IB/mlx5: Enable subscription for device events over DEVX

Enable subscription for device events over DEVX.

Each subscription is added to the two level xarray data structure
according to its event number and the DEVX object information in case was
given with the given target fd.

Those events will be reported over the given fd once will occur.
Downstream patches will mange the dispatching to any subscription.

Signed-off-by: Yishai Hadas <yishaih@mellanox.com>
Signed-off-by: Leon Romanovsky <leonro@mellanox.com>
Reviewed-by: Jason Gunthorpe <jgg@mellanox.com>
Signed-off-by: Jason Gunthorpe <jgg@mellanox.com>

2 files changed, 562 insertions, 7 deletions

diff --git a/drivers/infiniband/hw/mlx5/devx.c b/drivers/infiniband/hw/mlx5/devx.c
index a9affc905bfa..9c21cafc44a6 100644
--- a/drivers/infiniband/hw/mlx5/devx.c
+++ b/drivers/infiniband/hw/mlx5/devx.c
@@ -14,6 +14,7 @@
 #include <linux/mlx5/driver.h>
 #include <linux/mlx5/fs.h>
 #include "mlx5_ib.h"
+#include <linux/xarray.h>
 
 #define UVERBS_MODULE_NAME mlx5_ib
 #include <rdma/uverbs_named_ioctl.h>
@@ -33,6 +34,40 @@ struct devx_async_data {
 	struct mlx5_ib_uapi_devx_async_cmd_hdr hdr;
 };
 
+/* first level XA value data structure */
+struct devx_event {
+	struct xarray object_ids; /* second XA level, Key = object id */
+	struct list_head unaffiliated_list;
+};
+
+/* second level XA value data structure */
+struct devx_obj_event {
+	struct rcu_head rcu;
+	struct list_head obj_sub_list;
+};
+
+struct devx_event_subscription {
+	struct list_head file_list; /* headed in ev_file->
+				     * subscribed_events_list
+				     */
+	struct list_head xa_list; /* headed in devx_event->unaffiliated_list or
+				   * devx_obj_event->obj_sub_list
+				   */
+	struct list_head obj_list; /* headed in devx_object */
+	struct list_head event_list; /* headed in ev_file->event_list or in
+				      * temp list via subscription
+				      */
+
+	u8 is_cleaned:1;
+	u32 xa_key_level1;
+	u32 xa_key_level2;
+	struct rcu_head	rcu;
+	u64 cookie;
+	struct devx_async_event_file *ev_file;
+	struct file *filp; /* Upon hot unplug we need a direct access to */
+	struct eventfd_ctx *eventfd;
+};
+
 struct devx_async_event_file {
 	struct ib_uobject uobj;
 	/* Head of events that are subscribed to this FD */
@@ -55,6 +90,7 @@ struct devx_obj {
 		struct mlx5_ib_devx_mr	devx_mr;
 		struct mlx5_core_dct	core_dct;
 	};
+	struct list_head event_sub; /* holds devx_event_subscription entries */
 };
 
 struct devx_umem {
@@ -160,6 +196,104 @@ bool mlx5_ib_devx_is_flow_counter(void *obj, u32 *counter_id)
 	return false;
 }
 
