summaryrefslogtreecommitdiff
path: root/net/ipv4
diff options
context:
space:
mode:
Diffstat (limited to 'net/ipv4')
-rw-r--r--net/ipv4/cipso_ipv4.c47
-rw-r--r--net/ipv4/fib_frontend.c5
-rw-r--r--net/ipv4/inetpeer.c29
-rw-r--r--net/ipv4/ip_gre.c4
-rw-r--r--net/ipv4/ip_options.c2
-rw-r--r--net/ipv4/ipconfig.c2
-rw-r--r--net/ipv4/ipvs/ip_vs_ftp.c2
-rw-r--r--net/ipv4/ipvs/ip_vs_proto_tcp.c2
-rw-r--r--net/ipv4/ipvs/ip_vs_proto_udp.c8
-rw-r--r--net/ipv4/netfilter/arp_tables.c27
-rw-r--r--net/ipv4/netfilter/ip_conntrack_netlink.c72
-rw-r--r--net/ipv4/netfilter/ip_queue.c7
-rw-r--r--net/ipv4/netfilter/ip_tables.c70
-rw-r--r--net/ipv4/netfilter/ipt_ECN.c6
-rw-r--r--net/ipv4/netfilter/ipt_TOS.c6
-rw-r--r--net/ipv4/raw.c17
-rw-r--r--net/ipv4/route.c12
-rw-r--r--net/ipv4/sysctl_net_ipv4.c7
-rw-r--r--net/ipv4/tcp.c11
-rw-r--r--net/ipv4/tcp_cong.c8
-rw-r--r--net/ipv4/tcp_cubic.c6
-rw-r--r--net/ipv4/tcp_htcp.c2
-rw-r--r--net/ipv4/tcp_ipv4.c20
-rw-r--r--net/ipv4/tcp_output.c51
-rw-r--r--net/ipv4/xfrm4_policy.c2
25 files changed, 210 insertions, 215 deletions
diff --git a/net/ipv4/cipso_ipv4.c b/net/ipv4/cipso_ipv4.c
index a8e2e87..6460233 100644
--- a/net/ipv4/cipso_ipv4.c
+++ b/net/ipv4/cipso_ipv4.c
@@ -43,6 +43,7 @@
#include <net/tcp.h>
#include <net/netlabel.h>
#include <net/cipso_ipv4.h>
+#include <asm/atomic.h>
#include <asm/bug.h>
struct cipso_v4_domhsh_entry {
@@ -79,7 +80,7 @@ struct cipso_v4_map_cache_entry {
unsigned char *key;
size_t key_len;
- struct netlbl_lsm_cache lsm_data;
+ struct netlbl_lsm_cache *lsm_data;
u32 activity;
struct list_head list;
@@ -188,13 +189,14 @@ static void cipso_v4_doi_domhsh_free(struct rcu_head *entry)
* @entry: the entry to free
*
* Description:
- * This function frees the memory associated with a cache entry.
+ * This function frees the memory associated with a cache entry including the
+ * LSM cache data if there are no longer any users, i.e. reference count == 0.
*
*/
static void cipso_v4_cache_entry_free(struct cipso_v4_map_cache_entry *entry)
{
- if (entry->lsm_data.free)
- entry->lsm_data.free(entry->lsm_data.data);
+ if (entry->lsm_data)
+ netlbl_secattr_cache_free(entry->lsm_data);
kfree(entry->key);
kfree(entry);
}
@@ -315,8 +317,8 @@ static int cipso_v4_cache_check(const unsigned char *key,
entry->key_len == key_len &&
memcmp(entry->key, key, key_len) == 0) {
entry->activity += 1;
- secattr->cache.free = entry->lsm_data.free;
- secattr->cache.data = entry->lsm_data.data;
+ atomic_inc(&entry->lsm_data->refcount);
+ secattr->cache = entry->lsm_data;
if (prev_entry == NULL) {
spin_unlock_bh(&cipso_v4_cache[bkt].lock);
return 0;
@@ -383,8 +385,8 @@ int cipso_v4_cache_add(const struct sk_buff *skb,
memcpy(entry->key, cipso_ptr, cipso_ptr_len);
entry->key_len = cipso_ptr_len;
entry->hash = cipso_v4_map_cache_hash(cipso_ptr, cipso_ptr_len);
- entry->lsm_data.free = secattr->cache.free;
- entry->lsm_data.data = secattr->cache.data;
+ atomic_inc(&secattr->cache->refcount);
+ entry->lsm_data = secattr->cache;
bkt = entry->hash & (CIPSO_V4_CACHE_BUCKETBITS - 1);
spin_lock_bh(&cipso_v4_cache[bkt].lock);
@@ -771,13 +773,15 @@ static int cipso_v4_map_cat_rbm_valid(const struct cipso_v4_doi *doi_def,
{
int cat = -1;
u32 bitmap_len_bits = bitmap_len * 8;
- u32 cipso_cat_size = doi_def->map.std->cat.cipso_size;
- u32 *cipso_array = doi_def->map.std->cat.cipso;
+ u32 cipso_cat_size;
+ u32 *cipso_array;
switch (doi_def->type) {
case CIPSO_V4_MAP_PASS:
return 0;
case CIPSO_V4_MAP_STD:
+ cipso_cat_size = doi_def->map.std->cat.cipso_size;
+ cipso_array = doi_def->map.std->cat.cipso;
for (;;) {
cat = cipso_v4_bitmap_walk(bitmap,
bitmap_len_bits,
@@ -823,19 +827,21 @@ static int cipso_v4_map_cat_rbm_hton(const struct cipso_v4_doi *doi_def,
u32 net_spot_max = 0;
u32 host_clen_bits = host_cat_len * 8;
u32 net_clen_bits = net_cat_len * 8;
- u32 host_cat_size = doi_def->map.std->cat.local_size;
- u32 *host_cat_array = doi_def->map.std->cat.local;
+ u32 host_cat_size;
+ u32 *host_cat_array;
switch (doi_def->type) {
case CIPSO_V4_MAP_PASS:
- net_spot_max = host_cat_len - 1;
- while (net_spot_max > 0 && host_cat[net_spot_max] == 0)
+ net_spot_max = host_cat_len;
+ while (net_spot_max > 0 && host_cat[net_spot_max - 1] == 0)
net_spot_max--;
if (net_spot_max > net_cat_len)
return -EINVAL;
memcpy(net_cat, host_cat, net_spot_max);
return net_spot_max;
case CIPSO_V4_MAP_STD:
+ host_cat_size = doi_def->map.std->cat.local_size;
+ host_cat_array = doi_def->map.std->cat.local;
for (;;) {
host_spot = cipso_v4_bitmap_walk(host_cat,
host_clen_bits,
@@ -891,8 +897,8 @@ static int cipso_v4_map_cat_rbm_ntoh(const struct cipso_v4_doi *doi_def,
int net_spot = -1;
u32 net_clen_bits = net_cat_len * 8;
u32 host_clen_bits = host_cat_len * 8;
- u32 net_cat_size = doi_def->map.std->cat.cipso_size;
