Update Linux to v5.10.157
Sourced from [1]
[1] https://cdn.kernel.org/pub/linux/kernel/v5.x/linux-5.10.157.tar.xz
Signed-off-by: Olivier Deprez <olivier.deprez@arm.com>
Change-Id: I7b30d9e98d8c465d6b44de8e7433b4a40b3289ba
diff --git a/net/ipv4/Kconfig b/net/ipv4/Kconfig
index 87983e7..23b0606 100644
--- a/net/ipv4/Kconfig
+++ b/net/ipv4/Kconfig
@@ -403,6 +403,16 @@
If unsure, say Y.
+config INET_TABLE_PERTURB_ORDER
+ int "INET: Source port perturbation table size (as power of 2)" if EXPERT
+ default 16
+ help
+ Source port perturbation table size (as power of 2) for
+ RFC 6056 3.3.4. Algorithm 4: Double-Hash Port Selection Algorithm.
+
+ The default is almost always what you want.
+ Only change this if you know what you are doing.
+
config INET_XFRM_TUNNEL
tristate
select INET_TUNNEL
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 7422185..48223c2 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -158,7 +158,7 @@
kfree(rcu_dereference_protected(inet->inet_opt, 1));
dst_release(rcu_dereference_protected(sk->sk_dst_cache, 1));
- dst_release(sk->sk_rx_dst);
+ dst_release(rcu_dereference_protected(sk->sk_rx_dst, 1));
sk_refcnt_debug_dec(sk);
}
EXPORT_SYMBOL(inet_sock_destruct);
@@ -220,7 +220,7 @@
* 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) {
@@ -338,7 +338,7 @@
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;
@@ -1245,7 +1245,7 @@
if (new_saddr == old_saddr)
return 0;
- if (sock_net(sk)->ipv4.sysctl_ip_dynaddr > 1) {
+ if (READ_ONCE(sock_net(sk)->ipv4.sysctl_ip_dynaddr) > 1) {
pr_info("%s(): shifting inet->saddr from %pI4 to %pI4\n",
__func__, &old_saddr, &new_saddr);
}
@@ -1300,7 +1300,7 @@
* Other protocols have to map its equivalent state to TCP_SYN_SENT.
* DCCP maps its DCCP_REQUESTING state to TCP_SYN_SENT. -acme
*/
- if (!sock_net(sk)->ipv4.sysctl_ip_dynaddr ||
+ if (!READ_ONCE(sock_net(sk)->ipv4.sysctl_ip_dynaddr) ||
sk->sk_state != TCP_SYN_SENT ||
(sk->sk_userlocks & SOCK_BINDADDR_LOCK) ||
(err = inet_sk_reselect_saddr(sk)) != 0)
@@ -1726,12 +1726,7 @@
};
#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,
@@ -1739,12 +1734,7 @@
.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/arp.c b/net/ipv4/arp.c
index 922dd73..83a4799 100644
--- a/net/ipv4/arp.c
+++ b/net/ipv4/arp.c
@@ -1116,13 +1116,18 @@
return err;
}
-static int arp_invalidate(struct net_device *dev, __be32 ip)
+int arp_invalidate(struct net_device *dev, __be32 ip, bool force)
{
struct neighbour *neigh = neigh_lookup(&arp_tbl, &ip, dev);
int err = -ENXIO;
struct neigh_table *tbl = &arp_tbl;
if (neigh) {
+ if ((neigh->nud_state & NUD_VALID) && !force) {
+ neigh_release(neigh);
+ return 0;
+ }
+
if (neigh->nud_state & ~NUD_NOARP)
err = neigh_update(neigh, NULL, NUD_FAILED,
NEIGH_UPDATE_F_OVERRIDE|
@@ -1169,7 +1174,7 @@
if (!dev)
return -EINVAL;
}
- return arp_invalidate(dev, ip);
+ return arp_invalidate(dev, ip, true);
}
/*
diff --git a/net/ipv4/cipso_ipv4.c b/net/ipv4/cipso_ipv4.c
index ca217a6..d4a4160 100644
--- a/net/ipv4/cipso_ipv4.c
+++ b/net/ipv4/cipso_ipv4.c
@@ -240,7 +240,7 @@
struct cipso_v4_map_cache_entry *prev_entry = NULL;
u32 hash;
- if (!cipso_v4_cache_enabled)
+ if (!READ_ONCE(cipso_v4_cache_enabled))
return -ENOENT;
hash = cipso_v4_map_cache_hash(key, key_len);
@@ -297,13 +297,14 @@
int cipso_v4_cache_add(const unsigned char *cipso_ptr,
const struct netlbl_lsm_secattr *secattr)
{
+ int bkt_size = READ_ONCE(cipso_v4_cache_bucketsize);
int ret_val = -EPERM;
u32 bkt;
struct cipso_v4_map_cache_entry *entry = NULL;
struct cipso_v4_map_cache_entry *old_entry = NULL;
u32 cipso_ptr_len;
- if (!cipso_v4_cache_enabled || cipso_v4_cache_bucketsize <= 0)
+ if (!READ_ONCE(cipso_v4_cache_enabled) || bkt_size <= 0)
return 0;
cipso_ptr_len = cipso_ptr[1];
@@ -323,7 +324,7 @@
bkt = entry->hash & (CIPSO_V4_CACHE_BUCKETS - 1);
spin_lock_bh(&cipso_v4_cache[bkt].lock);
- if (cipso_v4_cache[bkt].size < cipso_v4_cache_bucketsize) {
+ if (cipso_v4_cache[bkt].size < bkt_size) {
list_add(&entry->list, &cipso_v4_cache[bkt].list);
cipso_v4_cache[bkt].size += 1;
} else {
@@ -1200,7 +1201,8 @@
/* This will send packets using the "optimized" format when
* possible as specified in section 3.4.2.6 of the
* CIPSO draft. */
- if (cipso_v4_rbm_optfmt && ret_val > 0 && ret_val <= 10)
+ if (READ_ONCE(cipso_v4_rbm_optfmt) && ret_val > 0 &&
+ ret_val <= 10)
tag_len = 14;
else
tag_len = 4 + ret_val;
@@ -1604,7 +1606,7 @@
* all the CIPSO validations here but it doesn't
* really specify _exactly_ what we need to validate
* ... so, just make it a sysctl tunable. */
- if (cipso_v4_rbm_strictvalid) {
+ if (READ_ONCE(cipso_v4_rbm_strictvalid)) {
if (cipso_v4_map_lvl_valid(doi_def,
tag[3]) < 0) {
err_offset = opt_iter + 3;
diff --git a/net/ipv4/datagram.c b/net/ipv4/datagram.c
index 4a8550c..112c6e8 100644
--- a/net/ipv4/datagram.c
+++ b/net/ipv4/datagram.c
@@ -70,7 +70,7 @@
}
inet->inet_daddr = fl4->daddr;
inet->inet_dport = usin->sin_port;
- reuseport_has_conns(sk, true);
+ reuseport_has_conns_set(sk);
sk->sk_state = TCP_ESTABLISHED;
sk_set_txhash(sk);
inet->inet_id = prandom_u32();
diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c
index 148ef48..88b6120 100644
--- a/net/ipv4/devinet.c
+++ b/net/ipv4/devinet.c
@@ -1244,7 +1244,7 @@
return ret;
}
-static int inet_gifconf(struct net_device *dev, char __user *buf, int len, int size)
+int inet_gifconf(struct net_device *dev, char __user *buf, int len, int size)
{
struct in_device *in_dev = __in_dev_get_rtnl(dev);
const struct in_ifaddr *ifa;
@@ -2668,23 +2668,27 @@
#endif
if (!net_eq(net, &init_net)) {
- if (IS_ENABLED(CONFIG_SYSCTL) &&
- sysctl_devconf_inherit_init_net == 3) {
+ switch (net_inherit_devconf()) {
+ case 3:
/* copy from the current netns */
memcpy(all, current->nsproxy->net_ns->ipv4.devconf_all,
sizeof(ipv4_devconf));
memcpy(dflt,
current->nsproxy->net_ns->ipv4.devconf_dflt,
sizeof(ipv4_devconf_dflt));
- } else if (!IS_ENABLED(CONFIG_SYSCTL) ||
- sysctl_devconf_inherit_init_net != 2) {
- /* inherit == 0 or 1: copy from init_net */
+ break;
+ case 0:
+ case 1:
+ /* copy from init_net */
memcpy(all, init_net.ipv4.devconf_all,
sizeof(ipv4_devconf));
memcpy(dflt, init_net.ipv4.devconf_dflt,
sizeof(ipv4_devconf_dflt));
+ break;
+ case 2:
+ /* use compiled values */
+ break;
}
- /* else inherit == 2: use compiled values */
}
#ifdef CONFIG_SYSCTL
@@ -2762,8 +2766,6 @@
INIT_HLIST_HEAD(&inet_addr_lst[i]);
register_pernet_subsys(&devinet_ops);
-
- register_gifconf(PF_INET, inet_gifconf);
register_netdevice_notifier(&ip_netdev_notifier);
queue_delayed_work(system_power_efficient_wq, &check_lifetime_work, 0);
diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c
index 9aae821..20d7381 100644
--- a/net/ipv4/esp4.c
+++ b/net/ipv4/esp4.c
@@ -448,7 +448,6 @@
struct page *page;
struct sk_buff *trailer;
int tailen = esp->tailen;
- unsigned int allocsz;
/* this is non-NULL only with TCP/UDP Encapsulation */
if (x->encap) {
@@ -458,8 +457,8 @@
return err;
}
- allocsz = ALIGN(skb->data_len + tailen, L1_CACHE_BYTES);
- if (allocsz > ESP_SKB_FRAG_MAXSIZE)
+ if (ALIGN(tailen, L1_CACHE_BYTES) > PAGE_SIZE ||
+ ALIGN(skb->data_len, L1_CACHE_BYTES) > PAGE_SIZE)
goto cow;
if (!skb_cloned(skb)) {
diff --git a/net/ipv4/esp4_offload.c b/net/ipv4/esp4_offload.c
index 3450c9b..8425767 100644
--- a/net/ipv4/esp4_offload.c
+++ b/net/ipv4/esp4_offload.c
@@ -312,6 +312,9 @@
xo->seq.low += skb_shinfo(skb)->gso_segs;
}
+ if (xo->seq.low < seq)
+ xo->seq.hi++;
+
esp.seqno = cpu_to_be64(seq + ((u64)xo->seq.hi << 32));
ip_hdr(skb)->tot_len = htons(skb->len);
diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index 917ea95..af8a425 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -389,7 +389,7 @@
dev_match = dev_match || (res.type == RTN_LOCAL &&
dev == net->loopback_dev);
if (dev_match) {
- ret = FIB_RES_NHC(res)->nhc_scope >= RT_SCOPE_HOST;
+ ret = FIB_RES_NHC(res)->nhc_scope >= RT_SCOPE_LINK;
return ret;
}
if (no_addr)
@@ -401,7 +401,7 @@
ret = 0;
if (fib_lookup(net, &fl4, &res, FIB_LOOKUP_IGNORE_LINKSTATE) == 0) {
if (res.type == RTN_UNICAST)
- ret = FIB_RES_NHC(res)->nhc_scope >= RT_SCOPE_HOST;
+ ret = FIB_RES_NHC(res)->nhc_scope >= RT_SCOPE_LINK;
}
return ret;
@@ -1112,9 +1112,11 @@
return;
/* Add broadcast address, if it is explicitly assigned. */
- if (ifa->ifa_broadcast && ifa->ifa_broadcast != htonl(0xFFFFFFFF))
+ if (ifa->ifa_broadcast && ifa->ifa_broadcast != htonl(0xFFFFFFFF)) {
fib_magic(RTM_NEWROUTE, RTN_BROADCAST, ifa->ifa_broadcast, 32,
prim, 0);
+ arp_invalidate(dev, ifa->ifa_broadcast, false);
+ }
if (!ipv4_is_zeronet(prefix) && !(ifa->ifa_flags & IFA_F_SECONDARY) &&
(prefix != addr || ifa->ifa_prefixlen < 32)) {
@@ -1130,6 +1132,7 @@
prim, 0);
fib_magic(RTM_NEWROUTE, RTN_BROADCAST, prefix | ~mask,
32, prim, 0);
+ arp_invalidate(dev, prefix | ~mask, false);
}
}
}
diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index 838a876..3824b7a 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -888,8 +888,13 @@
}
if (cfg->fc_oif || cfg->fc_gw_family) {
- struct fib_nh *nh = fib_info_nh(fi, 0);
+ struct fib_nh *nh;
+ /* cannot match on nexthop object attributes */
+ if (fi->nh)
+ return 1;
+
+ nh = fib_info_nh(fi, 0);
if (cfg->fc_encap) {
if (fib_encap_match(net, cfg->fc_encap_type,
cfg->fc_encap, nh, cfg, extack))
@@ -1224,7 +1229,7 @@
nh->fib_nh_dev = in_dev->dev;
dev_hold(nh->fib_nh_dev);
- nh->fib_nh_scope = RT_SCOPE_HOST;
+ nh->fib_nh_scope = RT_SCOPE_LINK;
if (!netif_carrier_ok(nh->fib_nh_dev))
nh->fib_nh_flags |= RTNH_F_LINKDOWN;
err = 0;
@@ -1826,7 +1831,7 @@
goto nla_put_failure;
if (nexthop_is_blackhole(fi->nh))
rtm->rtm_type = RTN_BLACKHOLE;
- if (!fi->fib_net->ipv4.sysctl_nexthop_compat_mode)
+ if (!READ_ONCE(fi->fib_net->ipv4.sysctl_nexthop_compat_mode))
goto offload;
}
@@ -2227,7 +2232,7 @@
}
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/fib_trie.c b/net/ipv4/fib_trie.c
index ffc5332..d11fb16 100644
--- a/net/ipv4/fib_trie.c
+++ b/net/ipv4/fib_trie.c
@@ -497,7 +497,7 @@
tn = container_of(head, struct tnode, rcu)->kv;
}
- if (tnode_free_size >= sysctl_fib_sync_mem) {
+ if (tnode_free_size >= READ_ONCE(sysctl_fib_sync_mem)) {
tnode_free_size = 0;
synchronize_rcu();
}
@@ -1331,8 +1331,10 @@
/* The alias was already inserted, so the node must exist. */
l = l ? l : fib_find_node(t, &tp, key);
- if (WARN_ON_ONCE(!l))
+ if (WARN_ON_ONCE(!l)) {
+ err = -ENOENT;
goto out_free_new_fa;
+ }
if (fib_find_alias(&l->leaf, new_fa->fa_slen, 0, 0, tb->tb_id, true) ==
new_fa) {
diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c
index b71b836..a1aacf5 100644
--- a/net/ipv4/icmp.c
+++ b/net/ipv4/icmp.c
@@ -261,11 +261,12 @@
spin_lock(&icmp_global.lock);
delta = min_t(u32, now - icmp_global.stamp, HZ);
if (delta >= HZ / 50) {
- incr = sysctl_icmp_msgs_per_sec * delta / HZ ;
+ incr = READ_ONCE(sysctl_icmp_msgs_per_sec) * delta / HZ;
if (incr)
WRITE_ONCE(icmp_global.stamp, now);
}
- credit = min_t(u32, icmp_global.credit + incr, sysctl_icmp_msgs_burst);
+ credit = min_t(u32, icmp_global.credit + incr,
+ READ_ONCE(sysctl_icmp_msgs_burst));
if (credit) {
/* We want to use a credit of one in average, but need to randomize
* it for security reasons.
