Merge branch 'switchdev-transaction-item-queue'

Jiri Pirko says:

====================
switchdev: transaction item queue and cleanup
====================
Acked-by: NScott Feldman <sfeldma@gmail.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>

Documentation/networking/switchdev.txt

@@ -369,3 +369,22 @@ The driver can monitor for updates to arp_tbl using the netevent notifier
 NETEVENT_NEIGH_UPDATE.  The device can be programmed with resolved nexthops
 for the routes as arp_tbl updates.  The driver implements ndo_neigh_destroy
 to know when arp_tbl neighbor entries are purged from the port.
+
+Transaction item queue
+^^^^^^^^^^^^^^^^^^^^^^
+
+For switchdev ops attr_set and obj_add, there is a 2 phase transaction model
+used. First phase is to "prepare" anything needed, including various checks,
+memory allocation, etc. The goal is to handle the stuff that is not unlikely
+to fail here. The second phase is to "commit" the actual changes.
+
+Switchdev provides an inftrastructure for sharing items (for example memory
+allocations) between the two phases.
+
+The object created by a driver in "prepare" phase and it is queued up by:
+switchdev_trans_item_enqueue()
+During the "commit" phase, the driver gets the object by:
+switchdev_trans_item_dequeue()
+
+If a transaction is aborted during "prepare" phase, switchdev code will handle
+cleanup of the queued-up objects.

include/net/switchdev.h

 /*
  * include/net/switchdev.h - Switch device API
- * Copyright (c) 2014 Jiri Pirko <jiri@resnulli.us>
+ * 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
@@ -13,16 +13,31 @@
 
 #include <linux/netdevice.h>
 #include <linux/notifier.h>
+#include <linux/list.h>
 
 #define SWITCHDEV_F_NO_RECURSE		BIT(0)
 
-enum switchdev_trans {
-	SWITCHDEV_TRANS_NONE,
-	SWITCHDEV_TRANS_PREPARE,
-	SWITCHDEV_TRANS_ABORT,
-	SWITCHDEV_TRANS_COMMIT,
+struct switchdev_trans_item {
+	struct list_head list;
+	void *data;
+	void (*destructor)(const void *data);
 };
 
+struct switchdev_trans {
+	struct list_head item_list;
+	bool ph_prepare;
+};
+
+static inline bool switchdev_trans_ph_prepare(struct switchdev_trans *trans)
+{
+	return trans && trans->ph_prepare;
+}
+
+static inline bool switchdev_trans_ph_commit(struct switchdev_trans *trans)
+{
+	return trans && !trans->ph_prepare;
+}
+
 enum switchdev_attr_id {
 	SWITCHDEV_ATTR_UNDEFINED,
 	SWITCHDEV_ATTR_PORT_PARENT_ID,
@@ -32,7 +47,6 @@ enum switchdev_attr_id {
 
 struct switchdev_attr {
 	enum switchdev_attr_id id;
-	enum switchdev_trans trans;
 	u32 flags;
 	union {
 		struct netdev_phys_item_id ppid;	/* PORT_PARENT_ID */
@@ -52,7 +66,6 @@ enum switchdev_obj_id {
 
 struct switchdev_obj {
 	enum switchdev_obj_id id;
-	enum switchdev_trans trans;
 	int (*cb)(struct net_device *dev, struct switchdev_obj *obj);
 	union {
 		struct switchdev_obj_vlan {		/* PORT_VLAN */
@@ -77,6 +90,11 @@ struct switchdev_obj {
 	} u;
 };
 
+void switchdev_trans_item_enqueue(struct switchdev_trans *trans,
+				  void *data, void (*destructor)(void const *),
+				  struct switchdev_trans_item *tritem);
+void *switchdev_trans_item_dequeue(struct switchdev_trans *trans);
+
 /**
  * struct switchdev_ops - switchdev operations
  *
@@ -94,9 +112,11 @@ struct switchdev_ops {
 	int	(*switchdev_port_attr_get)(struct net_device *dev,
 					   struct switchdev_attr *attr);
 	int	(*switchdev_port_attr_set)(struct net_device *dev,
-					   struct switchdev_attr *attr);
+					   struct switchdev_attr *attr,
+					   struct switchdev_trans *trans);
 	int	(*switchdev_port_obj_add)(struct net_device *dev,
-					  struct switchdev_obj *obj);
+					  struct switchdev_obj *obj,
+					  struct switchdev_trans *trans);
 	int	(*switchdev_port_obj_del)(struct net_device *dev,
 					  struct switchdev_obj *obj);
 	int	(*switchdev_port_obj_dump)(struct net_device *dev,

net/dsa/slave.c

@@ -242,7 +242,8 @@ static int dsa_bridge_check_vlan_range(struct dsa_switch *ds,
 }
 
 static int dsa_slave_port_vlan_add(struct net_device *dev,
-				   struct switchdev_obj *obj)
+				   struct switchdev_obj *obj,
+				   struct switchdev_trans *trans)
 {
 	struct switchdev_obj_vlan *vlan = &obj->u.vlan;
 	struct dsa_slave_priv *p = netdev_priv(dev);
@@ -250,8 +251,7 @@ static int dsa_slave_port_vlan_add(struct net_device *dev,
 	u16 vid;
 	int err;
 
