nfnetlink_log.c

linux 内核源代码

/*
 * This is a module which is used for logging packets to userspace via
 * nfetlink.
 *
 * (C) 2005 by Harald Welte <[e-mail]>
 *
 * Based on the old ipv4-only ipt_ULOG.c:
 * (C) 2000-2004 by Harald Welte <[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.
 */
#include <linux/module.h>
#include <linux/skbuff.h>
#include <linux/init.h>
#include <linux/ip.h>
#include <linux/ipv6.h>
#include <linux/netdevice.h>
#include <linux/netfilter.h>
#include <linux/netlink.h>
#include <linux/netfilter/nfnetlink.h>
#include <linux/netfilter/nfnetlink_log.h>
#include <linux/spinlock.h>
#include <linux/sysctl.h>
#include <linux/proc_fs.h>
#include <linux/security.h>
#include <linux/list.h>
#include <linux/jhash.h>
#include <linux/random.h>
#include <net/sock.h>

#include <asm/atomic.h>

#ifdef CONFIG_BRIDGE_NETFILTER
#include "../bridge/br_private.h"
#endif

#define NFULNL_NLBUFSIZ_DEFAULT	NLMSG_GOODSIZE
#define NFULNL_TIMEOUT_DEFAULT 	HZ	/* every second */
#define NFULNL_QTHRESH_DEFAULT 	100	/* 100 packets */
#define NFULNL_COPY_RANGE_MAX	0xFFFF	/* max packet size is limited by 16-bit struct nfattr nfa_len field */

#define PRINTR(x, args...)	do { if (net_ratelimit()) \
				     printk(x, ## args); } while (0);

#if 0
#define UDEBUG(x, args ...)	printk(KERN_DEBUG "%s(%d):%s():	" x, 	   \
					__FILE__, __LINE__, __FUNCTION__,  \
					## args)
#else
#define UDEBUG(x, ...)
#endif

struct nfulnl_instance {
	struct hlist_node hlist;	/* global list of instances */
	spinlock_t lock;
	atomic_t use;			/* use count */

	unsigned int qlen;		/* number of nlmsgs in skb */
	struct sk_buff *skb;		/* pre-allocatd skb */
	struct timer_list timer;
	int peer_pid;			/* PID of the peer process */

	/* configurable parameters */
	unsigned int flushtimeout;	/* timeout until queue flush */
	unsigned int nlbufsiz;		/* netlink buffer allocation size */
	unsigned int qthreshold;	/* threshold of the queue */
	u_int32_t copy_range;
	u_int32_t seq;			/* instance-local sequential counter */
	u_int16_t group_num;		/* number of this queue */
	u_int16_t flags;
	u_int8_t copy_mode;
};

static DEFINE_RWLOCK(instances_lock);
static atomic_t global_seq;

#define INSTANCE_BUCKETS	16
static struct hlist_head instance_table[INSTANCE_BUCKETS];
static unsigned int hash_init;

static inline u_int8_t instance_hashfn(u_int16_t group_num)
{
	return ((group_num & 0xff) % INSTANCE_BUCKETS);
}

static struct nfulnl_instance *
__instance_lookup(u_int16_t group_num)
{
	struct hlist_head *head;
	struct hlist_node *pos;
	struct nfulnl_instance *inst;

	UDEBUG("entering (group_num=%u)\n", group_num);

	head = &instance_table[instance_hashfn(group_num)];
	hlist_for_each_entry(inst, pos, head, hlist) {
		if (inst->group_num == group_num)
			return inst;
	}
	return NULL;
}

static inline void
instance_get(struct nfulnl_instance *inst)
{
	atomic_inc(&inst->use);
}

static struct nfulnl_instance *
instance_lookup_get(u_int16_t group_num)
{
	struct nfulnl_instance *inst;

	read_lock_bh(&instances_lock);
	inst = __instance_lookup(group_num);
	if (inst)
		instance_get(inst);
	read_unlock_bh(&instances_lock);

	return inst;
}

static void
instance_put(struct nfulnl_instance *inst)
{
	if (inst && atomic_dec_and_test(&inst->use)) {
		UDEBUG("kfree(inst=%p)\n", inst);
		kfree(inst);
		module_put(THIS_MODULE);
	}
}

static void nfulnl_timer(unsigned long data);

static struct nfulnl_instance *
instance_create(u_int16_t group_num, int pid)
{
	struct nfulnl_instance *inst;

