summaryrefslogtreecommitdiff
path: root/net/ipv4
diff options
context:
space:
mode:
Diffstat (limited to 'net/ipv4')
-rw-r--r--net/ipv4/devinet.c6
-rw-r--r--net/ipv4/esp4.c52
-rw-r--r--net/ipv4/fib_frontend.c26
-rw-r--r--net/ipv4/fib_semantics.c8
-rw-r--r--net/ipv4/igmp.c3
-rw-r--r--net/ipv4/inet_connection_sock.c14
-rw-r--r--net/ipv4/ip_fragment.c1
-rw-r--r--net/ipv4/ip_gre.c19
-rw-r--r--net/ipv4/ip_output.c8
-rw-r--r--net/ipv4/ip_sockglue.c2
-rw-r--r--net/ipv4/ip_tunnel.c23
-rw-r--r--net/ipv4/ipmr.c4
-rw-r--r--net/ipv4/netfilter/arp_tables.c293
-rw-r--r--net/ipv4/netfilter/ip_tables.c318
-rw-r--r--net/ipv4/netfilter/nf_defrag_ipv4.c2
-rw-r--r--net/ipv4/netfilter/nf_nat_masquerade_ipv4.c12
-rw-r--r--net/ipv4/ping.c4
-rw-r--r--net/ipv4/raw.c4
-rw-r--r--net/ipv4/route.c89
-rw-r--r--net/ipv4/tcp.c16
-rw-r--r--net/ipv4/tcp_ipv4.c46
-rw-r--r--net/ipv4/tcp_metrics.c2
-rw-r--r--net/ipv4/tcp_minisocks.c3
-rw-r--r--net/ipv4/tcp_output.c9
-rw-r--r--net/ipv4/tcp_yeah.c2
-rw-r--r--net/ipv4/udp.c24
-rw-r--r--net/ipv4/udp_tunnel.c2
27 files changed, 447 insertions, 545 deletions
diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c
index cebd9d31e65a..0212591b0077 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;
@@ -1847,7 +1851,7 @@ static int inet_netconf_get_devconf(struct sk_buff *in_skb,
if (err < 0)
goto errout;
- err = EINVAL;
+ err = -EINVAL;
if (!tb[NETCONFA_IFINDEX])
goto errout;
diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c
index 477937465a20..d95631d09248 100644
--- a/net/ipv4/esp4.c
+++ b/net/ipv4/esp4.c
@@ -23,6 +23,11 @@ struct esp_skb_cb {
void *tmp;
};
+struct esp_output_extra {
+ __be32 seqhi;
+ u32 esphoff;
+};
+
#define ESP_SKB_CB(__skb) ((struct esp_skb_cb *)&((__skb)->cb[0]))
static u32 esp4_get_mtu(struct xfrm_state *x, int mtu);
@@ -35,11 +40,11 @@ static u32 esp4_get_mtu(struct xfrm_state *x, int mtu);
*
* TODO: Use spare space in skb for this where possible.
*/
-static void *esp_alloc_tmp(struct crypto_aead *aead, int nfrags, int seqhilen)
+static void *esp_alloc_tmp(struct crypto_aead *aead, int nfrags, int extralen)
{
unsigned int len;
- len = seqhilen;
+ len = extralen;
len += crypto_aead_ivsize(aead);
@@ -57,15 +62,16 @@ static void *esp_alloc_tmp(struct crypto_aead *aead, int nfrags, int seqhilen)
return kmalloc(len, GFP_ATOMIC);
}
-static inline __be32 *esp_tmp_seqhi(void *tmp)
+static inline void *esp_tmp_extra(void *tmp)
{
- return PTR_ALIGN((__be32 *)tmp, __alignof__(__be32));
+ return PTR_ALIGN(tmp, __alignof__(struct esp_output_extra));
}
-static inline u8 *esp_tmp_iv(struct crypto_aead *aead, void *tmp, int seqhilen)
+
+static inline u8 *esp_tmp_iv(struct crypto_aead *aead, void *tmp, int extralen)
{
return crypto_aead_ivsize(aead) ?
- PTR_ALIGN((u8 *)tmp + seqhilen,
- crypto_aead_alignmask(aead) + 1) : tmp + seqhilen;
+ PTR_ALIGN((u8 *)tmp + extralen,
+ crypto_aead_alignmask(aead) + 1) : tmp + extralen;
}
static inline struct aead_request *esp_tmp_req(struct crypto_aead *aead, u8 *iv)
@@ -99,7 +105,7 @@ static void esp_restore_header(struct sk_buff *skb, unsigned int offset)
{
struct ip_esp_hdr *esph = (void *)(skb->data + offset);
void *tmp = ESP_SKB_CB(skb)->tmp;
- __be32 *seqhi = esp_tmp_seqhi(tmp);
+ __be32 *seqhi = esp_tmp_extra(tmp);
esph->seq_no = esph->spi;
esph->spi = *seqhi;
@@ -107,7 +113,11 @@ static void esp_restore_header(struct sk_buff *skb, unsigned int offset)
static void esp_output_restore_header(struct sk_buff *skb)
{
- esp_restore_header(skb, skb_transport_offset(skb) - sizeof(__be32));
+ void *tmp = ESP_SKB_CB(skb)->tmp;
+ struct esp_output_extra *extra = esp_tmp_extra(tmp);
+
+ esp_restore_header(skb, skb_transport_offset(skb) + extra->esphoff -
+ sizeof(__be32));
}
static void esp_output_done_esn(struct crypto_async_request *base, int err)
@@ -121,6 +131,7 @@ static void esp_output_done_esn(struct crypto_async_request *base, int err)
static int esp_output(struct xfrm_state *x, struct sk_buff *skb)
{
int err;
+ struct esp_output_extra *extra;
struct ip_esp_hdr *esph;
struct crypto_aead *aead;
struct aead_request *req;
@@ -137,8 +148,7 @@ static int esp_output(struct xfrm_state *x, struct sk_buff *skb)
int tfclen;
int nfrags;
int assoclen;
- int seqhilen;
- __be32 *seqhi;
+ int extralen;
__be64 seqno;
/* skb is pure payload to encrypt */
@@ -166,21 +176,21 @@ static int esp_output(struct xfrm_state *x, struct sk_buff *skb)
nfrags = err;
assoclen = sizeof(*esph);
- seqhilen = 0;
+ extralen = 0;
if (x->props.flags & XFRM_STATE_ESN) {
- seqhilen += sizeof(__be32);
- assoclen += seqhilen;
+ extralen += sizeof(*extra);
+ assoclen += sizeof(__be32);
}
- tmp = esp_alloc_tmp(aead, nfrags, seqhilen);
+ tmp = esp_alloc_tmp(aead, nfrags, extralen);
if (!tmp) {
err = -ENOMEM;
goto error;
}
- seqhi = esp_tmp_seqhi(tmp);
- iv = esp_tmp_iv(aead, tmp, seqhilen);
+ extra = esp_tmp_extra(tmp);
+ iv = esp_tmp_iv(aead, tmp, extralen);
req = esp_tmp_req(aead, iv);
sg = esp_req_sg(aead, req);
@@ -247,8 +257,10 @@ static int esp_output(struct xfrm_state *x, struct sk_buff *skb)
* encryption.
