aboutsummaryrefslogtreecommitdiffstats
path: root/net/ipv4
diff options
context:
space:
mode:
Diffstat (limited to 'net/ipv4')
-rw-r--r--net/ipv4/af_inet.c28
-rw-r--r--net/ipv4/devinet.c57
-rw-r--r--net/ipv4/esp4_offload.c3
-rw-r--r--net/ipv4/fib_frontend.c8
-rw-r--r--net/ipv4/igmp.c2
-rw-r--r--net/ipv4/ip_gre.c38
-rw-r--r--net/ipv4/ip_sockglue.c6
-rw-r--r--net/ipv4/ip_tunnel.c13
-rw-r--r--net/ipv4/ipconfig.c47
-rw-r--r--net/ipv4/raw.c15
-rw-r--r--net/ipv4/tcp.c26
-rw-r--r--net/ipv4/tcp_nv.c2
-rw-r--r--net/ipv4/tcp_offload.c3
-rw-r--r--net/ipv4/tcp_output.c6
-rw-r--r--net/ipv4/tcp_timer.c7
-rw-r--r--net/ipv4/udp.c15
-rw-r--r--net/ipv4/udp_offload.c3
-rw-r--r--net/ipv4/xfrm4_mode_tunnel.c1
18 files changed, 161 insertions, 119 deletions
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c
index 54cccdd8b1e3..c24008daa3d8 100644
--- a/net/ipv4/af_inet.c
+++ b/net/ipv4/af_inet.c
@@ -872,6 +872,9 @@ int inet_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg)
struct sock *sk = sock->sk;
int err = 0;
struct net *net = sock_net(sk);
+ void __user *p = (void __user *)arg;
+ struct ifreq ifr;
+ struct rtentry rt;
switch (cmd) {
case SIOCGSTAMP:
@@ -882,8 +885,12 @@ int inet_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg)
break;
case SIOCADDRT:
case SIOCDELRT:
+ if (copy_from_user(&rt, p, sizeof(struct rtentry)))
+ return -EFAULT;
+ err = ip_rt_ioctl(net, cmd, &rt);
+ break;
case SIOCRTMSG:
- err = ip_rt_ioctl(net, cmd, (void __user *)arg);
+ err = -EINVAL;
break;
case SIOCDARP:
case SIOCGARP:
@@ -891,17 +898,26 @@ int inet_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg)
err = arp_ioctl(net, cmd, (void __user *)arg);
break;
case SIOCGIFADDR:
- case SIOCSIFADDR:
case SIOCGIFBRDADDR:
- case SIOCSIFBRDADDR:
case SIOCGIFNETMASK:
- case SIOCSIFNETMASK:
case SIOCGIFDSTADDR:
+ case SIOCGIFPFLAGS:
+ if (copy_from_user(&ifr, p, sizeof(struct ifreq)))
+ return -EFAULT;
+ err = devinet_ioctl(net, cmd, &ifr);
+ if (!err && copy_to_user(p, &ifr, sizeof(struct ifreq)))
+ err = -EFAULT;
+ break;
+
+ case SIOCSIFADDR:
+ case SIOCSIFBRDADDR:
+ case SIOCSIFNETMASK:
case SIOCSIFDSTADDR:
case SIOCSIFPFLAGS:
- case SIOCGIFPFLAGS:
case SIOCSIFFLAGS:
- err = devinet_ioctl(net, cmd, (void __user *)arg);
+ if (copy_from_user(&ifr, p, sizeof(struct ifreq)))
+ return -EFAULT;
+ err = devinet_ioctl(net, cmd, &ifr);
break;
default:
if (sk->sk_prot->ioctl)
diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c
index 7a93359fbc72..e056c0067f2c 100644
--- a/net/ipv4/devinet.c
+++ b/net/ipv4/devinet.c
@@ -946,11 +946,10 @@ static int inet_abc_len(__be32 addr)
