RDMA/uverbs: Export ib_open_qp() capability to user space

Allow processes that share the same XRC domain to open an existing
shareable QP.  This permits those processes to receive events on the
shared QP and transfer ownership, so that any process may modify the
QP.  The latter allows the creating process to exit, while a remaining
process can still transition it for path migration purposes.

Signed-off-by: Sean Hefty <sean.hefty@intel.com>
Signed-off-by: Roland Dreier <roland@purestorage.com>

5 files changed, 110 insertions, 3 deletions

diff --git a/drivers/infiniband/core/uverbs.h b/drivers/infiniband/core/uverbs.h
index 00ce032fcead..5bcb2afd3dcb 100644
--- a/drivers/infiniband/core/uverbs.h
+++ b/drivers/infiniband/core/uverbs.h
@@ -195,6 +195,7 @@ IB_UVERBS_DECLARE_CMD(poll_cq);
 IB_UVERBS_DECLARE_CMD(req_notify_cq);
 IB_UVERBS_DECLARE_CMD(destroy_cq);
 IB_UVERBS_DECLARE_CMD(create_qp);
+IB_UVERBS_DECLARE_CMD(open_qp);
 IB_UVERBS_DECLARE_CMD(query_qp);
 IB_UVERBS_DECLARE_CMD(modify_qp);
 IB_UVERBS_DECLARE_CMD(destroy_qp);
diff --git a/drivers/infiniband/core/uverbs_cmd.c b/drivers/infiniband/core/uverbs_cmd.c
index c4c308cd2034..254f1649c734 100644
--- a/drivers/infiniband/core/uverbs_cmd.c
+++ b/drivers/infiniband/core/uverbs_cmd.c
@@ -1544,6 +1544,98 @@ err_put:
 	return ret;
 }
 
+ssize_t ib_uverbs_open_qp(struct ib_uverbs_file *file,
+			  const char __user *buf, int in_len, int out_len)
+{
+	struct ib_uverbs_open_qp        cmd;
+	struct ib_uverbs_create_qp_resp resp;
+	struct ib_udata                 udata;
+	struct ib_uqp_object           *obj;
+	struct ib_xrcd		       *xrcd;
+	struct ib_uobject	       *uninitialized_var(xrcd_uobj);
+	struct ib_qp                   *qp;
+	struct ib_qp_open_attr          attr;
+	int ret;
+
+	if (out_len < sizeof resp)
+		return -ENOSPC;
+
+	if (copy_from_user(&cmd, buf, sizeof cmd))
+		return -EFAULT;
+
+	INIT_UDATA(&udata, buf + sizeof cmd,
+		   (unsigned long) cmd.response + sizeof resp,
+		   in_len - sizeof cmd, out_len - sizeof resp);
+
+	obj = kmalloc(sizeof *obj, GFP_KERNEL);
+	if (!obj)
+		return -ENOMEM;
+
+	init_uobj(&obj->uevent.uobject, cmd.user_handle, file->ucontext, &qp_lock_key);
+	down_write(&obj->uevent.uobject.mutex);
+
+	xrcd = idr_read_xrcd(cmd.pd_handle, file->ucontext, &xrcd_uobj);
+	if (!xrcd) {
+		ret = -EINVAL;
+		goto err_put;
+	}
+
+	attr.event_handler = ib_uverbs_qp_event_handler;
+	attr.qp_context    = file;
+	attr.qp_num        = cmd.qpn;
+	attr.qp_type       = cmd.qp_type;
+
+	obj->uevent.events_reported = 0;
+	INIT_LIST_HEAD(&obj->uevent.event_list);
+	INIT_LIST_HEAD(&obj->mcast_list);
+
+	qp = ib_open_qp(xrcd, &attr);
+	if (IS_ERR(qp)) {
+		ret = PTR_ERR(qp);
+		goto err_put;
+	}
+
+	qp->uobject = &obj->uevent.uobject;
+
+	obj->uevent.uobject.object = qp;
+	ret = idr_add_uobj(&ib_uverbs_qp_idr, &obj->uevent.uobject);
+	if (ret)
+		goto err_destroy;
+
+	memset(&resp, 0, sizeof resp);
+	resp.qpn       = qp->qp_num;
+	resp.qp_handle = obj->uevent.uobject.id;
+
+	if (copy_to_user((void __user *) (unsigned long) cmd.response,
+			 &resp, sizeof resp)) {
+		ret = -EFAULT;
+		goto err_remove;
+	}
+
+	put_xrcd_read(xrcd_uobj);
+
+	mutex_lock(&file->mutex);
+	list_add_tail(&obj->uevent.uobject.list, &file->ucontext->qp_list);
+	mutex_unlock(&file->mutex);
+
+	obj->uevent.uobject.live = 1;
+
+	up_write(&obj->uevent.uobject.mutex);
+
+	return in_len;
+
+err_remove:
+	idr_remove_uobj(&ib_uverbs_qp_idr, &obj->uevent.uobject);
+
+err_destroy:
+	ib_destroy_qp(qp);
+
+err_put:
+	put_xrcd_read(xrcd_uobj);
+	put_uobj_write(&obj->uevent.uobject);
+	return ret;
+}
+
 ssize_t ib_uverbs_query_qp(struct ib_uverbs_file *file,
 			   const char __user *buf, int in_len,
 			   int out_len)
diff --git a/drivers/infiniband/core/uverbs_main.c b/drivers/infiniband/core/uverbs_main.c
index 9c877e24eb60..485ea6c60d8b 100644
--- a/drivers/infiniband/core/uverbs_main.c
+++ b/drivers/infiniband/core/uverbs_main.c
@@ -110,7 +110,8 @@ static ssize_t (*uverbs_cmd_table[])(struct ib_uverbs_file *file,
 	[IB_USER_VERBS_CMD_DESTROY_SRQ]		= ib_uverbs_destroy_srq,
 	[IB_USER_VERBS_CMD_OPEN_XRCD]		= ib_uverbs_open_xrcd,
 	[IB_USER_VERBS_CMD_CLOSE_XRCD]		= ib_uverbs_close_xrcd,
-	[IB_USER_VERBS_CMD_CREATE_XSRQ]		= ib_uverbs_create_xsrq
+	[IB_USER_VERBS_CMD_CREATE_XSRQ]		= ib_uverbs_create_xsrq,
+	[IB_USER_VERBS_CMD_OPEN_QP]		= ib_uverbs_open_qp
 };
 
