!1520 enable bonding XDP

Merge Pull Request from: @ci-robot 
 
PR sync from: Zhengchao Shao <shaozhengchao@huawei.com>
https://mailweb.openeuler.org/hyperkitty/list/kernel@openeuler.org/message/2ZEFKDERW5AM7E6QSKS2G7GLFUFEZXLL/ 
Currently, the 10G 82599 network adapter is used for the test on the
Intel(R) Xeon(R) Gold 6138 CPU @ 2.00 GHz platform. The peer end uses
the pktgen of the dpdk to send 64 bytes packets. The test performance
is as follows:

 without patch (1 dev):
   XDP_DROP:              1.00%      14.69Mpps
   XDP_TX:                2.20%      10.70Mpps    10.70Mpps
   XDP_DROP (RSS):        1.90%      10.13Mpps
   XDP_TX (RSS):          6.20%      10.09Mpps    10.09Mpps
 -----------------------
 with patch, bond (1 dev):
   XDP_DROP:              1.00%      14.69Mpps
   XDP_TX:                2.10%       6.84Mpps     6.84Mpps
   XDP_DROP (RSS):        2.00%      10.20pps
   XDP_TX (RSS):          8.40%      10.17Mpps    10.17Mpps
 -----------------------
 with patch, bond (2 devs):
   XDP_DROP:              1.90%      29.3Mpps
   XDP_TX:                4.20%      11.31Mpps    11.31Mpps
   XDP_DROP (RSS):        3.90%      20.40Mpps
   XDP_TX (RSS):         16.80%      18.55Mpps    18.55Mpps
 --------------------------------------------------------------

Jonathan Toppins (1):
  bonding: fix NULL deref in bond_rr_gen_slave_id

Jussi Maki (5):
  net, bonding: Refactor bond_xmit_hash for use with xdp_buff
  net, core: Add support for XDP redirection to slave device
  net, bonding: Add XDP support to the bonding driver
  bonding: Fix negative jump label count on nested bonding
  net: bonding: Use per-cpu rr_tx_counter

Moshe Tal (1):
  bonding: Fix extraction of ports from the packet headers

Zhengchao Shao (1):
  net: fix kabi change in struct net_device_ops


-- 
2.34.1
 
https://gitee.com/openeuler/kernel/issues/I7NDRB 
 
Link:https://gitee.com/openeuler/kernel/pulls/1520 

Reviewed-by: Yue Haibing <yuehaibing@huawei.com> 
Signed-off-by: Jialin Zhang <zhangjialin11@huawei.com> 

drivers/net/bonding/bond_main.c

@@ -302,6 +302,19 @@ netdev_tx_t bond_dev_queue_xmit(struct bonding *bond, struct sk_buff *skb,
 	return dev_queue_xmit(skb);
 }
 
+static bool bond_xdp_check(struct bonding *bond)
+{
+	switch (BOND_MODE(bond)) {
+	case BOND_MODE_ROUNDROBIN:
+	case BOND_MODE_ACTIVEBACKUP:
+	case BOND_MODE_8023AD:
+	case BOND_MODE_XOR:
+		return true;
+	default:
+		return false;
+	}
+}
+
 /*---------------------------------- VLAN -----------------------------------*/
 
 /* In the following 2 functions, bond_vlan_rx_add_vid and bond_vlan_rx_kill_vid,
@@ -2118,6 +2131,41 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev,
 		bond_update_slave_arr(bond, NULL);
 
