aboutsummaryrefslogtreecommitdiff
path: root/net
diff options
context:
space:
mode:
authorMark Brown <broonie@linaro.org>2013-11-05 20:06:43 +0000
committerMark Brown <broonie@linaro.org>2013-11-05 20:06:43 +0000
commit47cf66ff098ac408194713be6531a7bb57d1b99b (patch)
tree6711205bc3d5f6200adea4ba2173f2d1d9b0c063 /net
parent66cadb7bd46c6691eea6f671380405ab03b423ad (diff)
parent7c9373fbcd0b29f6ccc28407c11ecd51cfa7a3c2 (diff)
downloadvexpress-lsk-47cf66ff098ac408194713be6531a7bb57d1b99b.tar.gz
Merge branch 'linux-linaro-lsk' into linux-linaro-lsk-android
Diffstat (limited to 'net')
-rw-r--r--net/8021q/vlan_netlink.c2
-rw-r--r--net/bridge/br_stp_if.c2
-rw-r--r--net/compat.c2
-rw-r--r--net/core/secure_seq.c2
-rw-r--r--net/core/sock.c1
-rw-r--r--net/ipv4/inet_hashtables.c2
-rw-r--r--net/ipv4/ip_output.c2
-rw-r--r--net/ipv4/ip_vti.c14
-rw-r--r--net/ipv4/route.c2
-rw-r--r--net/ipv4/sysctl_net_ipv4.c10
-rw-r--r--net/ipv4/tcp.c28
-rw-r--r--net/ipv4/tcp_input.c41
-rw-r--r--net/ipv4/tcp_output.c28
-rw-r--r--net/ipv6/inet6_hashtables.c2
-rw-r--r--net/ipv6/ip6_output.c6
-rw-r--r--net/ipv6/route.c46
-rw-r--r--net/l2tp/l2tp_core.c36
-rw-r--r--net/l2tp/l2tp_core.h3
-rw-r--r--net/l2tp/l2tp_ppp.c4
-rw-r--r--net/netfilter/nf_conntrack_h323_main.c4
-rw-r--r--net/sctp/output.c3
-rw-r--r--net/socket.c24
-rw-r--r--net/unix/af_unix.c10
-rw-r--r--net/unix/diag.c1
-rw-r--r--net/wireless/radiotap.c7
25 files changed, 228 insertions, 54 deletions
diff --git a/net/8021q/vlan_netlink.c b/net/8021q/vlan_netlink.c
index 30912973228..c7e634af851 100644
--- a/net/8021q/vlan_netlink.c
+++ b/net/8021q/vlan_netlink.c
@@ -171,7 +171,7 @@ static size_t vlan_get_size(const struct net_device *dev)
return nla_total_size(2) + /* IFLA_VLAN_PROTOCOL */
nla_total_size(2) + /* IFLA_VLAN_ID */
- sizeof(struct ifla_vlan_flags) + /* IFLA_VLAN_FLAGS */
+ nla_total_size(sizeof(struct ifla_vlan_flags)) + /* IFLA_VLAN_FLAGS */
vlan_qos_map_size(vlan->nr_ingress_mappings) +
vlan_qos_map_size(vlan->nr_egress_mappings);
}
diff --git a/net/bridge/br_stp_if.c b/net/bridge/br_stp_if.c
index 108084a0467..656a6f3e40d 100644
--- a/net/bridge/br_stp_if.c
+++ b/net/bridge/br_stp_if.c
@@ -134,7 +134,7 @@ static void br_stp_start(struct net_bridge *br)
if (br->bridge_forward_delay < BR_MIN_FORWARD_DELAY)
__br_set_forward_delay(br, BR_MIN_FORWARD_DELAY);
- else if (br->bridge_forward_delay < BR_MAX_FORWARD_DELAY)
+ else if (br->bridge_forward_delay > BR_MAX_FORWARD_DELAY)
__br_set_forward_delay(br, BR_MAX_FORWARD_DELAY);
if (r == 0) {
diff --git a/net/compat.c b/net/compat.c
index f0a1ba6c808..89032580bd1 100644
--- a/net/compat.c
+++ b/net/compat.c
@@ -71,6 +71,8 @@ int get_compat_msghdr(struct msghdr *kmsg, struct compat_msghdr __user *umsg)
__get_user(kmsg->msg_controllen, &umsg->msg_controllen) ||
__get_user(kmsg->msg_flags, &umsg->msg_flags))
return -EFAULT;
+ if (kmsg->msg_namelen > sizeof(struct sockaddr_storage))
+ return -EINVAL;
kmsg->msg_name = compat_ptr(tmp1);
kmsg->msg_iov = compat_ptr(tmp2);
kmsg->msg_control = compat_ptr(tmp3);
diff --git a/net/core/secure_seq.c b/net/core/secure_seq.c
index 3f1ec1586ae..8d9d05edd2e 100644
--- a/net/core/secure_seq.c
+++ b/net/core/secure_seq.c
@@ -10,6 +10,7 @@
#include <net/secure_seq.h>
+#if IS_ENABLED(CONFIG_IPV6) || IS_ENABLED(CONFIG_INET)
#define NET_SECRET_SIZE (MD5_MESSAGE_BYTES / 4)
