Commit d16cf20e authored by Pablo Neira Ayuso's avatar Pablo Neira Ayuso

netfilter: remove ip_queue support

This patch removes ip_queue support which was marked as obsolete
years ago. The nfnetlink_queue modules provides more advanced
user-space packet queueing mechanism.

This patch also removes capability code included in SELinux that
refers to ip_queue. Otherwise, we break compilation.

Several warning has been sent regarding this to the mailing list
in the past month without anyone rising the hand to stop this
with some strong argument.
Signed-off-by: default avatarPablo Neira Ayuso <pablo@netfilter.org>
parent 6714cf54
What: ip_queue
Date: finally removed in kernel v3.5.0
Contact: Pablo Neira Ayuso <pablo@netfilter.org>
Description:
ip_queue has been replaced by nfnetlink_queue which provides
more advanced queueing mechanism to user-space. The ip_queue
module was already announced to become obsolete years ago.
Users:
header-y += ip_queue.h
header-y += ip_tables.h header-y += ip_tables.h
header-y += ipt_CLUSTERIP.h header-y += ipt_CLUSTERIP.h
header-y += ipt_ECN.h header-y += ipt_ECN.h
......
/*
* This is a module which is used for queueing IPv4 packets and
* communicating with userspace via netlink.
*
* (C) 2000 James Morris, this code is GPL.
*/
#ifndef _IP_QUEUE_H
#define _IP_QUEUE_H
#ifdef __KERNEL__
#ifdef DEBUG_IPQ
#define QDEBUG(x...) printk(KERN_DEBUG ## x)
#else
#define QDEBUG(x...)
#endif /* DEBUG_IPQ */
#else
#include <net/if.h>
#endif /* ! __KERNEL__ */
/* Messages sent from kernel */
typedef struct ipq_packet_msg {
unsigned long packet_id; /* ID of queued packet */
unsigned long mark; /* Netfilter mark value */
long timestamp_sec; /* Packet arrival time (seconds) */
long timestamp_usec; /* Packet arrvial time (+useconds) */
unsigned int hook; /* Netfilter hook we rode in on */
char indev_name[IFNAMSIZ]; /* Name of incoming interface */
char outdev_name[IFNAMSIZ]; /* Name of outgoing interface */
__be16 hw_protocol; /* Hardware protocol (network order) */
unsigned short hw_type; /* Hardware type */
unsigned char hw_addrlen; /* Hardware address length */
unsigned char hw_addr[8]; /* Hardware address */
size_t data_len; /* Length of packet data */
unsigned char payload[0]; /* Optional packet data */
} ipq_packet_msg_t;
/* Messages sent from userspace */
typedef struct ipq_mode_msg {
unsigned char value; /* Requested mode */
size_t range; /* Optional range of packet requested */
} ipq_mode_msg_t;
typedef struct ipq_verdict_msg {
unsigned int value; /* Verdict to hand to netfilter */
unsigned long id; /* Packet ID for this verdict */
size_t data_len; /* Length of replacement data */
unsigned char payload[0]; /* Optional replacement packet */
} ipq_verdict_msg_t;
typedef struct ipq_peer_msg {
union {
ipq_verdict_msg_t verdict;
ipq_mode_msg_t mode;
} msg;
} ipq_peer_msg_t;
/* Packet delivery modes */
enum {
IPQ_COPY_NONE, /* Initial mode, packets are dropped */
IPQ_COPY_META, /* Copy metadata */
IPQ_COPY_PACKET /* Copy metadata + packet (range) */
};
#define IPQ_COPY_MAX IPQ_COPY_PACKET
/* Types of messages */
#define IPQM_BASE 0x10 /* standard netlink messages below this */
#define IPQM_MODE (IPQM_BASE + 1) /* Mode request from peer */
#define IPQM_VERDICT (IPQM_BASE + 2) /* Verdict from peer */
#define IPQM_PACKET (IPQM_BASE + 3) /* Packet from kernel */
#define IPQM_MAX (IPQM_BASE + 4)
#endif /*_IP_QUEUE_H*/
...@@ -7,7 +7,7 @@ ...@@ -7,7 +7,7 @@
#define NETLINK_ROUTE 0 /* Routing/device hook */ #define NETLINK_ROUTE 0 /* Routing/device hook */
#define NETLINK_UNUSED 1 /* Unused number */ #define NETLINK_UNUSED 1 /* Unused number */
#define NETLINK_USERSOCK 2 /* Reserved for user mode socket protocols */ #define NETLINK_USERSOCK 2 /* Reserved for user mode socket protocols */
#define NETLINK_FIREWALL 3 /* Firewalling hook */ #define NETLINK_FIREWALL 3 /* Unused number, formerly ip_queue */
#define NETLINK_SOCK_DIAG 4 /* socket monitoring */ #define NETLINK_SOCK_DIAG 4 /* socket monitoring */
#define NETLINK_NFLOG 5 /* netfilter/iptables ULOG */ #define NETLINK_NFLOG 5 /* netfilter/iptables ULOG */
#define NETLINK_XFRM 6 /* ipsec */ #define NETLINK_XFRM 6 /* ipsec */
......
...@@ -66,6 +66,3 @@ obj-$(CONFIG_IP_NF_ARP_MANGLE) += arpt_mangle.o ...@@ -66,6 +66,3 @@ obj-$(CONFIG_IP_NF_ARP_MANGLE) += arpt_mangle.o
# just filtering instance of ARP tables for now # just filtering instance of ARP tables for now
obj-$(CONFIG_IP_NF_ARPFILTER) += arptable_filter.o obj-$(CONFIG_IP_NF_ARPFILTER) += arptable_filter.o
obj-$(CONFIG_IP_NF_QUEUE) += ip_queue.o
/*
* This is a module which is used for queueing IPv4 packets and
* communicating with userspace via netlink.
*
* (C) 2000-2002 James Morris <jmorris@intercode.com.au>
* (C) 2003-2005 Netfilter Core Team <coreteam@netfilter.org>
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License version 2 as
* published by the Free Software Foundation.
