summaryrefslogtreecommitdiffstats
path: root/net/ipv4
diff options
context:
space:
mode:
Diffstat (limited to 'net/ipv4')
-rw-r--r--net/ipv4/Kconfig7
-rw-r--r--net/ipv4/Makefile1
-rw-r--r--net/ipv4/af_inet.c8
-rw-r--r--net/ipv4/arp.c226
-rw-r--r--net/ipv4/gre.c151
-rw-r--r--net/ipv4/icmp.c4
-rw-r--r--net/ipv4/ip_fragment.c2
-rw-r--r--net/ipv4/ip_gre.c14
-rw-r--r--net/ipv4/ip_output.c15
-rw-r--r--net/ipv4/ipip.c2
-rw-r--r--net/ipv4/netfilter/ipt_CLUSTERIP.c31
-rw-r--r--net/ipv4/protocol.c31
-rw-r--r--net/ipv4/raw.c2
-rw-r--r--net/ipv4/route.c9
-rw-r--r--net/ipv4/tcp.c11
-rw-r--r--net/ipv4/tcp_input.c17
-rw-r--r--net/ipv4/tcp_ipv4.c2
-rw-r--r--net/ipv4/tcp_output.c23
-rw-r--r--net/ipv4/tcp_timer.c40
-rw-r--r--net/ipv4/tunnel4.c19
-rw-r--r--net/ipv4/udp.c4
-rw-r--r--net/ipv4/xfrm4_tunnel.c4
22 files changed, 392 insertions, 231 deletions
diff --git a/net/ipv4/Kconfig b/net/ipv4/Kconfig
index 571f8950ed06..5462e2d147a6 100644
--- a/net/ipv4/Kconfig
+++ b/net/ipv4/Kconfig
@@ -215,8 +215,15 @@ config NET_IPIP
be inserted in and removed from the running kernel whenever you
want). Most people won't need this and can say N.
+config NET_IPGRE_DEMUX
+ tristate "IP: GRE demultiplexer"
+ help
+ This is helper module to demultiplex GRE packets on GRE version field criteria.
+ Required by ip_gre and pptp modules.
+
config NET_IPGRE
tristate "IP: GRE tunnels over IP"
+ depends on NET_IPGRE_DEMUX
help
Tunneling means encapsulating data of one protocol type within
another protocol and sending it over a channel that understands the
diff --git a/net/ipv4/Makefile b/net/ipv4/Makefile
index 80ff87ce43aa..4978d22f9a75 100644
--- a/net/ipv4/Makefile
+++ b/net/ipv4/Makefile
@@ -20,6 +20,7 @@ obj-$(CONFIG_PROC_FS) += proc.o
obj-$(CONFIG_IP_MULTIPLE_TABLES) += fib_rules.o
obj-$(CONFIG_IP_MROUTE) += ipmr.o
obj-$(CONFIG_NET_IPIP) += ipip.o
+obj-$(CONFIG_NET_IPGRE_DEMUX) += gre.o
obj-$(CONFIG_NET_IPGRE) += ip_gre.o
obj-$(CONFIG_SYN_COOKIES) += syncookies.o
obj-$(CONFIG_INET_AH) += ah4.o
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 6a1100c25a9f..f581f77d1097 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -227,18 +227,16 @@ EXPORT_SYMBOL(inet_ehash_secret);
/*
* inet_ehash_secret must be set exactly once
- * Instead of using a dedicated spinlock, we (ab)use inetsw_lock
*/
void build_ehash_secret(void)
{
u32 rnd;
+
do {
get_random_bytes(&rnd, sizeof(rnd));
} while (rnd == 0);
- spin_lock_bh(&inetsw_lock);
- if (!inet_ehash_secret)
- inet_ehash_secret = rnd;
- spin_unlock_bh(&inetsw_lock);
+
+ cmpxchg(&inet_ehash_secret, 0, rnd);
}
EXPORT_SYMBOL(build_ehash_secret);
diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c
index 96c1955b3e2f..dcfe7e961c10 100644
--- a/net/ipv4/arp.c
+++ b/net/ipv4/arp.c
@@ -55,7 +55,7 @@
* Stuart Cheshire : Metricom and grat arp fixes
* *** FOR 2.1 clean this up ***
* Lawrence V. Stefani: (08/12/96) Added FDDI support.
- * Alan Cox : Took the AP1000 nasty FDDI hack and
+ * Alan Cox : Took the AP1000 nasty FDDI hack and
* folded into the mainstream FDDI code.
* Ack spit, Linus how did you allow that
* one in...
@@ -120,7 +120,7 @@ EXPORT_SYMBOL(clip_tbl_hook);
#endif
#include <asm/system.h>
-#include <asm/uaccess.h>
+#include <linux/uaccess.h>
#include <linux/netfilter_arp.h>
@@ -173,32 +173,32 @@ const struct neigh_ops arp_broken_ops = {
EXPORT_SYMBOL(arp_broken_ops);
struct neigh_table arp_tbl = {
- .family = AF_INET,
- .entry_size = sizeof(struct neighbour) + 4,
- .key_len = 4,
- .hash = arp_hash,
- .constructor = arp_constructor,
- .proxy_redo = parp_redo,
- .id = "arp_cache",
- .parms = {
- .tbl = &arp_tbl,
- .base_reachable_time = 30 * HZ,
- .retrans_time = 1 * HZ,
- .gc_staletime = 60 * HZ,
- .reachable_time = 30 * HZ,
- .delay_probe_time = 5 * HZ,
- .queue_len = 3,
- .ucast_probes = 3,
- .mcast_probes = 3,
- .anycast_delay = 1 * HZ,
- .proxy_delay = (8 * HZ) / 10,
- .proxy_qlen = 64,
- .locktime = 1 * HZ,
+ .family = AF_INET,
+ .entry_size = sizeof(struct neighbour) + 4,
+ .key_len = 4,
+ .hash = arp_hash,
+ .constructor = arp_constructor,
+ .proxy_redo = parp_redo,
+ .id = "arp_cache",
+ .parms = {
+ .tbl = &arp_tbl,
+ .base_reachable_time = 30 * HZ,
+ .retrans_time = 1 * HZ,
+ .gc_staletime = 60 * HZ,
+ .reachable_time = 30 * HZ,
+ .delay_probe_time = 5 * HZ,
+ .queue_len = 3,
+ .ucast_probes = 3,
+ .mcast_probes = 3,
+ .anycast_delay = 1 * HZ,