static u32 net_secret[NET_SECRET_SIZE] ____cacheline_aligned;
@@ -29,6 +30,7 @@ static void net_secret_init(void)
cmpxchg(&net_secret[--i], 0, tmp);
}
}
+#endif
#ifdef CONFIG_INET
static u32 seq_scale(u32 seq)
diff --git a/net/core/sock.c b/net/core/sock.c
index d6d024cfaaa..6565431b0e6 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -2271,6 +2271,7 @@ void sock_init_data(struct socket *sock, struct sock *sk)
sk->sk_stamp = ktime_set(-1L, 0);
+ sk->sk_pacing_rate = ~0U;
/*
* Before updating sk_refcnt, we must commit prior changes to memory
* (Documentation/RCU/rculist_nulls.txt for details)
diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c
index 6af375afeee..c95848d0003 100644
--- a/net/ipv4/inet_hashtables.c
+++ b/net/ipv4/inet_hashtables.c
@@ -287,7 +287,7 @@ begintw:
if (unlikely(!INET_TW_MATCH(sk, net, acookie,
saddr, daddr, ports,
dif))) {
- sock_put(sk);
+ inet_twsk_put(inet_twsk(sk));
goto begintw;
}
goto out;
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index ec2d430a6a5..6ca5873d617 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -844,7 +844,7 @@ static int __ip_append_data(struct sock *sk,
csummode = CHECKSUM_PARTIAL;
cork->length += length;
- if (((length > mtu) || (skb && skb_is_gso(skb))) &&
+ if (((length > mtu) || (skb && skb_has_frags(skb))) &&
(sk->sk_protocol == IPPROTO_UDP) &&
(rt->dst.dev->features & NETIF_F_UFO) && !rt->dst.header_len) {
err = ip_ufo_append_data(sk, queue, getfrag, from, length,
diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c
index 17cc0ffa8c0..06560412741 100644
--- a/net/ipv4/ip_vti.c
+++ b/net/ipv4/ip_vti.c
@@ -285,8 +285,17 @@ static int vti_rcv(struct sk_buff *skb)
tunnel = vti_tunnel_lookup(dev_net(skb->dev), iph->saddr, iph->daddr);
if (tunnel != NULL) {
struct pcpu_tstats *tstats;
+ u32 oldmark = skb->mark;
+ int ret;
- if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb))
+
+ /* temporarily mark the skb with the tunnel o_key, to
+ * only match policies with this mark.
+ */
+ skb->mark = be32_to_cpu(tunnel->parms.o_key);
+ ret = xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb);
+ skb->mark = oldmark;
+ if (!ret)
return -1;
tstats = this_cpu_ptr(tunnel->dev->tstats);
@@ -295,7 +304,6 @@ static int vti_rcv(struct sk_buff *skb)
tstats->rx_bytes += skb->len;
u64_stats_update_end(&tstats->syncp);
- skb->mark = 0;
secpath_reset(skb);
skb->dev = tunnel->dev;
return 1;
@@ -327,7 +335,7 @@ static netdev_tx_t vti_tunnel_xmit(struct sk_buff *skb, struct net_device *dev)
memset(&fl4, 0, sizeof(fl4));
flowi4_init_output(&fl4, tunnel->parms.link,
- be32_to_cpu(tunnel->parms.i_key), RT_TOS(tos),
+ be32_to_cpu(tunnel->parms.o_key), RT_TOS(tos),
RT_SCOPE_UNIVERSE,
IPPROTO_IPIP, 0,
dst, tiph->saddr, 0, 0);
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index d35bbf0cf40..d11e73ce936 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -2020,7 +2020,7 @@ struct rtable *__ip_route_output_key(struct net *net, struct flowi4 *fl4)
RT_SCOPE_LINK);
goto make_route;
}
- if (fl4->saddr) {
+ if (!fl4->saddr) {
if (ipv4_is_multicast(fl4->daddr))
fl4->saddr = inet_select_addr(dev_out, 0,
fl4->flowi4_scope);
diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index 3f25e75ae69..90b26beb84d 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -29,6 +29,7 @@
static int zero;
static int one = 1;
static int four = 4;