*/
if ((x->props.flags & XFRM_STATE_ESN)) {
- esph = (void *)(skb_transport_header(skb) - sizeof(__be32));
- *seqhi = esph->spi;
+ extra->esphoff = (unsigned char *)esph -
+ skb_transport_header(skb);
+ esph = (struct ip_esp_hdr *)((unsigned char *)esph - 4);
+ extra->seqhi = esph->spi;
esph->seq_no = htonl(XFRM_SKB_CB(skb)->seq.output.hi);
aead_request_set_callback(req, 0, esp_output_done_esn, skb);
}
@@ -445,7 +457,7 @@ static int esp_input(struct xfrm_state *x, struct sk_buff *skb)
goto out;
ESP_SKB_CB(skb)->tmp = tmp;
- seqhi = esp_tmp_seqhi(tmp);
+ seqhi = esp_tmp_extra(tmp);
iv = esp_tmp_iv(aead, tmp, seqhilen);
req = esp_tmp_req(aead, iv);
sg = esp_req_sg(aead, req);
diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index e10edb5e78b0..98c754e61024 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -280,7 +280,6 @@ __be32 fib_compute_spec_dst(struct sk_buff *skb)
struct in_device *in_dev;
struct fib_result res;
struct rtable *rt;
- struct flowi4 fl4;
struct net *net;
int scope;
@@ -296,14 +295,13 @@ __be32 fib_compute_spec_dst(struct sk_buff *skb)
scope = RT_SCOPE_UNIVERSE;
if (!ipv4_is_zeronet(ip_hdr(skb)->saddr)) {
- fl4.flowi4_oif = 0;
- fl4.flowi4_iif = LOOPBACK_IFINDEX;
- fl4.daddr = ip_hdr(skb)->saddr;
- fl4.saddr = 0;
- fl4.flowi4_tos = RT_TOS(ip_hdr(skb)->tos);
- fl4.flowi4_scope = scope;
- fl4.flowi4_mark = IN_DEV_SRC_VMARK(in_dev) ? skb->mark : 0;
- fl4.flowi4_tun_key.tun_id = 0;
+ struct flowi4 fl4 = {
+ .flowi4_iif = LOOPBACK_IFINDEX,
+ .daddr = ip_hdr(skb)->saddr,
+ .flowi4_tos = RT_TOS(ip_hdr(skb)->tos),
+ .flowi4_scope = scope,
+ .flowi4_mark = IN_DEV_SRC_VMARK(in_dev) ? skb->mark : 0,
+ };
if (!fib_lookup(net, &fl4, &res, 0))
return FIB_RES_PREFSRC(net, res);
} else {
@@ -907,7 +905,11 @@ void fib_del_ifaddr(struct in_ifaddr *ifa, struct in_ifaddr *iprim)
if (ifa->ifa_flags & IFA_F_SECONDARY) {
prim = inet_ifa_byprefix(in_dev, any, ifa->ifa_mask);
if (!prim) {
- pr_warn("%s: bug: prim == NULL\n", __func__);
+ /* if the device has been deleted, we don't perform
+ * address promotion
+ */
+ if (!in_dev->dead)
+ pr_warn("%s: bug: prim == NULL\n", __func__);
return;
}
if (iprim && iprim != prim) {
@@ -923,6 +925,9 @@ 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 :-)
*
@@ -998,6 +1003,7 @@ 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/fib_semantics.c b/net/ipv4/fib_semantics.c
index d97268e8ff10..ffe95d954007 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -479,6 +479,9 @@ static int fib_get_nhs(struct fib_info *fi, struct rtnexthop *rtnh,
if (!rtnh_ok(rtnh, remaining))
return -EINVAL;
+ if (rtnh->rtnh_flags & (RTNH_F_DEAD | RTNH_F_LINKDOWN))
+ return -EINVAL;
+
nexthop_nh->nh_flags =
(cfg->fc_flags & ~0xFF) | rtnh->rtnh_flags;
nexthop_nh->nh_oif = rtnh->rtnh_ifindex;
@@ -975,6 +978,8 @@ fib_convert_metrics(struct fib_info *fi, const struct fib_config *cfg)
val = 65535 - 40;
if (type == RTAX_MTU && val > 65535 - 15)
val = 65535 - 15;
+ if (type == RTAX_HOPLIMIT && val > 255)
+ val = 255;
if (type == RTAX_FEATURES && (val & ~RTAX_FEATURE_MASK))
return -EINVAL;
fi->fib_metrics[type - 1] = val;
@@ -1001,6 +1006,9 @@ struct fib_info *fib_create_info(struct fib_config *cfg)
if (fib_props[cfg->fc_type].scope > cfg->fc_scope)
goto err_inval;
+ if (cfg->fc_flags & (RTNH_F_DEAD | RTNH_F_LINKDOWN))
+ goto err_inval;
+
#ifdef CONFIG_IP_ROUTE_MULTIPATH
if (cfg->fc_mp) {
nhs = fib_count_nexthops(cfg->fc_mp, cfg->fc_mp_len);
diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c
index 05e4cba14162..b3086cf27027 100644
--- a/net/ipv4/igmp.c
+++ b/net/ipv4/igmp.c
@@ -356,9 +356,8 @@ static struct sk_buff *igmpv3_newpack(struct net_device *dev, unsigned int mtu)
skb_dst_set(skb, &rt->dst);
skb->dev = dev;
- skb->reserved_tailroom = skb_end_offset(skb) -
- min(mtu, skb_end_offset(skb));
skb_reserve(skb, hlen);
+ skb_tailroom_reserve(skb, mtu, tlen);
skb_reset_network_header(skb);
