summaryrefslogtreecommitdiff
path: root/net
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2009-12-16 10:33:18 -0800
committerLinus Torvalds <torvalds@linux-foundation.org>2009-12-16 10:33:18 -0800
commit59be2e04e50ac9947e4356c10099f49977f5f74d (patch)
tree56aa00a4499a1543da8728cb84b10bec5b211280 /net
parente69381b4175ba162229646f6753ff1d87c24d468 (diff)
parent503914cf4a4b5dbe3f844e0a92f412ae99fde70e (diff)
downloadlwn-59be2e04e50ac9947e4356c10099f49977f5f74d.tar.gz
lwn-59be2e04e50ac9947e4356c10099f49977f5f74d.zip
Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-2.6
* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-2.6: (26 commits) net: sh_eth alignment fix for sh7724 using NET_IP_ALIGN V2 ixgbe: allow tx of pre-formatted vlan tagged packets ixgbe: Fix 82598 premature copper PHY link indicatation ixgbe: Fix tx_restart_queue/non_eop_desc statistics counters bcm63xx_enet: fix compilation failure after get_stats_count removal packet: dont call sleeping functions while holding rcu_read_lock() tcp: Revert per-route SACK/DSACK/TIMESTAMP changes. ipvs: zero usvc and udest netfilter: fix crashes in bridge netfilter caused by fragment jumps ipv6: reassembly: use seperate reassembly queues for conntrack and local delivery sky2: leave PCI config space writeable sky2: print Optima chip name x25: Update maintainer. ipvs: fix synchronization on connection close netfilter: xtables: document minimal required version drivers/net/bonding/: : use pr_fmt can: CAN_MCP251X should depend on HAS_DMA drivers/net/usb: Correct code taking the size of a pointer drivers/net/cpmac.c: Correct code taking the size of a pointer drivers/net/sfc: Correct code taking the size of a pointer ...
Diffstat (limited to 'net')
-rw-r--r--net/core/dev.c11
-rw-r--r--net/core/rtnetlink.c6
-rw-r--r--net/ipv4/netfilter/nf_defrag_ipv4.c21
-rw-r--r--net/ipv4/syncookies.c27
-rw-r--r--net/ipv4/tcp_input.c24
-rw-r--r--net/ipv4/tcp_ipv4.c21
-rw-r--r--net/ipv4/tcp_minisocks.c10
-rw-r--r--net/ipv4/tcp_output.c18
-rw-r--r--net/ipv4/udp.c7
-rw-r--r--net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c19
-rw-r--r--net/ipv6/netfilter/nf_conntrack_reasm.c7
-rw-r--r--net/ipv6/reassembly.c5
-rw-r--r--net/ipv6/syncookies.c28
-rw-r--r--net/ipv6/tcp_ipv6.c3
-rw-r--r--net/netfilter/ipvs/ip_vs_core.c1
-rw-r--r--net/netfilter/ipvs/ip_vs_ctl.c4
-rw-r--r--net/packet/af_packet.c71
17 files changed, 149 insertions, 134 deletions
diff --git a/net/core/dev.c b/net/core/dev.c
index 6fe7d739e59b..be9924f60ec3 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -5035,6 +5035,11 @@ int register_netdevice(struct net_device *dev)
rollback_registered(dev);
dev->reg_state = NETREG_UNREGISTERED;
}
+ /*
+ * Prevent userspace races by waiting until the network
+ * device is fully setup before sending notifications.
+ */
+ rtmsg_ifinfo(RTM_NEWLINK, dev, ~0U);
out:
return ret;
@@ -5597,6 +5602,12 @@ int dev_change_net_namespace(struct net_device *dev, struct net *net, const char
/* Notify protocols, that a new device appeared. */
call_netdevice_notifiers(NETDEV_REGISTER, dev);
+ /*
+ * Prevent userspace races by waiting until the network
+ * device is fully setup before sending notifications.
