Merge branch 'net-sysctl-races-round2'

Kuniyuki Iwashima says:

====================
sysctl: Fix data-races around ipv4_net_table (Round 2).

This series fixes data-races around 15 knobs after ip_default_ttl in
ipv4_net_table.

These two knobs are skipped.
  - ip_local_port_range is safe with its own lock.
  - ip_local_reserved_ports uses proc_do_large_bitmap(), which will need
    an additional lock and can be fixed later.

So, the next round will start with igmp_link_local_mcast_reports.
====================

Signed-off-by: David S. Miller <[email protected]>

20 files changed, 35 insertions, 32 deletions

diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
index 0d8a0068e4ca..868d28f3b4e1 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c
@@ -10523,13 +10523,14 @@ static int mlxsw_sp_dscp_init(struct mlxsw_sp *mlxsw_sp)
 static int __mlxsw_sp_router_init(struct mlxsw_sp *mlxsw_sp)
 {
 	struct net *net = mlxsw_sp_net(mlxsw_sp);
-	bool usp = net->ipv4.sysctl_ip_fwd_update_priority;
 	char rgcr_pl[MLXSW_REG_RGCR_LEN];
 	u64 max_rifs;
+	bool usp;
 
 	if (!MLXSW_CORE_RES_VALID(mlxsw_sp->core, MAX_RIFS))
 		return -EIO;
 	max_rifs = MLXSW_CORE_RES_GET(mlxsw_sp->core, MAX_RIFS);
+	usp = READ_ONCE(net->ipv4.sysctl_ip_fwd_update_priority);
 
 	mlxsw_reg_rgcr_pack(rgcr_pl, true, true);
 	mlxsw_reg_rgcr_max_router_interfaces_set(rgcr_pl, max_rifs);
diff --git a/drivers/net/ethernet/netronome/nfp/flower/action.c b/drivers/net/ethernet/netronome/nfp/flower/action.c
index 0147de405365..ffb6f6d05a07 100644
--- a/drivers/net/ethernet/netronome/nfp/flower/action.c
+++ b/drivers/net/ethernet/netronome/nfp/flower/action.c
@@ -474,7 +474,7 @@ nfp_fl_set_tun(struct nfp_app *app, struct nfp_fl_set_tun *set_tun,
 			set_tun->ttl = ip4_dst_hoplimit(&rt->dst);
 			ip_rt_put(rt);
 		} else {
-			set_tun->ttl = net->ipv4.sysctl_ip_default_ttl;
+			set_tun->ttl = READ_ONCE(net->ipv4.sysctl_ip_default_ttl);
 		}
 	}
 
diff --git a/include/net/inet_hashtables.h b/include/net/inet_hashtables.h
index ebfa3df6f8dc..fd6b510d114b 100644
--- a/include/net/inet_hashtables.h
+++ b/include/net/inet_hashtables.h
@@ -179,7 +179,7 @@ static inline bool inet_sk_bound_dev_eq(struct net *net, int bound_dev_if,
 					int dif, int sdif)
 {
 #if IS_ENABLED(CONFIG_NET_L3_MASTER_DEV)
-	return inet_bound_dev_eq(!!net->ipv4.sysctl_tcp_l3mdev_accept,
+	return inet_bound_dev_eq(!!READ_ONCE(net->ipv4.sysctl_tcp_l3mdev_accept),
 				 bound_dev_if, dif, sdif);
 #else
 	return inet_bound_dev_eq(true, bound_dev_if, dif, sdif);
diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h
index daead5fb389a..6395f6b9a5d2 100644
--- a/include/net/inet_sock.h
+++ b/include/net/inet_sock.h
@@ -107,7 +107,8 @@ static inline struct inet_request_sock *inet_rsk(const struct request_sock *sk)
 
 static inline u32 inet_request_mark(const struct sock *sk, struct sk_buff *skb)
 {
-	if (!sk->sk_mark && sock_net(sk)->ipv4.sysctl_tcp_fwmark_accept)
+	if (!sk->sk_mark &&
+	    READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_fwmark_accept))
 		return skb->mark;
 
 	return sk->sk_mark;
@@ -120,7 +121,7 @@ static inline int inet_request_bound_dev_if(const struct sock *sk,
 #ifdef CONFIG_NET_L3_MASTER_DEV
 	struct net *net = sock_net(sk);
 