}
-int devinet_ioctl(struct net *net, unsigned int cmd, void __user *arg)
+int devinet_ioctl(struct net *net, unsigned int cmd, struct ifreq *ifr)
{
- struct ifreq ifr;
struct sockaddr_in sin_orig;
- struct sockaddr_in *sin = (struct sockaddr_in *)&ifr.ifr_addr;
+ struct sockaddr_in *sin = (struct sockaddr_in *)&ifr->ifr_addr;
struct in_device *in_dev;
struct in_ifaddr **ifap = NULL;
struct in_ifaddr *ifa = NULL;
@@ -959,22 +958,16 @@ int devinet_ioctl(struct net *net, unsigned int cmd, void __user *arg)
int ret = -EFAULT;
int tryaddrmatch = 0;
- /*
- * Fetch the caller's info block into kernel space
- */
-
- if (copy_from_user(&ifr, arg, sizeof(struct ifreq)))
- goto out;
- ifr.ifr_name[IFNAMSIZ - 1] = 0;
+ ifr->ifr_name[IFNAMSIZ - 1] = 0;
/* save original address for comparison */
memcpy(&sin_orig, sin, sizeof(*sin));
- colon = strchr(ifr.ifr_name, ':');
+ colon = strchr(ifr->ifr_name, ':');
if (colon)
*colon = 0;
- dev_load(net, ifr.ifr_name);
+ dev_load(net, ifr->ifr_name);
switch (cmd) {
case SIOCGIFADDR: /* Get interface address */
@@ -1014,7 +1007,7 @@ int devinet_ioctl(struct net *net, unsigned int cmd, void __user *arg)
rtnl_lock();
ret = -ENODEV;
- dev = __dev_get_by_name(net, ifr.ifr_name);
+ dev = __dev_get_by_name(net, ifr->ifr_name);
if (!dev)
goto done;
@@ -1031,7 +1024,7 @@ int devinet_ioctl(struct net *net, unsigned int cmd, void __user *arg)
This is checked above. */
for (ifap = &in_dev->ifa_list; (ifa = *ifap) != NULL;
ifap = &ifa->ifa_next) {
- if (!strcmp(ifr.ifr_name, ifa->ifa_label) &&
+ if (!strcmp(ifr->ifr_name, ifa->ifa_label) &&
sin_orig.sin_addr.s_addr ==
ifa->ifa_local) {
break; /* found */
@@ -1044,7 +1037,7 @@ int devinet_ioctl(struct net *net, unsigned int cmd, void __user *arg)
if (!ifa) {
for (ifap = &in_dev->ifa_list; (ifa = *ifap) != NULL;
ifap = &ifa->ifa_next)
- if (!strcmp(ifr.ifr_name, ifa->ifa_label))
+ if (!strcmp(ifr->ifr_name, ifa->ifa_label))
break;
}
}
@@ -1056,19 +1049,19 @@ int devinet_ioctl(struct net *net, unsigned int cmd, void __user *arg)
switch (cmd) {
case SIOCGIFADDR: /* Get interface address */
sin->sin_addr.s_addr = ifa->ifa_local;
- goto rarok;
+ break;
case SIOCGIFBRDADDR: /* Get the broadcast address */
sin->sin_addr.s_addr = ifa->ifa_broadcast;
- goto rarok;
+ break;
case SIOCGIFDSTADDR: /* Get the destination address */
sin->sin_addr.s_addr = ifa->ifa_address;
- goto rarok;
+ break;
case SIOCGIFNETMASK: /* Get the netmask for the interface */
sin->sin_addr.s_addr = ifa->ifa_mask;
- goto rarok;
+ break;
case SIOCSIFFLAGS:
if (colon) {
