Something went wrong. Try again.
Linux kernel mirror (for testing) git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git
Something went wrong. Try again.
123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181182183184185186187188189190191192193194195196197198199200201202203204205206207208209210211212213214215216217218219220221222223224225226227228229230231232233234235236237238239240241242243244245246247248249250251252253254255256257258259260261262263264265266267268269270271272273274275276277278279280281282283284285286287288289290291292293294295296297298299300301302303304305306307308309310311312313314315316317318319320321322323324325326327328329330331332333334335336337338339340341342343344345346347348349350351352353354355356357358359360361362363364365366367368369370371372373374375376377378379380381382383384385386387388389390391392393394395396397398399400401402403404405406407408409410411412413414415416417418419420421422423424425426427428429430431432433434435436437438439440441442443444445446447448449450451452453454455456457458459460461462463464465466467468469470471472473474475476477478479480481482483484485486487488489490491492493494495496497498499500501502503504505506507508509510511512513514515516517518519520521522523524525526527528529530531532533534535536537538539540541542543544545546547548549550551552553554555556557558559560561562563564565566567568569570571572573574575576577578579580581582583584585586587588589590591592593594595596597598599600601602603604605606607608609610611612613614615616617618619620621622623624625626627628629630631632633634635636637638639640641642643644645646647648649650651652653654655656657658659660661662663664665666667668669670671672673674675676677678679680681682683684685686687688689690691692693694695696697698699700701702703704705706707708709710711712713714715716717718719720721722723724725726727728729730731732733734735736737738739740741742743744745746747748749750751752753754755756757758759760761762763764765766767768769770771772773774775776777778779780781782783784785786787788789790791792793794795796797798799800801802803804805806807808809810811812813814815816817818819820821822823824825826827828829830831832833834835836837838839840841842843844845846847848849850851852853854855856857858859860861862863864865866867868869870871872873874875876877878879880881882883884885886887888889890891892893894895896897898899900901902903904905906907908909910911912913914915916917918919920921922923924925926927928929930931932933934935936937938939940941942943944945946947948949950951952953954955956957958959960961962963964965966967968969970971972973974975// SPDX-License-Identifier: GPL-2.0#include <linux/capability.h>#include <linux/compat.h>#include <linux/blkdev.h>#include <linux/export.h>#include <linux/gfp.h>#include <linux/blkpg.h>#include <linux/hdreg.h>#include <linux/backing-dev.h>#include <linux/fs.h>#include <linux/blktrace_api.h>#include <linux/pr.h>#include <linux/uaccess.h>#include <linux/pagemap.h>#include <linux/io_uring/cmd.h>#include <linux/blk-integrity.h>#include <uapi/linux/blkdev.h>#include "blk.h"#include "blk-crypto-internal.h"
static int blkpg_do_ioctl(struct block_device *bdev, struct blkpg_partition __user *upart, int op){ struct gendisk *disk = bdev->bd_disk; struct blkpg_partition p; sector_t start, length, capacity, end;