+static int gso_max_segs = GSO_MAX_SEGS;
static int tcp_retr1_max = 255;
static int ip_local_port_range_min[] = { 1, 1 };
static int ip_local_port_range_max[] = { 65535, 65535 };
@@ -753,6 +754,15 @@ static struct ctl_table ipv4_table[] = {
.extra2 = &four,
},
{
+ .procname = "tcp_min_tso_segs",
+ .data = &sysctl_tcp_min_tso_segs,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec_minmax,
+ .extra1 = &zero,
+ .extra2 = &gso_max_segs,
+ },
+ {
.procname = "udp_mem",
.data = &sysctl_udp_mem,
.maxlen = sizeof(sysctl_udp_mem),
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index a5b4f535a51..ce657df38cb 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -286,6 +286,8 @@
int sysctl_tcp_fin_timeout __read_mostly = TCP_FIN_TIMEOUT;
+int sysctl_tcp_min_tso_segs __read_mostly = 2;
+
struct percpu_counter tcp_orphan_count;
EXPORT_SYMBOL_GPL(tcp_orphan_count);
@@ -790,12 +792,28 @@ static unsigned int tcp_xmit_size_goal(struct sock *sk, u32 mss_now,
xmit_size_goal = mss_now;
if (large_allowed && sk_can_gso(sk)) {
- xmit_size_goal = ((sk->sk_gso_max_size - 1) -
- inet_csk(sk)->icsk_af_ops->net_header_len -
- inet_csk(sk)->icsk_ext_hdr_len -
- tp->tcp_header_len);
+ u32 gso_size, hlen;
+
+ /* Maybe we should/could use sk->sk_prot->max_header here ? */
+ hlen = inet_csk(sk)->icsk_af_ops->net_header_len +
+ inet_csk(sk)->icsk_ext_hdr_len +
+ tp->tcp_header_len;
+
+ /* Goal is to send at least one packet per ms,
+ * not one big TSO packet every 100 ms.
+ * This preserves ACK clocking and is consistent
+ * with tcp_tso_should_defer() heuristic.
+ */
+ gso_size = sk->sk_pacing_rate / (2 * MSEC_PER_SEC);
+ gso_size = max_t(u32, gso_size,
+ sysctl_tcp_min_tso_segs * mss_now);
+
+ xmit_size_goal = min_t(u32, gso_size,
+ sk->sk_gso_max_size - 1 - hlen);
- /* TSQ : try to have two TSO segments in flight */
+ /* TSQ : try to have at least two segments in flight
+ * (one in NIC TX ring, another in Qdisc)
+ */
xmit_size_goal = min_t(u32, xmit_size_goal,
sysctl_tcp_limit_output_bytes >> 1);
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 4b75aad14b0..e15d330919a 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -699,6 +699,34 @@ static void tcp_rtt_estimator(struct sock *sk, const __u32 mrtt)
}
}
+/* Set the sk_pacing_rate to allow proper sizing of TSO packets.
+ * Note: TCP stack does not yet implement pacing.
+ * FQ packet scheduler can be used to implement cheap but effective
+ * TCP pacing, to smooth the burst on large writes when packets
+ * in flight is significantly lower than cwnd (or rwin)
+ */
+static void tcp_update_pacing_rate(struct sock *sk)
+{
+ const struct tcp_sock *tp = tcp_sk(sk);
+ u64 rate;
+
+ /* set sk_pacing_rate to 200 % of current rate (mss * cwnd / srtt) */
+ rate = (u64)tp->mss_cache * 2 * (HZ << 3);
+
+ rate *= max(tp->snd_cwnd, tp->packets_out);
+
+ /* Correction for small srtt : minimum srtt being 8 (1 jiffy << 3),
+ * be conservative and assume srtt = 1 (125 us instead of 1.25 ms)
+ * We probably need usec resolution in the future.
+ * Note: This also takes care of possible srtt=0 case,
+ * when tcp_rtt_estimator() was not yet called.
+ */
+ if (tp->srtt > 8 + 2)
+ do_div(rate, tp->srtt);
+
+ sk->sk_pacing_rate = min_t(u64, rate, ~0U);
+}
+
/* Calculate rto without backoff. This is the second half of Van Jacobson's
* routine referred to above.
