// SPDX-License-Identifier: GPL-2.0/* * gendisk handling * * Portions Copyright (C) 2020 Christoph Hellwig */ #include <linux/module.h>#include <linux/ctype.h>#include <linux/fs.h>#include <linux/kdev_t.h>#include <linux/kernel.h>#include <linux/blkdev.h>#include <linux/backing-dev.h>#include <linux/init.h>#include <linux/spinlock.h>#include <linux/proc_fs.h>#include <linux/seq_file.h>#include <linux/slab.h>#include <linux/kmod.h>#include <linux/major.h>#include <linux/mutex.h>#include <linux/idr.h>#include <linux/log2.h>#include <linux/pm_runtime.h>#include <linux/badblocks.h>#include <linux/part_stat.h>#include <linux/blktrace_api.h> #include "blk-throttle.h"#include "blk.h"#include "blk-mq-sched.h"#include "blk-rq-qos.h"#include "blk-cgroup.h" static struct kobject *block_depr; /* * Unique, monotonically increasing sequential number associated with block * devices instances (i.e. incremented each time a device is attached). * Associating uevents with block devices in userspace is difficult and racy: * the uevent netlink socket is lossy, and on slow and overloaded systems has * a very high latency. * Block devices do not have exclusive owners in userspace, any process can set * one up (e.g. loop devices). Moreover, device names can be reused (e.g. loop0 * can be reused again and again). * A userspace process setting up a block device and watching for its events * cannot thus reliably tell whether an event relates to the device it just set * up or another earlier instance with the same name. * This sequential number allows userspace processes to solve this problem, and * uniquely associate an uevent to the lifetime to a device. */static atomic64_t diskseq; /* for extended dynamic devt allocation, currently only one major is used */#define NR_EXT_DEVT (1 << MINORBITS)static DEFINE_IDA(ext_devt_ida); void set_capacity(struct gendisk *disk, sector_t sectors){ if (sectors > BLK_DEV_MAX_SECTORS) { pr_warn_once("%s: truncate capacity from %lld to %lld\n", disk->disk_name, sectors, BLK_DEV_MAX_SECTORS); sectors = BLK_DEV_MAX_SECTORS; } bdev_set_nr_sectors(disk->part0, sectors);}EXPORT_SYMBOL(set_capacity); /* * Set disk capacity and notify if the size is not currently zero and will not * be set to zero. Returns true if a uevent was sent, otherwise false. */bool set_capacity_and_notify(struct gendisk *disk, sector_t size){ sector_t capacity = get_capacity(disk); char *envp[] = { "RESIZE=1", NULL }; set_capacity(disk, size); /* * Only print a message and send a uevent if the gendisk is user visible * and alive. This avoids spamming the log and udev when setting the * initial capacity during probing. */ if (size == capacity || !disk_live(disk) || (disk->flags & GENHD_FL_HIDDEN)) return false; pr_info_ratelimited("%s: detected capacity change from %lld to %lld\n", disk->disk_name, capacity, size); /* * Historically we did not send a uevent for changes to/from an empty * device. */ if (!capacity || !size) return false; kobject_uevent_env(&disk_to_dev(disk)->kobj, KOBJ_CHANGE, envp); return true;}EXPORT_SYMBOL_GPL(set_capacity_and_notify); static void part_stat_read_all(struct block_device *part, struct disk_stats *stat){ int cpu; memset(stat, 0, sizeof(struct disk_stats)); for_each_possible_cpu(cpu) { struct disk_stats *ptr = per_cpu_ptr(part->bd_stats, cpu); int group; for (group = 0; group < NR_STAT_GROUPS; group++) { stat->nsecs[group] += ptr->nsecs[group]; stat->sectors[group] += ptr->sectors[group]; stat->ios[group] += ptr->ios[group]; stat->merges[group] += ptr->merges[group]; } stat->io_ticks += ptr->io_ticks; }} static void