switchdev.c 16.7 KB
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611
// SPDX-License-Identifier: GPL-2.0-or-later
/*
 * net/switchdev/switchdev.c - Switch device API
 * Copyright (c) 2014-2015 Jiri Pirko <jiri@resnulli.us>
 * Copyright (c) 2014-2015 Scott Feldman <sfeldma@gmail.com>
 */

#include <linux/kernel.h>
#include <linux/types.h>
#include <linux/init.h>
#include <linux/mutex.h>
#include <linux/notifier.h>
#include <linux/netdevice.h>
#include <linux/etherdevice.h>
#include <linux/if_bridge.h>
#include <linux/list.h>
#include <linux/workqueue.h>
#include <linux/if_vlan.h>
#include <linux/rtnetlink.h>
#include <net/switchdev.h>

static LIST_HEAD(deferred);
static DEFINE_SPINLOCK(deferred_lock);

typedef void switchdev_deferred_func_t(struct net_device *dev,
				       const void *data);

struct switchdev_deferred_item {
	struct list_head list;
	struct net_device *dev;
	switchdev_deferred_func_t *func;
	unsigned long data[];
};

static struct switchdev_deferred_item *switchdev_deferred_dequeue(void)
{
	struct switchdev_deferred_item *dfitem;

	spin_lock_bh(&deferred_lock);
	if (list_empty(&deferred)) {
		dfitem = NULL;
		goto unlock;
	}
	dfitem = list_first_entry(&deferred,
				  struct switchdev_deferred_item, list);
	list_del(&dfitem->list);
unlock:
	spin_unlock_bh(&deferred_lock);
	return dfitem;
}

/**
 *	switchdev_deferred_process - Process ops in deferred queue
 *
 *	Called to flush the ops currently queued in deferred ops queue.
 *	rtnl_lock must be held.
 */
void switchdev_deferred_process(void)
{
	struct switchdev_deferred_item *dfitem;

	ASSERT_RTNL();

	while ((dfitem = switchdev_deferred_dequeue())) {
		dfitem->func(dfitem->dev, dfitem->data);
		dev_put(dfitem->dev);
		kfree(dfitem);
	}
}
EXPORT_SYMBOL_GPL(switchdev_deferred_process);

static void switchdev_deferred_process_work(struct work_struct *work)
{
	rtnl_lock();
	switchdev_deferred_process();
	rtnl_unlock();
}

static DECLARE_WORK(deferred_process_work, switchdev_deferred_process_work);

static int switchdev_deferred_enqueue(struct net_device *dev,
				      const void *data, size_t data_len,
				      switchdev_deferred_func_t *func)
{
	struct switchdev_deferred_item *dfitem;

	dfitem = kmalloc(sizeof(*dfitem) + data_len, GFP_ATOMIC);
	if (!dfitem)
		return -ENOMEM;
	dfitem->dev = dev;
	dfitem->func = func;
	memcpy(dfitem->data, data, data_len);
	dev_hold(dev);
	spin_lock_bh(&deferred_lock);
	list_add_tail(&dfitem->list, &deferred);
	spin_unlock_bh(&deferred_lock);
	schedule_work(&deferred_process_work);
	return 0;
}

static int switchdev_port_attr_notify(enum switchdev_notifier_type nt,
				      struct net_device *dev,
				      const struct switchdev_attr *attr,
				      struct switchdev_trans *trans)
{
	int err;
	int rc;

	struct switchdev_notifier_port_attr_info attr_info = {
		.attr = attr,
		.trans = trans,
		.handled = false,
	};

	rc = call_switchdev_blocking_notifiers(nt, dev,
					       &attr_info.info, NULL);
	err = notifier_to_errno(rc);
	if (err) {
		WARN_ON(!attr_info.handled);
		return err;
	}

	if (!attr_info.handled)
		return -EOPNOTSUPP;

	return 0;
}

static int switchdev_port_attr_set_now(struct net_device *dev,
				       const struct switchdev_attr *attr)
{
	struct switchdev_trans trans;
	int err;