+ */
+ rtmsg_ifinfo(RTM_NEWLINK, dev, ~0U);
+
synchronize_net();
err = 0;
out:
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 33148a568199..794bcb897ff0 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -1364,15 +1364,15 @@ static int rtnetlink_event(struct notifier_block *this, unsigned long event, voi
case NETDEV_UNREGISTER:
rtmsg_ifinfo(RTM_DELLINK, dev, ~0U);
break;
- case NETDEV_REGISTER:
- rtmsg_ifinfo(RTM_NEWLINK, dev, ~0U);
- break;
case NETDEV_UP:
case NETDEV_DOWN:
rtmsg_ifinfo(RTM_NEWLINK, dev, IFF_UP|IFF_RUNNING);
break;
+ case NETDEV_POST_INIT:
+ case NETDEV_REGISTER:
case NETDEV_CHANGE:
case NETDEV_GOING_DOWN:
+ case NETDEV_UNREGISTER_BATCH:
break;
default:
rtmsg_ifinfo(RTM_NEWLINK, dev, 0);
diff --git a/net/ipv4/netfilter/nf_defrag_ipv4.c b/net/ipv4/netfilter/nf_defrag_ipv4.c
index fa2d6b6fc3e5..331ead3ebd1b 100644
--- a/net/ipv4/netfilter/nf_defrag_ipv4.c
+++ b/net/ipv4/netfilter/nf_defrag_ipv4.c
@@ -14,6 +14,7 @@
#include <net/route.h>
#include <net/ip.h>
+#include <linux/netfilter_bridge.h>
#include <linux/netfilter_ipv4.h>
#include <net/netfilter/ipv4/nf_defrag_ipv4.h>
@@ -34,6 +35,20 @@ static int nf_ct_ipv4_gather_frags(struct sk_buff *skb, u_int32_t user)
return err;
}
+static enum ip_defrag_users nf_ct_defrag_user(unsigned int hooknum,
+ struct sk_buff *skb)
+{
+#ifdef CONFIG_BRIDGE_NETFILTER
+ if (skb->nf_bridge &&
+ skb->nf_bridge->mask & BRNF_NF_BRIDGE_PREROUTING)
+ return IP_DEFRAG_CONNTRACK_BRIDGE_IN;
+#endif
+ if (hooknum == NF_INET_PRE_ROUTING)
+ return IP_DEFRAG_CONNTRACK_IN;
+ else
+ return IP_DEFRAG_CONNTRACK_OUT;
+}
+
static unsigned int ipv4_conntrack_defrag(unsigned int hooknum,
struct sk_buff *skb,
const struct net_device *in,
@@ -50,10 +65,8 @@ static unsigned int ipv4_conntrack_defrag(unsigned int hooknum,
#endif
/* Gather fragments. */
if (ip_hdr(skb)->frag_off & htons(IP_MF | IP_OFFSET)) {
- if (nf_ct_ipv4_gather_frags(skb,
- hooknum == NF_INET_PRE_ROUTING ?
- IP_DEFRAG_CONNTRACK_IN :
- IP_DEFRAG_CONNTRACK_OUT))
+ enum ip_defrag_users user = nf_ct_defrag_user(hooknum, skb);
+ if (nf_ct_ipv4_gather_frags(skb, user))
return NF_STOLEN;
}
return NF_ACCEPT;
diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c
index 26399ad2a289..66fd80ef2473 100644
--- a/net/ipv4/syncookies.c
+++ b/net/ipv4/syncookies.c
@@ -277,6 +277,13 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb,
NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_SYNCOOKIESRECV);
+ /* check for timestamp cookie support */
+ memset(&tcp_opt, 0, sizeof(tcp_opt));
+ tcp_parse_options(skb, &tcp_opt, &hash_location, 0);
+
+ if (tcp_opt.saw_tstamp)
+ cookie_check_timestamp(&tcp_opt);
+
ret = NULL;
req = inet_reqsk_alloc(&tcp_request_sock_ops); /* for safety */
if (!req)
@@ -292,6 +299,12 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb,
ireq->loc_addr = ip_hdr(skb)->daddr;
ireq->rmt_addr = ip_hdr(skb)->saddr;
ireq->ecn_ok = 0;
+ ireq->snd_wscale = tcp_opt.snd_wscale;
+ ireq->rcv_wscale = tcp_opt.rcv_wscale;
+ ireq->sack_ok = tcp_opt.sack_ok;
+ ireq->wscale_ok = tcp_opt.wscale_ok;
+ ireq->tstamp_ok = tcp_opt.saw_tstamp;
+ req->ts_recent = tcp_opt.saw_tstamp ? tcp_opt.rcv_tsval : 0;
/* We throwed the options of the initial SYN away, so we hope
* the ACK carries the same options again (see RFC1122 4.2.3.8)
@@ -340,20 +353,6 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb,
}
}
- /* check for timestamp cookie support */
- memset(&tcp_opt, 0, sizeof(tcp_opt));
- tcp_parse_options(skb, &tcp_opt, &hash_location, 0, &rt->u.dst);
-
- if (tcp_opt.saw_tstamp)
- cookie_check_timestamp(&tcp_opt);
-
- ireq->snd_wscale = tcp_opt.snd_wscale;
- ireq->rcv_wscale = tcp_opt.rcv_wscale;
- ireq->sack_ok = tcp_opt.sack_ok;
- ireq->wscale_ok = tcp_opt.wscale_ok;
- ireq->tstamp_ok = tcp_opt.saw_tstamp;
- req->ts_recent = tcp_opt.saw_tstamp ? tcp_opt.rcv_tsval : 0;
-
/* Try to redo what tcp_v4_send_synack did. */
req->window_clamp = tp->window_clamp ? :dst_metric(&rt->u.dst, RTAX_WINDOW);
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 12cab7d74dba..28e029632493 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -3727,7 +3727,7 @@ old_ack:
* the fast version below fails.
