// SPDX-License-Identifier: GPL-2.0-only/* * Copyright 1993 by Theodore Ts'o. */#include <linux/module.h>#include <linux/moduleparam.h>#include <linux/sched.h>#include <linux/fs.h>#include <linux/pagemap.h>#include <linux/file.h>#include <linux/stat.h>#include <linux/errno.h>#include <linux/major.h>#include <linux/wait.h>#include <linux/blkpg.h>#include <linux/init.h>#include <linux/swap.h>#include <linux/slab.h>#include <linux/compat.h>#include <linux/suspend.h>#include <linux/freezer.h>#include <linux/mutex.h>#include <linux/writeback.h>#include <linux/completion.h>#include <linux/highmem.h>#include <linux/splice.h>#include <linux/sysfs.h>#include <linux/miscdevice.h>#include <linux/falloc.h>#include <linux/uio.h>#include <linux/ioprio.h>#include <linux/blk-cgroup.h>#include <linux/sched/mm.h>#include <linux/statfs.h>#include <linux/uaccess.h>#include <linux/blk-mq.h>#include <linux/spinlock.h>#include <uapi/linux/loop.h> /* Possible states of device */enum { Lo_unbound, Lo_bound, Lo_rundown, Lo_deleting,}; struct loop_device { int lo_number; loff_t lo_offset; loff_t lo_sizelimit; int lo_flags; char lo_file_name[LO_NAME_SIZE]; struct file *lo_backing_file; unsigned int lo_min_dio_size; struct block_device *lo_device; gfp_t old_gfp_mask; spinlock_t lo_lock; int lo_state; spinlock_t lo_work_lock; struct workqueue_struct *workqueue; struct work_struct rootcg_work; struct list_head rootcg_cmd_list; struct list_head idle_worker_list; struct rb_root worker_tree; struct timer_list timer; bool sysfs_inited; struct request_queue *lo_queue; struct blk_mq_tag_set tag_set; struct gendisk *lo_disk; struct mutex lo_mutex; bool idr_visible;}; struct loop_cmd { struct list_head list_entry; bool use_aio; /* use AIO interface to handle I/O */ atomic_t ref; /* only for aio */ long ret; struct kiocb iocb; struct bio_vec *bvec; struct cgroup_subsys_state *blkcg_css; struct cgroup_subsys_state *memcg_css;}; #define LOOP_IDLE_WORKER_TIMEOUT (60 * HZ)#define LOOP_DEFAULT_HW_Q_DEPTH 128 static DEFINE_IDR(loop_index_idr);static DEFINE_MUTEX(loop_ctl_mutex);static DEFINE_MUTEX(loop_validate_mutex); /** * loop_global_lock_killable() - take locks for safe loop_validate_file() test * * @lo: struct loop_device * @global: true if @lo is about to bind another "struct loop_device", false otherwise * * Returns 0 on success, -EINTR otherwise. * * Since loop_validate_file() traverses on other "struct loop_device" if * is_loop_device() is true, we need a global lock for serializing concurrent * loop_configure()/loop_change_fd()/__loop_clr_fd() calls. */static int loop_global_lock_killable(struct loop_device *lo, bool global){ int err; if (global) { err = mutex_lock_killable(&loop_validate_mutex); if (err) return err; } err = mutex_lock_killable(&lo->lo_mutex); if (err && global) mutex_unlock(&loop_validate_mutex); return err;} /** * loop_global_unlock() - release locks taken by loop_global_lock_killable() * * @lo: struct loop_device * @global: true if @lo was about to bind another "struct loop_device", false otherwise */static void loop_global_unlock(struct loop_device *lo, bool global){ mutex_unlock(&lo->lo_mutex); if (global) mutex_unlock(&loop_validate_mutex);} static int max_part;static int part_shift; static loff_t lo_calculate_size(struct loop_device *lo, struct file *file){ loff_t loopsize; int ret; if (S_ISBLK(file_inode(file)->i_mode)) { loopsize = i_size_read(file->f_mapping->host); } else { struct kstat stat; /* * Get the accurate file size. This provides better results than * cached inode