cregit-Linux how code gets into the kernel

Release 4.11 net/netfilter/nfnetlink_queue.c

Directory: net/netfilter
/*
 * This is a module which is used for queueing packets and communicating with
 * userspace via nfnetlink.
 *
 * (C) 2005 by Harald Welte <laforge@netfilter.org>
 * (C) 2007 by Patrick McHardy <kaber@trash.net>
 *
 * Based on the old ipv4-only ip_queue.c:
 * (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/spinlock.h>
#include <linux/slab.h>
#include <linux/notifier.h>
#include <linux/netdevice.h>
#include <linux/netfilter.h>
#include <linux/proc_fs.h>
#include <linux/netfilter_ipv4.h>
#include <linux/netfilter_ipv6.h>
#include <linux/netfilter_bridge.h>
#include <linux/netfilter/nfnetlink.h>
#include <linux/netfilter/nfnetlink_queue.h>
#include <linux/netfilter/nf_conntrack_common.h>
#include <linux/list.h>
#include <net/sock.h>
#include <net/tcp_states.h>
#include <net/netfilter/nf_queue.h>
#include <net/netns/generic.h>

#include <linux/atomic.h>

#if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
#include "../bridge/br_private.h"
#endif


#define NFQNL_QMAX_DEFAULT 1024

/* We're using struct nlattr which has 16bit nla_len. Note that nla_len
 * includes the header length. Thus, the maximum packet length that we
 * support is 65531 bytes. We send truncated packets if the specified length
 * is larger than that.  Userspace can check for presence of NFQA_CAP_LEN
 * attribute to detect truncation.
 */

#define NFQNL_MAX_COPY_RANGE (0xffff - NLA_HDRLEN)


struct nfqnl_instance {
	
struct hlist_node hlist;		/* global list of queues */
	
struct rcu_head rcu;

	
u32 peer_portid;
	
unsigned int queue_maxlen;
	
unsigned int copy_range;
	
unsigned int queue_dropped;
	
unsigned int queue_user_dropped;


	
u_int16_t queue_num;			/* number of this queue */
	
u_int8_t copy_mode;
	
u_int32_t flags;			/* Set using NFQA_CFG_FLAGS */
/*
 * Following fields are dirtied for each queued packet,
 * keep them in same cache line if possible.
 */
	
spinlock_t	lock	____cacheline_aligned_in_smp;
	
unsigned int	queue_total;
	
unsigned int	id_sequence;		/* 'sequence' of pkt ids */
	
struct list_head queue_list;		/* packets in queue */
};


typedef int (*nfqnl_cmpfn)(struct nf_queue_entry *, unsigned long);


static unsigned int nfnl_queue_net_id __read_mostly;


#define INSTANCE_BUCKETS	16

struct nfnl_queue_net {
	
spinlock_t instances_lock;
	
struct hlist_head instance_table[INSTANCE_BUCKETS];
};




static struct nfnl_queue_net *nfnl_queue_pernet(struct net *net)
{
	return net_generic(net, nfnl_queue_net_id);
}


Contributors
PersonTokensPropCommitsCommitProp
Gao Feng21100.00%1100.00%


Total21100.00%1100.00%






static inline u_int8_t instance_hashfn(u_int16_t queue_num)
{
	return ((queue_num >> 8) ^ queue_num) % INSTANCE_BUCKETS;
}


Contributors
PersonTokensPropCommitsCommitProp
Harald Welte2295.65%150.00%


Pablo Neira Ayuso14.35%150.00%


Total23100.00%2100.00%





static struct nfqnl_instance *

instance_lookup(struct nfnl_queue_net *q, u_int16_t queue_num)
{
	struct hlist_head *head;
	struct nfqnl_instance *inst;

	head = &q->instance_table[instance_hashfn(queue_num)];
	hlist_for_each_entry_rcu(inst, head, hlist) {
		if (inst->queue_num == queue_num)
			return inst;
	}
	return NULL;
}


