aboutsummaryrefslogtreecommitdiff
path: root/net/ipv4
diff options
context:
space:
mode:
Diffstat (limited to 'net/ipv4')
-rw-r--r--net/ipv4/af_inet.c5
-rw-r--r--net/ipv4/datagram.c16
-rw-r--r--net/ipv4/devinet.c4
-rw-r--r--net/ipv4/fib_frontend.c4
-rw-r--r--net/ipv4/fou.c3
-rw-r--r--net/ipv4/gre_offload.c3
-rw-r--r--net/ipv4/ip_fragment.c7
-rw-r--r--net/ipv4/ip_tunnel.c8
-rw-r--r--net/ipv4/ip_vti.c14
-rw-r--r--net/ipv4/ipmr.c21
-rw-r--r--net/ipv4/netfilter/arp_tables.c337
-rw-r--r--net/ipv4/netfilter/ip_tables.c371
-rw-r--r--net/ipv4/netfilter/nf_nat_masquerade_ipv4.c12
-rw-r--r--net/ipv4/route.c16
-rw-r--r--net/ipv4/sysctl_net_ipv4.c4
-rw-r--r--net/ipv4/tcp.c17
-rw-r--r--net/ipv4/tcp_cong.c6
-rw-r--r--net/ipv4/tcp_cubic.c22
-rw-r--r--net/ipv4/tcp_fastopen.c2
-rw-r--r--net/ipv4/tcp_input.c23
-rw-r--r--net/ipv4/tcp_ipv4.c8
-rw-r--r--net/ipv4/tcp_metrics.c2
-rw-r--r--net/ipv4/tcp_minisocks.c5
-rw-r--r--net/ipv4/tcp_output.c7
-rw-r--r--net/ipv4/tcp_yeah.c2
-rw-r--r--net/ipv4/udp.c41
-rw-r--r--net/ipv4/xfrm4_policy.c46
27 files changed, 456 insertions, 550 deletions
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index e67da4e6c324..6cf020ea4f46 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -228,6 +228,8 @@ int inet_listen(struct socket *sock, int backlog)
err = 0;
if (err)
goto out;
+
+ tcp_fastopen_init_key_once(true);
}
err = inet_csk_listen_start(sk, backlog);
if (err)
@@ -257,6 +259,9 @@ static int inet_create(struct net *net, struct socket *sock, int protocol,
int try_loading_module = 0;
int err;
+ if (protocol < 0 || protocol >= IPPROTO_MAX)
+ return -EINVAL;
+
sock->state = SS_UNCONNECTED;
/* Look for the requested type/protocol pair. */
diff --git a/net/ipv4/datagram.c b/net/ipv4/datagram.c
index 90c0e8386116..574fad9cca05 100644
--- a/net/ipv4/datagram.c
+++ b/net/ipv4/datagram.c
@@ -20,7 +20,7 @@
#include <net/route.h>
#include <net/tcp_states.h>
-int ip4_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
+int __ip4_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
{
struct inet_sock *inet = inet_sk(sk);
struct sockaddr_in *usin = (struct sockaddr_in *) uaddr;
@@ -39,8 +39,6 @@ int ip4_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
sk_dst_reset(sk);
- lock_sock(sk);
-
oif = sk->sk_bound_dev_if;
saddr = inet->inet_saddr;
if (ipv4_is_multicast(usin->sin_addr.s_addr)) {
@@ -82,9 +80,19 @@ int ip4_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
sk_dst_set(sk, &rt->dst);
err = 0;
out:
- release_sock(sk);
return err;
}
+EXPORT_SYMBOL(__ip4_datagram_connect);
+
+int ip4_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
+{
+ int res;
+
+ lock_sock(sk);
+ res = __ip4_datagram_connect(sk, uaddr, addr_len);
+ release_sock(sk);
+ return res;
+}
EXPORT_SYMBOL(ip4_datagram_connect);
/* Because UDP xmit path can manipulate sk_dst_cache without holding
diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c
index 214882e7d6de..464293c34b7a 100644
--- a/net/ipv4/devinet.c
+++ b/net/ipv4/devinet.c
@@ -334,6 +334,9 @@ static void __inet_del_ifa(struct in_device *in_dev, struct in_ifaddr **ifap,
ASSERT_RTNL();
+ if (in_dev->dead)
+ goto no_promotions;
+
/* 1. Deleting primary ifaddr forces deletion all secondaries
* unless alias promotion is set
**/
@@ -380,6 +383,7 @@ static void __inet_del_ifa(struct in_device *in_dev, struct in_ifaddr **ifap,
fib_del_ifaddr(ifa, ifa1);
}
+no_promotions:
/* 2. Unlink it */
*ifap = ifa1->ifa_next;
diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index 23104a3f2924..d4c698ce0838 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -814,6 +814,9 @@ void fib_del_ifaddr(struct in_ifaddr *ifa, struct in_ifaddr *iprim)
subnet = 1;
}
+ if (in_dev->dead)
+ goto no_promotions;
+
/* Deletion is more complicated than add.
* We should take care of not to delete too much :-)
*
@@ -889,6 +892,7 @@ void fib_del_ifaddr(struct in_ifaddr *ifa, struct in_ifaddr *iprim)
}
}
+no_promotions:
if (!(ok & BRD_OK))
fib_magic(RTM_DELROUTE, RTN_BROADCAST, ifa->ifa_broadcast, 32, prim);
if (subnet && ifa->ifa_prefixlen < 31) {
diff --git a/net/ipv4/fou.c b/net/ipv4/fou.c
index 606c520ffd5a..8ce8e82d1abb 100644
--- a/net/ipv4/fou.c
+++ b/net/ipv4/fou.c
@@ -25,6 +25,7 @@ struct fou {
u16 port;
struct udp_offload udp_offloads;
struct list_head list;
+ struct rcu_head rcu;
};
struct fou_cfg {
@@ -287,7 +288,7 @@ static void fou_release(struct fou *fou)
sock_release(sock);
- kfree(fou);
+ kfree_rcu(fou, rcu);
}
static int fou_encap_init(struct sock *sk, struct fou *fou, struct fou_cfg *cfg)
diff --git a/net/ipv4/gre_offload.c b/net/ipv4/gre_offload.c
index 51973ddc05a6..abc50b41bc39 100644
--- a/net/ipv4/gre_offload.c
+++ b/net/ipv4/gre_offload.c
@@ -36,7 +36,8 @@ static struct sk_buff *gre_gso_segment(struct sk_buff *skb,
SKB_GSO_TCP_ECN |
SKB_GSO_GRE |
SKB_GSO_GRE_CSUM |
- SKB_GSO_IPIP)))
+ SKB_GSO_IPIP |
+ SKB_GSO_SIT)))
goto out;
if (!skb->encapsulation)
diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c
index b48e03cd6656..9516031847f1 100644
--- a/net/ipv4/ip_fragment.c
+++ b/net/ipv4/ip_fragment.c
@@ -342,7 +342,7 @@ static int ip_frag_queue(struct ipq *qp, struct sk_buff *skb)
ihl = ip_hdrlen(skb);
/* Determine the position of this fragment. */
- end = offset + skb->len - ihl;
+ end = offset + skb->len - skb_network_offset(skb) - ihl;
err = -EINVAL;
/* Is this the final fragment? */
@@ -372,7 +372,7 @@ static int ip_frag_queue(struct ipq *qp, struct sk_buff *skb)
goto err;
err = -ENOMEM;
- if (pskb_pull(skb, ihl) == NULL)
+ if (!pskb_pull(skb, skb_network_offset(skb) + ihl))
goto err;
err = pskb_trim_rcsum(skb, end - offset);
@@ -612,6 +612,9 @@ static int ip_frag_reasm(struct ipq *qp, struct sk_buff *prev,
iph->frag_off = qp->q.max_size ? htons(IP_DF) : 0;
iph->tot_len = htons(len);
iph->tos |= ecn;
+
+ ip_send_check(iph);
+
IP_INC_STATS_BH(net, IPSTATS_MIB_REASMOKS);
qp->q.fragments = NULL;
qp->q.fragments_tail = NULL;
diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c
index 0bb8e141eacc..682257242971 100644
--- a/net/ipv4/ip_tunnel.c
+++ b/net/ipv4/ip_tunnel.c
@@ -587,7 +587,8 @@ int ip_tunnel_encap(struct sk_buff *skb, struct ip_tunnel *t,
EXPORT_SYMBOL(ip_tunnel_encap);
static int tnl_update_pmtu(struct net_device *dev, struct sk_buff *skb,
- struct rtable *rt, __be16 df)
+ struct rtable *rt, __be16 df,
+ const struct iphdr *inner_iph)
{
struct ip_tunnel *tunnel = netdev_priv(dev);
int pkt_size = skb->len - tunnel->hlen - dev->hard_header_len;
@@ -604,7 +605,8 @@ static int tnl_update_pmtu(struct net_device *dev, struct sk_buff *skb,
if (skb->protocol == htons(ETH_P_IP)) {
if (!skb_is_gso(skb) &&
- (df & htons(IP_DF)) && mtu < pkt_size) {
+ (inner_iph->frag_off & htons(IP_DF)) &&
+ mtu < pkt_size) {
memset(IPCB(skb), 0, sizeof(*IPCB(skb)));
icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED, htonl(mtu));
return -E2BIG;
@@ -738,7 +740,7 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev,
goto tx_error;
}
- if (tnl_update_pmtu(dev, skb, rt, tnl_params->frag_off)) {
+ if (tnl_update_pmtu(dev, skb, rt, tnl_params->frag_off, inner_iph)) {
ip_rt_put(rt);
goto tx_error;
}
diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c
index 1a7e979e80ba..15046aec8484 100644
--- a/net/ipv4/ip_vti.c
+++ b/net/ipv4/ip_vti.c
@@ -65,7 +65,6 @@ static int vti_input(struct sk_buff *skb, int nexthdr, __be32 spi,
goto drop;
XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip4 = tunnel;
- skb->mark = be32_to_cpu(tunnel->parms.i_key);
return xfrm_input(skb, nexthdr, spi, encap_type);
}
@@ -91,6 +90,8 @@ static int vti_rcv_cb(struct sk_buff *skb, int err)
struct pcpu_sw_netstats *tstats;
struct xfrm_state *x;
struct ip_tunnel *tunnel = XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip4;
+ u32 orig_mark = skb->mark;
+ int ret;
if (!tunnel)
return 1;
@@ -107,7 +108,11 @@ static int vti_rcv_cb(struct sk_buff *skb, int err)
x = xfrm_input_state(skb);
family = x->inner_mode->afinfo->family;