bdev_count_inflight_rw(struct block_device *part, unsigned int inflight[2], bool mq_driver){ int write = 0; int read = 0; int cpu; if (mq_driver) { blk_mq_in_driver_rw(part, inflight); return; } for_each_possible_cpu(cpu) { read += part_stat_local_read_cpu(part, in_flight[READ], cpu); write += part_stat_local_read_cpu(part, in_flight[WRITE], cpu); } /* * While iterating all CPUs, some IOs may be issued from a CPU already * traversed and complete on a CPU that has not yet been traversed, * causing the inflight number to be negative. */ inflight[READ] = read > 0 ? read : 0; inflight[WRITE] = write > 0 ? write : 0;} /** * bdev_count_inflight - get the number of inflight IOs for a block device. * * @part: the block device. * * Inflight here means started IO accounting, from bdev_start_io_acct() for * bio-based block device, and from blk_account_io_start() for rq-based block * device. */unsigned int bdev_count_inflight(struct block_device *part){ unsigned int inflight[2] = {0}; bdev_count_inflight_rw(part, inflight, false); return inflight[READ] + inflight[WRITE];}EXPORT_SYMBOL_GPL(bdev_count_inflight); /* * Can be deleted altogether. Later. * */#define BLKDEV_MAJOR_HASH_SIZE 255static struct blk_major_name { struct blk_major_name *next; int major; char name[16];#ifdef CONFIG_BLOCK_LEGACY_AUTOLOAD void (*probe)(dev_t devt);#endif} *major_names[BLKDEV_MAJOR_HASH_SIZE];static DEFINE_MUTEX(major_names_lock);static DEFINE_SPINLOCK(major_names_spinlock); /* index in the above - for now: assume no multimajor ranges */static inline int major_to_index(unsigned major){ return major % BLKDEV_MAJOR_HASH_SIZE;} #ifdef CONFIG_PROC_FSvoid blkdev_show(struct seq_file *seqf, off_t offset){ struct blk_major_name *dp; spin_lock(&major_names_spinlock); for (dp = major_names[major_to_index(offset)]; dp; dp = dp->next) if (dp->major == offset) seq_printf(seqf, "%3d %s\n", dp->major, dp->name); spin_unlock(&major_names_spinlock);}#endif /* CONFIG_PROC_FS */ /** * __register_blkdev - register a new block device * * @major: the requested major device number [1..BLKDEV_MAJOR_MAX-1]. If * @major = 0, try to allocate any unused major number. * @name: the name of the new block device as a zero terminated string * @probe: pre-devtmpfs / pre-udev callback used to create disks when their * pre-created device node is accessed. When a probe call uses * add_disk() and it fails the driver must cleanup resources. This * interface may soon be removed. * * The @name must be unique within the system. * * The return value depends on the @major input parameter: * * - if a major device number was requested in range [1..BLKDEV_MAJOR_MAX-1] * then the function returns zero on success, or a negative error code * - if any unused major number was requested with @major = 0 parameter * then the return value is the allocated major number in range * [1..BLKDEV_MAJOR_MAX-1] or a negative error code otherwise * * See Documentation/admin-guide/devices.txt for the list of allocated * major numbers. * * Use register_blkdev instead for any new code. */int __register_blkdev(unsigned int major, const char *name, void (*probe)(dev_t devt)){ struct blk_major_name **n, *p; int index, ret = 0; mutex_lock(&major_names_lock); /* temporary */ if (major == 0) { for (index = ARRAY_SIZE(major_names)-1; index > 0; index--) { if (major_names[index] == NULL) break; } if (index == 0) { printk("%s: failed to get major for %s\n", __func__, name); ret = -EBUSY; goto out; } major = index; ret = major; } if (major >= BLKDEV_MAJOR_MAX) { pr_err("%s: major requested (%u) is greater than the maximum (%u) for %s\n", __func__, major, BLKDEV_MAJOR_MAX-1, name); ret = -EINVAL; goto out; } p = kmalloc_obj(struct blk_major_name); if (p == NULL) { ret = -ENOMEM; goto out; } p->major = major;#ifdef CONFIG_BLOCK_LEGACY_AUTOLOAD p->probe = probe;#endif strscpy(p->name, name, sizeof(p->name)); p->next = NULL; index = major_to_index(major); spin_lock(&major_names_spinlock); for (n = &major_names[index]; *n; n = &(*n)->next) { if ((*n)->major == major) break; } if (!