@@ -1076,11 +1069,11 @@ int devinet_ioctl(struct net *net, unsigned int cmd, void __user *arg)
if (!ifa)
break;
ret = 0;
- if (!(ifr.ifr_flags & IFF_UP))
+ if (!(ifr->ifr_flags & IFF_UP))
inet_del_ifa(in_dev, ifap, 1);
break;
}
- ret = dev_change_flags(dev, ifr.ifr_flags);
+ ret = dev_change_flags(dev, ifr->ifr_flags);
break;
case SIOCSIFADDR: /* Set interface address (and family) */
@@ -1095,7 +1088,7 @@ int devinet_ioctl(struct net *net, unsigned int cmd, void __user *arg)
break;
INIT_HLIST_NODE(&ifa->hash);
if (colon)
- memcpy(ifa->ifa_label, ifr.ifr_name, IFNAMSIZ);
+ memcpy(ifa->ifa_label, ifr->ifr_name, IFNAMSIZ);
else
memcpy(ifa->ifa_label, dev->name, IFNAMSIZ);
} else {
@@ -1182,28 +1175,27 @@ done:
rtnl_unlock();
out:
return ret;
-rarok:
- rtnl_unlock();
- ret = copy_to_user(arg, &ifr, sizeof(struct ifreq)) ? -EFAULT : 0;
- goto out;
}
-static int inet_gifconf(struct net_device *dev, char __user *buf, int len)
+static int inet_gifconf(struct net_device *dev, char __user *buf, int len, int size)
{
struct in_device *in_dev = __in_dev_get_rtnl(dev);
struct in_ifaddr *ifa;
struct ifreq ifr;
int done = 0;
+ if (WARN_ON(size > sizeof(struct ifreq)))
+ goto out;
+
if (!in_dev)
goto out;
for (ifa = in_dev->ifa_list; ifa; ifa = ifa->ifa_next) {
if (!buf) {
- done += sizeof(ifr);
+ done += size;
continue;
}
- if (len < (int) sizeof(ifr))
+ if (len < size)
break;
memset(&ifr, 0, sizeof(struct ifreq));
strcpy(ifr.ifr_name, ifa->ifa_label);
@@ -1212,13 +1204,12 @@ static int inet_gifconf(struct net_device *dev, char __user *buf, int len)
(*(struct sockaddr_in *)&ifr.ifr_addr).sin_addr.s_addr =
ifa->ifa_local;
- if (copy_to_user(buf, &ifr, sizeof(struct ifreq))) {
+ if (copy_to_user(buf + done, &ifr, size)) {
done = -EFAULT;
break;
}
- buf += sizeof(struct ifreq);
- len -= sizeof(struct ifreq);
- done += sizeof(struct ifreq);
+ len -= size;
+ done += size;
}
out:
return done;
diff --git a/net/ipv4/esp4_offload.c b/net/ipv4/esp4_offload.c
index 32fbd9ba3609..da5635fc52c2 100644
--- a/net/ipv4/esp4_offload.c
+++ b/net/ipv4/esp4_offload.c
@@ -118,6 +118,9 @@ static struct sk_buff *esp4_gso_segment(struct sk_buff *skb,
if (!xo)
return ERR_PTR(-EINVAL);
+ if (!(skb_shinfo(skb)->gso_type & SKB_GSO_ESP))
+ return ERR_PTR(-EINVAL);
+
x = skb->sp->xvec[skb->sp->len - 1];
aead = x->data;
esph = ip_esp_hdr(skb);
diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index 08259d078b1c..f05afaf3235c 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -587,10 +587,9 @@ static int rtentry_to_fib_config(struct net *net, int cmd, struct rtentry *rt,
* Handle IP routing ioctl calls.
