From 8281b7ec5c56b71cb2cc5a1728b41607be66959c Mon Sep 17 00:00:00 2001 From: Kuniyuki Iwashima Date: Wed, 13 Jul 2022 13:51:51 -0700 Subject: [PATCH 01/15] ip: Fix data-races around sysctl_ip_default_ttl. While reading sysctl_ip_default_ttl, it can be changed concurrently. Thus, we need to add READ_ONCE() to its readers. Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Kuniyuki Iwashima Signed-off-by: David S. Miller --- drivers/net/ethernet/netronome/nfp/flower/action.c | 2 +- include/net/route.h | 2 +- net/ipv4/ip_sockglue.c | 2 +- net/ipv4/netfilter/nf_reject_ipv4.c | 4 ++-- net/ipv4/proc.c | 2 +- net/netfilter/nf_synproxy_core.c | 2 +- 6 files changed, 7 insertions(+), 7 deletions(-) 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/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/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/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; From 0968d2a441bf6afb551fd99e60fa65ed67068963 Mon Sep 17 00:00:00 2001 From: Kuniyuki Iwashima Date: Wed, 13 Jul 2022 13:51:52 -0700 Subject: [PATCH 02/15] ip: Fix data-races around sysctl_ip_no_pmtu_disc. While reading sysctl_ip_no_pmtu_disc, it can be changed concurrently. Thus, we need to add READ_ONCE() to its readers. Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Kuniyuki Iwashima Signed-off-by: David S. Miller --- net/ipv4/af_inet.c | 2 +- net/ipv4/icmp.c | 2 +- net/ipv6/af_inet6.c | 2 +- net/xfrm/xfrm_state.c | 2 +- 4 files changed, 4 insertions(+), 4 deletions(-) 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/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/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; From 60c158dc7b1f0558f6cadd5b50d0386da0000d50 Mon Sep 17 00:00:00 2001 From: Kuniyuki Iwashima Date: Wed, 13 Jul 2022 13:51:53 -0700 Subject: [PATCH 03/15] ip: Fix data-races around sysctl_ip_fwd_use_pmtu. While reading sysctl_ip_fwd_use_pmtu, it can be changed concurrently. Thus, we need to add READ_ONCE() to its readers. Fixes: f87c10a8aa1e ("ipv4: introduce ip_dst_mtu_maybe_forward and protect forwarding path against pmtu spoofing") Signed-off-by: Kuniyuki Iwashima Signed-off-by: David S. Miller --- include/net/ip.h | 2 +- net/ipv4/route.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/include/net/ip.h b/include/net/ip.h index 26fffda78cca..05fe313f72fa 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -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/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; From 7bf9e18d9a5e99e3c83482973557e9f047b051e7 Mon Sep 17 00:00:00 2001 From: Kuniyuki Iwashima Date: Wed, 13 Jul 2022 13:51:54 -0700 Subject: [PATCH 04/15] ip: Fix data-races around sysctl_ip_fwd_update_priority. While reading sysctl_ip_fwd_update_priority, it can be changed concurrently. Thus, we need to add READ_ONCE() to its readers. Fixes: 432e05d32892 ("net: ipv4: Control SKB reprioritization after forwarding") Signed-off-by: Kuniyuki Iwashima Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c | 3 ++- net/ipv4/ip_forward.c | 2 +- 2 files changed, 3 insertions(+), 2 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/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, From 289d3b21fb0bfc94c4e98f10635bba1824e5f83c Mon Sep 17 00:00:00 2001 From: Kuniyuki Iwashima Date: Wed, 13 Jul 2022 13:51:55 -0700 Subject: [PATCH 05/15] ip: Fix data-races around sysctl_ip_nonlocal_bind. While reading sysctl_ip_nonlocal_bind, it can be changed concurrently. Thus, we need to add READ_ONCE() to its readers. Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Signed-off-by: Kuniyuki Iwashima Signed-off-by: David S. Miller --- include/net/inet_sock.h | 2 +- net/sctp/protocol.