-	if (!bound_dev_if && net->ipv4.sysctl_tcp_l3mdev_accept)
+	if (!bound_dev_if && READ_ONCE(net->ipv4.sysctl_tcp_l3mdev_accept))
 		return l3mdev_master_ifindex_by_index(net, skb->skb_iif);
 #endif
 
@@ -132,7 +133,7 @@ static inline int inet_sk_bound_l3mdev(const struct sock *sk)
 #ifdef CONFIG_NET_L3_MASTER_DEV
 	struct net *net = sock_net(sk);
 
-	if (!net->ipv4.sysctl_tcp_l3mdev_accept)
+	if (!READ_ONCE(net->ipv4.sysctl_tcp_l3mdev_accept))
 		return l3mdev_master_ifindex_by_index(net,
 						      sk->sk_bound_dev_if);
 #endif
@@ -374,7 +375,7 @@ static inline bool inet_get_convert_csum(struct sock *sk)
 static inline bool inet_can_nonlocal_bind(struct net *net,
 					  struct inet_sock *inet)
 {
-	return net->ipv4.sysctl_ip_nonlocal_bind ||
+	return READ_ONCE(net->ipv4.sysctl_ip_nonlocal_bind) ||
 		inet->freebind || inet->transparent;
 }
 
diff --git a/include/net/ip.h b/include/net/ip.h
index 26fffda78cca..4a15b6bcb4b8 100644
--- a/include/net/ip.h
+++ b/include/net/ip.h
@@ -384,7 +384,7 @@ void ipfrag_init(void);
 void ip_static_sysctl_init(void);
 
 #define IP4_REPLY_MARK(net, mark) \
-	((net)->ipv4.sysctl_fwmark_reflect ? (mark) : 0)
+	(READ_ONCE((net)->ipv4.sysctl_fwmark_reflect) ? (mark) : 0)
 
 static inline bool ip_is_fragment(const struct iphdr *iph)
 {
@@ -446,7 +446,7 @@ static inline unsigned int ip_dst_mtu_maybe_forward(const struct dst_entry *dst,
 	struct net *net = dev_net(dst->dev);
 	unsigned int mtu;
 
-	if (net->ipv4.sysctl_ip_fwd_use_pmtu ||
+	if (READ_ONCE(net->ipv4.sysctl_ip_fwd_use_pmtu) ||
 	    ip_mtu_locked(dst) ||
 	    !forwarding) {
 		mtu = rt->rt_pmtu;
diff --git a/include/net/route.h b/include/net/route.h
index 991a3985712d..bbcf2aba149f 100644
--- a/include/net/route.h
+++ b/include/net/route.h
@@ -373,7 +373,7 @@ static inline int ip4_dst_hoplimit(const struct dst_entry *dst)
 	struct net *net = dev_net(dst->dev);
 
 	if (hoplimit == 0)
-		hoplimit = net->ipv4.sysctl_ip_default_ttl;
+		hoplimit = READ_ONCE(net->ipv4.sysctl_ip_default_ttl);
 	return hoplimit;
 }
 
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index ac67f6b4ec70..4bc24f9e38b3 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -335,7 +335,7 @@ lookup_protocol:
 			inet->hdrincl = 1;
 	}
 
-	if (net->ipv4.sysctl_ip_no_pmtu_disc)
+	if (READ_ONCE(net->ipv4.sysctl_ip_no_pmtu_disc))
 		inet->pmtudisc = IP_PMTUDISC_DONT;
 	else
 		inet->pmtudisc = IP_PMTUDISC_WANT;
diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c
index 57c4f0d87a7a..d5d745c3e345 100644
--- a/net/ipv4/icmp.c
+++ b/net/ipv4/icmp.c
@@ -881,7 +881,7 @@ static enum skb_drop_reason icmp_unreach(struct sk_buff *skb)
 			 * values please see
 			 * Documentation/networking/ip-sysctl.rst
 			 */
-			switch (net->ipv4.sysctl_ip_no_pmtu_disc) {
+			switch (READ_ONCE(net->ipv4.sysctl_ip_no_pmtu_disc)) {
 			default:
 				net_dbg_ratelimited("%pI4: fragmentation needed and DF set\n",
 						    &iph->daddr);
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index 53f5f956d948..2c44556af452 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -263,7 +263,7 @@ next_port:
 		goto other_half_scan;
 	}
 