 
+	if (!slave_dev->netdev_ops->ndo_bpf ||
+	    !slave_dev->netdev_ops->ndo_xdp_xmit) {
+		if (bond->xdp_prog) {
+			NL_SET_ERR_MSG(extack, "Slave does not support XDP");
+			slave_err(bond_dev, slave_dev, "Slave does not support XDP\n");
+			res = -EOPNOTSUPP;
+			goto err_sysfs_del;
+		}
+	} else if (bond->xdp_prog) {
+		struct netdev_bpf xdp = {
+			.command = XDP_SETUP_PROG,
+			.flags   = 0,
+			.prog    = bond->xdp_prog,
+			.extack  = extack,
+		};
+
+		if (dev_xdp_prog_count(slave_dev) > 0) {
+			NL_SET_ERR_MSG(extack,
+				       "Slave has XDP program loaded, please unload before enslaving");
+			slave_err(bond_dev, slave_dev,
+				  "Slave has XDP program loaded, please unload before enslaving\n");
+			res = -EOPNOTSUPP;
+			goto err_sysfs_del;
+		}
+
+		res = slave_dev->netdev_ops->ndo_bpf(slave_dev, &xdp);
+		if (res < 0) {
+			/* ndo_bpf() sets extack error message */
+			slave_dbg(bond_dev, slave_dev, "Error %d calling ndo_bpf\n", res);
+			goto err_sysfs_del;
+		}
+		if (bond->xdp_prog)
+			bpf_prog_inc(bond->xdp_prog);
+	}
+
 	slave_info(bond_dev, slave_dev, "Enslaving as %s interface with %s link\n",
 		   bond_is_active_slave(new_slave) ? "an active" : "a backup",
 		   new_slave->link != BOND_LINK_DOWN ? "an up" : "a down");
@@ -2235,6 +2283,17 @@ static int __bond_release_one(struct net_device *bond_dev,
 	/* recompute stats just before removing the slave */
 	bond_get_stats(bond->dev, &bond->bond_stats);
 
+	if (bond->xdp_prog) {
+		struct netdev_bpf xdp = {
+			.command = XDP_SETUP_PROG,
+			.flags   = 0,
+			.prog	 = NULL,
+			.extack  = NULL,
+		};
+		if (slave_dev->netdev_ops->ndo_bpf(slave_dev, &xdp))
+			slave_warn(bond_dev, slave_dev, "failed to unload XDP program\n");
+	}
+
 	/* unregister rx_handler early so bond_handle_frame wouldn't be called
 	 * for this slave anymore.
 	 */
@@ -3610,66 +3669,84 @@ static struct notifier_block bond_netdev_notifier = {
 };
 
 /*---------------------------- Hashing Policies -----------------------------*/
+/* Helper to access data in a packet, with or without a backing skb.
+ * If skb is given the data is linearized if necessary via pskb_may_pull.
+ */
+static inline void *bond_pull_data(struct sk_buff *skb,
+				   void *data, int hlen, int n)
+{
+	if (likely(n <= hlen))
+		return data;
+	else if (skb && likely(pskb_may_pull(skb, n)))
+		return skb->head;
+
+	return NULL;
+}
 
 /* L2 hash helper */
-static inline u32 bond_eth_hash(struct sk_buff *skb)
+static inline u32 bond_eth_hash(struct sk_buff *skb, void *data, int mhoff, int hlen)
 {
-	struct ethhdr *ep, hdr_tmp;
+	struct ethhdr *ep;
 
-	ep = skb_header_pointer(skb, 0, sizeof(hdr_tmp), &hdr_tmp);
-	if (ep)
-		return ep->h_dest[5] ^ ep->h_source[5] ^ ep->h_proto;
-	return 0;
+	data = bond_pull_data(skb, data, hlen, mhoff + sizeof(struct ethhdr));
+	if (!data)
+		return 0;
+
+	ep = (struct ethhdr *)(data + mhoff);
+	return ep->h_dest[5] ^ ep->h_source[5] ^ be16_to_cpu(ep->h_proto);
 }
 
-static bool bond_flow_ip(struct sk_buff *skb, struct flow_keys *fk,
-			 int *noff, int *proto, bool l34)
+static bool bond_flow_ip(struct sk_buff *skb, struct flow_keys *fk, void *data,
+			 int hlen, __be16 l2_proto, int *nhoff, int *ip_proto, bool l34)
 {
 	const struct ipv6hdr *iph6;
 	const struct iphdr *iph;
 
-	if (skb->protocol == htons(ETH_P_IP)) {
-		if (unlikely(!pskb_may_pull(skb, *noff + sizeof(*iph))))
+	if (l2_proto == htons(ETH_P_IP)) {
+		data = bond_pull_data(skb, data, hlen, *nhoff + sizeof(*iph));
+		if (!data)
 			return false;
-		iph = (const struct iphdr *)(skb->data + *noff);
+
+		iph = (const struct iphdr *)(data + *nhoff);
 		iph_to_flow_copy_v4addrs(fk, iph);
-		*noff += iph->ihl << 2;
+		*nhoff += iph->ihl << 2;
 		if (!ip_is_fragment(iph))
-			*proto = iph->protocol;
-	} else if (skb->protocol == htons(ETH_P_IPV6)) {
-		if (unlikely(!pskb_may_pull(skb, *noff + sizeof(*iph6))))
+			*ip_proto = iph->protocol;
+	} else if (l2_proto == htons(ETH_P_IPV6)) {
+		data = bond_pull_data(skb, data, hlen, *nhoff + sizeof(*iph6));
+		if (!data)
 			return false;
-		iph6 = (const struct ipv6hdr *)(skb->data + *noff);
+
+		iph6 = (const struct ipv6hdr *)(data + *nhoff);
 		iph_to_flow_copy_v6addrs(fk, iph6);
-		*noff += sizeof(*iph6);
-		*proto = iph6->nexthdr;
+		*nhoff += sizeof(*iph6);
+		*ip_proto = iph6->nexthdr;
 	} else {
 		return false;
 	}
 