	/* Phase I: prepare for attr set. Driver/device should fail
	 * here if there are going to be issues in the commit phase,
	 * such as lack of resources or support.  The driver/device
	 * should reserve resources needed for the commit phase here,
	 * but should not commit the attr.
	 */

	trans.ph_prepare = true;
	err = switchdev_port_attr_notify(SWITCHDEV_PORT_ATTR_SET, dev, attr,
					 &trans);
	if (err)
		return err;

	/* Phase II: commit attr set.  This cannot fail as a fault
	 * of driver/device.  If it does, it's a bug in the driver/device
	 * because the driver said everythings was OK in phase I.
	 */

	trans.ph_prepare = false;
	err = switchdev_port_attr_notify(SWITCHDEV_PORT_ATTR_SET, dev, attr,
					 &trans);
	WARN(err, "%s: Commit of attribute (id=%d) failed.\n",
	     dev->name, attr->id);

	return err;
}

static void switchdev_port_attr_set_deferred(struct net_device *dev,
					     const void *data)
{
	const struct switchdev_attr *attr = data;
	int err;

	err = switchdev_port_attr_set_now(dev, attr);
	if (err && err != -EOPNOTSUPP)
		netdev_err(dev, "failed (err=%d) to set attribute (id=%d)\n",
			   err, attr->id);
	if (attr->complete)
		attr->complete(dev, err, attr->complete_priv);
}

static int switchdev_port_attr_set_defer(struct net_device *dev,
					 const struct switchdev_attr *attr)
{
	return switchdev_deferred_enqueue(dev, attr, sizeof(*attr),
					  switchdev_port_attr_set_deferred);
}

/**
 *	switchdev_port_attr_set - Set port attribute
 *
 *	@dev: port device
 *	@attr: attribute to set
 *
 *	Use a 2-phase prepare-commit transaction model to ensure
 *	system is not left in a partially updated state due to
 *	failure from driver/device.
 *
 *	rtnl_lock must be held and must not be in atomic section,
 *	in case SWITCHDEV_F_DEFER flag is not set.
 */
int switchdev_port_attr_set(struct net_device *dev,
			    const struct switchdev_attr *attr)
{
	if (attr->flags & SWITCHDEV_F_DEFER)
		return switchdev_port_attr_set_defer(dev, attr);
	ASSERT_RTNL();
	return switchdev_port_attr_set_now(dev, attr);
}
EXPORT_SYMBOL_GPL(switchdev_port_attr_set);

static size_t switchdev_obj_size(const struct switchdev_obj *obj)
{
	switch (obj->id) {
	case SWITCHDEV_OBJ_ID_PORT_VLAN:
		return sizeof(struct switchdev_obj_port_vlan);
	case SWITCHDEV_OBJ_ID_PORT_MDB:
		return sizeof(struct switchdev_obj_port_mdb);
	case SWITCHDEV_OBJ_ID_HOST_MDB:
		return sizeof(struct switchdev_obj_port_mdb);
	default:
		BUG();
	}
	return 0;
}

static int switchdev_port_obj_notify(enum switchdev_notifier_type nt,
				     struct net_device *dev,
				     const struct switchdev_obj *obj,
				     struct switchdev_trans *trans,
				     struct netlink_ext_ack *extack)
{
	int rc;
	int err;

	struct switchdev_notifier_port_obj_info obj_info = {
		.obj = obj,
		.trans = trans,
		.handled = false,
	};

	rc = call_switchdev_blocking_notifiers(nt, dev, &obj_info.info, extack);
	err = notifier_to_errno(rc);
	if (err) {
		WARN_ON(!obj_info.handled);
		return err;
	}
	if (!obj_info.handled)
		return -EOPNOTSUPP;
	return 0;
}

static int switchdev_port_obj_add_now(struct net_device *dev,
				      const struct switchdev_obj *obj,
				      struct netlink_ext_ack *extack)
{
	struct switchdev_trans trans;
	int err;

	ASSERT_RTNL();

