Merge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

include/net/sock.h
  310731e2f161 ("net: Fix data-races around sysctl_mem.")
  e70f3c701276 ("Revert "net: set SK_MEM_QUANTUM to 4096"")
https://lore.kernel.org/all/20220711120211.7c8b7cba@canb.auug.org.au/

net/ipv4/fib_semantics.c
  747c14307214 ("ip: fix dflt addr selection for connected nexthop")
  d62607c3fe45 ("net: rename reference+tracking helpers")

net/tls/tls.h
include/net/tls.h
  3d8c51b25a23 ("net/tls: Check for errors in tls_device_init")
  587903142308 ("tls: create an internal header")

Signed-off-by: Jakub Kicinski <kuba@kernel.org>

13 files changed, 54 insertions, 31 deletions

diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 7abd652a558f..fac552e98eb9 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -1247,7 +1247,7 @@ static int inet_sk_reselect_saddr(struct sock *sk)
 	if (new_saddr == old_saddr)
 		return 0;
 
-	if (sock_net(sk)->ipv4.sysctl_ip_dynaddr > 1) {
+	if (READ_ONCE(sock_net(sk)->ipv4.sysctl_ip_dynaddr) > 1) {
 		pr_info("%s(): shifting inet->saddr from %pI4 to %pI4\n",
 			__func__, &old_saddr, &new_saddr);
 	}
@@ -1302,7 +1302,7 @@ int inet_sk_rebuild_header(struct sock *sk)
 		 * Other protocols have to map its equivalent state to TCP_SYN_SENT.
 		 * DCCP maps its DCCP_REQUESTING state to TCP_SYN_SENT. -acme
 		 */
-		if (!sock_net(sk)->ipv4.sysctl_ip_dynaddr ||
+		if (!READ_ONCE(sock_net(sk)->ipv4.sysctl_ip_dynaddr) ||
 		    sk->sk_state != TCP_SYN_SENT ||
 		    (sk->sk_userlocks & SOCK_BINDADDR_LOCK) ||
 		    (err = inet_sk_reselect_saddr(sk)) != 0)
diff --git a/net/ipv4/cipso_ipv4.c b/net/ipv4/cipso_ipv4.c
index 62d5f99760aa..6cd3b6c559f0 100644
--- a/net/ipv4/cipso_ipv4.c
+++ b/net/ipv4/cipso_ipv4.c
@@ -239,7 +239,7 @@ static int cipso_v4_cache_check(const unsigned char *key,
 	struct cipso_v4_map_cache_entry *prev_entry = NULL;
 	u32 hash;
 
-	if (!cipso_v4_cache_enabled)
+	if (!READ_ONCE(cipso_v4_cache_enabled))
 		return -ENOENT;
 
 	hash = cipso_v4_map_cache_hash(key, key_len);
@@ -296,13 +296,14 @@ static int cipso_v4_cache_check(const unsigned char *key,
 int cipso_v4_cache_add(const unsigned char *cipso_ptr,
 		       const struct netlbl_lsm_secattr *secattr)
 {
+	int bkt_size = READ_ONCE(cipso_v4_cache_bucketsize);
 	int ret_val = -EPERM;
 	u32 bkt;
 	struct cipso_v4_map_cache_entry *entry = NULL;
 	struct cipso_v4_map_cache_entry *old_entry = NULL;
 	u32 cipso_ptr_len;
 
-	if (!cipso_v4_cache_enabled || cipso_v4_cache_bucketsize <= 0)
+	if (!READ_ONCE(cipso_v4_cache_enabled) || bkt_size <= 0)
 		return 0;
 
 	cipso_ptr_len = cipso_ptr[1];
@@ -322,7 +323,7 @@ int cipso_v4_cache_add(const unsigned char *cipso_ptr,
 
