Merge https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next

Daniel Borkmann says:

====================
bpf-next 2021-08-10

We've added 31 non-merge commits during the last 8 day(s) which contain
a total of 28 files changed, 3644 insertions(+), 519 deletions(-).

1) Native XDP support for bonding driver & related BPF selftests, from Jussi Maki.

2) Large batch of new BPF JIT tests for test_bpf.ko that came out as a result from
   32-bit MIPS JIT development, from Johan Almbladh.

3) Rewrite of netcnt BPF selftest and merge into test_progs, from Stanislav Fomichev.

4) Fix XDP bpf_prog_test_run infra after net to net-next merge, from Andrii Nakryiko.

5) Follow-up fix in unix_bpf_update_proto() to enforce socket type, from Cong Wang.

6) Fix bpf-iter-tcp4 selftest to print the correct dest IP, from Jose Blanquicet.

7) Various misc BPF XDP sample improvements, from Niklas Söderlund, Matthew Cover,
   and Muhammad Falak R Wani.

* https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next: (31 commits)
  bpf, tests: Add tail call test suite
  bpf, tests: Add tests for BPF_CMPXCHG
  bpf, tests: Add tests for atomic operations
  bpf, tests: Add test for 32-bit context pointer argument passing
  bpf, tests: Add branch conversion JIT test
  bpf, tests: Add word-order tests for load/store of double words
  bpf, tests: Add tests for ALU operations implemented with function calls
  bpf, tests: Add more ALU64 BPF_MUL tests
  bpf, tests: Add more BPF_LSH/RSH/ARSH tests for ALU64
  bpf, tests: Add more ALU32 tests for BPF_LSH/RSH/ARSH
  bpf, tests: Add more tests of ALU32 and ALU64 bitwise operations
  bpf, tests: Fix typos in test case descriptions
  bpf, tests: Add BPF_MOV tests for zero and sign extension
  bpf, tests: Add BPF_JMP32 test cases
  samples, bpf: Add an explict comment to handle nested vlan tagging.
  selftests/bpf: Add tests for XDP bonding
  selftests/bpf: Fix xdp_tx.c prog section name
  net, core: Allow netdev_lower_get_next_private_rcu in bh context
  bpf, devmap: Exclude XDP broadcast to master device
  net, bonding: Add XDP support to the bonding driver
  ...
====================

Link: https://lore.kernel.org/r/20210810130038.16927-1-daniel@iogearbox.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

28 files changed, 3431 insertions, 306 deletions

diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 3ba5f4871162..365953e8013e 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -317,6 +317,19 @@ bool bond_sk_check(struct bonding *bond)
 	}
 }
 
+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,
@@ -2133,6 +2146,41 @@ 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 {
+		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");
@@ -2252,6 +2300,17 @@ 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.
 	 */
@@ -3614,55 +3673,80 @@ 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 const void *bond_pull_data(struct sk_buff *skb,
+					 const 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, const 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, const 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;
 }
 
-static u32 bond_vlan_srcmac_hash(struct sk_buff *skb)
+static u32 bond_vlan_srcmac_hash(struct sk_buff *skb, const void *data, int mhoff, int hlen)
 {
-	struct ethhdr *mac_hdr = (struct ethhdr *)skb_mac_header(skb);
+	struct ethhdr *mac_hdr;
 	u32 srcmac_vendor = 0, srcmac_dev = 0;
 	u16 vlan;
 	int i;
 
+	data = bond_pull_data(skb, data, hlen, mhoff + sizeof(struct ethhdr));
+	if (!data)
+		return 0;
+	mac_hdr = (struct ethhdr *)(data + mhoff);
+
 	for (i = 0; i < 3; i++)
 		srcmac_vendor = (srcmac_vendor << 8) | mac_hdr->h_source[i];
 
@@ -3678,26 +3762,25 @@ static u32 bond_vlan_srcmac_hash(struct sk_buff *skb)
 }
 
 /* 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, const 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;
 
 	switch (bond->params.xmit_policy) {
 	case BOND_XMIT_POLICY_ENCAP23:
 	case BOND_XMIT_POLICY_ENCAP34:
 		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);
 	default:
 		break;
 	}
 
 	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
@@ -3705,22 +3788,20 @@ 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;
@@ -3736,33 +3817,26 @@ static u32 bond_ip_hash(u32 hash, struct flow_keys *flow)
 	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
+/* 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, const 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_VLAN_SRCMAC)
-		return bond_vlan_srcmac_hash(skb);
+		return bond_vlan_srcmac_hash(skb, data, mhoff, hlen);
 
 	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));
@@ -3773,6 +3847,45 @@ u32 bond_xmit_hash(struct bonding *bond, struct sk_buff *skb)
 	return bond_ip_hash(hash, &flow);
 }
 
+/**
+ * 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->head, skb->protocol,
+				skb->mac_header, skb->network_header,
+				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)
@@ -4421,6 +4534,47 @@ non_igmp:
 	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)
 {
@@ -4434,8 +4588,7 @@ 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);
 }
@@ -4449,7 +4602,7 @@ 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);
 
@@ -4637,6 +4790,22 @@ 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.
@@ -4747,7 +4916,7 @@ 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:
@@ -4921,6 +5090,174 @@ 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 (old_prog)
+		bpf_prog_put(old_prog);
+
+	if (prog)
+		static_branch_inc(&bpf_master_redirect_enabled_key);
+	else
+		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)
@@ -5009,6 +5346,9 @@ static const struct net_device_ops bond_netdev_ops = {
 	.ndo_features_check	= passthru_features_check,
 	.ndo_get_xmit_slave	= bond_xmit_get_slave,
 	.ndo_sk_get_lower_dev	= bond_sk_get_lower_dev,
+	.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 = {
diff --git a/include/linux/filter.h b/include/linux/filter.h
index ff698c9d1c94..1797e8506929 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -776,6 +776,10 @@ 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)
 {
@@ -783,7 +787,14 @@ static __always_inline u32 bpf_prog_run_xdp(const struct bpf_prog *prog,
 	 * 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);
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 135c943699d0..bd8d5b8e2de3 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -1318,6 +1318,9 @@ 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
@@ -1545,6 +1548,8 @@ 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);
@@ -4076,6 +4081,7 @@ 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);
diff --git a/include/net/bonding.h b/include/net/bonding.h
index 46df47004803..9f3fdc180c6c 100644
--- a/include/net/bonding.h
+++ b/include/net/bonding.h
@@ -259,6 +259,7 @@ struct bonding {
 	/* protecting ipsec_list */
 	spinlock_t ipsec_lock;
 #endif /* CONFIG_XFRM_OFFLOAD */
+	struct bpf_prog *xdp_prog;
 };
 
 #define bond_slave_get_rcu(dev) \
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index b1a5fc04492b..fe807b203a6f 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -1562,7 +1562,7 @@ select_insn:
 
 		if (unlikely(index >= array->map.max_entries))
 			goto out;
-		if (unlikely(tail_call_cnt > MAX_TAIL_CALL_CNT))
+		if (unlikely(tail_call_cnt >= MAX_TAIL_CALL_CNT))
 			goto out;
 
 		tail_call_cnt++;
diff --git a/kernel/bpf/devmap.c b/kernel/bpf/devmap.c
index 542e94fa30b4..f02d04540c0c 100644
--- a/kernel/bpf/devmap.c
+++ b/kernel/bpf/devmap.c
@@ -534,10 +534,9 @@ int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_buff *xdp,
 	return __xdp_enqueue(dev, xdp, dev_rx, dst->xdp_prog);
 }
 
-static bool is_valid_dst(struct bpf_dtab_netdev *obj, struct xdp_buff *xdp,
-			 int exclude_ifindex)
+static bool is_valid_dst(struct bpf_dtab_netdev *obj, struct xdp_buff *xdp)
 {
-	if (!obj || obj->dev->ifindex == exclude_ifindex ||
+	if (!obj ||
 	    !obj->dev->netdev_ops->ndo_xdp_xmit)
 		return false;
 
@@ -562,17 +561,48 @@ static int dev_map_enqueue_clone(struct bpf_dtab_netdev *obj,
 	return 0;
 }
 
+static inline bool is_ifindex_excluded(int *excluded, int num_excluded, int ifindex)
+{
+	while (num_excluded--) {
+		if (ifindex == excluded[num_excluded])
+			return true;
+	}
+	return false;
+}
+
+/* Get ifindex of each upper device. 'indexes' must be able to hold at
+ * least MAX_NEST_DEV elements.
+ * Returns the number of ifindexes added.
+ */
+static int get_upper_ifindexes(struct net_device *dev, int *indexes)
+{
+	struct net_device *upper;
+	struct list_head *iter;
+	int n = 0;
+
+	netdev_for_each_upper_dev_rcu(dev, upper, iter) {
+		indexes[n++] = upper->ifindex;
+	}
+	return n;
+}
+
 int dev_map_enqueue_multi(struct xdp_buff *xdp, struct net_device *dev_rx,
 			  struct bpf_map *map, bool exclude_ingress)
 {
 	struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map);
-	int exclude_ifindex = exclude_ingress ? dev_rx->ifindex : 0;
 	struct bpf_dtab_netdev *dst, *last_dst = NULL;
+	int excluded_devices[1+MAX_NEST_DEV];
 	struct hlist_head *head;
 	struct xdp_frame *xdpf;
+	int num_excluded = 0;
 	unsigned int i;
 	int err;
 
+	if (exclude_ingress) {
+		num_excluded = get_upper_ifindexes(dev_rx, excluded_devices);
+		excluded_devices[num_excluded++] = dev_rx->ifindex;
+	}
+
 	xdpf = xdp_convert_buff_to_frame(xdp);
 	if (unlikely(!xdpf))
 		return -EOVERFLOW;
@@ -581,7 +611,10 @@ int dev_map_enqueue_multi(struct xdp_buff *xdp, struct net_device *dev_rx,
 		for (i = 0; i < map->max_entries; i++) {
 			dst = rcu_dereference_check(dtab->netdev_map[i],
 						    rcu_read_lock_bh_held());
-			if (!is_valid_dst(dst, xdp, exclude_ifindex))
+			if (!is_valid_dst(dst, xdp))
+				continue;
+
+			if (is_ifindex_excluded(excluded_devices, num_excluded, dst->dev->ifindex))
 				continue;
 
 			/* we only need n-1 clones; last_dst enqueued below */
@@ -601,7 +634,11 @@ int dev_map_enqueue_multi(struct xdp_buff *xdp, struct net_device *dev_rx,
 			head = dev_map_index_hash(dtab, i);
 			hlist_for_each_entry_rcu(dst, head, index_hlist,
 						 lockdep_is_held(&dtab->index_lock)) {
-				if (!is_valid_dst(dst, xdp, exclude_ifindex))
+				if (!is_valid_dst(dst, xdp))
+					continue;
+
+				if (is_ifindex_excluded(excluded_devices, num_excluded,
+							dst->dev->ifindex))
 					continue;
 
 				/* we only need n-1 clones; last_dst enqueued below */
@@ -675,18 +712,27 @@ int dev_map_redirect_multi(struct net_device *dev, struct sk_buff *skb,
 			   bool exclude_ingress)
 {
 	struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map);
-	int exclude_ifindex = exclude_ingress ? dev->ifindex : 0;
 	struct bpf_dtab_netdev *dst, *last_dst = NULL;
+	int excluded_devices[1+MAX_NEST_DEV];
 	struct hlist_head *head;
 	struct hlist_node *next;
+	int num_excluded = 0;
 	unsigned int i;
 	int err;
 
+	if (exclude_ingress) {
+		num_excluded = get_upper_ifindexes(dev, excluded_devices);
+		excluded_devices[num_excluded++] = dev->ifindex;
+	}
+
 	if (map->map_type == BPF_MAP_TYPE_DEVMAP) {
 		for (i = 0; i < map->max_entries; i++) {
 			dst = rcu_dereference_check(dtab->netdev_map[i],
 						    rcu_read_lock_bh_held());
-			if (!dst || dst->dev->ifindex == exclude_ifindex)
+			if (!dst)
+				continue;
+
+			if (is_ifindex_excluded(excluded_devices, num_excluded, dst->dev->ifindex))
 				continue;
 
 			/* we only need n-1 clones; last_dst enqueued below */
@@ -700,12 +746,17 @@ int dev_map_redirect_multi(struct net_device *dev, struct sk_buff *skb,
 				return err;
 
 			last_dst = dst;
+
 		}
 	} else { /* BPF_MAP_TYPE_DEVMAP_HASH */
 		for (i = 0; i < dtab->n_buckets; i++) {
 			head = dev_map_index_hash(dtab, i);
 			hlist_for_each_entry_safe(dst, next, head, index_hlist) {
-				if (!dst || dst->dev->ifindex == exclude_ifindex)
+				if (!dst)
+					continue;
+
+				if (is_ifindex_excluded(excluded_devices, num_excluded,
+							dst->dev->ifindex))
 					continue;
 
 				/* we only need n-1 clones; last_dst enqueued below */
diff --git a/lib/test_bpf.c b/lib/test_bpf.c
index f6d5d30d01bf..44d8197bbffb 100644
--- a/lib/test_bpf.c
+++ b/lib/test_bpf.c
@@ -461,6 +461,41 @@ static int bpf_fill_stxdw(struct bpf_test *self)
 	return __bpf_fill_stxdw(self, BPF_DW);
 }
 