*/
#include <linux/module.h>
#include <linux/skbuff.h>
#include <linux/init.h>
#include <linux/ip.h>
#include <linux/notifier.h>
#include <linux/netdevice.h>
#include <linux/netfilter.h>
#include <linux/netfilter_ipv4/ip_queue.h>
#include <linux/netfilter_ipv4/ip_tables.h>
#include <linux/netlink.h>
#include <linux/spinlock.h>
#include <linux/sysctl.h>
#include <linux/proc_fs.h>
#include <linux/seq_file.h>
#include <linux/security.h>
#include <linux/net.h>
#include <linux/mutex.h>
#include <linux/slab.h>
#include <net/net_namespace.h>
#include <net/sock.h>
#include <net/route.h>
#include <net/netfilter/nf_queue.h>
#include <net/ip.h>
#define IPQ_QMAX_DEFAULT 1024
#define IPQ_PROC_FS_NAME "ip_queue"
#define NET_IPQ_QMAX 2088
#define NET_IPQ_QMAX_NAME "ip_queue_maxlen"
typedef int (*ipq_cmpfn)(struct nf_queue_entry *, unsigned long);
static unsigned char copy_mode __read_mostly = IPQ_COPY_NONE;
static unsigned int queue_maxlen __read_mostly = IPQ_QMAX_DEFAULT;
static DEFINE_SPINLOCK(queue_lock);
static int peer_pid __read_mostly;
static unsigned int copy_range __read_mostly;
static unsigned int queue_total;
static unsigned int queue_dropped = 0;
static unsigned int queue_user_dropped = 0;
static struct sock *ipqnl __read_mostly;
static LIST_HEAD(queue_list);
static DEFINE_MUTEX(ipqnl_mutex);
static inline void
__ipq_enqueue_entry(struct nf_queue_entry *entry)
{
list_add_tail(&entry->list, &queue_list);
queue_total++;
}
static inline int
__ipq_set_mode(unsigned char mode, unsigned int range)
{
int status = 0;
switch(mode) {
case IPQ_COPY_NONE:
case IPQ_COPY_META:
copy_mode = mode;
copy_range = 0;
break;
case IPQ_COPY_PACKET:
if (range > 0xFFFF)
range = 0xFFFF;
copy_range = range;
copy_mode = mode;
break;
default:
status = -EINVAL;
}
return status;
}
static void __ipq_flush(ipq_cmpfn cmpfn, unsigned long data);
static inline void
__ipq_reset(void)
{
peer_pid = 0;
net_disable_timestamp();
__ipq_set_mode(IPQ_COPY_NONE, 0);
__ipq_flush(NULL, 0);
}
static struct nf_queue_entry *
ipq_find_dequeue_entry(unsigned long id)
{
struct nf_queue_entry *entry = NULL, *i;
spin_lock_bh(&queue_lock);
list_for_each_entry(i, &queue_list, list) {
if ((unsigned long)i == id) {
entry = i;
break;
}
}
if (entry) {
list_del(&entry->list);
queue_total--;
}
spin_unlock_bh(&queue_lock);
return entry;
}
static void
__ipq_flush(ipq_cmpfn cmpfn, unsigned long data)
{
struct nf_queue_entry *entry, *next;
list_for_each_entry_safe(entry, next, &queue_list, list) {
if (!cmpfn || cmpfn(entry, data)) {
list_del(&entry->list);
queue_total--;
nf_reinject(entry, NF_DROP);
}
}
}
static void
ipq_flush(ipq_cmpfn cmpfn, unsigned long data)
{
spin_lock_bh(&queue_lock);
__ipq_flush(cmpfn, data);
spin_unlock_bh(&queue_lock);
}
static struct sk_buff *
ipq_build_packet_message(struct nf_queue_entry *entry, int *errp)
{
sk_buff_data_t old_tail;
size_t size = 0;
size_t data_len = 0;
struct sk_buff *skb;
struct ipq_packet_msg *pmsg;
struct nlmsghdr *nlh;
struct timeval tv;
switch (ACCESS_ONCE(copy_mode)) {
case IPQ_COPY_META:
case IPQ_COPY_NONE:
size = NLMSG_SPACE(sizeof(*pmsg));
break;
case IPQ_COPY_PACKET:
if (entry->skb->ip_summed == CHECKSUM_PARTIAL &&
(*errp = skb_checksum_help(entry->skb)))
return NULL;
data_len = ACCESS_ONCE(copy_range);
if (data_len == 0 || data_len > entry->skb->len)
data_len = entry->skb->len;
size = NLMSG_SPACE(sizeof(*pmsg) + data_len);
break;
default:
*errp = -EINVAL;
return NULL;
}
skb = alloc_skb(size, GFP_ATOMIC);
if (!skb)
goto nlmsg_failure;
old_tail = skb->tail;
nlh = NLMSG_PUT(skb, 0, 0, IPQM_PACKET, size - sizeof(*nlh));
pmsg = NLMSG_DATA(nlh);
memset(pmsg, 0, sizeof(*pmsg));
pmsg->packet_id = (unsigned long )entry;
pmsg->data_len = data_len;
tv = ktime_to_timeval(entry->skb->tstamp);
pmsg->timestamp_sec = tv.tv_sec;
pmsg->timestamp_usec = tv.tv_usec;
pmsg->mark = entry->skb->mark;
pmsg->hook = entry->hook;
pmsg->hw_protocol = entry->skb->protocol;
if (entry->indev)
strcpy(pmsg->indev_name, entry->indev->name);
else
pmsg->indev_name[0] = '\0';
if (entry->outdev)
strcpy(pmsg->outdev_name, entry->outdev->name);
else
pmsg->outdev_name[0] = '\0';
if (entry->indev && entry->skb->dev &&
entry->skb->mac_header != entry->skb->network_header) {
pmsg->hw_type = entry->skb->dev->type;
pmsg->hw_addrlen = dev_parse_header(entry->skb,
pmsg->hw_addr);
}
if (data_len)
if (skb_copy_bits(entry->skb, 0, pmsg->payload, data_len))
BUG();
nlh->nlmsg_len = skb->tail - old_tail;
return skb;
nlmsg_failure:
kfree_skb(skb);
*errp = -EINVAL;
printk(KERN_ERR "ip_queue: error creating packet message\n");
