RDMA/core: Support IB sub device with type "SMI"

This patch adds 2 APIs, as well as driver operations to support adding
and deleting an IB sub device, which provides part of functionalities
of it's parent.

A sub device has a type; for a sub device with type "SMI", it provides
the smi capability through umad for its parent, meaning uverb is not
supported.

A sub device cannot live without a parent. So when a parent is
released, all it's sub devices are released as well.

Signed-off-by: Mark Zhang <markzhang@nvidia.com>
Link: https://lore.kernel.org/r/44253f7508b21eb2caefea3980c2bc072869116c.1718553901.git.leon@kernel.org
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>

2 files changed, 71 insertions, 1 deletions

diff --git a/drivers/infiniband/core/device.c b/drivers/infiniband/core/device.c
index e0cff28bb0ef..7b418c717f29 100644
--- a/drivers/infiniband/core/device.c
+++ b/drivers/infiniband/core/device.c
@@ -503,6 +503,7 @@ static void ib_device_release(struct device *device)
 			  rcu_head);
 	}
 
+	mutex_destroy(&dev->subdev_lock);
 	mutex_destroy(&dev->unregistration_lock);
 	mutex_destroy(&dev->compat_devs_mutex);
 
@@ -641,6 +642,11 @@ struct ib_device *_ib_alloc_device(size_t size)
 		BIT_ULL(IB_USER_VERBS_CMD_REG_MR) |
 		BIT_ULL(IB_USER_VERBS_CMD_REREG_MR) |
 		BIT_ULL(IB_USER_VERBS_CMD_RESIZE_CQ);
+
+	mutex_init(&device->subdev_lock);
+	INIT_LIST_HEAD(&device->subdev_list_head);
+	INIT_LIST_HEAD(&device->subdev_list);
+
 	return device;
 }
 EXPORT_SYMBOL(_ib_alloc_device);
@@ -1461,6 +1467,18 @@ EXPORT_SYMBOL(ib_register_device);
 /* Callers must hold a get on the device. */
 static void __ib_unregister_device(struct ib_device *ib_dev)
 {
+	struct ib_device *sub, *tmp;
+
+	mutex_lock(&ib_dev->subdev_lock);
+	list_for_each_entry_safe_reverse(sub, tmp,
+					 &ib_dev->subdev_list_head,
+					 subdev_list) {
+		list_del(&sub->subdev_list);
+		ib_dev->ops.del_sub_dev(sub);
+		ib_device_put(ib_dev);
+	}
+	mutex_unlock(&ib_dev->subdev_lock);
+
 	/*
 	 * We have a registration lock so that all the calls to unregister are
 	 * fully fenced, once any unregister returns the device is truely
@@ -2597,6 +2615,7 @@ void ib_set_device_ops(struct ib_device *dev, const struct ib_device_ops *ops)
 		ops->uverbs_no_driver_id_binding;
 
 	SET_DEVICE_OP(dev_ops, add_gid);
+	SET_DEVICE_OP(dev_ops, add_sub_dev);
 	SET_DEVICE_OP(dev_ops, advise_mr);
 	SET_DEVICE_OP(dev_ops, alloc_dm);
 	SET_DEVICE_OP(dev_ops, alloc_hw_device_stats);
@@ -2631,6 +2650,7 @@ void ib_set_device_ops(struct ib_device *dev, const struct ib_device_ops *ops)
 	SET_DEVICE_OP(dev_ops, dealloc_ucontext);
 	SET_DEVICE_OP(dev_ops, dealloc_xrcd);
 	SET_DEVICE_OP(dev_ops, del_gid);
+	SET_DEVICE_OP(dev_ops, del_sub_dev);
 	SET_DEVICE_OP(dev_ops, dereg_mr);
 	SET_DEVICE_OP(dev_ops, destroy_ah);
 	SET_DEVICE_OP(dev_ops, destroy_counters);
@@ -2727,6 +2747,55 @@ void ib_set_device_ops(struct ib_device *dev, const struct ib_device_ops *ops)
 }
 EXPORT_SYMBOL(ib_set_device_ops);
 
+int ib_add_sub_device(struct ib_device *parent,
+		      enum rdma_nl_dev_type type,
+		      const char *name)
+{
+	struct ib_device *sub;
+	int ret = 0;
+
+	if (!parent->ops.add_sub_dev || !parent->ops.del_sub_dev)
+		return -EOPNOTSUPP;
+
+	if (!ib_device_try_get(parent))
+		return -EINVAL;
+
+	sub = parent->ops.add_sub_dev(parent, type, name);
+	if (IS_ERR(sub)) {
+		ib_device_put(parent);
+		return PTR_ERR(sub);
+	}
+
+	sub->type = type;
+	sub->parent = parent;
+
+	mutex_lock(&parent->subdev_lock);
+	list_add_tail(&parent->subdev_list_head, &sub->subdev_list);
+	mutex_unlock(&parent->subdev_lock);
+
+	return ret;
+}
+EXPORT_SYMBOL(ib_add_sub_device);
+
+int ib_del_sub_device_and_put(struct ib_device *sub)
+{
+	struct ib_device *parent = sub->parent;
+
+	if (!parent)
+		return -EOPNOTSUPP;
+
+	mutex_lock(&parent->subdev_lock);
+	list_del(&sub->subdev_list);
+	mutex_unlock(&parent->subdev_lock);
+
+	ib_device_put(sub);
+	parent->ops.del_sub_dev(sub);
+	ib_device_put(parent);
+
+	return 0;
+}
+EXPORT_SYMBOL(ib_del_sub_device_and_put);
+
 #ifdef CONFIG_INFINIBAND_VIRT_DMA
 int ib_dma_virt_map_sg(struct ib_device *dev, struct scatterlist *sg, int nents)
 {
diff --git a/drivers/infiniband/core/uverbs_main.c b/drivers/infiniband/core/uverbs_main.c
index 495d5a5d0373..bc099287de9a 100644
--- a/drivers/infiniband/core/uverbs_main.c
+++ b/drivers/infiniband/core/uverbs_main.c
@@ -1114,7 +1114,8 @@ static int ib_uverbs_add_one(struct ib_device *device)
 	struct ib_uverbs_device *uverbs_dev;
 	int ret;
 
-	if (!device->ops.alloc_ucontext)
+	if (!device->ops.alloc_ucontext ||
+	    device->type == RDMA_DEVICE_TYPE_SMI)
 		return -EOPNOTSUPP;
 
 	uverbs_dev = kzalloc(sizeof(*uverbs_dev), GFP_KERNEL);