aboutsummaryrefslogtreecommitdiffstats
path: root/net/ipv4
diff options
context:
space:
mode:
authorDavid Woodhouse <David.Woodhouse@intel.com>2010-02-26 19:04:15 +0000
committerDavid Woodhouse <David.Woodhouse@intel.com>2010-02-26 19:06:24 +0000
commita7790532f5b7358c33a6b1834dc2b318de209f31 (patch)
tree0ceb9e24b3f54cb5c8453fb5a218e2a94a0f1cce /net/ipv4
parent2764fb4244cc1bc08df3667924ca4a972e90ac70 (diff)
parent60b341b778cc2929df16c0a504c91621b3c6a4ad (diff)
downloadkernel_samsung_smdk4412-a7790532f5b7358c33a6b1834dc2b318de209f31.zip
kernel_samsung_smdk4412-a7790532f5b7358c33a6b1834dc2b318de209f31.tar.gz
kernel_samsung_smdk4412-a7790532f5b7358c33a6b1834dc2b318de209f31.tar.bz2
Merge branch 'master' of git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux-2.6
The SmartMedia FTL code depends on new kfifo bits from 2.6.33
Diffstat (limited to 'net/ipv4')
-rw-r--r--net/ipv4/Kconfig6
-rw-r--r--net/ipv4/devinet.c8
-rw-r--r--net/ipv4/fib_frontend.c2
-rw-r--r--net/ipv4/igmp.c2
-rw-r--r--net/ipv4/inet_diag.c2
-rw-r--r--net/ipv4/ip_output.c2
-rw-r--r--net/ipv4/ipcomp.c6
-rw-r--r--net/ipv4/ipconfig.c2
-rw-r--r--net/ipv4/netfilter/arp_tables.c4
-rw-r--r--net/ipv4/netfilter/ip_tables.c4
-rw-r--r--net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c2
-rw-r--r--net/ipv4/netfilter/nf_conntrack_l3proto_ipv4_compat.c4
-rw-r--r--net/ipv4/netfilter/nf_defrag_ipv4.c21
-rw-r--r--net/ipv4/netfilter/nf_nat_core.c22
-rw-r--r--net/ipv4/route.c2
-rw-r--r--net/ipv4/syncookies.c27
-rw-r--r--net/ipv4/tcp_input.c30
-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/tcp_probe.c19
-rw-r--r--net/ipv4/udp.c7
-rw-r--r--net/ipv4/xfrm4_policy.c14
23 files changed, 115 insertions, 120 deletions
diff --git a/net/ipv4/Kconfig b/net/ipv4/Kconfig
index 70491d9..0c94a1a 100644
--- a/net/ipv4/Kconfig
+++ b/net/ipv4/Kconfig
@@ -166,7 +166,7 @@ config IP_PNP_DHCP
If unsure, say Y. Note that if you want to use DHCP, a DHCP server
must be operating on your network. Read
- <file:Documentation/filesystems/nfsroot.txt> for details.
+ <file:Documentation/filesystems/nfs/nfsroot.txt> for details.
config IP_PNP_BOOTP
bool "IP: BOOTP support"
@@ -181,7 +181,7 @@ config IP_PNP_BOOTP
does BOOTP itself, providing all necessary information on the kernel
command line, you can say N here. If unsure, say Y. Note that if you
want to use BOOTP, a BOOTP server must be operating on your network.
- Read <file:Documentation/filesystems/nfsroot.txt> for details.
+ Read <file:Documentation/filesystems/nfs/nfsroot.txt> for details.
config IP_PNP_RARP
bool "IP: RARP support"
@@ -194,7 +194,7 @@ config IP_PNP_RARP
older protocol which is being obsoleted by BOOTP and DHCP), say Y
here. Note that if you want to use RARP, a RARP server must be
operating on your network. Read
- <file:Documentation/filesystems/nfsroot.txt> for details.