return NULL;
}
static int
ipq_enqueue_packet(struct nf_queue_entry *entry, unsigned int queuenum)
{
int status = -EINVAL;
struct sk_buff *nskb;
if (copy_mode == IPQ_COPY_NONE)
return -EAGAIN;
nskb = ipq_build_packet_message(entry, &status);
if (nskb == NULL)
return status;
spin_lock_bh(&queue_lock);
if (!peer_pid)
goto err_out_free_nskb;
if (queue_total >= queue_maxlen) {
queue_dropped++;
status = -ENOSPC;
if (net_ratelimit())
printk (KERN_WARNING "ip_queue: full at %d entries, "
"dropping packets(s). Dropped: %d\n", queue_total,
queue_dropped);
goto err_out_free_nskb;
}
/* netlink_unicast will either free the nskb or attach it to a socket */
status = netlink_unicast(ipqnl, nskb, peer_pid, MSG_DONTWAIT);
if (status < 0) {
queue_user_dropped++;
goto err_out_unlock;
}
__ipq_enqueue_entry(entry);
spin_unlock_bh(&queue_lock);
return status;
err_out_free_nskb:
kfree_skb(nskb);
err_out_unlock:
spin_unlock_bh(&queue_lock);
return status;
}
static int
ipq_mangle_ipv4(ipq_verdict_msg_t *v, struct nf_queue_entry *e)
{
int diff;
struct iphdr *user_iph = (struct iphdr *)v->payload;
struct sk_buff *nskb;
if (v->data_len < sizeof(*user_iph))
return 0;
diff = v->data_len - e->skb->len;
if (diff < 0) {
if (pskb_trim(e->skb, v->data_len))
return -ENOMEM;
} else if (diff > 0) {
if (v->data_len > 0xFFFF)
return -EINVAL;
if (diff > skb_tailroom(e->skb)) {
nskb = skb_copy_expand(e->skb, skb_headroom(e->skb),
diff, GFP_ATOMIC);
if (!nskb) {
printk(KERN_WARNING "ip_queue: error "
"in mangle, dropping packet\n");
return -ENOMEM;
}
kfree_skb(e->skb);
e->skb = nskb;
}
skb_put(e->skb, diff);
}
if (!skb_make_writable(e->skb, v->data_len))
return -ENOMEM;
skb_copy_to_linear_data(e->skb, v->payload, v->data_len);
e->skb->ip_summed = CHECKSUM_NONE;
return 0;
}
static int
ipq_set_verdict(struct ipq_verdict_msg *vmsg, unsigned int len)
{
struct nf_queue_entry *entry;
if (vmsg->value > NF_MAX_VERDICT || vmsg->value == NF_STOLEN)
return -EINVAL;
entry = ipq_find_dequeue_entry(vmsg->id);
if (entry == NULL)
return -ENOENT;
else {
int verdict = vmsg->value;
if (vmsg->data_len && vmsg->data_len == len)
if (ipq_mangle_ipv4(vmsg, entry) < 0)
verdict = NF_DROP;
nf_reinject(entry, verdict);
return 0;
}
}
static int
ipq_set_mode(unsigned char mode, unsigned int range)
{
int status;
spin_lock_bh(&queue_lock);
status = __ipq_set_mode(mode, range);
spin_unlock_bh(&queue_lock);
return status;
}
static int
ipq_receive_peer(struct ipq_peer_msg *pmsg,
unsigned char type, unsigned int len)
{
int status = 0;
if (len < sizeof(*pmsg))
return -EINVAL;
switch (type) {
case IPQM_MODE:
status = ipq_set_mode(pmsg->msg.mode.value,
pmsg->msg.mode.range);
break;
case IPQM_VERDICT:
status = ipq_set_verdict(&pmsg->msg.verdict,
len - sizeof(*pmsg));
break;
default:
status = -EINVAL;
}
return status;
}
static int
dev_cmp(struct nf_queue_entry *entry, unsigned long ifindex)
{
if (entry->indev)
if (entry->indev->ifindex == ifindex)
return 1;
if (entry->outdev)
if (entry->outdev->ifindex == ifindex)
return 1;
#ifdef CONFIG_BRIDGE_NETFILTER
if (entry->skb->nf_bridge) {
if (entry->skb->nf_bridge->physindev &&
entry->skb->nf_bridge->physindev->ifindex == ifindex)
return 1;
if (entry->skb->nf_bridge->physoutdev &&
entry->skb->nf_bridge->physoutdev->ifindex == ifindex)
return 1;
}
#endif
return 0;
}
static void
ipq_dev_drop(int ifindex)
{
ipq_flush(dev_cmp, ifindex);
}
#define RCV_SKB_FAIL(err) do { netlink_ack(skb, nlh, (err)); return; } while (0)
static inline void
__ipq_rcv_skb(struct sk_buff *skb)
{
int status, type, pid, flags;
unsigned int nlmsglen, skblen;
struct nlmsghdr *nlh;
bool enable_timestamp = false;
skblen = skb->len;
if (skblen < sizeof(*nlh))
return;
nlh = nlmsg_hdr(skb);
nlmsglen = nlh->nlmsg_len;
if (nlmsglen < sizeof(*nlh) || skblen < nlmsglen)
return;
pid = nlh->nlmsg_pid;
flags = nlh->nlmsg_flags;
if(pid <= 0 || !(flags & NLM_F_REQUEST) || flags & NLM_F_MULTI)
RCV_SKB_FAIL(-EINVAL);
if (flags & MSG_TRUNC)
RCV_SKB_FAIL(-ECOMM);
type = nlh->nlmsg_type;
if (type < NLMSG_NOOP || type >= IPQM_MAX)
RCV_SKB_FAIL(-EINVAL);
if (type <= IPQM_BASE)
return;
if (!capable(CAP_NET_ADMIN))
RCV_SKB_FAIL(-EPERM);
spin_lock_bh(&queue_lock);
if (peer_pid) {
if (peer_pid != pid) {
spin_unlock_bh(&queue_lock);
RCV_SKB_FAIL(-EBUSY);
}
} else {
enable_timestamp = true;
peer_pid = pid;
}
spin_unlock_bh(&queue_lock);
if (enable_timestamp)
net_enable_timestamp();
status = ipq_receive_peer(NLMSG_DATA(nlh), type,
nlmsglen - NLMSG_LENGTH(0));
if (status < 0)
RCV_SKB_FAIL(status);