+ .proxy_delay = (8 * HZ) / 10,
+ .proxy_qlen = 64,
+ .locktime = 1 * HZ,
},
- .gc_interval = 30 * HZ,
- .gc_thresh1 = 128,
- .gc_thresh2 = 512,
- .gc_thresh3 = 1024,
+ .gc_interval = 30 * HZ,
+ .gc_thresh1 = 128,
+ .gc_thresh2 = 512,
+ .gc_thresh3 = 1024,
};
EXPORT_SYMBOL(arp_tbl);
@@ -233,7 +233,7 @@ static u32 arp_hash(const void *pkey, const struct net_device *dev)
static int arp_constructor(struct neighbour *neigh)
{
- __be32 addr = *(__be32*)neigh->primary_key;
+ __be32 addr = *(__be32 *)neigh->primary_key;
struct net_device *dev = neigh->dev;
struct in_device *in_dev;
struct neigh_parms *parms;
@@ -296,16 +296,19 @@ static int arp_constructor(struct neighbour *neigh)
neigh->ops = &arp_broken_ops;
neigh->output = neigh->ops->output;
return 0;
+#else
+ break;
#endif
- ;}
+ }
#endif
if (neigh->type == RTN_MULTICAST) {
neigh->nud_state = NUD_NOARP;
arp_mc_map(addr, neigh->ha, dev, 1);
- } else if (dev->flags&(IFF_NOARP|IFF_LOOPBACK)) {
+ } else if (dev->flags & (IFF_NOARP | IFF_LOOPBACK)) {
neigh->nud_state = NUD_NOARP;
memcpy(neigh->ha, dev->dev_addr, dev->addr_len);
- } else if (neigh->type == RTN_BROADCAST || dev->flags&IFF_POINTOPOINT) {
+ } else if (neigh->type == RTN_BROADCAST ||
+ (dev->flags & IFF_POINTOPOINT)) {
neigh->nud_state = NUD_NOARP;
memcpy(neigh->ha, dev->broadcast, dev->addr_len);
}
@@ -315,7 +318,7 @@ static int arp_constructor(struct neighbour *neigh)
else
neigh->ops = &arp_generic_ops;
- if (neigh->nud_state&NUD_VALID)
+ if (neigh->nud_state & NUD_VALID)
neigh->output = neigh->ops->connected_output;
else
neigh->output = neigh->ops->output;
@@ -334,7 +337,7 @@ static void arp_solicit(struct neighbour *neigh, struct sk_buff *skb)
__be32 saddr = 0;
u8 *dst_ha = NULL;
struct net_device *dev = neigh->dev;
- __be32 target = *(__be32*)neigh->primary_key;
+ __be32 target = *(__be32 *)neigh->primary_key;
int probes = atomic_read(&neigh->probes);
struct in_device *in_dev;
@@ -347,7 +350,8 @@ static void arp_solicit(struct neighbour *neigh, struct sk_buff *skb)
switch (IN_DEV_ARP_ANNOUNCE(in_dev)) {
default:
case 0: /* By default announce any local IP */
- if (skb && inet_addr_type(dev_net(dev), ip_hdr(skb)->saddr) == RTN_LOCAL)
+ if (skb && inet_addr_type(dev_net(dev),
+ ip_hdr(skb)->saddr) == RTN_LOCAL)
saddr = ip_hdr(skb)->saddr;
break;
case 1: /* Restrict announcements of saddr in same subnet */
@@ -369,16 +373,21 @@ static void arp_solicit(struct neighbour *neigh, struct sk_buff *skb)
if (!saddr)
saddr = inet_select_addr(dev, target, RT_SCOPE_LINK);
- if ((probes -= neigh->parms->ucast_probes) < 0) {
- if (!(neigh->nud_state&NUD_VALID))
- printk(KERN_DEBUG "trying to ucast probe in NUD_INVALID\n");
+ probes -= neigh->parms->ucast_probes;
+ if (probes < 0) {
+ if (!(neigh->nud_state & NUD_VALID))
+ printk(KERN_DEBUG
+ "trying to ucast probe in NUD_INVALID\n");
dst_ha = neigh->ha;
read_lock_bh(&neigh->lock);
- } else if ((probes -= neigh->parms->app_probes) < 0) {
+ } else {
+ probes -= neigh->parms->app_probes;
+ if (probes < 0) {
#ifdef CONFIG_ARPD
- neigh_app_ns(neigh);
+ neigh_app_ns(neigh);
#endif
- return;
+ return;
+ }
}
arp_send(ARPOP_REQUEST, ETH_P_ARP, target, dev, saddr,
@@ -451,7 +460,8 @@ static int arp_filter(__be32 sip, __be32 tip, struct net_device *dev)
* is allowed to use this function, it is scheduled to be removed. --ANK
*/
-static int arp_set_predefined(int addr_hint, unsigned char * haddr, __be32 paddr, struct net_device * dev)
+static int arp_set_predefined(int addr_hint, unsigned char *haddr,
+ __be32 paddr, struct net_device *dev)
{
switch (addr_hint) {
case RTN_LOCAL:
@@ -483,7 +493,8 @@ int arp_find(unsigned char *haddr, struct sk_buff *skb)
paddr = skb_rtable(skb)->rt_gateway;
- if (arp_set_predefined(inet_addr_type(dev_net(dev), paddr), haddr, paddr, dev))
+ if (arp_set_predefined(inet_addr_type(dev_net(dev), paddr), haddr,
+ paddr, dev))
return 0;
n = __neigh_lookup(&arp_tbl, &paddr, dev, 1);
@@ -515,13 +526,14 @@ int arp_bind_neighbour(struct dst_entry *dst)
return -EINVAL;
if (n == NULL) {
__be32 nexthop = ((struct rtable *)dst)->rt_gateway;
- if (dev->flags&(IFF_LOOPBACK|IFF_POINTOPOINT))
+ if (dev->flags & (IFF_LOOPBACK | IFF_POINTOPOINT))
nexthop = 0;
n = __neigh_lookup_errno(
#if defined(CONFIG_ATM_CLIP) || defined(CONFIG_ATM_CLIP_MODULE)
- dev->type == ARPHRD_ATM ? clip_tbl_hook :
+ dev->type == ARPHRD_ATM ?
