aboutsummaryrefslogtreecommitdiffstats
path: root/net/core/netprio_cgroup.c
blob: 8618242c677a4a767bccf2579abe25269fd03448 (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
291
292
293
294
295
296
297
298
299
300
301
302
// SPDX-License-Identifier: GPL-2.0-or-later
/*
 * net/core/netprio_cgroup.c	Priority Control Group
 *
 * Authors:	Neil Horman <nhorman@tuxdriver.com>
 */

#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt

#include <linux/module.h>
#include <linux/slab.h>
#include <linux/types.h>
#include <linux/string.h>
#include <linux/errno.h>
#include <linux/skbuff.h>
#include <linux/cgroup.h>
#include <linux/rcupdate.h>
#include <linux/atomic.h>
#include <linux/sched/task.h>

#include <net/rtnetlink.h>
#include <net/pkt_cls.h>
#include <net/sock.h>
#include <net/netprio_cgroup.h>

#include <linux/fdtable.h>

/*
 * netprio allocates per-net_device priomap array which is indexed by
 * css->id.  Limiting css ID to 16bits doesn't lose anything.
 */
#define NETPRIO_ID_MAX		USHRT_MAX

#define PRIOMAP_MIN_SZ		128

/*
 * Extend @dev->priomap so that it's large enough to accommodate
 * @target_idx.  @dev->priomap.priomap_len > @target_idx after successful
 * return.  Must be called under rtnl lock.
 */
static int extend_netdev_table(struct net_device *dev, u32 target_idx)
{
	struct netprio_map *old, *new;
	size_t new_sz, new_len;

	/* is the existing priomap large enough? */
	old = rtnl_dereference(dev->priomap);
	if (old && old->priomap_len > target_idx)
		return 0;

	/*
	 * Determine the new size.  Let's keep it power-of-two.  We start
	 * from PRIOMAP_MIN_SZ and double it until it's large enough to
	 * accommodate @target_idx.
	 */
	new_sz = PRIOMAP_MIN_SZ;
	while (true) {
		new_len = (new_sz - offsetof(struct netprio_map, priomap)) /
			sizeof(new->priomap[0]);
		if (new_len > target_idx)
			break;
		new_sz *= 2;
		/* overflowed? */
		if (WARN_ON(new_sz < PRIOMAP_MIN_SZ))
			return -ENOSPC;
	}

	/* allocate & copy */
	new = kzalloc(new_sz, GFP_KERNEL);
	if (!new)
		return -ENOMEM;

	if (old)
		memcpy(new->priomap, old->priomap,
		       old->priomap_len * sizeof(old->priomap[0]));

	new->priomap_len = new_len;

	/* install the new priomap */
	rcu_assign_pointer(dev->priomap, new);
	if (old)
		kfree_rcu(old, rcu);
	return 0;
}

/**
 * netprio_prio - return the effective netprio of a cgroup-net_device pair
 * @css: css part of the target pair
 * @dev: net_device part of the target pair
 *
 * Should be called under RCU read or rtnl lock.
 */
static u32 netprio_prio(struct cgroup_subsys_state *css, struct net_device *dev)
{
	struct netprio_map *map = rcu_dereference_rtnl(dev->priomap);
	int id = css->cgroup->id;

	if (map && id < map->priomap_len)
		return map->priomap[id];
	return 0;
}

/**
 * netprio_set_prio - set netprio on a cgroup-net_device pair
 * @css: css part of the target pair
 * @dev: net_device part of the target pair
 * @prio: prio to set
 *
 * Set netprio to @prio on @css-@dev pair.  Should be called under rtnl
 * lock and may fail under memory pressure for non-zero @prio.
 */
static int netprio_set_prio(struct cgroup_subsys_state *css,
			    struct net_device *dev, u32 prio)
{
	struct netprio_map *map;
	int id = css->cgroup->id;
	int ret;

	/* avoid extending priomap for zero writes */
	map = rtnl_dereference(dev->priomap);
	if (!prio && (!map || map->priomap_len <= id))
		return 0;

	ret = extend_netdev_table(dev, id);
	if (ret)
		return ret;

	map = rtnl_dereference(dev->priomap);
	map->priomap[id] = prio;
	return 0;
}

static struct cgroup_subsys_state *
cgrp_css_alloc(struct cgroup_subsys_state *parent_css)
{
	struct cgroup_subsys_state *css;

	css = kzalloc(sizeof(*css), GFP_KERNEL);
	if (!css)
		return ERR_PTR(-ENOMEM);

	return css;
}

static int cgrp_css_online(struct cgroup_subsys_state *css)
{
	struct cgroup_subsys_state *parent_css = css->parent;
	struct net_device *dev;
	int ret = 0;

	if (css->id > NETPRIO_ID_MAX)
		return -ENOSPC;

	if (!parent_css)
		return 0;

	rtnl_lock();
	/*
	 * Inherit prios from the parent.  As all prios are set during
	 * onlining, there is no need to clear them on offline.
	 */
	for_each_netdev(&init_net, dev) {
		u32 prio = netprio_prio(parent_css, dev);

		ret = netprio_set_prio(css, dev, prio);
		if (ret)
			break;
	}
	rtnl_unlock();
	return ret;
}

static void cgrp_css_free(struct cgroup_subsys_state *css)
{
	kfree(css);
}

static u64 read_prioidx(struct cgroup_subsys_state *css, struct cftype *cft)
{
	return css->cgroup->id;
}

static int read_priomap(struct seq_file *sf, void *v)
{
	struct net_device *dev;

	rcu_read_lock();
	for_each_netdev_rcu(&init_net, dev)
		seq_printf(sf, "%s %u\n", dev->name,
			   netprio_prio(seq_css(sf), dev));
	rcu_read_unlock();
	return 0;
}

static ssize_t write_priomap(struct kernfs_open_file *of,
			     char *buf, size_t nbytes, loff_t off)
{
	char devname[IFNAMSIZ + 1];
	struct net_device *dev;
	u32 prio;
	int ret;

	if (sscanf(buf, "%"__stringify(IFNAMSIZ)"s %u", devname, &prio) != 2)
		return -EINVAL;

	dev = dev_get_by_name(&init_net, devname);
	if (!dev)
		return -ENODEV;

	cgroup_sk_alloc_disable();

	rtnl_lock();

	ret = netprio_set_prio(of_css(of), dev, prio);

	rtnl_unlock();
	dev_put(dev);
	return ret ?: nbytes;
}

static int update_netprio(const void *v, struct file *file, unsigned n)
{
	int err;
	struct socket *sock = sock_from_file(file, &err);
	if (sock) {
		spin_lock(&cgroup_sk_update_lock);
		sock_cgroup_set_prioidx(&sock->sk->sk_cgrp_data,
					(unsigned long)v);
		spin_unlock(&cgroup_sk_update_lock);
	}
	return 0;
}

static void net_prio_attach(struct cgroup_taskset *tset)
{
	struct task_struct *p;
	struct cgroup_subsys_state *css;

	cgroup_sk_alloc_disable();

	cgroup_taskset_for_each(p, css, tset) {
		void *v = (void *)(unsigned long)css->cgroup->id;

		task_lock(p);
		iterate_fd(p->files, 0, update_netprio, v);
		task_unlock(p);
	}
}

static struct cftype ss_files[] = {
	{
		.name = "prioidx",
		.read_u64 = read_prioidx,
	},
	{
		.name = "ifpriomap",
		.seq_show = read_priomap,
		.write = write_priomap,
	},
	{ }	/* terminate */
};

struct cgroup_subsys net_prio_cgrp_subsys = {
	.css_alloc	= cgrp_css_alloc,
	.css_online	= cgrp_css_online,
	.css_free	= cgrp_css_free,
	.attach		= net_prio_attach,
	.legacy_cftypes	= ss_files,
};

static int netprio_device_event(struct notifier_block *unused,
				unsigned long event, void *ptr)
{
	struct net_device *dev = netdev_notifier_info_to_dev(ptr);
	struct netprio_map *old;

	/*
	 * Note this is called with rtnl_lock held so we have update side
	 * protection on our rcu assignments
	 */

	switch (event) {
	case NETDEV_UNREGISTER:
		old = rtnl_dereference(dev->priomap);
		RCU_INIT_POINTER(dev->priomap, NULL);
		if (old)
			kfree_rcu(old, rcu);
		break;
	}
	return NOTIFY_DONE;
}

static struct notifier_block netprio_device_notifier = {
	.notifier_call = netprio_device_event
};

static int __init init_cgroup_netprio(void)
{
	register_netdevice_notifier(&netprio_device_notifier);
	return 0;
}
subsys_initcall(init_cgroup_netprio);