@@ -289,7 +290,7 @@
return true;
/* Limit if icmp type is enabled in ratemask. */
- if (!((1 << type) & net->ipv4.sysctl_icmp_ratemask))
+ if (!((1 << type) & READ_ONCE(net->ipv4.sysctl_icmp_ratemask)))
return true;
return false;
@@ -327,7 +328,8 @@
vif = l3mdev_master_ifindex(dst->dev);
peer = inet_getpeer_v4(net->ipv4.peers, fl4->daddr, vif, 1);
- rc = inet_peer_xrlim_allow(peer, net->ipv4.sysctl_icmp_ratelimit);
+ rc = inet_peer_xrlim_allow(peer,
+ READ_ONCE(net->ipv4.sysctl_icmp_ratelimit));
if (peer)
inet_putpeer(peer);
out:
@@ -447,7 +449,7 @@
fl4.flowi4_tos = RT_TOS(ip_hdr(skb)->tos);
fl4.flowi4_proto = IPPROTO_ICMP;
fl4.flowi4_oif = l3mdev_master_ifindex(skb->dev);
- security_skb_classify_flow(skb, flowi4_to_flowi(&fl4));
+ security_skb_classify_flow(skb, flowi4_to_flowi_common(&fl4));
rt = ip_route_output_key(net, &fl4);
if (IS_ERR(rt))
goto out_unlock;
@@ -503,7 +505,7 @@
route_lookup_dev = icmp_get_route_lookup_dev(skb_in);
fl4->flowi4_oif = l3mdev_master_ifindex(route_lookup_dev);
- security_skb_classify_flow(skb_in, flowi4_to_flowi(fl4));
+ security_skb_classify_flow(skb_in, flowi4_to_flowi_common(fl4));
rt = ip_route_output_key_hash(net, fl4, skb_in);
if (IS_ERR(rt))
return rt;
@@ -885,7 +887,7 @@
* 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 0c32199..c71b863 100644
--- a/net/ipv4/igmp.c
+++ b/net/ipv4/igmp.c
@@ -467,7 +467,8 @@
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 @@
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 @@
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 @@
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 @@
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 @@
* 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 @@
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 @@
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 @@
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 @@
#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 @@
#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 @@
* 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 @@
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 @@
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 @@
#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 @@
/* 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 @@
#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 @@
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 @@
}
/* 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;
}
@@ -2401,9 +2408,10 @@
newpsl->sl_addr[i] = psl->sl_addr[i];
/* decrease mem now to avoid the memleak warning */
atomic_sub(IP_SFLSIZE(psl->sl_max), &sk->sk_omem_alloc);
- kfree_rcu(psl, rcu);
}
rcu_assign_pointer(pmc->sflist, newpsl);
+ if (psl)
+ kfree_rcu(psl, rcu);
psl = newpsl;
}
rv = 1; /* > 0 for insert logic below if sl_count is 0 */
@@ -2501,11 +2509,13 @@
psl->sl_count, psl->sl_addr, 0);
/* decrease mem now to avoid the memleak warning */
atomic_sub(IP_SFLSIZE(psl->sl_max), &sk->sk_omem_alloc);
- kfree_rcu(psl, rcu);
- } else
+ } else {
(void) ip_mc_del_src(in_dev, &msf->imsf_multiaddr, pmc->sfmode,
0, NULL, 0);
+ }
rcu_assign_pointer(pmc->sflist, newpsl);
+ if (psl)
+ kfree_rcu(psl, rcu);
pmc->sfmode = msf->imsf_fmode;
err = 0;
done:
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index addd595..4d97133 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -251,7 +251,7 @@
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;
@@ -602,7 +602,7 @@
(opt && opt->opt.srr) ? opt->opt.faddr : ireq->ir_rmt_addr,
ireq->ir_loc_addr, ireq->ir_rmt_port,
htons(ireq->ir_num), sk->sk_uid);
- security_req_classify_flow(req, flowi4_to_flowi(fl4));
+ security_req_classify_flow(req, flowi4_to_flowi_common(fl4));
rt = ip_route_output_flow(net, fl4, sk);
if (IS_ERR(rt))
goto no_route;
@@ -640,7 +640,7 @@
(opt && opt->opt.srr) ? opt->opt.faddr : ireq->ir_rmt_addr,
ireq->ir_loc_addr, ireq->ir_rmt_port,
htons(ireq->ir_num), sk->sk_uid);
- security_req_classify_flow(req, flowi4_to_flowi(fl4));
+ security_req_classify_flow(req, flowi4_to_flowi_common(fl4));
rt = ip_route_output_flow(net, fl4, sk);
if (IS_ERR(rt))
goto no_route;
diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c
index e093847..c68a1da 100644
--- a/net/ipv4/inet_hashtables.c
+++ b/net/ipv4/inet_hashtables.c
@@ -410,13 +410,11 @@
sk_nulls_for_each_rcu(sk, node, &head->chain) {
if (sk->sk_hash != hash)
continue;
- if (likely(INET_MATCH(sk, net, acookie,
- saddr, daddr, ports, dif, sdif))) {
+ if (likely(INET_MATCH(net, sk, acookie, ports, dif, sdif))) {
if (unlikely(!refcount_inc_not_zero(&sk->sk_refcnt)))
goto out;
- if (unlikely(!INET_MATCH(sk, net, acookie,
- saddr, daddr, ports,
- dif, sdif))) {
+ if (unlikely(!INET_MATCH(net, sk, acookie,
+ ports, dif, sdif))) {
sock_gen_put(sk);
goto begin;
}
@@ -465,8 +463,7 @@
if (sk2->sk_hash != hash)
continue;
- if (likely(INET_MATCH(sk2, net, acookie,
- saddr, daddr, ports, dif, sdif))) {
+ if (likely(INET_MATCH(net, sk2, acookie, ports, dif, sdif))) {
if (sk2->sk_state == TCP_TIME_WAIT) {
tw = inet_twsk(sk2);
if (twsk_unique(sk, sk2, twp))
@@ -504,7 +501,7 @@
return -EADDRNOTAVAIL;
}
-static u32 inet_sk_port_offset(const struct sock *sk)
+static u64 inet_sk_port_offset(const struct sock *sk)
{
const struct inet_sock *inet = inet_sk(sk);
@@ -532,16 +529,14 @@
if (esk->sk_hash != sk->sk_hash)
continue;
if (sk->sk_family == AF_INET) {
- if (unlikely(INET_MATCH(esk, net, acookie,
- sk->sk_daddr,
- sk->sk_rcv_saddr,
+ if (unlikely(INET_MATCH(net, esk, acookie,
ports, dif, sdif))) {
return true;
}
}
#if IS_ENABLED(CONFIG_IPV6)
else if (sk->sk_family == AF_INET6) {
- if (unlikely(INET6_MATCH(esk, net,
+ if (unlikely(inet6_match(net, esk,
&sk->sk_v6_daddr,
&sk->sk_v6_rcv_saddr,
ports, dif, sdif))) {
@@ -637,7 +632,9 @@
int err = 0;
if (sk->sk_state != TCP_LISTEN) {
+ local_bh_disable();
inet_ehash_nolisten(sk, osk, NULL);
+ local_bh_enable();
return 0;
}
WARN_ON(!sk_unhashed(sk));
@@ -669,50 +666,72 @@
{
int err = 0;
- if (sk->sk_state != TCP_CLOSE) {
- local_bh_disable();
+ if (sk->sk_state != TCP_CLOSE)
err = __inet_hash(sk, NULL);
- local_bh_enable();
- }
return err;
}
EXPORT_SYMBOL_GPL(inet_hash);
-void inet_unhash(struct sock *sk)
+static void __inet_unhash(struct sock *sk, struct inet_listen_hashbucket *ilb)
{
- struct inet_hashinfo *hashinfo = sk->sk_prot->h.hashinfo;
- struct inet_listen_hashbucket *ilb = NULL;
- spinlock_t *lock;
-
if (sk_unhashed(sk))
return;
- if (sk->sk_state == TCP_LISTEN) {
- ilb = &hashinfo->listening_hash[inet_sk_listen_hashfn(sk)];
- lock = &ilb->lock;
- } else {
- lock = inet_ehash_lockp(hashinfo, sk->sk_hash);
- }
- spin_lock_bh(lock);
- if (sk_unhashed(sk))
- goto unlock;
-
if (rcu_access_pointer(sk->sk_reuseport_cb))
reuseport_detach_sock(sk);
if (ilb) {
+ struct inet_hashinfo *hashinfo = sk->sk_prot->h.hashinfo;
+
inet_unhash2(hashinfo, sk);
ilb->count--;
}
__sk_nulls_del_node_init_rcu(sk);
sock_prot_inuse_add(sock_net(sk), sk->sk_prot, -1);
-unlock:
- spin_unlock_bh(lock);
+}
+
+void inet_unhash(struct sock *sk)
+{
+ struct inet_hashinfo *hashinfo = sk->sk_prot->h.hashinfo;
+
+ if (sk_unhashed(sk))
+ return;
+
+ if (sk->sk_state == TCP_LISTEN) {
+ struct inet_listen_hashbucket *ilb;
+
+ ilb = &hashinfo->listening_hash[inet_sk_listen_hashfn(sk)];
+ /* Don't disable bottom halves while acquiring the lock to
+ * avoid circular locking dependency on PREEMPT_RT.
