[PATCH 13/13] nvme: introduce generic per-namespace chardev

Christoph Hellwig hch at lst.de
Thu Apr 8 13:08:42 BST 2021


From: Minwoo Im <minwoo.im.dev at gmail.com>

Userspace has not been allowed to I/O to device that's failed to
be initialized.  This patch introduces generic per-namespace character
device to allow userspace to I/O regardless the block device is there or
not.

The chardev naming convention will similar to the existing blkdev naming,
using a ng prefix instead of nvme, i.e.

	- /dev/ngXnY

It also supports multipath which means it will not expose chardev for the
hidden namespace blkdevs (e.g., nvmeXcYnZ).  If /dev/ngXnY is created for
a ns_head, then I/O request will be routed to a specific controller
selected by the iopolicy of the subsystem.

Signed-off-by: Minwoo Im <minwoo.im.dev at gmail.com>
Signed-off-by: Javier González <javier.gonz at samsung.com>
[hch: rebased on top of the ioctl cleanups, split the ns_head and ns
 implementations]
Signed-off-by: Christoph Hellwig <hch at lst.de>
---
 drivers/nvme/host/core.c      | 81 +++++++++++++++++++++++++++++++++++
 drivers/nvme/host/ioctl.c     | 17 ++++++++
 drivers/nvme/host/multipath.c | 51 ++++++++++++++++++++--
 drivers/nvme/host/nvme.h      | 12 ++++++
 4 files changed, 158 insertions(+), 3 deletions(-)

diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index eba676b260b820..fa8bddc31442a3 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -89,6 +89,10 @@ static dev_t nvme_ctrl_base_chr_devt;
 static struct class *nvme_class;
 static struct class *nvme_subsys_class;
 
+static DEFINE_IDA(nvme_ns_chr_minor_ida);
+static dev_t nvme_ns_chr_devt;
+static struct class *nvme_ns_chr_class;
+
 static void nvme_put_subsystem(struct nvme_subsystem *subsys);
 static void nvme_remove_invalid_namespaces(struct nvme_ctrl *ctrl,
 					   unsigned nsid);
@@ -3424,6 +3428,60 @@ static int __nvme_check_ids(struct nvme_subsystem *subsys,
 	return 0;
 }
 
+int nvme_cdev_add(struct cdev *cdev, struct device *cdev_device,
+		const struct file_operations *fops, struct module *owner)
+{
+	int minor, ret;
+
+	minor = ida_simple_get(&nvme_ns_chr_minor_ida, 0, 0, GFP_KERNEL);
+	if (minor < 0)
+		return minor;
+	cdev_device->devt = MKDEV(MAJOR(nvme_ns_chr_devt), minor);
+	cdev_device->class = nvme_ns_chr_class;
+	device_initialize(cdev_device);
+	cdev_init(cdev, fops);
+	cdev->owner = owner;
+	ret = cdev_device_add(cdev, cdev_device);
+	if (ret)
+		ida_simple_remove(&nvme_ns_chr_minor_ida, minor);
+	return ret;
+}
+
+static int nvme_ns_chr_open(struct inode *inode, struct file *file)
+{
+	return nvme_ns_open(container_of(inode->i_cdev, struct nvme_ns, cdev));
+}
+
+static int nvme_ns_chr_release(struct inode *inode, struct file *file)
+{
+	nvme_ns_release(container_of(inode->i_cdev, struct nvme_ns, cdev));
+	return 0;
+}
+
+static const struct file_operations nvme_ns_chr_fops = {
+	.owner		= THIS_MODULE,
+	.open		= nvme_ns_chr_open,
+	.release	= nvme_ns_chr_release,
+	.unlocked_ioctl	= nvme_ns_chr_ioctl,
+	.compat_ioctl	= compat_ptr_ioctl,
+};
+
+static int nvme_add_ns_cdev(struct nvme_ns *ns)
+{
+	int ret;
+
+	ns->cdev_device.parent = ns->ctrl->device;
+	ret = dev_set_name(&ns->cdev_device, "ng%dn%d",
+			   ns->ctrl->instance, ns->head->instance);
+	if (ret)
+		return ret;
+	ret = nvme_cdev_add(&ns->cdev, &ns->cdev_device, &nvme_ns_chr_fops,
+			    ns->ctrl->ops->module);
+	if (ret)
+		kfree_const(ns->cdev_device.kobj.name);
+	return ret;
+}
+
 static struct nvme_ns_head *nvme_alloc_ns_head(struct nvme_ctrl *ctrl,
 		unsigned nsid, struct nvme_ns_ids *ids)
 {
@@ -3625,6 +3683,8 @@ static void nvme_alloc_ns(struct nvme_ctrl *ctrl, unsigned nsid,
 	nvme_get_ctrl(ctrl);
 
 	device_add_disk(ctrl->device, ns->disk, nvme_ns_id_attr_groups);
+	if (!nvme_ns_head_multipath(ns->head))
+		nvme_add_ns_cdev(ns);
 