if (flags & NLM_F_ACK)
netlink_ack(skb, nlh, 0);
}
static void
ipq_rcv_skb(struct sk_buff *skb)
{
mutex_lock(&ipqnl_mutex);
__ipq_rcv_skb(skb);
mutex_unlock(&ipqnl_mutex);
}
static int
ipq_rcv_dev_event(struct notifier_block *this,
unsigned long event, void *ptr)
{
struct net_device *dev = ptr;
if (!net_eq(dev_net(dev), &init_net))
return NOTIFY_DONE;
/* Drop any packets associated with the downed device */
if (event == NETDEV_DOWN)
ipq_dev_drop(dev->ifindex);
return NOTIFY_DONE;
}
static struct notifier_block ipq_dev_notifier = {
.notifier_call = ipq_rcv_dev_event,
};
static int
ipq_rcv_nl_event(struct notifier_block *this,
unsigned long event, void *ptr)
{
struct netlink_notify *n = ptr;
if (event == NETLINK_URELEASE && n->protocol == NETLINK_FIREWALL) {
spin_lock_bh(&queue_lock);
if ((net_eq(n->net, &init_net)) && (n->pid == peer_pid))
__ipq_reset();
spin_unlock_bh(&queue_lock);
}
return NOTIFY_DONE;
}
static struct notifier_block ipq_nl_notifier = {
.notifier_call = ipq_rcv_nl_event,
};
#ifdef CONFIG_SYSCTL
static struct ctl_table_header *ipq_sysctl_header;
static ctl_table ipq_table[] = {
{
.procname = NET_IPQ_QMAX_NAME,
.data = &queue_maxlen,
.maxlen = sizeof(queue_maxlen),
.mode = 0644,
.proc_handler = proc_dointvec
},
{ }
};
#endif
#ifdef CONFIG_PROC_FS
static int ip_queue_show(struct seq_file *m, void *v)
{
spin_lock_bh(&queue_lock);
seq_printf(m,
"Peer PID : %d\n"
"Copy mode : %hu\n"
"Copy range : %u\n"
"Queue length : %u\n"
"Queue max. length : %u\n"
"Queue dropped : %u\n"
"Netlink dropped : %u\n",
peer_pid,
copy_mode,
copy_range,
queue_total,
queue_maxlen,
queue_dropped,
queue_user_dropped);
spin_unlock_bh(&queue_lock);
return 0;
}
static int ip_queue_open(struct inode *inode, struct file *file)
{
return single_open(file, ip_queue_show, NULL);
}
static const struct file_operations ip_queue_proc_fops = {
.open = ip_queue_open,
.read = seq_read,
.llseek = seq_lseek,
.release = single_release,
.owner = THIS_MODULE,
};
#endif
static const struct nf_queue_handler nfqh = {
.name = "ip_queue",
.outfn = &ipq_enqueue_packet,
};
static int __init ip_queue_init(void)
{
int status = -ENOMEM;
struct proc_dir_entry *proc __maybe_unused;
netlink_register_notifier(&ipq_nl_notifier);
ipqnl = netlink_kernel_create(&init_net, NETLINK_FIREWALL, 0,
ipq_rcv_skb, NULL, THIS_MODULE);
if (ipqnl == NULL) {
printk(KERN_ERR "ip_queue: failed to create netlink socket\n");
goto cleanup_netlink_notifier;
}
#ifdef CONFIG_PROC_FS
proc = proc_create(IPQ_PROC_FS_NAME, 0, init_net.proc_net,
&ip_queue_proc_fops);
if (!proc) {
printk(KERN_ERR "ip_queue: failed to create proc entry\n");
goto cleanup_ipqnl;
}
#endif
register_netdevice_notifier(&ipq_dev_notifier);
#ifdef CONFIG_SYSCTL
ipq_sysctl_header = register_net_sysctl(&init_net, "net/ipv4", ipq_table);
#endif
status = nf_register_queue_handler(NFPROTO_IPV4, &nfqh);
if (status < 0) {
printk(KERN_ERR "ip_queue: failed to register queue handler\n");
goto cleanup_sysctl;
}
return status;
cleanup_sysctl:
#ifdef CONFIG_SYSCTL
unregister_net_sysctl_table(ipq_sysctl_header);
#endif
unregister_netdevice_notifier(&ipq_dev_notifier);
proc_net_remove(&init_net, IPQ_PROC_FS_NAME);
cleanup_ipqnl: __maybe_unused
netlink_kernel_release(ipqnl);
mutex_lock(&ipqnl_mutex);
mutex_unlock(&ipqnl_mutex);
cleanup_netlink_notifier:
netlink_unregister_notifier(&ipq_nl_notifier);
return status;
}
static void __exit ip_queue_fini(void)
{
nf_unregister_queue_handlers(&nfqh);
ipq_flush(NULL, 0);
#ifdef CONFIG_SYSCTL
unregister_net_sysctl_table(ipq_sysctl_header);
#endif
unregister_netdevice_notifier(&ipq_dev_notifier);
proc_net_remove(&init_net, IPQ_PROC_FS_NAME);
netlink_kernel_release(ipqnl);
mutex_lock(&ipqnl_mutex);
mutex_unlock(&ipqnl_mutex);
netlink_unregister_notifier(&ipq_nl_notifier);
}
MODULE_DESCRIPTION("IPv4 packet queue handler");
MODULE_AUTHOR("James Morris <jmorris@intercode.com.au>");
MODULE_LICENSE("GPL");
MODULE_ALIAS_NET_PF_PROTO(PF_NETLINK, NETLINK_FIREWALL);
module_init(ip_queue_init);
module_exit(ip_queue_fini);
...@@ -25,28 +25,6 @@ config NF_CONNTRACK_IPV6 ...@@ -25,28 +25,6 @@ config NF_CONNTRACK_IPV6
To compile it as a module, choose M here. If unsure, say N. To compile it as a module, choose M here. If unsure, say N.
config IP6_NF_QUEUE
tristate "IP6 Userspace queueing via NETLINK (OBSOLETE)"
depends on INET && IPV6 && NETFILTER
depends on NETFILTER_ADVANCED
---help---
This option adds a queue handler to the kernel for IPv6
packets which enables users to receive the filtered packets
with QUEUE target using libipq.