+ clip_tbl_hook :
#endif
- &arp_tbl, &nexthop, dev);
+ &arp_tbl, &nexthop, dev);
if (IS_ERR(n))
return PTR_ERR(n);
dst->neighbour = n;
@@ -543,8 +555,8 @@ static inline int arp_fwd_proxy(struct in_device *in_dev,
if (!IN_DEV_PROXY_ARP(in_dev))
return 0;
-
- if ((imi = IN_DEV_MEDIUM_ID(in_dev)) == 0)
+ imi = IN_DEV_MEDIUM_ID(in_dev);
+ if (imi == 0)
return 1;
if (imi == -1)
return 0;
@@ -685,7 +697,7 @@ struct sk_buff *arp_create(int type, int ptype, __be32 dest_ip,
arp->ar_pln = 4;
arp->ar_op = htons(type);
- arp_ptr=(unsigned char *)(arp+1);
+ arp_ptr = (unsigned char *)(arp + 1);
memcpy(arp_ptr, src_hw, dev->addr_len);
arp_ptr += dev->addr_len;
@@ -735,9 +747,8 @@ void arp_send(int type, int ptype, __be32 dest_ip,
skb = arp_create(type, ptype, dest_ip, dev, src_ip,
dest_hw, src_hw, target_hw);
- if (skb == NULL) {
+ if (skb == NULL)
return;
- }
arp_xmit(skb);
}
@@ -815,7 +826,7 @@ static int arp_process(struct sk_buff *skb)
/*
* Extract fields
*/
- arp_ptr= (unsigned char *)(arp+1);
+ arp_ptr = (unsigned char *)(arp + 1);
sha = arp_ptr;
arp_ptr += dev->addr_len;
memcpy(&sip, arp_ptr, 4);
@@ -869,16 +880,17 @@ static int arp_process(struct sk_buff *skb)
addr_type = rt->rt_type;
if (addr_type == RTN_LOCAL) {
- int dont_send = 0;
+ int dont_send;
- if (!dont_send)
- dont_send |= arp_ignore(in_dev,sip,tip);
+ dont_send = arp_ignore(in_dev, sip, tip);
if (!dont_send && IN_DEV_ARPFILTER(in_dev))
- dont_send |= arp_filter(sip,tip,dev);
+ dont_send |= arp_filter(sip, tip, dev);
if (!dont_send) {
n = neigh_event_ns(&arp_tbl, sha, &sip, dev);
if (n) {
- arp_send(ARPOP_REPLY,ETH_P_ARP,sip,dev,tip,sha,dev->dev_addr,sha);
+ arp_send(ARPOP_REPLY, ETH_P_ARP, sip,
+ dev, tip, sha, dev->dev_addr,
+ sha);
neigh_release(n);
}
}
@@ -887,8 +899,7 @@ static int arp_process(struct sk_buff *skb)
if (addr_type == RTN_UNICAST &&
(arp_fwd_proxy(in_dev, dev, rt) ||
arp_fwd_pvlan(in_dev, dev, rt, sip, tip) ||
- pneigh_lookup(&arp_tbl, net, &tip, dev, 0)))
- {
+ pneigh_lookup(&arp_tbl, net, &tip, dev, 0))) {
n = neigh_event_ns(&arp_tbl, sha, &sip, dev);
if (n)
neigh_release(n);
@@ -896,9 +907,12 @@ static int arp_process(struct sk_buff *skb)
if (NEIGH_CB(skb)->flags & LOCALLY_ENQUEUED ||
skb->pkt_type == PACKET_HOST ||
in_dev->arp_parms->proxy_delay == 0) {
- arp_send(ARPOP_REPLY,ETH_P_ARP,sip,dev,tip,sha,dev->dev_addr,sha);
+ arp_send(ARPOP_REPLY, ETH_P_ARP, sip,
+ dev, tip, sha, dev->dev_addr,
+ sha);
} else {
- pneigh_enqueue(&arp_tbl, in_dev->arp_parms, skb);
+ pneigh_enqueue(&arp_tbl,
+ in_dev->arp_parms, skb);
return 0;
}
goto out;
@@ -939,7 +953,8 @@ static int arp_process(struct sk_buff *skb)
if (arp->ar_op != htons(ARPOP_REPLY) ||
skb->pkt_type != PACKET_HOST)
state = NUD_STALE;
- neigh_update(n, sha, state, override ? NEIGH_UPDATE_F_OVERRIDE : 0);
+ neigh_update(n, sha, state,
+ override ? NEIGH_UPDATE_F_OVERRIDE : 0);
neigh_release(n);
}
@@ -975,7 +990,8 @@ static int arp_rcv(struct sk_buff *skb, struct net_device *dev,
arp->ar_pln != 4)
goto freeskb;
- if ((skb = skb_share_check(skb, GFP_ATOMIC)) == NULL)
+ skb = skb_share_check(skb, GFP_ATOMIC);
+ if (skb == NULL)
goto out_of_mem;
memset(NEIGH_CB(skb), 0, sizeof(struct neighbour_cb));
@@ -1019,7 +1035,7 @@ static int arp_req_set_public(struct net *net, struct arpreq *r,
return -EINVAL;
if (!dev && (r->arp_flags & ATF_COM)) {
dev = dev_getbyhwaddr(net, r->arp_ha.sa_family,
- r->arp_ha.sa_data);
+ r->arp_ha.sa_data);
if (!dev)
return -ENODEV;
}
@@ -1033,7 +1049,7 @@ static int arp_req_set_public(struct net *net, struct arpreq *r,
}
static int arp_req_set(struct net *net, struct arpreq *r,
- struct net_device * dev)
+ struct net_device *dev)
{
__be32 ip;
struct neighbour *neigh;
@@ -1046,10 +1062,11 @@ static int arp_req_set(struct net *net, struct arpreq *r,
if (r->arp_flags & ATF_PERM)
r->arp_flags |= ATF_COM;
if (dev == NULL) {
- struct flowi fl = { .nl_u = { .ip4_u = { .daddr = ip,
- .tos = RTO_ONLINK } } };
- struct rtable * rt;
- if ((err = ip_route_output_key(net, &rt, &fl)) != 0)
+ struct flowi fl = { .nl_u.ip4_u = { .daddr = ip,
+ .tos = RTO_ONLINK } };
+ struct rtable *rt;
+ err = ip_route_output_key(net, &rt, &fl);
+ if (err != 0)
return err;
dev = rt->dst.dev;
ip_rt_put(rt);
@@ -1083,9 +1100,9 @@ static int arp_req_set(struct net *net, struct arpreq *r,
unsigned state = NUD_STALE;
if (r->arp_flags & ATF_PERM)
state = NUD_PERMANENT;
- err = neigh_update(neigh, (r->arp_flags&ATF_COM) ?
+ err = neigh_update(neigh, (r->arp_flags & ATF_COM) ?