*/
@@ -1264,7 +1292,10 @@ static bool tcp_shifted_skb(struct sock *sk, struct sk_buff *skb,
tp->lost_cnt_hint -= tcp_skb_pcount(prev);
}
- TCP_SKB_CB(skb)->tcp_flags |= TCP_SKB_CB(prev)->tcp_flags;
+ TCP_SKB_CB(prev)->tcp_flags |= TCP_SKB_CB(skb)->tcp_flags;
+ if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN)
+ TCP_SKB_CB(prev)->end_seq++;
+
if (skb == tcp_highest_sack(sk))
tcp_advance_highest_sack(sk, skb);
@@ -3314,7 +3345,7 @@ static void tcp_process_tlp_ack(struct sock *sk, u32 ack, int flag)
tcp_init_cwnd_reduction(sk, true);
tcp_set_ca_state(sk, TCP_CA_CWR);
tcp_end_cwnd_reduction(sk);
- tcp_set_ca_state(sk, TCP_CA_Open);
+ tcp_try_keep_open(sk);
NET_INC_STATS_BH(sock_net(sk),
LINUX_MIB_TCPLOSSPROBERECOVERY);
}
@@ -3330,7 +3361,7 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag)
u32 ack_seq = TCP_SKB_CB(skb)->seq;
u32 ack = TCP_SKB_CB(skb)->ack_seq;
bool is_dupack = false;
- u32 prior_in_flight;
+ u32 prior_in_flight, prior_cwnd = tp->snd_cwnd, prior_rtt = tp->srtt;
u32 prior_fackets;
int prior_packets = tp->packets_out;
int prior_sacked = tp->sacked_out;
@@ -3438,6 +3469,8 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag)
if (icsk->icsk_pending == ICSK_TIME_RETRANS)
tcp_schedule_loss_probe(sk);
+ if (tp->srtt != prior_rtt || tp->snd_cwnd != prior_cwnd)
+ tcp_update_pacing_rate(sk);
return 1;
no_queue:
@@ -5736,6 +5769,8 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb,
} else
tcp_init_metrics(sk);
+ tcp_update_pacing_rate(sk);
+
/* Prevent spurious tcp_cwnd_restart() on
* first data packet.
*/
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 0145ce7e609..cd16eb06beb 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -887,8 +887,7 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it,
skb_orphan(skb);
skb->sk = sk;
- skb->destructor = (sysctl_tcp_limit_output_bytes > 0) ?
- tcp_wfree : sock_wfree;
+ skb->destructor = tcp_wfree;
atomic_add(skb->truesize, &sk->sk_wmem_alloc);
/* Build TCP header and checksum it. */
@@ -977,6 +976,9 @@ 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)
{
+ /* Make sure we own this skb before messing gso_size/gso_segs */
+ WARN_ON_ONCE(skb_cloned(skb));
+
if (skb->len <= mss_now || !sk_can_gso(sk) ||
skb->ip_summed == CHECKSUM_NONE) {
/* Avoid the costly divide in the normal
@@ -1058,9 +1060,7 @@ int tcp_fragment(struct sock *sk, struct sk_buff *skb, u32 len,
if (nsize < 0)
nsize = 0;
- if (skb_cloned(skb) &&
- skb_is_nonlinear(skb) &&
- pskb_expand_head(skb, 0, 0, GFP_ATOMIC))
+ if (skb_unclone(skb, GFP_ATOMIC))
return -ENOMEM;
/* Get a new skb... force flag on. */
@@ -1623,7 +1623,7 @@ static bool tcp_tso_should_defer(struct sock *sk, struct sk_buff *skb)
/* If a full-sized TSO skb can be sent, do it. */
if (limit >= min_t(unsigned int, sk->sk_gso_max_size,
- sk->sk_gso_max_segs * tp->mss_cache))
+ tp->xmit_size_goal_segs * tp->mss_cache))
goto send_now;
/* Middle in queue won't get any more data, full sendable already? */
@@ -1832,7 +1832,6 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle,
while ((skb = tcp_send_head(sk))) {
unsigned int limit;
-
tso_segs = tcp_init_tso_segs(sk, skb, mss_now);
BUG_ON(!tso_segs);
@@ -1861,13 +1860,20 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle,
break;
}
- /* TSQ : sk_wmem_alloc accounts skb truesize,
- * including skb overhead. But thats OK.
+ /* TCP Small Queues :
+ * Control number of packets in qdisc/devices to two packets / or ~1 ms.