*/
void tcp_parse_options(struct sk_buff *skb, struct tcp_options_received *opt_rx,
- u8 **hvpp, int estab, struct dst_entry *dst)
+ u8 **hvpp, int estab)
{
unsigned char *ptr;
struct tcphdr *th = tcp_hdr(skb);
@@ -3766,8 +3766,7 @@ void tcp_parse_options(struct sk_buff *skb, struct tcp_options_received *opt_rx,
break;
case TCPOPT_WINDOW:
if (opsize == TCPOLEN_WINDOW && th->syn &&
- !estab && sysctl_tcp_window_scaling &&
- !dst_feature(dst, RTAX_FEATURE_NO_WSCALE)) {
+ !estab && sysctl_tcp_window_scaling) {
__u8 snd_wscale = *(__u8 *)ptr;
opt_rx->wscale_ok = 1;
if (snd_wscale > 14) {
@@ -3783,8 +3782,7 @@ void tcp_parse_options(struct sk_buff *skb, struct tcp_options_received *opt_rx,
case TCPOPT_TIMESTAMP:
if ((opsize == TCPOLEN_TIMESTAMP) &&
((estab && opt_rx->tstamp_ok) ||
- (!estab && sysctl_tcp_timestamps &&
- !dst_feature(dst, RTAX_FEATURE_NO_TSTAMP)))) {
+ (!estab && sysctl_tcp_timestamps))) {
opt_rx->saw_tstamp = 1;
opt_rx->rcv_tsval = get_unaligned_be32(ptr);
opt_rx->rcv_tsecr = get_unaligned_be32(ptr + 4);
@@ -3792,8 +3790,7 @@ void tcp_parse_options(struct sk_buff *skb, struct tcp_options_received *opt_rx,
break;
case TCPOPT_SACK_PERM:
if (opsize == TCPOLEN_SACK_PERM && th->syn &&
- !estab && sysctl_tcp_sack &&
- !dst_feature(dst, RTAX_FEATURE_NO_SACK)) {
+ !estab && sysctl_tcp_sack) {
opt_rx->sack_ok = 1;
tcp_sack_reset(opt_rx);
}
@@ -3878,7 +3875,7 @@ static int tcp_fast_parse_options(struct sk_buff *skb, struct tcphdr *th,
if (tcp_parse_aligned_timestamp(tp, th))
return 1;
}
- tcp_parse_options(skb, &tp->rx_opt, hvpp, 1, NULL);
+ tcp_parse_options(skb, &tp->rx_opt, hvpp, 1);
return 1;
}
@@ -4133,10 +4130,8 @@ static inline int tcp_sack_extend(struct tcp_sack_block *sp, u32 seq,
static void tcp_dsack_set(struct sock *sk, u32 seq, u32 end_seq)
{
struct tcp_sock *tp = tcp_sk(sk);
- struct dst_entry *dst = __sk_dst_get(sk);
- if (tcp_is_sack(tp) && sysctl_tcp_dsack &&
- !dst_feature(dst, RTAX_FEATURE_NO_DSACK)) {
+ if (tcp_is_sack(tp) && sysctl_tcp_dsack) {
int mib_idx;
if (before(seq, tp->rcv_nxt))
@@ -4165,15 +4160,13 @@ static void tcp_dsack_extend(struct sock *sk, u32 seq, u32 end_seq)
static void tcp_send_dupack(struct sock *sk, struct sk_buff *skb)
{
struct tcp_sock *tp = tcp_sk(sk);
- struct dst_entry *dst = __sk_dst_get(sk);
if (TCP_SKB_CB(skb)->end_seq != TCP_SKB_CB(skb)->seq &&
before(TCP_SKB_CB(skb)->seq, tp->rcv_nxt)) {
NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_DELAYEDACKLOST);
tcp_enter_quickack_mode(sk);
- if (tcp_is_sack(tp) && sysctl_tcp_dsack &&
- !dst_feature(dst, RTAX_FEATURE_NO_DSACK)) {
+ if (tcp_is_sack(tp) && sysctl_tcp_dsack) {
u32 end_seq = TCP_SKB_CB(skb)->end_seq;
if (after(TCP_SKB_CB(skb)->end_seq, tp->rcv_nxt))
@@ -5428,11 +5421,10 @@ static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb,
u8 *hash_location;
struct inet_connection_sock *icsk = inet_csk(sk);
struct tcp_sock *tp = tcp_sk(sk);
- struct dst_entry *dst = __sk_dst_get(sk);
struct tcp_cookie_values *cvp = tp->cookie_values;
int saved_clamp = tp->rx_opt.mss_clamp;
- tcp_parse_options(skb, &tp->rx_opt, &hash_location, 0, dst);
+ tcp_parse_options(skb, &tp->rx_opt, &hash_location, 0);
if (th->ack) {
/* rfc793:
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 15e96030ce47..65b8ebfd078a 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -1262,20 +1262,10 @@ int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb)
tcp_rsk(req)->af_specific = &tcp_request_sock_ipv4_ops;
#endif
- ireq = inet_rsk(req);
- ireq->loc_addr = daddr;
- ireq->rmt_addr = saddr;
- ireq->no_srccheck = inet_sk(sk)->transparent;
- ireq->opt = tcp_v4_save_options(sk, skb);
-
- dst = inet_csk_route_req(sk, req);
- if(!dst)
- goto drop_and_free;
-
tcp_clear_options(&tmp_opt);
tmp_opt.mss_clamp = TCP_MSS_DEFAULT;
tmp_opt.user_mss = tp->rx_opt.user_mss;
- tcp_parse_options(skb, &tmp_opt, &hash_location, 0, dst);
+ tcp_parse_options(skb, &tmp_opt, &hash_location, 0);
if (tmp_opt.cookie_plus > 0 &&
tmp_opt.saw_tstamp &&
@@ -1319,8 +1309,14 @@ int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb)
tmp_opt.tstamp_ok = tmp_opt.saw_tstamp;
tcp_openreq_init(req, &tmp_opt, skb);
+ ireq = inet_rsk(req);
+ ireq->loc_addr = daddr;
+ ireq->rmt_addr = saddr;
+ ireq->no_srccheck = inet_sk(sk)->transparent;
+ ireq->opt = tcp_v4_save_options(sk, skb);
+
if (security_inet_conn_request(sk, skb, req))
- goto drop_and_release;
+ goto drop_and_free;
if (!want_cookie)
TCP_ECN_create_request(req, tcp_hdr(skb));
@@ -1345,6 +1341,7 @@ int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb)
*/
if (tmp_opt.saw_tstamp &&
tcp_death_row.sysctl_tw_recycle &&
+ (dst = inet_csk_route_req(sk, req)) != NULL &&
(peer = rt_get_peer((struct rtable *)dst)) != NULL &&
peer->v4daddr == saddr) {
if ((u32)get_seconds() - peer->tcp_ts_stamp < TCP_PAWS_MSL &&
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index 87accec8d097..f206ee5dda80 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -95,9 +95,9 @@ tcp_timewait_state_process(struct inet_timewait_sock *tw, struct sk_buff *skb,
struct tcp_timewait_sock *tcptw = tcp_twsk((struct sock *)tw);
int paws_reject = 0;
+ tmp_opt.saw_tstamp = 0;
if (th->doff > (sizeof(*th) >> 2) && tcptw->tw_ts_recent_stamp) {
- tmp_opt.tstamp_ok = 1;
- tcp_parse_options(skb, &tmp_opt, &hash_location, 1, NULL);
+ tcp_parse_options(skb, &tmp_opt, &hash_location, 0);
if (tmp_opt.saw_tstamp) {
tmp_opt.ts_recent = tcptw->tw_ts_recent;
@@ -526,9 +526,9 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb,
__be32 flg = tcp_flag_word(th) & (TCP_FLAG_RST|TCP_FLAG_SYN|TCP_FLAG_ACK);
int paws_reject = 0;
- if ((th->doff > (sizeof(*th) >> 2)) && (req->ts_recent)) {
- tmp_opt.tstamp_ok = 1;
- tcp_parse_options(skb, &tmp_opt, &hash_location, 1, NULL);
+ tmp_opt.saw_tstamp = 0;
+ if (th->doff > (sizeof(struct tcphdr)>>2)) {
+ tcp_parse_options(skb, &tmp_opt, &hash_location, 0);
if (tmp_opt.saw_tstamp) {
tmp_opt.ts_recent = req->ts_recent;
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 93316a96d820..383ce237640f 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -553,7 +553,6 @@ static unsigned tcp_syn_options(struct sock *sk, struct sk_buff *skb,
struct tcp_md5sig_key **md5) {
struct tcp_sock *tp = tcp_sk(sk);
struct tcp_cookie_values *cvp = tp->cookie_values;
- struct dst_entry *dst = __sk_dst_get(sk);
unsigned remaining = MAX_TCP_OPTION_SPACE;
u8 cookie_size = (!tp->rx_opt.cookie_out_never && cvp != NULL) ?
