summaryrefslogtreecommitdiff
path: root/net/ipv4
diff options
context:
space:
mode:
authorJakub Kicinski <kuba@kernel.org>2022-07-21 13:03:39 -0700
committerJakub Kicinski <kuba@kernel.org>2022-07-21 13:03:39 -0700
commit6e0e846ee2ab01bc44254e6a0a6a6a0db1cba16d (patch)
treee2a39b9ff9fbfa9adbaa004e3b42047664a8e57d /net/ipv4
parent5588d628027092e66195097bdf6835ddf64418b3 (diff)
parent7ca433dc6dedb2ec98dfc943f6db0c9b8996ed11 (diff)
Merge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net
No conflicts. Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Diffstat (limited to 'net/ipv4')
-rw-r--r--net/ipv4/af_inet.c18
-rw-r--r--net/ipv4/ah4.c2
-rw-r--r--net/ipv4/esp4.c2
-rw-r--r--net/ipv4/fib_semantics.c2
-rw-r--r--net/ipv4/icmp.c2
-rw-r--r--net/ipv4/igmp.c49
-rw-r--r--net/ipv4/inet_connection_sock.c5
-rw-r--r--net/ipv4/ip_forward.c2
-rw-r--r--net/ipv4/ip_input.c37
-rw-r--r--net/ipv4/ip_sockglue.c8
-rw-r--r--net/ipv4/netfilter/nf_reject_ipv4.c4
-rw-r--r--net/ipv4/proc.c2
-rw-r--r--net/ipv4/route.c10
-rw-r--r--net/ipv4/syncookies.c9
-rw-r--r--net/ipv4/sysctl_net_ipv4.c65
-rw-r--r--net/ipv4/tcp.c13
-rw-r--r--net/ipv4/tcp_fastopen.c9
-rw-r--r--net/ipv4/tcp_input.c51
-rw-r--r--net/ipv4/tcp_ipv4.c2
-rw-r--r--net/ipv4/tcp_metrics.c3
-rw-r--r--net/ipv4/tcp_minisocks.c4
-rw-r--r--net/ipv4/tcp_output.c29
-rw-r--r--net/ipv4/tcp_recovery.c6
-rw-r--r--net/ipv4/tcp_timer.c30
24 files changed, 169 insertions, 195 deletions
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index fac552e98eb9..3ca0cc467886 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -217,7 +217,7 @@ int inet_listen(struct socket *sock, int backlog)
* because the socket was in TCP_LISTEN state previously but
* was shutdown() rather than close().
*/
- tcp_fastopen = sock_net(sk)->ipv4.sysctl_tcp_fastopen;
+ tcp_fastopen = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_fastopen);
if ((tcp_fastopen & TFO_SERVER_WO_SOCKOPT1) &&
(tcp_fastopen & TFO_SERVER_ENABLE) &&
!inet_csk(sk)->icsk_accept_queue.fastopenq.max_qlen) {
@@ -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;
@@ -1711,24 +1711,14 @@ static const struct net_protocol igmp_protocol = {
};
#endif
-/* thinking of making this const? Don't.
- * early_demux can change based on sysctl.
- */
-static struct net_protocol tcp_protocol = {
- .early_demux = tcp_v4_early_demux,
- .early_demux_handler = tcp_v4_early_demux,
+static const struct net_protocol tcp_protocol = {
.handler = tcp_v4_rcv,
.err_handler = tcp_v4_err,
.no_policy = 1,
.icmp_strict_tag_validation = 1,
};
-/* thinking of making this const? Don't.
- * early_demux can change based on sysctl.
- */
-static struct net_protocol udp_protocol = {
- .early_demux = udp_v4_early_demux,
- .early_demux_handler = udp_v4_early_demux,
+static const struct net_protocol udp_protocol = {
.handler = udp_rcv,
.err_handler = udp_err,
.no_policy = 1,
diff --git a/net/ipv4/ah4.c b/net/ipv4/ah4.c
index 6eea1e9e998d..f8ad04470d3a 100644
--- a/net/ipv4/ah4.c
+++ b/net/ipv4/ah4.c
@@ -507,7 +507,7 @@ static int ah_init_state(struct xfrm_state *x)
if (aalg_desc->uinfo.auth.icv_fullbits/8 !=
crypto_ahash_digestsize(ahash)) {
- pr_info("%s: %s digestsize %u != %hu\n",
+ pr_info("%s: %s digestsize %u != %u\n",
__func__, x->aalg->alg_name,
crypto_ahash_digestsize(ahash),
aalg_desc->uinfo.auth.icv_fullbits / 8);
diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c
index 7eae8d686e20..5c03eba787e5 100644
--- a/net/ipv4/esp4.c
+++ b/net/ipv4/esp4.c
@@ -1106,7 +1106,7 @@ static int esp_init_authenc(struct xfrm_state *x)
err = -EINVAL;
if (aalg_desc->uinfo.auth.icv_fullbits / 8 !=
crypto_aead_authsize(aead)) {
- pr_info("ESP: %s digestsize %u != %hu\n",
+ pr_info("ESP: %s digestsize %u != %u\n",
x->aalg->alg_name,
crypto_aead_authsize(aead),
aalg_desc->uinfo.auth.icv_fullbits / 8);
diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index 14f037e8ac55..2dc97583d279 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -2217,7 +2217,7 @@ void fib_select_multipath(struct fib_result *res, int hash)
}
change_nexthops(fi) {
- if (net->ipv4.sysctl_fib_multipath_use_neigh) {
+ if (READ_ONCE(net->ipv4.sysctl_fib_multipath_use_neigh)) {
if (!fib_good_nh(nexthop_nh))
continue;
if (!first) {
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/igmp.c b/net/ipv4/igmp.c
index b65d074d9620..e3ab0cb61624 100644
--- a/net/ipv4/igmp.c
+++ b/net/ipv4/igmp.c
@@ -467,7 +467,8 @@ static struct sk_buff *add_grec(struct sk_buff *skb, struct ip_mc_list *pmc,
if (pmc->multiaddr == IGMP_ALL_HOSTS)
return skb;
- if (ipv4_is_local_multicast(pmc->multiaddr) && !net->ipv4.sysctl_igmp_llm_reports)
+ if (ipv4_is_local_multicast(pmc->multiaddr) &&
+ !READ_ONCE(net->ipv4.sysctl_igmp_llm_reports))
return skb;
mtu = READ_ONCE(dev->mtu);
@@ -593,7 +594,7 @@ static int igmpv3_send_report(struct in_device *in_dev, struct ip_mc_list *pmc)
if (pmc->multiaddr == IGMP_ALL_HOSTS)
continue;
if (ipv4_is_local_multicast(pmc->multiaddr) &&
- !net->ipv4.sysctl_igmp_llm_reports)
+ !READ_ONCE(net->ipv4.sysctl_igmp_llm_reports))
continue;
spin_lock_bh(&pmc->lock);
if (pmc->sfcount[MCAST_EXCLUDE])
@@ -736,7 +737,8 @@ static int igmp_send_report(struct in_device *in_dev, struct ip_mc_list *pmc,
if (type == IGMPV3_HOST_MEMBERSHIP_REPORT)
return igmpv3_send_report(in_dev, pmc);
- if (ipv4_is_local_multicast(group) && !net->ipv4.sysctl_igmp_llm_reports)
+ if (ipv4_is_local_multicast(group) &&
+ !READ_ONCE(net->ipv4.sysctl_igmp_llm_reports))
return 0;
if (type == IGMP_HOST_LEAVE_MESSAGE)
@@ -825,7 +827,7 @@ static void igmp_ifc_event(struct in_device *in_dev)
struct net *net = dev_net(in_dev->dev);
if (IGMP_V1_SEEN(in_dev) || IGMP_V2_SEEN(in_dev))
return;
- WRITE_ONCE(in_dev->mr_ifc_count, in_dev->mr_qrv ?: net->ipv4.sysctl_igmp_qrv);
+ WRITE_ONCE(in_dev->mr_ifc_count, in_dev->mr_qrv ?: READ_ONCE(net->ipv4.sysctl_igmp_qrv));
igmp_ifc_start_timer(in_dev, 1);
}
@@ -920,7 +922,8 @@ static bool igmp_heard_report(struct in_device *in_dev, __be32 group)
if (group == IGMP_ALL_HOSTS)
return false;
- if (ipv4_is_local_multicast(group) && !net->ipv4.sysctl_igmp_llm_reports)
+ if (ipv4_is_local_multicast(group) &&
+ !READ_ONCE(net->ipv4.sysctl_igmp_llm_reports))
return false;
rcu_read_lock();
@@ -1006,7 +1009,7 @@ static bool igmp_heard_query(struct in_device *in_dev, struct sk_buff *skb,
* received value was zero, use the default or statically
* configured value.