+static int bpf_fill_long_jmp(struct bpf_test *self)
+{
+	unsigned int len = BPF_MAXINSNS;
+	struct bpf_insn *insn;
+	int i;
+
+	insn = kmalloc_array(len, sizeof(*insn), GFP_KERNEL);
+	if (!insn)
+		return -ENOMEM;
+
+	insn[0] = BPF_ALU64_IMM(BPF_MOV, R0, 1);
+	insn[1] = BPF_JMP_IMM(BPF_JEQ, R0, 1, len - 2 - 1);
+
+	/*
+	 * Fill with a complex 64-bit operation that expands to a lot of
+	 * instructions on 32-bit JITs. The large jump offset can then
+	 * overflow the conditional branch field size, triggering a branch
+	 * conversion mechanism in some JITs.
+	 *
+	 * Note: BPF_MAXINSNS of ALU64 MUL is enough to trigger such branch
+	 * conversion on the 32-bit MIPS JIT. For other JITs, the instruction
+	 * count and/or operation may need to be modified to trigger the
+	 * branch conversion.
+	 */
+	for (i = 2; i < len - 1; i++)
+		insn[i] = BPF_ALU64_IMM(BPF_MUL, R0, (i << 16) + i);
+
+	insn[len - 1] = BPF_EXIT_INSN();
+
+	self->u.ptr.insns = insn;
+	self->u.ptr.len = len;
+
+	return 0;
+}
+
 static struct bpf_test tests[] = {
 	{
 		"TAX",
@@ -1917,6 +1952,163 @@ static struct bpf_test tests[] = {
 		{ { 0, -1 } }
 	},
 	{
+		/*
+		 * Register (non-)clobbering test, in the case where a 32-bit
+		 * JIT implements complex ALU64 operations via function calls.
+		 * If so, the function call must be invisible in the eBPF
+		 * registers. The JIT must then save and restore relevant
+		 * registers during the call. The following tests check that
+		 * the eBPF registers retain their values after such a call.
+		 */
+		"INT: Register clobbering, R1 updated",
+		.u.insns_int = {
+			BPF_ALU32_IMM(BPF_MOV, R0, 0),
+			BPF_ALU32_IMM(BPF_MOV, R1, 123456789),
+			BPF_ALU32_IMM(BPF_MOV, R2, 2),
+			BPF_ALU32_IMM(BPF_MOV, R3, 3),
+			BPF_ALU32_IMM(BPF_MOV, R4, 4),
+			BPF_ALU32_IMM(BPF_MOV, R5, 5),
+			BPF_ALU32_IMM(BPF_MOV, R6, 6),
+			BPF_ALU32_IMM(BPF_MOV, R7, 7),
+			BPF_ALU32_IMM(BPF_MOV, R8, 8),
+			BPF_ALU32_IMM(BPF_MOV, R9, 9),
+			BPF_ALU64_IMM(BPF_DIV, R1, 123456789),
+			BPF_JMP_IMM(BPF_JNE, R0, 0, 10),
+			BPF_JMP_IMM(BPF_JNE, R1, 1, 9),
+			BPF_JMP_IMM(BPF_JNE, R2, 2, 8),
+			BPF_JMP_IMM(BPF_JNE, R3, 3, 7),
+			BPF_JMP_IMM(BPF_JNE, R4, 4, 6),
+			BPF_JMP_IMM(BPF_JNE, R5, 5, 5),
+			BPF_JMP_IMM(BPF_JNE, R6, 6, 4),
+			BPF_JMP_IMM(BPF_JNE, R7, 7, 3),
+			BPF_JMP_IMM(BPF_JNE, R8, 8, 2),
+			BPF_JMP_IMM(BPF_JNE, R9, 9, 1),
+			BPF_ALU32_IMM(BPF_MOV, R0, 1),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 1 } }
+	},
+	{
+		"INT: Register clobbering, R2 updated",
+		.u.insns_int = {
+			BPF_ALU32_IMM(BPF_MOV, R0, 0),
+			BPF_ALU32_IMM(BPF_MOV, R1, 1),
+			BPF_ALU32_IMM(BPF_MOV, R2, 2 * 123456789),
+			BPF_ALU32_IMM(BPF_MOV, R3, 3),
+			BPF_ALU32_IMM(BPF_MOV, R4, 4),
+			BPF_ALU32_IMM(BPF_MOV, R5, 5),
+			BPF_ALU32_IMM(BPF_MOV, R6, 6),
+			BPF_ALU32_IMM(BPF_MOV, R7, 7),
+			BPF_ALU32_IMM(BPF_MOV, R8, 8),
+			BPF_ALU32_IMM(BPF_MOV, R9, 9),
+			BPF_ALU64_IMM(BPF_DIV, R2, 123456789),
+			BPF_JMP_IMM(BPF_JNE, R0, 0, 10),
+			BPF_JMP_IMM(BPF_JNE, R1, 1, 9),
+			BPF_JMP_IMM(BPF_JNE, R2, 2, 8),
+			BPF_JMP_IMM(BPF_JNE, R3, 3, 7),
+			BPF_JMP_IMM(BPF_JNE, R4, 4, 6),
+			BPF_JMP_IMM(BPF_JNE, R5, 5, 5),
+			BPF_JMP_IMM(BPF_JNE, R6, 6, 4),
+			BPF_JMP_IMM(BPF_JNE, R7, 7, 3),
+			BPF_JMP_IMM(BPF_JNE, R8, 8, 2),
+			BPF_JMP_IMM(BPF_JNE, R9, 9, 1),
+			BPF_ALU32_IMM(BPF_MOV, R0, 1),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 1 } }
+	},
+	{
+		/*
+		 * Test 32-bit JITs that implement complex ALU64 operations as
+		 * function calls R0 = f(R1, R2), and must re-arrange operands.
+		 */
+#define NUMER 0xfedcba9876543210ULL
+#define DENOM 0x0123456789abcdefULL
+		"ALU64_DIV X: Operand register permutations",
+		.u.insns_int = {
+			/* R0 / R2 */
+			BPF_LD_IMM64(R0, NUMER),
+			BPF_LD_IMM64(R2, DENOM),
+			BPF_ALU64_REG(BPF_DIV, R0, R2),
+			BPF_JMP_IMM(BPF_JEQ, R0, NUMER / DENOM, 1),
+			BPF_EXIT_INSN(),
+			/* R1 / R0 */
+			BPF_LD_IMM64(R1, NUMER),
+			BPF_LD_IMM64(R0, DENOM),
+			BPF_ALU64_REG(BPF_DIV, R1, R0),
+			BPF_JMP_IMM(BPF_JEQ, R1, NUMER / DENOM, 1),
+			BPF_EXIT_INSN(),
+			/* R0 / R1 */
+			BPF_LD_IMM64(R0, NUMER),
+			BPF_LD_IMM64(R1, DENOM),
+			BPF_ALU64_REG(BPF_DIV, R0, R1),
+			BPF_JMP_IMM(BPF_JEQ, R0, NUMER / DENOM, 1),
+			BPF_EXIT_INSN(),
+			/* R2 / R0 */
+			BPF_LD_IMM64(R2, NUMER),
+			BPF_LD_IMM64(R0, DENOM),
+			BPF_ALU64_REG(BPF_DIV, R2, R0),
+			BPF_JMP_IMM(BPF_JEQ, R2, NUMER / DENOM, 1),
+			BPF_EXIT_INSN(),
+			/* R2 / R1 */
+			BPF_LD_IMM64(R2, NUMER),
+			BPF_LD_IMM64(R1, DENOM),
+			BPF_ALU64_REG(BPF_DIV, R2, R1),
+			BPF_JMP_IMM(BPF_JEQ, R2, NUMER / DENOM, 1),
+			BPF_EXIT_INSN(),
+			/* R1 / R2 */
+			BPF_LD_IMM64(R1, NUMER),
+			BPF_LD_IMM64(R2, DENOM),
+			BPF_ALU64_REG(BPF_DIV, R1, R2),
+			BPF_JMP_IMM(BPF_JEQ, R1, NUMER / DENOM, 1),
+			BPF_EXIT_INSN(),
+			/* R1 / R1 */
+			BPF_LD_IMM64(R1, NUMER),
+			BPF_ALU64_REG(BPF_DIV, R1, R1),
+			BPF_JMP_IMM(BPF_JEQ, R1, 1, 1),
+			BPF_EXIT_INSN(),
+			/* R2 / R2 */
+			BPF_LD_IMM64(R2, DENOM),
+			BPF_ALU64_REG(BPF_DIV, R2, R2),
+			BPF_JMP_IMM(BPF_JEQ, R2, 1, 1),
+			BPF_EXIT_INSN(),
+			/* R3 / R4 */
+			BPF_LD_IMM64(R3, NUMER),
+			BPF_LD_IMM64(R4, DENOM),
+			BPF_ALU64_REG(BPF_DIV, R3, R4),
+			BPF_JMP_IMM(BPF_JEQ, R3, NUMER / DENOM, 1),
+			BPF_EXIT_INSN(),
+			/* Successful return */
+			BPF_LD_IMM64(R0, 1),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 1 } },
+#undef NUMER
+#undef DENOM
+	},
+#ifdef CONFIG_32BIT
+	{
+		"INT: 32-bit context pointer word order and zero-extension",
+		.u.insns_int = {
+			BPF_ALU32_IMM(BPF_MOV, R0, 0),
+			BPF_JMP32_IMM(BPF_JEQ, R1, 0, 3),
+			BPF_ALU64_IMM(BPF_RSH, R1, 32),
+			BPF_JMP32_IMM(BPF_JNE, R1, 0, 1),
+			BPF_ALU32_IMM(BPF_MOV, R0, 1),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 1 } }
+	},
+#endif
+	{
 		"check: missing ret",
 		.u.insns = {
 			BPF_STMT(BPF_LD | BPF_IMM, 1),
@@ -2361,6 +2553,48 @@ static struct bpf_test tests[] = {
 		{ { 0, 0x1 } },
 	},
 	{
+		"ALU_MOV_K: small negative",
+		.u.insns_int = {
+			BPF_ALU32_IMM(BPF_MOV, R0, -123),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, -123 } }
+	},
+	{
+		"ALU_MOV_K: small negative zero extension",
+		.u.insns_int = {
+			BPF_ALU32_IMM(BPF_MOV, R0, -123),
+			BPF_ALU64_IMM(BPF_RSH, R0, 32),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 0 } }
+	},
+	{
+		"ALU_MOV_K: large negative",
+		.u.insns_int = {
+			BPF_ALU32_IMM(BPF_MOV, R0, -123456789),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, -123456789 } }
+	},
+	{
+		"ALU_MOV_K: large negative zero extension",
+		.u.insns_int = {
+			BPF_ALU32_IMM(BPF_MOV, R0, -123456789),
+			BPF_ALU64_IMM(BPF_RSH, R0, 32),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 0 } }
+	},
+	{
 		"ALU64_MOV_K: dst = 2",
 		.u.insns_int = {
 			BPF_ALU64_IMM(BPF_MOV, R0, 2),
@@ -2412,6 +2646,48 @@ static struct bpf_test tests[] = {
 		{ },
 		{ { 0, 0x1 } },
 	},
+	{
+		"ALU64_MOV_K: small negative",
+		.u.insns_int = {
+			BPF_ALU64_IMM(BPF_MOV, R0, -123),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, -123 } }
+	},
+	{
+		"ALU64_MOV_K: small negative sign extension",
+		.u.insns_int = {
+			BPF_ALU64_IMM(BPF_MOV, R0, -123),
+			BPF_ALU64_IMM(BPF_RSH, R0, 32),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 0xffffffff } }
+	},
+	{
+		"ALU64_MOV_K: large negative",
+		.u.insns_int = {
+			BPF_ALU64_IMM(BPF_MOV, R0, -123456789),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, -123456789 } }
+	},
+	{
+		"ALU64_MOV_K: large negative sign extension",
+		.u.insns_int = {
+			BPF_ALU64_IMM(BPF_MOV, R0, -123456789),
+			BPF_ALU64_IMM(BPF_RSH, R0, 32),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 0xffffffff } }
+	},
 	/* BPF_ALU | BPF_ADD | BPF_X */
 	{
 		"ALU_ADD_X: 1 + 2 = 3",
@@ -2967,6 +3243,31 @@ static struct bpf_test tests[] = {
 		{ },
 		{ { 0, 2147483647 } },
 	},
+	{
+		"ALU64_MUL_X: 64x64 multiply, low word",
+		.u.insns_int = {
+			BPF_LD_IMM64(R0, 0x0fedcba987654321LL),
+			BPF_LD_IMM64(R1, 0x123456789abcdef0LL),
+			BPF_ALU64_REG(BPF_MUL, R0, R1),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 0xe5618cf0 } }
+	},
+	{
+		"ALU64_MUL_X: 64x64 multiply, high word",
+		.u.insns_int = {
+			BPF_LD_IMM64(R0, 0x0fedcba987654321LL),
+			BPF_LD_IMM64(R1, 0x123456789abcdef0LL),
+			BPF_ALU64_REG(BPF_MUL, R0, R1),
+			BPF_ALU64_IMM(BPF_RSH, R0, 32),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 0x2236d88f } }
+	},
 	/* BPF_ALU | BPF_MUL | BPF_K */
 	{
 		"ALU_MUL_K: 2 * 3 = 6",
@@ -3077,6 +3378,29 @@ static struct bpf_test tests[] = {
 		{ },
 		{ { 0, 0x1 } },
 	},
+	{
+		"ALU64_MUL_K: 64x32 multiply, low word",
+		.u.insns_int = {
+			BPF_LD_IMM64(R0, 0x0123456789abcdefLL),
+			BPF_ALU64_IMM(BPF_MUL, R0, 0x12345678),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 0xe242d208 } }
+	},
+	{
+		"ALU64_MUL_K: 64x32 multiply, high word",
+		.u.insns_int = {
+			BPF_LD_IMM64(R0, 0x0123456789abcdefLL),
+			BPF_ALU64_IMM(BPF_MUL, R0, 0x12345678),
+			BPF_ALU64_IMM(BPF_RSH, R0, 32),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 0xc28f5c28 } }
+	},
 	/* BPF_ALU | BPF_DIV | BPF_X */
 	{
 		"ALU_DIV_X: 6 / 2 = 3",
@@ -3431,6 +3755,44 @@ static struct bpf_test tests[] = {
 		{ { 0, 0xffffffff } },
 	},
 	{
+		"ALU_AND_K: Small immediate",
+		.u.insns_int = {
+			BPF_ALU32_IMM(BPF_MOV, R0, 0x01020304),
+			BPF_ALU32_IMM(BPF_AND, R0, 15),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 4 } }
+	},
+	{
+		"ALU_AND_K: Large immediate",
+		.u.insns_int = {
+			BPF_ALU32_IMM(BPF_MOV, R0, 0xf1f2f3f4),
+			BPF_ALU32_IMM(BPF_AND, R0, 0xafbfcfdf),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 0xa1b2c3d4 } }
+	},
+	{
+		"ALU_AND_K: Zero extension",
+		.u.insns_int = {
+			BPF_LD_IMM64(R0, 0x0123456789abcdefLL),
+			BPF_LD_IMM64(R1, 0x0000000080a0c0e0LL),
+			BPF_ALU32_IMM(BPF_AND, R0, 0xf0f0f0f0),
+			BPF_JMP_REG(BPF_JEQ, R0, R1, 2),
+			BPF_MOV32_IMM(R0, 2),
+			BPF_EXIT_INSN(),
+			BPF_MOV32_IMM(R0, 1),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 1 } }
+	},
+	{
 		"ALU64_AND_K: 3 & 2 = 2",
 		.u.insns_int = {
 			BPF_LD_IMM64(R0, 3),
@@ -3453,7 +3815,7 @@ static struct bpf_test tests[] = {
 		{ { 0, 0xffffffff } },
 	},
 	{
-		"ALU64_AND_K: 0x0000ffffffff0000 & 0x0 = 0x0000ffff00000000",
+		"ALU64_AND_K: 0x0000ffffffff0000 & 0x0 = 0x0000000000000000",
 		.u.insns_int = {
 			BPF_LD_IMM64(R2, 0x0000ffffffff0000LL),
 			BPF_LD_IMM64(R3, 0x0000000000000000LL),
@@ -3469,7 +3831,7 @@ static struct bpf_test tests[] = {
 		{ { 0, 0x1 } },
 	},
 	{
-		"ALU64_AND_K: 0x0000ffffffff0000 & -1 = 0x0000ffffffffffff",
+		"ALU64_AND_K: 0x0000ffffffff0000 & -1 = 0x0000ffffffff0000",
 		.u.insns_int = {
 			BPF_LD_IMM64(R2, 0x0000ffffffff0000LL),
 			BPF_LD_IMM64(R3, 0x0000ffffffff0000LL),
@@ -3500,6 +3862,38 @@ static struct bpf_test tests[] = {
 		{ },
 		{ { 0, 0x1 } },
 	},
+	{
+		"ALU64_AND_K: Sign extension 1",
+		.u.insns_int = {
+			BPF_LD_IMM64(R0, 0x0123456789abcdefLL),
+			BPF_LD_IMM64(R1, 0x00000000090b0d0fLL),
+			BPF_ALU64_IMM(BPF_AND, R0, 0x0f0f0f0f),
+			BPF_JMP_REG(BPF_JEQ, R0, R1, 2),
+			BPF_MOV32_IMM(R0, 2),
+			BPF_EXIT_INSN(),
+			BPF_MOV32_IMM(R0, 1),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 1 } }
+	},
+	{
+		"ALU64_AND_K: Sign extension 2",
+		.u.insns_int = {
+			BPF_LD_IMM64(R0, 0x0123456789abcdefLL),
+			BPF_LD_IMM64(R1, 0x0123456780a0c0e0LL),
+			BPF_ALU64_IMM(BPF_AND, R0, 0xf0f0f0f0),
+			BPF_JMP_REG(BPF_JEQ, R0, R1, 2),
+			BPF_MOV32_IMM(R0, 2),
+			BPF_EXIT_INSN(),
+			BPF_MOV32_IMM(R0, 1),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 1 } }
+	},
 	/* BPF_ALU | BPF_OR | BPF_X */
 	{
 		"ALU_OR_X: 1 | 2 = 3",
@@ -3573,6 +3967,44 @@ static struct bpf_test tests[] = {
 		{ { 0, 0xffffffff } },
 	},
 	{
+		"ALU_OR_K: Small immediate",
+		.u.insns_int = {
+			BPF_ALU32_IMM(BPF_MOV, R0, 0x01020304),
+			BPF_ALU32_IMM(BPF_OR, R0, 1),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 0x01020305 } }
+	},
+	{
+		"ALU_OR_K: Large immediate",
+		.u.insns_int = {
+			BPF_ALU32_IMM(BPF_MOV, R0, 0x01020304),
+			BPF_ALU32_IMM(BPF_OR, R0, 0xa0b0c0d0),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 0xa1b2c3d4 } }
+	},
+	{
+		"ALU_OR_K: Zero extension",
+		.u.insns_int = {
+			BPF_LD_IMM64(R0, 0x0123456789abcdefLL),
+			BPF_LD_IMM64(R1, 0x00000000f9fbfdffLL),
+			BPF_ALU32_IMM(BPF_OR, R0, 0xf0f0f0f0),
+			BPF_JMP_REG(BPF_JEQ, R0, R1, 2),
+			BPF_MOV32_IMM(R0, 2),
+			BPF_EXIT_INSN(),
+			BPF_MOV32_IMM(R0, 1),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 1 } }
+	},
+	{
 		"ALU64_OR_K: 1 | 2 = 3",
 		.u.insns_int = {
 			BPF_LD_IMM64(R0, 1),
@@ -3595,7 +4027,7 @@ static struct bpf_test tests[] = {
 		{ { 0, 0xffffffff } },
 	},
 	{
-		"ALU64_OR_K: 0x0000ffffffff0000 | 0x0 = 0x0000ffff00000000",
+		"ALU64_OR_K: 0x0000ffffffff0000 | 0x0 = 0x0000ffffffff0000",
 		.u.insns_int = {
 			BPF_LD_IMM64(R2, 0x0000ffffffff0000LL),
 			BPF_LD_IMM64(R3, 0x0000ffffffff0000LL),
@@ -3642,6 +4074,38 @@ static struct bpf_test tests[] = {
 		{ },
 		{ { 0, 0x1 } },
 	},
+	{
+		"ALU64_OR_K: Sign extension 1",
+		.u.insns_int = {
+			BPF_LD_IMM64(R0, 0x0123456789abcdefLL),
+			BPF_LD_IMM64(R1, 0x012345678fafcfefLL),
+			BPF_ALU64_IMM(BPF_OR, R0, 0x0f0f0f0f),
+			BPF_JMP_REG(BPF_JEQ, R0, R1, 2),
+			BPF_MOV32_IMM(R0, 2),
+			BPF_EXIT_INSN(),
+			BPF_MOV32_IMM(R0, 1),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 1 } }
+	},
+	{
+		"ALU64_OR_K: Sign extension 2",
+		.u.insns_int = {
+			BPF_LD_IMM64(R0, 0x0123456789abcdefLL),
+			BPF_LD_IMM64(R1, 0xfffffffff9fbfdffLL),
+			BPF_ALU64_IMM(BPF_OR, R0, 0xf0f0f0f0),
+			BPF_JMP_REG(BPF_JEQ, R0, R1, 2),
+			BPF_MOV32_IMM(R0, 2),
+			BPF_EXIT_INSN(),
+			BPF_MOV32_IMM(R0, 1),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 1 } }
+	},
 	/* BPF_ALU | BPF_XOR | BPF_X */
 	{
 		"ALU_XOR_X: 5 ^ 6 = 3",
@@ -3715,6 +4179,44 @@ static struct bpf_test tests[] = {
 		{ { 0, 0xfffffffe } },
 	},
 	{
+		"ALU_XOR_K: Small immediate",
+		.u.insns_int = {
+			BPF_ALU32_IMM(BPF_MOV, R0, 0x01020304),
+			BPF_ALU32_IMM(BPF_XOR, R0, 15),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 0x0102030b } }
+	},
+	{
+		"ALU_XOR_K: Large immediate",
+		.u.insns_int = {
+			BPF_ALU32_IMM(BPF_MOV, R0, 0xf1f2f3f4),
+			BPF_ALU32_IMM(BPF_XOR, R0, 0xafbfcfdf),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 0x5e4d3c2b } }
+	},
+	{
+		"ALU_XOR_K: Zero extension",
+		.u.insns_int = {
+			BPF_LD_IMM64(R0, 0x0123456789abcdefLL),
+			BPF_LD_IMM64(R1, 0x00000000795b3d1fLL),
+			BPF_ALU32_IMM(BPF_XOR, R0, 0xf0f0f0f0),
+			BPF_JMP_REG(BPF_JEQ, R0, R1, 2),
+			BPF_MOV32_IMM(R0, 2),
+			BPF_EXIT_INSN(),
+			BPF_MOV32_IMM(R0, 1),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 1 } }
+	},
+	{
 		"ALU64_XOR_K: 5 ^ 6 = 3",
 		.u.insns_int = {
 			BPF_LD_IMM64(R0, 5),
@@ -3726,7 +4228,7 @@ static struct bpf_test tests[] = {
 		{ { 0, 3 } },
 	},
 	{
-		"ALU64_XOR_K: 1 & 0xffffffff = 0xfffffffe",
+		"ALU64_XOR_K: 1 ^ 0xffffffff = 0xfffffffe",
 		.u.insns_int = {
 			BPF_LD_IMM64(R0, 1),
 			BPF_ALU64_IMM(BPF_XOR, R0, 0xffffffff),
@@ -3784,6 +4286,38 @@ static struct bpf_test tests[] = {
 		{ },
 		{ { 0, 0x1 } },
 	},
+	{
+		"ALU64_XOR_K: Sign extension 1",
+		.u.insns_int = {
+			BPF_LD_IMM64(R0, 0x0123456789abcdefLL),
+			BPF_LD_IMM64(R1, 0x0123456786a4c2e0LL),
+			BPF_ALU64_IMM(BPF_XOR, R0, 0x0f0f0f0f),
+			BPF_JMP_REG(BPF_JEQ, R0, R1, 2),
+			BPF_MOV32_IMM(R0, 2),
+			BPF_EXIT_INSN(),
+			BPF_MOV32_IMM(R0, 1),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 1 } }
+	},
+	{
+		"ALU64_XOR_K: Sign extension 2",
+		.u.insns_int = {
+			BPF_LD_IMM64(R0, 0x0123456789abcdefLL),
+			BPF_LD_IMM64(R1, 0xfedcba98795b3d1fLL),
+			BPF_ALU64_IMM(BPF_XOR, R0, 0xf0f0f0f0),
+			BPF_JMP_REG(BPF_JEQ, R0, R1, 2),
+			BPF_MOV32_IMM(R0, 2),
+			BPF_EXIT_INSN(),
+			BPF_MOV32_IMM(R0, 1),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 1 } }
+	},
 	/* BPF_ALU | BPF_LSH | BPF_X */
 	{
 		"ALU_LSH_X: 1 << 1 = 2",
@@ -3810,6 +4344,18 @@ static struct bpf_test tests[] = {
 		{ { 0, 0x80000000 } },
 	},
 	{
+		"ALU_LSH_X: 0x12345678 << 12 = 0x45678000",
+		.u.insns_int = {
+			BPF_ALU32_IMM(BPF_MOV, R0, 0x12345678),
+			BPF_ALU32_IMM(BPF_MOV, R1, 12),
+			BPF_ALU32_REG(BPF_LSH, R0, R1),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 0x45678000 } }
+	},
+	{
 		"ALU64_LSH_X: 1 << 1 = 2",
 		.u.insns_int = {
 			BPF_LD_IMM64(R0, 1),
@@ -3833,6 +4379,106 @@ static struct bpf_test tests[] = {
 		{ },
 		{ { 0, 0x80000000 } },
 	},
+	{
+		"ALU64_LSH_X: Shift < 32, low word",
+		.u.insns_int = {
+			BPF_LD_IMM64(R0, 0x0123456789abcdefLL),
+			BPF_ALU32_IMM(BPF_MOV, R1, 12),
+			BPF_ALU64_REG(BPF_LSH, R0, R1),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 0xbcdef000 } }
+	},
+	{
+		"ALU64_LSH_X: Shift < 32, high word",
+		.u.insns_int = {
+			BPF_LD_IMM64(R0, 0x0123456789abcdefLL),
+			BPF_ALU32_IMM(BPF_MOV, R1, 12),
+			BPF_ALU64_REG(BPF_LSH, R0, R1),
+			BPF_ALU64_IMM(BPF_RSH, R0, 32),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 0x3456789a } }
+	},
+	{
+		"ALU64_LSH_X: Shift > 32, low word",
+		.u.insns_int = {
+			BPF_LD_IMM64(R0, 0x0123456789abcdefLL),
+			BPF_ALU32_IMM(BPF_MOV, R1, 36),
+			BPF_ALU64_REG(BPF_LSH, R0, R1),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 0 } }
+	},
+	{
+		"ALU64_LSH_X: Shift > 32, high word",
+		.u.insns_int = {
+			BPF_LD_IMM64(R0, 0x0123456789abcdefLL),
+			BPF_ALU32_IMM(BPF_MOV, R1, 36),
+			BPF_ALU64_REG(BPF_LSH, R0, R1),
+			BPF_ALU64_IMM(BPF_RSH, R0, 32),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 0x9abcdef0 } }
+	},
+	{
+		"ALU64_LSH_X: Shift == 32, low word",
+		.u.insns_int = {
+			BPF_LD_IMM64(R0, 0x0123456789abcdefLL),
+			BPF_ALU32_IMM(BPF_MOV, R1, 32),
+			BPF_ALU64_REG(BPF_LSH, R0, R1),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 0 } }
+	},
+	{
+		"ALU64_LSH_X: Shift == 32, high word",
+		.u.insns_int = {
+			BPF_LD_IMM64(R0, 0x0123456789abcdefLL),
+			BPF_ALU32_IMM(BPF_MOV, R1, 32),
+			BPF_ALU64_REG(BPF_LSH, R0, R1),
+			BPF_ALU64_IMM(BPF_RSH, R0, 32),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 0x89abcdef } }
+	},
+	{
+		"ALU64_LSH_X: Zero shift, low word",
+		.u.insns_int = {
+			BPF_LD_IMM64(R0, 0x0123456789abcdefLL),
+			BPF_ALU32_IMM(BPF_MOV, R1, 0),
+			BPF_ALU64_REG(BPF_LSH, R0, R1),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 0x89abcdef } }
+	},
+	{
+		"ALU64_LSH_X: Zero shift, high word",
+		.u.insns_int = {
+			BPF_LD_IMM64(R0, 0x0123456789abcdefLL),
+			BPF_ALU32_IMM(BPF_MOV, R1, 0),
+			BPF_ALU64_REG(BPF_LSH, R0, R1),
+			BPF_ALU64_IMM(BPF_RSH, R0, 32),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 0x01234567 } }
+	},
 	/* BPF_ALU | BPF_LSH | BPF_K */
 	{
 		"ALU_LSH_K: 1 << 1 = 2",
@@ -3857,6 +4503,28 @@ static struct bpf_test tests[] = {
 		{ { 0, 0x80000000 } },
 	},
 	{
+		"ALU_LSH_K: 0x12345678 << 12 = 0x45678000",
+		.u.insns_int = {
+			BPF_ALU32_IMM(BPF_MOV, R0, 0x12345678),
+			BPF_ALU32_IMM(BPF_LSH, R0, 12),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 0x45678000 } }
+	},
+	{
+		"ALU_LSH_K: 0x12345678 << 0 = 0x12345678",
+		.u.insns_int = {
+			BPF_ALU32_IMM(BPF_MOV, R0, 0x12345678),
+			BPF_ALU32_IMM(BPF_LSH, R0, 0),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 0x12345678 } }
+	},
+	{
 		"ALU64_LSH_K: 1 << 1 = 2",
 		.u.insns_int = {
 			BPF_LD_IMM64(R0, 1),
@@ -3878,6 +4546,86 @@ static struct bpf_test tests[] = {
 		{ },
 		{ { 0, 0x80000000 } },
 	},
+	{
+		"ALU64_LSH_K: Shift < 32, low word",
+		.u.insns_int = {
+			BPF_LD_IMM64(R0, 0x0123456789abcdefLL),
+			BPF_ALU64_IMM(BPF_LSH, R0, 12),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 0xbcdef000 } }
+	},
+	{
+		"ALU64_LSH_K: Shift < 32, high word",
+		.u.insns_int = {
+			BPF_LD_IMM64(R0, 0x0123456789abcdefLL),
+			BPF_ALU64_IMM(BPF_LSH, R0, 12),
+			BPF_ALU64_IMM(BPF_RSH, R0, 32),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 0x3456789a } }
+	},
+	{
+		"ALU64_LSH_K: Shift > 32, low word",
