1218 lines · 29.9 KB · C
RawDownload
/* * 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> * * 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/types.h>#include <linux/init.h>#include <linux/mutex.h>#include <linux/notifier.h>#include <linux/netdevice.h>#include <linux/if_bridge.h>#include <linux/list.h>#include <net/ip_fib.h>#include <net/switchdev.h> /** *	switchdev_trans_item_enqueue - Enqueue data item to transaction queue * *	@trans: transaction *	@data: pointer to data being queued *	@destructor: data destructor *	@tritem: transaction item being queued * *	Enqeueue data item to transaction queue. tritem is typically placed in *	cointainter pointed at by data pointer. Destructor is called on *	transaction abort and after successful commit phase in case *	the caller did not dequeue the item before. */void switchdev_trans_item_enqueue(struct switchdev_trans *trans,				  void *data, void (*destructor)(void const *),				  struct switchdev_trans_item *tritem){	tritem->data = data;	tritem->destructor = destructor;	list_add_tail(&tritem->list, &trans->item_list);}EXPORT_SYMBOL_GPL(switchdev_trans_item_enqueue); static struct switchdev_trans_item *__switchdev_trans_item_dequeue(struct switchdev_trans *trans){	struct switchdev_trans_item *tritem; 	if (list_empty(&trans->item_list))		return NULL;	tritem = list_first_entry(&trans->item_list,				  struct switchdev_trans_item, list);	list_del(&tritem->list);	return tritem;} /** *	switchdev_trans_item_dequeue - Dequeue data item from transaction queue * *	@trans: transaction */void *switchdev_trans_item_dequeue(struct switchdev_trans *trans){	struct switchdev_trans_item *tritem; 	tritem = __switchdev_trans_item_dequeue(trans);	BUG_ON(!tritem);	return tritem->data;}EXPORT_SYMBOL_GPL(switchdev_trans_item_dequeue); static void switchdev_trans_init(struct switchdev_trans *trans){	INIT_LIST_HEAD(&trans->item_list);} static void switchdev_trans_items_destroy(struct switchdev_trans *trans){	struct switchdev_trans_item *tritem; 	while ((tritem = __switchdev_trans_item_dequeue(trans)))		tritem->destructor(tritem->data);} static void switchdev_trans_items_warn_destroy(struct net_device *dev,					       struct switchdev_trans *trans){	WARN(!list_empty(&trans->item_list), "%s: transaction item queue is not empty.\n",	     dev->name);	switchdev_trans_items_destroy(trans);} /** *	switchdev_port_attr_get - Get port attribute * *	@dev: port device *	@attr: attribute to get */int switchdev_port_attr_get(struct net_device *dev, struct switchdev_attr *attr){	const struct switchdev_ops *ops = dev->switchdev_ops;	struct net_device *lower_dev;	struct list_head *iter;	struct switchdev_attr first = {		.id = SWITCHDEV_ATTR_UNDEFINED	};	int err = -EOPNOTSUPP; 	if (ops && ops->switchdev_port_attr_get)		return ops->switchdev_port_attr_get(dev, attr); 	if (attr->flags & SWITCHDEV_F_NO_RECURSE)		return err; 	/* Switch device port(s) may be stacked under	 * bond/team/vlan dev, so recurse down to get attr on	 * each port.  Return -ENODATA if attr values don't	 * compare across ports.	 */ 	netdev_for_each_lower_dev(dev, lower_dev, iter) {		err = switchdev_port_attr_get(lower_dev, attr);		if (err)			break;		if (first.id == SWITCHDEV_ATTR_UNDEFINED)			first = *attr;		else if (memcmp(&first, attr, sizeof(*attr)))			return -ENODATA;	} 	return err;}EXPORT_SYMBOL_GPL(switchdev_port_attr_get); static int __switchdev_port_attr_set(struct net_device *dev,				     struct switchdev_attr *attr,				     struct switchdev_trans *trans){	const struct switchdev_ops *ops = dev->switchdev_ops;	struct net_device *lower_dev;	struct list_head *iter;	int err = -EOPNOTSUPP; 	if (ops && ops->switchdev_port_attr_set)		return ops->switchdev_port_attr_set(dev, attr, trans); 	if (attr->flags & SWITCHDEV_F_NO_RECURSE)		return err; 	/* Switch device port(s) may be stacked under	 * bond/team/vlan dev, so recurse down to set attr on	 * each port.	 */ 	netdev_for_each_lower_dev(dev, lower_dev, iter) {		err = __switchdev_port_attr_set(lower_dev, attr, trans);		if (err)			break;	} 	return err;} struct switchdev_attr_set_work {	struct work_struct work;	struct net_device *dev;	struct switchdev_attr attr;}; static void switchdev_port_attr_set_work(struct work_struct *work){	struct switchdev_attr_set_work *asw =		container_of(work, struct switchdev_attr_set_work, work);	int err; 	rtnl_lock();	err = switchdev_port_attr_set(asw->dev, &asw->attr);	if (err && err != -EOPNOTSUPP)		netdev_err(asw->dev, "failed (err=%d) to set attribute (id=%d)\n",			   err, asw->attr.id);	rtnl_unlock(); 	dev_put(asw->dev);	kfree(work);} static int switchdev_port_attr_set_defer(struct net_device *dev,					 struct switchdev_attr *attr){	struct switchdev_attr_set_work *asw; 	asw = kmalloc(sizeof(*asw), GFP_ATOMIC);	if (!asw)		return -ENOMEM; 	INIT_WORK(&asw->work, switchdev_port_attr_set_work); 	dev_hold(dev);	asw->dev = dev;	memcpy(&asw->attr, attr, sizeof(asw->attr)); 	schedule_work(&asw->work); 	return 0;} /** *	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. */int switchdev_port_attr_set(struct net_device *dev, struct switchdev_attr *attr){	struct switchdev_trans trans;	int err; 	if (!rtnl_is_locked()) {		/* Running prepare-commit transaction across stacked		 * devices requires nothing moves, so if rtnl_lock is		 * not held, schedule a worker thread to hold rtnl_lock		 * while setting attr.		 */ 		return switchdev_port_attr_set_defer(dev, attr);	} 	switchdev_trans_init(&trans); 	/* 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_set(dev, attr, &trans);	if (err) {		/* Prepare phase failed: abort the transaction.  Any		 * resources reserved in the prepare phase are		 * released.		 */ 		if (err != -EOPNOTSUPP)			switchdev_trans_items_destroy(&trans); 		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_set(dev, attr, &trans);	WARN(err, "%s: Commit of attribute (id=%d) failed.\n",	     dev->name, attr->id);	switchdev_trans_items_warn_destroy(dev, &trans); 	return err;}EXPORT_SYMBOL_GPL(switchdev_port_attr_set); static int __switchdev_port_obj_add(struct net_device *dev,				    struct switchdev_obj *obj,				    struct switchdev_trans *trans){	const struct switchdev_ops *ops = dev->switchdev_ops;	struct net_device *lower_dev;	struct list_head *iter;	int err = -EOPNOTSUPP; 	if (ops && ops->switchdev_port_obj_add)		return ops->switchdev_port_obj_add(dev, obj, trans); 	/* Switch device port(s) may be stacked under	 * bond/team/vlan dev, so recurse down to add object on	 * each port.	 */ 	netdev_for_each_lower_dev(dev, lower_dev, iter) {		err = __switchdev_port_obj_add(lower_dev, obj, trans);		if (err)			break;	} 	return err;} /** *	switchdev_port_obj_add - Add port object * *	@dev: port device *	@obj: object to add * *	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. */int switchdev_port_obj_add(struct net_device *dev, struct switchdev_obj *obj){	struct switchdev_trans trans;	int err; 	ASSERT_RTNL(); 	switchdev_trans_init(&trans); 	/* 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_add(dev, obj, &trans);	if (err) {		/* Prepare phase failed: abort the transaction.  Any		 * resources reserved in the prepare phase are		 * released.		 */ 		if (err != -EOPNOTSUPP)			switchdev_trans_items_destroy(&trans); 		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_add(dev, obj, &trans);	WARN(err, "%s: Commit of object (id=%d) failed.