void
nf_log_dump_packet_common(struct nf_log_buf *m, u_int8_t pf,
unsigned int hooknum, const struct sk_buff *skb,
const struct net_device *in,
const struct net_device *out,
const struct nf_loginfo *loginfo, const char *prefix)
{
nf_log_buf_add(m, KERN_SOH "%c%sIN=%s OUT=%s ",
'0' + loginfo->u.log.level, prefix,
in ? in->name : "",
out ? out->name : "");
#if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
if (skb->nf_bridge) {
const struct net_device *physindev;
const struct net_device *physoutdev;
physindev = nf_bridge_get_physindev(skb);
if (physindev && in != physindev)
nf_log_buf_add(m, "PHYSIN=%s ", physindev->name);
physoutdev = nf_bridge_get_physoutdev(skb);
if (physoutdev && out != physoutdev)
nf_log_buf_add(m, "PHYSOUT=%s ", physoutdev->name);
}
#endif
}
static bool
physdev_mt(const struct sk_buff *skb, struct xt_action_param *par)
{
const struct xt_physdev_info *info = par->matchinfo;
const struct net_device *physdev;
unsigned long ret;
const char *indev, *outdev;
/* Not a bridged IP packet or no info available yet:
* LOCAL_OUT/mangle and LOCAL_OUT/nat don't know if
* the destination device will be a bridge. */
if (!skb->nf_bridge) {
/* Return MATCH if the invert flags of the used options are on */
if ((info->bitmask & XT_PHYSDEV_OP_BRIDGED) &&
!(info->invert & XT_PHYSDEV_OP_BRIDGED))
return false;
if ((info->bitmask & XT_PHYSDEV_OP_ISIN) &&
!(info->invert & XT_PHYSDEV_OP_ISIN))
return false;
if ((info->bitmask & XT_PHYSDEV_OP_ISOUT) &&
!(info->invert & XT_PHYSDEV_OP_ISOUT))
return false;
if ((info->bitmask & XT_PHYSDEV_OP_IN) &&
!(info->invert & XT_PHYSDEV_OP_IN))
return false;
if ((info->bitmask & XT_PHYSDEV_OP_OUT) &&
!(info->invert & XT_PHYSDEV_OP_OUT))
return false;
return true;
}
physdev = nf_bridge_get_physoutdev(skb);
outdev = physdev ? physdev->name : NULL;
/* This only makes sense in the FORWARD and POSTROUTING chains */
if ((info->bitmask & XT_PHYSDEV_OP_BRIDGED) &&
(!!outdev ^ !(info->invert & XT_PHYSDEV_OP_BRIDGED)))
return false;
physdev = nf_bridge_get_physindev(skb);
indev = physdev ? physdev->name : NULL;
if ((info->bitmask & XT_PHYSDEV_OP_ISIN &&
(!indev ^ !!(info->invert & XT_PHYSDEV_OP_ISIN))) ||
(info->bitmask & XT_PHYSDEV_OP_ISOUT &&
(!outdev ^ !!(info->invert & XT_PHYSDEV_OP_ISOUT))))
return false;
if (!(info->bitmask & XT_PHYSDEV_OP_IN))
goto match_outdev;
if (indev) {
ret = ifname_compare_aligned(indev, info->physindev,
info->in_mask);
if (!ret ^ !(info->invert & XT_PHYSDEV_OP_IN))
return false;
}
match_outdev:
if (!(info->bitmask & XT_PHYSDEV_OP_OUT))
return true;
if (!outdev)
return false;
ret = ifname_compare_aligned(outdev, info->physoutdev, info->out_mask);
return (!!ret ^ !(info->invert & XT_PHYSDEV_OP_OUT));
}
/* This is an inline function, we don't really care about a long
* list of arguments */
static inline int
__build_packet_message(struct nfnl_log_net *log,
struct nfulnl_instance *inst,
const struct sk_buff *skb,
unsigned int data_len,
u_int8_t pf,
unsigned int hooknum,
const struct net_device *indev,
const struct net_device *outdev,
const char *prefix, unsigned int plen,
const struct nfnl_ct_hook *nfnl_ct,
struct nf_conn *ct, enum ip_conntrack_info ctinfo)
{
struct nfulnl_msg_packet_hdr pmsg;
struct nlmsghdr *nlh;
struct nfgenmsg *nfmsg;