if (!capable(CAP_SYS_ADMIN)) return -EACCES; if (copy_from_user(&p, upart, sizeof(struct blkpg_partition))) return -EFAULT; if (bdev_is_partition(bdev)) return -EINVAL;
if (p.pno <= 0) return -EINVAL;
if (op == BLKPG_DEL_PARTITION) return bdev_del_partition(disk, p.pno);
if (p.start < 0 || p.length <= 0 || LLONG_MAX - p.length < p.start) return -EINVAL; /* Check that the partition is aligned to the block size */ if (!IS_ALIGNED(p.start | p.length, bdev_logical_block_size(bdev))) return -EINVAL;
start = p.start >> SECTOR_SHIFT; length = p.length >> SECTOR_SHIFT; capacity = get_capacity(disk);
if (check_add_overflow(start, length, &end)) return -EINVAL;
if (start >= capacity || end > capacity) return -EINVAL;
switch (op) { case BLKPG_ADD_PARTITION: return bdev_add_partition(disk, p.pno, start, length); case BLKPG_RESIZE_PARTITION: return bdev_resize_partition(disk, p.pno, start, length); default: return -EINVAL; }}
static int blkpg_ioctl(struct block_device *bdev, struct blkpg_ioctl_arg __user *arg){ struct blkpg_partition __user *udata; int op;
if (get_user(op, &arg->op) || get_user(udata, &arg->data)) return -EFAULT;
return blkpg_do_ioctl(bdev, udata, op);}
#ifdef CONFIG_COMPATstruct compat_blkpg_ioctl_arg { compat_int_t op; compat_int_t flags; compat_int_t datalen; compat_caddr_t data;};
static int compat_blkpg_ioctl(struct block_device *bdev, struct compat_blkpg_ioctl_arg __user *arg){ compat_caddr_t udata; int op;
if (get_user(op, &arg->op) || get_user(udata, &arg->data)) return -EFAULT;
return blkpg_do_ioctl(bdev, compat_ptr(udata), op);}#endif
/* * Check that [start, start + len) is a valid range from the block device's * perspective, including verifying that it can be correctly translated into * logical block addresses. */static int blk_validate_byte_range(struct block_device *bdev, uint64_t start, uint64_t len){ unsigned int bs_mask = bdev_logical_block_size(bdev) - 1; uint64_t end;
if ((start | len) & bs_mask) return -EINVAL; if (!len) return -EINVAL; if (check_add_overflow(start, len, &end) || end > bdev_nr_bytes(bdev)) return -EINVAL;
return 0;}
static int blk_ioctl_discard(struct block_device *bdev, blk_mode_t mode, unsigned long arg){ uint64_t range[2], start, len; struct bio *prev = NULL, *bio; sector_t sector, nr_sects; struct blk_plug plug; int err;
if (copy_from_user(range, (void __user *)arg, sizeof(range))) return -EFAULT; start = range[0]; len = range[1];
if (!bdev_max_discard_sectors(bdev)) return -EOPNOTSUPP;
if (!(mode & BLK_OPEN_WRITE)) return -EBADF; if (bdev_read_only(bdev)) return -EPERM; err = blk_validate_byte_range(bdev, start, len); if (err) return err;
inode_lock(bdev->bd_mapping->host); filemap_invalidate_lock(bdev->bd_mapping); err = truncate_bdev_range(bdev, mode, start, start + len - 1); if (err) goto fail;
sector = start >> SECTOR_SHIFT; nr_sects = len >> SECTOR_SHIFT;
blk_start_plug(&plug); while (!fatal_signal_pending(current)) { bio = blk_alloc_discard_bio(bdev, §or, &nr_sects, GFP_KERNEL); if (!bio) break; prev = bio_chain_and_submit(prev, bio); } if (prev) { err = bio_submit_or_kill(prev, BLKDEV_ZERO_KILLABLE); if (err == -EOPNOTSUPP) err = 0; bio_put(prev); } blk_finish_plug(&plug);fail: filemap_invalidate_unlock(bdev->bd_mapping); inode_unlock(bdev->bd_mapping->host); return err;}