- if (!xfrm_policy_check(NULL, XFRM_POLICY_IN, skb, family))
+ skb->mark = be32_to_cpu(tunnel->parms.i_key);
+ ret = xfrm_policy_check(NULL, XFRM_POLICY_IN, skb, family);
+ skb->mark = orig_mark;
+
+ if (!ret)
return -EPERM;
skb_scrub_packet(skb, !net_eq(tunnel->net, dev_net(skb->dev)));
@@ -216,8 +221,6 @@ static netdev_tx_t vti_tunnel_xmit(struct sk_buff *skb, struct net_device *dev)
memset(&fl, 0, sizeof(fl));
- skb->mark = be32_to_cpu(tunnel->parms.o_key);
-
switch (skb->protocol) {
case htons(ETH_P_IP):
xfrm_decode_session(skb, &fl, AF_INET);
@@ -233,6 +236,9 @@ static netdev_tx_t vti_tunnel_xmit(struct sk_buff *skb, struct net_device *dev)
return NETDEV_TX_OK;
}
+ /* override mark with tunnel output key */
+ fl.flowi_mark = be32_to_cpu(tunnel->parms.o_key);
+
return vti_xmit(skb, dev, &fl);
}
diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index c8034587859d..1b7f6da99ef4 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -136,7 +136,7 @@ static int __ipmr_fill_mroute(struct mr_table *mrt, struct sk_buff *skb,
struct mfc_cache *c, struct rtmsg *rtm);
static void mroute_netlink_event(struct mr_table *mrt, struct mfc_cache *mfc,
int cmd);
-static void mroute_clean_tables(struct mr_table *mrt);
+static void mroute_clean_tables(struct mr_table *mrt, bool all);
static void ipmr_expire_process(unsigned long arg);
#ifdef CONFIG_IP_MROUTE_MULTIPLE_TABLES
@@ -348,7 +348,7 @@ static struct mr_table *ipmr_new_table(struct net *net, u32 id)
static void ipmr_free_table(struct mr_table *mrt)
{
del_timer_sync(&mrt->ipmr_expire_timer);
- mroute_clean_tables(mrt);
+ mroute_clean_tables(mrt, true);
kfree(mrt);
}
@@ -1201,7 +1201,7 @@ static int ipmr_mfc_add(struct net *net, struct mr_table *mrt,
* Close the multicast socket, and clear the vif tables etc
*/
-static void mroute_clean_tables(struct mr_table *mrt)
+static void mroute_clean_tables(struct mr_table *mrt, bool all)
{
int i;
LIST_HEAD(list);
@@ -1210,8 +1210,9 @@ static void mroute_clean_tables(struct mr_table *mrt)
/* Shut down all active vif entries */
for (i = 0; i < mrt->maxvif; i++) {
- if (!(mrt->vif_table[i].flags & VIFF_STATIC))
- vif_delete(mrt, i, 0, &list);
+ if (!all && (mrt->vif_table[i].flags & VIFF_STATIC))
+ continue;
+ vif_delete(mrt, i, 0, &list);
}
unregister_netdevice_many(&list);
@@ -1219,7 +1220,7 @@ static void mroute_clean_tables(struct mr_table *mrt)
for (i = 0; i < MFC_LINES; i++) {
list_for_each_entry_safe(c, next, &mrt->mfc_cache_array[i], list) {
- if (c->mfc_flags & MFC_STATIC)
+ if (!all && (c->mfc_flags & MFC_STATIC))
continue;
list_del_rcu(&c->list);
mroute_netlink_event(mrt, c, RTM_DELROUTE);
@@ -1254,7 +1255,7 @@ static void mrtsock_destruct(struct sock *sk)
NETCONFA_IFINDEX_ALL,
net->ipv4.devconf_all);
RCU_INIT_POINTER(mrt->mroute_sk, NULL);
- mroute_clean_tables(mrt);
+ mroute_clean_tables(mrt, false);
}
}
rtnl_unlock();
@@ -1674,8 +1675,8 @@ static inline int ipmr_forward_finish(struct sk_buff *skb)
{
struct ip_options *opt = &(IPCB(skb)->opt);
- IP_INC_STATS_BH(dev_net(skb_dst(skb)->dev), IPSTATS_MIB_OUTFORWDATAGRAMS);
- IP_ADD_STATS_BH(dev_net(skb_dst(skb)->dev), IPSTATS_MIB_OUTOCTETS, skb->len);
+ IP_INC_STATS(dev_net(skb_dst(skb)->dev), IPSTATS_MIB_OUTFORWDATAGRAMS);
+ IP_ADD_STATS(dev_net(skb_dst(skb)->dev), IPSTATS_MIB_OUTOCTETS, skb->len);
if (unlikely(opt->optlen))
ip_forward_options(skb);
@@ -1737,7 +1738,7 @@ static void ipmr_queue_xmit(struct net *net, struct mr_table *mrt,
* to blackhole.
*/
- IP_INC_STATS_BH(dev_net(dev), IPSTATS_MIB_FRAGFAILS);
+ IP_INC_STATS(dev_net(dev), IPSTATS_MIB_FRAGFAILS);
ip_rt_put(rt);
goto out_free;
}
diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c
index f95b6f93814b..b3bfa5111799 100644
--- a/net/ipv4/netfilter/arp_tables.c
+++ b/net/ipv4/netfilter/arp_tables.c
@@ -355,18 +355,20 @@ unsigned int arpt_do_table(struct sk_buff *skb,
}
/* All zeroes == unconditional rule. */
-static inline bool unconditional(const struct arpt_arp *arp)
+static inline bool unconditional(const struct arpt_entry *e)
{
static const struct arpt_arp uncond;
- return memcmp(arp, &uncond, sizeof(uncond)) == 0;
+ return e->target_offset == sizeof(struct arpt_entry) &&
+ memcmp(&e->arp, &uncond, sizeof(uncond)) == 0;
}
/* Figures out from what hook each rule can be called: returns 0 if
* there are loops. Puts hook bitmask in comefrom.
*/
static int mark_source_chains(const struct xt_table_info *newinfo,
- unsigned int valid_hooks, void *entry0)
+ unsigned int valid_hooks, void *entry0,
+ unsigned int *offsets)
{
unsigned int hook;
@@ -398,11 +400,10 @@ static int mark_source_chains(const struct xt_table_info *newinfo,
|= ((1 << hook) | (1 << NF_ARP_NUMHOOKS));
/* Unconditional return/END. */
- if ((e->target_offset == sizeof(struct arpt_entry) &&
+ if ((unconditional(e) &&
(strcmp(t->target.u.user.name,
XT_STANDARD_TARGET) == 0) &&
- t->verdict < 0 && unconditional(&e->arp)) ||
- visited) {
+ t->verdict < 0) || visited) {
unsigned int oldpos, size;
if ((strcmp(t->target.u.user.name,
@@ -435,6 +436,8 @@ static int mark_source_chains(const struct xt_table_info *newinfo,
size = e->next_offset;
e = (struct arpt_entry *)
(entry0 + pos + size);
+ if (pos + size >= newinfo->size)
+ return 0;
e->counters.pcnt = pos;
pos += size;
} else {
@@ -454,9 +457,16 @@ static int mark_source_chains(const struct xt_table_info *newinfo,
/* This a jump; chase it. */
duprintf("Jump rule %u -> %u\n",
pos, newpos);
+ if (!xt_find_jump_offset(offsets, newpos,
+ newinfo->number))
+ return 0;
+ e = (struct arpt_entry *)
+ (entry0 + newpos);
} else {
/* ... this is a fallthru */
newpos = pos + e->next_offset;
+ if (newpos >= newinfo->size)
+ return 0;
}
e = (struct arpt_entry *)
(entry0 + newpos);
@@ -470,25 +480,6 @@ static int mark_source_chains(const struct xt_table_info *newinfo,
return 1;
}
-static inline int check_entry(const struct arpt_entry *e, const char *name)
-{
- const struct xt_entry_target *t;
-
- if (!arp_checkentry(&e->arp)) {
- duprintf("arp_tables: arp check failed %p %s.\n", e, name);
- return -EINVAL;
- }
-
- if (e->target_offset + sizeof(struct xt_entry_target) > e->next_offset)
- return -EINVAL;
-
- t = arpt_get_target_c(e);
- if (e->target_offset + t->u.target_size > e->next_offset)
- return -EINVAL;
-
- return 0;
-}
-
static inline int check_target(struct arpt_entry *e, const char *name)
{
struct xt_entry_target *t = arpt_get_target(e);
@@ -518,10 +509,6 @@ find_check_entry(struct arpt_entry *e, const char *name, unsigned int size)
struct xt_target *target;
int ret;
- ret = check_entry(e, name);
- if (ret)
- return ret;
-
t = arpt_get_target(e);
target = xt_request_find_target(NFPROTO_ARP, t->u.user.name,
t->u.user.revision);
@@ -547,7 +534,7 @@ static bool check_underflow(const struct arpt_entry *e)
const struct xt_entry_target *t;
unsigned int verdict;
- if (!unconditional(&e->arp))
+ if (!unconditional(e))
return false;
t = arpt_get_target_c(e);
if (strcmp(t->u.user.name, XT_STANDARD_TARGET) != 0)
@@ -566,9 +553,11 @@ static inline int check_entry_size_and_hooks(struct arpt_entry *e,
unsigned int valid_hooks)
{
unsigned int h;
+ int err;
if ((unsigned long)e % __alignof__(struct arpt_entry) != 0 ||
- (unsigned char *)e + sizeof(struct arpt_entry) >= limit) {
+ (unsigned char *)e + sizeof(struct arpt_entry) >= limit ||
+ (unsigned char *)e + e->next_offset > limit) {
duprintf("Bad offset %p\n", e);
return -EINVAL;
}
@@ -580,6 +569,14 @@ static inline int check_entry_size_and_hooks(struct arpt_entry *e,
return -EINVAL;
}
+ if (!arp_checkentry(&e->arp))
+ return -EINVAL;
+
+ err = xt_check_entry_offsets(e, e->elems, e->target_offset,
+ e->next_offset);
+ if (err)
+ return err;
+
/* Check hooks & underflows */
for (h = 0; h < NF_ARP_NUMHOOKS; h++) {
if (!(valid_hooks & (1 << h)))
@@ -588,9 +585,9 @@ static inline int check_entry_size_and_hooks(struct arpt_entry *e,
newinfo->hook_entry[h] = hook_entries[h];
if ((unsigned char *)e - base == underflows[h]) {