*/
- in_dev->mr_qrv = ih3->qrv ?: net->ipv4.sysctl_igmp_qrv;
+ in_dev->mr_qrv = ih3->qrv ?: READ_ONCE(net->ipv4.sysctl_igmp_qrv);
in_dev->mr_qi = IGMPV3_QQIC(ih3->qqic)*HZ ?: IGMP_QUERY_INTERVAL;
/* RFC3376, 8.3. Query Response Interval:
@@ -1045,7 +1048,7 @@ static bool igmp_heard_query(struct in_device *in_dev, struct sk_buff *skb,
if (im->multiaddr == IGMP_ALL_HOSTS)
continue;
if (ipv4_is_local_multicast(im->multiaddr) &&
- !net->ipv4.sysctl_igmp_llm_reports)
+ !READ_ONCE(net->ipv4.sysctl_igmp_llm_reports))
continue;
spin_lock_bh(&im->lock);
if (im->tm_running)
@@ -1186,7 +1189,7 @@ static void igmpv3_add_delrec(struct in_device *in_dev, struct ip_mc_list *im,
pmc->interface = im->interface;
in_dev_hold(in_dev);
pmc->multiaddr = im->multiaddr;
- pmc->crcount = in_dev->mr_qrv ?: net->ipv4.sysctl_igmp_qrv;
+ pmc->crcount = in_dev->mr_qrv ?: READ_ONCE(net->ipv4.sysctl_igmp_qrv);
pmc->sfmode = im->sfmode;
if (pmc->sfmode == MCAST_INCLUDE) {
struct ip_sf_list *psf;
@@ -1237,9 +1240,11 @@ static void igmpv3_del_delrec(struct in_device *in_dev, struct ip_mc_list *im)
swap(im->tomb, pmc->tomb);
swap(im->sources, pmc->sources);
for (psf = im->sources; psf; psf = psf->sf_next)
- psf->sf_crcount = in_dev->mr_qrv ?: net->ipv4.sysctl_igmp_qrv;
+ psf->sf_crcount = in_dev->mr_qrv ?:
+ READ_ONCE(net->ipv4.sysctl_igmp_qrv);
} else {
- im->crcount = in_dev->mr_qrv ?: net->ipv4.sysctl_igmp_qrv;
+ im->crcount = in_dev->mr_qrv ?:
+ READ_ONCE(net->ipv4.sysctl_igmp_qrv);
}
in_dev_put(pmc->interface);
kfree_pmc(pmc);
@@ -1296,7 +1301,8 @@ static void __igmp_group_dropped(struct ip_mc_list *im, gfp_t gfp)
#ifdef CONFIG_IP_MULTICAST
if (im->multiaddr == IGMP_ALL_HOSTS)
return;
- if (ipv4_is_local_multicast(im->multiaddr) && !net->ipv4.sysctl_igmp_llm_reports)
+ if (ipv4_is_local_multicast(im->multiaddr) &&
+ !READ_ONCE(net->ipv4.sysctl_igmp_llm_reports))
return;
reporter = im->reporter;
@@ -1338,13 +1344,14 @@ static void igmp_group_added(struct ip_mc_list *im)
#ifdef CONFIG_IP_MULTICAST
if (im->multiaddr == IGMP_ALL_HOSTS)
return;
- if (ipv4_is_local_multicast(im->multiaddr) && !net->ipv4.sysctl_igmp_llm_reports)
+ if (ipv4_is_local_multicast(im->multiaddr) &&
+ !READ_ONCE(net->ipv4.sysctl_igmp_llm_reports))
return;
if (in_dev->dead)
return;
- im->unsolicit_count = net->ipv4.sysctl_igmp_qrv;
+ im->unsolicit_count = READ_ONCE(net->ipv4.sysctl_igmp_qrv);
if (IGMP_V1_SEEN(in_dev) || IGMP_V2_SEEN(in_dev)) {
spin_lock_bh(&im->lock);
igmp_start_timer(im, IGMP_INITIAL_REPORT_DELAY);
@@ -1358,7 +1365,7 @@ static void igmp_group_added(struct ip_mc_list *im)
* IN() to IN(A).
