RDMA/rxe: Use driver_unregister and new unregistration API

rxe does not have correct locking for its registration/unregistration
paths, use the core code to handle it instead. In this mode
ib_unregister_device will also do the dealloc, so rxe is required to do
clean up from a callback.

The core code ensures that unregistration is done only once, and generally
takes care of locking and concurrency problems for rxe.
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>

drivers/infiniband/sw/rxe/rxe.c

@@ -50,8 +50,10 @@ static void rxe_cleanup_ports(struct rxe_dev *rxe)
 /* free resources for a rxe device all objects created for this device must
  * have been destroyed
  */
-static void rxe_cleanup(struct rxe_dev *rxe)
+void rxe_dealloc(struct ib_device *ib_dev)
 {
+	struct rxe_dev *rxe = container_of(ib_dev, struct rxe_dev, ib_dev);
+
 	rxe_pool_cleanup(&rxe->uc_pool);
 	rxe_pool_cleanup(&rxe->pd_pool);
 	rxe_pool_cleanup(&rxe->ah_pool);
@@ -65,16 +67,10 @@ static void rxe_cleanup(struct rxe_dev *rxe)
 
 	rxe_cleanup_ports(rxe);
 
-	crypto_free_shash(rxe->tfm);
-}
+	if (rxe->tfm)
+		crypto_free_shash(rxe->tfm);
 
-/* called when all references have been dropped */
-void rxe_release(struct kref *kref)
-{
-	struct rxe_dev *rxe = container_of(kref, struct rxe_dev, ref_cnt);
-
-	rxe_cleanup(rxe);
-	ib_dealloc_device(&rxe->ib_dev);
+	list_del(&rxe->list);
 }
 
 /* initialize rxe device parameters */
@@ -312,31 +308,13 @@ int rxe_add(struct rxe_dev *rxe, unsigned int mtu)
 {
 	int err;
 
-	kref_init(&rxe->ref_cnt);
-
 	err = rxe_init(rxe);
 	if (err)
-		goto err1;
+		return err;
 
 	rxe_set_mtu(rxe, mtu);
 
-	err = rxe_register_device(rxe);
-	if (err)
-		goto err1;
-
-	return 0;
-
-err1:
-	rxe_dev_put(rxe);
-	return err;
-}
-
-/* called by the ifc layer to remove a device */
-void rxe_remove(struct rxe_dev *rxe)
-{
-	rxe_unregister_device(rxe);
-
-	rxe_dev_put(rxe);
+	return rxe_register_device(rxe);
 }
 
 static int __init rxe_module_init(void)
@@ -360,7 +338,7 @@ static int __init rxe_module_init(void)
 
 static void __exit rxe_module_exit(void)
 {
-	rxe_remove_all();
+	ib_unregister_driver(RDMA_DRIVER_RXE);
 	rxe_net_exit();
 	rxe_cache_exit();
 

drivers/infiniband/sw/rxe/rxe.h

@@ -96,15 +96,9 @@ static inline u32 rxe_crc32(struct rxe_dev *rxe,
 void rxe_set_mtu(struct rxe_dev *rxe, unsigned int dev_mtu);
 
 int rxe_add(struct rxe_dev *rxe, unsigned int mtu);
-void rxe_remove(struct rxe_dev *rxe);
-void rxe_remove_all(void);
 
 void rxe_rcv(struct sk_buff *skb);
 
-static inline void rxe_dev_put(struct rxe_dev *rxe)
-{
-	kref_put(&rxe->ref_cnt, rxe_release);
-}
 struct rxe_dev *get_rxe_by_name(const char *name);
 
 /* The caller must do a matching ib_device_put(&dev->ib_dev) */

drivers/infiniband/sw/rxe/rxe_loc.h

@@ -232,7 +232,7 @@ int rxe_srq_from_attr(struct rxe_dev *rxe, struct rxe_srq *srq,
 		      struct ib_srq_attr *attr, enum ib_srq_attr_mask mask,
 		      struct rxe_modify_srq_cmd *ucmd);
 
-void rxe_release(struct kref *kref);
+void rxe_dealloc(struct ib_device *ib_dev);
 
 int rxe_completer(void *arg);
 int rxe_requester(void *arg);

drivers/infiniband/sw/rxe/rxe_net.c

@@ -559,21 +559,6 @@ struct rxe_dev *rxe_net_add(struct net_device *ndev)
 	return rxe;
 }
 
-void rxe_remove_all(void)
-{
-	spin_lock_bh(&dev_list_lock);
-	while (!list_empty(&rxe_dev_list)) {
-		struct rxe_dev *rxe =
-			list_first_entry(&rxe_dev_list, struct rxe_dev, list);
-
-		list_del(&rxe->list);
-		spin_unlock_bh(&dev_list_lock);
-		rxe_remove(rxe);
-		spin_lock_bh(&dev_list_lock);
-	}
-	spin_unlock_bh(&dev_list_lock);
-}
-
 static void rxe_port_event(struct rxe_dev *rxe,
 			   enum ib_event_type event)
 {
@@ -631,10 +616,8 @@ static int rxe_notify(struct notifier_block *not_blk,
 
 	switch (event) {
 	case NETDEV_UNREGISTER:
-		list_del(&rxe->list);
-		ib_device_put(&rxe->ib_dev);
-		rxe_remove(rxe);
-		return NOTIFY_OK;
+		ib_unregister_device_queued(&rxe->ib_dev);
+		break;
 	case NETDEV_UP:
 		rxe_port_up(rxe);
 		break;

drivers/infiniband/sw/rxe/rxe_pool.c

@@ -398,25 +398,27 @@ void *rxe_alloc(struct rxe_pool *pool)
 	kref_get(&pool->ref_cnt);
 	read_unlock_irqrestore(&pool->pool_lock, flags);
 