\n", dev->name, obj->id);	switchdev_trans_items_warn_destroy(dev, &trans); 	return err;}EXPORT_SYMBOL_GPL(switchdev_port_obj_add); /** *	switchdev_port_obj_del - Delete port object * *	@dev: port device *	@obj: object to delete */int switchdev_port_obj_del(struct net_device *dev, struct switchdev_obj *obj){	const struct switchdev_ops *ops = dev->switchdev_ops;	struct net_device *lower_dev;	struct list_head *iter;	int err = -EOPNOTSUPP; 	if (ops && ops->switchdev_port_obj_del)		return ops->switchdev_port_obj_del(dev, obj); 	/* Switch device port(s) may be stacked under	 * bond/team/vlan dev, so recurse down to delete object on	 * each port.	 */ 	netdev_for_each_lower_dev(dev, lower_dev, iter) {		err = switchdev_port_obj_del(lower_dev, obj);		if (err)			break;	} 	return err;}EXPORT_SYMBOL_GPL(switchdev_port_obj_del); /** *	switchdev_port_obj_dump - Dump port objects * *	@dev: port device *	@obj: object to dump */int switchdev_port_obj_dump(struct net_device *dev, struct switchdev_obj *obj){	const struct switchdev_ops *ops = dev->switchdev_ops;	struct net_device *lower_dev;	struct list_head *iter;	int err = -EOPNOTSUPP; 	if (ops && ops->switchdev_port_obj_dump)		return ops->switchdev_port_obj_dump(dev, obj); 	/* Switch device port(s) may be stacked under	 * bond/team/vlan dev, so recurse down to dump objects on	 * first port at bottom of stack.	 */ 	netdev_for_each_lower_dev(dev, lower_dev, iter) {		err = switchdev_port_obj_dump(lower_dev, obj);		break;	} 	return err;}EXPORT_SYMBOL_GPL(switchdev_port_obj_dump); static DEFINE_MUTEX(switchdev_mutex);static RAW_NOTIFIER_HEAD(switchdev_notif_chain); /** *	register_switchdev_notifier - Register notifier *	@nb: notifier_block * *	Register switch device notifier. This should be used by code *	which needs to monitor events happening in particular device. *	Return values are same as for atomic_notifier_chain_register(). */int register_switchdev_notifier(struct notifier_block *nb){	int err; 	mutex_lock(&switchdev_mutex);	err = raw_notifier_chain_register(&switchdev_notif_chain, nb);	mutex_unlock(&switchdev_mutex);	return err;}EXPORT_SYMBOL_GPL(register_switchdev_notifier); /** *	unregister_switchdev_notifier - Unregister notifier *	@nb: notifier_block * *	Unregister switch device notifier. *	Return values are same as for atomic_notifier_chain_unregister(). */int unregister_switchdev_notifier(struct notifier_block *nb){	int err; 	mutex_lock(&switchdev_mutex);	err = raw_notifier_chain_unregister(&switchdev_notif_chain, nb);	mutex_unlock(&switchdev_mutex);	return err;}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 * *	Call all network notifier blocks. This should be called by driver *	when it needs to propagate hardware event. *	Return values are same as for atomic_notifier_call_chain(). */int call_switchdev_notifiers(unsigned long val, struct net_device *dev,			     struct switchdev_notifier_info *info){	int err; 	info->dev = dev;	mutex_lock(&switchdev_mutex);	err = raw_notifier_call_chain(&switchdev_notif_chain, val, info);	mutex_unlock(&switchdev_mutex);	return err;}EXPORT_SYMBOL_GPL(call_switchdev_notifiers); struct switchdev_vlan_dump {	struct switchdev_obj obj;	struct sk_buff *skb;	u32 filter_mask;	u16 flags;	u16 begin;	u16 end;}; static int switchdev_port_vlan_dump_put(struct switchdev_vlan_dump *dump){	struct bridge_vlan_info vinfo; 	vinfo.flags = dump->flags; 	if (dump->begin == 0 && dump->end == 0) {		return 0;	} else if (dump->begin == dump->end) {		vinfo.vid = dump->begin;		if (nla_put(dump->skb, IFLA_BRIDGE_VLAN_INFO,			    sizeof(vinfo), &vinfo))			return -EMSGSIZE;	} else {

Lines 1–500 of 1218.