*n) *n = p; else ret = -EBUSY; spin_unlock(&major_names_spinlock); if (ret < 0) { printk("register_blkdev: cannot get major %u for %s\n", major, name); kfree(p); }out: mutex_unlock(&major_names_lock); return ret;}EXPORT_SYMBOL(__register_blkdev); void unregister_blkdev(unsigned int major, const char *name){ struct blk_major_name **n; struct blk_major_name *p = NULL; int index = major_to_index(major); mutex_lock(&major_names_lock); spin_lock(&major_names_spinlock); for (n = &major_names[index]; *n; n = &(*n)->next) if ((*n)->major == major) break; if (!*n || strcmp((*n)->name, name)) { WARN_ON(1); } else { p = *n; *n = p->next; } spin_unlock(&major_names_spinlock); mutex_unlock(&major_names_lock); kfree(p);} EXPORT_SYMBOL(unregister_blkdev); int blk_alloc_ext_minor(void){ int idx; idx = ida_alloc_range(&ext_devt_ida, 0, NR_EXT_DEVT - 1, GFP_KERNEL); if (idx == -ENOSPC) return -EBUSY; return idx;} void blk_free_ext_minor(unsigned int minor){ ida_free(&ext_devt_ida, minor);} void disk_uevent(struct gendisk *disk, enum kobject_action action){ struct block_device *part; unsigned long idx; rcu_read_lock(); xa_for_each(&disk->part_tbl, idx, part) { if (bdev_is_partition(part) && !bdev_nr_sectors(part)) continue; if (!kobject_get_unless_zero(&part->bd_device.kobj)) continue; rcu_read_unlock(); kobject_uevent(bdev_kobj(part), action); put_device(&part->bd_device); rcu_read_lock(); } rcu_read_unlock();}EXPORT_SYMBOL_GPL(disk_uevent); int disk_scan_partitions(struct gendisk *disk, blk_mode_t mode){ struct file *file; int ret = 0; if (!disk_has_partscan(disk)) return -EINVAL; if (disk->open_partitions) return -EBUSY; /* * If the device is opened exclusively by current thread already, it's * safe to scan partitons, otherwise, use bd_prepare_to_claim() to * synchronize with other exclusive openers and other partition * scanners. */ if (!(mode & BLK_OPEN_EXCL)) { ret = bd_prepare_to_claim(disk->part0, disk_scan_partitions, NULL); if (ret) return ret; } set_bit(GD_NEED_PART_SCAN, &disk->state); file = bdev_file_open_by_dev(disk_devt(disk), mode & ~BLK_OPEN_EXCL, NULL, NULL); if (IS_ERR(file)) ret = PTR_ERR(file); else fput(file); /* * If blkdev_get_by_dev() failed early, GD_NEED_PART_SCAN is still set, * and this will cause that re-assemble partitioned raid device will * creat partition for underlying disk. */ clear_bit(GD_NEED_PART_SCAN, &disk->state); if (!(mode & BLK_OPEN_EXCL)) bd_abort_claiming(disk->part0, disk_scan_partitions); return ret;} static void add_disk_final(struct gendisk *disk){ struct device *ddev = disk_to_dev(disk); if (!(disk->flags & GENHD_FL_HIDDEN)) { bdev_add(disk->part0, ddev->devt); if (get_capacity(disk)) disk_scan_partitions(disk, BLK_OPEN_READ); /* * Announce the disk and partitions after all partitions are * created. (for hidden disks uevents remain suppressed forever) */ dev_set_uevent_suppress(ddev, 0); disk_uevent(disk, KOBJ_ADD); } blk_apply_bdi_limits(disk->bdi, &disk->queue->limits); disk_add_events(disk); set_bit(GD_ADDED, &disk->state);} static int __add_disk(struct device *parent, struct gendisk *disk, const struct attribute_group **groups, struct