summaryrefslogtreecommitdiffstats
path: root/net/ipv4
diff options
context:
space:
mode:
Diffstat (limited to 'net/ipv4')
-rw-r--r--net/ipv4/Kconfig11
-rw-r--r--net/ipv4/af_inet.c4
-rw-r--r--net/ipv4/ah4.c7
-rw-r--r--net/ipv4/arp.c8
-rw-r--r--net/ipv4/devinet.c2
-rw-r--r--net/ipv4/esp4.c7
-rw-r--r--net/ipv4/fib_frontend.c2
-rw-r--r--net/ipv4/icmp.c51
-rw-r--r--net/ipv4/igmp.c2
-rw-r--r--net/ipv4/ip_gre.c2
-rw-r--r--net/ipv4/ip_tunnel.c4
-rw-r--r--net/ipv4/ipcomp.c7
-rw-r--r--net/ipv4/ipip.c2
-rw-r--r--net/ipv4/ipmr.c10
-rw-r--r--net/ipv4/netfilter/ipt_MASQUERADE.c7
-rw-r--r--net/ipv4/ping.c641
-rw-r--r--net/ipv4/route.c77
-rw-r--r--net/ipv4/tcp.c104
-rw-r--r--net/ipv4/tcp_input.c501
-rw-r--r--net/ipv4/tcp_ipv4.c10
-rw-r--r--net/ipv4/tcp_minisocks.c6
-rw-r--r--net/ipv4/udp.c4
-rw-r--r--net/ipv4/xfrm4_tunnel.c2
23 files changed, 822 insertions, 649 deletions
diff --git a/net/ipv4/Kconfig b/net/ipv4/Kconfig
index 8603ca8..37cf1a6 100644
--- a/net/ipv4/Kconfig
+++ b/net/ipv4/Kconfig
@@ -9,10 +9,7 @@ config IP_MULTICAST
intend to participate in the MBONE, a high bandwidth network on top
of the Internet which carries audio and video broadcasts. More
information about the MBONE is on the WWW at
- <http://www.savetz.com/mbone/>. Information about the multicast
- capabilities of the various network cards is contained in
- <file:Documentation/networking/multicast.txt>. For most people, it's
- safe to say N.
+ <http://www.savetz.com/mbone/>. For most people, it's safe to say N.
config IP_ADVANCED_ROUTER
bool "IP: advanced router"
@@ -223,10 +220,8 @@ config IP_MROUTE
packets that have several destination addresses. It is needed on the
MBONE, a high bandwidth network on top of the Internet which carries
audio and video broadcasts. In order to do that, you would most
- likely run the program mrouted. Information about the multicast
- capabilities of the various network cards is contained in
- <file:Documentation/networking/multicast.txt>. If you haven't heard
- about it, you don't need it.
+ likely run the program mrouted. If you haven't heard about it, you
+ don't need it.
config IP_MROUTE_MULTIPLE_TABLES
bool "IP: multicast policy routing"
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index d01be2a..9c090c7 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -1295,6 +1295,7 @@ static struct sk_buff *inet_gso_segment(struct sk_buff *skb,
SKB_GSO_GRE |
SKB_GSO_TCPV6 |
SKB_GSO_UDP_TUNNEL |
+ SKB_GSO_MPLS |
0)))
goto out;
@@ -1384,7 +1385,7 @@ static struct sk_buff **inet_gro_receive(struct sk_buff **head,
goto out_unlock;
id = ntohl(*(__be32 *)&iph->id);
- flush = (u16)((ntohl(*(__be32 *)iph) ^ skb_gro_len(skb)) | (id ^ IP_DF));
+ flush = (u16)((ntohl(*(__be32 *)iph) ^ skb_gro_len(skb)) | (id & ~IP_DF));
id >>= 16;
for (p = *head; p; p = p->next) {
@@ -1406,6 +1407,7 @@ static struct sk_buff **inet_gro_receive(struct sk_buff **head,
NAPI_GRO_CB(p)->flush |=
(iph->ttl ^ iph2->ttl) |
(iph->tos ^ iph2->tos) |
+ ((iph->frag_off ^ iph2->frag_off) & htons(IP_DF)) |
((u16)(ntohs(iph2->id) + NAPI_GRO_CB(p)->count) ^ id);
NAPI_GRO_CB(p)->flush |= flush;
diff --git a/net/ipv4/ah4.c b/net/ipv4/ah4.c
index 2e7f194..7179026 100644
--- a/net/ipv4/ah4.c
+++ b/net/ipv4/ah4.c
@@ -419,12 +419,9 @@ static void ah4_err(struct sk_buff *skb, u32 info)
if (!x)
return;
- if (icmp_hdr(skb)->type == ICMP_DEST_UNREACH) {
- atomic_inc(&flow_cache_genid);
- rt_genid_bump(net);
-
+ if (icmp_hdr(skb)->type == ICMP_DEST_UNREACH)
ipv4_update_pmtu(skb, net, info, 0, 0, IPPROTO_AH, 0);
- } else
+ else
ipv4_redirect(skb, net, 0, 0, IPPROTO_AH, 0);
xfrm_state_put(x);
}
diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c
index 247ec19..4429b01 100644
--- a/net/ipv4/arp.c
+++ b/net/ipv4/arp.c
@@ -1234,13 +1234,19 @@ out:
static int arp_netdev_event(struct notifier_block *this, unsigned long event,
void *ptr)
{
- struct net_device *dev = ptr;
+ struct net_device *dev = netdev_notifier_info_to_dev(ptr);
+ struct netdev_notifier_change_info *change_info;
switch (event) {
case NETDEV_CHANGEADDR:
neigh_changeaddr(&arp_tbl, dev);
rt_cache_flush(dev_net(dev));
break;
+ case NETDEV_CHANGE:
+ change_info = ptr;
+ if (change_info->flags_changed & IFF_NOARP)
+ neigh_changeaddr(&arp_tbl, dev);
+ break;
default:
break;
}
diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c
index dfc39d4..b047e2d 100644
--- a/net/ipv4/devinet.c
+++ b/net/ipv4/devinet.c
@@ -1333,7 +1333,7 @@ static void inetdev_send_gratuitous_arp(struct net_device *dev,
static int inetdev_event(struct notifier_block *this, unsigned long event,
void *ptr)
{
- struct net_device *dev = ptr;
+ struct net_device *dev = netdev_notifier_info_to_dev(ptr);
struct in_device *in_dev = __in_dev_get_rtnl(dev);
ASSERT_RTNL();
diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c
index 4cfe34d..ab3d814b 100644
--- a/net/ipv4/esp4.c
+++ b/net/ipv4/esp4.c
@@ -502,12 +502,9 @@ static void esp4_err(struct sk_buff *skb, u32 info)
if (!x)
return;
- if (icmp_hdr(skb)->type == ICMP_DEST_UNREACH) {
- atomic_inc(&flow_cache_genid);
- rt_genid_bump(net);
-
+ if (icmp_hdr(skb)->type == ICMP_DEST_UNREACH)
ipv4_update_pmtu(skb, net, info, 0, 0, IPPROTO_ESP, 0);
- } else
+ else
ipv4_redirect(skb, net, 0, 0, IPPROTO_ESP, 0);
xfrm_state_put(x);
}
diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index c7629a2..05a4888 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -1038,7 +1038,7 @@ static int fib_inetaddr_event(struct notifier_block *this, unsigned long event,
static int fib_netdev_event(struct notifier_block *this, unsigned long event, void *ptr)
{
- struct net_device *dev = ptr;
+ struct net_device *dev = netdev_notifier_info_to_dev(ptr);
struct in_device *in_dev;
struct net *net = dev_net(dev);
diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c
index 76e10b4..5f7d11a 100644
--- a/net/ipv4/icmp.c
+++ b/net/ipv4/icmp.c
@@ -482,7 +482,7 @@ void icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info)
{
struct iphdr *iph;
int room;
- struct icmp_bxm icmp_param;
+ struct icmp_bxm *icmp_param;
struct rtable *rt = skb_rtable(skb_in);
struct ipcm_cookie ipc;
struct flowi4 fl4;
@@ -503,7 +503,8 @@ void icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info)
iph = ip_hdr(skb_in);
if ((u8 *)iph < skb_in->head ||
- (skb_in->network_header + sizeof(*iph)) > skb_in->tail)
+ (skb_network_header(skb_in) + sizeof(*iph)) >
+ skb_tail_pointer(skb_in))
goto out;
/*
@@ -557,9 +558,13 @@ void icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info)
}
}
+ icmp_param = kmalloc(sizeof(*icmp_param), GFP_ATOMIC);
+ if (!icmp_param)
+ return;
+
sk = icmp_xmit_lock(net);
if (sk == NULL)
- return;
+ goto out_free;
/*
* Construct source address and options.
@@ -585,7 +590,7 @@ void icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info)
IPTOS_PREC_INTERNETCONTROL) :
iph->tos;
- if (ip_options_echo(&icmp_param.replyopts.opt.opt, skb_in))
+ if (ip_options_echo(&icmp_param->replyopts.opt.opt, skb_in))
goto out_unlock;
@@ -593,19 +598,19 @@ void icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info)
* Prepare data for ICMP header.
*/
- icmp_param.data.icmph.type = type;
- icmp_param.data.icmph.code = code;
- icmp_param.data.icmph.un.gateway = info;
- icmp_param.data.icmph.checksum = 0;
- icmp_param.skb = skb_in;
- icmp_param.offset = skb_network_offset(skb_in);
+ icmp_param->data.icmph.type = type;
+ icmp_param->data.icmph.code = code;
+ icmp_param->data.icmph.un.gateway = info;
+ icmp_param->data.icmph.checksum = 0;
+ icmp_param->skb = skb_in;
+ icmp_param->offset = skb_network_offset(skb_in);
inet_sk(sk)->tos = tos;
ipc.addr = iph->saddr;
- ipc.opt = &icmp_param.replyopts.opt;
+ ipc.opt = &icmp_param->replyopts.opt;
ipc.tx_flags = 0;
rt = icmp_route_lookup(net, &fl4, skb_in, iph, saddr, tos,
- type, code, &icmp_param);
+ type, code, icmp_param);
if (IS_ERR(rt))
goto out_unlock;
@@ -617,19 +622,21 @@ void icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info)
room = dst_mtu(&rt->dst);
if (room > 576)
room = 576;
- room -= sizeof(struct iphdr) + icmp_param.replyopts.opt.opt.optlen;
+ room -= sizeof(struct iphdr) + icmp_param->replyopts.opt.opt.optlen;
room -= sizeof(struct icmphdr);
- icmp_param.data_len = skb_in->len - icmp_param.offset;
- if (icmp_param.data_len > room)
- icmp_param.data_len = room;
- icmp_param.head_len = sizeof(struct icmphdr);
+ icmp_param->data_len = skb_in->len - icmp_param->offset;
+ if (icmp_param->data_len > room)
+ icmp_param->data_len = room;
+ icmp_param->head_len = sizeof(struct icmphdr);
- icmp_push_reply(&icmp_param, &fl4, &ipc, &rt);
+ icmp_push_reply(icmp_param, &fl4, &ipc, &rt);
ende:
ip_rt_put(rt);
out_unlock:
icmp_xmit_unlock(sk);
+out_free:
+ kfree(icmp_param);
out:;
}
EXPORT_SYMBOL(icmp_send);
@@ -657,7 +664,8 @@ static void icmp_socket_deliver(struct sk_buff *skb, u32 info)
}
/*
- * Handle ICMP_DEST_UNREACH, ICMP_TIME_EXCEED, and ICMP_QUENCH.
+ * Handle ICMP_DEST_UNREACH, ICMP_TIME_EXCEED, ICMP_QUENCH, and
+ * ICMP_PARAMETERPROB.
*/
static void icmp_unreach(struct sk_buff *skb)
@@ -939,7 +947,8 @@ error:
void icmp_err(struct sk_buff *skb, u32 info)
{
struct iphdr *iph = (struct iphdr *)skb->data;
- struct icmphdr *icmph = (struct icmphdr *)(skb->data+(iph->ihl<<2));
+ int offset = iph->ihl<<2;
+ struct icmphdr *icmph = (struct icmphdr *)(skb->data + offset);
int type = icmp_hdr(skb)->type;
int code = icmp_hdr(skb)->code;
struct net *net = dev_net(skb->dev);
@@ -949,7 +958,7 @@ void icmp_err(struct sk_buff *skb, u32 info)
* triggered by ICMP_ECHOREPLY which sent from kernel.