-	if (l34 && *proto >= 0)
-		fk->ports.ports = skb_flow_get_ports(skb, *noff, *proto);
+	if (l34 && *ip_proto >= 0)
+		fk->ports.ports = __skb_flow_get_ports(skb, *nhoff, *ip_proto, data, hlen);
 
 	return true;
 }
 
 /* Extract the appropriate headers based on bond's xmit policy */
-static bool bond_flow_dissect(struct bonding *bond, struct sk_buff *skb,
-			      struct flow_keys *fk)
+static bool bond_flow_dissect(struct bonding *bond, struct sk_buff *skb, void *data,
+			      __be16 l2_proto, int nhoff, int hlen, struct flow_keys *fk)
 {
 	bool l34 = bond->params.xmit_policy == BOND_XMIT_POLICY_LAYER34;
-	int noff, proto = -1;
+	int ip_proto = -1;
 
 	if (bond->params.xmit_policy > BOND_XMIT_POLICY_LAYER23) {
 		memset(fk, 0, sizeof(*fk));
 		return __skb_flow_dissect(NULL, skb, &flow_keys_bonding,
-					  fk, NULL, 0, 0, 0, 0);
+					  fk, data, l2_proto, nhoff, hlen, 0);
 	}
 
 	fk->ports.ports = 0;
 	memset(&fk->icmp, 0, sizeof(fk->icmp));
-	noff = skb_network_offset(skb);
-	if (!bond_flow_ip(skb, fk, &noff, &proto, l34))
+	if (!bond_flow_ip(skb, fk, data, hlen, l2_proto, &nhoff, &ip_proto, l34))
 		return false;
 
 	/* ICMP error packets contains at least 8 bytes of the header
@@ -3677,51 +3754,41 @@ static bool bond_flow_dissect(struct bonding *bond, struct sk_buff *skb,
 	 * to correlate ICMP error packets within the same flow which
 	 * generated the error.
 	 */
-	if (proto == IPPROTO_ICMP || proto == IPPROTO_ICMPV6) {
-		skb_flow_get_icmp_tci(skb, &fk->icmp, skb->data,
-				      skb_transport_offset(skb),
-				      skb_headlen(skb));
-		if (proto == IPPROTO_ICMP) {
+	if (ip_proto == IPPROTO_ICMP || ip_proto == IPPROTO_ICMPV6) {
+		skb_flow_get_icmp_tci(skb, &fk->icmp, data, nhoff, hlen);
+		if (ip_proto == IPPROTO_ICMP) {
 			if (!icmp_is_err(fk->icmp.type))
 				return true;
 
-			noff += sizeof(struct icmphdr);
-		} else if (proto == IPPROTO_ICMPV6) {
+			nhoff += sizeof(struct icmphdr);
+		} else if (ip_proto == IPPROTO_ICMPV6) {
 			if (!icmpv6_is_err(fk->icmp.type))
 				return true;
 
-			noff += sizeof(struct icmp6hdr);
+			nhoff += sizeof(struct icmp6hdr);
 		}
-		return bond_flow_ip(skb, fk, &noff, &proto, l34);
+		return bond_flow_ip(skb, fk, data, hlen, l2_proto, &nhoff, &ip_proto, l34);
 	}
 
 	return true;
 }
-
-/**
- * bond_xmit_hash - generate a hash value based on the xmit policy
- * @bond: bonding device
- * @skb: buffer to use for headers
- *
- * This function will extract the necessary headers from the skb buffer and use
- * them to generate a hash based on the xmit_policy set in the bonding device
+/* Generate hash based on xmit policy. If @skb is given it is used to linearize
+ * the data as required, but this function can be used without it if the data is
+ * known to be linear (e.g. with xdp_buff).
  */
-u32 bond_xmit_hash(struct bonding *bond, struct sk_buff *skb)
+static u32 __bond_xmit_hash(struct bonding *bond, struct sk_buff *skb, void *data,
+			    __be16 l2_proto, int mhoff, int nhoff, int hlen)
 {
 	struct flow_keys flow;
 	u32 hash;
 