pip = ip_hdr(skb);
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index 728414dcea3b..030cd09dd2a2 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -789,14 +789,16 @@ static void inet_child_forget(struct sock *sk, struct request_sock *req,
reqsk_put(req);
}
-void inet_csk_reqsk_queue_add(struct sock *sk, struct request_sock *req,
- struct sock *child)
+struct sock *inet_csk_reqsk_queue_add(struct sock *sk,
+ struct request_sock *req,
+ struct sock *child)
{
struct request_sock_queue *queue = &inet_csk(sk)->icsk_accept_queue;
spin_lock(&queue->rskq_lock);
if (unlikely(sk->sk_state != TCP_LISTEN)) {
inet_child_forget(sk, req, child);
+ child = NULL;
} else {
req->sk = child;
req->dl_next = NULL;
@@ -808,6 +810,7 @@ void inet_csk_reqsk_queue_add(struct sock *sk, struct request_sock *req,
sk_acceptq_added(sk);
}
spin_unlock(&queue->rskq_lock);
+ return child;
}
EXPORT_SYMBOL(inet_csk_reqsk_queue_add);
@@ -817,11 +820,8 @@ struct sock *inet_csk_complete_hashdance(struct sock *sk, struct sock *child,
if (own_req) {
inet_csk_reqsk_queue_drop(sk, req);
reqsk_queue_removed(&inet_csk(sk)->icsk_accept_queue, req);
- inet_csk_reqsk_queue_add(sk, req, child);
- /* Warning: caller must not call reqsk_put(req);
- * child stole last reference on it.
- */
- return child;
+ if (inet_csk_reqsk_queue_add(sk, req, child))
+ return child;
}
/* Too bad, another child took ownership of the request, undo. */
bh_unlock_sock(child);
diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c
index 1fe55ae81781..b8a0607dab96 100644
--- a/net/ipv4/ip_fragment.c
+++ b/net/ipv4/ip_fragment.c
@@ -661,6 +661,7 @@ int ip_defrag(struct net *net, struct sk_buff *skb, u32 user)
struct ipq *qp;
IP_INC_STATS_BH(net, IPSTATS_MIB_REASMREQDS);
+ skb_orphan(skb);
/* Lookup (or create) queue header */
qp = ip_find(net, ip_hdr(skb), user, vif);
diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index 614521437e30..3e4184088082 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -180,6 +180,7 @@ static __be16 tnl_flags_to_gre_flags(__be16 tflags)
return flags;
}
+/* Fills in tpi and returns header length to be pulled. */
static int parse_gre_header(struct sk_buff *skb, struct tnl_ptk_info *tpi,
bool *csum_err)
{
@@ -239,7 +240,7 @@ static int parse_gre_header(struct sk_buff *skb, struct tnl_ptk_info *tpi,
return -EINVAL;
}
}
- return iptunnel_pull_header(skb, hdr_len, tpi->proto);
+ return hdr_len;
}
static void ipgre_err(struct sk_buff *skb, u32 info,
@@ -342,7 +343,7 @@ static void gre_err(struct sk_buff *skb, u32 info)
struct tnl_ptk_info tpi;
bool csum_err = false;
- if (parse_gre_header(skb, &tpi, &csum_err)) {
+ if (parse_gre_header(skb, &tpi, &csum_err) < 0) {
if (!csum_err) /* ignore csum errors. */
return;
}
@@ -420,6 +421,7 @@ static int gre_rcv(struct sk_buff *skb)
{
struct tnl_ptk_info tpi;
bool csum_err = false;
+ int hdr_len;
#ifdef CONFIG_NET_IPGRE_BROADCAST
if (ipv4_is_multicast(ip_hdr(skb)->daddr)) {
@@ -429,7 +431,10 @@ static int gre_rcv(struct sk_buff *skb)
}
#endif
- if (parse_gre_header(skb, &tpi, &csum_err) < 0)
+ hdr_len = parse_gre_header(skb, &tpi, &csum_err);
+ if (hdr_len < 0)
+ goto drop;
+ if (iptunnel_pull_header(skb, hdr_len, tpi.proto) < 0)
goto drop;
if (ipgre_rcv(skb, &tpi) == PACKET_RCVD)
@@ -1242,6 +1247,14 @@ struct net_device *gretap_fb_dev_create(struct net *net, const char *name,
err = ipgre_newlink(net, dev, tb, NULL);
if (err < 0)
goto out;
+
+ /* openvswitch users expect packet sizes to be unrestricted,
+ * so set the largest MTU we can.
+ */
+ err = __ip_tunnel_change_mtu(dev, IP_MAX_MTU, false);
+ if (err)
+ goto out;
+
return dev;
out:
free_netdev(dev);
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 33bef2763c72..dbf7f7ee2958 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -240,6 +240,7 @@ static int ip_finish_output_gso(struct net *net, struct sock *sk,
* from host network stack.