if (!check_underflow(e)) {
- pr_err("Underflows must be unconditional and "
- "use the STANDARD target with "
- "ACCEPT/DROP\n");
+ pr_debug("Underflows must be unconditional and "
+ "use the STANDARD target with "
+ "ACCEPT/DROP\n");
return -EINVAL;
}
newinfo->underflow[h] = underflows[h];
@@ -624,6 +621,7 @@ static int translate_table(struct xt_table_info *newinfo, void *entry0,
const struct arpt_replace *repl)
{
struct arpt_entry *iter;
+ unsigned int *offsets;
unsigned int i;
int ret = 0;
@@ -637,8 +635,10 @@ static int translate_table(struct xt_table_info *newinfo, void *entry0,
}
duprintf("translate_table: size %u\n", newinfo->size);
+ offsets = xt_alloc_entry_offsets(newinfo->number);
+ if (!offsets)
+ return -ENOMEM;
i = 0;
-
/* Walk through entries, checking offsets. */
xt_entry_foreach(iter, entry0, newinfo->size) {
ret = check_entry_size_and_hooks(iter, newinfo, entry0,
@@ -647,7 +647,9 @@ static int translate_table(struct xt_table_info *newinfo, void *entry0,
repl->underflow,
repl->valid_hooks);
if (ret != 0)
- break;
+ goto out_free;
+ if (i < repl->num_entries)
+ offsets[i] = (void *)iter - entry0;
++i;
if (strcmp(arpt_get_target(iter)->u.user.name,
XT_ERROR_TARGET) == 0)
@@ -655,12 +657,13 @@ static int translate_table(struct xt_table_info *newinfo, void *entry0,
}
duprintf("translate_table: ARPT_ENTRY_ITERATE gives %d\n", ret);
if (ret != 0)
- return ret;
+ goto out_free;
+ ret = -EINVAL;
if (i != repl->num_entries) {
duprintf("translate_table: %u not %u entries\n",
i, repl->num_entries);
- return -EINVAL;
+ goto out_free;
}
/* Check hooks all assigned */
@@ -671,19 +674,20 @@ static int translate_table(struct xt_table_info *newinfo, void *entry0,
if (newinfo->hook_entry[i] == 0xFFFFFFFF) {
duprintf("Invalid hook entry %u %u\n",
i, repl->hook_entry[i]);
- return -EINVAL;
+ goto out_free;
}
if (newinfo->underflow[i] == 0xFFFFFFFF) {
duprintf("Invalid underflow %u %u\n",
i, repl->underflow[i]);
- return -EINVAL;
+ goto out_free;
}
}
- if (!mark_source_chains(newinfo, repl->valid_hooks, entry0)) {
- duprintf("Looping hook\n");
- return -ELOOP;
+ if (!mark_source_chains(newinfo, repl->valid_hooks, entry0, offsets)) {
+ ret = -ELOOP;
+ goto out_free;
}
+ kvfree(offsets);
/* Finally, each sanity check must pass */
i = 0;
@@ -710,6 +714,9 @@ static int translate_table(struct xt_table_info *newinfo, void *entry0,
}
return ret;
+ out_free:
+ kvfree(offsets);
+ return ret;
}
static void get_counters(const struct xt_table_info *t,
@@ -1116,56 +1123,18 @@ static int do_add_counters(struct net *net, const void __user *user,
unsigned int i, curcpu;
struct xt_counters_info tmp;
struct xt_counters *paddc;
- unsigned int num_counters;
- const char *name;
- int size;
- void *ptmp;
struct xt_table *t;
const struct xt_table_info *private;
int ret = 0;
void *loc_cpu_entry;
struct arpt_entry *iter;
unsigned int addend;
-#ifdef CONFIG_COMPAT
- struct compat_xt_counters_info compat_tmp;
-
- if (compat) {
- ptmp = &compat_tmp;
- size = sizeof(struct compat_xt_counters_info);
- } else
-#endif
- {
- ptmp = &tmp;
- size = sizeof(struct xt_counters_info);
- }
-
- if (copy_from_user(ptmp, user, size) != 0)
- return -EFAULT;
-#ifdef CONFIG_COMPAT
- if (compat) {
- num_counters = compat_tmp.num_counters;
- name = compat_tmp.name;
- } else
-#endif
- {
- num_counters = tmp.num_counters;
- name = tmp.name;
- }
+ paddc = xt_copy_counters_from_user(user, len, &tmp, compat);
+ if (IS_ERR(paddc))
+ return PTR_ERR(paddc);
- if (len != size + num_counters * sizeof(struct xt_counters))
- return -EINVAL;
-
- paddc = vmalloc(len - size);
- if (!paddc)
- return -ENOMEM;
-
- if (copy_from_user(paddc, user + size, len - size) != 0) {
- ret = -EFAULT;
- goto free;
- }
-
- t = xt_find_table_lock(net, NFPROTO_ARP, name);
+ t = xt_find_table_lock(net, NFPROTO_ARP, tmp.name);
if (IS_ERR_OR_NULL(t)) {
ret = t ? PTR_ERR(t) : -ENOENT;
goto free;
@@ -1173,7 +1142,7 @@ static int do_add_counters(struct net *net, const void __user *user,
local_bh_disable();
private = t->private;
- if (private->number != num_counters) {
+ if (private->number != tmp.num_counters) {
ret = -EINVAL;
goto unlock_up_free;
}
@@ -1199,6 +1168,18 @@ static int do_add_counters(struct net *net, const void __user *user,
}
#ifdef CONFIG_COMPAT
+struct compat_arpt_replace {
+ char name[XT_TABLE_MAXNAMELEN];
+ u32 valid_hooks;
+ u32 num_entries;
+ u32 size;
+ u32 hook_entry[NF_ARP_NUMHOOKS];
+ u32 underflow[NF_ARP_NUMHOOKS];
+ u32 num_counters;
+ compat_uptr_t counters;
+ struct compat_arpt_entry entries[0];
+};
+
static inline void compat_release_entry(struct compat_arpt_entry *e)
{
struct xt_entry_target *t;
@@ -1207,24 +1188,22 @@ static inline void compat_release_entry(struct compat_arpt_entry *e)
module_put(t->u.kernel.target->me);
}
-static inline int
+static int
check_compat_entry_size_and_hooks(struct compat_arpt_entry *e,
struct xt_table_info *newinfo,
unsigned int *size,
const unsigned char *base,
- const unsigned char *limit,
- const unsigned int *hook_entries,
- const unsigned int *underflows,
- const char *name)
+ const unsigned char *limit)
{
struct xt_entry_target *t;
struct xt_target *target;
unsigned int entry_offset;
- int ret, off, h;
+ int ret, off;
duprintf("check_compat_entry_size_and_hooks %p\n", e);
if ((unsigned long)e % __alignof__(struct compat_arpt_entry) != 0 ||
- (unsigned char *)e + sizeof(struct compat_arpt_entry) >= limit) {
+ (unsigned char *)e + sizeof(struct compat_arpt_entry) >= limit ||
+ (unsigned char *)e + e->next_offset > limit) {
duprintf("Bad offset %p, limit = %p\n", e, limit);
return -EINVAL;
}
@@ -1236,8 +1215,11 @@ check_compat_entry_size_and_hooks(struct compat_arpt_entry *e,
return -EINVAL;
}
- /* For purposes of check_entry casting the compat entry is fine */
- ret = check_entry((struct arpt_entry *)e, name);
+ if (!arp_checkentry(&e->arp))
+ return -EINVAL;
+
+ ret = xt_compat_check_entry_offsets(e, e->elems, e->target_offset,
+ e->next_offset);
if (ret)
return ret;
@@ -1261,17 +1243,6 @@ check_compat_entry_size_and_hooks(struct compat_arpt_entry *e,
if (ret)
goto release_target;
- /* Check hooks & underflows */
- for (h = 0; h < NF_ARP_NUMHOOKS; h++) {
- if ((unsigned char *)e - base == hook_entries[h])
- newinfo->hook_entry[h] = hook_entries[h];
- if ((unsigned char *)e - base == underflows[h])
- newinfo->underflow[h] = underflows[h];
- }
-
- /* Clear counters and comefrom */
- memset(&e->counters, 0, sizeof(e->counters));
- e->comefrom = 0;
return 0;
release_target:
@@ -1280,18 +1251,17 @@ out:
return ret;
}
-static int
+static void
compat_copy_entry_from_user(struct compat_arpt_entry *e, void **dstptr,
- unsigned int *size, const char *name,
+ unsigned int *size,
struct xt_table_info *newinfo, unsigned char *base)
{
struct xt_entry_target *t;
struct xt_target *target;
struct arpt_entry *de;
unsigned int origsize;
- int ret, h;
+ int h;
- ret = 0;
origsize = *size;
de = (struct arpt_entry *)*dstptr;
memcpy(de, e, sizeof(struct arpt_entry));
@@ -1312,144 +1282,81 @@ compat_copy_entry_from_user(struct compat_arpt_entry *e, void **dstptr,
if ((unsigned char *)de - base < newinfo->underflow[h])
newinfo->underflow[h] -= origsize - *size;
}
- return ret;
}
-static int translate_compat_table(const char *name,
- unsigned int valid_hooks,
- struct xt_table_info **pinfo,
+static int translate_compat_table(struct xt_table_info **pinfo,
void **pentry0,
- unsigned int total_size,
- unsigned int number,
- unsigned int *hook_entries,
- unsigned int *underflows)
+ const struct compat_arpt_replace *compatr)
{
unsigned int i, j;
struct xt_table_info *newinfo, *info;
void *pos, *entry0, *entry1;
struct compat_arpt_entry *iter0;
- struct arpt_entry *iter1;
+ struct arpt_replace repl;
unsigned int size;
int ret = 0;
info = *pinfo;
entry0 = *pentry0;
- size = total_size;
- info->number = number;
-
- /* Init all hooks to impossible value. */
- for (i = 0; i < NF_ARP_NUMHOOKS; i++) {