+ <file:Documentation/filesystems/nfs/nfsroot.txt> for details.
# not yet ready..
# bool ' IP: ARP support' CONFIG_IP_PNP_ARP
diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c
index 5cdbc10..26dec2b 100644
--- a/net/ipv4/devinet.c
+++ b/net/ipv4/devinet.c
@@ -1317,14 +1317,19 @@ static int devinet_sysctl_forward(ctl_table *ctl, int write,
{
int *valp = ctl->data;
int val = *valp;
+ loff_t pos = *ppos;
int ret = proc_dointvec(ctl, write, buffer, lenp, ppos);
if (write && *valp != val) {
struct net *net = ctl->extra2;
if (valp != &IPV4_DEVCONF_DFLT(net, FORWARDING)) {
- if (!rtnl_trylock())
+ if (!rtnl_trylock()) {
+ /* Restore the original values before restarting */
+ *valp = val;
+ *ppos = pos;
return restart_syscall();
+ }
if (valp == &IPV4_DEVCONF_ALL(net, FORWARDING)) {
inet_forward_change(net);
} else if (*valp) {
@@ -1397,6 +1402,7 @@ static struct devinet_sysctl_table {
DEVINET_SYSCTL_RW_ENTRY(ACCEPT_SOURCE_ROUTE,
"accept_source_route"),
DEVINET_SYSCTL_RW_ENTRY(ACCEPT_LOCAL, "accept_local"),
+ DEVINET_SYSCTL_RW_ENTRY(SRC_VMARK, "src_valid_mark"),
DEVINET_SYSCTL_RW_ENTRY(PROXY_ARP, "proxy_arp"),
DEVINET_SYSCTL_RW_ENTRY(MEDIUM_ID, "medium_id"),
DEVINET_SYSCTL_RW_ENTRY(BOOTP_RELAY, "bootp_relay"),
diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index 3323168..82dbf71 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -252,6 +252,8 @@ int fib_validate_source(__be32 src, __be32 dst, u8 tos, int oif,
no_addr = in_dev->ifa_list == NULL;
rpf = IN_DEV_RPFILTER(in_dev);
accept_local = IN_DEV_ACCEPT_LOCAL(in_dev);
+ if (mark && !IN_DEV_SRC_VMARK(in_dev))
+ fl.mark = 0;
}
rcu_read_unlock();
diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c
index 76c0840..a42f658 100644
--- a/net/ipv4/igmp.c
+++ b/net/ipv4/igmp.c
@@ -946,7 +946,6 @@ int igmp_rcv(struct sk_buff *skb)
break;
case IGMP_HOST_MEMBERSHIP_REPORT:
case IGMPV2_HOST_MEMBERSHIP_REPORT:
- case IGMPV3_HOST_MEMBERSHIP_REPORT:
/* Is it our report looped back? */
if (skb_rtable(skb)->fl.iif == 0)
break;
@@ -960,6 +959,7 @@ int igmp_rcv(struct sk_buff *skb)
in_dev_put(in_dev);
return pim_rcv_v1(skb);
#endif
+ case IGMPV3_HOST_MEMBERSHIP_REPORT:
case IGMP_DVMRP:
case IGMP_TRACE:
case IGMP_HOST_LEAVE_MESSAGE:
diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c
index bdb78dd..1aaa811 100644
--- a/net/ipv4/inet_diag.c
+++ b/net/ipv4/inet_diag.c
@@ -368,7 +368,7 @@ static int inet_diag_bc_run(const void *bc, int len,
yes = entry->sport >= op[1].no;
break;
case INET_DIAG_BC_S_LE:
- yes = entry->dport <= op[1].no;
+ yes = entry->sport <= op[1].no;
break;
case INET_DIAG_BC_D_GE:
yes = entry->dport >= op[1].no;
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index e34013a..3451799 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -254,7 +254,7 @@ int ip_mc_output(struct sk_buff *skb)
*/
if (rt->rt_flags&RTCF_MULTICAST) {
- if ((!sk || inet_sk(sk)->mc_loop)
+ if (sk_mc_loop(sk)
#ifdef CONFIG_IP_MROUTE
/* Small optimization: do not loopback not local frames,
which returned after forwarding; they will be dropped