+		.u.insns_int = {
+			BPF_LD_IMM64(R0, 0x0123456789abcdefLL),
+			BPF_ALU64_IMM(BPF_LSH, R0, 36),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 0 } }
+	},
+	{
+		"ALU64_LSH_K: Shift > 32, high word",
+		.u.insns_int = {
+			BPF_LD_IMM64(R0, 0x0123456789abcdefLL),
+			BPF_ALU64_IMM(BPF_LSH, R0, 36),
+			BPF_ALU64_IMM(BPF_RSH, R0, 32),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 0x9abcdef0 } }
+	},
+	{
+		"ALU64_LSH_K: Shift == 32, low word",
+		.u.insns_int = {
+			BPF_LD_IMM64(R0, 0x0123456789abcdefLL),
+			BPF_ALU64_IMM(BPF_LSH, R0, 32),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 0 } }
+	},
+	{
+		"ALU64_LSH_K: Shift == 32, high word",
+		.u.insns_int = {
+			BPF_LD_IMM64(R0, 0x0123456789abcdefLL),
+			BPF_ALU64_IMM(BPF_LSH, R0, 32),
+			BPF_ALU64_IMM(BPF_RSH, R0, 32),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 0x89abcdef } }
+	},
+	{
+		"ALU64_LSH_K: Zero shift",
+		.u.insns_int = {
+			BPF_LD_IMM64(R0, 0x0123456789abcdefLL),
+			BPF_ALU64_IMM(BPF_LSH, R0, 0),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 0x89abcdef } }
+	},
 	/* BPF_ALU | BPF_RSH | BPF_X */
 	{
 		"ALU_RSH_X: 2 >> 1 = 1",
@@ -3904,6 +4652,18 @@ static struct bpf_test tests[] = {
 		{ { 0, 1 } },
 	},
 	{
+		"ALU_RSH_X: 0x12345678 >> 20 = 0x123",
+		.u.insns_int = {
+			BPF_ALU32_IMM(BPF_MOV, R0, 0x12345678),
+			BPF_ALU32_IMM(BPF_MOV, R1, 20),
+			BPF_ALU32_REG(BPF_RSH, R0, R1),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 0x123 } }
+	},
+	{
 		"ALU64_RSH_X: 2 >> 1 = 1",
 		.u.insns_int = {
 			BPF_LD_IMM64(R0, 2),
@@ -3927,6 +4687,106 @@ static struct bpf_test tests[] = {
 		{ },
 		{ { 0, 1 } },
 	},
+	{
+		"ALU64_RSH_X: Shift < 32, low word",
+		.u.insns_int = {
+			BPF_LD_IMM64(R0, 0x8123456789abcdefLL),
+			BPF_ALU32_IMM(BPF_MOV, R1, 12),
+			BPF_ALU64_REG(BPF_RSH, R0, R1),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 0x56789abc } }
+	},
+	{
+		"ALU64_RSH_X: Shift < 32, high word",
+		.u.insns_int = {
+			BPF_LD_IMM64(R0, 0x8123456789abcdefLL),
+			BPF_ALU32_IMM(BPF_MOV, R1, 12),
+			BPF_ALU64_REG(BPF_RSH, R0, R1),
+			BPF_ALU64_IMM(BPF_RSH, R0, 32),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 0x00081234 } }
+	},
+	{
+		"ALU64_RSH_X: Shift > 32, low word",
+		.u.insns_int = {
+			BPF_LD_IMM64(R0, 0x8123456789abcdefLL),
+			BPF_ALU32_IMM(BPF_MOV, R1, 36),
+			BPF_ALU64_REG(BPF_RSH, R0, R1),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 0x08123456 } }
+	},
+	{
+		"ALU64_RSH_X: Shift > 32, high word",
+		.u.insns_int = {
+			BPF_LD_IMM64(R0, 0x8123456789abcdefLL),
+			BPF_ALU32_IMM(BPF_MOV, R1, 36),
+			BPF_ALU64_REG(BPF_RSH, R0, R1),
+			BPF_ALU64_IMM(BPF_RSH, R0, 32),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 0 } }
+	},
+	{
+		"ALU64_RSH_X: Shift == 32, low word",
+		.u.insns_int = {
+			BPF_LD_IMM64(R0, 0x8123456789abcdefLL),
+			BPF_ALU32_IMM(BPF_MOV, R1, 32),
+			BPF_ALU64_REG(BPF_RSH, R0, R1),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 0x81234567 } }
+	},
+	{
+		"ALU64_RSH_X: Shift == 32, high word",
+		.u.insns_int = {
+			BPF_LD_IMM64(R0, 0x8123456789abcdefLL),
+			BPF_ALU32_IMM(BPF_MOV, R1, 32),
+			BPF_ALU64_REG(BPF_RSH, R0, R1),
+			BPF_ALU64_IMM(BPF_RSH, R0, 32),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 0 } }
+	},
+	{
+		"ALU64_RSH_X: Zero shift, low word",
+		.u.insns_int = {
+			BPF_LD_IMM64(R0, 0x8123456789abcdefLL),
+			BPF_ALU32_IMM(BPF_MOV, R1, 0),
+			BPF_ALU64_REG(BPF_RSH, R0, R1),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 0x89abcdef } }
+	},
+	{
+		"ALU64_RSH_X: Zero shift, high word",
+		.u.insns_int = {
+			BPF_LD_IMM64(R0, 0x8123456789abcdefLL),
+			BPF_ALU32_IMM(BPF_MOV, R1, 0),
+			BPF_ALU64_REG(BPF_RSH, R0, R1),
+			BPF_ALU64_IMM(BPF_RSH, R0, 32),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 0x81234567 } }
+	},
 	/* BPF_ALU | BPF_RSH | BPF_K */
 	{
 		"ALU_RSH_K: 2 >> 1 = 1",
@@ -3951,6 +4811,28 @@ static struct bpf_test tests[] = {
 		{ { 0, 1 } },
 	},
 	{
+		"ALU_RSH_K: 0x12345678 >> 20 = 0x123",
+		.u.insns_int = {
+			BPF_ALU32_IMM(BPF_MOV, R0, 0x12345678),
+			BPF_ALU32_IMM(BPF_RSH, R0, 20),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 0x123 } }
+	},
+	{
+		"ALU_RSH_K: 0x12345678 >> 0 = 0x12345678",
+		.u.insns_int = {
+			BPF_ALU32_IMM(BPF_MOV, R0, 0x12345678),
+			BPF_ALU32_IMM(BPF_RSH, R0, 0),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 0x12345678 } }
+	},
+	{
 		"ALU64_RSH_K: 2 >> 1 = 1",
 		.u.insns_int = {
 			BPF_LD_IMM64(R0, 2),
@@ -3972,9 +4854,101 @@ static struct bpf_test tests[] = {
 		{ },
 		{ { 0, 1 } },
 	},
+	{
+		"ALU64_RSH_K: Shift < 32, low word",
+		.u.insns_int = {
+			BPF_LD_IMM64(R0, 0x8123456789abcdefLL),
+			BPF_ALU64_IMM(BPF_RSH, R0, 12),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 0x56789abc } }
+	},
+	{
+		"ALU64_RSH_K: Shift < 32, high word",
+		.u.insns_int = {
+			BPF_LD_IMM64(R0, 0x8123456789abcdefLL),
+			BPF_ALU64_IMM(BPF_RSH, R0, 12),
+			BPF_ALU64_IMM(BPF_RSH, R0, 32),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 0x00081234 } }
+	},
+	{
+		"ALU64_RSH_K: Shift > 32, low word",
+		.u.insns_int = {
+			BPF_LD_IMM64(R0, 0x8123456789abcdefLL),
+			BPF_ALU64_IMM(BPF_RSH, R0, 36),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 0x08123456 } }
+	},
+	{
+		"ALU64_RSH_K: Shift > 32, high word",
+		.u.insns_int = {
+			BPF_LD_IMM64(R0, 0x8123456789abcdefLL),
+			BPF_ALU64_IMM(BPF_RSH, R0, 36),
+			BPF_ALU64_IMM(BPF_RSH, R0, 32),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 0 } }
+	},
+	{
+		"ALU64_RSH_K: Shift == 32, low word",
+		.u.insns_int = {
+			BPF_LD_IMM64(R0, 0x8123456789abcdefLL),
+			BPF_ALU64_IMM(BPF_RSH, R0, 32),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 0x81234567 } }
+	},
+	{
+		"ALU64_RSH_K: Shift == 32, high word",
+		.u.insns_int = {
+			BPF_LD_IMM64(R0, 0x8123456789abcdefLL),
+			BPF_ALU64_IMM(BPF_RSH, R0, 32),
+			BPF_ALU64_IMM(BPF_RSH, R0, 32),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 0 } }
+	},
+	{
+		"ALU64_RSH_K: Zero shift",
+		.u.insns_int = {
+			BPF_LD_IMM64(R0, 0x0123456789abcdefLL),
+			BPF_ALU64_IMM(BPF_RSH, R0, 0),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 0x89abcdef } }
+	},
 	/* BPF_ALU | BPF_ARSH | BPF_X */
 	{
-		"ALU_ARSH_X: 0xff00ff0000000000 >> 40 = 0xffffffffffff00ff",
+		"ALU32_ARSH_X: -1234 >> 7 = -10",
+		.u.insns_int = {
+			BPF_ALU32_IMM(BPF_MOV, R0, -1234),
+			BPF_ALU32_IMM(BPF_MOV, R1, 7),
+			BPF_ALU32_REG(BPF_ARSH, R0, R1),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, -10 } }
+	},
+	{
+		"ALU64_ARSH_X: 0xff00ff0000000000 >> 40 = 0xffffffffffff00ff",
 		.u.insns_int = {
 			BPF_LD_IMM64(R0, 0xff00ff0000000000LL),
 			BPF_ALU32_IMM(BPF_MOV, R1, 40),
@@ -3985,9 +4959,131 @@ static struct bpf_test tests[] = {
 		{ },
 		{ { 0, 0xffff00ff } },
 	},
+	{
+		"ALU64_ARSH_X: Shift < 32, low word",
+		.u.insns_int = {
+			BPF_LD_IMM64(R0, 0x8123456789abcdefLL),
+			BPF_ALU32_IMM(BPF_MOV, R1, 12),
+			BPF_ALU64_REG(BPF_ARSH, R0, R1),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 0x56789abc } }
+	},
+	{
+		"ALU64_ARSH_X: Shift < 32, high word",
+		.u.insns_int = {
+			BPF_LD_IMM64(R0, 0x8123456789abcdefLL),
+			BPF_ALU32_IMM(BPF_MOV, R1, 12),
+			BPF_ALU64_REG(BPF_ARSH, R0, R1),
+			BPF_ALU64_IMM(BPF_RSH, R0, 32),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 0xfff81234 } }
+	},
+	{
+		"ALU64_ARSH_X: Shift > 32, low word",
+		.u.insns_int = {
+			BPF_LD_IMM64(R0, 0x8123456789abcdefLL),
+			BPF_ALU32_IMM(BPF_MOV, R1, 36),
+			BPF_ALU64_REG(BPF_ARSH, R0, R1),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 0xf8123456 } }
+	},
+	{
+		"ALU64_ARSH_X: Shift > 32, high word",
+		.u.insns_int = {
+			BPF_LD_IMM64(R0, 0x8123456789abcdefLL),
+			BPF_ALU32_IMM(BPF_MOV, R1, 36),
+			BPF_ALU64_REG(BPF_ARSH, R0, R1),
+			BPF_ALU64_IMM(BPF_RSH, R0, 32),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, -1 } }
+	},
+	{
+		"ALU64_ARSH_X: Shift == 32, low word",
+		.u.insns_int = {
+			BPF_LD_IMM64(R0, 0x8123456789abcdefLL),
+			BPF_ALU32_IMM(BPF_MOV, R1, 32),
+			BPF_ALU64_REG(BPF_ARSH, R0, R1),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 0x81234567 } }
+	},
+	{
+		"ALU64_ARSH_X: Shift == 32, high word",
+		.u.insns_int = {
+			BPF_LD_IMM64(R0, 0x8123456789abcdefLL),
+			BPF_ALU32_IMM(BPF_MOV, R1, 32),
+			BPF_ALU64_REG(BPF_ARSH, R0, R1),
+			BPF_ALU64_IMM(BPF_RSH, R0, 32),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, -1 } }
+	},
+	{
+		"ALU64_ARSH_X: Zero shift, low word",
+		.u.insns_int = {
+			BPF_LD_IMM64(R0, 0x8123456789abcdefLL),
+			BPF_ALU32_IMM(BPF_MOV, R1, 0),
+			BPF_ALU64_REG(BPF_ARSH, R0, R1),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 0x89abcdef } }
+	},
+	{
+		"ALU64_ARSH_X: Zero shift, high word",
+		.u.insns_int = {
+			BPF_LD_IMM64(R0, 0x8123456789abcdefLL),
+			BPF_ALU32_IMM(BPF_MOV, R1, 0),
+			BPF_ALU64_REG(BPF_ARSH, R0, R1),
+			BPF_ALU64_IMM(BPF_RSH, R0, 32),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 0x81234567 } }
+	},
 	/* BPF_ALU | BPF_ARSH | BPF_K */
 	{
-		"ALU_ARSH_K: 0xff00ff0000000000 >> 40 = 0xffffffffffff00ff",
+		"ALU32_ARSH_K: -1234 >> 7 = -10",
+		.u.insns_int = {
+			BPF_ALU32_IMM(BPF_MOV, R0, -1234),
+			BPF_ALU32_IMM(BPF_ARSH, R0, 7),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, -10 } }
+	},
+	{
+		"ALU32_ARSH_K: -1234 >> 0 = -1234",
+		.u.insns_int = {
+			BPF_ALU32_IMM(BPF_MOV, R0, -1234),
+			BPF_ALU32_IMM(BPF_ARSH, R0, 0),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, -1234 } }
+	},
+	{
+		"ALU64_ARSH_K: 0xff00ff0000000000 >> 40 = 0xffffffffffff00ff",
 		.u.insns_int = {
 			BPF_LD_IMM64(R0, 0xff00ff0000000000LL),
 			BPF_ALU64_IMM(BPF_ARSH, R0, 40),
@@ -3997,6 +5093,86 @@ static struct bpf_test tests[] = {
 		{ },
 		{ { 0, 0xffff00ff } },
 	},
+	{
+		"ALU64_ARSH_K: Shift < 32, low word",
+		.u.insns_int = {
+			BPF_LD_IMM64(R0, 0x8123456789abcdefLL),
+			BPF_ALU64_IMM(BPF_RSH, R0, 12),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 0x56789abc } }
+	},
+	{
+		"ALU64_ARSH_K: Shift < 32, high word",
+		.u.insns_int = {
+			BPF_LD_IMM64(R0, 0x8123456789abcdefLL),
+			BPF_ALU64_IMM(BPF_ARSH, R0, 12),
+			BPF_ALU64_IMM(BPF_RSH, R0, 32),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 0xfff81234 } }
+	},
+	{
+		"ALU64_ARSH_K: Shift > 32, low word",
+		.u.insns_int = {
+			BPF_LD_IMM64(R0, 0x8123456789abcdefLL),
+			BPF_ALU64_IMM(BPF_ARSH, R0, 36),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 0xf8123456 } }
+	},
+	{
+		"ALU64_ARSH_K: Shift > 32, high word",
+		.u.insns_int = {
+			BPF_LD_IMM64(R0, 0xf123456789abcdefLL),
+			BPF_ALU64_IMM(BPF_ARSH, R0, 36),
+			BPF_ALU64_IMM(BPF_RSH, R0, 32),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, -1 } }
+	},
+	{
+		"ALU64_ARSH_K: Shift == 32, low word",
+		.u.insns_int = {
+			BPF_LD_IMM64(R0, 0x8123456789abcdefLL),
+			BPF_ALU64_IMM(BPF_ARSH, R0, 32),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 0x81234567 } }
+	},
+	{
+		"ALU64_ARSH_K: Shift == 32, high word",
+		.u.insns_int = {
+			BPF_LD_IMM64(R0, 0x8123456789abcdefLL),
+			BPF_ALU64_IMM(BPF_ARSH, R0, 32),
+			BPF_ALU64_IMM(BPF_RSH, R0, 32),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, -1 } }
+	},
+	{
+		"ALU64_ARSH_K: Zero shoft",
+		.u.insns_int = {
+			BPF_LD_IMM64(R0, 0x8123456789abcdefLL),
+			BPF_ALU64_IMM(BPF_ARSH, R0, 0),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 0x89abcdef } }
+	},
 	/* BPF_ALU | BPF_NEG */
 	{
 		"ALU_NEG: -(3) = -3",
@@ -4295,80 +5471,346 @@ static struct bpf_test tests[] = {
 		{ { 0, 0xffffffff } },
 		.stack_depth = 40,
 	},
+	{
+		"STX_MEM_DW: Store double word: first word in memory",
+		.u.insns_int = {
+			BPF_LD_IMM64(R0, 0),
+			BPF_LD_IMM64(R1, 0x0123456789abcdefLL),
+			BPF_STX_MEM(BPF_DW, R10, R1, -40),
+			BPF_LDX_MEM(BPF_W, R0, R10, -40),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+#ifdef __BIG_ENDIAN
+		{ { 0, 0x01234567 } },
+#else
+		{ { 0, 0x89abcdef } },
+#endif
+		.stack_depth = 40,
+	},
+	{
+		"STX_MEM_DW: Store double word: second word in memory",
+		.u.insns_int = {
+			BPF_LD_IMM64(R0, 0),
+			BPF_LD_IMM64(R1, 0x0123456789abcdefLL),
+			BPF_STX_MEM(BPF_DW, R10, R1, -40),
+			BPF_LDX_MEM(BPF_W, R0, R10, -36),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+#ifdef __BIG_ENDIAN
+		{ { 0, 0x89abcdef } },
+#else
+		{ { 0, 0x01234567 } },
+#endif
+		.stack_depth = 40,
+	},
 	/* BPF_STX | BPF_ATOMIC | BPF_W/DW */
 	{
-		"STX_XADD_W: Test: 0x12 + 0x10 = 0x22",
+		"STX_XADD_W: X + 1 + 1 + 1 + ...",
+		{ },
+		INTERNAL,
+		{ },
+		{ { 0, 4134 } },
+		.fill_helper = bpf_fill_stxw,
+	},
+	{
+		"STX_XADD_DW: X + 1 + 1 + 1 + ...",
+		{ },
+		INTERNAL,
+		{ },
+		{ { 0, 4134 } },
+		.fill_helper = bpf_fill_stxdw,
+	},
+	/*
+	 * Exhaustive tests of atomic operation variants.
+	 * Individual tests are expanded from template macros for all
+	 * combinations of ALU operation, word size and fetching.
+	 */
+#define BPF_ATOMIC_OP_TEST1(width, op, logic, old, update, result)	\
+{									\
+	"BPF_ATOMIC | " #width ", " #op ": Test: "			\
+		#old " " #logic " " #update " = " #result,		\
+	.u.insns_int = {						\
+		BPF_ALU32_IMM(BPF_MOV, R5, update),			\
+		BPF_ST_MEM(width, R10, -40, old),			\
+		BPF_ATOMIC_OP(width, op, R10, R5, -40),			\
+		BPF_LDX_MEM(width, R0, R10, -40),			\
+		BPF_EXIT_INSN(),					\
+	},								\
+	INTERNAL,							\
+	{ },								\
+	{ { 0, result } },						\
+	.stack_depth = 40,						\
+}
+#define BPF_ATOMIC_OP_TEST2(width, op, logic, old, update, result)	\
+{									\
+	"BPF_ATOMIC | " #width ", " #op ": Test side effects, r10: "	\
+		#old " " #logic " " #update " = " #result,		\
+	.u.insns_int = {						\
+		BPF_ALU64_REG(BPF_MOV, R1, R10),			\
+		BPF_ALU32_IMM(BPF_MOV, R0, update),			\
+		BPF_ST_MEM(BPF_W, R10, -40, old),			\
+		BPF_ATOMIC_OP(width, op, R10, R0, -40),			\
+		BPF_ALU64_REG(BPF_MOV, R0, R10),			\
+		BPF_ALU64_REG(BPF_SUB, R0, R1),				\
+		BPF_EXIT_INSN(),					\
+	},								\
+	INTERNAL,							\
+	{ },								\
+	{ { 0, 0 } },							\
+	.stack_depth = 40,						\
+}
+#define BPF_ATOMIC_OP_TEST3(width, op, logic, old, update, result)	\
+{									\
+	"BPF_ATOMIC | " #width ", " #op ": Test side effects, r0: "	\
+		#old " " #logic " " #update " = " #result,		\
+	.u.insns_int = {						\
+		BPF_ALU64_REG(BPF_MOV, R0, R10),			\
+		BPF_ALU32_IMM(BPF_MOV, R1, update),			\
+		BPF_ST_MEM(width, R10, -40, old),			\
+		BPF_ATOMIC_OP(width, op, R10, R1, -40),			\
+		BPF_ALU64_REG(BPF_SUB, R0, R10),			\
+		BPF_EXIT_INSN(),					\
+	},								\
+	INTERNAL,                                                       \
+	{ },                                                            \
+	{ { 0, 0 } },                                                   \
+	.stack_depth = 40,                                              \
+}
+#define BPF_ATOMIC_OP_TEST4(width, op, logic, old, update, result)	\
+{									\
+	"BPF_ATOMIC | " #width ", " #op ": Test fetch: "		\
+		#old " " #logic " " #update " = " #result,		\
+	.u.insns_int = {						\
+		BPF_ALU32_IMM(BPF_MOV, R3, update),			\
+		BPF_ST_MEM(width, R10, -40, old),			\
+		BPF_ATOMIC_OP(width, op, R10, R3, -40),			\
+		BPF_ALU64_REG(BPF_MOV, R0, R3),                         \
+		BPF_EXIT_INSN(),					\
+	},								\
+	INTERNAL,                                                       \
+	{ },                                                            \
+	{ { 0, (op) & BPF_FETCH ? old : update } },			\
+	.stack_depth = 40,                                              \
+}
+	/* BPF_ATOMIC | BPF_W: BPF_ADD */
+	BPF_ATOMIC_OP_TEST1(BPF_W, BPF_ADD, +, 0x12, 0xab, 0xbd),
+	BPF_ATOMIC_OP_TEST2(BPF_W, BPF_ADD, +, 0x12, 0xab, 0xbd),
+	BPF_ATOMIC_OP_TEST3(BPF_W, BPF_ADD, +, 0x12, 0xab, 0xbd),
+	BPF_ATOMIC_OP_TEST4(BPF_W, BPF_ADD, +, 0x12, 0xab, 0xbd),
+	/* BPF_ATOMIC | BPF_W: BPF_ADD | BPF_FETCH */
+	BPF_ATOMIC_OP_TEST1(BPF_W, BPF_ADD | BPF_FETCH, +, 0x12, 0xab, 0xbd),
+	BPF_ATOMIC_OP_TEST2(BPF_W, BPF_ADD | BPF_FETCH, +, 0x12, 0xab, 0xbd),
+	BPF_ATOMIC_OP_TEST3(BPF_W, BPF_ADD | BPF_FETCH, +, 0x12, 0xab, 0xbd),
+	BPF_ATOMIC_OP_TEST4(BPF_W, BPF_ADD | BPF_FETCH, +, 0x12, 0xab, 0xbd),
+	/* BPF_ATOMIC | BPF_DW: BPF_ADD */
+	BPF_ATOMIC_OP_TEST1(BPF_DW, BPF_ADD, +, 0x12, 0xab, 0xbd),
+	BPF_ATOMIC_OP_TEST2(BPF_DW, BPF_ADD, +, 0x12, 0xab, 0xbd),
+	BPF_ATOMIC_OP_TEST3(BPF_DW, BPF_ADD, +, 0x12, 0xab, 0xbd),
+	BPF_ATOMIC_OP_TEST4(BPF_DW, BPF_ADD, +, 0x12, 0xab, 0xbd),
+	/* BPF_ATOMIC | BPF_DW: BPF_ADD | BPF_FETCH */
+	BPF_ATOMIC_OP_TEST1(BPF_DW, BPF_ADD | BPF_FETCH, +, 0x12, 0xab, 0xbd),
+	BPF_ATOMIC_OP_TEST2(BPF_DW, BPF_ADD | BPF_FETCH, +, 0x12, 0xab, 0xbd),
+	BPF_ATOMIC_OP_TEST3(BPF_DW, BPF_ADD | BPF_FETCH, +, 0x12, 0xab, 0xbd),
+	BPF_ATOMIC_OP_TEST4(BPF_DW, BPF_ADD | BPF_FETCH, +, 0x12, 0xab, 0xbd),
+	/* BPF_ATOMIC | BPF_W: BPF_AND */
+	BPF_ATOMIC_OP_TEST1(BPF_W, BPF_AND, &, 0x12, 0xab, 0x02),
+	BPF_ATOMIC_OP_TEST2(BPF_W, BPF_AND, &, 0x12, 0xab, 0x02),
+	BPF_ATOMIC_OP_TEST3(BPF_W, BPF_AND, &, 0x12, 0xab, 0x02),
+	BPF_ATOMIC_OP_TEST4(BPF_W, BPF_AND, &, 0x12, 0xab, 0x02),
+	/* BPF_ATOMIC | BPF_W: BPF_AND | BPF_FETCH */
+	BPF_ATOMIC_OP_TEST1(BPF_W, BPF_AND | BPF_FETCH, &, 0x12, 0xab, 0x02),
+	BPF_ATOMIC_OP_TEST2(BPF_W, BPF_AND | BPF_FETCH, &, 0x12, 0xab, 0x02),
+	BPF_ATOMIC_OP_TEST3(BPF_W, BPF_AND | BPF_FETCH, &, 0x12, 0xab, 0x02),
+	BPF_ATOMIC_OP_TEST4(BPF_W, BPF_AND | BPF_FETCH, &, 0x12, 0xab, 0x02),
+	/* BPF_ATOMIC | BPF_DW: BPF_AND */
+	BPF_ATOMIC_OP_TEST1(BPF_DW, BPF_AND, &, 0x12, 0xab, 0x02),
+	BPF_ATOMIC_OP_TEST2(BPF_DW, BPF_AND, &, 0x12, 0xab, 0x02),
+	BPF_ATOMIC_OP_TEST3(BPF_DW, BPF_AND, &, 0x12, 0xab, 0x02),
+	BPF_ATOMIC_OP_TEST4(BPF_DW, BPF_AND, &, 0x12, 0xab, 0x02),
+	/* BPF_ATOMIC | BPF_DW: BPF_AND | BPF_FETCH */
+	BPF_ATOMIC_OP_TEST1(BPF_DW, BPF_AND | BPF_FETCH, &, 0x12, 0xab, 0x02),
+	BPF_ATOMIC_OP_TEST2(BPF_DW, BPF_AND | BPF_FETCH, &, 0x12, 0xab, 0x02),
+	BPF_ATOMIC_OP_TEST3(BPF_DW, BPF_AND | BPF_FETCH, &, 0x12, 0xab, 0x02),
+	BPF_ATOMIC_OP_TEST4(BPF_DW, BPF_AND | BPF_FETCH, &, 0x12, 0xab, 0x02),
+	/* BPF_ATOMIC | BPF_W: BPF_OR */
+	BPF_ATOMIC_OP_TEST1(BPF_W, BPF_OR, |, 0x12, 0xab, 0xbb),
+	BPF_ATOMIC_OP_TEST2(BPF_W, BPF_OR, |, 0x12, 0xab, 0xbb),
+	BPF_ATOMIC_OP_TEST3(BPF_W, BPF_OR, |, 0x12, 0xab, 0xbb),
+	BPF_ATOMIC_OP_TEST4(BPF_W, BPF_OR, |, 0x12, 0xab, 0xbb),
+	/* BPF_ATOMIC | BPF_W: BPF_OR | BPF_FETCH */
+	BPF_ATOMIC_OP_TEST1(BPF_W, BPF_OR | BPF_FETCH, |, 0x12, 0xab, 0xbb),
+	BPF_ATOMIC_OP_TEST2(BPF_W, BPF_OR | BPF_FETCH, |, 0x12, 0xab, 0xbb),
+	BPF_ATOMIC_OP_TEST3(BPF_W, BPF_OR | BPF_FETCH, |, 0x12, 0xab, 0xbb),
+	BPF_ATOMIC_OP_TEST4(BPF_W, BPF_OR | BPF_FETCH, |, 0x12, 0xab, 0xbb),
+	/* BPF_ATOMIC | BPF_DW: BPF_OR */
+	BPF_ATOMIC_OP_TEST1(BPF_DW, BPF_OR, |, 0x12, 0xab, 0xbb),
+	BPF_ATOMIC_OP_TEST2(BPF_DW, BPF_OR, |, 0x12, 0xab, 0xbb),
+	BPF_ATOMIC_OP_TEST3(BPF_DW, BPF_OR, |, 0x12, 0xab, 0xbb),
+	BPF_ATOMIC_OP_TEST4(BPF_DW, BPF_OR, |, 0x12, 0xab, 0xbb),
+	/* BPF_ATOMIC | BPF_DW: BPF_OR | BPF_FETCH */
+	BPF_ATOMIC_OP_TEST1(BPF_DW, BPF_OR | BPF_FETCH, |, 0x12, 0xab, 0xbb),
+	BPF_ATOMIC_OP_TEST2(BPF_DW, BPF_OR | BPF_FETCH, |, 0x12, 0xab, 0xbb),
+	BPF_ATOMIC_OP_TEST3(BPF_DW, BPF_OR | BPF_FETCH, |, 0x12, 0xab, 0xbb),
+	BPF_ATOMIC_OP_TEST4(BPF_DW, BPF_OR | BPF_FETCH, |, 0x12, 0xab, 0xbb),
+	/* BPF_ATOMIC | BPF_W: BPF_XOR */
+	BPF_ATOMIC_OP_TEST1(BPF_W, BPF_XOR, ^, 0x12, 0xab, 0xb9),
+	BPF_ATOMIC_OP_TEST2(BPF_W, BPF_XOR, ^, 0x12, 0xab, 0xb9),
+	BPF_ATOMIC_OP_TEST3(BPF_W, BPF_XOR, ^, 0x12, 0xab, 0xb9),
+	BPF_ATOMIC_OP_TEST4(BPF_W, BPF_XOR, ^, 0x12, 0xab, 0xb9),
+	/* BPF_ATOMIC | BPF_W: BPF_XOR | BPF_FETCH */
+	BPF_ATOMIC_OP_TEST1(BPF_W, BPF_XOR | BPF_FETCH, ^, 0x12, 0xab, 0xb9),
+	BPF_ATOMIC_OP_TEST2(BPF_W, BPF_XOR | BPF_FETCH, ^, 0x12, 0xab, 0xb9),
+	BPF_ATOMIC_OP_TEST3(BPF_W, BPF_XOR | BPF_FETCH, ^, 0x12, 0xab, 0xb9),
+	BPF_ATOMIC_OP_TEST4(BPF_W, BPF_XOR | BPF_FETCH, ^, 0x12, 0xab, 0xb9),
+	/* BPF_ATOMIC | BPF_DW: BPF_XOR */
+	BPF_ATOMIC_OP_TEST1(BPF_DW, BPF_XOR, ^, 0x12, 0xab, 0xb9),