- info->hook_entry[i] = 0xFFFFFFFF;
- info->underflow[i] = 0xFFFFFFFF;
- }
+ size = compatr->size;
+ info->number = compatr->num_entries;
duprintf("translate_compat_table: size %u\n", info->size);
j = 0;
xt_compat_lock(NFPROTO_ARP);
- xt_compat_init_offsets(NFPROTO_ARP, number);
+ xt_compat_init_offsets(NFPROTO_ARP, compatr->num_entries);
/* Walk through entries, checking offsets. */
- xt_entry_foreach(iter0, entry0, total_size) {
+ xt_entry_foreach(iter0, entry0, compatr->size) {
ret = check_compat_entry_size_and_hooks(iter0, info, &size,
entry0,
- entry0 + total_size,
- hook_entries,
- underflows,
- name);
+ entry0 + compatr->size);
if (ret != 0)
goto out_unlock;
++j;
}
ret = -EINVAL;
- if (j != number) {
+ if (j != compatr->num_entries) {
duprintf("translate_compat_table: %u not %u entries\n",
- j, number);
+ j, compatr->num_entries);
goto out_unlock;
}
- /* Check hooks all assigned */
- for (i = 0; i < NF_ARP_NUMHOOKS; i++) {
- /* Only hooks which are valid */
- if (!(valid_hooks & (1 << i)))
- continue;
- if (info->hook_entry[i] == 0xFFFFFFFF) {
- duprintf("Invalid hook entry %u %u\n",
- i, hook_entries[i]);
- goto out_unlock;
- }
- if (info->underflow[i] == 0xFFFFFFFF) {
- duprintf("Invalid underflow %u %u\n",
- i, underflows[i]);
- goto out_unlock;
- }
- }
-
ret = -ENOMEM;
newinfo = xt_alloc_table_info(size);
if (!newinfo)
goto out_unlock;
- newinfo->number = number;
+ newinfo->number = compatr->num_entries;
for (i = 0; i < NF_ARP_NUMHOOKS; i++) {
newinfo->hook_entry[i] = info->hook_entry[i];
newinfo->underflow[i] = info->underflow[i];
}
entry1 = newinfo->entries[raw_smp_processor_id()];
pos = entry1;
- size = total_size;
- xt_entry_foreach(iter0, entry0, total_size) {
- ret = compat_copy_entry_from_user(iter0, &pos, &size,
- name, newinfo, entry1);
- if (ret != 0)
- break;
- }
+ size = compatr->size;
+ xt_entry_foreach(iter0, entry0, compatr->size)
+ compat_copy_entry_from_user(iter0, &pos, &size,
+ newinfo, entry1);
+
+ /* all module references in entry0 are now gone */
+
xt_compat_flush_offsets(NFPROTO_ARP);
xt_compat_unlock(NFPROTO_ARP);
- if (ret)
- goto free_newinfo;
- ret = -ELOOP;
- if (!mark_source_chains(newinfo, valid_hooks, entry1))
- goto free_newinfo;
+ memcpy(&repl, compatr, sizeof(*compatr));
- i = 0;
- xt_entry_foreach(iter1, entry1, newinfo->size) {
- ret = check_target(iter1, name);
- if (ret != 0)
- break;
- ++i;
- if (strcmp(arpt_get_target(iter1)->u.user.name,
- XT_ERROR_TARGET) == 0)
- ++newinfo->stacksize;
- }
- if (ret) {
- /*
- * The first i matches need cleanup_entry (calls ->destroy)
- * because they had called ->check already. The other j-i
- * entries need only release.
- */
- int skip = i;
- j -= i;
- xt_entry_foreach(iter0, entry0, newinfo->size) {
- if (skip-- > 0)
- continue;
- if (j-- == 0)
- break;
- compat_release_entry(iter0);
- }
- xt_entry_foreach(iter1, entry1, newinfo->size) {
- if (i-- == 0)
- break;
- cleanup_entry(iter1);
- }
- xt_free_table_info(newinfo);
- return ret;
+ for (i = 0; i < NF_ARP_NUMHOOKS; i++) {
+ repl.hook_entry[i] = newinfo->hook_entry[i];
+ repl.underflow[i] = newinfo->underflow[i];
}
- /* And one copy for every other CPU */
- for_each_possible_cpu(i)
- if (newinfo->entries[i] && newinfo->entries[i] != entry1)
- memcpy(newinfo->entries[i], entry1, newinfo->size);
+ repl.num_counters = 0;
+ repl.counters = NULL;
+ repl.size = newinfo->size;
+ ret = translate_table(newinfo, entry1, &repl);
+ if (ret)
+ goto free_newinfo;
*pinfo = newinfo;
*pentry0 = entry1;
@@ -1458,31 +1365,18 @@ static int translate_compat_table(const char *name,
free_newinfo:
xt_free_table_info(newinfo);
-out:
- xt_entry_foreach(iter0, entry0, total_size) {
+ return ret;
+out_unlock:
+ xt_compat_flush_offsets(NFPROTO_ARP);
+ xt_compat_unlock(NFPROTO_ARP);
+ xt_entry_foreach(iter0, entry0, compatr->size) {
if (j-- == 0)
break;
compat_release_entry(iter0);
}
return ret;
-out_unlock:
- xt_compat_flush_offsets(NFPROTO_ARP);
- xt_compat_unlock(NFPROTO_ARP);
- goto out;
}
-struct compat_arpt_replace {
- char name[XT_TABLE_MAXNAMELEN];
- u32 valid_hooks;
- u32 num_entries;
- u32 size;
- u32 hook_entry[NF_ARP_NUMHOOKS];
- u32 underflow[NF_ARP_NUMHOOKS];
- u32 num_counters;
- compat_uptr_t counters;
- struct compat_arpt_entry entries[0];
-};
-
static int compat_do_replace(struct net *net, void __user *user,
unsigned int len)
{
@@ -1513,10 +1407,7 @@ static int compat_do_replace(struct net *net, void __user *user,
goto free_newinfo;
}
- ret = translate_compat_table(tmp.name, tmp.valid_hooks,
- &newinfo, &loc_cpu_entry, tmp.size,
- tmp.num_entries, tmp.hook_entry,
- tmp.underflow);
+ ret = translate_compat_table(&newinfo, &loc_cpu_entry, &tmp);
if (ret != 0)
goto free_newinfo;
diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c
index 99e810f84671..4e40f2ec2b68 100644
--- a/net/ipv4/netfilter/ip_tables.c
+++ b/net/ipv4/netfilter/ip_tables.c
@@ -168,11 +168,12 @@ get_entry(const void *base, unsigned int offset)
/* All zeroes == unconditional rule. */
/* Mildly perf critical (only if packet tracing is on) */
-static inline bool unconditional(const struct ipt_ip *ip)
+static inline bool unconditional(const struct ipt_entry *e)
{
static const struct ipt_ip uncond;
- return memcmp(ip, &uncond, sizeof(uncond)) == 0;
+ return e->target_offset == sizeof(struct ipt_entry) &&
+ memcmp(&e->ip, &uncond, sizeof(uncond)) == 0;
#undef FWINV
}
@@ -229,11 +230,10 @@ get_chainname_rulenum(const struct ipt_entry *s, const struct ipt_entry *e,
} else if (s == e) {
(*rulenum)++;
- if (s->target_offset == sizeof(struct ipt_entry) &&
+ if (unconditional(s) &&
strcmp(t->target.u.kernel.target->name,
XT_STANDARD_TARGET) == 0 &&
- t->verdict < 0 &&
- unconditional(&s->ip)) {
+ t->verdict < 0) {
/* Tail of chains: STANDARD target (return/policy) */
*comment = *chainname == hookname
? comments[NF_IP_TRACE_COMMENT_POLICY]
@@ -443,7 +443,8 @@ ipt_do_table(struct sk_buff *skb,
there are loops. Puts hook bitmask in comefrom. */
static int
mark_source_chains(const struct xt_table_info *newinfo,
- unsigned int valid_hooks, void *entry0)
+ unsigned int valid_hooks, void *entry0,
+ unsigned int *offsets)
{
unsigned int hook;
@@ -472,11 +473,10 @@ mark_source_chains(const struct xt_table_info *newinfo,
e->comefrom |= ((1 << hook) | (1 << NF_INET_NUMHOOKS));
/* Unconditional return/END. */
- if ((e->target_offset == sizeof(struct ipt_entry) &&
+ if ((unconditional(e) &&
(strcmp(t->target.u.user.name,
XT_STANDARD_TARGET) == 0) &&
- t->verdict < 0 && unconditional(&e->ip)) ||
- visited) {
+ t->verdict < 0) || visited) {
unsigned int oldpos, size;
if ((strcmp(t->target.u.user.name,
@@ -517,6 +517,8 @@ mark_source_chains(const struct xt_table_info *newinfo,
size = e->next_offset;
e = (struct ipt_entry *)
(entry0 + pos + size);
+ if (pos + size >= newinfo->size)
+ return 0;
e->counters.pcnt = pos;
pos += size;
} else {
@@ -535,9 +537,16 @@ mark_source_chains(const struct xt_table_info *newinfo,
/* This a jump; chase it. */
duprintf("Jump rule %u -> %u\n",
pos, newpos);
+ if (!xt_find_jump_offset(offsets, newpos,
+ newinfo->number))
+ return 0;
+ e = (struct ipt_entry *)
+ (entry0 + newpos);
} else {
/* ... this is a fallthru */
newpos = pos + e->next_offset;
+ if (newpos >= newinfo->size)
+ return 0;
}
e = (struct ipt_entry *)
(entry0 + newpos);
@@ -565,27 +574,6 @@ static void cleanup_match(struct xt_entry_match *m, struct net *net)
}
static int
-check_entry(const struct ipt_entry *e, const char *name)
-{
- const struct xt_entry_target *t;
-
- if (!ip_checkentry(&e->ip)) {
- duprintf("ip check failed %p %s.\n", e, name);
- return -EINVAL;
- }
-
- if (e->target_offset + sizeof(struct xt_entry_target) >
- e->next_offset)
- return -EINVAL;
-
- t = ipt_get_target_c(e);
- if (e->target_offset + t->u.target_size > e->next_offset)
- return -EINVAL;
-
- return 0;
-}
-
-static int
check_match(struct xt_entry_match *m, struct xt_mtchk_param *par)
{
