 7801db8aec
			
		
	
	
	7801db8aec
	
	
	
		
			
			When kernel generates a handle for a u32 filter, it tries to start from the max in the bucket. So when we have a filter with the max (fff) handle, it will cause kernel always generates the same handle for new filters. This can be shown by the following command: tc qdisc add dev eth0 ingress tc filter add dev eth0 parent ffff: protocol ip pref 770 handle 800::fff u32 match ip protocol 1 0xff tc filter add dev eth0 parent ffff: protocol ip pref 770 u32 match ip protocol 1 0xff ... we will get some u32 filters with same handle: # tc filter show dev eth0 parent ffff: filter protocol ip pref 770 u32 filter protocol ip pref 770 u32 fh 800: ht divisor 1 filter protocol ip pref 770 u32 fh 800::fff order 4095 key ht 800 bkt 0 match 00010000/00ff0000 at 8 filter protocol ip pref 770 u32 fh 800::fff order 4095 key ht 800 bkt 0 match 00010000/00ff0000 at 8 filter protocol ip pref 770 u32 fh 800::fff order 4095 key ht 800 bkt 0 match 00010000/00ff0000 at 8 filter protocol ip pref 770 u32 fh 800::fff order 4095 key ht 800 bkt 0 match 00010000/00ff0000 at 8 handles should be unique. This patch fixes it by looking up a bitmap, so that can guarantee the handle is as unique as possible. For compatibility, we still start from 0x800. Cc: "David S. Miller" <davem@davemloft.net> Signed-off-by: Cong Wang <cwang@twopensource.com> Signed-off-by: Cong Wang <xiyou.wangcong@gmail.com> Signed-off-by: Jamal Hadi Salim <jhs@mojatatu.com> Signed-off-by: David S. Miller <davem@davemloft.net>
		
			
				
	
	
		
			837 lines
		
	
	
	
		
			17 KiB
			
		
	
	
	
		
			C
		
	
	
	
	
	
			
		
		
	
	
			837 lines
		
	
	
	
		
			17 KiB
			
		
	
	
	
		
			C
		
	
	
	
	