r->arp_ha.sa_data : NULL, state,
- NEIGH_UPDATE_F_OVERRIDE|
+ NEIGH_UPDATE_F_OVERRIDE |
NEIGH_UPDATE_F_ADMIN);
neigh_release(neigh);
}
@@ -1094,12 +1111,12 @@ static int arp_req_set(struct net *net, struct arpreq *r,
static unsigned arp_state_to_flags(struct neighbour *neigh)
{
- unsigned flags = 0;
if (neigh->nud_state&NUD_PERMANENT)
- flags = ATF_PERM|ATF_COM;
+ return ATF_PERM | ATF_COM;
else if (neigh->nud_state&NUD_VALID)
- flags = ATF_COM;
- return flags;
+ return ATF_COM;
+ else
+ return 0;
}
/*
@@ -1142,7 +1159,7 @@ static int arp_req_delete_public(struct net *net, struct arpreq *r,
}
static int arp_req_delete(struct net *net, struct arpreq *r,
- struct net_device * dev)
+ struct net_device *dev)
{
int err;
__be32 ip;
@@ -1153,10 +1170,11 @@ static int arp_req_delete(struct net *net, struct arpreq *r,
ip = ((struct sockaddr_in *)&r->arp_pa)->sin_addr.s_addr;
if (dev == NULL) {
- struct flowi fl = { .nl_u = { .ip4_u = { .daddr = ip,
- .tos = RTO_ONLINK } } };
- struct rtable * rt;
- if ((err = ip_route_output_key(net, &rt, &fl)) != 0)
+ struct flowi fl = { .nl_u.ip4_u = { .daddr = ip,
+ .tos = RTO_ONLINK } };
+ struct rtable *rt;
+ err = ip_route_output_key(net, &rt, &fl);
+ if (err != 0)
return err;
dev = rt->dst.dev;
ip_rt_put(rt);
@@ -1166,7 +1184,7 @@ static int arp_req_delete(struct net *net, struct arpreq *r,
err = -ENXIO;
neigh = neigh_lookup(&arp_tbl, &ip, dev);
if (neigh) {
- if (neigh->nud_state&~NUD_NOARP)
+ if (neigh->nud_state & ~NUD_NOARP)
err = neigh_update(neigh, NULL, NUD_FAILED,
NEIGH_UPDATE_F_OVERRIDE|
NEIGH_UPDATE_F_ADMIN);
@@ -1186,24 +1204,24 @@ int arp_ioctl(struct net *net, unsigned int cmd, void __user *arg)
struct net_device *dev = NULL;
switch (cmd) {
- case SIOCDARP:
- case SIOCSARP:
- if (!capable(CAP_NET_ADMIN))
- return -EPERM;
- case SIOCGARP:
- err = copy_from_user(&r, arg, sizeof(struct arpreq));
- if (err)
- return -EFAULT;
- break;
- default:
- return -EINVAL;
+ case SIOCDARP:
+ case SIOCSARP:
+ if (!capable(CAP_NET_ADMIN))
+ return -EPERM;
+ case SIOCGARP:
+ err = copy_from_user(&r, arg, sizeof(struct arpreq));
+ if (err)
+ return -EFAULT;
+ break;
+ default:
+ return -EINVAL;
}
if (r.arp_pa.sa_family != AF_INET)
return -EPFNOSUPPORT;
if (!(r.arp_flags & ATF_PUBL) &&
- (r.arp_flags & (ATF_NETMASK|ATF_DONTPUB)))
+ (r.arp_flags & (ATF_NETMASK | ATF_DONTPUB)))
return -EINVAL;
if (!(r.arp_flags & ATF_NETMASK))
((struct sockaddr_in *)&r.arp_netmask)->sin_addr.s_addr =
@@ -1211,7 +1229,8 @@ int arp_ioctl(struct net *net, unsigned int cmd, void __user *arg)
rtnl_lock();
if (r.arp_dev[0]) {
err = -ENODEV;
- if ((dev = __dev_get_by_name(net, r.arp_dev)) == NULL)
+ dev = __dev_get_by_name(net, r.arp_dev);
+ if (dev == NULL)
goto out;
/* Mmmm... It is wrong... ARPHRD_NETROM==0 */
@@ -1243,7 +1262,8 @@ out:
return err;
}
-static int arp_netdev_event(struct notifier_block *this, unsigned long event, void *ptr)
+static int arp_netdev_event(struct notifier_block *this, unsigned long event,
+ void *ptr)
{
struct net_device *dev = ptr;
@@ -1311,12 +1331,13 @@ static char *ax2asc2(ax25_address *a, char *buf)
for (n = 0, s = buf; n < 6; n++) {
c = (a->ax25_call[n] >> 1) & 0x7F;
- if (c != ' ') *s++ = c;
+ if (c != ' ')
+ *s++ = c;
}
*s++ = '-';
-
- if ((n = ((a->ax25_call[6] >> 1) & 0x0F)) > 9) {
+ n = (a->ax25_call[6] >> 1) & 0x0F;
+ if (n > 9) {
*s++ = '1';
n -= 10;
}
@@ -1325,10 +1346,9 @@ static char *ax2asc2(ax25_address *a, char *buf)
*s++ = '\0';
if (*buf == '\0' || *buf == '-')
- return "*";
+ return "*";
return buf;
-
}
#endif /* CONFIG_AX25 */
@@ -1408,10 +1428,10 @@ static void *arp_seq_start(struct seq_file *seq, loff_t *pos)
/* ------------------------------------------------------------------------ */
static const struct seq_operations arp_seq_ops = {
- .start = arp_seq_start,
- .next = neigh_seq_next,
- .stop = neigh_seq_stop,
- .show = arp_seq_show,
+ .start = arp_seq_start,
+ .next = neigh_seq_next,
+ .stop = neigh_seq_stop,
+ .show = arp_seq_show,
};
static int arp_seq_open(struct inode *inode, struct file *file)
diff --git a/net/ipv4/gre.c b/net/ipv4/gre.c
new file mode 100644
index 000000000000..b546736da2e1
--- /dev/null
+++ b/net/ipv4/gre.c
@@ -0,0 +1,151 @@
+/*
+ * GRE over IPv4 demultiplexer driver
+ *
+ * Authors: Dmitry Kozlov (xeb@mail.ru)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ */
+
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/kmod.h>
+#include <linux/skbuff.h>
+#include <linux/in.h>
+#include <linux/netdevice.h>
+#include <linux/version.h>
+#include <linux/spinlock.h>
+#include <net/protocol.h>
+#include <net/gre.h>
+
+
+const struct gre_protocol *gre_proto[GREPROTO_MAX] __read_mostly;
+static DEFINE_SPINLOCK(gre_proto_lock);
+
+int gre_add_protocol(const struct gre_protocol *proto, u8 version)
+{
+ if (version >= GREPROTO_MAX)
+ goto err_out;
+
+ spin_lock(&gre_proto_lock);
+ if (gre_proto[version])
+ goto err_out_unlock;
+
+ rcu_assign_pointer(gre_proto[version], proto);
+ spin_unlock(&gre_proto_lock);
+ return 0;
+
+err_out_unlock:
+ spin_unlock(&gre_proto_lock);
+err_out:
+ return -1;
+}
+EXPORT_SYMBOL_GPL(gre_add_protocol);
+