*/
if (im->sfmode == MCAST_EXCLUDE)
- im->crcount = in_dev->mr_qrv ?: net->ipv4.sysctl_igmp_qrv;
+ im->crcount = in_dev->mr_qrv ?: READ_ONCE(net->ipv4.sysctl_igmp_qrv);
igmp_ifc_event(in_dev);
#endif
@@ -1642,7 +1649,7 @@ static void ip_mc_rejoin_groups(struct in_device *in_dev)
if (im->multiaddr == IGMP_ALL_HOSTS)
continue;
if (ipv4_is_local_multicast(im->multiaddr) &&
- !net->ipv4.sysctl_igmp_llm_reports)
+ !READ_ONCE(net->ipv4.sysctl_igmp_llm_reports))
continue;
/* a failover is happening and switches
@@ -1749,7 +1756,7 @@ static void ip_mc_reset(struct in_device *in_dev)
in_dev->mr_qi = IGMP_QUERY_INTERVAL;
in_dev->mr_qri = IGMP_QUERY_RESPONSE_INTERVAL;
- in_dev->mr_qrv = net->ipv4.sysctl_igmp_qrv;
+ in_dev->mr_qrv = READ_ONCE(net->ipv4.sysctl_igmp_qrv);
}
#else
static void ip_mc_reset(struct in_device *in_dev)
@@ -1883,7 +1890,7 @@ static int ip_mc_del1_src(struct ip_mc_list *pmc, int sfmode,
#ifdef CONFIG_IP_MULTICAST
if (psf->sf_oldin &&
!IGMP_V1_SEEN(in_dev) && !IGMP_V2_SEEN(in_dev)) {
- psf->sf_crcount = in_dev->mr_qrv ?: net->ipv4.sysctl_igmp_qrv;
+ psf->sf_crcount = in_dev->mr_qrv ?: READ_ONCE(net->ipv4.sysctl_igmp_qrv);
psf->sf_next = pmc->tomb;
pmc->tomb = psf;
rv = 1;
@@ -1947,7 +1954,7 @@ static int ip_mc_del_src(struct in_device *in_dev, __be32 *pmca, int sfmode,
/* filter mode change */
pmc->sfmode = MCAST_INCLUDE;
#ifdef CONFIG_IP_MULTICAST
- pmc->crcount = in_dev->mr_qrv ?: net->ipv4.sysctl_igmp_qrv;
+ pmc->crcount = in_dev->mr_qrv ?: READ_ONCE(net->ipv4.sysctl_igmp_qrv);
WRITE_ONCE(in_dev->mr_ifc_count, pmc->crcount);
for (psf = pmc->sources; psf; psf = psf->sf_next)
psf->sf_crcount = 0;
@@ -2126,7 +2133,7 @@ static int ip_mc_add_src(struct in_device *in_dev, __be32 *pmca, int sfmode,
#ifdef CONFIG_IP_MULTICAST
/* else no filters; keep old mode for reports */
- pmc->crcount = in_dev->mr_qrv ?: net->ipv4.sysctl_igmp_qrv;
+ pmc->crcount = in_dev->mr_qrv ?: READ_ONCE(net->ipv4.sysctl_igmp_qrv);
WRITE_ONCE(in_dev->mr_ifc_count, pmc->crcount);
for (psf = pmc->sources; psf; psf = psf->sf_next)
psf->sf_crcount = 0;
@@ -2192,7 +2199,7 @@ static int __ip_mc_join_group(struct sock *sk, struct ip_mreqn *imr,
count++;
}
err = -ENOBUFS;
- if (count >= net->ipv4.sysctl_igmp_max_memberships)
+ if (count >= READ_ONCE(net->ipv4.sysctl_igmp_max_memberships))
goto done;
iml = sock_kmalloc(sk, sizeof(*iml), GFP_KERNEL);
if (!iml)
@@ -2379,7 +2386,7 @@ int ip_mc_source(int add, int omode, struct sock *sk, struct
}
/* else, add a new source to the filter */
- if (psl && psl->sl_count >= net->ipv4.sysctl_igmp_max_msf) {
+ if (psl && psl->sl_count >= READ_ONCE(net->ipv4.sysctl_igmp_max_msf)) {
err = -ENOBUFS;
goto done;
}
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index 53f5f956d948..eb31c7158b39 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;
@@ -833,7 +833,8 @@ static void reqsk_timer_handler(struct timer_list *t)
icsk = inet_csk(sk_listener);
net = sock_net(sk_listener);
- max_syn_ack_retries = icsk->icsk_syn_retries ? : net->ipv4.sysctl_tcp_synack_retries;
+ max_syn_ack_retries = icsk->icsk_syn_retries ? :
+ READ_ONCE(net->ipv4.sysctl_tcp_synack_retries);
/* Normally all the openreqs are young and become mature
* (i.e. converted to established socket) for first timeout.
* If synack was not acknowledged for 1 second, it means
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_input.c b/net/ipv4/ip_input.c
index b1165f717cd1..1b512390b3cf 100644
--- a/net/ipv4/ip_input.c
+++ b/net/ipv4/ip_input.c
@@ -312,14 +312,13 @@ static bool ip_can_use_hint(const struct sk_buff *skb, const struct iphdr *iph,
ip_hdr(hint)->tos == iph->tos;
}
-INDIRECT_CALLABLE_DECLARE(int udp_v4_early_demux(struct sk_buff *));
-INDIRECT_CALLABLE_DECLARE(int tcp_v4_early_demux(struct sk_buff *));
+int tcp_v4_early_demux(struct sk_buff *skb);
+int udp_v4_early_demux(struct sk_buff *skb);
static int ip_rcv_finish_core(struct net *net, struct sock *sk,
struct sk_buff *skb, struct net_device *dev,
const struct sk_buff *hint)
{
const struct iphdr *iph = ip_hdr(skb);
- int (*edemux)(struct sk_buff *skb);
int err, drop_reason;
struct rtable *rt;
@@ -332,21 +331,29 @@ static int ip_rcv_finish_core(struct net *net, struct sock *sk,
goto drop_error;
}
- if (net->ipv4.sysctl_ip_early_demux &&
+ if (READ_ONCE(net->ipv4.sysctl_ip_early_demux) &&
!skb_dst(skb) &&
!skb->sk &&
!ip_is_fragment(iph)) {
- const struct net_protocol *ipprot;
- int protocol = iph->protocol;
-
- ipprot = rcu_dereference(inet_protos[protocol]);
- if (ipprot && (edemux = READ_ONCE(ipprot->early_demux))) {
- err = INDIRECT_CALL_2(edemux, tcp_v4_early_demux,
- udp_v4_early_demux, skb);
- if (unlikely(err))
- goto drop_error;
- /* must reload iph, skb->head might have changed */
- iph = ip_hdr(skb);
+ switch (iph->protocol) {
+ case IPPROTO_TCP:
+ if (READ_ONCE(net->ipv4.sysctl_tcp_early_demux)) {
+ tcp_v4_early_demux(skb);
+
+ /* must reload iph, skb->head might have changed */
+ iph = ip_hdr(skb);
+ }
+ break;
+ case IPPROTO_UDP:
+ if (READ_ONCE(net->ipv4.sysctl_udp_early_demux)) {
+ err = udp_v4_early_demux(skb);
+ if (unlikely(err))
+ goto drop_error;
+
+ /* must reload iph, skb->head might have changed */
+ iph = ip_hdr(skb);
+ }
+ break;
}
}
diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c
index 445a9ecaefa1..a8a323ecbb54 100644
--- a/net/ipv4/ip_sockglue.c
+++ b/net/ipv4/ip_sockglue.c
@@ -782,7 +782,7 @@ static int ip_set_mcast_msfilter(struct sock *sk, sockptr_t optval, int optlen)
/* numsrc >= (4G-140)/128 overflow in 32 bits */
err = -ENOBUFS;
if (gsf->gf_numsrc >= 0x1ffffff ||
- gsf->gf_numsrc > sock_net(sk)->ipv4.sysctl_igmp_max_msf)
+ gsf->gf_numsrc > READ_ONCE(sock_net(sk)->ipv4.sysctl_igmp_max_msf))
goto out_free_gsf;
err = -EINVAL;
@@ -832,7 +832,7 @@ static int compat_ip_set_mcast_msfilter(struct sock *sk, sockptr_t optval,
/* numsrc >= (4G-140)/128 overflow in 32 bits */
err = -ENOBUFS;
- if (n > sock_net(sk)->ipv4.sysctl_igmp_max_msf)
+ if (n > READ_ONCE(sock_net(sk)->ipv4.sysctl_igmp_max_msf))
goto out_free_gsf;
err = set_mcast_msfilter(sk, gf32->gf_interface, n, gf32->gf_fmode,
&gf32->gf_group, gf32->gf_slist_flex);
@@ -1244,7 +1244,7 @@ static int do_ip_setsockopt(struct sock *sk, int level, int optname,
}
/* numsrc >= (1G-4) overflow in 32 bits */
if (msf->imsf_numsrc >= 0x3ffffffcU ||
- msf->imsf_numsrc > net->ipv4.sysctl_igmp_max_msf) {
+ msf->imsf_numsrc > READ_ONCE(net->ipv4.sysctl_igmp_max_msf)) {
kfree(msf);
err = -ENOBUFS;
break;
@@ -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 8f4a8f66d604..bce603f399bd 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;
@@ -1928,7 +1928,7 @@ static u32 fib_multipath_custom_hash_outer(const struct net *net,
const struct sk_buff *skb,
bool *p_has_inner)
{
- u32 hash_fields = net->ipv4.sysctl_fib_multipath_hash_fields;
+ u32 hash_fields = READ_ONCE(net->ipv4.sysctl_fib_multipath_hash_fields);
struct flow_keys keys, hash_keys;
if (!(hash_fields & FIB_MULTIPATH_HASH_FIELD_OUTER_MASK))
@@ -1957,7 +1957,7 @@ static u32 fib_multipath_custom_hash_inner(const struct net *net,
const struct sk_buff *skb,
bool has_inner)
{
- u32 hash_fields = net->ipv4.sysctl_fib_multipath_hash_fields;
+ u32 hash_fields = READ_ONCE(net->ipv4.sysctl_fib_multipath_hash_fields);
struct flow_keys keys, hash_keys;
/* We assume the packet carries an encapsulation, but if none was
@@ -2017,7 +2017,7 @@ static u32 fib_multipath_custom_hash_skb(const struct net *net,
static u32 fib_multipath_custom_hash_fl4(const struct net *net,
const struct flowi4 *fl4)
{
- u32 hash_fields = net->ipv4.sysctl_fib_multipath_hash_fields;
+ u32 hash_fields = READ_ONCE(net->ipv4.sysctl_fib_multipath_hash_fields);
struct flow_keys hash_keys;
if (!(hash_fields & FIB_MULTIPATH_HASH_FIELD_OUTER_MASK))
@@ -2047,7 +2047,7 @@ int fib_multipath_hash(const struct net *net, const struct flowi4 *fl4,
struct flow_keys hash_keys;
u32 mhash = 0;
- switch (net->ipv4.sysctl_fib_multipath_hash_policy) {
+ switch (READ_ONCE(net->ipv4.sysctl_fib_multipath_hash_policy)) {
case 0:
memset(&hash_keys, 0, sizeof(hash_keys));
hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS;
diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c
index b387c4835155..942d2dfa1115 100644
--- a/net/ipv4/syncookies.c
+++ b/net/ipv4/syncookies.c
@@ -247,12 +247,12 @@ bool cookie_timestamp_decode(const struct net *net,
return true;
}
- if (!net->ipv4.sysctl_tcp_timestamps)
+ if (!READ_ONCE(net->ipv4.sysctl_tcp_timestamps))
return false;
tcp_opt->sack_ok = (options & TS_OPT_SACK) ? TCP_SACK_SEEN : 0;
- if (tcp_opt->sack_ok && !net->ipv4.sysctl_tcp_sack)
+ if (tcp_opt->sack_ok && !READ_ONCE(net->ipv4.sysctl_tcp_sack))
return false;
if ((options & TS_OPT_WSCALE_MASK) == TS_OPT_WSCALE_MASK)
@@ -261,7 +261,7 @@ bool cookie_timestamp_decode(const struct net *net,
tcp_opt->wscale_ok = 1;
tcp_opt->snd_wscale = options & TS_OPT_WSCALE_MASK;
- return net->ipv4.sysctl_tcp_window_scaling != 0;
+ return READ_ONCE(net->ipv4.sysctl_tcp_window_scaling) != 0;
}
EXPORT_SYMBOL(cookie_timestamp_decode);
@@ -340,7 +340,8 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb)
struct flowi4 fl4;
u32 tsoff = 0;
- if (!sock_net(sk)->ipv4.sysctl_tcp_syncookies || !th->ack || th->rst)
+ if (!READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_syncookies) ||
+ !th->ack || th->rst)
goto out;
if (tcp_synq_no_recent_overflow(sk))
diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index 108fd86f2718..5490c285668b 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -84,7 +84,7 @@ static int ipv4_local_port_range(struct ctl_table *table, int write,
* port limit.
