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

Alexei Starovoitov says:

====================
pull-request: bpf-next 2020-05-14

The following pull-request contains BPF updates for your *net-next* tree.

The main changes are:

1) Merged tag 'perf-for-bpf-2020-05-06' from tip tree that includes CAP_PERFMON.

2) support for narrow loads in bpf_sock_addr progs and additional
   helpers in cg-skb progs, from Andrey.

3) bpf benchmark runner, from Andrii.

4) arm and riscv JIT optimizations, from Luke.

5) bpf iterator infrastructure, from Yonghong.
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

10 files changed, 308 insertions, 70 deletions

diff --git a/net/core/filter.c b/net/core/filter.c
index dfaf5df13722..5815902bb617 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -4003,16 +4003,22 @@ static const struct bpf_func_proto bpf_skb_under_cgroup_proto = {
 };
 
 #ifdef CONFIG_SOCK_CGROUP_DATA
+static inline u64 __bpf_sk_cgroup_id(struct sock *sk)
+{
+	struct cgroup *cgrp;
+
+	cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data);
+	return cgroup_id(cgrp);
+}
+
 BPF_CALL_1(bpf_skb_cgroup_id, const struct sk_buff *, skb)
 {
 	struct sock *sk = skb_to_full_sk(skb);
-	struct cgroup *cgrp;
 
 	if (!sk || !sk_fullsock(sk))
 		return 0;
 
-	cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data);
-	return cgroup_id(cgrp);
+	return __bpf_sk_cgroup_id(sk);
 }
 
 static const struct bpf_func_proto bpf_skb_cgroup_id_proto = {
@@ -4022,16 +4028,12 @@ static const struct bpf_func_proto bpf_skb_cgroup_id_proto = {
 	.arg1_type      = ARG_PTR_TO_CTX,
 };
 
-BPF_CALL_2(bpf_skb_ancestor_cgroup_id, const struct sk_buff *, skb, int,
-	   ancestor_level)
+static inline u64 __bpf_sk_ancestor_cgroup_id(struct sock *sk,
+					      int ancestor_level)
 {
-	struct sock *sk = skb_to_full_sk(skb);
 	struct cgroup *ancestor;
 	struct cgroup *cgrp;
 
-	if (!sk || !sk_fullsock(sk))
-		return 0;
-
 	cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data);
 	ancestor = cgroup_ancestor(cgrp, ancestor_level);
 	if (!ancestor)
@@ -4040,6 +4042,17 @@ BPF_CALL_2(bpf_skb_ancestor_cgroup_id, const struct sk_buff *, skb, int,
 	return cgroup_id(ancestor);
 }
 
+BPF_CALL_2(bpf_skb_ancestor_cgroup_id, const struct sk_buff *, skb, int,
+	   ancestor_level)
+{
+	struct sock *sk = skb_to_full_sk(skb);
+
+	if (!sk || !sk_fullsock(sk))
+		return 0;
+
+	return __bpf_sk_ancestor_cgroup_id(sk, ancestor_level);
+}
+
 static const struct bpf_func_proto bpf_skb_ancestor_cgroup_id_proto = {
 	.func           = bpf_skb_ancestor_cgroup_id,
 	.gpl_only       = false,
@@ -4047,6 +4060,31 @@ static const struct bpf_func_proto bpf_skb_ancestor_cgroup_id_proto = {
 	.arg1_type      = ARG_PTR_TO_CTX,
 	.arg2_type      = ARG_ANYTHING,
 };
+
+BPF_CALL_1(bpf_sk_cgroup_id, struct sock *, sk)
+{
+	return __bpf_sk_cgroup_id(sk);
+}
+
+static const struct bpf_func_proto bpf_sk_cgroup_id_proto = {
+	.func           = bpf_sk_cgroup_id,
+	.gpl_only       = false,
+	.ret_type       = RET_INTEGER,
+	.arg1_type      = ARG_PTR_TO_SOCKET,
+};
+
+BPF_CALL_2(bpf_sk_ancestor_cgroup_id, struct sock *, sk, int, ancestor_level)
+{
+	return __bpf_sk_ancestor_cgroup_id(sk, ancestor_level);
+}
+
+static const struct bpf_func_proto bpf_sk_ancestor_cgroup_id_proto = {
+	.func           = bpf_sk_ancestor_cgroup_id,
+	.gpl_only       = false,
+	.ret_type       = RET_INTEGER,
+	.arg1_type      = ARG_PTR_TO_SOCKET,
+	.arg2_type      = ARG_ANYTHING,
+};
 #endif
 