*/
features = netif_skb_features(skb);
+ BUILD_BUG_ON(sizeof(*IPCB(skb)) > SKB_SGO_CB_OFFSET);
segs = skb_gso_segment(skb, features & ~NETIF_F_GSO_MASK);
if (IS_ERR_OR_NULL(segs)) {
kfree_skb(skb);
@@ -921,7 +922,7 @@ static int __ip_append_data(struct sock *sk,
if (((length > mtu) || (skb && skb_is_gso(skb))) &&
(sk->sk_protocol == IPPROTO_UDP) &&
(rt->dst.dev->features & NETIF_F_UFO) && !rt->dst.header_len &&
- (sk->sk_type == SOCK_DGRAM)) {
+ (sk->sk_type == SOCK_DGRAM) && !sk->sk_no_check_tx) {
err = ip_ufo_append_data(sk, queue, getfrag, from, length,
hh_len, fragheaderlen, transhdrlen,
maxfraglen, flags);
@@ -1236,13 +1237,16 @@ ssize_t ip_append_page(struct sock *sk, struct flowi4 *fl4, struct page *page,
if (!skb)
return -EINVAL;
- cork->length += size;
if ((size + skb->len > mtu) &&
(sk->sk_protocol == IPPROTO_UDP) &&
(rt->dst.dev->features & NETIF_F_UFO)) {
+ if (skb->ip_summed != CHECKSUM_PARTIAL)
+ return -EOPNOTSUPP;
+
skb_shinfo(skb)->gso_size = mtu - fragheaderlen;
skb_shinfo(skb)->gso_type = SKB_GSO_UDP;
}
+ cork->length += size;
while (size > 0) {
if (skb_is_gso(skb)) {
diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c
index 5f73a7c03e27..a50124260f5a 100644
--- a/net/ipv4/ip_sockglue.c
+++ b/net/ipv4/ip_sockglue.c
@@ -249,6 +249,8 @@ int ip_cmsg_send(struct net *net, struct msghdr *msg, struct ipcm_cookie *ipc,
switch (cmsg->cmsg_type) {
case IP_RETOPTS:
err = cmsg->cmsg_len - CMSG_ALIGN(sizeof(struct cmsghdr));
+
+ /* Our caller is responsible for freeing ipc->opt */
err = ip_options_get(net, &ipc->opt, CMSG_DATA(cmsg),
err < 40 ? err : 40);
if (err)
diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c
index cbb51f3fac06..3310ac75e3f3 100644
--- a/net/ipv4/ip_tunnel.c
+++ b/net/ipv4/ip_tunnel.c
@@ -663,6 +663,8 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev,
inner_iph = (const struct iphdr *)skb_inner_network_header(skb);
connected = (tunnel->parms.iph.daddr != 0);
+ memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt));
+
dst = tnl_params->daddr;
if (dst == 0) {
/* NBMA tunnel */
@@ -760,7 +762,6 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev,
tunnel->err_time + IPTUNNEL_ERR_TIMEO)) {
tunnel->err_count--;
- memset(IPCB(skb), 0, sizeof(*IPCB(skb)));
dst_link_failure(skb);
} else
tunnel->err_count = 0;
@@ -947,17 +948,31 @@ done:
}
EXPORT_SYMBOL_GPL(ip_tunnel_ioctl);
-int ip_tunnel_change_mtu(struct net_device *dev, int new_mtu)
+int __ip_tunnel_change_mtu(struct net_device *dev, int new_mtu, bool strict)
{
struct ip_tunnel *tunnel = netdev_priv(dev);
int t_hlen = tunnel->hlen + sizeof(struct iphdr);
+ int max_mtu = 0xFFF8 - dev->hard_header_len - t_hlen;
- if (new_mtu < 68 ||
- new_mtu > 0xFFF8 - dev->hard_header_len - t_hlen)
+ if (new_mtu < 68)
return -EINVAL;
+
+ if (new_mtu > max_mtu) {
+ if (strict)
+ return -EINVAL;
+
+ new_mtu = max_mtu;
+ }
+
dev->mtu = new_mtu;
return 0;
}
+EXPORT_SYMBOL_GPL(__ip_tunnel_change_mtu);
+
+int ip_tunnel_change_mtu(struct net_device *dev, int new_mtu)
+{
+ return __ip_tunnel_change_mtu(dev, new_mtu, true);
+}
EXPORT_SYMBOL_GPL(ip_tunnel_change_mtu);
static void ip_tunnel_dev_free(struct net_device *dev)
diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index c3a38353f5dc..9d1e555496e3 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -882,8 +882,10 @@ static struct mfc_cache *ipmr_cache_alloc(void)
{
struct mfc_cache *c = kmem_cache_zalloc(mrt_cachep, GFP_KERNEL);
- if (c)
+ if (c) {
+ c->mfc_un.res.last_assert = jiffies - MFC_ASSERT_THRESH - 1;
c->mfc_un.res.minvif = MAXVIFS;
+ }
return c;
}
diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c
index 36a30fab8625..6e3e0e8b1ce3 100644
--- a/net/ipv4/netfilter/arp_tables.c
+++ b/net/ipv4/netfilter/arp_tables.c
@@ -367,6 +367,18 @@ static inline bool unconditional(const struct arpt_entry *e)
memcmp(&e->arp, &uncond, sizeof(uncond)) == 0;
}
+static bool find_jump_target(const struct xt_table_info *t,
+ const struct arpt_entry *target)
+{
+ struct arpt_entry *iter;
+
+ xt_entry_foreach(iter, t->entries, t->size) {
+ if (iter == target)
+ return true;
+ }
+ return false;
+}
+
/* Figures out from what hook each rule can be called: returns 0 if
* there are loops. Puts hook bitmask in comefrom.