-	if (net->ipv4.sysctl_ip_autobind_reuse && !relax) {
+	if (READ_ONCE(net->ipv4.sysctl_ip_autobind_reuse) && !relax) {
 		/* We still have a chance to connect to different destinations */
 		relax = true;
 		goto ports_exhausted;
diff --git a/net/ipv4/ip_forward.c b/net/ipv4/ip_forward.c
index e3aa436a1bdf..e18931a6d153 100644
--- a/net/ipv4/ip_forward.c
+++ b/net/ipv4/ip_forward.c
@@ -157,7 +157,7 @@ int ip_forward(struct sk_buff *skb)
 	    !skb_sec_path(skb))
 		ip_rt_send_redirect(skb);
 
-	if (net->ipv4.sysctl_ip_fwd_update_priority)
+	if (READ_ONCE(net->ipv4.sysctl_ip_fwd_update_priority))
 		skb->priority = rt_tos2priority(iph->tos);
 
 	return NF_HOOK(NFPROTO_IPV4, NF_INET_FORWARD,
diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c
index 445a9ecaefa1..d497d525dea3 100644
--- a/net/ipv4/ip_sockglue.c
+++ b/net/ipv4/ip_sockglue.c
@@ -1606,7 +1606,7 @@ static int do_ip_getsockopt(struct sock *sk, int level, int optname,
 	{
 		struct net *net = sock_net(sk);
 		val = (inet->uc_ttl == -1 ?
-		       net->ipv4.sysctl_ip_default_ttl :
+		       READ_ONCE(net->ipv4.sysctl_ip_default_ttl) :
 		       inet->uc_ttl);
 		break;
 	}
diff --git a/net/ipv4/netfilter/nf_reject_ipv4.c b/net/ipv4/netfilter/nf_reject_ipv4.c
index 918c61fda0f3..d640adcaf1b1 100644
--- a/net/ipv4/netfilter/nf_reject_ipv4.c
+++ b/net/ipv4/netfilter/nf_reject_ipv4.c
@@ -62,7 +62,7 @@ struct sk_buff *nf_reject_skb_v4_tcp_reset(struct net *net,
 
 	skb_reserve(nskb, LL_MAX_HEADER);
 	niph = nf_reject_iphdr_put(nskb, oldskb, IPPROTO_TCP,
-				   net->ipv4.sysctl_ip_default_ttl);
+				   READ_ONCE(net->ipv4.sysctl_ip_default_ttl));
 	nf_reject_ip_tcphdr_put(nskb, oldskb, oth);
 	niph->tot_len = htons(nskb->len);
 	ip_send_check(niph);
@@ -117,7 +117,7 @@ struct sk_buff *nf_reject_skb_v4_unreach(struct net *net,
 
 	skb_reserve(nskb, LL_MAX_HEADER);
 	niph = nf_reject_iphdr_put(nskb, oldskb, IPPROTO_ICMP,
-				   net->ipv4.sysctl_ip_default_ttl);
+				   READ_ONCE(net->ipv4.sysctl_ip_default_ttl));
 
 	skb_reset_transport_header(nskb);
 	icmph = skb_put_zero(nskb, sizeof(struct icmphdr));
diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c
index 28836071f0a6..0088a4c64d77 100644
--- a/net/ipv4/proc.c
+++ b/net/ipv4/proc.c
@@ -387,7 +387,7 @@ static int snmp_seq_show_ipstats(struct seq_file *seq, void *v)
 
 	seq_printf(seq, "\nIp: %d %d",
 		   IPV4_DEVCONF_ALL(net, FORWARDING) ? 1 : 2,
-		   net->ipv4.sysctl_ip_default_ttl);
+		   READ_ONCE(net->ipv4.sysctl_ip_default_ttl));
 