const struct ipt_ip *ip = par->entryinfo;
@@ -662,10 +650,6 @@ find_check_entry(struct ipt_entry *e, struct net *net, const char *name,
struct xt_mtchk_param mtpar;
struct xt_entry_match *ematch;
- ret = check_entry(e, name);
- if (ret)
- return ret;
-
j = 0;
mtpar.net = net;
mtpar.table = name;
@@ -709,7 +693,7 @@ static bool check_underflow(const struct ipt_entry *e)
const struct xt_entry_target *t;
unsigned int verdict;
- if (!unconditional(&e->ip))
+ if (!unconditional(e))
return false;
t = ipt_get_target_c(e);
if (strcmp(t->u.user.name, XT_STANDARD_TARGET) != 0)
@@ -729,9 +713,11 @@ check_entry_size_and_hooks(struct ipt_entry *e,
unsigned int valid_hooks)
{
unsigned int h;
+ int err;
if ((unsigned long)e % __alignof__(struct ipt_entry) != 0 ||
- (unsigned char *)e + sizeof(struct ipt_entry) >= limit) {
+ (unsigned char *)e + sizeof(struct ipt_entry) >= limit ||
+ (unsigned char *)e + e->next_offset > limit) {
duprintf("Bad offset %p\n", e);
return -EINVAL;
}
@@ -743,6 +729,14 @@ check_entry_size_and_hooks(struct ipt_entry *e,
return -EINVAL;
}
+ if (!ip_checkentry(&e->ip))
+ return -EINVAL;
+
+ err = xt_check_entry_offsets(e, e->elems, e->target_offset,
+ e->next_offset);
+ if (err)
+ return err;
+
/* Check hooks & underflows */
for (h = 0; h < NF_INET_NUMHOOKS; h++) {
if (!(valid_hooks & (1 << h)))
@@ -751,9 +745,9 @@ check_entry_size_and_hooks(struct ipt_entry *e,
newinfo->hook_entry[h] = hook_entries[h];
if ((unsigned char *)e - base == underflows[h]) {
if (!check_underflow(e)) {
- pr_err("Underflows must be unconditional and "
- "use the STANDARD target with "
- "ACCEPT/DROP\n");
+ pr_debug("Underflows must be unconditional and "
+ "use the STANDARD target with "
+ "ACCEPT/DROP\n");
return -EINVAL;
}
newinfo->underflow[h] = underflows[h];
@@ -794,6 +788,7 @@ translate_table(struct net *net, struct xt_table_info *newinfo, void *entry0,
const struct ipt_replace *repl)
{
struct ipt_entry *iter;
+ unsigned int *offsets;
unsigned int i;
int ret = 0;
@@ -807,6 +802,9 @@ translate_table(struct net *net, struct xt_table_info *newinfo, void *entry0,
}
duprintf("translate_table: size %u\n", newinfo->size);
+ offsets = xt_alloc_entry_offsets(newinfo->number);
+ if (!offsets)
+ return -ENOMEM;
i = 0;
/* Walk through entries, checking offsets. */
xt_entry_foreach(iter, entry0, newinfo->size) {
@@ -816,17 +814,20 @@ translate_table(struct net *net, struct xt_table_info *newinfo, void *entry0,
repl->underflow,
repl->valid_hooks);
if (ret != 0)
- return ret;
+ goto out_free;
+ if (i < repl->num_entries)
+ offsets[i] = (void *)iter - entry0;
++i;
if (strcmp(ipt_get_target(iter)->u.user.name,
XT_ERROR_TARGET) == 0)
++newinfo->stacksize;
}
+ ret = -EINVAL;
if (i != repl->num_entries) {
duprintf("translate_table: %u not %u entries\n",
i, repl->num_entries);
- return -EINVAL;
+ goto out_free;
}
/* Check hooks all assigned */
@@ -837,17 +838,20 @@ translate_table(struct net *net, struct xt_table_info *newinfo, void *entry0,
if (newinfo->hook_entry[i] == 0xFFFFFFFF) {
duprintf("Invalid hook entry %u %u\n",
i, repl->hook_entry[i]);
- return -EINVAL;
+ goto out_free;
}
if (newinfo->underflow[i] == 0xFFFFFFFF) {
duprintf("Invalid underflow %u %u\n",
i, repl->underflow[i]);
- return -EINVAL;
+ goto out_free;
}
}
- if (!mark_source_chains(newinfo, repl->valid_hooks, entry0))
- return -ELOOP;
+ if (!mark_source_chains(newinfo, repl->valid_hooks, entry0, offsets)) {
+ ret = -ELOOP;
+ goto out_free;
+ }
+ kvfree(offsets);
/* Finally, each sanity check must pass */
i = 0;
@@ -874,6 +878,9 @@ translate_table(struct net *net, struct xt_table_info *newinfo, void *entry0,
}
return ret;
+ out_free:
+ kvfree(offsets);
+ return ret;
}
static void
@@ -1304,56 +1311,18 @@ do_add_counters(struct net *net, const void __user *user,
unsigned int i, curcpu;
struct xt_counters_info tmp;
struct xt_counters *paddc;
- unsigned int num_counters;
- const char *name;
- int size;
- void *ptmp;
struct xt_table *t;
const struct xt_table_info *private;
int ret = 0;
void *loc_cpu_entry;
struct ipt_entry *iter;
unsigned int addend;
-#ifdef CONFIG_COMPAT
- struct compat_xt_counters_info compat_tmp;
-
- if (compat) {
- ptmp = &compat_tmp;
- size = sizeof(struct compat_xt_counters_info);
- } else
-#endif
- {
- ptmp = &tmp;
- size = sizeof(struct xt_counters_info);
- }
- if (copy_from_user(ptmp, user, size) != 0)
- return -EFAULT;
+ paddc = xt_copy_counters_from_user(user, len, &tmp, compat);
+ if (IS_ERR(paddc))
+ return PTR_ERR(paddc);
-#ifdef CONFIG_COMPAT
- if (compat) {
- num_counters = compat_tmp.num_counters;
- name = compat_tmp.name;
- } else
-#endif
- {
- num_counters = tmp.num_counters;
- name = tmp.name;
- }
-
- if (len != size + num_counters * sizeof(struct xt_counters))
- return -EINVAL;
-
- paddc = vmalloc(len - size);
- if (!paddc)
- return -ENOMEM;
-
- if (copy_from_user(paddc, user + size, len - size) != 0) {
- ret = -EFAULT;
- goto free;
- }
-
- t = xt_find_table_lock(net, AF_INET, name);
+ t = xt_find_table_lock(net, AF_INET, tmp.name);
if (IS_ERR_OR_NULL(t)) {
ret = t ? PTR_ERR(t) : -ENOENT;
goto free;
@@ -1361,7 +1330,7 @@ do_add_counters(struct net *net, const void __user *user,
local_bh_disable();
private = t->private;
- if (private->number != num_counters) {
+ if (private->number != tmp.num_counters) {
ret = -EINVAL;
goto unlock_up_free;
}
@@ -1440,7 +1409,6 @@ compat_copy_entry_to_user(struct ipt_entry *e, void __user **dstptr,
static int
compat_find_calc_match(struct xt_entry_match *m,
- const char *name,
const struct ipt_ip *ip,
unsigned int hookmask,
int *size)
@@ -1476,21 +1444,19 @@ check_compat_entry_size_and_hooks(struct compat_ipt_entry *e,
struct xt_table_info *newinfo,
unsigned int *size,
const unsigned char *base,
- const unsigned char *limit,
- const unsigned int *hook_entries,
- const unsigned int *underflows,
- const char *name)
+ const unsigned char *limit)
{
struct xt_entry_match *ematch;
struct xt_entry_target *t;
struct xt_target *target;
unsigned int entry_offset;
unsigned int j;
- int ret, off, h;
+ int ret, off;
duprintf("check_compat_entry_size_and_hooks %p\n", e);
if ((unsigned long)e % __alignof__(struct compat_ipt_entry) != 0 ||
- (unsigned char *)e + sizeof(struct compat_ipt_entry) >= limit) {
+ (unsigned char *)e + sizeof(struct compat_ipt_entry) >= limit ||
+ (unsigned char *)e + e->next_offset > limit) {
duprintf("Bad offset %p, limit = %p\n", e, limit);
return -EINVAL;
}
@@ -1502,8 +1468,11 @@ check_compat_entry_size_and_hooks(struct compat_ipt_entry *e,
return -EINVAL;
}
- /* For purposes of check_entry casting the compat entry is fine */
- ret = check_entry((struct ipt_entry *)e, name);
+ if (!ip_checkentry(&e->ip))
+ return -EINVAL;
+
+ ret = xt_compat_check_entry_offsets(e, e->elems,
+ e->target_offset, e->next_offset);
if (ret)
return ret;
@@ -1511,8 +1480,8 @@ check_compat_entry_size_and_hooks(struct compat_ipt_entry *e,
entry_offset = (void *)e - (void *)base;
j = 0;
xt_ematch_foreach(ematch, e) {
- ret = compat_find_calc_match(ematch, name,
- &e->ip, e->comefrom, &off);
+ ret = compat_find_calc_match(ematch, &e->ip, e->comefrom,
+ &off);
if (ret != 0)
goto release_matches;
++j;
@@ -1535,17 +1504,6 @@ check_compat_entry_size_and_hooks(struct compat_ipt_entry *e,
if (ret)
goto out;
- /* Check hooks & underflows */
- for (h = 0; h < NF_INET_NUMHOOKS; h++) {
- if ((unsigned char *)e - base == hook_entries[h])
- newinfo->hook_entry[h] = hook_entries[h];
- if ((unsigned char *)e - base == underflows[h])
- newinfo->underflow[h] = underflows[h];
- }
-
- /* Clear counters and comefrom */
- memset(&e->counters, 0, sizeof(e->counters));
- e->comefrom = 0;
return 0;
out:
@@ -1559,19 +1517,18 @@ release_matches:
return ret;
}
-static int
+static void
compat_copy_entry_from_user(struct compat_ipt_entry *e, void **dstptr,
- unsigned int *size, const char *name,
+ unsigned int *size,
struct xt_table_info *newinfo, unsigned char *base)
{
struct xt_entry_target *t;