*/
if (icmph->type != ICMP_ECHOREPLY) {
- ping_err(skb, info);
+ ping_err(skb, offset, info);
return;
}
diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c
index d8c2327..450f625 100644
--- a/net/ipv4/igmp.c
+++ b/net/ipv4/igmp.c
@@ -363,7 +363,7 @@ static struct sk_buff *igmpv3_newpack(struct net_device *dev, int size)
static int igmpv3_sendpack(struct sk_buff *skb)
{
struct igmphdr *pig = igmp_hdr(skb);
- const int igmplen = skb->tail - skb->transport_header;
+ const int igmplen = skb_tail_pointer(skb) - skb_transport_header(skb);
pig->csum = ip_compute_csum(igmp_hdr(skb), igmplen);
diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index 2a83591..a982657 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -429,7 +429,7 @@ static void __gre_xmit(struct sk_buff *skb, struct net_device *dev,
return;
}
- ip_tunnel_xmit(skb, dev, tnl_params);
+ ip_tunnel_xmit(skb, dev, tnl_params, tnl_params->protocol);
}
static netdev_tx_t ipgre_xmit(struct sk_buff *skb,
diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c
index be2f8da..7c79cf8 100644
--- a/net/ipv4/ip_tunnel.c
+++ b/net/ipv4/ip_tunnel.c
@@ -487,7 +487,7 @@ drop:
EXPORT_SYMBOL_GPL(ip_tunnel_rcv);
void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev,
- const struct iphdr *tnl_params)
+ const struct iphdr *tnl_params, const u8 protocol)
{
struct ip_tunnel *tunnel = netdev_priv(dev);
const struct iphdr *inner_iph;
@@ -670,7 +670,7 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev,
iph->version = 4;
iph->ihl = sizeof(struct iphdr) >> 2;
iph->frag_off = df;
- iph->protocol = tnl_params->protocol;
+ iph->protocol = protocol;
iph->tos = ip_tunnel_ecn_encap(tos, inner_iph, skb);
iph->daddr = fl4.daddr;
iph->saddr = fl4.saddr;
diff --git a/net/ipv4/ipcomp.c b/net/ipv4/ipcomp.c
index 59cb8c7..826be4c 100644
--- a/net/ipv4/ipcomp.c
+++ b/net/ipv4/ipcomp.c
@@ -47,12 +47,9 @@ static void ipcomp4_err(struct sk_buff *skb, u32 info)
if (!x)
return;
- if (icmp_hdr(skb)->type == ICMP_DEST_UNREACH) {
- atomic_inc(&flow_cache_genid);
- rt_genid_bump(net);
-
+ if (icmp_hdr(skb)->type == ICMP_DEST_UNREACH)
ipv4_update_pmtu(skb, net, info, 0, 0, IPPROTO_COMP, 0);
- } else
+ else
ipv4_redirect(skb, net, 0, 0, IPPROTO_COMP, 0);
xfrm_state_put(x);
}
diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c
index 77bfcce..9df7ecd 100644
--- a/net/ipv4/ipip.c
+++ b/net/ipv4/ipip.c
@@ -222,7 +222,7 @@ static netdev_tx_t ipip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev)
skb->encapsulation = 1;
}
- ip_tunnel_xmit(skb, dev, tiph);
+ ip_tunnel_xmit(skb, dev, tiph, tiph->protocol);
return NETDEV_TX_OK;
tx_error:
diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index 9d9610a..df97f0a 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -945,6 +945,7 @@ static int ipmr_cache_report(struct mr_table *mrt,
struct igmpmsg *msg;
struct sock *mroute_sk;
int ret;
+ unsigned long tail_offset;
#ifdef CONFIG_IP_PIMSM
if (assert == IGMPMSG_WHOLEPKT)
@@ -980,7 +981,12 @@ static int ipmr_cache_report(struct mr_table *mrt,
/* Copy the IP header */
- skb->network_header = skb->tail;
+ tail_offset = skb_tail_offset(skb);
+ if (tail_offset > 0xffff) {
+ kfree_skb(skb);
+ return -EINVAL;
+ }
+ skb_set_network_header(skb, tail_offset);
skb_put(skb, ihl);
skb_copy_to_linear_data(skb, pkt->data, ihl);
ip_hdr(skb)->protocol = 0; /* Flag to the kernel this is a route add */
@@ -1609,7 +1615,7 @@ int ipmr_compat_ioctl(struct sock *sk, unsigned int cmd, void __user *arg)
static int ipmr_device_event(struct notifier_block *this, unsigned long event, void *ptr)
{
- struct net_device *dev = ptr;
+ struct net_device *dev = netdev_notifier_info_to_dev(ptr);
struct net *net = dev_net(dev);
struct mr_table *mrt;
struct vif_device *v;
diff --git a/net/ipv4/netfilter/ipt_MASQUERADE.c b/net/ipv4/netfilter/ipt_MASQUERADE.c
index 5d5d4d1..30e4de9 100644
--- a/net/ipv4/netfilter/ipt_MASQUERADE.c
+++ b/net/ipv4/netfilter/ipt_MASQUERADE.c
@@ -108,7 +108,7 @@ static int masq_device_event(struct notifier_block *this,
unsigned long event,
void *ptr)
{
- const struct net_device *dev = ptr;
+ const struct net_device *dev = netdev_notifier_info_to_dev(ptr);
struct net *net = dev_net(dev);
if (event == NETDEV_DOWN) {
@@ -129,7 +129,10 @@ static int masq_inet_event(struct notifier_block *this,
void *ptr)
{
struct net_device *dev = ((struct in_ifaddr *)ptr)->ifa_dev->dev;
- return masq_device_event(this, event, dev);
+ struct netdev_notifier_info info;
+
+ netdev_notifier_info_init(&info, dev);
+ return masq_device_event(this, event, &info);
}
static struct notifier_block masq_dev_notifier = {
diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c
index 7d93d62..1f1b2dd 100644
--- a/net/ipv4/ping.c
+++ b/net/ipv4/ping.c
@@ -33,7 +33,6 @@
#include <linux/netdevice.h>
#include <net/snmp.h>
#include <net/ip.h>
-#include <net/ipv6.h>
#include <net/icmp.h>
#include <net/protocol.h>
#include <linux/skbuff.h>
@@ -46,8 +45,18 @@
#include <net/inet_common.h>
#include <net/checksum.h>
+#if IS_ENABLED(CONFIG_IPV6)
+#include <linux/in6.h>
+#include <linux/icmpv6.h>
+#include <net/addrconf.h>
+#include <net/ipv6.h>
+#include <net/transp_v6.h>
+#endif
-static struct ping_table ping_table;
+
+struct ping_table ping_table;
+struct pingv6_ops pingv6_ops;
+EXPORT_SYMBOL_GPL(pingv6_ops);
static u16 ping_port_rover;
@@ -58,6 +67,7 @@ static inline int ping_hashfn(struct net *net, unsigned int num, unsigned int ma
pr_debug("hash(%d) = %d\n", num, res);
return res;
}
+EXPORT_SYMBOL_GPL(ping_hash);
static inline struct hlist_nulls_head *ping_hashslot(struct ping_table *table,
struct net *net, unsigned int num)
@@ -65,7 +75,7 @@ static inline struct hlist_nulls_head *ping_hashslot(struct ping_table *table,
return &table->hash[ping_hashfn(net, num, PING_HTABLE_MASK)];
}
-static int ping_v4_get_port(struct sock *sk, unsigned short ident)
+int ping_get_port(struct sock *sk, unsigned short ident)
{
struct hlist_nulls_node *node;
struct hlist_nulls_head *hlist;
@@ -103,6 +113,10 @@ next_port:
ping_portaddr_for_each_entry(sk2, node, hlist) {
isk2 = inet_sk(sk2);
+ /* BUG? Why is this reuse and not reuseaddr? ping.c
+ * doesn't turn off SO_REUSEADDR, and it doesn't expect
+ * that other ping processes can steal its packets.
+ */
if ((isk2->inet_num == ident) &&
(sk2 != sk) &&
(!sk2->sk_reuse || !sk->sk_reuse))
@@ -125,17 +139,18 @@ fail:
write_unlock_bh(&ping_table.lock);
return 1;
}
+EXPORT_SYMBOL_GPL(ping_get_port);
-static void ping_v4_hash(struct sock *sk)
+void ping_hash(struct sock *sk)
{
- pr_debug("ping_v4_hash(sk->port=%u)\n", inet_sk(sk)->inet_num);
+ pr_debug("ping_hash(sk->port=%u)\n", inet_sk(sk)->inet_num);
BUG(); /* "Please do not press this button again." */
}
-static void ping_v4_unhash(struct sock *sk)
+void ping_unhash(struct sock *sk)
{
struct inet_sock *isk = inet_sk(sk);
- pr_debug("ping_v4_unhash(isk=%p,isk->num=%u)\n", isk, isk->inet_num);
+ pr_debug("ping_unhash(isk=%p,isk->num=%u)\n", isk, isk->inet_num);
if (sk_hashed(sk)) {
write_lock_bh(&ping_table.lock);
hlist_nulls_del(&sk->sk_nulls_node);
@@ -146,31 +161,61 @@ static void ping_v4_unhash(struct sock *sk)
write_unlock_bh(&ping_table.lock);
}
}
+EXPORT_SYMBOL_GPL(ping_unhash);
-static struct sock *ping_v4_lookup(struct net *net, __be32 saddr, __be32 daddr,
- u16 ident, int dif)
+static struct sock *ping_lookup(struct net *net, struct sk_buff *skb, u16 ident)
{
struct hlist_nulls_head *hslot = ping_hashslot(&ping_table, net, ident);
struct sock *sk = NULL;
struct inet_sock *isk;
struct hlist_nulls_node *hnode;
+ int dif = skb->dev->ifindex;
+
+ if (skb->protocol == htons(ETH_P_IP)) {
+ pr_debug("try to find: num = %d, daddr = %pI4, dif = %d\n",
+ (int)ident, &ip_hdr(skb)->daddr, dif);
+#if IS_ENABLED(CONFIG_IPV6)
+ } else if (skb->protocol == htons(ETH_P_IPV6)) {
+ pr_debug("try to find: num = %d, daddr = %pI6c, dif = %d\n",
+ (int)ident, &ipv6_hdr(skb)->daddr, dif);
+#endif
+ }
- pr_debug("try to find: num = %d, daddr = %pI4, dif = %d\n",
- (int)ident, &daddr, dif);
read_lock_bh(&ping_table.lock);
ping_portaddr_for_each_entry(sk, hnode, hslot) {
isk = inet_sk(sk);
- pr_debug("found: %p: num = %d, daddr = %pI4, dif = %d\n", sk,
- (int)isk->inet_num, &isk->inet_rcv_saddr,
- sk->sk_bound_dev_if);
-
pr_debug("iterate\n");
if (isk->inet_num != ident)
continue;
- if (isk->inet_rcv_saddr && isk->inet_rcv_saddr != daddr)
- continue;
+
+ if (skb->protocol == htons(ETH_P_IP) &&
+ sk->sk_family == AF_INET) {
+ pr_debug("found: %p: num=%d, daddr=%pI4, dif=%d\n", sk,
+ (int) isk->inet_num, &isk->inet_rcv_saddr,
+ sk->sk_bound_dev_if);
+
+ if (isk->inet_rcv_saddr &&
+ isk->inet_rcv_saddr != ip_hdr(skb)->daddr)
+ continue;
+#if IS_ENABLED(CONFIG_IPV6)
+ } else if (skb->protocol == htons(ETH_P_IPV6) &&
+ sk->sk_family == AF_INET6) {
+ struct ipv6_pinfo *np = inet6_sk(sk);
+
+ pr_debug("found: %p: num=%d, daddr=%pI6c, dif=%d\n", sk,
+ (int) isk->inet_num,
+ &inet6_sk(sk)->rcv_saddr,
+ sk->sk_bound_dev_if);
+
+ if (!ipv6_addr_any(&np->rcv_saddr) &&
+ !ipv6_addr_equal(&np->rcv_saddr,
+ &ipv6_hdr(skb)->daddr))
+ continue;
+#endif
+ }
+
if (sk->sk_bound_dev_if && sk->sk_bound_dev_if != dif)
continue;
@@ -200,7 +245,7 @@ static void inet_get_ping_group_range_net(struct net *net, kgid_t *low,
}
-static int ping_init_sock(struct sock *sk)
+int ping_init_sock(struct sock *sk)
{
struct net *net = sock_net(sk);
kgid_t group = current_egid();
@@ -225,8 +270,9 @@ static int ping_init_sock(struct sock *sk)
return -EACCES;
}
+EXPORT_SYMBOL_GPL(ping_init_sock);
-static void ping_close(struct sock *sk, long timeout)
+void ping_close(struct sock *sk, long timeout)
{
pr_debug("ping_close(sk=%p,sk->num=%u)\n",
inet_sk(sk), inet_sk(sk)->inet_num);
@@ -234,36 +280,122 @@ static void ping_close(struct sock *sk, long timeout)
sk_common_release(sk);
}
+EXPORT_SYMBOL_GPL(ping_close);
+
+/* Checks the bind address and possibly modifies sk->sk_bound_dev_if. */
+int ping_check_bind_addr(struct sock *sk, struct inet_sock *isk,
+ struct sockaddr *uaddr, int addr_len) {
+ struct net *net = sock_net(sk);
+ if (sk->sk_family == AF_INET) {
+ struct sockaddr_in *addr = (struct sockaddr_in *) uaddr;
+ int chk_addr_ret;
+
+ if (addr_len < sizeof(*addr))
+ return -EINVAL;
+
+ pr_debug("ping_check_bind_addr(sk=%p,addr=%pI4,port=%d)\n",
+ sk, &addr->sin_addr.s_addr, ntohs(addr->sin_port));
+
+ chk_addr_ret = inet_addr_type(net, addr->sin_addr.s_addr);
+
+ if (addr->sin_addr.s_addr == htonl(INADDR_ANY))
+ chk_addr_ret = RTN_LOCAL;
+
+ if ((sysctl_ip_nonlocal_bind == 0 &&
+ isk->freebind == 0 && isk->transparent == 0 &&
+ chk_addr_ret != RTN_LOCAL) ||
+ chk_addr_ret == RTN_MULTICAST ||
+ chk_addr_ret == RTN_BROADCAST)
+ return -EADDRNOTAVAIL;
+
+#if IS_ENABLED(CONFIG_IPV6)
+ } else if (sk->sk_family == AF_INET6) {
+ struct sockaddr_in6 *addr = (struct sockaddr_in6 *) uaddr;
+ int addr_type, scoped, has_addr;
+ struct net_device *dev = NULL;
+
+ if (addr_len < sizeof(*addr))
+ return -EINVAL;
+
+ pr_debug("ping_check_bind_addr(sk=%p,addr=%pI6c,port=%d)\n",
+ sk, addr->sin6_addr.s6_addr, ntohs(addr->sin6_port));
+
+ addr_type = ipv6_addr_type(&addr->sin6_addr);
+ scoped = __ipv6_addr_needs_scope_id(addr_type);
+ if ((addr_type != IPV6_ADDR_ANY &&
+ !(addr_type & IPV6_ADDR_UNICAST)) ||
+ (scoped && !addr->sin6_scope_id))
+ return -EINVAL;
+
+ rcu_read_lock();
+ if (addr->sin6_scope_id) {
+ dev = dev_get_by_index_rcu(net, addr->sin6_scope_id);
+ if (!dev) {
+ rcu_read_unlock();
+ return -ENODEV;
+ }
+ }
+ has_addr = pingv6_ops.ipv6_chk_addr(net, &addr->sin6_addr, dev,
+ scoped);
+ rcu_read_unlock();
+
+ if (!(isk->freebind || isk->transparent || has_addr ||
+ addr_type == IPV6_ADDR_ANY))
+ return -EADDRNOTAVAIL;
+
+ if (scoped)
+ sk->sk_bound_dev_if = addr->sin6_scope_id;
+#endif
+ } else {
+ return -EAFNOSUPPORT;
+ }
+ return 0;
+}
+
+void ping_set_saddr(struct sock *sk, struct sockaddr *saddr)
+{
+ if (saddr->sa_family == AF_INET) {
+ struct inet_sock *isk = inet_sk(sk);
+ struct sockaddr_in *addr = (struct sockaddr_in *) saddr;
+ isk->inet_rcv_saddr = isk->inet_saddr = addr->sin_addr.s_addr;
+#if IS_ENABLED(CONFIG_IPV6)
+ } else if (saddr->sa_family == AF_INET6) {
+ struct sockaddr_in6 *addr = (struct sockaddr_in6 *) saddr;
+ struct ipv6_pinfo *np = inet6_sk(sk);
+ np->rcv_saddr = np->saddr = addr->sin6_addr;
+#endif
+ }
+}
+void ping_clear_saddr(struct sock *sk, int dif)
+{
+ sk->sk_bound_dev_if = dif;
+ if (sk->sk_family == AF_INET) {
+ struct inet_sock *isk = inet_sk(sk);
+ isk->inet_rcv_saddr = isk->inet_saddr = 0;
+#if IS_ENABLED(CONFIG_IPV6)
+ } else if (sk->sk_family == AF_INET6) {
+ struct ipv6_pinfo *np = inet6_sk(sk);
+ memset(&np->rcv_saddr, 0, sizeof(np->rcv_saddr));
+ memset(&np->saddr, 0, sizeof(np->saddr));
+#endif
+ }
+}
/*
* We need our own bind because there are no privileged id's == local ports.
