ip_queue.c

linux-2.6.15.6

/*
 * This is a module which is used for queueing IPv4 packets and
 * communicating with userspace via netlink.
 *
 * (C) 2000-2002 James Morris <[e-mail]>
 * (C) 2003-2005 Netfilter Core Team <[e-mail]>
 *
 * 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.
 *
 * 2000-03-27: Simplified code (thanks to Andi Kleen for clues).
 * 2000-05-20: Fixed notifier problems (following Miguel Freitas' report).
 * 2000-06-19: Fixed so nfmark is copied to metadata (reported by Sebastian 
 *             Zander).
 * 2000-08-01: Added Nick Williams' MAC support.
 * 2002-06-25: Code cleanup.
 * 2005-01-10: Added /proc counter for dropped packets; fixed so
 *             packets aren't delivered to user space if they're going 
 *             to be dropped. 
 * 2005-05-26: local_bh_{disable,enable} around nf_reinject (Harald Welte)
 *
 */
#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/security.h>
#include <net/sock.h>
#include <net/route.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"

struct ipq_queue_entry {
	struct list_head list;
	struct nf_info *info;
	struct sk_buff *skb;
};

typedef int (*ipq_cmpfn)(struct ipq_queue_entry *, unsigned long);

static unsigned char copy_mode = IPQ_COPY_NONE;
static unsigned int queue_maxlen = IPQ_QMAX_DEFAULT;
static DEFINE_RWLOCK(queue_lock);
static int peer_pid;
static unsigned int copy_range;
static unsigned int queue_total;
static unsigned int queue_dropped = 0;
static unsigned int queue_user_dropped = 0;
static struct sock *ipqnl;
static LIST_HEAD(queue_list);
static DECLARE_MUTEX(ipqnl_sem);

static void
ipq_issue_verdict(struct ipq_queue_entry *entry, int verdict)
{
	/* TCP input path (and probably other bits) assume to be called
	 * from softirq context, not from syscall, like ipq_issue_verdict is
	 * called.  TCP input path deadlocks with locks taken from timer
	 * softirq, e.g.  We therefore emulate this by local_bh_disable() */

	local_bh_disable();
	nf_reinject(entry->skb, entry->info, verdict);
	local_bh_enable();

	kfree(entry);
}

static inline void
__ipq_enqueue_entry(struct ipq_queue_entry *entry)
{
       list_add(&entry->list, &queue_list);
       queue_total++;
}

/*
 * Find and return a queued entry matched by cmpfn, or return the last
 * entry if cmpfn is NULL.
 */
static inline struct ipq_queue_entry *
__ipq_find_entry(ipq_cmpfn cmpfn, unsigned long data)
{
	struct list_head *p;

	list_for_each_prev(p, &queue_list) {
		struct ipq_queue_entry *entry = (struct ipq_queue_entry *)p;
		
		if (!cmpfn || cmpfn(entry, data))
			return entry;
	}
	return NULL;
}

static inline void
__ipq_dequeue_entry(struct ipq_queue_entry *entry)
{
	list_del(&entry->list);
	queue_total--;
}

static inline struct ipq_queue_entry *
__ipq_find_dequeue_entry(ipq_cmpfn cmpfn, unsigned long data)
{
	struct ipq_queue_entry *entry;

	entry = __ipq_find_entry(cmpfn, data);
	if (entry == NULL)
		return NULL;

	__ipq_dequeue_entry(entry);
	return entry;
}


static inline void
__ipq_flush(int verdict)
{
	struct ipq_queue_entry *entry;
	
	while ((entry = __ipq_find_dequeue_entry(NULL, 0)))
		ipq_issue_verdict(entry, verdict);
}

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:
		copy_mode = mode;
		copy_range = range;
		if (copy_range > 0xFFFF)
			copy_range = 0xFFFF;
		break;
		
	default:
		status = -EINVAL;