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h index daead5fb389a..68d337775564 100644 --- a/include/net/inet_sock.h +++ b/include/net/inet_sock.h @@ -374,7 +374,7 @@ 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/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))) From 0db232765887d9807df8bcb7b6f29b2871539eab Mon Sep 17 00:00:00 2001 From: Kuniyuki Iwashima Date: Wed, 13 Jul 2022 13:51:56 -0700 Subject: [PATCH 06/15] ip: Fix a data-race around sysctl_ip_autobind_reuse. While reading sysctl_ip_autobind_reuse, it can be changed concurrently. Thus, we need to add READ_ONCE() to its reader. Fixes: 4b01a9674231 ("tcp: bind(0) remove the SO_REUSEADDR restriction when ephemeral ports are exhausted.") Signed-off-by: Kuniyuki Iwashima Signed-off-by: David S. Miller --- net/ipv4/inet_connection_sock.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) 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; From 85d0b4dbd74b95cc492b1f4e34497d3f894f5d9a Mon Sep 17 00:00:00 2001 From: Kuniyuki Iwashima Date: Wed, 13 Jul 2022 13:51:57 -0700 Subject: [PATCH 07/15] ip: Fix a data-race around sysctl_fwmark_reflect. While reading sysctl_fwmark_reflect, it can be changed concurrently. Thus, we need to add READ_ONCE() to its reader. Fixes: e110861f8609 ("net: add a sysctl to reflect the fwmark on replies") Signed-off-by: Kuniyuki Iwashima Signed-off-by: David S. Miller --- include/net/ip.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/include/net/ip.h b/include/net/ip.h index 05fe313f72fa..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) { From 1a0008f9df59451d0a17806c1ee1a19857032fa8 Mon Sep 17 00:00:00 2001 From: Kuniyuki Iwashima Date: Wed, 13 Jul 2022 13:51:58 -0700 Subject: [PATCH 08/15] tcp/dccp: Fix a data-race around sysctl_tcp_fwmark_accept. While reading sysctl_tcp_fwmark_accept, it can be changed concurrently. Thus, we need to add READ_ONCE() to its reader. Fixes: 84f39b08d786 ("net: support marking accepting TCP sockets") Signed-off-by: Kuniyuki Iwashima Signed-off-by: David S. Miller --- include/net/inet_sock.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h index 68d337775564..b29108f0973a 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; From 08a75f10679470552a3a443f9aefd1399604d31d Mon Sep 17 00:00:00 2001 From: Kuniyuki Iwashima Date: Wed, 13 Jul 2022 13:51:59 -0700 Subject: [PATCH 09/15] tcp: Fix data-races around sysctl_tcp_l3mdev_accept. While reading sysctl_tcp_l3mdev_accept, it can be changed concurrently. Thus, we need to add READ_ONCE() to its readers. Fixes: 6dd9a14e92e5 ("net: Allow accepted sockets to be bound to l3mdev domain") Signed-off-by: Kuniyuki Iwashima Signed-off-by: David S. Miller --- include/net/inet_hashtables.h | 2 +- include/net/inet_sock.h | 4 ++-- 2 files changed, 3 insertions(+), 3 deletions(-) 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 b29108f0973a..6395f6b9a5d2 100644 --- a/include/net/inet_sock.h +++ b/include/net/inet_sock.h @@ -121,7 +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 @@ -133,7 +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 From f47d00e077e7d61baf69e46dde3210c886360207 Mon Sep 17 00:00:00 2001 From: Kuniyuki Iwashima Date: Wed, 13 Jul 2022 13:52:00 -0700 Subject: [PATCH 10/15] tcp: Fix data-races around sysctl_tcp_mtu_probing. While reading sysctl_tcp_mtu_probing, it can be changed concurrently. Thus, we need to add READ_ONCE() to its readers. Fixes: 5d424d5a674f ("[TCP]: MTU probing") Signed-off-by: Kuniyuki Iwashima Signed-off-by: David S. Miller --- net/ipv4/tcp_output.c | 2 +- net/ipv4/tcp_timer.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 11aa0ab10bba..3fcfc0f1e9f9 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -1762,7 +1762,7 @@ 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); diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index 20cf4a98c69d..98bb00e29e1e 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) { From 88d78bc097cd8ebc6541e93316c9d9bf651b13e8 Mon Sep 17 00:00:00 2001 From: Kuniyuki Iwashima Date: Wed, 13 Jul 2022 13:52:01 -0700 Subject: [PATCH 11/15] tcp: Fix data-races around sysctl_tcp_base_mss. While reading sysctl_tcp_base_mss, it can be changed concurrently. Thus, we need to add READ_ONCE() to its readers. Fixes: 5d424d5a674f ("[TCP]: MTU probing") Signed-off-by: Kuniyuki Iwashima Signed-off-by: David S. Miller --- net/ipv4/tcp_output.c | 2 +- net/ipv4/tcp_timer.c | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 3fcfc0f1e9f9..9450d8469871 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -1765,7 +1765,7 @@ void tcp_mtup_init(struct sock *sk) 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; diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index 98bb00e29e1e..04063c7e33ba 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -171,7 +171,7 @@ 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 = min(READ_ONCE(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); icsk->icsk_mtup.search_low = tcp_mss_to_mtu(sk, mss); From 78eb166cdefcc3221c8c7c1e2d514e91a2eb5014 Mon Sep 17 00:00:00 2001 From: Kuniyuki Iwashima Date: Wed, 13 Jul 2022 13:52:02 -0700 Subject: [PATCH 12/15] tcp: Fix data-races around sysctl_tcp_min_snd_mss. While reading sysctl_tcp_min_snd_mss, it can be changed concurrently. Thus, we need to add READ_ONCE() to its readers. Fixes: 5f3e2bf008c2 ("tcp: add tcp_min_snd_mss sysctl") Signed-off-by: Kuniyuki Iwashima Signed-off-by: David S. Miller --- net/ipv4/tcp_output.c | 3 ++- net/ipv4/tcp_timer.c | 2 +- 2 files changed, 3 insertions(+), 2 deletions(-) diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 9450d8469871..7130b405da21 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; } diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index 04063c7e33ba..39107bb730b0 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -173,7 +173,7 @@ static void tcp_mtu_probing(struct inet_connection_sock *icsk, struct sock *sk) mss = tcp_mtu_to_mss(sk, icsk->icsk_mtup.search_low) >> 1; mss = min(READ_ONCE(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 = 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); From 8e92d4423615a5257d0d871fc067aa561f597deb Mon Sep 17 00:00:00 2001 From: Kuniyuki Iwashima Date: Wed, 13 Jul 2022 13:52:03 -0700 Subject: [PATCH 13/15] tcp: Fix a data-race around sysctl_tcp_mtu_probe_floor. While reading sysctl_tcp_mtu_probe_floor, it can be changed concurrently. Thus, we need to add READ_ONCE() to its reader. Fixes: c04b79b6cfd7 ("tcp: add new tcp_mtu_probe_floor sysctl") Signed-off-by: Kuniyuki Iwashima Signed-off-by: David S. Miller --- net/ipv4/tcp_timer.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index 39107bb730b0..4f3b9ab222b6 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -172,7 +172,7 @@ static void tcp_mtu_probing(struct inet_connection_sock *icsk, struct sock *sk) } else { mss = tcp_mtu_to_mss(sk, icsk->icsk_mtup.search_low) >> 1; mss = min(READ_ONCE(net->ipv4.sysctl_tcp_base_mss), mss); - mss = max(mss, net->ipv4.sysctl_tcp_mtu_probe_floor); + 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); } From 92c0aa4175474483d6cf373314343d4e624e882a Mon Sep 17 00:00:00 2001 From: Kuniyuki Iwashima Date: Wed, 13 Jul 2022 13:52:04 -0700 Subject: [PATCH 14/15] tcp: Fix a data-race around sysctl_tcp_probe_threshold. While reading sysctl_tcp_probe_threshold, it can be changed concurrently. Thus, we need to add READ_ONCE() to its reader. Fixes: 6b58e0a5f32d ("ipv4: Use binary search to choose tcp PMTU probe_size") Signed-off-by: Kuniyuki Iwashima Signed-off-by: David S. Miller --- net/ipv4/tcp_output.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 7130b405da21..aa757c74dad4 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -2367,7 +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. */ From 2a85388f1d94a9f8b5a529118a2c5eaa0520d85c Mon Sep 17 00:00:00 2001 From: Kuniyuki Iwashima Date: Wed, 13 Jul 2022 13:52:05 -0700 Subject: [PATCH 15/15] tcp: Fix a data-race around sysctl_tcp_probe_interval. While reading sysctl_tcp_probe_interval, it can be changed concurrently. Thus, we need to add READ_ONCE() to its reader. Fixes: 05cbc0db03e8 ("ipv4: Create probe timer for tcp PMTU as per RFC4821") Signed-off-by: Kuniyuki Iwashima Signed-off-by: David S. Miller --- net/ipv4/tcp_output.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index aa757c74dad4..02ab3a9c6657 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -2283,7 +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);