struct xt_target *target;
struct ipt_entry *de;
unsigned int origsize;
- int ret, h;
+ int h;
struct xt_entry_match *ematch;
- ret = 0;
origsize = *size;
de = (struct ipt_entry *)*dstptr;
memcpy(de, e, sizeof(struct ipt_entry));
@@ -1580,198 +1537,104 @@ compat_copy_entry_from_user(struct compat_ipt_entry *e, void **dstptr,
*dstptr += sizeof(struct ipt_entry);
*size += sizeof(struct ipt_entry) - sizeof(struct compat_ipt_entry);
- xt_ematch_foreach(ematch, e) {
- ret = xt_compat_match_from_user(ematch, dstptr, size);
- if (ret != 0)
- return ret;
- }
+ xt_ematch_foreach(ematch, e)
+ xt_compat_match_from_user(ematch, dstptr, size);
+
de->target_offset = e->target_offset - (origsize - *size);
t = compat_ipt_get_target(e);
target = t->u.kernel.target;
xt_compat_target_from_user(t, dstptr, size);
de->next_offset = e->next_offset - (origsize - *size);
+
for (h = 0; h < NF_INET_NUMHOOKS; h++) {
if ((unsigned char *)de - base < newinfo->hook_entry[h])
newinfo->hook_entry[h] -= origsize - *size;
if ((unsigned char *)de - base < newinfo->underflow[h])
newinfo->underflow[h] -= origsize - *size;
}
- return ret;
-}
-
-static int
-compat_check_entry(struct ipt_entry *e, struct net *net, const char *name)
-{
- struct xt_entry_match *ematch;
- struct xt_mtchk_param mtpar;
- unsigned int j;
- int ret = 0;
-
- j = 0;
- mtpar.net = net;
- mtpar.table = name;
- mtpar.entryinfo = &e->ip;
- mtpar.hook_mask = e->comefrom;
- mtpar.family = NFPROTO_IPV4;
- xt_ematch_foreach(ematch, e) {
- ret = check_match(ematch, &mtpar);
- if (ret != 0)
- goto cleanup_matches;
- ++j;
- }
-
- ret = check_target(e, net, name);
- if (ret)
- goto cleanup_matches;
- return 0;
-
- cleanup_matches:
- xt_ematch_foreach(ematch, e) {
- if (j-- == 0)
- break;
- cleanup_match(ematch, net);
- }
- return ret;
}
static int
translate_compat_table(struct net *net,
- const char *name,
- unsigned int valid_hooks,
struct xt_table_info **pinfo,
void **pentry0,
- unsigned int total_size,
- unsigned int number,
- unsigned int *hook_entries,
- unsigned int *underflows)
+ const struct compat_ipt_replace *compatr)
{
unsigned int i, j;
struct xt_table_info *newinfo, *info;
void *pos, *entry0, *entry1;
struct compat_ipt_entry *iter0;
- struct ipt_entry *iter1;
+ struct ipt_replace repl;
unsigned int size;
int ret;
info = *pinfo;
entry0 = *pentry0;
- size = total_size;
- info->number = number;
-
- /* Init all hooks to impossible value. */
- for (i = 0; i < NF_INET_NUMHOOKS; i++) {
- info->hook_entry[i] = 0xFFFFFFFF;
- info->underflow[i] = 0xFFFFFFFF;
- }
+ size = compatr->size;
+ info->number = compatr->num_entries;
duprintf("translate_compat_table: size %u\n", info->size);
j = 0;
xt_compat_lock(AF_INET);
- xt_compat_init_offsets(AF_INET, number);
+ xt_compat_init_offsets(AF_INET, compatr->num_entries);
/* Walk through entries, checking offsets. */
- xt_entry_foreach(iter0, entry0, total_size) {
+ xt_entry_foreach(iter0, entry0, compatr->size) {
ret = check_compat_entry_size_and_hooks(iter0, info, &size,
entry0,
- entry0 + total_size,
- hook_entries,
- underflows,
- name);
+ entry0 + compatr->size);
if (ret != 0)
goto out_unlock;
++j;
}
ret = -EINVAL;
- if (j != number) {
+ if (j != compatr->num_entries) {
duprintf("translate_compat_table: %u not %u entries\n",
- j, number);
+ j, compatr->num_entries);
goto out_unlock;
}
- /* Check hooks all assigned */
- for (i = 0; i < NF_INET_NUMHOOKS; i++) {
- /* Only hooks which are valid */
- if (!(valid_hooks & (1 << i)))
- continue;
- if (info->hook_entry[i] == 0xFFFFFFFF) {
- duprintf("Invalid hook entry %u %u\n",
- i, hook_entries[i]);
- goto out_unlock;
- }
- if (info->underflow[i] == 0xFFFFFFFF) {
- duprintf("Invalid underflow %u %u\n",
- i, underflows[i]);
- goto out_unlock;
- }
- }
-
ret = -ENOMEM;
newinfo = xt_alloc_table_info(size);
if (!newinfo)
goto out_unlock;
- newinfo->number = number;
+ newinfo->number = compatr->num_entries;
for (i = 0; i < NF_INET_NUMHOOKS; i++) {
- newinfo->hook_entry[i] = info->hook_entry[i];
- newinfo->underflow[i] = info->underflow[i];
+ newinfo->hook_entry[i] = compatr->hook_entry[i];
+ newinfo->underflow[i] = compatr->underflow[i];
}
entry1 = newinfo->entries[raw_smp_processor_id()];
pos = entry1;
- size = total_size;
- xt_entry_foreach(iter0, entry0, total_size) {
- ret = compat_copy_entry_from_user(iter0, &pos, &size,
- name, newinfo, entry1);
- if (ret != 0)
- break;
- }
+ size = compatr->size;
+ xt_entry_foreach(iter0, entry0, compatr->size)
+ compat_copy_entry_from_user(iter0, &pos, &size,
+ newinfo, entry1);
+
+ /* all module references in entry0 are now gone.
+ * entry1/newinfo contains a 64bit ruleset that looks exactly as
+ * generated by 64bit userspace.
+ *
+ * Call standard translate_table() to validate all hook_entrys,
+ * underflows, check for loops, etc.
+ */
xt_compat_flush_offsets(AF_INET);
xt_compat_unlock(AF_INET);
- if (ret)
- goto free_newinfo;
- ret = -ELOOP;
- if (!mark_source_chains(newinfo, valid_hooks, entry1))
- goto free_newinfo;
+ memcpy(&repl, compatr, sizeof(*compatr));
- i = 0;
- xt_entry_foreach(iter1, entry1, newinfo->size) {
- ret = compat_check_entry(iter1, net, name);
- if (ret != 0)
- break;
- ++i;
- if (strcmp(ipt_get_target(iter1)->u.user.name,
- XT_ERROR_TARGET) == 0)
- ++newinfo->stacksize;
- }
- if (ret) {
- /*
- * The first i matches need cleanup_entry (calls ->destroy)
- * because they had called ->check already. The other j-i
- * entries need only release.
- */
- int skip = i;
- j -= i;
- xt_entry_foreach(iter0, entry0, newinfo->size) {
- if (skip-- > 0)
- continue;
- if (j-- == 0)
- break;
- compat_release_entry(iter0);
- }
- xt_entry_foreach(iter1, entry1, newinfo->size) {
- if (i-- == 0)
- break;
- cleanup_entry(iter1, net);
- }
- xt_free_table_info(newinfo);
- return ret;
+ for (i = 0; i < NF_INET_NUMHOOKS; i++) {
+ repl.hook_entry[i] = newinfo->hook_entry[i];
+ repl.underflow[i] = newinfo->underflow[i];
}
- /* And one copy for every other CPU */
- for_each_possible_cpu(i)
- if (newinfo->entries[i] && newinfo->entries[i] != entry1)
- memcpy(newinfo->entries[i], entry1, newinfo->size);
+ repl.num_counters = 0;
+ repl.counters = NULL;
+ repl.size = newinfo->size;
+ ret = translate_table(net, newinfo, entry1, &repl);
+ if (ret)
+ goto free_newinfo;
*pinfo = newinfo;
*pentry0 = entry1;
@@ -1780,17 +1643,16 @@ translate_compat_table(struct net *net,
free_newinfo:
xt_free_table_info(newinfo);
-out:
- xt_entry_foreach(iter0, entry0, total_size) {
+ return ret;
+out_unlock:
+ xt_compat_flush_offsets(AF_INET);
+ xt_compat_unlock(AF_INET);
+ xt_entry_foreach(iter0, entry0, compatr->size) {
if (j-- == 0)
break;
compat_release_entry(iter0);
}
return ret;
-out_unlock:
- xt_compat_flush_offsets(AF_INET);
- xt_compat_unlock(AF_INET);
- goto out;
}
static int
@@ -1824,10 +1686,7 @@ compat_do_replace(struct net *net, void __user *user, unsigned int len)
goto free_newinfo;
}
- ret = translate_compat_table(net, tmp.name, tmp.valid_hooks,
- &newinfo, &loc_cpu_entry, tmp.size,
- tmp.num_entries, tmp.hook_entry,
- tmp.underflow);
+ ret = translate_compat_table(net, &newinfo, &loc_cpu_entry, &tmp);
if (ret != 0)
goto free_newinfo;
diff --git a/net/ipv4/netfilter/nf_nat_masquerade_ipv4.c b/net/ipv4/netfilter/nf_nat_masquerade_ipv4.c
index c6eb42100e9a..ea91058b5f6f 100644
--- a/net/ipv4/netfilter/nf_nat_masquerade_ipv4.c
+++ b/net/ipv4/netfilter/nf_nat_masquerade_ipv4.c
@@ -108,10 +108,18 @@ static int masq_inet_event(struct notifier_block *this,
unsigned long event,
void *ptr)
{
- struct net_device *dev = ((struct in_ifaddr *)ptr)->ifa_dev->dev;
+ struct in_device *idev = ((struct in_ifaddr *)ptr)->ifa_dev;
struct netdev_notifier_info info;
- netdev_notifier_info_init(&info, dev);
+ /* The masq_dev_notifier will catch the case of the device going
+ * down. So if the inetdev is dead and being destroyed we have
+ * no work to do. Otherwise this is an individual address removal
+ * and we have to perform the flush.