+ */
+ spin_lock(&ilb->lock);
+ __inet_unhash(sk, ilb);
+ spin_unlock(&ilb->lock);
+ } else {
+ spinlock_t *lock = inet_ehash_lockp(hashinfo, sk->sk_hash);
+
+ spin_lock_bh(lock);
+ __inet_unhash(sk, NULL);
+ spin_unlock_bh(lock);
+ }
}
EXPORT_SYMBOL_GPL(inet_unhash);
+/* RFC 6056 3.3.4. Algorithm 4: Double-Hash Port Selection Algorithm
+ * Note that we use 32bit integers (vs RFC 'short integers')
+ * because 2^16 is not a multiple of num_ephemeral and this
+ * property might be used by clever attacker.
+ *
+ * RFC claims using TABLE_LENGTH=10 buckets gives an improvement, though
+ * attacks were since demonstrated, thus we use 65536 by default instead
+ * to really give more isolation and privacy, at the expense of 256kB
+ * of kernel memory.
+ */
+#define INET_TABLE_PERTURB_SIZE (1 << CONFIG_INET_TABLE_PERTURB_ORDER)
+static u32 *table_perturb;
+
int __inet_hash_connect(struct inet_timewait_death_row *death_row,
- struct sock *sk, u32 port_offset,
+ struct sock *sk, u64 port_offset,
int (*check_established)(struct inet_timewait_death_row *,
struct sock *, __u16, struct inet_timewait_sock **))
{
@@ -724,8 +743,8 @@
struct inet_bind_bucket *tb;
u32 remaining, offset;
int ret, i, low, high;
- static u32 hint;
int l3mdev;
+ u32 index;
if (port) {
head = &hinfo->bhash[inet_bhashfn(net, port,
@@ -752,7 +771,13 @@
if (likely(remaining > 1))
remaining &= ~1U;
- offset = (hint + port_offset) % remaining;
+ get_random_slow_once(table_perturb,
+ INET_TABLE_PERTURB_SIZE * sizeof(*table_perturb));
+ index = port_offset & (INET_TABLE_PERTURB_SIZE - 1);
+
+ offset = READ_ONCE(table_perturb[index]) + (port_offset >> 32);
+ offset %= remaining;
+
/* In first pass we try ports of @low parity.
* inet_csk_get_port() does the opposite choice.
*/
@@ -806,7 +831,13 @@
return -EADDRNOTAVAIL;
ok:
- hint += i + 2;
+ /* Here we want to add a little bit of randomness to the next source
+ * port that will be chosen. We use a max() with a random here so that
+ * on low contention the randomness is maximal and on high contention
+ * it may be inexistent.
+ */
+ i = max_t(int, i, (prandom_u32() & 7) * 2);
+ WRITE_ONCE(table_perturb[index], READ_ONCE(table_perturb[index]) + i + 2);
/* Head lock still held and bh's disabled */
inet_bind_hash(sk, tb, port);
@@ -829,7 +860,7 @@
int inet_hash_connect(struct inet_timewait_death_row *death_row,
struct sock *sk)
{
- u32 port_offset = 0;
+ u64 port_offset = 0;
if (!inet_sk(sk)->inet_num)
port_offset = inet_sk_port_offset(sk);
@@ -879,6 +910,12 @@
low_limit,
high_limit);
init_hashinfo_lhash2(h);
+
+ /* this one is used for source ports of outgoing connections */
+ table_perturb = kmalloc_array(INET_TABLE_PERTURB_SIZE,
+ sizeof(*table_perturb), GFP_KERNEL);
+ if (!table_perturb)
+ panic("TCP: failed to alloc table_perturb");
}
int inet_hashinfo2_init_mod(struct inet_hashinfo *h)
diff --git a/net/ipv4/inetpeer.c b/net/ipv4/inetpeer.c
index ff327a6..a186685 100644
--- a/net/ipv4/inetpeer.c
+++ b/net/ipv4/inetpeer.c
@@ -148,16 +148,20 @@
struct inet_peer *gc_stack[],
unsigned int gc_cnt)
{
+ int peer_threshold, peer_maxttl, peer_minttl;
struct inet_peer *p;
__u32 delta, ttl;
int i;
- if (base->total >= inet_peer_threshold)
+ peer_threshold = READ_ONCE(inet_peer_threshold);
+ peer_maxttl = READ_ONCE(inet_peer_maxttl);
+ peer_minttl = READ_ONCE(inet_peer_minttl);
+
+ if (base->total >= peer_threshold)
ttl = 0; /* be aggressive */
else
- ttl = inet_peer_maxttl
- - (inet_peer_maxttl - inet_peer_minttl) / HZ *
- base->total / inet_peer_threshold * HZ;
+ ttl = peer_maxttl - (peer_maxttl - peer_minttl) / HZ *
+ base->total / peer_threshold * HZ;
for (i = 0; i < gc_cnt; i++) {
p = gc_stack[i];
diff --git a/net/ipv4/ip_forward.c b/net/ipv4/ip_forward.c
index 00ec819..29730ed 100644
--- a/net/ipv4/ip_forward.c
+++ b/net/ipv4/ip_forward.c
@@ -151,7 +151,7 @@
!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_gre.c b/net/ipv4/ip_gre.c
index e4504dd..6ab5c50 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -454,14 +454,12 @@
__be16 proto)
{
struct ip_tunnel *tunnel = netdev_priv(dev);
-
- if (tunnel->parms.o_flags & TUNNEL_SEQ)
- tunnel->o_seqno++;
+ __be16 flags = tunnel->parms.o_flags;
/* Push GRE header. */
gre_build_header(skb, tunnel->tun_hlen,
- tunnel->parms.o_flags, proto, tunnel->parms.o_key,
- htonl(tunnel->o_seqno));
+ flags, proto, tunnel->parms.o_key,
+ (flags & TUNNEL_SEQ) ? htonl(atomic_fetch_inc(&tunnel->o_seqno)) : 0);
ip_tunnel_xmit(skb, dev, tnl_params, tnl_params->protocol);
}
@@ -499,7 +497,7 @@
(TUNNEL_CSUM | TUNNEL_KEY | TUNNEL_SEQ);
gre_build_header(skb, tunnel_hlen, flags, proto,
tunnel_id_to_key32(tun_info->key.tun_id),
- (flags & TUNNEL_SEQ) ? htonl(tunnel->o_seqno++) : 0);
+ (flags & TUNNEL_SEQ) ? htonl(atomic_fetch_inc(&tunnel->o_seqno)) : 0);
ip_md_tunnel_xmit(skb, dev, IPPROTO_GRE, tunnel_hlen);
@@ -521,7 +519,6 @@
int tunnel_hlen;
int version;
int nhoff;
- int thoff;
tun_info = skb_tunnel_info(skb);
if (unlikely(!tun_info || !(tun_info->mode & IP_TUNNEL_INFO_TX) ||
@@ -555,10 +552,16 @@
(ntohs(ip_hdr(skb)->tot_len) > skb->len - nhoff))
truncate = true;
- thoff = skb_transport_header(skb) - skb_mac_header(skb);
- if (skb->protocol == htons(ETH_P_IPV6) &&
- (ntohs(ipv6_hdr(skb)->payload_len) > skb->len - thoff))
- truncate = true;
+ if (skb->protocol == htons(ETH_P_IPV6)) {
+ int thoff;
+
+ if (skb_transport_header_was_set(skb))
+ thoff = skb_transport_header(skb) - skb_mac_header(skb);
+ else
+ thoff = nhoff + sizeof(struct ipv6hdr);
+ if (ntohs(ipv6_hdr(skb)->payload_len) > skb->len - thoff)
+ truncate = true;
+ }
if (version == 1) {
erspan_build_header(skb, ntohl(tunnel_id_to_key32(key->tun_id)),
@@ -576,7 +579,7 @@
}
gre_build_header(skb, 8, TUNNEL_SEQ,
- proto, 0, htonl(tunnel->o_seqno++));
+ proto, 0, htonl(atomic_fetch_inc(&tunnel->o_seqno)));
ip_md_tunnel_xmit(skb, dev, IPPROTO_GRE, tunnel_hlen);
@@ -626,21 +629,20 @@
}
if (dev->header_ops) {
- const int pull_len = tunnel->hlen + sizeof(struct iphdr);
-
if (skb_cow_head(skb, 0))
goto free_skb;
tnl_params = (const struct iphdr *)skb->data;
- if (pull_len > skb_transport_offset(skb))
- goto free_skb;
-
/* Pull skb since ip_tunnel_xmit() needs skb->data pointing
* to gre header.
*/
- skb_pull(skb, pull_len);
+ skb_pull(skb, tunnel->hlen + sizeof(struct iphdr));
skb_reset_mac_header(skb);
+
+ if (skb->ip_summed == CHECKSUM_PARTIAL &&
+ skb_checksum_start(skb) < skb->data)
+ goto free_skb;
} else {
if (skb_cow_head(skb, dev->needed_headroom))
goto free_skb;
diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c
index b0c244a..eccd789 100644
--- a/net/ipv4/ip_input.c
+++ b/net/ipv4/ip_input.c
@@ -309,14 +309,13 @@
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);
struct rtable *rt;
int err;
@@ -327,21 +326,29 @@
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;
+ switch (iph->protocol) {
+ case IPPROTO_TCP:
+ if (READ_ONCE(net->ipv4.sysctl_tcp_early_demux)) {
+ tcp_v4_early_demux(skb);
- 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);
+ /* 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;
}
}
@@ -354,6 +361,11 @@
iph->tos, dev);
if (unlikely(err))
goto drop_error;
+ } else {
+ struct in_device *in_dev = __in_dev_get_rcu(dev);
+
+ if (in_dev && IN_DEV_ORCONF(in_dev, NOPOLICY))
+ IPCB(skb)->flags |= IPSKB_NOPOLICY;
}
#ifdef CONFIG_IP_ROUTE_CLASSID
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 5e48b3d..0dbf950 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -1712,7 +1712,7 @@
daddr, saddr,
tcp_hdr(skb)->source, tcp_hdr(skb)->dest,
arg->uid);
- security_skb_classify_flow(skb, flowi4_to_flowi(&fl4));
+ security_skb_classify_flow(skb, flowi4_to_flowi_common(&fl4));
rt = ip_route_output_key(net, &fl4);
if (IS_ERR(rt))
return;
@@ -1721,7 +1721,7 @@
sk->sk_protocol = ip_hdr(skb)->protocol;
sk->sk_bound_dev_if = arg->bound_dev_if;
- sk->sk_sndbuf = sysctl_wmem_default;
+ sk->sk_sndbuf = READ_ONCE(sysctl_wmem_default);
ipc.sockc.mark = fl4.flowi4_mark;
err = ip_append_data(sk, &fl4, ip_reply_glue_bits, arg->iov->iov_base,
len, 0, &ipc, &rt, MSG_DONTWAIT);
diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c
index ec60367..4cc39c6 100644
--- a/net/ipv4/ip_sockglue.c
+++ b/net/ipv4/ip_sockglue.c
@@ -773,7 +773,7 @@
if (optlen < GROUP_FILTER_SIZE(0))
return -EINVAL;
- if (optlen > sysctl_optmem_max)
+ if (optlen > READ_ONCE(sysctl_optmem_max))
return -ENOBUFS;
gsf = memdup_sockptr(optval, optlen);
@@ -783,7 +783,7 @@
/* 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;
@@ -808,7 +808,7 @@
if (optlen < size0)
return -EINVAL;
- if (optlen > sysctl_optmem_max - 4)
+ if (optlen > READ_ONCE(sysctl_optmem_max) - 4)
return -ENOBUFS;
p = kmalloc(optlen + 4, GFP_KERNEL);
@@ -832,7 +832,7 @@
/* 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);
@@ -1231,7 +1231,7 @@
if (optlen < IP_MSFILTER_SIZE(0))
goto e_inval;
- if (optlen > sysctl_optmem_max) {
+ if (optlen > READ_ONCE(sysctl_optmem_max)) {
err = -ENOBUFS;
break;
}
@@ -1242,7 +1242,7 @@
}
/* 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;