 static void ib_uverbs_add_one(struct ib_device *device);
diff --git a/drivers/infiniband/hw/mlx4/main.c b/drivers/infiniband/hw/mlx4/main.c
index aec76ad77872..8a9ae720b56a 100644
--- a/drivers/infiniband/hw/mlx4/main.c
+++ b/drivers/infiniband/hw/mlx4/main.c
@@ -1098,7 +1098,8 @@ static void *mlx4_ib_add(struct mlx4_dev *dev)
 		(1ull << IB_USER_VERBS_CMD_MODIFY_SRQ)		|
 		(1ull << IB_USER_VERBS_CMD_QUERY_SRQ)		|
 		(1ull << IB_USER_VERBS_CMD_DESTROY_SRQ)		|
-		(1ull << IB_USER_VERBS_CMD_CREATE_XSRQ);
+		(1ull << IB_USER_VERBS_CMD_CREATE_XSRQ)		|
+		(1ull << IB_USER_VERBS_CMD_OPEN_QP);
 
 	ibdev->ib_dev.query_device	= mlx4_ib_query_device;
 	ibdev->ib_dev.query_port	= mlx4_ib_query_port;
diff --git a/include/rdma/ib_user_verbs.h b/include/rdma/ib_user_verbs.h
index 100abbbd6e6e..81aba3a73aa3 100644
--- a/include/rdma/ib_user_verbs.h
+++ b/include/rdma/ib_user_verbs.h
@@ -84,7 +84,8 @@ enum {
 	IB_USER_VERBS_CMD_POST_SRQ_RECV,
 	IB_USER_VERBS_CMD_OPEN_XRCD,
 	IB_USER_VERBS_CMD_CLOSE_XRCD,
-	IB_USER_VERBS_CMD_CREATE_XSRQ
+	IB_USER_VERBS_CMD_CREATE_XSRQ,
+	IB_USER_VERBS_CMD_OPEN_QP
 };
 
 /*
@@ -422,6 +423,17 @@ struct ib_uverbs_create_qp {
 	__u64 driver_data[0];
 };
 
+struct ib_uverbs_open_qp {
+	__u64 response;
+	__u64 user_handle;
+	__u32 pd_handle;
+	__u32 qpn;
+	__u8  qp_type;
+	__u8  reserved[7];
+	__u64 driver_data[0];
+};
+
+/* also used for open response */
 struct ib_uverbs_create_qp_resp {
 	__u32 qp_handle;
 	__u32 qpn;