	}
	return status;
}

static inline void
__ipq_reset(void)
{
	peer_pid = 0;
	net_disable_timestamp();
	__ipq_set_mode(IPQ_COPY_NONE, 0);
	__ipq_flush(NF_DROP);
}

static struct ipq_queue_entry *
ipq_find_dequeue_entry(ipq_cmpfn cmpfn, unsigned long data)
{
	struct ipq_queue_entry *entry;
	
	write_lock_bh(&queue_lock);
	entry = __ipq_find_dequeue_entry(cmpfn, data);
	write_unlock_bh(&queue_lock);
	return entry;
}

static void
ipq_flush(int verdict)
{
	write_lock_bh(&queue_lock);
	__ipq_flush(verdict);
	write_unlock_bh(&queue_lock);
}

static struct sk_buff *
ipq_build_packet_message(struct ipq_queue_entry *entry, int *errp)
{
	unsigned char *old_tail;
	size_t size = 0;
	size_t data_len = 0;
	struct sk_buff *skb;
	struct ipq_packet_msg *pmsg;
	struct nlmsghdr *nlh;

	read_lock_bh(&queue_lock);
	
	switch (copy_mode) {
	case IPQ_COPY_META:
	case IPQ_COPY_NONE:
		size = NLMSG_SPACE(sizeof(*pmsg));
		data_len = 0;
		break;
	
	case IPQ_COPY_PACKET:
		if (entry->skb->ip_summed == CHECKSUM_HW &&
		    (*errp = skb_checksum_help(entry->skb,
		                               entry->info->outdev == NULL))) {
			read_unlock_bh(&queue_lock);
			return NULL;
		}
		if (copy_range == 0 || copy_range > entry->skb->len)
			data_len = entry->skb->len;
		else
			data_len = copy_range;
		
		size = NLMSG_SPACE(sizeof(*pmsg) + data_len);
		break;
	
	default:
		*errp = -EINVAL;
		read_unlock_bh(&queue_lock);
		return NULL;
	}

	read_unlock_bh(&queue_lock);

	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;
	pmsg->timestamp_sec   = entry->skb->tstamp.off_sec;
	pmsg->timestamp_usec  = entry->skb->tstamp.off_usec;
	pmsg->mark            = entry->skb->nfmark;
	pmsg->hook            = entry->info->hook;
	pmsg->hw_protocol     = entry->skb->protocol;
	
	if (entry->info->indev)
		strcpy(pmsg->indev_name, entry->info->indev->name);
	else
		pmsg->indev_name[0] = '\0';
	
	if (entry->info->outdev)
		strcpy(pmsg->outdev_name, entry->info->outdev->name);
	else
		pmsg->outdev_name[0] = '\0';
	
	if (entry->info->indev && entry->skb->dev) {
		pmsg->hw_type = entry->skb->dev->type;
		if (entry->skb->dev->hard_header_parse)
			pmsg->hw_addrlen =
				entry->skb->dev->hard_header_parse(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:
	if (skb)
		kfree_skb(skb);
	*errp = -EINVAL;
	printk(KERN_ERR "ip_queue: error creating packet message\n");
	return NULL;
}

static int
ipq_enqueue_packet(struct sk_buff *skb, struct nf_info *info,
		   unsigned int queuenum, void *data)
{
	int status = -EINVAL;
	struct sk_buff *nskb;
	struct ipq_queue_entry *entry;

	if (copy_mode == IPQ_COPY_NONE)
		return -EAGAIN;

	entry = kmalloc(sizeof(*entry), GFP_ATOMIC);
	if (entry == NULL) {
		printk(KERN_ERR "ip_queue: OOM in ipq_enqueue_packet()\n");
		return -ENOMEM;
	}

	entry->info = info;
	entry->skb = skb;

	nskb = ipq_build_packet_message(entry, &status);
	if (nskb == NULL)
		goto err_out_free;
		
	write_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);

	write_unlock_bh(&queue_lock);
	return status;

err_out_free_nskb:
	kfree_skb(nskb); 
	
err_out_unlock:
	write_unlock_bh(&queue_lock);

err_out_free:
	kfree(entry);
	return status;
}

static int
ipq_mangle_ipv4(ipq_verdict_msg_t *v, struct ipq_queue_entry *e)
{
	int diff;
	struct iphdr *user_iph = (struct iphdr *)v->payload;

	if (v->data_len < sizeof(*user_iph))
		return 0;
	diff = v->data_len - e->skb->len;
	if (diff < 0)
		skb_trim(e->skb, v->data_len);
	else if (diff > 0) {
		if (v->data_len > 0xFFFF)
			return -EINVAL;
		if (diff > skb_tailroom(e->skb)) {
			struct sk_buff *newskb;
			
			newskb = skb_copy_expand(e->skb,
			                         skb_headroom(e->skb),
			                         diff,
			                         GFP_ATOMIC);
			if (newskb == NULL) {
				printk(KERN_WARNING "ip_queue: OOM "
				      "in mangle, dropping packet\n");
				return -ENOMEM;