+ */
+ if (idev->dead)
+ return NOTIFY_DONE;
+
+ netdev_notifier_info_init(&info, idev->dev);
return masq_device_event(this, event, &info);
}
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index d58dd0ec3e53..12c5df33c0b7 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -903,6 +903,10 @@ static int ip_error(struct sk_buff *skb)
bool send;
int code;
+ /* IP on this device is disabled. */
+ if (!in_dev)
+ goto out;
+
net = dev_net(rt->dst.dev);
if (!IN_DEV_FORWARD(in_dev)) {
switch (rt->dst.error) {
@@ -1920,6 +1924,18 @@ static struct rtable *__mkroute_output(const struct fib_result *res,
*/
if (fi && res->prefixlen < 4)
fi = NULL;
+ } else if ((type == RTN_LOCAL) && (orig_oif != 0) &&
+ (orig_oif != dev_out->ifindex)) {
+ /* For local routes that require a particular output interface
+ * we do not want to cache the result. Caching the result
+ * causes incorrect behaviour when there are multiple source
+ * addresses on the interface, the end result being that if the
+ * intended recipient is waiting on that interface for the
+ * packet he won't receive it because it will be delivered on
+ * the loopback interface and the IP_PKTINFO ipi_ifindex will
+ * be set to the loopback interface as well.
+ */
+ fi = NULL;
}
fnhe = NULL;
diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index 9096dbb067d1..034e4c0e2121 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -45,10 +45,10 @@ static int ip_ping_group_range_max[] = { GID_T_MAX, GID_T_MAX };
/* Update system visible IP port range */
static void set_local_port_range(struct net *net, int range[2])
{
- write_seqlock(&net->ipv4.ip_local_ports.lock);
+ write_seqlock_bh(&net->ipv4.ip_local_ports.lock);
net->ipv4.ip_local_ports.range[0] = range[0];
net->ipv4.ip_local_ports.range[1] = range[1];
- write_sequnlock(&net->ipv4.ip_local_ports.lock);
+ write_sequnlock_bh(&net->ipv4.ip_local_ports.lock);
}
/* Validate changes from /proc interface. */
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 38c2bcb8dd5d..32b25cc96fff 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -2585,10 +2585,13 @@ static int do_tcp_setsockopt(struct sock *sk, int level,
case TCP_FASTOPEN:
if (val >= 0 && ((1 << sk->sk_state) & (TCPF_CLOSE |
- TCPF_LISTEN)))
+ TCPF_LISTEN))) {
+ tcp_fastopen_init_key_once(true);
+
err = fastopen_init_queue(sk, val);
- else
+ } else {
err = -EINVAL;
+ }
break;
case TCP_TIMESTAMP:
if (!tp->repair)
@@ -2639,6 +2642,7 @@ void tcp_get_info(const struct sock *sk, struct tcp_info *info)
const struct tcp_sock *tp = tcp_sk(sk);
const struct inet_connection_sock *icsk = inet_csk(sk);
u32 now = tcp_time_stamp;
+ u32 rate;
memset(info, 0, sizeof(*info));
@@ -2699,10 +2703,11 @@ void tcp_get_info(const struct sock *sk, struct tcp_info *info)
info->tcpi_total_retrans = tp->total_retrans;
- info->tcpi_pacing_rate = sk->sk_pacing_rate != ~0U ?
- sk->sk_pacing_rate : ~0ULL;
- info->tcpi_max_pacing_rate = sk->sk_max_pacing_rate != ~0U ?
- sk->sk_max_pacing_rate : ~0ULL;
+ rate = READ_ONCE(sk->sk_pacing_rate);
+ info->tcpi_pacing_rate = rate != ~0U ? rate : ~0ULL;
+
+ rate = READ_ONCE(sk->sk_max_pacing_rate);
+ info->tcpi_max_pacing_rate = rate != ~0U ? rate : ~0ULL;
}
EXPORT_SYMBOL_GPL(tcp_get_info);
diff --git a/net/ipv4/tcp_cong.c b/net/ipv4/tcp_cong.c
index b1c5970d47a1..b3316c8279a0 100644
--- a/net/ipv4/tcp_cong.c
+++ b/net/ipv4/tcp_cong.c
@@ -248,9 +248,10 @@ int tcp_set_congestion_control(struct sock *sk, const char *name)
ca = tcp_ca_find(name);
/* no change asking for existing value */
- if (ca == icsk->icsk_ca_ops)
+ if (ca == icsk->icsk_ca_ops) {
+ icsk->icsk_ca_setsockopt = 1;
goto out;
-
+ }
#ifdef CONFIG_MODULES
/* not found attempt to autoload module */
if (!ca && capable(CAP_NET_ADMIN)) {
@@ -273,6 +274,7 @@ int tcp_set_congestion_control(struct sock *sk, const char *name)
else {
tcp_cleanup_congestion_control(sk);
icsk->icsk_ca_ops = ca;
+ icsk->icsk_ca_setsockopt = 1;
if (sk->sk_state != TCP_CLOSE && icsk->icsk_ca_ops->init)
icsk->icsk_ca_ops->init(sk);
diff --git a/net/ipv4/tcp_cubic.c b/net/ipv4/tcp_cubic.c
index 20de0118c98e..9332ec123a6c 100644
--- a/net/ipv4/tcp_cubic.c
+++ b/net/ipv4/tcp_cubic.c
@@ -154,6 +154,27 @@ static void bictcp_init(struct sock *sk)
tcp_sk(sk)->snd_ssthresh = initial_ssthresh;
}
+static void bictcp_cwnd_event(struct sock *sk, enum tcp_ca_event event)
+{
+ if (event == CA_EVENT_TX_START) {
+ struct bictcp *ca = inet_csk_ca(sk);
+ u32 now = tcp_time_stamp;
+ s32 delta;
+
+ delta = now - tcp_sk(sk)->lsndtime;
+
+ /* We were application limited (idle) for a while.
+ * Shift epoch_start to keep cwnd growth to cubic curve.
+ */
+ if (ca->epoch_start && delta > 0) {
+ ca->epoch_start += delta;
+ if (after(ca->epoch_start, now))
+ ca->epoch_start = now;
+ }
+ return;
+ }
+}
+
/* calculate the cubic root of x using a table lookup followed by one
* Newton-Raphson iteration.
* Avg err ~= 0.195%
@@ -440,6 +461,7 @@ static struct tcp_congestion_ops cubictcp __read_mostly = {
.cong_avoid = bictcp_cong_avoid,
.set_state = bictcp_state,
.undo_cwnd = bictcp_undo_cwnd,
+ .cwnd_event = bictcp_cwnd_event,
.pkts_acked = bictcp_acked,
.owner = THIS_MODULE,
.name = "cubic",
diff --git a/net/ipv4/tcp_fastopen.c b/net/ipv4/tcp_fastopen.c
index c73077280ad4..b01d5bd6d6ca 100644
--- a/net/ipv4/tcp_fastopen.c
+++ b/net/ipv4/tcp_fastopen.c
@@ -78,8 +78,6 @@ static bool __tcp_fastopen_cookie_gen(const void *path,
struct tcp_fastopen_context *ctx;
bool ok = false;
- tcp_fastopen_init_key_once(true);
-
rcu_read_lock();
ctx = rcu_dereference(tcp_fastopen_ctx);
if (ctx) {
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 6f46cde58e54..0c96055b2382 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -4356,19 +4356,34 @@ static int __must_check tcp_queue_rcv(struct sock *sk, struct sk_buff *skb, int
int tcp_send_rcvq(struct sock *sk, struct msghdr *msg, size_t size)
{
struct sk_buff *skb;
+ int err = -ENOMEM;
+ int data_len = 0;
bool fragstolen;
if (size == 0)
return 0;
- skb = alloc_skb(size, sk->sk_allocation);
+ if (size > PAGE_SIZE) {
+ int npages = min_t(size_t, size >> PAGE_SHIFT, MAX_SKB_FRAGS);
+
+ data_len = npages << PAGE_SHIFT;
+ size = data_len + (size & ~PAGE_MASK);
+ }
+ skb = alloc_skb_with_frags(size - data_len, data_len,
+ PAGE_ALLOC_COSTLY_ORDER,
+ &err, sk->sk_allocation);
if (!skb)
goto err;
+ skb_put(skb, size - data_len);
+ skb->data_len = data_len;
+ skb->len = size;
+
if (tcp_try_rmem_schedule(sk, skb, skb->truesize))
goto err_free;
- if (memcpy_fromiovec(skb_put(skb, size), msg->msg_iov, size))
+ err = skb_copy_datagram_iovec(skb, 0, msg->msg_iov, size);
+ if (err)
goto err_free;
TCP_SKB_CB(skb)->seq = tcp_sk(sk)->rcv_nxt;
@@ -4384,7 +4399,8 @@ int tcp_send_rcvq(struct sock *sk, struct msghdr *msg, size_t size)
err_free:
kfree_skb(skb);
err:
- return -ENOMEM;
+ return err;
+
}
static void tcp_data_queue(struct sock *sk, struct sk_buff *skb)
@@ -5524,6 +5540,7 @@ discard:
}
tp->rcv_nxt = TCP_SKB_CB(skb)->seq + 1;
+ tp->copied_seq = tp->rcv_nxt;
tp->rcv_wup = TCP_SKB_CB(skb)->seq + 1;
/* RFC1323: The window in SYN & SYN/ACK segments is
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index a5fdfe9fa542..5d5390299277 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -959,7 +959,8 @@ int tcp_md5_do_add(struct sock *sk, const union tcp_md5_addr *addr,
}
md5sig = rcu_dereference_protected(tp->md5sig_info,
- sock_owned_by_user(sk));
+ sock_owned_by_user(sk) ||
+ lockdep_is_held(&sk->sk_lock.slock));
if (!md5sig) {
md5sig = kmalloc(sizeof(*md5sig), gfp);
if (!md5sig)
@@ -1552,7 +1553,7 @@ bool tcp_prequeue(struct sock *sk, struct sk_buff *skb)
if (likely(sk->sk_rx_dst))
skb_dst_drop(skb);
else
- skb_dst_force(skb);
+ skb_dst_force_safe(skb);