-	if (bond->params.xmit_policy == BOND_XMIT_POLICY_ENCAP34 &&
-	    skb->l4_hash)
-		return skb->hash;
-
 	if (bond->params.xmit_policy == BOND_XMIT_POLICY_LAYER2 ||
-	    !bond_flow_dissect(bond, skb, &flow))
-		return bond_eth_hash(skb);
+	    !bond_flow_dissect(bond, skb, data, l2_proto, nhoff, hlen, &flow))
+		return bond_eth_hash(skb, data, mhoff, hlen);
 
 	if (bond->params.xmit_policy == BOND_XMIT_POLICY_LAYER23 ||
 	    bond->params.xmit_policy == BOND_XMIT_POLICY_ENCAP23) {
-		hash = bond_eth_hash(skb);
+		hash = bond_eth_hash(skb, data, mhoff, hlen);
 	} else {
 		if (flow.icmp.id)
 			memcpy(&hash, &flow.icmp, sizeof(hash));
@@ -3736,6 +3803,45 @@ u32 bond_xmit_hash(struct bonding *bond, struct sk_buff *skb)
 	return hash >> 1;
 }
 
+/**
+ * bond_xmit_hash - generate a hash value based on the xmit policy
+ * @bond: bonding device
+ * @skb: buffer to use for headers
+ *
+ * This function will extract the necessary headers from the skb buffer and use
+ * them to generate a hash based on the xmit_policy set in the bonding device
+ */
+u32 bond_xmit_hash(struct bonding *bond, struct sk_buff *skb)
+{
+	if (bond->params.xmit_policy == BOND_XMIT_POLICY_ENCAP34 &&
+	    skb->l4_hash)
+		return skb->hash;
+
+	return __bond_xmit_hash(bond, skb, skb->data, skb->protocol,
+				skb_mac_offset(skb), skb_network_offset(skb),
+				skb_headlen(skb));
+}
+
+/**
+ * bond_xmit_hash_xdp - generate a hash value based on the xmit policy
+ * @bond: bonding device
+ * @xdp: buffer to use for headers
+ *
+ * The XDP variant of bond_xmit_hash.
+ */
+static u32 bond_xmit_hash_xdp(struct bonding *bond, struct xdp_buff *xdp)
+{
+	struct ethhdr *eth;
+
+	if (xdp->data + sizeof(struct ethhdr) > xdp->data_end)
+		return 0;
+
+	eth = (struct ethhdr *)xdp->data;
+
+	return __bond_xmit_hash(bond, NULL, xdp->data, eth->h_proto, 0,
+				sizeof(struct ethhdr), xdp->data_end - xdp->data);
+}
+
 /*-------------------------- Device entry points ----------------------------*/
 
 void bond_work_init_all(struct bonding *bond)
@@ -3765,6 +3871,12 @@ static int bond_open(struct net_device *bond_dev)
 	struct list_head *iter;
 	struct slave *slave;
 
+	if (BOND_MODE(bond) == BOND_MODE_ROUNDROBIN && !bond->rr_tx_counter) {
+		bond->rr_tx_counter = alloc_percpu(u32);
+		if (!bond->rr_tx_counter)
+			return -ENOMEM;
+	}
+
 	/* reset slave->backup and slave->inactive */
 	if (bond_has_slaves(bond)) {
 		bond_for_each_slave(bond, slave, iter) {
@@ -4317,16 +4429,16 @@ static u32 bond_rr_gen_slave_id(struct bonding *bond)
 		slave_id = prandom_u32();
 		break;
 	case 1:
-		slave_id = bond->rr_tx_counter;
+		slave_id = this_cpu_inc_return(*bond->rr_tx_counter);
 		break;
 	default:
 		reciprocal_packets_per_slave =
 			bond->params.reciprocal_packets_per_slave;
-		slave_id = reciprocal_divide(bond->rr_tx_counter,
+		slave_id = this_cpu_inc_return(*bond->rr_tx_counter);
+		slave_id = reciprocal_divide(slave_id,
 					     reciprocal_packets_per_slave);
 		break;
 	}
-	bond->rr_tx_counter++;
 
 	return slave_id;
 }
@@ -4369,6 +4481,47 @@ static struct slave *bond_xmit_roundrobin_slave_get(struct bonding *bond,
 	return NULL;
 }
 
