summaryrefslogtreecommitdiff
path: root/net/ipv4
diff options
context:
space:
mode:
Diffstat (limited to 'net/ipv4')
-rw-r--r--net/ipv4/devinet.c21
-rw-r--r--net/ipv4/esp4.c2
-rw-r--r--net/ipv4/fib_rules.c25
-rw-r--r--net/ipv4/fib_trie.c7
-rw-r--r--net/ipv4/igmp.c34
-rw-r--r--net/ipv4/ip_gre.c6
-rw-r--r--net/ipv4/ip_input.c8
-rw-r--r--net/ipv4/ip_tunnel.c65
-rw-r--r--net/ipv4/ip_tunnel_core.c4
-rw-r--r--net/ipv4/ip_vti.c2
-rw-r--r--net/ipv4/ipip.c3
-rw-r--r--net/ipv4/ping.c2
-rw-r--r--net/ipv4/proc.c9
-rw-r--r--net/ipv4/raw.c2
-rw-r--r--net/ipv4/route.c16
-rw-r--r--net/ipv4/sysctl_net_ipv4.c6
-rw-r--r--net/ipv4/tcp.c4
-rw-r--r--net/ipv4/tcp_cubic.c12
-rw-r--r--net/ipv4/tcp_fastopen.c13
-rw-r--r--net/ipv4/tcp_input.c9
-rw-r--r--net/ipv4/tcp_ipv4.c19
-rw-r--r--net/ipv4/udp.c5
22 files changed, 183 insertions, 91 deletions
diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c
index 8d48c392adcc..a1b5bcbd04ae 100644
--- a/net/ipv4/devinet.c
+++ b/net/ipv4/devinet.c
@@ -73,6 +73,8 @@ static struct ipv4_devconf ipv4_devconf = {
[IPV4_DEVCONF_SEND_REDIRECTS - 1] = 1,
[IPV4_DEVCONF_SECURE_REDIRECTS - 1] = 1,
[IPV4_DEVCONF_SHARED_MEDIA - 1] = 1,
+ [IPV4_DEVCONF_IGMPV2_UNSOLICITED_REPORT_INTERVAL - 1] = 10000 /*ms*/,
+ [IPV4_DEVCONF_IGMPV3_UNSOLICITED_REPORT_INTERVAL - 1] = 1000 /*ms*/,
},
};
@@ -83,6 +85,8 @@ static struct ipv4_devconf ipv4_devconf_dflt = {
[IPV4_DEVCONF_SECURE_REDIRECTS - 1] = 1,
[IPV4_DEVCONF_SHARED_MEDIA - 1] = 1,
[IPV4_DEVCONF_ACCEPT_SOURCE_ROUTE - 1] = 1,
+ [IPV4_DEVCONF_IGMPV2_UNSOLICITED_REPORT_INTERVAL - 1] = 10000 /*ms*/,
+ [IPV4_DEVCONF_IGMPV3_UNSOLICITED_REPORT_INTERVAL - 1] = 1000 /*ms*/,
},
};
@@ -772,7 +776,7 @@ static struct in_ifaddr *rtm_to_ifaddr(struct net *net, struct nlmsghdr *nlh,
ci = nla_data(tb[IFA_CACHEINFO]);
if (!ci->ifa_valid || ci->ifa_prefered > ci->ifa_valid) {
err = -EINVAL;
- goto errout;
+ goto errout_free;
}
*pvalid_lft = ci->ifa_valid;
*pprefered_lft = ci->ifa_prefered;
@@ -780,6 +784,8 @@ static struct in_ifaddr *rtm_to_ifaddr(struct net *net, struct nlmsghdr *nlh,
return ifa;
+errout_free:
+ inet_free_ifa(ifa);
errout:
return ERR_PTR(err);
}
@@ -1124,10 +1130,7 @@ static int inet_gifconf(struct net_device *dev, char __user *buf, int len)
if (len < (int) sizeof(ifr))
break;
memset(&ifr, 0, sizeof(struct ifreq));
- if (ifa->ifa_label)
- strcpy(ifr.ifr_name, ifa->ifa_label);
- else
- strcpy(ifr.ifr_name, dev->name);
+ strcpy(ifr.ifr_name, ifa->ifa_label);
(*(struct sockaddr_in *)&ifr.ifr_addr).sin_family = AF_INET;
(*(struct sockaddr_in *)&ifr.ifr_addr).sin_addr.s_addr =
@@ -2095,11 +2098,15 @@ static struct devinet_sysctl_table {
DEVINET_SYSCTL_RW_ENTRY(ARP_ACCEPT, "arp_accept"),
DEVINET_SYSCTL_RW_ENTRY(ARP_NOTIFY, "arp_notify"),
DEVINET_SYSCTL_RW_ENTRY(PROXY_ARP_PVLAN, "proxy_arp_pvlan"),
+ DEVINET_SYSCTL_RW_ENTRY(FORCE_IGMP_VERSION,
+ "force_igmp_version"),
+ DEVINET_SYSCTL_RW_ENTRY(IGMPV2_UNSOLICITED_REPORT_INTERVAL,
+ "igmpv2_unsolicited_report_interval"),
+ DEVINET_SYSCTL_RW_ENTRY(IGMPV3_UNSOLICITED_REPORT_INTERVAL,
+ "igmpv3_unsolicited_report_interval"),
DEVINET_SYSCTL_FLUSHING_ENTRY(NOXFRM, "disable_xfrm"),
DEVINET_SYSCTL_FLUSHING_ENTRY(NOPOLICY, "disable_policy"),
- DEVINET_SYSCTL_FLUSHING_ENTRY(FORCE_IGMP_VERSION,
- "force_igmp_version"),
DEVINET_SYSCTL_FLUSHING_ENTRY(PROMOTE_SECONDARIES,
"promote_secondaries"),
DEVINET_SYSCTL_FLUSHING_ENTRY(ROUTE_LOCALNET,
diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c
index ab3d814bc80a..109ee89f123e 100644
--- a/net/ipv4/esp4.c
+++ b/net/ipv4/esp4.c
@@ -477,7 +477,7 @@ static u32 esp4_get_mtu(struct xfrm_state *x, int mtu)
}
return ((mtu - x->props.header_len - crypto_aead_authsize(esp->aead) -
