[linux-2.6-block.git] / net / sched / cls_flower.c

/*
 * net/sched/cls_flower.c		Flower classifier
 *
 * Copyright (c) 2015 Jiri Pirko <jiri@resnulli.us>
 *
 * This program is free software; you can redistribute it and/or modify
 * it under the terms of the GNU General Public License as published by
 * the Free Software Foundation; either version 2 of the License, or
 * (at your option) any later version.
 */

#include <linux/kernel.h>
#include <linux/init.h>
#include <linux/module.h>
#include <linux/rhashtable.h>

#include <linux/if_ether.h>
#include <linux/in6.h>
#include <linux/ip.h>

#include <net/sch_generic.h>
#include <net/pkt_cls.h>
#include <net/ip.h>
#include <net/flow_dissector.h>

struct fl_flow_key {
	int	indev_ifindex;
	struct flow_dissector_key_control control;
	struct flow_dissector_key_basic basic;
	struct flow_dissector_key_eth_addrs eth;
	struct flow_dissector_key_addrs ipaddrs;
	union {
		struct flow_dissector_key_ipv4_addrs ipv4;
		struct flow_dissector_key_ipv6_addrs ipv6;
	};
	struct flow_dissector_key_ports tp;
} __aligned(BITS_PER_LONG / 8); /* Ensure that we can do comparisons as longs. */

struct fl_flow_mask_range {
	unsigned short int start;
	unsigned short int end;
};

struct fl_flow_mask {
	struct fl_flow_key key;
	struct fl_flow_mask_range range;
	struct rcu_head	rcu;
};

struct cls_fl_head {
	struct rhashtable ht;
	struct fl_flow_mask mask;
	struct flow_dissector dissector;
	u32 hgen;
	bool mask_assigned;
	struct list_head filters;
	struct rhashtable_params ht_params;
	struct rcu_head rcu;
};

struct cls_fl_filter {
	struct rhash_head ht_node;
	struct fl_flow_key mkey;
	struct tcf_exts exts;
	struct tcf_result res;
	struct fl_flow_key key;
	struct list_head list;
	u32 handle;
	struct rcu_head	rcu;
};

static unsigned short int fl_mask_range(const struct fl_flow_mask *mask)
{
	return mask->range.end - mask->range.start;
}

static void fl_mask_update_range(struct fl_flow_mask *mask)
{
	const u8 *bytes = (const u8 *) &mask->key;
	size_t size = sizeof(mask->key);
	size_t i, first = 0, last = size - 1;

	for (i = 0; i < sizeof(mask->key); i++) {
		if (bytes[i]) {
			if (!first && i)
				first = i;
			last = i;
		}
	}
	mask->range.start = rounddown(first, sizeof(long));
	mask->range.end = roundup(last + 1, sizeof(long));
}

static void *fl_key_get_start(struct fl_flow_key *key,
			      const struct fl_flow_mask *mask)
{
	return (u8 *) key + mask->range.start;
}

static void fl_set_masked_key(struct fl_flow_key *mkey, struct fl_flow_key *key,
			      struct fl_flow_mask *mask)
{
	const long *lkey = fl_key_get_start(key, mask);
	const long *lmask = fl_key_get_start(&mask->key, mask);
	long *lmkey = fl_key_get_start(mkey, mask);
	int i;

	for (i = 0; i < fl_mask_range(mask); i += sizeof(long))
		*lmkey++ = *lkey++ & *lmask++;
}

static void fl_clear_masked_range(struct fl_flow_key *key,
				  struct fl_flow_mask *mask)
{
	memset(fl_key_get_start(key, mask), 0, fl_mask_range(mask));
}

static int fl_classify(struct sk_buff *skb, const struct tcf_proto *tp,
		       struct tcf_result *res)
{
	struct cls_fl_head *head = rcu_dereference_bh(tp->root);
	struct cls_fl_filter *f;
	struct fl_flow_key skb_key;
	struct fl_flow_key skb_mkey;

	fl_clear_masked_range(&skb_key, &head->mask);
	skb_key.indev_ifindex = skb->skb_iif;
	/* skb_flow_dissect() does not set n_proto in case an unknown protocol,
	 * so do it rather here.
	 */
	skb_key.basic.n_proto = skb->protocol;
	skb_flow_dissect(skb, &head->dissector, &skb_key, 0);

	fl_set_masked_key(&skb_mkey, &skb_key, &head->mask);

	f = rhashtable_lookup_fast(&head->ht,
				   fl_key_get_start(&skb_mkey, &head->mask),
				   head->ht_params);
	if (f) {
		*res = f->res;
		return tcf_exts_exec(skb, &f->exts, res);
	}
	return -1;
}

static int fl_init(struct tcf_proto *tp)
{
	struct cls_fl_head *head;

	head = kzalloc(sizeof(*head), GFP_KERNEL);
	if (!head)
		return -ENOBUFS;

	INIT_LIST_HEAD_RCU(&head->filters);
	rcu_assign_pointer(tp->root, head);

	return 0;
}

static void fl_destroy_filter(struct rcu_head *head)
{
	struct cls_fl_filter *f = container_of(head, struct cls_fl_filter, rcu);

	tcf_exts_destroy(&f->exts);
	kfree(f);
}

static bool fl_destroy(struct tcf_proto *tp, bool force)
{
	struct cls_fl_head *head = rtnl_dereference(tp->root);
	struct cls_fl_filter *f, *next;

	if (!force && !list_empty(&head->filters))
		return false;

	list_for_each_entry_safe(f, next, &head->filters, list) {
		list_del_rcu(&f->list);
		call_rcu(&f->rcu, fl_destroy_filter);
	}
	RCU_INIT_POINTER(tp->root, NULL);
	if (head->mask_assigned)
		rhashtable_destroy(&head->ht);
	kfree_rcu(head, rcu);
	return true;
}

static unsigned long fl_get(struct tcf_proto *tp, u32 handle)
{
	struct cls_fl_head *head = rtnl_dereference(tp->root);
	struct cls_fl_filter *f;

	list_for_each_entry(f, &head->filters, list)
		if (f->handle == handle)
			return (unsigned long) f;
	return 0;
}

static const struct nla_policy fl_policy[TCA_FLOWER_MAX + 1] = {
	[TCA_FLOWER_UNSPEC]		= { .type = NLA_UNSPEC },
	[TCA_FLOWER_CLASSID]		= { .type = NLA_U32 },
	[TCA_FLOWER_INDEV]		= { .type = NLA_STRING,
					    .len = IFNAMSIZ },
	[TCA_FLOWER_KEY_ETH_DST]	= { .len = ETH_ALEN },
	[TCA_FLOWER_KEY_ETH_DST_MASK]	= { .len = ETH_ALEN },
	[TCA_FLOWER_KEY_ETH_SRC]	= { .len = ETH_ALEN },
	[TCA_FLOWER_KEY_ETH_SRC_MASK]	= { .len = ETH_ALEN },
	[TCA_FLOWER_KEY_ETH_TYPE]	= { .type = NLA_U16 },
	[TCA_FLOWER_KEY_IP_PROTO]	= { .type = NLA_U8 },
	[TCA_FLOWER_KEY_IPV4_SRC]	= { .type = NLA_U32 },
	[TCA_FLOWER_KEY_IPV4_SRC_MASK]	= { .type = NLA_U32 },
	[TCA_FLOWER_KEY_IPV4_DST]	= { .type = NLA_U32 },
	[TCA_FLOWER_KEY_IPV4_DST_MASK]	= { .type = NLA_U32 },
	[TCA_FLOWER_KEY_IPV6_SRC]	= { .len = sizeof(struct in6_addr) },
	[TCA_FLOWER_KEY_IPV6_SRC_MASK]	= { .len = sizeof(struct in6_addr) },
	[TCA_FLOWER_KEY_IPV6_DST]	= { .len = sizeof(struct in6_addr) },
	[TCA_FLOWER_KEY_IPV6_DST_MASK]	= { .len = sizeof(struct in6_addr) },
	[TCA_FLOWER_KEY_TCP_SRC]	= { .type = NLA_U16 },
	[TCA_FLOWER_KEY_TCP_DST]	= { .type = NLA_U16 },
	[TCA_FLOWER_KEY_UDP_SRC]	= { .type = NLA_U16 },
	[TCA_FLOWER_KEY_UDP_DST]	= { .type = NLA_U16 },
};