+	BPF_ATOMIC_OP_TEST2(BPF_DW, BPF_XOR, ^, 0x12, 0xab, 0xb9),
+	BPF_ATOMIC_OP_TEST3(BPF_DW, BPF_XOR, ^, 0x12, 0xab, 0xb9),
+	BPF_ATOMIC_OP_TEST4(BPF_DW, BPF_XOR, ^, 0x12, 0xab, 0xb9),
+	/* BPF_ATOMIC | BPF_DW: BPF_XOR | BPF_FETCH */
+	BPF_ATOMIC_OP_TEST1(BPF_DW, BPF_XOR | BPF_FETCH, ^, 0x12, 0xab, 0xb9),
+	BPF_ATOMIC_OP_TEST2(BPF_DW, BPF_XOR | BPF_FETCH, ^, 0x12, 0xab, 0xb9),
+	BPF_ATOMIC_OP_TEST3(BPF_DW, BPF_XOR | BPF_FETCH, ^, 0x12, 0xab, 0xb9),
+	BPF_ATOMIC_OP_TEST4(BPF_DW, BPF_XOR | BPF_FETCH, ^, 0x12, 0xab, 0xb9),
+	/* BPF_ATOMIC | BPF_W: BPF_XCHG */
+	BPF_ATOMIC_OP_TEST1(BPF_W, BPF_XCHG, xchg, 0x12, 0xab, 0xab),
+	BPF_ATOMIC_OP_TEST2(BPF_W, BPF_XCHG, xchg, 0x12, 0xab, 0xab),
+	BPF_ATOMIC_OP_TEST3(BPF_W, BPF_XCHG, xchg, 0x12, 0xab, 0xab),
+	BPF_ATOMIC_OP_TEST4(BPF_W, BPF_XCHG, xchg, 0x12, 0xab, 0xab),
+	/* BPF_ATOMIC | BPF_DW: BPF_XCHG */
+	BPF_ATOMIC_OP_TEST1(BPF_DW, BPF_XCHG, xchg, 0x12, 0xab, 0xab),
+	BPF_ATOMIC_OP_TEST2(BPF_DW, BPF_XCHG, xchg, 0x12, 0xab, 0xab),
+	BPF_ATOMIC_OP_TEST3(BPF_DW, BPF_XCHG, xchg, 0x12, 0xab, 0xab),
+	BPF_ATOMIC_OP_TEST4(BPF_DW, BPF_XCHG, xchg, 0x12, 0xab, 0xab),
+#undef BPF_ATOMIC_OP_TEST1
+#undef BPF_ATOMIC_OP_TEST2
+#undef BPF_ATOMIC_OP_TEST3
+#undef BPF_ATOMIC_OP_TEST4
+	/* BPF_ATOMIC | BPF_W, BPF_CMPXCHG */
+	{
+		"BPF_ATOMIC | BPF_W, BPF_CMPXCHG: Test successful return",
+		.u.insns_int = {
+			BPF_ST_MEM(BPF_W, R10, -40, 0x01234567),
+			BPF_ALU32_IMM(BPF_MOV, R0, 0x01234567),
+			BPF_ALU32_IMM(BPF_MOV, R3, 0x89abcdef),
+			BPF_ATOMIC_OP(BPF_W, BPF_CMPXCHG, R10, R3, -40),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 0x01234567 } },
+		.stack_depth = 40,
+	},
+	{
+		"BPF_ATOMIC | BPF_W, BPF_CMPXCHG: Test successful store",
 		.u.insns_int = {
-			BPF_ALU32_IMM(BPF_MOV, R0, 0x12),
-			BPF_ST_MEM(BPF_W, R10, -40, 0x10),
-			BPF_ATOMIC_OP(BPF_W, BPF_ADD, R10, R0, -40),
+			BPF_ST_MEM(BPF_W, R10, -40, 0x01234567),
+			BPF_ALU32_IMM(BPF_MOV, R0, 0x01234567),
+			BPF_ALU32_IMM(BPF_MOV, R3, 0x89abcdef),
+			BPF_ATOMIC_OP(BPF_W, BPF_CMPXCHG, R10, R3, -40),
 			BPF_LDX_MEM(BPF_W, R0, R10, -40),
 			BPF_EXIT_INSN(),
 		},
 		INTERNAL,
 		{ },
-		{ { 0, 0x22 } },
+		{ { 0, 0x89abcdef } },
 		.stack_depth = 40,
 	},
 	{
-		"STX_XADD_W: Test side-effects, r10: 0x12 + 0x10 = 0x22",
+		"BPF_ATOMIC | BPF_W, BPF_CMPXCHG: Test failure return",
 		.u.insns_int = {
-			BPF_ALU64_REG(BPF_MOV, R1, R10),
-			BPF_ALU32_IMM(BPF_MOV, R0, 0x12),
-			BPF_ST_MEM(BPF_W, R10, -40, 0x10),
-			BPF_ATOMIC_OP(BPF_W, BPF_ADD, R10, R0, -40),
-			BPF_ALU64_REG(BPF_MOV, R0, R10),
-			BPF_ALU64_REG(BPF_SUB, R0, R1),
+			BPF_ST_MEM(BPF_W, R10, -40, 0x01234567),
+			BPF_ALU32_IMM(BPF_MOV, R0, 0x76543210),
+			BPF_ALU32_IMM(BPF_MOV, R3, 0x89abcdef),
+			BPF_ATOMIC_OP(BPF_W, BPF_CMPXCHG, R10, R3, -40),
 			BPF_EXIT_INSN(),
 		},
 		INTERNAL,
 		{ },
-		{ { 0, 0 } },
+		{ { 0, 0x01234567 } },
 		.stack_depth = 40,
 	},
 	{
-		"STX_XADD_W: Test side-effects, r0: 0x12 + 0x10 = 0x22",
+		"BPF_ATOMIC | BPF_W, BPF_CMPXCHG: Test failure store",
 		.u.insns_int = {
-			BPF_ALU32_IMM(BPF_MOV, R0, 0x12),
-			BPF_ST_MEM(BPF_W, R10, -40, 0x10),
-			BPF_ATOMIC_OP(BPF_W, BPF_ADD, R10, R0, -40),
+			BPF_ST_MEM(BPF_W, R10, -40, 0x01234567),
+			BPF_ALU32_IMM(BPF_MOV, R0, 0x76543210),
+			BPF_ALU32_IMM(BPF_MOV, R3, 0x89abcdef),
+			BPF_ATOMIC_OP(BPF_W, BPF_CMPXCHG, R10, R3, -40),
+			BPF_LDX_MEM(BPF_W, R0, R10, -40),
 			BPF_EXIT_INSN(),
 		},
 		INTERNAL,
 		{ },
-		{ { 0, 0x12 } },
+		{ { 0, 0x01234567 } },
 		.stack_depth = 40,
 	},
 	{
-		"STX_XADD_W: X + 1 + 1 + 1 + ...",
+		"BPF_ATOMIC | BPF_W, BPF_CMPXCHG: Test side effects",
+		.u.insns_int = {
+			BPF_ST_MEM(BPF_W, R10, -40, 0x01234567),
+			BPF_ALU32_IMM(BPF_MOV, R0, 0x01234567),
+			BPF_ALU32_IMM(BPF_MOV, R3, 0x89abcdef),
+			BPF_ATOMIC_OP(BPF_W, BPF_CMPXCHG, R10, R3, -40),
+			BPF_ATOMIC_OP(BPF_W, BPF_CMPXCHG, R10, R3, -40),
+			BPF_ALU32_REG(BPF_MOV, R0, R3),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
 		{ },
+		{ { 0, 0x89abcdef } },
+		.stack_depth = 40,
+	},
+	/* BPF_ATOMIC | BPF_DW, BPF_CMPXCHG */
+	{
+		"BPF_ATOMIC | BPF_DW, BPF_CMPXCHG: Test successful return",
+		.u.insns_int = {
+			BPF_LD_IMM64(R1, 0x0123456789abcdefULL),
+			BPF_LD_IMM64(R2, 0xfecdba9876543210ULL),
+			BPF_ALU64_REG(BPF_MOV, R0, R1),
+			BPF_STX_MEM(BPF_DW, R10, R1, -40),
+			BPF_ATOMIC_OP(BPF_DW, BPF_CMPXCHG, R10, R2, -40),
+			BPF_JMP_REG(BPF_JNE, R0, R1, 1),
+			BPF_ALU64_REG(BPF_SUB, R0, R1),
+			BPF_EXIT_INSN(),
+		},
 		INTERNAL,
 		{ },
-		{ { 0, 4134 } },
-		.fill_helper = bpf_fill_stxw,
+		{ { 0, 0 } },
+		.stack_depth = 40,
 	},
 	{
-		"STX_XADD_DW: Test: 0x12 + 0x10 = 0x22",
+		"BPF_ATOMIC | BPF_DW, BPF_CMPXCHG: Test successful store",
 		.u.insns_int = {
-			BPF_ALU32_IMM(BPF_MOV, R0, 0x12),
-			BPF_ST_MEM(BPF_DW, R10, -40, 0x10),
-			BPF_ATOMIC_OP(BPF_DW, BPF_ADD, R10, R0, -40),
+			BPF_LD_IMM64(R1, 0x0123456789abcdefULL),
+			BPF_LD_IMM64(R2, 0xfecdba9876543210ULL),
+			BPF_ALU64_REG(BPF_MOV, R0, R1),
+			BPF_STX_MEM(BPF_DW, R10, R0, -40),
+			BPF_ATOMIC_OP(BPF_DW, BPF_CMPXCHG, R10, R2, -40),
 			BPF_LDX_MEM(BPF_DW, R0, R10, -40),
+			BPF_JMP_REG(BPF_JNE, R0, R2, 1),
+			BPF_ALU64_REG(BPF_SUB, R0, R2),
 			BPF_EXIT_INSN(),
 		},
 		INTERNAL,
 		{ },
-		{ { 0, 0x22 } },
+		{ { 0, 0 } },
 		.stack_depth = 40,
 	},
 	{
-		"STX_XADD_DW: Test side-effects, r10: 0x12 + 0x10 = 0x22",
+		"BPF_ATOMIC | BPF_DW, BPF_CMPXCHG: Test failure return",
 		.u.insns_int = {
-			BPF_ALU64_REG(BPF_MOV, R1, R10),
-			BPF_ALU32_IMM(BPF_MOV, R0, 0x12),
-			BPF_ST_MEM(BPF_DW, R10, -40, 0x10),
-			BPF_ATOMIC_OP(BPF_DW, BPF_ADD, R10, R0, -40),
-			BPF_ALU64_REG(BPF_MOV, R0, R10),
+			BPF_LD_IMM64(R1, 0x0123456789abcdefULL),
+			BPF_LD_IMM64(R2, 0xfecdba9876543210ULL),
+			BPF_ALU64_REG(BPF_MOV, R0, R1),
+			BPF_ALU64_IMM(BPF_ADD, R0, 1),
+			BPF_STX_MEM(BPF_DW, R10, R1, -40),
+			BPF_ATOMIC_OP(BPF_DW, BPF_CMPXCHG, R10, R2, -40),
+			BPF_JMP_REG(BPF_JNE, R0, R1, 1),
 			BPF_ALU64_REG(BPF_SUB, R0, R1),
 			BPF_EXIT_INSN(),
 		},
@@ -4378,25 +5820,552 @@ static struct bpf_test tests[] = {
 		.stack_depth = 40,
 	},
 	{
-		"STX_XADD_DW: Test side-effects, r0: 0x12 + 0x10 = 0x22",
+		"BPF_ATOMIC | BPF_DW, BPF_CMPXCHG: Test failure store",
 		.u.insns_int = {
-			BPF_ALU32_IMM(BPF_MOV, R0, 0x12),
-			BPF_ST_MEM(BPF_DW, R10, -40, 0x10),
-			BPF_ATOMIC_OP(BPF_DW, BPF_ADD, R10, R0, -40),
+			BPF_LD_IMM64(R1, 0x0123456789abcdefULL),
+			BPF_LD_IMM64(R2, 0xfecdba9876543210ULL),
+			BPF_ALU64_REG(BPF_MOV, R0, R1),
+			BPF_ALU64_IMM(BPF_ADD, R0, 1),
+			BPF_STX_MEM(BPF_DW, R10, R1, -40),
+			BPF_ATOMIC_OP(BPF_DW, BPF_CMPXCHG, R10, R2, -40),
+			BPF_LDX_MEM(BPF_DW, R0, R10, -40),
+			BPF_JMP_REG(BPF_JNE, R0, R1, 1),
+			BPF_ALU64_REG(BPF_SUB, R0, R1),
 			BPF_EXIT_INSN(),
 		},
 		INTERNAL,
 		{ },
-		{ { 0, 0x12 } },
+		{ { 0, 0 } },
 		.stack_depth = 40,
 	},
 	{
-		"STX_XADD_DW: X + 1 + 1 + 1 + ...",
+		"BPF_ATOMIC | BPF_DW, BPF_CMPXCHG: Test side effects",
+		.u.insns_int = {
+			BPF_LD_IMM64(R1, 0x0123456789abcdefULL),
+			BPF_LD_IMM64(R2, 0xfecdba9876543210ULL),
+			BPF_ALU64_REG(BPF_MOV, R0, R1),
+			BPF_STX_MEM(BPF_DW, R10, R1, -40),
+			BPF_ATOMIC_OP(BPF_DW, BPF_CMPXCHG, R10, R2, -40),
+			BPF_LD_IMM64(R0, 0xfecdba9876543210ULL),
+			BPF_JMP_REG(BPF_JNE, R0, R2, 1),
+			BPF_ALU64_REG(BPF_SUB, R0, R2),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
 		{ },
+		{ { 0, 0 } },
+		.stack_depth = 40,
+	},
+	/* BPF_JMP32 | BPF_JEQ | BPF_K */
+	{
+		"JMP32_JEQ_K: Small immediate",
+		.u.insns_int = {
+			BPF_ALU32_IMM(BPF_MOV, R0, 123),
+			BPF_JMP32_IMM(BPF_JEQ, R0, 321, 1),
+			BPF_JMP32_IMM(BPF_JEQ, R0, 123, 1),
+			BPF_ALU32_IMM(BPF_MOV, R0, 0),
+			BPF_EXIT_INSN(),
+		},
 		INTERNAL,
 		{ },
-		{ { 0, 4134 } },
-		.fill_helper = bpf_fill_stxdw,
+		{ { 0, 123 } }
+	},
+	{
+		"JMP32_JEQ_K: Large immediate",
+		.u.insns_int = {
+			BPF_ALU32_IMM(BPF_MOV, R0, 12345678),
+			BPF_JMP32_IMM(BPF_JEQ, R0, 12345678 & 0xffff, 1),
+			BPF_JMP32_IMM(BPF_JEQ, R0, 12345678, 1),
+			BPF_ALU32_IMM(BPF_MOV, R0, 0),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 12345678 } }
+	},
+	{
+		"JMP32_JEQ_K: negative immediate",
+		.u.insns_int = {
+			BPF_ALU32_IMM(BPF_MOV, R0, -123),
+			BPF_JMP32_IMM(BPF_JEQ, R0,  123, 1),
+			BPF_JMP32_IMM(BPF_JEQ, R0, -123, 1),
+			BPF_ALU32_IMM(BPF_MOV, R0, 0),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, -123 } }
+	},
+	/* BPF_JMP32 | BPF_JEQ | BPF_X */
+	{
+		"JMP32_JEQ_X",
+		.u.insns_int = {
+			BPF_ALU32_IMM(BPF_MOV, R0, 1234),
+			BPF_ALU32_IMM(BPF_MOV, R1, 4321),
+			BPF_JMP32_REG(BPF_JEQ, R0, R1, 2),
+			BPF_ALU32_IMM(BPF_MOV, R1, 1234),
+			BPF_JMP32_REG(BPF_JEQ, R0, R1, 1),
+			BPF_ALU32_IMM(BPF_MOV, R0, 0),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 1234 } }
+	},
+	/* BPF_JMP32 | BPF_JNE | BPF_K */
+	{
+		"JMP32_JNE_K: Small immediate",
+		.u.insns_int = {
+			BPF_ALU32_IMM(BPF_MOV, R0, 123),
+			BPF_JMP32_IMM(BPF_JNE, R0, 123, 1),
+			BPF_JMP32_IMM(BPF_JNE, R0, 321, 1),
+			BPF_ALU32_IMM(BPF_MOV, R0, 0),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 123 } }
+	},
+	{
+		"JMP32_JNE_K: Large immediate",
+		.u.insns_int = {
+			BPF_ALU32_IMM(BPF_MOV, R0, 12345678),
+			BPF_JMP32_IMM(BPF_JNE, R0, 12345678, 1),
+			BPF_JMP32_IMM(BPF_JNE, R0, 12345678 & 0xffff, 1),
+			BPF_ALU32_IMM(BPF_MOV, R0, 0),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 12345678 } }
+	},
+	{
+		"JMP32_JNE_K: negative immediate",
+		.u.insns_int = {
+			BPF_ALU32_IMM(BPF_MOV, R0, -123),
+			BPF_JMP32_IMM(BPF_JNE, R0, -123, 1),
+			BPF_JMP32_IMM(BPF_JNE, R0,  123, 1),
+			BPF_ALU32_IMM(BPF_MOV, R0, 0),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, -123 } }
+	},
+	/* BPF_JMP32 | BPF_JNE | BPF_X */
+	{
+		"JMP32_JNE_X",
+		.u.insns_int = {
+			BPF_ALU32_IMM(BPF_MOV, R0, 1234),
+			BPF_ALU32_IMM(BPF_MOV, R1, 1234),
+			BPF_JMP32_REG(BPF_JNE, R0, R1, 2),
+			BPF_ALU32_IMM(BPF_MOV, R1, 4321),
+			BPF_JMP32_REG(BPF_JNE, R0, R1, 1),
+			BPF_ALU32_IMM(BPF_MOV, R0, 0),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 1234 } }
+	},
+	/* BPF_JMP32 | BPF_JSET | BPF_K */
+	{
+		"JMP32_JSET_K: Small immediate",
+		.u.insns_int = {
+			BPF_ALU32_IMM(BPF_MOV, R0, 1),
+			BPF_JMP32_IMM(BPF_JSET, R0, 2, 1),
+			BPF_JMP32_IMM(BPF_JSET, R0, 3, 1),
+			BPF_ALU32_IMM(BPF_MOV, R0, 0),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 1 } }
+	},
+	{
+		"JMP32_JSET_K: Large immediate",
+		.u.insns_int = {
+			BPF_ALU32_IMM(BPF_MOV, R0, 0x40000000),
+			BPF_JMP32_IMM(BPF_JSET, R0, 0x3fffffff, 1),
+			BPF_JMP32_IMM(BPF_JSET, R0, 0x60000000, 1),
+			BPF_ALU32_IMM(BPF_MOV, R0, 0),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 0x40000000 } }
+	},
+	{
+		"JMP32_JSET_K: negative immediate",
+		.u.insns_int = {
+			BPF_ALU32_IMM(BPF_MOV, R0, -123),
+			BPF_JMP32_IMM(BPF_JSET, R0, -1, 1),
+			BPF_ALU32_IMM(BPF_MOV, R0, 0),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, -123 } }
+	},
+	/* BPF_JMP32 | BPF_JSET | BPF_X */
+	{
+		"JMP32_JSET_X",
+		.u.insns_int = {
+			BPF_ALU32_IMM(BPF_MOV, R0, 8),
+			BPF_ALU32_IMM(BPF_MOV, R1, 7),
+			BPF_JMP32_REG(BPF_JSET, R0, R1, 2),
+			BPF_ALU32_IMM(BPF_MOV, R1, 8 | 2),
+			BPF_JMP32_REG(BPF_JNE, R0, R1, 1),
+			BPF_ALU32_IMM(BPF_MOV, R0, 0),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 8 } }
+	},
+	/* BPF_JMP32 | BPF_JGT | BPF_K */
+	{
+		"JMP32_JGT_K: Small immediate",
+		.u.insns_int = {
+			BPF_ALU32_IMM(BPF_MOV, R0, 123),
+			BPF_JMP32_IMM(BPF_JGT, R0, 123, 1),
+			BPF_JMP32_IMM(BPF_JGT, R0, 122, 1),
+			BPF_ALU32_IMM(BPF_MOV, R0, 0),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 123 } }
+	},
+	{
+		"JMP32_JGT_K: Large immediate",
+		.u.insns_int = {
+			BPF_ALU32_IMM(BPF_MOV, R0, 0xfffffffe),
+			BPF_JMP32_IMM(BPF_JGT, R0, 0xffffffff, 1),
+			BPF_JMP32_IMM(BPF_JGT, R0, 0xfffffffd, 1),
+			BPF_ALU32_IMM(BPF_MOV, R0, 0),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 0xfffffffe } }
+	},
+	/* BPF_JMP32 | BPF_JGT | BPF_X */
+	{
+		"JMP32_JGT_X",
+		.u.insns_int = {
+			BPF_ALU32_IMM(BPF_MOV, R0, 0xfffffffe),
+			BPF_ALU32_IMM(BPF_MOV, R1, 0xffffffff),
+			BPF_JMP32_REG(BPF_JGT, R0, R1, 2),
+			BPF_ALU32_IMM(BPF_MOV, R1, 0xfffffffd),
+			BPF_JMP32_REG(BPF_JGT, R0, R1, 1),
+			BPF_ALU32_IMM(BPF_MOV, R0, 0),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 0xfffffffe } }
+	},
+	/* BPF_JMP32 | BPF_JGE | BPF_K */
+	{
+		"JMP32_JGE_K: Small immediate",
+		.u.insns_int = {
+			BPF_ALU32_IMM(BPF_MOV, R0, 123),
+			BPF_JMP32_IMM(BPF_JGE, R0, 124, 1),
+			BPF_JMP32_IMM(BPF_JGE, R0, 123, 1),
+			BPF_ALU32_IMM(BPF_MOV, R0, 0),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 123 } }
+	},
+	{
+		"JMP32_JGE_K: Large immediate",
+		.u.insns_int = {
+			BPF_ALU32_IMM(BPF_MOV, R0, 0xfffffffe),
+			BPF_JMP32_IMM(BPF_JGE, R0, 0xffffffff, 1),
+			BPF_JMP32_IMM(BPF_JGE, R0, 0xfffffffe, 1),
+			BPF_ALU32_IMM(BPF_MOV, R0, 0),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 0xfffffffe } }
+	},
+	/* BPF_JMP32 | BPF_JGE | BPF_X */
+	{
+		"JMP32_JGE_X",
+		.u.insns_int = {
+			BPF_ALU32_IMM(BPF_MOV, R0, 0xfffffffe),
+			BPF_ALU32_IMM(BPF_MOV, R1, 0xffffffff),
+			BPF_JMP32_REG(BPF_JGE, R0, R1, 2),
+			BPF_ALU32_IMM(BPF_MOV, R1, 0xfffffffe),
+			BPF_JMP32_REG(BPF_JGE, R0, R1, 1),
+			BPF_ALU32_IMM(BPF_MOV, R0, 0),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 0xfffffffe } }
+	},
+	/* BPF_JMP32 | BPF_JLT | BPF_K */
+	{
+		"JMP32_JLT_K: Small immediate",
+		.u.insns_int = {
+			BPF_ALU32_IMM(BPF_MOV, R0, 123),
+			BPF_JMP32_IMM(BPF_JLT, R0, 123, 1),
+			BPF_JMP32_IMM(BPF_JLT, R0, 124, 1),
+			BPF_ALU32_IMM(BPF_MOV, R0, 0),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 123 } }
+	},
+	{
+		"JMP32_JLT_K: Large immediate",
+		.u.insns_int = {
+			BPF_ALU32_IMM(BPF_MOV, R0, 0xfffffffe),
+			BPF_JMP32_IMM(BPF_JLT, R0, 0xfffffffd, 1),
+			BPF_JMP32_IMM(BPF_JLT, R0, 0xffffffff, 1),
+			BPF_ALU32_IMM(BPF_MOV, R0, 0),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 0xfffffffe } }
+	},
+	/* BPF_JMP32 | BPF_JLT | BPF_X */
+	{
+		"JMP32_JLT_X",
+		.u.insns_int = {
+			BPF_ALU32_IMM(BPF_MOV, R0, 0xfffffffe),
+			BPF_ALU32_IMM(BPF_MOV, R1, 0xfffffffd),
+			BPF_JMP32_REG(BPF_JLT, R0, R1, 2),
+			BPF_ALU32_IMM(BPF_MOV, R1, 0xffffffff),
+			BPF_JMP32_REG(BPF_JLT, R0, R1, 1),
+			BPF_ALU32_IMM(BPF_MOV, R0, 0),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 0xfffffffe } }
+	},
+	/* BPF_JMP32 | BPF_JLE | BPF_K */
+	{
+		"JMP32_JLE_K: Small immediate",
+		.u.insns_int = {
+			BPF_ALU32_IMM(BPF_MOV, R0, 123),
+			BPF_JMP32_IMM(BPF_JLE, R0, 122, 1),
+			BPF_JMP32_IMM(BPF_JLE, R0, 123, 1),
+			BPF_ALU32_IMM(BPF_MOV, R0, 0),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 123 } }
+	},
+	{
+		"JMP32_JLE_K: Large immediate",
+		.u.insns_int = {
+			BPF_ALU32_IMM(BPF_MOV, R0, 0xfffffffe),
+			BPF_JMP32_IMM(BPF_JLE, R0, 0xfffffffd, 1),
+			BPF_JMP32_IMM(BPF_JLE, R0, 0xfffffffe, 1),
+			BPF_ALU32_IMM(BPF_MOV, R0, 0),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 0xfffffffe } }
+	},
+	/* BPF_JMP32 | BPF_JLE | BPF_X */
+	{
+		"JMP32_JLE_X",
+		.u.insns_int = {
+			BPF_ALU32_IMM(BPF_MOV, R0, 0xfffffffe),
+			BPF_ALU32_IMM(BPF_MOV, R1, 0xfffffffd),
+			BPF_JMP32_REG(BPF_JLE, R0, R1, 2),
+			BPF_ALU32_IMM(BPF_MOV, R1, 0xfffffffe),
+			BPF_JMP32_REG(BPF_JLE, R0, R1, 1),
+			BPF_ALU32_IMM(BPF_MOV, R0, 0),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, 0xfffffffe } }
+	},
+	/* BPF_JMP32 | BPF_JSGT | BPF_K */
+	{
+		"JMP32_JSGT_K: Small immediate",
+		.u.insns_int = {
+			BPF_ALU32_IMM(BPF_MOV, R0, -123),
+			BPF_JMP32_IMM(BPF_JSGT, R0, -123, 1),
+			BPF_JMP32_IMM(BPF_JSGT, R0, -124, 1),
+			BPF_ALU32_IMM(BPF_MOV, R0, 0),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, -123 } }
+	},
+	{
+		"JMP32_JSGT_K: Large immediate",
+		.u.insns_int = {
+			BPF_ALU32_IMM(BPF_MOV, R0, -12345678),
+			BPF_JMP32_IMM(BPF_JSGT, R0, -12345678, 1),
+			BPF_JMP32_IMM(BPF_JSGT, R0, -12345679, 1),
+			BPF_ALU32_IMM(BPF_MOV, R0, 0),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, -12345678 } }
+	},
+	/* BPF_JMP32 | BPF_JSGT | BPF_X */
+	{
+		"JMP32_JSGT_X",
+		.u.insns_int = {
+			BPF_ALU32_IMM(BPF_MOV, R0, -12345678),
+			BPF_ALU32_IMM(BPF_MOV, R1, -12345678),
+			BPF_JMP32_REG(BPF_JSGT, R0, R1, 2),
+			BPF_ALU32_IMM(BPF_MOV, R1, -12345679),
+			BPF_JMP32_REG(BPF_JSGT, R0, R1, 1),
+			BPF_ALU32_IMM(BPF_MOV, R0, 0),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, -12345678 } }
+	},
+	/* BPF_JMP32 | BPF_JSGE | BPF_K */
+	{
+		"JMP32_JSGE_K: Small immediate",
+		.u.insns_int = {
+			BPF_ALU32_IMM(BPF_MOV, R0, -123),
+			BPF_JMP32_IMM(BPF_JSGE, R0, -122, 1),
+			BPF_JMP32_IMM(BPF_JSGE, R0, -123, 1),
+			BPF_ALU32_IMM(BPF_MOV, R0, 0),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, -123 } }
+	},
+	{
+		"JMP32_JSGE_K: Large immediate",
+		.u.insns_int = {
+			BPF_ALU32_IMM(BPF_MOV, R0, -12345678),
+			BPF_JMP32_IMM(BPF_JSGE, R0, -12345677, 1),
+			BPF_JMP32_IMM(BPF_JSGE, R0, -12345678, 1),
+			BPF_ALU32_IMM(BPF_MOV, R0, 0),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, -12345678 } }
+	},
+	/* BPF_JMP32 | BPF_JSGE | BPF_X */
+	{
+		"JMP32_JSGE_X",
+		.u.insns_int = {
+			BPF_ALU32_IMM(BPF_MOV, R0, -12345678),
+			BPF_ALU32_IMM(BPF_MOV, R1, -12345677),
+			BPF_JMP32_REG(BPF_JSGE, R0, R1, 2),
+			BPF_ALU32_IMM(BPF_MOV, R1, -12345678),
+			BPF_JMP32_REG(BPF_JSGE, R0, R1, 1),
+			BPF_ALU32_IMM(BPF_MOV, R0, 0),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, -12345678 } }
+	},
+	/* BPF_JMP32 | BPF_JSLT | BPF_K */
+	{
+		"JMP32_JSLT_K: Small immediate",
+		.u.insns_int = {
+			BPF_ALU32_IMM(BPF_MOV, R0, -123),
+			BPF_JMP32_IMM(BPF_JSLT, R0, -123, 1),
+			BPF_JMP32_IMM(BPF_JSLT, R0, -122, 1),
+			BPF_ALU32_IMM(BPF_MOV, R0, 0),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, -123 } }
+	},
+	{
+		"JMP32_JSLT_K: Large immediate",
+		.u.insns_int = {
+			BPF_ALU32_IMM(BPF_MOV, R0, -12345678),
+			BPF_JMP32_IMM(BPF_JSLT, R0, -12345678, 1),
+			BPF_JMP32_IMM(BPF_JSLT, R0, -12345677, 1),
+			BPF_ALU32_IMM(BPF_MOV, R0, 0),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, -12345678 } }
+	},
+	/* BPF_JMP32 | BPF_JSLT | BPF_X */
+	{
+		"JMP32_JSLT_X",
+		.u.insns_int = {
+			BPF_ALU32_IMM(BPF_MOV, R0, -12345678),
+			BPF_ALU32_IMM(BPF_MOV, R1, -12345678),
+			BPF_JMP32_REG(BPF_JSLT, R0, R1, 2),
+			BPF_ALU32_IMM(BPF_MOV, R1, -12345677),
+			BPF_JMP32_REG(BPF_JSLT, R0, R1, 1),
+			BPF_ALU32_IMM(BPF_MOV, R0, 0),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, -12345678 } }
+	},
+	/* BPF_JMP32 | BPF_JSLE | BPF_K */
+	{
+		"JMP32_JSLE_K: Small immediate",
+		.u.insns_int = {
+			BPF_ALU32_IMM(BPF_MOV, R0, -123),
+			BPF_JMP32_IMM(BPF_JSLE, R0, -124, 1),
+			BPF_JMP32_IMM(BPF_JSLE, R0, -123, 1),
+			BPF_ALU32_IMM(BPF_MOV, R0, 0),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, -123 } }
+	},
+	{
+		"JMP32_JSLE_K: Large immediate",
+		.u.insns_int = {
+			BPF_ALU32_IMM(BPF_MOV, R0, -12345678),
+			BPF_JMP32_IMM(BPF_JSLE, R0, -12345679, 1),
+			BPF_JMP32_IMM(BPF_JSLE, R0, -12345678, 1),
+			BPF_ALU32_IMM(BPF_MOV, R0, 0),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, -12345678 } }
+	},
+	/* BPF_JMP32 | BPF_JSLE | BPF_K */
+	{
+		"JMP32_JSLE_X",
+		.u.insns_int = {
+			BPF_ALU32_IMM(BPF_MOV, R0, -12345678),
+			BPF_ALU32_IMM(BPF_MOV, R1, -12345679),
+			BPF_JMP32_REG(BPF_JSLE, R0, R1, 2),
+			BPF_ALU32_IMM(BPF_MOV, R1, -12345678),
+			BPF_JMP32_REG(BPF_JSLE, R0, R1, 1),
+			BPF_ALU32_IMM(BPF_MOV, R0, 0),
+			BPF_EXIT_INSN(),
+		},
+		INTERNAL,
+		{ },
+		{ { 0, -12345678 } }
 	},
 	/* BPF_JMP | BPF_EXIT */
 	{
@@ -5223,6 +7192,14 @@ static struct bpf_test tests[] = {
 		{ },
 		{ { 0, 1 } },
 	},
+	{	/* Mainly checking JIT here. */
+		"BPF_MAXINSNS: Very long conditional jump",
+		{ },
+		INTERNAL | FLAG_NO_DATA,
+		{ },
+		{ { 0, 1 } },
+		.fill_helper = bpf_fill_long_jmp,
+	},
 	{
 		"JMP_JA: Jump, gap, jump, ...",
 		{ },
@@ -7012,8 +8989,248 @@ static __init int test_bpf(void)
 	return err_cnt ? -EINVAL : 0;
 }
 