 	bkt = entry->hash & (CIPSO_V4_CACHE_BUCKETS - 1);
 	spin_lock_bh(&cipso_v4_cache[bkt].lock);
-	if (cipso_v4_cache[bkt].size < cipso_v4_cache_bucketsize) {
+	if (cipso_v4_cache[bkt].size < bkt_size) {
 		list_add(&entry->list, &cipso_v4_cache[bkt].list);
 		cipso_v4_cache[bkt].size += 1;
 	} else {
@@ -1199,7 +1200,8 @@ static int cipso_v4_gentag_rbm(const struct cipso_v4_doi *doi_def,
 		/* This will send packets using the "optimized" format when
 		 * possible as specified in  section 3.4.2.6 of the
 		 * CIPSO draft. */
-		if (cipso_v4_rbm_optfmt && ret_val > 0 && ret_val <= 10)
+		if (READ_ONCE(cipso_v4_rbm_optfmt) && ret_val > 0 &&
+		    ret_val <= 10)
 			tag_len = 14;
 		else
 			tag_len = 4 + ret_val;
@@ -1603,7 +1605,7 @@ int cipso_v4_validate(const struct sk_buff *skb, unsigned char **option)
 			 * all the CIPSO validations here but it doesn't
 			 * really specify _exactly_ what we need to validate
 			 * ... so, just make it a sysctl tunable. */
-			if (cipso_v4_rbm_strictvalid) {
+			if (READ_ONCE(cipso_v4_rbm_strictvalid)) {
 				if (cipso_v4_map_lvl_valid(doi_def,
 							   tag[3]) < 0) {
 					err_offset = opt_iter + 3;
diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index a5439a8414d4..14f037e8ac55 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -1231,7 +1231,7 @@ static int fib_check_nh_nongw(struct net *net, struct fib_nh *nh,
 
 	nh->fib_nh_dev = in_dev->dev;
 	netdev_hold(nh->fib_nh_dev, &nh->fib_nh_dev_tracker, GFP_ATOMIC);
-	nh->fib_nh_scope = RT_SCOPE_HOST;
+	nh->fib_nh_scope = RT_SCOPE_LINK;
 	if (!netif_carrier_ok(nh->fib_nh_dev))
 		nh->fib_nh_flags |= RTNH_F_LINKDOWN;
 	err = 0;
@@ -1812,7 +1812,7 @@ int fib_dump_info(struct sk_buff *skb, u32 portid, u32 seq, int event,
 			goto nla_put_failure;
 		if (nexthop_is_blackhole(fi->nh))
 			rtm->rtm_type = RTN_BLACKHOLE;
-		if (!fi->fib_net->ipv4.sysctl_nexthop_compat_mode)
+		if (!READ_ONCE(fi->fib_net->ipv4.sysctl_nexthop_compat_mode))
 			goto offload;
 	}
 
diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c
index 2734c3af7e24..46e8a5125853 100644
--- a/net/ipv4/fib_trie.c
+++ b/net/ipv4/fib_trie.c
@@ -498,7 +498,7 @@ static void tnode_free(struct key_vector *tn)
 		tn = container_of(head, struct tnode, rcu)->kv;
 	}
 
-	if (tnode_free_size >= sysctl_fib_sync_mem) {
+	if (tnode_free_size >= READ_ONCE(sysctl_fib_sync_mem)) {
 		tnode_free_size = 0;
 		synchronize_rcu();
 	}
diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c
index efea0e796f06..57c4f0d87a7a 100644
--- a/net/ipv4/icmp.c
+++ b/net/ipv4/icmp.c
@@ -253,11 +253,12 @@ bool icmp_global_allow(void)
 	spin_lock(&icmp_global.lock);
 	delta = min_t(u32, now - icmp_global.stamp, HZ);
 	if (delta >= HZ / 50) {
-		incr = sysctl_icmp_msgs_per_sec * delta / HZ ;
+		incr = READ_ONCE(sysctl_icmp_msgs_per_sec) * delta / HZ;
 		if (incr)
 			WRITE_ONCE(icmp_global.stamp, now);
 	}
-	credit = min_t(u32, icmp_global.credit + incr, sysctl_icmp_msgs_burst);
+	credit = min_t(u32, icmp_global.credit + incr,
+		       READ_ONCE(sysctl_icmp_msgs_burst));
 	if (credit) {
 		/* We want to use a credit of one in average, but need to randomize
 		 * it for security reasons.
@@ -281,7 +282,7 @@ static bool icmpv4_mask_allow(struct net *net, int type, int code)
 		return true;
 