diff --git a/net/ipv4/ip_tunnel_core.c b/net/ipv4/ip_tunnel_core.c
index e25be2d..4b74c67 100644
--- a/net/ipv4/ip_tunnel_core.c
+++ b/net/ipv4/ip_tunnel_core.c
@@ -410,7 +410,7 @@
u32 mtu = dst_mtu(encap_dst) - headroom;
if ((skb_is_gso(skb) && skb_gso_validate_network_len(skb, mtu)) ||
- (!skb_is_gso(skb) && (skb->len - skb_mac_header_len(skb)) <= mtu))
+ (!skb_is_gso(skb) && (skb->len - skb_network_offset(skb)) <= mtu))
return 0;
skb_dst_update_pmtu_no_confirm(skb, mtu);
diff --git a/net/ipv4/netfilter/ipt_CLUSTERIP.c b/net/ipv4/netfilter/ipt_CLUSTERIP.c
index 1088564..77e3b67 100644
--- a/net/ipv4/netfilter/ipt_CLUSTERIP.c
+++ b/net/ipv4/netfilter/ipt_CLUSTERIP.c
@@ -424,7 +424,7 @@
switch (ctinfo) {
case IP_CT_NEW:
- ct->mark = hash;
+ WRITE_ONCE(ct->mark, hash);
break;
case IP_CT_RELATED:
case IP_CT_RELATED_REPLY:
@@ -441,7 +441,7 @@
#ifdef DEBUG
nf_ct_dump_tuple_ip(&ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple);
#endif
- pr_debug("hash=%u ct_hash=%u ", hash, ct->mark);
+ pr_debug("hash=%u ct_hash=%u ", hash, READ_ONCE(ct->mark));
if (!clusterip_responsible(cipinfo->config, hash)) {
pr_debug("not responsible\n");
return NF_DROP;
diff --git a/net/ipv4/netfilter/nft_dup_ipv4.c b/net/ipv4/netfilter/nft_dup_ipv4.c
index bcdb37f..aeb6317 100644
--- a/net/ipv4/netfilter/nft_dup_ipv4.c
+++ b/net/ipv4/netfilter/nft_dup_ipv4.c
@@ -13,8 +13,8 @@
#include <net/netfilter/ipv4/nf_dup_ipv4.h>
struct nft_dup_ipv4 {
- enum nft_registers sreg_addr:8;
- enum nft_registers sreg_dev:8;
+ u8 sreg_addr;
+ u8 sreg_dev;
};
static void nft_dup_ipv4_eval(const struct nft_expr *expr,
@@ -40,16 +40,16 @@
if (tb[NFTA_DUP_SREG_ADDR] == NULL)
return -EINVAL;
- priv->sreg_addr = nft_parse_register(tb[NFTA_DUP_SREG_ADDR]);
- err = nft_validate_register_load(priv->sreg_addr, sizeof(struct in_addr));
+ err = nft_parse_register_load(tb[NFTA_DUP_SREG_ADDR], &priv->sreg_addr,
+ sizeof(struct in_addr));
if (err < 0)
return err;
- if (tb[NFTA_DUP_SREG_DEV] != NULL) {
- priv->sreg_dev = nft_parse_register(tb[NFTA_DUP_SREG_DEV]);
- return nft_validate_register_load(priv->sreg_dev, sizeof(int));
- }
- return 0;
+ if (tb[NFTA_DUP_SREG_DEV])
+ err = nft_parse_register_load(tb[NFTA_DUP_SREG_DEV],
+ &priv->sreg_dev, sizeof(int));
+
+ return err;
}
static int nft_dup_ipv4_dump(struct sk_buff *skb, const struct nft_expr *expr)
diff --git a/net/ipv4/netfilter/nft_fib_ipv4.c b/net/ipv4/netfilter/nft_fib_ipv4.c
index 03df986..9e6f0f1 100644
--- a/net/ipv4/netfilter/nft_fib_ipv4.c
+++ b/net/ipv4/netfilter/nft_fib_ipv4.c
@@ -83,6 +83,9 @@
else
oif = NULL;
+ if (priv->flags & NFTA_FIB_F_IIF)
+ fl4.flowi4_oif = l3mdev_master_ifindex_rcu(oif);
+
if (nft_hook(pkt) == NF_INET_PRE_ROUTING &&
nft_fib_is_loopback(pkt->skb, nft_in(pkt))) {
nft_fib_store_result(dest, priv, nft_in(pkt));
diff --git a/net/ipv4/nexthop.c b/net/ipv4/nexthop.c
index 8bd3f5e..7a0102a 100644
--- a/net/ipv4/nexthop.c
+++ b/net/ipv4/nexthop.c
@@ -882,7 +882,7 @@
/* __ip6_del_rt does a release, so do a hold here */
fib6_info_hold(f6i);
ipv6_stub->ip6_del_rt(net, f6i,
- !net->ipv4.sysctl_nexthop_compat_mode);
+ !READ_ONCE(net->ipv4.sysctl_nexthop_compat_mode));
}
}
@@ -1194,7 +1194,8 @@
if (!rc) {
nh_base_seq_inc(net);
nexthop_notify(RTM_NEWNEXTHOP, new_nh, &cfg->nlinfo);
- if (replace_notify && net->ipv4.sysctl_nexthop_compat_mode)
+ if (replace_notify &&
+ READ_ONCE(net->ipv4.sysctl_nexthop_compat_mode))
nexthop_replace_notify(net, new_nh, &cfg->nlinfo);
}
@@ -1345,7 +1346,7 @@
if (!err) {
nh->nh_flags = fib_nh->fib_nh_flags;
fib_info_update_nhc_saddr(net, &fib_nh->nh_common,
- fib_nh->fib_nh_scope);
+ !fib_nh->fib_nh_scope ? 0 : fib_nh->fib_nh_scope - 1);
} else {
fib_nh_release(net, fib_nh);
}
diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c
index e60ca03..1bad851 100644
--- a/net/ipv4/ping.c
+++ b/net/ipv4/ping.c
@@ -305,6 +305,7 @@
struct net *net = sock_net(sk);
if (sk->sk_family == AF_INET) {
struct sockaddr_in *addr = (struct sockaddr_in *) uaddr;
+ u32 tb_id = RT_TABLE_LOCAL;
int chk_addr_ret;
if (addr_len < sizeof(*addr))
@@ -320,8 +321,10 @@
if (addr->sin_addr.s_addr == htonl(INADDR_ANY))
chk_addr_ret = RTN_LOCAL;
- else
- chk_addr_ret = inet_addr_type(net, addr->sin_addr.s_addr);
+ else {
+ tb_id = l3mdev_fib_table_by_index(net, sk->sk_bound_dev_if) ? : tb_id;
+ chk_addr_ret = inet_addr_type_table(net, addr->sin_addr.s_addr, tb_id);
+ }
if ((!inet_can_nonlocal_bind(net, isk) &&
chk_addr_ret != RTN_LOCAL) ||
@@ -359,6 +362,14 @@
return -ENODEV;
}
}
+
+ if (!dev && sk->sk_bound_dev_if) {
+ dev = dev_get_by_index_rcu(net, sk->sk_bound_dev_if);
+ if (!dev) {
+ rcu_read_unlock();
+ return -ENODEV;
+ }
+ }
has_addr = pingv6_ops.ipv6_chk_addr(net, &addr->sin6_addr, dev,
scoped);
rcu_read_unlock();
@@ -785,7 +796,7 @@
fl4.fl4_icmp_type = user_icmph.type;
fl4.fl4_icmp_code = user_icmph.code;
- security_sk_classify_flow(sk, flowi4_to_flowi(&fl4));
+ security_sk_classify_flow(sk, flowi4_to_flowi_common(&fl4));
rt = ip_route_output_flow(net, &fl4, sk);
if (IS_ERR(rt)) {
err = PTR_ERR(rt);
diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c
index 5d95f80..4899ebe 100644
--- a/net/ipv4/raw.c
+++ b/net/ipv4/raw.c
@@ -640,7 +640,7 @@
goto done;
}
- security_sk_classify_flow(sk, flowi4_to_flowi(&fl4));
+ security_sk_classify_flow(sk, flowi4_to_flowi_common(&fl4));
rt = ip_route_output_flow(net, &fl4, sk);
if (IS_ERR(rt)) {
err = PTR_ERR(rt);
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index ce787c3..3746476 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -529,6 +529,15 @@
}
EXPORT_SYMBOL(__ip_select_ident);
+static void ip_rt_fix_tos(struct flowi4 *fl4)
+{
+ __u8 tos = RT_FL_TOS(fl4);
+
+ fl4->flowi4_tos = tos & IPTOS_RT_MASK;
+ fl4->flowi4_scope = tos & RTO_ONLINK ?
+ RT_SCOPE_LINK : RT_SCOPE_UNIVERSE;
+}
+
static void __build_flow_key(const struct net *net, struct flowi4 *fl4,
const struct sock *sk,
const struct iphdr *iph,
@@ -853,6 +862,7 @@
rt = (struct rtable *) dst;
__build_flow_key(net, &fl4, sk, iph, oif, tos, prot, mark, 0);
+ ip_rt_fix_tos(&fl4);
__ip_do_redirect(rt, skb, &fl4, true);
}
@@ -1077,6 +1087,7 @@
struct flowi4 fl4;
ip_rt_build_flow_key(&fl4, sk, skb);
+ ip_rt_fix_tos(&fl4);
/* Don't make lookup fail for bridged encapsulations */
if (skb && netif_is_any_bridge_port(skb->dev))
@@ -1151,6 +1162,8 @@
goto out;
new = true;
+ } else {
+ ip_rt_fix_tos(&fl4);
}
__ip_rt_update_pmtu((struct rtable *)xfrm_dst_path(&rt->dst), &fl4, mtu);
@@ -1429,7 +1442,7 @@
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;
@@ -1752,6 +1765,7 @@
struct in_device *in_dev = __in_dev_get_rcu(dev);
unsigned int flags = RTCF_MULTICAST;
struct rtable *rth;
+ bool no_policy;
u32 itag = 0;
int err;
@@ -1762,8 +1776,12 @@
if (our)
flags |= RTCF_LOCAL;
+ no_policy = IN_DEV_ORCONF(in_dev, NOPOLICY);
+ if (no_policy)
+ IPCB(skb)->flags |= IPSKB_NOPOLICY;
+
rth = rt_dst_alloc(dev_net(dev)->loopback_dev, flags, RTN_MULTICAST,
- IN_DEV_CONF_GET(in_dev, NOPOLICY), false);
+ no_policy, false);
if (!rth)
return -ENOBUFS;
@@ -1779,6 +1797,7 @@
#endif
RT_CACHE_STAT_INC(in_slow_mc);
+ skb_dst_drop(skb);
skb_dst_set(skb, &rth->dst);
return 0;
}
@@ -1821,7 +1840,7 @@
struct rtable *rth;
int err;
struct in_device *out_dev;
- bool do_cache;
+ bool do_cache, no_policy;
u32 itag = 0;
/* get a working reference to the output device */
@@ -1866,6 +1885,10 @@
}
}
+ no_policy = IN_DEV_ORCONF(in_dev, NOPOLICY);
+ if (no_policy)
+ IPCB(skb)->flags |= IPSKB_NOPOLICY;
+
fnhe = find_exception(nhc, daddr);
if (do_cache) {
if (fnhe)
@@ -1878,9 +1901,8 @@
}
}
- rth = rt_dst_alloc(out_dev->dev, 0, res->type,
- IN_DEV_CONF_GET(in_dev, NOPOLICY),
- IN_DEV_CONF_GET(out_dev, NOXFRM));
+ rth = rt_dst_alloc(out_dev->dev, 0, res->type, no_policy,
+ IN_DEV_ORCONF(out_dev, NOXFRM));
if (!rth) {
err = -ENOBUFS;
goto cleanup;
@@ -2131,6 +2153,7 @@
struct rtable *rth;
struct flowi4 fl4;
bool do_cache = true;
+ bool no_policy;
/* IP on this device is disabled. */
@@ -2248,6 +2271,10 @@
RT_CACHE_STAT_INC(in_brd);
local_input:
+ no_policy = IN_DEV_ORCONF(in_dev, NOPOLICY);
+ if (no_policy)
+ IPCB(skb)->flags |= IPSKB_NOPOLICY;
+
do_cache &= res->fi && !itag;
if (do_cache) {
struct fib_nh_common *nhc = FIB_RES_NHC(*res);
@@ -2262,7 +2289,7 @@
rth = rt_dst_alloc(ip_rt_get_dev(net, res),
flags | RTCF_LOCAL, res->type,
- IN_DEV_CONF_GET(in_dev, NOPOLICY), false);
+ no_policy, false);
if (!rth)
goto e_nobufs;
@@ -2485,8 +2512,8 @@
add:
rth = rt_dst_alloc(dev_out, flags, type,
- IN_DEV_CONF_GET(in_dev, NOPOLICY),
- IN_DEV_CONF_GET(in_dev, NOXFRM));
+ IN_DEV_ORCONF(in_dev, NOPOLICY),
+ IN_DEV_ORCONF(in_dev, NOXFRM));
if (!rth)
return ERR_PTR(-ENOBUFS);
@@ -2524,7 +2551,6 @@
struct rtable *ip_route_output_key_hash(struct net *net, struct flowi4 *fl4,
const struct sk_buff *skb)
{
- __u8 tos = RT_FL_TOS(fl4);
struct fib_result res = {
.type = RTN_UNSPEC,
.fi = NULL,
@@ -2534,9 +2560,7 @@
struct rtable *rth;
fl4->flowi4_iif = LOOPBACK_IFINDEX;
- fl4->flowi4_tos = tos & IPTOS_RT_MASK;
- fl4->flowi4_scope = ((tos & RTO_ONLINK) ?