data, particularly for network filesystems where * metadata may be stale. */ ret = vfs_getattr_nosec(&file->f_path, &stat, STATX_SIZE, 0); if (ret) return 0; loopsize = stat.size; } if (lo->lo_offset > 0) loopsize -= lo->lo_offset; /* offset is beyond i_size, weird but possible */ if (loopsize < 0) return 0; if (lo->lo_sizelimit > 0 && lo->lo_sizelimit < loopsize) loopsize = lo->lo_sizelimit; /* * Unfortunately, if we want to do I/O on the device, * the number of 512-byte sectors has to fit into a sector_t. */ return loopsize >> 9;} /* * We support direct I/O only if lo_offset is aligned with the logical I/O size * of backing device, and the logical block size of loop is bigger than that of * the backing device. */static bool lo_can_use_dio(struct loop_device *lo){ if (!(lo->lo_backing_file->f_mode & FMODE_CAN_ODIRECT)) return false; if (queue_logical_block_size(lo->lo_queue) < lo->lo_min_dio_size) return false; if (lo->lo_offset & (lo->lo_min_dio_size - 1)) return false; return true;} /* * Direct I/O can be enabled either by using an O_DIRECT file descriptor, or by * passing in the LO_FLAGS_DIRECT_IO flag from userspace. It will be silently * disabled when the device block size is too small or the offset is unaligned. * * loop_get_status will always report the effective LO_FLAGS_DIRECT_IO flag and * not the originally passed in one. */static inline void loop_update_dio(struct loop_device *lo){ lockdep_assert_held(&lo->lo_mutex); WARN_ON_ONCE(lo->lo_state == Lo_bound && lo->lo_queue->mq_freeze_depth == 0); if ((lo->lo_flags & LO_FLAGS_DIRECT_IO) && !lo_can_use_dio(lo)) lo->lo_flags &= ~LO_FLAGS_DIRECT_IO;} /** * loop_set_size() - sets device size and notifies userspace * @lo: struct loop_device to set the size for * @size: new size of the loop device * * Callers must validate that the size passed into this function fits into * a sector_t, eg using loop_validate_size() */static void loop_set_size(struct loop_device *lo, loff_t size){ if (!set_capacity_and_notify(lo->lo_disk, size)) kobject_uevent(&disk_to_dev(lo->lo_disk)->kobj, KOBJ_CHANGE);} static void loop_clear_limits(struct loop_device *lo, int mode){ struct queue_limits lim = queue_limits_start_update(lo->lo_queue); if (mode & FALLOC_FL_ZERO_RANGE) lim.max_write_zeroes_sectors = 0; if (mode & FALLOC_FL_PUNCH_HOLE) { lim.max_hw_discard_sectors = 0; lim.discard_granularity = 0; } /* * XXX: this updates the queue limits without freezing the queue, which * is against the locking protocol and dangerous. But we can't just * freeze the queue as we're inside the ->queue_rq method here. So this * should move out into a workqueue unless we get the file operations to * advertise if they support specific fallocate operations. */ queue_limits_commit_update(lo->lo_queue, &lim);} static int lo_fallocate(struct loop_device *lo, struct request *rq, loff_t pos, int mode){ /* * We use fallocate to manipulate the space mappings used by the image * a.k.a. discard/zerorange. */ struct file *file = lo->lo_backing_file; int ret; mode |= FALLOC_FL_KEEP_SIZE; if (!bdev_max_discard_sectors(lo->lo_device)) return -EOPNOTSUPP; ret = file->f_op->fallocate(file, mode, pos, blk_rq_bytes(rq)); if (unlikely(ret && ret != -EINVAL && ret != -EOPNOTSUPP)) return -EIO; /* * We initially configure the limits in a hope that fallocate is * supported and clear them here if that turns out not to be true. */ if (unlikely(ret == -EOPNOTSUPP)) loop_clear_limits(lo, mode); return ret;} static int lo_req_flush(struct loop_device *lo, struct request *rq){ int ret = vfs_fsync(lo->lo_backing_file, 0); if (unlikely(ret && ret != -EINVAL)) ret = -EIO; return ret;} static void lo_complete_rq(struct request *rq){ struct loop_cmd *cmd = blk_mq_rq_to_pdu(rq); blk_status_t ret = BLK_STS_OK; if (cmd->ret < 0 || cmd->ret == blk_rq_bytes(rq) || req_op(rq) != REQ_OP_READ) { if (cmd->ret < 0) ret = errno_to_blk_status(cmd->ret); goto end_io; } /* * Short READ - if we got some data, advance our request and * retry it. If we got no data, end the rest with EIO. */ if (cmd->ret) { blk_update_request(rq, BLK_STS_OK, cmd->ret); cmd->ret = 0; blk_mq_requeue_request(rq, true); } else { struct bio *bio = rq->bio; while (bio) { zero_fill_bio(bio); bio = bio->bi_next; } ret = BLK_STS_IOERR;end_io: blk_mq_end_request(rq, ret); }} static void lo_rw_aio_do_completion(struct loop_cmd *cmd){ struct request *rq = blk_mq_rq_from_pdu(cmd); if (!atomic_dec_and_test(&cmd->ref)) return; kfree(cmd->bvec); cmd->bvec = NULL; if (req_op(rq) == REQ_OP_WRITE) kiocb_end_write(&cmd->iocb); if (likely(!blk_should_fake_timeout(rq->q))) blk_mq_complete_request(rq);} static void lo_rw_aio_complete(struct kiocb *iocb, long ret){ struct loop_cmd *cmd = container_of(iocb, struct loop_cmd, iocb); cmd->ret = ret; lo_rw_aio_do_completion(cmd);} static int lo_rw_aio(struct loop_device *lo, struct loop_cmd *cmd, loff_t pos, int rw){ struct iov_iter iter; struct req_iterator rq_iter; struct bio_vec *bvec; struct request *rq = blk_mq_rq_from_pdu(cmd); struct bio *bio = rq->bio; struct file *file = lo->lo_backing_file; struct bio_vec tmp; unsigned int offset; int nr_bvec = 0; int ret; rq_for_each_bvec(tmp, rq, rq_iter) nr_bvec++; if (rq->bio != rq->biotail) { bvec = kmalloc_array(nr_bvec, sizeof(struct bio_vec), GFP_NOIO); if (!bvec) return -EIO; cmd->bvec = bvec; /* * The bios of the request may be started from the middle of * the 'bvec' because of bio splitting, so we can't directly * copy bio->bi_iov_vec to new bvec. The rq_for_each_bvec * API will take care of all details for us. */ rq_for_each_bvec(tmp, rq, rq_iter) { *bvec = tmp; bvec++; } bvec = cmd->bvec; offset = 0; } else { /* * Same here, this bio may be started from the middle of the * 'bvec' because of bio splitting, so offset from the bvec * must be passed to iov iterator */ offset = bio->bi_iter.bi_bvec_done; bvec = __bvec_iter_bvec(bio->bi_io_vec, bio->bi_iter); } atomic_set(&cmd->ref, 2); iov_iter_bvec(&iter, rw, bvec, nr_bvec, blk_rq_bytes(rq)); iter.iov_offset = offset; cmd->iocb.ki_pos = pos; cmd->iocb.ki_filp = file; cmd->iocb.ki_ioprio = req_get_ioprio(rq); if (cmd->use_aio) { cmd->iocb.ki_complete = lo_rw_aio_complete; cmd->iocb.ki_flags = IOCB_DIRECT; } else { cmd->iocb.ki_complete = NULL; cmd->iocb.ki_flags = 0; } if (rw == ITER_SOURCE) { kiocb_start_write(&cmd->iocb); ret = file->f_op->write_iter(&cmd->iocb, &iter); } else ret = file->f_op->read_iter(&cmd->iocb, &iter); lo_rw_aio_do_completion(cmd); if (ret != -EIOCBQUEUED) lo_rw_aio_complete(&cmd->iocb, ret); return -EIOCBQUEUED;} static int do_req_filebacked(struct loop_device *lo, struct request *rq){ struct loop_cmd *cmd = blk_mq_rq_to_pdu(rq); loff_t pos = ((loff_t) blk_rq_pos(rq) << 9) + lo->lo_offset; switch (req_op(rq)) { case REQ_OP_FLUSH: return lo_req_flush(lo, rq); case REQ_OP_WRITE_ZEROES: /* * If the caller doesn't want deallocation, call zeroout to * write zeroes the range. Otherwise, punch them out. */ return lo_fallocate(lo, rq, pos, (rq->cmd_flags & REQ_NOUNMAP) ? FALLOC_FL_ZERO_RANGE : FALLOC_FL_PUNCH_HOLE); case REQ_OP_DISCARD: return lo_fallocate(lo, rq, pos, FALLOC_FL_PUNCH_HOLE); case REQ_OP_WRITE: return lo_rw_aio(lo, cmd, pos, ITER_SOURCE); case REQ_OP_READ: return lo_rw_aio(lo, cmd, pos, ITER_DEST); default: WARN_ON_ONCE(1); return -EIO; }} static void loop_reread_partitions(struct loop_device *lo){ int rc; mutex_lock(&lo->lo_disk->open_mutex); rc = bdev_disk_changed(lo->lo_disk, false); mutex_unlock(&lo->lo_disk->open_mutex); if (rc) pr_warn("%s: partition scan of loop%d (%s) failed (rc=%d)\n", __func__, lo->lo_number, lo->lo_file_name, rc);} static unsigned int loop_query_min_dio_size(struct loop_device *lo){ struct file *file = lo->lo_backing_file; struct block_device *sb_bdev = file->f_mapping->host->i_sb->s_bdev; struct kstat st; /* * Use the minimal dio alignment of the file system if provided. */ if (!vfs_getattr(&file->f_path, &st, STATX_DIOALIGN, 0) && (st.result_mask & STATX_DIOALIGN)) return st.dio_offset_align; /* * In a perfect world this wouldn't be needed, but as of Linux 6.13 only * a handful of file systems support the STATX_DIOALIGN flag. */ if (sb_bdev) return bdev_logical_block_size(sb_bdev); return SECTOR_SIZE;} static inline int is_loop_device(struct file *file){ struct inode *i = file->f_mapping->host; return i && S_ISBLK(i->i_mode) && imajor(i) == LOOP_MAJOR;} static int loop_validate_file(struct file *file, struct block_device *bdev){ struct inode *inode = file->f_mapping->host; struct file *f = file; /* Avoid recursion */ while (is_loop_device(f)) { struct loop_device *l; lockdep_assert_held(&loop_validate_mutex); if (f->f_mapping->host->i_rdev == bdev->bd_dev) return -EBADF; l = I_BDEV(f->f_mapping->host)->bd_disk->private_data; if (l->lo_state != Lo_bound) return -EINVAL;Lines 1–500 of 2327. Load more
// SPDX-License-Identifier: GPL-2.0-only /* * Copyright 1993 by Theodore Ts'o. */ #include <linux/module.h> #include <linux/moduleparam.h> #include <linux/sched.h> #include <linux/fs.h> #include <linux/pagemap.h> #include <linux/file.h> #include <linux/stat.h> #include <linux/errno.h> #include <linux/major.h> #include <linux/wait.h> #include <linux/blkpg.h> #include <linux/init.h> #include <linux/swap.h> #include <linux/slab.h> #include <linux/compat.h> #include <linux/suspend.h> #include <linux/freezer.h> #include <linux/mutex.h> #include <linux/writeback.h> #include <linux/completion.h> #include <linux/highmem.h> #include <linux/splice.h> #include <linux/sysfs.h> #include <linux/miscdevice.h> #include <linux/falloc.h> #include <linux/uio.h> #include <linux/ioprio.h> #include <linux/blk-cgroup.h> #include <linux/sched/mm.h> #include <linux/statfs.h> #include <linux/uaccess.h> #include <linux/blk-mq.h> #include <linux/spinlock.h> #include <uapi/linux/loop.h> /* Possible states of device */ enum { Lo_unbound, Lo_bound, Lo_rundown, Lo_deleting, }; struct loop_device { int lo_number; loff_t lo_offset; loff_t lo_sizelimit; int lo_flags; char lo_file_name[LO_NAME_SIZE]; struct file *lo_backing_file; unsigned int lo_min_dio_size; struct block_device *lo_device; gfp_t old_gfp_mask; spinlock_t lo_lock; int lo_state; spinlock_t lo_work_lock; struct workqueue_struct *workqueue; struct work_struct rootcg_work; struct list_head rootcg_cmd_list; struct list_head idle_worker_list; struct rb_root worker_tree; struct timer_list timer; bool sysfs_inited; struct request_queue *lo_queue; struct blk_mq_tag_set tag_set; struct gendisk *lo_disk; struct mutex lo_mutex; bool idr_visible; }; struct loop_cmd { struct list_head list_entry; bool use_aio; /* use AIO interface to handle I/O */ atomic_t ref; /* only for aio */ long ret; struct kiocb iocb; struct bio_vec *bvec; struct cgroup_subsys_state *blkcg_css; struct cgroup_subsys_state *memcg_css; }; #define LOOP_IDLE_WORKER_TIMEOUT (60 * HZ) #define LOOP_DEFAULT_HW_Q_DEPTH 128 static DEFINE_IDR(loop_index_idr); static DEFINE_MUTEX(loop_ctl_mutex); static DEFINE_MUTEX(loop_validate_mutex); /** * loop_global_lock_killable() - take locks for safe loop_validate_file() test * * @lo: struct loop_device * @global: true if @lo is about to bind another "struct loop_device", false otherwise * * Returns 0 on success, -EINTR otherwise. * * Since loop_validate_file() traverses on other "struct loop_device" if * is_loop_device() is true, we need a global lock for serializing concurrent * loop_configure()/loop_change_fd()/__loop_clr_fd() calls. */ static int loop_global_lock_killable(struct loop_device *lo, bool global) { int err; if (global) { err = mutex_lock_killable(&loop_validate_mutex); if (err) return err; } err = mutex_lock_killable(&lo->lo_mutex); if (err && global) mutex_unlock(&loop_validate_mutex); return err; } /** * loop_global_unlock() - release locks taken by loop_global_lock_killable() * * @lo: struct loop_device * @global: true if @lo was about to bind another "struct loop_device", false otherwise */ static void loop_global_unlock(struct loop_device *lo, bool global) { mutex_unlock(&lo->lo_mutex); if (global) mutex_unlock(&loop_validate_mutex); } static int max_part; static int part_shift; static loff_t lo_calculate_size(struct loop_device *lo, struct file *file) { loff_t loopsize; int ret; if (S_ISBLK(file_inode(file)->i_mode)) { loopsize = i_size_read(file->f_mapping->host); } else { struct kstat stat; /* * Get the accurate file size. This provides better results than * cached inode data, particularly for network filesystems where * metadata may be stale. */ ret = vfs_getattr_nosec(&file->f_path, &stat, STATX_SIZE, 0); if (ret) return 0; loopsize = stat.size; } if (lo->lo_offset > 0) loopsize -= lo->lo_offset; /* offset is beyond i_size, weird but possible */ if (loopsize < 0) return 0; if (lo->lo_sizelimit > 0 && lo->lo_sizelimit < loopsize) loopsize = lo->lo_sizelimit; /* * Unfortunately, if we want to do I/O on the device, * the number of 512-byte sectors has to fit into a sector_t. */ return loopsize >> 9; } /* * We support direct I/O only if lo_offset is aligned with the logical I/O size * of backing device, and the logical block size of loop is bigger than that of * the backing device. */ static bool lo_can_use_dio(struct loop_device *lo) { if (!(lo->lo_backing_file->f_mode & FMODE_CAN_ODIRECT)) return false; if (queue_logical_block_size(lo->lo_queue) < lo->lo_min_dio_size) return false; if (lo->lo_offset & (lo->lo_min_dio_size - 1)) return false; return true; } /* * Direct I/O can be enabled either by using an O_DIRECT file descriptor, or by * passing in the LO_FLAGS_DIRECT_IO flag from userspace. It will be silently * disabled when the device block size is too small or the offset is unaligned. * * loop_get_status will always report the effective LO_FLAGS_DIRECT_IO flag and * not the originally passed in one. */ static inline void loop_update_dio(struct loop_device *lo) { lockdep_assert_held(&lo->lo_mutex); WARN_ON_ONCE(lo->lo_state == Lo_bound && lo->lo_queue->mq_freeze_depth == 0); if ((lo->lo_flags & LO_FLAGS_DIRECT_IO) && !lo_can_use_dio(lo)) lo->lo_flags &= ~LO_FLAGS_DIRECT_IO; } /** * loop_set_size() - sets device size and notifies userspace * @lo: struct loop_device to set the