Merge branch 'ipv6-more-data-race-annotations'

Eric Dumazet says:

====================
ipv6: more data-race annotations

Inspired by one unrelated syzbot report.

This series adds missing (and boring) data-race annotations in IPv6.

Only the first patch adds sysctl_ipv6_flowlabel group
to speedup ip6_make_flowlabel() a bit.
====================

Link: https://patch.msgid.link/20260115094141.3124990-1-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

include/net/ipv6.h

@@ -931,10 +931,10 @@ static inline void iph_to_flow_copy_v6addrs(struct flow_keys *flow,
 
 #if IS_ENABLED(CONFIG_IPV6)
 
-static inline bool ipv6_can_nonlocal_bind(struct net *net,
-					  struct inet_sock *inet)
+static inline bool ipv6_can_nonlocal_bind(const struct net *net,
+					  const struct inet_sock *inet)
 {
-	return net->ipv6.sysctl.ip_nonlocal_bind ||
+	return READ_ONCE(net->ipv6.sysctl.ip_nonlocal_bind) ||
 		test_bit(INET_FLAGS_FREEBIND, &inet->inet_flags) ||
 		test_bit(INET_FLAGS_TRANSPARENT, &inet->inet_flags);
 }
@@ -949,10 +949,12 @@ static inline bool ipv6_can_nonlocal_bind(struct net *net,
 
 #define IP6_DEFAULT_AUTO_FLOW_LABELS	IP6_AUTO_FLOW_LABEL_OPTOUT
 
-static inline __be32 ip6_make_flowlabel(struct net *net, struct sk_buff *skb,
+static inline __be32 ip6_make_flowlabel(const struct net *net,
+					struct sk_buff *skb,
 					__be32 flowlabel, bool autolabel,
 					struct flowi6 *fl6)
 {
+	u8 auto_flowlabels;
 	u32 hash;
 
 	/* @flowlabel may include more than a flow label, eg, the traffic class.
@@ -960,10 +962,12 @@ static inline __be32 ip6_make_flowlabel(struct net *net, struct sk_buff *skb,
 	 */
 	flowlabel &= IPV6_FLOWLABEL_MASK;
 
-	if (flowlabel ||
-	    net->ipv6.sysctl.auto_flowlabels == IP6_AUTO_FLOW_LABEL_OFF ||
-	    (!autolabel &&
-	     net->ipv6.sysctl.auto_flowlabels != IP6_AUTO_FLOW_LABEL_FORCED))
+	if (flowlabel)
+		return flowlabel;
+
+	auto_flowlabels = READ_ONCE(net->ipv6.sysctl.auto_flowlabels);
+	if (auto_flowlabels == IP6_AUTO_FLOW_LABEL_OFF ||
+	    (!autolabel && auto_flowlabels != IP6_AUTO_FLOW_LABEL_FORCED))
 		return flowlabel;
 
 	hash = skb_get_hash_flowi6(skb, fl6);
@@ -976,15 +980,15 @@ static inline __be32 ip6_make_flowlabel(struct net *net, struct sk_buff *skb,
 
 	flowlabel = (__force __be32)hash & IPV6_FLOWLABEL_MASK;
 
-	if (net->ipv6.sysctl.flowlabel_state_ranges)
+	if (READ_ONCE(net->ipv6.sysctl.flowlabel_state_ranges))
 		flowlabel |= IPV6_FLOWLABEL_STATELESS_FLAG;
 
 	return flowlabel;
 }
 
-static inline int ip6_default_np_autolabel(struct net *net)
+static inline int ip6_default_np_autolabel(const struct net *net)
 {
-	switch (net->ipv6.sysctl.auto_flowlabels) {
+	switch (READ_ONCE(net->ipv6.sysctl.auto_flowlabels)) {
 	case IP6_AUTO_FLOW_LABEL_OFF:
 	case IP6_AUTO_FLOW_LABEL_OPTIN:
 	default:
@@ -995,13 +999,13 @@ static inline int ip6_default_np_autolabel(struct net *net)
 	}
 }
 #else
-static inline __be32 ip6_make_flowlabel(struct net *net, struct sk_buff *skb,
+static inline __be32 ip6_make_flowlabel(const struct net *net, struct sk_buff *skb,
 					__be32 flowlabel, bool autolabel,
 					struct flowi6 *fl6)
 {
 	return flowlabel;
 }
-static inline int ip6_default_np_autolabel(struct net *net)
+static inline int ip6_default_np_autolabel(const struct net *net)
 {
 	return 0;
 }
@@ -1010,11 +1014,11 @@ static inline int ip6_default_np_autolabel(struct net *net)
 #if IS_ENABLED(CONFIG_IPV6)
 static inline int ip6_multipath_hash_policy(const struct net *net)
 {
-	return net->ipv6.sysctl.multipath_hash_policy;
+	return READ_ONCE(net->ipv6.sysctl.multipath_hash_policy);
 }
 static inline u32 ip6_multipath_hash_fields(const struct net *net)
 {
-	return net->ipv6.sysctl.multipath_hash_fields;
+	return READ_ONCE(net->ipv6.sysctl.multipath_hash_fields);
 }
 #else
 static inline int ip6_multipath_hash_policy(const struct net *net)