This option enables the old IPv6-only "ip6_queue" implementation
which has been obsoleted by the new "nfnetlink_queue" code (see
CONFIG_NETFILTER_NETLINK_QUEUE).
(C) Fernando Anton 2001
IPv64 Project - Work based in IPv64 draft by Arturo Azcorra.
Universidad Carlos III de Madrid
Universidad Politecnica de Alcala de Henares
email: <fanton@it.uc3m.es>.
To compile it as a module, choose M here. If unsure, say N.
config IP6_NF_IPTABLES config IP6_NF_IPTABLES
tristate "IP6 tables support (required for filtering)" tristate "IP6 tables support (required for filtering)"
depends on INET && IPV6 depends on INET && IPV6
......
...@@ -6,7 +6,6 @@ ...@@ -6,7 +6,6 @@
obj-$(CONFIG_IP6_NF_IPTABLES) += ip6_tables.o obj-$(CONFIG_IP6_NF_IPTABLES) += ip6_tables.o
obj-$(CONFIG_IP6_NF_FILTER) += ip6table_filter.o obj-$(CONFIG_IP6_NF_FILTER) += ip6table_filter.o
obj-$(CONFIG_IP6_NF_MANGLE) += ip6table_mangle.o obj-$(CONFIG_IP6_NF_MANGLE) += ip6table_mangle.o
obj-$(CONFIG_IP6_NF_QUEUE) += ip6_queue.o
obj-$(CONFIG_IP6_NF_RAW) += ip6table_raw.o obj-$(CONFIG_IP6_NF_RAW) += ip6table_raw.o
obj-$(CONFIG_IP6_NF_SECURITY) += ip6table_security.o obj-$(CONFIG_IP6_NF_SECURITY) += ip6table_security.o
......
/*
* This is a module which is used for queueing IPv6 packets and
* communicating with userspace via netlink.
*
* (C) 2001 Fernando Anton, this code is GPL.
* IPv64 Project - Work based in IPv64 draft by Arturo Azcorra.
* Universidad Carlos III de Madrid - Leganes (Madrid) - Spain
* Universidad Politecnica de Alcala de Henares - Alcala de H. (Madrid) - Spain
* email: fanton@it.uc3m.es
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License version 2 as
* published by the Free Software Foundation.
*/
#include <linux/module.h>
#include <linux/skbuff.h>
#include <linux/init.h>
#include <linux/ipv6.h>
#include <linux/notifier.h>
#include <linux/netdevice.h>
#include <linux/netfilter.h>
#include <linux/netlink.h>
#include <linux/spinlock.h>
#include <linux/sysctl.h>
#include <linux/proc_fs.h>
#include <linux/seq_file.h>
#include <linux/mutex.h>
#include <linux/slab.h>
#include <net/net_namespace.h>
#include <net/sock.h>
#include <net/ipv6.h>
#include <net/ip6_route.h>
#include <net/netfilter/nf_queue.h>
#include <linux/netfilter_ipv4/ip_queue.h>
#include <linux/netfilter_ipv4/ip_tables.h>
#include <linux/netfilter_ipv6/ip6_tables.h>
#define IPQ_QMAX_DEFAULT 1024
#define IPQ_PROC_FS_NAME "ip6_queue"
#define NET_IPQ_QMAX_NAME "ip6_queue_maxlen"
typedef int (*ipq_cmpfn)(struct nf_queue_entry *, unsigned long);
static unsigned char copy_mode __read_mostly = IPQ_COPY_NONE;
static unsigned int queue_maxlen __read_mostly = IPQ_QMAX_DEFAULT;
static DEFINE_SPINLOCK(queue_lock);
static int peer_pid __read_mostly;
static unsigned int copy_range __read_mostly;
static unsigned int queue_total;
static unsigned int queue_dropped = 0;
static unsigned int queue_user_dropped = 0;
static struct sock *ipqnl __read_mostly;
static LIST_HEAD(queue_list);
static DEFINE_MUTEX(ipqnl_mutex);
static inline void
__ipq_enqueue_entry(struct nf_queue_entry *entry)
{
list_add_tail(&entry->list, &queue_list);
queue_total++;
}
static inline int
__ipq_set_mode(unsigned char mode, unsigned int range)
{
int status = 0;
switch(mode) {
case IPQ_COPY_NONE:
case IPQ_COPY_META:
copy_mode = mode;
copy_range = 0;
break;
case IPQ_COPY_PACKET:
if (range > 0xFFFF)
range = 0xFFFF;
copy_range = range;
copy_mode = mode;
break;
default:
status = -EINVAL;
}
return status;
}
static void __ipq_flush(ipq_cmpfn cmpfn, unsigned long data);
static inline void
__ipq_reset(void)
{
peer_pid = 0;
net_disable_timestamp();
__ipq_set_mode(IPQ_COPY_NONE, 0);
__ipq_flush(NULL, 0);
}
static struct nf_queue_entry *
ipq_find_dequeue_entry(unsigned long id)
{
struct nf_queue_entry *entry = NULL, *i;
spin_lock_bh(&queue_lock);
list_for_each_entry(i, &queue_list, list) {
if ((unsigned long)i == id) {
entry = i;
break;
}
}
if (entry) {
list_del(&entry->list);
queue_total--;
}
spin_unlock_bh(&queue_lock);
return entry;
}
static void
__ipq_flush(ipq_cmpfn cmpfn, unsigned long data)
{
struct nf_queue_entry *entry, *next;