+static bool is_legacy_unaffiliated_event_num(u16 event_num)
+{
+	switch (event_num) {
+	case MLX5_EVENT_TYPE_PORT_CHANGE:
+		return true;
+	default:
+		return false;
+	}
+}
+
+static bool is_legacy_obj_event_num(u16 event_num)
+{
+	switch (event_num) {
+	case MLX5_EVENT_TYPE_PATH_MIG:
+	case MLX5_EVENT_TYPE_COMM_EST:
+	case MLX5_EVENT_TYPE_SQ_DRAINED:
+	case MLX5_EVENT_TYPE_SRQ_LAST_WQE:
+	case MLX5_EVENT_TYPE_SRQ_RQ_LIMIT:
+	case MLX5_EVENT_TYPE_CQ_ERROR:
+	case MLX5_EVENT_TYPE_WQ_CATAS_ERROR:
+	case MLX5_EVENT_TYPE_PATH_MIG_FAILED:
+	case MLX5_EVENT_TYPE_WQ_INVAL_REQ_ERROR:
+	case MLX5_EVENT_TYPE_WQ_ACCESS_ERROR:
+	case MLX5_EVENT_TYPE_SRQ_CATAS_ERROR:
+	case MLX5_EVENT_TYPE_DCT_DRAINED:
+	case MLX5_EVENT_TYPE_COMP:
+		return true;
+	default:
+		return false;
+	}
+}
+
+static u16 get_legacy_obj_type(u16 opcode)
+{
+	switch (opcode) {
+	case MLX5_CMD_OP_CREATE_RQ:
+		return MLX5_EVENT_QUEUE_TYPE_RQ;
+	case MLX5_CMD_OP_CREATE_QP:
+		return MLX5_EVENT_QUEUE_TYPE_QP;
+	case MLX5_CMD_OP_CREATE_SQ:
+		return MLX5_EVENT_QUEUE_TYPE_SQ;
+	case MLX5_CMD_OP_CREATE_DCT:
+		return MLX5_EVENT_QUEUE_TYPE_DCT;
+	default:
+		return 0;
+	}
+}
+
+static u16 get_dec_obj_type(struct devx_obj *obj, u16 event_num)
+{
+	u16 opcode;
+
+	opcode = (obj->obj_id >> 32) & 0xffff;
+
+	if (is_legacy_obj_event_num(event_num))
+		return get_legacy_obj_type(opcode);
+
+	switch (opcode) {
+	case MLX5_CMD_OP_CREATE_GENERAL_OBJECT:
+		return (obj->obj_id >> 48);
+	case MLX5_CMD_OP_CREATE_RQ:
+		return MLX5_OBJ_TYPE_RQ;
+	case MLX5_CMD_OP_CREATE_QP:
+		return MLX5_OBJ_TYPE_QP;
+	case MLX5_CMD_OP_CREATE_SQ:
+		return MLX5_OBJ_TYPE_SQ;
+	case MLX5_CMD_OP_CREATE_DCT:
+		return MLX5_OBJ_TYPE_DCT;
+	case MLX5_CMD_OP_CREATE_TIR:
+		return MLX5_OBJ_TYPE_TIR;
+	case MLX5_CMD_OP_CREATE_TIS:
+		return MLX5_OBJ_TYPE_TIS;
+	case MLX5_CMD_OP_CREATE_PSV:
+		return MLX5_OBJ_TYPE_PSV;
+	case MLX5_OBJ_TYPE_MKEY:
+		return MLX5_OBJ_TYPE_MKEY;
+	case MLX5_CMD_OP_CREATE_RMP:
+		return MLX5_OBJ_TYPE_RMP;
+	case MLX5_CMD_OP_CREATE_XRC_SRQ:
+		return MLX5_OBJ_TYPE_XRC_SRQ;
+	case MLX5_CMD_OP_CREATE_XRQ:
+		return MLX5_OBJ_TYPE_XRQ;
+	case MLX5_CMD_OP_CREATE_RQT:
+		return MLX5_OBJ_TYPE_RQT;
+	case MLX5_CMD_OP_ALLOC_FLOW_COUNTER:
+		return MLX5_OBJ_TYPE_FLOW_COUNTER;
+	case MLX5_CMD_OP_CREATE_CQ:
+		return MLX5_OBJ_TYPE_CQ;
+	default:
+		return 0;
+	}
+}
+
+static u32 get_dec_obj_id(u64 obj_id)
+{
+	return (obj_id & 0xffffffff);
+}
+
 /*
  * As the obj_id in the firmware is not globally unique the object type
  * must be considered upon checking for a valid object id.
@@ -1126,14 +1260,47 @@ static void devx_cleanup_mkey(struct devx_obj *obj)
 		 mlx5_base_mkey(obj->devx_mr.mmkey.key));
 }
 