* These are used to manipulate the routing tables
*/
-int ip_rt_ioctl(struct net *net, unsigned int cmd, void __user *arg)
+int ip_rt_ioctl(struct net *net, unsigned int cmd, struct rtentry *rt)
{
struct fib_config cfg;
- struct rtentry rt;
int err;
switch (cmd) {
@@ -599,11 +598,8 @@ int ip_rt_ioctl(struct net *net, unsigned int cmd, void __user *arg)
if (!ns_capable(net->user_ns, CAP_NET_ADMIN))
return -EPERM;
- if (copy_from_user(&rt, arg, sizeof(rt)))
- return -EFAULT;
-
rtnl_lock();
- err = rtentry_to_fib_config(net, cmd, &rt, &cfg);
+ err = rtentry_to_fib_config(net, cmd, rt, &cfg);
if (err == 0) {
struct fib_table *tb;
diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c
index 02f00be12bb0..10f7f74a0831 100644
--- a/net/ipv4/igmp.c
+++ b/net/ipv4/igmp.c
@@ -332,7 +332,7 @@ static __be32 igmpv3_get_srcaddr(struct net_device *dev,
return htonl(INADDR_ANY);
for_ifa(in_dev) {
- if (inet_ifa_match(fl4->saddr, ifa))
+ if (fl4->saddr == ifa->ifa_local)
return fl4->saddr;
} endfor_ifa(in_dev);
diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c
index b61f2285816d..6ec670fbbbdd 100644
--- a/net/ipv4/ip_gre.c
+++ b/net/ipv4/ip_gre.c
@@ -114,7 +114,7 @@ MODULE_PARM_DESC(log_ecn_error, "Log packets received with corrupted ECN");
static struct rtnl_link_ops ipgre_link_ops __read_mostly;
static int ipgre_tunnel_init(struct net_device *dev);
static void erspan_build_header(struct sk_buff *skb,
- __be32 id, u32 index,
+ u32 id, u32 index,
bool truncate, bool is_ipv4);
static unsigned int ipgre_net_id __read_mostly;
@@ -273,12 +273,12 @@ static int erspan_rcv(struct sk_buff *skb, struct tnl_ptk_info *tpi,
iph = ip_hdr(skb);
ershdr = (struct erspan_base_hdr *)(skb->data + gre_hdr_len);
- ver = (ntohs(ershdr->ver_vlan) & VER_MASK) >> VER_OFFSET;
+ ver = ershdr->ver;
/* The original GRE header does not have key field,
* Use ERSPAN 10-bit session ID as key.
*/
- tpi->key = cpu_to_be32(ntohs(ershdr->session_id) & ID_MASK);
+ tpi->key = cpu_to_be32(get_session_id(ershdr));
tunnel = ip_tunnel_lookup(itn, skb->dev->ifindex,
tpi->flags | TUNNEL_KEY,
iph->saddr, iph->daddr, tpi->key);
@@ -324,14 +324,8 @@ static int erspan_rcv(struct sk_buff *skb, struct tnl_ptk_info *tpi,
if (ver == 1) {
tunnel->index = ntohl(pkt_md->u.index);
} else {
- u16 md2_flags;
- u16 dir, hwid;
-
- md2_flags = ntohs(pkt_md->u.md2.flags);
- dir = (md2_flags & DIR_MASK) >> DIR_OFFSET;
- hwid = (md2_flags & HWID_MASK) >> HWID_OFFSET;
- tunnel->dir = dir;
- tunnel->hwid = hwid;
+ tunnel->dir = pkt_md->u.md2.dir;
+ tunnel->hwid = get_hwid(&pkt_md->u.md2);
}
}
@@ -615,19 +609,14 @@ static void erspan_fb_xmit(struct sk_buff *skb, struct net_device *dev,
}
if (version == 1) {
- erspan_build_header(skb, tunnel_id_to_key32(key->tun_id),
+ erspan_build_header(skb, ntohl(tunnel_id_to_key32(key->tun_id)),
ntohl(md->u.index), truncate, true);
} else if (version == 2) {
- u16 md2_flags;
- u8 direction;
- u16 hwid;
-
- md2_flags = ntohs(md->u.md2.flags);
- direction = (md2_flags & DIR_MASK) >> DIR_OFFSET;
- hwid = (md2_flags & HWID_MASK) >> HWID_OFFSET;
-