*/
if ((range[1] < range[0]) ||
- (range[0] < net->ipv4.sysctl_ip_prot_sock))
+ (range[0] < READ_ONCE(net->ipv4.sysctl_ip_prot_sock)))
ret = -EINVAL;
else
set_local_port_range(net, range);
@@ -110,7 +110,7 @@ static int ipv4_privileged_ports(struct ctl_table *table, int write,
.extra2 = &ip_privileged_port_max,
};
- pports = net->ipv4.sysctl_ip_prot_sock;
+ pports = READ_ONCE(net->ipv4.sysctl_ip_prot_sock);
ret = proc_dointvec_minmax(&tmp, write, buffer, lenp, ppos);
@@ -122,7 +122,7 @@ static int ipv4_privileged_ports(struct ctl_table *table, int write,
if (range[0] < pports)
ret = -EINVAL;
else
- net->ipv4.sysctl_ip_prot_sock = pports;
+ WRITE_ONCE(net->ipv4.sysctl_ip_prot_sock, pports);
}
return ret;
@@ -350,61 +350,6 @@ bad_key:
return ret;
}
-static void proc_configure_early_demux(int enabled, int protocol)
-{
- struct net_protocol *ipprot;
-#if IS_ENABLED(CONFIG_IPV6)
- struct inet6_protocol *ip6prot;
-#endif
-
- rcu_read_lock();
-
- ipprot = rcu_dereference(inet_protos[protocol]);
- if (ipprot)
- ipprot->early_demux = enabled ? ipprot->early_demux_handler :
- NULL;
-
-#if IS_ENABLED(CONFIG_IPV6)
- ip6prot = rcu_dereference(inet6_protos[protocol]);
- if (ip6prot)
- ip6prot->early_demux = enabled ? ip6prot->early_demux_handler :
- NULL;
-#endif
- rcu_read_unlock();
-}
-
-static int proc_tcp_early_demux(struct ctl_table *table, int write,
- void *buffer, size_t *lenp, loff_t *ppos)
-{
- int ret = 0;
-
- ret = proc_dou8vec_minmax(table, write, buffer, lenp, ppos);
-
- if (write && !ret) {
- int enabled = init_net.ipv4.sysctl_tcp_early_demux;
-
- proc_configure_early_demux(enabled, IPPROTO_TCP);
- }
-
- return ret;
-}
-
-static int proc_udp_early_demux(struct ctl_table *table, int write,
- void *buffer, size_t *lenp, loff_t *ppos)
-{
- int ret = 0;
-
- ret = proc_dou8vec_minmax(table, write, buffer, lenp, ppos);
-
- if (write && !ret) {
- int enabled = init_net.ipv4.sysctl_udp_early_demux;
-
- proc_configure_early_demux(enabled, IPPROTO_UDP);
- }
-
- return ret;
-}
-
static int proc_tfo_blackhole_detect_timeout(struct ctl_table *table,
int write, void *buffer,
size_t *lenp, loff_t *ppos)
@@ -707,14 +652,14 @@ static struct ctl_table ipv4_net_table[] = {
.data = &init_net.ipv4.sysctl_udp_early_demux,
.maxlen = sizeof(u8),
.mode = 0644,
- .proc_handler = proc_udp_early_demux
+ .proc_handler = proc_dou8vec_minmax,
},
{
.procname = "tcp_early_demux",
.data = &init_net.ipv4.sysctl_tcp_early_demux,
.maxlen = sizeof(u8),
.mode = 0644,
- .proc_handler = proc_tcp_early_demux
+ .proc_handler = proc_dou8vec_minmax,
},
{
.procname = "nexthop_compat_mode",
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index ddf63a0ad643..ba2bdc811374 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -443,7 +443,7 @@ void tcp_init_sock(struct sock *sk)
tp->snd_cwnd_clamp = ~0;
tp->mss_cache = TCP_MSS_DEFAULT;
- tp->reordering = sock_net(sk)->ipv4.sysctl_tcp_reordering;
+ tp->reordering = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_reordering);
tcp_assign_congestion_control(sk);
tp->tsoffset = 0;
@@ -1171,7 +1171,8 @@ static int tcp_sendmsg_fastopen(struct sock *sk, struct msghdr *msg,
struct sockaddr *uaddr = msg->msg_name;
int err, flags;
- if (!(sock_net(sk)->ipv4.sysctl_tcp_fastopen & TFO_CLIENT_ENABLE) ||
+ if (!(READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_fastopen) &
+ TFO_CLIENT_ENABLE) ||
(uaddr && msg->msg_namelen >= sizeof(uaddr->sa_family) &&
uaddr->sa_family == AF_UNSPEC))
return -EOPNOTSUPP;
@@ -3691,7 +3692,8 @@ static int do_tcp_setsockopt(struct sock *sk, int level, int optname,
case TCP_FASTOPEN_CONNECT:
if (val > 1 || val < 0) {
err = -EINVAL;
- } else if (net->ipv4.sysctl_tcp_fastopen & TFO_CLIENT_ENABLE) {
+ } else if (READ_ONCE(net->ipv4.sysctl_tcp_fastopen) &
+ TFO_CLIENT_ENABLE) {
if (sk->sk_state == TCP_CLOSE)
tp->fastopen_connect = val;
else
@@ -4041,12 +4043,13 @@ static int do_tcp_getsockopt(struct sock *sk, int level,
val = keepalive_probes(tp);
break;
case TCP_SYNCNT:
- val = icsk->icsk_syn_retries ? : net->ipv4.sysctl_tcp_syn_retries;
+ val = icsk->icsk_syn_retries ? :
+ READ_ONCE(net->ipv4.sysctl_tcp_syn_retries);
break;
case TCP_LINGER2:
val = tp->linger2;
if (val >= 0)
- val = (val ? : net->ipv4.sysctl_tcp_fin_timeout) / HZ;
+ val = (val ? : READ_ONCE(net->ipv4.sysctl_tcp_fin_timeout)) / HZ;
break;
case TCP_DEFER_ACCEPT:
val = retrans_to_secs(icsk->icsk_accept_queue.rskq_defer_accept,
diff --git a/net/ipv4/tcp_fastopen.c b/net/ipv4/tcp_fastopen.c
index fdbcf2a6d08e..825b216d11f5 100644
--- a/net/ipv4/tcp_fastopen.c
+++ b/net/ipv4/tcp_fastopen.c
@@ -332,7 +332,7 @@ static bool tcp_fastopen_no_cookie(const struct sock *sk,
const struct dst_entry *dst,
int flag)
{
- return (sock_net(sk)->ipv4.sysctl_tcp_fastopen & flag) ||
+ return (READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_fastopen) & flag) ||
tcp_sk(sk)->fastopen_no_cookie ||
(dst && dst_metric(dst, RTAX_FASTOPEN_NO_COOKIE));
}
@@ -347,7 +347,7 @@ struct sock *tcp_try_fastopen(struct sock *sk, struct sk_buff *skb,
const struct dst_entry *dst)
{
bool syn_data = TCP_SKB_CB(skb)->end_seq != TCP_SKB_CB(skb)->seq + 1;
- int tcp_fastopen = sock_net(sk)->ipv4.sysctl_tcp_fastopen;
+ int tcp_fastopen = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_fastopen);
struct tcp_fastopen_cookie valid_foc = { .len = -1 };
struct sock *child;
int ret = 0;
@@ -489,7 +489,7 @@ void tcp_fastopen_active_disable(struct sock *sk)
{
struct net *net = sock_net(sk);
- if (!sock_net(sk)->ipv4.sysctl_tcp_fastopen_blackhole_timeout)
+ if (!READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_fastopen_blackhole_timeout))
return;
/* Paired with READ_ONCE() in tcp_fastopen_active_should_disable() */
@@ -510,7 +510,8 @@ void tcp_fastopen_active_disable(struct sock *sk)
*/
bool tcp_fastopen_active_should_disable(struct sock *sk)
{