- u32 *net_cat_array = doi_def->map.std->cat.cipso;
+ u32 net_cat_size;
+ u32 *net_cat_array;
switch (doi_def->type) {
case CIPSO_V4_MAP_PASS:
@@ -901,6 +907,8 @@ static int cipso_v4_map_cat_rbm_ntoh(const struct cipso_v4_doi *doi_def,
memcpy(host_cat, net_cat, net_cat_len);
return net_cat_len;
case CIPSO_V4_MAP_STD:
+ net_cat_size = doi_def->map.std->cat.cipso_size;
+ net_cat_array = doi_def->map.std->cat.cipso;
for (;;) {
net_spot = cipso_v4_bitmap_walk(net_cat,
net_clen_bits,
@@ -1299,7 +1307,8 @@ int cipso_v4_socket_setattr(const struct socket *sock,
/* We can't use ip_options_get() directly because it makes a call to
* ip_options_get_alloc() which allocates memory with GFP_KERNEL and
- * we can't block here. */
+ * we won't always have CAP_NET_RAW even though we _always_ want to
+ * set the IPOPT_CIPSO option. */
opt_len = (buf_len + 3) & ~3;
opt = kzalloc(sizeof(*opt) + opt_len, GFP_ATOMIC);
if (opt == NULL) {
@@ -1309,11 +1318,9 @@ int cipso_v4_socket_setattr(const struct socket *sock,
memcpy(opt->__data, buf, buf_len);
opt->optlen = opt_len;
opt->is_data = 1;
+ opt->cipso = sizeof(struct iphdr);
kfree(buf);
buf = NULL;
- ret_val = ip_options_compile(opt, NULL);
- if (ret_val != 0)
- goto socket_setattr_failure;
sk_inet = inet_sk(sk);
if (sk_inet->is_icsk) {
diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index 9c399a7..af0190d 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -482,9 +482,7 @@ static int rtm_to_fib_config(struct sk_buff *skb, struct nlmsghdr *nlh,
memset(cfg, 0, sizeof(*cfg));
rtm = nlmsg_data(nlh);
- cfg->fc_family = rtm->rtm_family;
cfg->fc_dst_len = rtm->rtm_dst_len;
- cfg->fc_src_len = rtm->rtm_src_len;
cfg->fc_tos = rtm->rtm_tos;
cfg->fc_table = rtm->rtm_table;
cfg->fc_protocol = rtm->rtm_protocol;
@@ -501,9 +499,6 @@ static int rtm_to_fib_config(struct sk_buff *skb, struct nlmsghdr *nlh,
case RTA_DST:
cfg->fc_dst = nla_get_be32(attr);
break;
- case RTA_SRC:
- cfg->fc_src = nla_get_be32(attr);
- break;
case RTA_OIF:
cfg->fc_oif = nla_get_u32(attr);
break;
diff --git a/net/ipv4/inetpeer.c b/net/ipv4/inetpeer.c
index 2b1a54b..f072f38 100644
--- a/net/ipv4/inetpeer.c
+++ b/net/ipv4/inetpeer.c
@@ -94,10 +94,8 @@ int inet_peer_minttl = 120 * HZ; /* TTL under high load: 120 sec */
int inet_peer_maxttl = 10 * 60 * HZ; /* usual time to live: 10 min */
static struct inet_peer *inet_peer_unused_head;
-/* Exported for inet_putpeer inline function. */
-struct inet_peer **inet_peer_unused_tailp = &inet_peer_unused_head;
-DEFINE_SPINLOCK(inet_peer_unused_lock);
-#define PEER_MAX_CLEANUP_WORK 30
+static struct inet_peer **inet_peer_unused_tailp = &inet_peer_unused_head;
+static DEFINE_SPINLOCK(inet_peer_unused_lock);
static void peer_check_expire(unsigned long dummy);
static DEFINE_TIMER(peer_periodic_timer, peer_check_expire, 0, 0);
@@ -340,7 +338,8 @@ static int cleanup_once(unsigned long ttl)
spin_lock_bh(&inet_peer_unused_lock);
p = inet_peer_unused_head;
if (p != NULL) {
- if (time_after(p->dtime + ttl, jiffies)) {
+ __u32 delta = (__u32)jiffies - p->dtime;
+ if (delta < ttl) {
/* Do not prune fresh entries. */
spin_unlock_bh(&inet_peer_unused_lock);
return -1;
@@ -432,7 +431,7 @@ out_free:
/* Called with local BH disabled. */
static void peer_check_expire(unsigned long dummy)
{
- int i;
+ unsigned long now = jiffies;
int ttl;
if (peer_total >= inet_peer_threshold)
@@ -441,7 +440,10 @@ static void peer_check_expire(unsigned long dummy)
ttl = inet_peer_maxttl
- (inet_peer_maxttl - inet_peer_minttl) / HZ *
peer_total / inet_peer_threshold * HZ;
- for (i = 0; i < PEER_MAX_CLEANUP_WORK && !cleanup_once(ttl); i++);
+ while (!cleanup_once(ttl)) {
+ if (jiffies != now)
+ break;
+ }
/* Trigger the timer after inet_peer_gc_mintime .. inet_peer_gc_maxtime
* interval depending on the total number of entries (more entries,
@@ -455,3 +457,16 @@ static void peer_check_expire(unsigned long dummy)
peer_total / inet_peer_threshold * HZ;
add_timer(&peer_periodic_timer);
}
+
+void inet_putpeer(struct inet_peer *p)
+{
+ spin_lock_bh(&inet_peer_unused_lock);
+ if (atomic_dec_and_test(&p->refcnt)) {
+ p->unused_prevp = inet_peer_unused_tailp;
+ p->unused_next = NULL;
+ *inet_peer_unused_tailp = p;
+ inet_peer_unused_tailp = &p->unused_next;
+ p->dtime = (__u32)jiffies;
+ }
+ spin_unlock_bh(&inet_peer_unused_lock);
+}
diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index f5fba05..d5b5dec 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -611,8 +611,8 @@ static int ipgre_rcv(struct sk_buff *skb)
* - When dealing with WCCPv2, Skip extra 4 bytes in GRE header
*/
if (flags == 0 &&
- skb->protocol == __constant_htons(ETH_P_WCCP)) {
- skb->protocol = __constant_htons(ETH_P_IP);
+ skb->protocol == htons(ETH_P_WCCP)) {
+ skb->protocol = htons(ETH_P_IP);