 static unsigned long bpf_xdp_copy(void *dst_buff, const void *src_buff,
@@ -4525,30 +4563,28 @@ BPF_CALL_3(bpf_bind, struct bpf_sock_addr_kern *, ctx, struct sockaddr *, addr,
 {
 #ifdef CONFIG_INET
 	struct sock *sk = ctx->sk;
+	u32 flags = BIND_FROM_BPF;
 	int err;
 
-	/* Binding to port can be expensive so it's prohibited in the helper.
-	 * Only binding to IP is supported.
-	 */
 	err = -EINVAL;
 	if (addr_len < offsetofend(struct sockaddr, sa_family))
 		return err;
 	if (addr->sa_family == AF_INET) {
 		if (addr_len < sizeof(struct sockaddr_in))
 			return err;
-		if (((struct sockaddr_in *)addr)->sin_port != htons(0))
-			return err;
-		return __inet_bind(sk, addr, addr_len, true, false);
+		if (((struct sockaddr_in *)addr)->sin_port == htons(0))
+			flags |= BIND_FORCE_ADDRESS_NO_PORT;
+		return __inet_bind(sk, addr, addr_len, flags);
 #if IS_ENABLED(CONFIG_IPV6)
 	} else if (addr->sa_family == AF_INET6) {
 		if (addr_len < SIN6_LEN_RFC2133)
 			return err;
-		if (((struct sockaddr_in6 *)addr)->sin6_port != htons(0))
-			return err;
+		if (((struct sockaddr_in6 *)addr)->sin6_port == htons(0))
+			flags |= BIND_FORCE_ADDRESS_NO_PORT;
 		/* ipv6_bpf_stub cannot be NULL, since it's called from
 		 * bpf_cgroup_inet6_connect hook and ipv6 is already loaded
 		 */
-		return ipv6_bpf_stub->inet6_bind(sk, addr, addr_len, true, false);
+		return ipv6_bpf_stub->inet6_bind(sk, addr, addr_len, flags);
 #endif /* CONFIG_IPV6 */
 	}
 #endif /* CONFIG_INET */
@@ -6159,8 +6195,22 @@ cg_skb_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 #ifdef CONFIG_SOCK_CGROUP_DATA
 	case BPF_FUNC_skb_cgroup_id:
 		return &bpf_skb_cgroup_id_proto;
+	case BPF_FUNC_skb_ancestor_cgroup_id:
+		return &bpf_skb_ancestor_cgroup_id_proto;
+	case BPF_FUNC_sk_cgroup_id:
+		return &bpf_sk_cgroup_id_proto;
+	case BPF_FUNC_sk_ancestor_cgroup_id:
+		return &bpf_sk_ancestor_cgroup_id_proto;
 #endif
 #ifdef CONFIG_INET
+	case BPF_FUNC_sk_lookup_tcp:
+		return &bpf_sk_lookup_tcp_proto;
+	case BPF_FUNC_sk_lookup_udp:
+		return &bpf_sk_lookup_udp_proto;
+	case BPF_FUNC_sk_release:
+		return &bpf_sk_release_proto;
+	case BPF_FUNC_skc_lookup_tcp:
+		return &bpf_skc_lookup_tcp_proto;
 	case BPF_FUNC_tcp_sock:
 		return &bpf_tcp_sock_proto;
 	case BPF_FUNC_get_listener_sock:
@@ -7031,6 +7081,7 @@ static bool sock_addr_is_valid_access(int off, int size,
 	case bpf_ctx_range(struct bpf_sock_addr, msg_src_ip4):
 	case bpf_ctx_range_till(struct bpf_sock_addr, msg_src_ip6[0],
 				msg_src_ip6[3]):
+	case bpf_ctx_range(struct bpf_sock_addr, user_port):
 		if (type == BPF_READ) {
 			bpf_ctx_record_field_size(info, size_default);
 
