diff --git a/drivers/net/veth.c b/drivers/net/veth.c
index 091e5b4ba042..8c737668008a 100644
--- a/drivers/net/veth.c
+++ b/drivers/net/veth.c
@@ -420,6 +420,14 @@ static int veth_select_rxq(struct net_device *dev)
return smp_processor_id() % dev->real_num_rx_queues;
}
+static struct net_device *veth_peer_dev(struct net_device *dev)
+{
+ struct veth_priv *priv = netdev_priv(dev);
+
+ /* Callers must be under RCU read side. */
+ return rcu_dereference(priv->peer);
+}
+
static int veth_xdp_xmit(struct net_device *dev, int n,
struct xdp_frame **frames,
u32 flags, bool ndo_xmit)
@@ -1224,6 +1232,7 @@ static const struct net_device_ops veth_netdev_ops = {
.ndo_set_rx_headroom = veth_set_rx_headroom,
.ndo_bpf = veth_xdp,
.ndo_xdp_xmit = veth_ndo_xdp_xmit,
+ .ndo_get_peer_dev = veth_peer_dev,
};
#define VETH_FEATURES (NETIF_F_SG | NETIF_F_FRAGLIST | NETIF_F_HW_CSUM | \
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 28cfa53daf72..0533f86018dd 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -1277,6 +1277,9 @@ struct netdev_net_notifier {
* int (*ndo_tunnel_ctl)(struct net_device *dev, struct ip_tunnel_parm *p,
* int cmd);
* Add, change, delete or get information on an IPv4 tunnel.
+ * 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.
*/
struct net_device_ops {
int (*ndo_init)(struct net_device *dev);
@@ -1484,6 +1487,7 @@ struct net_device_ops {
struct devlink_port * (*ndo_get_devlink_port)(struct net_device *dev);
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);
};
/**
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 4272cc53d478..b97bc5abb3b8 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -3719,6 +3719,22 @@ union bpf_attr {
* never return NULL.
* Return
* A pointer pointing to the kernel percpu variable on this cpu.
+ *
+ * long bpf_redirect_peer(u32 ifindex, u64 flags)
+ * Description
+ * Redirect the packet to another net device of index *ifindex*.
+ * This helper is somewhat similar to **bpf_redirect**\ (), except
+ * that the redirection happens to the *ifindex*' peer device and
+ * the netns switch takes place from ingress to ingress without
+ * going through the CPU's backlog queue.
+ *
+ * The *flags* argument is reserved and must be 0. The helper is
+ * currently only supported for tc BPF program types at the ingress
+ * hook and for veth device types. The peer device must reside in a
+ * different network namespace.
+ * Return
+ * The helper returns **TC_ACT_REDIRECT** on success or
+ * **TC_ACT_SHOT** on error.
*/
#define __BPF_FUNC_MAPPER(FN) \
FN(unspec), \
@@ -3876,6 +3892,7 @@ union bpf_attr {
FN(redirect_neigh), \
FN(bpf_per_cpu_ptr), \
FN(bpf_this_cpu_ptr), \
+ FN(redirect_peer), \
/* */
/* integer value in 'imm' field of BPF_CALL instruction selects which helper
diff --git a/net/core/dev.c b/net/core/dev.c
index 9d55bf5d1a65..7dd015823593 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -4930,7 +4930,7 @@ EXPORT_SYMBOL_GPL(br_fdb_test_addr_hook);
static inline struct sk_buff *
sch_handle_ingress(struct sk_buff *skb, struct packet_type **pt_prev, int *ret,
- struct net_device *orig_dev)
+ struct net_device *orig_dev, bool *another)
{
#ifdef CONFIG_NET_CLS_ACT
struct mini_Qdisc *miniq = rcu_dereference_bh(skb->dev->miniq_ingress);
@@ -4974,7 +4974,11 @@ sch_handle_ingress(struct sk_buff *skb, struct packet_type **pt_prev, int *ret,
* redirecting to another netdev
*/
__skb_push(skb, skb->mac_len);
- skb_do_redirect(skb);
+ if (skb_do_redirect(skb) == -EAGAIN) {
+ __skb_pull(skb, skb->mac_len);
+ *another = true;
+ break;
+ }
return NULL;
case TC_ACT_CONSUMED:
return NULL;
@@ -5163,7 +5167,12 @@ another_round:
skip_taps:
#ifdef CONFIG_NET_INGRESS
if (static_branch_unlikely(&ingress_needed_key)) {
- skb = sch_handle_ingress(skb, &pt_prev, &ret, orig_dev);
+ bool another = false;
+
+ skb = sch_handle_ingress(skb, &pt_prev, &ret, orig_dev,
+ &another);
+ if (another)
