nvme generic per-namespace char device
Christoph Hellwig
maintainerHi all,
this series picks up the generic per-namespace character device from Minwoo and Javier with a few small fixes.
Changes since v1:
- ensure the cdev idea is freed
- dropped the already merged ioctl cleanup
_______________________________________________
Linux-nvme mailing list
[email protected]
http://lists.infradead.org/mailman/listinfo/linux-nvme
Christoph Hellwig
maintainerPATCH 1/1 nvme: introduce generic per-namespace chardev
From: Minwoo Im <[email protected]>
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.
[hch: rebased on top of the ioctl cleanups, split the ns_head and ns
implementations]
--- drivers/nvme/host/core.c | 87 +++++++++++++++++++++++++++++++++++ drivers/nvme/host/ioctl.c | 17 +++++++ drivers/nvme/host/multipath.c | 51 ++++++++++++++++++-- drivers/nvme/host/nvme.h | 13 ++++++ 4 files changed, 165 insertions(+), 3 deletions(-)
drivers/nvme/host/core.c +87 -0
@@ -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);
@@ -3429,6 +3433,66 @@ static int __nvme_check_ids(struct nvme_subsystem *subsys,return 0 ; } +void nvme_cdev_del (struct cdev *cdev,struct device *cdev_device) +{ +cdev_device_del (cdev, cdev_device); +ida_simple_remove (&nvme_ns_chr_minor_ida,MINOR (cdev_device->devt)); +} + +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) {
@@ -3630,6 +3694,8 @@ 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);
@@ -3674,6 +3740,8 @@ 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)) +nvme_cdev_del (&ns->cdev, &ns->cdev_device);del_gendisk (ns->disk);blk_cleanup_queue (ns->queue);if (blk_get_integrity (ns->disk))
@@ -4464,8 +4532,24 @@ 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:
@@ -4482,12 +4566,15 @@ 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); }
drivers/nvme/host/ioctl.c +17 -0
@@ -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)
drivers/nvme/host/multipath.c +48 -3
75 lines not on this page · raw message
drivers/nvme/host/nvme.h +13 -0
@@ -412,6 +412,10 @@ 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;
@@ -464,6 +468,9 @@ 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; };
@@ -658,10 +665,16 @@ 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); +void nvme_cdev_del (struct cdev *cdev,struct device *cdev_device);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);
Signature · 7 lines
2.30.1 _______________________________________________ Linux-nvme mailing list [email protected] http://lists.infradead.org/mailman/listinfo/linux-nvme
Re: [PATCH] nvme: introduce generic per-namespace chardev
Quoted 7 lines · Christoph Hellwig
From: Minwoo Im <[email protected]>
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.
When an application uses this interface to issue passthrough IO, it needs to know the lba size (at least) to form the command correctly. But determining lba size would require an admin ioctl.
Do you see there is a way to go about this issue?
Signature · 6 lines
Joshi _______________________________________________ Linux-nvme mailing list [email protected] http://lists.infradead.org/mailman/listinfo/linux-nvme
Keith Busch
maintainerRe: [PATCH] nvme: introduce generic per-namespace chardev
Quoted 9 lines · Kanchan Joshi
Quoted 7 lines · Christoph Hellwig
From: Minwoo Im <[email protected]>
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.
Quoted 4 lines
When an application uses this interface to issue passthrough IO, it needs to know the lba size (at least) to form the command correctly. But determining lba size would require an admin ioctl.
Do you see there is a way to go about this issue?
You'd have to look up the parent controller and issue the command through that.
If your application doesn't have permissions to open the controller, then it wouldn't work.
So I guess all applications that can open generic namespaces would need access to the controller handle. But if you do that, then is there a point to this indirection anymore?
I have to agree, the ability to query your namespaces settings through the namespace's handle really does simplify things...
_______________________________________________
Linux-nvme mailing list
[email protected]
http://lists.infradead.org/mailman/listinfo/linux-nvme