Contributors
PersonTokensPropCommitsCommitProp
Harald Welte5485.71%133.33%


Gao Feng711.11%133.33%


Patrick McHardy23.17%133.33%


Total63100.00%3100.00%





static struct nfqnl_instance *

instance_create(struct nfnl_queue_net *q, u_int16_t queue_num, u32 portid)
{
	struct nfqnl_instance *inst;
	unsigned int h;
	int err;

	spin_lock(&q->instances_lock);
	if (instance_lookup(q, queue_num)) {
		err = -EEXIST;
		goto out_unlock;
	}

	inst = kzalloc(sizeof(*inst), GFP_ATOMIC);
	if (!inst) {
		err = -ENOMEM;
		goto out_unlock;
	}

	inst->queue_num = queue_num;
	inst->peer_portid = portid;
	inst->queue_maxlen = NFQNL_QMAX_DEFAULT;
	inst->copy_range = NFQNL_MAX_COPY_RANGE;
	inst->copy_mode = NFQNL_COPY_NONE;
	spin_lock_init(&inst->lock);
	INIT_LIST_HEAD(&inst->queue_list);

	if (!try_module_get(THIS_MODULE)) {
		err = -EAGAIN;
		goto out_free;
	}

	h = instance_hashfn(queue_num);
	hlist_add_head_rcu(&inst->hlist, &q->instance_table[h]);

	spin_unlock(&q->instances_lock);

	return inst;

out_free:
	kfree(inst);
out_unlock:
	spin_unlock(&q->instances_lock);
	return ERR_PTR(err);
}


Contributors
PersonTokensPropCommitsCommitProp
Harald Welte13565.22%330.00%


Patrick McHardy4923.67%220.00%


Gao Feng157.25%110.00%


Eric W. Biedermann31.45%110.00%


Hideaki Yoshifuji / 吉藤英明31.45%110.00%


Richard Weinberger10.48%110.00%


Florian Westphal10.48%110.00%


Total207100.00%10100.00%



static void nfqnl_flush(struct nfqnl_instance *queue, nfqnl_cmpfn cmpfn,
			unsigned long data);



static void

instance_destroy_rcu(struct rcu_head *head)
{
	struct nfqnl_instance *inst = container_of(head, struct nfqnl_instance,
						   rcu);

	nfqnl_flush(inst, NULL, 0);
	kfree(inst);
	module_put(THIS_MODULE);
}


Contributors
PersonTokensPropCommitsCommitProp
Harald Welte2760.00%133.33%


Patrick McHardy1840.00%266.67%


Total45100.00%3100.00%





static void

__instance_destroy(struct nfqnl_instance *inst)
{
	hlist_del_rcu(&inst->hlist);
	call_rcu(&inst->rcu, instance_destroy_rcu);
}


Contributors
PersonTokensPropCommitsCommitProp
Harald Welte1655.17%150.00%


Patrick McHardy1344.83%150.00%


Total29100.00%2100.00%





static void

instance_destroy(struct nfnl_queue_net *q, struct nfqnl_instance *inst)
{
	spin_lock(&q->instances_lock);
	__instance_destroy(inst);
	spin_unlock(&q->instances_lock);
}


Contributors
PersonTokensPropCommitsCommitProp
Harald Welte1540.54%133.33%


Patrick McHardy1335.14%133.33%


Gao Feng924.32%133.33%


Total37100.00%3100.00%





static inline void

__enqueue_entry(struct nfqnl_instance *queue, struct nf_queue_entry *entry)
{
       list_add_tail(&entry->list, &queue->queue_list);
       queue->queue_total++;
}


Contributors
PersonTokensPropCommitsCommitProp
Harald Welte3394.29%133.33%


Patrick McHardy25.71%266.67%


Total35100.00%3100.00%





static void

__dequeue_entry(struct nfqnl_instance *queue, struct nf_queue_entry *entry)
{
	list_del(&entry->list);
	queue->queue_total--;
}