+int gre_del_protocol(const struct gre_protocol *proto, u8 version)
+{
+ if (version >= GREPROTO_MAX)
+ goto err_out;
+
+ spin_lock(&gre_proto_lock);
+ if (gre_proto[version] != proto)
+ goto err_out_unlock;
+ rcu_assign_pointer(gre_proto[version], NULL);
+ spin_unlock(&gre_proto_lock);
+ synchronize_rcu();
+ return 0;
+
+err_out_unlock:
+ spin_unlock(&gre_proto_lock);
+err_out:
+ return -1;
+}
+EXPORT_SYMBOL_GPL(gre_del_protocol);
+
+static int gre_rcv(struct sk_buff *skb)
+{
+ const struct gre_protocol *proto;
+ u8 ver;
+ int ret;
+
+ if (!pskb_may_pull(skb, 12))
+ goto drop;
+
+ ver = skb->data[1]&0x7f;
+ if (ver >= GREPROTO_MAX)
+ goto drop;
+
+ rcu_read_lock();
+ proto = rcu_dereference(gre_proto[ver]);
+ if (!proto || !proto->handler)
+ goto drop_unlock;
+ ret = proto->handler(skb);
+ rcu_read_unlock();
+ return ret;
+
+drop_unlock:
+ rcu_read_unlock();
+drop:
+ kfree_skb(skb);
+ return NET_RX_DROP;
+}
+
+static void gre_err(struct sk_buff *skb, u32 info)
+{
+ const struct gre_protocol *proto;
+ u8 ver;
+
+ if (!pskb_may_pull(skb, 12))
+ goto drop;
+
+ ver = skb->data[1]&0x7f;
+ if (ver >= GREPROTO_MAX)
+ goto drop;
+
+ rcu_read_lock();
+ proto = rcu_dereference(gre_proto[ver]);
+ if (!proto || !proto->err_handler)
+ goto drop_unlock;
+ proto->err_handler(skb, info);
+ rcu_read_unlock();
+ return;
+
+drop_unlock:
+ rcu_read_unlock();
+drop:
+ kfree_skb(skb);
+}
+
+static const struct net_protocol net_gre_protocol = {
+ .handler = gre_rcv,
+ .err_handler = gre_err,
+ .netns_ok = 1,
+};
+
+static int __init gre_init(void)
+{
+ pr_info("GRE over IPv4 demultiplexor driver");
+
+ if (inet_add_protocol(&net_gre_protocol, IPPROTO_GRE) < 0) {
+ pr_err("gre: can't add protocol\n");
+ return -EAGAIN;
+ }
+
+ return 0;
+}
+
+static void __exit gre_exit(void)
+{
+ inet_del_protocol(&net_gre_protocol, IPPROTO_GRE);
+}
+
+module_init(gre_init);
+module_exit(gre_exit);
+
+MODULE_DESCRIPTION("GRE over IPv4 demultiplexer driver");
+MODULE_AUTHOR("D. Kozlov (xeb@mail.ru)");
+MODULE_LICENSE("GPL");
+
diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c
index a0d847c7cba5..96bc7f9475a3 100644
--- a/net/ipv4/icmp.c
+++ b/net/ipv4/icmp.c
@@ -379,7 +379,7 @@ static void icmp_reply(struct icmp_bxm *icmp_param, struct sk_buff *skb)
inet->tos = ip_hdr(skb)->tos;
daddr = ipc.addr = rt->rt_src;
ipc.opt = NULL;
- ipc.shtx.flags = 0;
+ ipc.tx_flags = 0;
if (icmp_param->replyopts.optlen) {
ipc.opt = &icmp_param->replyopts;
if (ipc.opt->srr)
@@ -538,7 +538,7 @@ void icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info)
inet_sk(sk)->tos = tos;
ipc.addr = iph->saddr;
ipc.opt = &icmp_param.replyopts;
- ipc.shtx.flags = 0;
+ ipc.tx_flags = 0;
{
struct flowi fl = {
diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c
index b7c41654dde5..f4dc879e258e 100644
--- a/net/ipv4/ip_fragment.c
+++ b/net/ipv4/ip_fragment.c
@@ -542,7 +542,7 @@ static int ip_frag_reasm(struct ipq *qp, struct sk_buff *prev,
/* If the first fragment is fragmented itself, we split
* it to two chunks: the first with data and paged part
* and the second, holding only fragments. */
- if (skb_has_frags(head)) {
+ if (skb_has_frag_list(head)) {
struct sk_buff *clone;
int i, plen = 0;
diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index 945b20a5ad50..85176895495a 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -44,6 +44,7 @@
#include <net/net_namespace.h>
#include <net/netns/generic.h>
#include <net/rtnetlink.h>
+#include <net/gre.h>
#ifdef CONFIG_IPV6
#include <net/ipv6.h>
@@ -1278,10 +1279,9 @@ static void ipgre_fb_tunnel_init(struct net_device *dev)
}
-static const struct net_protocol ipgre_protocol = {
- .handler = ipgre_rcv,
- .err_handler = ipgre_err,
- .netns_ok = 1,
+static const struct gre_protocol ipgre_protocol = {
+ .handler = ipgre_rcv,
+ .err_handler = ipgre_err,
};
static void ipgre_destroy_tunnels(struct ipgre_net *ign, struct list_head *head)
@@ -1663,7 +1663,7 @@ static int __init ipgre_init(void)
if (err < 0)
return err;
- err = inet_add_protocol(&ipgre_protocol, IPPROTO_GRE);
+ err = gre_add_protocol(&ipgre_protocol, GREPROTO_CISCO);
if (err < 0) {
printk(KERN_INFO "ipgre init: can't add protocol\n");
goto add_proto_failed;
@@ -1683,7 +1683,7 @@ out:
tap_ops_failed:
rtnl_link_unregister(&ipgre_link_ops);
rtnl_link_failed:
- inet_del_protocol(&ipgre_protocol, IPPROTO_GRE);
+ gre_del_protocol(&ipgre_protocol, GREPROTO_CISCO);
add_proto_failed:
unregister_pernet_device(&ipgre_net_ops);
goto out;
@@ -1693,7 +1693,7 @@ static void __exit ipgre_fini(void)
{
rtnl_link_unregister(&ipgre_tap_ops);
rtnl_link_unregister(&ipgre_link_ops);
- if (inet_del_protocol(&ipgre_protocol, IPPROTO_GRE) < 0)
+ if (gre_del_protocol(&ipgre_protocol, GREPROTO_CISCO) < 0)
printk(KERN_INFO "ipgre close: can't remove protocol\n");
unregister_pernet_device(&ipgre_net_ops);
}
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 04b69896df5f..e42762023c27 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -487,7 +487,7 @@ int ip_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *))
* LATER: this step can be merged to real generation of fragments,
* we can switch to copy when see the first bad fragment.