static void fl_set_key_val(struct nlattr **tb,
			   void *val, int val_type,
			   void *mask, int mask_type, int len)
{
	if (!tb[val_type])
		return;
	memcpy(val, nla_data(tb[val_type]), len);
	if (mask_type == TCA_FLOWER_UNSPEC || !tb[mask_type])
		memset(mask, 0xff, len);
	else
		memcpy(mask, nla_data(tb[mask_type]), len);
}

static int fl_set_key(struct net *net, struct nlattr **tb,
		      struct fl_flow_key *key, struct fl_flow_key *mask)
{
#ifdef CONFIG_NET_CLS_IND
	if (tb[TCA_FLOWER_INDEV]) {
		int err = tcf_change_indev(net, tb[TCA_FLOWER_INDEV]);
		if (err < 0)
			return err;
		key->indev_ifindex = err;
		mask->indev_ifindex = 0xffffffff;
	}
#endif

	fl_set_key_val(tb, key->eth.dst, TCA_FLOWER_KEY_ETH_DST,
		       mask->eth.dst, TCA_FLOWER_KEY_ETH_DST_MASK,
		       sizeof(key->eth.dst));
	fl_set_key_val(tb, key->eth.src, TCA_FLOWER_KEY_ETH_SRC,
		       mask->eth.src, TCA_FLOWER_KEY_ETH_SRC_MASK,
		       sizeof(key->eth.src));

	fl_set_key_val(tb, &key->basic.n_proto, TCA_FLOWER_KEY_ETH_TYPE,
		       &mask->basic.n_proto, TCA_FLOWER_UNSPEC,
		       sizeof(key->basic.n_proto));

	if (key->basic.n_proto == htons(ETH_P_IP) ||
	    key->basic.n_proto == htons(ETH_P_IPV6)) {
		fl_set_key_val(tb, &key->basic.ip_proto, TCA_FLOWER_KEY_IP_PROTO,
			       &mask->basic.ip_proto, TCA_FLOWER_UNSPEC,
			       sizeof(key->basic.ip_proto));
	}

	if (tb[TCA_FLOWER_KEY_IPV4_SRC] || tb[TCA_FLOWER_KEY_IPV4_DST]) {
		key->control.addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS;
		fl_set_key_val(tb, &key->ipv4.src, TCA_FLOWER_KEY_IPV4_SRC,
			       &mask->ipv4.src, TCA_FLOWER_KEY_IPV4_SRC_MASK,
			       sizeof(key->ipv4.src));
		fl_set_key_val(tb, &key->ipv4.dst, TCA_FLOWER_KEY_IPV4_DST,
			       &mask->ipv4.dst, TCA_FLOWER_KEY_IPV4_DST_MASK,
			       sizeof(key->ipv4.dst));
	} else if (tb[TCA_FLOWER_KEY_IPV6_SRC] || tb[TCA_FLOWER_KEY_IPV6_DST]) {
		key->control.addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS;
		fl_set_key_val(tb, &key->ipv6.src, TCA_FLOWER_KEY_IPV6_SRC,
			       &mask->ipv6.src, TCA_FLOWER_KEY_IPV6_SRC_MASK,
			       sizeof(key->ipv6.src));
		fl_set_key_val(tb, &key->ipv6.dst, TCA_FLOWER_KEY_IPV6_DST,
			       &mask->ipv6.dst, TCA_FLOWER_KEY_IPV6_DST_MASK,
			       sizeof(key->ipv6.dst));
	}

	if (key->basic.ip_proto == IPPROTO_TCP) {
		fl_set_key_val(tb, &key->tp.src, TCA_FLOWER_KEY_TCP_SRC,
			       &mask->tp.src, TCA_FLOWER_UNSPEC,
			       sizeof(key->tp.src));
		fl_set_key_val(tb, &key->tp.dst, TCA_FLOWER_KEY_TCP_DST,
			       &mask->tp.dst, TCA_FLOWER_UNSPEC,
			       sizeof(key->tp.dst));
	} else if (key->basic.ip_proto == IPPROTO_UDP) {
		fl_set_key_val(tb, &key->tp.src, TCA_FLOWER_KEY_UDP_SRC,
			       &mask->tp.src, TCA_FLOWER_UNSPEC,
			       sizeof(key->tp.src));
		fl_set_key_val(tb, &key->tp.dst, TCA_FLOWER_KEY_UDP_DST,
			       &mask->tp.dst, TCA_FLOWER_UNSPEC,
			       sizeof(key->tp.dst));
	}

	return 0;
}

static bool fl_mask_eq(struct fl_flow_mask *mask1,
		       struct fl_flow_mask *mask2)
{
	const long *lmask1 = fl_key_get_start(&mask1->key, mask1);
	const long *lmask2 = fl_key_get_start(&mask2->key, mask2);

	return !memcmp(&mask1->range, &mask2->range, sizeof(mask1->range)) &&
	       !memcmp(lmask1, lmask2, fl_mask_range(mask1));
}

static const struct rhashtable_params fl_ht_params = {
	.key_offset = offsetof(struct cls_fl_filter, mkey), /* base offset */
	.head_offset = offsetof(struct cls_fl_filter, ht_node),
	.automatic_shrinking = true,
};

static int fl_init_hashtable(struct cls_fl_head *head,
			     struct fl_flow_mask *mask)
{
	head->ht_params = fl_ht_params;
	head->ht_params.key_len = fl_mask_range(mask);
	head->ht_params.key_offset += mask->range.start;

	return rhashtable_init(&head->ht, &head->ht_params);
}

#define FL_KEY_MEMBER_OFFSET(member) offsetof(struct fl_flow_key, member)
#define FL_KEY_MEMBER_SIZE(member) (sizeof(((struct fl_flow_key *) 0)->member))
#define FL_KEY_MEMBER_END_OFFSET(member)					\
	(FL_KEY_MEMBER_OFFSET(member) + FL_KEY_MEMBER_SIZE(member))

#define FL_KEY_IN_RANGE(mask, member)						\
        (FL_KEY_MEMBER_OFFSET(member) <= (mask)->range.end &&			\
         FL_KEY_MEMBER_END_OFFSET(member) >= (mask)->range.start)

#define FL_KEY_SET(keys, cnt, id, member)					\
	do {									\
		keys[cnt].key_id = id;						\
		keys[cnt].offset = FL_KEY_MEMBER_OFFSET(member);		\
		cnt++;								\
	} while(0);