 	nvme_mpath_add_disk(ns, id);
 	nvme_fault_inject_init(&ns->fault_inject, ns->disk->disk_name);
@@ -3669,6 +3729,8 @@ static void nvme_ns_remove(struct nvme_ns *ns)
 	synchronize_srcu(&ns->head->srcu); /* wait for concurrent submissions */
 
 	if (ns->disk->flags & GENHD_FL_UP) {
+		if (!nvme_ns_head_multipath(ns->head))
+			cdev_device_del(&ns->cdev, &ns->cdev_device);
 		del_gendisk(ns->disk);
 		blk_cleanup_queue(ns->queue);
 		if (blk_get_integrity(ns->disk))
@@ -4459,8 +4521,24 @@ static int __init nvme_core_init(void)
 		result = PTR_ERR(nvme_subsys_class);
 		goto destroy_class;
 	}
+
+	result = alloc_chrdev_region(&nvme_ns_chr_devt, 0, NVME_MINORS,
+				     "nvme-generic");
+	if (result < 0)
+		goto destroy_subsys_class;
+
+	nvme_ns_chr_class = class_create(THIS_MODULE, "nvme-generic");
+	if (IS_ERR(nvme_ns_chr_class)) {
+		result = PTR_ERR(nvme_ns_chr_class);
+		goto unregister_generic_ns;
+	}
+
 	return 0;
 
+unregister_generic_ns:
+	unregister_chrdev_region(nvme_ns_chr_devt, NVME_MINORS);
+destroy_subsys_class:
+	class_destroy(nvme_subsys_class);
 destroy_class:
 	class_destroy(nvme_class);
 unregister_chrdev:
@@ -4477,12 +4555,15 @@ static int __init nvme_core_init(void)
 
 static void __exit nvme_core_exit(void)
 {
+	class_destroy(nvme_ns_chr_class);
 	class_destroy(nvme_subsys_class);
 	class_destroy(nvme_class);
+	unregister_chrdev_region(nvme_ns_chr_devt, NVME_MINORS);
 	unregister_chrdev_region(nvme_ctrl_base_chr_devt, NVME_MINORS);
 	destroy_workqueue(nvme_delete_wq);
 	destroy_workqueue(nvme_reset_wq);
 	destroy_workqueue(nvme_wq);
+	ida_destroy(&nvme_ns_chr_minor_ida);
 	ida_destroy(&nvme_instance_ida);
 }
 
diff --git a/drivers/nvme/host/ioctl.c b/drivers/nvme/host/ioctl.c
index 001faf31fb944f..304dc66bcebf22 100644
--- a/drivers/nvme/host/ioctl.c
+++ b/drivers/nvme/host/ioctl.c
@@ -357,6 +357,14 @@ int nvme_ioctl(struct block_device *bdev, fmode_t mode,
 	return nvme_ns_ioctl(ns, cmd, argp);
 }
 
+long nvme_ns_chr_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
+{
+	struct nvme_ns *ns =
+		container_of(file_inode(file)->i_cdev, struct nvme_ns, cdev);
+
+	return nvme_ns_ioctl(ns, cmd, (void __user *)arg);
+}
+
 #ifdef CONFIG_NVME_MULTIPATH
 static int nvme_ns_head_ctrl_ioctl(struct nvme_ns_head *head,
 		unsigned int cmd, void __user *argp)
@@ -393,6 +401,15 @@ int nvme_ns_head_ioctl(struct block_device *bdev, fmode_t mode,
 		return nvme_ns_head_ctrl_ioctl(head, cmd, (void __user *)arg);
 	return nvme_ns_head_ns_ioctl(head, cmd, (void __user *)arg);
 }
+
+long nvme_ns_head_chr_ioctl(struct file *file, unsigned int cmd,
+		unsigned long arg)
+{
+	struct cdev *cdev = file_inode(file)->i_cdev;
+	struct nvme_ns_head *head = container_of(cdev, struct nvme_ns_head, cdev);
+
+	return nvme_ns_head_ns_ioctl(head, cmd, (void __user *)arg);
+}
 #endif /* CONFIG_NVME_MULTIPATH */
 
 static int nvme_dev_user_cmd(struct nvme_ctrl *ctrl, void __user *argp)
diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c
index 2bbc1685799d44..40c6cc989e373a 100644
--- a/drivers/nvme/host/multipath.c
+++ b/drivers/nvme/host/multipath.c
@@ -357,6 +357,48 @@ const struct block_device_operations nvme_ns_head_ops = {
 	.pr_ops		= &nvme_pr_ops,
 };
 