- RT_SCOPE_LINK : RT_SCOPE_UNIVERSE);
+ ip_rt_fix_tos(fl4);
rcu_read_lock();
rth = ip_route_output_key_hash_rcu(net, fl4, &res, skb);
diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c
index 00dc3f9..41afc91 100644
--- a/net/ipv4/syncookies.c
+++ b/net/ipv4/syncookies.c
@@ -249,12 +249,12 @@
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)
@@ -263,7 +263,7 @@
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);
@@ -283,6 +283,7 @@
EXPORT_SYMBOL(cookie_ecn_ok);
struct request_sock *cookie_tcp_reqsk_alloc(const struct request_sock_ops *ops,
+ const struct tcp_request_sock_ops *af_ops,
struct sock *sk,
struct sk_buff *skb)
{
@@ -299,6 +300,10 @@
return NULL;
treq = tcp_rsk(req);
+
+ /* treq->af_specific might be used to perform TCP_MD5 lookup */
+ treq->af_specific = af_ops;
+
treq->syn_tos = TCP_SKB_CB(skb)->ip_dsfield;
#if IS_ENABLED(CONFIG_MPTCP)
treq->is_mptcp = sk_is_mptcp(sk);
@@ -337,7 +342,8 @@
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))
@@ -366,7 +372,8 @@
goto out;
ret = NULL;
- req = cookie_tcp_reqsk_alloc(&tcp_request_sock_ops, sk, skb);
+ req = cookie_tcp_reqsk_alloc(&tcp_request_sock_ops,
+ &tcp_request_sock_ipv4_ops, sk, skb);
if (!req)
goto out;
@@ -418,7 +425,7 @@
inet_sk_flowi_flags(sk),
opt->srr ? opt->faddr : ireq->ir_rmt_addr,
ireq->ir_loc_addr, th->source, th->dest, sk->sk_uid);
- security_req_classify_flow(req, flowi4_to_flowi(&fl4));
+ security_req_classify_flow(req, flowi4_to_flowi_common(&fl4));
rt = ip_route_output_key(sock_net(sk), &fl4);
if (IS_ERR(rt)) {
reqsk_free(req);
diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index 0882980..439970e 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -95,7 +95,7 @@
* 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);
@@ -121,7 +121,7 @@
.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);
@@ -133,7 +133,7 @@
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;
@@ -361,61 +361,6 @@
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_dointvec(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_dointvec(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)
@@ -685,14 +630,14 @@
.data = &init_net.ipv4.sysctl_udp_early_demux,
.maxlen = sizeof(int),
.mode = 0644,
- .proc_handler = proc_udp_early_demux
+ .proc_handler = proc_douintvec_minmax,
},
{
.procname = "tcp_early_demux",
.data = &init_net.ipv4.sysctl_tcp_early_demux,
.maxlen = sizeof(int),
.mode = 0644,
- .proc_handler = proc_tcp_early_demux
+ .proc_handler = proc_douintvec_minmax,
},
{
.procname = "nexthop_compat_mode",
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index a3ec2a0..cc588bc 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -440,7 +440,7 @@
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;
@@ -451,8 +451,8 @@
icsk->icsk_sync_mss = tcp_sync_mss;
- WRITE_ONCE(sk->sk_sndbuf, sock_net(sk)->ipv4.sysctl_tcp_wmem[1]);
- WRITE_ONCE(sk->sk_rcvbuf, sock_net(sk)->ipv4.sysctl_tcp_rmem[1]);
+ WRITE_ONCE(sk->sk_sndbuf, READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_wmem[1]));
+ WRITE_ONCE(sk->sk_rcvbuf, READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_rmem[1]));
sk_sockets_allocated_inc(sk);
sk->sk_route_forced_caps = NETIF_F_GSO;
@@ -698,7 +698,7 @@
int size_goal)
{
return skb->len < size_goal &&
- sock_net(sk)->ipv4.sysctl_tcp_autocorking &&
+ READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_autocorking) &&
!tcp_rtx_queue_empty(sk) &&
refcount_read(&sk->sk_wmem_alloc) > skb->truesize;
}
@@ -1148,7 +1148,8 @@
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;
@@ -1710,7 +1711,7 @@
if (sk->sk_userlocks & SOCK_RCVBUF_LOCK)
cap = sk->sk_rcvbuf >> 1;
else
- cap = sock_net(sk)->ipv4.sysctl_tcp_rmem[2] >> 1;
+ cap = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_rmem[2]) >> 1;
val = min(val, cap);
WRITE_ONCE(sk->sk_rcvlowat, val ? : 1);
@@ -2490,7 +2491,8 @@
static bool tcp_too_many_orphans(int shift)
{
- return READ_ONCE(tcp_orphan_cache) << shift > sysctl_tcp_max_orphans;
+ return READ_ONCE(tcp_orphan_cache) << shift >
+ READ_ONCE(sysctl_tcp_max_orphans);
}
bool tcp_check_oom(struct sock *sk, int shift)
@@ -2794,6 +2796,8 @@
tp->snd_ssthresh = TCP_INFINITE_SSTHRESH;
tp->snd_cwnd = TCP_INIT_CWND;
tp->snd_cwnd_cnt = 0;
+ tp->is_cwnd_limited = 0;
+ tp->max_packets_out = 0;
tp->window_clamp = 0;
tp->delivered = 0;
tp->delivered_ce = 0;
@@ -2812,8 +2816,7 @@
icsk->icsk_ack.rcv_mss = TCP_MIN_MSS;
memset(&tp->rx_opt, 0, sizeof(tp->rx_opt));
__sk_dst_reset(sk);
- dst_release(sk->sk_rx_dst);
- sk->sk_rx_dst = NULL;
+ dst_release(xchg((__force struct dst_entry **)&sk->sk_rx_dst, NULL));
tcp_saved_syn_free(tp);
tp->compressed_ack = 0;
tp->segs_in = 0;
@@ -3288,7 +3291,7 @@
case TCP_REPAIR_OPTIONS:
if (!tp->repair)
err = -EINVAL;
- else if (sk->sk_state == TCP_ESTABLISHED)
+ else if (sk->sk_state == TCP_ESTABLISHED && !tp->bytes_sent)
err = tcp_repair_options_est(sk, optval, optlen);
else
err = -EPERM;
@@ -3389,7 +3392,8 @@
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
@@ -3726,7 +3730,7 @@
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,
@@ -4038,12 +4042,16 @@
* to memory. See smp_rmb() in tcp_get_md5sig_pool()
*/
smp_wmb();
- tcp_md5sig_pool_populated = true;
+ /* Paired with READ_ONCE() from tcp_alloc_md5sig_pool()
+ * and tcp_get_md5sig_pool().
+ */
+ WRITE_ONCE(tcp_md5sig_pool_populated, true);
}
bool tcp_alloc_md5sig_pool(void)
{
- if (unlikely(!tcp_md5sig_pool_populated)) {
+ /* Paired with WRITE_ONCE() from __tcp_alloc_md5sig_pool() */
+ if (unlikely(!READ_ONCE(tcp_md5sig_pool_populated))) {
mutex_lock(&tcp_md5sig_mutex);
if (!tcp_md5sig_pool_populated) {
@@ -4054,7 +4062,8 @@
mutex_unlock(&tcp_md5sig_mutex);
}
- return tcp_md5sig_pool_populated;
+ /* Paired with WRITE_ONCE() from __tcp_alloc_md5sig_pool() */
+ return READ_ONCE(tcp_md5sig_pool_populated);
}
EXPORT_SYMBOL(tcp_alloc_md5sig_pool);
@@ -4070,7 +4079,8 @@
{
local_bh_disable();
- if (tcp_md5sig_pool_populated) {
+ /* Paired with WRITE_ONCE() from __tcp_alloc_md5sig_pool() */
+ if (READ_ONCE(tcp_md5sig_pool_populated)) {
/* coupled with smp_wmb() in __tcp_alloc_md5sig_pool() */
smp_rmb();
return this_cpu_ptr(&tcp_md5sig_pool);
diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c
index 6b745ce..809ee0f 100644
--- a/net/ipv4/tcp_bpf.c
+++ b/net/ipv4/tcp_bpf.c
@@ -218,10 +218,9 @@
struct sk_psock *psock = sk_psock_get(sk);
int ret;
- if (unlikely(!psock)) {
- sk_msg_free(sk, msg);
- return 0;
- }
+ if (unlikely(!psock))
+ return -EPIPE;
+
ret = ingress ? bpf_tcp_ingress(sk, psock, msg, bytes, flags) :
tcp_bpf_push_locked(sk, msg, bytes, flags, false);
sk_psock_put(sk, psock);
@@ -316,7 +315,7 @@
{
bool cork = false, enospc = sk_msg_full(msg);
struct sock *sk_redir;
- u32 tosend, delta = 0;
+ u32 tosend, origsize, sent, delta = 0;
u32 eval = __SK_NONE;
int ret;
@@ -374,7 +373,9 @@
sk_msg_return(sk, msg, tosend);
release_sock(sk);
+ origsize = msg->sg.size;
ret = tcp_bpf_sendmsg_redir(sk_redir, msg, tosend, flags);
+ sent = origsize - msg->sg.size;
if (eval == __SK_REDIRECT)
sock_put(sk_redir);
@@ -411,8 +412,11 @@
}
if (msg &&
msg->sg.data[msg->sg.start].page_link &&
- msg->sg.data[msg->sg.start].length)
+ msg->sg.data[msg->sg.start].length) {
+ if (eval == __SK_REDIRECT)
+ sk_mem_charge(sk, tosend - sent);
goto more_data;
+ }
}
return ret;
}
diff --git a/net/ipv4/tcp_cdg.c b/net/ipv4/tcp_cdg.c
index 709d238..56dede4 100644
--- a/net/ipv4/tcp_cdg.c
+++ b/net/ipv4/tcp_cdg.c
@@ -375,6 +375,7 @@
struct cdg *ca = inet_csk_ca(sk);
struct tcp_sock *tp = tcp_sk(sk);
+ ca->gradients = NULL;
/* We silently fall back to window = 1 if allocation fails. */
if (window > 1)
ca->gradients = kcalloc(window, sizeof(ca->gradients[0]),
@@ -388,6 +389,7 @@
struct cdg *ca = inet_csk_ca(sk);
kfree(ca->gradients);
+ ca->gradients = NULL;
}
static struct tcp_congestion_ops tcp_cdg __read_mostly = {
diff --git a/net/ipv4/tcp_fastopen.c b/net/ipv4/tcp_fastopen.c
index 1071119..39fb037 100644
--- a/net/ipv4/tcp_fastopen.c
+++ b/net/ipv4/tcp_fastopen.c
@@ -349,7 +349,7 @@
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));
}
@@ -364,7 +364,7 @@
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;
@@ -506,7 +506,7 @@
{
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() */
@@ -527,7 +527,8 @@
*/
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 12dd08a..541758c 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -425,7 +425,7 @@
if (sk->sk_sndbuf < sndmem)
WRITE_ONCE(sk->sk_sndbuf,
- min(sndmem, sock_net(sk)->ipv4.sysctl_tcp_wmem[2]));
+ min(sndmem, READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_wmem[2])));
}
/* 2. Tuning advertised window (window_clamp, rcv_ssthresh)
@@ -454,12 +454,13 @@
*/
/* Slow part of check#2. */
-static int __tcp_grow_window(const struct sock *sk, const struct sk_buff *skb)
+static int __tcp_grow_window(const struct sock *sk, const struct sk_buff *skb,
+ unsigned int skbtruesize)
{
struct tcp_sock *tp = tcp_sk(sk);
/* Optimize this! */
- int truesize = tcp_win_from_space(sk, skb->truesize) >> 1;
- int window = tcp_win_from_space(sk, sock_net(sk)->ipv4.sysctl_tcp_rmem[2]) >> 1;
+ int truesize = tcp_win_from_space(sk, skbtruesize) >> 1;
+ int window = tcp_win_from_space(sk, READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_rmem[2])) >> 1;
while (tp->rcv_ssthresh <= window) {
if (truesize <= skb->len)
@@ -471,7 +472,27 @@
return 0;
}
-static void tcp_grow_window(struct sock *sk, const struct sk_buff *skb)
+/* Even if skb appears to have a bad len/truesize ratio, TCP coalescing
+ * can play nice with us, as sk_buff and skb->head might be either
+ * freed or shared with up to MAX_SKB_FRAGS segments.