static int blk_ioctl_secure_erase(struct block_device *bdev, blk_mode_t mode, void __user *argp){ uint64_t start, len, end; uint64_t range[2]; int err;
if (!(mode & BLK_OPEN_WRITE)) return -EBADF; if (!bdev_max_secure_erase_sectors(bdev)) return -EOPNOTSUPP; if (copy_from_user(range, argp, sizeof(range))) return -EFAULT;
start = range[0]; len = range[1]; if ((start & 511) || (len & 511)) return -EINVAL; if (check_add_overflow(start, len, &end) || end > bdev_nr_bytes(bdev)) return -EINVAL;
inode_lock(bdev->bd_mapping->host); filemap_invalidate_lock(bdev->bd_mapping); err = truncate_bdev_range(bdev, mode, start, end - 1); if (!err) err = blkdev_issue_secure_erase(bdev, start >> 9, len >> 9, GFP_KERNEL); filemap_invalidate_unlock(bdev->bd_mapping); inode_unlock(bdev->bd_mapping->host); return err;}
static int blk_ioctl_zeroout(struct block_device *bdev, blk_mode_t mode, unsigned long arg){ uint64_t range[2]; uint64_t start, end, len; int err;
if (!(mode & BLK_OPEN_WRITE)) return -EBADF;
if (copy_from_user(range, (void __user *)arg, sizeof(range))) return -EFAULT;
start = range[0]; len = range[1]; end = start + len - 1;
if (start & 511) return -EINVAL; if (len & 511) return -EINVAL; if (end >= (uint64_t)bdev_nr_bytes(bdev)) return -EINVAL; if (end < start) return -EINVAL;
/* Invalidate the page cache, including dirty pages */ inode_lock(bdev->bd_mapping->host); filemap_invalidate_lock(bdev->bd_mapping); err = truncate_bdev_range(bdev, mode, start, end); if (err) goto fail;
err = blkdev_issue_zeroout(bdev, start >> 9, len >> 9, GFP_KERNEL, BLKDEV_ZERO_NOUNMAP | BLKDEV_ZERO_KILLABLE);
fail: filemap_invalidate_unlock(bdev->bd_mapping); inode_unlock(bdev->bd_mapping->host); return err;}
static int put_ushort(unsigned short __user *argp, unsigned short val){ return put_user(val, argp);}
static int put_int(int __user *argp, int val){ return put_user(val, argp);}
static int put_uint(unsigned int __user *argp, unsigned int val){ return put_user(val, argp);}
static int put_long(long __user *argp, long val){ return put_user(val, argp);}
static int put_ulong(unsigned long __user *argp, unsigned long val){ return put_user(val, argp);}
static int put_u64(u64 __user *argp, u64 val){ return put_user(val, argp);}
#ifdef CONFIG_COMPATstatic int compat_put_long(compat_long_t __user *argp, long val){ return put_user(val, argp);}
static int compat_put_ulong(compat_ulong_t __user *argp, compat_ulong_t val){ return put_user(val, argp);}#endif
#ifdef CONFIG_COMPAT/* * This is the equivalent of compat_ptr_ioctl(), to be used by block * drivers that implement only commands that are completely compatible * between 32-bit and 64-bit user space */int blkdev_compat_ptr_ioctl(struct block_device *bdev, blk_mode_t mode, unsigned cmd, unsigned long arg){ struct gendisk *disk = bdev->bd_disk;
if (disk->fops->ioctl) return disk->fops->ioctl(bdev, mode, cmd, (unsigned long)compat_ptr(arg));
return -ENOIOCTLCMD;}EXPORT_SYMBOL(blkdev_compat_ptr_ioctl);#endif
enum pr_direction { PR_IN, /* read from device */ PR_OUT, /* write to device */};