+ * This allows for :
+ * - better RTT estimation and ACK scheduling
+ * - faster recovery
+ * - high rates
*/
- if (atomic_read(&sk->sk_wmem_alloc) >= sysctl_tcp_limit_output_bytes) {
+ limit = max(skb->truesize, sk->sk_pacing_rate >> 10);
+
+ if (atomic_read(&sk->sk_wmem_alloc) > limit) {
set_bit(TSQ_THROTTLED, &tp->tsq_flags);
break;
}
+
limit = mss_now;
if (tso_segs > 1 && !tcp_urg_mode(tp))
limit = tcp_mss_split_point(sk, skb, mss_now,
@@ -2329,6 +2335,8 @@ int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb)
int oldpcount = tcp_skb_pcount(skb);
if (unlikely(oldpcount > 1)) {
+ if (skb_unclone(skb, GFP_ATOMIC))
+ return -ENOMEM;
tcp_init_tso_segs(sk, skb, cur_mss);
tcp_adjust_pcount(sk, skb, oldpcount - tcp_skb_pcount(skb));
}
diff --git a/net/ipv6/inet6_hashtables.c b/net/ipv6/inet6_hashtables.c
index 32b4a1675d8..066640e0ba8 100644
--- a/net/ipv6/inet6_hashtables.c
+++ b/net/ipv6/inet6_hashtables.c
@@ -116,7 +116,7 @@ begintw:
}
if (unlikely(!INET6_TW_MATCH(sk, net, saddr, daddr,
ports, dif))) {
- sock_put(sk);
+ inet_twsk_put(inet_twsk(sk));
goto begintw;
}
goto out;
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 44ffdb99a62..878f8027ebf 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -130,7 +130,7 @@ static int ip6_finish_output2(struct sk_buff *skb)
}
rcu_read_lock_bh();
- nexthop = rt6_nexthop((struct rt6_info *)dst, &ipv6_hdr(skb)->daddr);
+ nexthop = rt6_nexthop((struct rt6_info *)dst);
neigh = __ipv6_neigh_lookup_noref(dst->dev, nexthop);
if (unlikely(!neigh))
neigh = __neigh_create(&nd_tbl, nexthop, dst->dev, false);
@@ -898,7 +898,7 @@ static int ip6_dst_lookup_tail(struct sock *sk,
*/
rt = (struct rt6_info *) *dst;
rcu_read_lock_bh();
- n = __ipv6_neigh_lookup_noref(rt->dst.dev, rt6_nexthop(rt, &fl6->daddr));
+ n = __ipv6_neigh_lookup_noref(rt->dst.dev, rt6_nexthop(rt));
err = n && !(n->nud_state & NUD_VALID) ? -EINVAL : 0;
rcu_read_unlock_bh();
@@ -1250,7 +1250,7 @@ int ip6_append_data(struct sock *sk, int getfrag(void *from, char *to,
skb = skb_peek_tail(&sk->sk_write_queue);
cork->length += length;
if (((length > mtu) ||
- (skb && skb_is_gso(skb))) &&
+ (skb && skb_has_frags(skb))) &&
(sk->sk_protocol == IPPROTO_UDP) &&
(rt->dst.dev->features & NETIF_F_UFO)) {
err = ip6_ufo_append_data(sk, getfrag, from, length,
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index bacce6c0864..3c1f493ccc6 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -473,6 +473,24 @@ out:
}
#ifdef CONFIG_IPV6_ROUTER_PREF
+struct __rt6_probe_work {
+ struct work_struct work;
+ struct in6_addr target;
+ struct net_device *dev;
+};
+
+static void rt6_probe_deferred(struct work_struct *w)
+{
+ struct in6_addr mcaddr;
+ struct __rt6_probe_work *work =
+ container_of(w, struct __rt6_probe_work, work);
+
+ addrconf_addr_solict_mult(&work->target, &mcaddr);
+ ndisc_send_ns(work->dev, NULL, &work->target, &mcaddr, NULL);
+ dev_put(work->dev);
+ kfree(w);
+}
+
static void rt6_probe(struct rt6_info *rt)
{
struct neighbour *neigh;
@@ -496,17 +514,23 @@ static void rt6_probe(struct rt6_info *rt)
if (!neigh ||
time_after(jiffies, neigh->updated + rt->rt6i_idev->cnf.rtr_probe_interval)) {
- struct in6_addr mcaddr;
- struct in6_addr *target;
+ struct __rt6_probe_work *work;
- if (neigh) {
+ work = kmalloc(sizeof(*work), GFP_ATOMIC);
+
+ if (neigh && work)
neigh->updated = jiffies;
+