+ * Only give a boost to drivers using page frag(s) to hold the frame(s),
+ * and if no payload was pulled in skb->head before reaching us.
+ */
+static u32 truesize_adjust(bool adjust, const struct sk_buff *skb)
+{
+ u32 truesize = skb->truesize;
+
+ if (adjust && !skb_headlen(skb)) {
+ truesize -= SKB_TRUESIZE(skb_end_offset(skb));
+ /* paranoid check, some drivers might be buggy */
+ if (unlikely((int)truesize < (int)skb->len))
+ truesize = skb->truesize;
+ }
+ return truesize;
+}
+
+static void tcp_grow_window(struct sock *sk, const struct sk_buff *skb,
+ bool adjust)
{
struct tcp_sock *tp = tcp_sk(sk);
int room;
@@ -480,15 +501,16 @@
/* Check #1 */
if (room > 0 && !tcp_under_memory_pressure(sk)) {
+ unsigned int truesize = truesize_adjust(adjust, skb);
int incr;
/* Check #2. Increase window, if skb with such overhead
* will fit to rcvbuf in future.
*/
- if (tcp_win_from_space(sk, skb->truesize) <= skb->len)
+ if (tcp_win_from_space(sk, truesize) <= skb->len)
incr = 2 * tp->advmss;
else
- incr = __tcp_grow_window(sk, skb);
+ incr = __tcp_grow_window(sk, skb, truesize);
if (incr) {
incr = max_t(int, incr, 2 * skb->len);
@@ -503,7 +525,7 @@
*/
static void tcp_init_buffer_space(struct sock *sk)
{
- int tcp_app_win = sock_net(sk)->ipv4.sysctl_tcp_app_win;
+ int tcp_app_win = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_app_win);
struct tcp_sock *tp = tcp_sk(sk);
int maxwin;
@@ -543,16 +565,17 @@
struct tcp_sock *tp = tcp_sk(sk);
struct inet_connection_sock *icsk = inet_csk(sk);
struct net *net = sock_net(sk);
+ int rmem2;
icsk->icsk_ack.quick = 0;
+ rmem2 = READ_ONCE(net->ipv4.sysctl_tcp_rmem[2]);
- if (sk->sk_rcvbuf < net->ipv4.sysctl_tcp_rmem[2] &&
+ if (sk->sk_rcvbuf < rmem2 &&
!(sk->sk_userlocks & SOCK_RCVBUF_LOCK) &&
!tcp_under_memory_pressure(sk) &&
sk_memory_allocated(sk) < sk_prot_mem_limits(sk, 0)) {
WRITE_ONCE(sk->sk_rcvbuf,
- min(atomic_read(&sk->sk_rmem_alloc),
- net->ipv4.sysctl_tcp_rmem[2]));
+ min(atomic_read(&sk->sk_rmem_alloc), rmem2));
}
if (atomic_read(&sk->sk_rmem_alloc) > sk->sk_rcvbuf)
tp->rcv_ssthresh = min(tp->window_clamp, 2U * tp->advmss);
@@ -693,7 +716,7 @@
* <prev RTT . ><current RTT .. ><next RTT .... >
*/
- if (sock_net(sk)->ipv4.sysctl_tcp_moderate_rcvbuf &&
+ if (READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_moderate_rcvbuf) &&
!(sk->sk_userlocks & SOCK_RCVBUF_LOCK)) {
int rcvmem, rcvbuf;
u64 rcvwin, grow;
@@ -714,7 +737,7 @@
do_div(rcvwin, tp->advmss);
rcvbuf = min_t(u64, rcvwin * rcvmem,
- sock_net(sk)->ipv4.sysctl_tcp_rmem[2]);
+ READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_rmem[2]));
if (rcvbuf > sk->sk_rcvbuf) {
WRITE_ONCE(sk->sk_rcvbuf, rcvbuf);
@@ -782,7 +805,7 @@
tcp_ecn_check_ce(sk, skb);
if (skb->len >= 128)
- tcp_grow_window(sk, skb);
+ tcp_grow_window(sk, skb, true);
}
/* Called to compute a smoothed rtt estimate. The data fed to this
@@ -1011,7 +1034,7 @@
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) */
@@ -1990,7 +2013,7 @@
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);
}
@@ -2055,7 +2078,8 @@
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
@@ -2099,6 +2123,7 @@
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);
@@ -2119,10 +2144,12 @@
/* 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);
@@ -2131,7 +2158,7 @@
* loss recovery is underway except recurring timeout(s) on
* the same SND.UNA (sec 3.2). Disable F-RTO on path MTU probing
*/
- tp->frto = net->ipv4.sysctl_tcp_frto &&
+ tp->frto = READ_ONCE(net->ipv4.sysctl_tcp_frto) &&
(new_recovery || icsk->icsk_retransmits) &&
!inet_csk(sk)->icsk_mtup.probe_size;
}
@@ -2148,7 +2175,8 @@
*/
static bool tcp_check_sack_reneging(struct sock *sk, int flag)
{
- if (flag & FLAG_SACK_RENEGING) {
+ if (flag & FLAG_SACK_RENEGING &&
+ flag & FLAG_SND_UNA_ADVANCED) {
struct tcp_sock *tp = tcp_sk(sk);
unsigned long delay = max(usecs_to_jiffies(tp->srtt_us >> 4),
msecs_to_jiffies(10));
@@ -2469,6 +2497,21 @@
return tp->undo_marker && (!tp->undo_retrans || tcp_packet_delayed(tp));
}
+static bool tcp_is_non_sack_preventing_reopen(struct sock *sk)
+{
+ struct tcp_sock *tp = tcp_sk(sk);
+
+ if (tp->snd_una == tp->high_seq && tcp_is_reno(tp)) {
+ /* Hold old state until something *above* high_seq
+ * is ACKed. For Reno it is MUST to prevent false
+ * fast retransmits (RFC2582). SACK TCP is safe. */
+ if (!tcp_any_retrans_done(sk))
+ tp->retrans_stamp = 0;
+ return true;
+ }
+ return false;
+}
+
/* People celebrate: "We love our President!" */
static bool tcp_try_undo_recovery(struct sock *sk)
{
@@ -2491,14 +2534,8 @@
} else if (tp->rack.reo_wnd_persist) {
tp->rack.reo_wnd_persist--;
}
- if (tp->snd_una == tp->high_seq && tcp_is_reno(tp)) {
- /* Hold old state until something *above* high_seq
- * is ACKed. For Reno it is MUST to prevent false
- * fast retransmits (RFC2582). SACK TCP is safe. */
- if (!tcp_any_retrans_done(sk))
- tp->retrans_stamp = 0;
+ if (tcp_is_non_sack_preventing_reopen(sk))
return true;
- }
tcp_set_ca_state(sk, TCP_CA_Open);
tp->is_sack_reneg = 0;
return false;
@@ -2534,6 +2571,8 @@
NET_INC_STATS(sock_net(sk),
LINUX_MIB_TCPSPURIOUSRTOS);
inet_csk(sk)->icsk_retransmits = 0;
+ if (tcp_is_non_sack_preventing_reopen(sk))
+ return true;
if (frto_undo || tcp_is_sack(tp)) {
tcp_set_ca_state(sk, TCP_CA_Open);
tp->is_sack_reneg = 0;
@@ -2667,12 +2706,15 @@
{
struct tcp_sock *tp = tcp_sk(sk);
struct inet_connection_sock *icsk = inet_csk(sk);
+ u64 val;
- /* FIXME: breaks with very large cwnd */
tp->prior_ssthresh = tcp_current_ssthresh(sk);
- tp->snd_cwnd = tp->snd_cwnd *
- tcp_mss_to_mtu(sk, tp->mss_cache) /
- icsk->icsk_mtup.probe_size;
+
+ val = (u64)tp->snd_cwnd * tcp_mss_to_mtu(sk, tp->mss_cache);
+ do_div(val, icsk->icsk_mtup.probe_size);
+ WARN_ON_ONCE((u32)val != val);
+ tp->snd_cwnd = max_t(u32, 1U, val);
+
tp->snd_cwnd_cnt = 0;
tp->snd_cwnd_stamp = tcp_jiffies32;
tp->snd_ssthresh = tcp_current_ssthresh(sk);
@@ -2997,7 +3039,7 @@
static void tcp_update_rtt_min(struct sock *sk, u32 rtt_us, const int flag)
{
- u32 wlen = sock_net(sk)->ipv4.sysctl_tcp_min_rtt_wlen * HZ;
+ u32 wlen = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_min_rtt_wlen) * HZ;
struct tcp_sock *tp = tcp_sk(sk);
if ((flag & FLAG_ACK_MAYBE_DELAYED) && rtt_us > tcp_min_rtt(tp)) {
@@ -3408,7 +3450,8 @@
* 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;
@@ -3520,7 +3563,8 @@
if (*last_oow_ack_time) {
s32 elapsed = (s32)(tcp_jiffies32 - *last_oow_ack_time);
- if (0 <= elapsed && elapsed < net->ipv4.sysctl_tcp_invalid_ratelimit) {
+ if (0 <= elapsed &&
+ elapsed < READ_ONCE(net->ipv4.sysctl_tcp_invalid_ratelimit)) {
NET_INC_STATS(net, mib_idx);
return true; /* rate-limited: don't send yet! */
}
@@ -3567,11 +3611,11 @@
/* Then check host-wide RFC 5961 rate limit. */
now = jiffies / HZ;
- if (now != challenge_timestamp) {
- u32 ack_limit = net->ipv4.sysctl_tcp_challenge_ack_limit;
+ if (now != READ_ONCE(challenge_timestamp)) {
+ u32 ack_limit = READ_ONCE(net->ipv4.sysctl_tcp_challenge_ack_limit);
u32 half = (ack_limit + 1) >> 1;
- challenge_timestamp = now;
+ WRITE_ONCE(challenge_timestamp, now);
WRITE_ONCE(challenge_count, half + prandom_u32_max(ack_limit));
}
count = READ_ONCE(challenge_count);
@@ -3814,7 +3858,8 @@
tcp_process_tlp_ack(sk, ack, flag);
if (tcp_ack_is_dubious(sk, flag)) {
- if (!(flag & (FLAG_SND_UNA_ADVANCED | FLAG_NOT_DUP))) {
+ if (!(flag & (FLAG_SND_UNA_ADVANCED |
+ FLAG_NOT_DUP | FLAG_DSACKING_ACK))) {
num_dupack = 1;
/* Consider if pure acks were aggregated in tcp_add_backlog() */
if (!(flag & FLAG_DATA))
@@ -3999,7 +4044,7 @@
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) {
@@ -4015,7 +4060,7 @@
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);
@@ -4023,7 +4068,7 @@
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);
}
@@ -4358,7 +4403,7 @@
{
struct tcp_sock *tp = tcp_sk(sk);
- if (tcp_is_sack(tp) && sock_net(sk)->ipv4.sysctl_tcp_dsack) {
+ if (tcp_is_sack(tp) && READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_dsack)) {
int mib_idx;
if (before(seq, tp->rcv_nxt))
@@ -4405,7 +4450,7 @@
NET_INC_STATS(sock_net(sk), LINUX_MIB_DELAYEDACKLOST);
tcp_enter_quickack_mode(sk, TCP_MAX_QUICKACKS);
- if (tcp_is_sack(tp) && sock_net(sk)->ipv4.sysctl_tcp_dsack) {
+ if (tcp_is_sack(tp) && READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_dsack)) {
u32 end_seq = TCP_SKB_CB(skb)->end_seq;
tcp_rcv_spurious_retrans(sk, skb);
@@ -4751,7 +4796,7 @@
* and trigger fast retransmit.
*/
if (tcp_is_sack(tp))
- tcp_grow_window(sk, skb);
+ tcp_grow_window(sk, skb, true);
kfree_skb_partial(skb, fragstolen);
skb = NULL;
goto add_sack;
@@ -4839,7 +4884,7 @@
* and trigger fast retransmit.