Contributors
PersonTokensPropCommitsCommitProp
Florian Westphal2896.55%150.00%


Harald Welte13.45%150.00%


Total29100.00%2100.00%





static struct nf_queue_entry *

find_dequeue_entry(struct nfqnl_instance *queue, unsigned int id)
{
	struct nf_queue_entry *entry = NULL, *i;

	spin_lock_bh(&queue->lock);

	list_for_each_entry(i, &queue->queue_list, list) {
		if (i->id == id) {
			entry = i;
			break;
		}
	}

	if (entry)
		__dequeue_entry(queue, entry);

	spin_unlock_bh(&queue->lock);

	return entry;
}


Contributors
PersonTokensPropCommitsCommitProp
Harald Welte4048.78%125.00%


Patrick McHardy3846.34%250.00%


Florian Westphal44.88%125.00%


Total82100.00%4100.00%





static void

nfqnl_flush(struct nfqnl_instance *queue, nfqnl_cmpfn cmpfn, unsigned long data)
{
	struct nf_queue_entry *entry, *next;

	spin_lock_bh(&queue->lock);
	list_for_each_entry_safe(entry, next, &queue->queue_list, list) {
		if (!cmpfn || cmpfn(entry, data)) {
			list_del(&entry->list);
			queue->queue_total--;
			nf_reinject(entry, NF_DROP);
		}
	}
	spin_unlock_bh(&queue->lock);
}


Contributors
PersonTokensPropCommitsCommitProp
Patrick McHardy5562.50%375.00%


Harald Welte3337.50%125.00%


Total88100.00%4100.00%





static int

nfqnl_put_packet_info(struct sk_buff *nlskb, struct sk_buff *packet,
		      bool csum_verify)
{
	__u32 flags = 0;

	if (packet->ip_summed == CHECKSUM_PARTIAL)
		flags = NFQA_SKB_CSUMNOTREADY;
	else if (csum_verify)
		flags = NFQA_SKB_CSUM_NOTVERIFIED;

	if (skb_is_gso(packet))
		flags |= NFQA_SKB_GSO;

	return flags ? nla_put_be32(nlskb, NFQA_SKB_INFO, htonl(flags)) : 0;
}


Contributors
PersonTokensPropCommitsCommitProp
Florian Westphal7298.63%266.67%


Harald Welte11.37%133.33%


Total73100.00%3100.00%






static int nfqnl_put_sk_uidgid(struct sk_buff *skb, struct sock *sk)
{
	const struct cred *cred;

	if (!sk_fullsock(sk))
		return 0;

	read_lock_bh(&sk->sk_callback_lock);
	if (sk->sk_socket && sk->sk_socket->file) {
		cred = sk->sk_socket->file->f_cred;
		if (nla_put_be32(skb, NFQA_UID,
		    htonl(from_kuid_munged(&init_user_ns, cred->fsuid))))
			goto nla_put_failure;
		if (nla_put_be32(skb, NFQA_GID,
		    htonl(from_kgid_munged(&init_user_ns, cred->fsgid))))
			goto nla_put_failure;
	}
	read_unlock_bh(&sk->sk_callback_lock);
	return 0;

nla_put_failure:
	read_unlock_bh(&sk->sk_callback_lock);
	return -1;
}


Contributors
PersonTokensPropCommitsCommitProp
Valentina Giusti13697.14%150.00%


Eric Dumazet42.86%150.00%


Total140100.00%2100.00%






static u32 nfqnl_get_sk_secctx(struct sk_buff *skb, char **secdata)
{
	u32 seclen = 0;
#if IS_ENABLED(CONFIG_NETWORK_SECMARK)
	if (!skb || !sk_fullsock(skb->sk))
		return 0;

	read_lock_bh(&skb->sk->sk_callback_lock);

	if (skb->secmark)
		security_secid_to_secctx(skb->secmark, secdata, &seclen);

	read_unlock_bh(&skb->sk->sk_callback_lock);
#endif
	return seclen;
}


Contributors
PersonTokensPropCommitsCommitProp
Roman Kubiak86100.00%1100.00%


Total86100.00%1100.00%






static u32 nfqnl_get_bridge_size(struct nf_queue_entry *entry)
{
	struct sk_buff *entskb = entry->skb;
	u32 nlalen = 0;