if ((*(h + offset) & 0xF0) != 0x40)
offset += 4;
}
diff --git a/net/ipv4/ip_options.c b/net/ipv4/ip_options.c
index 8dabbfc..9f02917 100644
--- a/net/ipv4/ip_options.c
+++ b/net/ipv4/ip_options.c
@@ -443,7 +443,7 @@ int ip_options_compile(struct ip_options * opt, struct sk_buff * skb)
opt->router_alert = optptr - iph;
break;
case IPOPT_CIPSO:
- if (opt->cipso) {
+ if ((!skb && !capable(CAP_NET_RAW)) || opt->cipso) {
pp_ptr = optptr;
goto error;
}
diff --git a/net/ipv4/ipconfig.c b/net/ipv4/ipconfig.c
index f8ce847..955a07a 100644
--- a/net/ipv4/ipconfig.c
+++ b/net/ipv4/ipconfig.c
@@ -420,7 +420,7 @@ ic_rarp_recv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt
{
struct arphdr *rarp;
unsigned char *rarp_ptr;
- unsigned long sip, tip;
+ u32 sip, tip;
unsigned char *sha, *tha; /* s for "source", t for "target" */
struct ic_device *d;
diff --git a/net/ipv4/ipvs/ip_vs_ftp.c b/net/ipv4/ipvs/ip_vs_ftp.c
index 6d398f1..687c1de 100644
--- a/net/ipv4/ipvs/ip_vs_ftp.c
+++ b/net/ipv4/ipvs/ip_vs_ftp.c
@@ -200,7 +200,7 @@ static int ip_vs_ftp_out(struct ip_vs_app *app, struct ip_vs_conn *cp,
from = n_cp->vaddr;
port = n_cp->vport;
sprintf(buf,"%d,%d,%d,%d,%d,%d", NIPQUAD(from),
- ntohs(port)&255, (ntohs(port)>>8)&255);
+ (ntohs(port)>>8)&255, ntohs(port)&255);
buf_len = strlen(buf);
/*
diff --git a/net/ipv4/ipvs/ip_vs_proto_tcp.c b/net/ipv4/ipvs/ip_vs_proto_tcp.c
index bfe779e..6ff05c3 100644
--- a/net/ipv4/ipvs/ip_vs_proto_tcp.c
+++ b/net/ipv4/ipvs/ip_vs_proto_tcp.c
@@ -117,7 +117,7 @@ tcp_fast_csum_update(struct tcphdr *tcph, __be32 oldip, __be32 newip,
{
tcph->check =
ip_vs_check_diff(~oldip, newip,
- ip_vs_check_diff(oldport ^ htonl(0xFFFF),
+ ip_vs_check_diff(oldport ^ htons(0xFFFF),
newport, tcph->check));
}
diff --git a/net/ipv4/ipvs/ip_vs_proto_udp.c b/net/ipv4/ipvs/ip_vs_proto_udp.c
index 54aa760..691c8b6 100644
--- a/net/ipv4/ipvs/ip_vs_proto_udp.c
+++ b/net/ipv4/ipvs/ip_vs_proto_udp.c
@@ -122,10 +122,10 @@ udp_fast_csum_update(struct udphdr *uhdr, __be32 oldip, __be32 newip,
{
uhdr->check =
ip_vs_check_diff(~oldip, newip,
- ip_vs_check_diff(oldport ^ htonl(0xFFFF),
+ ip_vs_check_diff(oldport ^ htons(0xFFFF),
newport, uhdr->check));
if (!uhdr->check)
- uhdr->check = htonl(0xFFFF);
+ uhdr->check = -1;
}
static int
@@ -173,7 +173,7 @@ udp_snat_handler(struct sk_buff **pskb,
cp->protocol,
(*pskb)->csum);
if (udph->check == 0)
- udph->check = htonl(0xFFFF);
+ udph->check = -1;
IP_VS_DBG(11, "O-pkt: %s O-csum=%d (+%zd)\n",
pp->name, udph->check,
(char*)&(udph->check) - (char*)udph);
@@ -228,7 +228,7 @@ udp_dnat_handler(struct sk_buff **pskb,
cp->protocol,
(*pskb)->csum);
if (udph->check == 0)
- udph->check = 0xFFFF;
+ udph->check = -1;
(*pskb)->ip_summed = CHECKSUM_UNNECESSARY;
}
return 1;
diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c
index 17e1a68..413c2d0a 100644
--- a/net/ipv4/netfilter/arp_tables.c
+++ b/net/ipv4/netfilter/arp_tables.c
@@ -466,7 +466,13 @@ static inline int check_entry(struct arpt_entry *e, const char *name, unsigned i
return -EINVAL;
}
+ if (e->target_offset + sizeof(struct arpt_entry_target) > e->next_offset)
+ return -EINVAL;
+
t = arpt_get_target(e);
+ if (e->target_offset + t->u.target_size > e->next_offset)
+ return -EINVAL;
+
target = try_then_request_module(xt_find_target(NF_ARP, t->u.user.name,
t->u.user.revision),
"arpt_%s", t->u.user.name);
@@ -621,20 +627,18 @@ static int translate_table(const char *name,
}
}
- if (!mark_source_chains(newinfo, valid_hooks, entry0)) {
- duprintf("Looping hook\n");
- return -ELOOP;
- }
-
/* Finally, each sanity check must pass */
i = 0;
ret = ARPT_ENTRY_ITERATE(entry0, newinfo->size,
check_entry, name, size, &i);
- if (ret != 0) {
- ARPT_ENTRY_ITERATE(entry0, newinfo->size,
- cleanup_entry, &i);
- return ret;
+ if (ret != 0)
+ goto cleanup;
+
+ ret = -ELOOP;
+ if (!mark_source_chains(newinfo, valid_hooks, entry0)) {
+ duprintf("Looping hook\n");
+ goto cleanup;
}
/* And one copy for every other CPU */
@@ -643,6 +647,9 @@ static int translate_table(const char *name,
memcpy(newinfo->entries[i], entry0, newinfo->size);
}
+ return 0;
+cleanup:
+ ARPT_ENTRY_ITERATE(entry0, newinfo->size, cleanup_entry, &i);
return ret;
}
@@ -1196,6 +1203,8 @@ err1:
static void __exit arp_tables_fini(void)
{
nf_unregister_sockopt(&arpt_sockopts);
+ xt_unregister_target(&arpt_error_target);
+ xt_unregister_target(&arpt_standard_target);
xt_proto_fini(NF_ARP);
}
diff --git a/net/ipv4/netfilter/ip_conntrack_netlink.c b/net/ipv4/netfilter/ip_conntrack_netlink.c
index 53b6dff..262d0d4 100644
--- a/net/ipv4/netfilter/ip_conntrack_netlink.c
+++ b/net/ipv4/netfilter/ip_conntrack_netlink.c
@@ -44,13 +44,6 @@ MODULE_LICENSE("GPL");
static char __initdata version[] = "0.90";
-#if 0
-#define DEBUGP printk
-#else
-#define DEBUGP(format, args...)