diff --git a/net/ipv4/ipcomp.c b/net/ipv4/ipcomp.c
index 38fbf04..544ce08 100644
--- a/net/ipv4/ipcomp.c
+++ b/net/ipv4/ipcomp.c
@@ -124,16 +124,12 @@ static int ipcomp4_init_state(struct xfrm_state *x)
if (x->props.mode == XFRM_MODE_TUNNEL) {
err = ipcomp_tunnel_attach(x);
if (err)
- goto error_tunnel;
+ goto out;
}
err = 0;
out:
return err;
-
-error_tunnel:
- ipcomp_destroy(x);
- goto out;
}
static const struct xfrm_type ipcomp_type = {
diff --git a/net/ipv4/ipconfig.c b/net/ipv4/ipconfig.c
index 4e08b7f..10a6a60 100644
--- a/net/ipv4/ipconfig.c
+++ b/net/ipv4/ipconfig.c
@@ -1446,7 +1446,7 @@ late_initcall(ip_auto_config);
/*
* Decode any IP configuration options in the "ip=" or "nfsaddrs=" kernel
- * command line parameter. See Documentation/filesystems/nfsroot.txt.
+ * command line parameter. See Documentation/filesystems/nfs/nfsroot.txt.
*/
static int __init ic_proto_name(char *name)
{
diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c
index 0663276..90203e1 100644
--- a/net/ipv4/netfilter/arp_tables.c
+++ b/net/ipv4/netfilter/arp_tables.c
@@ -925,10 +925,10 @@ static int get_info(struct net *net, void __user *user, int *len, int compat)
if (t && !IS_ERR(t)) {
struct arpt_getinfo info;
const struct xt_table_info *private = t->private;
-
#ifdef CONFIG_COMPAT
+ struct xt_table_info tmp;
+
if (compat) {
- struct xt_table_info tmp;
ret = compat_table_info(private, &tmp);
xt_compat_flush_offsets(NFPROTO_ARP);
private = &tmp;
diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c
index 572330a..3ce53cf 100644
--- a/net/ipv4/netfilter/ip_tables.c
+++ b/net/ipv4/netfilter/ip_tables.c
@@ -1132,10 +1132,10 @@ static int get_info(struct net *net, void __user *user, int *len, int compat)
if (t && !IS_ERR(t)) {
struct ipt_getinfo info;
const struct xt_table_info *private = t->private;
-
#ifdef CONFIG_COMPAT
+ struct xt_table_info tmp;
+
if (compat) {
- struct xt_table_info tmp;
ret = compat_table_info(private, &tmp);
xt_compat_flush_offsets(AF_INET);
private = &tmp;
diff --git a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c
index d171b12..d1ea38a 100644
--- a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c
+++ b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c
@@ -210,7 +210,7 @@ static ctl_table ip_ct_sysctl_table[] = {
},
{
.procname = "ip_conntrack_buckets",
- .data = &nf_conntrack_htable_size,
+ .data = &init_net.ct.htable_size,
.maxlen = sizeof(unsigned int),
.mode = 0444,
.proc_handler = proc_dointvec,
diff --git a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4_compat.c b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4_compat.c
index 8668a3d..2fb7b76 100644
--- a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4_compat.c
+++ b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4_compat.c
@@ -32,7 +32,7 @@ static struct hlist_nulls_node *ct_get_first(struct seq_file *seq)
struct hlist_nulls_node *n;
for (st->bucket = 0;
- st->bucket < nf_conntrack_htable_size;
+ st->bucket < net->ct.htable_size;
st->bucket++) {