+ if (neigh)
write_unlock(&neigh->lock);
- }
- target = (struct in6_addr *)&rt->rt6i_gateway;
- addrconf_addr_solict_mult(target, &mcaddr);
- ndisc_send_ns(rt->dst.dev, NULL, target, &mcaddr, NULL);
+ if (work) {
+ INIT_WORK(&work->work, rt6_probe_deferred);
+ work->target = rt->rt6i_gateway;
+ dev_hold(rt->dst.dev);
+ work->dev = rt->dst.dev;
+ schedule_work(&work->work);
+ }
} else {
out:
write_unlock(&neigh->lock);
@@ -848,7 +872,6 @@ static struct rt6_info *rt6_alloc_cow(struct rt6_info *ort,
if (ort->rt6i_dst.plen != 128 &&
ipv6_addr_equal(&ort->rt6i_dst.addr, daddr))
rt->rt6i_flags |= RTF_ANYCAST;
- rt->rt6i_gateway = *daddr;
}
rt->rt6i_flags |= RTF_CACHE;
@@ -1245,6 +1268,7 @@ struct dst_entry *icmp6_dst_alloc(struct net_device *dev,
rt->dst.flags |= DST_HOST;
rt->dst.output = ip6_output;
atomic_set(&rt->dst.__refcnt, 1);
+ rt->rt6i_gateway = fl6->daddr;
rt->rt6i_dst.addr = fl6->daddr;
rt->rt6i_dst.plen = 128;
rt->rt6i_idev = idev;
@@ -1801,7 +1825,10 @@ static struct rt6_info *ip6_rt_copy(struct rt6_info *ort,
in6_dev_hold(rt->rt6i_idev);
rt->dst.lastuse = jiffies;
- rt->rt6i_gateway = ort->rt6i_gateway;
+ if (ort->rt6i_flags & RTF_GATEWAY)
+ rt->rt6i_gateway = ort->rt6i_gateway;
+ else
+ rt->rt6i_gateway = *dest;
rt->rt6i_flags = ort->rt6i_flags;
if ((ort->rt6i_flags & (RTF_DEFAULT | RTF_ADDRCONF)) ==
(RTF_DEFAULT | RTF_ADDRCONF))
@@ -2088,6 +2115,7 @@ struct rt6_info *addrconf_dst_alloc(struct inet6_dev *idev,
else
rt->rt6i_flags |= RTF_LOCAL;
+ rt->rt6i_gateway = *addr;
rt->rt6i_dst.addr = *addr;
rt->rt6i_dst.plen = 128;
rt->rt6i_table = fib6_get_table(net, RT6_TABLE_LOCAL);
diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c
index 6984c3a353c..8c27de2b4d5 100644
--- a/net/l2tp/l2tp_core.c
+++ b/net/l2tp/l2tp_core.c
@@ -115,6 +115,11 @@ struct l2tp_net {
static void l2tp_session_set_header_len(struct l2tp_session *session, int version);
static void l2tp_tunnel_free(struct l2tp_tunnel *tunnel);
+static inline struct l2tp_tunnel *l2tp_tunnel(struct sock *sk)
+{
+ return sk->sk_user_data;
+}
+
static inline struct l2tp_net *l2tp_pernet(struct net *net)
{
BUG_ON(!net);
@@ -507,7 +512,7 @@ static inline int l2tp_verify_udp_checksum(struct sock *sk,
return 0;
#if IS_ENABLED(CONFIG_IPV6)
- if (sk->sk_family == PF_INET6) {
+ if (sk->sk_family == PF_INET6 && !l2tp_tunnel(sk)->v4mapped) {
if (!uh->check) {
LIMIT_NETDEBUG(KERN_INFO "L2TP: IPv6: checksum is 0\n");
return 1;
@@ -1071,7 +1076,7 @@ static int l2tp_xmit_core(struct l2tp_session *session, struct sk_buff *skb,
/* Queue the packet to IP for output */
skb->local_df = 1;
#if IS_ENABLED(CONFIG_IPV6)
- if (skb->sk->sk_family == PF_INET6)
+ if (skb->sk->sk_family == PF_INET6 && !tunnel->v4mapped)
error = inet6_csk_xmit(skb, NULL);
else
#endif
@@ -1198,7 +1203,7 @@ int l2tp_xmit_skb(struct l2tp_session *session, struct sk_buff *skb, int hdr_len
/* Calculate UDP checksum if configured to do so */
#if IS_ENABLED(CONFIG_IPV6)
- if (sk->sk_family == PF_INET6)
+ if (sk->sk_family == PF_INET6 && !tunnel->v4mapped)
l2tp_xmit_ipv6_csum(sk, skb, udp_len);
else
#endif
@@ -1247,10 +1252,9 @@ EXPORT_SYMBOL_GPL(l2tp_xmit_skb);
*/
static void l2tp_tunnel_destruct(struct sock *sk)
{
- struct l2tp_tunnel *tunnel;
+ struct l2tp_tunnel *tunnel = l2tp_tunnel(sk);
struct l2tp_net *pn;
- tunnel = sk->sk_user_data;
if (tunnel == NULL)
goto end;