#define FL_KEY_SET_IF_IN_RANGE(mask, keys, cnt, id, member)			\
	do {									\
		if (FL_KEY_IN_RANGE(mask, member))				\
			FL_KEY_SET(keys, cnt, id, member);			\
	} while(0);

static void fl_init_dissector(struct cls_fl_head *head,
			      struct fl_flow_mask *mask)
{
	struct flow_dissector_key keys[FLOW_DISSECTOR_KEY_MAX];
	size_t cnt = 0;

	FL_KEY_SET(keys, cnt, FLOW_DISSECTOR_KEY_CONTROL, control);
	FL_KEY_SET(keys, cnt, FLOW_DISSECTOR_KEY_BASIC, basic);
	FL_KEY_SET_IF_IN_RANGE(mask, keys, cnt,
			       FLOW_DISSECTOR_KEY_ETH_ADDRS, eth);
	FL_KEY_SET_IF_IN_RANGE(mask, keys, cnt,
			       FLOW_DISSECTOR_KEY_IPV4_ADDRS, ipv4);
	FL_KEY_SET_IF_IN_RANGE(mask, keys, cnt,
			       FLOW_DISSECTOR_KEY_IPV6_ADDRS, ipv6);
	FL_KEY_SET_IF_IN_RANGE(mask, keys, cnt,
			       FLOW_DISSECTOR_KEY_PORTS, tp);

	skb_flow_dissector_init(&head->dissector, keys, cnt);
}

static int fl_check_assign_mask(struct cls_fl_head *head,
				struct fl_flow_mask *mask)
{
	int err;

	if (head->mask_assigned) {
		if (!fl_mask_eq(&head->mask, mask))
			return -EINVAL;
		else
			return 0;
	}

	/* Mask is not assigned yet. So assign it and init hashtable
	 * according to that.
	 */
	err = fl_init_hashtable(head, mask);
	if (err)
		return err;
	memcpy(&head->mask, mask, sizeof(head->mask));
	head->mask_assigned = true;

	fl_init_dissector(head, mask);

	return 0;
}

static int fl_set_parms(struct net *net, struct tcf_proto *tp,
			struct cls_fl_filter *f, struct fl_flow_mask *mask,
			unsigned long base, struct nlattr **tb,
			struct nlattr *est, bool ovr)
{
	struct tcf_exts e;
	int err;

	tcf_exts_init(&e, TCA_FLOWER_ACT, 0);
	err = tcf_exts_validate(net, tp, tb, est, &e, ovr);
	if (err < 0)
		return err;

	if (tb[TCA_FLOWER_CLASSID]) {
		f->res.classid = nla_get_u32(tb[TCA_FLOWER_CLASSID]);
		tcf_bind_filter(tp, &f->res, base);
	}

	err = fl_set_key(net, tb, &f->key, &mask->key);
	if (err)
		goto errout;

	fl_mask_update_range(mask);
	fl_set_masked_key(&f->mkey, &f->key, mask);

	tcf_exts_change(tp, &f->exts, &e);

	return 0;
errout:
	tcf_exts_destroy(&e);
	return err;
}

static u32 fl_grab_new_handle(struct tcf_proto *tp,
			      struct cls_fl_head *head)
{
	unsigned int i = 0x80000000;
	u32 handle;

	do {
		if (++head->hgen == 0x7FFFFFFF)
			head->hgen = 1;
	} while (--i > 0 && fl_get(tp, head->hgen));

	if (unlikely(i == 0)) {
		pr_err("Insufficient number of handles\n");
		handle = 0;
	} else {
		handle = head->hgen;
	}

	return handle;
}

static int fl_change(struct net *net, struct sk_buff *in_skb,
		     struct tcf_proto *tp, unsigned long base,
		     u32 handle, struct nlattr **tca,
		     unsigned long *arg, bool ovr)
{
	struct cls_fl_head *head = rtnl_dereference(tp->root);
	struct cls_fl_filter *fold = (struct cls_fl_filter *) *arg;
	struct cls_fl_filter *fnew;
	struct nlattr *tb[TCA_FLOWER_MAX + 1];
	struct fl_flow_mask mask = {};
	int err;

	if (!tca[TCA_OPTIONS])
		return -EINVAL;

	err = nla_parse_nested(tb, TCA_FLOWER_MAX, tca[TCA_OPTIONS], fl_policy);
	if (err < 0)
		return err;

	if (fold && handle && fold->handle != handle)
		return -EINVAL;

	fnew = kzalloc(sizeof(*fnew), GFP_KERNEL);
	if (!fnew)
		return -ENOBUFS;

	tcf_exts_init(&fnew->exts, TCA_FLOWER_ACT, 0);

	if (!handle) {
		handle = fl_grab_new_handle(tp, head);
		if (!handle) {
			err = -EINVAL;
			goto errout;
		}
	}
	fnew->handle = handle;

	err = fl_set_parms(net, tp, fnew, &mask, base, tb, tca[TCA_RATE], ovr);
	if (err)
		goto errout;

	err = fl_check_assign_mask(head, &mask);
	if (err)
		goto errout;

	err = rhashtable_insert_fast(&head->ht, &fnew->ht_node,
				     head->ht_params);
	if (err)
		goto errout;
	if (fold)
		rhashtable_remove_fast(&head->ht, &fold->ht_node,
				       head->ht_params);

	*arg = (unsigned long) fnew;

	if (fold) {
		list_replace_rcu(&fold->list, &fnew->list);
		tcf_unbind_filter(tp, &fold->res);
		call_rcu(&fold->rcu, fl_destroy_filter);
	} else {
		list_add_tail_rcu(&fnew->list, &head->filters);
	}

	return 0;

errout:
	kfree(fnew);
	return err;
}

static int fl_delete(struct tcf_proto *tp, unsigned long arg)
{
	struct cls_fl_head *head = rtnl_dereference(tp->root);
	struct cls_fl_filter *f = (struct cls_fl_filter *) arg;

	rhashtable_remove_fast(&head->ht, &f->ht_node,
			       head->ht_params);
	list_del_rcu(&f->list);
	tcf_unbind_filter(tp, &f->res);
	call_rcu(&f->rcu, fl_destroy_filter);
	return 0;
}

static void fl_walk(struct tcf_proto *tp, struct tcf_walker *arg)
{
	struct cls_fl_head *head = rtnl_dereference(tp->root);
	struct cls_fl_filter *f;

	list_for_each_entry_rcu(f, &head->filters, list) {
		if (arg->count < arg->skip)
			goto skip;
		if (arg->fn(tp, (unsigned long) f, arg) < 0) {
			arg->stop = 1;
			break;
		}
skip:
		arg->count++;
	}
}

static int fl_dump_key_val(struct sk_buff *skb,
			   void *val, int val_type,
			   void *mask, int mask_type, int len)
{
	int err;

	if (!memchr_inv(mask, 0, len))
		return 0;
	err = nla_put(skb, val_type, len, val);
	if (err)
		return err;
	if (mask_type != TCA_FLOWER_UNSPEC) {
		err = nla_put(skb, mask_type, len, mask);
		if (err)
			return err;
	}
	return 0;
}

static int fl_dump(struct net *net, struct tcf_proto *tp, unsigned long fh,
		   struct sk_buff *skb, struct tcmsg *t)
{
	struct cls_fl_head *head = rtnl_dereference(tp->root);
	struct cls_fl_filter *f = (struct cls_fl_filter *) fh;
	struct nlattr *nest;
	struct fl_flow_key *key, *mask;

	if (!f)
		return skb->len;