static bool blkdev_pr_allowed(struct block_device *bdev, blk_mode_t mode, enum pr_direction dir){ /* no sense to make reservations for partitions */ if (bdev_is_partition(bdev)) return false;
if (capable(CAP_SYS_ADMIN)) return true;
/* * Only allow unprivileged reservation _out_ commands if the file * descriptor is open for writing. Allow reservation _in_ commands if * the file descriptor is open for reading since they do not modify the * device. */ if (dir == PR_IN) return mode & BLK_OPEN_READ; else return mode & BLK_OPEN_WRITE;}
static int blkdev_pr_register(struct block_device *bdev, blk_mode_t mode, struct pr_registration __user *arg){ const struct pr_ops *ops = bdev->bd_disk->fops->pr_ops; struct pr_registration reg;
if (!blkdev_pr_allowed(bdev, mode, PR_OUT)) return -EPERM; if (!ops || !ops->pr_register) return -EOPNOTSUPP; if (copy_from_user(®, arg, sizeof(reg))) return -EFAULT;
if (reg.flags & ~PR_FL_IGNORE_KEY) return -EOPNOTSUPP; return ops->pr_register(bdev, reg.old_key, reg.new_key, reg.flags);}
static int blkdev_pr_reserve(struct block_device *bdev, blk_mode_t mode, struct pr_reservation __user *arg){ const struct pr_ops *ops = bdev->bd_disk->fops->pr_ops; struct pr_reservation rsv;
if (!blkdev_pr_allowed(bdev, mode, PR_OUT)) return -EPERM; if (!ops || !ops->pr_reserve) return -EOPNOTSUPP; if (copy_from_user(&rsv, arg, sizeof(rsv))) return -EFAULT;
if (rsv.flags & ~PR_FL_IGNORE_KEY) return -EOPNOTSUPP; return ops->pr_reserve(bdev, rsv.key, rsv.type, rsv.flags);}
static int blkdev_pr_release(struct block_device *bdev, blk_mode_t mode, struct pr_reservation __user *arg){ const struct pr_ops *ops = bdev->bd_disk->fops->pr_ops; struct pr_reservation rsv;
if (!blkdev_pr_allowed(bdev, mode, PR_OUT)) return -EPERM; if (!ops || !ops->pr_release) return -EOPNOTSUPP; if (copy_from_user(&rsv, arg, sizeof(rsv))) return -EFAULT;
if (rsv.flags) return -EOPNOTSUPP; return ops->pr_release(bdev, rsv.key, rsv.type);}
static int blkdev_pr_preempt(struct block_device *bdev, blk_mode_t mode, struct pr_preempt __user *arg, bool abort){ const struct pr_ops *ops = bdev->bd_disk->fops->pr_ops; struct pr_preempt p;
if (!blkdev_pr_allowed(bdev, mode, PR_OUT)) return -EPERM; if (!ops || !ops->pr_preempt) return -EOPNOTSUPP; if (copy_from_user(&p, arg, sizeof(p))) return -EFAULT;
if (p.flags) return -EOPNOTSUPP; return ops->pr_preempt(bdev, p.old_key, p.new_key, p.type, abort);}
static int blkdev_pr_clear(struct block_device *bdev, blk_mode_t mode, struct pr_clear __user *arg){ const struct pr_ops *ops = bdev->bd_disk->fops->pr_ops; struct pr_clear c;
if (!blkdev_pr_allowed(bdev, mode, PR_OUT)) return -EPERM; if (!ops || !ops->pr_clear) return -EOPNOTSUPP; if (copy_from_user(&c, arg, sizeof(c))) return -EFAULT;
if (c.flags) return -EOPNOTSUPP; return ops->pr_clear(bdev, c.key);}
static int blkdev_pr_read_keys(struct block_device *bdev, blk_mode_t mode, struct pr_read_keys __user *arg){ const struct pr_ops *ops = bdev->bd_disk->fops->pr_ops; struct pr_keys *keys_info; struct pr_read_keys read_keys; u64 __user *keys_ptr; size_t keys_info_len; size_t keys_copy_len; int ret;
if (!blkdev_pr_allowed(bdev, mode, PR_IN)) return -EPERM; if (!ops || !ops->pr_read_keys) return -EOPNOTSUPP;
if (copy_from_user(&read_keys, arg, sizeof(read_keys))) return -EFAULT;