-#endif
-
-
static inline int
ctnetlink_dump_tuples_proto(struct sk_buff *skb,
const struct ip_conntrack_tuple *tuple,
@@ -398,7 +391,6 @@ nfattr_failure:
static int ctnetlink_done(struct netlink_callback *cb)
{
- DEBUGP("entered %s\n", __FUNCTION__);
if (cb->args[1])
ip_conntrack_put((struct ip_conntrack *)cb->args[1]);
return 0;
@@ -411,9 +403,6 @@ ctnetlink_dump_table(struct sk_buff *skb, struct netlink_callback *cb)
struct ip_conntrack_tuple_hash *h;
struct list_head *i;
- DEBUGP("entered %s, last bucket=%lu id=%u\n", __FUNCTION__,
- cb->args[0], *id);
-
read_lock_bh(&ip_conntrack_lock);
last = (struct ip_conntrack *)cb->args[1];
for (; cb->args[0] < ip_conntrack_htable_size; cb->args[0]++) {
@@ -452,7 +441,6 @@ out:
if (last)
ip_conntrack_put(last);
- DEBUGP("leaving, last bucket=%lu id=%u\n", cb->args[0], *id);
return skb->len;
}
@@ -466,8 +454,6 @@ ctnetlink_parse_tuple_ip(struct nfattr *attr, struct ip_conntrack_tuple *tuple)
{
struct nfattr *tb[CTA_IP_MAX];
- DEBUGP("entered %s\n", __FUNCTION__);
-
nfattr_parse_nested(tb, CTA_IP_MAX, attr);
if (nfattr_bad_size(tb, CTA_IP_MAX, cta_min_ip))
@@ -481,8 +467,6 @@ ctnetlink_parse_tuple_ip(struct nfattr *attr, struct ip_conntrack_tuple *tuple)
return -EINVAL;
tuple->dst.ip = *(__be32 *)NFA_DATA(tb[CTA_IP_V4_DST-1]);
- DEBUGP("leaving\n");
-
return 0;
}
@@ -503,8 +487,6 @@ ctnetlink_parse_tuple_proto(struct nfattr *attr,
struct ip_conntrack_protocol *proto;
int ret = 0;
- DEBUGP("entered %s\n", __FUNCTION__);
-
nfattr_parse_nested(tb, CTA_PROTO_MAX, attr);
if (nfattr_bad_size(tb, CTA_PROTO_MAX, cta_min_proto))
@@ -531,8 +513,6 @@ ctnetlink_parse_tuple(struct nfattr *cda[], struct ip_conntrack_tuple *tuple,
struct nfattr *tb[CTA_TUPLE_MAX];
int err;
- DEBUGP("entered %s\n", __FUNCTION__);
-
memset(tuple, 0, sizeof(*tuple));
nfattr_parse_nested(tb, CTA_TUPLE_MAX, cda[type-1]);
@@ -557,10 +537,6 @@ ctnetlink_parse_tuple(struct nfattr *cda[], struct ip_conntrack_tuple *tuple,
else
tuple->dst.dir = IP_CT_DIR_ORIGINAL;
- DUMP_TUPLE(tuple);
-
- DEBUGP("leaving\n");
-
return 0;
}
@@ -577,8 +553,6 @@ static int ctnetlink_parse_nat_proto(struct nfattr *attr,
struct nfattr *tb[CTA_PROTONAT_MAX];
struct ip_nat_protocol *npt;
- DEBUGP("entered %s\n", __FUNCTION__);
-
nfattr_parse_nested(tb, CTA_PROTONAT_MAX, attr);
if (nfattr_bad_size(tb, CTA_PROTONAT_MAX, cta_min_protonat))
@@ -597,7 +571,6 @@ static int ctnetlink_parse_nat_proto(struct nfattr *attr,
ip_nat_proto_put(npt);
- DEBUGP("leaving\n");
return 0;
}
@@ -613,8 +586,6 @@ ctnetlink_parse_nat(struct nfattr *nat,
struct nfattr *tb[CTA_NAT_MAX];
int err;
- DEBUGP("entered %s\n", __FUNCTION__);
-
memset(range, 0, sizeof(*range));
nfattr_parse_nested(tb, CTA_NAT_MAX, nat);
@@ -640,7 +611,6 @@ ctnetlink_parse_nat(struct nfattr *nat,
if (err < 0)
return err;
- DEBUGP("leaving\n");
return 0;
}
#endif
@@ -650,8 +620,6 @@ ctnetlink_parse_help(struct nfattr *attr, char **helper_name)
{
struct nfattr *tb[CTA_HELP_MAX];
- DEBUGP("entered %s\n", __FUNCTION__);
-
nfattr_parse_nested(tb, CTA_HELP_MAX, attr);
if (!tb[CTA_HELP_NAME-1])
@@ -679,8 +647,6 @@ ctnetlink_del_conntrack(struct sock *ctnl, struct sk_buff *skb,
struct ip_conntrack *ct;
int err = 0;
- DEBUGP("entered %s\n", __FUNCTION__);
-
if (nfattr_bad_size(cda, CTA_MAX, cta_min))
return -EINVAL;
@@ -698,10 +664,8 @@ ctnetlink_del_conntrack(struct sock *ctnl, struct sk_buff *skb,
return err;
h = ip_conntrack_find_get(&tuple, NULL);
- if (!h) {
- DEBUGP("tuple not found in conntrack hash\n");
+ if (!h)
return -ENOENT;
- }
ct = tuplehash_to_ctrack(h);
@@ -716,7 +680,6 @@ ctnetlink_del_conntrack(struct sock *ctnl, struct sk_buff *skb,
ct->timeout.function((unsigned long)ct);
ip_conntrack_put(ct);
- DEBUGP("leaving\n");
return 0;
}
@@ -731,8 +694,6 @@ ctnetlink_get_conntrack(struct sock *ctnl, struct sk_buff *skb,
struct sk_buff *skb2 = NULL;
int err = 0;
- DEBUGP("entered %s\n", __FUNCTION__);
-
if (nlh->nlmsg_flags & NLM_F_DUMP) {
struct nfgenmsg *msg = NLMSG_DATA(nlh);
u32 rlen;
@@ -770,11 +731,9 @@ ctnetlink_get_conntrack(struct sock *ctnl, struct sk_buff *skb,
return err;
h = ip_conntrack_find_get(&tuple, NULL);
- if (!h) {
- DEBUGP("tuple not found in conntrack hash");
+ if (!h)
return -ENOENT;
- }
- DEBUGP("tuple found\n");
+
ct = tuplehash_to_ctrack(h);
err = -ENOMEM;
@@ -795,7 +754,6 @@ ctnetlink_get_conntrack(struct sock *ctnl, struct sk_buff *skb,
if (err < 0)
goto out;
- DEBUGP("leaving\n");
return 0;
free:
@@ -866,8 +824,6 @@ ctnetlink_change_helper(struct ip_conntrack *ct, struct nfattr *cda[])
char *helpname;
int err;
- DEBUGP("entered %s\n", __FUNCTION__);
-
/* don't change helper of sibling connections */
if (ct->master)
return -EINVAL;
@@ -938,8 +894,6 @@ ctnetlink_change_conntrack(struct ip_conntrack *ct, struct nfattr *cda[])
{
int err;
- DEBUGP("entered %s\n", __FUNCTION__);
-
if (cda[CTA_HELP-1]) {
err = ctnetlink_change_helper(ct, cda);
if (err < 0)
@@ -969,7 +923,6 @@ ctnetlink_change_conntrack(struct ip_conntrack *ct, struct nfattr *cda[])
ct->mark = ntohl(*(__be32 *)NFA_DATA(cda[CTA_MARK-1]));
#endif
- DEBUGP("all done\n");
return 0;
}
@@ -981,8 +934,6 @@ ctnetlink_create_conntrack(struct nfattr *cda[],
struct ip_conntrack *ct;
int err = -EINVAL;
- DEBUGP("entered %s\n", __FUNCTION__);
-
ct = ip_conntrack_alloc(otuple, rtuple);
if (ct == NULL || IS_ERR(ct))
return -ENOMEM;
@@ -1017,7 +968,6 @@ ctnetlink_create_conntrack(struct nfattr *cda[],
if (ct->helper)
ip_conntrack_helper_put(ct->helper);
- DEBUGP("conntrack with id %u inserted\n", ct->id);
return 0;
err:
@@ -1033,8 +983,6 @@ ctnetlink_new_conntrack(struct sock *ctnl, struct sk_buff *skb,
struct ip_conntrack_tuple_hash *h = NULL;
int err = 0;
- DEBUGP("entered %s\n", __FUNCTION__);
-
if (nfattr_bad_size(cda, CTA_MAX, cta_min))
return -EINVAL;
@@ -1058,7 +1006,6 @@ ctnetlink_new_conntrack(struct sock *ctnl, struct sk_buff *skb,
if (h == NULL) {
write_unlock_bh(&ip_conntrack_lock);
- DEBUGP("no such conntrack, create new\n");
err = -ENOENT;
if (nlh->nlmsg_flags & NLM_F_CREATE)
err = ctnetlink_create_conntrack(cda, &otuple, &rtuple);