	t->tcm_handle = f->handle;

	nest = nla_nest_start(skb, TCA_OPTIONS);
	if (!nest)
		goto nla_put_failure;

	if (f->res.classid &&
	    nla_put_u32(skb, TCA_FLOWER_CLASSID, f->res.classid))
		goto nla_put_failure;

	key = &f->key;
	mask = &head->mask.key;

	if (mask->indev_ifindex) {
		struct net_device *dev;

		dev = __dev_get_by_index(net, key->indev_ifindex);
		if (dev && nla_put_string(skb, TCA_FLOWER_INDEV, dev->name))
			goto nla_put_failure;
	}

	if (fl_dump_key_val(skb, key->eth.dst, TCA_FLOWER_KEY_ETH_DST,
			    mask->eth.dst, TCA_FLOWER_KEY_ETH_DST_MASK,
			    sizeof(key->eth.dst)) ||
	    fl_dump_key_val(skb, key->eth.src, TCA_FLOWER_KEY_ETH_SRC,
			    mask->eth.src, TCA_FLOWER_KEY_ETH_SRC_MASK,
			    sizeof(key->eth.src)) ||
	    fl_dump_key_val(skb, &key->basic.n_proto, TCA_FLOWER_KEY_ETH_TYPE,
			    &mask->basic.n_proto, TCA_FLOWER_UNSPEC,
			    sizeof(key->basic.n_proto)))
		goto nla_put_failure;
	if ((key->basic.n_proto == htons(ETH_P_IP) ||
	     key->basic.n_proto == htons(ETH_P_IPV6)) &&
	    fl_dump_key_val(skb, &key->basic.ip_proto, TCA_FLOWER_KEY_IP_PROTO,
			    &mask->basic.ip_proto, TCA_FLOWER_UNSPEC,
			    sizeof(key->basic.ip_proto)))
		goto nla_put_failure;

	if (key->control.addr_type == FLOW_DISSECTOR_KEY_IPV4_ADDRS &&
	    (fl_dump_key_val(skb, &key->ipv4.src, TCA_FLOWER_KEY_IPV4_SRC,
			     &mask->ipv4.src, TCA_FLOWER_KEY_IPV4_SRC_MASK,
			     sizeof(key->ipv4.src)) ||
	     fl_dump_key_val(skb, &key->ipv4.dst, TCA_FLOWER_KEY_IPV4_DST,
			     &mask->ipv4.dst, TCA_FLOWER_KEY_IPV4_DST_MASK,
			     sizeof(key->ipv4.dst))))
		goto nla_put_failure;
	else if (key->control.addr_type == FLOW_DISSECTOR_KEY_IPV6_ADDRS &&
		 (fl_dump_key_val(skb, &key->ipv6.src, TCA_FLOWER_KEY_IPV6_SRC,
				  &mask->ipv6.src, TCA_FLOWER_KEY_IPV6_SRC_MASK,
				  sizeof(key->ipv6.src)) ||
		  fl_dump_key_val(skb, &key->ipv6.dst, TCA_FLOWER_KEY_IPV6_DST,
				  &mask->ipv6.dst, TCA_FLOWER_KEY_IPV6_DST_MASK,
				  sizeof(key->ipv6.dst))))
		goto nla_put_failure;

	if (key->basic.ip_proto == IPPROTO_TCP &&
	    (fl_dump_key_val(skb, &key->tp.src, TCA_FLOWER_KEY_TCP_SRC,
			     &mask->tp.src, TCA_FLOWER_UNSPEC,
			     sizeof(key->tp.src)) ||
	     fl_dump_key_val(skb, &key->tp.dst, TCA_FLOWER_KEY_TCP_DST,
			     &mask->tp.dst, TCA_FLOWER_UNSPEC,
			     sizeof(key->tp.dst))))
		goto nla_put_failure;
	else if (key->basic.ip_proto == IPPROTO_UDP &&
		 (fl_dump_key_val(skb, &key->tp.src, TCA_FLOWER_KEY_UDP_SRC,
				  &mask->tp.src, TCA_FLOWER_UNSPEC,
				  sizeof(key->tp.src)) ||
		  fl_dump_key_val(skb, &key->tp.dst, TCA_FLOWER_KEY_UDP_DST,
				  &mask->tp.dst, TCA_FLOWER_UNSPEC,
				  sizeof(key->tp.dst))))
		goto nla_put_failure;

	if (tcf_exts_dump(skb, &f->exts))
		goto nla_put_failure;

	nla_nest_end(skb, nest);

	if (tcf_exts_dump_stats(skb, &f->exts) < 0)
		goto nla_put_failure;

	return skb->len;

nla_put_failure:
	nla_nest_cancel(skb, nest);
	return -1;
}

static struct tcf_proto_ops cls_fl_ops __read_mostly = {
	.kind		= "flower",
	.classify	= fl_classify,
	.init		= fl_init,
	.destroy	= fl_destroy,
	.get		= fl_get,
	.change		= fl_change,
	.delete		= fl_delete,
	.walk		= fl_walk,
	.dump		= fl_dump,
	.owner		= THIS_MODULE,
};

static int __init cls_fl_init(void)
{
	return register_tcf_proto_ops(&cls_fl_ops);
}

static void __exit cls_fl_exit(void)
{
	unregister_tcf_proto_ops(&cls_fl_ops);
}

module_init(cls_fl_init);
module_exit(cls_fl_exit);