if (read_keys.num_keys > PR_KEYS_MAX) return -EINVAL;
keys_info_len = struct_size(keys_info, keys, read_keys.num_keys);
keys_info = kvzalloc(keys_info_len, GFP_KERNEL); if (!keys_info) return -ENOMEM;
keys_info->num_keys = read_keys.num_keys;
ret = ops->pr_read_keys(bdev, keys_info); if (ret) goto out;
/* Copy out individual keys */ keys_ptr = u64_to_user_ptr(read_keys.keys_ptr); keys_copy_len = min(read_keys.num_keys, keys_info->num_keys) * sizeof(keys_info->keys[0]);
if (copy_to_user(keys_ptr, keys_info->keys, keys_copy_len)) { ret = -EFAULT; goto out; }
/* Copy out the arg struct */ read_keys.generation = keys_info->generation; read_keys.num_keys = keys_info->num_keys;
if (copy_to_user(arg, &read_keys, sizeof(read_keys))) ret = -EFAULT;out: kvfree(keys_info); return ret;}
static int blkdev_pr_read_reservation(struct block_device *bdev, blk_mode_t mode, struct pr_read_reservation __user *arg){ const struct pr_ops *ops = bdev->bd_disk->fops->pr_ops; struct pr_held_reservation rsv = {}; struct pr_read_reservation out = {}; int ret;
if (!blkdev_pr_allowed(bdev, mode, PR_IN)) return -EPERM; if (!ops || !ops->pr_read_reservation) return -EOPNOTSUPP;
ret = ops->pr_read_reservation(bdev, &rsv); if (ret) return ret;
out.key = rsv.key; out.generation = rsv.generation; out.type = rsv.type;
if (copy_to_user(arg, &out, sizeof(out))) return -EFAULT; return 0;}
static int blkdev_flushbuf(struct block_device *bdev, unsigned cmd, unsigned long arg){ if (!capable(CAP_SYS_ADMIN)) return -EACCES;
mutex_lock(&bdev->bd_holder_lock); if (bdev->bd_holder_ops && bdev->bd_holder_ops->sync) bdev->bd_holder_ops->sync(bdev); else { mutex_unlock(&bdev->bd_holder_lock); sync_blockdev(bdev); }
invalidate_bdev(bdev); return 0;}
static int blkdev_roset(struct block_device *bdev, unsigned cmd, unsigned long arg){ int ret, n;
if (!capable(CAP_SYS_ADMIN)) return -EACCES;
if (get_user(n, (int __user *)arg)) return -EFAULT; if (bdev->bd_disk->fops->set_read_only) { ret = bdev->bd_disk->fops->set_read_only(bdev, n); if (ret) return ret; } if (n) bdev_set_flag(bdev, BD_READ_ONLY); else bdev_clear_flag(bdev, BD_READ_ONLY); return 0;}
static int blkdev_getgeo(struct block_device *bdev, struct hd_geometry __user *argp){ struct gendisk *disk = bdev->bd_disk; struct hd_geometry geo; int ret;
if (!argp) return -EINVAL; if (!disk->fops->getgeo) return -ENOTTY;
/* * We need to set the startsect first, the driver may * want to override it. */ memset(&geo, 0, sizeof(geo)); geo.start = get_start_sect(bdev); ret = disk->fops->getgeo(disk, &geo); if (ret) return ret; if (copy_to_user(argp, &geo, sizeof(geo))) return -EFAULT; return 0;}
#ifdef CONFIG_COMPATstruct compat_hd_geometry { unsigned char heads; unsigned char sectors; unsigned short cylinders; u32 start;};
static int compat_hdio_getgeo(struct block_device *bdev, struct compat_hd_geometry __user *ugeo){ struct gendisk *disk = bdev->bd_disk; struct hd_geometry geo; int ret;
if (!ugeo) return -EINVAL; if (!disk->fops->getgeo) return -ENOTTY;
memset(&geo, 0, sizeof(geo)); /* * We need to set the startsect first, the driver may * want to override it. */ geo.start = get_start_sect(bdev); ret = disk->fops->getgeo(disk, &geo); if (ret) return ret;