	UDEBUG("entering (group_num=%u, pid=%d)\n", group_num,
		pid);

	write_lock_bh(&instances_lock);
	if (__instance_lookup(group_num)) {
		inst = NULL;
		UDEBUG("aborting, instance already exists\n");
		goto out_unlock;
	}

	inst = kzalloc(sizeof(*inst), GFP_ATOMIC);
	if (!inst)
		goto out_unlock;

	if (!try_module_get(THIS_MODULE)) {
		kfree(inst);
		goto out_unlock;
	}

	INIT_HLIST_NODE(&inst->hlist);
	spin_lock_init(&inst->lock);
	/* needs to be two, since we _put() after creation */
	atomic_set(&inst->use, 2);

	setup_timer(&inst->timer, nfulnl_timer, (unsigned long)inst);

	inst->peer_pid = pid;
	inst->group_num = group_num;

	inst->qthreshold 	= NFULNL_QTHRESH_DEFAULT;
	inst->flushtimeout 	= NFULNL_TIMEOUT_DEFAULT;
	inst->nlbufsiz 		= NFULNL_NLBUFSIZ_DEFAULT;
	inst->copy_mode 	= NFULNL_COPY_PACKET;
	inst->copy_range 	= NFULNL_COPY_RANGE_MAX;

	hlist_add_head(&inst->hlist,
		       &instance_table[instance_hashfn(group_num)]);

	UDEBUG("newly added node: %p, next=%p\n", &inst->hlist,
		inst->hlist.next);

	write_unlock_bh(&instances_lock);

	return inst;

out_unlock:
	write_unlock_bh(&instances_lock);
	return NULL;
}

static void __nfulnl_flush(struct nfulnl_instance *inst);

static void
__instance_destroy(struct nfulnl_instance *inst)
{
	/* first pull it out of the global list */
	UDEBUG("removing instance %p (queuenum=%u) from hash\n",
		inst, inst->group_num);

	hlist_del(&inst->hlist);

	/* then flush all pending packets from skb */

	spin_lock_bh(&inst->lock);
	if (inst->skb)
		__nfulnl_flush(inst);
	spin_unlock_bh(&inst->lock);

	/* and finally put the refcount */
	instance_put(inst);
}

static inline void
instance_destroy(struct nfulnl_instance *inst)
{
	write_lock_bh(&instances_lock);
	__instance_destroy(inst);
	write_unlock_bh(&instances_lock);
}

static int
nfulnl_set_mode(struct nfulnl_instance *inst, u_int8_t mode,
		  unsigned int range)
{
	int status = 0;

	spin_lock_bh(&inst->lock);

	switch (mode) {
	case NFULNL_COPY_NONE:
	case NFULNL_COPY_META:
		inst->copy_mode = mode;
		inst->copy_range = 0;
		break;

	case NFULNL_COPY_PACKET:
		inst->copy_mode = mode;
		inst->copy_range = min_t(unsigned int,
					 range, NFULNL_COPY_RANGE_MAX);
		break;

	default:
		status = -EINVAL;
		break;
	}

	spin_unlock_bh(&inst->lock);

	return status;
}

static int
nfulnl_set_nlbufsiz(struct nfulnl_instance *inst, u_int32_t nlbufsiz)
{
	int status;

	spin_lock_bh(&inst->lock);
	if (nlbufsiz < NFULNL_NLBUFSIZ_DEFAULT)
		status = -ERANGE;
	else if (nlbufsiz > 131072)
		status = -ERANGE;
	else {
		inst->nlbufsiz = nlbufsiz;
		status = 0;
	}
	spin_unlock_bh(&inst->lock);

	return status;
}

static int
nfulnl_set_timeout(struct nfulnl_instance *inst, u_int32_t timeout)
{
	spin_lock_bh(&inst->lock);
	inst->flushtimeout = timeout;
	spin_unlock_bh(&inst->lock);

	return 0;
}

static int
nfulnl_set_qthresh(struct nfulnl_instance *inst, u_int32_t qthresh)
{
	spin_lock_bh(&inst->lock);
	inst->qthreshold = qthresh;
	spin_unlock_bh(&inst->lock);

	return 0;
}

static int
nfulnl_set_flags(struct nfulnl_instance *inst, u_int16_t flags)
{
	spin_lock_bh(&inst->lock);
	inst->flags = flags;
	spin_unlock_bh(&inst->lock);

	return 0;
}

static struct sk_buff *
nfulnl_alloc_skb(unsigned int inst_size, unsigned int pkt_size)
{
	struct sk_buff *skb;
	unsigned int n;