include/net/netns/ipv6.h

@@ -30,19 +30,23 @@ struct netns_sysctl_ipv6 {
 	int ip6_rt_min_advmss;
 	u32 multipath_hash_fields;
 	u8 multipath_hash_policy;
-	u8 bindv6only;
+
+	__cacheline_group_begin(sysctl_ipv6_flowlabel);
 	u8 flowlabel_consistency;
 	u8 auto_flowlabels;
-	int icmpv6_time;
+	u8 flowlabel_state_ranges;
+	__cacheline_group_end(sysctl_ipv6_flowlabel);
+
 	u8 icmpv6_echo_ignore_all;
 	u8 icmpv6_echo_ignore_multicast;
 	u8 icmpv6_echo_ignore_anycast;
+	int icmpv6_time;
 	DECLARE_BITMAP(icmpv6_ratemask, ICMPV6_MSG_MAX + 1);
 	unsigned long *icmpv6_ratemask_ptr;
 	u8 anycast_src_echo_reply;
+	u8 bindv6only;
 	u8 ip_nonlocal_bind;
 	u8 fwmark_reflect;
-	u8 flowlabel_state_ranges;
 	int idgen_retries;
 	int idgen_delay;
 	int flowlabel_reflect;

net/ipv6/af_inet6.c

@@ -224,8 +224,8 @@ static int inet6_create(struct net *net, struct socket *sock, int protocol,
 	inet6_set_bit(MC6_LOOP, sk);
 	inet6_set_bit(MC6_ALL, sk);
 	np->pmtudisc	= IPV6_PMTUDISC_WANT;
-	inet6_assign_bit(REPFLOW, sk, net->ipv6.sysctl.flowlabel_reflect &
-				     FLOWLABEL_REFLECT_ESTABLISHED);
+	inet6_assign_bit(REPFLOW, sk, READ_ONCE(net->ipv6.sysctl.flowlabel_reflect) &
+				      FLOWLABEL_REFLECT_ESTABLISHED);
 	sk->sk_ipv6only	= net->ipv6.sysctl.bindv6only;
 	sk->sk_txrehash = READ_ONCE(net->core.sysctl_txrehash);
 

net/ipv6/exthdrs.c

@@ -314,7 +314,7 @@ static int ipv6_destopt_rcv(struct sk_buff *skb)
 	}
 
 	extlen = (skb_transport_header(skb)[1] + 1) << 3;
-	if (extlen > net->ipv6.sysctl.max_dst_opts_len)
+	if (extlen > READ_ONCE(net->ipv6.sysctl.max_dst_opts_len))
 		goto fail_and_free;
 
 	opt->lastopt = opt->dst1 = skb_network_header_len(skb);
@@ -322,7 +322,8 @@ static int ipv6_destopt_rcv(struct sk_buff *skb)
 	dstbuf = opt->dst1;
 #endif
 
-	if (ip6_parse_tlv(false, skb, net->ipv6.sysctl.max_dst_opts_cnt)) {
+	if (ip6_parse_tlv(false, skb,
+			  READ_ONCE(net->ipv6.sysctl.max_dst_opts_cnt))) {
 		skb->transport_header += extlen;
 		opt = IP6CB(skb);
 #if IS_ENABLED(CONFIG_IPV6_MIP6)
@@ -1049,11 +1050,12 @@ int ipv6_parse_hopopts(struct sk_buff *skb)
 	}
 
 	extlen = (skb_transport_header(skb)[1] + 1) << 3;
-	if (extlen > net->ipv6.sysctl.max_hbh_opts_len)
+	if (extlen > READ_ONCE(net->ipv6.sysctl.max_hbh_opts_len))
 		goto fail_and_free;
 