	if (entry->state.pf != PF_BRIDGE || !skb_mac_header_was_set(entskb))
		return 0;

	if (skb_vlan_tag_present(entskb))
		nlalen += nla_total_size(nla_total_size(sizeof(__be16)) +
					 nla_total_size(sizeof(__be16)));

	if (entskb->network_header > entskb->mac_header)
		nlalen += nla_total_size((entskb->network_header -
					  entskb->mac_header));

	return nlalen;
}


Contributors
PersonTokensPropCommitsCommitProp
Stephane Bryant100100.00%1100.00%


Total100100.00%1100.00%






static int nfqnl_put_bridge(struct nf_queue_entry *entry, struct sk_buff *skb)
{
	struct sk_buff *entskb = entry->skb;

	if (entry->state.pf != PF_BRIDGE || !skb_mac_header_was_set(entskb))
		return 0;

	if (skb_vlan_tag_present(entskb)) {
		struct nlattr *nest;

		nest = nla_nest_start(skb, NFQA_VLAN | NLA_F_NESTED);
		if (!nest)
			goto nla_put_failure;

		if (nla_put_be16(skb, NFQA_VLAN_TCI, htons(entskb->vlan_tci)) ||
		    nla_put_be16(skb, NFQA_VLAN_PROTO, entskb->vlan_proto))
			goto nla_put_failure;

		nla_nest_end(skb, nest);
	}

	if (entskb->mac_header < entskb->network_header) {
		int len = (int)(entskb->network_header - entskb->mac_header);

		if (nla_put(skb, NFQA_L2HDR, len, skb_mac_header(entskb)))
			goto nla_put_failure;
	}

	return 0;

nla_put_failure:
	return -1;
}


Contributors
PersonTokensPropCommitsCommitProp
Stephane Bryant170100.00%1100.00%


Total170100.00%1100.00%





static struct sk_buff *

nfqnl_build_packet_message(struct net *net, struct nfqnl_instance *queue,
			   struct nf_queue_entry *entry,
			   __be32 **packet_id_ptr)
{
	size_t size;
	size_t data_len = 0, cap_len = 0;
	unsigned int hlen = 0;
	struct sk_buff *skb;
	struct nlattr *nla;
	struct nfqnl_msg_packet_hdr *pmsg;
	struct nlmsghdr *nlh;
	struct nfgenmsg *nfmsg;
	struct sk_buff *entskb = entry->skb;
	struct net_device *indev;
	struct net_device *outdev;
	struct nf_conn *ct = NULL;
	enum ip_conntrack_info uninitialized_var(ctinfo);
	struct nfnl_ct_hook *nfnl_ct;
	bool csum_verify;
	char *secdata = NULL;
	u32 seclen = 0;

	size =    nlmsg_total_size(sizeof(struct nfgenmsg))
		+ nla_total_size(sizeof(struct nfqnl_msg_packet_hdr))
		+ nla_total_size(sizeof(u_int32_t))	/* ifindex */
		+ nla_total_size(sizeof(u_int32_t))	/* ifindex */
#if IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
		+ nla_total_size(sizeof(u_int32_t))	/* ifindex */
		+ nla_total_size(sizeof(u_int32_t))	/* ifindex */
#endif
		+ nla_total_size(sizeof(u_int32_t))	/* mark */
		+ nla_total_size(sizeof(struct nfqnl_msg_packet_hw))
		+ nla_total_size(sizeof(u_int32_t))	/* skbinfo */
		+ nla_total_size(sizeof(u_int32_t));	/* cap_len */

	if (entskb->tstamp)
		size += nla_total_size(sizeof(struct nfqnl_msg_packet_timestamp));

	size += nfqnl_get_bridge_size(entry);

	if (entry->state.hook <= NF_INET_FORWARD ||
	   (entry->state.hook == NF_INET_POST_ROUTING && entskb->sk == NULL))
		csum_verify = !skb_csum_unnecessary(entskb);
	else
		csum_verify = false;