@@ -1074,7 +1021,6 @@ ctnetlink_new_conntrack(struct sock *ctnl, struct sk_buff *skb,
/* We manipulate the conntrack inside the global conntrack table lock,
* so there's no need to increase the refcount */
- DEBUGP("conntrack found\n");
err = -EEXIST;
if (!(nlh->nlmsg_flags & NLM_F_EXCL))
err = ctnetlink_change_conntrack(tuplehash_to_ctrack(h), cda);
@@ -1249,8 +1195,6 @@ ctnetlink_exp_dump_table(struct sk_buff *skb, struct netlink_callback *cb)
struct list_head *i;
u_int32_t *id = (u_int32_t *) &cb->args[0];
- DEBUGP("entered %s, last id=%llu\n", __FUNCTION__, *id);
-
read_lock_bh(&ip_conntrack_lock);
list_for_each_prev(i, &ip_conntrack_expect_list) {
exp = (struct ip_conntrack_expect *) i;
@@ -1266,8 +1210,6 @@ ctnetlink_exp_dump_table(struct sk_buff *skb, struct netlink_callback *cb)
out:
read_unlock_bh(&ip_conntrack_lock);
- DEBUGP("leaving, last id=%llu\n", *id);
-
return skb->len;
}
@@ -1285,8 +1227,6 @@ ctnetlink_get_expect(struct sock *ctnl, struct sk_buff *skb,
struct sk_buff *skb2;
int err = 0;
- DEBUGP("entered %s\n", __FUNCTION__);
-
if (nfattr_bad_size(cda, CTA_EXPECT_MAX, cta_min_exp))
return -EINVAL;
@@ -1437,8 +1377,6 @@ ctnetlink_create_expect(struct nfattr *cda[])
struct ip_conntrack *ct;
int err = 0;
- DEBUGP("entered %s\n", __FUNCTION__);
-
/* caller guarantees that those three CTA_EXPECT_* exist */
err = ctnetlink_parse_tuple(cda, &tuple, CTA_EXPECT_TUPLE);
if (err < 0)
@@ -1490,8 +1428,6 @@ ctnetlink_new_expect(struct sock *ctnl, struct sk_buff *skb,
struct ip_conntrack_expect *exp;
int err = 0;
- DEBUGP("entered %s\n", __FUNCTION__);
-
if (nfattr_bad_size(cda, CTA_EXPECT_MAX, cta_min_exp))
return -EINVAL;
@@ -1520,8 +1456,6 @@ ctnetlink_new_expect(struct sock *ctnl, struct sk_buff *skb,
err = ctnetlink_change_expect(exp, cda);
write_unlock_bh(&ip_conntrack_lock);
- DEBUGP("leaving\n");
-
return err;
}
diff --git a/net/ipv4/netfilter/ip_queue.c b/net/ipv4/netfilter/ip_queue.c
index 7edad79..97556cc 100644
--- a/net/ipv4/netfilter/ip_queue.c
+++ b/net/ipv4/netfilter/ip_queue.c
@@ -351,9 +351,10 @@ ipq_mangle_ipv4(ipq_verdict_msg_t *v, struct ipq_queue_entry *e)
if (v->data_len < sizeof(*user_iph))
return 0;
diff = v->data_len - e->skb->len;
- if (diff < 0)
- skb_trim(e->skb, v->data_len);
- else if (diff > 0) {
+ if (diff < 0) {
+ if (pskb_trim(e->skb, v->data_len))
+ return -ENOMEM;
+ } else if (diff > 0) {
if (v->data_len > 0xFFFF)
return -EINVAL;
if (diff > skb_tailroom(e->skb)) {
diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c
index 78a44b0..8a45543 100644
--- a/net/ipv4/netfilter/ip_tables.c
+++ b/net/ipv4/netfilter/ip_tables.c
@@ -547,12 +547,18 @@ check_entry(struct ipt_entry *e, const char *name, unsigned int size,
return -EINVAL;
}
+ if (e->target_offset + sizeof(struct ipt_entry_target) > e->next_offset)
+ return -EINVAL;
+
j = 0;
ret = IPT_MATCH_ITERATE(e, check_match, name, &e->ip, e->comefrom, &j);
if (ret != 0)
goto cleanup_matches;
t = ipt_get_target(e);
+ ret = -EINVAL;
+ if (e->target_offset + t->u.target_size > e->next_offset)
+ goto cleanup_matches;
target = try_then_request_module(xt_find_target(AF_INET,
t->u.user.name,
t->u.user.revision),
@@ -712,19 +718,17 @@ translate_table(const char *name,
}
}
- if (!mark_source_chains(newinfo, valid_hooks, entry0))
- return -ELOOP;
-
/* Finally, each sanity check must pass */
i = 0;
ret = IPT_ENTRY_ITERATE(entry0, newinfo->size,
check_entry, name, size, &i);
- if (ret != 0) {
- IPT_ENTRY_ITERATE(entry0, newinfo->size,
- cleanup_entry, &i);
- return ret;
- }
+ if (ret != 0)
+ goto cleanup;
+
+ ret = -ELOOP;
+ if (!mark_source_chains(newinfo, valid_hooks, entry0))
+ goto cleanup;
/* And one copy for every other CPU */
for_each_possible_cpu(i) {
@@ -732,6 +736,9 @@ translate_table(const char *name,
memcpy(newinfo->entries[i], entry0, newinfo->size);
}
+ return 0;
+cleanup:
+ IPT_ENTRY_ITERATE(entry0, newinfo->size, cleanup_entry, &i);
return ret;
}
@@ -1463,6 +1470,10 @@ check_compat_entry_size_and_hooks(struct ipt_entry *e,
return -EINVAL;
}
+ if (e->target_offset + sizeof(struct compat_xt_entry_target) >
+ e->next_offset)
+ return -EINVAL;
+
off = 0;
entry_offset = (void *)e - (void *)base;
j = 0;
@@ -1472,6 +1483,9 @@ check_compat_entry_size_and_hooks(struct ipt_entry *e,
goto cleanup_matches;
t = ipt_get_target(e);
+ ret = -EINVAL;
+ if (e->target_offset + t->u.target_size > e->next_offset)
+ goto cleanup_matches;
target = try_then_request_module(xt_find_target(AF_INET,
t->u.user.name,
t->u.user.revision),
@@ -1513,7 +1527,7 @@ cleanup_matches:
static inline int compat_copy_match_from_user(struct ipt_entry_match *m,
void **dstptr, compat_uint_t *size, const char *name,
- const struct ipt_ip *ip, unsigned int hookmask, int *i)
+ const struct ipt_ip *ip, unsigned int hookmask)
{
struct ipt_entry_match *dm;
struct ipt_match *match;
@@ -1526,22 +1540,13 @@ static inline int compat_copy_match_from_user(struct ipt_entry_match *m,
ret = xt_check_match(match, AF_INET, dm->u.match_size - sizeof(*dm),
name, hookmask, ip->proto,
ip->invflags & IPT_INV_PROTO);
- if (ret)
- goto err;
-
- if (m->u.kernel.match->checkentry
+ if (!ret && m->u.kernel.match->checkentry
&& !m->u.kernel.match->checkentry(name, ip, match, dm->data,
hookmask)) {
duprintf("ip_tables: check failed for `%s'.\n",
m->u.kernel.match->name);
ret = -EINVAL;
- goto err;
}
- (*i)++;
- return 0;
-
-err:
- module_put(m->u.kernel.match->me);
return ret;
}
@@ -1553,19 +1558,18 @@ static int compat_copy_entry_from_user(struct ipt_entry *e, void **dstptr,
struct ipt_target *target;
struct ipt_entry *de;
unsigned int origsize;
- int ret, h, j;
+ int ret, h;
ret = 0;
origsize = *size;
de = (struct ipt_entry *)*dstptr;
memcpy(de, e, sizeof(struct ipt_entry));
- j = 0;
*dstptr += sizeof(struct compat_ipt_entry);
ret = IPT_MATCH_ITERATE(e, compat_copy_match_from_user, dstptr, size,
- name, &de->ip, de->comefrom, &j);
+ name, &de->ip, de->comefrom);
if (ret)
- goto cleanup_matches;
+ goto err;
de->target_offset = e->target_offset - (origsize - *size);
t = ipt_get_target(e);
target = t->u.kernel.target;
@@ -1599,12 +1603,7 @@ static int compat_copy_entry_from_user(struct ipt_entry *e, void **dstptr,