sk_buff_data_t old_tail = inst->skb->tail;
struct sock *sk;
const unsigned char *hwhdrp;
nlh = nlmsg_put(inst->skb, 0, 0,
nfnl_msg_type(NFNL_SUBSYS_ULOG, NFULNL_MSG_PACKET),
sizeof(struct nfgenmsg), 0);
if (!nlh)
return -1;
nfmsg = nlmsg_data(nlh);
nfmsg->nfgen_family = pf;
nfmsg->version = NFNETLINK_V0;
nfmsg->res_id = htons(inst->group_num);
memset(&pmsg, 0, sizeof(pmsg));
pmsg.hw_protocol = skb->protocol;
pmsg.hook = hooknum;
if (nla_put(inst->skb, NFULA_PACKET_HDR, sizeof(pmsg), &pmsg))
goto nla_put_failure;
if (prefix &&
nla_put(inst->skb, NFULA_PREFIX, plen, prefix))
goto nla_put_failure;
if (indev) {
#if !IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
if (nla_put_be32(inst->skb, NFULA_IFINDEX_INDEV,
htonl(indev->ifindex)))
goto nla_put_failure;
#else
if (pf == PF_BRIDGE) {
/* Case 1: outdev is physical input device, we need to
* look for bridge group (when called from
* netfilter_bridge) */
if (nla_put_be32(inst->skb, NFULA_IFINDEX_PHYSINDEV,
htonl(indev->ifindex)) ||
/* this is the bridge group "brX" */
/* rcu_read_lock()ed by nf_hook_thresh or
* nf_log_packet.
*/
nla_put_be32(inst->skb, NFULA_IFINDEX_INDEV,
htonl(br_port_get_rcu(indev)->br->dev->ifindex)))
goto nla_put_failure;
} else {
struct net_device *physindev;
/* Case 2: indev is bridge group, we need to look for
* physical device (when called from ipv4) */
if (nla_put_be32(inst->skb, NFULA_IFINDEX_INDEV,
htonl(indev->ifindex)))
goto nla_put_failure;
physindev = nf_bridge_get_physindev(skb);
if (physindev &&
nla_put_be32(inst->skb, NFULA_IFINDEX_PHYSINDEV,
htonl(physindev->ifindex)))
goto nla_put_failure;
}
#endif
}
if (outdev) {
#if !IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
if (nla_put_be32(inst->skb, NFULA_IFINDEX_OUTDEV,
htonl(outdev->ifindex)))
goto nla_put_failure;
#else
if (pf == PF_BRIDGE) {
/* Case 1: outdev is physical output device, we need to
* look for bridge group (when called from
* netfilter_bridge) */
if (nla_put_be32(inst->skb, NFULA_IFINDEX_PHYSOUTDEV,
htonl(outdev->ifindex)) ||
/* this is the bridge group "brX" */
/* rcu_read_lock()ed by nf_hook_thresh or
* nf_log_packet.
*/
nla_put_be32(inst->skb, NFULA_IFINDEX_OUTDEV,
htonl(br_port_get_rcu(outdev)->br->dev->ifindex)))
goto nla_put_failure;
} else {
struct net_device *physoutdev;
/* Case 2: indev is a bridge group, we need to look
* for physical device (when called from ipv4) */
if (nla_put_be32(inst->skb, NFULA_IFINDEX_OUTDEV,
htonl(outdev->ifindex)))
goto nla_put_failure;
physoutdev = nf_bridge_get_physoutdev(skb);
if (physoutdev &&
nla_put_be32(inst->skb, NFULA_IFINDEX_PHYSOUTDEV,
htonl(physoutdev->ifindex)))
goto nla_put_failure;
}
#endif
}
if (skb->mark &&
nla_put_be32(inst->skb, NFULA_MARK, htonl(skb->mark)))
goto nla_put_failure;
if (indev && skb->dev &&
skb->mac_header != skb->network_header) {
struct nfulnl_msg_packet_hw phw;
int len;
memset(&phw, 0, sizeof(phw));
len = dev_parse_header(skb, phw.hw_addr);
if (len > 0) {
phw.hw_addrlen = htons(len);
if (nla_put(inst->skb, NFULA_HWADDR, sizeof(phw), &phw))
goto nla_put_failure;
}
}
if (indev && skb_mac_header_was_set(skb)) {
if (nla_put_be16(inst->skb, NFULA_HWTYPE, htons(skb->dev->type)) ||
nla_put_be16(inst->skb, NFULA_HWLEN,
htons(skb->dev->hard_header_len)))
goto nla_put_failure;