*/
@@ -439,6 +451,8 @@ 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 {
@@ -458,9 +472,15 @@ static int mark_source_chains(const struct xt_table_info *newinfo,
/* This a jump; chase it. */
duprintf("Jump rule %u -> %u\n",
pos, newpos);
+ e = (struct arpt_entry *)
+ (entry0 + newpos);
+ if (!find_jump_target(newinfo, e))
+ return 0;
} else {
/* ... this is a fallthru */
newpos = pos + e->next_offset;
+ if (newpos >= newinfo->size)
+ return 0;
}
e = (struct arpt_entry *)
(entry0 + newpos);
@@ -474,23 +494,6 @@ next:
return 1;
}
-static inline int check_entry(const struct arpt_entry *e)
-{
- const struct xt_entry_target *t;
-
- if (!arp_checkentry(&e->arp))
- 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);
@@ -586,7 +589,11 @@ static inline int check_entry_size_and_hooks(struct arpt_entry *e,
return -EINVAL;
}
- err = check_entry(e);
+ 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;
@@ -691,10 +698,8 @@ static int translate_table(struct xt_table_info *newinfo, void *entry0,
}
}
- if (!mark_source_chains(newinfo, repl->valid_hooks, entry0)) {
- duprintf("Looping hook\n");
+ if (!mark_source_chains(newinfo, repl->valid_hooks, entry0))
return -ELOOP;
- }
/* Finally, each sanity check must pass */
i = 0;
@@ -1125,55 +1130,17 @@ static int do_add_counters(struct net *net, const void __user *user,
unsigned int i;
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;
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);
- }
+ paddc = xt_copy_counters_from_user(user, len, &tmp, compat);
+ if (IS_ERR(paddc))
+ return PTR_ERR(paddc);
- 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;
- }
-
- 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;
@@ -1181,7 +1148,7 @@ 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;
}
@@ -1208,6 +1175,18 @@ 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;
@@ -1216,20 +1195,17 @@ 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 ||
@@ -1246,8 +1222,11 @@ 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);
+ 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;
@@ -1271,17 +1250,6 @@ 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:
@@ -1290,18 +1258,17 @@ 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));
@@ -1322,148 +1289,82 @@ 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;
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) {
- iter1->counters.pcnt = xt_percpu_counter_alloc();
- if (IS_ERR_VALUE(iter1->counters.pcnt)) {
- ret = -ENOMEM;
- break;
- }
-
- ret = check_target(iter1, name);
- if (ret != 0) {
- xt_percpu_counter_free(iter1->counters.pcnt);
- 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];
}
+ 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;
xt_free_table_info(info);
@@ -1471,31 +1372,18 @@ 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)
{
@@ -1528,10 +1416,7 @@ 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 99d46b0a4ead..a399c5419622 100644
--- a/net/ipv4/netfilter/ip_tables.c
+++ b/net/ipv4/netfilter/ip_tables.c
@@ -443,6 +443,18 @@ ipt_do_table(struct sk_buff *skb,
#endif
}
+static bool find_jump_target(const struct xt_table_info *t,
+ const struct ipt_entry *target)
+{
+ struct ipt_entry *iter;
+
+ xt_entry_foreach(iter, t->entries, t->size) {
+ if (iter == target)
+ return true;
+ }
+ return false;
+}
+
/* Figures out from what hook each rule can be called: returns 0 if
there are loops. Puts hook bitmask in comefrom. */
static int
@@ -520,6 +532,8 @@ 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 {
@@ -538,9 +552,15 @@ mark_source_chains(const struct xt_table_info *newinfo,
/* This a jump; chase it. */
duprintf("Jump rule %u -> %u\n",
pos, newpos);
+ e = (struct ipt_entry *)
+ (entry0 + newpos);
+ if (!find_jump_target(newinfo, e))
+ return 0;
} else {
/* ... this is a fallthru */
newpos = pos + e->next_offset;
+ if (newpos >= newinfo->size)
+ return 0;
}
e = (struct ipt_entry *)
(entry0 + newpos);
@@ -568,25 +588,6 @@ static void cleanup_match(struct xt_entry_match *m, struct net *net)
}
static int
-check_entry(const struct ipt_entry *e)
-{
- const struct xt_entry_target *t;
-
- if (!ip_checkentry(&e->ip))
- 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;
@@ -750,7 +751,11 @@ check_entry_size_and_hooks(struct ipt_entry *e,
return -EINVAL;
}
- err = check_entry(e);
+ 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;
@@ -1308,55 +1313,17 @@ do_add_counters(struct net *net, const void __user *user,
unsigned int i;
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;
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;
-
-#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, 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;
@@ -1364,7 +1331,7 @@ 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;
}
@@ -1443,7 +1410,6 @@ 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,
int *size)
{
@@ -1478,17 +1444,14 @@ 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 ||
@@ -1505,8 +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);
+ 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;
@@ -1514,7 +1480,7 @@ 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, &off);
+ ret = compat_find_calc_match(ematch, &e->ip, &off);
if (ret != 0)
goto release_matches;
++j;
@@ -1537,17 +1503,6 @@ 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:
@@ -1561,19 +1516,18 @@ 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));
@@ -1582,201 +1536,105 @@ 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;
-
- e->counters.pcnt = xt_percpu_counter_alloc();
- if (IS_ERR_VALUE(e->counters.pcnt))
- return -ENOMEM;
-
- 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);
- }
-
- xt_percpu_counter_free(e->counters.pcnt);
-
- 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;
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];
}
+ 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;
xt_free_table_info(info);
@@ -1784,17 +1642,16 @@ 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
@@ -1830,10 +1687,7 @@ 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_defrag_ipv4.c b/net/ipv4/netfilter/nf_defrag_ipv4.c
index 6fb869f646bf..a04dee536b8e 100644
--- a/net/ipv4/netfilter/nf_defrag_ipv4.c
+++ b/net/ipv4/netfilter/nf_defrag_ipv4.c
@@ -27,8 +27,6 @@ static int nf_ct_ipv4_gather_frags(struct net *net, struct sk_buff *skb,
{
int err;
- skb_orphan(skb);
-
local_bh_disable();
err = ip_defrag(net, skb, user);
local_bh_enable();
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/ping.c b/net/ipv4/ping.c
index b27e98010dea..0d5278ca4777 100644
--- a/net/ipv4/ping.c
+++ b/net/ipv4/ping.c
@@ -746,8 +746,10 @@ static int ping_v4_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
if (msg->msg_controllen) {
err = ip_cmsg_send(sock_net(sk), msg, &ipc, false);
- if (err)
+ if (unlikely(err)) {
+ kfree(ipc.opt);
return err;
+ }
if (ipc.opt)
free = 1;
}
diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c
index 865895d3fb27..a9b479a1c4a0 100644
--- a/net/ipv4/raw.c
+++ b/net/ipv4/raw.c
@@ -547,8 +547,10 @@ static int raw_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
if (msg->msg_controllen) {
err = ip_cmsg_send(net, msg, &ipc, false);
- if (err)
+ if (unlikely(err)) {
+ kfree(ipc.opt);
goto out;
+ }
if (ipc.opt)
free = 1;
}
diff --git a/net/ipv4/route.c b/net/ipv4/route.c
index a0d842f4e9cf..fb54659320d8 100644
--- a/net/ipv4/route.c
+++ b/net/ipv4/route.c
@@ -129,6 +129,7 @@ static int ip_rt_mtu_expires __read_mostly = 10 * 60 * HZ;
static int ip_rt_min_pmtu __read_mostly = 512 + 20 + 20;
static int ip_rt_min_advmss __read_mostly = 256;
+static int ip_rt_gc_timeout __read_mostly = RT_GC_TIMEOUT;
/*
* Interface to generic destination cache.