*/
- if (skb_has_frags(skb)) {
+ if (skb_has_frag_list(skb)) {
struct sk_buff *frag;
int first_len = skb_pagelen(skb);
int truesizes = 0;
@@ -837,10 +837,9 @@ int ip_append_data(struct sock *sk,
inet->cork.length = 0;
sk->sk_sndmsg_page = NULL;
sk->sk_sndmsg_off = 0;
- if ((exthdrlen = rt->dst.header_len) != 0) {
- length += exthdrlen;
- transhdrlen += exthdrlen;
- }
+ exthdrlen = rt->dst.header_len;
+ length += exthdrlen;
+ transhdrlen += exthdrlen;
} else {
rt = (struct rtable *)inet->cork.dst;
if (inet->cork.flags & IPCORK_OPT)
@@ -953,7 +952,7 @@ alloc_new_skb:
else
/* only the initial fragment is
time stamped */
- ipc->shtx.flags = 0;
+ ipc->tx_flags = 0;
}
if (skb == NULL)
goto error;
@@ -964,7 +963,7 @@ alloc_new_skb:
skb->ip_summed = csummode;
skb->csum = 0;
skb_reserve(skb, hh_len);
- *skb_tx(skb) = ipc->shtx;
+ skb_shinfo(skb)->tx_flags = ipc->tx_flags;
/*
* Find where to start putting bytes.
@@ -1384,7 +1383,7 @@ void ip_send_reply(struct sock *sk, struct sk_buff *skb, struct ip_reply_arg *ar
daddr = ipc.addr = rt->rt_src;
ipc.opt = NULL;
- ipc.shtx.flags = 0;
+ ipc.tx_flags = 0;
if (replyopts.opt.optlen) {
ipc.opt = &replyopts.opt;
diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c
index ec036731a70b..3c6f8f3968a6 100644
--- a/net/ipv4/ipip.c
+++ b/net/ipv4/ipip.c
@@ -744,7 +744,7 @@ static void __net_init ipip_fb_tunnel_init(struct net_device *dev)
ipn->tunnels_wc[0] = tunnel;
}
-static struct xfrm_tunnel ipip_handler = {
+static struct xfrm_tunnel ipip_handler __read_mostly = {
.handler = ipip_rcv,
.err_handler = ipip_err,
.priority = 1,
diff --git a/net/ipv4/netfilter/ipt_CLUSTERIP.c b/net/ipv4/netfilter/ipt_CLUSTERIP.c
index 3a43cf36db87..1e26a4897655 100644
--- a/net/ipv4/netfilter/ipt_CLUSTERIP.c
+++ b/net/ipv4/netfilter/ipt_CLUSTERIP.c
@@ -29,6 +29,7 @@
#include <net/netfilter/nf_conntrack.h>
#include <net/net_namespace.h>
#include <net/checksum.h>
+#include <net/ip.h>
#define CLUSTERIP_VERSION "0.8"
@@ -231,24 +232,22 @@ clusterip_hashfn(const struct sk_buff *skb,
{
const struct iphdr *iph = ip_hdr(skb);
unsigned long hashval;
- u_int16_t sport, dport;
- const u_int16_t *ports;
-
- switch (iph->protocol) {
- case IPPROTO_TCP:
- case IPPROTO_UDP:
- case IPPROTO_UDPLITE:
- case IPPROTO_SCTP:
- case IPPROTO_DCCP:
- case IPPROTO_ICMP:
- ports = (const void *)iph+iph->ihl*4;
- sport = ports[0];
- dport = ports[1];
- break;
- default:
+ u_int16_t sport = 0, dport = 0;
+ int poff;
+
+ poff = proto_ports_offset(iph->protocol);
+ if (poff >= 0) {
+ const u_int16_t *ports;
+ u16 _ports[2];
+
+ ports = skb_header_pointer(skb, iph->ihl * 4 + poff, 4, _ports);
+ if (ports) {
+ sport = ports[0];
+ dport = ports[1];
+ }
+ } else {
if (net_ratelimit())
pr_info("unknown protocol %u\n", iph->protocol);
- sport = dport = 0;
}
switch (config->hash_mode) {
diff --git a/net/ipv4/protocol.c b/net/ipv4/protocol.c
index f2d297351405..65699c24411c 100644
--- a/net/ipv4/protocol.c
+++ b/net/ipv4/protocol.c
@@ -28,8 +28,7 @@
#include <linux/spinlock.h>
#include <net/protocol.h>
-const struct net_protocol *inet_protos[MAX_INET_PROTOS] ____cacheline_aligned_in_smp;
-static DEFINE_SPINLOCK(inet_proto_lock);
+const struct net_protocol *inet_protos[MAX_INET_PROTOS] __read_mostly;
/*
* Add a protocol handler to the hash tables
@@ -37,20 +36,9 @@ static DEFINE_SPINLOCK(inet_proto_lock);
int inet_add_protocol(const struct net_protocol *prot, unsigned char protocol)
{
- int hash, ret;
+ int hash = protocol & (MAX_INET_PROTOS - 1);
- hash = protocol & (MAX_INET_PROTOS - 1);
-
- spin_lock_bh(&inet_proto_lock);
- if (inet_protos[hash]) {
- ret = -1;
- } else {
- inet_protos[hash] = prot;
- ret = 0;
- }
- spin_unlock_bh(&inet_proto_lock);
-
- return ret;
+ return !cmpxchg(&inet_protos[hash], NULL, prot) ? 0 : -1;
}
EXPORT_SYMBOL(inet_add_protocol);
@@ -60,18 +48,9 @@ EXPORT_SYMBOL(inet_add_protocol);
int inet_del_protocol(const struct net_protocol *prot, unsigned char protocol)
{
- int hash, ret;
-
- hash = protocol & (MAX_INET_PROTOS - 1);
+ int ret, hash = protocol & (MAX_INET_PROTOS - 1);
- spin_lock_bh(&inet_proto_lock);
- if (inet_protos[hash] == prot) {
- inet_protos[hash] = NULL;
- ret = 0;
- } else {
- ret = -1;
- }
- spin_unlock_bh(&inet_proto_lock);
+ ret = (cmpxchg(&inet_protos[hash], prot, NULL) == prot) ? 0 : -1;
synchronize_net();
diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c
index 009a7b2aa1ef..1f85ef289895 100644
--- a/net/ipv4/raw.c
+++ b/net/ipv4/raw.c
@@ -505,7 +505,7 @@ static int raw_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
ipc.addr = inet->inet_saddr;
ipc.opt = NULL;
- ipc.shtx.flags = 0;
+ ipc.tx_flags = 0;
ipc.oif = sk->sk_bound_dev_if;
if (msg->msg_controllen) {
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index 6298f75d5e93..e24d48dd99d3 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -1268,18 +1268,11 @@ skip_hashing:
void rt_bind_peer(struct rtable *rt, int create)
{
- static DEFINE_SPINLOCK(rt_peer_lock);
struct inet_peer *peer;
peer = inet_getpeer(rt->rt_dst, create);
- spin_lock_bh(&rt_peer_lock);
- if (rt->peer == NULL) {
- rt->peer = peer;
- peer = NULL;
- }
- spin_unlock_bh(&rt_peer_lock);
- if (peer)
+ if (peer && cmpxchg(&rt->peer, NULL, peer) != NULL)
inet_putpeer(peer);
}
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 3fb1428e526e..3e8a4dbc721b 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -2389,7 +2389,12 @@ static int do_tcp_setsockopt(struct sock *sk, int level,
err = tp->af_specific->md5_parse(sk, optval, optlen);
break;
#endif
-
+ case TCP_USER_TIMEOUT:
+ /* Cap the max timeout in ms TCP will retry/retrans
+ * before giving up and aborting (ETIMEDOUT) a connection.