size for * @size: new size of the loop device * * Callers must validate that the size passed into this function fits into * a sector_t, eg using loop_validate_size() */ static void loop_set_size(struct loop_device *lo, loff_t size) { if (!set_capacity_and_notify(lo->lo_disk, size)) kobject_uevent(&disk_to_dev(lo->lo_disk)->kobj, KOBJ_CHANGE); } static void loop_clear_limits(struct loop_device *lo, int mode) { struct queue_limits lim = queue_limits_start_update(lo->lo_queue); if (mode & FALLOC_FL_ZERO_RANGE) lim.max_write_zeroes_sectors = 0; if (mode & FALLOC_FL_PUNCH_HOLE) { lim.max_hw_discard_sectors = 0; lim.discard_granularity = 0; } /* * XXX: this updates the queue limits without freezing the queue, which * is against the locking protocol and dangerous. But we can't just * freeze the queue as we're inside the ->queue_rq method here. So this * should move out into a workqueue unless we get the file operations to * advertise if they support specific fallocate operations. */ queue_limits_commit_update(lo->lo_queue, &lim); } static int lo_fallocate(struct loop_device *lo, struct request *rq, loff_t pos, int mode) { /* * We use fallocate to manipulate the space mappings used by the image * a.k.a. discard/zerorange. */ struct file *file = lo->lo_backing_file; int ret; mode |= FALLOC_FL_KEEP_SIZE; if (!bdev_max_discard_sectors(lo->lo_device)) return -EOPNOTSUPP; ret = file->f_op->fallocate(file, mode, pos, blk_rq_bytes(rq)); if (unlikely(ret && ret != -EINVAL && ret != -EOPNOTSUPP)) return -EIO; /* * We initially configure the limits in a hope that fallocate is * supported and clear them here if that turns out not to be true. */ if (unlikely(ret == -EOPNOTSUPP)) loop_clear_limits(lo, mode); return ret; } static int lo_req_flush(struct loop_device *lo, struct request *rq) { int ret = vfs_fsync(lo->lo_backing_file, 0); if (unlikely(ret && ret != -EINVAL)) ret = -EIO; return ret; } static void lo_complete_rq(struct request *rq) { struct loop_cmd *cmd = blk_mq_rq_to_pdu(rq); blk_status_t ret = BLK_STS_OK; if (cmd->ret < 0 || cmd->ret == blk_rq_bytes(rq) || req_op(rq) != REQ_OP_READ) { if (cmd->ret < 0) ret = errno_to_blk_status(cmd->ret); goto end_io; } /* * Short READ - if we got some data, advance our request and * retry it. If we got no data, end the rest with EIO. */ if (cmd->ret) { blk_update_request(rq, BLK_STS_OK, cmd->ret); cmd->ret = 0; blk_mq_requeue_request(rq, true); } else { struct bio *bio = rq->bio; while (bio) { zero_fill_bio(bio); bio = bio->bi_next; } ret = BLK_STS_IOERR; end_io: blk_mq_end_request(rq, ret); } } static void lo_rw_aio_do_completion(struct loop_cmd *cmd) { struct request *rq = blk_mq_rq_from_pdu(cmd); if (!atomic_dec_and_test(&cmd->ref)) return; kfree(cmd->bvec); cmd->bvec = NULL; if (req_op(rq) == REQ_OP_WRITE) kiocb_end_write(&cmd->iocb); if (likely(!blk_should_fake_timeout(rq->q))) blk_mq_complete_request(rq); } static void lo_rw_aio_complete(struct kiocb *iocb, long ret) { struct loop_cmd *cmd = container_of(iocb, struct loop_cmd, iocb); cmd->ret = ret; lo_rw_aio_do_completion(cmd); } static int lo_rw_aio(struct loop_device *lo, struct loop_cmd *cmd, loff_t pos, int rw) { struct iov_iter iter; struct req_iterator rq_iter; struct bio_vec *bvec; struct request *rq = blk_mq_rq_from_pdu(cmd); struct bio *bio = rq->bio; struct file *file = lo->lo_backing_file; struct bio_vec tmp; unsigned int offset; int nr_bvec = 0; int ret; rq_for_each_bvec(tmp, rq, rq_iter) nr_bvec++; if (rq->bio != rq->biotail) { bvec = kmalloc_array(nr_bvec, sizeof(struct