+ goto another_round;
if (!skb)
goto out;
diff --git a/net/core/filter.c b/net/core/filter.c
index 5da44b11e1ec..fab951c6be57 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -2380,8 +2380,9 @@ out:
/* Internal, non-exposed redirect flags. */
enum {
- BPF_F_NEIGH = (1ULL << 1),
-#define BPF_F_REDIRECT_INTERNAL (BPF_F_NEIGH)
+ BPF_F_NEIGH = (1ULL << 1),
+ BPF_F_PEER = (1ULL << 2),
+#define BPF_F_REDIRECT_INTERNAL (BPF_F_NEIGH | BPF_F_PEER)
};
BPF_CALL_3(bpf_clone_redirect, struct sk_buff *, skb, u32, ifindex, u64, flags)
@@ -2430,19 +2431,35 @@ EXPORT_PER_CPU_SYMBOL_GPL(bpf_redirect_info);
int skb_do_redirect(struct sk_buff *skb)
{
struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info);
+ struct net *net = dev_net(skb->dev);
struct net_device *dev;
u32 flags = ri->flags;
- dev = dev_get_by_index_rcu(dev_net(skb->dev), ri->tgt_index);
+ dev = dev_get_by_index_rcu(net, ri->tgt_index);
ri->tgt_index = 0;
- if (unlikely(!dev)) {
- kfree_skb(skb);
- return -EINVAL;
- }
+ ri->flags = 0;
+ if (unlikely(!dev))
+ goto out_drop;
+ if (flags & BPF_F_PEER) {
+ const struct net_device_ops *ops = dev->netdev_ops;
+ if (unlikely(!ops->ndo_get_peer_dev ||
+ !skb_at_tc_ingress(skb)))
+ goto out_drop;
+ dev = ops->ndo_get_peer_dev(dev);
+ if (unlikely(!dev ||
+ !is_skb_forwardable(dev, skb) ||
+ net_eq(net, dev_net(dev))))
+ goto out_drop;
+ skb->dev = dev;
+ return -EAGAIN;
+ }
return flags & BPF_F_NEIGH ?
__bpf_redirect_neigh(skb, dev) :
__bpf_redirect(skb, dev, flags);
+out_drop:
+ kfree_skb(skb);
+ return -EINVAL;
}
BPF_CALL_2(bpf_redirect, u32, ifindex, u64, flags)
@@ -2466,6 +2483,27 @@ static const struct bpf_func_proto bpf_redirect_proto = {
.arg2_type = ARG_ANYTHING,
};
+BPF_CALL_2(bpf_redirect_peer, u32, ifindex, u64, flags)
+{
+ struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info);
+
+ if (unlikely(flags))
+ return TC_ACT_SHOT;
+
+ ri->flags = BPF_F_PEER;
+ ri->tgt_index = ifindex;
+
+ return TC_ACT_REDIRECT;
+}
+
+static const struct bpf_func_proto bpf_redirect_peer_proto = {
+ .func = bpf_redirect_peer,
+ .gpl_only = false,
+ .ret_type = RET_INTEGER,
+ .arg1_type = ARG_ANYTHING,
+ .arg2_type = ARG_ANYTHING,
+};
+
BPF_CALL_2(bpf_redirect_neigh, u32, ifindex, u64, flags)
{
struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info);
@@ -7053,6 +7091,8 @@ tc_cls_act_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
return &bpf_redirect_proto;
case BPF_FUNC_redirect_neigh:
return &bpf_redirect_neigh_proto;
+ case BPF_FUNC_redirect_peer:
+ return &bpf_redirect_peer_proto;
case BPF_FUNC_get_route_realm:
return &bpf_get_route_realm_proto;
case BPF_FUNC_get_hash_recalc:
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 4272cc53d478..b97bc5abb3b8 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -3719,6 +3719,22 @@ union bpf_attr {
* never return NULL.
* Return
* A pointer pointing to the kernel percpu variable on this cpu.
+ *
+ * long bpf_redirect_peer(u32 ifindex, u64 flags)
+ * Description
+ * Redirect the packet to another net device of index *ifindex*.
+ * This helper is somewhat similar to **bpf_redirect**\ (), except
+ * that the redirection happens to the *ifindex*' peer device and
+ * the netns switch takes place from ingress to ingress without
+ * going through the CPU's backlog queue.
+ *
+ * The *flags* argument is reserved and must be 0. The helper is
+ * currently only supported for tc BPF program types at the ingress
+ * hook and for veth device types. The peer device must reside in a
+ * different network namespace.
+ * Return
+ * The helper returns **TC_ACT_REDIRECT** on success or
+ * **TC_ACT_SHOT** on error.
*/
#define __BPF_FUNC_MAPPER(FN) \
FN(unspec), \
@@ -3876,6 +3892,7 @@ union bpf_attr {
FN(redirect_neigh), \
FN(bpf_per_cpu_ptr), \
FN(bpf_this_cpu_ptr), \
+ FN(redirect_peer), \
/* */
/* integer value in 'imm' field of BPF_CALL instruction selects which helper