+ */
+ icsk->icsk_user_timeout = msecs_to_jiffies(val);
+ break;
default:
err = -ENOPROTOOPT;
break;
@@ -2608,6 +2613,10 @@ static int do_tcp_getsockopt(struct sock *sk, int level,
case TCP_THIN_DUPACK:
val = tp->thin_dupack;
break;
+
+ case TCP_USER_TIMEOUT:
+ val = jiffies_to_msecs(icsk->icsk_user_timeout);
+ break;
default:
return -ENOPROTOOPT;
}
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index e663b78a2ef6..1bc87a05c734 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -805,25 +805,12 @@ void tcp_update_metrics(struct sock *sk)
}
}
-/* Numbers are taken from RFC3390.
- *
- * John Heffner states:
- *
- * The RFC specifies a window of no more than 4380 bytes
- * unless 2*MSS > 4380. Reading the pseudocode in the RFC
- * is a bit misleading because they use a clamp at 4380 bytes
- * rather than use a multiplier in the relevant range.
- */
__u32 tcp_init_cwnd(struct tcp_sock *tp, struct dst_entry *dst)
{
__u32 cwnd = (dst ? dst_metric(dst, RTAX_INITCWND) : 0);
- if (!cwnd) {
- if (tp->mss_cache > 1460)
- cwnd = 2;
- else
- cwnd = (tp->mss_cache > 1095) ? 3 : 4;
- }
+ if (!cwnd)
+ cwnd = rfc3390_bytes_to_packets(tp->mss_cache);
return min_t(__u32, cwnd, tp->snd_cwnd_clamp);
}
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 020766292bb0..a0232f3a358b 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -2571,7 +2571,6 @@ struct sk_buff **tcp4_gro_receive(struct sk_buff **head, struct sk_buff *skb)
return tcp_gro_receive(head, skb);
}
-EXPORT_SYMBOL(tcp4_gro_receive);
int tcp4_gro_complete(struct sk_buff *skb)
{
@@ -2584,7 +2583,6 @@ int tcp4_gro_complete(struct sk_buff *skb)
return tcp_gro_complete(skb);
}
-EXPORT_SYMBOL(tcp4_gro_complete);
struct proto tcp_prot = {
.name = "TCP",
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index de3bd8458588..ea09d2fd50c7 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -224,16 +224,10 @@ void tcp_select_initial_window(int __space, __u32 mss,
}
}
- /* Set initial window to value enough for senders,
- * following RFC2414. Senders, not following this RFC,
- * will be satisfied with 2.
- */
+ /* Set initial window to value enough for senders, following RFC5681. */
if (mss > (1 << *rcv_wscale)) {
- int init_cwnd = 4;
- if (mss > 1460 * 3)
- init_cwnd = 2;
- else if (mss > 1460)
- init_cwnd = 3;
+ int init_cwnd = rfc3390_bytes_to_packets(mss);
+
/* when initializing use the value from init_rcv_wnd
* rather than the default from above
*/
@@ -2429,6 +2423,12 @@ struct sk_buff *tcp_make_synack(struct sock *sk, struct dst_entry *dst,
__u8 rcv_wscale;
/* Set this up on the first call only */
req->window_clamp = tp->window_clamp ? : dst_metric(dst, RTAX_WINDOW);
+
+ /* limit the window selection if the user enforce a smaller rx buffer */
+ if (sk->sk_userlocks & SOCK_RCVBUF_LOCK &&
+ (req->window_clamp > tcp_full_space(sk) || req->window_clamp == 0))
+ req->window_clamp = tcp_full_space(sk);
+
/* tcp_full_space because it is guaranteed to be the first packet */
tcp_select_initial_window(tcp_full_space(sk),
mss - (ireq->tstamp_ok ? TCPOLEN_TSTAMP_ALIGNED : 0),
@@ -2555,6 +2555,11 @@ static void tcp_connect_init(struct sock *sk)
tcp_initialize_rcv_mss(sk);
+ /* limit the window selection if the user enforce a smaller rx buffer */
+ if (sk->sk_userlocks & SOCK_RCVBUF_LOCK &&
+ (tp->window_clamp > tcp_full_space(sk) || tp->window_clamp == 0))
+ tp->window_clamp = tcp_full_space(sk);
+
tcp_select_initial_window(tcp_full_space(sk),
tp->advmss - (tp->rx_opt.ts_recent_stamp ? tp->tcp_header_len - sizeof(struct tcphdr) : 0),
&tp->rcv_wnd,
diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c
index c35b469e851c..baea4a129022 100644
--- a/net/ipv4/tcp_timer.c
+++ b/net/ipv4/tcp_timer.c
@@ -138,10 +138,10 @@ static void tcp_mtu_probing(struct inet_connection_sock *icsk, struct sock *sk)
* retransmissions with an initial RTO of TCP_RTO_MIN.