*/
if (tcp_is_sack(tp))
- tcp_grow_window(sk, skb);
+ tcp_grow_window(sk, skb, false);
skb_condense(skb);
skb_set_owner_r(skb, sk);
}
@@ -5370,7 +5415,17 @@
sk->sk_write_space(sk);
}
-static void tcp_check_space(struct sock *sk)
+/* Caller made space either from:
+ * 1) Freeing skbs in rtx queues (after tp->snd_una has advanced)
+ * 2) Sent skbs from output queue (and thus advancing tp->snd_nxt)
+ *
+ * We might be able to generate EPOLLOUT to the application if:
+ * 1) Space consumed in output/rtx queues is below sk->sk_sndbuf/2
+ * 2) notsent amount (tp->write_seq - tp->snd_nxt) became
+ * small enough that tcp_stream_memory_free() decides it
+ * is time to generate EPOLLOUT.
+ */
+void tcp_check_space(struct sock *sk)
{
/* pairs with tcp_poll() */
smp_mb();
@@ -5420,7 +5475,7 @@
}
if (!tcp_is_sack(tp) ||
- tp->compressed_ack >= sock_net(sk)->ipv4.sysctl_tcp_comp_sack_nr)
+ tp->compressed_ack >= READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_comp_sack_nr))
goto send_now;
if (tp->compressed_ack_rcv_nxt != tp->rcv_nxt) {
@@ -5441,11 +5496,12 @@
if (tp->srtt_us && tp->srtt_us < rtt)
rtt = tp->srtt_us;
- delay = min_t(unsigned long, sock_net(sk)->ipv4.sysctl_tcp_comp_sack_delay_ns,
+ delay = min_t(unsigned long,
+ READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_comp_sack_delay_ns),
rtt * (NSEC_PER_USEC >> 3)/20);
sock_hold(sk);
hrtimer_start_range_ns(&tp->compressed_ack_timer, ns_to_ktime(delay),
- sock_net(sk)->ipv4.sysctl_tcp_comp_sack_slack_ns,
+ READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_comp_sack_slack_ns),
HRTIMER_MODE_REL_PINNED_SOFT);
}
@@ -5473,7 +5529,7 @@
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);
@@ -5722,7 +5778,7 @@
trace_tcp_probe(sk, skb);
tcp_mstamp_refresh(tp);
- if (unlikely(!sk->sk_rx_dst))
+ if (unlikely(!rcu_access_pointer(sk->sk_rx_dst)))
inet_csk(sk)->icsk_af_ops->sk_rx_dst_set(sk, skb);
/*
* Header prediction.
@@ -6669,11 +6725,14 @@
{
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);
@@ -6681,8 +6740,7 @@
#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);
@@ -6731,7 +6789,7 @@
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;
@@ -6765,13 +6823,15 @@
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;
@@ -6825,10 +6885,12 @@
goto drop_and_free;
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 017cd66..8bd7b1e 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -106,10 +106,10 @@
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
@@ -322,6 +322,8 @@
* if necessary.
*/
tcp_set_state(sk, TCP_CLOSE);
+ if (!(sk->sk_userlocks & SOCK_BINDADDR_LOCK))
+ inet_reset_saddr(sk);
ip_rt_put(rt);
sk->sk_route_caps = 0;
inet->inet_dport = 0;
@@ -983,7 +985,7 @@
if (skb) {
__tcp_v4_send_check(skb, ireq->ir_loc_addr, ireq->ir_rmt_addr);
- tos = sock_net(sk)->ipv4.sysctl_tcp_reflect_tos ?
+ tos = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_reflect_tos) ?
(tcp_rsk(req)->syn_tos & ~INET_ECN_MASK) |
(inet_sk(sk)->tos & INET_ECN_MASK) :
inet_sk(sk)->tos;
@@ -1558,7 +1560,7 @@
/* Set ToS of the new socket based upon the value of incoming SYN.
* ECT bits are set later in tcp_init_transfer().
*/
- if (sock_net(sk)->ipv4.sysctl_tcp_reflect_tos)
+ if (READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_reflect_tos))
newinet->tos = tcp_rsk(req)->syn_tos & ~INET_ECN_MASK;
if (!dst) {
@@ -1670,15 +1672,18 @@
struct sock *rsk;
if (sk->sk_state == TCP_ESTABLISHED) { /* Fast path */
- struct dst_entry *dst = sk->sk_rx_dst;
+ struct dst_entry *dst;
+
+ dst = rcu_dereference_protected(sk->sk_rx_dst,
+ lockdep_sock_is_held(sk));
sock_rps_save_rxhash(sk, skb);
sk_mark_napi_id(sk, skb);
if (dst) {
if (inet_sk(sk)->rx_dst_ifindex != skb->skb_iif ||
!dst->ops->check(dst, 0)) {
+ RCU_INIT_POINTER(sk->sk_rx_dst, NULL);
dst_release(dst);
- sk->sk_rx_dst = NULL;
}
}
tcp_rcv_established(sk, skb);
@@ -1753,7 +1758,7 @@
skb->sk = sk;
skb->destructor = sock_edemux;
if (sk_fullsock(sk)) {
- struct dst_entry *dst = READ_ONCE(sk->sk_rx_dst);
+ struct dst_entry *dst = rcu_dereference(sk->sk_rx_dst);
if (dst)
dst = dst_check(dst, 0);
@@ -1767,8 +1772,7 @@
bool tcp_add_backlog(struct sock *sk, struct sk_buff *skb)
{
- u32 limit = READ_ONCE(sk->sk_rcvbuf) + READ_ONCE(sk->sk_sndbuf);
- u32 tail_gso_size, tail_gso_segs;
+ u32 limit, tail_gso_size, tail_gso_segs;
struct skb_shared_info *shinfo;
const struct tcphdr *th;
struct tcphdr *thtail;
@@ -1871,11 +1875,13 @@
__skb_push(skb, hdrlen);
no_coalesce:
+ limit = (u32)READ_ONCE(sk->sk_rcvbuf) + (u32)(READ_ONCE(sk->sk_sndbuf) >> 1);
+
/* Only socket owner can try to collapse/prune rx queues
* to reduce memory overhead, so add a little headroom here.
* Few sockets backlog are possibly concurrently non empty.
*/
- limit += 64*1024;
+ limit += 64 * 1024;
if (unlikely(sk_add_backlog(sk, skb, limit))) {
bh_unlock_sock(sk);
@@ -1980,7 +1986,8 @@
struct sock *nsk;
sk = req->rsk_listener;
- if (unlikely(tcp_v4_inbound_md5_hash(sk, skb, dif, sdif))) {
+ if (unlikely(!xfrm4_policy_check(sk, XFRM_POLICY_IN, skb) ||
+ tcp_v4_inbound_md5_hash(sk, skb, dif, sdif))) {
sk_drops_add(sk, skb);
reqsk_put(req);
goto discard_it;
@@ -2019,6 +2026,7 @@
}
goto discard_and_relse;
}
+ nf_reset_ct(skb);
if (nsk == sk) {
reqsk_put(req);
tcp_v4_restore_cb(skb);
@@ -2160,7 +2168,7 @@
struct dst_entry *dst = skb_dst(skb);
if (dst && dst_hold_safe(dst)) {
- sk->sk_rx_dst = dst;
+ rcu_assign_pointer(sk->sk_rx_dst, dst);
inet_sk(sk)->rx_dst_ifindex = skb->skb_iif;
}
}
diff --git a/net/ipv4/tcp_metrics.c b/net/ipv4/tcp_metrics.c
index 6b27c48..f3ca6ee 100644
--- a/net/ipv4/tcp_metrics.c
+++ b/net/ipv4/tcp_metrics.c
@@ -329,7 +329,7 @@
int m;
sk_dst_confirm(sk);
- if (net->ipv4.sysctl_tcp_nometrics_save || !dst)
+ if (READ_ONCE(net->ipv4.sysctl_tcp_nometrics_save) || !dst)
return;
rcu_read_lock();
@@ -385,7 +385,7 @@
if (tcp_in_initial_slowstart(tp)) {
/* Slow start still did not finish. */
- if (!net->ipv4.sysctl_tcp_no_ssthresh_metrics_save &&
+ if (!READ_ONCE(net->ipv4.sysctl_tcp_no_ssthresh_metrics_save) &&
!tcp_metric_locked(tm, TCP_METRIC_SSTHRESH)) {
val = tcp_metric_get(tm, TCP_METRIC_SSTHRESH);
if (val && (tp->snd_cwnd >> 1) > val)
@@ -401,7 +401,7 @@
} else if (!tcp_in_slow_start(tp) &&
icsk->icsk_ca_state == TCP_CA_Open) {
/* Cong. avoidance phase, cwnd is reliable. */
- if (!net->ipv4.sysctl_tcp_no_ssthresh_metrics_save &&
+ if (!READ_ONCE(net->ipv4.sysctl_tcp_no_ssthresh_metrics_save) &&
!tcp_metric_locked(tm, TCP_METRIC_SSTHRESH))
tcp_metric_set(tm, TCP_METRIC_SSTHRESH,
max(tp->snd_cwnd >> 1, tp->snd_ssthresh));
@@ -418,7 +418,7 @@
tcp_metric_set(tm, TCP_METRIC_CWND,
(val + tp->snd_ssthresh) >> 1);
}
- if (!net->ipv4.sysctl_tcp_no_ssthresh_metrics_save &&
+ if (!READ_ONCE(net->ipv4.sysctl_tcp_no_ssthresh_metrics_save) &&
!tcp_metric_locked(tm, TCP_METRIC_SSTHRESH)) {
val = tcp_metric_get(tm, TCP_METRIC_SSTHRESH);
if (val && tp->snd_ssthresh > val)
@@ -428,7 +428,8 @@
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);
}
@@ -462,7 +463,7 @@
if (tcp_metric_locked(tm, TCP_METRIC_CWND))
tp->snd_cwnd_clamp = tcp_metric_get(tm, TCP_METRIC_CWND);
- val = net->ipv4.sysctl_tcp_no_ssthresh_metrics_save ?
+ val = READ_ONCE(net->ipv4.sysctl_tcp_no_ssthresh_metrics_save) ?
0 : tcp_metric_get(tm, TCP_METRIC_SSTHRESH);
if (val) {
tp->snd_ssthresh = val;
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index f0f67b2..e423123 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -180,7 +180,7 @@
* 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;
@@ -538,7 +538,7 @@
newtp->tsoffset = treq->ts_off;
#ifdef CONFIG_TCP_MD5SIG
newtp->md5sig_info = NULL; /*XXX*/
- if (newtp->af_specific->md5_lookup(sk, newsk))
+ if (treq->af_specific->req_md5_lookup(sk, req_to_sk(req)))
newtp->tcp_header_len += TCPOLEN_MD5SIG_ALIGNED;
#endif
if (skb->len >= TCP_MSS_DEFAULT + newtp->tcp_header_len)
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 19ef457..eefd032 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -82,6 +82,7 @@
NET_ADD_STATS(sock_net(sk), LINUX_MIB_TCPORIGDATASENT,
tcp_skb_pcount(skb));
+ tcp_check_space(sk);
}
/* SND.NXT, if window was not shrunk or the amount of shrunk was less than one
@@ -166,16 +167,13 @@
if (tcp_packets_in_flight(tp) == 0)
tcp_ca_event(sk, CA_EVENT_TX_START);
- /* If this is the first data packet sent in response to the
- * previous received data,
- * and it is a reply for ato after last received packet,
- * increase pingpong count.
- */
- if (before(tp->lsndtime, icsk->icsk_ack.lrcvtime) &&
- (u32)(now - icsk->icsk_ack.lrcvtime) < icsk->icsk_ack.ato)
- inet_csk_inc_pingpong_cnt(sk);
-
tp->lsndtime = now;
+
+ /* If it is a reply for ato after last received
+ * packet, enter pingpong mode.
+ */
+ if ((u32)(now - icsk->icsk_ack.lrcvtime) < icsk->icsk_ack.ato)
+ inet_csk_enter_pingpong_mode(sk);
}
/* Account for an ACK we sent. */
@@ -240,8 +238,8 @@
*rcv_wscale = 0;
if (wscale_ok) {
/* Set window scaling on max possible window */
- space = max_t(u32, space, sock_net(sk)->ipv4.sysctl_tcp_rmem[2]);
- space = max_t(u32, space, sysctl_rmem_max);
+ space = max_t(u32, space, READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_rmem[2]));
+ space = max_t(u32, space, READ_ONCE(sysctl_rmem_max));
space = min_t(u32, space, *window_clamp);
*rcv_wscale = clamp_t(int, ilog2(space) - 15,
0, TCP_MAX_WSCALE);
@@ -788,18 +786,18 @@
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 +1717,8 @@
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 +1761,10 @@
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;
@@ -1877,15 +1876,20 @@
const struct tcp_congestion_ops *ca_ops = inet_csk(sk)->icsk_ca_ops;
struct tcp_sock *tp = tcp_sk(sk);
- /* Track the maximum number of outstanding packets in each
- * window, and remember whether we were cwnd-limited then.