- unsigned int tfo_bh_timeout = sock_net(sk)->ipv4.sysctl_tcp_fastopen_blackhole_timeout;
+ unsigned int tfo_bh_timeout =
+ READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_fastopen_blackhole_timeout);
unsigned long timeout;
int tfo_da_times;
int multiplier;
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index acee998c14b2..ae73b34d32e9 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -1050,7 +1050,7 @@ static void tcp_check_sack_reordering(struct sock *sk, const u32 low_seq,
tp->undo_marker ? tp->undo_retrans : 0);
#endif
tp->reordering = min_t(u32, (metric + mss - 1) / mss,
- sock_net(sk)->ipv4.sysctl_tcp_max_reordering);
+ READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_max_reordering));
}
/* This exciting event is worth to be remembered. 8) */
@@ -2029,7 +2029,7 @@ static void tcp_check_reno_reordering(struct sock *sk, const int addend)
return;
tp->reordering = min_t(u32, tp->packets_out + addend,
- sock_net(sk)->ipv4.sysctl_tcp_max_reordering);
+ READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_max_reordering));
tp->reord_seen++;
NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPRENOREORDER);
}
@@ -2094,7 +2094,8 @@ static inline void tcp_init_undo(struct tcp_sock *tp)
static bool tcp_is_rack(const struct sock *sk)
{
- return sock_net(sk)->ipv4.sysctl_tcp_recovery & TCP_RACK_LOSS_DETECTION;
+ return READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_recovery) &
+ TCP_RACK_LOSS_DETECTION;
}
/* If we detect SACK reneging, forget all SACK information
@@ -2138,6 +2139,7 @@ void tcp_enter_loss(struct sock *sk)
struct tcp_sock *tp = tcp_sk(sk);
struct net *net = sock_net(sk);
bool new_recovery = icsk->icsk_ca_state < TCP_CA_Recovery;
+ u8 reordering;
tcp_timeout_mark_lost(sk);
@@ -2158,10 +2160,12 @@ void tcp_enter_loss(struct sock *sk)
/* Timeout in disordered state after receiving substantial DUPACKs
* suggests that the degree of reordering is over-estimated.
*/
+ reordering = READ_ONCE(net->ipv4.sysctl_tcp_reordering);
if (icsk->icsk_ca_state <= TCP_CA_Disorder &&
- tp->sacked_out >= net->ipv4.sysctl_tcp_reordering)
+ tp->sacked_out >= reordering)
tp->reordering = min_t(unsigned int, tp->reordering,
- net->ipv4.sysctl_tcp_reordering);
+ reordering);
+
tcp_set_ca_state(sk, TCP_CA_Loss);
tp->high_seq = tp->snd_nxt;
tcp_ecn_queue_cwr(tp);
@@ -3463,7 +3467,8 @@ static inline bool tcp_may_raise_cwnd(const struct sock *sk, const int flag)
* new SACK or ECE mark may first advance cwnd here and later reduce
* cwnd in tcp_fastretrans_alert() based on more states.
*/
- if (tcp_sk(sk)->reordering > sock_net(sk)->ipv4.sysctl_tcp_reordering)
+ if (tcp_sk(sk)->reordering >
+ READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_reordering))
return flag & FLAG_FORWARD_PROGRESS;
return flag & FLAG_DATA_ACKED;
@@ -4056,7 +4061,7 @@ void tcp_parse_options(const struct net *net,
break;
case TCPOPT_WINDOW:
if (opsize == TCPOLEN_WINDOW && th->syn &&
- !estab && net->ipv4.sysctl_tcp_window_scaling) {
+ !estab && READ_ONCE(net->ipv4.sysctl_tcp_window_scaling)) {
__u8 snd_wscale = *(__u8 *)ptr;
opt_rx->wscale_ok = 1;
if (snd_wscale > TCP_MAX_WSCALE) {
@@ -4072,7 +4077,7 @@ void tcp_parse_options(const struct net *net,
case TCPOPT_TIMESTAMP:
if ((opsize == TCPOLEN_TIMESTAMP) &&
((estab && opt_rx->tstamp_ok) ||
- (!estab && net->ipv4.sysctl_tcp_timestamps))) {
+ (!estab && READ_ONCE(net->ipv4.sysctl_tcp_timestamps)))) {
opt_rx->saw_tstamp = 1;
opt_rx->rcv_tsval = get_unaligned_be32(ptr);
opt_rx->rcv_tsecr = get_unaligned_be32(ptr + 4);
@@ -4080,7 +4085,7 @@ void tcp_parse_options(const struct net *net,
break;
case TCPOPT_SACK_PERM:
if (opsize == TCPOLEN_SACK_PERM && th->syn &&
- !estab && net->ipv4.sysctl_tcp_sack) {
+ !estab && READ_ONCE(net->ipv4.sysctl_tcp_sack)) {
opt_rx->sack_ok = TCP_SACK_SEEN;
tcp_sack_reset(opt_rx);
}
@@ -5564,7 +5569,7 @@ static void tcp_check_urg(struct sock *sk, const struct tcphdr *th)
struct tcp_sock *tp = tcp_sk(sk);
u32 ptr = ntohs(th->urg_ptr);
- if (ptr && !sock_net(sk)->ipv4.sysctl_tcp_stdurg)
+ if (ptr && !READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_stdurg))
ptr--;
ptr += ntohl(th->seq);
@@ -6794,11 +6799,14 @@ static bool tcp_syn_flood_action(const struct sock *sk, const char *proto)
{
struct request_sock_queue *queue = &inet_csk(sk)->icsk_accept_queue;
const char *msg = "Dropping request";
- bool want_cookie = false;
struct net *net = sock_net(sk);
+ bool want_cookie = false;
+ u8 syncookies;
+
+ syncookies = READ_ONCE(net->ipv4.sysctl_tcp_syncookies);
#ifdef CONFIG_SYN_COOKIES
- if (net->ipv4.sysctl_tcp_syncookies) {
+ if (syncookies) {
msg = "Sending cookies";
want_cookie = true;
__NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPREQQFULLDOCOOKIES);
@@ -6806,8 +6814,7 @@ static bool tcp_syn_flood_action(const struct sock *sk, const char *proto)
#endif
__NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPREQQFULLDROP);
- if (!queue->synflood_warned &&
- net->ipv4.sysctl_tcp_syncookies != 2 &&
+ if (!queue->synflood_warned && syncookies != 2 &&
xchg(&queue->synflood_warned, 1) == 0)
net_info_ratelimited("%s: Possible SYN flooding on port %d. %s. Check SNMP counters.\n",
proto, sk->sk_num, msg);
@@ -6856,7 +6863,7 @@ u16 tcp_get_syncookie_mss(struct request_sock_ops *rsk_ops,
struct tcp_sock *tp = tcp_sk(sk);
u16 mss;
- if (sock_net(sk)->ipv4.sysctl_tcp_syncookies != 2 &&
+ if (READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_syncookies) != 2 &&
!inet_csk_reqsk_queue_is_full(sk))
return 0;
@@ -6890,13 +6897,15 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops,
bool want_cookie = false;
struct dst_entry *dst;
struct flowi fl;
+ u8 syncookies;
+
+ syncookies = READ_ONCE(net->ipv4.sysctl_tcp_syncookies);
/* TW buckets are converted to open requests without
* limitations, they conserve resources and peer is
* evidently real one.