- net_adj) & ~(align - 1)) + (net_adj - 2);
+ net_adj) & ~(align - 1)) + net_adj - 2;
}
static void esp4_err(struct sk_buff *skb, u32 info)
diff --git a/net/ipv4/fib_rules.c b/net/ipv4/fib_rules.c
index 26aa65d1fce4..523be38e37de 100644
--- a/net/ipv4/fib_rules.c
+++ b/net/ipv4/fib_rules.c
@@ -101,6 +101,30 @@ errout:
return err;
}
+static bool fib4_rule_suppress(struct fib_rule *rule, struct fib_lookup_arg *arg)
+{
+ struct fib_result *result = (struct fib_result *) arg->result;
+ struct net_device *dev = result->fi->fib_dev;
+
+ /* do not accept result if the route does
+ * not meet the required prefix length
+ */
+ if (result->prefixlen <= rule->suppress_prefixlen)
+ goto suppress_route;
+
+ /* do not accept result if the route uses a device
+ * belonging to a forbidden interface group
+ */
+ if (rule->suppress_ifgroup != -1 && dev && dev->group == rule->suppress_ifgroup)
+ goto suppress_route;
+
+ return false;
+
+suppress_route:
+ if (!(arg->flags & FIB_LOOKUP_NOREF))
+ fib_info_put(result->fi);
+ return true;
+}
static int fib4_rule_match(struct fib_rule *rule, struct flowi *fl, int flags)
{
@@ -267,6 +291,7 @@ static const struct fib_rules_ops __net_initconst fib4_rules_ops_template = {
.rule_size = sizeof(struct fib4_rule),
.addr_size = sizeof(u32),
.action = fib4_rule_action,
+ .suppress = fib4_rule_suppress,
.match = fib4_rule_match,
.configure = fib4_rule_configure,
.delete = fib4_rule_delete,
diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c
index 49616fed9340..3df6d3edb2a1 100644
--- a/net/ipv4/fib_trie.c
+++ b/net/ipv4/fib_trie.c
@@ -71,7 +71,6 @@
#include <linux/init.h>
#include <linux/list.h>
#include <linux/slab.h>
-#include <linux/prefetch.h>
#include <linux/export.h>
#include <net/net_namespace.h>
#include <net/ip.h>
@@ -1761,10 +1760,8 @@ static struct leaf *leaf_walk_rcu(struct tnode *p, struct rt_trie_node *c)
if (!c)
continue;
- if (IS_LEAF(c)) {
- prefetch(rcu_dereference_rtnl(p->child[idx]));
+ if (IS_LEAF(c))
return (struct leaf *) c;
- }
/* Rescan start scanning in new node */
p = (struct tnode *) c;
@@ -2133,7 +2130,7 @@ static void trie_show_stats(struct seq_file *seq, struct trie_stat *stat)
max--;
pointers = 0;
- for (i = 1; i <= max; i++)
+ for (i = 1; i < max; i++)
if (stat->nodesizes[i] != 0) {
seq_printf(seq, " %u: %u", i, stat->nodesizes[i]);
pointers += (1<<i) * stat->nodesizes[i];
diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c
index 375aca372250..d6c0e64ec97f 100644
--- a/net/ipv4/igmp.c
+++ b/net/ipv4/igmp.c
@@ -88,6 +88,7 @@
#include <linux/if_arp.h>
#include <linux/rtnetlink.h>
#include <linux/times.h>
+#include <linux/pkt_sched.h>
#include <net/net_namespace.h>
#include <net/arp.h>
@@ -113,7 +114,8 @@
#define IGMP_V1_Router_Present_Timeout (400*HZ)
#define IGMP_V2_Router_Present_Timeout (400*HZ)
-#define IGMP_Unsolicited_Report_Interval (10*HZ)
+#define IGMP_V2_Unsolicited_Report_Interval (10*HZ)
+#define IGMP_V3_Unsolicited_Report_Interval (1*HZ)
#define IGMP_Query_Response_Interval (10*HZ)
#define IGMP_Unsolicited_Report_Count 2
@@ -138,6 +140,29 @@
((in_dev)->mr_v2_seen && \
time_before(jiffies, (in_dev)->mr_v2_seen)))
+static int unsolicited_report_interval(struct in_device *in_dev)
+{
+ int interval_ms, interval_jiffies;
+
+ if (IGMP_V1_SEEN(in_dev) || IGMP_V2_SEEN(in_dev))
+ interval_ms = IN_DEV_CONF_GET(
+ in_dev,
+ IGMPV2_UNSOLICITED_REPORT_INTERVAL);
+ else /* v3 */
+ interval_ms = IN_DEV_CONF_GET(
+ in_dev,
+ IGMPV3_UNSOLICITED_REPORT_INTERVAL);
+
+ interval_jiffies = msecs_to_jiffies(interval_ms);
+
+ /* _timer functions can't handle a delay of 0 jiffies so ensure
+ * we always return a positive value.