tcp_cookie_size_check(cvp->cookie_desired) :
@@ -581,22 +580,18 @@ static unsigned tcp_syn_options(struct sock *sk, struct sk_buff *skb,
opts->mss = tcp_advertise_mss(sk);
remaining -= TCPOLEN_MSS_ALIGNED;
- if (likely(sysctl_tcp_timestamps &&
- !dst_feature(dst, RTAX_FEATURE_NO_TSTAMP) &&
- *md5 == NULL)) {
+ if (likely(sysctl_tcp_timestamps && *md5 == NULL)) {
opts->options |= OPTION_TS;
opts->tsval = TCP_SKB_CB(skb)->when;
opts->tsecr = tp->rx_opt.ts_recent;
remaining -= TCPOLEN_TSTAMP_ALIGNED;
}
- if (likely(sysctl_tcp_window_scaling &&
- !dst_feature(dst, RTAX_FEATURE_NO_WSCALE))) {
+ if (likely(sysctl_tcp_window_scaling)) {
opts->ws = tp->rx_opt.rcv_wscale;
opts->options |= OPTION_WSCALE;
remaining -= TCPOLEN_WSCALE_ALIGNED;
}
- if (likely(sysctl_tcp_sack &&
- !dst_feature(dst, RTAX_FEATURE_NO_SACK))) {
+ if (likely(sysctl_tcp_sack)) {
opts->options |= OPTION_SACK_ADVERTISE;
if (unlikely(!(OPTION_TS & opts->options)))
remaining -= TCPOLEN_SACKPERM_ALIGNED;
@@ -2527,9 +2522,7 @@ static void tcp_connect_init(struct sock *sk)
* See tcp_input.c:tcp_rcv_state_process case TCP_SYN_SENT.
*/
tp->tcp_header_len = sizeof(struct tcphdr) +
- (sysctl_tcp_timestamps &&
- (!dst_feature(dst, RTAX_FEATURE_NO_TSTAMP) ?
- TCPOLEN_TSTAMP_ALIGNED : 0));
+ (sysctl_tcp_timestamps ? TCPOLEN_TSTAMP_ALIGNED : 0);
#ifdef CONFIG_TCP_MD5SIG
if (tp->af_specific->md5_lookup(sk, sk) != NULL)
@@ -2555,8 +2548,7 @@ static void tcp_connect_init(struct sock *sk)
tp->advmss - (tp->rx_opt.ts_recent_stamp ? tp->tcp_header_len - sizeof(struct tcphdr) : 0),
&tp->rcv_wnd,
&tp->window_clamp,
- (sysctl_tcp_window_scaling &&
- !dst_feature(dst, RTAX_FEATURE_NO_WSCALE)),
+ sysctl_tcp_window_scaling,
&rcv_wscale);
tp->rx_opt.rcv_wscale = rcv_wscale;
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 1f9534846ca9..f0126fdd7e04 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -216,9 +216,8 @@ int udp_lib_get_port(struct sock *sk, unsigned short snum,
* force rand to be an odd multiple of UDP_HTABLE_SIZE
*/
rand = (rand | 1) * (udptable->mask + 1);
- for (last = first + udptable->mask + 1;
- first != last;
- first++) {
+ last = first + udptable->mask + 1;
+ do {
hslot = udp_hashslot(udptable, net, first);
bitmap_zero(bitmap, PORTS_PER_CHAIN);
spin_lock_bh(&hslot->lock);
@@ -238,7 +237,7 @@ int udp_lib_get_port(struct sock *sk, unsigned short snum,
snum += rand;
} while (snum != first);
spin_unlock_bh(&hslot->lock);
- }
+ } while (++first != last);
goto fail;
} else {
hslot = udp_hashslot(udptable, net, snum);
diff --git a/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c b/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c
index 5f2ec208a8c3..0956ebabbff2 100644
--- a/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c
+++ b/net/ipv6/netfilter/nf_conntrack_l3proto_ipv6.c
@@ -20,6 +20,7 @@
#include <net/ipv6.h>
#include <net/inet_frag.h>
+#include <linux/netfilter_bridge.h>
#include <linux/netfilter_ipv6.h>
#include <net/netfilter/nf_conntrack.h>
#include <net/netfilter/nf_conntrack_helper.h>
@@ -187,6 +188,21 @@ out:
return nf_conntrack_confirm(skb);
}
+static enum ip6_defrag_users nf_ct6_defrag_user(unsigned int hooknum,
+ struct sk_buff *skb)
+{
+#ifdef CONFIG_BRIDGE_NETFILTER