-	switch (obj->trans) {
-	case SWITCHDEV_TRANS_PREPARE:
+	if (switchdev_trans_ph_prepare(trans)) {
 		if (!ds->drv->port_vlan_add || !ds->drv->port_pvid_set)
 			return -EOPNOTSUPP;
 
@@ -263,8 +263,7 @@ static int dsa_slave_port_vlan_add(struct net_device *dev,
 						  vlan->vid_end);
 		if (err)
 			return err;
-		break;
-	case SWITCHDEV_TRANS_COMMIT:
+	} else {
 		for (vid = vlan->vid_begin; vid <= vlan->vid_end; ++vid) {
 			err = ds->drv->port_vlan_add(ds, p->port, vid,
 						     vlan->flags &
@@ -274,9 +273,6 @@ static int dsa_slave_port_vlan_add(struct net_device *dev,
 			if (err)
 				return err;
 		}
-		break;
-	default:
-		return -EOPNOTSUPP;
 	}
 
 	return 0;
@@ -347,16 +343,17 @@ static int dsa_slave_port_vlan_dump(struct net_device *dev,
 }
 
 static int dsa_slave_port_fdb_add(struct net_device *dev,
-				  struct switchdev_obj *obj)
+				  struct switchdev_obj *obj,
+				  struct switchdev_trans *trans)
 {
 	struct switchdev_obj_fdb *fdb = &obj->u.fdb;
 	struct dsa_slave_priv *p = netdev_priv(dev);
 	struct dsa_switch *ds = p->parent;
 	int ret = -EOPNOTSUPP;
 
-	if (obj->trans == SWITCHDEV_TRANS_PREPARE)
+	if (switchdev_trans_ph_prepare(trans))
 		ret = ds->drv->port_fdb_add ? 0 : -EOPNOTSUPP;
-	else if (obj->trans == SWITCHDEV_TRANS_COMMIT)
+	else
 		ret = ds->drv->port_fdb_add(ds, p->port, fdb->addr, fdb->vid);
 
 	return ret;
@@ -456,13 +453,14 @@ static int dsa_slave_stp_update(struct net_device *dev, u8 state)
 }
 
 static int dsa_slave_port_attr_set(struct net_device *dev,
-				   struct switchdev_attr *attr)
+				   struct switchdev_attr *attr,
+				   struct switchdev_trans *trans)
 {
 	int ret = 0;
 
 	switch (attr->id) {
 	case SWITCHDEV_ATTR_PORT_STP_STATE:
-		if (attr->trans == SWITCHDEV_TRANS_COMMIT)
+		if (switchdev_trans_ph_commit(trans))
 			ret = dsa_slave_stp_update(dev, attr->u.stp_state);
 		break;
 	default:
@@ -474,7 +472,8 @@ static int dsa_slave_port_attr_set(struct net_device *dev,
 }
 
 static int dsa_slave_port_obj_add(struct net_device *dev,
-				  struct switchdev_obj *obj)
+				  struct switchdev_obj *obj,
+				  struct switchdev_trans *trans)
 {
 	int err;
 
@@ -485,10 +484,10 @@ static int dsa_slave_port_obj_add(struct net_device *dev,
 
 	switch (obj->id) {
 	case SWITCHDEV_OBJ_PORT_FDB:
-		err = dsa_slave_port_fdb_add(dev, obj);
+		err = dsa_slave_port_fdb_add(dev, obj, trans);
 		break;
 	case SWITCHDEV_OBJ_PORT_VLAN:
-		err = dsa_slave_port_vlan_add(dev, obj);
+		err = dsa_slave_port_vlan_add(dev, obj, trans);
 		break;
 	default:
 		err = -EOPNOTSUPP;

net/switchdev/switchdev.c

 /*
  * net/switchdev/switchdev.c - Switch device API
- * Copyright (c) 2014 Jiri Pirko <jiri@resnulli.us>
+ * 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
@@ -16,9 +16,82 @@
 #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
  *
@@ -62,7 +135,8 @@ int switchdev_port_attr_get(struct net_device *dev, struct switchdev_attr *attr)
 EXPORT_SYMBOL_GPL(switchdev_port_attr_get);
 