 	opt->flags |= IP6SKB_HOPBYHOP;
-	if (ip6_parse_tlv(true, skb, net->ipv6.sysctl.max_hbh_opts_cnt)) {
+	if (ip6_parse_tlv(true, skb,
+			  READ_ONCE(net->ipv6.sysctl.max_hbh_opts_cnt))) {
 		skb->transport_header += extlen;
 		opt = IP6CB(skb);
 		opt->nhoff = sizeof(struct ipv6hdr);

net/ipv6/icmp.c

@@ -958,7 +958,8 @@ static enum skb_drop_reason icmpv6_echo_reply(struct sk_buff *skb)
 	tmp_hdr.icmp6_type = type;
 
 	memset(&fl6, 0, sizeof(fl6));
-	if (net->ipv6.sysctl.flowlabel_reflect & FLOWLABEL_REFLECT_ICMPV6_ECHO_REPLIES)
+	if (READ_ONCE(net->ipv6.sysctl.flowlabel_reflect) &
+	    FLOWLABEL_REFLECT_ICMPV6_ECHO_REPLIES)
 		fl6.flowlabel = ip6_flowlabel(ipv6_hdr(skb));
 
 	fl6.flowi6_proto = IPPROTO_ICMPV6;

net/ipv6/ip6_fib.c

@@ -1374,14 +1374,14 @@ static void fib6_start_gc(struct net *net, struct fib6_info *rt)
 	if (!timer_pending(&net->ipv6.ip6_fib_timer) &&
 	    (rt->fib6_flags & RTF_EXPIRES))
 		mod_timer(&net->ipv6.ip6_fib_timer,
-			  jiffies + net->ipv6.sysctl.ip6_rt_gc_interval);
+			  jiffies + READ_ONCE(net->ipv6.sysctl.ip6_rt_gc_interval));
 }
 
 void fib6_force_start_gc(struct net *net)
 {
 	if (!timer_pending(&net->ipv6.ip6_fib_timer))
 		mod_timer(&net->ipv6.ip6_fib_timer,
-			  jiffies + net->ipv6.sysctl.ip6_rt_gc_interval);
+			  jiffies + READ_ONCE(net->ipv6.sysctl.ip6_rt_gc_interval));
 }
 
 static void __fib6_update_sernum_upto_root(struct fib6_info *rt,
@@ -2413,6 +2413,7 @@ static void fib6_gc_all(struct net *net, struct fib6_gc_args *gc_args)
 void fib6_run_gc(unsigned long expires, struct net *net, bool force)
 {
 	struct fib6_gc_args gc_args;
+	int ip6_rt_gc_interval;
 	unsigned long now;
 
 	if (force) {
@@ -2421,8 +2422,8 @@ void fib6_run_gc(unsigned long expires, struct net *net, bool force)
 		mod_timer(&net->ipv6.ip6_fib_timer, jiffies + HZ);
 		return;
 	}
-	gc_args.timeout = expires ? (int)expires :
-			  net->ipv6.sysctl.ip6_rt_gc_interval;
+	ip6_rt_gc_interval = READ_ONCE(net->ipv6.sysctl.ip6_rt_gc_interval);
+	gc_args.timeout = expires ? (int)expires : ip6_rt_gc_interval;
 	gc_args.more = 0;
 
 	fib6_gc_all(net, &gc_args);
@@ -2431,8 +2432,7 @@ void fib6_run_gc(unsigned long expires, struct net *net, bool force)
 
 	if (gc_args.more)
 		mod_timer(&net->ipv6.ip6_fib_timer,
-			  round_jiffies(now
-					+ net->ipv6.sysctl.ip6_rt_gc_interval));
+			  round_jiffies(now + ip6_rt_gc_interval));
 	else
 		timer_delete(&net->ipv6.ip6_fib_timer);
 	spin_unlock_bh(&net->ipv6.fib6_gc_lock);

net/ipv6/route.c

@@ -2895,7 +2895,7 @@ static void rt6_do_update_pmtu(struct rt6_info *rt, u32 mtu)
 
 	dst_metric_set(&rt->dst, RTAX_MTU, mtu);
 	rt->rt6i_flags |= RTF_MODIFIED;
-	rt6_update_expires(rt, net->ipv6.sysctl.ip6_rt_mtu_expires);
+	rt6_update_expires(rt, READ_ONCE(net->ipv6.sysctl.ip6_rt_mtu_expires));
 }
 
 static bool rt6_cache_allowed_for_pmtu(const struct rt6_info *rt)
@@ -3256,8 +3256,8 @@ static unsigned int ip6_default_advmss(const struct dst_entry *dst)
 	rcu_read_lock();
 
 	net = dst_dev_net_rcu(dst);
-	if (mtu < net->ipv6.sysctl.ip6_rt_min_advmss)
-		mtu = net->ipv6.sysctl.ip6_rt_min_advmss;
+	mtu = max_t(unsigned int, mtu,
+		    READ_ONCE(net->ipv6.sysctl.ip6_rt_min_advmss));
 
 	rcu_read_unlock();
 