- erspan_build_header_v2(skb, tunnel_id_to_key32(key->tun_id),
- direction, hwid, truncate, true);
+ erspan_build_header_v2(skb,
+ ntohl(tunnel_id_to_key32(key->tun_id)),
+ md->u.md2.dir,
+ get_hwid(&md->u.md2),
+ truncate, true);
} else {
goto err_free_rt;
}
@@ -733,10 +722,11 @@ static netdev_tx_t erspan_xmit(struct sk_buff *skb,
/* Push ERSPAN header */
if (tunnel->erspan_ver == 1)
- erspan_build_header(skb, tunnel->parms.o_key, tunnel->index,
+ erspan_build_header(skb, ntohl(tunnel->parms.o_key),
+ tunnel->index,
truncate, true);
else
- erspan_build_header_v2(skb, tunnel->parms.o_key,
+ erspan_build_header_v2(skb, ntohl(tunnel->parms.o_key),
tunnel->dir, tunnel->hwid,
truncate, true);
diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c
index 60fb1eb7d7d8..6cc70fa488cb 100644
--- a/net/ipv4/ip_sockglue.c
+++ b/net/ipv4/ip_sockglue.c
@@ -808,6 +808,7 @@ static int do_ip_setsockopt(struct sock *sk, int level,
{
struct net_device *dev = NULL;
int ifindex;
+ int midx;
if (optlen != sizeof(int))
goto e_inval;
@@ -823,10 +824,13 @@ static int do_ip_setsockopt(struct sock *sk, int level,
err = -EADDRNOTAVAIL;
if (!dev)
break;
+
+ midx = l3mdev_master_ifindex(dev);
dev_put(dev);
err = -EINVAL;
- if (sk->sk_bound_dev_if)
+ if (sk->sk_bound_dev_if &&
+ (!midx || midx != sk->sk_bound_dev_if))
break;
inet->uc_index = ifindex;
diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c
index 5ddb1cb52bd4..141f5e865731 100644
--- a/net/ipv4/ip_tunnel.c
+++ b/net/ipv4/ip_tunnel.c
@@ -711,9 +711,16 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev,
}
}
- init_tunnel_flow(&fl4, protocol, dst, tnl_params->saddr,
- tunnel->parms.o_key, RT_TOS(tos), tunnel->parms.link,
- tunnel->fwmark);
+ if (tunnel->fwmark) {
+ init_tunnel_flow(&fl4, protocol, dst, tnl_params->saddr,
+ tunnel->parms.o_key, RT_TOS(tos), tunnel->parms.link,
+ tunnel->fwmark);
+ }
+ else {
+ init_tunnel_flow(&fl4, protocol, dst, tnl_params->saddr,
+ tunnel->parms.o_key, RT_TOS(tos), tunnel->parms.link,
+ skb->mark);
+ }
if (ip_tunnel_encap(skb, tunnel, &protocol, &fl4) < 0)
goto tx_error;
diff --git a/net/ipv4/ipconfig.c b/net/ipv4/ipconfig.c
index e9e488e72900..f75802ad960f 100644
--- a/net/ipv4/ipconfig.c
+++ b/net/ipv4/ipconfig.c
@@ -329,39 +329,6 @@ set_sockaddr(struct sockaddr_in *sin, __be32 addr, __be16 port)
sin->sin_port = port;
}
-static int __init ic_devinet_ioctl(unsigned int cmd, struct ifreq *arg)
-{
- int res;
-
- mm_segment_t oldfs = get_fs();
- set_fs(get_ds());
- res = devinet_ioctl(&init_net, cmd, (struct ifreq __user *) arg);
- set_fs(oldfs);
- return res;
-}
-
-static int __init ic_dev_ioctl(unsigned int cmd, struct ifreq *arg)
-{
- int res;
-
- mm_segment_t oldfs = get_fs();
- set_fs(get_ds());
- res = dev_ioctl(&init_net, cmd, (struct ifreq __user *) arg);
- set_fs(oldfs);
- return res;
-}
-
-static int __init ic_route_ioctl(unsigned int cmd, struct rtentry *arg)
-{
- int res;
-
- mm_segment_t oldfs = get_fs();
- set_fs(get_ds());
- res = ip_rt_ioctl(&init_net, cmd, (void __user *) arg);
- set_fs(oldfs);
- return res;
-}
-
/*
* Set up interface addresses and routes.