@@ -7061,10 +7112,6 @@ static bool sock_addr_is_valid_access(int off, int size,
 				return false;
 		}
 		break;
-	case bpf_ctx_range(struct bpf_sock_addr, user_port):
-		if (size != size_default)
-			return false;
-		break;
 	case offsetof(struct bpf_sock_addr, sk):
 		if (type != BPF_READ)
 			return false;
@@ -7960,8 +8007,8 @@ static u32 sock_addr_convert_ctx_access(enum bpf_access_type type,
 					struct bpf_insn *insn_buf,
 					struct bpf_prog *prog, u32 *target_size)
 {
+	int off, port_size = sizeof_field(struct sockaddr_in6, sin6_port);
 	struct bpf_insn *insn = insn_buf;
-	int off;
 
 	switch (si->off) {
 	case offsetof(struct bpf_sock_addr, user_family):
@@ -7996,9 +8043,11 @@ static u32 sock_addr_convert_ctx_access(enum bpf_access_type type,
 			     offsetof(struct sockaddr_in6, sin6_port));
 		BUILD_BUG_ON(sizeof_field(struct sockaddr_in, sin_port) !=
 			     sizeof_field(struct sockaddr_in6, sin6_port));
-		SOCK_ADDR_LOAD_OR_STORE_NESTED_FIELD(struct bpf_sock_addr_kern,
-						     struct sockaddr_in6, uaddr,
-						     sin6_port, tmp_reg);
+		/* Account for sin6_port being smaller than user_port. */
+		port_size = min(port_size, BPF_LDST_BYTES(si));
+		SOCK_ADDR_LOAD_OR_STORE_NESTED_FIELD_SIZE_OFF(
+			struct bpf_sock_addr_kern, struct sockaddr_in6, uaddr,
+			sin6_port, bytes_to_bpf_size(port_size), 0, tmp_reg);
 		break;
 
 	case offsetof(struct bpf_sock_addr, family):
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 6177c4ba0037..fcf0d12a407a 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -450,12 +450,12 @@ int inet_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
 	if (err)
 		return err;
 
-	return __inet_bind(sk, uaddr, addr_len, false, true);
+	return __inet_bind(sk, uaddr, addr_len, BIND_WITH_LOCK);
 }
 EXPORT_SYMBOL(inet_bind);
 
 int __inet_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len,
-		bool force_bind_address_no_port, bool with_lock)
+		u32 flags)
 {
 	struct sockaddr_in *addr = (struct sockaddr_in *)uaddr;
 	struct inet_sock *inet = inet_sk(sk);
@@ -506,7 +506,7 @@ int __inet_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len,
 	 *      would be illegal to use them (multicast/broadcast) in
 	 *      which case the sending device address is used.
 	 */
-	if (with_lock)
+	if (flags & BIND_WITH_LOCK)
 		lock_sock(sk);
 
 	/* Check these errors (active socket, double bind). */
@@ -520,16 +520,18 @@ int __inet_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len,
 
 	/* Make sure we are allowed to bind here. */
 	if (snum || !(inet->bind_address_no_port ||
-		      force_bind_address_no_port)) {
+		      (flags & BIND_FORCE_ADDRESS_NO_PORT))) {
 		if (sk->sk_prot->get_port(sk, snum)) {
 			inet->inet_saddr = inet->inet_rcv_saddr = 0;
 			err = -EADDRINUSE;
 			goto out_release_sock;
 		}
-		err = BPF_CGROUP_RUN_PROG_INET4_POST_BIND(sk);
-		if (err) {
-			inet->inet_saddr = inet->inet_rcv_saddr = 0;
-			goto out_release_sock;
+		if (!(flags & BIND_FROM_BPF)) {
+			err = BPF_CGROUP_RUN_PROG_INET4_POST_BIND(sk);
+			if (err) {
+				inet->inet_saddr = inet->inet_rcv_saddr = 0;
+				goto out_release_sock;
+			}
 		}
 	}
 
@@ -543,7 +545,7 @@ int __inet_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len,
 	sk_dst_reset(sk);
 	err = 0;
 out_release_sock:
-	if (with_lock)
+	if (flags & BIND_WITH_LOCK)
 		release_sock(sk);
 out:
 	return err;
diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index 345baa0a754f..771a462a8322 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -273,7 +273,7 @@ out_rcu_unlock:
 }
 
 static int __inet6_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len,
-			bool force_bind_address_no_port, bool with_lock)
+			u32 flags)
 {
 	struct sockaddr_in6 *addr = (struct sockaddr_in6 *)uaddr;
 	struct inet_sock *inet = inet_sk(sk);
@@ -297,7 +297,7 @@ static int __inet6_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len,
 	    !ns_capable(net->user_ns, CAP_NET_BIND_SERVICE))
 		return -EACCES;
 