 	/* Limit if icmp type is enabled in ratemask. */
-	if (!((1 << type) & net->ipv4.sysctl_icmp_ratemask))
+	if (!((1 << type) & READ_ONCE(net->ipv4.sysctl_icmp_ratemask)))
 		return true;
 
 	return false;
@@ -319,7 +320,8 @@ static bool icmpv4_xrlim_allow(struct net *net, struct rtable *rt,
 
 	vif = l3mdev_master_ifindex(dst->dev);
 	peer = inet_getpeer_v4(net->ipv4.peers, fl4->daddr, vif, 1);
-	rc = inet_peer_xrlim_allow(peer, net->ipv4.sysctl_icmp_ratelimit);
+	rc = inet_peer_xrlim_allow(peer,
+				   READ_ONCE(net->ipv4.sysctl_icmp_ratelimit));
 	if (peer)
 		inet_putpeer(peer);
 out:
@@ -692,7 +694,7 @@ void __icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info,
 
 		rcu_read_lock();
 		if (rt_is_input_route(rt) &&
-		    net->ipv4.sysctl_icmp_errors_use_inbound_ifaddr)
+		    READ_ONCE(net->ipv4.sysctl_icmp_errors_use_inbound_ifaddr))
 			dev = dev_get_by_index_rcu(net, inet_iif(skb_in));
 
 		if (dev)
@@ -932,7 +934,7 @@ static enum skb_drop_reason icmp_unreach(struct sk_buff *skb)
 	 *	get the other vendor to fix their kit.
 	 */
 
-	if (!net->ipv4.sysctl_icmp_ignore_bogus_error_responses &&
+	if (!READ_ONCE(net->ipv4.sysctl_icmp_ignore_bogus_error_responses) &&
 	    inet_addr_type_dev_table(net, skb->dev, iph->daddr) == RTN_BROADCAST) {
 		net_warn_ratelimited("%pI4 sent an invalid ICMP type %u, code %u error to a broadcast: %pI4 on %s\n",
 				     &ip_hdr(skb)->saddr,
@@ -992,7 +994,7 @@ static enum skb_drop_reason icmp_echo(struct sk_buff *skb)
 
 	net = dev_net(skb_dst(skb)->dev);
 	/* should there be an ICMP stat for ignored echos? */
-	if (net->ipv4.sysctl_icmp_echo_ignore_all)
+	if (READ_ONCE(net->ipv4.sysctl_icmp_echo_ignore_all))
 		return SKB_NOT_DROPPED_YET;
 
 	icmp_param.data.icmph	   = *icmp_hdr(skb);
@@ -1027,7 +1029,7 @@ bool icmp_build_probe(struct sk_buff *skb, struct icmphdr *icmphdr)
 	u16 ident_len;
 	u8 status;
 
-	if (!net->ipv4.sysctl_icmp_echo_enable_probe)
+	if (!READ_ONCE(net->ipv4.sysctl_icmp_echo_enable_probe))
 		return false;
 
 	/* We currently only support probing interfaces on the proxy node
@@ -1248,7 +1250,7 @@ int icmp_rcv(struct sk_buff *skb)
 		 */
 		if ((icmph->type == ICMP_ECHO ||
 		     icmph->type == ICMP_TIMESTAMP) &&
-		    net->ipv4.sysctl_icmp_echo_ignore_broadcasts) {
+		    READ_ONCE(net->ipv4.sysctl_icmp_echo_ignore_broadcasts)) {
 			reason = SKB_DROP_REASON_INVALID_PROTO;
 			goto error;
 		}
diff --git a/net/ipv4/inet_timewait_sock.c b/net/ipv4/inet_timewait_sock.c
index 0ec501845cb3..47ccc343c9fb 100644
--- a/net/ipv4/inet_timewait_sock.c
+++ b/net/ipv4/inet_timewait_sock.c
@@ -156,7 +156,8 @@ struct inet_timewait_sock *inet_twsk_alloc(const struct sock *sk,
 {
 	struct inet_timewait_sock *tw;
 