@@ -1618,7 +1622,7 @@ int l2tp_tunnel_create(struct net *net, int fd, int version, u32 tunnel_id, u32
}
/* Check if this socket has already been prepped */
- tunnel = (struct l2tp_tunnel *)sk->sk_user_data;
+ tunnel = l2tp_tunnel(sk);
if (tunnel != NULL) {
/* This socket has already been prepped */
err = -EBUSY;
@@ -1647,6 +1651,24 @@ int l2tp_tunnel_create(struct net *net, int fd, int version, u32 tunnel_id, u32
if (cfg != NULL)
tunnel->debug = cfg->debug;
+#if IS_ENABLED(CONFIG_IPV6)
+ if (sk->sk_family == PF_INET6) {
+ struct ipv6_pinfo *np = inet6_sk(sk);
+
+ if (ipv6_addr_v4mapped(&np->saddr) &&
+ ipv6_addr_v4mapped(&np->daddr)) {
+ struct inet_sock *inet = inet_sk(sk);
+
+ tunnel->v4mapped = true;
+ inet->inet_saddr = np->saddr.s6_addr32[3];
+ inet->inet_rcv_saddr = np->rcv_saddr.s6_addr32[3];
+ inet->inet_daddr = np->daddr.s6_addr32[3];
+ } else {
+ tunnel->v4mapped = false;
+ }
+ }
+#endif
+
/* Mark socket as an encapsulation socket. See net/ipv4/udp.c */
tunnel->encap = encap;
if (encap == L2TP_ENCAPTYPE_UDP) {
@@ -1655,7 +1677,7 @@ int l2tp_tunnel_create(struct net *net, int fd, int version, u32 tunnel_id, u32
udp_sk(sk)->encap_rcv = l2tp_udp_encap_recv;
udp_sk(sk)->encap_destroy = l2tp_udp_encap_destroy;
#if IS_ENABLED(CONFIG_IPV6)
- if (sk->sk_family == PF_INET6)
+ if (sk->sk_family == PF_INET6 && !tunnel->v4mapped)
udpv6_encap_enable();
else
#endif
diff --git a/net/l2tp/l2tp_core.h b/net/l2tp/l2tp_core.h
index 485a490fd99..2f89d43877d 100644
--- a/net/l2tp/l2tp_core.h
+++ b/net/l2tp/l2tp_core.h
@@ -189,6 +189,9 @@ struct l2tp_tunnel {
struct sock *sock; /* Parent socket */
int fd; /* Parent fd, if tunnel socket
* was created by userspace */
+#if IS_ENABLED(CONFIG_IPV6)
+ bool v4mapped;
+#endif
struct work_struct del_work;
diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c
index 5ebee2ded9e..8c46b271064 100644
--- a/net/l2tp/l2tp_ppp.c
+++ b/net/l2tp/l2tp_ppp.c
@@ -353,7 +353,9 @@ static int pppol2tp_sendmsg(struct kiocb *iocb, struct socket *sock, struct msgh
goto error_put_sess_tun;
}
+ local_bh_disable();
l2tp_xmit_skb(session, skb, session->hdr_len);
+ local_bh_enable();
sock_put(ps->tunnel_sock);
sock_put(sk);
@@ -422,7 +424,9 @@ static int pppol2tp_xmit(struct ppp_channel *chan, struct sk_buff *skb)
skb->data[0] = ppph[0];
skb->data[1] = ppph[1];
+ local_bh_disable();
l2tp_xmit_skb(session, skb, session->hdr_len);
+ local_bh_enable();
sock_put(sk_tun);
sock_put(sk);
diff --git a/net/netfilter/nf_conntrack_h323_main.c b/net/netfilter/nf_conntrack_h323_main.c
index bdebd03bc8c..70866d192ef 100644
--- a/net/netfilter/nf_conntrack_h323_main.c
+++ b/net/netfilter/nf_conntrack_h323_main.c
@@ -778,8 +778,8 @@ static int callforward_do_filter(const union nf_inet_addr *src,
flowi6_to_flowi(&fl1), false)) {
if (!afinfo->route(&init_net, (struct dst_entry **)&rt2,
flowi6_to_flowi(&fl2), false)) {
- if (!memcmp(&rt1->rt6i_gateway, &rt2->rt6i_gateway,
- sizeof(rt1->rt6i_gateway)) &&
+ if (ipv6_addr_equal(rt6_nexthop(rt1),
+ rt6_nexthop(rt2)) &&
rt1->dst.dev == rt2->dst.dev)
ret = 1;
dst_release(&rt2->dst);
diff --git a/net/sctp/output.c b/net/sctp/output.c
index bbef4a7a9b5..0beb2f9c8a7 100644
--- a/net/sctp/output.c
+++ b/net/sctp/output.c
@@ -547,7 +547,8 @@ int sctp_packet_transmit(struct sctp_packet *packet)
* by CRC32-C as described in <draft-ietf-tsvwg-sctpcsum-02.txt>.