+ if (skb->nf_bridge &&
+ skb->nf_bridge->mask & BRNF_NF_BRIDGE_PREROUTING)
+ return IP6_DEFRAG_CONNTRACK_BRIDGE_IN;
+#endif
+ if (hooknum == NF_INET_PRE_ROUTING)
+ return IP6_DEFRAG_CONNTRACK_IN;
+ else
+ return IP6_DEFRAG_CONNTRACK_OUT;
+
+}
+
static unsigned int ipv6_defrag(unsigned int hooknum,
struct sk_buff *skb,
const struct net_device *in,
@@ -199,8 +215,7 @@ static unsigned int ipv6_defrag(unsigned int hooknum,
if (skb->nfct)
return NF_ACCEPT;
- reasm = nf_ct_frag6_gather(skb);
-
+ reasm = nf_ct_frag6_gather(skb, nf_ct6_defrag_user(hooknum, skb));
/* queued */
if (reasm == NULL)
return NF_STOLEN;
diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c
index e0b9424fa1b2..312c20adc83f 100644
--- a/net/ipv6/netfilter/nf_conntrack_reasm.c
+++ b/net/ipv6/netfilter/nf_conntrack_reasm.c
@@ -168,13 +168,14 @@ out:
/* Creation primitives. */
static __inline__ struct nf_ct_frag6_queue *
-fq_find(__be32 id, struct in6_addr *src, struct in6_addr *dst)
+fq_find(__be32 id, u32 user, struct in6_addr *src, struct in6_addr *dst)
{
struct inet_frag_queue *q;
struct ip6_create_arg arg;
unsigned int hash;
arg.id = id;
+ arg.user = user;
arg.src = src;
arg.dst = dst;
@@ -559,7 +560,7 @@ find_prev_fhdr(struct sk_buff *skb, u8 *prevhdrp, int *prevhoff, int *fhoff)
return 0;
}
-struct sk_buff *nf_ct_frag6_gather(struct sk_buff *skb)
+struct sk_buff *nf_ct_frag6_gather(struct sk_buff *skb, u32 user)
{
struct sk_buff *clone;
struct net_device *dev = skb->dev;
@@ -605,7 +606,7 @@ struct sk_buff *nf_ct_frag6_gather(struct sk_buff *skb)
if (atomic_read(&nf_init_frags.mem) > nf_init_frags.high_thresh)
nf_ct_frag6_evictor();
- fq = fq_find(fhdr->identification, &hdr->saddr, &hdr->daddr);
+ fq = fq_find(fhdr->identification, user, &hdr->saddr, &hdr->daddr);
if (fq == NULL) {
pr_debug("Can't find and can't create new queue\n");
goto ret_orig;
diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c
index 4d98549a6868..3b3a95607125 100644
--- a/net/ipv6/reassembly.c
+++ b/net/ipv6/reassembly.c
@@ -72,6 +72,7 @@ struct frag_queue
struct inet_frag_queue q;
__be32 id; /* fragment id */
+ u32 user;
struct in6_addr saddr;
struct in6_addr daddr;
@@ -141,7 +142,7 @@ int ip6_frag_match(struct inet_frag_queue *q, void *a)
struct ip6_create_arg *arg = a;
fq = container_of(q, struct frag_queue, q);
- return (fq->id == arg->id &&
+ return (fq->id == arg->id && fq->user == arg->user &&
ipv6_addr_equal(&fq->saddr, arg->src) &&
ipv6_addr_equal(&fq->daddr, arg->dst));
}
@@ -163,6 +164,7 @@ void ip6_frag_init(struct inet_frag_queue *q, void *a)
struct ip6_create_arg *arg = a;
fq->id = arg->id;
+ fq->user = arg->user;
ipv6_addr_copy(&fq->saddr, arg->src);
ipv6_addr_copy(&fq->daddr, arg->dst);
}
@@ -243,6 +245,7 @@ fq_find(struct net *net, __be32 id, struct in6_addr *src, struct in6_addr *dst,
unsigned int hash;
arg.id = id;
+ arg.user = IP6_DEFRAG_LOCAL_DELIVER;
arg.src = src;
arg.dst = dst;
diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c
index 5b9af508b8f2..7208a06576c6 100644
--- a/net/ipv6/syncookies.c
+++ b/net/ipv6/syncookies.c
@@ -185,6 +185,13 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb)
NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_SYNCOOKIESRECV);