*/
static bool retransmits_timed_out(struct sock *sk,
- unsigned int boundary)
+ unsigned int boundary,
+ unsigned int timeout)
{
- unsigned int timeout, linear_backoff_thresh;
- unsigned int start_ts;
+ unsigned int linear_backoff_thresh, start_ts;
if (!inet_csk(sk)->icsk_retransmits)
return false;
@@ -151,14 +151,15 @@ static bool retransmits_timed_out(struct sock *sk,
else
start_ts = tcp_sk(sk)->retrans_stamp;
- linear_backoff_thresh = ilog2(TCP_RTO_MAX/TCP_RTO_MIN);
-
- if (boundary <= linear_backoff_thresh)
- timeout = ((2 << boundary) - 1) * TCP_RTO_MIN;
- else
- timeout = ((2 << linear_backoff_thresh) - 1) * TCP_RTO_MIN +
- (boundary - linear_backoff_thresh) * TCP_RTO_MAX;
+ if (likely(timeout == 0)) {
+ linear_backoff_thresh = ilog2(TCP_RTO_MAX/TCP_RTO_MIN);
+ if (boundary <= linear_backoff_thresh)
+ timeout = ((2 << boundary) - 1) * TCP_RTO_MIN;
+ else
+ timeout = ((2 << linear_backoff_thresh) - 1) * TCP_RTO_MIN +
+ (boundary - linear_backoff_thresh) * TCP_RTO_MAX;
+ }
return (tcp_time_stamp - start_ts) >= timeout;
}
@@ -174,7 +175,7 @@ static int tcp_write_timeout(struct sock *sk)
dst_negative_advice(sk);
retry_until = icsk->icsk_syn_retries ? : sysctl_tcp_syn_retries;
} else {
- if (retransmits_timed_out(sk, sysctl_tcp_retries1)) {
+ if (retransmits_timed_out(sk, sysctl_tcp_retries1, 0)) {
/* Black hole detection */
tcp_mtu_probing(icsk, sk);
@@ -187,14 +188,16 @@ static int tcp_write_timeout(struct sock *sk)
retry_until = tcp_orphan_retries(sk, alive);
do_reset = alive ||
- !retransmits_timed_out(sk, retry_until);
+ !retransmits_timed_out(sk, retry_until, 0);
if (tcp_out_of_resources(sk, do_reset))
return 1;
}
}
- if (retransmits_timed_out(sk, retry_until)) {
+ if (retransmits_timed_out(sk, retry_until,
+ (1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV) ? 0 :
+ icsk->icsk_user_timeout)) {
/* Has it gone just too far? */
tcp_write_err(sk);
return 1;
@@ -436,7 +439,7 @@ out_reset_timer:
icsk->icsk_rto = min(icsk->icsk_rto << 1, TCP_RTO_MAX);
}
inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS, icsk->icsk_rto, TCP_RTO_MAX);
- if (retransmits_timed_out(sk, sysctl_tcp_retries1 + 1))
+ if (retransmits_timed_out(sk, sysctl_tcp_retries1 + 1, 0))
__sk_dst_reset(sk);
out:;
@@ -556,7 +559,14 @@ static void tcp_keepalive_timer (unsigned long data)
elapsed = keepalive_time_elapsed(tp);
if (elapsed >= keepalive_time_when(tp)) {
- if (icsk->icsk_probes_out >= keepalive_probes(tp)) {
+ /* If the TCP_USER_TIMEOUT option is enabled, use that
+ * to determine when to timeout instead.
+ */
+ if ((icsk->icsk_user_timeout != 0 &&
+ elapsed >= icsk->icsk_user_timeout &&
+ icsk->icsk_probes_out > 0) ||
+ (icsk->icsk_user_timeout == 0 &&
+ icsk->icsk_probes_out >= keepalive_probes(tp))) {
tcp_send_active_reset(sk, GFP_ATOMIC);
tcp_write_err(sk);
goto out;
diff --git a/net/ipv4/tunnel4.c b/net/ipv4/tunnel4.c
index 59186ca7808a..9a17bd2a0a37 100644
--- a/net/ipv4/tunnel4.c
+++ b/net/ipv4/tunnel4.c
@@ -14,8 +14,8 @@
#include <net/protocol.h>
#include <net/xfrm.h>
-static struct xfrm_tunnel *tunnel4_handlers;
-static struct xfrm_tunnel *tunnel64_handlers;
+static struct xfrm_tunnel *tunnel4_handlers __read_mostly;
+static struct xfrm_tunnel *tunnel64_handlers __read_mostly;
static DEFINE_MUTEX(tunnel4_mutex);
static inline struct xfrm_tunnel **fam_handlers(unsigned short family)
@@ -39,7 +39,7 @@ int xfrm4_tunnel_register(struct xfrm_tunnel *handler, unsigned short family)
}
handler->next = *pprev;
- *pprev = handler;
+ rcu_assign_pointer(*pprev, handler);
ret = 0;
@@ -73,6 +73,11 @@ int xfrm4_tunnel_deregister(struct xfrm_tunnel *handler, unsigned short family)
}
EXPORT_SYMBOL(xfrm4_tunnel_deregister);
+#define for_each_tunnel_rcu(head, handler) \
+ for (handler = rcu_dereference(head); \
+ handler != NULL; \
+ handler = rcu_dereference(handler->next)) \
+
static int tunnel4_rcv(struct sk_buff *skb)
{
struct xfrm_tunnel *handler;
@@ -80,7 +85,7 @@ static int tunnel4_rcv(struct sk_buff *skb)
if (!pskb_may_pull(skb, sizeof(struct iphdr)))
goto drop;
- for (handler = tunnel4_handlers; handler; handler = handler->next)
+ for_each_tunnel_rcu(tunnel4_handlers, handler)
if (!handler->handler(skb))
return 0;
@@ -99,7 +104,7 @@ static int tunnel64_rcv(struct sk_buff *skb)
if (!pskb_may_pull(skb, sizeof(struct ipv6hdr)))
goto drop;
- for (handler = tunnel64_handlers; handler; handler = handler->next)
+ for_each_tunnel_rcu(tunnel64_handlers, handler)
if (!handler->handler(skb))
return 0;
@@ -115,7 +120,7 @@ static void tunnel4_err(struct sk_buff *skb, u32 info)
{
struct xfrm_tunnel *handler;
- for (handler = tunnel4_handlers; handler; handler = handler->next)
+ for_each_tunnel_rcu(tunnel4_handlers, handler)
if (!handler->err_handler(skb, info))
break;
}
@@ -125,7 +130,7 @@ static void tunnel64_err(struct sk_buff *skb, u32 info)
{
struct xfrm_tunnel *handler;
- for (handler = tunnel64_handlers; handler; handler = handler->next)
+ for_each_tunnel_rcu(tunnel64_handlers, handler)
if (!handler->err_handler(skb, info))
break;
}
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index fb23c2e63b52..b3f7e8cf18ac 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -797,7 +797,7 @@ int udp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
return -EOPNOTSUPP;
ipc.opt = NULL;
- ipc.shtx.flags = 0;
+ ipc.tx_flags = 0;
if (up->pending) {
/*
@@ -845,7 +845,7 @@ int udp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
ipc.addr = inet->inet_saddr;
ipc.oif = sk->sk_bound_dev_if;
- err = sock_tx_timestamp(msg, sk, &ipc.shtx);
+ err = sock_tx_timestamp(sk, &ipc.tx_flags);
if (err)
return err;
if (msg->msg_controllen) {
diff --git a/net/ipv4/xfrm4_tunnel.c b/net/ipv4/xfrm4_tunnel.c
index 41f5982d2087..82806455e859 100644
--- a/net/ipv4/xfrm4_tunnel.c
+++ b/net/ipv4/xfrm4_tunnel.c
@@ -58,14 +58,14 @@ static int xfrm_tunnel_err(struct sk_buff *skb, u32 info)
return -ENOENT;
}
-static struct xfrm_tunnel xfrm_tunnel_handler = {
+static struct xfrm_tunnel xfrm_tunnel_handler __read_mostly = {
.handler = xfrm_tunnel_rcv,
.err_handler = xfrm_tunnel_err,
.priority = 2,
};
#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE)
-static struct xfrm_tunnel xfrm64_tunnel_handler = {
+static struct xfrm_tunnel xfrm64_tunnel_handler __read_mostly = {
.handler = xfrm_tunnel_rcv,
.err_handler = xfrm_tunnel_err,
.priority = 2,
OpenPOWER on IntegriCloud