+static void devx_cleanup_subscription(struct mlx5_ib_dev *dev,
+				      struct devx_event_subscription *sub)
+{
+	struct devx_event *event;
+	struct devx_obj_event *xa_val_level2;
+
+	if (sub->is_cleaned)
+		return;
+
+	sub->is_cleaned = 1;
+	list_del_rcu(&sub->xa_list);
+
+	if (list_empty(&sub->obj_list))
+		return;
+
+	list_del_rcu(&sub->obj_list);
+	/* check whether key level 1 for this obj_sub_list is empty */
+	event = xa_load(&dev->devx_event_table.event_xa,
+			sub->xa_key_level1);
+	WARN_ON(!event);
+
+	xa_val_level2 = xa_load(&event->object_ids, sub->xa_key_level2);
+	if (list_empty(&xa_val_level2->obj_sub_list)) {
+		xa_erase(&event->object_ids,
+			 sub->xa_key_level2);
+		kfree_rcu(xa_val_level2, rcu);
+	}
+}
+
 static int devx_obj_cleanup(struct ib_uobject *uobject,
 			    enum rdma_remove_reason why,
 			    struct uverbs_attr_bundle *attrs)
 {
 	u32 out[MLX5_ST_SZ_DW(general_obj_out_cmd_hdr)];
+	struct mlx5_devx_event_table *devx_event_table;
 	struct devx_obj *obj = uobject->object;
+	struct devx_event_subscription *sub_entry, *tmp;
+	struct mlx5_ib_dev *dev;
 	int ret;
 
+	dev = mlx5_udata_to_mdev(&attrs->driver_udata);
 	if (obj->flags & DEVX_OBJ_FLAGS_INDIRECT_MKEY)
 		devx_cleanup_mkey(obj);
 
@@ -1145,10 +1312,14 @@ static int devx_obj_cleanup(struct ib_uobject *uobject,
 	if (ib_is_destroy_retryable(ret, why, uobject))
 		return ret;
 
-	if (obj->flags & DEVX_OBJ_FLAGS_INDIRECT_MKEY) {
-		struct mlx5_ib_dev *dev =
-			mlx5_udata_to_mdev(&attrs->driver_udata);
+	devx_event_table = &dev->devx_event_table;
+
+	mutex_lock(&devx_event_table->event_xa_lock);
+	list_for_each_entry_safe(sub_entry, tmp, &obj->event_sub, obj_list)
+		devx_cleanup_subscription(dev, sub_entry);
+	mutex_unlock(&devx_event_table->event_xa_lock);
 
+	if (obj->flags & DEVX_OBJ_FLAGS_INDIRECT_MKEY) {
 		call_srcu(&dev->mr_srcu, &obj->devx_mr.rcu,
 			  devx_free_indirect_mkey);
 		return ret;
@@ -1220,6 +1391,7 @@ static int UVERBS_HANDLER(MLX5_IB_METHOD_DEVX_OBJ_CREATE)(
 
 	uobj->object = obj;
 	obj->mdev = dev->mdev;
+	INIT_LIST_HEAD(&obj->event_sub);
 	devx_obj_build_destroy_cmd(cmd_in, cmd_out, obj->dinbox, &obj->dinlen,
 				   &obj_id);
 	WARN_ON(obj->dinlen > MLX5_MAX_DESTROY_INBOX_SIZE_DW * sizeof(u32));
@@ -1404,6 +1576,7 @@ static int UVERBS_HANDLER(MLX5_IB_METHOD_DEVX_ASYNC_EVENT_FD_ALLOC)(
 		ev_file->omit_data = 1;
 	INIT_LIST_HEAD(&ev_file->subscribed_events_list);
 	ev_file->dev = dev;
+	get_device(&dev->ib_dev.dev);
 	return 0;
 }
 