+ /* check for timestamp cookie support */
+ memset(&tcp_opt, 0, sizeof(tcp_opt));
+ tcp_parse_options(skb, &tcp_opt, &hash_location, 0);
+
+ if (tcp_opt.saw_tstamp)
+ cookie_check_timestamp(&tcp_opt);
+
ret = NULL;
req = inet6_reqsk_alloc(&tcp6_request_sock_ops);
if (!req)
@@ -218,6 +225,12 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb)
req->expires = 0UL;
req->retrans = 0;
ireq->ecn_ok = 0;
+ ireq->snd_wscale = tcp_opt.snd_wscale;
+ ireq->rcv_wscale = tcp_opt.rcv_wscale;
+ ireq->sack_ok = tcp_opt.sack_ok;
+ ireq->wscale_ok = tcp_opt.wscale_ok;
+ ireq->tstamp_ok = tcp_opt.saw_tstamp;
+ req->ts_recent = tcp_opt.saw_tstamp ? tcp_opt.rcv_tsval : 0;
treq->rcv_isn = ntohl(th->seq) - 1;
treq->snt_isn = cookie;
@@ -253,21 +266,6 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb)
goto out_free;
}
- /* check for timestamp cookie support */
- memset(&tcp_opt, 0, sizeof(tcp_opt));
- tcp_parse_options(skb, &tcp_opt, &hash_location, 0, dst);
-
- if (tcp_opt.saw_tstamp)
- cookie_check_timestamp(&tcp_opt);
-
- req->ts_recent = tcp_opt.saw_tstamp ? tcp_opt.rcv_tsval : 0;
-
- ireq->snd_wscale = tcp_opt.snd_wscale;
- ireq->rcv_wscale = tcp_opt.rcv_wscale;
- ireq->sack_ok = tcp_opt.sack_ok;
- ireq->wscale_ok = tcp_opt.wscale_ok;
- ireq->tstamp_ok = tcp_opt.saw_tstamp;
-
req->window_clamp = tp->window_clamp ? :dst_metric(dst, RTAX_WINDOW);
tcp_select_initial_window(tcp_full_space(sk), req->mss,
&req->rcv_wnd, &req->window_clamp,
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index ee9cf62458d4..febfd595a40d 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -1169,7 +1169,6 @@ static int tcp_v6_conn_request(struct sock *sk, struct sk_buff *skb)
struct inet6_request_sock *treq;
struct ipv6_pinfo *np = inet6_sk(sk);
struct tcp_sock *tp = tcp_sk(sk);
- struct dst_entry *dst = __sk_dst_get(sk);
__u32 isn = TCP_SKB_CB(skb)->when;
#ifdef CONFIG_SYN_COOKIES
int want_cookie = 0;
@@ -1208,7 +1207,7 @@ static int tcp_v6_conn_request(struct sock *sk, struct sk_buff *skb)
tcp_clear_options(&tmp_opt);
tmp_opt.mss_clamp = IPV6_MIN_MTU - sizeof(struct tcphdr) - sizeof(struct ipv6hdr);
tmp_opt.user_mss = tp->rx_opt.user_mss;
- tcp_parse_options(skb, &tmp_opt, &hash_location, 0, dst);
+ tcp_parse_options(skb, &tmp_opt, &hash_location, 0);
if (tmp_opt.cookie_plus > 0 &&
tmp_opt.saw_tstamp &&
diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c
index b95699f00545..847ffca40184 100644
--- a/net/netfilter/ipvs/ip_vs_core.c
+++ b/net/netfilter/ipvs/ip_vs_core.c
@@ -1366,6 +1366,7 @@ ip_vs_in(unsigned int hooknum, struct sk_buff *skb,
== sysctl_ip_vs_sync_threshold[0])) ||
((cp->protocol == IPPROTO_TCP) && (cp->old_state != cp->state) &&
((cp->state == IP_VS_TCP_S_FIN_WAIT) ||
+ (cp->state == IP_VS_TCP_S_CLOSE) ||
(cp->state == IP_VS_TCP_S_CLOSE_WAIT) ||
(cp->state == IP_VS_TCP_S_TIME_WAIT)))))
ip_vs_sync_conn(cp);
diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c
index e55a6861d26f..6bde12da2fe0 100644
--- a/net/netfilter/ipvs/ip_vs_ctl.c
+++ b/net/netfilter/ipvs/ip_vs_ctl.c
@@ -2714,6 +2714,8 @@ static int ip_vs_genl_parse_service(struct ip_vs_service_user_kern *usvc,
if (!(nla_af && (nla_fwmark || (nla_port && nla_protocol && nla_addr))))
return -EINVAL;