fwnode_handle *fwnode) { struct device *ddev = disk_to_dev(disk); int ret; if (WARN_ON_ONCE(bdev_nr_sectors(disk->part0) > BLK_DEV_MAX_SECTORS)) return -EINVAL; if (queue_is_mq(disk->queue)) { /* * ->submit_bio and ->poll_bio are bypassed for blk-mq drivers. */ if (disk->fops->submit_bio || disk->fops->poll_bio) return -EINVAL; } else { if (!disk->fops->submit_bio) return -EINVAL; bdev_set_flag(disk->part0, BD_HAS_SUBMIT_BIO); } /* * We do not support partitions with zoned block devices, so do not try * to scan the partitions table. */ if (blk_queue_is_zoned(disk->queue)) disk->flags |= GENHD_FL_NO_PART; /* * If the driver provides an explicit major number it also must provide * the number of minors numbers supported, and those will be used to * setup the gendisk. * Otherwise just allocate the device numbers for both the whole device * and all partitions from the extended dev_t space. */ ret = -EINVAL; if (disk->major) { if (WARN_ON(!disk->minors)) goto out; if (disk->minors > DISK_MAX_PARTS) { pr_err("block: can't allocate more than %d partitions\n", DISK_MAX_PARTS); disk->minors = DISK_MAX_PARTS; } if (disk->first_minor > MINORMASK || disk->minors > MINORMASK + 1 || disk->first_minor + disk->minors > MINORMASK + 1) goto out; } else { if (WARN_ON(disk->minors)) goto out; ret = blk_alloc_ext_minor(); if (ret < 0) goto out; disk->major = BLOCK_EXT_MAJOR; disk->first_minor = ret; } /* delay uevents, until we scanned partition table */ dev_set_uevent_suppress(ddev, 1); ddev->parent = parent; ddev->groups = groups; dev_set_name(ddev, "%s", disk->disk_name); if (fwnode) device_set_node(ddev, fwnode); if (!(disk->flags & GENHD_FL_HIDDEN)) ddev->devt = MKDEV(disk->major, disk->first_minor); ret = device_add(ddev); if (ret)Lines 1–500 of 1596. Load more
// SPDX-License-Identifier: GPL-2.0 /* * gendisk handling * * Portions Copyright (C) 2020 Christoph Hellwig */ #include <linux/module.h> #include <linux/ctype.h> #include <linux/fs.h> #include <linux/kdev_t.h> #include <linux/kernel.h> #include <linux/blkdev.h> #include <linux/backing-dev.h> #include <linux/init.h> #include <linux/spinlock.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <linux/slab.h> #include <linux/kmod.h> #include <linux/major.h> #include <linux/mutex.h> #include <linux/idr.h> #include <linux/log2.h> #include <linux/pm_runtime.h> #include <linux/badblocks.h> #include <linux/part_stat.h> #include <linux/blktrace_api.h> #include "blk-throttle.h" #include "blk.h" #include "blk-mq-sched.h" #include "blk-rq-qos.h" #include "blk-cgroup.h" static struct kobject *block_depr; /* * Unique, monotonically increasing sequential number associated with block * devices instances (i.e. incremented each time a device is attached). * Associating uevents with block devices in userspace is difficult and racy: * the uevent netlink socket is lossy, and on slow and overloaded systems has * a very high latency. * Block devices do not have exclusive owners in userspace, any process can set * one up (e.g. loop devices). Moreover, device names can be reused (e.g. loop0 * can be reused again and again). * A userspace process setting up a block device and watching for its events * cannot thus reliably tell whether an event relates to the device it just set * up or another earlier instance with the same name. * This sequential number allows userspace processes to solve this problem, and * uniquely associate an uevent to the lifetime to a device. */ static atomic64_t diskseq; /* for extended dynamic devt allocation, currently only one major is used */ #define NR_EXT_DEVT (1 << MINORBITS) static