+struct tail_call_test {
+	const char *descr;
+	struct bpf_insn insns[MAX_INSNS];
+	int result;
+	int stack_depth;
+};
+
+/*
+ * Magic marker used in test snippets for tail calls below.
+ * BPF_LD/MOV to R2 and R2 with this immediate value is replaced
+ * with the proper values by the test runner.
+ */
+#define TAIL_CALL_MARKER 0x7a11ca11
+
+/* Special offset to indicate a NULL call target */
+#define TAIL_CALL_NULL 0x7fff
+
+/* Special offset to indicate an out-of-range index */
+#define TAIL_CALL_INVALID 0x7ffe
+
+#define TAIL_CALL(offset)			       \
+	BPF_LD_IMM64(R2, TAIL_CALL_MARKER),	       \
+	BPF_RAW_INSN(BPF_ALU | BPF_MOV | BPF_K, R3, 0, \
+		     offset, TAIL_CALL_MARKER),	       \
+	BPF_JMP_IMM(BPF_TAIL_CALL, 0, 0, 0)
+
+/*
+ * Tail call tests. Each test case may call any other test in the table,
+ * including itself, specified as a relative index offset from the calling
+ * test. The index TAIL_CALL_NULL can be used to specify a NULL target
+ * function to test the JIT error path. Similarly, the index TAIL_CALL_INVALID
+ * results in a target index that is out of range.
+ */
+static struct tail_call_test tail_call_tests[] = {
+	{
+		"Tail call leaf",
+		.insns = {
+			BPF_ALU64_REG(BPF_MOV, R0, R1),
+			BPF_ALU64_IMM(BPF_ADD, R0, 1),
+			BPF_EXIT_INSN(),
+		},
+		.result = 1,
+	},
+	{
+		"Tail call 2",
+		.insns = {
+			BPF_ALU64_IMM(BPF_ADD, R1, 2),
+			TAIL_CALL(-1),
+			BPF_ALU64_IMM(BPF_MOV, R0, -1),
+			BPF_EXIT_INSN(),
+		},
+		.result = 3,
+	},
+	{
+		"Tail call 3",
+		.insns = {
+			BPF_ALU64_IMM(BPF_ADD, R1, 3),
+			TAIL_CALL(-1),
+			BPF_ALU64_IMM(BPF_MOV, R0, -1),
+			BPF_EXIT_INSN(),
+		},
+		.result = 6,
+	},
+	{
+		"Tail call 4",
+		.insns = {
+			BPF_ALU64_IMM(BPF_ADD, R1, 4),
+			TAIL_CALL(-1),
+			BPF_ALU64_IMM(BPF_MOV, R0, -1),
+			BPF_EXIT_INSN(),
+		},
+		.result = 10,
+	},
+	{
+		"Tail call error path, max count reached",
+		.insns = {
+			BPF_ALU64_IMM(BPF_ADD, R1, 1),
+			BPF_ALU64_REG(BPF_MOV, R0, R1),
+			TAIL_CALL(0),
+			BPF_EXIT_INSN(),
+		},
+		.result = MAX_TAIL_CALL_CNT + 1,
+	},
+	{
+		"Tail call error path, NULL target",
+		.insns = {
+			BPF_ALU64_IMM(BPF_MOV, R0, -1),
+			TAIL_CALL(TAIL_CALL_NULL),
+			BPF_ALU64_IMM(BPF_MOV, R0, 1),
+			BPF_EXIT_INSN(),
+		},
+		.result = 1,
+	},
+	{
+		"Tail call error path, index out of range",
+		.insns = {
+			BPF_ALU64_IMM(BPF_MOV, R0, -1),
+			TAIL_CALL(TAIL_CALL_INVALID),
+			BPF_ALU64_IMM(BPF_MOV, R0, 1),
+			BPF_EXIT_INSN(),
+		},
+		.result = 1,
+	},
+};
+
+static void __init destroy_tail_call_tests(struct bpf_array *progs)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(tail_call_tests); i++)
+		if (progs->ptrs[i])
+			bpf_prog_free(progs->ptrs[i]);
+	kfree(progs);
+}
+
+static __init int prepare_tail_call_tests(struct bpf_array **pprogs)
+{
+	int ntests = ARRAY_SIZE(tail_call_tests);
+	struct bpf_array *progs;
+	int which, err;
+
+	/* Allocate the table of programs to be used for tall calls */
+	progs = kzalloc(sizeof(*progs) + (ntests + 1) * sizeof(progs->ptrs[0]),
+			GFP_KERNEL);
+	if (!progs)
+		goto out_nomem;
+
+	/* Create all eBPF programs and populate the table */
+	for (which = 0; which < ntests; which++) {
+		struct tail_call_test *test = &tail_call_tests[which];
+		struct bpf_prog *fp;
+		int len, i;
+
+		/* Compute the number of program instructions */
+		for (len = 0; len < MAX_INSNS; len++) {
+			struct bpf_insn *insn = &test->insns[len];
+
+			if (len < MAX_INSNS - 1 &&
+			    insn->code == (BPF_LD | BPF_DW | BPF_IMM))
+				len++;
+			if (insn->code == 0)
+				break;
+		}
+
+		/* Allocate and initialize the program */
+		fp = bpf_prog_alloc(bpf_prog_size(len), 0);
+		if (!fp)
+			goto out_nomem;
+
+		fp->len = len;
+		fp->type = BPF_PROG_TYPE_SOCKET_FILTER;
+		fp->aux->stack_depth = test->stack_depth;
+		memcpy(fp->insnsi, test->insns, len * sizeof(struct bpf_insn));
+
+		/* Relocate runtime tail call offsets and addresses */
+		for (i = 0; i < len; i++) {
+			struct bpf_insn *insn = &fp->insnsi[i];
+
+			if (insn->imm != TAIL_CALL_MARKER)
+				continue;
+
+			switch (insn->code) {
+			case BPF_LD | BPF_DW | BPF_IMM:
+				insn[0].imm = (u32)(long)progs;
+				insn[1].imm = ((u64)(long)progs) >> 32;
+				break;
+
+			case BPF_ALU | BPF_MOV | BPF_K:
+				if (insn->off == TAIL_CALL_NULL)
+					insn->imm = ntests;
+				else if (insn->off == TAIL_CALL_INVALID)
+					insn->imm = ntests + 1;
+				else
+					insn->imm = which + insn->off;
+				insn->off = 0;
+			}
+		}
+
+		fp = bpf_prog_select_runtime(fp, &err);
+		if (err)
+			goto out_err;
+
+		progs->ptrs[which] = fp;
+	}
+
+	/* The last entry contains a NULL program pointer */
+	progs->map.max_entries = ntests + 1;
+	*pprogs = progs;
+	return 0;
+
+out_nomem:
+	err = -ENOMEM;
+
+out_err:
+	if (progs)
+		destroy_tail_call_tests(progs);
+	return err;
+}
+
+static __init int test_tail_calls(struct bpf_array *progs)
+{
+	int i, err_cnt = 0, pass_cnt = 0;
+	int jit_cnt = 0, run_cnt = 0;
+
+	for (i = 0; i < ARRAY_SIZE(tail_call_tests); i++) {
+		struct tail_call_test *test = &tail_call_tests[i];
+		struct bpf_prog *fp = progs->ptrs[i];
+		u64 duration;
+		int ret;
+
+		cond_resched();
+
+		pr_info("#%d %s ", i, test->descr);
+		if (!fp) {
+			err_cnt++;
+			continue;
+		}
+		pr_cont("jited:%u ", fp->jited);
+
+		run_cnt++;
+		if (fp->jited)
+			jit_cnt++;
+
+		ret = __run_one(fp, NULL, MAX_TESTRUNS, &duration);
+		if (ret == test->result) {
+			pr_cont("%lld PASS", duration);
+			pass_cnt++;
+		} else {
+			pr_cont("ret %d != %d FAIL", ret, test->result);
+			err_cnt++;
+		}
+	}
+
+	pr_info("%s: Summary: %d PASSED, %d FAILED, [%d/%d JIT'ed]\n",
+		__func__, pass_cnt, err_cnt, jit_cnt, run_cnt);
+
+	return err_cnt ? -EINVAL : 0;
+}
+
 static int __init test_bpf_init(void)
 {
+	struct bpf_array *progs = NULL;
 	int ret;
 