-	if (with_lock)
+	if (flags & BIND_WITH_LOCK)
 		lock_sock(sk);
 
 	/* Check these errors (active socket, double bind). */
@@ -400,18 +400,20 @@ static int __inet6_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len,
 
 	/* Make sure we are allowed to bind here. */
 	if (snum || !(inet->bind_address_no_port ||
-		      force_bind_address_no_port)) {
+		      (flags & BIND_FORCE_ADDRESS_NO_PORT))) {
 		if (sk->sk_prot->get_port(sk, snum)) {
 			sk->sk_ipv6only = saved_ipv6only;
 			inet_reset_saddr(sk);
 			err = -EADDRINUSE;
 			goto out;
 		}
-		err = BPF_CGROUP_RUN_PROG_INET6_POST_BIND(sk);
-		if (err) {
-			sk->sk_ipv6only = saved_ipv6only;
-			inet_reset_saddr(sk);
-			goto out;
+		if (!(flags & BIND_FROM_BPF)) {
+			err = BPF_CGROUP_RUN_PROG_INET6_POST_BIND(sk);
+			if (err) {
+				sk->sk_ipv6only = saved_ipv6only;
+				inet_reset_saddr(sk);
+				goto out;
+			}
 		}
 	}
 
@@ -423,7 +425,7 @@ static int __inet6_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len,
 	inet->inet_dport = 0;
 	inet->inet_daddr = 0;
 out:
-	if (with_lock)
+	if (flags & BIND_WITH_LOCK)
 		release_sock(sk);
 	return err;
 out_unlock:
@@ -451,7 +453,7 @@ int inet6_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
 	if (err)
 		return err;
 
-	return __inet6_bind(sk, uaddr, addr_len, false, true);
+	return __inet6_bind(sk, uaddr, addr_len, BIND_WITH_LOCK);
 }
 EXPORT_SYMBOL(inet6_bind);
 
diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c
index 46ed56719476..250ff52c674e 100644
--- a/net/ipv6/ip6_fib.c
+++ b/net/ipv6/ip6_fib.c
@@ -2467,7 +2467,7 @@ void fib6_gc_cleanup(void)
 }
 
 #ifdef CONFIG_PROC_FS
-static int ipv6_route_seq_show(struct seq_file *seq, void *v)
+static int ipv6_route_native_seq_show(struct seq_file *seq, void *v)
 {
 	struct fib6_info *rt = v;
 	struct ipv6_route_iter *iter = seq->private;
@@ -2625,7 +2625,7 @@ static bool ipv6_route_iter_active(struct ipv6_route_iter *iter)
 	return w->node && !(w->state == FWS_U && w->node == w->root);
 }
 
-static void ipv6_route_seq_stop(struct seq_file *seq, void *v)
+static void ipv6_route_native_seq_stop(struct seq_file *seq, void *v)
 	__releases(RCU_BH)
 {
 	struct net *net = seq_file_net(seq);
@@ -2637,6 +2637,62 @@ static void ipv6_route_seq_stop(struct seq_file *seq, void *v)
 	rcu_read_unlock_bh();
 }
 