ret = copy_to_user(ugeo, &geo, 4); ret |= put_user(geo.start, &ugeo->start); if (ret) ret = -EFAULT;
return ret;}#endif
/* set the logical block size */static int blkdev_bszset(struct file *file, blk_mode_t mode, int __user *argp){ // this one might be file_inode(file)->i_rdev - a rare valid // use of file_inode() for those. dev_t dev = I_BDEV(file->f_mapping->host)->bd_dev; struct file *excl_file; int ret, n;
if (!capable(CAP_SYS_ADMIN)) return -EACCES; if (!argp) return -EINVAL; if (get_user(n, argp)) return -EFAULT;
if (mode & BLK_OPEN_EXCL) return set_blocksize(file, n);
excl_file = bdev_file_open_by_dev(dev, mode, &dev, NULL); if (IS_ERR(excl_file)) return -EBUSY; ret = set_blocksize(excl_file, n); fput(excl_file); return ret;}
/* * Common commands that are handled the same way on native and compat * user space. Note the separate arg/argp parameters that are needed * to deal with the compat_ptr() conversion. */static int blkdev_common_ioctl(struct block_device *bdev, blk_mode_t mode, unsigned int cmd, unsigned long arg, void __user *argp){ unsigned int max_sectors;
switch (cmd) { case BLKFLSBUF: return blkdev_flushbuf(bdev, cmd, arg); case BLKROSET: return blkdev_roset(bdev, cmd, arg); case BLKDISCARD: return blk_ioctl_discard(bdev, mode, arg); case BLKSECDISCARD: return blk_ioctl_secure_erase(bdev, mode, argp); case BLKZEROOUT: return blk_ioctl_zeroout(bdev, mode, arg); case BLKGETDISKSEQ: return put_u64(argp, bdev->bd_disk->diskseq); case BLKREPORTZONE: case BLKREPORTZONEV2: return blkdev_report_zones_ioctl(bdev, cmd, arg); case BLKRESETZONE: case BLKOPENZONE: case BLKCLOSEZONE: case BLKFINISHZONE: return blkdev_zone_mgmt_ioctl(bdev, mode, cmd, arg); case BLKGETZONESZ: return put_uint(argp, bdev_zone_sectors(bdev)); case BLKGETNRZONES: return put_uint(argp, bdev_nr_zones(bdev)); case BLKROGET: return put_int(argp, bdev_read_only(bdev) != 0); case BLKSSZGET: /* get block device logical block size */ return put_int(argp, bdev_logical_block_size(bdev)); case BLKPBSZGET: /* get block device physical block size */ return put_uint(argp, bdev_physical_block_size(bdev)); case BLKIOMIN: return put_uint(argp, bdev_io_min(bdev)); case BLKIOOPT: return put_uint(argp, bdev_io_opt(bdev)); case BLKALIGNOFF: return put_int(argp, bdev_alignment_offset(bdev)); case BLKDISCARDZEROES: return put_uint(argp, 0); case BLKSECTGET: max_sectors = min_t(unsigned int, USHRT_MAX, queue_max_sectors(bdev_get_queue(bdev))); return put_ushort(argp, max_sectors); case BLKROTATIONAL: return put_ushort(argp, bdev_rot(bdev)); case BLKRASET: case BLKFRASET: if(!capable(CAP_SYS_ADMIN)) return -EACCES; bdev->bd_disk->bdi->ra_pages = (arg * 512) / PAGE_SIZE; return 0; case BLKRRPART: if (!capable(CAP_SYS_ADMIN)) return -EACCES; if (bdev_is_partition(bdev)) return -EINVAL; return disk_scan_partitions(bdev->bd_disk, mode | BLK_OPEN_STRICT_SCAN); case BLKTRACESTART: case BLKTRACESTOP: case BLKTRACETEARDOWN: return blk_trace_ioctl(bdev, cmd, argp); case BLKCRYPTOIMPORTKEY: case BLKCRYPTOGENERATEKEY: case BLKCRYPTOPREPAREKEY: return blk_crypto_ioctl(bdev, cmd, argp); case IOC_PR_REGISTER: return blkdev_pr_register(bdev, mode, argp); case IOC_PR_RESERVE: return blkdev_pr_reserve(bdev, mode, argp); case IOC_PR_RELEASE: return blkdev_pr_release(bdev, mode, argp); case IOC_PR_PREEMPT: return blkdev_pr_preempt(bdev, mode, argp, false); case IOC_PR_PREEMPT_ABORT: return blkdev_pr_preempt(bdev, mode, argp, true); case IOC_PR_CLEAR: return blkdev_pr_clear(bdev, mode, argp); case IOC_PR_READ_KEYS: return blkdev_pr_read_keys(bdev, mode, argp); case IOC_PR_READ_RESERVATION: return blkdev_pr_read_reservation(bdev, mode, argp); default: return blk_get_meta_cap(bdev, cmd, argp); }}