-	kref_get(&pool->rxe->ref_cnt);
+	if (!ib_device_try_get(&pool->rxe->ib_dev))
+		goto out_put_pool;
 
 	if (atomic_inc_return(&pool->num_elem) > pool->max_elem)
-		goto out_put_pool;
+		goto out_cnt;
 
 	elem = kmem_cache_zalloc(pool_cache(pool),
 				 (pool->flags & RXE_POOL_ATOMIC) ?
 				 GFP_ATOMIC : GFP_KERNEL);
 	if (!elem)
-		goto out_put_pool;
+		goto out_cnt;
 
 	elem->pool = pool;
 	kref_init(&elem->ref_cnt);
 
 	return elem;
 
-out_put_pool:
+out_cnt:
 	atomic_dec(&pool->num_elem);
-	rxe_dev_put(pool->rxe);
+	ib_device_put(&pool->rxe->ib_dev);
+out_put_pool:
 	rxe_pool_put(pool);
 	return NULL;
 }
@@ -435,19 +437,21 @@ int rxe_add_to_pool(struct rxe_pool *pool, struct rxe_pool_entry *elem)
 	kref_get(&pool->ref_cnt);
 	read_unlock_irqrestore(&pool->pool_lock, flags);
 
-	kref_get(&pool->rxe->ref_cnt);
+	if (!ib_device_try_get(&pool->rxe->ib_dev))
+		goto out_put_pool;
 
 	if (atomic_inc_return(&pool->num_elem) > pool->max_elem)
-		goto out_put_pool;
+		goto out_cnt;
 
 	elem->pool = pool;
 	kref_init(&elem->ref_cnt);
 
 	return 0;
 
-out_put_pool:
+out_cnt:
 	atomic_dec(&pool->num_elem);
-	rxe_dev_put(pool->rxe);
+	ib_device_put(&pool->rxe->ib_dev);
+out_put_pool:
 	rxe_pool_put(pool);
 	return -EINVAL;
 }
@@ -464,7 +468,7 @@ void rxe_elem_release(struct kref *kref)
 	if (!(pool->flags & RXE_POOL_NO_ALLOC))
 		kmem_cache_free(pool_cache(pool), elem);
 	atomic_dec(&pool->num_elem);
-	rxe_dev_put(pool->rxe);
+	ib_device_put(&pool->rxe->ib_dev);
 	rxe_pool_put(pool);
 }
 

drivers/infiniband/sw/rxe/rxe_sysfs.c

@@ -111,7 +111,7 @@ static int rxe_param_set_remove(const char *val, const struct kernel_param *kp)
 
 	if (strncmp("all", intf, len) == 0) {
 		pr_info("rxe_sys: remove all");
-		rxe_remove_all();
+		ib_unregister_driver(RDMA_DRIVER_RXE);
 		return 0;
 	}
 
@@ -122,8 +122,7 @@ static int rxe_param_set_remove(const char *val, const struct kernel_param *kp)
 		return -EINVAL;
 	}
 
-	list_del(&rxe->list);
-	rxe_remove(rxe);
+	ib_unregister_device(&rxe->ib_dev);
 
 	return 0;
 }

drivers/infiniband/sw/rxe/rxe_verbs.c

@@ -1135,6 +1135,7 @@ static const struct ib_device_ops rxe_dev_ops = {
 	.create_cq = rxe_create_cq,
 	.create_qp = rxe_create_qp,
 	.create_srq = rxe_create_srq,
+	.dealloc_driver = rxe_dealloc,
 	.dealloc_pd = rxe_dealloc_pd,
 	.dealloc_ucontext = rxe_dealloc_ucontext,
 	.dereg_mr = rxe_dereg_mr,
@@ -1241,22 +1242,8 @@ int rxe_register_device(struct rxe_dev *rxe)
 	rdma_set_device_sysfs_group(dev, &rxe_attr_group);
 	dev->driver_id = RDMA_DRIVER_RXE;
 	err = ib_register_device(dev, "rxe%d");
-	if (err) {
+	if (err)
 		pr_warn("%s failed with error %d\n", __func__, err);
-		goto err1;
-	}
-
-	return 0;
-
-err1:
-	crypto_free_shash(rxe->tfm);
 
 	return err;
 }
-
-void rxe_unregister_device(struct rxe_dev *rxe)
-{
-	struct ib_device *dev = &rxe->ib_dev;
-
-	ib_unregister_device(dev);
-}

drivers/infiniband/sw/rxe/rxe_verbs.h

@@ -385,7 +385,6 @@ struct rxe_dev {
 	struct ib_device_attr	attr;
 	int			max_ucontext;
 	int			max_inline_data;
-	struct kref		ref_cnt;
 	struct mutex	usdev_lock;
 
 	struct net_device	*ndev;
@@ -467,7 +466,6 @@ static inline struct rxe_mem *to_rmw(struct ib_mw *mw)
 }
 
 int rxe_register_device(struct rxe_dev *rxe);
-void rxe_unregister_device(struct rxe_dev *rxe);
 
 void rxe_mc_cleanup(struct rxe_pool_entry *arg);