+#if IS_BUILTIN(CONFIG_IPV6) && defined(CONFIG_BPF_SYSCALL)
+static int ipv6_route_prog_seq_show(struct bpf_prog *prog,
+				    struct bpf_iter_meta *meta,
+				    void *v)
+{
+	struct bpf_iter__ipv6_route ctx;
+
+	ctx.meta = meta;
+	ctx.rt = v;
+	return bpf_iter_run_prog(prog, &ctx);
+}
+
+static int ipv6_route_seq_show(struct seq_file *seq, void *v)
+{
+	struct ipv6_route_iter *iter = seq->private;
+	struct bpf_iter_meta meta;
+	struct bpf_prog *prog;
+	int ret;
+
+	meta.seq = seq;
+	prog = bpf_iter_get_info(&meta, false);
+	if (!prog)
+		return ipv6_route_native_seq_show(seq, v);
+
+	ret = ipv6_route_prog_seq_show(prog, &meta, v);
+	iter->w.leaf = NULL;
+
+	return ret;
+}
+
+static void ipv6_route_seq_stop(struct seq_file *seq, void *v)
+{
+	struct bpf_iter_meta meta;
+	struct bpf_prog *prog;
+
+	if (!v) {
+		meta.seq = seq;
+		prog = bpf_iter_get_info(&meta, true);
+		if (prog)
+			(void)ipv6_route_prog_seq_show(prog, &meta, v);
+	}
+
+	ipv6_route_native_seq_stop(seq, v);
+}
+#else
+static int ipv6_route_seq_show(struct seq_file *seq, void *v)
+{
+	return ipv6_route_native_seq_show(seq, v);
+}
+
+static void ipv6_route_seq_stop(struct seq_file *seq, void *v)
+{
+	ipv6_route_native_seq_stop(seq, v);
+}
+#endif
+
 const struct seq_operations ipv6_route_seq_ops = {
 	.start	= ipv6_route_seq_start,
 	.next	= ipv6_route_seq_next,
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 4292653af533..fcf0d5c87d09 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -6421,6 +6421,35 @@ void __init ip6_route_init_special_entries(void)
   #endif
 }
 
+#if IS_BUILTIN(CONFIG_IPV6)
+#if defined(CONFIG_BPF_SYSCALL) && defined(CONFIG_PROC_FS)
+DEFINE_BPF_ITER_FUNC(ipv6_route, struct bpf_iter_meta *meta, struct fib6_info *rt)
+
+static const struct bpf_iter_reg ipv6_route_reg_info = {
+	.target			= "ipv6_route",
+	.seq_ops		= &ipv6_route_seq_ops,
+	.init_seq_private	= bpf_iter_init_seq_net,
+	.fini_seq_private	= bpf_iter_fini_seq_net,
+	.seq_priv_size		= sizeof(struct ipv6_route_iter),
+	.ctx_arg_info_size	= 1,
+	.ctx_arg_info		= {
+		{ offsetof(struct bpf_iter__ipv6_route, rt),
+		  PTR_TO_BTF_ID_OR_NULL },
+	},
+};
+
+static int __init bpf_iter_register(void)
+{
+	return bpf_iter_reg_target(&ipv6_route_reg_info);
+}
+
+static void bpf_iter_unregister(void)
+{
+	bpf_iter_unreg_target(&ipv6_route_reg_info);
+}
+#endif
+#endif
+
 int __init ip6_route_init(void)
 {
 	int ret;
@@ -6483,6 +6512,14 @@ int __init ip6_route_init(void)
 	if (ret)
 		goto out_register_late_subsys;
 
+#if IS_BUILTIN(CONFIG_IPV6)
+#if defined(CONFIG_BPF_SYSCALL) && defined(CONFIG_PROC_FS)
+	ret = bpf_iter_register();
+	if (ret)
+		goto out_register_late_subsys;
+#endif
+#endif
+
 	for_each_possible_cpu(cpu) {
 		struct uncached_list *ul = per_cpu_ptr(&rt6_uncached_list, cpu);
 
@@ -6515,6 +6552,11 @@ out_kmem_cache:
 
 void ip6_route_cleanup(void)
 {
+#if IS_BUILTIN(CONFIG_IPV6)
+#if defined(CONFIG_BPF_SYSCALL) && defined(CONFIG_PROC_FS)
+	bpf_iter_unregister();
+#endif
+#endif
 	unregister_netdevice_notifier(&ip6_route_dev_notifier);
 	unregister_pernet_subsys(&ip6_route_net_late_ops);
 	fib6_rules_cleanup();
diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index 5ded01ca8b20..4f2c3b14ddbf 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -2596,7 +2596,7 @@ static void *netlink_seq_next(struct seq_file *seq, void *v, loff_t *pos)
 	return __netlink_seq_next(seq);
 }
 
-static void netlink_seq_stop(struct seq_file *seq, void *v)
+static void netlink_native_seq_stop(struct seq_file *seq, void *v)
 {
 	struct nl_seq_iter *iter = seq->private;
 
@@ -2607,7 +2607,7 @@ static void netlink_seq_stop(struct seq_file *seq, void *v)
 }
 