DEFINE_IDA(ext_devt_ida); void set_capacity(struct gendisk *disk, sector_t sectors) { if (sectors > BLK_DEV_MAX_SECTORS) { pr_warn_once("%s: truncate capacity from %lld to %lld\n", disk->disk_name, sectors, BLK_DEV_MAX_SECTORS); sectors = BLK_DEV_MAX_SECTORS; } bdev_set_nr_sectors(disk->part0, sectors); } EXPORT_SYMBOL(set_capacity); /* * Set disk capacity and notify if the size is not currently zero and will not * be set to zero. Returns true if a uevent was sent, otherwise false. */ bool set_capacity_and_notify(struct gendisk *disk, sector_t size) { sector_t capacity = get_capacity(disk); char *envp[] = { "RESIZE=1", NULL }; set_capacity(disk, size); /* * Only print a message and send a uevent if the gendisk is user visible * and alive. This avoids spamming the log and udev when setting the * initial capacity during probing. */ if (size == capacity || !disk_live(disk) || (disk->flags & GENHD_FL_HIDDEN)) return false; pr_info_ratelimited("%s: detected capacity change from %lld to %lld\n", disk->disk_name, capacity, size); /* * Historically we did not send a uevent for changes to/from an empty * device. */ if (!capacity || !size) return false; kobject_uevent_env(&disk_to_dev(disk)->kobj, KOBJ_CHANGE, envp); return true; } EXPORT_SYMBOL_GPL(set_capacity_and_notify); static void part_stat_read_all(struct block_device *part, struct disk_stats *stat) { int cpu; memset(stat, 0, sizeof(struct disk_stats)); for_each_possible_cpu(cpu) { struct disk_stats *ptr = per_cpu_ptr(part->bd_stats, cpu); int group; for (group = 0; group < NR_STAT_GROUPS; group++) { stat->nsecs[group] += ptr->nsecs[group]; stat->sectors[group] += ptr->sectors[group]; stat->ios[group] += ptr->ios[group]; stat->merges[group] += ptr->merges[group]; } stat->io_ticks += ptr->io_ticks; } } static void bdev_count_inflight_rw(struct block_device *part, unsigned int inflight[2], bool mq_driver) { int write = 0; int read = 0; int cpu; if (mq_driver) { blk_mq_in_driver_rw(part, inflight); return; } for_each_possible_cpu(cpu) { read += part_stat_local_read_cpu(part, in_flight[READ], cpu); write += part_stat_local_read_cpu(part, in_flight[WRITE], cpu); } /* * While iterating all CPUs, some IOs may be issued from a CPU already * traversed and complete on a CPU that has not yet been traversed, * causing the inflight number to be negative. */ inflight[READ] = read > 0 ? read : 0; inflight[WRITE] = write > 0 ? write : 0; } /** * bdev_count_inflight - get the number of inflight IOs for a block device. * * @part: the block device. * * Inflight here means started IO accounting, from bdev_start_io_acct() for * bio-based block device, and from blk_account_io_start() for rq-based block * device. */ unsigned int bdev_count_inflight(struct block_device *part) { unsigned int inflight[2] = {0}; bdev_count_inflight_rw(part, inflight, false); return inflight[READ] + inflight[WRITE]; } EXPORT_SYMBOL_GPL(bdev_count_inflight); /* * Can be deleted altogether. Later. * */ #define BLKDEV_MAJOR_HASH_SIZE 255 static struct blk_major_name { struct blk_major_name *next; int major; char name[16]; #ifdef CONFIG_BLOCK_LEGACY_AUTOLOAD void (*probe)(dev_t devt); #endif } *major_names[BLKDEV_MAJOR_HASH_SIZE]; static DEFINE_MUTEX(major_names_lock); static DEFINE_SPINLOCK(major_names_spinlock); /* index in the above - for now: assume no multimajor ranges */ static inline int major_to_index(unsigned major) { return major % BLKDEV_MAJOR_HASH_SIZE; } #ifdef CONFIG_PROC_FS void blkdev_show(struct seq_file *seqf, off_t offset) { struct blk_major_name *dp; spin_lock(&major_names_spinlock); for (dp = major_names[major_to_index(offset)]; dp; dp = dp->next) if (dp->major == offset) seq_printf(seqf, "%3d %s\n", dp->major, dp->name); spin_unlock(&major_names_spinlock); } #endif /* CONFIG_PROC_FS */ /** * __register_blkdev - register a new block device * * @major: the requested major device number [1..BLKDEV_MAJOR_MAX-1]. If * @major = 0, try to allocate any unused major number. * @name: the name of the new block device as a zero terminated string * @probe: pre-devtmpfs / pre-udev callback used to create disks when their * pre-created device node is accessed. When a probe call uses * add_disk() and it fails the driver must cleanup resources. This * interface may soon be removed. * * The @name must be unique within the system. * * The return value depends on the @major input parameter: * * - if a major device number was requested in range [1..BLKDEV_MAJOR_MAX-1] * then the function returns zero on success, or a negative error code * - if any unused major number was requested with @major = 0 parameter * then the return value is the allocated major number in range * [1..BLKDEV_MAJOR_MAX-1] or a negative error code otherwise * * See Documentation/admin-guide/devices.txt for the list of allocated * major numbers. * * Use register_blkdev instead for any new code. */ int __register_blkdev(unsigned int major, const char *name, void (*probe)(dev_t devt)) { struct blk_major_name **n, *p; int index, ret = 0; mutex_lock(&major_names_lock); /* temporary */ if (major == 0) { for (index = ARRAY_SIZE(major_names)-1; index > 0; index--) { if (major_names[index] == NULL) break; } if (index == 0) { printk("%s: failed to get major for %s\n", __func__, name); ret = -EBUSY; goto out; } major = index; ret = major; } if (major >= BLKDEV_MAJOR_MAX) { pr_err("%s: major requested (%u) is greater than the maximum (%u) for %s\n", __func__, major, BLKDEV_MAJOR_MAX-1, name); ret = -EINVAL; goto out; } p = kmalloc_obj(struct blk_major_name); if (p == NULL) { ret = -ENOMEM; goto out; } p->major = major; #ifdef CONFIG_BLOCK_LEGACY_AUTOLOAD p->probe = probe; #endif strscpy(p->name, name, sizeof(p->name)); p->next = NULL; index = major_to_index(major); spin_lock(&major_names_spinlock); for (n = &major_names[index]; *n; n = &(*n)->next) { if ((*n)->major == major) break; } if (!*n) *n = p; else ret = -EBUSY; spin_unlock(&major_names_spinlock); if (ret < 0) { printk("register_blkdev: cannot get major %u for %s\n", major, name); kfree(p); } out: mutex_unlock(&major_names_lock); return ret; } EXPORT_SYMBOL(__register_blkdev); void unregister_blkdev(unsigned int major, const char *name) { struct blk_major_name **n; struct blk_major_name *p = NULL; int index = major_to_index(major); mutex_lock(&major_names_lock); spin_lock(&major_names_spinlock); for (n = &major_names[index]; *n; n = &(*n)->next) if ((*n)->major == major) break; if (!*n || strcmp((*n)->name, name)) { WARN_ON(1); } else { p = *n; *n = p->next; } spin_unlock(&major_names_spinlock); mutex_unlock(&major_names_lock); kfree(p); } EXPORT_SYMBOL(unregister_blkdev); int blk_alloc_ext_minor(void) { int idx; idx = ida_alloc_range(&ext_devt_ida, 0, NR_EXT_DEVT - 1, GFP_KERNEL); if (idx == -ENOSPC) return -EBUSY; return idx; } void blk_free_ext_minor(unsigned int minor) { ida_free(&ext_devt_ida, minor); } void disk_uevent(struct gendisk *disk, enum kobject_action action) { struct block_device *part; unsigned long idx; rcu_read_lock(); xa_for_each(&disk->part_tbl, idx, part) { if (bdev_is_partition(part) && !bdev_nr_sectors(part)) continue; if (!kobject_get_unless_zero(&part->bd_device.kobj)) continue; rcu_read_unlock(); kobject_uevent(bdev_kobj(part), action); put_device(&part->bd_device); rcu_read_lock(); } rcu_read_unlock(); } EXPORT_SYMBOL_GPL(disk_uevent); int disk_scan_partitions(struct gendisk *disk, blk_mode_t mode) { struct file *file; int ret = 0; if (!disk_has_partscan(disk)) return -EINVAL; if (disk->open_partitions) return -EBUSY; /* * If the device is opened exclusively by current thread already, it's * safe to scan partitons, otherwise, use bd_prepare_to_claim() to * synchronize with other exclusive openers and other partition * scanners. */ if (!(mode & BLK_OPEN_EXCL)) { ret = bd_prepare_to_claim(disk->part0, disk_scan_partitions, NULL); if (ret) return ret; } set_bit(GD_NEED_PART_SCAN, &disk->state); file = bdev_file_open_by_dev(disk_devt(disk), mode & ~BLK_OPEN_EXCL, NULL, NULL); if (IS_ERR(file)) ret = PTR_ERR(file); else fput(file); /* * If blkdev_get_by_dev() failed early, GD_NEED_PART_SCAN is still set, * and this will cause that re-assemble partitioned raid device will * creat partition for underlying disk. */ clear_bit(GD_NEED_PART_SCAN, &disk->state); if (!(mode & BLK_OPEN_EXCL)) bd_abort_claiming(disk->part0, disk_scan_partitions); return ret; } static void add_disk_final(struct gendisk *disk) { struct device *ddev = disk_to_dev(disk); if (!(disk->flags & GENHD_FL_HIDDEN)) { bdev_add(disk->part0, ddev->devt); if (get_capacity(disk)) disk_scan_partitions(disk, BLK_OPEN_READ); /* * Announce the disk and partitions after all partitions are * created. (for hidden disks uevents remain suppressed forever) */ dev_set_uevent_suppress(ddev, 0); disk_uevent(disk, KOBJ_ADD); } blk_apply_bdi_limits(disk->bdi, &disk->queue->limits); disk_add_events(disk); set_bit(GD_ADDED, &disk->state); } static int __add_disk(struct device *parent, struct gendisk *disk, const struct attribute_group **groups, struct fwnode_handle *fwnode) { struct device *ddev = disk_to_dev(disk); int ret; if (WARN_ON_ONCE(bdev_nr_sectors(disk->part0) > BLK_DEV_MAX_SECTORS)) return -EINVAL; if (queue_is_mq(disk->queue)) { /* * ->submit_bio and ->poll_bio are bypassed for blk-mq drivers. */ if (disk->fops->submit_bio || disk->fops->poll_bio) return -EINVAL; } else { if (!disk->fops->submit_bio) return -EINVAL; bdev_set_flag(disk->part0, BD_HAS_SUBMIT_BIO); } /* * We do not support partitions with zoned block devices, so do not try * to scan the partitions table. */ if (blk_queue_is_zoned(disk->queue)) disk->flags |= GENHD_FL_NO_PART; /* * If the driver provides an explicit major number it also must provide * the number of minors numbers supported, and those will be used to * setup the gendisk. * Otherwise just allocate the device numbers for both the whole device * and all partitions from the extended dev_t space. */ ret = -EINVAL; if (disk->major) { if (WARN_ON(!disk->minors)) goto out; if (disk->minors > DISK_MAX_PARTS) { pr_err("block: can't allocate more than %d partitions\n", DISK_MAX_PARTS); disk->minors = DISK_MAX_PARTS; } if (disk->first_minor > MINORMASK || disk->minors > MINORMASK + 1 || disk->first_minor + disk->minors > MINORMASK + 1) goto out; } else { if (WARN_ON(disk->minors)) goto out; ret = blk_alloc_ext_minor(); if (ret < 0) goto out; disk->major = BLOCK_EXT_MAJOR; disk->first_minor = ret; } /* delay uevents, until we scanned partition table */ dev_set_uevent_suppress(ddev, 1); ddev->parent = parent; ddev->groups = groups; dev_set_name(ddev, "%s", disk->disk_name); if (fwnode) device_set_node(ddev, fwnode); if (!(disk->flags & GENHD_FL_HIDDEN)) ddev->devt = MKDEV(disk->major, disk->first_minor); ret = device_add(ddev); if (ret)