@@ -1516,6 +1689,331 @@ sub_bytes:
 	return err;
 }
 
+static void
+subscribe_event_xa_dealloc(struct mlx5_devx_event_table *devx_event_table,
+			   u32 key_level1,
+			   bool is_level2,
+			   u32 key_level2)
+{
+	struct devx_event *event;
+	struct devx_obj_event *xa_val_level2;
+
+	/* Level 1 is valid for future use, no need to free */
+	if (!is_level2)
+		return;
+
+	event = xa_load(&devx_event_table->event_xa, key_level1);
+	WARN_ON(!event);
+
+	xa_val_level2 = xa_load(&event->object_ids,
+				key_level2);
+	if (list_empty(&xa_val_level2->obj_sub_list)) {
+		xa_erase(&event->object_ids,
+			 key_level2);
+		kfree_rcu(xa_val_level2, rcu);
+	}
+}
+
+static int
+subscribe_event_xa_alloc(struct mlx5_devx_event_table *devx_event_table,
+			 u32 key_level1,
+			 bool is_level2,
+			 u32 key_level2)
+{
+	struct devx_obj_event *obj_event;
+	struct devx_event *event;
+	int err;
+
+	event = xa_load(&devx_event_table->event_xa, key_level1);
+	if (!event) {
+		event = kzalloc(sizeof(*event), GFP_KERNEL);
+		if (!event)
+			return -ENOMEM;
+
+		INIT_LIST_HEAD(&event->unaffiliated_list);
+		xa_init(&event->object_ids);
+
+		err = xa_insert(&devx_event_table->event_xa,
+				key_level1,
+				event,
+				GFP_KERNEL);
+		if (err) {
+			kfree(event);
+			return err;
+		}
+	}
+
+	if (!is_level2)
+		return 0;
+
+	obj_event = xa_load(&event->object_ids, key_level2);
+	if (!obj_event) {
+		obj_event = kzalloc(sizeof(*obj_event), GFP_KERNEL);
+		if (!obj_event)
+			/* Level1 is valid for future use, no need to free */
+			return -ENOMEM;
+
+		err = xa_insert(&event->object_ids,
+				key_level2,
+				obj_event,
+				GFP_KERNEL);
+		if (err)
+			return err;
+		INIT_LIST_HEAD(&obj_event->obj_sub_list);
+	}
+
+	return 0;
+}
+
+static bool is_valid_events_legacy(int num_events, u16 *event_type_num_list,
+				   struct devx_obj *obj)
+{
+	int i;
+
+	for (i = 0; i < num_events; i++) {
+		if (obj) {
+			if (!is_legacy_obj_event_num(event_type_num_list[i]))
+				return false;
+		} else if (!is_legacy_unaffiliated_event_num(
+				event_type_num_list[i])) {
+			return false;
+		}
+	}
+
+	return true;
+}
+
+#define MAX_SUPP_EVENT_NUM 255
+static bool is_valid_events(struct mlx5_core_dev *dev,
+			    int num_events, u16 *event_type_num_list,
+			    struct devx_obj *obj)
+{
+	__be64 *aff_events;
+	__be64 *unaff_events;
+	int mask_entry;
+	int mask_bit;
+	int i;
+
+	if (MLX5_CAP_GEN(dev, event_cap)) {
+		aff_events = MLX5_CAP_DEV_EVENT(dev,
+						user_affiliated_events);
+		unaff_events = MLX5_CAP_DEV_EVENT(dev,
+						  user_unaffiliated_events);
+	} else {
+		return is_valid_events_legacy(num_events, event_type_num_list,
+					      obj);
+	}
+
+	for (i = 0; i < num_events; i++) {
+		if (event_type_num_list[i] > MAX_SUPP_EVENT_NUM)
+			return false;
+
+		mask_entry = event_type_num_list[i] / 64;
+		mask_bit = event_type_num_list[i] % 64;
+
+		if (obj) {
+			/* CQ completion */
+			if (event_type_num_list[i] == 0)
+				continue;
+
+			if (!(be64_to_cpu(aff_events[mask_entry]) &
+					(1ull << mask_bit)))
+				return false;
+
+			continue;
+		}
+
+		if (!(be64_to_cpu(unaff_events[mask_entry]) &
+				(1ull << mask_bit)))
+			return false;
+	}
+
+	return true;
+}
+
+#define MAX_NUM_EVENTS 16
+static int UVERBS_HANDLER(MLX5_IB_METHOD_DEVX_SUBSCRIBE_EVENT)(
+	struct uverbs_attr_bundle *attrs)
+{
+	struct ib_uobject *devx_uobj = uverbs_attr_get_uobject(
+				attrs,
+				MLX5_IB_ATTR_DEVX_SUBSCRIBE_EVENT_OBJ_HANDLE);
+	struct mlx5_ib_ucontext *c = rdma_udata_to_drv_context(
+		&attrs->driver_udata, struct mlx5_ib_ucontext, ibucontext);
+	struct mlx5_ib_dev *dev = to_mdev(c->ibucontext.device);
+	struct ib_uobject *fd_uobj;
+	struct devx_obj *obj = NULL;
+	struct devx_async_event_file *ev_file;
+	struct mlx5_devx_event_table *devx_event_table = &dev->devx_event_table;
+	u16 *event_type_num_list;
+	struct devx_event_subscription *event_sub, *tmp_sub;
+	struct list_head sub_list;
+	int redirect_fd;
+	bool use_eventfd = false;
+	int num_events;
+	int num_alloc_xa_entries = 0;
+	u16 obj_type = 0;
+	u64 cookie = 0;
+	u32 obj_id = 0;
+	int err;
+	int i;
+
+	if (!c->devx_uid)
+		return -EINVAL;
+
+	if (!IS_ERR(devx_uobj)) {
+		obj = (struct devx_obj *)devx_uobj->object;
+		if (obj)
+			obj_id = get_dec_obj_id(obj->obj_id);
+	}
+