+ */
+ if (interval_jiffies <= 0)
+ interval_jiffies = 1;
+ return interval_jiffies;
+}
+
static void igmpv3_add_delrec(struct in_device *in_dev, struct ip_mc_list *im);
static void igmpv3_del_delrec(struct in_device *in_dev, __be32 multiaddr);
static void igmpv3_clear_delrec(struct in_device *in_dev);
@@ -315,6 +340,7 @@ static struct sk_buff *igmpv3_newpack(struct net_device *dev, int size)
if (size < 256)
return NULL;
}
+ skb->priority = TC_PRIO_CONTROL;
igmp_skb_size(skb) = size;
rt = ip_route_output_ports(net, &fl4, NULL, IGMPV3_ALL_MCR, 0,
@@ -670,6 +696,7 @@ static int igmp_send_report(struct in_device *in_dev, struct ip_mc_list *pmc,
ip_rt_put(rt);
return -1;
}
+ skb->priority = TC_PRIO_CONTROL;
skb_dst_set(skb, &rt->dst);
@@ -719,7 +746,8 @@ static void igmp_ifc_timer_expire(unsigned long data)
igmpv3_send_cr(in_dev);
if (in_dev->mr_ifc_count) {
in_dev->mr_ifc_count--;
- igmp_ifc_start_timer(in_dev, IGMP_Unsolicited_Report_Interval);
+ igmp_ifc_start_timer(in_dev,
+ unsolicited_report_interval(in_dev));
}
__in_dev_put(in_dev);
}
@@ -744,7 +772,7 @@ static void igmp_timer_expire(unsigned long data)
if (im->unsolicit_count) {
im->unsolicit_count--;
- igmp_start_timer(im, IGMP_Unsolicited_Report_Interval);
+ igmp_start_timer(im, unsolicited_report_interval(in_dev));
}
im->reporter = 1;
spin_unlock(&im->lock);
diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index 1f6eab66f7ce..d7aea4c5b940 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -383,7 +383,7 @@ static int ipgre_header(struct sk_buff *skb, struct net_device *dev,
if (daddr)
memcpy(&iph->daddr, daddr, 4);
if (iph->daddr)
- return t->hlen;
+ return t->hlen + sizeof(*iph);
return -(t->hlen + sizeof(*iph));
}
@@ -534,7 +534,7 @@ static int __net_init ipgre_init_net(struct net *net)
static void __net_exit ipgre_exit_net(struct net *net)
{
struct ip_tunnel_net *itn = net_generic(net, ipgre_net_id);
- ip_tunnel_delete_net(itn);
+ ip_tunnel_delete_net(itn, &ipgre_link_ops);
}
static struct pernet_operations ipgre_net_ops = {
@@ -767,7 +767,7 @@ static int __net_init ipgre_tap_init_net(struct net *net)
static void __net_exit ipgre_tap_exit_net(struct net *net)
{
struct ip_tunnel_net *itn = net_generic(net, gre_tap_net_id);
- ip_tunnel_delete_net(itn);
+ ip_tunnel_delete_net(itn, &ipgre_tap_ops);
}
static struct pernet_operations ipgre_tap_net_ops = {
diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c
index 15e3e683adec..054a3e97d822 100644
--- a/net/ipv4/ip_input.c
+++ b/net/ipv4/ip_input.c
@@ -141,6 +141,7 @@
#include <net/icmp.h>
#include <net/raw.h>
#include <net/checksum.h>
+#include <net/inet_ecn.h>
#include <linux/netfilter_ipv4.h>
#include <net/xfrm.h>
#include <linux/mroute.h>
@@ -410,6 +411,13 @@ int ip_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt,
if (iph->ihl < 5 || iph->version != 4)
goto inhdr_error;
+ BUILD_BUG_ON(IPSTATS_MIB_ECT1PKTS != IPSTATS_MIB_NOECTPKTS + INET_ECN_ECT_1);
+ BUILD_BUG_ON(IPSTATS_MIB_ECT0PKTS != IPSTATS_MIB_NOECTPKTS + INET_ECN_ECT_0);
+ BUILD_BUG_ON(IPSTATS_MIB_CEPKTS != IPSTATS_MIB_NOECTPKTS + INET_ECN_CE);
+ IP_ADD_STATS_BH(dev_net(dev),
+ IPSTATS_MIB_NOECTPKTS + (iph->tos & INET_ECN_MASK),
+ max_t(unsigned short, 1, skb_shinfo(skb)->gso_segs));
+
if (!pskb_may_pull(skb, iph->ihl*4))
goto inhdr_error;
diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c
index ca1cb2d5f6e2..a4d9126c7b51 100644
--- a/net/ipv4/ip_tunnel.c
+++ b/net/ipv4/ip_tunnel.c
@@ -350,7 +350,7 @@ static int ip_tunnel_bind_dev(struct net_device *dev)
struct flowi4 fl4;
struct rtable *rt;
- rt = ip_route_output_tunnel(dev_net(dev), &fl4,