*/
@@ -375,19 +342,19 @@ static int __init ic_setup_if(void)
memset(&ir, 0, sizeof(ir));
strcpy(ir.ifr_ifrn.ifrn_name, ic_dev->dev->name);
set_sockaddr(sin, ic_myaddr, 0);
- if ((err = ic_devinet_ioctl(SIOCSIFADDR, &ir)) < 0) {
+ if ((err = devinet_ioctl(&init_net, SIOCSIFADDR, &ir)) < 0) {
pr_err("IP-Config: Unable to set interface address (%d)\n",
err);
return -1;
}
set_sockaddr(sin, ic_netmask, 0);
- if ((err = ic_devinet_ioctl(SIOCSIFNETMASK, &ir)) < 0) {
+ if ((err = devinet_ioctl(&init_net, SIOCSIFNETMASK, &ir)) < 0) {
pr_err("IP-Config: Unable to set interface netmask (%d)\n",
err);
return -1;
}
set_sockaddr(sin, ic_myaddr | ~ic_netmask, 0);
- if ((err = ic_devinet_ioctl(SIOCSIFBRDADDR, &ir)) < 0) {
+ if ((err = devinet_ioctl(&init_net, SIOCSIFBRDADDR, &ir)) < 0) {
pr_err("IP-Config: Unable to set interface broadcast address (%d)\n",
err);
return -1;
@@ -397,11 +364,11 @@ static int __init ic_setup_if(void)
* out, we'll try to muddle along.
*/
if (ic_dev_mtu != 0) {
- strcpy(ir.ifr_name, ic_dev->dev->name);
- ir.ifr_mtu = ic_dev_mtu;
- if ((err = ic_dev_ioctl(SIOCSIFMTU, &ir)) < 0)
+ rtnl_lock();
+ if ((err = dev_set_mtu(ic_dev->dev, ic_dev_mtu)) < 0)
pr_err("IP-Config: Unable to set interface mtu to %d (%d)\n",
ic_dev_mtu, err);
+ rtnl_unlock();
}
return 0;
}
@@ -423,7 +390,7 @@ static int __init ic_setup_routes(void)
set_sockaddr((struct sockaddr_in *) &rm.rt_genmask, 0, 0);
set_sockaddr((struct sockaddr_in *) &rm.rt_gateway, ic_gateway, 0);
rm.rt_flags = RTF_UP | RTF_GATEWAY;
- if ((err = ic_route_ioctl(SIOCADDRT, &rm)) < 0) {
+ if ((err = ip_rt_ioctl(&init_net, SIOCADDRT, &rm)) < 0) {
pr_err("IP-Config: Cannot add default route (%d)\n",
err);
return -1;
diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c
index 136544b36a46..7c509697ebc7 100644
--- a/net/ipv4/raw.c
+++ b/net/ipv4/raw.c
@@ -617,8 +617,21 @@ static int raw_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
ipc.oif = inet->mc_index;
if (!saddr)
saddr = inet->mc_addr;
- } else if (!ipc.oif)
+ } else if (!ipc.oif) {
ipc.oif = inet->uc_index;
+ } else if (ipv4_is_lbcast(daddr) && inet->uc_index) {
+ /* oif is set, packet is to local broadcast and
+ * and uc_index is set. oif is most likely set
+ * by sk_bound_dev_if. If uc_index != oif check if the
+ * oif is an L3 master and uc_index is an L3 slave.
+ * If so, we want to allow the send using the uc_index.
+ */
+ if (ipc.oif != inet->uc_index &&
+ ipc.oif == l3mdev_master_ifindex_by_index(sock_net(sk),
+ inet->uc_index)) {
+ ipc.oif = inet->uc_index;
+ }
+ }
flowi4_init_output(&fl4, ipc.oif, sk->sk_mark, tos,
RT_SCOPE_UNIVERSE,
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index d7cf861bf699..f013ddc191e0 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -463,7 +463,7 @@ void tcp_init_transfer(struct sock *sk, int bpf_op)
tcp_mtup_init(sk);
icsk->icsk_af_ops->rebuild_header(sk);
tcp_init_metrics(sk);
- tcp_call_bpf(sk, bpf_op);
+ tcp_call_bpf(sk, bpf_op, 0, NULL);
tcp_init_congestion_control(sk);
tcp_init_buffer_space(sk);
}
@@ -2042,6 +2042,30 @@ void tcp_set_state(struct sock *sk, int state)
{
int oldstate = sk->sk_state;
+ /* We defined a new enum for TCP states that are exported in BPF
+ * so as not force the internal TCP states to be frozen. The
+ * following checks will detect if an internal state value ever
+ * differs from the BPF value. If this ever happens, then we will
+ * need to remap the internal value to the BPF value before calling
+ * tcp_call_bpf_2arg.