MODULE_AUTHOR("Jiri Pirko <jiri@resnulli.us>");
MODULE_DESCRIPTION("Flower classifier");
MODULE_LICENSE("GPL v2");
Commit	Line	Data
77b9900e JP	1	/*
	2	* net/sched/cls_flower.c Flower classifier
	3	*
	4	* Copyright (c) 2015 Jiri Pirko <jiri@resnulli.us>
	5	*
	6	* This program is free software; you can redistribute it and/or modify
	7	* it under the terms of the GNU General Public License as published by
	8	* the Free Software Foundation; either version 2 of the License, or
	9	* (at your option) any later version.
	10	*/
	11
	12	#include <linux/kernel.h>
	13	#include <linux/init.h>
	14	#include <linux/module.h>
	15	#include <linux/rhashtable.h>
	16
	17	#include <linux/if_ether.h>
	18	#include <linux/in6.h>
	19	#include <linux/ip.h>
	20
	21	#include <net/sch_generic.h>
	22	#include <net/pkt_cls.h>
	23	#include <net/ip.h>
	24	#include <net/flow_dissector.h>
	25
	26	struct fl_flow_key {
	27	int indev_ifindex;
42aecaa9	28	struct flow_dissector_key_control control;
77b9900e JP	29	struct flow_dissector_key_basic basic;
77b9900e JP	30	struct flow_dissector_key_eth_addrs eth;
c3f83241	31	struct flow_dissector_key_addrs ipaddrs;
77b9900e	32	union {
c3f83241	33	struct flow_dissector_key_ipv4_addrs ipv4;
77b9900e JP	34	struct flow_dissector_key_ipv6_addrs ipv6;
	35	};
	36	struct flow_dissector_key_ports tp;
	37	} __aligned(BITS_PER_LONG / 8); /* Ensure that we can do comparisons as longs. */
	38
	39	struct fl_flow_mask_range {
	40	unsigned short int start;
	41	unsigned short int end;
	42	};
	43
	44	struct fl_flow_mask {
	45	struct fl_flow_key key;
	46	struct fl_flow_mask_range range;
	47	struct rcu_head rcu;
	48	};
	49
	50	struct cls_fl_head {
	51	struct rhashtable ht;
	52	struct fl_flow_mask mask;
	53	struct flow_dissector dissector;
	54	u32 hgen;
	55	bool mask_assigned;
	56	struct list_head filters;
	57	struct rhashtable_params ht_params;
	58	struct rcu_head rcu;
	59	};
	60
	61	struct cls_fl_filter {
	62	struct rhash_head ht_node;
	63	struct fl_flow_key mkey;
	64	struct tcf_exts exts;
	65	struct tcf_result res;
	66	struct fl_flow_key key;
	67	struct list_head list;
	68	u32 handle;
	69	struct rcu_head rcu;
	70	};
	71
	72	static unsigned short int fl_mask_range(const struct fl_flow_mask *mask)
	73	{
	74	return mask->range.end - mask->range.start;
	75	}
	76
	77	static void fl_mask_update_range(struct fl_flow_mask *mask)
	78	{
	79	const u8 bytes = (const u8 ) &mask->key;
	80	size_t size = sizeof(mask->key);
	81	size_t i, first = 0, last = size - 1;
	82
	83	for (i = 0; i < sizeof(mask->key); i++) {
	84	if (bytes[i]) {
	85	if (!first && i)
	86	first = i;
	87	last = i;
	88	}
	89	}
	90	mask->range.start = rounddown(first, sizeof(long));
	91	mask->range.end = roundup(last + 1, sizeof(long));
	92	}
	93
	94	static void fl_key_get_start(struct fl_flow_key key,
	95	const struct fl_flow_mask *mask)
	96	{
	97	return (u8 *) key + mask->range.start;
98	}
99
100	static void fl_set_masked_key(struct fl_flow_key mkey, struct fl_flow_key key,
101	struct fl_flow_mask *mask)
102	{
103	const long *lkey = fl_key_get_start(key, mask);
104	const long *lmask = fl_key_get_start(&mask->key, mask);
105	long *lmkey = fl_key_get_start(mkey, mask);
106	int i;
107
108	for (i = 0; i < fl_mask_range(mask); i += sizeof(long))
109	lmkey++ = lkey++ & *lmask++;
110	}
111
112	static void fl_clear_masked_range(struct fl_flow_key *key,
113	struct fl_flow_mask *mask)
114	{
115	memset(fl_key_get_start(key, mask), 0, fl_mask_range(mask));
116	}
117
118	static int fl_classify(struct sk_buff skb, const struct tcf_proto tp,
119	struct tcf_result *res)
120	{
121	struct cls_fl_head *head = rcu_dereference_bh(tp->root);
122	struct cls_fl_filter *f;
123	struct fl_flow_key skb_key;
124	struct fl_flow_key skb_mkey;
125
126	fl_clear_masked_range(&skb_key, &head->mask);
127	skb_key.indev_ifindex = skb->skb_iif;
128	/* skb_flow_dissect() does not set n_proto in case an unknown protocol,
129	* so do it rather here.
130	*/
131	skb_key.basic.n_proto = skb->protocol;
cd79a238	132	skb_flow_dissect(skb, &head->dissector, &skb_key, 0);
77b9900e JP	133
	134	fl_set_masked_key(&skb_mkey, &skb_key, &head->mask);
	135
	136	f = rhashtable_lookup_fast(&head->ht,
	137	fl_key_get_start(&skb_mkey, &head->mask),
	138	head->ht_params);
	139	if (f) {
	140	*res = f->res;
	141	return tcf_exts_exec(skb, &f->exts, res);
	142	}
	143	return -1;
	144	}
	145
	146	static int fl_init(struct tcf_proto *tp)
	147	{
	148	struct cls_fl_head *head;
	149
	150	head = kzalloc(sizeof(*head), GFP_KERNEL);
	151	if (!head)
	152	return -ENOBUFS;
	153
	154	INIT_LIST_HEAD_RCU(&head->filters);
	155	rcu_assign_pointer(tp->root, head);
	156
	157	return 0;
	158	}
	159
	160	static void fl_destroy_filter(struct rcu_head *head)
	161	{
	162	struct cls_fl_filter *f = container_of(head, struct cls_fl_filter, rcu);
	163
	164	tcf_exts_destroy(&f->exts);
	165	kfree(f);
	166	}
	167
	168	static bool fl_destroy(struct tcf_proto *tp, bool force)
	169	{
	170	struct cls_fl_head *head = rtnl_dereference(tp->root);
	171	struct cls_fl_filter f, next;
	172
	173	if (!force && !list_empty(&head->filters))
	174	return false;
	175
	176	list_for_each_entry_safe(f, next, &head->filters, list) {
	177	list_del_rcu(&f->list);
	178	call_rcu(&f->rcu, fl_destroy_filter);
	179	}
	180	RCU_INIT_POINTER(tp->root, NULL);
	181	if (head->mask_assigned)
	182	rhashtable_destroy(&head->ht);
	183	kfree_rcu(head, rcu);
	184	return true;
	185	}
	186