+	fd_uobj = uverbs_attr_get_uobject(attrs,
+				MLX5_IB_ATTR_DEVX_SUBSCRIBE_EVENT_FD_HANDLE);
+	if (IS_ERR(fd_uobj))
+		return PTR_ERR(fd_uobj);
+
+	ev_file = container_of(fd_uobj, struct devx_async_event_file,
+			       uobj);
+
+	if (uverbs_attr_is_valid(attrs,
+				 MLX5_IB_ATTR_DEVX_SUBSCRIBE_EVENT_FD_NUM)) {
+		err = uverbs_copy_from(&redirect_fd, attrs,
+			       MLX5_IB_ATTR_DEVX_SUBSCRIBE_EVENT_FD_NUM);
+		if (err)
+			return err;
+
+		use_eventfd = true;
+	}
+
+	if (uverbs_attr_is_valid(attrs,
+				 MLX5_IB_ATTR_DEVX_SUBSCRIBE_EVENT_COOKIE)) {
+		if (use_eventfd)
+			return -EINVAL;
+
+		err = uverbs_copy_from(&cookie, attrs,
+				MLX5_IB_ATTR_DEVX_SUBSCRIBE_EVENT_COOKIE);
+		if (err)
+			return err;
+	}
+
+	num_events = uverbs_attr_ptr_get_array_size(
+		attrs, MLX5_IB_ATTR_DEVX_SUBSCRIBE_EVENT_TYPE_NUM_LIST,
+		sizeof(u16));
+
+	if (num_events < 0)
+		return num_events;
+
+	if (num_events > MAX_NUM_EVENTS)
+		return -EINVAL;
+
+	event_type_num_list = uverbs_attr_get_alloced_ptr(attrs,
+			MLX5_IB_ATTR_DEVX_SUBSCRIBE_EVENT_TYPE_NUM_LIST);
+
+	if (!is_valid_events(dev->mdev, num_events, event_type_num_list, obj))
+		return -EINVAL;
+
+	INIT_LIST_HEAD(&sub_list);
+
+	/* Protect from concurrent subscriptions to same XA entries to allow
+	 * both to succeed
+	 */
+	mutex_lock(&devx_event_table->event_xa_lock);
+	for (i = 0; i < num_events; i++) {
+		u32 key_level1;
+
+		if (obj)
+			obj_type = get_dec_obj_type(obj,
+						    event_type_num_list[i]);
+		key_level1 = event_type_num_list[i] | obj_type << 16;
+
+		err = subscribe_event_xa_alloc(devx_event_table,
+					       key_level1,
+					       obj,
+					       obj_id);
+		if (err)
+			goto err;
+
+		num_alloc_xa_entries++;
+		event_sub = kzalloc(sizeof(*event_sub), GFP_KERNEL);
+		if (!event_sub)
+			goto err;
+
+		list_add_tail(&event_sub->event_list, &sub_list);
+		if (use_eventfd) {
+			event_sub->eventfd =
+				eventfd_ctx_fdget(redirect_fd);
+
+			if (IS_ERR(event_sub)) {
+				err = PTR_ERR(event_sub->eventfd);
+				event_sub->eventfd = NULL;
+				goto err;
+			}
+		}
+
+		event_sub->cookie = cookie;
+		event_sub->ev_file = ev_file;
+		event_sub->filp = fd_uobj->object;
+		/* May be needed upon cleanup the devx object/subscription */
+		event_sub->xa_key_level1 = key_level1;
+		event_sub->xa_key_level2 = obj_id;
+		INIT_LIST_HEAD(&event_sub->obj_list);
+	}
+
+	/* Once all the allocations and the XA data insertions were done we
+	 * can go ahead and add all the subscriptions to the relevant lists
+	 * without concern of a failure.
+	 */
+	list_for_each_entry_safe(event_sub, tmp_sub, &sub_list, event_list) {
+		struct devx_event *event;
+		struct devx_obj_event *obj_event;
+
+		list_del_init(&event_sub->event_list);
+
+		spin_lock_irq(&ev_file->lock);
+		list_add_tail_rcu(&event_sub->file_list,
+				  &ev_file->subscribed_events_list);
+		spin_unlock_irq(&ev_file->lock);
+
+		event = xa_load(&devx_event_table->event_xa,
+				event_sub->xa_key_level1);
+		WARN_ON(!event);
+
+		if (!obj) {
+			list_add_tail_rcu(&event_sub->xa_list,
+					  &event->unaffiliated_list);
+			continue;
+		}
+
+		obj_event = xa_load(&event->object_ids, obj_id);
+		WARN_ON(!obj_event);
+		list_add_tail_rcu(&event_sub->xa_list,
+				  &obj_event->obj_sub_list);
+		list_add_tail_rcu(&event_sub->obj_list,
+				  &obj->event_sub);
+	}
+
+	mutex_unlock(&devx_event_table->event_xa_lock);
+	return 0;
+
+err:
+	list_for_each_entry_safe(event_sub, tmp_sub, &sub_list, event_list) {
+		list_del(&event_sub->event_list);
+
+		subscribe_event_xa_dealloc(devx_event_table,
+					   event_sub->xa_key_level1,
+					   obj,
+					   obj_id);
+
+		if (event_sub->eventfd)
+			eventfd_ctx_put(event_sub->eventfd);
+
+		kfree(event_sub);
+	}
+
+	mutex_unlock(&devx_event_table->event_xa_lock);
+	return err;
+}
+
 static int devx_umem_get(struct mlx5_ib_dev *dev, struct ib_ucontext *ucontext,
 			 struct uverbs_attr_bundle *attrs,
 			 struct devx_umem *obj)
@@ -1682,14 +2180,21 @@ void mlx5_ib_devx_init_event_table(struct mlx5_ib_dev *dev)
 void mlx5_ib_devx_cleanup_event_table(struct mlx5_ib_dev *dev)
 {
 	struct mlx5_devx_event_table *table = &dev->devx_event_table;
+	struct devx_event_subscription *sub, *tmp;
+	struct devx_event *event;
 	void *entry;
 	unsigned long id;
 