/* * Always keep this in sync with compat_blkdev_ioctl() * to handle all incompatible commands in both functions. * * New commands must be compatible and go into blkdev_common_ioctl */long blkdev_ioctl(struct file *file, unsigned cmd, unsigned long arg){ struct block_device *bdev = I_BDEV(file->f_mapping->host); void __user *argp = (void __user *)arg; blk_mode_t mode = file_to_blk_mode(file); int ret;
switch (cmd) { /* These need separate implementations for the data structure */ case HDIO_GETGEO: return blkdev_getgeo(bdev, argp); case BLKPG: return blkpg_ioctl(bdev, argp);
/* Compat mode returns 32-bit data instead of 'long' */ case BLKRAGET: case BLKFRAGET: if (!argp) return -EINVAL; return put_long(argp, (bdev->bd_disk->bdi->ra_pages * PAGE_SIZE) / 512); case BLKGETSIZE: if (bdev_nr_sectors(bdev) > ~0UL) return -EFBIG; return put_ulong(argp, bdev_nr_sectors(bdev));
/* The data is compatible, but the command number is different */ case BLKBSZGET: /* get block device soft block size (cf. BLKSSZGET) */ return put_int(argp, block_size(bdev)); case BLKBSZSET: return blkdev_bszset(file, mode, argp); case BLKGETSIZE64: return put_u64(argp, bdev_nr_bytes(bdev));
/* Incompatible alignment on i386 */ case BLKTRACESETUP: case BLKTRACESETUP2: return blk_trace_ioctl(bdev, cmd, argp); default: break; }
ret = blkdev_common_ioctl(bdev, mode, cmd, arg, argp); if (ret != -ENOIOCTLCMD) return ret;
if (!bdev->bd_disk->fops->ioctl) return -ENOTTY; return bdev->bd_disk->fops->ioctl(bdev, mode, cmd, arg);}
#ifdef CONFIG_COMPAT
#define BLKBSZGET_32 _IOR(0x12, 112, int)#define BLKBSZSET_32 _IOW(0x12, 113, int)#define BLKGETSIZE64_32 _IOR(0x12, 114, int)
/* Most of the generic ioctls are handled in the normal fallback path. This assumes the blkdev's low level compat_ioctl always returns ENOIOCTLCMD for unknown ioctls. */long compat_blkdev_ioctl(struct file *file, unsigned cmd, unsigned long arg){ int ret; void __user *argp = compat_ptr(arg); struct block_device *bdev = I_BDEV(file->f_mapping->host); struct gendisk *disk = bdev->bd_disk; blk_mode_t mode = file_to_blk_mode(file);
switch (cmd) { /* These need separate implementations for the data structure */ case HDIO_GETGEO: return compat_hdio_getgeo(bdev, argp); case BLKPG: return compat_blkpg_ioctl(bdev, argp);
/* Compat mode returns 32-bit data instead of 'long' */ case BLKRAGET: case BLKFRAGET: if (!argp) return -EINVAL; return compat_put_long(argp, (bdev->bd_disk->bdi->ra_pages * PAGE_SIZE) / 512); case BLKGETSIZE: if (bdev_nr_sectors(bdev) > ~(compat_ulong_t)0) return -EFBIG; return compat_put_ulong(argp, bdev_nr_sectors(bdev));
/* The data is compatible, but the command number is different */ case BLKBSZGET_32: /* get the logical block size (cf. BLKSSZGET) */ return put_int(argp, bdev_logical_block_size(bdev)); case BLKBSZSET_32: return blkdev_bszset(file, mode, argp); case BLKGETSIZE64_32: return put_u64(argp, bdev_nr_bytes(bdev));
