summaryrefslogtreecommitdiffstats
path: root/net/ipv4
diff options
context:
space:
mode:
Diffstat (limited to 'net/ipv4')
-rw-r--r--net/ipv4/icmp.c3
-rw-r--r--net/ipv4/inet_diag.c5
-rw-r--r--net/ipv4/ip_sockglue.c35
-rw-r--r--net/ipv4/ip_vti.c5
-rw-r--r--net/ipv4/ipmr.c4
-rw-r--r--net/ipv4/netfilter/iptable_nat.c4
-rw-r--r--net/ipv4/route.c9
-rw-r--r--net/ipv4/tcp.c19
-rw-r--r--net/ipv4/tcp_illinois.c8
-rw-r--r--net/ipv4/tcp_input.c18
-rw-r--r--net/ipv4/tcp_metrics.c14
-rw-r--r--net/ipv4/tcp_output.c4
-rw-r--r--net/ipv4/xfrm4_policy.c13
13 files changed, 87 insertions, 54 deletions
diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c
index f2eccd5..17ff9fd 100644
--- a/net/ipv4/icmp.c
+++ b/net/ipv4/icmp.c
@@ -257,7 +257,8 @@ static inline bool icmpv4_xrlim_allow(struct net *net, struct rtable *rt,
struct inet_peer *peer = inet_getpeer_v4(net->ipv4.peers, fl4->daddr, 1);
rc = inet_peer_xrlim_allow(peer,
net->ipv4.sysctl_icmp_ratelimit);
- inet_putpeer(peer);
+ if (peer)
+ inet_putpeer(peer);
}
out:
return rc;
diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c
index 535584c..0c34bfa 100644
--- a/net/ipv4/inet_diag.c
+++ b/net/ipv4/inet_diag.c
@@ -892,13 +892,16 @@ static int __inet_diag_dump(struct sk_buff *skb, struct netlink_callback *cb,
struct inet_diag_req_v2 *r, struct nlattr *bc)
{
const struct inet_diag_handler *handler;
+ int err = 0;
handler = inet_diag_lock_handler(r->sdiag_protocol);
if (!IS_ERR(handler))
handler->dump(skb, cb, r, bc);
+ else
+ err = PTR_ERR(handler);
inet_diag_unlock_handler(handler);
- return skb->len;
+ return err ? : skb->len;
}
static int inet_diag_dump(struct sk_buff *skb, struct netlink_callback *cb)
diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c
index 5eea4a8..14bbfcf 100644
--- a/net/ipv4/ip_sockglue.c
+++ b/net/ipv4/ip_sockglue.c
@@ -457,19 +457,28 @@ static int do_ip_setsockopt(struct sock *sk, int level,
struct inet_sock *inet = inet_sk(sk);
int val = 0, err;
- if (((1<<optname) & ((1<<IP_PKTINFO) | (1<<IP_RECVTTL) |
- (1<<IP_RECVOPTS) | (1<<IP_RECVTOS) |
- (1<<IP_RETOPTS) | (1<<IP_TOS) |
- (1<<IP_TTL) | (1<<IP_HDRINCL) |
- (1<<IP_MTU_DISCOVER) | (1<<IP_RECVERR) |
- (1<<IP_ROUTER_ALERT) | (1<<IP_FREEBIND) |
- (1<<IP_PASSSEC) | (1<<IP_TRANSPARENT) |
- (1<<IP_MINTTL) | (1<<IP_NODEFRAG))) ||
- optname == IP_UNICAST_IF ||
- optname == IP_MULTICAST_TTL ||
- optname == IP_MULTICAST_ALL ||
- optname == IP_MULTICAST_LOOP ||
- optname == IP_RECVORIGDSTADDR) {
+ switch (optname) {
+ case IP_PKTINFO:
+ case IP_RECVTTL:
+ case IP_RECVOPTS:
+ case IP_RECVTOS:
+ case IP_RETOPTS:
+ case IP_TOS:
+ case IP_TTL:
+ case IP_HDRINCL:
+ case IP_MTU_DISCOVER:
+ case IP_RECVERR:
+ case IP_ROUTER_ALERT:
+ case IP_FREEBIND:
+ case IP_PASSSEC:
+ case IP_TRANSPARENT:
+ case IP_MINTTL:
+ case IP_NODEFRAG:
+ case IP_UNICAST_IF:
+ case IP_MULTICAST_TTL:
+ case IP_MULTICAST_ALL:
+ case IP_MULTICAST_LOOP:
+ case IP_RECVORIGDSTADDR:
if (optlen >= sizeof(int)) {
if (get_user(val, (int __user *) optval))
return -EFAULT;
diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c
index 1831092..858fddf 100644
--- a/net/ipv4/ip_vti.c
+++ b/net/ipv4/ip_vti.c
@@ -338,12 +338,17 @@ static int vti_rcv(struct sk_buff *skb)
if (tunnel != NULL) {
struct pcpu_tstats *tstats;
+ if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb))
+ return -1;
+
tstats = this_cpu_ptr(tunnel->dev->tstats);
u64_stats_update_begin(&tstats->syncp);
tstats->rx_packets++;
tstats->rx_bytes += skb->len;
u64_stats_update_end(&tstats->syncp);
+ skb->mark = 0;
+ secpath_reset(skb);
skb->dev = tunnel->dev;
return 1;
}
diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index 6168c4d..3eab2b2 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -1318,6 +1318,10 @@ int ip_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, unsi
if (get_user(v, (u32 __user *)optval))
return -EFAULT;
+ /* "pimreg%u" should not exceed 16 bytes (IFNAMSIZ) */
+ if (v != RT_TABLE_DEFAULT && v >= 1000000000)
+ return -EINVAL;
+
rtnl_lock();
ret = 0;
if (sk == rtnl_dereference(mrt->mroute_sk)) {
diff --git a/net/ipv4/netfilter/iptable_nat.c b/net/ipv4/netfilter/iptable_nat.c
index 9e0ffaf..a820472 100644
--- a/net/ipv4/netfilter/iptable_nat.c
+++ b/net/ipv4/netfilter/iptable_nat.c
@@ -184,7 +184,8 @@ nf_nat_ipv4_out(unsigned int hooknum,
if ((ct->tuplehash[dir].tuple.src.u3.ip !=
ct->tuplehash[!dir].tuple.dst.u3.ip) ||
- (ct->tuplehash[dir].tuple.src.u.all !=
+ (ct->tuplehash[dir].tuple.dst.protonum != IPPROTO_ICMP &&
+ ct->tuplehash[dir].tuple.src.u.all !=
ct->tuplehash[!dir].tuple.dst.u.all))
if (nf_xfrm_me_harder(skb, AF_INET) < 0)
ret = NF_DROP;
@@ -221,6 +222,7 @@ nf_nat_ipv4_local_fn(unsigned int hooknum,
}
#ifdef CONFIG_XFRM
else if (!(IPCB(skb)->flags & IPSKB_XFRM_TRANSFORMED) &&
+ ct->tuplehash[dir].tuple.dst.protonum != IPPROTO_ICMP &&
ct->tuplehash[dir].tuple.dst.u.all !=
ct->tuplehash[!dir].tuple.src.u.all)
if (nf_xfrm_me_harder(skb, AF_INET) < 0)
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index a8c65121..df25142 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -1785,6 +1785,7 @@ static struct rtable *__mkroute_output(const struct fib_result *res,
if (dev_out->flags & IFF_LOOPBACK)
flags |= RTCF_LOCAL;
+ do_cache = true;
if (type == RTN_BROADCAST) {
flags |= RTCF_BROADCAST | RTCF_LOCAL;
fi = NULL;
@@ -1793,6 +1794,8 @@ static struct rtable *__mkroute_output(const struct fib_result *res,
if (!ip_check_mc_rcu(in_dev, fl4->daddr, fl4->saddr,
fl4->flowi4_proto))
flags &= ~RTCF_LOCAL;
+ else
+ do_cache = false;
/* If multicast route do not exist use
* default one, but do not gateway in this case.
* Yes, it is hack.
@@ -1802,8 +1805,8 @@ static struct rtable *__mkroute_output(const struct fib_result *res,
}
fnhe = NULL;
- do_cache = fi != NULL;
- if (fi) {
+ do_cache &= fi != NULL;
+ if (do_cache) {
struct rtable __rcu **prth;
struct fib_nh *nh = &FIB_RES_NH(*res);
@@ -2597,7 +2600,7 @@ int __init ip_rt_init(void)
pr_err("Unable to create route proc files\n");
#ifdef CONFIG_XFRM
xfrm_init();
- xfrm4_init(ip_rt_max_size);
+ xfrm4_init();
#endif
rtnl_register(PF_INET, RTM_GETROUTE, inet_rtm_getroute, NULL, NULL);
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 197c000..e457c7a 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -830,8 +830,8 @@ static int tcp_send_mss(struct sock *sk, int *size_goal, int flags)
return mss_now;
}
-static ssize_t do_tcp_sendpages(struct sock *sk, struct page **pages, int poffset,
- size_t psize, int flags)
+static ssize_t do_tcp_sendpages(struct sock *sk, struct page *page, int offset,
+ size_t size, int flags)
{
struct tcp_sock *tp = tcp_sk(sk);
int mss_now, size_goal;
@@ -858,12 +858,9 @@ static ssize_t do_tcp_sendpages(struct sock *sk, struct page **pages, int poffse
if (sk->sk_err || (sk->sk_shutdown & SEND_SHUTDOWN))
goto out_err;
- while (psize > 0) {
+ while (size > 0) {
struct sk_buff *skb = tcp_write_queue_tail(sk);
- struct page *page = pages[poffset / PAGE_SIZE];
int copy, i;
- int offset = poffset % PAGE_SIZE;
- int size = min_t(size_t, psize, PAGE_SIZE - offset);
bool can_coalesce;
if (!tcp_send_head(sk) || (copy = size_goal - skb->len) <= 0) {
@@ -912,8 +909,8 @@ new_segment:
TCP_SKB_CB(skb)->tcp_flags &= ~TCPHDR_PSH;
copied += copy;
- poffset += copy;
- if (!(psize -= copy))
+ offset += copy;
+ if (!(size -= copy))
goto out;
if (skb->len < size_goal || (flags & MSG_OOB))
@@ -960,7 +957,7 @@ int tcp_sendpage(struct sock *sk, struct page *page, int offset,
flags);
lock_sock(sk);
- res = do_tcp_sendpages(sk, &page, offset, size, flags);
+ res = do_tcp_sendpages(sk, page, offset, size, flags);
release_sock(sk);
return res;
}
@@ -1212,7 +1209,7 @@ new_segment:
wait_for_sndbuf:
set_bit(SOCK_NOSPACE, &sk->sk_socket->flags);
wait_for_memory:
- if (copied && likely(!tp->repair))
+ if (copied)
tcp_push(sk, flags & ~MSG_MORE, mss_now, TCP_NAGLE_PUSH);
if ((err = sk_stream_wait_memory(sk, &timeo)) != 0)
@@ -1223,7 +1220,7 @@ wait_for_memory:
}
out:
- if (copied && likely(!tp->repair))
+ if (copied)
tcp_push(sk, flags, mss_now, tp->nonagle);
release_sock(sk);
return copied + copied_syn;
diff --git a/net/ipv4/tcp_illinois.c b/net/ipv4/tcp_illinois.c
index 813b43a..834857f 100644
--- a/net/ipv4/tcp_illinois.c
+++ b/net/ipv4/tcp_illinois.c
@@ -313,11 +313,13 @@ static void tcp_illinois_info(struct sock *sk, u32 ext,
.tcpv_rttcnt = ca->cnt_rtt,
.tcpv_minrtt = ca->base_rtt,
};
- u64 t = ca->sum_rtt;
- do_div(t, ca->cnt_rtt);
- info.tcpv_rtt = t;
+ if (info.tcpv_rttcnt > 0) {
+ u64 t = ca->sum_rtt;
+ do_div(t, info.tcpv_rttcnt);
+ info.tcpv_rtt = t;
+ }
nla_put(skb, INET_DIAG_VEGASINFO, sizeof(info), &info);
}
}
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 1db6639..609ff98 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -4529,6 +4529,9 @@ int tcp_send_rcvq(struct sock *sk, struct msghdr *msg, size_t size)
struct tcphdr *th;
bool fragstolen;
+ if (size == 0)
+ return 0;
+
skb = alloc_skb(size + sizeof(*th), sk->sk_allocation);
if (!skb)
goto err;
@@ -5310,11 +5313,6 @@ static bool tcp_validate_incoming(struct sock *sk, struct sk_buff *skb,
goto discard;
}
- /* ts_recent update must be made after we are sure that the packet
- * is in window.
- */
- tcp_replace_ts_recent(tp, TCP_SKB_CB(skb)->seq);
-
/* step 3: check security and precedence [ignored] */
/* step 4: Check for a SYN
@@ -5549,6 +5547,11 @@ step5:
if (th->ack && tcp_ack(sk, skb, FLAG_SLOWPATH) < 0)
goto discard;
+ /* ts_recent update must be made after we are sure that the packet
+ * is in window.
+ */
+ tcp_replace_ts_recent(tp, TCP_SKB_CB(skb)->seq);
+
tcp_rcv_rtt_measure_ts(sk, skb);
/* Process urgent data. */
@@ -6127,6 +6130,11 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb,
} else
goto discard;
+ /* ts_recent update must be made after we are sure that the packet
+ * is in window.