+ */
+ BUILD_BUG_ON((int)BPF_TCP_ESTABLISHED != (int)TCP_ESTABLISHED);
+ BUILD_BUG_ON((int)BPF_TCP_SYN_SENT != (int)TCP_SYN_SENT);
+ BUILD_BUG_ON((int)BPF_TCP_SYN_RECV != (int)TCP_SYN_RECV);
+ BUILD_BUG_ON((int)BPF_TCP_FIN_WAIT1 != (int)TCP_FIN_WAIT1);
+ BUILD_BUG_ON((int)BPF_TCP_FIN_WAIT2 != (int)TCP_FIN_WAIT2);
+ BUILD_BUG_ON((int)BPF_TCP_TIME_WAIT != (int)TCP_TIME_WAIT);
+ BUILD_BUG_ON((int)BPF_TCP_CLOSE != (int)TCP_CLOSE);
+ BUILD_BUG_ON((int)BPF_TCP_CLOSE_WAIT != (int)TCP_CLOSE_WAIT);
+ BUILD_BUG_ON((int)BPF_TCP_LAST_ACK != (int)TCP_LAST_ACK);
+ BUILD_BUG_ON((int)BPF_TCP_LISTEN != (int)TCP_LISTEN);
+ BUILD_BUG_ON((int)BPF_TCP_CLOSING != (int)TCP_CLOSING);
+ BUILD_BUG_ON((int)BPF_TCP_NEW_SYN_RECV != (int)TCP_NEW_SYN_RECV);
+ BUILD_BUG_ON((int)BPF_TCP_MAX_STATES != (int)TCP_MAX_STATES);
+
+ if (BPF_SOCK_OPS_TEST_FLAG(tcp_sk(sk), BPF_SOCK_OPS_STATE_CB_FLAG))
+ tcp_call_bpf_2arg(sk, BPF_SOCK_OPS_STATE_CB, oldstate, state);
+
switch (state) {
case TCP_ESTABLISHED:
if (oldstate != TCP_ESTABLISHED)
diff --git a/net/ipv4/tcp_nv.c b/net/ipv4/tcp_nv.c
index 0b5a05bd82e3..ddbce73edae8 100644
--- a/net/ipv4/tcp_nv.c
+++ b/net/ipv4/tcp_nv.c
@@ -146,7 +146,7 @@ static void tcpnv_init(struct sock *sk)
* within a datacenter, where we have reasonable estimates of
* RTTs
*/
- base_rtt = tcp_call_bpf(sk, BPF_SOCK_OPS_BASE_RTT);
+ base_rtt = tcp_call_bpf(sk, BPF_SOCK_OPS_BASE_RTT, 0, NULL);
if (base_rtt > 0) {
ca->nv_base_rtt = base_rtt;
ca->nv_lower_bound_rtt = (base_rtt * 205) >> 8; /* 80% */
diff --git a/net/ipv4/tcp_offload.c b/net/ipv4/tcp_offload.c
index b6a2aa1dcf56..4d58e2ce0b5b 100644
--- a/net/ipv4/tcp_offload.c
+++ b/net/ipv4/tcp_offload.c
@@ -32,6 +32,9 @@ static void tcp_gso_tstamp(struct sk_buff *skb, unsigned int ts_seq,
static struct sk_buff *tcp4_gso_segment(struct sk_buff *skb,
netdev_features_t features)
{
+ if (!(skb_shinfo(skb)->gso_type & SKB_GSO_TCPV4))
+ return ERR_PTR(-EINVAL);
+
if (!pskb_may_pull(skb, sizeof(struct tcphdr)))
return ERR_PTR(-EINVAL);
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 95461f02ac9a..e9f985e42405 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -2905,6 +2905,10 @@ int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb, int segs)
err = tcp_transmit_skb(sk, skb, 1, GFP_ATOMIC);
}
+ if (BPF_SOCK_OPS_TEST_FLAG(tp, BPF_SOCK_OPS_RETRANS_CB_FLAG))
+ tcp_call_bpf_3arg(sk, BPF_SOCK_OPS_RETRANS_CB,
+ TCP_SKB_CB(skb)->seq, segs, err);
+
if (likely(!err)) {
TCP_SKB_CB(skb)->sacked |= TCPCB_EVER_RETRANS;
trace_tcp_retransmit_skb(sk, skb);