-	if (refcount_read(&dr->tw_refcount) - 1 >= dr->sysctl_max_tw_buckets)
+	if (refcount_read(&dr->tw_refcount) - 1 >=
+	    READ_ONCE(dr->sysctl_max_tw_buckets))
 		return NULL;
 
 	tw = kmem_cache_alloc(sk->sk_prot_creator->twsk_prot->twsk_slab,
diff --git a/net/ipv4/inetpeer.c b/net/ipv4/inetpeer.c
index da21dfce24d7..e9fed83e9b3c 100644
--- a/net/ipv4/inetpeer.c
+++ b/net/ipv4/inetpeer.c
@@ -141,16 +141,20 @@ static void inet_peer_gc(struct inet_peer_base *base,
 			 struct inet_peer *gc_stack[],
 			 unsigned int gc_cnt)
 {
+	int peer_threshold, peer_maxttl, peer_minttl;
 	struct inet_peer *p;
 	__u32 delta, ttl;
 	int i;
 
-	if (base->total >= inet_peer_threshold)
+	peer_threshold = READ_ONCE(inet_peer_threshold);
+	peer_maxttl = READ_ONCE(inet_peer_maxttl);
+	peer_minttl = READ_ONCE(inet_peer_minttl);
+
+	if (base->total >= peer_threshold)
 		ttl = 0; /* be aggressive */
 	else
-		ttl = inet_peer_maxttl
-				- (inet_peer_maxttl - inet_peer_minttl) / HZ *
-					base->total / inet_peer_threshold * HZ;
+		ttl = peer_maxttl - (peer_maxttl - peer_minttl) / HZ *
+			base->total / peer_threshold * HZ;
 	for (i = 0; i < gc_cnt; i++) {
 		p = gc_stack[i];
 
diff --git a/net/ipv4/nexthop.c b/net/ipv4/nexthop.c
index e459a391e607..853a75a8fbaf 100644
--- a/net/ipv4/nexthop.c
+++ b/net/ipv4/nexthop.c
@@ -1858,7 +1858,7 @@ static void __remove_nexthop_fib(struct net *net, struct nexthop *nh)
 		/* __ip6_del_rt does a release, so do a hold here */
 		fib6_info_hold(f6i);
 		ipv6_stub->ip6_del_rt(net, f6i,
-				      !net->ipv4.sysctl_nexthop_compat_mode);
+				      !READ_ONCE(net->ipv4.sysctl_nexthop_compat_mode));
 	}
 }
 
@@ -2361,7 +2361,8 @@ out:
 	if (!rc) {
 		nh_base_seq_inc(net);
 		nexthop_notify(RTM_NEWNEXTHOP, new_nh, &cfg->nlinfo);
-		if (replace_notify && net->ipv4.sysctl_nexthop_compat_mode)
+		if (replace_notify &&
+		    READ_ONCE(net->ipv4.sysctl_nexthop_compat_mode))
 			nexthop_replace_notify(net, new_nh, &cfg->nlinfo);
 	}
 
diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c
index f33c31dd7366..b387c4835155 100644
--- a/net/ipv4/syncookies.c
+++ b/net/ipv4/syncookies.c
@@ -273,7 +273,7 @@ bool cookie_ecn_ok(const struct tcp_options_received *tcp_opt,
 	if (!ecn_ok)
 		return false;
 
-	if (net->ipv4.sysctl_tcp_ecn)
+	if (READ_ONCE(net->ipv4.sysctl_tcp_ecn))
 		return true;
 