	187	static unsigned long fl_get(struct tcf_proto *tp, u32 handle)
	188	{
	189	struct cls_fl_head *head = rtnl_dereference(tp->root);
	190	struct cls_fl_filter *f;
	191
	192	list_for_each_entry(f, &head->filters, list)
	193	if (f->handle == handle)
	194	return (unsigned long) f;
	195	return 0;
	196	}
197
198	static const struct nla_policy fl_policy[TCA_FLOWER_MAX + 1] = {
199	[TCA_FLOWER_UNSPEC] = { .type = NLA_UNSPEC },
200	[TCA_FLOWER_CLASSID] = { .type = NLA_U32 },
201	[TCA_FLOWER_INDEV] = { .type = NLA_STRING,
202	.len = IFNAMSIZ },
203	[TCA_FLOWER_KEY_ETH_DST] = { .len = ETH_ALEN },
204	[TCA_FLOWER_KEY_ETH_DST_MASK] = { .len = ETH_ALEN },
205	[TCA_FLOWER_KEY_ETH_SRC] = { .len = ETH_ALEN },
206	[TCA_FLOWER_KEY_ETH_SRC_MASK] = { .len = ETH_ALEN },
207	[TCA_FLOWER_KEY_ETH_TYPE] = { .type = NLA_U16 },
208	[TCA_FLOWER_KEY_IP_PROTO] = { .type = NLA_U8 },
209	[TCA_FLOWER_KEY_IPV4_SRC] = { .type = NLA_U32 },
210	[TCA_FLOWER_KEY_IPV4_SRC_MASK] = { .type = NLA_U32 },
211	[TCA_FLOWER_KEY_IPV4_DST] = { .type = NLA_U32 },
212	[TCA_FLOWER_KEY_IPV4_DST_MASK] = { .type = NLA_U32 },
213	[TCA_FLOWER_KEY_IPV6_SRC] = { .len = sizeof(struct in6_addr) },
214	[TCA_FLOWER_KEY_IPV6_SRC_MASK] = { .len = sizeof(struct in6_addr) },
215	[TCA_FLOWER_KEY_IPV6_DST] = { .len = sizeof(struct in6_addr) },
216	[TCA_FLOWER_KEY_IPV6_DST_MASK] = { .len = sizeof(struct in6_addr) },
217	[TCA_FLOWER_KEY_TCP_SRC] = { .type = NLA_U16 },
218	[TCA_FLOWER_KEY_TCP_DST] = { .type = NLA_U16 },
b175c3a4 JHS	219	[TCA_FLOWER_KEY_UDP_SRC] = { .type = NLA_U16 },
b175c3a4 JHS	220	[TCA_FLOWER_KEY_UDP_DST] = { .type = NLA_U16 },
77b9900e JP	221	};
	222
	223	static void fl_set_key_val(struct nlattr **tb,
	224	void *val, int val_type,
	225	void *mask, int mask_type, int len)
	226	{
	227	if (!tb[val_type])
	228	return;
	229	memcpy(val, nla_data(tb[val_type]), len);
	230	if (mask_type == TCA_FLOWER_UNSPEC \|\| !tb[mask_type])
	231	memset(mask, 0xff, len);
	232	else
	233	memcpy(mask, nla_data(tb[mask_type]), len);
	234	}
	235
	236	static int fl_set_key(struct net net, struct nlattr *tb,
	237	struct fl_flow_key key, struct fl_flow_key mask)
	238	{
dd3aa3b5	239	#ifdef CONFIG_NET_CLS_IND
77b9900e	240	if (tb[TCA_FLOWER_INDEV]) {
dd3aa3b5	241	int err = tcf_change_indev(net, tb[TCA_FLOWER_INDEV]);
77b9900e JP	242	if (err < 0)
	243	return err;
	244	key->indev_ifindex = err;
	245	mask->indev_ifindex = 0xffffffff;
	246	}
dd3aa3b5	247	#endif
77b9900e JP	248
	249	fl_set_key_val(tb, key->eth.dst, TCA_FLOWER_KEY_ETH_DST,
	250	mask->eth.dst, TCA_FLOWER_KEY_ETH_DST_MASK,
	251	sizeof(key->eth.dst));
	252	fl_set_key_val(tb, key->eth.src, TCA_FLOWER_KEY_ETH_SRC,
	253	mask->eth.src, TCA_FLOWER_KEY_ETH_SRC_MASK,
	254	sizeof(key->eth.src));
66530bdf	255
77b9900e JP	256	fl_set_key_val(tb, &key->basic.n_proto, TCA_FLOWER_KEY_ETH_TYPE,
	257	&mask->basic.n_proto, TCA_FLOWER_UNSPEC,
	258	sizeof(key->basic.n_proto));
66530bdf	259
77b9900e JP	260	if (key->basic.n_proto == htons(ETH_P_IP) \|\|
	261	key->basic.n_proto == htons(ETH_P_IPV6)) {
	262	fl_set_key_val(tb, &key->basic.ip_proto, TCA_FLOWER_KEY_IP_PROTO,
	263	&mask->basic.ip_proto, TCA_FLOWER_UNSPEC,
	264	sizeof(key->basic.ip_proto));
	265	}
66530bdf JHS	266
	267	if (tb[TCA_FLOWER_KEY_IPV4_SRC] \|\| tb[TCA_FLOWER_KEY_IPV4_DST]) {
	268	key->control.addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS;
77b9900e JP	269	fl_set_key_val(tb, &key->ipv4.src, TCA_FLOWER_KEY_IPV4_SRC,
	270	&mask->ipv4.src, TCA_FLOWER_KEY_IPV4_SRC_MASK,
	271	sizeof(key->ipv4.src));
	272	fl_set_key_val(tb, &key->ipv4.dst, TCA_FLOWER_KEY_IPV4_DST,
	273	&mask->ipv4.dst, TCA_FLOWER_KEY_IPV4_DST_MASK,
	274	sizeof(key->ipv4.dst));
66530bdf JHS	275	} else if (tb[TCA_FLOWER_KEY_IPV6_SRC] \|\| tb[TCA_FLOWER_KEY_IPV6_DST]) {
66530bdf JHS	276	key->control.addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS;
77b9900e JP	277	fl_set_key_val(tb, &key->ipv6.src, TCA_FLOWER_KEY_IPV6_SRC,
	278	&mask->ipv6.src, TCA_FLOWER_KEY_IPV6_SRC_MASK,
	279	sizeof(key->ipv6.src));
	280	fl_set_key_val(tb, &key->ipv6.dst, TCA_FLOWER_KEY_IPV6_DST,
	281	&mask->ipv6.dst, TCA_FLOWER_KEY_IPV6_DST_MASK,
	282	sizeof(key->ipv6.dst));
	283	}
66530bdf	284
77b9900e JP	285	if (key->basic.ip_proto == IPPROTO_TCP) {
	286	fl_set_key_val(tb, &key->tp.src, TCA_FLOWER_KEY_TCP_SRC,
	287	&mask->tp.src, TCA_FLOWER_UNSPEC,
	288	sizeof(key->tp.src));
	289	fl_set_key_val(tb, &key->tp.dst, TCA_FLOWER_KEY_TCP_DST,
	290	&mask->tp.dst, TCA_FLOWER_UNSPEC,
	291	sizeof(key->tp.dst));
	292	} else if (key->basic.ip_proto == IPPROTO_UDP) {
	293	fl_set_key_val(tb, &key->tp.src, TCA_FLOWER_KEY_UDP_SRC,
	294	&mask->tp.src, TCA_FLOWER_UNSPEC,
	295	sizeof(key->tp.src));
	296	fl_set_key_val(tb, &key->tp.dst, TCA_FLOWER_KEY_UDP_DST,
	297	&mask->tp.dst, TCA_FLOWER_UNSPEC,
	298	sizeof(key->tp.dst));
	299	}
	300
	301	return 0;
	302	}
	303
	304	static bool fl_mask_eq(struct fl_flow_mask *mask1,
	305	struct fl_flow_mask *mask2)
	306	{
	307	const long *lmask1 = fl_key_get_start(&mask1->key, mask1);
	308	const long *lmask2 = fl_key_get_start(&mask2->key, mask2);
	309
	310	return !memcmp(&mask1->range, &mask2->range, sizeof(mask1->range)) &&
	311	!memcmp(lmask1, lmask2, fl_mask_range(mask1));
	312	}
	313
	314	static const struct rhashtable_params fl_ht_params = {
	315	.key_offset = offsetof(struct cls_fl_filter, mkey), /* base offset */
	316	.head_offset = offsetof(struct cls_fl_filter, ht_node),
	317	.automatic_shrinking = true,
	318	};
	319
	320	static int fl_init_hashtable(struct cls_fl_head *head,