*/
if (!sctp_checksum_disable) {
- if (!(dst->dev->features & NETIF_F_SCTP_CSUM)) {
+ if (!(dst->dev->features & NETIF_F_SCTP_CSUM) ||
+ (dst_xfrm(dst) != NULL) || packet->ipfragok) {
__u32 crc32 = sctp_start_cksum((__u8 *)sh, cksum_buf_len);
/* 3) Put the resultant value into the checksum field in the
diff --git a/net/socket.c b/net/socket.c
index 4ca1526db75..9c467b2afc8 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -1956,6 +1956,16 @@ struct used_address {
unsigned int name_len;
};
+static int copy_msghdr_from_user(struct msghdr *kmsg,
+ struct msghdr __user *umsg)
+{
+ if (copy_from_user(kmsg, umsg, sizeof(struct msghdr)))
+ return -EFAULT;
+ if (kmsg->msg_namelen > sizeof(struct sockaddr_storage))
+ return -EINVAL;
+ return 0;
+}
+
static int ___sys_sendmsg(struct socket *sock, struct msghdr __user *msg,
struct msghdr *msg_sys, unsigned int flags,
struct used_address *used_address)
@@ -1974,8 +1984,11 @@ static int ___sys_sendmsg(struct socket *sock, struct msghdr __user *msg,
if (MSG_CMSG_COMPAT & flags) {
if (get_compat_msghdr(msg_sys, msg_compat))
return -EFAULT;
- } else if (copy_from_user(msg_sys, msg, sizeof(struct msghdr)))
- return -EFAULT;
+ } else {
+ err = copy_msghdr_from_user(msg_sys, msg);
+ if (err)
+ return err;
+ }
if (msg_sys->msg_iovlen > UIO_FASTIOV) {
err = -EMSGSIZE;
@@ -2183,8 +2196,11 @@ static int ___sys_recvmsg(struct socket *sock, struct msghdr __user *msg,
if (MSG_CMSG_COMPAT & flags) {
if (get_compat_msghdr(msg_sys, msg_compat))
return -EFAULT;
- } else if (copy_from_user(msg_sys, msg, sizeof(struct msghdr)))
- return -EFAULT;
+ } else {
+ err = copy_msghdr_from_user(msg_sys, msg);
+ if (err)
+ return err;
+ }
if (msg_sys->msg_iovlen > UIO_FASTIOV) {
err = -EMSGSIZE;
diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index c4ce243824b..e64bbcf5fb2 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -1246,6 +1246,15 @@ static int unix_socketpair(struct socket *socka, struct socket *sockb)
return 0;
}
+static void unix_sock_inherit_flags(const struct socket *old,
+ struct socket *new)
+{
+ if (test_bit(SOCK_PASSCRED, &old->flags))
+ set_bit(SOCK_PASSCRED, &new->flags);
+ if (test_bit(SOCK_PASSSEC, &old->flags))
+ set_bit(SOCK_PASSSEC, &new->flags);
+}
+
static int unix_accept(struct socket *sock, struct socket *newsock, int flags)
{
struct sock *sk = sock->sk;
@@ -1280,6 +1289,7 @@ static int unix_accept(struct socket *sock, struct socket *newsock, int flags)
/* attach accepted sock to socket */
unix_state_lock(tsk);
newsock->state = SS_CONNECTED;
+ unix_sock_inherit_flags(sock, newsock);
sock_graft(tsk, newsock);
unix_state_unlock(tsk);
return 0;
diff --git a/net/unix/diag.c b/net/unix/diag.c
index d591091603b..86fa0f3b2ca 100644
--- a/net/unix/diag.c
+++ b/net/unix/diag.c
@@ -124,6 +124,7 @@ static int sk_diag_fill(struct sock *sk, struct sk_buff *skb, struct unix_diag_r
rep->udiag_family = AF_UNIX;
rep->udiag_type = sk->sk_type;
rep->udiag_state = sk->sk_state;
+ rep->pad = 0;
rep->udiag_ino = sk_ino;
sock_diag_save_cookie(sk, rep->udiag_cookie);
diff --git a/net/wireless/radiotap.c b/net/wireless/radiotap.c
index 7d604c06c3d..a271c27fac7 100644
--- a/net/wireless/radiotap.c
+++ b/net/wireless/radiotap.c
@@ -97,6 +97,10 @@ int ieee80211_radiotap_iterator_init(
struct ieee80211_radiotap_header *radiotap_header,
int max_length, const struct ieee80211_radiotap_vendor_namespaces *vns)
{
+ /* check the radiotap header can actually be present */
+ if (max_length < sizeof(struct ieee80211_radiotap_header))
+ return -EINVAL;
+
/* Linux only supports version 0 radiotap format */
if (radiotap_header->it_version)
return -EINVAL;
@@ -131,7 +135,8 @@ int ieee80211_radiotap_iterator_init(
*/
if ((unsigned long)iterator->_arg -
- (unsigned long)iterator->_rtheader >
+ (unsigned long)iterator->_rtheader +
+ sizeof(uint32_t) >
(unsigned long)iterator->_max_length)
return -EINVAL;
}