__skb_queue_tail(&tp->ucopy.prequeue, skb);
tp->ucopy.memory += skb->truesize;
@@ -1757,8 +1758,7 @@ void inet_sk_rx_dst_set(struct sock *sk, const struct sk_buff *skb)
{
struct dst_entry *dst = skb_dst(skb);
- if (dst) {
- dst_hold(dst);
+ if (dst && dst_hold_safe(dst)) {
sk->sk_rx_dst = dst;
inet_sk(sk)->rx_dst_ifindex = skb->skb_iif;
}
diff --git a/net/ipv4/tcp_metrics.c b/net/ipv4/tcp_metrics.c
index ed9c9a91851c..c90e76c2eca0 100644
--- a/net/ipv4/tcp_metrics.c
+++ b/net/ipv4/tcp_metrics.c
@@ -550,7 +550,7 @@ reset:
*/
if (crtt > tp->srtt_us) {
/* Set RTO like tcp_rtt_estimator(), but from cached RTT. */
- crtt /= 8 * USEC_PER_MSEC;
+ crtt /= 8 * USEC_PER_SEC / HZ;
inet_csk(sk)->icsk_rto = crtt + max(2 * crtt, tcp_rto_min(sk));
} else if (tp->srtt_us == 0) {
/* RFC6298: 5.7 We've failed to get a valid RTT sample from
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index 63d2680b65db..2f6667116e85 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -297,7 +297,7 @@ void tcp_time_wait(struct sock *sk, int state, int timeo)
tw->tw_v6_daddr = sk->sk_v6_daddr;
tw->tw_v6_rcv_saddr = sk->sk_v6_rcv_saddr;
tw->tw_tclass = np->tclass;
- tw->tw_flowlabel = np->flow_label >> 12;
+ tw->tw_flowlabel = be32_to_cpu(np->flow_label & IPV6_FLOWLABEL_MASK);
tw->tw_ipv6only = sk->sk_ipv6only;
}
#endif
@@ -451,7 +451,8 @@ struct sock *tcp_create_openreq_child(struct sock *sk, struct request_sock *req,
newtp->snd_cwnd = TCP_INIT_CWND;
newtp->snd_cwnd_cnt = 0;
- if (!try_module_get(newicsk->icsk_ca_ops->owner))
+ if (!newicsk->icsk_ca_setsockopt ||
+ !try_module_get(newicsk->icsk_ca_ops->owner))
tcp_assign_congestion_control(newsk);
tcp_set_ca_state(newsk, TCP_CA_Open);
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index dc9f925b0cd5..af2f64eeb98f 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -2532,8 +2532,10 @@ int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb)
*/
if (unlikely((NET_IP_ALIGN && ((unsigned long)skb->data & 3)) ||
skb_headroom(skb) >= 0xFFFF)) {
- struct sk_buff *nskb = __pskb_copy(skb, MAX_TCP_HEADER,
- GFP_ATOMIC);
+ struct sk_buff *nskb;
+
+ skb_mstamp_get(&skb->skb_mstamp);
+ nskb = __pskb_copy(skb, MAX_TCP_HEADER, GFP_ATOMIC);
err = nskb ? tcp_transmit_skb(sk, nskb, 0, GFP_ATOMIC) :
-ENOBUFS;
} else {
@@ -2798,6 +2800,7 @@ void tcp_send_active_reset(struct sock *sk, gfp_t priority)
skb_reserve(skb, MAX_TCP_HEADER);
tcp_init_nondata_skb(skb, tcp_acceptable_seq(sk),
TCPHDR_ACK | TCPHDR_RST);
+ skb_mstamp_get(&skb->skb_mstamp);
/* Send it off. */
if (tcp_transmit_skb(sk, skb, 0, priority))
NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPABORTFAILED);
diff --git a/net/ipv4/tcp_yeah.c b/net/ipv4/tcp_yeah.c
index cd7273218598..25a229764e7f 100644
--- a/net/ipv4/tcp_yeah.c
+++ b/net/ipv4/tcp_yeah.c
@@ -219,7 +219,7 @@ static u32 tcp_yeah_ssthresh(struct sock *sk)
yeah->fast_count = 0;
yeah->reno_count = max(yeah->reno_count>>1, 2U);
- return tp->snd_cwnd - reduction;
+ return max_t(int, tp->snd_cwnd - reduction, 2);
}
static struct tcp_congestion_ops tcp_yeah __read_mostly = {
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index cd0db5471bb5..2a5d388d76a4 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -90,6 +90,7 @@
#include <linux/socket.h>
#include <linux/sockios.h>
#include <linux/igmp.h>
+#include <linux/inetdevice.h>
#include <linux/in.h>
#include <linux/errno.h>
#include <linux/timer.h>
@@ -1336,10 +1337,8 @@ csum_copy_err:
}
unlock_sock_fast(sk, slow);
- if (noblock)
- return -EAGAIN;
-
- /* starting over for a new packet */
+ /* starting over for a new packet, but check if we need to yield */
+ cond_resched();
msg->msg_flags &= ~MSG_TRUNC;
goto try_again;
}
@@ -1950,6 +1949,7 @@ void udp_v4_early_demux(struct sk_buff *skb)
struct sock *sk;
struct dst_entry *dst;
int dif = skb->dev->ifindex;
+ int ours;
/* validate the packet */
if (!pskb_may_pull(skb, skb_transport_offset(skb) + sizeof(struct udphdr)))
@@ -1959,26 +1959,47 @@ void udp_v4_early_demux(struct sk_buff *skb)
uh = udp_hdr(skb);
if (skb->pkt_type == PACKET_BROADCAST ||
- skb->pkt_type == PACKET_MULTICAST)
+ skb->pkt_type == PACKET_MULTICAST) {
+ struct in_device *in_dev = __in_dev_get_rcu(skb->dev);
+
+ if (!in_dev)
+ return;
+
+ /* we are supposed to accept bcast packets */
+ if (skb->pkt_type == PACKET_MULTICAST) {
+ ours = ip_check_mc_rcu(in_dev, iph->daddr, iph->saddr,
+ iph->protocol);
+ if (!ours)
+ return;
+ }
+
sk = __udp4_lib_mcast_demux_lookup(net, uh->dest, iph->daddr,
uh->source, iph->saddr, dif);
- else if (skb->pkt_type == PACKET_HOST)
+ } else if (skb->pkt_type == PACKET_HOST) {
sk = __udp4_lib_demux_lookup(net, uh->dest, iph->daddr,
uh->source, iph->saddr, dif);
- else
+ } else {
return;
+ }
if (!sk)
return;
skb->sk = sk;
skb->destructor = sock_efree;
- dst = sk->sk_rx_dst;
+ dst = READ_ONCE(sk->sk_rx_dst);
if (dst)
dst = dst_check(dst, 0);
- if (dst)
- skb_dst_set_noref(skb, dst);
+ if (dst) {
+ /* DST_NOCACHE can not be used without taking a reference */
+ if (dst->flags & DST_NOCACHE) {
+ if (likely(atomic_inc_not_zero(&dst->__refcnt)))
+ skb_dst_set(skb, dst);
+ } else {
+ skb_dst_set_noref(skb, dst);
+ }
+ }
}
int udp_rcv(struct sk_buff *skb)
diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c
index 6156f68a1e90..94fc16dad6c6 100644
--- a/net/ipv4/xfrm4_policy.c
+++ b/net/ipv4/xfrm4_policy.c
@@ -230,7 +230,7 @@ static void xfrm4_dst_ifdown(struct dst_entry *dst, struct net_device *dev,
xfrm_dst_ifdown(dst, dev);
}
-static struct dst_ops xfrm4_dst_ops = {
+static struct dst_ops xfrm4_dst_ops_template = {
.family = AF_INET,
.protocol = cpu_to_be16(ETH_P_IP),
.gc = xfrm4_garbage_collect,
@@ -245,7 +245,7 @@ static struct dst_ops xfrm4_dst_ops = {
static struct xfrm_policy_afinfo xfrm4_policy_afinfo = {
.family = AF_INET,
- .dst_ops = &xfrm4_dst_ops,
+ .dst_ops = &xfrm4_dst_ops_template,
.dst_lookup = xfrm4_dst_lookup,
.get_saddr = xfrm4_get_saddr,
.decode_session = _decode_session4,
@@ -267,7 +267,7 @@ static struct ctl_table xfrm4_policy_table[] = {
{ }
};
-static int __net_init xfrm4_net_init(struct net *net)
+static int __net_init xfrm4_net_sysctl_init(struct net *net)
{
struct ctl_table *table;
struct ctl_table_header *hdr;
@@ -295,7 +295,7 @@ err_alloc:
return -ENOMEM;
}
-static void __net_exit xfrm4_net_exit(struct net *net)
+static void __net_exit xfrm4_net_sysctl_exit(struct net *net)
{
struct ctl_table *table;
@@ -307,12 +307,44 @@ static void __net_exit xfrm4_net_exit(struct net *net)
if (!net_eq(net, &init_net))
kfree(table);
}
+#else /* CONFIG_SYSCTL */
+static int inline xfrm4_net_sysctl_init(struct net *net)
+{
+ return 0;
+}
+
+static void inline xfrm4_net_sysctl_exit(struct net *net)
+{
+}
+#endif
+
+static int __net_init xfrm4_net_init(struct net *net)
+{
+ int ret;
+
+ memcpy(&net->xfrm.xfrm4_dst_ops, &xfrm4_dst_ops_template,
+ sizeof(xfrm4_dst_ops_template));
+ ret = dst_entries_init(&net->xfrm.xfrm4_dst_ops);
+ if (ret)
+ return ret;
+
+ ret = xfrm4_net_sysctl_init(net);
+ if (ret)
+ dst_entries_destroy(&net->xfrm.xfrm4_dst_ops);
+
+ return ret;
+}
+
+static void __net_exit xfrm4_net_exit(struct net *net)
+{
+ xfrm4_net_sysctl_exit(net);
+ dst_entries_destroy(&net->xfrm.xfrm4_dst_ops);
+}
static struct pernet_operations __net_initdata xfrm4_net_ops = {
.init = xfrm4_net_init,
.exit = xfrm4_net_exit,
};
-#endif
static void __init xfrm4_policy_init(void)
{
@@ -321,13 +353,9 @@ static void __init xfrm4_policy_init(void)
void __init xfrm4_init(void)
{
- dst_entries_init(&xfrm4_dst_ops);
-
xfrm4_state_init();
xfrm4_policy_init();
xfrm4_protocol_init();
-#ifdef CONFIG_SYSCTL
register_pernet_subsys(&xfrm4_net_ops);
-#endif
}
generated by cgit v1.2.3 (git 2.25.1) at 2024-05-30 19:28:20 +0000