 	BUILD_BUG_ON(offsetof(struct ipstats_mib, mibs) != 0);
 	snmp_get_cpu_field64_batch(buff64, snmp4_ipstats_list,
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 356f535f3443..91c4f60de75a 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -1398,7 +1398,7 @@ u32 ip_mtu_from_fib_result(struct fib_result *res, __be32 daddr)
 	struct fib_info *fi = res->fi;
 	u32 mtu = 0;
 
-	if (dev_net(dev)->ipv4.sysctl_ip_fwd_use_pmtu ||
+	if (READ_ONCE(dev_net(dev)->ipv4.sysctl_ip_fwd_use_pmtu) ||
 	    fi->fib_metrics->metrics[RTAX_LOCK - 1] & (1 << RTAX_MTU))
 		mtu = fi->fib_mtu;
 
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 11aa0ab10bba..02ab3a9c6657 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -1719,7 +1719,8 @@ static inline int __tcp_mtu_to_mss(struct sock *sk, int pmtu)
 	mss_now -= icsk->icsk_ext_hdr_len;
 
 	/* Then reserve room for full set of TCP options and 8 bytes of data */
-	mss_now = max(mss_now, sock_net(sk)->ipv4.sysctl_tcp_min_snd_mss);
+	mss_now = max(mss_now,
+		      READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_min_snd_mss));
 	return mss_now;
 }
 
@@ -1762,10 +1763,10 @@ void tcp_mtup_init(struct sock *sk)
 	struct inet_connection_sock *icsk = inet_csk(sk);
 	struct net *net = sock_net(sk);
 
-	icsk->icsk_mtup.enabled = net->ipv4.sysctl_tcp_mtu_probing > 1;
+	icsk->icsk_mtup.enabled = READ_ONCE(net->ipv4.sysctl_tcp_mtu_probing) > 1;
 	icsk->icsk_mtup.search_high = tp->rx_opt.mss_clamp + sizeof(struct tcphdr) +
 			       icsk->icsk_af_ops->net_header_len;
-	icsk->icsk_mtup.search_low = tcp_mss_to_mtu(sk, net->ipv4.sysctl_tcp_base_mss);
+	icsk->icsk_mtup.search_low = tcp_mss_to_mtu(sk, READ_ONCE(net->ipv4.sysctl_tcp_base_mss));
 	icsk->icsk_mtup.probe_size = 0;
 	if (icsk->icsk_mtup.enabled)
 		icsk->icsk_mtup.probe_timestamp = tcp_jiffies32;
@@ -2282,7 +2283,7 @@ static inline void tcp_mtu_check_reprobe(struct sock *sk)
 	u32 interval;
 	s32 delta;
 
-	interval = net->ipv4.sysctl_tcp_probe_interval;
+	interval = READ_ONCE(net->ipv4.sysctl_tcp_probe_interval);
 	delta = tcp_jiffies32 - icsk->icsk_mtup.probe_timestamp;
 	if (unlikely(delta >= interval * HZ)) {
 		int mss = tcp_current_mss(sk);
@@ -2366,7 +2367,7 @@ static int tcp_mtu_probe(struct sock *sk)
 	 * probing process by not resetting search range to its orignal.
 	 */
 	if (probe_size > tcp_mtu_to_mss(sk, icsk->icsk_mtup.search_high) ||
-		interval < net->ipv4.sysctl_tcp_probe_threshold) {
+	    interval < READ_ONCE(net->ipv4.sysctl_tcp_probe_threshold)) {
 		/* Check whether enough time has elaplased for
 		 * another round of probing.
 		 */
diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c
index 20cf4a98c69d..4f3b9ab222b6 100644
--- a/net/ipv4/tcp_timer.c
+++ b/net/ipv4/tcp_timer.c
@@ -163,7 +163,7 @@ static void tcp_mtu_probing(struct inet_connection_sock *icsk, struct sock *sk)
 	int mss;
 