*/
- if ((net->ipv4.sysctl_tcp_syncookies == 2 ||
- inet_csk_reqsk_queue_is_full(sk)) && !isn) {
+ if ((syncookies == 2 || inet_csk_reqsk_queue_is_full(sk)) && !isn) {
want_cookie = tcp_syn_flood_action(sk, rsk_ops->slab_name);
if (!want_cookie)
goto drop;
@@ -6945,10 +6954,12 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops,
tcp_rsk(req)->ts_off = af_ops->init_ts_off(net, skb);
if (!want_cookie && !isn) {
+ int max_syn_backlog = READ_ONCE(net->ipv4.sysctl_max_syn_backlog);
+
/* Kill the following clause, if you dislike this way. */
- if (!net->ipv4.sysctl_tcp_syncookies &&
- (net->ipv4.sysctl_max_syn_backlog - inet_csk_reqsk_queue_len(sk) <
- (net->ipv4.sysctl_max_syn_backlog >> 2)) &&
+ if (!syncookies &&
+ (max_syn_backlog - inet_csk_reqsk_queue_len(sk) <
+ (max_syn_backlog >> 2)) &&
!tcp_peer_is_proven(req, dst)) {
/* Without syncookies last quarter of
* backlog is filled with destinations,
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 228d36692d08..c7e7101647dc 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -108,10 +108,10 @@ static u32 tcp_v4_init_ts_off(const struct net *net, const struct sk_buff *skb)
int tcp_twsk_unique(struct sock *sk, struct sock *sktw, void *twp)
{
+ int reuse = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_tw_reuse);
const struct inet_timewait_sock *tw = inet_twsk(sktw);
const struct tcp_timewait_sock *tcptw = tcp_twsk(sktw);
struct tcp_sock *tp = tcp_sk(sk);
- int reuse = sock_net(sk)->ipv4.sysctl_tcp_tw_reuse;
if (reuse == 2) {
/* Still does not detect *everything* that goes through
diff --git a/net/ipv4/tcp_metrics.c b/net/ipv4/tcp_metrics.c
index 7029b0e98edb..a501150deaa3 100644
--- a/net/ipv4/tcp_metrics.c
+++ b/net/ipv4/tcp_metrics.c
@@ -428,7 +428,8 @@ void tcp_update_metrics(struct sock *sk)
if (!tcp_metric_locked(tm, TCP_METRIC_REORDERING)) {
val = tcp_metric_get(tm, TCP_METRIC_REORDERING);
if (val < tp->reordering &&
- tp->reordering != net->ipv4.sysctl_tcp_reordering)
+ tp->reordering !=
+ READ_ONCE(net->ipv4.sysctl_tcp_reordering))
tcp_metric_set(tm, TCP_METRIC_REORDERING,
tp->reordering);
}
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index 6854bb1fb32b..cb95d88497ae 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -173,7 +173,7 @@ tcp_timewait_state_process(struct inet_timewait_sock *tw, struct sk_buff *skb,
* Oh well... nobody has a sufficient solution to this
* protocol bug yet.
*/
- if (twsk_net(tw)->ipv4.sysctl_tcp_rfc1337 == 0) {
+ if (!READ_ONCE(twsk_net(tw)->ipv4.sysctl_tcp_rfc1337)) {
kill:
inet_twsk_deschedule_put(tw);
return TCP_TW_SUCCESS;
@@ -781,7 +781,7 @@ listen_overflow:
if (sk != req->rsk_listener)
__NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPMIGRATEREQFAILURE);
- if (!sock_net(sk)->ipv4.sysctl_tcp_abort_on_overflow) {
+ if (!READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_abort_on_overflow)) {
inet_rsk(req)->acked = 1;
return NULL;
}
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 858a15cc2cc9..2b72ccd2e651 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -791,18 +791,18 @@ static unsigned int tcp_syn_options(struct sock *sk, struct sk_buff *skb,
opts->mss = tcp_advertise_mss(sk);
remaining -= TCPOLEN_MSS_ALIGNED;
- if (likely(sock_net(sk)->ipv4.sysctl_tcp_timestamps && !*md5)) {
+ if (likely(READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_timestamps) && !*md5)) {
opts->options |= OPTION_TS;
opts->tsval = tcp_skb_timestamp(skb) + tp->tsoffset;
opts->tsecr = tp->rx_opt.ts_recent;
remaining -= TCPOLEN_TSTAMP_ALIGNED;
}
- if (likely(sock_net(sk)->ipv4.sysctl_tcp_window_scaling)) {
+ if (likely(READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_window_scaling))) {
opts->ws = tp->rx_opt.rcv_wscale;
opts->options |= OPTION_WSCALE;
remaining -= TCPOLEN_WSCALE_ALIGNED;
}
- if (likely(sock_net(sk)->ipv4.sysctl_tcp_sack)) {
+ if (likely(READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_sack))) {
opts->options |= OPTION_SACK_ADVERTISE;
if (unlikely(!(OPTION_TS & opts->options)))
remaining -= TCPOLEN_SACKPERM_ALIGNED;
@@ -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;
@@ -1897,7 +1898,7 @@ static void tcp_cwnd_validate(struct sock *sk, bool is_cwnd_limited)
if (tp->packets_out > tp->snd_cwnd_used)
tp->snd_cwnd_used = tp->packets_out;
- if (sock_net(sk)->ipv4.sysctl_tcp_slow_start_after_idle &&
+ if (READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_slow_start_after_idle) &&
(s32)(tcp_jiffies32 - tp->snd_cwnd_stamp) >= inet_csk(sk)->icsk_rto &&
!ca_ops->cong_control)
tcp_cwnd_application_limited(sk);
@@ -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.
*/
@@ -2740,7 +2741,7 @@ bool tcp_schedule_loss_probe(struct sock *sk, bool advancing_rto)
if (rcu_access_pointer(tp->fastopen_rsk))
return false;
- early_retrans = sock_net(sk)->ipv4.sysctl_tcp_early_retrans;
+ early_retrans = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_early_retrans);
/* Schedule a loss probe in 2*RTT for SACK capable connections
* not in loss recovery, that are either limited by cwnd or application.