+ */
+ tcp_replace_ts_recent(tp, TCP_SKB_CB(skb)->seq);
+
/* step 6: check the URG bit */
tcp_urg(sk, skb, th);
diff --git a/net/ipv4/tcp_metrics.c b/net/ipv4/tcp_metrics.c
index 4c752a6..f696d7c 100644
--- a/net/ipv4/tcp_metrics.c
+++ b/net/ipv4/tcp_metrics.c
@@ -1,7 +1,6 @@
#include <linux/rcupdate.h>
#include <linux/spinlock.h>
#include <linux/jiffies.h>
-#include <linux/bootmem.h>
#include <linux/module.h>
#include <linux/cache.h>
#include <linux/slab.h>
@@ -9,6 +8,7 @@
#include <linux/tcp.h>
#include <linux/hash.h>
#include <linux/tcp_metrics.h>
+#include <linux/vmalloc.h>
#include <net/inet_connection_sock.h>
#include <net/net_namespace.h>
@@ -864,7 +864,7 @@ static int parse_nl_addr(struct genl_info *info, struct inetpeer_addr *addr,
}
a = info->attrs[TCP_METRICS_ATTR_ADDR_IPV6];
if (a) {
- if (nla_len(a) != sizeof(sizeof(struct in6_addr)))
+ if (nla_len(a) != sizeof(struct in6_addr))
return -EINVAL;
addr->family = AF_INET6;
memcpy(addr->addr.a6, nla_data(a), sizeof(addr->addr.a6));
@@ -1034,7 +1034,10 @@ static int __net_init tcp_net_metrics_init(struct net *net)
net->ipv4.tcp_metrics_hash_log = order_base_2(slots);
size = sizeof(struct tcpm_hash_bucket) << net->ipv4.tcp_metrics_hash_log;
- net->ipv4.tcp_metrics_hash = kzalloc(size, GFP_KERNEL);
+ net->ipv4.tcp_metrics_hash = kzalloc(size, GFP_KERNEL | __GFP_NOWARN);
+ if (!net->ipv4.tcp_metrics_hash)
+ net->ipv4.tcp_metrics_hash = vzalloc(size);
+
if (!net->ipv4.tcp_metrics_hash)
return -ENOMEM;
@@ -1055,7 +1058,10 @@ static void __net_exit tcp_net_metrics_exit(struct net *net)
tm = next;
}
}
- kfree(net->ipv4.tcp_metrics_hash);
+ if (is_vmalloc_addr(net->ipv4.tcp_metrics_hash))
+ vfree(net->ipv4.tcp_metrics_hash);
+ else
+ kfree(net->ipv4.tcp_metrics_hash);
}
static __net_initdata struct pernet_operations tcp_net_metrics_ops = {
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index cfe6ffe..2798706 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -1986,6 +1986,9 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle,
tso_segs = tcp_init_tso_segs(sk, skb, mss_now);
BUG_ON(!tso_segs);
+ if (unlikely(tp->repair) && tp->repair_queue == TCP_SEND_QUEUE)
+ goto repair; /* Skip network transmission */
+
cwnd_quota = tcp_cwnd_test(tp, skb);
if (!cwnd_quota)
break;
@@ -2026,6 +2029,7 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle,
if (unlikely(tcp_transmit_skb(sk, skb, 1, gfp)))
break;
+repair:
/* Advance the send_head. This one is sent out.
* This call will increment packets_out.
*/
diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c
index 05c5ab8..3be0ac2 100644
--- a/net/ipv4/xfrm4_policy.c
+++ b/net/ipv4/xfrm4_policy.c
@@ -279,19 +279,8 @@ static void __exit xfrm4_policy_fini(void)
xfrm_policy_unregister_afinfo(&xfrm4_policy_afinfo);
}
-void __init xfrm4_init(int rt_max_size)
+void __init xfrm4_init(void)
{
- /*
- * Select a default value for the gc_thresh based on the main route
- * table hash size. It seems to me the worst case scenario is when
- * we have ipsec operating in transport mode, in which we create a
- * dst_entry per socket. The xfrm gc algorithm starts trying to remove
- * entries at gc_thresh, and prevents new allocations as 2*gc_thresh
- * so lets set an initial xfrm gc_thresh value at the rt_max_size/2.
- * That will let us store an ipsec connection per route table entry,
- * and start cleaning when were 1/2 full
- */
- xfrm4_dst_ops.gc_thresh = rt_max_size/2;
dst_entries_init(&xfrm4_dst_ops);
xfrm4_state_init();
OpenPOWER on IntegriCloud