	/* Phase I: prepare for obj add. Driver/device should fail
	 * here if there are going to be issues in the commit phase,
	 * such as lack of resources or support.  The driver/device
	 * should reserve resources needed for the commit phase here,
	 * but should not commit the obj.
	 */

	trans.ph_prepare = true;
	err = switchdev_port_obj_notify(SWITCHDEV_PORT_OBJ_ADD,
					dev, obj, &trans, extack);
	if (err)
		return err;

	/* Phase II: commit obj add.  This cannot fail as a fault
	 * of driver/device.  If it does, it's a bug in the driver/device
	 * because the driver said everythings was OK in phase I.
	 */

	trans.ph_prepare = false;
	err = switchdev_port_obj_notify(SWITCHDEV_PORT_OBJ_ADD,
					dev, obj, &trans, extack);
	WARN(err, "%s: Commit of object (id=%d) failed.\n", dev->name, obj->id);

	return err;
}

static void switchdev_port_obj_add_deferred(struct net_device *dev,
					    const void *data)
{
	const struct switchdev_obj *obj = data;
	int err;

	err = switchdev_port_obj_add_now(dev, obj, NULL);
	if (err && err != -EOPNOTSUPP)
		netdev_err(dev, "failed (err=%d) to add object (id=%d)\n",
			   err, obj->id);
	if (obj->complete)
		obj->complete(dev, err, obj->complete_priv);
}

static int switchdev_port_obj_add_defer(struct net_device *dev,
					const struct switchdev_obj *obj)
{
	return switchdev_deferred_enqueue(dev, obj, switchdev_obj_size(obj),
					  switchdev_port_obj_add_deferred);
}

/**
 *	switchdev_port_obj_add - Add port object
 *
 *	@dev: port device
 *	@obj: object to add
 *	@extack: netlink extended ack
 *
 *	Use a 2-phase prepare-commit transaction model to ensure
 *	system is not left in a partially updated state due to
 *	failure from driver/device.
 *
 *	rtnl_lock must be held and must not be in atomic section,
 *	in case SWITCHDEV_F_DEFER flag is not set.
 */
int switchdev_port_obj_add(struct net_device *dev,
			   const struct switchdev_obj *obj,
			   struct netlink_ext_ack *extack)
{
	if (obj->flags & SWITCHDEV_F_DEFER)
		return switchdev_port_obj_add_defer(dev, obj);
	ASSERT_RTNL();
	return switchdev_port_obj_add_now(dev, obj, extack);
}
EXPORT_SYMBOL_GPL(switchdev_port_obj_add);

static int switchdev_port_obj_del_now(struct net_device *dev,
				      const struct switchdev_obj *obj)
{
	return switchdev_port_obj_notify(SWITCHDEV_PORT_OBJ_DEL,
					 dev, obj, NULL, NULL);
}

static void switchdev_port_obj_del_deferred(struct net_device *dev,
					    const void *data)
{
	const struct switchdev_obj *obj = data;
	int err;

	err = switchdev_port_obj_del_now(dev, obj);
	if (err && err != -EOPNOTSUPP)
		netdev_err(dev, "failed (err=%d) to del object (id=%d)\n",
			   err, obj->id);
	if (obj->complete)
		obj->complete(dev, err, obj->complete_priv);
}

static int switchdev_port_obj_del_defer(struct net_device *dev,
					const struct switchdev_obj *obj)
{
	return switchdev_deferred_enqueue(dev, obj, switchdev_obj_size(obj),
					  switchdev_port_obj_del_deferred);
}

/**
 *	switchdev_port_obj_del - Delete port object
 *
 *	@dev: port device
 *	@obj: object to delete
 *
 *	rtnl_lock must be held and must not be in atomic section,
 *	in case SWITCHDEV_F_DEFER flag is not set.
 */
int switchdev_port_obj_del(struct net_device *dev,
			   const struct switchdev_obj *obj)
{
	if (obj->flags & SWITCHDEV_F_DEFER)
		return switchdev_port_obj_del_defer(dev, obj);
	ASSERT_RTNL();
	return switchdev_port_obj_del_now(dev, obj);
}
EXPORT_SYMBOL_GPL(switchdev_port_obj_del);

static ATOMIC_NOTIFIER_HEAD(switchdev_notif_chain);
static BLOCKING_NOTIFIER_HEAD(switchdev_blocking_notif_chain);