bio_vec), GFP_NOIO); if (!bvec) return -EIO; cmd->bvec = bvec; /* * The bios of the request may be started from the middle of * the 'bvec' because of bio splitting, so we can't directly * copy bio->bi_iov_vec to new bvec. The rq_for_each_bvec * API will take care of all details for us. */ rq_for_each_bvec(tmp, rq, rq_iter) { *bvec = tmp; bvec++; } bvec = cmd->bvec; offset = 0; } else { /* * Same here, this bio may be started from the middle of the * 'bvec' because of bio splitting, so offset from the bvec * must be passed to iov iterator */ offset = bio->bi_iter.bi_bvec_done; bvec = __bvec_iter_bvec(bio->bi_io_vec, bio->bi_iter); } atomic_set(&cmd->ref, 2); iov_iter_bvec(&iter, rw, bvec, nr_bvec, blk_rq_bytes(rq)); iter.iov_offset = offset; cmd->iocb.ki_pos = pos; cmd->iocb.ki_filp = file; cmd->iocb.ki_ioprio = req_get_ioprio(rq); if (cmd->use_aio) { cmd->iocb.ki_complete = lo_rw_aio_complete; cmd->iocb.ki_flags = IOCB_DIRECT; } else { cmd->iocb.ki_complete = NULL; cmd->iocb.ki_flags = 0; } if (rw == ITER_SOURCE) { kiocb_start_write(&cmd->iocb); ret = file->f_op->write_iter(&cmd->iocb, &iter); } else ret = file->f_op->read_iter(&cmd->iocb, &iter); lo_rw_aio_do_completion(cmd); if (ret != -EIOCBQUEUED) lo_rw_aio_complete(&cmd->iocb, ret); return -EIOCBQUEUED; } static int do_req_filebacked(struct loop_device *lo, struct request *rq) { struct loop_cmd *cmd = blk_mq_rq_to_pdu(rq); loff_t pos = ((loff_t) blk_rq_pos(rq) << 9) + lo->lo_offset; switch (req_op(rq)) { case REQ_OP_FLUSH: return lo_req_flush(lo, rq); case REQ_OP_WRITE_ZEROES: /* * If the caller doesn't want deallocation, call zeroout to * write zeroes the range. Otherwise, punch them out. */ return lo_fallocate(lo, rq, pos, (rq->cmd_flags & REQ_NOUNMAP) ? FALLOC_FL_ZERO_RANGE : FALLOC_FL_PUNCH_HOLE); case REQ_OP_DISCARD: return lo_fallocate(lo, rq, pos, FALLOC_FL_PUNCH_HOLE); case REQ_OP_WRITE: return lo_rw_aio(lo, cmd, pos, ITER_SOURCE); case REQ_OP_READ: return lo_rw_aio(lo, cmd, pos, ITER_DEST); default: WARN_ON_ONCE(1); return -EIO; } } static void loop_reread_partitions(struct loop_device *lo) { int rc; mutex_lock(&lo->lo_disk->open_mutex); rc = bdev_disk_changed(lo->lo_disk, false); mutex_unlock(&lo->lo_disk->open_mutex); if (rc) pr_warn("%s: partition scan of loop%d (%s) failed (rc=%d)\n", __func__, lo->lo_number, lo->lo_file_name, rc); } static unsigned int loop_query_min_dio_size(struct loop_device *lo) { struct file *file = lo->lo_backing_file; struct block_device *sb_bdev = file->f_mapping->host->i_sb->s_bdev; struct kstat st; /* * Use the minimal dio alignment of the file system if provided. */ if (!vfs_getattr(&file->f_path, &st, STATX_DIOALIGN, 0) && (st.result_mask & STATX_DIOALIGN)) return st.dio_offset_align; /* * In a perfect world this wouldn't be needed, but as of Linux 6.13 only * a handful of file systems support the STATX_DIOALIGN flag. */ if (sb_bdev) return bdev_logical_block_size(sb_bdev); return SECTOR_SIZE; } static inline int is_loop_device(struct file *file) { struct inode *i = file->f_mapping->host; return i && S_ISBLK(i->i_mode) && imajor(i) == LOOP_MAJOR; } static int loop_validate_file(struct file *file, struct block_device *bdev) { struct inode *inode = file->f_mapping->host; struct file *f = file; /* Avoid recursion */ while (is_loop_device(f)) { struct loop_device *l; lockdep_assert_held(&loop_validate_mutex); if (f->f_mapping->host->i_rdev == bdev->bd_dev) return -EBADF; l = I_BDEV(f->f_mapping->host)->bd_disk->private_data; if (l->lo_state != Lo_bound) return -EINVAL;