goto err;
}
ret = 0;
- return ret;
-
err:
- module_put(t->u.kernel.target->me);
-cleanup_matches:
- IPT_MATCH_ITERATE(e, cleanup_match, &j);
return ret;
}
@@ -1618,7 +1617,7 @@ translate_compat_table(const char *name,
unsigned int *hook_entries,
unsigned int *underflows)
{
- unsigned int i;
+ unsigned int i, j;
struct xt_table_info *newinfo, *info;
void *pos, *entry0, *entry1;
unsigned int size;
@@ -1636,21 +1635,21 @@ translate_compat_table(const char *name,
}
duprintf("translate_compat_table: size %u\n", info->size);
- i = 0;
+ j = 0;
xt_compat_lock(AF_INET);
/* Walk through entries, checking offsets. */
ret = IPT_ENTRY_ITERATE(entry0, total_size,
check_compat_entry_size_and_hooks,
info, &size, entry0,
entry0 + total_size,
- hook_entries, underflows, &i, name);
+ hook_entries, underflows, &j, name);
if (ret != 0)
goto out_unlock;
ret = -EINVAL;
- if (i != number) {
+ if (j != number) {
duprintf("translate_compat_table: %u not %u entries\n",
- i, number);
+ j, number);
goto out_unlock;
}
@@ -1709,8 +1708,10 @@ translate_compat_table(const char *name,
free_newinfo:
xt_free_table_info(newinfo);
out:
+ IPT_ENTRY_ITERATE(entry0, total_size, cleanup_entry, &j);
return ret;
out_unlock:
+ compat_flush_offsets();
xt_compat_unlock(AF_INET);
goto out;
}
@@ -1932,6 +1933,9 @@ compat_do_ipt_get_ctl(struct sock *sk, int cmd, void __user *user, int *len)
{
int ret;
+ if (!capable(CAP_NET_ADMIN))
+ return -EPERM;
+
switch (cmd) {
case IPT_SO_GET_INFO:
ret = get_info(user, len, 1);
diff --git a/net/ipv4/netfilter/ipt_ECN.c b/net/ipv4/netfilter/ipt_ECN.c
index 12a818a..1aa4517 100644
--- a/net/ipv4/netfilter/ipt_ECN.c
+++ b/net/ipv4/netfilter/ipt_ECN.c
@@ -28,7 +28,7 @@ static inline int
set_ect_ip(struct sk_buff **pskb, const struct ipt_ECN_info *einfo)
{
struct iphdr *iph = (*pskb)->nh.iph;
- __be16 oldtos;
+ u_int16_t oldtos;
if ((iph->tos & IPT_ECN_IP_MASK) != (einfo->ip_ect & IPT_ECN_IP_MASK)) {
if (!skb_make_writable(pskb, sizeof(struct iphdr)))
@@ -37,8 +37,8 @@ set_ect_ip(struct sk_buff **pskb, const struct ipt_ECN_info *einfo)
oldtos = iph->tos;
iph->tos &= ~IPT_ECN_IP_MASK;
iph->tos |= (einfo->ip_ect & IPT_ECN_IP_MASK);
- iph->check = nf_csum_update(oldtos ^ htons(0xFFFF), iph->tos,
- iph->check);
+ iph->check = nf_csum_update(htons(oldtos) ^ htons(0xFFFF),
+ htons(iph->tos), iph->check);
}
return 1;
}
diff --git a/net/ipv4/netfilter/ipt_TOS.c b/net/ipv4/netfilter/ipt_TOS.c
index 6b8b14c..83b80b3 100644
--- a/net/ipv4/netfilter/ipt_TOS.c
+++ b/net/ipv4/netfilter/ipt_TOS.c
@@ -30,7 +30,7 @@ target(struct sk_buff **pskb,
{
const struct ipt_tos_target_info *tosinfo = targinfo;
struct iphdr *iph = (*pskb)->nh.iph;
- __be16 oldtos;
+ u_int16_t oldtos;
if ((iph->tos & IPTOS_TOS_MASK) != tosinfo->tos) {
if (!skb_make_writable(pskb, sizeof(struct iphdr)))
@@ -38,8 +38,8 @@ target(struct sk_buff **pskb,
iph = (*pskb)->nh.iph;
oldtos = iph->tos;
iph->tos = (iph->tos & IPTOS_PREC_MASK) | tosinfo->tos;
- iph->check = nf_csum_update(oldtos ^ htons(0xFFFF), iph->tos,
- iph->check);
+ iph->check = nf_csum_update(htons(oldtos) ^ htons(0xFFFF),
+ htons(iph->tos), iph->check);
}
return IPT_CONTINUE;
}
diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c
index b430cf2..5c31dea 100644
--- a/net/ipv4/raw.c
+++ b/net/ipv4/raw.c
@@ -329,7 +329,7 @@ error:
return err;
}
-static void raw_probe_proto_opt(struct flowi *fl, struct msghdr *msg)
+static int raw_probe_proto_opt(struct flowi *fl, struct msghdr *msg)
{
struct iovec *iov;
u8 __user *type = NULL;
@@ -338,7 +338,7 @@ static void raw_probe_proto_opt(struct flowi *fl, struct msghdr *msg)
unsigned int i;
if (!msg->msg_iov)
- return;
+ return 0;
for (i = 0; i < msg->msg_iovlen; i++) {
iov = &msg->msg_iov[i];
@@ -360,8 +360,9 @@ static void raw_probe_proto_opt(struct flowi *fl, struct msghdr *msg)
code = iov->iov_base;
if (type && code) {
- get_user(fl->fl_icmp_type, type);
- get_user(fl->fl_icmp_code, code);
+ if (get_user(fl->fl_icmp_type, type) ||
+ get_user(fl->fl_icmp_code, code))
+ return -EFAULT;
probed = 1;
}
break;
@@ -372,6 +373,7 @@ static void raw_probe_proto_opt(struct flowi *fl, struct msghdr *msg)
if (probed)
break;
}
+ return 0;
}
static int raw_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
@@ -480,8 +482,11 @@ static int raw_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
.proto = inet->hdrincl ? IPPROTO_RAW :
sk->sk_protocol,
};
- if (!inet->hdrincl)
- raw_probe_proto_opt(&fl, msg);
+ if (!inet->hdrincl) {
+ err = raw_probe_proto_opt(&fl, msg);
+ if (err)
+ goto done;
+ }
security_sk_classify_flow(sk, &fl);
err = ip_route_output_flow(&rt, &fl, sk, !(msg->msg_flags&MSG_DONTWAIT));
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index c41ddba..925ee4d 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -566,9 +566,15 @@ static inline u32 rt_score(struct rtable *rt)
static inline int compare_keys(struct flowi *fl1, struct flowi *fl2)
{
- return memcmp(&fl1->nl_u.ip4_u, &fl2->nl_u.ip4_u, sizeof(fl1->nl_u.ip4_u)) == 0 &&
- fl1->oif == fl2->oif &&
- fl1->iif == fl2->iif;
+ return ((fl1->nl_u.ip4_u.daddr ^ fl2->nl_u.ip4_u.daddr) |
+ (fl1->nl_u.ip4_u.saddr ^ fl2->nl_u.ip4_u.saddr) |
+#ifdef CONFIG_IP_ROUTE_FWMARK
+ (fl1->nl_u.ip4_u.fwmark ^ fl2->nl_u.ip4_u.fwmark) |
+#endif
+ (*(u16 *)&fl1->nl_u.ip4_u.tos ^
+ *(u16 *)&fl2->nl_u.ip4_u.tos) |
+ (fl1->oif ^ fl2->oif) |
+ (fl1->iif ^ fl2->iif)) == 0;
}
#ifdef CONFIG_IP_ROUTE_MULTIPATH_CACHED
diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index e82a5be..15061b3 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -129,13 +129,6 @@ static int sysctl_tcp_congestion_control(ctl_table *table, int __user *name,
return ret;
}
-static int __init tcp_congestion_default(void)
-{
- return tcp_set_default_congestion_control(CONFIG_DEFAULT_TCP_CONG);
-}
-
-late_initcall(tcp_congestion_default);
-
ctl_table ipv4_table[] = {
{
.ctl_name = NET_IPV4_TCP_TIMESTAMPS,
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 66e9a72..c05e8ed 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -2270,7 +2270,7 @@ void __init tcp_init(void)
thash_entries,
(num_physpages >= 128 * 1024) ?