list_for_each_entry_safe(entry, next, &queue_list, list) {
if (!cmpfn || cmpfn(entry, data)) {
list_del(&entry->list);
queue_total--;
nf_reinject(entry, NF_DROP);
}
}
}
static void
ipq_flush(ipq_cmpfn cmpfn, unsigned long data)
{
spin_lock_bh(&queue_lock);
__ipq_flush(cmpfn, data);
spin_unlock_bh(&queue_lock);
}
static struct sk_buff *
ipq_build_packet_message(struct nf_queue_entry *entry, int *errp)
{
sk_buff_data_t old_tail;
size_t size = 0;
size_t data_len = 0;
struct sk_buff *skb;
struct ipq_packet_msg *pmsg;
struct nlmsghdr *nlh;
struct timeval tv;
switch (ACCESS_ONCE(copy_mode)) {
case IPQ_COPY_META:
case IPQ_COPY_NONE:
size = NLMSG_SPACE(sizeof(*pmsg));
break;
case IPQ_COPY_PACKET:
if (entry->skb->ip_summed == CHECKSUM_PARTIAL &&
(*errp = skb_checksum_help(entry->skb)))
return NULL;
data_len = ACCESS_ONCE(copy_range);
if (data_len == 0 || data_len > entry->skb->len)
data_len = entry->skb->len;
size = NLMSG_SPACE(sizeof(*pmsg) + data_len);
break;
default:
*errp = -EINVAL;
return NULL;
}
skb = alloc_skb(size, GFP_ATOMIC);
if (!skb)
goto nlmsg_failure;
old_tail = skb->tail;
nlh = NLMSG_PUT(skb, 0, 0, IPQM_PACKET, size - sizeof(*nlh));
pmsg = NLMSG_DATA(nlh);
memset(pmsg, 0, sizeof(*pmsg));
pmsg->packet_id = (unsigned long )entry;
pmsg->data_len = data_len;
tv = ktime_to_timeval(entry->skb->tstamp);
pmsg->timestamp_sec = tv.tv_sec;
pmsg->timestamp_usec = tv.tv_usec;
pmsg->mark = entry->skb->mark;
pmsg->hook = entry->hook;
pmsg->hw_protocol = entry->skb->protocol;
if (entry->indev)
strcpy(pmsg->indev_name, entry->indev->name);
else
pmsg->indev_name[0] = '\0';
if (entry->outdev)
strcpy(pmsg->outdev_name, entry->outdev->name);
else
pmsg->outdev_name[0] = '\0';
if (entry->indev && entry->skb->dev &&
entry->skb->mac_header != entry->skb->network_header) {
pmsg->hw_type = entry->skb->dev->type;
pmsg->hw_addrlen = dev_parse_header(entry->skb, pmsg->hw_addr);
}
if (data_len)
if (skb_copy_bits(entry->skb, 0, pmsg->payload, data_len))
BUG();
nlh->nlmsg_len = skb->tail - old_tail;
return skb;
nlmsg_failure:
kfree_skb(skb);
*errp = -EINVAL;
printk(KERN_ERR "ip6_queue: error creating packet message\n");
return NULL;
}
static int
ipq_enqueue_packet(struct nf_queue_entry *entry, unsigned int queuenum)
{
int status = -EINVAL;
struct sk_buff *nskb;
if (copy_mode == IPQ_COPY_NONE)
return -EAGAIN;
nskb = ipq_build_packet_message(entry, &status);
if (nskb == NULL)
return status;
spin_lock_bh(&queue_lock);
if (!peer_pid)
goto err_out_free_nskb;
if (queue_total >= queue_maxlen) {
queue_dropped++;
status = -ENOSPC;
if (net_ratelimit())
printk (KERN_WARNING "ip6_queue: fill at %d entries, "
"dropping packet(s). Dropped: %d\n", queue_total,
queue_dropped);
goto err_out_free_nskb;
}
/* netlink_unicast will either free the nskb or attach it to a socket */
status = netlink_unicast(ipqnl, nskb, peer_pid, MSG_DONTWAIT);
if (status < 0) {
queue_user_dropped++;
goto err_out_unlock;
}
__ipq_enqueue_entry(entry);
spin_unlock_bh(&queue_lock);
return status;
err_out_free_nskb:
kfree_skb(nskb);
err_out_unlock:
spin_unlock_bh(&queue_lock);
return status;
}
static int
ipq_mangle_ipv6(ipq_verdict_msg_t *v, struct nf_queue_entry *e)
{
int diff;
struct ipv6hdr *user_iph = (struct ipv6hdr *)v->payload;
struct sk_buff *nskb;
if (v->data_len < sizeof(*user_iph))
return 0;
diff = v->data_len - e->skb->len;
if (diff < 0) {
if (pskb_trim(e->skb, v->data_len))
return -ENOMEM;
} else if (diff > 0) {
if (v->data_len > 0xFFFF)
return -EINVAL;
if (diff > skb_tailroom(e->skb)) {
nskb = skb_copy_expand(e->skb, skb_headroom(e->skb),
diff, GFP_ATOMIC);
if (!nskb) {
printk(KERN_WARNING "ip6_queue: OOM "
"in mangle, dropping packet\n");
return -ENOMEM;
}
kfree_skb(e->skb);
e->skb = nskb;
}
skb_put(e->skb, diff);
}
if (!skb_make_writable(e->skb, v->data_len))
return -ENOMEM;
skb_copy_to_linear_data(e->skb, v->payload, v->data_len);
e->skb->ip_summed = CHECKSUM_NONE;
return 0;
}
static int
ipq_set_verdict(struct ipq_verdict_msg *vmsg, unsigned int len)
{
struct nf_queue_entry *entry;
if (vmsg->value > NF_MAX_VERDICT || vmsg->value == NF_STOLEN)
return -EINVAL;
entry = ipq_find_dequeue_entry(vmsg->id);