n = rcu_dereference(net->ct.hash[st->bucket].first);
if (!is_a_nulls(n))
@@ -50,7 +50,7 @@ static struct hlist_nulls_node *ct_get_next(struct seq_file *seq,
head = rcu_dereference(head->next);
while (is_a_nulls(head)) {
if (likely(get_nulls_value(head) == st->bucket)) {
- if (++st->bucket >= nf_conntrack_htable_size)
+ if (++st->bucket >= net->ct.htable_size)
return NULL;
}
head = rcu_dereference(net->ct.hash[st->bucket].first);
diff --git a/net/ipv4/netfilter/nf_defrag_ipv4.c b/net/ipv4/netfilter/nf_defrag_ipv4.c
index fa2d6b6..331ead3 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/netfilter/nf_nat_core.c b/net/ipv4/netfilter/nf_nat_core.c
index fe1a644..26066a2 100644
--- a/net/ipv4/netfilter/nf_nat_core.c
+++ b/net/ipv4/netfilter/nf_nat_core.c
@@ -35,9 +35,6 @@ static DEFINE_SPINLOCK(nf_nat_lock);
static struct nf_conntrack_l3proto *l3proto __read_mostly;
-/* Calculated at init based on memory size */
-static unsigned int nf_nat_htable_size __read_mostly;
-
#define MAX_IP_NAT_PROTO 256
static const struct nf_nat_protocol *nf_nat_protos[MAX_IP_NAT_PROTO]
__read_mostly;
@@ -72,7 +69,7 @@ EXPORT_SYMBOL_GPL(nf_nat_proto_put);
/* We keep an extra hash for each conntrack, for fast searching. */
static inline unsigned int
-hash_by_src(const struct nf_conntrack_tuple *tuple)
+hash_by_src(const struct net *net, const struct nf_conntrack_tuple *tuple)
{
unsigned int hash;
@@ -80,7 +77,7 @@ hash_by_src(const struct nf_conntrack_tuple *tuple)
hash = jhash_3words((__force u32)tuple->src.u3.ip,
(__force u32)tuple->src.u.all,
tuple->dst.protonum, 0);
- return ((u64)hash * nf_nat_htable_size) >> 32;
+ return ((u64)hash * net->ipv4.nat_htable_size) >> 32;
}
/* Is this tuple already taken? (not by us) */
@@ -147,7 +144,7 @@ find_appropriate_src(struct net *net,
struct nf_conntrack_tuple *result,
const struct nf_nat_range *range)
{
- unsigned int h = hash_by_src(tuple);
+ unsigned int h = hash_by_src(net, tuple);
const struct nf_conn_nat *nat;
const struct nf_conn *ct;
const struct hlist_node *n;
@@ -330,7 +327,7 @@ nf_nat_setup_info(struct nf_conn *ct,
if (have_to_hash) {
unsigned int srchash;
- srchash = hash_by_src(&ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple);
+ srchash = hash_by_src(net, &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple);
spin_lock_bh(&nf_nat_lock);
/* nf_conntrack_alter_reply might re-allocate exntension aera */
nat = nfct_nat(ct);
@@ -679,8 +676,10 @@ nfnetlink_parse_nat_setup(struct nf_conn *ct,
static int __net_init nf_nat_net_init(struct net *net)
{
- net->ipv4.nat_bysource = nf_ct_alloc_hashtable(&nf_nat_htable_size,
- &net->ipv4.nat_vmalloced, 0);
+ /* Leave them the same for the moment. */
+ net->ipv4.nat_htable_size = net->ct.htable_size;
+ net->ipv4.nat_bysource = nf_ct_alloc_hashtable(&net->ipv4.nat_htable_size,
+ &net->ipv4.nat_vmalloced, 0);
if (!net->ipv4.nat_bysource)
return -ENOMEM;
return 0;
@@ -703,7 +702,7 @@ static void __net_exit nf_nat_net_exit(struct net *net)
nf_ct_iterate_cleanup(net, &clean_nat, NULL);