13 : 15,
- HASH_HIGHMEM,
+ 0,
&tcp_hashinfo.ehash_size,
NULL,
0);
@@ -2286,7 +2286,7 @@ void __init tcp_init(void)
tcp_hashinfo.ehash_size,
(num_physpages >= 128 * 1024) ?
13 : 15,
- HASH_HIGHMEM,
+ 0,
&tcp_hashinfo.bhash_size,
NULL,
64 * 1024);
@@ -2316,9 +2316,10 @@ void __init tcp_init(void)
sysctl_max_syn_backlog = 128;
}
- sysctl_tcp_mem[0] = 768 << order;
- sysctl_tcp_mem[1] = 1024 << order;
- sysctl_tcp_mem[2] = 1536 << order;
+ /* Allow no more than 3/4 kernel memory (usually less) allocated to TCP */
+ sysctl_tcp_mem[0] = (1536 / sizeof (struct inet_bind_hashbucket)) << order;
+ sysctl_tcp_mem[1] = sysctl_tcp_mem[0] * 4 / 3;
+ sysctl_tcp_mem[2] = sysctl_tcp_mem[0] * 2;
limit = ((unsigned long)sysctl_tcp_mem[1]) << (PAGE_SHIFT - 7);
max_share = min(4UL*1024*1024, limit);
diff --git a/net/ipv4/tcp_cong.c b/net/ipv4/tcp_cong.c
index af0aca1..1e2982f 100644
--- a/net/ipv4/tcp_cong.c
+++ b/net/ipv4/tcp_cong.c
@@ -131,6 +131,14 @@ int tcp_set_default_congestion_control(const char *name)
return ret;
}
+/* Set default value from kernel configuration at bootup */
+static int __init tcp_congestion_default(void)
+{
+ return tcp_set_default_congestion_control(CONFIG_DEFAULT_TCP_CONG);
+}
+late_initcall(tcp_congestion_default);
+
+
/* Get current default congestion control */
void tcp_get_default_congestion_control(char *name)
{
diff --git a/net/ipv4/tcp_cubic.c b/net/ipv4/tcp_cubic.c
index a60ef38..6ad1848 100644
--- a/net/ipv4/tcp_cubic.c
+++ b/net/ipv4/tcp_cubic.c
@@ -190,7 +190,7 @@ static inline void bictcp_update(struct bictcp *ca, u32 cwnd)
*/
/* change the unit from HZ to bictcp_HZ */
- t = ((tcp_time_stamp + ca->delay_min - ca->epoch_start)
+ t = ((tcp_time_stamp + (ca->delay_min>>3) - ca->epoch_start)
<< BICTCP_HZ) / HZ;
if (t < ca->bic_K) /* t - K */
@@ -259,7 +259,7 @@ static inline void measure_delay(struct sock *sk)
(s32)(tcp_time_stamp - ca->epoch_start) < HZ)
return;
- delay = tcp_time_stamp - tp->rx_opt.rcv_tsecr;
+ delay = (tcp_time_stamp - tp->rx_opt.rcv_tsecr)<<3;
if (delay == 0)
delay = 1;
@@ -366,7 +366,7 @@ static int __init cubictcp_register(void)
beta_scale = 8*(BICTCP_BETA_SCALE+beta)/ 3 / (BICTCP_BETA_SCALE - beta);
- cube_rtt_scale = (bic_scale << 3) / 10; /* 1024*c/rtt */
+ cube_rtt_scale = (bic_scale * 10); /* 1024*c/rtt */
/* calculate the "K" for (wmax-cwnd) = c/rtt * K^3
* so K = cubic_root( (wmax-cwnd)*rtt/c )
diff --git a/net/ipv4/tcp_htcp.c b/net/ipv4/tcp_htcp.c
index 682e7d5..283be3c 100644
--- a/net/ipv4/tcp_htcp.c
+++ b/net/ipv4/tcp_htcp.c
@@ -23,7 +23,7 @@ module_param(use_bandwidth_switch, int, 0644);
MODULE_PARM_DESC(use_bandwidth_switch, "turn on/off bandwidth switcher");
struct htcp {
- u16 alpha; /* Fixed point arith, << 7 */
+ u32 alpha; /* Fixed point arith, << 7 */
u8 beta; /* Fixed point arith, << 7 */
u8 modeswitch; /* Delay modeswitch until we had at least one congestion event */
u32 last_cong; /* Time since last congestion event end */
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index c83938b..22ef8bd 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -355,7 +355,7 @@ void tcp_v4_err(struct sk_buff *skb, u32 info)
return;
}
if (sk->sk_state == TCP_TIME_WAIT) {
- inet_twsk_put((struct inet_timewait_sock *)sk);
+ inet_twsk_put(inet_twsk(sk));
return;
}
@@ -373,7 +373,7 @@ void tcp_v4_err(struct sk_buff *skb, u32 info)
seq = ntohl(th->seq);
if (sk->sk_state != TCP_LISTEN &&
!between(seq, tp->snd_una, tp->snd_nxt)) {
- NET_INC_STATS(LINUX_MIB_OUTOFWINDOWICMPS);
+ NET_INC_STATS_BH(LINUX_MIB_OUTOFWINDOWICMPS);
goto out;
}
@@ -578,7 +578,7 @@ static void tcp_v4_send_ack(struct sk_buff *skb, u32 seq, u32 ack,
struct tcphdr *th = skb->h.th;
struct {
struct tcphdr th;
- u32 tsopt[3];
+ u32 tsopt[TCPOLEN_TSTAMP_ALIGNED >> 2];
} rep;
struct ip_reply_arg arg;
@@ -960,7 +960,7 @@ static struct sock *tcp_v4_hnd_req(struct sock *sk, struct sk_buff *skb)
bh_lock_sock(nsk);
return nsk;
}
- inet_twsk_put((struct inet_timewait_sock *)nsk);
+ inet_twsk_put(inet_twsk(nsk));
return NULL;
}
@@ -1154,26 +1154,24 @@ discard_and_relse:
do_time_wait:
if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb)) {
- inet_twsk_put((struct inet_timewait_sock *) sk);
+ inet_twsk_put(inet_twsk(sk));
goto discard_it;
}
if (skb->len < (th->doff << 2) || tcp_checksum_complete(skb)) {
TCP_INC_STATS_BH(TCP_MIB_INERRS);
- inet_twsk_put((struct inet_timewait_sock *) sk);