	
| /*
 | |
|  * net/sched/cls_u32.c	Ugly (or Universal) 32bit key Packet Classifier.
 | |
|  *
 | |
|  *		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.
 | |
|  *
 | |
|  * Authors:	Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru>
 | |
|  *
 | |
|  *	The filters are packed to hash tables of key nodes
 | |
|  *	with a set of 32bit key/mask pairs at every node.
 | |
|  *	Nodes reference next level hash tables etc.
 | |
|  *
 | |
|  *	This scheme is the best universal classifier I managed to
 | |
|  *	invent; it is not super-fast, but it is not slow (provided you
 | |
|  *	program it correctly), and general enough.  And its relative
 | |
|  *	speed grows as the number of rules becomes larger.
 | |
|  *
 | |
|  *	It seems that it represents the best middle point between
 | |
|  *	speed and manageability both by human and by machine.
 | |
|  *
 | |
|  *	It is especially useful for link sharing combined with QoS;
 | |
|  *	pure RSVP doesn't need such a general approach and can use
 | |
|  *	much simpler (and faster) schemes, sort of cls_rsvp.c.
 | |
|  *
 | |
|  *	JHS: We should remove the CONFIG_NET_CLS_IND from here
 | |
|  *	eventually when the meta match extension is made available
 | |
|  *
 | |
|  *	nfmark match added by Catalin(ux aka Dino) BOIE <catab at umbrella.ro>
 | |
|  */
 | |
| 
 | |
| #include <linux/module.h>
 | |
| #include <linux/slab.h>
 | |
| #include <linux/types.h>
 | |
| #include <linux/kernel.h>
 | |
| #include <linux/string.h>
 | |
| #include <linux/errno.h>
 | |
| #include <linux/rtnetlink.h>
 | |
| #include <linux/skbuff.h>
 | |
| #include <linux/bitmap.h>
 | |
| #include <net/netlink.h>
 | |
| #include <net/act_api.h>
 | |
| #include <net/pkt_cls.h>
 | |
| 
 | |
| struct tc_u_knode {
 | |
| 	struct tc_u_knode	*next;
 | |
| 	u32			handle;
 | |
| 	struct tc_u_hnode	*ht_up;
 | |
| 	struct tcf_exts		exts;
 | |
| #ifdef CONFIG_NET_CLS_IND
 | |
| 	int			ifindex;
 | |
| #endif
 | |
| 	u8			fshift;
 | |
| 	struct tcf_result	res;
 | |
| 	struct tc_u_hnode	*ht_down;
 | |
| #ifdef CONFIG_CLS_U32_PERF
 | |
| 	struct tc_u32_pcnt	*pf;
 | |
| #endif
 | |
| #ifdef CONFIG_CLS_U32_MARK
 | |
| 	struct tc_u32_mark	mark;
 | |
| #endif
 | |
| 	struct tc_u32_sel	sel;
 | |
| };
 | |
| 
 | |
| struct tc_u_hnode {
 | |
| 	struct tc_u_hnode	*next;
 | |
| 	u32			handle;
 | |
| 	u32			prio;
 | |
| 	struct tc_u_common	*tp_c;
 | |
| 	int			refcnt;
 | |
| 	unsigned int		divisor;
 | |
| 	struct tc_u_knode	*ht[1];
 | |
| };
 | |
| 
 | |
| struct tc_u_common {
 | |
| 	struct tc_u_hnode	*hlist;
 | |
| 	struct Qdisc		*q;
 | |
| 	int			refcnt;
 | |
| 	u32			hgenerator;
 | |
| };
 | |
| 
 | |
| static inline unsigned int u32_hash_fold(__be32 key,
 | |
| 					 const struct tc_u32_sel *sel,
 | |
| 					 u8 fshift)
 | |
| {
 | |
| 	unsigned int h = ntohl(key & sel->hmask) >> fshift;
 | |
| 
 | |
| 	return h;
 | |
| }
 | |
| 
 | |
| static int u32_classify(struct sk_buff *skb, const struct tcf_proto *tp, struct tcf_result *res)
 | |
| {
 | |
| 	struct {
 | |
| 		struct tc_u_knode *knode;
 | |
| 		unsigned int	  off;
 | |
| 	} stack[TC_U32_MAXDEPTH];
 | |
| 
 | |
| 	struct tc_u_hnode *ht = tp->root;
 | |
| 	unsigned int off = skb_network_offset(skb);
 | |
| 	struct tc_u_knode *n;
 | |
| 	int sdepth = 0;
 | |
| 	int off2 = 0;
 | |
| 	int sel = 0;
 | |
| #ifdef CONFIG_CLS_U32_PERF
 | |
| 	int j;
 | |
| #endif
 | |
| 	int i, r;
 | |
| 
 | |
| next_ht:
 | |
| 	n = ht->ht[sel];
 | |
| 
 | |
| next_knode:
 | |
| 	if (n) {
 | |
| 		struct tc_u32_key *key = n->sel.keys;
 | |
| 
 | |
| #ifdef CONFIG_CLS_U32_PERF
 | |
| 		n->pf->rcnt += 1;
 | |
| 		j = 0;
 | |
| #endif
 | |
| 
 | |
| #ifdef CONFIG_CLS_U32_MARK
 | |
| 		if ((skb->mark & n->mark.mask) != n->mark.val) {
 | |
| 			n = n->next;
 | |
| 			goto next_knode;
 | |
| 		} else {
 | |
| 			n->mark.success++;
 | |
| 		}
 | |
| #endif
 | |
| 
 | |
| 		for (i = n->sel.nkeys; i > 0; i--, key++) {
 | |
| 			int toff = off + key->off + (off2 & key->offmask);
 | |
| 			__be32 *data, hdata;
 | |
| 
 | |
| 			if (skb_headroom(skb) + toff > INT_MAX)
 | |
| 				goto out;
 | |
| 
 | |
| 			data = skb_header_pointer(skb, toff, 4, &hdata);
 | |
| 			if (!data)
 | |
| 				goto out;
 | |
| 			if ((*data ^ key->val) & key->mask) {
 | |
| 				n = n->next;
 | |
| 				goto next_knode;
 | |
| 			}
 | |
| #ifdef CONFIG_CLS_U32_PERF
 | |
| 			n->pf->kcnts[j] += 1;
 | |
| 			j++;
 | |
| #endif
 | |
| 		}
 | |
| 		if (n->ht_down == NULL) {
 | |
| check_terminal:
 | |
| 			if (n->sel.flags & TC_U32_TERMINAL) {
 | |
| 
 | |
| 				*res = n->res;
 | |
| #ifdef CONFIG_NET_CLS_IND
 | |
| 				if (!tcf_match_indev(skb, n->ifindex)) {
 | |
| 					n = n->next;
 | |
| 					goto next_knode;
 | |
| 				}
 | |
| #endif
 | |
| #ifdef CONFIG_CLS_U32_PERF
 | |
| 				n->pf->rhit += 1;
 | |
| #endif
 | |
| 				r = tcf_exts_exec(skb, &n->exts, res);
 | |
| 				if (r < 0) {
 | |
| 					n = n->next;
 | |
| 					goto next_knode;
 | |
| 				}
 | |
| 
 | |
| 				return r;
 | |
| 			}
 | |
| 			n = n->next;
 | |
| 			goto next_knode;
 | |
| 		}
 | |
| 
 | |
| 		/* PUSH */
 | |
| 		if (sdepth >= TC_U32_MAXDEPTH)
 | |
| 			goto deadloop;
 | |
| 		stack[sdepth].knode = n;
 | |
| 		stack[sdepth].off = off;
 | |
| 		sdepth++;
 | |
| 
 | |
| 		ht = n->ht_down;
 | |
| 		sel = 0;
 | |
| 		if (ht->divisor) {
 | |
| 			__be32 *data, hdata;
 | |
| 
 | |
| 			data = skb_header_pointer(skb, off + n->sel.hoff, 4,
 | |
| 						  &hdata);
 | |
| 			if (!data)
 | |
| 				goto out;
 | |
| 			sel = ht->divisor & u32_hash_fold(*data, &n->sel,
 | |
| 							  n->fshift);
 | |
| 		}
 | |
| 		if (!(n->sel.flags & (TC_U32_VAROFFSET | TC_U32_OFFSET | TC_U32_EAT)))
 | |
| 			goto next_ht;
 | |
| 
 | |
| 		if (n->sel.flags & (TC_U32_OFFSET | TC_U32_VAROFFSET)) {
 | |
| 			off2 = n->sel.off + 3;
 | |
| 			if (n->sel.flags & TC_U32_VAROFFSET) {
 | |
| 				__be16 *data, hdata;
 | |
| 
 | |
| 				data = skb_header_pointer(skb,
 | |
| 							  off + n->sel.offoff,
 | |
| 							  2, &hdata);
 | |
| 				if (!data)
 | |
| 					goto out;
 | |
| 				off2 += ntohs(n->sel.offmask & *data) >>
 | |
| 					n->sel.offshift;
 | |
| 			}
 | |
| 			off2 &= ~3;
 | |
| 		}
 | |
| 		if (n->sel.flags & TC_U32_EAT) {
 | |
| 			off += off2;
 | |
| 			off2 = 0;
 | |
| 		}
 | |
| 
 | |
| 		if (off < skb->len)
 | |
| 			goto next_ht;
 | |
| 	}
 | |
| 
 | |
| 	/* POP */
 | |
| 	if (sdepth--) {
 | |
| 		n = stack[sdepth].knode;
 | |
| 		ht = n->ht_up;
 | |
| 		off = stack[sdepth].off;
 | |
| 		goto check_terminal;
 | |
| 	}
 | |
| out:
 | |
| 	return -1;
 | |
| 
 | |
| deadloop:
 | |
| 	net_warn_ratelimited("cls_u32: dead loop\n");
 | |
| 	return -1;
 | |
| }
 | |
| 
 | |
| static struct tc_u_hnode *
 | |
| u32_lookup_ht(struct tc_u_common *tp_c, u32 handle)
 | |
| {
 | |
| 	struct tc_u_hnode *ht;
 | |
| 
 | |
| 	for (ht = tp_c->hlist; ht; ht = ht->next)
 | |
| 		if (ht->handle == handle)
 | |
| 			break;
 | |
| 
 | |
| 	return ht;
 | |
| }
 | |
| 
 | |
| static struct tc_u_knode *
 | |
| u32_lookup_key(struct tc_u_hnode *ht, u32 handle)
 | |
| {
 | |
| 	unsigned int sel;
 | |
| 	struct tc_u_knode *n = NULL;
 | |
| 
 | |
| 	sel = TC_U32_HASH(handle);
 | |
| 	if (sel > ht->divisor)
 | |
| 		goto out;
 | |
| 
 | |
| 	for (n = ht->ht[sel]; n; n = n->next)
 | |
| 		if (n->handle == handle)
 | |
| 			break;
 | |
| out:
 | |
| 	return n;
 | |
| }
 | |
| 
 | |
| 
 | |
| static unsigned long u32_get(struct tcf_proto *tp, u32 handle)
 | |
| {
 | |
| 	struct tc_u_hnode *ht;
 | |
| 	struct tc_u_common *tp_c = tp->data;
 | |
| 
 | |
| 	if (TC_U32_HTID(handle) == TC_U32_ROOT)
 | |
| 		ht = tp->root;
 | |
| 	else
 | |
| 		ht = u32_lookup_ht(tp_c, TC_U32_HTID(handle));
 | |
| 
 | |
| 	if (!ht)
 | |
| 		return 0;
 | |
| 
 | |
| 	if (TC_U32_KEY(handle) == 0)
 | |
| 		return (unsigned long)ht;
 | |
| 
 | |
| 	return (unsigned long)u32_lookup_key(ht, handle);
 | |
| }
 | |
| 
 | |
| static void u32_put(struct tcf_proto *tp, unsigned long f)
 | |
| {
 | |
| }
 | |
| 
 | |
| static u32 gen_new_htid(struct tc_u_common *tp_c)
 | |
| {
 | |
| 	int i = 0x800;
 | |
| 
 | |
| 	do {
 | |
| 		if (++tp_c->hgenerator == 0x7FF)
 | |
| 			tp_c->hgenerator = 1;
 | |
| 	} while (--i > 0 && u32_lookup_ht(tp_c, (tp_c->hgenerator|0x800)<<20));
 | |
| 
 | |
| 	return i > 0 ? (tp_c->hgenerator|0x800)<<20 : 0;
 | |
| }
 | |
| 
 | |
| static int u32_init(struct tcf_proto *tp)
 | |
| {
 | |
| 	struct tc_u_hnode *root_ht;
 | |
| 	struct tc_u_common *tp_c;
 | |
| 
 | |
| 	tp_c = tp->q->u32_node;
 | |
| 
 | |
| 	root_ht = kzalloc(sizeof(*root_ht), GFP_KERNEL);
 | |
| 	if (root_ht == NULL)
 | |
| 		return -ENOBUFS;
 | |
| 
 | |
| 	root_ht->divisor = 0;
 | |
| 	root_ht->refcnt++;
 | |
| 	root_ht->handle = tp_c ? gen_new_htid(tp_c) : 0x80000000;
 | |
| 	root_ht->prio = tp->prio;
 | |
| 
 | |
| 	if (tp_c == NULL) {
 | |
| 		tp_c = kzalloc(sizeof(*tp_c), GFP_KERNEL);
 | |
| 		if (tp_c == NULL) {
 | |
| 			kfree(root_ht);
 | |
| 			return -ENOBUFS;
 | |
| 		}
 | |
| 		tp_c->q = tp->q;
 | |
| 		tp->q->u32_node = tp_c;
 | |
| 	}
 | |
| 
 | |
| 	tp_c->refcnt++;
 | |
| 	root_ht->next = tp_c->hlist;
 | |
| 	tp_c->hlist = root_ht;
 | |
| 	root_ht->tp_c = tp_c;
 | |
| 
 | |
| 	tp->root = root_ht;
 | |
| 	tp->data = tp_c;
 | |
| 	return 0;
 | |
| }
 | |
| 
 | |
| static int u32_destroy_key(struct tcf_proto *tp, struct tc_u_knode *n)
 | |
| {
 | |
| 	tcf_unbind_filter(tp, &n->res);
 | |
| 	tcf_exts_destroy(tp, &n->exts);
 | |
| 	if (n->ht_down)
 | |
| 		n->ht_down->refcnt--;
 | |
| #ifdef CONFIG_CLS_U32_PERF
 | |
| 	kfree(n->pf);
 | |
| #endif
 | |
| 	kfree(n);
 | |
| 	return 0;
 | |
| }
 | |
| 
 | |
| static int u32_delete_key(struct tcf_proto *tp, struct tc_u_knode *key)
 | |
| {
 | |
| 	struct tc_u_knode **kp;
 | |
| 	struct tc_u_hnode *ht = key->ht_up;
 | |
| 
 | |
| 	if (ht) {
 | |
| 		for (kp = &ht->ht[TC_U32_HASH(key->handle)]; *kp; kp = &(*kp)->next) {
 | |
| 			if (*kp == key) {
 | |
| 				tcf_tree_lock(tp);
 | |
| 				*kp = key->next;
 | |
| 				tcf_tree_unlock(tp);
 | |
| 
 | |
| 				u32_destroy_key(tp, key);
 | |
| 				return 0;
 | |
| 			}
 | |
| 		}
 | |
| 	}
 | |
| 	WARN_ON(1);
 | |
| 	return 0;
 | |
| }
 | |
| 
 | |
| static void u32_clear_hnode(struct tcf_proto *tp, struct tc_u_hnode *ht)
 | |
| {
 | |
| 	struct tc_u_knode *n;
 | |
| 	unsigned int h;
 | |
| 
 | |
| 	for (h = 0; h <= ht->divisor; h++) {
 | |
| 		while ((n = ht->ht[h]) != NULL) {
 | |
| 			ht->ht[h] = n->next;
 | |
| 
 | |
| 			u32_destroy_key(tp, n);
 | |
| 		}
 | |
| 	}
 | |
| }
 | |
| 
 | |
| static int u32_destroy_hnode(struct tcf_proto *tp, struct tc_u_hnode *ht)
 | |
| {
 | |
| 	struct tc_u_common *tp_c = tp->data;
 | |
| 	struct tc_u_hnode **hn;
 | |
| 
 | |
| 	WARN_ON(ht->refcnt);
 | |
| 
 | |
| 	u32_clear_hnode(tp, ht);
 | |
| 
 | |
| 	for (hn = &tp_c->hlist; *hn; hn = &(*hn)->next) {
 | |
| 		if (*hn == ht) {
 | |
| 			*hn = ht->next;
 | |
| 			kfree(ht);
 | |
| 			return 0;
 | |
| 		}
 | |
| 	}
 | |
| 
 | |
| 	WARN_ON(1);
 | |
| 	return -ENOENT;
 | |
| }
 | |
| 
 | |
| static void u32_destroy(struct tcf_proto *tp)
 | |
| {
 | |
| 	struct tc_u_common *tp_c = tp->data;
 | |
| 	struct tc_u_hnode *root_ht = tp->root;
 | |
| 
 | |
| 	WARN_ON(root_ht == NULL);
 | |
| 
 | |
| 	if (root_ht && --root_ht->refcnt == 0)
 | |
| 		u32_destroy_hnode(tp, root_ht);
 | |
| 
 | |
| 	if (--tp_c->refcnt == 0) {
 | |
| 		struct tc_u_hnode *ht;
 | |
| 
 | |
| 		tp->q->u32_node = NULL;
 | |
| 
 | |
| 		for (ht = tp_c->hlist; ht; ht = ht->next) {
 | |
| 			ht->refcnt--;
 | |
| 			u32_clear_hnode(tp, ht);
 | |
| 		}
 | |
| 
 | |
| 		while ((ht = tp_c->hlist) != NULL) {
 | |
| 			tp_c->hlist = ht->next;
 | |
| 
 | |
| 			WARN_ON(ht->refcnt != 0);
 | |
| 
 | |
| 			kfree(ht);
 | |
| 		}
 | |
| 
 | |
| 		kfree(tp_c);
 | |
| 	}
 | |
| 
 | |
| 	tp->data = NULL;
 | |
| }
 | |
| 
 | |
| static int u32_delete(struct tcf_proto *tp, unsigned long arg)
 | |
| {
 | |
| 	struct tc_u_hnode *ht = (struct tc_u_hnode *)arg;
 | |
| 
 | |
| 	if (ht == NULL)
 | |
| 		return 0;
 | |
| 
 | |
| 	if (TC_U32_KEY(ht->handle))
 | |
| 		return u32_delete_key(tp, (struct tc_u_knode *)ht);
 | |
| 
 | |
| 	if (tp->root == ht)
 | |
| 		return -EINVAL;
 | |
| 
 | |
| 	if (ht->refcnt == 1) {
 | |
| 		ht->refcnt--;
 | |
| 		u32_destroy_hnode(tp, ht);
 | |
| 	} else {
 | |
| 		return -EBUSY;
 | |
| 	}
 | |
| 
 | |
| 	return 0;
 | |
| }
 | |
| 
 | |
| #define NR_U32_NODE (1<<12)
 | |
| static u32 gen_new_kid(struct tc_u_hnode *ht, u32 handle)
 | |
| {
 | |
| 	struct tc_u_knode *n;
 | |
| 	unsigned long i;
 | |
| 	unsigned long *bitmap = kzalloc(BITS_TO_LONGS(NR_U32_NODE) * sizeof(unsigned long),
 | |
| 					GFP_KERNEL);
 | |
| 	if (!bitmap)
 | |
| 		return handle | 0xFFF;
 | |
| 
 | |
| 	for (n = ht->ht[TC_U32_HASH(handle)]; n; n = n->next)
 | |
| 		set_bit(TC_U32_NODE(n->handle), bitmap);
 | |
| 
 | |
| 	i = find_next_zero_bit(bitmap, NR_U32_NODE, 0x800);
 | |
| 	if (i >= NR_U32_NODE)
 | |
| 		i = find_next_zero_bit(bitmap, NR_U32_NODE, 1);
 | |
| 
 | |
| 	kfree(bitmap);
 | |
| 	return handle | (i >= NR_U32_NODE ? 0xFFF : i);
 | |
| }
 | |
| 
 | |
| static const struct nla_policy u32_policy[TCA_U32_MAX + 1] = {
 | |
| 	[TCA_U32_CLASSID]	= { .type = NLA_U32 },
 | |
| 	[TCA_U32_HASH]		= { .type = NLA_U32 },
 | |
| 	[TCA_U32_LINK]		= { .type = NLA_U32 },
 | |
| 	[TCA_U32_DIVISOR]	= { .type = NLA_U32 },
 | |
| 	[TCA_U32_SEL]		= { .len = sizeof(struct tc_u32_sel) },
 | |
| 	[TCA_U32_INDEV]		= { .type = NLA_STRING, .len = IFNAMSIZ },
 | |
| 	[TCA_U32_MARK]		= { .len = sizeof(struct tc_u32_mark) },
 | |
| };
 | |
| 
 | |
| static int u32_set_parms(struct net *net, struct tcf_proto *tp,
 | |
| 			 unsigned long base, struct tc_u_hnode *ht,
 | |
| 			 struct tc_u_knode *n, struct nlattr **tb,
 | |
| 			 struct nlattr *est, bool ovr)
 | |
| {
 | |
| 	int err;
 | |
| 	struct tcf_exts e;
 | |
| 
 | |
| 	tcf_exts_init(&e, TCA_U32_ACT, TCA_U32_POLICE);
 | |
| 	err = tcf_exts_validate(net, tp, tb, est, &e, ovr);
 | |
| 	if (err < 0)
 | |
| 		return err;
 | |
| 
 | |
| 	err = -EINVAL;
 | |
| 	if (tb[TCA_U32_LINK]) {
 | |
| 		u32 handle = nla_get_u32(tb[TCA_U32_LINK]);
 | |
| 		struct tc_u_hnode *ht_down = NULL, *ht_old;
 | |
| 
 | |
| 		if (TC_U32_KEY(handle))
 | |
| 			goto errout;
 | |
| 
 | |
| 		if (handle) {
 | |
| 			ht_down = u32_lookup_ht(ht->tp_c, handle);
 | |
| 
 | |
| 			if (ht_down == NULL)
 | |
| 				goto errout;
 | |
| 			ht_down->refcnt++;
 | |
| 		}
 | |
| 
 | |
| 		tcf_tree_lock(tp);
 | |
| 		ht_old = n->ht_down;
 | |
| 		n->ht_down = ht_down;
 | |
| 		tcf_tree_unlock(tp);
 | |
| 
 | |
| 		if (ht_old)
 | |
| 			ht_old->refcnt--;
 | |
| 	}
 | |
| 	if (tb[TCA_U32_CLASSID]) {
 | |
| 		n->res.classid = nla_get_u32(tb[TCA_U32_CLASSID]);
 | |
| 		tcf_bind_filter(tp, &n->res, base);
 | |
| 	}
 | |
| 
 | |
| #ifdef CONFIG_NET_CLS_IND
 | |
| 	if (tb[TCA_U32_INDEV]) {
 | |
| 		int ret;
 | |
| 		ret = tcf_change_indev(net, tb[TCA_U32_INDEV]);
 | |
| 		if (ret < 0)
 | |
| 			goto errout;
 | |
| 		n->ifindex = ret;
 | |
| 	}
 | |
| #endif
 | |
| 	tcf_exts_change(tp, &n->exts, &e);
 | |
| 
 | |
| 	return 0;
 | |
| errout:
 | |
| 	tcf_exts_destroy(tp, &e);
 | |
| 	return err;
 | |
| }
 | |
| 
 | |
| static int u32_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 tc_u_common *tp_c = tp->data;
 | |
| 	struct tc_u_hnode *ht;
 | |
| 	struct tc_u_knode *n;
 | |
| 	struct tc_u32_sel *s;
 | |
| 	struct nlattr *opt = tca[TCA_OPTIONS];
 | |
| 	struct nlattr *tb[TCA_U32_MAX + 1];
 | |
| 	u32 htid;
 | |
| 	int err;
 | |
| 
 | |
| 	if (opt == NULL)
 | |
| 		return handle ? -EINVAL : 0;
 | |
| 
 | |
| 	err = nla_parse_nested(tb, TCA_U32_MAX, opt, u32_policy);
 | |
| 	if (err < 0)
 | |
| 		return err;
 | |
| 
 | |
| 	n = (struct tc_u_knode *)*arg;
 | |
| 	if (n) {
 | |
| 		if (TC_U32_KEY(n->handle) == 0)
 | |
| 			return -EINVAL;
 | |
| 
 | |
| 		return u32_set_parms(net, tp, base, n->ht_up, n, tb,
 | |
| 				     tca[TCA_RATE], ovr);
 | |
| 	}
 | |
| 
 | |
| 	if (tb[TCA_U32_DIVISOR]) {
 | |
| 		unsigned int divisor = nla_get_u32(tb[TCA_U32_DIVISOR]);
 | |
| 
 | |
| 		if (--divisor > 0x100)
 | |
| 			return -EINVAL;
 | |
| 		if (TC_U32_KEY(handle))
 | |
| 			return -EINVAL;
 | |
| 		if (handle == 0) {
 | |
| 			handle = gen_new_htid(tp->data);
 | |
| 			if (handle == 0)
 | |
| 				return -ENOMEM;
 | |
| 		}
 | |
| 		ht = kzalloc(sizeof(*ht) + divisor*sizeof(void *), GFP_KERNEL);
 | |
| 		if (ht == NULL)
 | |
| 			return -ENOBUFS;
 | |
| 		ht->tp_c = tp_c;
 | |
| 		ht->refcnt = 1;
 | |
| 		ht->divisor = divisor;
 | |
| 		ht->handle = handle;
 | |
| 		ht->prio = tp->prio;
 | |
| 		ht->next = tp_c->hlist;
 | |
| 		tp_c->hlist = ht;
 | |
| 		*arg = (unsigned long)ht;
 | |
| 		return 0;
 | |
| 	}
 | |
| 
 | |
| 	if (tb[TCA_U32_HASH]) {
 | |
| 		htid = nla_get_u32(tb[TCA_U32_HASH]);
 | |
| 		if (TC_U32_HTID(htid) == TC_U32_ROOT) {
 | |
| 			ht = tp->root;
 | |
| 			htid = ht->handle;
 | |
| 		} else {
 | |
| 			ht = u32_lookup_ht(tp->data, TC_U32_HTID(htid));
 | |
| 			if (ht == NULL)
 | |
| 				return -EINVAL;
 | |
| 		}
 | |
| 	} else {
 | |
| 		ht = tp->root;
 | |
| 		htid = ht->handle;
 | |
| 	}
 | |
| 
 | |
| 	if (ht->divisor < TC_U32_HASH(htid))
 | |
| 		return -EINVAL;
 | |
| 
 | |
| 	if (handle) {
 | |
| 		if (TC_U32_HTID(handle) && TC_U32_HTID(handle^htid))
 | |
| 			return -EINVAL;
 | |
| 		handle = htid | TC_U32_NODE(handle);
 | |
| 	} else
 | |
| 		handle = gen_new_kid(ht, htid);
 | |
| 
 | |
| 	if (tb[TCA_U32_SEL] == NULL)
 | |
| 		return -EINVAL;
 | |
| 
 | |
| 	s = nla_data(tb[TCA_U32_SEL]);
 | |
| 
 | |
| 	n = kzalloc(sizeof(*n) + s->nkeys*sizeof(struct tc_u32_key), GFP_KERNEL);
 | |
| 	if (n == NULL)
 | |
| 		return -ENOBUFS;
 | |
| 
 | |
| #ifdef CONFIG_CLS_U32_PERF
 | |
| 	n->pf = kzalloc(sizeof(struct tc_u32_pcnt) + s->nkeys*sizeof(u64), GFP_KERNEL);
 | |
| 	if (n->pf == NULL) {
 | |
| 		kfree(n);
 | |
| 		return -ENOBUFS;
 | |
| 	}
 | |
| #endif
 | |
| 
 | |
| 	memcpy(&n->sel, s, sizeof(*s) + s->nkeys*sizeof(struct tc_u32_key));
 | |
| 	n->ht_up = ht;
 | |
| 	n->handle = handle;
 | |
| 	n->fshift = s->hmask ? ffs(ntohl(s->hmask)) - 1 : 0;
 | |
| 	tcf_exts_init(&n->exts, TCA_U32_ACT, TCA_U32_POLICE);
 | |
| 
 | |
| #ifdef CONFIG_CLS_U32_MARK
 | |
| 	if (tb[TCA_U32_MARK]) {
 | |
| 		struct tc_u32_mark *mark;
 | |
| 
 | |
| 		mark = nla_data(tb[TCA_U32_MARK]);
 | |
| 		memcpy(&n->mark, mark, sizeof(struct tc_u32_mark));
 | |
| 		n->mark.success = 0;
 | |
| 	}
 | |
| #endif
 | |
| 
 | |
| 	err = u32_set_parms(net, tp, base, ht, n, tb, tca[TCA_RATE], ovr);
 | |
| 	if (err == 0) {
 | |
| 		struct tc_u_knode **ins;
 | |
| 		for (ins = &ht->ht[TC_U32_HASH(handle)]; *ins; ins = &(*ins)->next)
 | |
| 			if (TC_U32_NODE(handle) < TC_U32_NODE((*ins)->handle))
 | |
| 				break;
 | |
| 
 | |
| 		n->next = *ins;
 | |
| 		tcf_tree_lock(tp);
 | |
| 		*ins = n;
 | |
| 		tcf_tree_unlock(tp);
 | |
| 
 | |
| 		*arg = (unsigned long)n;
 | |
| 		return 0;
 | |
| 	}
 | |
| #ifdef CONFIG_CLS_U32_PERF
 | |
| 	kfree(n->pf);
 | |
| #endif
 | |
| 	kfree(n);
 | |
| 	return err;
 | |
| }
 | |
| 
 | |
| static void u32_walk(struct tcf_proto *tp, struct tcf_walker *arg)
 | |
| {
 | |
| 	struct tc_u_common *tp_c = tp->data;
 | |
| 	struct tc_u_hnode *ht;
 | |
| 	struct tc_u_knode *n;
 | |
| 	unsigned int h;
 | |
| 
 | |
| 	if (arg->stop)
 | |
| 		return;
 | |
| 
 | |
| 	for (ht = tp_c->hlist; ht; ht = ht->next) {
 | |
| 		if (ht->prio != tp->prio)
 | |
| 			continue;
 | |
| 		if (arg->count >= arg->skip) {
 | |
| 			if (arg->fn(tp, (unsigned long)ht, arg) < 0) {
 | |
| 				arg->stop = 1;
 | |
| 				return;
 | |
| 			}
 | |
| 		}
 | |
| 		arg->count++;
 | |
| 		for (h = 0; h <= ht->divisor; h++) {
 | |
| 			for (n = ht->ht[h]; n; n = n->next) {
 | |
| 				if (arg->count < arg->skip) {
 | |
| 					arg->count++;
 | |
| 					continue;
 | |
| 				}
 | |
| 				if (arg->fn(tp, (unsigned long)n, arg) < 0) {
 | |
| 					arg->stop = 1;
 | |
| 					return;
 | |
| 				}
 | |
| 				arg->count++;
 | |
| 			}
 | |
| 		}
 | |
| 	}
 | |
| }
 | |
| 
 | |
| static int u32_dump(struct net *net, struct tcf_proto *tp, unsigned long fh,
 | |
| 		     struct sk_buff *skb, struct tcmsg *t)
 | |
| {
 | |
| 	struct tc_u_knode *n = (struct tc_u_knode *)fh;
 | |
| 	struct nlattr *nest;
 | |
| 
 | |
| 	if (n == NULL)
 | |
| 		return skb->len;
 | |
| 
 | |
| 	t->tcm_handle = n->handle;
 | |
| 
 | |
| 	nest = nla_nest_start(skb, TCA_OPTIONS);
 | |
| 	if (nest == NULL)
 | |
| 		goto nla_put_failure;
 | |
| 
 | |
| 	if (TC_U32_KEY(n->handle) == 0) {
 | |
| 		struct tc_u_hnode *ht = (struct tc_u_hnode *)fh;
 | |
| 		u32 divisor = ht->divisor + 1;
 | |
| 
 | |
| 		if (nla_put_u32(skb, TCA_U32_DIVISOR, divisor))
 | |
| 			goto nla_put_failure;
 | |
| 	} else {
 | |
| 		if (nla_put(skb, TCA_U32_SEL,
 | |
| 			    sizeof(n->sel) + n->sel.nkeys*sizeof(struct tc_u32_key),
 | |
| 			    &n->sel))
 | |
| 			goto nla_put_failure;
 | |
| 		if (n->ht_up) {
 | |
| 			u32 htid = n->handle & 0xFFFFF000;
 | |
| 			if (nla_put_u32(skb, TCA_U32_HASH, htid))
 | |
| 				goto nla_put_failure;
 | |
| 		}
 | |
| 		if (n->res.classid &&
 | |
| 		    nla_put_u32(skb, TCA_U32_CLASSID, n->res.classid))
 | |
| 			goto nla_put_failure;
 | |
| 		if (n->ht_down &&
 | |
| 		    nla_put_u32(skb, TCA_U32_LINK, n->ht_down->handle))
 | |
| 			goto nla_put_failure;
 | |
| 
 | |
| #ifdef CONFIG_CLS_U32_MARK
 | |
| 		if ((n->mark.val || n->mark.mask) &&
 | |
| 		    nla_put(skb, TCA_U32_MARK, sizeof(n->mark), &n->mark))
 | |
| 			goto nla_put_failure;
 | |
| #endif
 | |
| 
 | |
| 		if (tcf_exts_dump(skb, &n->exts) < 0)
 | |
| 			goto nla_put_failure;
 | |
| 
 | |
| #ifdef CONFIG_NET_CLS_IND
 | |
| 		if (n->ifindex) {
 | |
| 			struct net_device *dev;
 | |
| 			dev = __dev_get_by_index(net, n->ifindex);
 | |
| 			if (dev && nla_put_string(skb, TCA_U32_INDEV, dev->name))
 | |
| 				goto nla_put_failure;
 | |
| 		}
 | |
| #endif
 | |
| #ifdef CONFIG_CLS_U32_PERF
 | |
| 		if (nla_put(skb, TCA_U32_PCNT,
 | |
| 			    sizeof(struct tc_u32_pcnt) + n->sel.nkeys*sizeof(u64),
 | |
| 			    n->pf))
 | |
| 			goto nla_put_failure;
 | |
| #endif
 | |
| 	}
 | |
| 
 | |
| 	nla_nest_end(skb, nest);
 | |
| 
 | |
| 	if (TC_U32_KEY(n->handle))
 | |
| 		if (tcf_exts_dump_stats(skb, &n->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_u32_ops __read_mostly = {
 | |
| 	.kind		=	"u32",
 | |
| 	.classify	=	u32_classify,
 | |
| 	.init		=	u32_init,
 | |
| 	.destroy	=	u32_destroy,
 | |
| 	.get		=	u32_get,
 | |
| 	.put		=	u32_put,
 | |
| 	.change		=	u32_change,
 | |
| 	.delete		=	u32_delete,
 | |
| 	.walk		=	u32_walk,
 | |
| 	.dump		=	u32_dump,
 | |
| 	.owner		=	THIS_MODULE,
 | |
| };
 | |
| 
 | |
| static int __init init_u32(void)
 | |
| {
 | |
| 	pr_info("u32 classifier\n");
 | |
| #ifdef CONFIG_CLS_U32_PERF
 | |
| 	pr_info("    Performance counters on\n");
 | |
| #endif
 | |
| #ifdef CONFIG_NET_CLS_IND
 | |
| 	pr_info("    input device check on\n");
 | |
| #endif
 | |
| #ifdef CONFIG_NET_CLS_ACT
 | |
| 	pr_info("    Actions configured\n");
 | |
| #endif
 | |
| 	return register_tcf_proto_ops(&cls_u32_ops);
 | |
| }
 | |
| 
 | |
| static void __exit exit_u32(void)
 | |
| {
 | |
| 	unregister_tcf_proto_ops(&cls_u32_ops);
 | |
| }
 | |
| 
 | |
| module_init(init_u32)
 | |
| module_exit(exit_u32)
 | |
| MODULE_LICENSE("GPL");
 |