diff options
author | Minwoo Im <minwoo.im.dev@gmail.com> | 2021-04-21 16:45:04 +0900 |
---|---|---|
committer | Christoph Hellwig <hch@lst.de> | 2021-04-22 07:25:17 +0200 |
commit | 2637baed78010eeaae274feb5b99ce90933fadfb (patch) | |
tree | f62d5575463b77bd8ca7da8d6d2ed8086d54a8a3 /drivers/nvme | |
parent | 60df5de9b0532aff59a00475b57c265b4a3620e1 (diff) | |
download | lwn-2637baed78010eeaae274feb5b99ce90933fadfb.tar.gz lwn-2637baed78010eeaae274feb5b99ce90933fadfb.zip |
nvme: introduce generic per-namespace chardev
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@gmail.com>
Signed-off-by: Javier González <javier.gonz@samsung.com>
Reviewed-by: Keith Busch <kbusch@kernel.org>
Tested-by: Kanchan Joshi <joshi.k@samsung.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Diffstat (limited to 'drivers/nvme')
-rw-r--r-- | drivers/nvme/host/core.c | 87 | ||||
-rw-r--r-- | drivers/nvme/host/ioctl.c | 38 | ||||
-rw-r--r-- | drivers/nvme/host/multipath.c | 51 | ||||
-rw-r--r-- | drivers/nvme/host/nvme.h | 13 |
4 files changed, 180 insertions, 9 deletions
diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c index b905f91f14eb..2f45e8fcdd7c 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); @@ -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 @@ out: 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 8e05d65c9e93..502f8e4a2a1f 100644 --- a/drivers/nvme/host/ioctl.c +++ b/drivers/nvme/host/ioctl.c @@ -346,15 +346,27 @@ static int nvme_ns_ioctl(struct nvme_ns *ns, unsigned int cmd, } } +static int __nvme_ioctl(struct nvme_ns *ns, unsigned int cmd, void __user *arg) +{ + if (is_ctrl_ioctl(cmd)) + return nvme_ctrl_ioctl(ns->ctrl, cmd, arg); + return nvme_ns_ioctl(ns, cmd, arg); +} + int nvme_ioctl(struct block_device *bdev, fmode_t mode, unsigned int cmd, unsigned long arg) { struct nvme_ns *ns = bdev->bd_disk->private_data; - void __user *argp = (void __user *)arg; - if (is_ctrl_ioctl(cmd)) - return nvme_ctrl_ioctl(ns->ctrl, cmd, argp); - return nvme_ns_ioctl(ns, cmd, argp); + return __nvme_ioctl(ns, cmd, (void __user *)arg); +} + +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_ioctl(ns, cmd, (void __user *)arg); } #ifdef CONFIG_NVME_MULTIPATH @@ -388,10 +400,24 @@ int nvme_ns_head_ioctl(struct block_device *bdev, fmode_t mode, unsigned int cmd, unsigned long arg) { struct nvme_ns_head *head = bdev->bd_disk->private_data; + void __user *argp = (void __user *)arg; + + if (is_ctrl_ioctl(cmd)) + return nvme_ns_head_ctrl_ioctl(head, cmd, argp); + return nvme_ns_head_ns_ioctl(head, cmd, argp); +} + +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); + void __user *argp = (void __user *)arg; if (is_ctrl_ioctl(cmd)) - return nvme_ns_head_ctrl_ioctl(head, cmd, (void __user *)arg); - return nvme_ns_head_ns_ioctl(head, cmd, (void __user *)arg); + return nvme_ns_head_ctrl_ioctl(head, cmd, argp); + return nvme_ns_head_ns_ioctl(head, cmd, argp); } #endif /* CONFIG_NVME_MULTIPATH */ diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c index 68918ea1d3d0..0d0de3433f37 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) { + nvme_cdev_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 49276186d5bd..773dde5b231d 100644 --- a/drivers/nvme/host/nvme.h +++ b/drivers/nvme/host/nvme.h @@ -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); |