+ inet_twsk_put(inet_twsk(sk));
goto discard_it;
}
- switch (tcp_timewait_state_process((struct inet_timewait_sock *)sk,
- skb, th)) {
+ switch (tcp_timewait_state_process(inet_twsk(sk), skb, th)) {
case TCP_TW_SYN: {
struct sock *sk2 = inet_lookup_listener(&tcp_hashinfo,
skb->nh.iph->daddr,
th->dest,
inet_iif(skb));
if (sk2) {
- inet_twsk_deschedule((struct inet_timewait_sock *)sk,
- &tcp_death_row);
- inet_twsk_put((struct inet_timewait_sock *)sk);
+ inet_twsk_deschedule(inet_twsk(sk), &tcp_death_row);
+ inet_twsk_put(inet_twsk(sk));
sk = sk2;
goto process;
}
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 9a253fa..ca40615 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -273,10 +273,10 @@ static void tcp_build_and_update_options(__be32 *ptr, struct tcp_sock *tp,
__u32 tstamp)
{
if (tp->rx_opt.tstamp_ok) {
- *ptr++ = __constant_htonl((TCPOPT_NOP << 24) |
- (TCPOPT_NOP << 16) |
- (TCPOPT_TIMESTAMP << 8) |
- TCPOLEN_TIMESTAMP);
+ *ptr++ = htonl((TCPOPT_NOP << 24) |
+ (TCPOPT_NOP << 16) |
+ (TCPOPT_TIMESTAMP << 8) |
+ TCPOLEN_TIMESTAMP);
*ptr++ = htonl(tstamp);
*ptr++ = htonl(tp->rx_opt.ts_recent);
}
@@ -325,18 +325,27 @@ static void tcp_syn_build_options(__be32 *ptr, int mss, int ts, int sack,
*ptr++ = htonl((TCPOPT_MSS << 24) | (TCPOLEN_MSS << 16) | mss);
if (ts) {
if(sack)
- *ptr++ = __constant_htonl((TCPOPT_SACK_PERM << 24) | (TCPOLEN_SACK_PERM << 16) |
- (TCPOPT_TIMESTAMP << 8) | TCPOLEN_TIMESTAMP);
+ *ptr++ = htonl((TCPOPT_SACK_PERM << 24) |
+ (TCPOLEN_SACK_PERM << 16) |
+ (TCPOPT_TIMESTAMP << 8) |
+ TCPOLEN_TIMESTAMP);
else
- *ptr++ = __constant_htonl((TCPOPT_NOP << 24) | (TCPOPT_NOP << 16) |
- (TCPOPT_TIMESTAMP << 8) | TCPOLEN_TIMESTAMP);
+ *ptr++ = htonl((TCPOPT_NOP << 24) |
+ (TCPOPT_NOP << 16) |
+ (TCPOPT_TIMESTAMP << 8) |
+ TCPOLEN_TIMESTAMP);
*ptr++ = htonl(tstamp); /* TSVAL */
*ptr++ = htonl(ts_recent); /* TSECR */
} else if(sack)
- *ptr++ = __constant_htonl((TCPOPT_NOP << 24) | (TCPOPT_NOP << 16) |
- (TCPOPT_SACK_PERM << 8) | TCPOLEN_SACK_PERM);
+ *ptr++ = htonl((TCPOPT_NOP << 24) |
+ (TCPOPT_NOP << 16) |
+ (TCPOPT_SACK_PERM << 8) |
+ TCPOLEN_SACK_PERM);
if (offer_wscale)
- *ptr++ = htonl((TCPOPT_NOP << 24) | (TCPOPT_WINDOW << 16) | (TCPOLEN_WINDOW << 8) | (wscale));
+ *ptr++ = htonl((TCPOPT_NOP << 24) |
+ (TCPOPT_WINDOW << 16) |
+ (TCPOLEN_WINDOW << 8) |
+ (wscale));
}
/* This routine actually transmits TCP packets queued in by
@@ -1087,10 +1096,14 @@ static int tcp_tso_should_defer(struct sock *sk, struct tcp_sock *tp, struct sk_
u32 send_win, cong_win, limit, in_flight;
if (TCP_SKB_CB(skb)->flags & TCPCB_FLAG_FIN)
- return 0;
+ goto send_now;
if (icsk->icsk_ca_state != TCP_CA_Open)
- return 0;
+ goto send_now;
+
+ /* Defer for less than two clock ticks. */
+ if (!tp->tso_deferred && ((jiffies<<1)>>1) - (tp->tso_deferred>>1) > 1)
+ goto send_now;
in_flight = tcp_packets_in_flight(tp);
@@ -1106,7 +1119,7 @@ static int tcp_tso_should_defer(struct sock *sk, struct tcp_sock *tp, struct sk_
/* If a full-sized TSO skb can be sent, do it. */
if (limit >= 65536)
- return 0;
+ goto send_now;
if (sysctl_tcp_tso_win_divisor) {
u32 chunk = min(tp->snd_wnd, tp->snd_cwnd * tp->mss_cache);
@@ -1116,7 +1129,7 @@ static int tcp_tso_should_defer(struct sock *sk, struct tcp_sock *tp, struct sk_
*/
chunk /= sysctl_tcp_tso_win_divisor;
if (limit >= chunk)
- return 0;
+ goto send_now;
} else {
/* Different approach, try not to defer past a single
* ACK. Receiver should ACK every other full sized
@@ -1124,11 +1137,17 @@ static int tcp_tso_should_defer(struct sock *sk, struct tcp_sock *tp, struct sk_
* then send now.
*/
if (limit > tcp_max_burst(tp) * tp->mss_cache)
- return 0;
+ goto send_now;
}
/* Ok, it looks like it is advisable to defer. */
+ tp->tso_deferred = 1 | (jiffies<<1);
+
return 1;
+
+send_now:
+ tp->tso_deferred = 0;
+ return 0;
}
/* Create a new MTU probe if we are ready.
diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c
index 7a7a001..1bed0cd 100644
--- a/net/ipv4/xfrm4_policy.c
+++ b/net/ipv4/xfrm4_policy.c
@@ -52,7 +52,7 @@ __xfrm4_find_bundle(struct flowi *fl, struct xfrm_policy *policy)
xdst->u.rt.fl.fl4_dst == fl->fl4_dst &&
xdst->u.rt.fl.fl4_src == fl->fl4_src &&
xdst->u.rt.fl.fl4_tos == fl->fl4_tos &&
- xfrm_bundle_ok(xdst, fl, AF_INET, 0)) {
+ xfrm_bundle_ok(policy, xdst, fl, AF_INET, 0)) {
dst_clone(dst);
break;
}
generated by cgit v0.10.2 at 2024-09-19 07:41:53 (GMT)