*/
@@ -3104,7 +3105,7 @@ static void tcp_retrans_try_collapse(struct sock *sk, struct sk_buff *to,
struct sk_buff *skb = to, *tmp;
bool first = true;
- if (!sock_net(sk)->ipv4.sysctl_tcp_retrans_collapse)
+ if (!READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_retrans_collapse))
return;
if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_SYN)
return;
@@ -3656,7 +3657,7 @@ static void tcp_connect_init(struct sock *sk)
* See tcp_input.c:tcp_rcv_state_process case TCP_SYN_SENT.
*/
tp->tcp_header_len = sizeof(struct tcphdr);
- if (sock_net(sk)->ipv4.sysctl_tcp_timestamps)
+ if (READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_timestamps))
tp->tcp_header_len += TCPOLEN_TSTAMP_ALIGNED;
#ifdef CONFIG_TCP_MD5SIG
@@ -3692,7 +3693,7 @@ static void tcp_connect_init(struct sock *sk)
tp->advmss - (tp->rx_opt.ts_recent_stamp ? tp->tcp_header_len - sizeof(struct tcphdr) : 0),
&tp->rcv_wnd,
&tp->window_clamp,
- sock_net(sk)->ipv4.sysctl_tcp_window_scaling,
+ READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_window_scaling),
&rcv_wscale,
rcv_wnd);
@@ -4099,7 +4100,7 @@ void tcp_send_probe0(struct sock *sk)
icsk->icsk_probes_out++;
if (err <= 0) {
- if (icsk->icsk_backoff < net->ipv4.sysctl_tcp_retries2)
+ if (icsk->icsk_backoff < READ_ONCE(net->ipv4.sysctl_tcp_retries2))
icsk->icsk_backoff++;
timeout = tcp_probe0_when(sk, TCP_RTO_MAX);
} else {
diff --git a/net/ipv4/tcp_recovery.c b/net/ipv4/tcp_recovery.c
index 48f30e7209f2..50abaa941387 100644
--- a/net/ipv4/tcp_recovery.c
+++ b/net/ipv4/tcp_recovery.c
@@ -14,7 +14,8 @@ static u32 tcp_rack_reo_wnd(const struct sock *sk)
return 0;
if (tp->sacked_out >= tp->reordering &&
- !(sock_net(sk)->ipv4.sysctl_tcp_recovery & TCP_RACK_NO_DUPTHRESH))
+ !(READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_recovery) &
+ TCP_RACK_NO_DUPTHRESH))
return 0;
}
@@ -187,7 +188,8 @@ void tcp_rack_update_reo_wnd(struct sock *sk, struct rate_sample *rs)
{
struct tcp_sock *tp = tcp_sk(sk);
- if (sock_net(sk)->ipv4.sysctl_tcp_recovery & TCP_RACK_STATIC_REO_WND ||
+ if ((READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_recovery) &
+ TCP_RACK_STATIC_REO_WND) ||
!rs->prior_delivered)
return;
diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c
index 2208755e8efc..b4dfb82d6ecb 100644
--- a/net/ipv4/tcp_timer.c
+++ b/net/ipv4/tcp_timer.c
@@ -143,7 +143,7 @@ static int tcp_out_of_resources(struct sock *sk, bool do_reset)
*/
static int tcp_orphan_retries(struct sock *sk, bool alive)
{
- int retries = sock_net(sk)->ipv4.sysctl_tcp_orphan_retries; /* May be zero. */
+ int retries = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_orphan_retries); /* May be zero. */
/* We know from an ICMP that something is wrong. */
if (sk->sk_err_soft && !alive)
@@ -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);
@@ -239,17 +239,18 @@ static int tcp_write_timeout(struct sock *sk)
if ((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV)) {
if (icsk->icsk_retransmits)
__dst_negative_advice(sk);
- retry_until = icsk->icsk_syn_retries ? : net->ipv4.sysctl_tcp_syn_retries;
+ retry_until = icsk->icsk_syn_retries ? :
+ READ_ONCE(net->ipv4.sysctl_tcp_syn_retries);
expired = icsk->icsk_retransmits >= retry_until;
} else {
- if (retransmits_timed_out(sk, net->ipv4.sysctl_tcp_retries1, 0)) {
+ if (retransmits_timed_out(sk, READ_ONCE(net->ipv4.sysctl_tcp_retries1), 0)) {
/* Black hole detection */
tcp_mtu_probing(icsk, sk);
__dst_negative_advice(sk);
}
- retry_until = net->ipv4.sysctl_tcp_retries2;
+ retry_until = READ_ONCE(net->ipv4.sysctl_tcp_retries2);
if (sock_flag(sk, SOCK_DEAD)) {
const bool alive = icsk->icsk_rto < TCP_RTO_MAX;
@@ -374,7 +375,7 @@ static void tcp_probe_timer(struct sock *sk)
msecs_to_jiffies(icsk->icsk_user_timeout))
goto abort;
- max_probes = sock_net(sk)->ipv4.sysctl_tcp_retries2;
+ max_probes = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_retries2);
if (sock_flag(sk, SOCK_DEAD)) {
const bool alive = inet_csk_rto_backoff(icsk, TCP_RTO_MAX) < TCP_RTO_MAX;
@@ -400,12 +401,15 @@ abort: tcp_write_err(sk);
static void tcp_fastopen_synack_timer(struct sock *sk, struct request_sock *req)
{
struct inet_connection_sock *icsk = inet_csk(sk);
- int max_retries = icsk->icsk_syn_retries ? :
- sock_net(sk)->ipv4.sysctl_tcp_synack_retries + 1; /* add one more retry for fastopen */
struct tcp_sock *tp = tcp_sk(sk);
+ int max_retries;
req->rsk_ops->syn_ack_timeout(req);
+ /* add one more retry for fastopen */
+ max_retries = icsk->icsk_syn_retries ? :
+ READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_synack_retries) + 1;
+
if (req->num_timeout >= max_retries) {
tcp_write_err(sk);
return;
@@ -568,7 +572,7 @@ out_reset_timer:
* linear-timeout retransmissions into a black hole
*/
if (sk->sk_state == TCP_ESTABLISHED &&
- (tp->thin_lto || net->ipv4.sysctl_tcp_thin_linear_timeouts) &&
+ (tp->thin_lto || READ_ONCE(net->ipv4.sysctl_tcp_thin_linear_timeouts)) &&
tcp_stream_is_thin(tp) &&
icsk->icsk_retransmits <= TCP_THIN_LINEAR_RETRIES) {
icsk->icsk_backoff = 0;
@@ -579,7 +583,7 @@ out_reset_timer:
}
inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS,
tcp_clamp_rto_to_user_timeout(sk), TCP_RTO_MAX);
- if (retransmits_timed_out(sk, net->ipv4.sysctl_tcp_retries1 + 1, 0))
+ if (retransmits_timed_out(sk, READ_ONCE(net->ipv4.sysctl_tcp_retries1) + 1, 0))
__sk_dst_reset(sk);
out:;