@@ -3359,10 +3359,10 @@ struct dst_entry *icmp6_dst_alloc(struct net_device *dev,
 static void ip6_dst_gc(struct dst_ops *ops)
 {
 	struct net *net = container_of(ops, struct net, ipv6.ip6_dst_ops);
-	int rt_min_interval = net->ipv6.sysctl.ip6_rt_gc_min_interval;
-	int rt_elasticity = net->ipv6.sysctl.ip6_rt_gc_elasticity;
-	int rt_gc_timeout = net->ipv6.sysctl.ip6_rt_gc_timeout;
-	unsigned long rt_last_gc = net->ipv6.ip6_rt_last_gc;
+	int rt_min_interval = READ_ONCE(net->ipv6.sysctl.ip6_rt_gc_min_interval);
+	int rt_elasticity = READ_ONCE(net->ipv6.sysctl.ip6_rt_gc_elasticity);
+	int rt_gc_timeout = READ_ONCE(net->ipv6.sysctl.ip6_rt_gc_timeout);
+	unsigned long rt_last_gc = READ_ONCE(net->ipv6.ip6_rt_last_gc);
 	unsigned int val;
 	int entries;
 
@@ -5005,7 +5005,7 @@ void rt6_sync_down_dev(struct net_device *dev, unsigned long event)
 	};
 	struct net *net = dev_net(dev);
 
-	if (net->ipv6.sysctl.skip_notify_on_dev_down)
+	if (READ_ONCE(net->ipv6.sysctl.skip_notify_on_dev_down))
 		fib6_clean_all_skip_notify(net, fib6_ifdown, &arg);
 	else
 		fib6_clean_all(net, fib6_ifdown, &arg);
@@ -6405,6 +6405,7 @@ void fib6_rt_update(struct net *net, struct fib6_info *rt,
 void fib6_info_hw_flags_set(struct net *net, struct fib6_info *f6i,
 			    bool offload, bool trap, bool offload_failed)
 {
+	u8 fib_notify_on_flag_change;
 	struct sk_buff *skb;
 	int err;
 
@@ -6416,8 +6417,9 @@ void fib6_info_hw_flags_set(struct net *net, struct fib6_info *f6i,
 	WRITE_ONCE(f6i->offload, offload);
 	WRITE_ONCE(f6i->trap, trap);
 
+	fib_notify_on_flag_change = READ_ONCE(net->ipv6.sysctl.fib_notify_on_flag_change);
 	/* 2 means send notifications only if offload_failed was changed. */
-	if (net->ipv6.sysctl.fib_notify_on_flag_change == 2 &&
+	if (fib_notify_on_flag_change == 2 &&
 	    READ_ONCE(f6i->offload_failed) == offload_failed)
 		return;
 
@@ -6429,7 +6431,7 @@ void fib6_info_hw_flags_set(struct net *net, struct fib6_info *f6i,
 		 */
 		return;
 
-	if (!net->ipv6.sysctl.fib_notify_on_flag_change)
+	if (!fib_notify_on_flag_change)
 		return;
 
 	skb = nlmsg_new(rt6_nlmsg_size(f6i), GFP_KERNEL);
@@ -6526,7 +6528,7 @@ static int ipv6_sysctl_rtcache_flush(const struct ctl_table *ctl, int write,
 		return ret;
 
 	net = (struct net *)ctl->extra1;
-	delay = net->ipv6.sysctl.flush_delay;
+	delay = READ_ONCE(net->ipv6.sysctl.flush_delay);
 	fib6_run_gc(delay <= 0 ? 0 : (unsigned long)delay, net, delay > 0);
 	return 0;
 }

net/ipv6/tcp_ipv6.c

@@ -1085,7 +1085,8 @@ static void tcp_v6_send_reset(const struct sock *sk, struct sk_buff *skb,
 			txhash = inet_twsk(sk)->tw_txhash;
 		}
 	} else {
-		if (net->ipv6.sysctl.flowlabel_reflect & FLOWLABEL_REFLECT_TCP_RESET)
+		if (READ_ONCE(net->ipv6.sysctl.flowlabel_reflect) &
+		    FLOWLABEL_REFLECT_TCP_RESET)
 			label = ip6_flowlabel(ipv6h);
 	}