/* Incompatible alignment on i386 */ case BLKTRACESETUP32: return blk_trace_ioctl(bdev, cmd, argp); default: break; }
ret = blkdev_common_ioctl(bdev, mode, cmd, arg, argp); if (ret == -ENOIOCTLCMD && disk->fops->compat_ioctl) ret = disk->fops->compat_ioctl(bdev, mode, cmd, arg);
return ret;}#endif
struct blk_iou_cmd { u64 start; u64 len; int res; bool nowait;};
static void blk_cmd_complete(struct io_tw_req tw_req, io_tw_token_t tw){ struct io_uring_cmd *cmd = io_uring_cmd_from_tw(tw_req); struct blk_iou_cmd *bic = io_uring_cmd_to_pdu(cmd, struct blk_iou_cmd);
if (bic->res == -EAGAIN && bic->nowait) io_uring_cmd_issue_blocking(cmd); else io_uring_cmd_done(cmd, bic->res, IO_URING_CMD_TASK_WORK_ISSUE_FLAGS);}
static void bio_cmd_bio_end_io(struct bio *bio){ struct io_uring_cmd *cmd = bio->bi_private; struct blk_iou_cmd *bic = io_uring_cmd_to_pdu(cmd, struct blk_iou_cmd);
if (unlikely(bio->bi_status) && !bic->res) bic->res = blk_status_to_errno(bio->bi_status);
io_uring_cmd_do_in_task_lazy(cmd, blk_cmd_complete); bio_put(bio);}
static int blkdev_cmd_discard(struct io_uring_cmd *cmd, struct block_device *bdev, uint64_t start, uint64_t len, bool nowait){ struct blk_iou_cmd *bic = io_uring_cmd_to_pdu(cmd, struct blk_iou_cmd); gfp_t gfp = nowait ? GFP_NOWAIT : GFP_KERNEL; sector_t sector = start >> SECTOR_SHIFT; sector_t nr_sects = len >> SECTOR_SHIFT; struct bio *prev = NULL, *bio; int err;
if (!bdev_max_discard_sectors(bdev)) return -EOPNOTSUPP; if (!(file_to_blk_mode(cmd->file) & BLK_OPEN_WRITE)) return -EBADF; if (bdev_read_only(bdev)) return -EPERM; err = blk_validate_byte_range(bdev, start, len); if (err) return err;
err = filemap_invalidate_pages(bdev->bd_mapping, start, start + len - 1, nowait); if (err) return err;
while (true) { bio = blk_alloc_discard_bio(bdev, §or, &nr_sects, gfp); if (!bio) break; if (nowait) { /* * Don't allow multi-bio non-blocking submissions as * subsequent bios may fail but we won't get a direct * indication of that. Normally, the caller should * retry from a blocking context. */ if (unlikely(nr_sects)) { bio_put(bio); return -EAGAIN; } bio->bi_opf |= REQ_NOWAIT; }
prev = bio_chain_and_submit(prev, bio); } if (unlikely(!prev)) return -EAGAIN; if (unlikely(nr_sects)) bic->res = -EAGAIN;
prev->bi_private = cmd; prev->bi_end_io = bio_cmd_bio_end_io; submit_bio(prev); return -EIOCBQUEUED;}
int blkdev_uring_cmd(struct io_uring_cmd *cmd, unsigned int issue_flags){ struct block_device *bdev = I_BDEV(cmd->file->f_mapping->host); struct blk_iou_cmd *bic = io_uring_cmd_to_pdu(cmd, struct blk_iou_cmd); u32 cmd_op = cmd->cmd_op;
/* Read what we need from the SQE on the first issue */ if (!(cmd->flags & IORING_URING_CMD_REISSUE)) { const struct io_uring_sqe *sqe = cmd->sqe;
if (unlikely(sqe->ioprio || sqe->__pad1 || sqe->len || sqe->rw_flags || sqe->file_index)) return -EINVAL;
bic->start = READ_ONCE(sqe->addr); bic->len = READ_ONCE(sqe->addr3); }
bic->res = 0; bic->nowait = issue_flags & IO_URING_F_NONBLOCK;
switch (cmd_op) { case BLOCK_URING_CMD_DISCARD: return blkdev_cmd_discard(cmd, bdev, bic->start, bic->len, bic->nowait); } return -EINVAL;}