* Moreover, we don't allow binding to multi- and broadcast addresses.
*/
-static int ping_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len)
+int ping_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len)
{
- struct sockaddr_in *addr = (struct sockaddr_in *)uaddr;
struct inet_sock *isk = inet_sk(sk);
unsigned short snum;
- int chk_addr_ret;
int err;
+ int dif = sk->sk_bound_dev_if;
- if (addr_len < sizeof(struct sockaddr_in))
- return -EINVAL;
-
- pr_debug("ping_v4_bind(sk=%p,sa_addr=%08x,sa_port=%d)\n",
- sk, addr->sin_addr.s_addr, ntohs(addr->sin_port));
-
- chk_addr_ret = inet_addr_type(sock_net(sk), addr->sin_addr.s_addr);
- if (addr->sin_addr.s_addr == htonl(INADDR_ANY))
- chk_addr_ret = RTN_LOCAL;
-
- if ((sysctl_ip_nonlocal_bind == 0 &&
- isk->freebind == 0 && isk->transparent == 0 &&
- chk_addr_ret != RTN_LOCAL) ||
- chk_addr_ret == RTN_MULTICAST ||
- chk_addr_ret == RTN_BROADCAST)
- return -EADDRNOTAVAIL;
+ err = ping_check_bind_addr(sk, isk, uaddr, addr_len);
+ if (err)
+ return err;
lock_sock(sk);
@@ -272,42 +404,50 @@ static int ping_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len)
goto out;
err = -EADDRINUSE;
- isk->inet_rcv_saddr = isk->inet_saddr = addr->sin_addr.s_addr;
- snum = ntohs(addr->sin_port);
- if (ping_v4_get_port(sk, snum) != 0) {
- isk->inet_saddr = isk->inet_rcv_saddr = 0;
+ ping_set_saddr(sk, uaddr);
+ snum = ntohs(((struct sockaddr_in *)uaddr)->sin_port);
+ if (ping_get_port(sk, snum) != 0) {
+ ping_clear_saddr(sk, dif);
goto out;
}
- pr_debug("after bind(): num = %d, daddr = %pI4, dif = %d\n",
+ pr_debug("after bind(): num = %d, dif = %d\n",
(int)isk->inet_num,
- &isk->inet_rcv_saddr,
(int)sk->sk_bound_dev_if);
err = 0;
- if (isk->inet_rcv_saddr)
+ if ((sk->sk_family == AF_INET && isk->inet_rcv_saddr) ||
+ (sk->sk_family == AF_INET6 &&
+ !ipv6_addr_any(&inet6_sk(sk)->rcv_saddr)))
sk->sk_userlocks |= SOCK_BINDADDR_LOCK;
+
if (snum)
sk->sk_userlocks |= SOCK_BINDPORT_LOCK;
isk->inet_sport = htons(isk->inet_num);
isk->inet_daddr = 0;
isk->inet_dport = 0;
+
+#if IS_ENABLED(CONFIG_IPV6)
+ if (sk->sk_family == AF_INET6)
+ memset(&inet6_sk(sk)->daddr, 0, sizeof(inet6_sk(sk)->daddr));
+#endif
+
sk_dst_reset(sk);
out:
release_sock(sk);
pr_debug("ping_v4_bind -> %d\n", err);
return err;
}
+EXPORT_SYMBOL_GPL(ping_bind);
/*
* Is this a supported type of ICMP message?
*/
-static inline int ping_supported(int type, int code)
+static inline int ping_supported(int family, int type, int code)
{
- if (type == ICMP_ECHO && code == 0)
- return 1;
- return 0;
+ return (family == AF_INET && type == ICMP_ECHO && code == 0) ||
+ (family == AF_INET6 && type == ICMPV6_ECHO_REQUEST && code == 0);
}
/*
@@ -315,30 +455,42 @@ static inline int ping_supported(int type, int code)
* sort of error condition.
*/
-static int ping_queue_rcv_skb(struct sock *sk, struct sk_buff *skb);
-
-void ping_err(struct sk_buff *skb, u32 info)
+void ping_err(struct sk_buff *skb, int offset, u32 info)
{
- struct iphdr *iph = (struct iphdr *)skb->data;
- struct icmphdr *icmph = (struct icmphdr *)(skb->data+(iph->ihl<<2));
+ int family;
+ struct icmphdr *icmph;
struct inet_sock *inet_sock;
- int type = icmp_hdr(skb)->type;
- int code = icmp_hdr(skb)->code;
+ int type;
+ int code;
struct net *net = dev_net(skb->dev);
struct sock *sk;
int harderr;
int err;
+ if (skb->protocol == htons(ETH_P_IP)) {
+ family = AF_INET;
+ type = icmp_hdr(skb)->type;
+ code = icmp_hdr(skb)->code;
+ icmph = (struct icmphdr *)(skb->data + offset);
+ } else if (skb->protocol == htons(ETH_P_IPV6)) {
+ family = AF_INET6;
+ type = icmp6_hdr(skb)->icmp6_type;
+ code = icmp6_hdr(skb)->icmp6_code;
+ icmph = (struct icmphdr *) (skb->data + offset);
+ } else {
+ BUG();
+ }
+
/* We assume the packet has already been checked by icmp_unreach */
- if (!ping_supported(icmph->type, icmph->code))
+ if (!ping_supported(family, icmph->type, icmph->code))
return;
- pr_debug("ping_err(type=%04x,code=%04x,id=%04x,seq=%04x)\n", type,
- code, ntohs(icmph->un.echo.id), ntohs(icmph->un.echo.sequence));
+ pr_debug("ping_err(proto=0x%x,type=%d,code=%d,id=%04x,seq=%04x)\n",
+ skb->protocol, type, code, ntohs(icmph->un.echo.id),
+ ntohs(icmph->un.echo.sequence));
- sk = ping_v4_lookup(net, iph->daddr, iph->saddr,
- ntohs(icmph->un.echo.id), skb->dev->ifindex);
+ sk = ping_lookup(net, skb, ntohs(icmph->un.echo.id));
if (sk == NULL) {
pr_debug("no socket, dropping\n");
return; /* No socket for error */
@@ -349,72 +501,83 @@ void ping_err(struct sk_buff *skb, u32 info)
harderr = 0;
inet_sock = inet_sk(sk);
- switch (type) {
- default:
- case ICMP_TIME_EXCEEDED:
- err = EHOSTUNREACH;
- break;
- case ICMP_SOURCE_QUENCH:
- /* This is not a real error but ping wants to see it.
- * Report it with some fake errno. */
- err = EREMOTEIO;
- break;
- case ICMP_PARAMETERPROB:
- err = EPROTO;
- harderr = 1;
- break;
- case ICMP_DEST_UNREACH:
- if (code == ICMP_FRAG_NEEDED) { /* Path MTU discovery */
- ipv4_sk_update_pmtu(skb, sk, info);
- if (inet_sock->pmtudisc != IP_PMTUDISC_DONT) {
- err = EMSGSIZE;
- harderr = 1;
- break;
+ if (skb->protocol == htons(ETH_P_IP)) {
+ switch (type) {
+ default:
+ case ICMP_TIME_EXCEEDED:
+ err = EHOSTUNREACH;
+ break;
+ case ICMP_SOURCE_QUENCH:
+ /* This is not a real error but ping wants to see it.
+ * Report it with some fake errno.
+ */
+ err = EREMOTEIO;
+ break;
+ case ICMP_PARAMETERPROB:
+ err = EPROTO;
+ harderr = 1;
+ break;
+ case ICMP_DEST_UNREACH:
+ if (code == ICMP_FRAG_NEEDED) { /* Path MTU discovery */
+ ipv4_sk_update_pmtu(skb, sk, info);
+ if (inet_sock->pmtudisc != IP_PMTUDISC_DONT) {
+ err = EMSGSIZE;
+ harderr = 1;
+ break;
+ }
+ goto out;
}
- goto out;
- }
- err = EHOSTUNREACH;
- if (code <= NR_ICMP_UNREACH) {
- harderr = icmp_err_convert[code].fatal;
- err = icmp_err_convert[code].errno;
+ err = EHOSTUNREACH;
+ if (code <= NR_ICMP_UNREACH) {
+ harderr = icmp_err_convert[code].fatal;
+ err = icmp_err_convert[code].errno;
+ }
+ break;
+ case ICMP_REDIRECT:
+ /* See ICMP_SOURCE_QUENCH */
+ ipv4_sk_redirect(skb, sk);
+ err = EREMOTEIO;
+ break;
}
- break;
- case ICMP_REDIRECT:
- /* See ICMP_SOURCE_QUENCH */
- ipv4_sk_redirect(skb, sk);
- err = EREMOTEIO;
- break;
+#if IS_ENABLED(CONFIG_IPV6)
+ } else if (skb->protocol == htons(ETH_P_IPV6)) {
+ harderr = pingv6_ops.icmpv6_err_convert(type, code, &err);
+#endif
}
/*
* RFC1122: OK. Passes ICMP errors back to application, as per
* 4.1.3.3.