synchronize_rcu();
nf_ct_free_hashtable(net->ipv4.nat_bysource, net->ipv4.nat_vmalloced,
- nf_nat_htable_size);
+ net->ipv4.nat_htable_size);
}
static struct pernet_operations nf_nat_net_ops = {
@@ -724,9 +723,6 @@ static int __init nf_nat_init(void)
return ret;
}
- /* Leave them the same for the moment. */
- nf_nat_htable_size = nf_conntrack_htable_size;
-
ret = register_pernet_subsys(&nf_nat_net_ops);
if (ret < 0)
goto cleanup_extend;
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index e446496..d62b05d 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -586,7 +586,9 @@ static void __net_exit ip_rt_do_proc_exit(struct net *net)
{
remove_proc_entry("rt_cache", net->proc_net_stat);
remove_proc_entry("rt_cache", net->proc_net);
+#ifdef CONFIG_NET_CLS_ROUTE
remove_proc_entry("rt_acct", net->proc_net);
+#endif
}
static struct pernet_operations ip_rt_proc_ops __net_initdata = {
diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c
index 26399ad..66fd80e 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 12cab7d..3fddc69 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:
@@ -5791,11 +5783,9 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb,
/* tcp_ack considers this ACK as duplicate
* and does not calculate rtt.
- * Fix it at least with timestamps.
+ * Force it here.
*/
- if (tp->rx_opt.saw_tstamp &&
- tp->rx_opt.rcv_tsecr && !tp->srtt)
- tcp_ack_saw_tstamp(sk, 0);
+ tcp_ack_update_rtt(sk, 0, 0);
if (tp->rx_opt.tstamp_ok)
tp->advmss -= TCPOLEN_TSTAMP_ALIGNED;
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 15e9603..65b8ebf 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 87accec..f206ee5 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 93316a9..383ce23 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/tcp_probe.c b/net/ipv4/tcp_probe.c
index bb110c5..9bc805d 100644
--- a/net/ipv4/tcp_probe.c
+++ b/net/ipv4/tcp_probe.c
@@ -39,9 +39,9 @@ static int port __read_mostly = 0;
MODULE_PARM_DESC(port, "Port to match (0=all)");
module_param(port, int, 0);
-static int bufsize __read_mostly = 4096;
+static unsigned int bufsize __read_mostly = 4096;
MODULE_PARM_DESC(bufsize, "Log buffer size in packets (4096)");
-module_param(bufsize, int, 0);
+module_param(bufsize, uint, 0);
static int full __read_mostly;
MODULE_PARM_DESC(full, "Full log (1=every ack packet received, 0=only cwnd changes)");
@@ -75,12 +75,12 @@ static struct {
static inline int tcp_probe_used(void)
{
- return (tcp_probe.head - tcp_probe.tail) % bufsize;
+ return (tcp_probe.head - tcp_probe.tail) & (bufsize - 1);
}
static inline int tcp_probe_avail(void)
{
- return bufsize - tcp_probe_used();
+ return bufsize - tcp_probe_used() - 1;
}
/*
@@ -116,7 +116,7 @@ static int jtcp_rcv_established(struct sock *sk, struct sk_buff *skb,
p->ssthresh = tcp_current_ssthresh(sk);
p->srtt = tp->srtt >> 3;
- tcp_probe.head = (tcp_probe.head + 1) % bufsize;
+ tcp_probe.head = (tcp_probe.head + 1) & (bufsize - 1);
}
tcp_probe.lastcwnd = tp->snd_cwnd;
spin_unlock(&tcp_probe.lock);