	321	struct fl_flow_mask *mask)
	322	{
	323	head->ht_params = fl_ht_params;
	324	head->ht_params.key_len = fl_mask_range(mask);
	325	head->ht_params.key_offset += mask->range.start;
	326
	327	return rhashtable_init(&head->ht, &head->ht_params);
	328	}
	329
	330	#define FL_KEY_MEMBER_OFFSET(member) offsetof(struct fl_flow_key, member)
	331	#define FL_KEY_MEMBER_SIZE(member) (sizeof(((struct fl_flow_key *) 0)->member))
	332	#define FL_KEY_MEMBER_END_OFFSET(member) \
	333	(FL_KEY_MEMBER_OFFSET(member) + FL_KEY_MEMBER_SIZE(member))
	334
	335	#define FL_KEY_IN_RANGE(mask, member) \
	336	(FL_KEY_MEMBER_OFFSET(member) <= (mask)->range.end && \
	337	FL_KEY_MEMBER_END_OFFSET(member) >= (mask)->range.start)
	338
	339	#define FL_KEY_SET(keys, cnt, id, member) \
	340	do { \
	341	keys[cnt].key_id = id; \
	342	keys[cnt].offset = FL_KEY_MEMBER_OFFSET(member); \
	343	cnt++; \
	344	} while(0);
	345
	346	#define FL_KEY_SET_IF_IN_RANGE(mask, keys, cnt, id, member) \
	347	do { \
	348	if (FL_KEY_IN_RANGE(mask, member)) \
349	FL_KEY_SET(keys, cnt, id, member); \
350	} while(0);
351
352	static void fl_init_dissector(struct cls_fl_head *head,
353	struct fl_flow_mask *mask)
354	{
355	struct flow_dissector_key keys[FLOW_DISSECTOR_KEY_MAX];
356	size_t cnt = 0;
357
42aecaa9	358	FL_KEY_SET(keys, cnt, FLOW_DISSECTOR_KEY_CONTROL, control);
77b9900e JP	359	FL_KEY_SET(keys, cnt, FLOW_DISSECTOR_KEY_BASIC, basic);
	360	FL_KEY_SET_IF_IN_RANGE(mask, keys, cnt,
	361	FLOW_DISSECTOR_KEY_ETH_ADDRS, eth);
	362	FL_KEY_SET_IF_IN_RANGE(mask, keys, cnt,
	363	FLOW_DISSECTOR_KEY_IPV4_ADDRS, ipv4);
	364	FL_KEY_SET_IF_IN_RANGE(mask, keys, cnt,
	365	FLOW_DISSECTOR_KEY_IPV6_ADDRS, ipv6);
	366	FL_KEY_SET_IF_IN_RANGE(mask, keys, cnt,
	367	FLOW_DISSECTOR_KEY_PORTS, tp);
	368
	369	skb_flow_dissector_init(&head->dissector, keys, cnt);
	370	}
	371
	372	static int fl_check_assign_mask(struct cls_fl_head *head,
	373	struct fl_flow_mask *mask)
	374	{
	375	int err;
	376
	377	if (head->mask_assigned) {
	378	if (!fl_mask_eq(&head->mask, mask))
	379	return -EINVAL;
	380	else
	381	return 0;
	382	}
	383
	384	/* Mask is not assigned yet. So assign it and init hashtable
	385	* according to that.
	386	*/
	387	err = fl_init_hashtable(head, mask);
	388	if (err)
	389	return err;
	390	memcpy(&head->mask, mask, sizeof(head->mask));
	391	head->mask_assigned = true;
	392
	393	fl_init_dissector(head, mask);
	394
	395	return 0;
	396	}
	397
	398	static int fl_set_parms(struct net net, struct tcf_proto tp,
	399	struct cls_fl_filter f, struct fl_flow_mask mask,
	400	unsigned long base, struct nlattr **tb,
	401	struct nlattr *est, bool ovr)
	402	{
	403	struct tcf_exts e;
	404	int err;
	405
	406	tcf_exts_init(&e, TCA_FLOWER_ACT, 0);
	407	err = tcf_exts_validate(net, tp, tb, est, &e, ovr);
	408	if (err < 0)
	409	return err;
	410
	411	if (tb[TCA_FLOWER_CLASSID]) {
	412	f->res.classid = nla_get_u32(tb[TCA_FLOWER_CLASSID]);
	413	tcf_bind_filter(tp, &f->res, base);
	414	}
	415
	416	err = fl_set_key(net, tb, &f->key, &mask->key);
	417	if (err)
	418	goto errout;
	419
	420	fl_mask_update_range(mask);
	421	fl_set_masked_key(&f->mkey, &f->key, mask);
	422
423	tcf_exts_change(tp, &f->exts, &e);
424
425	return 0;
426	errout:
427	tcf_exts_destroy(&e);
428	return err;
429	}
430
431	static u32 fl_grab_new_handle(struct tcf_proto *tp,
432	struct cls_fl_head *head)
433	{
434	unsigned int i = 0x80000000;
435	u32 handle;
436
437	do {
438	if (++head->hgen == 0x7FFFFFFF)
439	head->hgen = 1;
440	} while (--i > 0 && fl_get(tp, head->hgen));
441
442	if (unlikely(i == 0)) {
443	pr_err("Insufficient number of handles\n");
444	handle = 0;
445	} else {
446	handle = head->hgen;
447	}
448
449	return handle;
450	}
451
452	static int fl_change(struct net net, struct sk_buff in_skb,
453	struct tcf_proto *tp, unsigned long base,
454	u32 handle, struct nlattr **tca,
455	unsigned long *arg, bool ovr)
456	{
457	struct cls_fl_head *head = rtnl_dereference(tp->root);
458	struct cls_fl_filter fold = (struct cls_fl_filter ) *arg;
459	struct cls_fl_filter *fnew;
460	struct nlattr *tb[TCA_FLOWER_MAX + 1];
461	struct fl_flow_mask mask = {};
462	int err;
463
464	if (!tca[TCA_OPTIONS])
465	return -EINVAL;
466
467	err = nla_parse_nested(tb, TCA_FLOWER_MAX, tca[TCA_OPTIONS], fl_policy);
468	if (err < 0)
469	return err;
470
471	if (fold && handle && fold->handle != handle)
472	return -EINVAL;
473
474	fnew = kzalloc(sizeof(*fnew), GFP_KERNEL);
475	if (!fnew)
476	return -ENOBUFS;
477
478	tcf_exts_init(&fnew->exts, TCA_FLOWER_ACT, 0);
479
480	if (!handle) {
481	handle = fl_grab_new_handle(tp, head);
482	if (!handle) {
483	err = -EINVAL;
484	goto errout;
485	}
486	}
487	fnew->handle = handle;
488
489	err = fl_set_parms(net, tp, fnew, &mask, base, tb, tca[TCA_RATE], ovr);
490	if (err)
491	goto errout;
492
493	err = fl_check_assign_mask(head, &mask);
494	if (err)
495	goto errout;
496
497	err = rhashtable_insert_fast(&head->ht, &fnew->ht_node,
498	head->ht_params);
499	if (err)
500	goto errout;
501	if (fold)
502	rhashtable_remove_fast(&head->ht, &fold->ht_node,
503	head->ht_params);
504
505	*arg = (unsigned long) fnew;
506
507	if (fold) {
ff3532f2	508	list_replace_rcu(&fold->list, &fnew->list);
77b9900e JP	509	tcf_unbind_filter(tp, &fold->res);
	510	call_rcu(&fold->rcu, fl_destroy_filter);
	511	} else {
	512	list_add_tail_rcu(&fnew->list, &head->filters);
	513	}
	514
	515	return 0;
	516
	517	errout:
	518	kfree(fnew);
	519	return err;