/**
 *	register_switchdev_notifier - Register notifier
 *	@nb: notifier_block
 *
 *	Register switch device notifier.
 */
int register_switchdev_notifier(struct notifier_block *nb)
{
	return atomic_notifier_chain_register(&switchdev_notif_chain, nb);
}
EXPORT_SYMBOL_GPL(register_switchdev_notifier);

/**
 *	unregister_switchdev_notifier - Unregister notifier
 *	@nb: notifier_block
 *
 *	Unregister switch device notifier.
 */
int unregister_switchdev_notifier(struct notifier_block *nb)
{
	return atomic_notifier_chain_unregister(&switchdev_notif_chain, nb);
}
EXPORT_SYMBOL_GPL(unregister_switchdev_notifier);

/**
 *	call_switchdev_notifiers - Call notifiers
 *	@val: value passed unmodified to notifier function
 *	@dev: port device
 *	@info: notifier information data
 *	@extack: netlink extended ack
 *	Call all network notifier blocks.
 */
int call_switchdev_notifiers(unsigned long val, struct net_device *dev,
			     struct switchdev_notifier_info *info,
			     struct netlink_ext_ack *extack)
{
	info->dev = dev;
	info->extack = extack;
	return atomic_notifier_call_chain(&switchdev_notif_chain, val, info);
}
EXPORT_SYMBOL_GPL(call_switchdev_notifiers);

int register_switchdev_blocking_notifier(struct notifier_block *nb)
{
	struct blocking_notifier_head *chain = &switchdev_blocking_notif_chain;

	return blocking_notifier_chain_register(chain, nb);
}
EXPORT_SYMBOL_GPL(register_switchdev_blocking_notifier);

int unregister_switchdev_blocking_notifier(struct notifier_block *nb)
{
	struct blocking_notifier_head *chain = &switchdev_blocking_notif_chain;

	return blocking_notifier_chain_unregister(chain, nb);
}
EXPORT_SYMBOL_GPL(unregister_switchdev_blocking_notifier);

int call_switchdev_blocking_notifiers(unsigned long val, struct net_device *dev,
				      struct switchdev_notifier_info *info,
				      struct netlink_ext_ack *extack)
{
	info->dev = dev;
	info->extack = extack;
	return blocking_notifier_call_chain(&switchdev_blocking_notif_chain,
					    val, info);
}
EXPORT_SYMBOL_GPL(call_switchdev_blocking_notifiers);

static int __switchdev_handle_port_obj_add(struct net_device *dev,
			struct switchdev_notifier_port_obj_info *port_obj_info,
			bool (*check_cb)(const struct net_device *dev),
			int (*add_cb)(struct net_device *dev,
				      const struct switchdev_obj *obj,
				      struct switchdev_trans *trans,
				      struct netlink_ext_ack *extack))
{
	struct netlink_ext_ack *extack;
	struct net_device *lower_dev;
	struct list_head *iter;
	int err = -EOPNOTSUPP;

	extack = switchdev_notifier_info_to_extack(&port_obj_info->info);

	if (check_cb(dev)) {
		/* This flag is only checked if the return value is success. */
		port_obj_info->handled = true;
		return add_cb(dev, port_obj_info->obj, port_obj_info->trans,
			      extack);
	}

	/* Switch ports might be stacked under e.g. a LAG. Ignore the
	 * unsupported devices, another driver might be able to handle them. But
	 * propagate to the callers any hard errors.
	 *
	 * If the driver does its own bookkeeping of stacked ports, it's not
	 * necessary to go through this helper.
	 */
	netdev_for_each_lower_dev(dev, lower_dev, iter) {
		if (netif_is_bridge_master(lower_dev))
			continue;

		err = __switchdev_handle_port_obj_add(lower_dev, port_obj_info,
						      check_cb, add_cb);
		if (err && err != -EOPNOTSUPP)
			return err;
	}

	return err;
}

int switchdev_handle_port_obj_add(struct net_device *dev,
			struct switchdev_notifier_port_obj_info *port_obj_info,
			bool (*check_cb)(const struct net_device *dev),
			int (*add_cb)(struct net_device *dev,
				      const struct switchdev_obj *obj,
				      struct switchdev_trans *trans,
				      struct netlink_ext_ack *extack))
{
	int err;