hwhdrp = skb_mac_header(skb);
if (skb->dev->type == ARPHRD_SIT)
hwhdrp -= ETH_HLEN;
if (hwhdrp >= skb->head &&
nla_put(inst->skb, NFULA_HWHEADER,
skb->dev->hard_header_len, hwhdrp))
goto nla_put_failure;
}
if (skb->tstamp) {
struct nfulnl_msg_packet_timestamp ts;
struct timespec64 kts = ktime_to_timespec64(skb->tstamp);
ts.sec = cpu_to_be64(kts.tv_sec);
ts.usec = cpu_to_be64(kts.tv_nsec / NSEC_PER_USEC);
if (nla_put(inst->skb, NFULA_TIMESTAMP, sizeof(ts), &ts))
goto nla_put_failure;
}
/* UID */
sk = skb->sk;
if (sk && sk_fullsock(sk)) {
read_lock_bh(&sk->sk_callback_lock);
if (sk->sk_socket && sk->sk_socket->file) {
struct file *file = sk->sk_socket->file;
const struct cred *cred = file->f_cred;
struct user_namespace *user_ns = inst->peer_user_ns;
__be32 uid = htonl(from_kuid_munged(user_ns, cred->fsuid));
__be32 gid = htonl(from_kgid_munged(user_ns, cred->fsgid));
read_unlock_bh(&sk->sk_callback_lock);
if (nla_put_be32(inst->skb, NFULA_UID, uid) ||
nla_put_be32(inst->skb, NFULA_GID, gid))
goto nla_put_failure;
} else
read_unlock_bh(&sk->sk_callback_lock);
}
/* local sequence number */
if ((inst->flags & NFULNL_CFG_F_SEQ) &&
nla_put_be32(inst->skb, NFULA_SEQ, htonl(inst->seq++)))
goto nla_put_failure;
/* global sequence number */
if ((inst->flags & NFULNL_CFG_F_SEQ_GLOBAL) &&
nla_put_be32(inst->skb, NFULA_SEQ_GLOBAL,
htonl(atomic_inc_return(&log->global_seq))))
goto nla_put_failure;
if (ct && nfnl_ct->build(inst->skb, ct, ctinfo,
NFULA_CT, NFULA_CT_INFO) < 0)
goto nla_put_failure;
if (data_len) {
struct nlattr *nla;
int size = nla_attr_size(data_len);
if (skb_tailroom(inst->skb) < nla_total_size(data_len))
goto nla_put_failure;
nla = skb_put(inst->skb, nla_total_size(data_len));
nla->nla_type = NFULA_PAYLOAD;
nla->nla_len = size;
if (skb_copy_bits(skb, 0, nla_data(nla), data_len))
BUG();
}
nlh->nlmsg_len = inst->skb->tail - old_tail;
return 0;
nla_put_failure:
PRINTR(KERN_ERR "nfnetlink_log: error creating log nlmsg\n");
return -1;
}
/* Send RST reply */
void nf_send_reset(struct net *net, struct sk_buff *oldskb, int hook)
{
struct sk_buff *nskb;
struct iphdr *niph;
const struct tcphdr *oth;
struct tcphdr _oth;
oth = nf_reject_ip_tcphdr_get(oldskb, &_oth, hook);
if (!oth)
return;
if (skb_rtable(oldskb)->rt_flags & (RTCF_BROADCAST | RTCF_MULTICAST))
return;
nskb = alloc_skb(sizeof(struct iphdr) + sizeof(struct tcphdr) +
LL_MAX_HEADER, GFP_ATOMIC);
if (!nskb)
return;
/* ip_route_me_harder expects skb->dst to be set */
skb_dst_set_noref(nskb, skb_dst(oldskb));
nskb->mark = IP4_REPLY_MARK(net, oldskb->mark);
skb_reserve(nskb, LL_MAX_HEADER);
niph = nf_reject_iphdr_put(nskb, oldskb, IPPROTO_TCP,
ip4_dst_hoplimit(skb_dst(nskb)));
nf_reject_ip_tcphdr_put(nskb, oldskb, oth);
if (ip_route_me_harder(net, nskb, RTN_UNSPEC))
goto free_nskb;
niph = ip_hdr(nskb);
/* "Never happens" */
if (nskb->len > dst_mtu(skb_dst(nskb)))
goto free_nskb;
nf_ct_attach(nskb, oldskb);
#if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
/* If we use ip_local_out for bridged traffic, the MAC source on
* the RST will be ours, instead of the destination's. This confuses
* some routers/firewalls, and they drop the packet. So we need to
* build the eth header using the original destination's MAC as the
* source, and send the RST packet directly.