	outdev = entry->state.out;

	switch ((enum nfqnl_config_mode)ACCESS_ONCE(queue->copy_mode)) {
	case NFQNL_COPY_META:
	case NFQNL_COPY_NONE:
		break;

	case NFQNL_COPY_PACKET:
		if (!(queue->flags & NFQA_CFG_F_GSO) &&
		    entskb->ip_summed == CHECKSUM_PARTIAL &&
		    skb_checksum_help(entskb))
			return NULL;

		data_len = ACCESS_ONCE(queue->copy_range);
		if (data_len > entskb->len)
			data_len = entskb->len;

		hlen = skb_zerocopy_headlen(entskb);
		hlen = min_t(unsigned int, hlen, data_len);
		size += sizeof(struct nlattr) + hlen;
		cap_len = entskb->len;
		break;
	}

	nfnl_ct = rcu_dereference(nfnl_ct_hook);

	if (queue->flags & NFQA_CFG_F_CONNTRACK) {
		if (nfnl_ct != NULL) {
			ct = nfnl_ct->get_ct(entskb, &ctinfo);
			if (ct != NULL)
				size += nfnl_ct->build_size(ct);
		}
	}

	if (queue->flags & NFQA_CFG_F_UID_GID) {
		size +=  (nla_total_size(sizeof(u_int32_t))	/* uid */
			+ nla_total_size(sizeof(u_int32_t)));	/* gid */
	}

	if ((queue->flags & NFQA_CFG_F_SECCTX) && entskb->sk) {
		seclen = nfqnl_get_sk_secctx(entskb, &secdata);
		if (seclen)
			size += nla_total_size(seclen);
	}

	skb = alloc_skb(size, GFP_ATOMIC);
	if (!skb) {
		skb_tx_error(entskb);
		goto nlmsg_failure;
	}

	nlh = nlmsg_put(skb, 0, 0,
			NFNL_SUBSYS_QUEUE << 8 | NFQNL_MSG_PACKET,
			sizeof(struct nfgenmsg), 0);
	if (!nlh) {
		skb_tx_error(entskb);
		kfree_skb(skb);
		goto nlmsg_failure;
	}
	nfmsg = nlmsg_data(nlh);
	nfmsg->nfgen_family = entry->state.pf;
	nfmsg->version = NFNETLINK_V0;
	nfmsg->res_id = htons(queue->queue_num);

	nla = __nla_reserve(skb, NFQA_PACKET_HDR, sizeof(*pmsg));
	pmsg = nla_data(nla);
	pmsg->hw_protocol	= entskb->protocol;
	pmsg->hook		= entry->state.hook;
	*packet_id_ptr		= &pmsg->packet_id;

	indev = entry->state.in;
	if (indev) {
#if !IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
		if (nla_put_be32(skb, NFQA_IFINDEX_INDEV, htonl(indev->ifindex)))
			goto nla_put_failure;
#else
		if (entry->state.pf == PF_BRIDGE) {
			/* Case 1: indev is physical input device, we need to
                         * look for bridge group (when called from
                         * netfilter_bridge) */
			if (nla_put_be32(skb, NFQA_IFINDEX_PHYSINDEV,
					 htonl(indev->ifindex)) ||
			/* this is the bridge group "brX" */
			/* rcu_read_lock()ed by __nf_queue */
			    nla_put_be32(skb, NFQA_IFINDEX_INDEV,
					 htonl(br_port_get_rcu(indev)->br->dev->ifindex)))
				goto nla_put_failure;
		} else {
			int physinif;