+static struct slave *bond_xdp_xmit_roundrobin_slave_get(struct bonding *bond,
+							struct xdp_buff *xdp)
+{
+	struct slave *slave;
+	int slave_cnt;
+	u32 slave_id;
+	const struct ethhdr *eth;
+	void *data = xdp->data;
+
+	if (data + sizeof(struct ethhdr) > xdp->data_end)
+		goto non_igmp;
+
+	eth = (struct ethhdr *)data;
+	data += sizeof(struct ethhdr);
+
+	/* See comment on IGMP in bond_xmit_roundrobin_slave_get() */
+	if (eth->h_proto == htons(ETH_P_IP)) {
+		const struct iphdr *iph;
+
+		if (data + sizeof(struct iphdr) > xdp->data_end)
+			goto non_igmp;
+
+		iph = (struct iphdr *)data;
+
+		if (iph->protocol == IPPROTO_IGMP) {
+			slave = rcu_dereference(bond->curr_active_slave);
+			if (slave)
+				return slave;
+			return bond_get_slave_by_id(bond, 0);
+		}
+	}
+
+non_igmp:
+	slave_cnt = READ_ONCE(bond->slave_cnt);
+	if (likely(slave_cnt)) {
+		slave_id = bond_rr_gen_slave_id(bond) % slave_cnt;
+		return bond_get_slave_by_id(bond, slave_id);
+	}
+	return NULL;
+}
+
 static netdev_tx_t bond_xmit_roundrobin(struct sk_buff *skb,
 					struct net_device *bond_dev)
 {
@@ -4382,8 +4535,7 @@ static netdev_tx_t bond_xmit_roundrobin(struct sk_buff *skb,
 	return bond_tx_drop(bond_dev, skb);
 }
 
-static struct slave *bond_xmit_activebackup_slave_get(struct bonding *bond,
-						      struct sk_buff *skb)
+static struct slave *bond_xmit_activebackup_slave_get(struct bonding *bond)
 {
 	return rcu_dereference(bond->curr_active_slave);
 }
@@ -4397,7 +4549,7 @@ static netdev_tx_t bond_xmit_activebackup(struct sk_buff *skb,
 	struct bonding *bond = netdev_priv(bond_dev);
 	struct slave *slave;
 
-	slave = bond_xmit_activebackup_slave_get(bond, skb);
+	slave = bond_xmit_activebackup_slave_get(bond);
 	if (slave)
 		return bond_dev_queue_xmit(bond, skb, slave->dev);
 
@@ -4618,6 +4770,22 @@ static struct slave *bond_xmit_3ad_xor_slave_get(struct bonding *bond,
 	return slave;
 }
 
+static struct slave *bond_xdp_xmit_3ad_xor_slave_get(struct bonding *bond,
+						     struct xdp_buff *xdp)
+{
+	struct bond_up_slave *slaves;
+	unsigned int count;
+	u32 hash;
+
+	hash = bond_xmit_hash_xdp(bond, xdp);
+	slaves = rcu_dereference(bond->usable_slaves);
+	count = slaves ? READ_ONCE(slaves->count) : 0;
+	if (unlikely(!count))
+		return NULL;
+
+	return slaves->arr[hash % count];
+}
+
 /* Use this Xmit function for 3AD as well as XOR modes. The current
  * usable slave array is formed in the control path. The xmit function
  * just calculates hash and sends the packet out.
@@ -4746,7 +4914,7 @@ static struct net_device *bond_xmit_get_slave(struct net_device *master_dev,
 		slave = bond_xmit_roundrobin_slave_get(bond, skb);
 		break;
 	case BOND_MODE_ACTIVEBACKUP:
-		slave = bond_xmit_activebackup_slave_get(bond, skb);
+		slave = bond_xmit_activebackup_slave_get(bond);
 		break;
 	case BOND_MODE_8023AD:
 	case BOND_MODE_XOR:
@@ -4826,6 +4994,173 @@ static netdev_tx_t bond_start_xmit(struct sk_buff *skb, struct net_device *dev)
 	return ret;
 }
 
+static struct net_device *
+bond_xdp_get_xmit_slave(struct net_device *bond_dev, struct xdp_buff *xdp)
+{
+	struct bonding *bond = netdev_priv(bond_dev);
+	struct slave *slave;
+
+	/* Caller needs to hold rcu_read_lock() */
+
+	switch (BOND_MODE(bond)) {
+	case BOND_MODE_ROUNDROBIN:
+		slave = bond_xdp_xmit_roundrobin_slave_get(bond, xdp);
+		break;
+
+	case BOND_MODE_ACTIVEBACKUP:
+		slave = bond_xmit_activebackup_slave_get(bond);
+		break;
+
+	case BOND_MODE_8023AD:
+	case BOND_MODE_XOR:
+		slave = bond_xdp_xmit_3ad_xor_slave_get(bond, xdp);
+		break;
+
+	default:
+		/* Should never happen. Mode guarded by bond_xdp_check() */
+		netdev_err(bond_dev, "Unknown bonding mode %d for xdp xmit\n", BOND_MODE(bond));
+		WARN_ON_ONCE(1);
+		return NULL;
+	}
+
+	if (slave)
+		return slave->dev;
+
+	return NULL;
+}
+
+static int bond_xdp_xmit(struct net_device *bond_dev,
+			 int n, struct xdp_frame **frames, u32 flags)
+{
+	int nxmit, err = -ENXIO;
+
+	rcu_read_lock();
+
+	for (nxmit = 0; nxmit < n; nxmit++) {
+		struct xdp_frame *frame = frames[nxmit];
+		struct xdp_frame *frames1[] = {frame};
+		struct net_device *slave_dev;
+		struct xdp_buff xdp;
+
+		xdp_convert_frame_to_buff(frame, &xdp);
+
+		slave_dev = bond_xdp_get_xmit_slave(bond_dev, &xdp);
+		if (!slave_dev) {
+			err = -ENXIO;
+			break;
+		}
+
+		err = slave_dev->netdev_ops->ndo_xdp_xmit(slave_dev, 1, frames1, flags);
+		if (err < 1)
+			break;
+	}
+
+	rcu_read_unlock();
+
+	/* If error happened on the first frame then we can pass the error up, otherwise
+	 * report the number of frames that were xmitted.
+	 */
+	if (err < 0)
+		return (nxmit == 0 ? err : nxmit);
+
+	return nxmit;
+}
+
+static int bond_xdp_set(struct net_device *dev, struct bpf_prog *prog,
+			struct netlink_ext_ack *extack)
+{
+	struct bonding *bond = netdev_priv(dev);
+	struct list_head *iter;
+	struct slave *slave, *rollback_slave;
+	struct bpf_prog *old_prog;
+	struct netdev_bpf xdp = {
+		.command = XDP_SETUP_PROG,
+		.flags   = 0,
+		.prog    = prog,
+		.extack  = extack,
+	};
+	int err;
+
+	ASSERT_RTNL();
+
+	if (!bond_xdp_check(bond))
+		return -EOPNOTSUPP;
+
+	old_prog = bond->xdp_prog;
+	bond->xdp_prog = prog;
+
+	bond_for_each_slave(bond, slave, iter) {
+		struct net_device *slave_dev = slave->dev;
+
+		if (!slave_dev->netdev_ops->ndo_bpf ||
+		    !slave_dev->netdev_ops->ndo_xdp_xmit) {
+			NL_SET_ERR_MSG(extack, "Slave device does not support XDP");
+			slave_err(dev, slave_dev, "Slave does not support XDP\n");
+			err = -EOPNOTSUPP;
+			goto err;
+		}
+
+		if (dev_xdp_prog_count(slave_dev) > 0) {
+			NL_SET_ERR_MSG(extack,
+				       "Slave has XDP program loaded, please unload before enslaving");
+			slave_err(dev, slave_dev,
+				  "Slave has XDP program loaded, please unload before enslaving\n");
+			err = -EOPNOTSUPP;
+			goto err;
+		}
+
+		err = slave_dev->netdev_ops->ndo_bpf(slave_dev, &xdp);
+		if (err < 0) {
+			/* ndo_bpf() sets extack error message */
+			slave_err(dev, slave_dev, "Error %d calling ndo_bpf\n", err);
+			goto err;
+		}
+		if (prog)
+			bpf_prog_inc(prog);
+	}
+
+	if (prog) {
+		static_branch_inc(&bpf_master_redirect_enabled_key);
+	} else if (old_prog) {
+		bpf_prog_put(old_prog);
+		static_branch_dec(&bpf_master_redirect_enabled_key);
+	}
+
+	return 0;
+
+err:
+	/* unwind the program changes */
+	bond->xdp_prog = old_prog;
+	xdp.prog = old_prog;
+	xdp.extack = NULL; /* do not overwrite original error */
+
+	bond_for_each_slave(bond, rollback_slave, iter) {
+		struct net_device *slave_dev = rollback_slave->dev;
+		int err_unwind;
+
+		if (slave == rollback_slave)
+			break;
+
+		err_unwind = slave_dev->netdev_ops->ndo_bpf(slave_dev, &xdp);
+		if (err_unwind < 0)
+			slave_err(dev, slave_dev,
+				  "Error %d when unwinding XDP program change\n", err_unwind);
+		else if (xdp.prog)
+			bpf_prog_inc(xdp.prog);
+	}
+	return err;
+}
+
+static int bond_xdp(struct net_device *dev, struct netdev_bpf *xdp)
+{
+	switch (xdp->command) {
+	case XDP_SETUP_PROG:
+		return bond_xdp_set(dev, xdp->prog, xdp->extack);
+	default:
+		return -EINVAL;
+	}
+}
+
 static u32 bond_mode_bcast_speed(struct slave *slave, u32 speed)
 {
 	if (speed == 0 || speed == SPEED_UNKNOWN)
@@ -4911,6 +5246,9 @@ static const struct net_device_ops bond_netdev_ops = {
 	.ndo_fix_features	= bond_fix_features,
 	.ndo_features_check	= passthru_features_check,
 	.ndo_get_xmit_slave	= bond_xmit_get_slave,
+	.ndo_bpf		= bond_xdp,
+	.ndo_xdp_xmit		= bond_xdp_xmit,
+	.ndo_xdp_get_xmit_slave	= bond_xdp_get_xmit_slave,
 };
 
 static const struct device_type bond_type = {
@@ -4922,6 +5260,9 @@ static void bond_destructor(struct net_device *bond_dev)
 	struct bonding *bond = netdev_priv(bond_dev);
 	if (bond->wq)
 		destroy_workqueue(bond->wq);
+
+	if (bond->rr_tx_counter)
+		free_percpu(bond->rr_tx_counter);
 }
 
 void bond_setup(struct net_device *bond_dev)

include/linux/filter.h

@@ -747,6 +747,10 @@ 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)
 {
@@ -756,7 +760,14 @@ static __always_inline u32 bpf_prog_run_xdp(const struct bpf_prog *prog,
 	 * already takes rcu_read_lock() when fetching the program, so
 	 * it's not necessary here anymore.
 	 */
-	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

@@ -1301,6 +1301,9 @@ 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
@@ -1526,7 +1529,8 @@ struct net_device_ops {
 						  struct ip_tunnel_parm *p, int cmd);
 	struct net_device *	(*ndo_get_peer_dev)(struct net_device *dev);
 
-	KABI_RESERVE(1)
+	KABI_USE(1, struct net_device *(*ndo_xdp_get_xmit_slave)(struct net_device *dev,
+								 struct xdp_buff *xdp))
 	KABI_RESERVE(2)
 	KABI_RESERVE(3)
 	KABI_RESERVE(4)
@@ -3994,6 +3998,7 @@ 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 xdp_umem_query(struct net_device *dev, u16 queue_id);

include/net/bonding.h

@@ -237,7 +237,7 @@ struct bonding {
 	char     proc_file_name[IFNAMSIZ];
 #endif /* CONFIG_PROC_FS */
 	struct   list_head bond_list;
-	u32      rr_tx_counter;
+	u32 __percpu *rr_tx_counter;
 	struct   ad_bond_info ad_info;
 	struct   alb_bond_info alb_info;
 	struct   bond_params params;
@@ -258,6 +258,7 @@ struct bonding {
 	/* protecting ipsec_list */
 	spinlock_t ipsec_lock;
 #endif /* CONFIG_XFRM_OFFLOAD */
+	struct bpf_prog *xdp_prog;
 };
 
 #define bond_slave_get_rcu(dev) \

net/core/dev.c

@@ -9037,7 +9037,7 @@ 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;
@@ -9047,6 +9047,7 @@ 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)
 {
@@ -9140,6 +9141,8 @@ 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;
@@ -9178,6 +9181,14 @@ 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

@@ -3990,6 +3990,31 @@ 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; TODO: how to usage?
+		//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)
 {