summaryrefslogtreecommitdiff
path: root/net/sched/cls_matchall.c
blob: f2141cb5556235b7520606cb88384c062f3ffbd2 (plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
/*
 * net/sched/cls_matchll.c		Match-all classifier
 *
 * Copyright (c) 2016 Jiri Pirko <jiri@mellanox.com>
 *
 * 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 <net/sch_generic.h>
#include <net/pkt_cls.h>

struct cls_mall_head {
	struct tcf_exts exts;
	struct tcf_result res;
	u32 handle;
	u32 flags;
	struct rcu_head	rcu;
};

static int mall_classify(struct sk_buff *skb, const struct tcf_proto *tp,
			 struct tcf_result *res)
{
	struct cls_mall_head *head = rcu_dereference_bh(tp->root);

	if (tc_skip_sw(head->flags))
		return -1;

	return tcf_exts_exec(skb, &head->exts, res);
}

static int mall_init(struct tcf_proto *tp)
{
	return 0;
}

static void mall_destroy_rcu(struct rcu_head *rcu)
{
	struct cls_mall_head *head = container_of(rcu, struct cls_mall_head,
						  rcu);

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

static int mall_replace_hw_filter(struct tcf_proto *tp,
				  struct cls_mall_head *head,
				  unsigned long cookie)
{
	struct net_device *dev = tp->q->dev_queue->dev;
	struct tc_to_netdev offload;
	struct tc_cls_matchall_offload mall_offload = {0};

	offload.type = TC_SETUP_MATCHALL;
	offload.cls_mall = &mall_offload;
	offload.cls_mall->command = TC_CLSMATCHALL_REPLACE;
	offload.cls_mall->exts = &head->exts;
	offload.cls_mall->cookie = cookie;

	return dev->netdev_ops->ndo_setup_tc(dev, tp->q->handle, tp->protocol,
					     &offload);
}

static void mall_destroy_hw_filter(struct tcf_proto *tp,
				   struct cls_mall_head *head,
				   unsigned long cookie)
{
	struct net_device *dev = tp->q->dev_queue->dev;
	struct tc_to_netdev offload;
	struct tc_cls_matchall_offload mall_offload = {0};

	offload.type = TC_SETUP_MATCHALL;
	offload.cls_mall = &mall_offload;
	offload.cls_mall->command = TC_CLSMATCHALL_DESTROY;
	offload.cls_mall->exts = NULL;
	offload.cls_mall->cookie = cookie;

	dev->netdev_ops->ndo_setup_tc(dev, tp->q->handle, tp->protocol,
					     &offload);
}

static bool mall_destroy(struct tcf_proto *tp, bool force)
{
	struct cls_mall_head *head = rtnl_dereference(tp->root);
	struct net_device *dev = tp->q->dev_queue->dev;

	if (!head)
		return true;

	if (tc_should_offload(dev, tp, head->flags))
		mall_destroy_hw_filter(tp, head, (unsigned long) head);

	call_rcu(&head->rcu, mall_destroy_rcu);
	return true;
}

static unsigned long mall_get(struct tcf_proto *tp, u32 handle)
{
	return 0UL;
}

static const struct nla_policy mall_policy[TCA_MATCHALL_MAX + 1] = {
	[TCA_MATCHALL_UNSPEC]		= { .type = NLA_UNSPEC },
	[TCA_MATCHALL_CLASSID]		= { .type = NLA_U32 },
};

static int mall_set_parms(struct net *net, struct tcf_proto *tp,
			  struct cls_mall_head *head,
			  unsigned long base, struct nlattr **tb,
			  struct nlattr *est, bool ovr)
{
	struct tcf_exts e;
	int err;

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

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

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

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

static int mall_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_mall_head *head = rtnl_dereference(tp->root);
	struct net_device *dev = tp->q->dev_queue->dev;
	struct nlattr *tb[TCA_MATCHALL_MAX + 1];
	struct cls_mall_head *new;
	u32 flags = 0;
	int err;

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

	if (head)
		return -EEXIST;

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

	if (tb[TCA_MATCHALL_FLAGS]) {
		flags = nla_get_u32(tb[TCA_MATCHALL_FLAGS]);
		if (!tc_flags_valid(flags))
			return -EINVAL;
	}

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

	err = tcf_exts_init(&new->exts, TCA_MATCHALL_ACT, 0);
	if (err)
		goto err_exts_init;

	if (!handle)
		handle = 1;
	new->handle = handle;
	new->flags = flags;

	err = mall_set_parms(net, tp, new, base, tb, tca[TCA_RATE], ovr);
	if (err)
		goto err_set_parms;

	if (tc_should_offload(dev, tp, flags)) {
		err = mall_replace_hw_filter(tp, new, (unsigned long) new);
		if (err) {
			if (tc_skip_sw(flags))
				goto err_replace_hw_filter;
			else
				err = 0;
		}
	}

	*arg = (unsigned long) head;
	rcu_assign_pointer(tp->root, new);
	if (head)
		call_rcu(&head->rcu, mall_destroy_rcu);
	return 0;

err_replace_hw_filter:
err_set_parms:
	tcf_exts_destroy(&new->exts);
err_exts_init:
	kfree(new);
	return err;
}

static int mall_delete(struct tcf_proto *tp, unsigned long arg)
{
	return -EOPNOTSUPP;
}

static void mall_walk(struct tcf_proto *tp, struct tcf_walker *arg)
{
	struct cls_mall_head *head = rtnl_dereference(tp->root);

	if (arg->count < arg->skip)
		goto skip;
	if (arg->fn(tp, (unsigned long) head, arg) < 0)
		arg->stop = 1;
skip:
	arg->count++;
}

static int mall_dump(struct net *net, struct tcf_proto *tp, unsigned long fh,
		     struct sk_buff *skb, struct tcmsg *t)
{
	struct cls_mall_head *head = (struct cls_mall_head *) fh;
	struct nlattr *nest;

	if (!head)
		return skb->len;

	t->tcm_handle = head->handle;

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

	if (head->res.classid &&
	    nla_put_u32(skb, TCA_MATCHALL_CLASSID, head->res.classid))
		goto nla_put_failure;

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

	nla_nest_end(skb, nest);

	if (tcf_exts_dump_stats(skb, &head->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_mall_ops __read_mostly = {
	.kind		= "matchall",
	.classify	= mall_classify,
	.init		= mall_init,
	.destroy	= mall_destroy,
	.get		= mall_get,
	.change		= mall_change,
	.delete		= mall_delete,
	.walk		= mall_walk,
	.dump		= mall_dump,
	.owner		= THIS_MODULE,
};

static int __init cls_mall_init(void)
{
	return register_tcf_proto_ops(&cls_mall_ops);
}

static void __exit cls_mall_exit(void)
{
	unregister_tcf_proto_ops(&cls_mall_ops);
}

module_init(cls_mall_init);
module_exit(cls_mall_exit);

MODULE_AUTHOR("Jiri Pirko <jiri@mellanox.com>");
MODULE_DESCRIPTION("Match-all classifier");
MODULE_LICENSE("GPL v2");
100:3:: dev lo proto none metric 0 pref medium local 2100:3::4 dev lo proto none metric 0 pref medium local fe80:: dev lo proto none metric 0 pref medium ... Set rt6i_protocol to RTPROT_KERNEL for consistency with IPv4. Now routes show up with proto "kernel": $ ip -6 ro ls table local local ::1 dev lo proto kernel metric 0 pref medium local 2100:3:: dev lo proto kernel metric 0 pref medium local 2100:3::4 dev lo proto kernel metric 0 pref medium local fe80:: dev lo proto kernel metric 0 pref medium ... Signed-off-by: David Ahern <dsa@cumulusnetworks.com> Signed-off-by: David S. Miller <davem@davemloft.net> 2017-02-03bridge: vlan dst_metadata hooks in ingress and egress pathsRoopa Prabhu6-2/+82 - ingress hook: - if port is a tunnel port, use tunnel info in attached dst_metadata to map it to a local vlan - egress hook: - if port is a tunnel port, use tunnel info attached to vlan to set dst_metadata on the skb CC: Nikolay Aleksandrov <nikolay@cumulusnetworks.com> Signed-off-by: Roopa Prabhu <roopa@cumulusnetworks.com> Signed-off-by: David S. Miller <davem@davemloft.net> 2017-02-03bridge: per vlan dst_metadata netlink supportRoopa Prabhu7-48/+641 This patch adds support to attach per vlan tunnel info dst metadata. This enables bridge driver to map vlan to tunnel_info at ingress and egress. It uses the kernel dst_metadata infrastructure. The initial use case is vlan to vni bridging, but the api is generic to extend to any tunnel_info in the future: - Uapi to configure/unconfigure/dump per vlan tunnel data - netlink functions to configure vlan and tunnel_info mapping - Introduces bridge port flag BR_LWT_VLAN to enable attach/detach dst_metadata to bridged packets on ports. off by default. - changes to existing code is mainly refactor some existing vlan handling netlink code + hooks for new vlan tunnel code - I have kept the vlan tunnel code isolated in separate files. - most of the netlink vlan tunnel code is handling of vlan-tunid ranges (follows the vlan range handling code). To conserve space vlan-tunid by default are always dumped in ranges if applicable. Use case: example use for this is a vxlan bridging gateway or vtep which maps vlans to vn-segments (or vnis). iproute2 example (patched and pruned iproute2 output to just show relevant fdb entries): example shows same host mac learnt on two vni's and vlan 100 maps to vni 1000, vlan 101 maps to vni 1001 before (netdev per vni): $bridge fdb show | grep "00:02:00:00:00:03" 00:02:00:00:00:03 dev vxlan1001 vlan 101 master bridge 00:02:00:00:00:03 dev vxlan1001 dst 12.0.0.8 self 00:02:00:00:00:03 dev vxlan1000 vlan 100 master bridge 00:02:00:00:00:03 dev vxlan1000 dst 12.0.0.8 self after this patch with collect metdata in bridged mode (single netdev): $bridge fdb show | grep "00:02:00:00:00:03" 00:02:00:00:00:03 dev vxlan0 vlan 101 master bridge 00:02:00:00:00:03 dev vxlan0 src_vni 1001 dst 12.0.0.8 self 00:02:00:00:00:03 dev vxlan0 vlan 100 master bridge 00:02:00:00:00:03 dev vxlan0 src_vni 1000 dst 12.0.0.8 self CC: Nikolay Aleksandrov <nikolay@cumulusnetworks.com> Signed-off-by: Roopa Prabhu <roopa@cumulusnetworks.com> Signed-off-by: David S. Miller <davem@davemloft.net> 2017-02-03net/sched: act_ife: Change to use ife moduleYotam Gigi2-78/+33 Use the encode/decode functionality from the ife module instead of using implementation inside the act_ife. Reviewed-by: Jiri Pirko <jiri@mellanox.com> Signed-off-by: Yotam Gigi <yotamg@mellanox.com> Signed-off-by: Jamal Hadi Salim <jhs@mojatatu.com> Signed-off-by: Roman Mashak <mrv@mojatatu.com> Signed-off-by: David S. Miller <davem@davemloft.net> 2017-02-03net: Introduce ife encapsulation moduleYotam Gigi5-0/+165 This module is responsible for the ife encapsulation protocol encode/decode logics. That module can: - ife_encode: encode skb and reserve space for the ife meta header - ife_decode: decode skb and extract the meta header size - ife_tlv_meta_encode - encodes one tlv entry into the reserved ife header space. - ife_tlv_meta_decode - decodes one tlv entry from the packet - ife_tlv_meta_next - advance to the next tlv Reviewed-by: Jiri Pirko <jiri@mellanox.com> Signed-off-by: Yotam Gigi <yotamg@mellanox.com> Signed-off-by: Jamal Hadi Salim <jhs@mojatatu.com> Signed-off-by: Roman Mashak <mrv@mojatatu.com> Signed-off-by: David S. Miller <davem@davemloft.net> 2017-02-03net/sched: act_ife: Unexport ife_tlv_meta_encodeYotam Gigi1-2/+2 As the function ife_tlv_meta_encode is not used by any other module, unexport it and make it static for the act_ife module. Signed-off-by: Yotam Gigi <yotamg@mellanox.com> Signed-off-by: Jamal Hadi Salim <jhs@mojatatu.com> Signed-off-by: Roman Mashak <mrv@mojatatu.com> Signed-off-by: David S. Miller <davem@davemloft.net> 2017-02-03tcp: add tcp_mss_clamp() helperEric Dumazet