 	mlx5_eq_notifier_unregister(dev->mdev, &table->devx_nb);
-
-	xa_for_each(&table->event_xa, id, entry)
+	mutex_lock(&dev->devx_event_table.event_xa_lock);
+	xa_for_each(&table->event_xa, id, entry) {
+		event = entry;
+		list_for_each_entry_safe(sub, tmp, &event->unaffiliated_list,
+					 xa_list)
+			devx_cleanup_subscription(dev, sub);
 		kfree(entry);
-
+	}
+	mutex_unlock(&dev->devx_event_table.event_xa_lock);
 	xa_destroy(&table->event_xa);
 }
 
@@ -1805,7 +2310,26 @@ static __poll_t devx_async_event_poll(struct file *filp,
 
 static int devx_async_event_close(struct inode *inode, struct file *filp)
 {
+	struct devx_async_event_file *ev_file = filp->private_data;
+	struct devx_event_subscription *event_sub, *event_sub_tmp;
+
+	mutex_lock(&ev_file->dev->devx_event_table.event_xa_lock);
+	/* delete the subscriptions which are related to this FD */
+	list_for_each_entry_safe(event_sub, event_sub_tmp,
+				 &ev_file->subscribed_events_list, file_list) {
+		devx_cleanup_subscription(ev_file->dev, event_sub);
+		if (event_sub->eventfd)
+			eventfd_ctx_put(event_sub->eventfd);
+
+		list_del_rcu(&event_sub->file_list);
+		/* subscription may not be used by the read API any more */
+		kfree_rcu(event_sub, rcu);
+	}
+
+	mutex_unlock(&ev_file->dev->devx_event_table.event_xa_lock);
+
 	uverbs_close_fd(filp);
+	put_device(&ev_file->dev->ib_dev.dev);
 	return 0;
 }
 
@@ -1973,10 +2497,32 @@ DECLARE_UVERBS_NAMED_METHOD(
 		UVERBS_ATTR_TYPE(u64),
 		UA_MANDATORY));
 
