net, core: Add support for XDP redirection to slave device

This adds the ndo_xdp_get_xmit_slave hook for transforming XDP_TX
into XDP_REDIRECT after BPF program run when the ingress device
is a bond slave.

The dev_xdp_prog_count is exposed so that slave devices can be checked
for loaded XDP programs in order to avoid the situation where both
bond master and slave have programs loaded according to xdp_state.

Signed-off-by: Jussi Maki <[email protected]>
Signed-off-by: Daniel Borkmann <[email protected]>
Cc: Jay Vosburgh <[email protected]>
Cc: Veaceslav Falico <[email protected]>
Cc: Andy Gospodarek <[email protected]>
Link: https://lore.kernel.org/bpf/[email protected]

Author: joamaki

include/linux/filter.h

@@ -776,14 +776,25 @@ static inline u32 bpf_prog_run_clear_cb(const struct bpf_prog *prog,
 
 DECLARE_BPF_DISPATCHER(xdp)
 
+DECLARE_STATIC_KEY_FALSE(bpf_master_redirect_enabled_key);
+
+u32 xdp_master_redirect(struct xdp_buff *xdp);
+
 static __always_inline u32 bpf_prog_run_xdp(const struct bpf_prog *prog,
 					    struct xdp_buff *xdp)
 {
 	/* Driver XDP hooks are invoked within a single NAPI poll cycle and thus
 	 * under local_bh_disable(), which provides the needed RCU protection
 	 * for accessing map entries.
 	 */
-	return __BPF_PROG_RUN(prog, xdp, BPF_DISPATCHER_FUNC(xdp));
+	u32 act = __BPF_PROG_RUN(prog, xdp, BPF_DISPATCHER_FUNC(xdp));
+
+	if (static_branch_unlikely(&bpf_master_redirect_enabled_key)) {
+		if (act == XDP_TX && netif_is_bond_slave(xdp->rxq->dev))
+			act = xdp_master_redirect(xdp);
+	}
+
+	return act;
 }
 
 void bpf_prog_change_xdp(struct bpf_prog *prev_prog, struct bpf_prog *prog);

include/linux/netdevice.h

@@ -1330,6 +1330,9 @@ struct netdev_net_notifier {
  *	that got dropped are freed/returned via xdp_return_frame().
  *	Returns negative number, means general error invoking ndo, meaning
  *	no frames were xmit'ed and core-caller will free all frames.
+ * struct net_device *(*ndo_xdp_get_xmit_slave)(struct net_device *dev,
+ *					        struct xdp_buff *xdp);
+ *      Get the xmit slave of master device based on the xdp_buff.
  * int (*ndo_xsk_wakeup)(struct net_device *dev, u32 queue_id, u32 flags);
  *      This function is used to wake up the softirq, ksoftirqd or kthread
  *	responsible for sending and/or receiving packets on a specific
@@ -1557,6 +1560,8 @@ struct net_device_ops {
 	int			(*ndo_xdp_xmit)(struct net_device *dev, int n,
 						struct xdp_frame **xdp,
 						u32 flags);
+	struct net_device *	(*ndo_xdp_get_xmit_slave)(struct net_device *dev,
+							  struct xdp_buff *xdp);
 	int			(*ndo_xsk_wakeup)(struct net_device *dev,
 						  u32 queue_id, u32 flags);
 	struct devlink_port *	(*ndo_get_devlink_port)(struct net_device *dev);
@@ -4087,6 +4092,7 @@ typedef int (*bpf_op_t)(struct net_device *dev, struct netdev_bpf *bpf);
 int dev_change_xdp_fd(struct net_device *dev, struct netlink_ext_ack *extack,
 		      int fd, int expected_fd, u32 flags);
 int bpf_xdp_link_attach(const union bpf_attr *attr, struct bpf_prog *prog);
+u8 dev_xdp_prog_count(struct net_device *dev);
 u32 dev_xdp_prog_id(struct net_device *dev, enum bpf_xdp_mode mode);
 
 int __dev_forward_skb(struct net_device *dev, struct sk_buff *skb);

net/core/dev.c

@@ -9380,7 +9380,7 @@ static struct bpf_prog *dev_xdp_prog(struct net_device *dev,
 	return dev->xdp_state[mode].prog;
 }
 
-static u8 dev_xdp_prog_count(struct net_device *dev)
+u8 dev_xdp_prog_count(struct net_device *dev)
 {
 	u8 count = 0;
 	int i;
@@ -9390,6 +9390,7 @@ static u8 dev_xdp_prog_count(struct net_device *dev)
 			count++;
 	return count;
 }
+EXPORT_SYMBOL_GPL(dev_xdp_prog_count);
 
 u32 dev_xdp_prog_id(struct net_device *dev, enum bpf_xdp_mode mode)
 {
@@ -9483,6 +9484,8 @@ static int dev_xdp_attach(struct net_device *dev, struct netlink_ext_ack *extack
 {
 	unsigned int num_modes = hweight32(flags & XDP_FLAGS_MODES);
 	struct bpf_prog *cur_prog;
+	struct net_device *upper;
+	struct list_head *iter;
 	enum bpf_xdp_mode mode;
 	bpf_op_t bpf_op;
 	int err;
@@ -9521,6 +9524,14 @@ static int dev_xdp_attach(struct net_device *dev, struct netlink_ext_ack *extack
 		return -EBUSY;
 	}
 
+	/* don't allow if an upper device already has a program */
+	netdev_for_each_upper_dev_rcu(dev, upper, iter) {
+		if (dev_xdp_prog_count(upper) > 0) {
+			NL_SET_ERR_MSG(extack, "Cannot attach when an upper device already has a program");
+			return -EEXIST;
+		}
+	}
+
 	cur_prog = dev_xdp_prog(dev, mode);
 	/* can't replace attached prog with link */
 	if (link && cur_prog) {

net/core/filter.c

@@ -3950,6 +3950,31 @@ void bpf_clear_redirect_map(struct bpf_map *map)
 	}
 }
 
+DEFINE_STATIC_KEY_FALSE(bpf_master_redirect_enabled_key);
+EXPORT_SYMBOL_GPL(bpf_master_redirect_enabled_key);
+
+u32 xdp_master_redirect(struct xdp_buff *xdp)
+{
+	struct net_device *master, *slave;
+	struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info);
+
+	master = netdev_master_upper_dev_get_rcu(xdp->rxq->dev);
+	slave = master->netdev_ops->ndo_xdp_get_xmit_slave(master, xdp);
+	if (slave && slave != xdp->rxq->dev) {
+		/* The target device is different from the receiving device, so
+		 * redirect it to the new device.
+		 * Using XDP_REDIRECT gets the correct behaviour from XDP enabled
+		 * drivers to unmap the packet from their rx ring.
+		 */
+		ri->tgt_index = slave->ifindex;
+		ri->map_id = INT_MAX;
+		ri->map_type = BPF_MAP_TYPE_UNSPEC;
+		return XDP_REDIRECT;
+	}
+	return XDP_TX;
+}
+EXPORT_SYMBOL_GPL(xdp_master_redirect);
+
 int xdp_do_redirect(struct net_device *dev, struct xdp_buff *xdp,
 		    struct bpf_prog *xdp_prog)
 {