@@ -3469,7 +3473,7 @@ int tcp_connect(struct sock *sk)
struct sk_buff *buff;
int err;
- tcp_call_bpf(sk, BPF_SOCK_OPS_TCP_CONNECT_CB);
+ tcp_call_bpf(sk, BPF_SOCK_OPS_TCP_CONNECT_CB, 0, NULL);
if (inet_csk(sk)->icsk_af_ops->rebuild_header(sk))
return -EHOSTUNREACH; /* Routing failure or similar. */
diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c
index 6db3124cdbda..257abdde23b0 100644
--- a/net/ipv4/tcp_timer.c
+++ b/net/ipv4/tcp_timer.c
@@ -213,11 +213,18 @@ static int tcp_write_timeout(struct sock *sk)
icsk->icsk_user_timeout);
}
tcp_fastopen_active_detect_blackhole(sk, expired);
+
+ if (BPF_SOCK_OPS_TEST_FLAG(tp, BPF_SOCK_OPS_RTO_CB_FLAG))
+ tcp_call_bpf_3arg(sk, BPF_SOCK_OPS_RTO_CB,
+ icsk->icsk_retransmits,
+ icsk->icsk_rto, (int)expired);
+
if (expired) {
/* Has it gone just too far? */
tcp_write_err(sk);
return 1;
}
+
return 0;
}
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 853321555a4e..3f018f34cf56 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -977,8 +977,21 @@ int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
if (!saddr)
saddr = inet->mc_addr;
connected = 0;
- } else if (!ipc.oif)
+ } else if (!ipc.oif) {
ipc.oif = inet->uc_index;
+ } else if (ipv4_is_lbcast(daddr) && inet->uc_index) {
+ /* oif is set, packet is to local broadcast and
+ * and uc_index is set. oif is most likely set
+ * by sk_bound_dev_if. If uc_index != oif check if the
+ * oif is an L3 master and uc_index is an L3 slave.
+ * If so, we want to allow the send using the uc_index.
+ */
+ if (ipc.oif != inet->uc_index &&
+ ipc.oif == l3mdev_master_ifindex_by_index(sock_net(sk),
+ inet->uc_index)) {
+ ipc.oif = inet->uc_index;
+ }
+ }
if (connected)
rt = (struct rtable *)sk_dst_check(sk, 0);
diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c
index 01801b77bd0d..ea6e6e7df0ee 100644
--- a/net/ipv4/udp_offload.c
+++ b/net/ipv4/udp_offload.c
@@ -203,6 +203,9 @@ static struct sk_buff *udp4_ufo_fragment(struct sk_buff *skb,
goto out;
}
+ if (!(skb_shinfo(skb)->gso_type & SKB_GSO_UDP))
+ goto out;
+
if (!pskb_may_pull(skb, sizeof(struct udphdr)))
goto out;
diff --git a/net/ipv4/xfrm4_mode_tunnel.c b/net/ipv4/xfrm4_mode_tunnel.c
index 8affc6d83d58..63faeee989a9 100644
--- a/net/ipv4/xfrm4_mode_tunnel.c
+++ b/net/ipv4/xfrm4_mode_tunnel.c
@@ -92,6 +92,7 @@ static int xfrm4_mode_tunnel_input(struct xfrm_state *x, struct sk_buff *skb)
skb_reset_network_header(skb);
skb_mac_header_rebuild(skb);
+ eth_hdr(skb)->h_proto = skb->protocol;
err = 0;
Copyright © 1996 – 2023 Jason A. Donenfeld. All Rights Reverse Engineered.