 	ret = prepare_bpf_tests();
@@ -7025,6 +9242,14 @@ static int __init test_bpf_init(void)
 	if (ret)
 		return ret;
 
+	ret = prepare_tail_call_tests(&progs);
+	if (ret)
+		return ret;
+	ret = test_tail_calls(progs);
+	destroy_tail_call_tests(progs);
+	if (ret)
+		return ret;
+
 	return test_skb_segment();
 }
 
diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c
index 695449088e42..335e1d8c17f8 100644
--- a/net/bpf/test_run.c
+++ b/net/bpf/test_run.c
@@ -763,8 +763,7 @@ int bpf_prog_test_run_xdp(struct bpf_prog *prog, const union bpf_attr *kattr,
 	if (prog->expected_attach_type == BPF_XDP_DEVMAP ||
 	    prog->expected_attach_type == BPF_XDP_CPUMAP)
 		return -EINVAL;
-	if (kattr->test.ctx_in || kattr->test.ctx_out)
-		return -EINVAL;
+
 	ctx = bpf_ctx_init(kattr, sizeof(struct xdp_md));
 	if (IS_ERR(ctx))
 		return PTR_ERR(ctx);
diff --git a/net/core/dev.c b/net/core/dev.c
index eaaeff404ce9..88650791c360 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -7532,7 +7532,7 @@ void *netdev_lower_get_next_private_rcu(struct net_device *dev,
 {
 	struct netdev_adjacent *lower;
 
-	WARN_ON_ONCE(!rcu_read_lock_held());
+	WARN_ON_ONCE(!rcu_read_lock_held() && !rcu_read_lock_bh_held());
 
 	lower = list_entry_rcu((*iter)->next, struct netdev_adjacent, list);
 
@@ -9297,7 +9297,7 @@ 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;
@@ -9307,6 +9307,7 @@ 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)
 {
@@ -9400,6 +9401,8 @@ 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;
@@ -9438,6 +9441,14 @@ 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) {
diff --git a/net/core/filter.c b/net/core/filter.c
index 6f493ef5bb14..3aca07c44fad 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -3933,6 +3933,31 @@ 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)
 {
diff --git a/net/unix/unix_bpf.c b/net/unix/unix_bpf.c
index 177e883f451e..20f53575b5c9 100644
--- a/net/unix/unix_bpf.c
+++ b/net/unix/unix_bpf.c
@@ -105,6 +105,9 @@ static void unix_bpf_check_needs_rebuild(struct proto *ops)
 
 int unix_bpf_update_proto(struct sock *sk, struct sk_psock *psock, bool restore)
 {
+	if (sk->sk_type != SOCK_DGRAM)
+		return -EOPNOTSUPP;
+
 	if (restore) {
 		sk->sk_write_space = psock->saved_write_space;
 		WRITE_ONCE(sk->sk_prot, psock->sk_proto);
diff --git a/samples/bpf/xdp1_kern.c b/samples/bpf/xdp1_kern.c
index 34b64394ed9c..f0c5d95084de 100644
--- a/samples/bpf/xdp1_kern.c
+++ b/samples/bpf/xdp1_kern.c
@@ -57,6 +57,7 @@ int xdp_prog1(struct xdp_md *ctx)
 
 	h_proto = eth->h_proto;
 
+	/* Handle VLAN tagged packet */
 	if (h_proto == htons(ETH_P_8021Q) || h_proto == htons(ETH_P_8021AD)) {
 		struct vlan_hdr *vhdr;
 
@@ -66,6 +67,7 @@ int xdp_prog1(struct xdp_md *ctx)
 			return rc;
 		h_proto = vhdr->h_vlan_encapsulated_proto;
 	}
+	/* Handle double VLAN tagged packet */
 	if (h_proto == htons(ETH_P_8021Q) || h_proto == htons(ETH_P_8021AD)) {
 		struct vlan_hdr *vhdr;
 
diff --git a/samples/bpf/xdp2_kern.c b/samples/bpf/xdp2_kern.c
index c787f4b49646..d8a64ab077b0 100644
--- a/samples/bpf/xdp2_kern.c
+++ b/samples/bpf/xdp2_kern.c
@@ -73,6 +73,7 @@ int xdp_prog1(struct xdp_md *ctx)
 
 	h_proto = eth->h_proto;
 
+	/* Handle VLAN tagged packet */
 	if (h_proto == htons(ETH_P_8021Q) || h_proto == htons(ETH_P_8021AD)) {
 		struct vlan_hdr *vhdr;
 
@@ -82,6 +83,7 @@ int xdp_prog1(struct xdp_md *ctx)
 			return rc;
 		h_proto = vhdr->h_vlan_encapsulated_proto;
 	}
+	/* Handle double VLAN tagged packet */
 	if (h_proto == htons(ETH_P_8021Q) || h_proto == htons(ETH_P_8021AD)) {
 		struct vlan_hdr *vhdr;
 
diff --git a/samples/bpf/xdp_redirect_cpu_user.c b/samples/bpf/xdp_redirect_cpu_user.c
index d3ecdc18b9c1..9e225c96b77e 100644
--- a/samples/bpf/xdp_redirect_cpu_user.c
+++ b/samples/bpf/xdp_redirect_cpu_user.c
@@ -841,7 +841,7 @@ int main(int argc, char **argv)
 	memset(cpu, 0, n_cpus * sizeof(int));
 
 	/* Parse commands line args */
-	while ((opt = getopt_long(argc, argv, "hSd:s:p:q:c:xzFf:e:r:m:",
+	while ((opt = getopt_long(argc, argv, "hSd:s:p:q:c:xzFf:e:r:m:n",
 				  long_options, &longindex)) != -1) {
 		switch (opt) {
 		case 'd':
diff --git a/samples/bpf/xdpsock_user.c b/samples/bpf/xdpsock_user.c
index 33d0bdebbed8..49d7a6ad7e39 100644
--- a/samples/bpf/xdpsock_user.c
+++ b/samples/bpf/xdpsock_user.c
@@ -1,12 +1,10 @@
 // SPDX-License-Identifier: GPL-2.0
 /* Copyright(c) 2017 - 2018 Intel Corporation. */
 
-#include <asm/barrier.h>
 #include <errno.h>
 #include <getopt.h>
 #include <libgen.h>
 #include <linux/bpf.h>
-#include <linux/compiler.h>
 #include <linux/if_link.h>
 #include <linux/if_xdp.h>
 #include <linux/if_ether.h>
@@ -653,17 +651,15 @@ out:
 	return result;
 }
 
-__sum16 ip_fast_csum(const void *iph, unsigned int ihl);
-
 /*
  *	This is a version of ip_compute_csum() optimized for IP headers,
  *	which always checksum on 4 octet boundaries.
  *	This function code has been taken from
  *	Linux kernel lib/checksum.c
  */
-__sum16 ip_fast_csum(const void *iph, unsigned int ihl)
+static inline __sum16 ip_fast_csum(const void *iph, unsigned int ihl)
 {
-	return (__force __sum16)~do_csum(iph, ihl * 4);
+	return (__sum16)~do_csum(iph, ihl * 4);
 }
 