+ rt = ip_route_output_tunnel(tunnel->net, &fl4,
tunnel->parms.iph.protocol,
iph->daddr, iph->saddr,
tunnel->parms.o_key,
@@ -365,7 +365,7 @@ static int ip_tunnel_bind_dev(struct net_device *dev)
}
if (!tdev && tunnel->parms.link)
- tdev = __dev_get_by_index(dev_net(dev), tunnel->parms.link);
+ tdev = __dev_get_by_index(tunnel->net, tunnel->parms.link);
if (tdev) {
hlen = tdev->hard_header_len + tdev->needed_headroom;
@@ -454,15 +454,16 @@ int ip_tunnel_rcv(struct ip_tunnel *tunnel, struct sk_buff *skb,
tstats->rx_bytes += skb->len;
u64_stats_update_end(&tstats->syncp);
- if (tunnel->net != dev_net(tunnel->dev))
- skb_scrub_packet(skb);
-
if (tunnel->dev->type == ARPHRD_ETHER) {
skb->protocol = eth_type_trans(skb, tunnel->dev);
skb_postpull_rcsum(skb, eth_hdr(skb), ETH_HLEN);
} else {
skb->dev = tunnel->dev;
}
+
+ if (!net_eq(tunnel->net, dev_net(tunnel->dev)))
+ skb_scrub_packet(skb);
+
gro_cells_receive(&tunnel->gro_cells, skb);
return 0;
@@ -613,7 +614,7 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev,
goto tx_error;
}
- if (tunnel->net != dev_net(dev))
+ if (!net_eq(tunnel->net, dev_net(dev)))
skb_scrub_packet(skb);
if (tunnel->err_count > 0) {
@@ -653,7 +654,7 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev,
}
}
- err = iptunnel_xmit(dev_net(dev), rt, skb,
+ err = iptunnel_xmit(tunnel->net, rt, skb,
fl4.saddr, fl4.daddr, protocol,
ip_tunnel_ecn_encap(tos, inner_iph, skb), ttl, df);
iptunnel_xmit_stats(err, &dev->stats, dev->tstats);
@@ -820,11 +821,10 @@ static void ip_tunnel_dev_free(struct net_device *dev)
void ip_tunnel_dellink(struct net_device *dev, struct list_head *head)
{
- struct net *net = dev_net(dev);
struct ip_tunnel *tunnel = netdev_priv(dev);
struct ip_tunnel_net *itn;
- itn = net_generic(net, tunnel->ip_tnl_net_id);
+ itn = net_generic(tunnel->net, tunnel->ip_tnl_net_id);
if (itn->fb_tunnel_dev != dev) {
ip_tunnel_del(netdev_priv(dev));
@@ -838,56 +838,70 @@ int ip_tunnel_init_net(struct net *net, int ip_tnl_net_id,
{
struct ip_tunnel_net *itn = net_generic(net, ip_tnl_net_id);
struct ip_tunnel_parm parms;
+ unsigned int i;
- itn->tunnels = kzalloc(IP_TNL_HASH_SIZE * sizeof(struct hlist_head), GFP_KERNEL);
- if (!itn->tunnels)
- return -ENOMEM;
+ for (i = 0; i < IP_TNL_HASH_SIZE; i++)
+ INIT_HLIST_HEAD(&itn->tunnels[i]);
if (!ops) {
itn->fb_tunnel_dev = NULL;
return 0;
}
+
memset(&parms, 0, sizeof(parms));
if (devname)
strlcpy(parms.name, devname, IFNAMSIZ);
rtnl_lock();
itn->fb_tunnel_dev = __ip_tunnel_create(net, ops, &parms);
+ /* FB netdevice is special: we have one, and only one per netns.
+ * Allowing to move it to another netns is clearly unsafe.
+ */
+ itn->fb_tunnel_dev->features |= NETIF_F_NETNS_LOCAL;
rtnl_unlock();
- if (IS_ERR(itn->fb_tunnel_dev)) {
- kfree(itn->tunnels);
+
+ if (IS_ERR(itn->fb_tunnel_dev))
return PTR_ERR(itn->fb_tunnel_dev);
- }
return 0;
}
EXPORT_SYMBOL_GPL(ip_tunnel_init_net);
-static void ip_tunnel_destroy(struct ip_tunnel_net *itn, struct list_head *head)
+static void ip_tunnel_destroy(struct ip_tunnel_net *itn, struct list_head *head,
+ struct rtnl_link_ops *ops)
{
+ struct net *net = dev_net(itn->fb_tunnel_dev);
+ struct net_device *dev, *aux;
int h;
+ for_each_netdev_safe(net, dev, aux)
+ if (dev->rtnl_link_ops == ops)
+ unregister_netdevice_queue(dev, head);
+
for (h = 0; h < IP_TNL_HASH_SIZE; h++) {
struct ip_tunnel *t;
struct hlist_node *n;
struct hlist_head *thead = &itn->tunnels[h];
hlist_for_each_entry_safe(t, n, thead, hash_node)
- unregister_netdevice_queue(t->dev, head);
+ /* If dev is in the same netns, it has already
+ * been added to the list by the previous loop.
+ */
+ if (!net_eq(dev_net(t->dev), net))
+ unregister_netdevice_queue(t->dev, head);
}
if (itn->fb_tunnel_dev)
unregister_netdevice_queue(itn->fb_tunnel_dev, head);
}
-void ip_tunnel_delete_net(struct ip_tunnel_net *itn)
+void ip_tunnel_delete_net(struct ip_tunnel_net *itn, struct rtnl_link_ops *ops)
{
LIST_HEAD(list);
rtnl_lock();
- ip_tunnel_destroy(itn, &list);
+ ip_tunnel_destroy(itn, &list, ops);
unregister_netdevice_many(&list);
rtnl_unlock();
- kfree(itn->tunnels);
}
EXPORT_SYMBOL_GPL(ip_tunnel_delete_net);
@@ -929,23 +943,21 @@ EXPORT_SYMBOL_GPL(ip_tunnel_newlink);
int ip_tunnel_changelink(struct net_device *dev, struct nlattr *tb[],
struct ip_tunnel_parm *p)
{
- struct ip_tunnel *t, *nt;
- struct net *net = dev_net(dev);
+ struct ip_tunnel *t;
struct ip_tunnel *tunnel = netdev_priv(dev);
+ struct net *net = tunnel->net;
struct ip_tunnel_net *itn = net_generic(net, tunnel->ip_tnl_net_id);
if (dev == itn->fb_tunnel_dev)
return -EINVAL;
- nt = netdev_priv(dev);
-
t = ip_tunnel_find(itn, p, dev->type);
if (t) {
if (t->dev != dev)
return -EEXIST;
} else {
- t = nt;
+ t = tunnel;
if (dev->type != ARPHRD_ETHER) {
unsigned int nflags = 0;
@@ -984,6 +996,7 @@ int ip_tunnel_init(struct net_device *dev)
}
tunnel->dev = dev;
+ tunnel->net = dev_net(dev);
strcpy(tunnel->parms.name, dev->name);
iph->version = 4;
iph->ihl = 5;
@@ -994,8 +1007,8 @@ EXPORT_SYMBOL_GPL(ip_tunnel_init);
void ip_tunnel_uninit(struct net_device *dev)
{
- struct net *net = dev_net(dev);
struct ip_tunnel *tunnel = netdev_priv(dev);
+ struct net *net = tunnel->net;
struct ip_tunnel_net *itn;
itn = net_generic(net, tunnel->ip_tnl_net_id);
diff --git a/net/ipv4/ip_tunnel_core.c b/net/ipv4/ip_tunnel_core.c
index 7167b08977df..850525b34899 100644
--- a/net/ipv4/ip_tunnel_core.c
+++ b/net/ipv4/ip_tunnel_core.c
@@ -76,9 +76,7 @@ int iptunnel_xmit(struct net *net, struct rtable *rt,
iph->daddr = dst;
iph->saddr = src;
iph->ttl = ttl;
- tunnel_ip_select_ident(skb,
- (const struct iphdr *)skb_inner_network_header(skb),
- &rt->dst);
+ __ip_select_ident(iph, &rt->dst, (skb_shinfo(skb)->gso_segs ?: 1) - 1);
err = ip_local_out(skb);
if (unlikely(net_xmit_eval(err)))
diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c
index 79b263da4168..e805e7b3030e 100644
--- a/net/ipv4/ip_vti.c
+++ b/net/ipv4/ip_vti.c
@@ -318,7 +318,7 @@ static int __net_init vti_init_net(struct net *net)
static void __net_exit vti_exit_net(struct net *net)
{
struct ip_tunnel_net *itn = net_generic(net, vti_net_id);
- ip_tunnel_delete_net(itn);
+ ip_tunnel_delete_net(itn, &vti_link_ops);
}
static struct pernet_operations vti_net_ops = {
diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c
index 51fc2a1dcdd3..87bd2952c733 100644
--- a/net/ipv4/ipip.c
+++ b/net/ipv4/ipip.c
@@ -286,7 +286,6 @@ static void ipip_tunnel_setup(struct net_device *dev)
dev->flags = IFF_NOARP;
dev->iflink = 0;
dev->addr_len = 4;
- dev->features |= NETIF_F_NETNS_LOCAL;
dev->features |= NETIF_F_LLTX;
dev->priv_flags &= ~IFF_XMIT_DST_RELEASE;
@@ -437,7 +436,7 @@ static int __net_init ipip_init_net(struct net *net)
static void __net_exit ipip_exit_net(struct net *net)
{
struct ip_tunnel_net *itn = net_generic(net, ipip_net_id);
- ip_tunnel_delete_net(itn);
+ ip_tunnel_delete_net(itn, &ipip_link_ops);
}
static struct pernet_operations ipip_net_ops = {
diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c
index 746427c9e719..d7d9882d4cae 100644
--- a/net/ipv4/ping.c
+++ b/net/ipv4/ping.c
@@ -1082,7 +1082,7 @@ static void ping_v4_format_sock(struct sock *sp, struct seq_file *f,
__u16 srcp = ntohs(inet->inet_sport);
seq_printf(f, "%5d: %08X:%04X %08X:%04X"
- " %02X %08X:%08X %02X:%08lX %08X %5d %8d %lu %d %pK %d%n",
+ " %02X %08X:%08X %02X:%08lX %08X %5u %8d %lu %d %pK %d%n",
bucket, src, srcp, dest, destp, sp->sk_state,
sk_wmem_alloc_get(sp),
sk_rmem_alloc_get(sp),
diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c
index 6577a1149a47..4a0335854b89 100644
--- a/net/ipv4/proc.c
+++ b/net/ipv4/proc.c
@@ -111,7 +111,7 @@ static const struct snmp_mib snmp4_ipstats_list[] = {
SNMP_MIB_SENTINEL
};
-/* Following RFC4293 items are displayed in /proc/net/netstat */
+/* Following items are displayed in /proc/net/netstat */
static const struct snmp_mib snmp4_ipextstats_list[] = {
SNMP_MIB_ITEM("InNoRoutes", IPSTATS_MIB_INNOROUTES),
SNMP_MIB_ITEM("InTruncatedPkts", IPSTATS_MIB_INTRUNCATEDPKTS),
@@ -125,7 +125,12 @@ static const struct snmp_mib snmp4_ipextstats_list[] = {
SNMP_MIB_ITEM("OutMcastOctets", IPSTATS_MIB_OUTMCASTOCTETS),
SNMP_MIB_ITEM("InBcastOctets", IPSTATS_MIB_INBCASTOCTETS),
SNMP_MIB_ITEM("OutBcastOctets", IPSTATS_MIB_OUTBCASTOCTETS),
+ /* Non RFC4293 fields */
SNMP_MIB_ITEM("InCsumErrors", IPSTATS_MIB_CSUMERRORS),
+ SNMP_MIB_ITEM("InNoECTPkts", IPSTATS_MIB_NOECTPKTS),
+ SNMP_MIB_ITEM("InECT1Pkts", IPSTATS_MIB_ECT1PKTS),
+ SNMP_MIB_ITEM("InECT0Pkts", IPSTATS_MIB_ECT0PKTS),
+ SNMP_MIB_ITEM("InCEPkts", IPSTATS_MIB_CEPKTS),
SNMP_MIB_SENTINEL
};
@@ -273,7 +278,7 @@ static const struct snmp_mib snmp4_net_list[] = {
SNMP_MIB_ITEM("TCPFastOpenListenOverflow", LINUX_MIB_TCPFASTOPENLISTENOVERFLOW),
SNMP_MIB_ITEM("TCPFastOpenCookieReqd", LINUX_MIB_TCPFASTOPENCOOKIEREQD),
SNMP_MIB_ITEM("TCPSpuriousRtxHostQueues", LINUX_MIB_TCPSPURIOUS_RTX_HOSTQUEUES),
- SNMP_MIB_ITEM("LowLatencyRxPackets", LINUX_MIB_LOWLATENCYRXPACKETS),
+ SNMP_MIB_ITEM("BusyPollRxPackets", LINUX_MIB_BUSYPOLLRXPACKETS),
SNMP_MIB_SENTINEL
};
diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c
index dd44e0ab600c..41d84505a922 100644
--- a/net/ipv4/raw.c
+++ b/net/ipv4/raw.c
@@ -987,7 +987,7 @@ static void raw_sock_seq_show(struct seq_file *seq, struct sock *sp, int i)
srcp = inet->inet_num;
seq_printf(seq, "%4d: %08X:%04X %08X:%04X"
- " %02X %08X:%08X %02X:%08lX %08X %5d %8d %lu %d %pK %d\n",
+ " %02X %08X:%08X %02X:%08lX %08X %5u %8d %lu %d %pK %d\n",
i, src, srcp, dest, destp, sp->sk_state,
sk_wmem_alloc_get(sp),
sk_rmem_alloc_get(sp),
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index a9a54a236832..e805481eff72 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -435,12 +435,12 @@ static inline int ip_rt_proc_init(void)
static inline bool rt_is_expired(const struct rtable *rth)
{
- return rth->rt_genid != rt_genid(dev_net(rth->dst.dev));
+ return rth->rt_genid != rt_genid_ipv4(dev_net(rth->dst.dev));
}
void rt_cache_flush(struct net *net)
{
- rt_genid_bump(net);
+ rt_genid_bump_ipv4(net);
}
static struct neighbour *ipv4_neigh_lookup(const struct dst_entry *dst,
@@ -1458,7 +1458,7 @@ static int ip_route_input_mc(struct sk_buff *skb, __be32 daddr, __be32 saddr,
#endif
rth->dst.output = ip_rt_bug;
- rth->rt_genid = rt_genid(dev_net(dev));
+ rth->rt_genid = rt_genid_ipv4(dev_net(dev));
rth->rt_flags = RTCF_MULTICAST;
rth->rt_type = RTN_MULTICAST;
rth->rt_is_input= 1;
@@ -1589,7 +1589,7 @@ static int __mkroute_input(struct sk_buff *skb,
goto cleanup;
}
- rth->rt_genid = rt_genid(dev_net(rth->dst.dev));
+ rth->rt_genid = rt_genid_ipv4(dev_net(rth->dst.dev));
rth->rt_flags = flags;
rth->rt_type = res->type;
rth->rt_is_input = 1;
@@ -1760,7 +1760,7 @@ local_input:
rth->dst.tclassid = itag;
#endif
- rth->rt_genid = rt_genid(net);
+ rth->rt_genid = rt_genid_ipv4(net);
rth->rt_flags = flags|RTCF_LOCAL;
rth->rt_type = res.type;
rth->rt_is_input = 1;
@@ -1945,7 +1945,7 @@ add:
rth->dst.output = ip_output;
- rth->rt_genid = rt_genid(dev_net(dev_out));
+ rth->rt_genid = rt_genid_ipv4(dev_net(dev_out));
rth->rt_flags = flags;
rth->rt_type = type;
rth->rt_is_input = 0;
@@ -2227,7 +2227,7 @@ struct dst_entry *ipv4_blackhole_route(struct net *net, struct dst_entry *dst_or
rt->rt_iif = ort->rt_iif;
rt->rt_pmtu = ort->rt_pmtu;
- rt->rt_genid = rt_genid(net);
+ rt->rt_genid = rt_genid_ipv4(net);
rt->rt_flags = ort->rt_flags;
rt->rt_type = ort->rt_type;
rt->rt_gateway = ort->rt_gateway;
@@ -2665,7 +2665,7 @@ static __net_initdata struct pernet_operations sysctl_route_ops = {
static __net_init int rt_genid_init(struct net *net)
{
- atomic_set(&net->rt_genid, 0);
+ atomic_set(&net->ipv4.rt_genid, 0);
atomic_set(&net->fnhe_genid, 0);
get_random_bytes(&net->ipv4.dev_addr_genid,
sizeof(net->ipv4.dev_addr_genid));
diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index 69ed203802da..8ed7c32ae28e 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -36,6 +36,8 @@ static int tcp_adv_win_scale_min = -31;
static int tcp_adv_win_scale_max = 31;
static int ip_ttl_min = 1;
static int ip_ttl_max = 255;
+static int tcp_syn_retries_min = 1;
+static int tcp_syn_retries_max = MAX_TCP_SYNCNT;
static int ip_ping_group_range_min[] = { 0, 0 };
static int ip_ping_group_range_max[] = { GID_T_MAX, GID_T_MAX };
@@ -332,7 +334,9 @@ static struct ctl_table ipv4_table[] = {
.data = &sysctl_tcp_syn_retries,
.maxlen = sizeof(int),
.mode = 0644,
- .proc_handler = proc_dointvec
+ .proc_handler = proc_dointvec_minmax,
+ .extra1 = &tcp_syn_retries_min,
+ .extra2 = &tcp_syn_retries_max
},
{
.procname = "tcp_synack_retries",
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index c27e81392398..ab64eea042fa 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -410,10 +410,6 @@ void tcp_init_sock(struct sock *sk)
icsk->icsk_sync_mss = tcp_sync_mss;
- /* Presumed zeroed, in order of appearance:
- * cookie_in_always, cookie_out_never,
- * s_data_constant, s_data_in, s_data_out
- */
sk->sk_sndbuf = sysctl_tcp_wmem[1];
sk->sk_rcvbuf = sysctl_tcp_rmem[1];
diff --git a/net/ipv4/tcp_cubic.c b/net/ipv4/tcp_cubic.c
index a9077f441cb2..b6ae92a51f58 100644
--- a/net/ipv4/tcp_cubic.c
+++ b/net/ipv4/tcp_cubic.c
@@ -206,8 +206,8 @@ static u32 cubic_root(u64 a)
*/
static inline void bictcp_update(struct bictcp *ca, u32 cwnd)
{
- u64 offs;
- u32 delta, t, bic_target, max_cnt;
+ u32 delta, bic_target, max_cnt;
+ u64 offs, t;
ca->ack_cnt++; /* count the number of ACKs */
@@ -250,9 +250,11 @@ static inline void bictcp_update(struct bictcp *ca, u32 cwnd)
* if the cwnd < 1 million packets !!!
*/
+ t = (s32)(tcp_time_stamp - ca->epoch_start);
+ t += msecs_to_jiffies(ca->delay_min >> 3);
/* change the unit from HZ to bictcp_HZ */
- t = ((tcp_time_stamp + msecs_to_jiffies(ca->delay_min>>3)
- - ca->epoch_start) << BICTCP_HZ) / HZ;
+ t <<= BICTCP_HZ;
+ do_div(t, HZ);
if (t < ca->bic_K) /* t - K */
offs = ca->bic_K - t;
@@ -414,7 +416,7 @@ static void bictcp_acked(struct sock *sk, u32 cnt, s32 rtt_us)
return;
/* Discard delay samples right after fast recovery */
- if ((s32)(tcp_time_stamp - ca->epoch_start) < HZ)
+ if (ca->epoch_start && (s32)(tcp_time_stamp - ca->epoch_start) < HZ)
return;
delay = (rtt_us << 3) / USEC_PER_MSEC;
diff --git a/net/ipv4/tcp_fastopen.c b/net/ipv4/tcp_fastopen.c
index 8f7ef0ad80e5..ab7bd35bb312 100644
--- a/net/ipv4/tcp_fastopen.c
+++ b/net/ipv4/tcp_fastopen.c
@@ -58,23 +58,22 @@ error: kfree(ctx);
return err;
}
-/* Computes the fastopen cookie for the peer.
- * The peer address is a 128 bits long (pad with zeros for IPv4).
+/* Computes the fastopen cookie for the IP path.
+ * The path is a 128 bits long (pad with zeros for IPv4).
*
* The caller must check foc->len to determine if a valid cookie
* has been generated successfully.
*/
-void tcp_fastopen_cookie_gen(__be32 addr, struct tcp_fastopen_cookie *foc)
+void tcp_fastopen_cookie_gen(__be32 src, __be32 dst,
+ struct tcp_fastopen_cookie *foc)
{
- __be32 peer_addr[4] = { addr, 0, 0, 0 };
+ __be32 path[4] = { src, dst, 0, 0 };
struct tcp_fastopen_context *ctx;
rcu_read_lock();
ctx = rcu_dereference(tcp_fastopen_ctx);
if (ctx) {
- crypto_cipher_encrypt_one(ctx->tfm,
- foc->val,
- (__u8 *)peer_addr);
+ crypto_cipher_encrypt_one(ctx->tfm, foc->val, (__u8 *)path);
foc->len = TCP_FASTOPEN_COOKIE_SIZE;
}
rcu_read_unlock();
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index b61274b666f6..e965cc7b87ff 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -1877,8 +1877,13 @@ void tcp_enter_loss(struct sock *sk, int how)
}
tcp_verify_left_out(tp);
- tp->reordering = min_t(unsigned int, tp->reordering,
- sysctl_tcp_reordering);
+ /* Timeout in disordered state after receiving substantial DUPACKs
+ * suggests that the degree of reordering is over-estimated.
+ */
+ if (icsk->icsk_ca_state <= TCP_CA_Disorder &&
+ tp->sacked_out >= sysctl_tcp_reordering)
+ tp->reordering = min_t(unsigned int, tp->reordering,
+ sysctl_tcp_reordering);
tcp_set_ca_state(sk, TCP_CA_Loss);
tp->high_seq = tp->snd_nxt;
TCP_ECN_queue_cwr(tp);
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 2a5d5c469d17..05a3d45d3102 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -890,7 +890,7 @@ bool tcp_syn_flood_action(struct sock *sk,
NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPREQQFULLDROP);
lopt = inet_csk(sk)->icsk_accept_queue.listen_opt;
- if (!lopt->synflood_warned) {
+ if (!lopt->synflood_warned && sysctl_tcp_syncookies != 2) {
lopt->synflood_warned = 1;
pr_info("%s: Possible SYN flooding on port %d. %s. Check SNMP counters.\n",
proto, ntohs(tcp_hdr(skb)->dest), msg);
@@ -1316,9 +1316,11 @@ static bool tcp_fastopen_check(struct sock *sk, struct sk_buff *skb,
tcp_rsk(req)->rcv_nxt = TCP_SKB_CB(skb)->end_seq;
return true;
}
+
if (foc->len == TCP_FASTOPEN_COOKIE_SIZE) {
if ((sysctl_tcp_fastopen & TFO_SERVER_COOKIE_NOT_CHKED) == 0) {
- tcp_fastopen_cookie_gen(ip_hdr(skb)->saddr, valid_foc);
+ tcp_fastopen_cookie_gen(ip_hdr(skb)->saddr,
+ ip_hdr(skb)->daddr, valid_foc);
if ((valid_foc->len != TCP_FASTOPEN_COOKIE_SIZE) ||
memcmp(&foc->val[0], &valid_foc->val[0],
TCP_FASTOPEN_COOKIE_SIZE) != 0)
@@ -1329,14 +1331,16 @@ static bool tcp_fastopen_check(struct sock *sk, struct sk_buff *skb,
tcp_rsk(req)->rcv_nxt = TCP_SKB_CB(skb)->end_seq;
return true;
} else if (foc->len == 0) { /* Client requesting a cookie */
- tcp_fastopen_cookie_gen(ip_hdr(skb)->saddr, valid_foc);
+ tcp_fastopen_cookie_gen(ip_hdr(skb)->saddr,
+ ip_hdr(skb)->daddr, valid_foc);
NET_INC_STATS_BH(sock_net(sk),
LINUX_MIB_TCPFASTOPENCOOKIEREQD);
} else {
/* Client sent a cookie with wrong size. Treat it
* the same as invalid and return a valid one.
*/
- tcp_fastopen_cookie_gen(ip_hdr(skb)->saddr, valid_foc);
+ tcp_fastopen_cookie_gen(ip_hdr(skb)->saddr,
+ ip_hdr(skb)->daddr, valid_foc);
}
return false;
}
@@ -1462,7 +1466,8 @@ int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb)
* limitations, they conserve resources and peer is
* evidently real one.
*/
- if (inet_csk_reqsk_queue_is_full(sk) && !isn) {
+ if ((sysctl_tcp_syncookies == 2 ||
+ inet_csk_reqsk_queue_is_full(sk)) && !isn) {
want_cookie = tcp_syn_flood_action(sk, skb, "TCP");
if (!want_cookie)
goto drop;
@@ -2603,7 +2608,7 @@ static void get_openreq4(const struct sock *sk, const struct request_sock *req,
long delta = req->expires - jiffies;
seq_printf(f, "%4d: %08X:%04X %08X:%04X"
- " %02X %08X:%08X %02X:%08lX %08X %5d %8d %u %d %pK%n",
+ " %02X %08X:%08X %02X:%08lX %08X %5u %8d %u %d %pK%n",
i,
ireq->loc_addr,
ntohs(inet_sk(sk)->inet_sport),
@@ -2661,7 +2666,7 @@ static void get_tcp4_sock(struct sock *sk, struct seq_file *f, int i, int *len)
rx_queue = max_t(int, tp->rcv_nxt - tp->copied_seq, 0);
seq_printf(f, "%4d: %08X:%04X %08X:%04X %02X %08X:%08X %02X:%08lX "
- "%08X %5d %8d %lu %d %pK %lu %lu %u %u %d%n",
+ "%08X %5u %8d %lu %d %pK %lu %lu %u %u %d%n",
i, src, srcp, dest, destp, sk->sk_state,
tp->write_seq - tp->snd_una,
rx_queue,
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 766e6bab9113..0b24508bcdc4 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -704,7 +704,7 @@ EXPORT_SYMBOL(udp_flush_pending_frames);
* @src: source IP address
* @dst: destination IP address
*/
-static void udp4_hwcsum(struct sk_buff *skb, __be32 src, __be32 dst)
+void udp4_hwcsum(struct sk_buff *skb, __be32 src, __be32 dst)
{
struct udphdr *uh = udp_hdr(skb);
struct sk_buff *frags = skb_shinfo(skb)->frag_list;
@@ -740,6 +740,7 @@ static void udp4_hwcsum(struct sk_buff *skb, __be32 src, __be32 dst)
uh->check = CSUM_MANGLED_0;
}
}
+EXPORT_SYMBOL_GPL(udp4_hwcsum);
static int udp_send_skb(struct sk_buff *skb, struct flowi4 *fl4)
{
@@ -2158,7 +2159,7 @@ static void udp4_format_sock(struct sock *sp, struct seq_file *f,
__u16 srcp = ntohs(inet->inet_sport);
seq_printf(f, "%5d: %08X:%04X %08X:%04X"
- " %02X %08X:%08X %02X:%08lX %08X %5d %8d %lu %d %pK %d%n",
+ " %02X %08X:%08X %02X:%08lX %08X %5u %8d %lu %d %pK %d%n",
bucket, src, srcp, dest, destp, sp->sk_state,
sk_wmem_alloc_get(sp),
sk_rmem_alloc_get(sp),
generated by cgit v1.2.3 (git 2.39.0) at 2025-01-25 07:18:31 +0300