	err = __switchdev_handle_port_obj_add(dev, port_obj_info, check_cb,
					      add_cb);
	if (err == -EOPNOTSUPP)
		err = 0;
	return err;
}
EXPORT_SYMBOL_GPL(switchdev_handle_port_obj_add);

static int __switchdev_handle_port_obj_del(struct net_device *dev,
			struct switchdev_notifier_port_obj_info *port_obj_info,
			bool (*check_cb)(const struct net_device *dev),
			int (*del_cb)(struct net_device *dev,
				      const struct switchdev_obj *obj))
{
	struct net_device *lower_dev;
	struct list_head *iter;
	int err = -EOPNOTSUPP;

	if (check_cb(dev)) {
		/* This flag is only checked if the return value is success. */
		port_obj_info->handled = true;
		return del_cb(dev, port_obj_info->obj);
	}

	/* Switch ports might be stacked under e.g. a LAG. Ignore the
	 * unsupported devices, another driver might be able to handle them. But
	 * propagate to the callers any hard errors.
	 *
	 * If the driver does its own bookkeeping of stacked ports, it's not
	 * necessary to go through this helper.
	 */
	netdev_for_each_lower_dev(dev, lower_dev, iter) {
		if (netif_is_bridge_master(lower_dev))
			continue;

		err = __switchdev_handle_port_obj_del(lower_dev, port_obj_info,
						      check_cb, del_cb);
		if (err && err != -EOPNOTSUPP)
			return err;
	}

	return err;
}

int switchdev_handle_port_obj_del(struct net_device *dev,
			struct switchdev_notifier_port_obj_info *port_obj_info,
			bool (*check_cb)(const struct net_device *dev),
			int (*del_cb)(struct net_device *dev,
				      const struct switchdev_obj *obj))
{
	int err;

	err = __switchdev_handle_port_obj_del(dev, port_obj_info, check_cb,
					      del_cb);
	if (err == -EOPNOTSUPP)
		err = 0;
	return err;
}
EXPORT_SYMBOL_GPL(switchdev_handle_port_obj_del);

static int __switchdev_handle_port_attr_set(struct net_device *dev,
			struct switchdev_notifier_port_attr_info *port_attr_info,
			bool (*check_cb)(const struct net_device *dev),
			int (*set_cb)(struct net_device *dev,
				      const struct switchdev_attr *attr,
				      struct switchdev_trans *trans))
{
	struct net_device *lower_dev;
	struct list_head *iter;
	int err = -EOPNOTSUPP;

	if (check_cb(dev)) {
		port_attr_info->handled = true;
		return set_cb(dev, port_attr_info->attr,
			      port_attr_info->trans);
	}

	/* Switch ports might be stacked under e.g. a LAG. Ignore the
	 * unsupported devices, another driver might be able to handle them. But
	 * propagate to the callers any hard errors.
	 *
	 * If the driver does its own bookkeeping of stacked ports, it's not
	 * necessary to go through this helper.
	 */
	netdev_for_each_lower_dev(dev, lower_dev, iter) {
		if (netif_is_bridge_master(lower_dev))
			continue;

		err = __switchdev_handle_port_attr_set(lower_dev, port_attr_info,
						       check_cb, set_cb);
		if (err && err != -EOPNOTSUPP)
			return err;
	}

	return err;
}

int switchdev_handle_port_attr_set(struct net_device *dev,
			struct switchdev_notifier_port_attr_info *port_attr_info,
			bool (*check_cb)(const struct net_device *dev),
			int (*set_cb)(struct net_device *dev,
				      const struct switchdev_attr *attr,
				      struct switchdev_trans *trans))
{
	int err;

	err = __switchdev_handle_port_attr_set(dev, port_attr_info, check_cb,
					       set_cb);
	if (err == -EOPNOTSUPP)
		err = 0;
	return err;
}
EXPORT_SYMBOL_GPL(switchdev_handle_port_attr_set);