if (entry == NULL)
return -ENOENT;
else {
int verdict = vmsg->value;
if (vmsg->data_len && vmsg->data_len == len)
if (ipq_mangle_ipv6(vmsg, entry) < 0)
verdict = NF_DROP;
nf_reinject(entry, verdict);
return 0;
}
}
static int
ipq_set_mode(unsigned char mode, unsigned int range)
{
int status;
spin_lock_bh(&queue_lock);
status = __ipq_set_mode(mode, range);
spin_unlock_bh(&queue_lock);
return status;
}
static int
ipq_receive_peer(struct ipq_peer_msg *pmsg,
unsigned char type, unsigned int len)
{
int status = 0;
if (len < sizeof(*pmsg))
return -EINVAL;
switch (type) {
case IPQM_MODE:
status = ipq_set_mode(pmsg->msg.mode.value,
pmsg->msg.mode.range);
break;
case IPQM_VERDICT:
status = ipq_set_verdict(&pmsg->msg.verdict,
len - sizeof(*pmsg));
break;
default:
status = -EINVAL;
}
return status;
}
static int
dev_cmp(struct nf_queue_entry *entry, unsigned long ifindex)
{
if (entry->indev)
if (entry->indev->ifindex == ifindex)
return 1;
if (entry->outdev)
if (entry->outdev->ifindex == ifindex)
return 1;
#ifdef CONFIG_BRIDGE_NETFILTER
if (entry->skb->nf_bridge) {
if (entry->skb->nf_bridge->physindev &&
entry->skb->nf_bridge->physindev->ifindex == ifindex)
return 1;
if (entry->skb->nf_bridge->physoutdev &&
entry->skb->nf_bridge->physoutdev->ifindex == ifindex)
return 1;
}
#endif
return 0;
}
static void
ipq_dev_drop(int ifindex)
{
ipq_flush(dev_cmp, ifindex);
}
#define RCV_SKB_FAIL(err) do { netlink_ack(skb, nlh, (err)); return; } while (0)
static inline void
__ipq_rcv_skb(struct sk_buff *skb)
{
int status, type, pid, flags;
unsigned int nlmsglen, skblen;
struct nlmsghdr *nlh;
bool enable_timestamp = false;
skblen = skb->len;
if (skblen < sizeof(*nlh))
return;
nlh = nlmsg_hdr(skb);
nlmsglen = nlh->nlmsg_len;
if (nlmsglen < sizeof(*nlh) || skblen < nlmsglen)
return;
pid = nlh->nlmsg_pid;
flags = nlh->nlmsg_flags;
if(pid <= 0 || !(flags & NLM_F_REQUEST) || flags & NLM_F_MULTI)
RCV_SKB_FAIL(-EINVAL);
if (flags & MSG_TRUNC)
RCV_SKB_FAIL(-ECOMM);
type = nlh->nlmsg_type;
if (type < NLMSG_NOOP || type >= IPQM_MAX)
RCV_SKB_FAIL(-EINVAL);
if (type <= IPQM_BASE)
return;
if (!capable(CAP_NET_ADMIN))
RCV_SKB_FAIL(-EPERM);
spin_lock_bh(&queue_lock);
if (peer_pid) {
if (peer_pid != pid) {
spin_unlock_bh(&queue_lock);
RCV_SKB_FAIL(-EBUSY);
}
} else {
enable_timestamp = true;
peer_pid = pid;
}
spin_unlock_bh(&queue_lock);
if (enable_timestamp)
net_enable_timestamp();
status = ipq_receive_peer(NLMSG_DATA(nlh), type,
nlmsglen - NLMSG_LENGTH(0));
if (status < 0)
RCV_SKB_FAIL(status);
if (flags & NLM_F_ACK)
netlink_ack(skb, nlh, 0);
}
static void
ipq_rcv_skb(struct sk_buff *skb)
{
mutex_lock(&ipqnl_mutex);
__ipq_rcv_skb(skb);
mutex_unlock(&ipqnl_mutex);
}
static int
ipq_rcv_dev_event(struct notifier_block *this,
unsigned long event, void *ptr)
{
struct net_device *dev = ptr;
if (!net_eq(dev_net(dev), &init_net))
return NOTIFY_DONE;
/* Drop any packets associated with the downed device */
if (event == NETDEV_DOWN)
ipq_dev_drop(dev->ifindex);
return NOTIFY_DONE;
}
static struct notifier_block ipq_dev_notifier = {
.notifier_call = ipq_rcv_dev_event,
};
static int
ipq_rcv_nl_event(struct notifier_block *this,
unsigned long event, void *ptr)
{
struct netlink_notify *n = ptr;
if (event == NETLINK_URELEASE && n->protocol == NETLINK_IP6_FW) {
spin_lock_bh(&queue_lock);
if ((net_eq(n->net, &init_net)) && (n->pid == peer_pid))
__ipq_reset();
spin_unlock_bh(&queue_lock);
}
return NOTIFY_DONE;
}
static struct notifier_block ipq_nl_notifier = {
.notifier_call = ipq_rcv_nl_event,
};
#ifdef CONFIG_SYSCTL
static struct ctl_table_header *ipq_sysctl_header;
static ctl_table ipq_table[] = {
{
.procname = NET_IPQ_QMAX_NAME,
.data = &queue_maxlen,
.maxlen = sizeof(queue_maxlen),
.mode = 0644,
.proc_handler = proc_dointvec
},
{ }
};
#endif
#ifdef CONFIG_PROC_FS
static int ip6_queue_show(struct seq_file *m, void *v)
{
spin_lock_bh(&queue_lock);
seq_printf(m,
"Peer PID : %d\n"
"Copy mode : %hu\n"
"Copy range : %u\n"
"Queue length : %u\n"
"Queue max. length : %u\n"
"Queue dropped : %u\n"
"Netfilter dropped : %u\n",
peer_pid,
copy_mode,
copy_range,
queue_total,
queue_maxlen,
queue_dropped,