*/
@@ -757,7 +758,7 @@ static void __ip_do_redirect(struct rtable *rt, struct sk_buff *skb, struct flow
struct fib_nh *nh = &FIB_RES_NH(res);
update_or_create_fnhe(nh, fl4->daddr, new_gw,
- 0, 0);
+ 0, jiffies + ip_rt_gc_timeout);
}
if (kill_route)
rt->dst.obsolete = DST_OBSOLETE_KILL;
@@ -1558,6 +1559,36 @@ static void ip_handle_martian_source(struct net_device *dev,
#endif
}
+static void ip_del_fnhe(struct fib_nh *nh, __be32 daddr)
+{
+ struct fnhe_hash_bucket *hash;
+ struct fib_nh_exception *fnhe, __rcu **fnhe_p;
+ u32 hval = fnhe_hashfun(daddr);
+
+ spin_lock_bh(&fnhe_lock);
+
+ hash = rcu_dereference_protected(nh->nh_exceptions,
+ lockdep_is_held(&fnhe_lock));
+ hash += hval;
+
+ fnhe_p = &hash->chain;
+ fnhe = rcu_dereference_protected(*fnhe_p, lockdep_is_held(&fnhe_lock));
+ while (fnhe) {
+ if (fnhe->fnhe_daddr == daddr) {
+ rcu_assign_pointer(*fnhe_p, rcu_dereference_protected(
+ fnhe->fnhe_next, lockdep_is_held(&fnhe_lock)));
+ fnhe_flush_routes(fnhe);
+ kfree_rcu(fnhe, rcu);
+ break;
+ }
+ fnhe_p = &fnhe->fnhe_next;
+ fnhe = rcu_dereference_protected(fnhe->fnhe_next,
+ lockdep_is_held(&fnhe_lock));
+ }
+
+ spin_unlock_bh(&fnhe_lock);
+}
+
/* called in rcu_read_lock() section */
static int __mkroute_input(struct sk_buff *skb,
const struct fib_result *res,
@@ -1611,11 +1642,20 @@ static int __mkroute_input(struct sk_buff *skb,
fnhe = find_exception(&FIB_RES_NH(*res), daddr);
if (do_cache) {
- if (fnhe)
+ if (fnhe) {
rth = rcu_dereference(fnhe->fnhe_rth_input);
- else
- rth = rcu_dereference(FIB_RES_NH(*res).nh_rth_input);
+ if (rth && rth->dst.expires &&
+ time_after(jiffies, rth->dst.expires)) {
+ ip_del_fnhe(&FIB_RES_NH(*res), daddr);
+ fnhe = NULL;
+ } else {
+ goto rt_cache;
+ }
+ }
+
+ rth = rcu_dereference(FIB_RES_NH(*res).nh_rth_input);
+rt_cache:
if (rt_cache_valid(rth)) {
skb_dst_set_noref(skb, &rth->dst);
goto out;
@@ -2007,6 +2047,18 @@ 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;
@@ -2016,19 +2068,29 @@ static struct rtable *__mkroute_output(const struct fib_result *res,
struct fib_nh *nh = &FIB_RES_NH(*res);
fnhe = find_exception(nh, fl4->daddr);
- if (fnhe)
+ if (fnhe) {
prth = &fnhe->fnhe_rth_output;
- else {
- if (unlikely(fl4->flowi4_flags &
- FLOWI_FLAG_KNOWN_NH &&
- !(nh->nh_gw &&
- nh->nh_scope == RT_SCOPE_LINK))) {
- do_cache = false;
- goto add;
+ rth = rcu_dereference(*prth);
+ if (rth && rth->dst.expires &&
+ time_after(jiffies, rth->dst.expires)) {
+ ip_del_fnhe(nh, fl4->daddr);
+ fnhe = NULL;
+ } else {
+ goto rt_cache;
}
- prth = raw_cpu_ptr(nh->nh_pcpu_rth_output);
}
+
+ if (unlikely(fl4->flowi4_flags &
+ FLOWI_FLAG_KNOWN_NH &&
+ !(nh->nh_gw &&
+ nh->nh_scope == RT_SCOPE_LINK))) {
+ do_cache = false;
+ goto add;
+ }
+ prth = raw_cpu_ptr(nh->nh_pcpu_rth_output);
rth = rcu_dereference(*prth);
+
+rt_cache:
if (rt_cache_valid(rth)) {
dst_hold(&rth->dst);
return rth;
@@ -2582,7 +2644,6 @@ void ip_rt_multicast_event(struct in_device *in_dev)
}
#ifdef CONFIG_SYSCTL
-static int ip_rt_gc_timeout __read_mostly = RT_GC_TIMEOUT;
static int ip_rt_gc_interval __read_mostly = 60 * HZ;
static int ip_rt_gc_min_interval __read_mostly = HZ / 2;
static int ip_rt_gc_elasticity __read_mostly = 8;
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index a1d5c67e251d..6ecfc9de599c 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -279,6 +279,7 @@
#include <asm/uaccess.h>
#include <asm/ioctls.h>
+#include <asm/unaligned.h>
#include <net/busy_poll.h>
int sysctl_tcp_fin_timeout __read_mostly = TCP_FIN_TIMEOUT;
@@ -938,7 +939,7 @@ new_segment:
i = skb_shinfo(skb)->nr_frags;
can_coalesce = skb_can_coalesce(skb, i, page, offset);
- if (!can_coalesce && i >= MAX_SKB_FRAGS) {
+ if (!can_coalesce && i >= sysctl_max_skb_frags) {
tcp_mark_push(tp, skb);
goto new_segment;
}
@@ -1211,7 +1212,7 @@ new_segment:
if (!skb_can_coalesce(skb, i, pfrag->page,
pfrag->offset)) {
- if (i == MAX_SKB_FRAGS || !sg) {
+ if (i == sysctl_max_skb_frags || !sg) {
tcp_mark_push(tp, skb);
goto new_segment;
}
@@ -2637,6 +2638,7 @@ void tcp_get_info(struct sock *sk, struct tcp_info *info)
const struct inet_connection_sock *icsk = inet_csk(sk);
u32 now = tcp_time_stamp;
unsigned int start;
+ u64 rate64;
u32 rate;
memset(info, 0, sizeof(*info));
@@ -2702,15 +2704,17 @@ void tcp_get_info(struct sock *sk, struct tcp_info *info)
info->tcpi_total_retrans = tp->total_retrans;
rate = READ_ONCE(sk->sk_pacing_rate);
- info->tcpi_pacing_rate = rate != ~0U ? rate : ~0ULL;
+ rate64 = rate != ~0U ? rate : ~0ULL;
+ put_unaligned(rate64, &info->tcpi_pacing_rate);
rate = READ_ONCE(sk->sk_max_pacing_rate);
- info->tcpi_max_pacing_rate = rate != ~0U ? rate : ~0ULL;
+ rate64 = rate != ~0U ? rate : ~0ULL;
+ put_unaligned(rate64, &info->tcpi_max_pacing_rate);
do {
start = u64_stats_fetch_begin_irq(&tp->syncp);
- info->tcpi_bytes_acked = tp->bytes_acked;
- info->tcpi_bytes_received = tp->bytes_received;
+ put_unaligned(tp->bytes_acked, &info->tcpi_bytes_acked);
+ put_unaligned(tp->bytes_received, &info->tcpi_bytes_received);
} while (u64_stats_fetch_retry_irq(&tp->syncp, start));
info->tcpi_segs_out = tp->segs_out;
info->tcpi_segs_in = tp->segs_in;
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 205e6745393f..7decaa439360 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -312,7 +312,7 @@ static void do_redirect(struct sk_buff *skb, struct sock *sk)
/* handle ICMP messages on TCP_NEW_SYN_RECV request sockets */
-void tcp_req_err(struct sock *sk, u32 seq)
+void tcp_req_err(struct sock *sk, u32 seq, bool abort)
{
struct request_sock *req = inet_reqsk(sk);
struct net *net = sock_net(sk);
@@ -320,11 +320,9 @@ void tcp_req_err(struct sock *sk, u32 seq)
/* ICMPs are not backlogged, hence we cannot get
* an established socket here.
*/
- WARN_ON(req->sk);
-
if (seq != tcp_rsk(req)->snt_isn) {
NET_INC_STATS_BH(net, LINUX_MIB_OUTOFWINDOWICMPS);
- } else {
+ } else if (abort) {
/*
* Still in SYN_RECV, just remove it silently.
* There is no good way to pass the error to the newly
@@ -384,7 +382,12 @@ void tcp_v4_err(struct sk_buff *icmp_skb, u32 info)
}
seq = ntohl(th->seq);
if (sk->sk_state == TCP_NEW_SYN_RECV)
- return tcp_req_err(sk, seq);
+ return tcp_req_err(sk, seq,
+ type == ICMP_PARAMETERPROB ||
+ type == ICMP_TIME_EXCEEDED ||
+ (type == ICMP_DEST_UNREACH &&
+ (code == ICMP_NET_UNREACH ||
+ code == ICMP_HOST_UNREACH)));
bh_lock_sock(sk);
/* If too many ICMPs get dropped on busy
@@ -705,7 +708,8 @@ release_sk1:
outside socket context is ugly, certainly. What can I do?
*/
-static void tcp_v4_send_ack(struct sk_buff *skb, u32 seq, u32 ack,
+static void tcp_v4_send_ack(struct net *net,
+ struct sk_buff *skb, u32 seq, u32 ack,
u32 win, u32 tsval, u32 tsecr, int oif,
struct tcp_md5sig_key *key,
int reply_flags, u8 tos)
@@ -720,7 +724,6 @@ static void tcp_v4_send_ack(struct sk_buff *skb, u32 seq, u32 ack,
];
} rep;
struct ip_reply_arg arg;
- struct net *net = dev_net(skb_dst(skb)->dev);
memset(&rep.th, 0, sizeof(struct tcphdr));
memset(&arg, 0, sizeof(arg));
@@ -782,7 +785,8 @@ static void tcp_v4_timewait_ack(struct sock *sk, struct sk_buff *skb)
struct inet_timewait_sock *tw = inet_twsk(sk);
struct tcp_timewait_sock *tcptw = tcp_twsk(sk);
- tcp_v4_send_ack(skb, tcptw->tw_snd_nxt, tcptw->tw_rcv_nxt,
+ tcp_v4_send_ack(sock_net(sk), skb,
+ tcptw->tw_snd_nxt, tcptw->tw_rcv_nxt,
tcptw->tw_rcv_wnd >> tw->tw_rcv_wscale,
tcp_time_stamp + tcptw->tw_ts_offset,
tcptw->tw_ts_recent,
@@ -801,8 +805,10 @@ static void tcp_v4_reqsk_send_ack(const struct sock *sk, struct sk_buff *skb,
/* sk->sk_state == TCP_LISTEN -> for regular TCP_SYN_RECV
* sk->sk_state == TCP_SYN_RECV -> for Fast Open.
*/
- tcp_v4_send_ack(skb, (sk->sk_state == TCP_LISTEN) ?
- tcp_rsk(req)->snt_isn + 1 : tcp_sk(sk)->snd_nxt,
+ u32 seq = (sk->sk_state == TCP_LISTEN) ? tcp_rsk(req)->snt_isn + 1 :
+ tcp_sk(sk)->snd_nxt;
+
+ tcp_v4_send_ack(sock_net(sk), skb, seq,
tcp_rsk(req)->rcv_nxt, req->rsk_rcv_wnd,
tcp_time_stamp,
req->ts_recent,
@@ -1586,28 +1592,30 @@ process:
if (sk->sk_state == TCP_NEW_SYN_RECV) {
struct request_sock *req = inet_reqsk(sk);
- struct sock *nsk = NULL;
+ struct sock *nsk;
sk = req->rsk_listener;
- if (tcp_v4_inbound_md5_hash(sk, skb))
- goto discard_and_relse;
- if (likely(sk->sk_state == TCP_LISTEN)) {
- nsk = tcp_check_req(sk, skb, req, false);
- } else {
+ if (unlikely(tcp_v4_inbound_md5_hash(sk, skb))) {
+ reqsk_put(req);
+ goto discard_it;
+ }
+ if (unlikely(sk->sk_state != TCP_LISTEN)) {
inet_csk_reqsk_queue_drop_and_put(sk, req);
goto lookup;
}
+ sock_hold(sk);
+ nsk = tcp_check_req(sk, skb, req, false);
if (!nsk) {
reqsk_put(req);
- goto discard_it;
+ goto discard_and_relse;
}
if (nsk == sk) {
- sock_hold(sk);
reqsk_put(req);
} else if (tcp_child_process(sk, nsk, skb)) {
tcp_v4_send_reset(nsk, skb);
- goto discard_it;
+ goto discard_and_relse;
} else {
+ sock_put(sk);
return 0;
}
}
diff --git a/net/ipv4/tcp_metrics.c b/net/ipv4/tcp_metrics.c
index c8cbc2b4b792..a726d7853ce5 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 ac6b1961ffeb..9475a2748a9a 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -458,7 +458,7 @@ struct sock *tcp_create_openreq_child(const struct sock *sk,
newtp->rcv_wup = newtp->copied_seq =
newtp->rcv_nxt = treq->rcv_isn + 1;
- newtp->segs_in = 0;
+ newtp->segs_in = 1;
newtp->snd_sml = newtp->snd_una =
newtp->snd_nxt = newtp->snd_up = treq->snt_isn + 1;
@@ -818,6 +818,7 @@ int tcp_child_process(struct sock *parent, struct sock *child,
int ret = 0;
int state = child->sk_state;
+ tcp_sk(child)->segs_in += max_t(u16, 1, skb_shinfo(skb)->gso_segs);
if (!sock_owned_by_user(child)) {
ret = tcp_rcv_state_process(child, skb);
/* Wakeup parent, send SIGIO */
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 9f069bd9de46..9eb81a4b0da2 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -239,7 +239,8 @@ void tcp_select_initial_window(int __space, __u32 mss,
/* Set window scaling on max possible window
* See RFC1323 for an explanation of the limit to 14
*/
- space = max_t(u32, sysctl_tcp_rmem[2], sysctl_rmem_max);
+ space = max_t(u32, space, sysctl_tcp_rmem[2]);
+ space = max_t(u32, space, sysctl_rmem_max);
space = min_t(u32, space, *window_clamp);
while (space > 65535 && (*rcv_wscale) < 14) {
space >>= 1;
@@ -2625,8 +2626,10 @@ 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 {
diff --git a/net/ipv4/tcp_yeah.c b/net/ipv4/tcp_yeah.c
index 17d35662930d..3e6a472e6b88 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 660933edd2d2..defc9cad1797 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -966,8 +966,10 @@ int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
if (msg->msg_controllen) {
err = ip_cmsg_send(sock_net(sk), msg, &ipc,
sk->sk_family == AF_INET6);
- if (err)
+ if (unlikely(err)) {
+ kfree(ipc.opt);
return err;
+ }
if (ipc.opt)
free = 1;
connected = 0;
@@ -1274,6 +1276,7 @@ int udp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int noblock,
int peeked, off = 0;
int err;
int is_udplite = IS_UDPLITE(sk);
+ bool checksum_valid = false;
bool slow;
if (flags & MSG_ERRQUEUE)
@@ -1299,11 +1302,12 @@ try_again:
*/
if (copied < ulen || UDP_SKB_CB(skb)->partial_cov) {
- if (udp_lib_checksum_complete(skb))
+ checksum_valid = !udp_lib_checksum_complete(skb);
+ if (!checksum_valid)
goto csum_copy_err;
}
- if (skb_csum_unnecessary(skb))
+ if (checksum_valid || skb_csum_unnecessary(skb))
err = skb_copy_datagram_msg(skb, sizeof(struct udphdr),
msg, copied);
else {
@@ -1530,7 +1534,7 @@ int udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
/* if we're overly short, let UDP handle it */
encap_rcv = ACCESS_ONCE(up->encap_rcv);
- if (skb->len > sizeof(struct udphdr) && encap_rcv) {
+ if (encap_rcv) {
int ret;
/* Verify checksum before giving to encap */
@@ -1989,10 +1993,14 @@ void udp_v4_early_demux(struct sk_buff *skb)
if (!in_dev)
return;
- ours = ip_check_mc_rcu(in_dev, iph->daddr, iph->saddr,
- iph->protocol);
- if (!ours)
- 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) {
diff --git a/net/ipv4/udp_tunnel.c b/net/ipv4/udp_tunnel.c
index aba428626b52..280a9bdeddee 100644
--- a/net/ipv4/udp_tunnel.c
+++ b/net/ipv4/udp_tunnel.c
@@ -89,6 +89,8 @@ int udp_tunnel_xmit_skb(struct rtable *rt, struct sock *sk, struct sk_buff *skb,
uh->source = src_port;
uh->len = htons(skb->len);
+ memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt));
+
udp_set_csum(nocheck, skb, src, dst, skb->len);
return iptunnel_xmit(sk, rt, skb, src, dst, IPPROTO_UDP,
generated by cgit v1.2.3 (git 2.25.1) at 2025-10-23 00:17:21 +0000