 /*
@@ -673,11 +669,11 @@ __sum16 ip_fast_csum(const void *iph, unsigned int ihl)
  */
 static inline __sum16 csum_fold(__wsum csum)
 {
-	u32 sum = (__force u32)csum;
+	u32 sum = (u32)csum;
 
 	sum = (sum & 0xffff) + (sum >> 16);
 	sum = (sum & 0xffff) + (sum >> 16);
-	return (__force __sum16)~sum;
+	return (__sum16)~sum;
 }
 
 /*
@@ -703,16 +699,16 @@ __wsum csum_tcpudp_nofold(__be32 saddr, __be32 daddr,
 __wsum csum_tcpudp_nofold(__be32 saddr, __be32 daddr,
 			  __u32 len, __u8 proto, __wsum sum)
 {
-	unsigned long long s = (__force u32)sum;
+	unsigned long long s = (u32)sum;
 
-	s += (__force u32)saddr;
-	s += (__force u32)daddr;
+	s += (u32)saddr;
+	s += (u32)daddr;
 #ifdef __BIG_ENDIAN__
 	s += proto + len;
 #else
 	s += (proto + len) << 8;
 #endif
-	return (__force __wsum)from64to32(s);
+	return (__wsum)from64to32(s);
 }
 
 /*
diff --git a/tools/testing/selftests/bpf/.gitignore b/tools/testing/selftests/bpf/.gitignore
index addcfd8b615e..433f8bef261e 100644
--- a/tools/testing/selftests/bpf/.gitignore
+++ b/tools/testing/selftests/bpf/.gitignore
@@ -23,7 +23,6 @@ test_skb_cgroup_id_user
 test_cgroup_storage
 test_flow_dissector
 flow_dissector_load
-test_netcnt
 test_tcpnotify_user
 test_libbpf
 test_tcp_check_syncookie_user
diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
index f405b20c1e6c..2a58b7b5aea4 100644
--- a/tools/testing/selftests/bpf/Makefile
+++ b/tools/testing/selftests/bpf/Makefile
@@ -38,7 +38,7 @@ TEST_GEN_PROGS = test_verifier test_tag test_maps test_lru_map test_lpm_map test
 	test_verifier_log test_dev_cgroup \
 	test_sock test_sockmap get_cgroup_id_user \
 	test_cgroup_storage \
-	test_netcnt test_tcpnotify_user test_sysctl \
+	test_tcpnotify_user test_sysctl \
 	test_progs-no_alu32
 
 # Also test bpf-gcc, if present
@@ -197,7 +197,6 @@ $(OUTPUT)/test_sockmap: cgroup_helpers.c
 $(OUTPUT)/test_tcpnotify_user: cgroup_helpers.c trace_helpers.c
 $(OUTPUT)/get_cgroup_id_user: cgroup_helpers.c
 $(OUTPUT)/test_cgroup_storage: cgroup_helpers.c
-$(OUTPUT)/test_netcnt: cgroup_helpers.c
 $(OUTPUT)/test_sock_fields: cgroup_helpers.c
 $(OUTPUT)/test_sysctl: cgroup_helpers.c
 
diff --git a/tools/testing/selftests/bpf/network_helpers.c b/tools/testing/selftests/bpf/network_helpers.c
index 26468a8f44f3..d6857683397f 100644
--- a/tools/testing/selftests/bpf/network_helpers.c
+++ b/tools/testing/selftests/bpf/network_helpers.c
@@ -310,3 +310,15 @@ int make_sockaddr(int family, const char *addr_str, __u16 port,
 	}
 	return -1;
 }
+
+char *ping_command(int family)
+{
+	if (family == AF_INET6) {
+		/* On some systems 'ping' doesn't support IPv6, so use ping6 if it is present. */
+		if (!system("which ping6 >/dev/null 2>&1"))
+			return "ping6";
+		else
+			return "ping -6";
+	}
+	return "ping";
+}
diff --git a/tools/testing/selftests/bpf/network_helpers.h b/tools/testing/selftests/bpf/network_helpers.h
index d60bc2897770..c59a8f6d770b 100644
--- a/tools/testing/selftests/bpf/network_helpers.h
+++ b/tools/testing/selftests/bpf/network_helpers.h
@@ -46,5 +46,6 @@ int fastopen_connect(int server_fd, const char *data, unsigned int data_len,
 		     int timeout_ms);
 int make_sockaddr(int family, const char *addr_str, __u16 port,
 		  struct sockaddr_storage *addr, socklen_t *len);
+char *ping_command(int family);
 
 #endif
diff --git a/tools/testing/selftests/bpf/prog_tests/netcnt.c b/tools/testing/selftests/bpf/prog_tests/netcnt.c
new file mode 100644
index 000000000000..6ede48bde91b
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/netcnt.c
@@ -0,0 +1,82 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <sys/sysinfo.h>
+#include <test_progs.h>
+#include "network_helpers.h"
+#include "netcnt_prog.skel.h"
+#include "netcnt_common.h"
+
+#define CG_NAME "/netcnt"
+
+void test_netcnt(void)
+{
+	union percpu_net_cnt *percpu_netcnt = NULL;
+	struct bpf_cgroup_storage_key key;
+	int map_fd, percpu_map_fd;
+	struct netcnt_prog *skel;
+	unsigned long packets;
+	union net_cnt netcnt;
+	unsigned long bytes;
+	int cpu, nproc;
+	int cg_fd = -1;
+	char cmd[128];
+
+	skel = netcnt_prog__open_and_load();
+	if (!ASSERT_OK_PTR(skel, "netcnt_prog__open_and_load"))
+		return;
+
+	nproc = get_nprocs_conf();
+	percpu_netcnt = malloc(sizeof(*percpu_netcnt) * nproc);
+	if (!ASSERT_OK_PTR(percpu_netcnt, "malloc(percpu_netcnt)"))
+		goto err;
+
+	cg_fd = test__join_cgroup(CG_NAME);
+	if (!ASSERT_GE(cg_fd, 0, "test__join_cgroup"))
+		goto err;
+
+	skel->links.bpf_nextcnt = bpf_program__attach_cgroup(skel->progs.bpf_nextcnt, cg_fd);
+	if (!ASSERT_OK_PTR(skel->links.bpf_nextcnt,
+			   "attach_cgroup(bpf_nextcnt)"))
+		goto err;
+
+	snprintf(cmd, sizeof(cmd), "%s ::1 -A -c 10000 -q > /dev/null", ping_command(AF_INET6));
+	ASSERT_OK(system(cmd), cmd);
+
+	map_fd = bpf_map__fd(skel->maps.netcnt);
+	if (!ASSERT_OK(bpf_map_get_next_key(map_fd, NULL, &key), "bpf_map_get_next_key"))
+		goto err;
+
+	if (!ASSERT_OK(bpf_map_lookup_elem(map_fd, &key, &netcnt), "bpf_map_lookup_elem(netcnt)"))
+		goto err;
+
+	percpu_map_fd = bpf_map__fd(skel->maps.percpu_netcnt);
+	if (!ASSERT_OK(bpf_map_lookup_elem(percpu_map_fd, &key, &percpu_netcnt[0]),
+		       "bpf_map_lookup_elem(percpu_netcnt)"))
+		goto err;
+
+	/* Some packets can be still in per-cpu cache, but not more than
+	 * MAX_PERCPU_PACKETS.
+	 */
+	packets = netcnt.packets;
+	bytes = netcnt.bytes;
+	for (cpu = 0; cpu < nproc; cpu++) {
+		ASSERT_LE(percpu_netcnt[cpu].packets, MAX_PERCPU_PACKETS, "MAX_PERCPU_PACKETS");
+
+		packets += percpu_netcnt[cpu].packets;
+		bytes += percpu_netcnt[cpu].bytes;
+	}
+
+	/* No packets should be lost */
+	ASSERT_EQ(packets, 10000, "packets");
+
+	/* Let's check that bytes counter matches the number of packets
+	 * multiplied by the size of ipv6 ICMP packet.
+	 */
+	ASSERT_EQ(bytes, packets * 104, "bytes");
+
+err:
+	if (cg_fd != -1)
+		close(cg_fd);
+	free(percpu_netcnt);
+	netcnt_prog__destroy(skel);
+}
diff --git a/tools/testing/selftests/bpf/prog_tests/reference_tracking.c b/tools/testing/selftests/bpf/prog_tests/reference_tracking.c
index de2688166696..4e91f4d6466c 100644
--- a/tools/testing/selftests/bpf/prog_tests/reference_tracking.c
+++ b/tools/testing/selftests/bpf/prog_tests/reference_tracking.c
@@ -34,8 +34,8 @@ void test_reference_tracking(void)
 		if (!test__start_subtest(title))
 			continue;
 
-		/* Expect verifier failure if test name has 'fail' */
-		if (strstr(title, "fail") != NULL) {
+		/* Expect verifier failure if test name has 'err' */
+		if (strstr(title, "err_") != NULL) {
 			libbpf_print_fn_t old_print_fn;
 
 			old_print_fn = libbpf_set_print(NULL);
diff --git a/tools/testing/selftests/bpf/prog_tests/tc_redirect.c b/tools/testing/selftests/bpf/prog_tests/tc_redirect.c
index 932e4ee3f97c..e7201ba29ccd 100644
--- a/tools/testing/selftests/bpf/prog_tests/tc_redirect.c
+++ b/tools/testing/selftests/bpf/prog_tests/tc_redirect.c
@@ -390,18 +390,6 @@ done:
 		close(client_fd);
 }
 
-static char *ping_command(int family)
-{
-	if (family == AF_INET6) {
-		/* On some systems 'ping' doesn't support IPv6, so use ping6 if it is present. */
-		if (!system("which ping6 >/dev/null 2>&1"))
-			return "ping6";
-		else
-			return "ping -6";
-	}
-	return "ping";
-}
-
 static int test_ping(int family, const char *addr)
 {
 	SYS("ip netns exec " NS_SRC " %s " PING_ARGS " %s > /dev/null", ping_command(family), addr);
diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_bonding.c b/tools/testing/selftests/bpf/prog_tests/xdp_bonding.c
new file mode 100644
index 000000000000..6b186b4238d0
--- /dev/null
+++ b/tools/testing/selftests/bpf/prog_tests/xdp_bonding.c
@@ -0,0 +1,520 @@
+// SPDX-License-Identifier: GPL-2.0
+
+/**
+ * Test XDP bonding support
+ *
+ * Sets up two bonded veth pairs between two fresh namespaces
+ * and verifies that XDP_TX program loaded on a bond device
+ * are correctly loaded onto the slave devices and XDP_TX'd
+ * packets are balanced using bonding.
+ */
+
+#define _GNU_SOURCE
+#include <sched.h>
+#include <net/if.h>
+#include <linux/if_link.h>
+#include "test_progs.h"
+#include "network_helpers.h"
+#include <linux/if_bonding.h>
+#include <linux/limits.h>
+#include <linux/udp.h>
+
+#include "xdp_dummy.skel.h"
+#include "xdp_redirect_multi_kern.skel.h"
+#include "xdp_tx.skel.h"
+
+#define BOND1_MAC {0x00, 0x11, 0x22, 0x33, 0x44, 0x55}
+#define BOND1_MAC_STR "00:11:22:33:44:55"
+#define BOND2_MAC {0x00, 0x22, 0x33, 0x44, 0x55, 0x66}
+#define BOND2_MAC_STR "00:22:33:44:55:66"
+#define NPACKETS 100
+
+static int root_netns_fd = -1;
+
+static void restore_root_netns(void)
+{
+	ASSERT_OK(setns(root_netns_fd, CLONE_NEWNET), "restore_root_netns");
+}
+
+static int setns_by_name(char *name)
+{
+	int nsfd, err;
+	char nspath[PATH_MAX];
+
+	snprintf(nspath, sizeof(nspath), "%s/%s", "/var/run/netns", name);
+	nsfd = open(nspath, O_RDONLY | O_CLOEXEC);
+	if (nsfd < 0)
+		return -1;
+
+	err = setns(nsfd, CLONE_NEWNET);
+	close(nsfd);
+	return err;
+}
+
+static int get_rx_packets(const char *iface)
+{
+	FILE *f;
+	char line[512];
+	int iface_len = strlen(iface);
+
+	f = fopen("/proc/net/dev", "r");
+	if (!f)
+		return -1;
+
+	while (fgets(line, sizeof(line), f)) {
+		char *p = line;
+
+		while (*p == ' ')
+			p++; /* skip whitespace */
+		if (!strncmp(p, iface, iface_len)) {
+			p += iface_len;
+			if (*p++ != ':')
+				continue;
+			while (*p == ' ')
+				p++; /* skip whitespace */
+			while (*p && *p != ' ')
+				p++; /* skip rx bytes */
+			while (*p == ' ')
+				p++; /* skip whitespace */
+			fclose(f);
+			return atoi(p);
+		}
+	}
+	fclose(f);
+	return -1;
+}
+
+#define MAX_BPF_LINKS 8
+
+struct skeletons {
+	struct xdp_dummy *xdp_dummy;
+	struct xdp_tx *xdp_tx;
+	struct xdp_redirect_multi_kern *xdp_redirect_multi_kern;
+
+	int nlinks;
+	struct bpf_link *links[MAX_BPF_LINKS];
+};
+
+static int xdp_attach(struct skeletons *skeletons, struct bpf_program *prog, char *iface)
+{
+	struct bpf_link *link;
+	int ifindex;
+
+	ifindex = if_nametoindex(iface);
+	if (!ASSERT_GT(ifindex, 0, "get ifindex"))
+		return -1;
+
+	if (!ASSERT_LE(skeletons->nlinks+1, MAX_BPF_LINKS, "too many XDP programs attached"))
+		return -1;
+
+	link = bpf_program__attach_xdp(prog, ifindex);
+	if (!ASSERT_OK_PTR(link, "attach xdp program"))
+		return -1;
+
+	skeletons->links[skeletons->nlinks++] = link;
+	return 0;
+}
+
+enum {
+	BOND_ONE_NO_ATTACH = 0,
+	BOND_BOTH_AND_ATTACH,
+};
+
+static const char * const mode_names[] = {
+	[BOND_MODE_ROUNDROBIN]   = "balance-rr",
+	[BOND_MODE_ACTIVEBACKUP] = "active-backup",
+	[BOND_MODE_XOR]          = "balance-xor",
+	[BOND_MODE_BROADCAST]    = "broadcast",
+	[BOND_MODE_8023AD]       = "802.3ad",
+	[BOND_MODE_TLB]          = "balance-tlb",
+	[BOND_MODE_ALB]          = "balance-alb",
+};
+
+static const char * const xmit_policy_names[] = {
+	[BOND_XMIT_POLICY_LAYER2]       = "layer2",
+	[BOND_XMIT_POLICY_LAYER34]      = "layer3+4",
+	[BOND_XMIT_POLICY_LAYER23]      = "layer2+3",
+	[BOND_XMIT_POLICY_ENCAP23]      = "encap2+3",
+	[BOND_XMIT_POLICY_ENCAP34]      = "encap3+4",
+};
+
+static int bonding_setup(struct skeletons *skeletons, int mode, int xmit_policy,
+			 int bond_both_attach)
+{
+#define SYS(fmt, ...)						\
+	({							\
+		char cmd[1024];					\
+		snprintf(cmd, sizeof(cmd), fmt, ##__VA_ARGS__);	\
+		if (!ASSERT_OK(system(cmd), cmd))		\
+			return -1;				\
+	})
+
+	SYS("ip netns add ns_dst");
+	SYS("ip link add veth1_1 type veth peer name veth2_1 netns ns_dst");
+	SYS("ip link add veth1_2 type veth peer name veth2_2 netns ns_dst");
+
+	SYS("ip link add bond1 type bond mode %s xmit_hash_policy %s",
+	    mode_names[mode], xmit_policy_names[xmit_policy]);
+	SYS("ip link set bond1 up address " BOND1_MAC_STR " addrgenmode none");
+	SYS("ip -netns ns_dst link add bond2 type bond mode %s xmit_hash_policy %s",
+	    mode_names[mode], xmit_policy_names[xmit_policy]);
+	SYS("ip -netns ns_dst link set bond2 up address " BOND2_MAC_STR " addrgenmode none");
+
+	SYS("ip link set veth1_1 master bond1");
+	if (bond_both_attach == BOND_BOTH_AND_ATTACH) {
+		SYS("ip link set veth1_2 master bond1");
+	} else {
+		SYS("ip link set veth1_2 up addrgenmode none");
+
+		if (xdp_attach(skeletons, skeletons->xdp_dummy->progs.xdp_dummy_prog, "veth1_2"))
+			return -1;
+	}
+
+	SYS("ip -netns ns_dst link set veth2_1 master bond2");
+
+	if (bond_both_attach == BOND_BOTH_AND_ATTACH)
+		SYS("ip -netns ns_dst link set veth2_2 master bond2");
+	else
+		SYS("ip -netns ns_dst link set veth2_2 up addrgenmode none");
+
+	/* Load a dummy program on sending side as with veth peer needs to have a
+	 * XDP program loaded as well.
+	 */
+	if (xdp_attach(skeletons, skeletons->xdp_dummy->progs.xdp_dummy_prog, "bond1"))
+		return -1;
+
+	if (bond_both_attach == BOND_BOTH_AND_ATTACH) {
+		if (!ASSERT_OK(setns_by_name("ns_dst"), "set netns to ns_dst"))
+			return -1;
+
+		if (xdp_attach(skeletons, skeletons->xdp_tx->progs.xdp_tx, "bond2"))
+			return -1;
+
+		restore_root_netns();
+	}
+
+	return 0;
+
+#undef SYS
+}
+
+static void bonding_cleanup(struct skeletons *skeletons)
+{
+	restore_root_netns();
+	while (skeletons->nlinks) {
+		skeletons->nlinks--;
+		bpf_link__destroy(skeletons->links[skeletons->nlinks]);
+	}
+	ASSERT_OK(system("ip link delete bond1"), "delete bond1");
+	ASSERT_OK(system("ip link delete veth1_1"), "delete veth1_1");
+	ASSERT_OK(system("ip link delete veth1_2"), "delete veth1_2");
+	ASSERT_OK(system("ip netns delete ns_dst"), "delete ns_dst");
+}
+
+static int send_udp_packets(int vary_dst_ip)
+{
+	struct ethhdr eh = {
+		.h_source = BOND1_MAC,
+		.h_dest = BOND2_MAC,
+		.h_proto = htons(ETH_P_IP),
+	};
+	uint8_t buf[128] = {};
+	struct iphdr *iph = (struct iphdr *)(buf + sizeof(eh));
+	struct udphdr *uh = (struct udphdr *)(buf + sizeof(eh) + sizeof(*iph));
+	int i, s = -1;
+	int ifindex;
+
+	s = socket(AF_PACKET, SOCK_RAW, IPPROTO_RAW);
+	if (!ASSERT_GE(s, 0, "socket"))
+		goto err;
+
+	ifindex = if_nametoindex("bond1");
+	if (!ASSERT_GT(ifindex, 0, "get bond1 ifindex"))
+		goto err;
+
+	memcpy(buf, &eh, sizeof(eh));
+	iph->ihl = 5;
+	iph->version = 4;
+	iph->tos = 16;
+	iph->id = 1;
+	iph->ttl = 64;
+	iph->protocol = IPPROTO_UDP;
+	iph->saddr = 1;
+	iph->daddr = 2;
+	iph->tot_len = htons(sizeof(buf) - ETH_HLEN);
+	iph->check = 0;
+
+	for (i = 1; i <= NPACKETS; i++) {
+		int n;
+		struct sockaddr_ll saddr_ll = {
+			.sll_ifindex = ifindex,
+			.sll_halen = ETH_ALEN,
+			.sll_addr = BOND2_MAC,
+		};
+
+		/* vary the UDP destination port for even distribution with roundrobin/xor modes */
+		uh->dest++;
+
+		if (vary_dst_ip)
+			iph->daddr++;
+
+		n = sendto(s, buf, sizeof(buf), 0, (struct sockaddr *)&saddr_ll, sizeof(saddr_ll));
+		if (!ASSERT_EQ(n, sizeof(buf), "sendto"))
+			goto err;
+	}
+
+	return 0;
+
+err:
+	if (s >= 0)
+		close(s);
+	return -1;
+}
+
+static void test_xdp_bonding_with_mode(struct skeletons *skeletons, int mode, int xmit_policy)
+{
+	int bond1_rx;
+
+	if (bonding_setup(skeletons, mode, xmit_policy, BOND_BOTH_AND_ATTACH))
+		goto out;
+
+	if (send_udp_packets(xmit_policy != BOND_XMIT_POLICY_LAYER34))
+		goto out;
+
+	bond1_rx = get_rx_packets("bond1");
+	ASSERT_EQ(bond1_rx, NPACKETS, "expected more received packets");
+
+	switch (mode) {
+	case BOND_MODE_ROUNDROBIN:
+	case BOND_MODE_XOR: {
+		int veth1_rx = get_rx_packets("veth1_1");
+		int veth2_rx = get_rx_packets("veth1_2");
+		int diff = abs(veth1_rx - veth2_rx);
+
+		ASSERT_GE(veth1_rx + veth2_rx, NPACKETS, "expected more packets");
+
+		switch (xmit_policy) {
+		case BOND_XMIT_POLICY_LAYER2:
+			ASSERT_GE(diff, NPACKETS,
+				  "expected packets on only one of the interfaces");
+			break;
+		case BOND_XMIT_POLICY_LAYER23:
+		case BOND_XMIT_POLICY_LAYER34:
+			ASSERT_LT(diff, NPACKETS/2,
+				  "expected even distribution of packets");
+			break;
+		default:
+			PRINT_FAIL("Unimplemented xmit_policy=%d\n", xmit_policy);
+			break;
+		}
+		break;
+	}
+	case BOND_MODE_ACTIVEBACKUP: {
+		int veth1_rx = get_rx_packets("veth1_1");
+		int veth2_rx = get_rx_packets("veth1_2");
+		int diff = abs(veth1_rx - veth2_rx);
+
+		ASSERT_GE(diff, NPACKETS,
+			  "expected packets on only one of the interfaces");
+		break;
+	}
+	default:
+		PRINT_FAIL("Unimplemented xmit_policy=%d\n", xmit_policy);
+		break;
+	}
+
+out:
+	bonding_cleanup(skeletons);
+}
+
+/* Test the broadcast redirection using xdp_redirect_map_multi_prog and adding
+ * all the interfaces to it and checking that broadcasting won't send the packet
+ * to neither the ingress bond device (bond2) or its slave (veth2_1).
+ */
+static void test_xdp_bonding_redirect_multi(struct skeletons *skeletons)
+{
+	static const char * const ifaces[] = {"bond2", "veth2_1", "veth2_2"};
+	int veth1_1_rx, veth1_2_rx;
+	int err;
+
+	if (bonding_setup(skeletons, BOND_MODE_ROUNDROBIN, BOND_XMIT_POLICY_LAYER23,
+			  BOND_ONE_NO_ATTACH))
+		goto out;
+
+
+	if (!ASSERT_OK(setns_by_name("ns_dst"), "could not set netns to ns_dst"))
+		goto out;
+
+	/* populate the devmap with the relevant interfaces */
+	for (int i = 0; i < ARRAY_SIZE(ifaces); i++) {
+		int ifindex = if_nametoindex(ifaces[i]);
+		int map_fd = bpf_map__fd(skeletons->xdp_redirect_multi_kern->maps.map_all);
+
+		if (!ASSERT_GT(ifindex, 0, "could not get interface index"))
+			goto out;
+
+		err = bpf_map_update_elem(map_fd, &ifindex, &ifindex, 0);
+		if (!ASSERT_OK(err, "add interface to map_all"))
+			goto out;
+	}
+
+	if (xdp_attach(skeletons,
+		       skeletons->xdp_redirect_multi_kern->progs.xdp_redirect_map_multi_prog,
+		       "bond2"))
+		goto out;
+
+	restore_root_netns();
+
+	if (send_udp_packets(BOND_MODE_ROUNDROBIN))
+		goto out;
+
+	veth1_1_rx = get_rx_packets("veth1_1");
+	veth1_2_rx = get_rx_packets("veth1_2");
+
+	ASSERT_EQ(veth1_1_rx, 0, "expected no packets on veth1_1");
+	ASSERT_GE(veth1_2_rx, NPACKETS, "expected packets on veth1_2");
+
+out:
+	restore_root_netns();
+	bonding_cleanup(skeletons);
+}
+
+/* Test that XDP programs cannot be attached to both the bond master and slaves simultaneously */
+static void test_xdp_bonding_attach(struct skeletons *skeletons)
+{
+	struct bpf_link *link = NULL;
+	struct bpf_link *link2 = NULL;
+	int veth, bond;
+	int err;
+
+	if (!ASSERT_OK(system("ip link add veth type veth"), "add veth"))
+		goto out;
+	if (!ASSERT_OK(system("ip link add bond type bond"), "add bond"))
+		goto out;
+
+	veth = if_nametoindex("veth");
+	if (!ASSERT_GE(veth, 0, "if_nametoindex veth"))
+		goto out;
+	bond = if_nametoindex("bond");
+	if (!ASSERT_GE(bond, 0, "if_nametoindex bond"))
+		goto out;
+
+	/* enslaving with a XDP program loaded fails */
+	link = bpf_program__attach_xdp(skeletons->xdp_dummy->progs.xdp_dummy_prog, veth);
+	if (!ASSERT_OK_PTR(link, "attach program to veth"))
+		goto out;
+
+	err = system("ip link set veth master bond");
+	if (!ASSERT_NEQ(err, 0, "attaching slave with xdp program expected to fail"))
+		goto out;
+
+	bpf_link__destroy(link);
+	link = NULL;
+
+	err = system("ip link set veth master bond");
+	if (!ASSERT_OK(err, "set veth master"))
+		goto out;
+
+	/* attaching to slave when master has no program is allowed */
+	link = bpf_program__attach_xdp(skeletons->xdp_dummy->progs.xdp_dummy_prog, veth);
+	if (!ASSERT_OK_PTR(link, "attach program to slave when enslaved"))
+		goto out;
+
+	/* attaching to master not allowed when slave has program loaded */
+	link2 = bpf_program__attach_xdp(skeletons->xdp_dummy->progs.xdp_dummy_prog, bond);
+	if (!ASSERT_ERR_PTR(link2, "attach program to master when slave has program"))
+		goto out;
+
+	bpf_link__destroy(link);
+	link = NULL;
+
+	/* attaching XDP program to master allowed when slave has no program */
+	link = bpf_program__attach_xdp(skeletons->xdp_dummy->progs.xdp_dummy_prog, bond);
+	if (!ASSERT_OK_PTR(link, "attach program to master"))
+		goto out;
+
+	/* attaching to slave not allowed when master has program loaded */
+	link2 = bpf_program__attach_xdp(skeletons->xdp_dummy->progs.xdp_dummy_prog, bond);
+	ASSERT_ERR_PTR(link2, "attach program to slave when master has program");
+
+out:
+	bpf_link__destroy(link);
+	bpf_link__destroy(link2);
+
+	system("ip link del veth");
+	system("ip link del bond");
+}
+
+static int libbpf_debug_print(enum libbpf_print_level level,
+			      const char *format, va_list args)
+{
+	if (level != LIBBPF_WARN)
+		vprintf(format, args);
+	return 0;
+}
+
+struct bond_test_case {
+	char *name;
+	int mode;
+	int xmit_policy;
+};
+
+static struct bond_test_case bond_test_cases[] = {
+	{ "xdp_bonding_roundrobin", BOND_MODE_ROUNDROBIN, BOND_XMIT_POLICY_LAYER23, },
+	{ "xdp_bonding_activebackup", BOND_MODE_ACTIVEBACKUP, BOND_XMIT_POLICY_LAYER23 },
+
+	{ "xdp_bonding_xor_layer2", BOND_MODE_XOR, BOND_XMIT_POLICY_LAYER2, },
+	{ "xdp_bonding_xor_layer23", BOND_MODE_XOR, BOND_XMIT_POLICY_LAYER23, },
+	{ "xdp_bonding_xor_layer34", BOND_MODE_XOR, BOND_XMIT_POLICY_LAYER34, },
+};
+
+void test_xdp_bonding(void)
+{
+	libbpf_print_fn_t old_print_fn;
+	struct skeletons skeletons = {};
+	int i;
+
+	old_print_fn = libbpf_set_print(libbpf_debug_print);
+
+	root_netns_fd = open("/proc/self/ns/net", O_RDONLY);
+	if (!ASSERT_GE(root_netns_fd, 0, "open /proc/self/ns/net"))
+		goto out;
+
+	skeletons.xdp_dummy = xdp_dummy__open_and_load();
+	if (!ASSERT_OK_PTR(skeletons.xdp_dummy, "xdp_dummy__open_and_load"))
+		goto out;
+
+	skeletons.xdp_tx = xdp_tx__open_and_load();
+	if (!ASSERT_OK_PTR(skeletons.xdp_tx, "xdp_tx__open_and_load"))
+		goto out;
+
+	skeletons.xdp_redirect_multi_kern = xdp_redirect_multi_kern__open_and_load();
+	if (!ASSERT_OK_PTR(skeletons.xdp_redirect_multi_kern,
+			   "xdp_redirect_multi_kern__open_and_load"))
+		goto out;
+
+	if (!test__start_subtest("xdp_bonding_attach"))
+		test_xdp_bonding_attach(&skeletons);
+
+	for (i = 0; i < ARRAY_SIZE(bond_test_cases); i++) {
+		struct bond_test_case *test_case = &bond_test_cases[i];
+
+		if (!test__start_subtest(test_case->name))
+			test_xdp_bonding_with_mode(
+				&skeletons,
+				test_case->mode,
+				test_case->xmit_policy);
+	}
+
+	if (!test__start_subtest("xdp_bonding_redirect_multi"))
+		test_xdp_bonding_redirect_multi(&skeletons);
+
+out:
+	xdp_dummy__destroy(skeletons.xdp_dummy);
+	xdp_tx__destroy(skeletons.xdp_tx);
+	xdp_redirect_multi_kern__destroy(skeletons.xdp_redirect_multi_kern);
+
+	libbpf_set_print(old_print_fn);
+	if (root_netns_fd >= 0)
+		close(root_netns_fd);
+}
diff --git a/tools/testing/selftests/bpf/progs/bpf_iter_tcp4.c b/tools/testing/selftests/bpf/progs/bpf_iter_tcp4.c
index 2e4775c35414..92267abb462f 100644
--- a/tools/testing/selftests/bpf/progs/bpf_iter_tcp4.c
+++ b/tools/testing/selftests/bpf/progs/bpf_iter_tcp4.c
@@ -121,7 +121,7 @@ static int dump_tcp_sock(struct seq_file *seq, struct tcp_sock *tp,
 	}
 
 	BPF_SEQ_PRINTF(seq, "%4d: %08X:%04X %08X:%04X ",
-		       seq_num, src, srcp, destp, destp);
+		       seq_num, src, srcp, dest, destp);
 	BPF_SEQ_PRINTF(seq, "%02X %08X:%08X %02X:%08lX %08X %5u %8d %lu %d ",
 		       state,
 		       tp->write_seq - tp->snd_una, rx_queue,
diff --git a/tools/testing/selftests/bpf/progs/test_sk_lookup_kern.c b/tools/testing/selftests/bpf/progs/test_sk_lookup_kern.c
index e83d0b48d80c..8249075f088f 100644
--- a/tools/testing/selftests/bpf/progs/test_sk_lookup_kern.c
+++ b/tools/testing/selftests/bpf/progs/test_sk_lookup_kern.c
@@ -91,7 +91,7 @@ int bpf_sk_lookup_test1(struct __sk_buff *skb)
 	return 0;
 }
 
-SEC("classifier/fail_use_after_free")
+SEC("classifier/err_use_after_free")
 int bpf_sk_lookup_uaf(struct __sk_buff *skb)
 {
 	struct bpf_sock_tuple tuple = {};
@@ -106,7 +106,7 @@ int bpf_sk_lookup_uaf(struct __sk_buff *skb)
 	return family;
 }
 
-SEC("classifier/fail_modify_sk_pointer")
+SEC("classifier/err_modify_sk_pointer")
 int bpf_sk_lookup_modptr(struct __sk_buff *skb)
 {
 	struct bpf_sock_tuple tuple = {};
@@ -121,7 +121,7 @@ int bpf_sk_lookup_modptr(struct __sk_buff *skb)
 	return 0;
 }
 
-SEC("classifier/fail_modify_sk_or_null_pointer")
+SEC("classifier/err_modify_sk_or_null_pointer")
 int bpf_sk_lookup_modptr_or_null(struct __sk_buff *skb)
 {
 	struct bpf_sock_tuple tuple = {};
@@ -135,7 +135,7 @@ int bpf_sk_lookup_modptr_or_null(struct __sk_buff *skb)
 	return 0;
 }
 
-SEC("classifier/fail_no_release")
+SEC("classifier/err_no_release")
 int bpf_sk_lookup_test2(struct __sk_buff *skb)
 {
 	struct bpf_sock_tuple tuple = {};
@@ -144,7 +144,7 @@ int bpf_sk_lookup_test2(struct __sk_buff *skb)
 	return 0;
 }
 
-SEC("classifier/fail_release_twice")
+SEC("classifier/err_release_twice")
 int bpf_sk_lookup_test3(struct __sk_buff *skb)
 {
 	struct bpf_sock_tuple tuple = {};
@@ -156,7 +156,7 @@ int bpf_sk_lookup_test3(struct __sk_buff *skb)
 	return 0;
 }
 
-SEC("classifier/fail_release_unchecked")
+SEC("classifier/err_release_unchecked")
 int bpf_sk_lookup_test4(struct __sk_buff *skb)
 {
 	struct bpf_sock_tuple tuple = {};
@@ -173,7 +173,7 @@ void lookup_no_release(struct __sk_buff *skb)
 	bpf_sk_lookup_tcp(skb, &tuple, sizeof(tuple), BPF_F_CURRENT_NETNS, 0);
 }
 
-SEC("classifier/fail_no_release_subcall")
+SEC("classifier/err_no_release_subcall")
 int bpf_sk_lookup_test5(struct __sk_buff *skb)
 {
 	lookup_no_release(skb);
diff --git a/tools/testing/selftests/bpf/progs/xdp_tx.c b/tools/testing/selftests/bpf/progs/xdp_tx.c
index 94e6c2b281cb..5f725c720e00 100644
--- a/tools/testing/selftests/bpf/progs/xdp_tx.c
+++ b/tools/testing/selftests/bpf/progs/xdp_tx.c
@@ -3,7 +3,7 @@
 #include <linux/bpf.h>
 #include <bpf/bpf_helpers.h>
 
-SEC("tx")
+SEC("xdp")
 int xdp_tx(struct xdp_md *xdp)
 {
 	return XDP_TX;
diff --git a/tools/testing/selftests/bpf/test_netcnt.c b/tools/testing/selftests/bpf/test_netcnt.c
deleted file mode 100644
index 4990a99e7381..000000000000
--- a/tools/testing/selftests/bpf/test_netcnt.c
+++ /dev/null
@@ -1,148 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-#include <stdio.h>
-#include <stdlib.h>
-#include <string.h>
-#include <errno.h>
-#include <assert.h>
-#include <sys/sysinfo.h>
-#include <sys/time.h>
-
-#include <linux/bpf.h>
-#include <bpf/bpf.h>
-#include <bpf/libbpf.h>
-
-#include "cgroup_helpers.h"
-#include "bpf_rlimit.h"
-#include "netcnt_common.h"
-
-#define BPF_PROG "./netcnt_prog.o"
-#define TEST_CGROUP "/test-network-counters/"
-
-static int bpf_find_map(const char *test, struct bpf_object *obj,
-			const char *name)
-{
-	struct bpf_map *map;
-
-	map = bpf_object__find_map_by_name(obj, name);
-	if (!map) {
-		printf("%s:FAIL:map '%s' not found\n", test, name);
-		return -1;
-	}
-	return bpf_map__fd(map);
-}
-
-int main(int argc, char **argv)
-{
-	union percpu_net_cnt *percpu_netcnt;
-	struct bpf_cgroup_storage_key key;
-	int map_fd, percpu_map_fd;
-	int error = EXIT_FAILURE;
-	struct bpf_object *obj;
-	int prog_fd, cgroup_fd;
-	unsigned long packets;
-	union net_cnt netcnt;
-	unsigned long bytes;
-	int cpu, nproc;
-	__u32 prog_cnt;
-
-	nproc = get_nprocs_conf();
-	percpu_netcnt = malloc(sizeof(*percpu_netcnt) * nproc);
-	if (!percpu_netcnt) {
-		printf("Not enough memory for per-cpu area (%d cpus)\n", nproc);
-		goto err;
-	}
-
-	if (bpf_prog_load(BPF_PROG, BPF_PROG_TYPE_CGROUP_SKB,
-			  &obj, &prog_fd)) {
-		printf("Failed to load bpf program\n");
-		goto out;
-	}
-
-	cgroup_fd = cgroup_setup_and_join(TEST_CGROUP);
-	if (cgroup_fd < 0)
-		goto err;
-
-	/* Attach bpf program */
-	if (bpf_prog_attach(prog_fd, cgroup_fd, BPF_CGROUP_INET_EGRESS, 0)) {
-		printf("Failed to attach bpf program");
-		goto err;
-	}
-
-	if (system("which ping6 &>/dev/null") == 0)
-		assert(!system("ping6 ::1 -c 10000 -f -q > /dev/null"));
-	else
-		assert(!system("ping -6 ::1 -c 10000 -f -q > /dev/null"));
-
-	if (bpf_prog_query(cgroup_fd, BPF_CGROUP_INET_EGRESS, 0, NULL, NULL,
-			   &prog_cnt)) {
-		printf("Failed to query attached programs");
-		goto err;
-	}
-
-	map_fd = bpf_find_map(__func__, obj, "netcnt");
-	if (map_fd < 0) {
-		printf("Failed to find bpf map with net counters");
-		goto err;
-	}
-
-	percpu_map_fd = bpf_find_map(__func__, obj, "percpu_netcnt");
-	if (percpu_map_fd < 0) {
-		printf("Failed to find bpf map with percpu net counters");
-		goto err;
-	}
-
-	if (bpf_map_get_next_key(map_fd, NULL, &key)) {
-		printf("Failed to get key in cgroup storage\n");
-		goto err;
-	}
-
-	if (bpf_map_lookup_elem(map_fd, &key, &netcnt)) {
-		printf("Failed to lookup cgroup storage\n");
-		goto err;
-	}
-
-	if (bpf_map_lookup_elem(percpu_map_fd, &key, &percpu_netcnt[0])) {
-		printf("Failed to lookup percpu cgroup storage\n");
-		goto err;
-	}
-
-	/* Some packets can be still in per-cpu cache, but not more than
-	 * MAX_PERCPU_PACKETS.
-	 */
-	packets = netcnt.packets;
-	bytes = netcnt.bytes;
-	for (cpu = 0; cpu < nproc; cpu++) {
-		if (percpu_netcnt[cpu].packets > MAX_PERCPU_PACKETS) {
-			printf("Unexpected percpu value: %llu\n",
-			       percpu_netcnt[cpu].packets);
-			goto err;
-		}
-
-		packets += percpu_netcnt[cpu].packets;
-		bytes += percpu_netcnt[cpu].bytes;
-	}
-
-	/* No packets should be lost */
-	if (packets != 10000) {
-		printf("Unexpected packet count: %lu\n", packets);
-		goto err;
-	}
-
-	/* Let's check that bytes counter matches the number of packets
-	 * multiplied by the size of ipv6 ICMP packet.
-	 */
-	if (bytes != packets * 104) {
-		printf("Unexpected bytes count: %lu\n", bytes);
-		goto err;
-	}
-
-	error = 0;
-	printf("test_netcnt:PASS\n");
-
-err:
-	cleanup_cgroup_environment();
-	free(percpu_netcnt);
-
-out:
-	return error;
-}
diff --git a/tools/testing/selftests/bpf/test_xdp_veth.sh b/tools/testing/selftests/bpf/test_xdp_veth.sh
index ba8ffcdaac30..995278e684b6 100755
--- a/tools/testing/selftests/bpf/test_xdp_veth.sh
+++ b/tools/testing/selftests/bpf/test_xdp_veth.sh
@@ -108,7 +108,7 @@ ip link set dev veth2 xdp pinned $BPF_DIR/progs/redirect_map_1
 ip link set dev veth3 xdp pinned $BPF_DIR/progs/redirect_map_2
 
 ip -n ns1 link set dev veth11 xdp obj xdp_dummy.o sec xdp_dummy
-ip -n ns2 link set dev veth22 xdp obj xdp_tx.o sec tx
+ip -n ns2 link set dev veth22 xdp obj xdp_tx.o sec xdp
 ip -n ns3 link set dev veth33 xdp obj xdp_dummy.o sec xdp_dummy
 
 trap cleanup EXIT