[PATCH] nvme: introduce passthrough ioctl for multipath

[Minwoo Im]

We don't allow NVME_IOCTL_IO_CMD ioctl in case that a controller has
multiple namespaces attached.  Also, I/O request to the controller
character device has not been recommended and deprecated because we have
block device to I/O with where the multipath consideration is taken.

Once kernel decided a path to I/O for a namespace based on the I/O
policy of a NVMe subsystem, userspace is not allowed to choose a path to
I/O.  If a path is broken(inaccessible state in ANA), then it will not
try to I/O to that path.

This patch introduced NVME_IOCTL_MPATH_IO command for controller
device(e.g., /dev/nvme0) to support multipath I/O passthrough for
userspace.  Regardless driver's path decision, userspace can target a
namespace to I/O.  In this case, `cmd.nsid` will be used to find out the
namespace instance target which is hidden(e.g., nvmeXcYnZ).

Signed-off-by: Minwoo Im <minwoo.im.dev at gmail.com>
---
 drivers/nvme/host/core.c        | 31 +++++++++++++++++++++++++++++++
 include/uapi/linux/nvme_ioctl.h |  1 +
 2 files changed, 32 insertions(+)

diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index d77f3f26d8d3..fed9fc41b021 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -1707,6 +1707,35 @@ static int nvme_user_cmd64(struct nvme_ctrl *ctrl, struct nvme_ns *ns,
 	return status;
 }
 
+#ifdef CONFIG_NVME_MULTIPATH
+static int nvme_dev_mpath_cmd(struct nvme_ctrl *ctrl,
+		struct nvme_passthru_cmd __user *ucmd)
+{
+	struct nvme_passthru_cmd cmd;
+	struct nvme_ns *ns;
+
+	if (!capable(CAP_SYS_ADMIN))
+		return -EACCES;
+	if (copy_from_user(&cmd, ucmd, sizeof(cmd)))
+		return -EFAULT;
+
+	ns = nvme_find_get_ns(ctrl, cmd.nsid);
+	if (unlikely(!ns))
+		return -EINVAL;
+	if (WARN_ON_ONCE(!(ns->disk->flags & GENHD_FL_HIDDEN)))
+		return -EINVAL;
+
+	return nvme_user_cmd(ctrl, ns, ucmd);
+}
+#else
+static int nvme_dev_mpath_cmd(struct nvme_ctrl *ctrl,
+		struct nvme_passthru_cmd __user *ucmd)
+{
+	dev_warn(ctrl->device, "CONFIG_NVME_MULTIPATH should be enabled\n");
+	return -EINVAL;
+}
+#endif
+
 /*
  * Issue ioctl requests on the first available path.  Note that unlike normal
  * block layer requests we will not retry failed request on another controller.
@@ -3329,6 +3358,8 @@ static long nvme_dev_ioctl(struct file *file, unsigned int cmd,
 		return nvme_user_cmd64(ctrl, NULL, argp);
 	case NVME_IOCTL_IO_CMD:
 		return nvme_dev_user_cmd(ctrl, argp);
+	case NVME_IOCTL_MPATH_IO:
+		return nvme_dev_mpath_cmd(ctrl, argp);
 	case NVME_IOCTL_RESET:
 		dev_warn(ctrl->device, "resetting controller\n");
 		return nvme_reset_ctrl_sync(ctrl);
diff --git a/include/uapi/linux/nvme_ioctl.h b/include/uapi/linux/nvme_ioctl.h
index d99b5a772698..38bd330e5416 100644
--- a/include/uapi/linux/nvme_ioctl.h
+++ b/include/uapi/linux/nvme_ioctl.h
@@ -78,5 +78,6 @@ struct nvme_passthru_cmd64 {
 #define NVME_IOCTL_RESCAN	_IO('N', 0x46)
 #define NVME_IOCTL_ADMIN64_CMD	_IOWR('N', 0x47, struct nvme_passthru_cmd64)
 #define NVME_IOCTL_IO64_CMD	_IOWR('N', 0x48, struct nvme_passthru_cmd64)
+#define NVME_IOCTL_MPATH_IO	_IOWR('N', 0x49, struct nvme_passthru_cmd)
 
 #endif /* _UAPI_LINUX_NVME_IOCTL_H */
-- 
2.17.1