	UDEBUG("entered (%u, %u)\n", inst_size, pkt_size);

	/* alloc skb which should be big enough for a whole multipart
	 * message.  WARNING: has to be <= 128k due to slab restrictions */

	n = max(inst_size, pkt_size);
	skb = alloc_skb(n, GFP_ATOMIC);
	if (!skb) {
		PRINTR("nfnetlink_log: can't alloc whole buffer (%u bytes)\n",
			inst_size);

		if (n > pkt_size) {
			/* try to allocate only as much as we need for current
			 * packet */

			skb = alloc_skb(pkt_size, GFP_ATOMIC);
			if (!skb)
				PRINTR("nfnetlink_log: can't even alloc %u "
				       "bytes\n", pkt_size);
		}
	}

	return skb;
}

static int
__nfulnl_send(struct nfulnl_instance *inst)
{
	int status = -1;

	if (inst->qlen > 1)
		NLMSG_PUT(inst->skb, 0, 0,
			  NLMSG_DONE,
			  sizeof(struct nfgenmsg));

	status = nfnetlink_unicast(inst->skb, inst->peer_pid, MSG_DONTWAIT);
	if (status < 0) {
		UDEBUG("netlink_unicast() failed\n");
		/* FIXME: statistics */
	}

	inst->qlen = 0;
	inst->skb = NULL;

nlmsg_failure:
	return status;
}

static void
__nfulnl_flush(struct nfulnl_instance *inst)
{
	/* timer holds a reference */
	if (del_timer(&inst->timer))
		instance_put(inst);
	if (inst->skb)
		__nfulnl_send(inst);
}

static void
nfulnl_timer(unsigned long data)
{
	struct nfulnl_instance *inst = (struct nfulnl_instance *)data;

	UDEBUG("timer function called, flushing buffer\n");

	spin_lock_bh(&inst->lock);
	if (inst->skb)
		__nfulnl_send(inst);
	spin_unlock_bh(&inst->lock);
	instance_put(inst);
}

/* This is an inline function, we don't really care about a long
 * list of arguments */
static inline int
__build_packet_message(struct nfulnl_instance *inst,
			const struct sk_buff *skb,
			unsigned int data_len,
			unsigned int pf,
			unsigned int hooknum,
			const struct net_device *indev,
			const struct net_device *outdev,
			const struct nf_loginfo *li,
			const char *prefix, unsigned int plen)
{
	struct nfulnl_msg_packet_hdr pmsg;
	struct nlmsghdr *nlh;
	struct nfgenmsg *nfmsg;
	__be32 tmp_uint;
	sk_buff_data_t old_tail = inst->skb->tail;

	UDEBUG("entered\n");

	nlh = NLMSG_PUT(inst->skb, 0, 0,
			NFNL_SUBSYS_ULOG << 8 | NFULNL_MSG_PACKET,
			sizeof(struct nfgenmsg));
	nfmsg = NLMSG_DATA(nlh);
	nfmsg->nfgen_family = pf;
	nfmsg->version = NFNETLINK_V0;
	nfmsg->res_id = htons(inst->group_num);

	pmsg.hw_protocol	= skb->protocol;
	pmsg.hook		= hooknum;