+static inline struct nvme_ns_head *cdev_to_ns_head(struct cdev *cdev)
+{
+	return container_of(cdev, struct nvme_ns_head, cdev);
+}
+
+static int nvme_ns_head_chr_open(struct inode *inode, struct file *file)
+{
+	if (!nvme_tryget_ns_head(cdev_to_ns_head(inode->i_cdev)))
+		return -ENXIO;
+	return 0;
+}
+
+static int nvme_ns_head_chr_release(struct inode *inode, struct file *file)
+{
+	nvme_put_ns_head(cdev_to_ns_head(inode->i_cdev));
+	return 0;
+}
+
+static const struct file_operations nvme_ns_head_chr_fops = {
+	.owner		= THIS_MODULE,
+	.open		= nvme_ns_head_chr_open,
+	.release	= nvme_ns_head_chr_release,
+	.unlocked_ioctl	= nvme_ns_head_chr_ioctl,
+	.compat_ioctl	= compat_ptr_ioctl,
+};
+
+static int nvme_add_ns_head_cdev(struct nvme_ns_head *head)
+{
+	int ret;
+
+	head->cdev_device.parent = &head->subsys->dev;
+	ret = dev_set_name(&head->cdev_device, "ng%dn%d",
+			   head->subsys->instance, head->instance);
+	if (ret)
+		return ret;
+	ret = nvme_cdev_add(&head->cdev, &head->cdev_device,
+			    &nvme_ns_head_chr_fops, THIS_MODULE);
+	if (ret)
+		kfree_const(head->cdev_device.kobj.name);
+	return ret;
+}
+
 static void nvme_requeue_work(struct work_struct *work)
 {
 	struct nvme_ns_head *head =
@@ -435,9 +477,11 @@ static void nvme_mpath_set_live(struct nvme_ns *ns)
 	if (!head->disk)
 		return;
 
-	if (!test_and_set_bit(NVME_NSHEAD_DISK_LIVE, &head->flags))
+	if (!test_and_set_bit(NVME_NSHEAD_DISK_LIVE, &head->flags)) {
 		device_add_disk(&head->subsys->dev, head->disk,
 				nvme_ns_id_attr_groups);
+		nvme_add_ns_head_cdev(head);
+	}
 
 	mutex_lock(&head->lock);
 	if (nvme_path_is_optimized(ns)) {
@@ -714,8 +758,10 @@ void nvme_mpath_remove_disk(struct nvme_ns_head *head)
 {
 	if (!head->disk)
 		return;
-	if (head->disk->flags & GENHD_FL_UP)
+	if (head->disk->flags & GENHD_FL_UP) {
+		cdev_device_del(&head->cdev, &head->cdev_device);
 		del_gendisk(head->disk);
+	}
 	blk_set_queue_dying(head->disk->queue);
 	/* make sure all pending bios are cleaned up */
 	kblockd_schedule_work(&head->requeue_work);
@@ -785,4 +831,3 @@ void nvme_mpath_uninit(struct nvme_ctrl *ctrl)
 	kfree(ctrl->ana_log_buf);
 	ctrl->ana_log_buf = NULL;
 }
-
diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
index c6102ce83bb405..d34e29d76abb54 100644
--- a/drivers/nvme/host/nvme.h
+++ b/drivers/nvme/host/nvme.h
@@ -413,6 +413,10 @@ struct nvme_ns_head {
 	bool			shared;
 	int			instance;
 	struct nvme_effects_log *effects;
+
+	struct cdev		cdev;
+	struct device		cdev_device;
+
 	struct gendisk		*disk;
 #ifdef CONFIG_NVME_MULTIPATH
 	struct bio_list		requeue_list;
@@ -465,6 +469,9 @@ struct nvme_ns {
 #define NVME_NS_ANA_PENDING	2
 #define NVME_NS_FORCE_RO	3
 
+	struct cdev		cdev;
+	struct device		cdev_device;
+
 	struct nvme_fault_inject fault_inject;
 
 };
@@ -659,10 +666,15 @@ void nvme_put_ns_from_disk(struct nvme_ns_head *head, int idx);
 bool nvme_tryget_ns_head(struct nvme_ns_head *head);
 void nvme_put_ns_head(struct nvme_ns_head *head);
 struct nvme_ctrl *nvme_find_get_live_ctrl(struct nvme_subsystem *subsys);
+int nvme_cdev_add(struct cdev *cdev, struct device *cdev_device,
+		const struct file_operations *fops, struct module *owner);
 int nvme_ioctl(struct block_device *bdev, fmode_t mode,
 		unsigned int cmd, unsigned long arg);
+long nvme_ns_chr_ioctl(struct file *file, unsigned int cmd, unsigned long arg);
 int nvme_ns_head_ioctl(struct block_device *bdev, fmode_t mode,
 		unsigned int cmd, unsigned long arg);
+long nvme_ns_head_chr_ioctl(struct file *file, unsigned int cmd,
+		unsigned long arg);
 long nvme_dev_ioctl(struct file *file, unsigned int cmd,
 		unsigned long arg);
 int nvme_getgeo(struct block_device *bdev, struct hd_geometry *geo);
-- 
2.30.1




More information about the Linux-nvme mailing list