 static int __switchdev_port_attr_set(struct net_device *dev,
-				     struct switchdev_attr *attr)
+				     struct switchdev_attr *attr,
+				     struct switchdev_trans *trans)
 {
 	const struct switchdev_ops *ops = dev->switchdev_ops;
 	struct net_device *lower_dev;
@@ -70,7 +144,7 @@ static int __switchdev_port_attr_set(struct net_device *dev,
 	int err = -EOPNOTSUPP;
 
 	if (ops && ops->switchdev_port_attr_set)
-		return ops->switchdev_port_attr_set(dev, attr);
+		return ops->switchdev_port_attr_set(dev, attr, trans);
 
 	if (attr->flags & SWITCHDEV_F_NO_RECURSE)
 		return err;
@@ -81,7 +155,7 @@ static int __switchdev_port_attr_set(struct net_device *dev,
 	 */
 
 	netdev_for_each_lower_dev(dev, lower_dev, iter) {
-		err = __switchdev_port_attr_set(lower_dev, attr);
+		err = __switchdev_port_attr_set(lower_dev, attr, trans);
 		if (err)
 			break;
 	}
@@ -144,6 +218,7 @@ static int switchdev_port_attr_set_defer(struct net_device *dev,
  */
 int switchdev_port_attr_set(struct net_device *dev, struct switchdev_attr *attr)
 {
+	struct switchdev_trans trans;
 	int err;
 
 	if (!rtnl_is_locked()) {
@@ -156,6 +231,8 @@ int switchdev_port_attr_set(struct net_device *dev, struct switchdev_attr *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
@@ -163,18 +240,16 @@ int switchdev_port_attr_set(struct net_device *dev, struct switchdev_attr *attr)
 	 * but should not commit the attr.
 	 */
 
-	attr->trans = SWITCHDEV_TRANS_PREPARE;
-	err = __switchdev_port_attr_set(dev, 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) {
-			attr->trans = SWITCHDEV_TRANS_ABORT;
-			__switchdev_port_attr_set(dev, attr);
-		}
+		if (err != -EOPNOTSUPP)
+			switchdev_trans_items_destroy(&trans);
 
 		return err;
 	}
@@ -184,17 +259,19 @@ int switchdev_port_attr_set(struct net_device *dev, struct switchdev_attr *attr)
 	 * because the driver said everythings was OK in phase I.
 	 */
 
-	attr->trans = SWITCHDEV_TRANS_COMMIT;
-	err = __switchdev_port_attr_set(dev, attr);
+	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_obj *obj,
+				    struct switchdev_trans *trans)
 {
 	const struct switchdev_ops *ops = dev->switchdev_ops;
 	struct net_device *lower_dev;
@@ -202,7 +279,7 @@ static int __switchdev_port_obj_add(struct net_device *dev,
 	int err = -EOPNOTSUPP;
 
 	if (ops && ops->switchdev_port_obj_add)
-		return ops->switchdev_port_obj_add(dev, obj);
+		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
@@ -210,7 +287,7 @@ static int __switchdev_port_obj_add(struct net_device *dev,
 	 */
 
 	netdev_for_each_lower_dev(dev, lower_dev, iter) {
-		err = __switchdev_port_obj_add(lower_dev, obj);
+		err = __switchdev_port_obj_add(lower_dev, obj, trans);
 		if (err)
 			break;
 	}
@@ -232,10 +309,13 @@ static int __switchdev_port_obj_add(struct net_device *dev,
  */
 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
@@ -243,18 +323,16 @@ int switchdev_port_obj_add(struct net_device *dev, struct switchdev_obj *obj)
 	 * but should not commit the obj.
 	 */
 
-	obj->trans = SWITCHDEV_TRANS_PREPARE;
-	err = __switchdev_port_obj_add(dev, 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) {
-			obj->trans = SWITCHDEV_TRANS_ABORT;
-			__switchdev_port_obj_add(dev, obj);
-		}
+		if (err != -EOPNOTSUPP)
+			switchdev_trans_items_destroy(&trans);
 
 		return err;
 	}
@@ -264,9 +342,10 @@ int switchdev_port_obj_add(struct net_device *dev, struct switchdev_obj *obj)
 	 * because the driver said everythings was OK in phase I.
 	 */
 
-	obj->trans = SWITCHDEV_TRANS_COMMIT;
-	err = __switchdev_port_obj_add(dev, obj);
+	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;
 }