 	return dst_feature(dst, RTAX_FEATURE_ECN);
diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index cd448cdd3b38..108fd86f2718 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -599,6 +599,8 @@ static struct ctl_table ipv4_net_table[] = {
 		.maxlen		= sizeof(u8),
 		.mode		= 0644,
 		.proc_handler	= proc_dou8vec_minmax,
+		.extra1		= SYSCTL_ZERO,
+		.extra2		= SYSCTL_ONE
 	},
 	{
 		.procname	= "icmp_echo_enable_probe",
@@ -615,6 +617,8 @@ static struct ctl_table ipv4_net_table[] = {
 		.maxlen		= sizeof(u8),
 		.mode		= 0644,
 		.proc_handler	= proc_dou8vec_minmax,
+		.extra1		= SYSCTL_ZERO,
+		.extra2		= SYSCTL_ONE
 	},
 	{
 		.procname	= "icmp_ignore_bogus_error_responses",
@@ -622,6 +626,8 @@ static struct ctl_table ipv4_net_table[] = {
 		.maxlen		= sizeof(u8),
 		.mode		= 0644,
 		.proc_handler	= proc_dou8vec_minmax,
+		.extra1		= SYSCTL_ZERO,
+		.extra2		= SYSCTL_ONE
 	},
 	{
 		.procname	= "icmp_errors_use_inbound_ifaddr",
@@ -629,6 +635,8 @@ static struct ctl_table ipv4_net_table[] = {
 		.maxlen		= sizeof(u8),
 		.mode		= 0644,
 		.proc_handler	= proc_dou8vec_minmax,
+		.extra1		= SYSCTL_ZERO,
+		.extra2		= SYSCTL_ONE
 	},
 	{
 		.procname	= "icmp_ratelimit",
@@ -668,6 +676,8 @@ static struct ctl_table ipv4_net_table[] = {
 		.maxlen		= sizeof(u8),
 		.mode		= 0644,
 		.proc_handler	= proc_dou8vec_minmax,
+		.extra1		= SYSCTL_ZERO,
+		.extra2		= SYSCTL_TWO,
 	},
 	{
 		.procname	= "tcp_ecn_fallback",
@@ -675,6 +685,8 @@ static struct ctl_table ipv4_net_table[] = {
 		.maxlen		= sizeof(u8),
 		.mode		= 0644,
 		.proc_handler	= proc_dou8vec_minmax,
+		.extra1		= SYSCTL_ZERO,
+		.extra2		= SYSCTL_ONE,
 	},
 	{
 		.procname	= "ip_dynaddr",
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 21bdee88383b..96b6e9c22068 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -2784,7 +2784,8 @@ static void tcp_orphan_update(struct timer_list *unused)
 
 static bool tcp_too_many_orphans(int shift)
 {
-	return READ_ONCE(tcp_orphan_cache) << shift > sysctl_tcp_max_orphans;
+	return READ_ONCE(tcp_orphan_cache) << shift >
+		READ_ONCE(sysctl_tcp_max_orphans);
 }
 
 bool tcp_check_oom(struct sock *sk, int shift)
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 80cb112ef142..acee998c14b2 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -6726,7 +6726,7 @@ static void tcp_ecn_create_request(struct request_sock *req,
 
 	ect = !INET_ECN_is_not_ect(TCP_SKB_CB(skb)->ip_dsfield);
 	ecn_ok_dst = dst_feature(dst, DST_FEATURE_ECN_MASK);
-	ecn_ok = net->ipv4.sysctl_tcp_ecn || ecn_ok_dst;
+	ecn_ok = READ_ONCE(net->ipv4.sysctl_tcp_ecn) || ecn_ok_dst;
 
 	if (((!ect || th->res1) && ecn_ok) || tcp_ca_needs_ecn(listen_sk) ||
 	    (ecn_ok_dst & DST_FEATURE_ECN_CA) ||
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index d1ca3df275df..858a15cc2cc9 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -324,7 +324,7 @@ static void tcp_ecn_send_syn(struct sock *sk, struct sk_buff *skb)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 	bool bpf_needs_ecn = tcp_bpf_ca_needs_ecn(sk);
-	bool use_ecn = sock_net(sk)->ipv4.sysctl_tcp_ecn == 1 ||
+	bool use_ecn = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_ecn) == 1 ||
 		tcp_ca_needs_ecn(sk) || bpf_needs_ecn;
 
 	if (!use_ecn) {
@@ -346,7 +346,7 @@ static void tcp_ecn_send_syn(struct sock *sk, struct sk_buff *skb)
 
 static void tcp_ecn_clear_syn(struct sock *sk, struct sk_buff *skb)
 {
-	if (sock_net(sk)->ipv4.sysctl_tcp_ecn_fallback)
+	if (READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_ecn_fallback))
 		/* tp->ecn_flags are cleared at a later point in time when
 		 * SYN ACK is ultimatively being received.
 		 */