+DECLARE_UVERBS_NAMED_METHOD(
+	MLX5_IB_METHOD_DEVX_SUBSCRIBE_EVENT,
+	UVERBS_ATTR_FD(MLX5_IB_ATTR_DEVX_SUBSCRIBE_EVENT_FD_HANDLE,
+		MLX5_IB_OBJECT_DEVX_ASYNC_EVENT_FD,
+		UVERBS_ACCESS_READ,
+		UA_MANDATORY),
+	UVERBS_ATTR_IDR(MLX5_IB_ATTR_DEVX_SUBSCRIBE_EVENT_OBJ_HANDLE,
+		MLX5_IB_OBJECT_DEVX_OBJ,
+		UVERBS_ACCESS_READ,
+		UA_OPTIONAL),
+	UVERBS_ATTR_PTR_IN(MLX5_IB_ATTR_DEVX_SUBSCRIBE_EVENT_TYPE_NUM_LIST,
+		UVERBS_ATTR_MIN_SIZE(sizeof(u16)),
+		UA_MANDATORY,
+		UA_ALLOC_AND_COPY),
+	UVERBS_ATTR_PTR_IN(MLX5_IB_ATTR_DEVX_SUBSCRIBE_EVENT_COOKIE,
+		UVERBS_ATTR_TYPE(u64),
+		UA_OPTIONAL),
+	UVERBS_ATTR_PTR_IN(MLX5_IB_ATTR_DEVX_SUBSCRIBE_EVENT_FD_NUM,
+		UVERBS_ATTR_TYPE(u32),
+		UA_OPTIONAL));
+
 DECLARE_UVERBS_GLOBAL_METHODS(MLX5_IB_OBJECT_DEVX,
 			      &UVERBS_METHOD(MLX5_IB_METHOD_DEVX_OTHER),
 			      &UVERBS_METHOD(MLX5_IB_METHOD_DEVX_QUERY_UAR),
-			      &UVERBS_METHOD(MLX5_IB_METHOD_DEVX_QUERY_EQN));
+			      &UVERBS_METHOD(MLX5_IB_METHOD_DEVX_QUERY_EQN),
+			      &UVERBS_METHOD(MLX5_IB_METHOD_DEVX_SUBSCRIBE_EVENT));
 
 DECLARE_UVERBS_NAMED_OBJECT(MLX5_IB_OBJECT_DEVX_OBJ,
 			    UVERBS_TYPE_ALLOC_IDR(devx_obj_cleanup),
diff --git a/include/uapi/rdma/mlx5_user_ioctl_cmds.h b/include/uapi/rdma/mlx5_user_ioctl_cmds.h
index 6ad8f4f11ddd..d0da070cf0ab 100644
--- a/include/uapi/rdma/mlx5_user_ioctl_cmds.h
+++ b/include/uapi/rdma/mlx5_user_ioctl_cmds.h
@@ -51,6 +51,7 @@ enum mlx5_ib_devx_methods {
 	MLX5_IB_METHOD_DEVX_OTHER  = (1U << UVERBS_ID_NS_SHIFT),
 	MLX5_IB_METHOD_DEVX_QUERY_UAR,
 	MLX5_IB_METHOD_DEVX_QUERY_EQN,
+	MLX5_IB_METHOD_DEVX_SUBSCRIBE_EVENT,
 };
 
 enum  mlx5_ib_devx_other_attrs {
@@ -93,6 +94,14 @@ enum mlx5_ib_devx_obj_query_async_attrs {
 	MLX5_IB_ATTR_DEVX_OBJ_QUERY_ASYNC_OUT_LEN,
 };
 
+enum mlx5_ib_devx_subscribe_event_attrs {
+	MLX5_IB_ATTR_DEVX_SUBSCRIBE_EVENT_FD_HANDLE = (1U << UVERBS_ID_NS_SHIFT),
+	MLX5_IB_ATTR_DEVX_SUBSCRIBE_EVENT_OBJ_HANDLE,
+	MLX5_IB_ATTR_DEVX_SUBSCRIBE_EVENT_TYPE_NUM_LIST,
+	MLX5_IB_ATTR_DEVX_SUBSCRIBE_EVENT_FD_NUM,
+	MLX5_IB_ATTR_DEVX_SUBSCRIBE_EVENT_COOKIE,
+};
+
 enum  mlx5_ib_devx_query_eqn_attrs {
 	MLX5_IB_ATTR_DEVX_QUERY_EQN_USER_VEC = (1U << UVERBS_ID_NS_SHIFT),
 	MLX5_IB_ATTR_DEVX_QUERY_EQN_DEV_EQN,