*/
if (oldskb->nf_bridge) {
struct ethhdr *oeth = eth_hdr(oldskb);
nskb->dev = nf_bridge_get_physindev(oldskb);
niph->tot_len = htons(nskb->len);
ip_send_check(niph);
if (dev_hard_header(nskb, nskb->dev, ntohs(nskb->protocol),
oeth->h_source, oeth->h_dest, nskb->len) < 0)
goto free_nskb;
dev_queue_xmit(nskb);
} else
#endif
ip_local_out(net, nskb->sk, nskb);
return;
free_nskb:
kfree_skb(nskb);
}
void nf_send_reset6(struct net *net, struct sk_buff *oldskb, int hook)
{
struct sk_buff *nskb;
struct tcphdr _otcph;
const struct tcphdr *otcph;
unsigned int otcplen, hh_len;
const struct ipv6hdr *oip6h = ipv6_hdr(oldskb);
struct ipv6hdr *ip6h;
struct dst_entry *dst = NULL;
struct flowi6 fl6;
if ((!(ipv6_addr_type(&oip6h->saddr) & IPV6_ADDR_UNICAST)) ||
(!(ipv6_addr_type(&oip6h->daddr) & IPV6_ADDR_UNICAST))) {
pr_debug("addr is not unicast.\n");
return;
}
otcph = nf_reject_ip6_tcphdr_get(oldskb, &_otcph, &otcplen, hook);
if (!otcph)
return;
memset(&fl6, 0, sizeof(fl6));
fl6.flowi6_proto = IPPROTO_TCP;
fl6.saddr = oip6h->daddr;
fl6.daddr = oip6h->saddr;
fl6.fl6_sport = otcph->dest;
fl6.fl6_dport = otcph->source;
security_skb_classify_flow(oldskb, flowi6_to_flowi(&fl6));
dst = ip6_route_output(net, NULL, &fl6);
if (dst == NULL || dst->error) {
dst_release(dst);
return;
}
dst = xfrm_lookup(net, dst, flowi6_to_flowi(&fl6), NULL, 0);
if (IS_ERR(dst))
return;
hh_len = (dst->dev->hard_header_len + 15)&~15;
nskb = alloc_skb(hh_len + 15 + dst->header_len + sizeof(struct ipv6hdr)
+ sizeof(struct tcphdr) + dst->trailer_len,
GFP_ATOMIC);
if (!nskb) {
net_dbg_ratelimited("cannot alloc skb\n");
dst_release(dst);
return;
}
skb_dst_set(nskb, dst);
skb_reserve(nskb, hh_len + dst->header_len);
ip6h = nf_reject_ip6hdr_put(nskb, oldskb, IPPROTO_TCP,
ip6_dst_hoplimit(dst));
nf_reject_ip6_tcphdr_put(nskb, oldskb, otcph, otcplen);
nf_ct_attach(nskb, oldskb);
#if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
/* If we use ip6_local_out for bridged traffic, the MAC source on
* the RST will be ours, instead of the destination's. This confuses
* some routers/firewalls, and they drop the packet. So we need to
* build the eth header using the original destination's MAC as the
* source, and send the RST packet directly.
*/
if (oldskb->nf_bridge) {
struct ethhdr *oeth = eth_hdr(oldskb);
nskb->dev = nf_bridge_get_physindev(oldskb);
nskb->protocol = htons(ETH_P_IPV6);
ip6h->payload_len = htons(sizeof(struct tcphdr));
if (dev_hard_header(nskb, nskb->dev, ntohs(nskb->protocol),
oeth->h_source, oeth->h_dest, nskb->len) < 0)
return;
dev_queue_xmit(nskb);
} else
#endif
ip6_local_out(net, nskb->sk, nskb);
}