*/
- if (!inet_sock->recverr) {
+ if ((family == AF_INET && !inet_sock->recverr) ||
+ (family == AF_INET6 && !inet6_sk(sk)->recverr)) {
if (!harderr || sk->sk_state != TCP_ESTABLISHED)
goto out;
} else {
- ip_icmp_error(sk, skb, err, 0 /* no remote port */,
- info, (u8 *)icmph);
+ if (family == AF_INET) {
+ ip_icmp_error(sk, skb, err, 0 /* no remote port */,
+ info, (u8 *)icmph);
+#if IS_ENABLED(CONFIG_IPV6)
+ } else if (family == AF_INET6) {
+ pingv6_ops.ipv6_icmp_error(sk, skb, err, 0,
+ info, (u8 *)icmph);
+#endif
+ }
}
sk->sk_err = err;
sk->sk_error_report(sk);
out:
sock_put(sk);
}
+EXPORT_SYMBOL_GPL(ping_err);
/*
- * Copy and checksum an ICMP Echo packet from user space into a buffer.
+ * Copy and checksum an ICMP Echo packet from user space into a buffer
+ * starting from the payload.
*/
-struct pingfakehdr {
- struct icmphdr icmph;
- struct iovec *iov;
- __wsum wcheck;
-};
-
-static int ping_getfrag(void *from, char *to,
- int offset, int fraglen, int odd, struct sk_buff *skb)
+int ping_getfrag(void *from, char *to,
+ int offset, int fraglen, int odd, struct sk_buff *skb)
{
struct pingfakehdr *pfh = (struct pingfakehdr *)from;
@@ -425,20 +588,33 @@ static int ping_getfrag(void *from, char *to,
pfh->iov, 0, fraglen - sizeof(struct icmphdr),
&pfh->wcheck))
return -EFAULT;
+ } else if (offset < sizeof(struct icmphdr)) {
+ BUG();
+ } else {
+ if (csum_partial_copy_fromiovecend
+ (to, pfh->iov, offset - sizeof(struct icmphdr),
+ fraglen, &pfh->wcheck))
+ return -EFAULT;
+ }
- return 0;
+#if IS_ENABLED(CONFIG_IPV6)
+ /* For IPv6, checksum each skb as we go along, as expected by
+ * icmpv6_push_pending_frames. For IPv4, accumulate the checksum in
+ * wcheck, it will be finalized in ping_v4_push_pending_frames.
+ */
+ if (pfh->family == AF_INET6) {
+ skb->csum = pfh->wcheck;
+ skb->ip_summed = CHECKSUM_NONE;
+ pfh->wcheck = 0;
}
- if (offset < sizeof(struct icmphdr))
- BUG();
- if (csum_partial_copy_fromiovecend
- (to, pfh->iov, offset - sizeof(struct icmphdr),
- fraglen, &pfh->wcheck))
- return -EFAULT;
+#endif
+
return 0;
}
+EXPORT_SYMBOL_GPL(ping_getfrag);
-static int ping_push_pending_frames(struct sock *sk, struct pingfakehdr *pfh,
- struct flowi4 *fl4)
+static int ping_v4_push_pending_frames(struct sock *sk, struct pingfakehdr *pfh,
+ struct flowi4 *fl4)
{
struct sk_buff *skb = skb_peek(&sk->sk_write_queue);
@@ -450,24 +626,9 @@ static int ping_push_pending_frames(struct sock *sk, struct pingfakehdr *pfh,
return ip_push_pending_frames(sk, fl4);
}
-static int ping_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
- size_t len)
-{
- struct net *net = sock_net(sk);
- struct flowi4 fl4;
- struct inet_sock *inet = inet_sk(sk);
- struct ipcm_cookie ipc;
- struct icmphdr user_icmph;
- struct pingfakehdr pfh;
- struct rtable *rt = NULL;
- struct ip_options_data opt_copy;
- int free = 0;
- __be32 saddr, daddr, faddr;
- u8 tos;
- int err;
-
- pr_debug("ping_sendmsg(sk=%p,sk->num=%u)\n", inet, inet->inet_num);
-
+int ping_common_sendmsg(int family, struct msghdr *msg, size_t len,
+ void *user_icmph, size_t icmph_len) {
+ u8 type, code;
if (len > 0xFFFF)
return -EMSGSIZE;
@@ -482,15 +643,53 @@ static int ping_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
/*
* Fetch the ICMP header provided by the userland.
- * iovec is modified!
+ * iovec is modified! The ICMP header is consumed.
*/
-
- if (memcpy_fromiovec((u8 *)&user_icmph, msg->msg_iov,
- sizeof(struct icmphdr)))
+ if (memcpy_fromiovec(user_icmph, msg->msg_iov, icmph_len))
return -EFAULT;
- if (!ping_supported(user_icmph.type, user_icmph.code))
+
+ if (family == AF_INET) {
+ type = ((struct icmphdr *) user_icmph)->type;
+ code = ((struct icmphdr *) user_icmph)->code;
+#if IS_ENABLED(CONFIG_IPV6)
+ } else if (family == AF_INET6) {
+ type = ((struct icmp6hdr *) user_icmph)->icmp6_type;
+ code = ((struct icmp6hdr *) user_icmph)->icmp6_code;
+#endif
+ } else {
+ BUG();
+ }
+
+ if (!ping_supported(family, type, code))
return -EINVAL;
+ return 0;
+}
+EXPORT_SYMBOL_GPL(ping_common_sendmsg);
+
+int ping_v4_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
+ size_t len)
+{
+ struct net *net = sock_net(sk);
+ struct flowi4 fl4;
+ struct inet_sock *inet = inet_sk(sk);
+ struct ipcm_cookie ipc;
+ struct icmphdr user_icmph;
+ struct pingfakehdr pfh;
+ struct rtable *rt = NULL;
+ struct ip_options_data opt_copy;
+ int free = 0;
+ __be32 saddr, daddr, faddr;
+ u8 tos;
+ int err;
+
+ pr_debug("ping_v4_sendmsg(sk=%p,sk->num=%u)\n", inet, inet->inet_num);
+
+ err = ping_common_sendmsg(AF_INET, msg, len, &user_icmph,
+ sizeof(user_icmph));
+ if (err)
+ return err;
+
/*
* Get and verify the address.
*/
@@ -595,13 +794,14 @@ back_from_confirm:
pfh.icmph.un.echo.sequence = user_icmph.un.echo.sequence;
pfh.iov = msg->msg_iov;
pfh.wcheck = 0;
+ pfh.family = AF_INET;
err = ip_append_data(sk, &fl4, ping_getfrag, &pfh, len,
0, &ipc, &rt, msg->msg_flags);
if (err)
ip_flush_pending_frames(sk);
else
- err = ping_push_pending_frames(sk, &pfh, &fl4);
+ err = ping_v4_push_pending_frames(sk, &pfh, &fl4);
release_sock(sk);
out:
@@ -622,11 +822,13 @@ do_confirm:
goto out;
}
-static int ping_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
- size_t len, int noblock, int flags, int *addr_len)
+int ping_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
+ size_t len, int noblock, int flags, int *addr_len)
{
struct inet_sock *isk = inet_sk(sk);
- struct sockaddr_in *sin = (struct sockaddr_in *)msg->msg_name;
+ int family = sk->sk_family;
+ struct sockaddr_in *sin;
+ struct sockaddr_in6 *sin6;
struct sk_buff *skb;
int copied, err;
@@ -636,11 +838,22 @@ static int ping_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
if (flags & MSG_OOB)
goto out;
- if (addr_len)
- *addr_len = sizeof(*sin);
+ if (addr_len) {
+ if (family == AF_INET)
+ *addr_len = sizeof(*sin);
+ else if (family == AF_INET6 && addr_len)
+ *addr_len = sizeof(*sin6);
+ }
- if (flags & MSG_ERRQUEUE)
- return ip_recv_error(sk, msg, len);
+ if (flags & MSG_ERRQUEUE) {
+ if (family == AF_INET) {
+ return ip_recv_error(sk, msg, len);
+#if IS_ENABLED(CONFIG_IPV6)
+ } else if (family == AF_INET6) {
+ return pingv6_ops.ipv6_recv_error(sk, msg, len);
+#endif
+ }
+ }
skb = skb_recv_datagram(sk, flags, noblock, &err);
if (!skb)
@@ -659,15 +872,40 @@ static int ping_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
sock_recv_timestamp(msg, sk, skb);
- /* Copy the address. */
- if (sin) {
+ /* Copy the address and add cmsg data. */
+ if (family == AF_INET) {
+ sin = (struct sockaddr_in *) msg->msg_name;
sin->sin_family = AF_INET;
sin->sin_port = 0 /* skb->h.uh->source */;
sin->sin_addr.s_addr = ip_hdr(skb)->saddr;
memset(sin->sin_zero, 0, sizeof(sin->sin_zero));
+
+ if (isk->cmsg_flags)
+ ip_cmsg_recv(msg, skb);
+
+#if IS_ENABLED(CONFIG_IPV6)
+ } else if (family == AF_INET6) {
+ struct ipv6_pinfo *np = inet6_sk(sk);
+ struct ipv6hdr *ip6 = ipv6_hdr(skb);
+ sin6 = (struct sockaddr_in6 *) msg->msg_name;
+ sin6->sin6_family = AF_INET6;
+ sin6->sin6_port = 0;
+ sin6->sin6_addr = ip6->saddr;
+
+ sin6->sin6_flowinfo = 0;
+ if (np->sndflow)
+ sin6->sin6_flowinfo = ip6_flowinfo(ip6);
+
+ sin6->sin6_scope_id = ipv6_iface_scope_id(&sin6->sin6_addr,
+ IP6CB(skb)->iif);
+
+ if (inet6_sk(sk)->rxopt.all)
+ pingv6_ops.ip6_datagram_recv_ctl(sk, msg, skb);
+#endif
+ } else {
+ BUG();
}
- if (isk->cmsg_flags)
- ip_cmsg_recv(msg, skb);
+
err = copied;
done:
@@ -676,8 +914,9 @@ out:
pr_debug("ping_recvmsg -> %d\n", err);
return err;
}
+EXPORT_SYMBOL_GPL(ping_recvmsg);
-static int ping_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
+int ping_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
{
pr_debug("ping_queue_rcv_skb(sk=%p,sk->num=%d,skb=%p)\n",
inet_sk(sk), inet_sk(sk)->inet_num, skb);
@@ -688,6 +927,7 @@ static int ping_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
}
return 0;
}
+EXPORT_SYMBOL_GPL(ping_queue_rcv_skb);
/*
@@ -698,10 +938,7 @@ void ping_rcv(struct sk_buff *skb)
{
struct sock *sk;
struct net *net = dev_net(skb->dev);
- struct iphdr *iph = ip_hdr(skb);
struct icmphdr *icmph = icmp_hdr(skb);
- __be32 saddr = iph->saddr;
- __be32 daddr = iph->daddr;
/* We assume the packet has already been checked by icmp_rcv */
@@ -711,8 +948,7 @@ void ping_rcv(struct sk_buff *skb)
/* Push ICMP header back */
skb_push(skb, skb->data - (u8 *)icmph);
- sk = ping_v4_lookup(net, saddr, daddr, ntohs(icmph->un.echo.id),
- skb->dev->ifindex);
+ sk = ping_lookup(net, skb, ntohs(icmph->un.echo.id));
if (sk != NULL) {
pr_debug("rcv on socket %p\n", sk);
ping_queue_rcv_skb(sk, skb_get(skb));
@@ -723,6 +959,7 @@ void ping_rcv(struct sk_buff *skb)
/* We're called from icmp_rcv(). kfree_skb() is done there. */
}
+EXPORT_SYMBOL_GPL(ping_rcv);
struct proto ping_prot = {
.name = "PING",
@@ -733,14 +970,14 @@ struct proto ping_prot = {
.disconnect = udp_disconnect,
.setsockopt = ip_setsockopt,
.getsockopt = ip_getsockopt,
- .sendmsg = ping_sendmsg,
+ .sendmsg = ping_v4_sendmsg,
.recvmsg = ping_recvmsg,
.bind = ping_bind,
.backlog_rcv = ping_queue_rcv_skb,
.release_cb = ip4_datagram_release_cb,
- .hash = ping_v4_hash,
- .unhash = ping_v4_unhash,
- .get_port = ping_v4_get_port,
+ .hash = ping_hash,
+ .unhash = ping_unhash,
+ .get_port = ping_get_port,
.obj_size = sizeof(struct inet_sock),
};
EXPORT_SYMBOL(ping_prot);
@@ -764,7 +1001,8 @@ static struct sock *ping_get_first(struct seq_file *seq, int start)
continue;
sk_nulls_for_each(sk, node, hslot) {
- if (net_eq(sock_net(sk), net))
+ if (net_eq(sock_net(sk), net) &&
+ sk->sk_family == state->family)
goto found;
}
}
@@ -797,17 +1035,24 @@ static struct sock *ping_get_idx(struct seq_file *seq, loff_t pos)
return pos ? NULL : sk;
}
-static void *ping_seq_start(struct seq_file *seq, loff_t *pos)
+void *ping_seq_start(struct seq_file *seq, loff_t *pos, sa_family_t family)
{
struct ping_iter_state *state = seq->private;
state->bucket = 0;
+ state->family = family;
read_lock_bh(&ping_table.lock);
return *pos ? ping_get_idx(seq, *pos-1) : SEQ_START_TOKEN;
}
+EXPORT_SYMBOL_GPL(ping_seq_start);
+
+static void *ping_v4_seq_start(struct seq_file *seq, loff_t *pos)
+{
+ return ping_seq_start(seq, pos, AF_INET);
+}
-static void *ping_seq_next(struct seq_file *seq, void *v, loff_t *pos)
+void *ping_seq_next(struct seq_file *seq, void *v, loff_t *pos)
{
struct sock *sk;
@@ -819,13 +1064,15 @@ static void *ping_seq_next(struct seq_file *seq, void *v, loff_t *pos)
++*pos;
return sk;
}
+EXPORT_SYMBOL_GPL(ping_seq_next);
-static void ping_seq_stop(struct seq_file *seq, void *v)
+void ping_seq_stop(struct seq_file *seq, void *v)
{
read_unlock_bh(&ping_table.lock);
}
+EXPORT_SYMBOL_GPL(ping_seq_stop);
-static void ping_format_sock(struct sock *sp, struct seq_file *f,
+static void ping_v4_format_sock(struct sock *sp, struct seq_file *f,
int bucket, int *len)
{
struct inet_sock *inet = inet_sk(sp);
@@ -846,7 +1093,7 @@ static void ping_format_sock(struct sock *sp, struct seq_file *f,
atomic_read(&sp->sk_drops), len);
}
-static int ping_seq_show(struct seq_file *seq, void *v)
+static int ping_v4_seq_show(struct seq_file *seq, void *v)
{
if (v == SEQ_START_TOKEN)
seq_printf(seq, "%-127s\n",
@@ -857,72 +1104,86 @@ static int ping_seq_show(struct seq_file *seq, void *v)
struct ping_iter_state *state = seq->private;
int len;
- ping_format_sock(v, seq, state->bucket, &len);
+ ping_v4_format_sock(v, seq, state->bucket, &len);
seq_printf(seq, "%*s\n", 127 - len, "");
}
return 0;
}
-static const struct seq_operations ping_seq_ops = {
- .show = ping_seq_show,
- .start = ping_seq_start,
+static const struct seq_operations ping_v4_seq_ops = {
+ .show = ping_v4_seq_show,
+ .start = ping_v4_seq_start,
.next = ping_seq_next,
.stop = ping_seq_stop,
};
static int ping_seq_open(struct inode *inode, struct file *file)
{
- return seq_open_net(inode, file, &ping_seq_ops,
+ struct ping_seq_afinfo *afinfo = PDE_DATA(inode);
+ return seq_open_net(inode, file, &afinfo->seq_ops,
sizeof(struct ping_iter_state));
}
-static const struct file_operations ping_seq_fops = {
+const struct file_operations ping_seq_fops = {
.open = ping_seq_open,
.read = seq_read,
.llseek = seq_lseek,
.release = seq_release_net,
};
+EXPORT_SYMBOL_GPL(ping_seq_fops);
+
+static struct ping_seq_afinfo ping_v4_seq_afinfo = {
+ .name = "icmp",
+ .family = AF_INET,
+ .seq_fops = &ping_seq_fops,
+ .seq_ops = {
+ .start = ping_v4_seq_start,
+ .show = ping_v4_seq_show,
+ .next = ping_seq_next,
+ .stop = ping_seq_stop,
+ },
+};
-static int ping_proc_register(struct net *net)
+int ping_proc_register(struct net *net, struct ping_seq_afinfo *afinfo)
{
struct proc_dir_entry *p;
- int rc = 0;
-
- p = proc_create("icmp", S_IRUGO, net->proc_net, &ping_seq_fops);
+ p = proc_create_data(afinfo->name, S_IRUGO, net->proc_net,
+ afinfo->seq_fops, afinfo);
if (!p)
- rc = -ENOMEM;
- return rc;
+ return -ENOMEM;
+ return 0;
}
+EXPORT_SYMBOL_GPL(ping_proc_register);
-static void ping_proc_unregister(struct net *net)
+void ping_proc_unregister(struct net *net, struct ping_seq_afinfo *afinfo)
{
- remove_proc_entry("icmp", net->proc_net);
+ remove_proc_entry(afinfo->name, net->proc_net);
}
+EXPORT_SYMBOL_GPL(ping_proc_unregister);
-
-static int __net_init ping_proc_init_net(struct net *net)
+static int __net_init ping_v4_proc_init_net(struct net *net)
{
- return ping_proc_register(net);
+ return ping_proc_register(net, &ping_v4_seq_afinfo);
}
-static void __net_exit ping_proc_exit_net(struct net *net)
+static void __net_exit ping_v4_proc_exit_net(struct net *net)
{
- ping_proc_unregister(net);
+ ping_proc_unregister(net, &ping_v4_seq_afinfo);
}
-static struct pernet_operations ping_net_ops = {
- .init = ping_proc_init_net,
- .exit = ping_proc_exit_net,
+static struct pernet_operations ping_v4_net_ops = {
+ .init = ping_v4_proc_init_net,
+ .exit = ping_v4_proc_exit_net,
};
int __init ping_proc_init(void)
{
- return register_pernet_subsys(&ping_net_ops);
+ return register_pernet_subsys(&ping_v4_net_ops);
}
void ping_proc_exit(void)
{
- unregister_pernet_subsys(&ping_net_ops);
+ unregister_pernet_subsys(&ping_v4_net_ops);
}
#endif
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index d35bbf0..198ea59 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -594,11 +594,25 @@ static inline u32 fnhe_hashfun(__be32 daddr)
return hval & (FNHE_HASH_SIZE - 1);
}
+static void fill_route_from_fnhe(struct rtable *rt, struct fib_nh_exception *fnhe)
+{
+ rt->rt_pmtu = fnhe->fnhe_pmtu;
+ rt->dst.expires = fnhe->fnhe_expires;
+
+ if (fnhe->fnhe_gw) {
+ rt->rt_flags |= RTCF_REDIRECTED;
+ rt->rt_gateway = fnhe->fnhe_gw;
+ rt->rt_uses_gateway = 1;
+ }
+}
+
static void update_or_create_fnhe(struct fib_nh *nh, __be32 daddr, __be32 gw,
u32 pmtu, unsigned long expires)
{
struct fnhe_hash_bucket *hash;
struct fib_nh_exception *fnhe;
+ struct rtable *rt;
+ unsigned int i;
int depth;
u32 hval = fnhe_hashfun(daddr);
@@ -627,8 +641,12 @@ static void update_or_create_fnhe(struct fib_nh *nh, __be32 daddr, __be32 gw,
fnhe->fnhe_gw = gw;
if (pmtu) {
fnhe->fnhe_pmtu = pmtu;
- fnhe->fnhe_expires = expires;
+ fnhe->fnhe_expires = max(1UL, expires);
}
+ /* Update all cached dsts too */
+ rt = rcu_dereference(fnhe->fnhe_rth);
+ if (rt)
+ fill_route_from_fnhe(rt, fnhe);
} else {
if (depth > FNHE_RECLAIM_DEPTH)
fnhe = fnhe_oldest(hash);
@@ -640,10 +658,23 @@ static void update_or_create_fnhe(struct fib_nh *nh, __be32 daddr, __be32 gw,
fnhe->fnhe_next = hash->chain;
rcu_assign_pointer(hash->chain, fnhe);
}
+ fnhe->fnhe_genid = fnhe_genid(dev_net(nh->nh_dev));
fnhe->fnhe_daddr = daddr;
fnhe->fnhe_gw = gw;
fnhe->fnhe_pmtu = pmtu;
fnhe->fnhe_expires = expires;
+
+ /* Exception created; mark the cached routes for the nexthop
+ * stale, so anyone caching it rechecks if this exception
+ * applies to them.
+ */
+ for_each_possible_cpu(i) {
+ struct rtable __rcu **prt;
+ prt = per_cpu_ptr(nh->nh_pcpu_rth_output, i);
+ rt = rcu_dereference(*prt);
+ if (rt)
+ rt->dst.obsolete = DST_OBSOLETE_KILL;
+ }
}
fnhe->fnhe_stamp = jiffies;
@@ -922,12 +953,9 @@ static void __ip_rt_update_pmtu(struct rtable *rt, struct flowi4 *fl4, u32 mtu)
if (mtu < ip_rt_min_pmtu)
mtu = ip_rt_min_pmtu;
- if (!rt->rt_pmtu) {
- dst->obsolete = DST_OBSOLETE_KILL;
- } else {
- rt->rt_pmtu = mtu;
- dst->expires = max(1UL, jiffies + ip_rt_mtu_expires);
- }
+ if (rt->rt_pmtu == mtu &&
+ time_before(jiffies, dst->expires - ip_rt_mtu_expires / 2))
+ return;
rcu_read_lock();
if (fib_lookup(dev_net(dst->dev), fl4, &res) == 0) {
@@ -1068,11 +1096,11 @@ static struct dst_entry *ipv4_dst_check(struct dst_entry *dst, u32 cookie)
* DST_OBSOLETE_FORCE_CHK which forces validation calls down
* into this function always.
*
- * When a PMTU/redirect information update invalidates a
- * route, this is indicated by setting obsolete to
- * DST_OBSOLETE_KILL.
+ * When a PMTU/redirect information update invalidates a route,
+ * this is indicated by setting obsolete to DST_OBSOLETE_KILL or
+ * DST_OBSOLETE_DEAD by dst_free().
*/
- if (dst->obsolete == DST_OBSOLETE_KILL || rt_is_expired(rt))
+ if (dst->obsolete != DST_OBSOLETE_FORCE_CHK || rt_is_expired(rt))
return NULL;
return dst;
}
@@ -1214,26 +1242,17 @@ static bool rt_bind_exception(struct rtable *rt, struct fib_nh_exception *fnhe,
spin_lock_bh(&fnhe_lock);
if (daddr == fnhe->fnhe_daddr) {
+ int genid = fnhe_genid(dev_net(rt->dst.dev));
struct rtable *orig = rcu_dereference(fnhe->fnhe_rth);
- if (orig && rt_is_expired(orig)) {
+
+ if (fnhe->fnhe_genid != genid) {
+ fnhe->fnhe_genid = genid;
fnhe->fnhe_gw = 0;
fnhe->fnhe_pmtu = 0;
fnhe->fnhe_expires = 0;
}
- if (fnhe->fnhe_pmtu) {
- unsigned long expires = fnhe->fnhe_expires;
- unsigned long diff = expires - jiffies;
-
- if (time_before(jiffies, expires)) {
- rt->rt_pmtu = fnhe->fnhe_pmtu;
- dst_set_expires(&rt->dst, diff);
- }
- }
- if (fnhe->fnhe_gw) {
- rt->rt_flags |= RTCF_REDIRECTED;
- rt->rt_gateway = fnhe->fnhe_gw;
- rt->rt_uses_gateway = 1;
- } else if (!rt->rt_gateway)
+ fill_route_from_fnhe(rt, fnhe);
+ if (!rt->rt_gateway)
rt->rt_gateway = daddr;
rcu_assign_pointer(fnhe->fnhe_rth, rt);
@@ -2433,8 +2452,11 @@ static int ipv4_sysctl_rtcache_flush(ctl_table *__ctl, int write,
void __user *buffer,
size_t *lenp, loff_t *ppos)
{
+ struct net *net = (struct net *)__ctl->extra1;
+
if (write) {
- rt_cache_flush((struct net *)__ctl->extra1);
+ rt_cache_flush(net);
+ fnhe_genid_bump(net);
return 0;
}
@@ -2609,6 +2631,7 @@ 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->fnhe_genid, 0);
get_random_bytes(&net->ipv4.dev_addr_genid,
sizeof(net->ipv4.dev_addr_genid));
return 0;
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index ab450c0..b5d4ad9 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -436,6 +436,8 @@ unsigned int tcp_poll(struct file *file, struct socket *sock, poll_table *wait)
struct sock *sk = sock->sk;
const struct tcp_sock *tp = tcp_sk(sk);
+ sock_rps_record_flow(sk);
+
sock_poll_wait(file, sk_sleep(sk), wait);
if (sk->sk_state == TCP_LISTEN)
return inet_csk_listen_poll(sk);
@@ -2917,6 +2919,7 @@ struct sk_buff *tcp_tso_segment(struct sk_buff *skb,
SKB_GSO_TCP_ECN |
SKB_GSO_TCPV6 |
SKB_GSO_GRE |
+ SKB_GSO_MPLS |
SKB_GSO_UDP_TUNNEL |
0) ||
!(type & (SKB_GSO_TCPV4 | SKB_GSO_TCPV6))))
@@ -2988,7 +2991,8 @@ struct sk_buff *tcp_tso_segment(struct sk_buff *skb,
swap(gso_skb->truesize, skb->truesize);
}
- delta = htonl(oldlen + (skb->tail - skb->transport_header) +
+ delta = htonl(oldlen + (skb_tail_pointer(skb) -
+ skb_transport_header(skb)) +
skb->data_len);
th->check = ~csum_fold((__force __wsum)((__force u32)th->check +
(__force u32)delta));
@@ -3115,9 +3119,8 @@ int tcp_gro_complete(struct sk_buff *skb)
EXPORT_SYMBOL(tcp_gro_complete);
#ifdef CONFIG_TCP_MD5SIG
-static unsigned long tcp_md5sig_users;
-static struct tcp_md5sig_pool __percpu *tcp_md5sig_pool;
-static DEFINE_SPINLOCK(tcp_md5sig_pool_lock);
+static struct tcp_md5sig_pool __percpu *tcp_md5sig_pool __read_mostly;
+static DEFINE_MUTEX(tcp_md5sig_mutex);
static void __tcp_free_md5sig_pool(struct tcp_md5sig_pool __percpu *pool)
{
@@ -3132,30 +3135,14 @@ static void __tcp_free_md5sig_pool(struct tcp_md5sig_pool __percpu *pool)
free_percpu(pool);
}
-void tcp_free_md5sig_pool(void)
-{
- struct tcp_md5sig_pool __percpu *pool = NULL;
-
- spin_lock_bh(&tcp_md5sig_pool_lock);
- if (--tcp_md5sig_users == 0) {
- pool = tcp_md5sig_pool;
- tcp_md5sig_pool = NULL;
- }
- spin_unlock_bh(&tcp_md5sig_pool_lock);
- if (pool)
- __tcp_free_md5sig_pool(pool);
-}
-EXPORT_SYMBOL(tcp_free_md5sig_pool);
-
-static struct tcp_md5sig_pool __percpu *
-__tcp_alloc_md5sig_pool(struct sock *sk)
+static void __tcp_alloc_md5sig_pool(void)
{
int cpu;
struct tcp_md5sig_pool __percpu *pool;
pool = alloc_percpu(struct tcp_md5sig_pool);
if (!pool)
- return NULL;
+ return;
for_each_possible_cpu(cpu) {
struct crypto_hash *hash;
@@ -3166,53 +3153,27 @@ __tcp_alloc_md5sig_pool(struct sock *sk)
per_cpu_ptr(pool, cpu)->md5_desc.tfm = hash;
}
- return pool;
+ /* before setting tcp_md5sig_pool, we must commit all writes
+ * to memory. See ACCESS_ONCE() in tcp_get_md5sig_pool()
+ */
+ smp_wmb();
+ tcp_md5sig_pool = pool;
+ return;
out_free:
__tcp_free_md5sig_pool(pool);
- return NULL;
}
-struct tcp_md5sig_pool __percpu *tcp_alloc_md5sig_pool(struct sock *sk)
+bool tcp_alloc_md5sig_pool(void)
{
- struct tcp_md5sig_pool __percpu *pool;
- bool alloc = false;
-
-retry:
- spin_lock_bh(&tcp_md5sig_pool_lock);
- pool = tcp_md5sig_pool;
- if (tcp_md5sig_users++ == 0) {
- alloc = true;
- spin_unlock_bh(&tcp_md5sig_pool_lock);
- } else if (!pool) {
- tcp_md5sig_users--;
- spin_unlock_bh(&tcp_md5sig_pool_lock);
- cpu_relax();
- goto retry;
- } else
- spin_unlock_bh(&tcp_md5sig_pool_lock);
-
- if (alloc) {
- /* we cannot hold spinlock here because this may sleep. */
- struct tcp_md5sig_pool __percpu *p;
-
- p = __tcp_alloc_md5sig_pool(sk);
- spin_lock_bh(&tcp_md5sig_pool_lock);
- if (!p) {
- tcp_md5sig_users--;
- spin_unlock_bh(&tcp_md5sig_pool_lock);
- return NULL;
- }
- pool = tcp_md5sig_pool;
- if (pool) {
- /* oops, it has already been assigned. */
- spin_unlock_bh(&tcp_md5sig_pool_lock);
- __tcp_free_md5sig_pool(p);
- } else {
- tcp_md5sig_pool = pool = p;
- spin_unlock_bh(&tcp_md5sig_pool_lock);
- }
+ if (unlikely(!tcp_md5sig_pool)) {
+ mutex_lock(&tcp_md5sig_mutex);
+
+ if (!tcp_md5sig_pool)
+ __tcp_alloc_md5sig_pool();
+
+ mutex_unlock(&tcp_md5sig_mutex);
}
- return pool;
+ return tcp_md5sig_pool != NULL;
}
EXPORT_SYMBOL(tcp_alloc_md5sig_pool);
@@ -3229,28 +3190,15 @@ struct tcp_md5sig_pool *tcp_get_md5sig_pool(void)
struct tcp_md5sig_pool __percpu *p;
local_bh_disable();
-
- spin_lock(&tcp_md5sig_pool_lock);
- p = tcp_md5sig_pool;
+ p = ACCESS_ONCE(tcp_md5sig_pool);
if (p)
- tcp_md5sig_users++;
- spin_unlock(&tcp_md5sig_pool_lock);
-
- if (p)
- return this_cpu_ptr(p);
+ return __this_cpu_ptr(p);
local_bh_enable();
return NULL;
}
EXPORT_SYMBOL(tcp_get_md5sig_pool);
-void tcp_put_md5sig_pool(void)
-{
- local_bh_enable();
- tcp_free_md5sig_pool();
-}
-EXPORT_SYMBOL(tcp_put_md5sig_pool);
-
int tcp_md5_hash_header(struct tcp_md5sig_pool *hp,
const struct tcphdr *th)
{
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 9c62257..907311c 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -360,9 +360,7 @@ static void tcp_fixup_rcvbuf(struct sock *sk)
if (mss > 1460)
icwnd = max_t(u32, (1460 * TCP_DEFAULT_INIT_RCVWND) / mss, 2);
- rcvmem = SKB_TRUESIZE(mss + MAX_TCP_HEADER);
- while (tcp_win_from_space(rcvmem) < mss)
- rcvmem += 128;
+ rcvmem = 2 * SKB_TRUESIZE(mss + MAX_TCP_HEADER);
rcvmem *= icwnd;
@@ -1257,8 +1255,6 @@ static bool tcp_shifted_skb(struct sock *sk, struct sk_buff *skb,
if (skb == tp->retransmit_skb_hint)
tp->retransmit_skb_hint = prev;
- if (skb == tp->scoreboard_skb_hint)
- tp->scoreboard_skb_hint = prev;
if (skb == tp->lost_skb_hint) {
tp->lost_skb_hint = prev;
tp->lost_cnt_hint -= tcp_skb_pcount(prev);
@@ -1966,20 +1962,6 @@ static bool tcp_pause_early_retransmit(struct sock *sk, int flag)
return true;
}
-static inline int tcp_skb_timedout(const struct sock *sk,
- const struct sk_buff *skb)
-{
- return tcp_time_stamp - TCP_SKB_CB(skb)->when > inet_csk(sk)->icsk_rto;
-}
-
-static inline int tcp_head_timedout(const struct sock *sk)
-{
- const struct tcp_sock *tp = tcp_sk(sk);
-
- return tp->packets_out &&
- tcp_skb_timedout(sk, tcp_write_queue_head(sk));
-}
-
/* Linux NewReno/SACK/FACK/ECN state machine.
* --------------------------------------
*
@@ -2086,12 +2068,6 @@ static bool tcp_time_to_recover(struct sock *sk, int flag)
if (tcp_dupack_heuristics(tp) > tp->reordering)
return true;
- /* Trick#3 : when we use RFC2988 timer restart, fast
- * retransmit can be triggered by timeout of queue head.
- */
- if (tcp_is_fack(tp) && tcp_head_timedout(sk))
- return true;
-
/* Trick#4: It is still not OK... But will it be useful to delay
* recovery more?
*/
@@ -2128,44 +2104,6 @@ static bool tcp_time_to_recover(struct sock *sk, int flag)
return false;
}
-/* New heuristics: it is possible only after we switched to restart timer
- * each time when something is ACKed. Hence, we can detect timed out packets
- * during fast retransmit without falling to slow start.
- *
- * Usefulness of this as is very questionable, since we should know which of
- * the segments is the next to timeout which is relatively expensive to find
- * in general case unless we add some data structure just for that. The
- * current approach certainly won't find the right one too often and when it
- * finally does find _something_ it usually marks large part of the window
- * right away (because a retransmission with a larger timestamp blocks the
- * loop from advancing). -ij
- */
-static void tcp_timeout_skbs(struct sock *sk)
-{
- struct tcp_sock *tp = tcp_sk(sk);
- struct sk_buff *skb;
-
- if (!tcp_is_fack(tp) || !tcp_head_timedout(sk))
- return;
-
- skb = tp->scoreboard_skb_hint;
- if (tp->scoreboard_skb_hint == NULL)
- skb = tcp_write_queue_head(sk);
-
- tcp_for_write_queue_from(skb, sk) {
- if (skb == tcp_send_head(sk))
- break;
- if (!tcp_skb_timedout(sk, skb))
- break;
-
- tcp_skb_mark_lost(tp, skb);
- }
-
- tp->scoreboard_skb_hint = skb;
-
- tcp_verify_left_out(tp);
-}
-
/* Detect loss in event "A" above by marking head of queue up as lost.
* For FACK or non-SACK(Reno) senders, the first "packets" number of segments
* are considered lost. For RFC3517 SACK, a segment is considered lost if it
@@ -2251,8 +2189,6 @@ static void tcp_update_scoreboard(struct sock *sk, int fast_rexmit)
else if (fast_rexmit)
tcp_mark_head_lost(sk, 1, 1);
}
-
- tcp_timeout_skbs(sk);
}
/* CWND moderation, preventing bursts due to too big ACKs
@@ -2307,10 +2243,22 @@ static void DBGUNDO(struct sock *sk, const char *msg)
#define DBGUNDO(x...) do { } while (0)
#endif
-static void tcp_undo_cwr(struct sock *sk, const bool undo_ssthresh)
+static void tcp_undo_cwnd_reduction(struct sock *sk, bool unmark_loss)
{
struct tcp_sock *tp = tcp_sk(sk);
+ if (unmark_loss) {
+ struct sk_buff *skb;
+
+ tcp_for_write_queue(skb, sk) {
+ if (skb == tcp_send_head(sk))
+ break;
+ TCP_SKB_CB(skb)->sacked &= ~TCPCB_LOST;
+ }
+ tp->lost_out = 0;
+ tcp_clear_all_retrans_hints(tp);
+ }
+
if (tp->prior_ssthresh) {
const struct inet_connection_sock *icsk = inet_csk(sk);
@@ -2319,7 +2267,7 @@ static void tcp_undo_cwr(struct sock *sk, const bool undo_ssthresh)
else
tp->snd_cwnd = max(tp->snd_cwnd, tp->snd_ssthresh << 1);
- if (undo_ssthresh && tp->prior_ssthresh > tp->snd_ssthresh) {
+ if (tp->prior_ssthresh > tp->snd_ssthresh) {
tp->snd_ssthresh = tp->prior_ssthresh;
TCP_ECN_withdraw_cwr(tp);
}
@@ -2327,6 +2275,7 @@ static void tcp_undo_cwr(struct sock *sk, const bool undo_ssthresh)
tp->snd_cwnd = max(tp->snd_cwnd, tp->snd_ssthresh);
}
tp->snd_cwnd_stamp = tcp_time_stamp;
+ tp->undo_marker = 0;
}
static inline bool tcp_may_undo(const struct tcp_sock *tp)
@@ -2346,14 +2295,13 @@ static bool tcp_try_undo_recovery(struct sock *sk)
* or our original transmission succeeded.
*/
DBGUNDO(sk, inet_csk(sk)->icsk_ca_state == TCP_CA_Loss ? "loss" : "retrans");
- tcp_undo_cwr(sk, true);
+ tcp_undo_cwnd_reduction(sk, false);
if (inet_csk(sk)->icsk_ca_state == TCP_CA_Loss)
mib_idx = LINUX_MIB_TCPLOSSUNDO;
else
mib_idx = LINUX_MIB_TCPFULLUNDO;
NET_INC_STATS_BH(sock_net(sk), mib_idx);
- tp->undo_marker = 0;
}
if (tp->snd_una == tp->high_seq && tcp_is_reno(tp)) {
/* Hold old state until something *above* high_seq
@@ -2367,16 +2315,17 @@ static bool tcp_try_undo_recovery(struct sock *sk)
}
/* Try to undo cwnd reduction, because D-SACKs acked all retransmitted data */
-static void tcp_try_undo_dsack(struct sock *sk)
+static bool tcp_try_undo_dsack(struct sock *sk)
{
struct tcp_sock *tp = tcp_sk(sk);
if (tp->undo_marker && !tp->undo_retrans) {
DBGUNDO(sk, "D-SACK");
- tcp_undo_cwr(sk, true);
- tp->undo_marker = 0;
+ tcp_undo_cwnd_reduction(sk, false);
NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPDSACKUNDO);
+ return true;
}
+ return false;
}
/* We can clear retrans_stamp when there are no retransmissions in the
@@ -2408,60 +2357,20 @@ static bool tcp_any_retrans_done(const struct sock *sk)
return false;
}
-/* Undo during fast recovery after partial ACK. */
-
-static int tcp_try_undo_partial(struct sock *sk, int acked)
-{
- struct tcp_sock *tp = tcp_sk(sk);
- /* Partial ACK arrived. Force Hoe's retransmit. */
- int failed = tcp_is_reno(tp) || (tcp_fackets_out(tp) > tp->reordering);
-
- if (tcp_may_undo(tp)) {
- /* Plain luck! Hole if filled with delayed
- * packet, rather than with a retransmit.
- */
- if (!tcp_any_retrans_done(sk))
- tp->retrans_stamp = 0;
-
- tcp_update_reordering(sk, tcp_fackets_out(tp) + acked, 1);
-
- DBGUNDO(sk, "Hoe");
- tcp_undo_cwr(sk, false);
- NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPPARTIALUNDO);
-
- /* So... Do not make Hoe's retransmit yet.
- * If the first packet was delayed, the rest
- * ones are most probably delayed as well.
- */
- failed = 0;
- }
- return failed;
-}
-
/* Undo during loss recovery after partial ACK or using F-RTO. */
static bool tcp_try_undo_loss(struct sock *sk, bool frto_undo)
{
struct tcp_sock *tp = tcp_sk(sk);
if (frto_undo || tcp_may_undo(tp)) {
- struct sk_buff *skb;
- tcp_for_write_queue(skb, sk) {
- if (skb == tcp_send_head(sk))
- break;
- TCP_SKB_CB(skb)->sacked &= ~TCPCB_LOST;
- }
-
- tcp_clear_all_retrans_hints(tp);
+ tcp_undo_cwnd_reduction(sk, true);
DBGUNDO(sk, "partial loss");
- tp->lost_out = 0;
- tcp_undo_cwr(sk, true);
NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPLOSSUNDO);
if (frto_undo)
NET_INC_STATS_BH(sock_net(sk),
LINUX_MIB_TCPSPURIOUSRTOS);
inet_csk(sk)->icsk_retransmits = 0;
- tp->undo_marker = 0;
if (frto_undo || tcp_is_sack(tp))
tcp_set_ca_state(sk, TCP_CA_Open);
return true;
@@ -2494,12 +2403,14 @@ static void tcp_init_cwnd_reduction(struct sock *sk, const bool set_ssthresh)
TCP_ECN_queue_cwr(tp);
}
-static void tcp_cwnd_reduction(struct sock *sk, int newly_acked_sacked,
+static void tcp_cwnd_reduction(struct sock *sk, const int prior_unsacked,
int fast_rexmit)
{
struct tcp_sock *tp = tcp_sk(sk);
int sndcnt = 0;
int delta = tp->snd_ssthresh - tcp_packets_in_flight(tp);
+ int newly_acked_sacked = prior_unsacked -
+ (tp->packets_out - tp->sacked_out);
tp->prr_delivered += newly_acked_sacked;
if (tcp_packets_in_flight(tp) > tp->snd_ssthresh) {
@@ -2556,7 +2467,7 @@ static void tcp_try_keep_open(struct sock *sk)
}
}
-static void tcp_try_to_open(struct sock *sk, int flag, int newly_acked_sacked)
+static void tcp_try_to_open(struct sock *sk, int flag, const int prior_unsacked)
{
struct tcp_sock *tp = tcp_sk(sk);
@@ -2573,7 +2484,7 @@ static void tcp_try_to_open(struct sock *sk, int flag, int newly_acked_sacked)
if (inet_csk(sk)->icsk_ca_state != TCP_CA_Open)
tcp_moderate_cwnd(tp);
} else {
- tcp_cwnd_reduction(sk, newly_acked_sacked, 0);
+ tcp_cwnd_reduction(sk, prior_unsacked, 0);
}
}
@@ -2731,6 +2642,40 @@ static void tcp_process_loss(struct sock *sk, int flag, bool is_dupack)
tcp_xmit_retransmit_queue(sk);
}
+/* Undo during fast recovery after partial ACK. */
+static bool tcp_try_undo_partial(struct sock *sk, const int acked,
+ const int prior_unsacked)
+{
+ struct tcp_sock *tp = tcp_sk(sk);
+
+ if (tp->undo_marker && tcp_packet_delayed(tp)) {
+ /* Plain luck! Hole if filled with delayed
+ * packet, rather than with a retransmit.
+ */
+ tcp_update_reordering(sk, tcp_fackets_out(tp) + acked, 1);
+
+ /* We are getting evidence that the reordering degree is higher
+ * than we realized. If there are no retransmits out then we
+ * can undo. Otherwise we clock out new packets but do not
+ * mark more packets lost or retransmit more.
+ */
+ if (tp->retrans_out) {
+ tcp_cwnd_reduction(sk, prior_unsacked, 0);
+ return true;
+ }
+
+ if (!tcp_any_retrans_done(sk))
+ tp->retrans_stamp = 0;
+
+ DBGUNDO(sk, "partial recovery");
+ tcp_undo_cwnd_reduction(sk, true);
+ NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPPARTIALUNDO);
+ tcp_try_keep_open(sk);
+ return true;
+ }
+ return false;
+}
+
/* Process an event, which can update packets-in-flight not trivially.
* Main goal of this function is to calculate new estimate for left_out,
* taking into account both packets sitting in receiver's buffer and
@@ -2742,15 +2687,14 @@ static void tcp_process_loss(struct sock *sk, int flag, bool is_dupack)
* It does _not_ decide what to send, it is made in function
* tcp_xmit_retransmit_queue().
*/
-static void tcp_fastretrans_alert(struct sock *sk, int pkts_acked,
- int prior_sacked, int prior_packets,
+static void tcp_fastretrans_alert(struct sock *sk, const int acked,
+ const int prior_unsacked,
bool is_dupack, int flag)
{
struct inet_connection_sock *icsk = inet_csk(sk);
struct tcp_sock *tp = tcp_sk(sk);
- int do_lost = is_dupack || ((flag & FLAG_DATA_SACKED) &&
+ bool do_lost = is_dupack || ((flag & FLAG_DATA_SACKED) &&
(tcp_fackets_out(tp) > tp->reordering));
- int newly_acked_sacked = 0;
int fast_rexmit = 0;
if (WARN_ON(!tp->packets_out && tp->sacked_out))
@@ -2802,10 +2746,17 @@ static void tcp_fastretrans_alert(struct sock *sk, int pkts_acked,
if (!(flag & FLAG_SND_UNA_ADVANCED)) {
if (tcp_is_reno(tp) && is_dupack)
tcp_add_reno_sack(sk);
- } else
- do_lost = tcp_try_undo_partial(sk, pkts_acked);
- newly_acked_sacked = prior_packets - tp->packets_out +
- tp->sacked_out - prior_sacked;
+ } else {
+ if (tcp_try_undo_partial(sk, acked, prior_unsacked))
+ return;
+ /* Partial ACK arrived. Force fast retransmit. */
+ do_lost = tcp_is_reno(tp) ||
+ tcp_fackets_out(tp) > tp->reordering;
+ }
+ if (tcp_try_undo_dsack(sk)) {
+ tcp_try_keep_open(sk);
+ return;
+ }
break;
case TCP_CA_Loss:
tcp_process_loss(sk, flag, is_dupack);
@@ -2819,14 +2770,12 @@ static void tcp_fastretrans_alert(struct sock *sk, int pkts_acked,
if (is_dupack)
tcp_add_reno_sack(sk);
}
- newly_acked_sacked = prior_packets - tp->packets_out +
- tp->sacked_out - prior_sacked;
if (icsk->icsk_ca_state <= TCP_CA_Disorder)
tcp_try_undo_dsack(sk);
if (!tcp_time_to_recover(sk, flag)) {
- tcp_try_to_open(sk, flag, newly_acked_sacked);
+ tcp_try_to_open(sk, flag, prior_unsacked);
return;
}
@@ -2846,9 +2795,9 @@ static void tcp_fastretrans_alert(struct sock *sk, int pkts_acked,
fast_rexmit = 1;
}
- if (do_lost || (tcp_is_fack(tp) && tcp_head_timedout(sk)))
+ if (do_lost)
tcp_update_scoreboard(sk, fast_rexmit);
- tcp_cwnd_reduction(sk, newly_acked_sacked, fast_rexmit);
+ tcp_cwnd_reduction(sk, prior_unsacked, fast_rexmit);
tcp_xmit_retransmit_queue(sk);
}
@@ -3079,7 +3028,6 @@ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets,
tcp_unlink_write_queue(skb, sk);
sk_wmem_free_skb(sk, skb);
- tp->scoreboard_skb_hint = NULL;
if (skb == tp->retransmit_skb_hint)
tp->retransmit_skb_hint = NULL;
if (skb == tp->lost_skb_hint)
@@ -3333,9 +3281,8 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag)
u32 prior_in_flight;
u32 prior_fackets;
int prior_packets = tp->packets_out;
- int prior_sacked = tp->sacked_out;
- int pkts_acked = 0;
- int previous_packets_out = 0;
+ const int prior_unsacked = tp->packets_out - tp->sacked_out;
+ int acked = 0; /* Number of packets newly acked */
/* If the ack is older than previous acks
* then we can probably ignore it.
@@ -3410,18 +3357,17 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag)
goto no_queue;
/* See if we can take anything off of the retransmit queue. */
- previous_packets_out = tp->packets_out;
+ acked = tp->packets_out;
flag |= tcp_clean_rtx_queue(sk, prior_fackets, prior_snd_una);
-
- pkts_acked = previous_packets_out - tp->packets_out;
+ acked -= tp->packets_out;
if (tcp_ack_is_dubious(sk, flag)) {
/* Advance CWND, if state allows this. */
if ((flag & FLAG_DATA_ACKED) && tcp_may_raise_cwnd(sk, flag))
tcp_cong_avoid(sk, ack, prior_in_flight);
is_dupack = !(flag & (FLAG_SND_UNA_ADVANCED | FLAG_NOT_DUP));
- tcp_fastretrans_alert(sk, pkts_acked, prior_sacked,
- prior_packets, is_dupack, flag);
+ tcp_fastretrans_alert(sk, acked, prior_unsacked,
+ is_dupack, flag);
} else {
if (flag & FLAG_DATA_ACKED)
tcp_cong_avoid(sk, ack, prior_in_flight);
@@ -3443,8 +3389,8 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag)
no_queue:
/* If data was DSACKed, see if we can undo a cwnd reduction. */
if (flag & FLAG_DSACKING_ACK)
- tcp_fastretrans_alert(sk, pkts_acked, prior_sacked,
- prior_packets, is_dupack, flag);
+ tcp_fastretrans_alert(sk, acked, prior_unsacked,
+ is_dupack, flag);
/* If this ack opens up a zero window, clear backoff. It was
* being used to time the probes, and is probably far higher than
* it needs to be for normal retransmission.
@@ -3466,8 +3412,8 @@ old_ack:
*/
if (TCP_SKB_CB(skb)->sacked) {
flag |= tcp_sacktag_write_queue(sk, skb, prior_snd_una);
- tcp_fastretrans_alert(sk, pkts_acked, prior_sacked,
- prior_packets, is_dupack, flag);
+ tcp_fastretrans_alert(sk, acked, prior_unsacked,
+ is_dupack, flag);
}
SOCK_DEBUG(sk, "Ack %u before %u:%u\n", ack, tp->snd_una, tp->snd_nxt);
@@ -5601,6 +5547,7 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb,
struct inet_connection_sock *icsk = inet_csk(sk);
struct request_sock *req;
int queued = 0;
+ bool acceptable;
tp->rx_opt.saw_tstamp = 0;
@@ -5671,157 +5618,147 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb,
return 0;
/* step 5: check the ACK field */
- if (true) {
- int acceptable = tcp_ack(sk, skb, FLAG_SLOWPATH |
- FLAG_UPDATE_TS_RECENT) > 0;
-
- switch (sk->sk_state) {
- case TCP_SYN_RECV:
- if (acceptable) {
- /* Once we leave TCP_SYN_RECV, we no longer
- * need req so release it.
- */
- if (req) {
- tcp_synack_rtt_meas(sk, req);
- tp->total_retrans = req->num_retrans;
-
- reqsk_fastopen_remove(sk, req, false);
- } else {
- /* Make sure socket is routed, for
- * correct metrics.
- */
- icsk->icsk_af_ops->rebuild_header(sk);
- tcp_init_congestion_control(sk);
+ acceptable = tcp_ack(sk, skb, FLAG_SLOWPATH |
+ FLAG_UPDATE_TS_RECENT) > 0;
- tcp_mtup_init(sk);
- tcp_init_buffer_space(sk);
- tp->copied_seq = tp->rcv_nxt;
- }
- smp_mb();
- tcp_set_state(sk, TCP_ESTABLISHED);
- sk->sk_state_change(sk);
-
- /* Note, that this wakeup is only for marginal
- * crossed SYN case. Passively open sockets
- * are not waked up, because sk->sk_sleep ==
- * NULL and sk->sk_socket == NULL.
- */
- if (sk->sk_socket)
- sk_wake_async(sk,
- SOCK_WAKE_IO, POLL_OUT);
-
- tp->snd_una = TCP_SKB_CB(skb)->ack_seq;
- tp->snd_wnd = ntohs(th->window) <<
- tp->rx_opt.snd_wscale;
- tcp_init_wl(tp, TCP_SKB_CB(skb)->seq);
-
- if (tp->rx_opt.tstamp_ok)
- tp->advmss -= TCPOLEN_TSTAMP_ALIGNED;
-
- if (req) {
- /* Re-arm the timer because data may
- * have been sent out. This is similar
- * to the regular data transmission case
- * when new data has just been ack'ed.
- *
- * (TFO) - we could try to be more
- * aggressive and retranmitting any data
- * sooner based on when they were sent
- * out.
- */
- tcp_rearm_rto(sk);
- } else
- tcp_init_metrics(sk);
+ switch (sk->sk_state) {
+ case TCP_SYN_RECV:
+ if (!acceptable)
+ return 1;
- /* Prevent spurious tcp_cwnd_restart() on
- * first data packet.
- */
- tp->lsndtime = tcp_time_stamp;
+ /* Once we leave TCP_SYN_RECV, we no longer need req
+ * so release it.
+ */
+ if (req) {
+ tcp_synack_rtt_meas(sk, req);
+ tp->total_retrans = req->num_retrans;
- tcp_initialize_rcv_mss(sk);
- tcp_fast_path_on(tp);
- } else {
- return 1;
- }
- break;
+ reqsk_fastopen_remove(sk, req, false);
+ } else {
+ /* Make sure socket is routed, for correct metrics. */
+ icsk->icsk_af_ops->rebuild_header(sk);
+ tcp_init_congestion_control(sk);
+
+ tcp_mtup_init(sk);
+ tcp_init_buffer_space(sk);
+ tp->copied_seq = tp->rcv_nxt;
+ }
+ smp_mb();
+ tcp_set_state(sk, TCP_ESTABLISHED);
+ sk->sk_state_change(sk);
+
+ /* Note, that this wakeup is only for marginal crossed SYN case.
+ * Passively open sockets are not waked up, because
+ * sk->sk_sleep == NULL and sk->sk_socket == NULL.
+ */
+ if (sk->sk_socket)
+ sk_wake_async(sk, SOCK_WAKE_IO, POLL_OUT);
+
+ tp->snd_una = TCP_SKB_CB(skb)->ack_seq;
+ tp->snd_wnd = ntohs(th->window) << tp->rx_opt.snd_wscale;
+ tcp_init_wl(tp, TCP_SKB_CB(skb)->seq);
+
+ if (tp->rx_opt.tstamp_ok)
+ tp->advmss -= TCPOLEN_TSTAMP_ALIGNED;
- case TCP_FIN_WAIT1:
- /* If we enter the TCP_FIN_WAIT1 state and we are a
- * Fast Open socket and this is the first acceptable
- * ACK we have received, this would have acknowledged
- * our SYNACK so stop the SYNACK timer.
+ if (req) {
+ /* Re-arm the timer because data may have been sent out.
+ * This is similar to the regular data transmission case
+ * when new data has just been ack'ed.
+ *
+ * (TFO) - we could try to be more aggressive and
+ * retransmitting any data sooner based on when they
+ * are sent out.
*/
- if (req != NULL) {
- /* Return RST if ack_seq is invalid.
- * Note that RFC793 only says to generate a
- * DUPACK for it but for TCP Fast Open it seems
- * better to treat this case like TCP_SYN_RECV
- * above.
- */
- if (!acceptable)
- return 1;
- /* We no longer need the request sock. */
- reqsk_fastopen_remove(sk, req, false);
- tcp_rearm_rto(sk);
- }
- if (tp->snd_una == tp->write_seq) {
- struct dst_entry *dst;
-
- tcp_set_state(sk, TCP_FIN_WAIT2);
- sk->sk_shutdown |= SEND_SHUTDOWN;
-
- dst = __sk_dst_get(sk);
- if (dst)
- dst_confirm(dst);
-
- if (!sock_flag(sk, SOCK_DEAD))
- /* Wake up lingering close() */
- sk->sk_state_change(sk);
- else {
- int tmo;
-
- if (tp->linger2 < 0 ||
- (TCP_SKB_CB(skb)->end_seq != TCP_SKB_CB(skb)->seq &&
- after(TCP_SKB_CB(skb)->end_seq - th->fin, tp->rcv_nxt))) {
- tcp_done(sk);
- NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPABORTONDATA);
- return 1;
- }
+ tcp_rearm_rto(sk);
+ } else
+ tcp_init_metrics(sk);
- tmo = tcp_fin_time(sk);
- if (tmo > TCP_TIMEWAIT_LEN) {
- inet_csk_reset_keepalive_timer(sk, tmo - TCP_TIMEWAIT_LEN);
- } else if (th->fin || sock_owned_by_user(sk)) {
- /* Bad case. We could lose such FIN otherwise.
- * It is not a big problem, but it looks confusing
- * and not so rare event. We still can lose it now,
- * if it spins in bh_lock_sock(), but it is really
- * marginal case.
- */
- inet_csk_reset_keepalive_timer(sk, tmo);
- } else {
- tcp_time_wait(sk, TCP_FIN_WAIT2, tmo);
- goto discard;
- }
- }
- }
- break;
+ /* Prevent spurious tcp_cwnd_restart() on first data packet */
+ tp->lsndtime = tcp_time_stamp;
- case TCP_CLOSING:
- if (tp->snd_una == tp->write_seq) {
- tcp_time_wait(sk, TCP_TIME_WAIT, 0);
- goto discard;
- }
+ tcp_initialize_rcv_mss(sk);
+ tcp_fast_path_on(tp);
+ break;
+
+ case TCP_FIN_WAIT1: {
+ struct dst_entry *dst;
+ int tmo;
+
+ /* If we enter the TCP_FIN_WAIT1 state and we are a
+ * Fast Open socket and this is the first acceptable
+ * ACK we have received, this would have acknowledged
+ * our SYNACK so stop the SYNACK timer.
+ */
+ if (req != NULL) {
+ /* Return RST if ack_seq is invalid.
+ * Note that RFC793 only says to generate a
+ * DUPACK for it but for TCP Fast Open it seems
+ * better to treat this case like TCP_SYN_RECV
+ * above.
+ */
+ if (!acceptable)
+ return 1;
+ /* We no longer need the request sock. */
+ reqsk_fastopen_remove(sk, req, false);
+ tcp_rearm_rto(sk);
+ }
+ if (tp->snd_una != tp->write_seq)
break;
- case TCP_LAST_ACK:
- if (tp->snd_una == tp->write_seq) {
- tcp_update_metrics(sk);
- tcp_done(sk);
- goto discard;
- }
+ tcp_set_state(sk, TCP_FIN_WAIT2);
+ sk->sk_shutdown |= SEND_SHUTDOWN;
+
+ dst = __sk_dst_get(sk);
+ if (dst)
+ dst_confirm(dst);
+
+ if (!sock_flag(sk, SOCK_DEAD)) {
+ /* Wake up lingering close() */
+ sk->sk_state_change(sk);
break;
}
+
+ if (tp->linger2 < 0 ||
+ (TCP_SKB_CB(skb)->end_seq != TCP_SKB_CB(skb)->seq &&
+ after(TCP_SKB_CB(skb)->end_seq - th->fin, tp->rcv_nxt))) {
+ tcp_done(sk);
+ NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPABORTONDATA);
+ return 1;
+ }
+
+ tmo = tcp_fin_time(sk);
+ if (tmo > TCP_TIMEWAIT_LEN) {
+ inet_csk_reset_keepalive_timer(sk, tmo - TCP_TIMEWAIT_LEN);
+ } else if (th->fin || sock_owned_by_user(sk)) {
+ /* Bad case. We could lose such FIN otherwise.
+ * It is not a big problem, but it looks confusing
+ * and not so rare event. We still can lose it now,
+ * if it spins in bh_lock_sock(), but it is really
+ * marginal case.
+ */
+ inet_csk_reset_keepalive_timer(sk, tmo);
+ } else {
+ tcp_time_wait(sk, TCP_FIN_WAIT2, tmo);
+ goto discard;
+ }
+ break;
+ }
+
+ case TCP_CLOSING:
+ if (tp->snd_una == tp->write_seq) {
+ tcp_time_wait(sk, TCP_TIME_WAIT, 0);
+ goto discard;
+ }
+ break;
+
+ case TCP_LAST_ACK:
+ if (tp->snd_una == tp->write_seq) {
+ tcp_update_metrics(sk);
+ tcp_done(sk);
+ goto discard;
+ }
+ break;
}
/* step 6: check the URG bit */
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 7196523..d20ede0 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -1026,7 +1026,7 @@ int tcp_md5_do_add(struct sock *sk, const union tcp_md5_addr *addr,
key = sock_kmalloc(sk, sizeof(*key), gfp);
if (!key)
return -ENOMEM;
- if (hlist_empty(&md5sig->head) && !tcp_alloc_md5sig_pool(sk)) {
+ if (!tcp_alloc_md5sig_pool()) {
sock_kfree_s(sk, key, sizeof(*key));
return -ENOMEM;
}
@@ -1044,9 +1044,7 @@ EXPORT_SYMBOL(tcp_md5_do_add);
int tcp_md5_do_del(struct sock *sk, const union tcp_md5_addr *addr, int family)
{
- struct tcp_sock *tp = tcp_sk(sk);
struct tcp_md5sig_key *key;
- struct tcp_md5sig_info *md5sig;
key = tcp_md5_do_lookup(sk, (union tcp_md5_addr *)&addr, AF_INET);
if (!key)
@@ -1054,10 +1052,6 @@ int tcp_md5_do_del(struct sock *sk, const union tcp_md5_addr *addr, int family)
hlist_del_rcu(&key->node);
atomic_sub(sizeof(*key), &sk->sk_omem_alloc);
kfree_rcu(key, rcu);
- md5sig = rcu_dereference_protected(tp->md5sig_info,
- sock_owned_by_user(sk));
- if (hlist_empty(&md5sig->head))
- tcp_free_md5sig_pool();
return 0;
}
EXPORT_SYMBOL(tcp_md5_do_del);
@@ -1071,8 +1065,6 @@ static void tcp_clear_md5_list(struct sock *sk)
md5sig = rcu_dereference_protected(tp->md5sig_info, 1);
- if (!hlist_empty(&md5sig->head))
- tcp_free_md5sig_pool();
hlist_for_each_entry_safe(key, n, &md5sig->head, node) {
hlist_del_rcu(&key->node);
atomic_sub(sizeof(*key), &sk->sk_omem_alloc);
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index 0f01788..ab1c086 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -317,7 +317,7 @@ void tcp_time_wait(struct sock *sk, int state, int timeo)
key = tp->af_specific->md5_lookup(sk, sk);
if (key != NULL) {
tcptw->tw_md5_key = kmemdup(key, sizeof(*key), GFP_ATOMIC);
- if (tcptw->tw_md5_key && tcp_alloc_md5sig_pool(sk) == NULL)
+ if (tcptw->tw_md5_key && !tcp_alloc_md5sig_pool())
BUG();
}
} while (0);
@@ -358,10 +358,8 @@ void tcp_twsk_destructor(struct sock *sk)
#ifdef CONFIG_TCP_MD5SIG
struct tcp_timewait_sock *twsk = tcp_twsk(sk);
- if (twsk->tw_md5_key) {
- tcp_free_md5sig_pool();
+ if (twsk->tw_md5_key)
kfree_rcu(twsk->tw_md5_key, rcu);
- }
#endif
}
EXPORT_SYMBOL_GPL(tcp_twsk_destructor);
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 0bf5d39..c7338ec 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -1967,6 +1967,8 @@ unsigned int udp_poll(struct file *file, struct socket *sock, poll_table *wait)
unsigned int mask = datagram_poll(file, sock, wait);
struct sock *sk = sock->sk;
+ sock_rps_record_flow(sk);
+
/* Check for false positives due to checksum errors */
if ((mask & POLLRDNORM) && !(file->f_flags & O_NONBLOCK) &&
!(sk->sk_shutdown & RCV_SHUTDOWN) && !first_packet_length(sk))
@@ -2381,7 +2383,7 @@ struct sk_buff *udp4_ufo_fragment(struct sk_buff *skb,
if (unlikely(type & ~(SKB_GSO_UDP | SKB_GSO_DODGY |
SKB_GSO_UDP_TUNNEL |
- SKB_GSO_GRE) ||
+ SKB_GSO_GRE | SKB_GSO_MPLS) ||
!(type & (SKB_GSO_UDP))))
goto out;
diff --git a/net/ipv4/xfrm4_tunnel.c b/net/ipv4/xfrm4_tunnel.c
index 05a5df2..06347db 100644
--- a/net/ipv4/xfrm4_tunnel.c
+++ b/net/ipv4/xfrm4_tunnel.c
@@ -63,7 +63,7 @@ static int xfrm_tunnel_err(struct sk_buff *skb, u32 info)
static struct xfrm_tunnel xfrm_tunnel_handler __read_mostly = {
.handler = xfrm_tunnel_rcv,
.err_handler = xfrm_tunnel_err,
- .priority = 2,
+ .priority = 3,
};
#if IS_ENABLED(CONFIG_IPV6)
OpenPOWER on IntegriCloud