	520	}
	521
	522	static int fl_delete(struct tcf_proto *tp, unsigned long arg)
	523	{
	524	struct cls_fl_head *head = rtnl_dereference(tp->root);
	525	struct cls_fl_filter f = (struct cls_fl_filter ) arg;
	526
	527	rhashtable_remove_fast(&head->ht, &f->ht_node,
	528	head->ht_params);
	529	list_del_rcu(&f->list);
	530	tcf_unbind_filter(tp, &f->res);
	531	call_rcu(&f->rcu, fl_destroy_filter);
	532	return 0;
	533	}
	534
	535	static void fl_walk(struct tcf_proto tp, struct tcf_walker arg)
	536	{
	537	struct cls_fl_head *head = rtnl_dereference(tp->root);
	538	struct cls_fl_filter *f;
	539
	540	list_for_each_entry_rcu(f, &head->filters, list) {
	541	if (arg->count < arg->skip)
	542	goto skip;
	543	if (arg->fn(tp, (unsigned long) f, arg) < 0) {
	544	arg->stop = 1;
	545	break;
	546	}
	547	skip:
	548	arg->count++;
	549	}
	550	}
	551
	552	static int fl_dump_key_val(struct sk_buff *skb,
	553	void *val, int val_type,
	554	void *mask, int mask_type, int len)
	555	{
	556	int err;
	557
	558	if (!memchr_inv(mask, 0, len))
	559	return 0;
	560	err = nla_put(skb, val_type, len, val);
	561	if (err)
	562	return err;
	563	if (mask_type != TCA_FLOWER_UNSPEC) {
	564	err = nla_put(skb, mask_type, len, mask);
	565	if (err)
	566	return err;
	567	}
	568	return 0;
	569	}
	570
	571	static int fl_dump(struct net net, struct tcf_proto tp, unsigned long fh,
	572	struct sk_buff skb, struct tcmsg t)
573	{
574	struct cls_fl_head *head = rtnl_dereference(tp->root);
575	struct cls_fl_filter f = (struct cls_fl_filter ) fh;
576	struct nlattr *nest;
577	struct fl_flow_key key, mask;
578
579	if (!f)
580	return skb->len;
581
582	t->tcm_handle = f->handle;
583
584	nest = nla_nest_start(skb, TCA_OPTIONS);
585	if (!nest)
586	goto nla_put_failure;
587
588	if (f->res.classid &&
589	nla_put_u32(skb, TCA_FLOWER_CLASSID, f->res.classid))
590	goto nla_put_failure;
591
592	key = &f->key;
593	mask = &head->mask.key;
594
595	if (mask->indev_ifindex) {
596	struct net_device *dev;
597
598	dev = __dev_get_by_index(net, key->indev_ifindex);
599	if (dev && nla_put_string(skb, TCA_FLOWER_INDEV, dev->name))
600	goto nla_put_failure;
601	}
602
603	if (fl_dump_key_val(skb, key->eth.dst, TCA_FLOWER_KEY_ETH_DST,
604	mask->eth.dst, TCA_FLOWER_KEY_ETH_DST_MASK,
605	sizeof(key->eth.dst)) \|\|
606	fl_dump_key_val(skb, key->eth.src, TCA_FLOWER_KEY_ETH_SRC,
607	mask->eth.src, TCA_FLOWER_KEY_ETH_SRC_MASK,
608	sizeof(key->eth.src)) \|\|
609	fl_dump_key_val(skb, &key->basic.n_proto, TCA_FLOWER_KEY_ETH_TYPE,
610	&mask->basic.n_proto, TCA_FLOWER_UNSPEC,
611	sizeof(key->basic.n_proto)))
612	goto nla_put_failure;
613	if ((key->basic.n_proto == htons(ETH_P_IP) \|\|
614	key->basic.n_proto == htons(ETH_P_IPV6)) &&
615	fl_dump_key_val(skb, &key->basic.ip_proto, TCA_FLOWER_KEY_IP_PROTO,
616	&mask->basic.ip_proto, TCA_FLOWER_UNSPEC,
617	sizeof(key->basic.ip_proto)))
618	goto nla_put_failure;
619
c3f83241	620	if (key->control.addr_type == FLOW_DISSECTOR_KEY_IPV4_ADDRS &&
77b9900e JP	621	(fl_dump_key_val(skb, &key->ipv4.src, TCA_FLOWER_KEY_IPV4_SRC,
	622	&mask->ipv4.src, TCA_FLOWER_KEY_IPV4_SRC_MASK,
	623	sizeof(key->ipv4.src)) \|\|
	624	fl_dump_key_val(skb, &key->ipv4.dst, TCA_FLOWER_KEY_IPV4_DST,
	625	&mask->ipv4.dst, TCA_FLOWER_KEY_IPV4_DST_MASK,
	626	sizeof(key->ipv4.dst))))
	627	goto nla_put_failure;
c3f83241	628	else if (key->control.addr_type == FLOW_DISSECTOR_KEY_IPV6_ADDRS &&
77b9900e JP	629	(fl_dump_key_val(skb, &key->ipv6.src, TCA_FLOWER_KEY_IPV6_SRC,
	630	&mask->ipv6.src, TCA_FLOWER_KEY_IPV6_SRC_MASK,
	631	sizeof(key->ipv6.src)) \|\|
	632	fl_dump_key_val(skb, &key->ipv6.dst, TCA_FLOWER_KEY_IPV6_DST,
	633	&mask->ipv6.dst, TCA_FLOWER_KEY_IPV6_DST_MASK,
	634	sizeof(key->ipv6.dst))))
	635	goto nla_put_failure;
	636
	637	if (key->basic.ip_proto == IPPROTO_TCP &&
	638	(fl_dump_key_val(skb, &key->tp.src, TCA_FLOWER_KEY_TCP_SRC,
	639	&mask->tp.src, TCA_FLOWER_UNSPEC,
	640	sizeof(key->tp.src)) \|\|
	641	fl_dump_key_val(skb, &key->tp.dst, TCA_FLOWER_KEY_TCP_DST,
	642	&mask->tp.dst, TCA_FLOWER_UNSPEC,
	643	sizeof(key->tp.dst))))
	644	goto nla_put_failure;
	645	else if (key->basic.ip_proto == IPPROTO_UDP &&
	646	(fl_dump_key_val(skb, &key->tp.src, TCA_FLOWER_KEY_UDP_SRC,
	647	&mask->tp.src, TCA_FLOWER_UNSPEC,
	648	sizeof(key->tp.src)) \|\|
	649	fl_dump_key_val(skb, &key->tp.dst, TCA_FLOWER_KEY_UDP_DST,
	650	&mask->tp.dst, TCA_FLOWER_UNSPEC,
	651	sizeof(key->tp.dst))))
	652	goto nla_put_failure;
	653
	654	if (tcf_exts_dump(skb, &f->exts))
	655	goto nla_put_failure;
	656
	657	nla_nest_end(skb, nest);
	658
	659	if (tcf_exts_dump_stats(skb, &f->exts) < 0)
	660	goto nla_put_failure;
	661
	662	return skb->len;
	663
	664	nla_put_failure:
	665	nla_nest_cancel(skb, nest);
	666	return -1;
	667	}
	668
	669	static struct tcf_proto_ops cls_fl_ops __read_mostly = {
	670	.kind = "flower",
	671	.classify = fl_classify,
	672	.init = fl_init,
	673	.destroy = fl_destroy,
	674	.get = fl_get,
	675	.change = fl_change,
	676	.delete = fl_delete,
	677	.walk = fl_walk,
	678	.dump = fl_dump,
	679	.owner = THIS_MODULE,
	680	};
	681
	682	static int __init cls_fl_init(void)
	683	{
	684	return register_tcf_proto_ops(&cls_fl_ops);
	685	}
	686
	687	static void __exit cls_fl_exit(void)
	688	{
	689	unregister_tcf_proto_ops(&cls_fl_ops);
	690	}
	691
	692	module_init(cls_fl_init);
693	module_exit(cls_fl_exit);
694
695	MODULE_AUTHOR("Jiri Pirko <jiri@resnulli.us>");
696	MODULE_DESCRIPTION("Flower classifier");
697	MODULE_LICENSE("GPL v2");