+ memset(usvc, 0, sizeof(*usvc));
+
usvc->af = nla_get_u16(nla_af);
#ifdef CONFIG_IP_VS_IPV6
if (usvc->af != AF_INET && usvc->af != AF_INET6)
@@ -2901,6 +2903,8 @@ static int ip_vs_genl_parse_dest(struct ip_vs_dest_user_kern *udest,
if (!(nla_addr && nla_port))
return -EINVAL;
+ memset(udest, 0, sizeof(*udest));
+
nla_memcpy(&udest->addr, nla_addr, sizeof(udest->addr));
udest->port = nla_get_u16(nla_port);
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 020562164b56..e0516a22be2e 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -415,7 +415,7 @@ static int packet_sendmsg_spkt(struct kiocb *iocb, struct socket *sock,
{
struct sock *sk = sock->sk;
struct sockaddr_pkt *saddr = (struct sockaddr_pkt *)msg->msg_name;
- struct sk_buff *skb;
+ struct sk_buff *skb = NULL;
struct net_device *dev;
__be16 proto = 0;
int err;
@@ -437,6 +437,7 @@ static int packet_sendmsg_spkt(struct kiocb *iocb, struct socket *sock,
*/
saddr->spkt_device[13] = 0;
+retry:
rcu_read_lock();
dev = dev_get_by_name_rcu(sock_net(sk), saddr->spkt_device);
err = -ENODEV;
@@ -456,58 +457,48 @@ static int packet_sendmsg_spkt(struct kiocb *iocb, struct socket *sock,
if (len > dev->mtu + dev->hard_header_len)
goto out_unlock;
- err = -ENOBUFS;
- skb = sock_wmalloc(sk, len + LL_RESERVED_SPACE(dev), 0, GFP_KERNEL);
-
- /*
- * If the write buffer is full, then tough. At this level the user
- * gets to deal with the problem - do your own algorithmic backoffs.
- * That's far more flexible.
- */
-
- if (skb == NULL)
- goto out_unlock;
-
- /*
- * Fill it in
- */
-
- /* FIXME: Save some space for broken drivers that write a
- * hard header at transmission time by themselves. PPP is the
- * notable one here. This should really be fixed at the driver level.
- */
- skb_reserve(skb, LL_RESERVED_SPACE(dev));
- skb_reset_network_header(skb);
-
- /* Try to align data part correctly */
- if (dev->header_ops) {
- skb->data -= dev->hard_header_len;
- skb->tail -= dev->hard_header_len;
- if (len < dev->hard_header_len)
- skb_reset_network_header(skb);
+ if (!skb) {
+ size_t reserved = LL_RESERVED_SPACE(dev);
+ unsigned int hhlen = dev->header_ops ? dev->hard_header_len : 0;
+
+ rcu_read_unlock();
+ skb = sock_wmalloc(sk, len + reserved, 0, GFP_KERNEL);
+ if (skb == NULL)
+ return -ENOBUFS;
+ /* FIXME: Save some space for broken drivers that write a hard
+ * header at transmission time by themselves. PPP is the notable
+ * one here. This should really be fixed at the driver level.
+ */
+ skb_reserve(skb, reserved);
+ skb_reset_network_header(skb);
+
+ /* Try to align data part correctly */
+ if (hhlen) {
+ skb->data -= hhlen;
+ skb->tail -= hhlen;
+ if (len < hhlen)
+ skb_reset_network_header(skb);
+ }
+ err = memcpy_fromiovec(skb_put(skb, len), msg->msg_iov, len);
+ if (err)
+ goto out_free;
+ goto retry;
}
- /* Returns -EFAULT on error */
- err = memcpy_fromiovec(skb_put(skb, len), msg->msg_iov, len);
+
skb->protocol = proto;
skb->dev = dev;
skb->priority = sk->sk_priority;
skb->mark = sk->sk_mark;
- if (err)
- goto out_free;
-
- /*
- * Now send it
- */
dev_queue_xmit(skb);
rcu_read_unlock();
return len;
-out_free:
- kfree_skb(skb);
out_unlock:
rcu_read_unlock();
+out_free:
+ kfree_skb(skb);
return err;
}