@@ -149,7 +149,7 @@ static int tcpprobe_open(struct inode * inode, struct file * file)
static int tcpprobe_sprint(char *tbuf, int n)
{
const struct tcp_log *p
- = tcp_probe.log + tcp_probe.tail % bufsize;
+ = tcp_probe.log + tcp_probe.tail;
struct timespec tv
= ktime_to_timespec(ktime_sub(p->tstamp, tcp_probe.start));
@@ -192,7 +192,7 @@ static ssize_t tcpprobe_read(struct file *file, char __user *buf,
width = tcpprobe_sprint(tbuf, sizeof(tbuf));
if (cnt + width < len)
- tcp_probe.tail = (tcp_probe.tail + 1) % bufsize;
+ tcp_probe.tail = (tcp_probe.tail + 1) & (bufsize - 1);
spin_unlock_bh(&tcp_probe.lock);
@@ -222,9 +222,10 @@ static __init int tcpprobe_init(void)
init_waitqueue_head(&tcp_probe.wait);
spin_lock_init(&tcp_probe.lock);
- if (bufsize < 0)
+ if (bufsize == 0)
return -EINVAL;
+ bufsize = roundup_pow_of_two(bufsize);
tcp_probe.log = kcalloc(bufsize, sizeof(struct tcp_log), GFP_KERNEL);
if (!tcp_probe.log)
goto err0;
@@ -236,7 +237,7 @@ static __init int tcpprobe_init(void)
if (ret)
goto err1;
- pr_info("TCP probe registered (port=%d)\n", port);
+ pr_info("TCP probe registered (port=%d) bufsize=%u\n", port, bufsize);
return 0;
err1:
proc_net_remove(&init_net, procname);
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 1f95348..f0126fd 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/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c
index 8c08a28..67107d6 100644
--- a/net/ipv4/xfrm4_policy.c
+++ b/net/ipv4/xfrm4_policy.c
@@ -15,7 +15,6 @@
#include <net/xfrm.h>
#include <net/ip.h>
-static struct dst_ops xfrm4_dst_ops;
static struct xfrm_policy_afinfo xfrm4_policy_afinfo;
static struct dst_entry *xfrm4_dst_lookup(struct net *net, int tos,
@@ -190,8 +189,10 @@ _decode_session4(struct sk_buff *skb, struct flowi *fl, int reverse)
static inline int xfrm4_garbage_collect(struct dst_ops *ops)
{
- xfrm4_policy_afinfo.garbage_collect(&init_net);
- return (atomic_read(&xfrm4_dst_ops.entries) > xfrm4_dst_ops.gc_thresh*2);
+ struct net *net = container_of(ops, struct net, xfrm.xfrm4_dst_ops);
+
+ xfrm4_policy_afinfo.garbage_collect(net);
+ return (atomic_read(&ops->entries) > ops->gc_thresh * 2);
}
static void xfrm4_update_pmtu(struct dst_entry *dst, u32 mtu)
@@ -268,7 +269,7 @@ static struct xfrm_policy_afinfo xfrm4_policy_afinfo = {
static struct ctl_table xfrm4_policy_table[] = {
{
.procname = "xfrm4_gc_thresh",
- .data = &xfrm4_dst_ops.gc_thresh,
+ .data = &init_net.xfrm.xfrm4_dst_ops.gc_thresh,
.maxlen = sizeof(int),
.mode = 0644,
.proc_handler = proc_dointvec,
@@ -295,8 +296,6 @@ static void __exit xfrm4_policy_fini(void)
void __init xfrm4_init(int rt_max_size)
{
- xfrm4_state_init();
- xfrm4_policy_init();
/*
* 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
@@ -308,6 +307,9 @@ void __init xfrm4_init(int rt_max_size)
* and start cleaning when were 1/2 full
*/
xfrm4_dst_ops.gc_thresh = rt_max_size/2;
+
+ xfrm4_state_init();
+ xfrm4_policy_init();
#ifdef CONFIG_SYSCTL
sysctl_hdr = register_net_sysctl_table(&init_net, net_ipv4_ctl_path,
xfrm4_policy_table);