
For L3 devices like VRF it would be better to intercept the packet at the
L3 layer. This patch adds a new handler to be invoked by the L3 protocol.
For the RFC I re-use the existing data_handler and only allow 1 of the
rx_handlers to be set. This could be expanded to alllow both intercepts
if desired.
Signed-off-by: David Ahern <d...@cumulusnetworks.com>
---
include/linux/netdevice.h | 6 ++++++
net/core/dev.c | 55 ++++++++++++++++++++++++++++++++++++++---------
2 files changed, 51 insertions(+), 10 deletions(-)
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 6abe0d6f1e1d..c1b5a651a32f 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -1451,6 +1451,8 @@ enum netdev_priv_flags {
* @real_num_rx_queues: Number of RX queues currently active in device
*
* @rx_handler: handler for received packets
+ * @l3_rx_handler: L3 handler for received packets
+ * Only rx_handler OR l3_rx_handler can be set
* @rx_handler_data: XXX: need comments on this one
* @ingress_queue: XXX: need comments on this one
* @broadcast: hw bcast address
@@ -1683,6 +1685,7 @@ struct net_device {
unsigned long gro_flush_timeout;
rx_handler_func_t __rcu *rx_handler;
+ rx_handler_func_t __rcu *l3_rx_handler;
void __rcu *rx_handler_data;
#ifdef CONFIG_NET_CLS_ACT
@@ -3015,6 +3018,9 @@ static inline void napi_free_frags(struct napi_struct
*napi)
int netdev_rx_handler_register(struct net_device *dev,
rx_handler_func_t *rx_handler,
void *rx_handler_data);
+int netdev_l3_rx_handler_register(struct net_device *dev,
+ rx_handler_func_t *rx_handler,
+ void *rx_handler_data);
void netdev_rx_handler_unregister(struct net_device *dev);
bool dev_valid_name(const char *name);
diff --git a/net/core/dev.c b/net/core/dev.c
index 7bb24f1879b8..5698f43f9c5b 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -3675,6 +3675,26 @@ static inline struct sk_buff *handle_ing(struct sk_buff
*skb,
return skb;
}
+static int __netdev_rx_handler_register(struct net_device *dev,
+ rx_handler_func_t *rx_handler,
+ void *rx_handler_data,
+ bool l3_hdlr)
+{
+ ASSERT_RTNL();
+
+ if (dev->rx_handler || dev->l3_rx_handler)
+ return -EBUSY;
+
+ /* Note: rx_handler_data must be set before rx_handler */
+ rcu_assign_pointer(dev->rx_handler_data, rx_handler_data);
+ if (l3_hdlr)
+ rcu_assign_pointer(dev->l3_rx_handler, rx_handler);
+ else
+ rcu_assign_pointer(dev->rx_handler, rx_handler);
+
+ return 0;
+}
+
/**
* netdev_rx_handler_register - register receive handler
* @dev: device to register a handler for
@@ -3693,20 +3713,35 @@ int netdev_rx_handler_register(struct net_device *dev,
rx_handler_func_t *rx_handler,
void *rx_handler_data)
{
- ASSERT_RTNL();
-
- if (dev->rx_handler)
- return -EBUSY;
-
- /* Note: rx_handler_data must be set before rx_handler */
- rcu_assign_pointer(dev->rx_handler_data, rx_handler_data);
- rcu_assign_pointer(dev->rx_handler, rx_handler);
-
- return 0;
+ return __netdev_rx_handler_register(dev, rx_handler,
+ rx_handler_data, 0);
}
EXPORT_SYMBOL_GPL(netdev_rx_handler_register);
/**
+ * netdev_l3_rx_handler_register - register L3 receive handler
+ * @dev: device to register a handler for
+ * @rx_handler: receive handler to register
+ * @rx_handler_data: data pointer that is used by rx handler
+ *
+ * Register a receive handler 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.
+ *
+ * For a general description of rx_handler, see enum rx_handler_result.
+ */
+int netdev_l3_rx_handler_register(struct net_device *dev,
+ rx_handler_func_t *rx_handler,
+ void *rx_handler_data)
+{
+ return __netdev_rx_handler_register(dev, rx_handler,
+ rx_handler_data, 1);
+}
+EXPORT_SYMBOL_GPL(netdev_l3_rx_handler_register);
+
+/**
* netdev_rx_handler_unregister - unregister receive handler
* @dev: device to unregister a handler from
*
--
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