 	/* Black hole detection */
-	if (!net->ipv4.sysctl_tcp_mtu_probing)
+	if (!READ_ONCE(net->ipv4.sysctl_tcp_mtu_probing))
 		return;
 
 	if (!icsk->icsk_mtup.enabled) {
@@ -171,9 +171,9 @@ static void tcp_mtu_probing(struct inet_connection_sock *icsk, struct sock *sk)
 		icsk->icsk_mtup.probe_timestamp = tcp_jiffies32;
 	} else {
 		mss = tcp_mtu_to_mss(sk, icsk->icsk_mtup.search_low) >> 1;
-		mss = min(net->ipv4.sysctl_tcp_base_mss, mss);
-		mss = max(mss, net->ipv4.sysctl_tcp_mtu_probe_floor);
-		mss = max(mss, net->ipv4.sysctl_tcp_min_snd_mss);
+		mss = min(READ_ONCE(net->ipv4.sysctl_tcp_base_mss), mss);
+		mss = max(mss, READ_ONCE(net->ipv4.sysctl_tcp_mtu_probe_floor));
+		mss = max(mss, READ_ONCE(net->ipv4.sysctl_tcp_min_snd_mss));
 		icsk->icsk_mtup.search_low = tcp_mss_to_mtu(sk, mss);
 	}
 	tcp_sync_mss(sk, icsk->icsk_pmtu_cookie);
diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c
index 70564ddccc46..6f354f8be2c5 100644
--- a/net/ipv6/af_inet6.c
+++ b/net/ipv6/af_inet6.c
@@ -226,7 +226,7 @@ lookup_protocol:
 	RCU_INIT_POINTER(inet->mc_list, NULL);
 	inet->rcv_tos	= 0;
 
-	if (net->ipv4.sysctl_ip_no_pmtu_disc)
+	if (READ_ONCE(net->ipv4.sysctl_ip_no_pmtu_disc))
 		inet->pmtudisc = IP_PMTUDISC_DONT;
 	else
 		inet->pmtudisc = IP_PMTUDISC_WANT;
diff --git a/net/netfilter/nf_synproxy_core.c b/net/netfilter/nf_synproxy_core.c
index e479dd0561c5..16915f8eef2b 100644
--- a/net/netfilter/nf_synproxy_core.c
+++ b/net/netfilter/nf_synproxy_core.c
@@ -405,7 +405,7 @@ synproxy_build_ip(struct net *net, struct sk_buff *skb, __be32 saddr,
 	iph->tos	= 0;
 	iph->id		= 0;
 	iph->frag_off	= htons(IP_DF);
-	iph->ttl	= net->ipv4.sysctl_ip_default_ttl;
+	iph->ttl	= READ_ONCE(net->ipv4.sysctl_ip_default_ttl);
 	iph->protocol	= IPPROTO_TCP;
 	iph->check	= 0;
 	iph->saddr	= saddr;
diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c
index 35928fefae33..1a094b087d88 100644
--- a/net/sctp/protocol.c
+++ b/net/sctp/protocol.c
@@ -358,7 +358,7 @@ static int sctp_v4_available(union sctp_addr *addr, struct sctp_sock *sp)
 	if (addr->v4.sin_addr.s_addr != htonl(INADDR_ANY) &&
 	   ret != RTN_LOCAL &&
 	   !sp->inet.freebind &&
-	   !net->ipv4.sysctl_ip_nonlocal_bind)
+	    !READ_ONCE(net->ipv4.sysctl_ip_nonlocal_bind))
 		return 0;
 
 	if (ipv6_only_sock(sctp_opt2sk(sp)))
diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c
index 08564e0eef20..ccfb172eb5b8 100644
--- a/net/xfrm/xfrm_state.c
+++ b/net/xfrm/xfrm_state.c
@@ -2620,7 +2620,7 @@ int __xfrm_init_state(struct xfrm_state *x, bool init_replay, bool offload)
 	int err;
 
 	if (family == AF_INET &&
-	    xs_net(x)->ipv4.sysctl_ip_no_pmtu_disc)
+	    READ_ONCE(xs_net(x)->ipv4.sysctl_ip_no_pmtu_disc))
 		x->props.flags |= XFRM_STATE_NOPMTUDISC;
 
 	err = -EPROTONOSUPPORT;