netprio_cgroup.c 7.9 KB
Newer Older
1 2 3 4 5 6 7 8 9 10 11
/*
 * net/core/netprio_cgroup.c	Priority Control Group
 *
 *		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:	Neil Horman <nhorman@tuxdriver.com>
 */

J
Joe Perches 已提交
12 13
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt

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

#define PRIOIDX_SZ 128

static unsigned long prioidx_map[PRIOIDX_SZ];
static DEFINE_SPINLOCK(prioidx_map_lock);
static atomic_t max_prioidx = ATOMIC_INIT(0);

static inline struct cgroup_netprio_state *cgrp_netprio_state(struct cgroup *cgrp)
{
	return container_of(cgroup_subsys_state(cgrp, net_prio_subsys_id),
			    struct cgroup_netprio_state, css);
}

static int get_prioidx(u32 *prio)
{
	unsigned long flags;
	u32 prioidx;

	spin_lock_irqsave(&prioidx_map_lock, flags);
	prioidx = find_first_zero_bit(prioidx_map, sizeof(unsigned long) * PRIOIDX_SZ);
47 48 49 50
	if (prioidx == sizeof(unsigned long) * PRIOIDX_SZ) {
		spin_unlock_irqrestore(&prioidx_map_lock, flags);
		return -ENOSPC;
	}
51
	set_bit(prioidx, prioidx_map);
G
Gao feng 已提交
52 53
	if (atomic_read(&max_prioidx) < prioidx)
		atomic_set(&max_prioidx, prioidx);
54 55 56 57 58 59 60 61 62 63 64 65 66 67
	spin_unlock_irqrestore(&prioidx_map_lock, flags);
	*prio = prioidx;
	return 0;
}

static void put_prioidx(u32 idx)
{
	unsigned long flags;

	spin_lock_irqsave(&prioidx_map_lock, flags);
	clear_bit(idx, prioidx_map);
	spin_unlock_irqrestore(&prioidx_map_lock, flags);
}

68
static int extend_netdev_table(struct net_device *dev, u32 new_len)
69 70 71 72 73 74 75 76 77 78
{
	size_t new_size = sizeof(struct netprio_map) +
			   ((sizeof(u32) * new_len));
	struct netprio_map *new_priomap = kzalloc(new_size, GFP_KERNEL);
	struct netprio_map *old_priomap;
	int i;

	old_priomap  = rtnl_dereference(dev->priomap);

	if (!new_priomap) {
J
Joe Perches 已提交
79
		pr_warn("Unable to alloc new priomap!\n");
80
		return -ENOMEM;
81 82 83 84 85 86 87 88 89 90 91 92
	}

	for (i = 0;
	     old_priomap && (i < old_priomap->priomap_len);
	     i++)
		new_priomap->priomap[i] = old_priomap->priomap[i];

	new_priomap->priomap_len = new_len;

	rcu_assign_pointer(dev->priomap, new_priomap);
	if (old_priomap)
		kfree_rcu(old_priomap, rcu);
93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109
	return 0;
}

static int write_update_netdev_table(struct net_device *dev)
{
	int ret = 0;
	u32 max_len;
	struct netprio_map *map;

	rtnl_lock();
	max_len = atomic_read(&max_prioidx) + 1;
	map = rtnl_dereference(dev->priomap);
	if (!map || map->priomap_len < max_len)
		ret = extend_netdev_table(dev, max_len);
	rtnl_unlock();

	return ret;
110 111
}

112
static int update_netdev_tables(void)
113
{
114
	int ret = 0;
115
	struct net_device *dev;
116
	u32 max_len;
117 118 119
	struct netprio_map *map;

	rtnl_lock();
120
	max_len = atomic_read(&max_prioidx) + 1;
121 122
	for_each_netdev(&init_net, dev) {
		map = rtnl_dereference(dev->priomap);
123 124 125 126 127 128 129 130 131 132
		/*
		 * don't allocate priomap if we didn't
		 * change net_prio.ifpriomap (map == NULL),
		 * this will speed up skb_update_prio.
		 */
		if (map && map->priomap_len < max_len) {
			ret = extend_netdev_table(dev, max_len);
			if (ret < 0)
				break;
		}
133 134
	}
	rtnl_unlock();
135
	return ret;
136 137
}

138
static struct cgroup_subsys_state *cgrp_create(struct cgroup *cgrp)
139 140
{
	struct cgroup_netprio_state *cs;
141
	int ret = -EINVAL;
142 143 144 145 146

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

147 148
	if (cgrp->parent && cgrp_netprio_state(cgrp->parent)->prioidx)
		goto out;
149 150

	ret = get_prioidx(&cs->prioidx);
151
	if (ret < 0) {
J
Joe Perches 已提交
152
		pr_warn("No space in priority index array\n");
153 154 155 156 157 158 159
		goto out;
	}

	ret = update_netdev_tables();
	if (ret < 0) {
		put_prioidx(cs->prioidx);
		goto out;
160 161 162
	}

	return &cs->css;
163 164 165
out:
	kfree(cs);
	return ERR_PTR(ret);
166 167
}

168
static void cgrp_destroy(struct cgroup *cgrp)
169 170 171 172 173 174 175 176 177
{
	struct cgroup_netprio_state *cs;
	struct net_device *dev;
	struct netprio_map *map;

	cs = cgrp_netprio_state(cgrp);
	rtnl_lock();
	for_each_netdev(&init_net, dev) {
		map = rtnl_dereference(dev->priomap);
178
		if (map && cs->prioidx < map->priomap_len)
179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201
			map->priomap[cs->prioidx] = 0;
	}
	rtnl_unlock();
	put_prioidx(cs->prioidx);
	kfree(cs);
}

static u64 read_prioidx(struct cgroup *cgrp, struct cftype *cft)
{
	return (u64)cgrp_netprio_state(cgrp)->prioidx;
}

static int read_priomap(struct cgroup *cont, struct cftype *cft,
			struct cgroup_map_cb *cb)
{
	struct net_device *dev;
	u32 prioidx = cgrp_netprio_state(cont)->prioidx;
	u32 priority;
	struct netprio_map *map;

	rcu_read_lock();
	for_each_netdev_rcu(&init_net, dev) {
		map = rcu_dereference(dev->priomap);
202
		priority = (map && prioidx < map->priomap_len) ? map->priomap[prioidx] : 0;
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
		cb->fill(cb, dev->name, priority);
	}
	rcu_read_unlock();
	return 0;
}

static int write_priomap(struct cgroup *cgrp, struct cftype *cft,
			 const char *buffer)
{
	char *devname = kstrdup(buffer, GFP_KERNEL);
	int ret = -EINVAL;
	u32 prioidx = cgrp_netprio_state(cgrp)->prioidx;
	unsigned long priority;
	char *priostr;
	struct net_device *dev;
	struct netprio_map *map;

	if (!devname)
		return -ENOMEM;

	/*
	 * Minimally sized valid priomap string
	 */
	if (strlen(devname) < 3)
		goto out_free_devname;

	priostr = strstr(devname, " ");
	if (!priostr)
		goto out_free_devname;

	/*
	 *Separate the devname from the associated priority
	 *and advance the priostr poitner to the priority value
	 */
	*priostr = '\0';
	priostr++;

	/*
	 * If the priostr points to NULL, we're at the end of the passed
	 * in string, and its not a valid write
	 */
	if (*priostr == '\0')
		goto out_free_devname;

	ret = kstrtoul(priostr, 10, &priority);
	if (ret < 0)
		goto out_free_devname;

	ret = -ENODEV;

	dev = dev_get_by_name(&init_net, devname);
	if (!dev)
		goto out_free_devname;

257 258 259 260
	ret = write_update_netdev_table(dev);
	if (ret < 0)
		goto out_put_dev;

261 262 263 264 265
	rcu_read_lock();
	map = rcu_dereference(dev->priomap);
	if (map)
		map->priomap[prioidx] = priority;
	rcu_read_unlock();
266 267

out_put_dev:
268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284
	dev_put(dev);

out_free_devname:
	kfree(devname);
	return ret;
}

static struct cftype ss_files[] = {
	{
		.name = "prioidx",
		.read_u64 = read_prioidx,
	},
	{
		.name = "ifpriomap",
		.read_map = read_priomap,
		.write_string = write_priomap,
	},
285
	{ }	/* terminate */
286 287
};

288 289 290 291 292 293 294
struct cgroup_subsys net_prio_subsys = {
	.name		= "net_prio",
	.create		= cgrp_create,
	.destroy	= cgrp_destroy,
#ifdef CONFIG_NETPRIO_CGROUP
	.subsys_id	= net_prio_subsys_id,
#endif
295
	.base_cftypes	= ss_files,
296 297
	.module		= THIS_MODULE
};
298 299 300 301 302 303 304 305 306 307 308 309 310 311 312

static int netprio_device_event(struct notifier_block *unused,
				unsigned long event, void *ptr)
{
	struct net_device *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);
313
		RCU_INIT_POINTER(dev->priomap, NULL);
314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359
		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)
{
	int ret;

	ret = cgroup_load_subsys(&net_prio_subsys);
	if (ret)
		goto out;
#ifndef CONFIG_NETPRIO_CGROUP
	smp_wmb();
	net_prio_subsys_id = net_prio_subsys.subsys_id;
#endif

	register_netdevice_notifier(&netprio_device_notifier);

out:
	return ret;
}

static void __exit exit_cgroup_netprio(void)
{
	struct netprio_map *old;
	struct net_device *dev;

	unregister_netdevice_notifier(&netprio_device_notifier);

	cgroup_unload_subsys(&net_prio_subsys);

#ifndef CONFIG_NETPRIO_CGROUP
	net_prio_subsys_id = -1;
	synchronize_rcu();
#endif

	rtnl_lock();
	for_each_netdev(&init_net, dev) {
		old = rtnl_dereference(dev->priomap);
360
		RCU_INIT_POINTER(dev->priomap, NULL);
361 362 363 364 365 366 367 368 369
		if (old)
			kfree_rcu(old, rcu);
	}
	rtnl_unlock();
}

module_init(init_cgroup_netprio);
module_exit(exit_cgroup_netprio);
MODULE_LICENSE("GPL v2");