	NLA_PUT(inst->skb, NFULA_PACKET_HDR, sizeof(pmsg), &pmsg);

	if (prefix)
		NLA_PUT(inst->skb, NFULA_PREFIX, plen, prefix);

	if (indev) {
		tmp_uint = htonl(indev->ifindex);
#ifndef CONFIG_BRIDGE_NETFILTER
		NLA_PUT(inst->skb, NFULA_IFINDEX_INDEV, sizeof(tmp_uint),
			&tmp_uint);
#else
		if (pf == PF_BRIDGE) {
			/* Case 1: outdev is physical input device, we need to
			 * look for bridge group (when called from
			 * netfilter_bridge) */
			NLA_PUT(inst->skb, NFULA_IFINDEX_PHYSINDEV,
				sizeof(tmp_uint), &tmp_uint);
			/* this is the bridge group "brX" */
			tmp_uint = htonl(indev->br_port->br->dev->ifindex);
			NLA_PUT(inst->skb, NFULA_IFINDEX_INDEV,
				sizeof(tmp_uint), &tmp_uint);
		} else {
			/* Case 2: indev is bridge group, we need to look for
			 * physical device (when called from ipv4) */
			NLA_PUT(inst->skb, NFULA_IFINDEX_INDEV,
				sizeof(tmp_uint), &tmp_uint);
			if (skb->nf_bridge && skb->nf_bridge->physindev) {
				tmp_uint =
				    htonl(skb->nf_bridge->physindev->ifindex);
				NLA_PUT(inst->skb, NFULA_IFINDEX_PHYSINDEV,
					sizeof(tmp_uint), &tmp_uint);
			}
		}
#endif
	}

	if (outdev) {
		tmp_uint = htonl(outdev->ifindex);
#ifndef CONFIG_BRIDGE_NETFILTER
		NLA_PUT(inst->skb, NFULA_IFINDEX_OUTDEV, sizeof(tmp_uint),
			&tmp_uint);
#else
		if (pf == PF_BRIDGE) {
			/* Case 1: outdev is physical output device, we need to
			 * look for bridge group (when called from
			 * netfilter_bridge) */
			NLA_PUT(inst->skb, NFULA_IFINDEX_PHYSOUTDEV,
				sizeof(tmp_uint), &tmp_uint);
			/* this is the bridge group "brX" */
			tmp_uint = htonl(outdev->br_port->br->dev->ifindex);
			NLA_PUT(inst->skb, NFULA_IFINDEX_OUTDEV,
				sizeof(tmp_uint), &tmp_uint);
		} else {
			/* Case 2: indev is a bridge group, we need to look
			 * for physical device (when called from ipv4) */
			NLA_PUT(inst->skb, NFULA_IFINDEX_OUTDEV,
				sizeof(tmp_uint), &tmp_uint);
			if (skb->nf_bridge && skb->nf_bridge->physoutdev) {
				tmp_uint =
				    htonl(skb->nf_bridge->physoutdev->ifindex);
				NLA_PUT(inst->skb, NFULA_IFINDEX_PHYSOUTDEV,
					sizeof(tmp_uint), &tmp_uint);
			}
		}
#endif
	}

	if (skb->mark) {
		tmp_uint = htonl(skb->mark);
		NLA_PUT(inst->skb, NFULA_MARK, sizeof(tmp_uint), &tmp_uint);
	}

	if (indev && skb->dev) {
		struct nfulnl_msg_packet_hw phw;
		int len = dev_parse_header(skb, phw.hw_addr);
		if (len > 0) {
			phw.hw_addrlen = htons(len);
			NLA_PUT(inst->skb, NFULA_HWADDR, sizeof(phw), &phw);
		}
	}

	if (skb->tstamp.tv64) {
		struct nfulnl_msg_packet_timestamp ts;
		struct timeval tv = ktime_to_timeval(skb->tstamp);
		ts.sec = cpu_to_be64(tv.tv_sec);
		ts.usec = cpu_to_be64(tv.tv_usec);

		NLA_PUT(inst->skb, NFULA_TIMESTAMP, sizeof(ts), &ts);
	}

	/* UID */
	if (skb->sk) {
		read_lock_bh(&skb->sk->sk_callback_lock);
		if (skb->sk->sk_socket && skb->sk->sk_socket->file) {
			__be32 uid = htonl(skb->sk->sk_socket->file->f_uid);
			/* need to unlock here since NLA_PUT may goto */
			read_unlock_bh(&skb->sk->sk_callback_lock);
			NLA_PUT(inst->skb, NFULA_UID, sizeof(uid), &uid);
		} else
			read_unlock_bh(&skb->sk->sk_callback_lock);
	}