 
-static int netlink_seq_show(struct seq_file *seq, void *v)
+static int netlink_native_seq_show(struct seq_file *seq, void *v)
 {
 	if (v == SEQ_START_TOKEN) {
 		seq_puts(seq,
@@ -2634,6 +2634,68 @@ static int netlink_seq_show(struct seq_file *seq, void *v)
 	return 0;
 }
 
+#ifdef CONFIG_BPF_SYSCALL
+struct bpf_iter__netlink {
+	__bpf_md_ptr(struct bpf_iter_meta *, meta);
+	__bpf_md_ptr(struct netlink_sock *, sk);
+};
+
+DEFINE_BPF_ITER_FUNC(netlink, struct bpf_iter_meta *meta, struct netlink_sock *sk)
+
+static int netlink_prog_seq_show(struct bpf_prog *prog,
+				  struct bpf_iter_meta *meta,
+				  void *v)
+{
+	struct bpf_iter__netlink ctx;
+
+	meta->seq_num--;  /* skip SEQ_START_TOKEN */
+	ctx.meta = meta;
+	ctx.sk = nlk_sk((struct sock *)v);
+	return bpf_iter_run_prog(prog, &ctx);
+}
+
+static int netlink_seq_show(struct seq_file *seq, void *v)
+{
+	struct bpf_iter_meta meta;
+	struct bpf_prog *prog;
+
+	meta.seq = seq;
+	prog = bpf_iter_get_info(&meta, false);
+	if (!prog)
+		return netlink_native_seq_show(seq, v);
+
+	if (v != SEQ_START_TOKEN)
+		return netlink_prog_seq_show(prog, &meta, v);
+
+	return 0;
+}
+
+static void netlink_seq_stop(struct seq_file *seq, void *v)
+{
+	struct bpf_iter_meta meta;
+	struct bpf_prog *prog;
+
+	if (!v) {
+		meta.seq = seq;
+		prog = bpf_iter_get_info(&meta, true);
+		if (prog)
+			(void)netlink_prog_seq_show(prog, &meta, v);
+	}
+
+	netlink_native_seq_stop(seq, v);
+}
+#else
+static int netlink_seq_show(struct seq_file *seq, void *v)
+{
+	return netlink_native_seq_show(seq, v);
+}
+
+static void netlink_seq_stop(struct seq_file *seq, void *v)
+{
+	netlink_native_seq_stop(seq, v);
+}
+#endif
+
 static const struct seq_operations netlink_seq_ops = {
 	.start  = netlink_seq_start,
 	.next   = netlink_seq_next,
@@ -2740,6 +2802,26 @@ static const struct rhashtable_params netlink_rhashtable_params = {
 	.automatic_shrinking = true,
 };
 
+#if defined(CONFIG_BPF_SYSCALL) && defined(CONFIG_PROC_FS)
+static const struct bpf_iter_reg netlink_reg_info = {
+	.target			= "netlink",
+	.seq_ops		= &netlink_seq_ops,
+	.init_seq_private	= bpf_iter_init_seq_net,
+	.fini_seq_private	= bpf_iter_fini_seq_net,
+	.seq_priv_size		= sizeof(struct nl_seq_iter),
+	.ctx_arg_info_size	= 1,
+	.ctx_arg_info		= {
+		{ offsetof(struct bpf_iter__netlink, sk),
+		  PTR_TO_BTF_ID_OR_NULL },
+	},
+};
+
+static int __init bpf_iter_register(void)
+{
+	return bpf_iter_reg_target(&netlink_reg_info);
+}
+#endif
+
 static int __init netlink_proto_init(void)
 {
 	int i;
@@ -2748,6 +2830,12 @@ static int __init netlink_proto_init(void)
 	if (err != 0)
 		goto out;
 
+#if defined(CONFIG_BPF_SYSCALL) && defined(CONFIG_PROC_FS)
+	err = bpf_iter_register();
+	if (err)
+		goto out;
+#endif
+
 	BUILD_BUG_ON(sizeof(struct netlink_skb_parms) > sizeof_field(struct sk_buff, cb));
 
 	nl_table = kcalloc(MAX_LINKS, sizeof(*nl_table), GFP_KERNEL);
diff --git a/net/xdp/xdp_umem.c b/net/xdp/xdp_umem.c
index ed7a6060f73c..37ace3bc0d48 100644
--- a/net/xdp/xdp_umem.c
+++ b/net/xdp/xdp_umem.c
@@ -30,9 +30,9 @@ void xdp_add_sk_umem(struct xdp_umem *umem, struct xdp_sock *xs)
 	if (!xs->tx)
 		return;
 
-	spin_lock_irqsave(&umem->xsk_list_lock, flags);
-	list_add_rcu(&xs->list, &umem->xsk_list);
-	spin_unlock_irqrestore(&umem->xsk_list_lock, flags);
+	spin_lock_irqsave(&umem->xsk_tx_list_lock, flags);
+	list_add_rcu(&xs->list, &umem->xsk_tx_list);
+	spin_unlock_irqrestore(&umem->xsk_tx_list_lock, flags);
 }
 
 void xdp_del_sk_umem(struct xdp_umem *umem, struct xdp_sock *xs)
@@ -42,9 +42,9 @@ void xdp_del_sk_umem(struct xdp_umem *umem, struct xdp_sock *xs)
 	if (!xs->tx)
 		return;
 
-	spin_lock_irqsave(&umem->xsk_list_lock, flags);
+	spin_lock_irqsave(&umem->xsk_tx_list_lock, flags);
 	list_del_rcu(&xs->list);
-	spin_unlock_irqrestore(&umem->xsk_list_lock, flags);
+	spin_unlock_irqrestore(&umem->xsk_tx_list_lock, flags);
 }
 
 /* The umem is stored both in the _rx struct and the _tx struct as we do
@@ -279,7 +279,7 @@ void xdp_put_umem(struct xdp_umem *umem)
 	}
 }
 
-static int xdp_umem_pin_pages(struct xdp_umem *umem)
+static int xdp_umem_pin_pages(struct xdp_umem *umem, unsigned long address)
 {
 	unsigned int gup_flags = FOLL_WRITE;
 	long npgs;
@@ -291,7 +291,7 @@ static int xdp_umem_pin_pages(struct xdp_umem *umem)
 		return -ENOMEM;
 
 	down_read(&current->mm->mmap_sem);
-	npgs = pin_user_pages(umem->address, umem->npgs,
+	npgs = pin_user_pages(address, umem->npgs,
 			      gup_flags | FOLL_LONGTERM, &umem->pgs[0], NULL);
 	up_read(&current->mm->mmap_sem);
 
@@ -385,7 +385,6 @@ static int xdp_umem_reg(struct xdp_umem *umem, struct xdp_umem_reg *mr)
 	if (headroom >= chunk_size - XDP_PACKET_HEADROOM)
 		return -EINVAL;
 
-	umem->address = (unsigned long)addr;
 	umem->chunk_mask = unaligned_chunks ? XSK_UNALIGNED_BUF_ADDR_MASK
 					    : ~((u64)chunk_size - 1);
 	umem->size = size;
@@ -395,8 +394,8 @@ static int xdp_umem_reg(struct xdp_umem *umem, struct xdp_umem_reg *mr)
 	umem->pgs = NULL;
 	umem->user = NULL;
 	umem->flags = mr->flags;
-	INIT_LIST_HEAD(&umem->xsk_list);
-	spin_lock_init(&umem->xsk_list_lock);
+	INIT_LIST_HEAD(&umem->xsk_tx_list);
+	spin_lock_init(&umem->xsk_tx_list_lock);
 
 	refcount_set(&umem->users, 1);
 
@@ -404,7 +403,7 @@ static int xdp_umem_reg(struct xdp_umem *umem, struct xdp_umem_reg *mr)
 	if (err)
 		return err;
 
-	err = xdp_umem_pin_pages(umem);
+	err = xdp_umem_pin_pages(umem, (unsigned long)addr);
 	if (err)
 		goto out_account;
 
diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c
index f6e6609f70a3..45ffd67b367d 100644
--- a/net/xdp/xsk.c
+++ b/net/xdp/xsk.c
@@ -75,7 +75,7 @@ void xsk_set_tx_need_wakeup(struct xdp_umem *umem)
 		return;
 
 	rcu_read_lock();
-	list_for_each_entry_rcu(xs, &umem->xsk_list, list) {
+	list_for_each_entry_rcu(xs, &umem->xsk_tx_list, list) {
 		xs->tx->ring->flags |= XDP_RING_NEED_WAKEUP;
 	}
 	rcu_read_unlock();
@@ -102,7 +102,7 @@ void xsk_clear_tx_need_wakeup(struct xdp_umem *umem)
 		return;
 
 	rcu_read_lock();
-	list_for_each_entry_rcu(xs, &umem->xsk_list, list) {
+	list_for_each_entry_rcu(xs, &umem->xsk_tx_list, list) {
 		xs->tx->ring->flags &= ~XDP_RING_NEED_WAKEUP;
 	}
 	rcu_read_unlock();
@@ -305,7 +305,7 @@ void xsk_umem_consume_tx_done(struct xdp_umem *umem)
 	struct xdp_sock *xs;
 
 	rcu_read_lock();
-	list_for_each_entry_rcu(xs, &umem->xsk_list, list) {
+	list_for_each_entry_rcu(xs, &umem->xsk_tx_list, list) {
 		__xskq_cons_release(xs->tx);
 		xs->sk.sk_write_space(&xs->sk);
 	}
@@ -318,7 +318,7 @@ bool xsk_umem_consume_tx(struct xdp_umem *umem, struct xdp_desc *desc)
 	struct xdp_sock *xs;
 
 	rcu_read_lock();
-	list_for_each_entry_rcu(xs, &umem->xsk_list, list) {
+	list_for_each_entry_rcu(xs, &umem->xsk_tx_list, list) {
 		if (!xskq_cons_peek_desc(xs->tx, desc, umem))
 			continue;
 
diff --git a/net/xdp/xsk_queue.c b/net/xdp/xsk_queue.c
index c90e9c1e3c63..57fb81bd593c 100644
--- a/net/xdp/xsk_queue.c
+++ b/net/xdp/xsk_queue.c
@@ -9,12 +9,12 @@
 
 #include "xsk_queue.h"
 
-void xskq_set_umem(struct xsk_queue *q, u64 size, u64 chunk_mask)
+void xskq_set_umem(struct xsk_queue *q, u64 umem_size, u64 chunk_mask)
 {
 	if (!q)
 		return;
 
-	q->size = size;
+	q->umem_size = umem_size;
 	q->chunk_mask = chunk_mask;
 }
 
diff --git a/net/xdp/xsk_queue.h b/net/xdp/xsk_queue.h
index b50bb5c76da5..648733ec24ac 100644
--- a/net/xdp/xsk_queue.h
+++ b/net/xdp/xsk_queue.h
@@ -30,7 +30,7 @@ struct xdp_umem_ring {
 
 struct xsk_queue {
 	u64 chunk_mask;
-	u64 size;
+	u64 umem_size;
 	u32 ring_mask;
 	u32 nentries;
 	u32 cached_prod;
@@ -123,7 +123,7 @@ static inline bool xskq_cons_is_valid_unaligned(struct xsk_queue *q,
 	u64 base_addr = xsk_umem_extract_addr(addr);
 
 	addr = xsk_umem_add_offset_to_addr(addr);
-	if (base_addr >= q->size || addr >= q->size ||
+	if (base_addr >= q->umem_size || addr >= q->umem_size ||
 	    xskq_cons_crosses_non_contig_pg(umem, addr, length)) {
 		q->invalid_descs++;
 		return false;
@@ -134,7 +134,7 @@ static inline bool xskq_cons_is_valid_unaligned(struct xsk_queue *q,
 
 static inline bool xskq_cons_is_valid_addr(struct xsk_queue *q, u64 addr)
 {
-	if (addr >= q->size) {
+	if (addr >= q->umem_size) {
 		q->invalid_descs++;
 		return false;
 	}
@@ -379,7 +379,7 @@ static inline u64 xskq_nb_invalid_descs(struct xsk_queue *q)
 	return q ? q->invalid_descs : 0;
 }
 
-void xskq_set_umem(struct xsk_queue *q, u64 size, u64 chunk_mask);
+void xskq_set_umem(struct xsk_queue *q, u64 umem_size, u64 chunk_mask);
 struct xsk_queue *xskq_create(u32 nentries, bool umem_queue);
 void xskq_destroy(struct xsk_queue *q_ops);