queue_user_dropped);
spin_unlock_bh(&queue_lock);
return 0;
}
static int ip6_queue_open(struct inode *inode, struct file *file)
{
return single_open(file, ip6_queue_show, NULL);
}
static const struct file_operations ip6_queue_proc_fops = {
.open = ip6_queue_open,
.read = seq_read,
.llseek = seq_lseek,
.release = single_release,
.owner = THIS_MODULE,
};
#endif
static const struct nf_queue_handler nfqh = {
.name = "ip6_queue",
.outfn = &ipq_enqueue_packet,
};
static int __init ip6_queue_init(void)
{
int status = -ENOMEM;
struct proc_dir_entry *proc __maybe_unused;
netlink_register_notifier(&ipq_nl_notifier);
ipqnl = netlink_kernel_create(&init_net, NETLINK_IP6_FW, 0,
ipq_rcv_skb, NULL, THIS_MODULE);
if (ipqnl == NULL) {
printk(KERN_ERR "ip6_queue: failed to create netlink socket\n");
goto cleanup_netlink_notifier;
}
#ifdef CONFIG_PROC_FS
proc = proc_create(IPQ_PROC_FS_NAME, 0, init_net.proc_net,
&ip6_queue_proc_fops);
if (!proc) {
printk(KERN_ERR "ip6_queue: failed to create proc entry\n");
goto cleanup_ipqnl;
}
#endif
register_netdevice_notifier(&ipq_dev_notifier);
#ifdef CONFIG_SYSCTL
ipq_sysctl_header = register_net_sysctl(&init_net, "net/ipv6", ipq_table);
#endif
status = nf_register_queue_handler(NFPROTO_IPV6, &nfqh);
if (status < 0) {
printk(KERN_ERR "ip6_queue: failed to register queue handler\n");
goto cleanup_sysctl;
}
return status;
cleanup_sysctl:
#ifdef CONFIG_SYSCTL
unregister_net_sysctl_table(ipq_sysctl_header);
#endif
unregister_netdevice_notifier(&ipq_dev_notifier);
proc_net_remove(&init_net, IPQ_PROC_FS_NAME);
cleanup_ipqnl: __maybe_unused
netlink_kernel_release(ipqnl);
mutex_lock(&ipqnl_mutex);
mutex_unlock(&ipqnl_mutex);
cleanup_netlink_notifier:
netlink_unregister_notifier(&ipq_nl_notifier);
return status;
}
static void __exit ip6_queue_fini(void)
{
nf_unregister_queue_handlers(&nfqh);
ipq_flush(NULL, 0);
#ifdef CONFIG_SYSCTL
unregister_net_sysctl_table(ipq_sysctl_header);
#endif
unregister_netdevice_notifier(&ipq_dev_notifier);
proc_net_remove(&init_net, IPQ_PROC_FS_NAME);
netlink_kernel_release(ipqnl);
mutex_lock(&ipqnl_mutex);
mutex_unlock(&ipqnl_mutex);
netlink_unregister_notifier(&ipq_nl_notifier);
}
MODULE_DESCRIPTION("IPv6 packet queue handler");
MODULE_LICENSE("GPL");
MODULE_ALIAS_NET_PF_PROTO(PF_NETLINK, NETLINK_IP6_FW);
module_init(ip6_queue_init);
module_exit(ip6_queue_fini);
...@@ -14,7 +14,6 @@ ...@@ -14,7 +14,6 @@
#include <linux/netlink.h> #include <linux/netlink.h>
#include <linux/rtnetlink.h> #include <linux/rtnetlink.h>
#include <linux/if.h> #include <linux/if.h>
#include <linux/netfilter_ipv4/ip_queue.h>
#include <linux/inet_diag.h> #include <linux/inet_diag.h>
#include <linux/xfrm.h> #include <linux/xfrm.h>
#include <linux/audit.h> #include <linux/audit.h>
...@@ -70,12 +69,6 @@ static struct nlmsg_perm nlmsg_route_perms[] = ...@@ -70,12 +69,6 @@ static struct nlmsg_perm nlmsg_route_perms[] =
{ RTM_SETDCB, NETLINK_ROUTE_SOCKET__NLMSG_WRITE }, { RTM_SETDCB, NETLINK_ROUTE_SOCKET__NLMSG_WRITE },
}; };
static struct nlmsg_perm nlmsg_firewall_perms[] =
{
{ IPQM_MODE, NETLINK_FIREWALL_SOCKET__NLMSG_WRITE },
{ IPQM_VERDICT, NETLINK_FIREWALL_SOCKET__NLMSG_WRITE },
};
static struct nlmsg_perm nlmsg_tcpdiag_perms[] = static struct nlmsg_perm nlmsg_tcpdiag_perms[] =
{ {
{ TCPDIAG_GETSOCK, NETLINK_TCPDIAG_SOCKET__NLMSG_READ }, { TCPDIAG_GETSOCK, NETLINK_TCPDIAG_SOCKET__NLMSG_READ },
...@@ -145,12 +138,6 @@ int selinux_nlmsg_lookup(u16 sclass, u16 nlmsg_type, u32 *perm) ...@@ -145,12 +138,6 @@ int selinux_nlmsg_lookup(u16 sclass, u16 nlmsg_type, u32 *perm)
sizeof(nlmsg_route_perms)); sizeof(nlmsg_route_perms));
break; break;
case SECCLASS_NETLINK_FIREWALL_SOCKET:
case SECCLASS_NETLINK_IP6FW_SOCKET:
err = nlmsg_perm(nlmsg_type, perm, nlmsg_firewall_perms,
sizeof(nlmsg_firewall_perms));
break;
case SECCLASS_NETLINK_TCPDIAG_SOCKET: case SECCLASS_NETLINK_TCPDIAG_SOCKET:
err = nlmsg_perm(nlmsg_type, perm, nlmsg_tcpdiag_perms, err = nlmsg_perm(nlmsg_type, perm, nlmsg_tcpdiag_perms,
sizeof(nlmsg_tcpdiag_perms)); sizeof(nlmsg_tcpdiag_perms));
......
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment