vport.c 10.1 KB
Newer Older
1
/*
2
 * Copyright (c) 2007-2012 Nicira, Inc.
3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21
 *
 * This program is free software; you can redistribute it and/or
 * modify it under the terms of version 2 of the GNU General Public
 * License as published by the Free Software Foundation.
 *
 * This program is distributed in the hope that it will be useful, but
 * WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
 * General Public License for more details.
 *
 * You should have received a copy of the GNU General Public License
 * along with this program; if not, write to the Free Software
 * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA
 * 02110-1301, USA
 */

#include <linux/etherdevice.h>
#include <linux/if.h>
#include <linux/if_vlan.h>
22
#include <linux/jhash.h>
23 24 25 26 27 28 29
#include <linux/kernel.h>
#include <linux/list.h>
#include <linux/mutex.h>
#include <linux/percpu.h>
#include <linux/rcupdate.h>
#include <linux/rtnetlink.h>
#include <linux/compat.h>
30
#include <net/net_namespace.h>
31

32
#include "datapath.h"
33 34 35 36 37 38 39 40 41 42
#include "vport.h"
#include "vport-internal_dev.h"

/* List of statically compiled vport implementations.  Don't forget to also
 * add yours to the list at the bottom of vport.h. */
static const struct vport_ops *vport_ops_list[] = {
	&ovs_netdev_vport_ops,
	&ovs_internal_vport_ops,
};

43
/* Protected by RCU read lock for reading, ovs_mutex for writing. */
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
static struct hlist_head *dev_table;
#define VPORT_HASH_BUCKETS 1024

/**
 *	ovs_vport_init - initialize vport subsystem
 *
 * Called at module load time to initialize the vport subsystem.
 */
int ovs_vport_init(void)
{
	dev_table = kzalloc(VPORT_HASH_BUCKETS * sizeof(struct hlist_head),
			    GFP_KERNEL);
	if (!dev_table)
		return -ENOMEM;

	return 0;
}

/**
 *	ovs_vport_exit - shutdown vport subsystem
 *
 * Called at module exit time to shutdown the vport subsystem.
 */
void ovs_vport_exit(void)
{
	kfree(dev_table);
}

72
static struct hlist_head *hash_bucket(struct net *net, const char *name)
73
{
74
	unsigned int hash = jhash(name, strlen(name), (unsigned long) net);
75 76 77 78 79 80 81 82
	return &dev_table[hash & (VPORT_HASH_BUCKETS - 1)];
}

/**
 *	ovs_vport_locate - find a port that has already been created
 *
 * @name: name of port to find
 *
83
 * Must be called with ovs or RCU read lock.
84
 */
85
struct vport *ovs_vport_locate(struct net *net, const char *name)
86
{
87
	struct hlist_head *bucket = hash_bucket(net, name);
88 89
	struct vport *vport;

90
	hlist_for_each_entry_rcu(vport, bucket, hash_node)
91 92
		if (!strcmp(name, vport->ops->get_name(vport)) &&
		    net_eq(ovs_dp_get_net(vport->dp), net))
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
			return vport;

	return NULL;
}

/**
 *	ovs_vport_alloc - allocate and initialize new vport
 *
 * @priv_size: Size of private data area to allocate.
 * @ops: vport device ops
 *
 * Allocate and initialize a new vport defined by @ops.  The vport will contain
 * a private data area of size @priv_size that can be accessed using
 * vport_priv().  vports that are no longer needed should be released with
 * vport_free().
 */
struct vport *ovs_vport_alloc(int priv_size, const struct vport_ops *ops,
			  const struct vport_parms *parms)
{
	struct vport *vport;
	size_t alloc_size;

	alloc_size = sizeof(struct vport);
	if (priv_size) {
		alloc_size = ALIGN(alloc_size, VPORT_ALIGN);
		alloc_size += priv_size;
	}

	vport = kzalloc(alloc_size, GFP_KERNEL);
	if (!vport)
		return ERR_PTR(-ENOMEM);

	vport->dp = parms->dp;
	vport->port_no = parms->port_no;
127
	vport->upcall_portid = parms->upcall_portid;
128
	vport->ops = ops;
129
	INIT_HLIST_NODE(&vport->dp_hash_node);
130 131

	vport->percpu_stats = alloc_percpu(struct vport_percpu_stats);
132 133
	if (!vport->percpu_stats) {
		kfree(vport);
134
		return ERR_PTR(-ENOMEM);
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

	spin_lock_init(&vport->stats_lock);

	return vport;
}

/**
 *	ovs_vport_free - uninitialize and free vport
 *
 * @vport: vport to free
 *
 * Frees a vport allocated with vport_alloc() when it is no longer needed.
 *
 * The caller must ensure that an RCU grace period has passed since the last
 * time @vport was in a datapath.
 */
void ovs_vport_free(struct vport *vport)
{
	free_percpu(vport->percpu_stats);
	kfree(vport);
}

/**
 *	ovs_vport_add - add vport device (for kernel callers)
 *
 * @parms: Information about new vport.
 *
 * Creates a new vport with the specified configuration (which is dependent on
164
 * device type).  ovs_mutex must be held.
165 166 167 168 169 170 171 172 173
 */
struct vport *ovs_vport_add(const struct vport_parms *parms)
{
	struct vport *vport;
	int err = 0;
	int i;

	for (i = 0; i < ARRAY_SIZE(vport_ops_list); i++) {
		if (vport_ops_list[i]->type == parms->type) {
174 175
			struct hlist_head *bucket;

176 177 178 179 180 181
			vport = vport_ops_list[i]->create(parms);
			if (IS_ERR(vport)) {
				err = PTR_ERR(vport);
				goto out;
			}

182 183 184
			bucket = hash_bucket(ovs_dp_get_net(vport->dp),
					     vport->ops->get_name(vport));
			hlist_add_head_rcu(&vport->hash_node, bucket);
185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201
			return vport;
		}
	}

	err = -EAFNOSUPPORT;

out:
	return ERR_PTR(err);
}

/**
 *	ovs_vport_set_options - modify existing vport device (for kernel callers)
 *
 * @vport: vport to modify.
 * @port: New configuration.
 *
 * Modifies an existing device with the specified configuration (which is
202
 * dependent on device type).  ovs_mutex must be held.
203 204 205 206 207 208 209 210 211 212 213 214 215 216
 */
int ovs_vport_set_options(struct vport *vport, struct nlattr *options)
{
	if (!vport->ops->set_options)
		return -EOPNOTSUPP;
	return vport->ops->set_options(vport, options);
}

/**
 *	ovs_vport_del - delete existing vport device
 *
 * @vport: vport to delete.
 *
 * Detaches @vport from its datapath and destroys it.  It is possible to fail
217
 * for reasons such as lack of memory.  ovs_mutex must be held.
218 219 220
 */
void ovs_vport_del(struct vport *vport)
{
221
	ASSERT_OVSL();
222 223 224 225 226 227 228 229 230 231 232 233 234 235

	hlist_del_rcu(&vport->hash_node);

	vport->ops->destroy(vport);
}

/**
 *	ovs_vport_get_stats - retrieve device stats
 *
 * @vport: vport from which to retrieve the stats
 * @stats: location to store stats
 *
 * Retrieves transmit, receive, and error stats for the given device.
 *
236
 * Must be called with ovs_mutex or rcu_read_lock.
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
 */
void ovs_vport_get_stats(struct vport *vport, struct ovs_vport_stats *stats)
{
	int i;

	memset(stats, 0, sizeof(*stats));

	/* We potentially have 2 sources of stats that need to be combined:
	 * those we have collected (split into err_stats and percpu_stats) from
	 * set_stats() and device error stats from netdev->get_stats() (for
	 * errors that happen  downstream and therefore aren't reported through
	 * our vport_record_error() function).
	 * Stats from first source are reported by ovs (OVS_VPORT_ATTR_STATS).
	 * netdev-stats can be directly read over netlink-ioctl.
	 */

	spin_lock_bh(&vport->stats_lock);

	stats->rx_errors	= vport->err_stats.rx_errors;
	stats->tx_errors	= vport->err_stats.tx_errors;
	stats->tx_dropped	= vport->err_stats.tx_dropped;
	stats->rx_dropped	= vport->err_stats.rx_dropped;

	spin_unlock_bh(&vport->stats_lock);

	for_each_possible_cpu(i) {
		const struct vport_percpu_stats *percpu_stats;
		struct vport_percpu_stats local_stats;
		unsigned int start;

		percpu_stats = per_cpu_ptr(vport->percpu_stats, i);

		do {
			start = u64_stats_fetch_begin_bh(&percpu_stats->sync);
			local_stats = *percpu_stats;
		} while (u64_stats_fetch_retry_bh(&percpu_stats->sync, start));

		stats->rx_bytes		+= local_stats.rx_bytes;
		stats->rx_packets	+= local_stats.rx_packets;
		stats->tx_bytes		+= local_stats.tx_bytes;
		stats->tx_packets	+= local_stats.tx_packets;
	}
}

/**
 *	ovs_vport_get_options - retrieve device options
 *
 * @vport: vport from which to retrieve the options.
 * @skb: sk_buff where options should be appended.
 *
 * Retrieves the configuration of the given device, appending an
 * %OVS_VPORT_ATTR_OPTIONS attribute that in turn contains nested
 * vport-specific attributes to @skb.
 *
 * Returns 0 if successful, -EMSGSIZE if @skb has insufficient room, or another
 * negative error code if a real error occurred.  If an error occurs, @skb is
 * left unmodified.
 *
295
 * Must be called with ovs_mutex or rcu_read_lock.
296 297 298 299
 */
int ovs_vport_get_options(const struct vport *vport, struct sk_buff *skb)
{
	struct nlattr *nla;
300 301 302 303
	int err;

	if (!vport->ops->get_options)
		return 0;
304 305 306 307 308

	nla = nla_nest_start(skb, OVS_VPORT_ATTR_OPTIONS);
	if (!nla)
		return -EMSGSIZE;

309 310 311 312
	err = vport->ops->get_options(vport, skb);
	if (err) {
		nla_nest_cancel(skb, nla);
		return err;
313 314 315 316 317 318 319 320 321 322 323 324 325
	}

	nla_nest_end(skb, nla);
	return 0;
}

/**
 *	ovs_vport_receive - pass up received packet to the datapath for processing
 *
 * @vport: vport that received the packet
 * @skb: skb that was received
 *
 * Must be called with rcu_read_lock.  The packet cannot be shared and
326
 * skb->data should point to the Ethernet header.
327 328 329 330 331
 */
void ovs_vport_receive(struct vport *vport, struct sk_buff *skb)
{
	struct vport_percpu_stats *stats;

332
	stats = this_cpu_ptr(vport->percpu_stats);
333 334 335 336 337 338 339 340 341 342 343 344 345 346
	u64_stats_update_begin(&stats->sync);
	stats->rx_packets++;
	stats->rx_bytes += skb->len;
	u64_stats_update_end(&stats->sync);

	ovs_dp_process_received_packet(vport, skb);
}

/**
 *	ovs_vport_send - send a packet on a device
 *
 * @vport: vport on which to send the packet
 * @skb: skb to send
 *
347
 * Sends the given packet and returns the length of data sent.  Either ovs
348 349 350 351 352 353 354 355 356
 * lock or rcu_read_lock must be held.
 */
int ovs_vport_send(struct vport *vport, struct sk_buff *skb)
{
	int sent = vport->ops->send(vport, skb);

	if (likely(sent)) {
		struct vport_percpu_stats *stats;

357
		stats = this_cpu_ptr(vport->percpu_stats);
358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395

		u64_stats_update_begin(&stats->sync);
		stats->tx_packets++;
		stats->tx_bytes += sent;
		u64_stats_update_end(&stats->sync);
	}
	return sent;
}

/**
 *	ovs_vport_record_error - indicate device error to generic stats layer
 *
 * @vport: vport that encountered the error
 * @err_type: one of enum vport_err_type types to indicate the error type
 *
 * If using the vport generic stats layer indicate that an error of the given
 * type has occured.
 */
void ovs_vport_record_error(struct vport *vport, enum vport_err_type err_type)
{
	spin_lock(&vport->stats_lock);

	switch (err_type) {
	case VPORT_E_RX_DROPPED:
		vport->err_stats.rx_dropped++;
		break;

	case VPORT_E_RX_ERROR:
		vport->err_stats.rx_errors++;
		break;

	case VPORT_E_TX_DROPPED:
		vport->err_stats.tx_dropped++;
		break;

	case VPORT_E_TX_ERROR:
		vport->err_stats.tx_errors++;
		break;
396
	}
397 398 399

	spin_unlock(&vport->stats_lock);
}