			/* Case 2: indev is bridge group, we need to look for
                         * physical device (when called from ipv4) */
			if (nla_put_be32(skb, NFQA_IFINDEX_INDEV,
					 htonl(indev->ifindex)))
				goto nla_put_failure;

			physinif = nf_bridge_get_physinif(entskb);
			if (physinif &&
			    nla_put_be32(skb, NFQA_IFINDEX_PHYSINDEV,
					 htonl(physinif)))
				goto nla_put_failure;
		}
#endif
	}

	if (outdev) {
#if !IS_ENABLED(CONFIG_BRIDGE_NETFILTER)
		if (nla_put_be32(skb, NFQA_IFINDEX_OUTDEV, htonl(outdev->ifindex)))
			goto nla_put_failure;
#else
		if (entry->state.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(skb, NFQA_IFINDEX_PHYSOUTDEV,
					 htonl(outdev->ifindex)) ||
			/* this is the bridge group "brX" */
			/* rcu_read_lock()ed by __nf_queue */
			    nla_put_be32(skb, NFQA_IFINDEX_OUTDEV,
					 htonl(br_port_get_rcu(outdev)->br->dev->ifindex)))
				goto nla_put_failure;
		} else {
			int physoutif;

			/* Case 2: outdev is bridge group, we need to look for
                         * physical output device (when called from ipv4) */
			if (nla_put_be32(skb, NFQA_IFINDEX_OUTDEV,
					 htonl(outdev->ifindex)))
				goto nla_put_failure;

			physoutif = nf_bridge_get_physoutif(entskb);
			if (physoutif &&
			    nla_put_be32(skb, NFQA_IFINDEX_PHYSOUTDEV,
					 htonl(physoutif)))
				goto nla_put_failure;
		}
#endif
	}

	if (entskb->mark &&
	    nla_put_be32(skb, NFQA_MARK, htonl(entskb->mark)))
		goto nla_put_failure;

	if (indev && entskb->dev &&
	    entskb->mac_header != entskb->network_header) {
		struct nfqnl_msg_packet_hw phw;
		int len;

		memset(&phw, 0, sizeof(phw));
		len = dev_parse_header(entskb, phw.hw_addr);
		if (len) {
			phw.hw_addrlen = htons(len);
			if (nla_put(skb, NFQA_HWADDR, sizeof(phw), &phw))
				goto nla_put_failure;
		}
	}

	if (nfqnl_put_bridge(entry, skb) < 0)
		goto nla_put_failure;

	if (entskb->tstamp) {
		struct nfqnl_msg_packet_timestamp ts;
		struct timespec64 kts = ktime_to_timespec64(entskb->tstamp);

		ts.sec = cpu_to_be64(kts.tv_sec);
		ts.usec = cpu_to_be64(kts.tv_nsec / NSEC_PER_USEC);

		if (nla_put(skb, NFQA_TIMESTAMP, sizeof(ts), &ts))
			goto nla_put_failure;
	}

	if ((queue->flags & NFQA_CFG_F_UID_GID) && entskb->sk &&
	    nfqnl_put_sk_uidgid(skb, entskb->sk) < 0)
		goto nla_put_failure;

	if (seclen && nla_put(skb, NFQA_SECCTX, seclen, secdata))
		goto nla_put_failure;

	if (ct && nfnl_ct->build(skb, ct, ctinfo, NFQA_CT, NFQA_CT_INFO) < 0)
		goto nla_put_failure;

	if (cap_len > data_len &&
	    nla_put_be32(skb, NFQA_CAP_LEN, htonl(cap_len)))
		goto nla_put_failure;

	if (nfqnl_put_packet_info(skb, entskb, csum_verify))
		goto nla_put_failure;

	if (data_len) {
		struct nlattr *nla;

		if (skb_tailroom(skb) < sizeof(*nla) + hlen)
			goto nla_put_failure;

		nla = (struct nlattr *)skb_put(skb, sizeof(*nla));
		nla->nla_type = NFQA_PAYLOAD;
		nla->nla_len = nla_attr_size(data_len);

		if (skb_zerocopy(skb, entskb, data_len, hlen))
			goto nla_put_failure;
	}

	nlh->nlmsg_len = skb->len;
	if (seclen)
		security_release_secctx(secdata, seclen);
	return skb;

nla_put_failure:
	skb_tx_error(entskb);
	kfree_skb(skb);
	net_err_ratelimited("nf_queue: error creating packet message\n");
nlmsg_failure:
	if (seclen)
		security_release_secctx(secdata, seclen);