summaryrefslogtreecommitdiffstats
path: root/net/ipv4
diff options
context:
space:
mode:
Diffstat (limited to 'net/ipv4')
-rw-r--r--net/ipv4/af_inet.c21
-rw-r--r--net/ipv4/ah4.c3
-rw-r--r--net/ipv4/arp.c25
-rw-r--r--net/ipv4/fib_trie.c18
-rw-r--r--net/ipv4/gre.c118
-rw-r--r--net/ipv4/igmp.c11
-rw-r--r--net/ipv4/ip_fragment.c2
-rw-r--r--net/ipv4/ip_gre.c82
-rw-r--r--net/ipv4/ip_input.c7
-rw-r--r--net/ipv4/ip_output.c1
-rw-r--r--net/ipv4/ipconfig.c2
-rw-r--r--net/ipv4/ipmr.c10
-rw-r--r--net/ipv4/netfilter/nf_conntrack_l3proto_ipv4_compat.c14
-rw-r--r--net/ipv4/ping.c4
-rw-r--r--net/ipv4/proc.c17
-rw-r--r--net/ipv4/protocol.c6
-rw-r--r--net/ipv4/raw.c4
-rw-r--r--net/ipv4/route.c4
-rw-r--r--net/ipv4/sysctl_net_ipv4.c7
-rw-r--r--net/ipv4/tcp.c17
-rw-r--r--net/ipv4/tcp_cong.c42
-rw-r--r--net/ipv4/tcp_input.c35
-rw-r--r--net/ipv4/tcp_ipv4.c20
-rw-r--r--net/ipv4/tcp_minisocks.c4
-rw-r--r--net/ipv4/tcp_output.c10
-rw-r--r--net/ipv4/tcp_probe.c6
-rw-r--r--net/ipv4/udp.c5
-rw-r--r--net/ipv4/xfrm4_input.c2
-rw-r--r--net/ipv4/xfrm4_mode_tunnel.c4
-rw-r--r--net/ipv4/xfrm4_policy.c58
30 files changed, 373 insertions, 186 deletions
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 49ddca31c4d..e225a4e5b57 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -263,21 +263,6 @@ void build_ehash_secret(void)
}
EXPORT_SYMBOL(build_ehash_secret);
-static inline int inet_netns_ok(struct net *net, __u8 protocol)
-{
- const struct net_protocol *ipprot;
-
- if (net_eq(net, &init_net))
- return 1;
-
- ipprot = rcu_dereference(inet_protos[protocol]);
- if (ipprot == NULL) {
- /* raw IP is OK */
- return 1;
- }
- return ipprot->netns_ok;
-}
-
/*
* Create an inet socket.
*/
@@ -350,10 +335,6 @@ lookup_protocol:
!ns_capable(net->user_ns, CAP_NET_RAW))
goto out_rcu_unlock;
- err = -EAFNOSUPPORT;
- if (!inet_netns_ok(net, protocol))
- goto out_rcu_unlock;
-
sock->ops = answer->ops;
answer_prot = answer->prot;
answer_no_check = answer->no_check;
@@ -1306,7 +1287,7 @@ static struct sk_buff *inet_gso_segment(struct sk_buff *skb,
SKB_GSO_UDP |
SKB_GSO_DODGY |
SKB_GSO_TCP_ECN |
- SKB_GSO_SHARED_FRAG |
+ SKB_GSO_GRE |
0)))
goto out;
diff --git a/net/ipv4/ah4.c b/net/ipv4/ah4.c
index a69b4e4a02b..2e7f1948216 100644
--- a/net/ipv4/ah4.c
+++ b/net/ipv4/ah4.c
@@ -321,8 +321,7 @@ static int ah_input(struct xfrm_state *x, struct sk_buff *skb)
/* We are going to _remove_ AH header to keep sockets happy,
* so... Later this can change. */
- if (skb_cloned(skb) &&
- pskb_expand_head(skb, 0, 0, GFP_ATOMIC))
+ if (skb_unclone(skb, GFP_ATOMIC))
goto out;
skb->ip_summed = CHECKSUM_NONE;
diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c
index 9547a273b9e..fea4929f620 100644
--- a/net/ipv4/arp.c
+++ b/net/ipv4/arp.c
@@ -928,24 +928,25 @@ static void parp_redo(struct sk_buff *skb)
static int arp_rcv(struct sk_buff *skb, struct net_device *dev,
struct packet_type *pt, struct net_device *orig_dev)
{
- struct arphdr *arp;
+ const struct arphdr *arp;
+
+ if (dev->flags & IFF_NOARP ||
+ skb->pkt_type == PACKET_OTHERHOST ||
+ skb->pkt_type == PACKET_LOOPBACK)
+ goto freeskb;
+
+ skb = skb_share_check(skb, GFP_ATOMIC);
+ if (!skb)
+ goto out_of_mem;
/* ARP header, plus 2 device addresses, plus 2 IP addresses. */
if (!pskb_may_pull(skb, arp_hdr_len(dev)))
goto freeskb;
arp = arp_hdr(skb);
- if (arp->ar_hln != dev->addr_len ||
- dev->flags & IFF_NOARP ||
- skb->pkt_type == PACKET_OTHERHOST ||
- skb->pkt_type == PACKET_LOOPBACK ||
- arp->ar_pln != 4)
+ if (arp->ar_hln != dev->addr_len || arp->ar_pln != 4)
goto freeskb;
- skb = skb_share_check(skb, GFP_ATOMIC);
- if (skb == NULL)
- goto out_of_mem;
-
memset(NEIGH_CB(skb), 0, sizeof(struct neighbour_cb));
return NF_HOOK(NFPROTO_ARP, NF_ARP_IN, skb, dev, NULL, arp_process);
@@ -1404,14 +1405,14 @@ static const struct file_operations arp_seq_fops = {
static int __net_init arp_net_init(struct net *net)
{
- if (!proc_net_fops_create(net, "arp", S_IRUGO, &arp_seq_fops))
+ if (!proc_create("arp", S_IRUGO, net->proc_net, &arp_seq_fops))
return -ENOMEM;
return 0;
}
static void __net_exit arp_net_exit(struct net *net)
{
- proc_net_remove(net, "arp");
+ remove_proc_entry("arp", net->proc_net);
}
static struct pernet_operations arp_net_ops = {
diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c
index 31d771ca9a7..61e03da3e1f 100644
--- a/net/ipv4/fib_trie.c
+++ b/net/ipv4/fib_trie.c
@@ -2607,31 +2607,31 @@ static const struct file_operations fib_route_fops = {
int __net_init fib_proc_init(struct net *net)
{
- if (!proc_net_fops_create(net, "fib_trie", S_IRUGO, &fib_trie_fops))
+ if (!proc_create("fib_trie", S_IRUGO, net->proc_net, &fib_trie_fops))
goto out1;
- if (!proc_net_fops_create(net, "fib_triestat", S_IRUGO,
- &fib_triestat_fops))
+ if (!proc_create("fib_triestat", S_IRUGO, net->proc_net,
+ &fib_triestat_fops))
goto out2;
- if (!proc_net_fops_create(net, "route", S_IRUGO, &fib_route_fops))
+ if (!proc_create("route", S_IRUGO, net->proc_net, &fib_route_fops))
goto out3;
return 0;
out3:
- proc_net_remove(net, "fib_triestat");
+ remove_proc_entry("fib_triestat", net->proc_net);
out2:
- proc_net_remove(net, "fib_trie");
+ remove_proc_entry("fib_trie", net->proc_net);
out1:
return -ENOMEM;
}
void __net_exit fib_proc_exit(struct net *net)
{
- proc_net_remove(net, "fib_trie");
- proc_net_remove(net, "fib_triestat");
- proc_net_remove(net, "route");
+ remove_proc_entry("fib_trie", net->proc_net);
+ remove_proc_entry("fib_triestat", net->proc_net);
+ remove_proc_entry("route", net->proc_net);
}
#endif /* CONFIG_PROC_FS */
diff --git a/net/ipv4/gre.c b/net/ipv4/gre.c
index 42a491055c7..7a4c710c4cd 100644
--- a/net/ipv4/gre.c
+++ b/net/ipv4/gre.c
@@ -19,6 +19,7 @@
#include <linux/in.h>
#include <linux/ip.h>
#include <linux/netdevice.h>
+#include <linux/if_tunnel.h>
#include <linux/spinlock.h>
#include <net/protocol.h>
#include <net/gre.h>
@@ -26,6 +27,11 @@
static const struct gre_protocol __rcu *gre_proto[GREPROTO_MAX] __read_mostly;
static DEFINE_SPINLOCK(gre_proto_lock);
+struct gre_base_hdr {
+ __be16 flags;
+ __be16 protocol;
+};
+#define GRE_HEADER_SECTION 4
int gre_add_protocol(const struct gre_protocol *proto, u8 version)
{
@@ -112,12 +118,117 @@ static void gre_err(struct sk_buff *skb, u32 info)
rcu_read_unlock();
}
+static struct sk_buff *gre_gso_segment(struct sk_buff *skb,
+ netdev_features_t features)
+{
+ struct sk_buff *segs = ERR_PTR(-EINVAL);
+ netdev_features_t enc_features;
+ int ghl = GRE_HEADER_SECTION;
+ struct gre_base_hdr *greh;
+ int mac_len = skb->mac_len;
+ int tnl_hlen;
+ bool csum;
+
+ if (unlikely(skb_shinfo(skb)->gso_type &
+ ~(SKB_GSO_TCPV4 |
+ SKB_GSO_TCPV6 |
+ SKB_GSO_UDP |
+ SKB_GSO_DODGY |
+ SKB_GSO_TCP_ECN |
+ SKB_GSO_GRE)))
+ goto out;
+
+ if (unlikely(!pskb_may_pull(skb, sizeof(*greh))))
+ goto out;
+
+ greh = (struct gre_base_hdr *)skb_transport_header(skb);
+
+ if (greh->flags & GRE_KEY)
+ ghl += GRE_HEADER_SECTION;
+ if (greh->flags & GRE_SEQ)
+ ghl += GRE_HEADER_SECTION;
+ if (greh->flags & GRE_CSUM) {
+ ghl += GRE_HEADER_SECTION;
+ csum = true;
+ } else
+ csum = false;
+
+ /* setup inner skb. */
+ if (greh->protocol == htons(ETH_P_TEB)) {
+ struct ethhdr *eth = eth_hdr(skb);
+ skb->protocol = eth->h_proto;
+ } else {
+ skb->protocol = greh->protocol;
+ }
+
+ skb->encapsulation = 0;
+
+ if (unlikely(!pskb_may_pull(skb, ghl)))
+ goto out;
+ __skb_pull(skb, ghl);
+ skb_reset_mac_header(skb);
+ skb_set_network_header(skb, skb_inner_network_offset(skb));
+ skb->mac_len = skb_inner_network_offset(skb);
+
+ /* segment inner packet. */
+ enc_features = skb->dev->hw_enc_features & netif_skb_features(skb);
+ segs = skb_mac_gso_segment(skb, enc_features);
+ if (!segs || IS_ERR(segs))
+ goto out;
+
+ skb = segs;
+ tnl_hlen = skb_tnl_header_len(skb);
+ do {
+ __skb_push(skb, ghl);
+ if (csum) {
+ __be32 *pcsum;
+
+ if (skb_has_shared_frag(skb)) {
+ int err;
+
+ err = __skb_linearize(skb);
+ if (err) {
+ kfree_skb(segs);
+ segs = ERR_PTR(err);
+ goto out;
+ }
+ }
+
+ greh = (struct gre_base_hdr *)(skb->data);
+ pcsum = (__be32 *)(greh + 1);
+ *pcsum = 0;
+ *(__sum16 *)pcsum = csum_fold(skb_checksum(skb, 0, skb->len, 0));
+ }
+ __skb_push(skb, tnl_hlen - ghl);
+
+ skb_reset_mac_header(skb);
+ skb_set_network_header(skb, mac_len);
+ skb->mac_len = mac_len;
+ } while ((skb = skb->next));
+out:
+ return segs;
+}
+
+static int gre_gso_send_check(struct sk_buff *skb)
+{
+ if (!skb->encapsulation)
+ return -EINVAL;
+ return 0;
+}
+
static const struct net_protocol net_gre_protocol = {
.handler = gre_rcv,
.err_handler = gre_err,
.netns_ok = 1,
};
+static const struct net_offload gre_offload = {
+ .callbacks = {
+ .gso_send_check = gre_gso_send_check,
+ .gso_segment = gre_gso_segment,
+ },
+};
+
static int __init gre_init(void)
{
pr_info("GRE over IPv4 demultiplexor driver\n");
@@ -127,11 +238,18 @@ static int __init gre_init(void)
return -EAGAIN;
}
+ if (inet_add_offload(&gre_offload, IPPROTO_GRE)) {
+ pr_err("can't add protocol offload\n");
+ inet_del_protocol(&net_gre_protocol, IPPROTO_GRE);
+ return -EAGAIN;
+ }
+
return 0;
}
static void __exit gre_exit(void)
{
+ inet_del_offload(&gre_offload, IPPROTO_GRE);
inet_del_protocol(&net_gre_protocol, IPPROTO_GRE);
}
diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c
index 736ab70fd17..d8c232794bc 100644
--- a/net/ipv4/igmp.c
+++ b/net/ipv4/igmp.c
@@ -2646,24 +2646,25 @@ static int __net_init igmp_net_init(struct net *net)
{
struct proc_dir_entry *pde;
- pde = proc_net_fops_create(net, "igmp", S_IRUGO, &igmp_mc_seq_fops);
+ pde = proc_create("igmp", S_IRUGO, net->proc_net, &igmp_mc_seq_fops);
if (!pde)
goto out_igmp;
- pde = proc_net_fops_create(net, "mcfilter", S_IRUGO, &igmp_mcf_seq_fops);
+ pde = proc_create("mcfilter", S_IRUGO, net->proc_net,
+ &igmp_mcf_seq_fops);
if (!pde)
goto out_mcfilter;
return 0;
out_mcfilter:
- proc_net_remove(net, "igmp");
+ remove_proc_entry("igmp", net->proc_net);
out_igmp:
return -ENOMEM;
}
static void __net_exit igmp_net_exit(struct net *net)
{
- proc_net_remove(net, "mcfilter");
- proc_net_remove(net, "igmp");
+ remove_proc_entry("mcfilter", net->proc_net);
+ remove_proc_entry("igmp", net->proc_net);
}
static struct pernet_operations igmp_net_ops = {
diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c
index 1211613c6c3..b6d30acb600 100644
--- a/net/ipv4/ip_fragment.c
+++ b/net/ipv4/ip_fragment.c
@@ -590,7 +590,7 @@ static int ip_frag_reasm(struct ipq *qp, struct sk_buff *prev,
goto out_oversize;
/* Head of list must not be cloned. */
- if (skb_cloned(head) && pskb_expand_head(head, 0, 0, GFP_ATOMIC))
+ if (skb_unclone(head, GFP_ATOMIC))
goto out_nomem;
/* If the first fragment is fragmented itself, we split
diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index 00a14b9864e..a56f1182c17 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -735,8 +735,33 @@ drop:
return 0;
}
+static struct sk_buff *handle_offloads(struct sk_buff *skb)
+{
+ int err;
+
+ if (skb_is_gso(skb)) {
+ err = skb_unclone(skb, GFP_ATOMIC);
+ if (unlikely(err))
+ goto error;
+ skb_shinfo(skb)->gso_type |= SKB_GSO_GRE;
+ return skb;
+ } else if (skb->ip_summed == CHECKSUM_PARTIAL) {
+ err = skb_checksum_help(skb);
+ if (unlikely(err))
+ goto error;
+ }
+ skb->ip_summed = CHECKSUM_NONE;
+
+ return skb;
+
+error:
+ kfree_skb(skb);
+ return ERR_PTR(err);
+}
+
static netdev_tx_t ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev)
{
+ struct pcpu_tstats *tstats = this_cpu_ptr(dev->tstats);
struct ip_tunnel *tunnel = netdev_priv(dev);
const struct iphdr *old_iph;
const struct iphdr *tiph;
@@ -751,10 +776,19 @@ static netdev_tx_t ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev
__be32 dst;
int mtu;
u8 ttl;
+ int err;
+ int pkt_len;
- if (skb->ip_summed == CHECKSUM_PARTIAL &&
- skb_checksum_help(skb))
- goto tx_error;
+ skb = handle_offloads(skb);
+ if (IS_ERR(skb)) {
+ dev->stats.tx_dropped++;
+ return NETDEV_TX_OK;
+ }
+
+ if (!skb->encapsulation) {
+ skb_reset_inner_headers(skb);
+ skb->encapsulation = 1;
+ }
old_iph = ip_hdr(skb);
@@ -855,7 +889,8 @@ static netdev_tx_t ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev
if (skb->protocol == htons(ETH_P_IP)) {
df |= (old_iph->frag_off&htons(IP_DF));
- if ((old_iph->frag_off&htons(IP_DF)) &&
+ if (!skb_is_gso(skb) &&
+ (old_iph->frag_off&htons(IP_DF)) &&
mtu < ntohs(old_iph->tot_len)) {
icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED, htonl(mtu));
ip_rt_put(rt);
@@ -875,7 +910,9 @@ static netdev_tx_t ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev
}
}
- if (mtu >= IPV6_MIN_MTU && mtu < skb->len - tunnel->hlen + gre_hlen) {
+ if (!skb_is_gso(skb) &&
+ mtu >= IPV6_MIN_MTU &&
+ mtu < skb->len - tunnel->hlen + gre_hlen) {
icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);
ip_rt_put(rt);
goto tx_error;
@@ -936,6 +973,7 @@ static netdev_tx_t ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev
iph->daddr = fl4.daddr;
iph->saddr = fl4.saddr;
iph->ttl = ttl;
+ iph->id = 0;
if (ttl == 0) {
if (skb->protocol == htons(ETH_P_IP))
@@ -964,9 +1002,19 @@ static netdev_tx_t ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev
*ptr = tunnel->parms.o_key;
ptr--;
}
- if (tunnel->parms.o_flags&GRE_CSUM) {
+ /* Skip GRE checksum if skb is getting offloaded. */
+ if (!(skb_shinfo(skb)->gso_type & SKB_GSO_GRE) &&
+ (tunnel->parms.o_flags&GRE_CSUM)) {
int offset = skb_transport_offset(skb);
+ if (skb_has_shared_frag(skb)) {
+ err = __skb_linearize(skb);
+ if (err) {
+ ip_rt_put(rt);
+ goto tx_error;
+ }
+ }
+
*ptr = 0;
*(__sum16 *)ptr = csum_fold(skb_checksum(skb, offset,
skb->len - offset,
@@ -974,7 +1022,19 @@ static netdev_tx_t ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev
}
}
- iptunnel_xmit(skb, dev);
+ nf_reset(skb);
+
+ pkt_len = skb->len - skb_transport_offset(skb);
+ err = ip_local_out(skb);
+ if (likely(net_xmit_eval(err) == 0)) {
+ u64_stats_update_begin(&tstats->syncp);
+ tstats->tx_bytes += pkt_len;
+ tstats->tx_packets++;
+ u64_stats_update_end(&tstats->syncp);
+ } else {
+ dev->stats.tx_errors++;
+ dev->stats.tx_aborted_errors++;
+ }
return NETDEV_TX_OK;
#if IS_ENABLED(CONFIG_IPV6)
@@ -1044,6 +1104,11 @@ static int ipgre_tunnel_bind_dev(struct net_device *dev)
mtu = 68;
tunnel->hlen = addend;
+ /* TCP offload with GRE SEQ is not supported. */
+ if (!(tunnel->parms.o_flags & GRE_SEQ)) {
+ dev->features |= NETIF_F_GSO_SOFTWARE;
+ dev->hw_features |= NETIF_F_GSO_SOFTWARE;
+ }
return mtu;
}
@@ -1593,6 +1658,9 @@ static void ipgre_tap_setup(struct net_device *dev)
dev->iflink = 0;
dev->features |= NETIF_F_NETNS_LOCAL;
+
+ dev->features |= GRE_FEATURES;
+ dev->hw_features |= GRE_FEATURES;
}
static int ipgre_newlink(struct net *src_net, struct net_device *dev, struct nlattr *tb[],
diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c
index f1395a6fb35..87abd3e2bd3 100644
--- a/net/ipv4/ip_input.c
+++ b/net/ipv4/ip_input.c
@@ -208,13 +208,6 @@ static int ip_local_deliver_finish(struct sk_buff *skb)
if (ipprot != NULL) {
int ret;
- if (!net_eq(net, &init_net) && !ipprot->netns_ok) {
- net_info_ratelimited("%s: proto %d isn't netns-ready\n",
- __func__, protocol);
- kfree_skb(skb);
- goto out;
- }
-
if (!ipprot->no_policy) {
if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb)) {
kfree_skb(skb);
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 3e98ed2bff5..5e12dca7b3d 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -598,6 +598,7 @@ slow_path:
/* for offloaded checksums cleanup checksum before fragmentation */
if ((skb->ip_summed == CHECKSUM_PARTIAL) && skb_checksum_help(skb))
goto fail;
+ iph = ip_hdr(skb);
left = skb->len - hlen; /* Space per frame */
ptr = hlen; /* Where to start from */
diff --git a/net/ipv4/ipconfig.c b/net/ipv4/ipconfig.c
index a2e50ae80b5..98cbc687701 100644
--- a/net/ipv4/ipconfig.c
+++ b/net/ipv4/ipconfig.c
@@ -1394,7 +1394,7 @@ static int __init ip_auto_config(void)
unsigned int i;
#ifdef CONFIG_PROC_FS
- proc_net_fops_create(&init_net, "pnp", S_IRUGO, &pnp_seq_fops);
+ proc_create("pnp", S_IRUGO, init_net.proc_net, &pnp_seq_fops);
#endif /* CONFIG_PROC_FS */
if (!ic_enable)
diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index 7085b9b51e7..5f95b3aa579 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -2703,16 +2703,16 @@ static int __net_init ipmr_net_init(struct net *net)
#ifdef CONFIG_PROC_FS
err = -ENOMEM;
- if (!proc_net_fops_create(net, "ip_mr_vif", 0, &ipmr_vif_fops))
+ if (!proc_create("ip_mr_vif", 0, net->proc_net, &ipmr_vif_fops))
goto proc_vif_fail;
- if (!proc_net_fops_create(net, "ip_mr_cache", 0, &ipmr_mfc_fops))
+ if (!proc_create("ip_mr_cache", 0, net->proc_net, &ipmr_mfc_fops))
goto proc_cache_fail;
#endif
return 0;
#ifdef CONFIG_PROC_FS
proc_cache_fail:
- proc_net_remove(net, "ip_mr_vif");
+ remove_proc_entry("ip_mr_vif", net->proc_net);
proc_vif_fail:
ipmr_rules_exit(net);
#endif
@@ -2723,8 +2723,8 @@ fail:
static void __net_exit ipmr_net_exit(struct net *net)
{
#ifdef CONFIG_PROC_FS
- proc_net_remove(net, "ip_mr_cache");
- proc_net_remove(net, "ip_mr_vif");
+ remove_proc_entry("ip_mr_cache", net->proc_net);
+ remove_proc_entry("ip_mr_vif", net->proc_net);
#endif
ipmr_rules_exit(net);
}
diff --git a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4_compat.c b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4_compat.c
index 9682b36df38..f2ca1279408 100644
--- a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4_compat.c
+++ b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4_compat.c
@@ -417,12 +417,12 @@ static int __net_init ip_conntrack_net_init(struct net *net)
{
struct proc_dir_entry *proc, *proc_exp, *proc_stat;
- proc = proc_net_fops_create(net, "ip_conntrack", 0440, &ct_file_ops);
+ proc = proc_create("ip_conntrack", 0440, net->proc_net, &ct_file_ops);
if (!proc)
goto err1;
- proc_exp = proc_net_fops_create(net, "ip_conntrack_expect", 0440,
- &ip_exp_file_ops);
+ proc_exp = proc_create("ip_conntrack_expect", 0440, net->proc_net,
+ &ip_exp_file_ops);
if (!proc_exp)
goto err2;
@@ -433,9 +433,9 @@ static int __net_init ip_conntrack_net_init(struct net *net)
return 0;
err3:
- proc_net_remove(net, "ip_conntrack_expect");
+ remove_proc_entry("ip_conntrack_expect", net->proc_net);
err2:
- proc_net_remove(net, "ip_conntrack");
+ remove_proc_entry("ip_conntrack", net->proc_net);
err1:
return -ENOMEM;
}
@@ -443,8 +443,8 @@ err1:
static void __net_exit ip_conntrack_net_exit(struct net *net)
{
remove_proc_entry("ip_conntrack", net->proc_net_stat);
- proc_net_remove(net, "ip_conntrack_expect");
- proc_net_remove(net, "ip_conntrack");
+ remove_proc_entry("ip_conntrack_expect", net->proc_net);
+ remove_proc_entry("ip_conntrack", net->proc_net);
}
static struct pernet_operations ip_conntrack_net_ops = {
diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c
index 6f9c07268cf..55c4ee1bba0 100644
--- a/net/ipv4/ping.c
+++ b/net/ipv4/ping.c
@@ -889,7 +889,7 @@ static int ping_proc_register(struct net *net)
struct proc_dir_entry *p;
int rc = 0;
- p = proc_net_fops_create(net, "icmp", S_IRUGO, &ping_seq_fops);
+ p = proc_create("icmp", S_IRUGO, net->proc_net, &ping_seq_fops);
if (!p)
rc = -ENOMEM;
return rc;
@@ -897,7 +897,7 @@ static int ping_proc_register(struct net *net)
static void ping_proc_unregister(struct net *net)
{
- proc_net_remove(net, "icmp");
+ remove_proc_entry("icmp", net->proc_net);
}
diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c
index 8de53e1ddd5..32030a24e77 100644
--- a/net/ipv4/proc.c
+++ b/net/ipv4/proc.c
@@ -471,28 +471,29 @@ static const struct file_operations netstat_seq_fops = {
static __net_init int ip_proc_init_net(struct net *net)
{
- if (!proc_net_fops_create(net, "sockstat", S_IRUGO, &sockstat_seq_fops))
+ if (!proc_create("sockstat", S_IRUGO, net->proc_net,
+ &sockstat_seq_fops))
goto out_sockstat;
- if (!proc_net_fops_create(net, "netstat", S_IRUGO, &netstat_seq_fops))
+ if (!proc_create("netstat", S_IRUGO, net->proc_net, &netstat_seq_fops))
goto out_netstat;
- if (!proc_net_fops_create(net, "snmp", S_IRUGO, &snmp_seq_fops))
+ if (!proc_create("snmp", S_IRUGO, net->proc_net, &snmp_seq_fops))
goto out_snmp;
return 0;
out_snmp:
- proc_net_remove(net, "netstat");
+ remove_proc_entry("netstat", net->proc_net);
out_netstat:
- proc_net_remove(net, "sockstat");
+ remove_proc_entry("sockstat", net->proc_net);
out_sockstat:
return -ENOMEM;
}
static __net_exit void ip_proc_exit_net(struct net *net)
{
- proc_net_remove(net, "snmp");
- proc_net_remove(net, "netstat");
- proc_net_remove(net, "sockstat");
+ remove_proc_entry("snmp", net->proc_net);
+ remove_proc_entry("netstat", net->proc_net);
+ remove_proc_entry("sockstat", net->proc_net);
}
static __net_initdata struct pernet_operations ip_proc_ops = {
diff --git a/net/ipv4/protocol.c b/net/ipv4/protocol.c
index 0f9d09f54bd..ce848461acb 100644
--- a/net/ipv4/protocol.c
+++ b/net/ipv4/protocol.c
@@ -37,6 +37,12 @@ const struct net_offload __rcu *inet_offloads[MAX_INET_PROTOS] __read_mostly;
int inet_add_protocol(const struct net_protocol *prot, unsigned char protocol)
{
+ if (!prot->netns_ok) {
+ pr_err("Protocol %u is not namespace aware, cannot register.\n",
+ protocol);
+ return -EINVAL;
+ }
+
return !cmpxchg((const struct net_protocol **)&inet_protos[protocol],
NULL, prot) ? 0 : -1;
}
diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c
index 6f08991409c..53ddebc292b 100644
--- a/net/ipv4/raw.c
+++ b/net/ipv4/raw.c
@@ -1050,7 +1050,7 @@ static const struct file_operations raw_seq_fops = {
static __net_init int raw_init_net(struct net *net)
{
- if (!proc_net_fops_create(net, "raw", S_IRUGO, &raw_seq_fops))
+ if (!proc_create("raw", S_IRUGO, net->proc_net, &raw_seq_fops))
return -ENOMEM;
return 0;
@@ -1058,7 +1058,7 @@ static __net_init int raw_init_net(struct net *net)
static __net_exit void raw_exit_net(struct net *net)
{
- proc_net_remove(net, "raw");
+ remove_proc_entry("raw", net->proc_net);
}
static __net_initdata struct pernet_operations raw_net_ops = {
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index a0fcc47fee7..3bdd1b1ad1b 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -384,8 +384,8 @@ static int __net_init ip_rt_do_proc_init(struct net *net)
{
struct proc_dir_entry *pde;
- pde = proc_net_fops_create(net, "rt_cache", S_IRUGO,
- &rt_cache_seq_fops);
+ pde = proc_create("rt_cache", S_IRUGO, net->proc_net,
+ &rt_cache_seq_fops);
if (!pde)
goto err1;
diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index 2622707602d..960fd29d9b8 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -633,13 +633,6 @@ static struct ctl_table ipv4_table[] = {
.proc_handler = proc_tcp_congestion_control,
},
{
- .procname = "tcp_abc",
- .data = &sysctl_tcp_abc,
- .maxlen = sizeof(int),
- .mode = 0644,
- .proc_handler = proc_dointvec,
- },
- {
.procname = "tcp_mtu_probing",
.data = &sysctl_tcp_mtu_probing,
.maxlen = sizeof(int),
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 3ec1f69c5ce..7a5ba48c2cc 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -400,6 +400,8 @@ void tcp_init_sock(struct sock *sk)
tcp_enable_early_retrans(tp);
icsk->icsk_ca_ops = &tcp_init_congestion_ops;
+ tp->tsoffset = 0;
+
sk->sk_state = TCP_CLOSE;
sk->sk_write_space = sk_stream_write_space;
@@ -895,8 +897,7 @@ new_segment:
get_page(page);
skb_fill_page_desc(skb, i, page, offset, copy);
}
-
- skb_shinfo(skb)->gso_type |= SKB_GSO_SHARED_FRAG;
+ skb_shinfo(skb)->tx_flags |= SKBTX_SHARED_FRAG;
skb->len += copy;
skb->data_len += copy;
@@ -2289,7 +2290,6 @@ int tcp_disconnect(struct sock *sk, int flags)
tp->packets_out = 0;
tp->snd_ssthresh = TCP_INFINITE_SSTHRESH;
tp->snd_cwnd_cnt = 0;
- tp->bytes_acked = 0;
tp->window_clamp = 0;
tcp_set_ca_state(sk, TCP_CA_Open);
tcp_clear_retrans(tp);
@@ -2713,6 +2713,12 @@ static int do_tcp_setsockopt(struct sock *sk, int level,
else
err = -EINVAL;
break;
+ case TCP_TIMESTAMP:
+ if (!tp->repair)
+ err = -EPERM;
+ else
+ tp->tsoffset = val - tcp_time_stamp;
+ break;
default:
err = -ENOPROTOOPT;
break;
@@ -2961,6 +2967,9 @@ static int do_tcp_getsockopt(struct sock *sk, int level,
case TCP_USER_TIMEOUT:
val = jiffies_to_msecs(icsk->icsk_user_timeout);
break;
+ case TCP_TIMESTAMP:
+ val = tcp_time_stamp + tp->tsoffset;
+ break;
default:
return -ENOPROTOOPT;
}
@@ -3034,7 +3043,7 @@ struct sk_buff *tcp_tso_segment(struct sk_buff *skb,
SKB_GSO_DODGY |
SKB_GSO_TCP_ECN |
SKB_GSO_TCPV6 |
- SKB_GSO_SHARED_FRAG |
+ SKB_GSO_GRE |
0) ||
!(type & (SKB_GSO_TCPV4 | SKB_GSO_TCPV6))))
goto out;
diff --git a/net/ipv4/tcp_cong.c b/net/ipv4/tcp_cong.c
index 291f2ed7cc3..019c2389a34 100644
--- a/net/ipv4/tcp_cong.c
+++ b/net/ipv4/tcp_cong.c
@@ -310,35 +310,24 @@ void tcp_slow_start(struct tcp_sock *tp)
{
int cnt; /* increase in packets */
unsigned int delta = 0;
+ u32 snd_cwnd = tp->snd_cwnd;
- /* RFC3465: ABC Slow start
- * Increase only after a full MSS of bytes is acked
- *
- * TCP sender SHOULD increase cwnd by the number of
- * previously unacknowledged bytes ACKed by each incoming
- * acknowledgment, provided the increase is not more than L
- */
- if (sysctl_tcp_abc && tp->bytes_acked < tp->mss_cache)
- return;
+ if (unlikely(!snd_cwnd)) {
+ pr_err_once("snd_cwnd is nul, please report this bug.\n");
+ snd_cwnd = 1U;
+ }
if (sysctl_tcp_max_ssthresh > 0 && tp->snd_cwnd > sysctl_tcp_max_ssthresh)
cnt = sysctl_tcp_max_ssthresh >> 1; /* limited slow start */
else
- cnt = tp->snd_cwnd; /* exponential increase */
-
- /* RFC3465: ABC
- * We MAY increase by 2 if discovered delayed ack
- */
- if (sysctl_tcp_abc > 1 && tp->bytes_acked >= 2*tp->mss_cache)
- cnt <<= 1;
- tp->bytes_acked = 0;
+ cnt = snd_cwnd; /* exponential increase */
tp->snd_cwnd_cnt += cnt;
- while (tp->snd_cwnd_cnt >= tp->snd_cwnd) {
- tp->snd_cwnd_cnt -= tp->snd_cwnd;
+ while (tp->snd_cwnd_cnt >= snd_cwnd) {
+ tp->snd_cwnd_cnt -= snd_cwnd;
delta++;
}
- tp->snd_cwnd = min(tp->snd_cwnd + delta, tp->snd_cwnd_clamp);
+ tp->snd_cwnd = min(snd_cwnd + delta, tp->snd_cwnd_clamp);
}
EXPORT_SYMBOL_GPL(tcp_slow_start);
@@ -372,20 +361,9 @@ void tcp_reno_cong_avoid(struct sock *sk, u32 ack, u32 in_flight)
/* In "safe" area, increase. */
if (tp->snd_cwnd <= tp->snd_ssthresh)
tcp_slow_start(tp);
-
/* In dangerous area, increase slowly. */
- else if (sysctl_tcp_abc) {
- /* RFC3465: Appropriate Byte Count
- * increase once for each full cwnd acked
- */
- if (tp->bytes_acked >= tp->snd_cwnd*tp->mss_cache) {
- tp->bytes_acked -= tp->snd_cwnd*tp->mss_cache;
- if (tp->snd_cwnd < tp->snd_cwnd_clamp)
- tp->snd_cwnd++;
- }
- } else {
+ else
tcp_cong_avoid_ai(tp, tp->snd_cwnd);
- }
}
EXPORT_SYMBOL_GPL(tcp_reno_cong_avoid);
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 492c7cfe145..a759e19496d 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -98,7 +98,6 @@ int sysctl_tcp_frto_response __read_mostly;
int sysctl_tcp_thin_dupack __read_mostly;
int sysctl_tcp_moderate_rcvbuf __read_mostly = 1;
-int sysctl_tcp_abc __read_mostly;
int sysctl_tcp_early_retrans __read_mostly = 2;
#define FLAG_DATA 0x01 /* Incoming frame contained data. */
@@ -1240,13 +1239,13 @@ static bool tcp_shifted_skb(struct sock *sk, struct sk_buff *skb,
*/
if (!skb_shinfo(prev)->gso_size) {
skb_shinfo(prev)->gso_size = mss;
- skb_shinfo(prev)->gso_type |= sk->sk_gso_type;
+ skb_shinfo(prev)->gso_type = sk->sk_gso_type;
}
/* CHECKME: To clear or not to clear? Mimics normal skb currently */
if (skb_shinfo(skb)->gso_segs <= 1) {
skb_shinfo(skb)->gso_size = 0;
- skb_shinfo(skb)->gso_type &= SKB_GSO_SHARED_FRAG;
+ skb_shinfo(skb)->gso_type = 0;
}
/* Difference in this won't matter, both ACKed by the same cumul. ACK */
@@ -2007,7 +2006,6 @@ static void tcp_enter_frto_loss(struct sock *sk, int allowed_segments, int flag)
tp->snd_cwnd_cnt = 0;
tp->snd_cwnd_stamp = tcp_time_stamp;
tp->frto_counter = 0;
- tp->bytes_acked = 0;
tp->reordering = min_t(unsigned int, tp->reordering,
sysctl_tcp_reordering);
@@ -2056,7 +2054,6 @@ void tcp_enter_loss(struct sock *sk, int how)
tp->snd_cwnd_cnt = 0;
tp->snd_cwnd_stamp = tcp_time_stamp;
- tp->bytes_acked = 0;
tcp_clear_retrans_partial(tp);
if (tcp_is_reno(tp))
@@ -2684,7 +2681,6 @@ static void tcp_init_cwnd_reduction(struct sock *sk, const bool set_ssthresh)
struct tcp_sock *tp = tcp_sk(sk);
tp->high_seq = tp->snd_nxt;
- tp->bytes_acked = 0;
tp->snd_cwnd_cnt = 0;
tp->prior_cwnd = tp->snd_cwnd;
tp->prr_delivered = 0;
@@ -2735,7 +2731,6 @@ void tcp_enter_cwr(struct sock *sk, const int set_ssthresh)
struct tcp_sock *tp = tcp_sk(sk);
tp->prior_ssthresh = 0;
- tp->bytes_acked = 0;
if (inet_csk(sk)->icsk_ca_state < TCP_CA_CWR) {
tp->undo_marker = 0;
tcp_init_cwnd_reduction(sk, set_ssthresh);
@@ -3417,7 +3412,6 @@ static void tcp_conservative_spur_to_response(struct tcp_sock *tp)
{
tp->snd_cwnd = min(tp->snd_cwnd, tp->snd_ssthresh);
tp->snd_cwnd_cnt = 0;
- tp->bytes_acked = 0;
TCP_ECN_queue_cwr(tp);
tcp_moderate_cwnd(tp);
}
@@ -3502,6 +3496,11 @@ static bool tcp_process_frto(struct sock *sk, int flag)
}
} else {
if (!(flag & FLAG_DATA_ACKED) && (tp->frto_counter == 1)) {
+ if (!tcp_packets_in_flight(tp)) {
+ tcp_enter_frto_loss(sk, 2, flag);
+ return true;
+ }
+
/* Prevent sending of new data. */
tp->snd_cwnd = min(tp->snd_cwnd,
tcp_packets_in_flight(tp));
@@ -3608,15 +3607,6 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag)
if (after(ack, prior_snd_una))
flag |= FLAG_SND_UNA_ADVANCED;
- if (sysctl_tcp_abc) {
- if (icsk->icsk_ca_state < TCP_CA_CWR)
- tp->bytes_acked += ack - prior_snd_una;
- else if (icsk->icsk_ca_state == TCP_CA_Loss)
- /* we assume just one segment left network */
- tp->bytes_acked += min(ack - prior_snd_una,
- tp->mss_cache);
- }
-
prior_fackets = tp->fackets_out;
prior_in_flight = tcp_packets_in_flight(tp);
@@ -3870,7 +3860,7 @@ static bool tcp_parse_aligned_timestamp(struct tcp_sock *tp, const struct tcphdr
++ptr;
tp->rx_opt.rcv_tsval = ntohl(*ptr);
++ptr;
- tp->rx_opt.rcv_tsecr = ntohl(*ptr);
+ tp->rx_opt.rcv_tsecr = ntohl(*ptr) - tp->tsoffset;
return true;
}
return false;
@@ -3894,7 +3884,11 @@ static bool tcp_fast_parse_options(const struct sk_buff *skb,
if (tcp_parse_aligned_timestamp(tp, th))
return true;
}
+
tcp_parse_options(skb, &tp->rx_opt, hvpp, 1, NULL);
+ if (tp->rx_opt.saw_tstamp)
+ tp->rx_opt.rcv_tsecr -= tp->tsoffset;
+
return true;
}
@@ -5647,8 +5641,7 @@ static bool tcp_rcv_fastopen_synack(struct sock *sk, struct sk_buff *synack,
* the remote receives only the retransmitted (regular) SYNs: either
* the original SYN-data or the corresponding SYN-ACK is lost.
*/
- syn_drop = (cookie->len <= 0 && data &&
- inet_csk(sk)->icsk_retransmits);
+ syn_drop = (cookie->len <= 0 && data && tp->total_retrans);
tcp_fastopen_cache_set(sk, mss, cookie, syn_drop);
@@ -5676,6 +5669,8 @@ static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb,
int saved_clamp = tp->rx_opt.mss_clamp;
tcp_parse_options(skb, &tp->rx_opt, &hash_location, 0, &foc);
+ if (tp->rx_opt.saw_tstamp)
+ tp->rx_opt.rcv_tsecr -= tp->tsoffset;
if (th->ack) {
/* rfc793:
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 5a1cfc692df..145d3bf8df8 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -496,6 +496,7 @@ void tcp_v4_err(struct sk_buff *icmp_skb, u32 info)
* errors returned from accept().
*/
inet_csk_reqsk_queue_drop(sk, req, prev);
+ NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_LISTENDROPS);
goto out;
case TCP_SYN_SENT:
@@ -725,7 +726,7 @@ release_sk1:
*/
static void tcp_v4_send_ack(struct sk_buff *skb, u32 seq, u32 ack,
- u32 win, u32 ts, int oif,
+ u32 win, u32 tsval, u32 tsecr, int oif,
struct tcp_md5sig_key *key,
int reply_flags, u8 tos)
{
@@ -746,12 +747,12 @@ static void tcp_v4_send_ack(struct sk_buff *skb, u32 seq, u32 ack,
arg.iov[0].iov_base = (unsigned char *)&rep;
arg.iov[0].iov_len = sizeof(rep.th);
- if (ts) {
+ if (tsecr) {
rep.opt[0] = htonl((TCPOPT_NOP << 24) | (TCPOPT_NOP << 16) |
(TCPOPT_TIMESTAMP << 8) |
TCPOLEN_TIMESTAMP);
- rep.opt[1] = htonl(tcp_time_stamp);
- rep.opt[2] = htonl(ts);
+ rep.opt[1] = htonl(tsval);
+ rep.opt[2] = htonl(tsecr);
arg.iov[0].iov_len += TCPOLEN_TSTAMP_ALIGNED;
}
@@ -766,7 +767,7 @@ static void tcp_v4_send_ack(struct sk_buff *skb, u32 seq, u32 ack,
#ifdef CONFIG_TCP_MD5SIG
if (key) {
- int offset = (ts) ? 3 : 0;
+ int offset = (tsecr) ? 3 : 0;
rep.opt[offset++] = htonl((TCPOPT_NOP << 24) |
(TCPOPT_NOP << 16) |
@@ -801,6 +802,7 @@ static void tcp_v4_timewait_ack(struct sock *sk, struct sk_buff *skb)
tcp_v4_send_ack(skb, tcptw->tw_snd_nxt, tcptw->tw_rcv_nxt,
tcptw->tw_rcv_wnd >> tw->tw_rcv_wscale,
+ tcp_time_stamp + tcptw->tw_ts_offset,
tcptw->tw_ts_recent,
tw->tw_bound_dev_if,
tcp_twsk_md5_key(tcptw),
@@ -820,6 +822,7 @@ static void tcp_v4_reqsk_send_ack(struct sock *sk, struct sk_buff *skb,
tcp_v4_send_ack(skb, (sk->sk_state == TCP_LISTEN) ?
tcp_rsk(req)->snt_isn + 1 : tcp_sk(sk)->snd_nxt,
tcp_rsk(req)->rcv_nxt, req->rcv_wnd,
+ tcp_time_stamp,
req->ts_recent,
0,
tcp_md5_do_lookup(sk, (union tcp_md5_addr *)&ip_hdr(skb)->daddr,
@@ -1501,8 +1504,10 @@ int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb)
* clogging syn queue with openreqs with exponentially increasing
* timeout.
*/
- if (sk_acceptq_is_full(sk) && inet_csk_reqsk_queue_young(sk) > 1)
+ if (sk_acceptq_is_full(sk) && inet_csk_reqsk_queue_young(sk) > 1) {
+ NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_LISTENOVERFLOWS);
goto drop;
+ }
req = inet_reqsk_alloc(&tcp_request_sock_ops);
if (!req)
@@ -1667,6 +1672,7 @@ drop_and_release:
drop_and_free:
reqsk_free(req);
drop:
+ NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_LISTENDROPS);
return 0;
}
EXPORT_SYMBOL(tcp_v4_conn_request);
@@ -2610,7 +2616,7 @@ EXPORT_SYMBOL(tcp_proc_register);
void tcp_proc_unregister(struct net *net, struct tcp_seq_afinfo *afinfo)
{
- proc_net_remove(net, afinfo->name);
+ remove_proc_entry(afinfo->name, net->proc_net);
}
EXPORT_SYMBOL(tcp_proc_unregister);
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index f35f2dfb640..b83a49cc381 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -102,6 +102,7 @@ tcp_timewait_state_process(struct inet_timewait_sock *tw, struct sk_buff *skb,
tcp_parse_options(skb, &tmp_opt, &hash_location, 0, NULL);
if (tmp_opt.saw_tstamp) {
+ tmp_opt.rcv_tsecr -= tcptw->tw_ts_offset;
tmp_opt.ts_recent = tcptw->tw_ts_recent;
tmp_opt.ts_recent_stamp = tcptw->tw_ts_recent_stamp;
paws_reject = tcp_paws_reject(&tmp_opt, th->rst);
@@ -288,6 +289,7 @@ void tcp_time_wait(struct sock *sk, int state, int timeo)
tcptw->tw_rcv_wnd = tcp_receive_window(tp);
tcptw->tw_ts_recent = tp->rx_opt.ts_recent;
tcptw->tw_ts_recent_stamp = tp->rx_opt.ts_recent_stamp;
+ tcptw->tw_ts_offset = tp->tsoffset;
#if IS_ENABLED(CONFIG_IPV6)
if (tw->tw_family == PF_INET6) {
@@ -446,7 +448,6 @@ struct sock *tcp_create_openreq_child(struct sock *sk, struct request_sock *req,
*/
newtp->snd_cwnd = TCP_INIT_CWND;
newtp->snd_cwnd_cnt = 0;
- newtp->bytes_acked = 0;
newtp->frto_counter = 0;
newtp->frto_highmark = 0;
@@ -500,6 +501,7 @@ struct sock *tcp_create_openreq_child(struct sock *sk, struct request_sock *req,
newtp->rx_opt.ts_recent_stamp = 0;
newtp->tcp_header_len = sizeof(struct tcphdr);
}
+ newtp->tsoffset = 0;
#ifdef CONFIG_TCP_MD5SIG
newtp->md5sig_info = NULL; /*XXX*/
if (newtp->af_specific->md5_lookup(sk, newsk))
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 367e2ec01da..fd0cea114b5 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -622,7 +622,7 @@ static unsigned int tcp_syn_options(struct sock *sk, struct sk_buff *skb,
if (likely(sysctl_tcp_timestamps && *md5 == NULL)) {
opts->options |= OPTION_TS;
- opts->tsval = TCP_SKB_CB(skb)->when;
+ opts->tsval = TCP_SKB_CB(skb)->when + tp->tsoffset;
opts->tsecr = tp->rx_opt.ts_recent;
remaining -= TCPOLEN_TSTAMP_ALIGNED;
}
@@ -806,7 +806,7 @@ static unsigned int tcp_established_options(struct sock *sk, struct sk_buff *skb
if (likely(tp->rx_opt.tstamp_ok)) {
opts->options |= OPTION_TS;
- opts->tsval = tcb ? tcb->when : 0;
+ opts->tsval = tcb ? tcb->when + tp->tsoffset : 0;
opts->tsecr = tp->rx_opt.ts_recent;
size += TCPOLEN_TSTAMP_ALIGNED;
}
@@ -1133,7 +1133,6 @@ static void tcp_queue_skb(struct sock *sk, struct sk_buff *skb)
static void tcp_set_skb_tso_segs(const struct sock *sk, struct sk_buff *skb,
unsigned int mss_now)
{
- skb_shinfo(skb)->gso_type &= SKB_GSO_SHARED_FRAG;
if (skb->len <= mss_now || !sk_can_gso(sk) ||
skb->ip_summed == CHECKSUM_NONE) {
/* Avoid the costly divide in the normal
@@ -1141,10 +1140,11 @@ static void tcp_set_skb_tso_segs(const struct sock *sk, struct sk_buff *skb,
*/
skb_shinfo(skb)->gso_segs = 1;
skb_shinfo(skb)->gso_size = 0;
+ skb_shinfo(skb)->gso_type = 0;
} else {
skb_shinfo(skb)->gso_segs = DIV_ROUND_UP(skb->len, mss_now);
skb_shinfo(skb)->gso_size = mss_now;
- skb_shinfo(skb)->gso_type |= sk->sk_gso_type;
+ skb_shinfo(skb)->gso_type = sk->sk_gso_type;
}
}
@@ -1331,7 +1331,7 @@ static void __pskb_trim_head(struct sk_buff *skb, int len)
/* Remove acked data from a packet in the transmit queue. */
int tcp_trim_head(struct sock *sk, struct sk_buff *skb, u32 len)
{
- if (skb_cloned(skb) && pskb_expand_head(skb, 0, 0, GFP_ATOMIC))
+ if (skb_unclone(skb, GFP_ATOMIC))
return -ENOMEM;
__pskb_trim_head(skb, len);
diff --git a/net/ipv4/tcp_probe.c b/net/ipv4/tcp_probe.c
index 4526fe68e60..d4943f67aff 100644
--- a/net/ipv4/tcp_probe.c
+++ b/net/ipv4/tcp_probe.c
@@ -234,7 +234,7 @@ static __init int tcpprobe_init(void)
if (!tcp_probe.log)
goto err0;
- if (!proc_net_fops_create(&init_net, procname, S_IRUSR, &tcpprobe_fops))
+ if (!proc_create(procname, S_IRUSR, init_net.proc_net, &tcpprobe_fops))
goto err0;
ret = register_jprobe(&tcp_jprobe);
@@ -244,7 +244,7 @@ static __init int tcpprobe_init(void)
pr_info("probe registered (port=%d) bufsize=%u\n", port, bufsize);
return 0;
err1:
- proc_net_remove(&init_net, procname);
+ remove_proc_entry(procname, init_net.proc_net);
err0:
kfree(tcp_probe.log);
return ret;
@@ -253,7 +253,7 @@ module_init(tcpprobe_init);
static __exit void tcpprobe_exit(void)
{
- proc_net_remove(&init_net, procname);
+ remove_proc_entry(procname, init_net.proc_net);
unregister_jprobe(&tcp_jprobe);
kfree(tcp_probe.log);
}
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 6791aac06ea..265c42cf963 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -2122,7 +2122,7 @@ EXPORT_SYMBOL(udp_proc_register);
void udp_proc_unregister(struct net *net, struct udp_seq_afinfo *afinfo)
{
- proc_net_remove(net, afinfo->name);
+ remove_proc_entry(afinfo->name, net->proc_net);
}
EXPORT_SYMBOL(udp_proc_unregister);
@@ -2305,7 +2305,8 @@ struct sk_buff *udp4_ufo_fragment(struct sk_buff *skb,
/* Packet is from an untrusted source, reset gso_segs. */
int type = skb_shinfo(skb)->gso_type;
- if (unlikely(type & ~(SKB_GSO_UDP | SKB_GSO_DODGY) ||
+ if (unlikely(type & ~(SKB_GSO_UDP | SKB_GSO_DODGY |
+ SKB_GSO_GRE) ||
!(type & (SKB_GSO_UDP))))
goto out;
diff --git a/net/ipv4/xfrm4_input.c b/net/ipv4/xfrm4_input.c
index 06814b6216d..1f12c8b4586 100644
--- a/net/ipv4/xfrm4_input.c
+++ b/net/ipv4/xfrm4_input.c
@@ -132,7 +132,7 @@ int xfrm4_udp_encap_rcv(struct sock *sk, struct sk_buff *skb)
* header and optional ESP marker bytes) and then modify the
* protocol to ESP, and then call into the transform receiver.
*/
- if (skb_cloned(skb) && pskb_expand_head(skb, 0, 0, GFP_ATOMIC))
+ if (skb_unclone(skb, GFP_ATOMIC))
goto drop;
/* Now we can update and verify the packet length... */
diff --git a/net/ipv4/xfrm4_mode_tunnel.c b/net/ipv4/xfrm4_mode_tunnel.c
index ddee0a099a2..fe5189e2e11 100644
--- a/net/ipv4/xfrm4_mode_tunnel.c
+++ b/net/ipv4/xfrm4_mode_tunnel.c
@@ -142,8 +142,8 @@ static int xfrm4_mode_tunnel_input(struct xfrm_state *x, struct sk_buff *skb)
for_each_input_rcu(rcv_notify_handlers, handler)
handler->handler(skb);
- if (skb_cloned(skb) &&
- (err = pskb_expand_head(skb, 0, 0, GFP_ATOMIC)))
+ err = skb_unclone(skb, GFP_ATOMIC);
+ if (err)
goto out;
if (x->props.flags & XFRM_STATE_DECAP_DSCP)
diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c
index 3be0ac2c192..9a459be24af 100644
--- a/net/ipv4/xfrm4_policy.c
+++ b/net/ipv4/xfrm4_policy.c
@@ -262,21 +262,56 @@ static struct ctl_table xfrm4_policy_table[] = {
{ }
};
-static struct ctl_table_header *sysctl_hdr;
-#endif
-
-static void __init xfrm4_policy_init(void)
+static int __net_init xfrm4_net_init(struct net *net)
{
- xfrm_policy_register_afinfo(&xfrm4_policy_afinfo);
+ struct ctl_table *table;
+ struct ctl_table_header *hdr;
+
+ table = xfrm4_policy_table;
+ if (!net_eq(net, &init_net)) {
+ table = kmemdup(table, sizeof(xfrm4_policy_table), GFP_KERNEL);
+ if (!table)
+ goto err_alloc;
+
+ table[0].data = &net->xfrm.xfrm4_dst_ops.gc_thresh;
+ }
+
+ hdr = register_net_sysctl(net, "net/ipv4", table);
+ if (!hdr)
+ goto err_reg;
+
+ net->ipv4.xfrm4_hdr = hdr;
+ return 0;
+
+err_reg:
+ if (!net_eq(net, &init_net))
+ kfree(table);
+err_alloc:
+ return -ENOMEM;
}
-static void __exit xfrm4_policy_fini(void)
+static void __net_exit xfrm4_net_exit(struct net *net)
{
-#ifdef CONFIG_SYSCTL
- if (sysctl_hdr)
- unregister_net_sysctl_table(sysctl_hdr);
+ struct ctl_table *table;
+
+ if (net->ipv4.xfrm4_hdr == NULL)
+ return;
+
+ table = net->ipv4.xfrm4_hdr->ctl_table_arg;
+ unregister_net_sysctl_table(net->ipv4.xfrm4_hdr);
+ if (!net_eq(net, &init_net))
+ kfree(table);
+}
+
+static struct pernet_operations __net_initdata xfrm4_net_ops = {
+ .init = xfrm4_net_init,
+ .exit = xfrm4_net_exit,
+};
#endif
- xfrm_policy_unregister_afinfo(&xfrm4_policy_afinfo);
+
+static void __init xfrm4_policy_init(void)
+{
+ xfrm_policy_register_afinfo(&xfrm4_policy_afinfo);
}
void __init xfrm4_init(void)
@@ -286,8 +321,7 @@ void __init xfrm4_init(void)
xfrm4_state_init();
xfrm4_policy_init();
#ifdef CONFIG_SYSCTL
- sysctl_hdr = register_net_sysctl(&init_net, "net/ipv4",
- xfrm4_policy_table);
+ register_pernet_subsys(&xfrm4_net_ops);
#endif
}
generated by cgit v1.2.3-70-g09d2 (git 2.46.0) at 2025-01-29 12:08:06 +0000