+ /* Track the strongest available signal of the degree to which the cwnd
+ * is fully utilized. If cwnd-limited then remember that fact for the
+ * current window. If not cwnd-limited then track the maximum number of
+ * outstanding packets in the current window. (If cwnd-limited then we
+ * chose to not update tp->max_packets_out to avoid an extra else
+ * clause with no functional impact.)
*/
- if (!before(tp->snd_una, tp->max_packets_seq) ||
- tp->packets_out > tp->max_packets_out ||
- is_cwnd_limited) {
- tp->max_packets_out = tp->packets_out;
- tp->max_packets_seq = tp->snd_nxt;
+ if (!before(tp->snd_una, tp->cwnd_usage_seq) ||
+ is_cwnd_limited ||
+ (!tp->is_cwnd_limited &&
+ tp->packets_out > tp->max_packets_out)) {
tp->is_cwnd_limited = is_cwnd_limited;
+ tp->max_packets_out = tp->packets_out;
+ tp->cwnd_usage_seq = tp->snd_nxt;
}
if (tcp_is_cwnd_limited(sk)) {
@@ -1897,7 +1901,7 @@
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);
@@ -1985,7 +1989,7 @@
min_tso = ca_ops->min_tso_segs ?
ca_ops->min_tso_segs(sk) :
- sock_net(sk)->ipv4.sysctl_tcp_min_tso_segs;
+ READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_min_tso_segs);
tso_segs = tcp_tso_autosize(sk, mss_now, min_tso);
return min_t(u32, tso_segs, sk->sk_gso_max_segs);
@@ -2276,7 +2280,7 @@
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);
@@ -2358,7 +2362,7 @@
* 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.
*/
@@ -2500,7 +2504,7 @@
sk->sk_pacing_rate >> READ_ONCE(sk->sk_pacing_shift));
if (sk->sk_pacing_status == SK_PACING_NONE)
limit = min_t(unsigned long, limit,
- sock_net(sk)->ipv4.sysctl_tcp_limit_output_bytes);
+ READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_limit_output_bytes));
limit <<= factor;
if (static_branch_unlikely(&tcp_tx_delay_enabled) &&
@@ -2733,7 +2737,7 @@
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.
*/
@@ -3098,7 +3102,7 @@
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;
@@ -3138,7 +3142,7 @@
struct tcp_sock *tp = tcp_sk(sk);
unsigned int cur_mss;
int diff, len, err;
-
+ int avail_wnd;
/* Inconclusive MTU probe */
if (icsk->icsk_mtup.probe_size)
@@ -3168,17 +3172,25 @@
return -EHOSTUNREACH; /* Routing failure or similar. */
cur_mss = tcp_current_mss(sk);
+ avail_wnd = tcp_wnd_end(tp) - TCP_SKB_CB(skb)->seq;
/* If receiver has shrunk his window, and skb is out of
* new window, do not retransmit it. The exception is the
* case, when window is shrunk to zero. In this case
- * our retransmit serves as a zero window probe.
+ * our retransmit of one segment serves as a zero window probe.
*/
- if (!before(TCP_SKB_CB(skb)->seq, tcp_wnd_end(tp)) &&
- TCP_SKB_CB(skb)->seq != tp->snd_una)
- return -EAGAIN;
+ if (avail_wnd <= 0) {
+ if (TCP_SKB_CB(skb)->seq != tp->snd_una)
+ return -EAGAIN;
+ avail_wnd = cur_mss;
+ }
len = cur_mss * segs;
+ if (len > avail_wnd) {
+ len = rounddown(avail_wnd, cur_mss);
+ if (!len)
+ len = avail_wnd;
+ }
if (skb->len > len) {
if (tcp_fragment(sk, TCP_FRAG_IN_RTX_QUEUE, skb, len,
cur_mss, GFP_ATOMIC))
@@ -3192,8 +3204,9 @@
diff -= tcp_skb_pcount(skb);
if (diff)
tcp_adjust_pcount(sk, skb, diff);
- if (skb->len < cur_mss)
- tcp_retrans_try_collapse(sk, skb, cur_mss);
+ avail_wnd = min_t(int, avail_wnd, cur_mss);
+ if (skb->len < avail_wnd)
+ tcp_retrans_try_collapse(sk, skb, avail_wnd);
}
/* RFC3168, section 6.1.1.1. ECN fallback */
@@ -3364,11 +3377,12 @@
*/
void sk_forced_mem_schedule(struct sock *sk, int size)
{
- int amt;
+ int delta, amt;
- if (size <= sk->sk_forward_alloc)
+ delta = size - sk->sk_forward_alloc;
+ if (delta <= 0)
return;
- amt = sk_mem_pages(size);
+ amt = sk_mem_pages(delta);
sk->sk_forward_alloc += amt * SK_MEM_QUANTUM;
sk_memory_allocated_add(sk, amt);
@@ -3646,7 +3660,7 @@
* 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
@@ -3682,7 +3696,7 @@
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);
@@ -3733,6 +3747,7 @@
*/
static int tcp_send_syn_data(struct sock *sk, struct sk_buff *syn)
{
+ struct inet_connection_sock *icsk = inet_csk(sk);
struct tcp_sock *tp = tcp_sk(sk);
struct tcp_fastopen_request *fo = tp->fastopen_req;
int space, err = 0;
@@ -3747,8 +3762,10 @@
* private TCP options. The cost is reduced data space in SYN :(
*/
tp->rx_opt.mss_clamp = tcp_mss_clamp(tp, tp->rx_opt.mss_clamp);
+ /* Sync mss_cache after updating the mss_clamp */
+ tcp_sync_mss(sk, icsk->icsk_pmtu_cookie);
- space = __tcp_mtu_to_mss(sk, inet_csk(sk)->icsk_pmtu_cookie) -
+ space = __tcp_mtu_to_mss(sk, icsk->icsk_pmtu_cookie) -
MAX_TCP_OPTION_SPACE;
space = min_t(size_t, space, fo->size);
@@ -4087,7 +4104,7 @@
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 {
@@ -4111,8 +4128,8 @@
res = af_ops->send_synack(sk, NULL, &fl, req, NULL, TCP_SYNACK_NORMAL,
NULL);
if (!res) {
- __TCP_INC_STATS(sock_net(sk), TCP_MIB_RETRANSSEGS);
- __NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPSYNRETRANS);
+ TCP_INC_STATS(sock_net(sk), TCP_MIB_RETRANSSEGS);
+ NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPSYNRETRANS);
if (unlikely(tcp_passive_fastopen(sk)))
tcp_sk(sk)->total_retrans++;
trace_tcp_retransmit_synack(sk, req);
diff --git a/net/ipv4/tcp_rate.c b/net/ipv4/tcp_rate.c
index 0de6935..6ab1979 100644
--- a/net/ipv4/tcp_rate.c
+++ b/net/ipv4/tcp_rate.c
@@ -73,26 +73,31 @@
*
* If an ACK (s)acks multiple skbs (e.g., stretched-acks), this function is
* called multiple times. We favor the information from the most recently
- * sent skb, i.e., the skb with the highest prior_delivered count.
+ * sent skb, i.e., the skb with the most recently sent time and the highest
+ * sequence.
*/
void tcp_rate_skb_delivered(struct sock *sk, struct sk_buff *skb,
struct rate_sample *rs)
{
struct tcp_sock *tp = tcp_sk(sk);
struct tcp_skb_cb *scb = TCP_SKB_CB(skb);
+ u64 tx_tstamp;
if (!scb->tx.delivered_mstamp)
return;
+ tx_tstamp = tcp_skb_timestamp_us(skb);
if (!rs->prior_delivered ||
- after(scb->tx.delivered, rs->prior_delivered)) {
+ tcp_skb_sent_after(tx_tstamp, tp->first_tx_mstamp,
+ scb->end_seq, rs->last_end_seq)) {
rs->prior_delivered = scb->tx.delivered;
rs->prior_mstamp = scb->tx.delivered_mstamp;
rs->is_app_limited = scb->tx.is_app_limited;
rs->is_retrans = scb->sacked & TCPCB_RETRANS;
+ rs->last_end_seq = scb->end_seq;
/* Record send time of most recently ACKed packet: */
- tp->first_tx_mstamp = tcp_skb_timestamp_us(skb);
+ tp->first_tx_mstamp = tx_tstamp;
/* Find the duration of the "send phase" of this window: */
rs->interval_us = tcp_stamp_us_delta(tp->first_tx_mstamp,
scb->tx.first_tx_mstamp);
diff --git a/net/ipv4/tcp_recovery.c b/net/ipv4/tcp_recovery.c
index 31fc178..21fc985 100644
--- a/net/ipv4/tcp_recovery.c
+++ b/net/ipv4/tcp_recovery.c
@@ -19,7 +19,8 @@
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;
}
@@ -190,7 +191,8 @@
{
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 4ef0807..888683f 100644
--- a/net/ipv4/tcp_timer.c
+++ b/net/ipv4/tcp_timer.c
@@ -143,7 +143,7 @@
*/
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 @@
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 @@
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);
@@ -242,14 +242,14 @@
retry_until = icsk->icsk_syn_retries ? : 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;
@@ -380,7 +380,7 @@
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;
@@ -574,7 +574,7 @@
* 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;
@@ -585,7 +585,7 @@
}
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:;
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index ef2068a..b093daa 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -446,7 +446,7 @@
result = lookup_reuseport(net, sk, skb,
saddr, sport, daddr, hnum);
/* Fall back to scoring if group has connections */
- if (result && !reuseport_has_conns(sk, false))
+ if (result && !reuseport_has_conns(sk))
return result;
result = result ? : sk;
@@ -598,6 +598,12 @@
}
EXPORT_SYMBOL(udp_encap_enable);
+void udp_encap_disable(void)
+{
+ static_branch_dec(&udp_encap_needed_key);
+}
+EXPORT_SYMBOL(udp_encap_disable);
+
/* Handler for tunnels with arbitrary destination ports: no socket lookup, go
* through error handlers in encapsulations looking for a match.
*/
@@ -1198,7 +1204,7 @@
faddr, saddr, dport, inet->inet_sport,
sk->sk_uid);
- security_sk_classify_flow(sk, flowi4_to_flowi(fl4));
+ security_sk_classify_flow(sk, flowi4_to_flowi_common(fl4));
rt = ip_route_output_flow(net, fl4, sk);
if (IS_ERR(rt)) {
err = PTR_ERR(rt);
@@ -2187,7 +2193,7 @@
struct dst_entry *old;
if (dst_hold_safe(dst)) {
- old = xchg(&sk->sk_rx_dst, dst);
+ old = xchg((__force struct dst_entry **)&sk->sk_rx_dst, dst);
dst_release(old);
return old != dst;
}
@@ -2377,7 +2383,7 @@
struct dst_entry *dst = skb_dst(skb);
int ret;
- if (unlikely(sk->sk_rx_dst != dst))
+ if (unlikely(rcu_dereference(sk->sk_rx_dst) != dst))
udp_sk_rx_dst_set(sk, dst);
ret = udp_unicast_rcv_skb(sk, skb, uh);
@@ -2484,8 +2490,7 @@
struct sock *sk;
udp_portaddr_for_each_entry_rcu(sk, &hslot2->head) {
- if (INET_MATCH(sk, net, acookie, rmt_addr,
- loc_addr, ports, dif, sdif))
+ if (INET_MATCH(net, sk, acookie, ports, dif, sdif))
return sk;
/* Only check first socket in chain */
break;
@@ -2536,7 +2541,7 @@
skb->sk = sk;
skb->destructor = sock_efree;
- dst = READ_ONCE(sk->sk_rx_dst);
+ dst = rcu_dereference(sk->sk_rx_dst);
if (dst)
dst = dst_check(dst, 0);
diff --git a/net/ipv4/xfrm4_protocol.c b/net/ipv4/xfrm4_protocol.c
index ea595c8..cfd4622 100644
--- a/net/ipv4/xfrm4_protocol.c
+++ b/net/ipv4/xfrm4_protocol.c
@@ -307,4 +307,3 @@
{
xfrm_input_register_afinfo(&xfrm4_input_afinfo);
}
-EXPORT_SYMBOL(xfrm4_protocol_init);