KVM: SVM: Move spec control call after restore of GS

[mirror_ubuntu-artful-kernel.git] / drivers / block / loop.c

/*
 *  linux/drivers/block/loop.c
 *
 *  Written by Theodore Ts'o, 3/29/93
 *
 * Copyright 1993 by Theodore Ts'o.  Redistribution of this file is
 * permitted under the GNU General Public License.
 *
 * DES encryption plus some minor changes by Werner Almesberger, 30-MAY-1993
 * more DES encryption plus IDEA encryption by Nicholas J. Leon, June 20, 1996
 *
 * Modularized and updated for 1.1.16 kernel - Mitch Dsouza 28th May 1994
 * Adapted for 1.3.59 kernel - Andries Brouwer, 1 Feb 1996
 *
 * Fixed do_loop_request() re-entrancy - Vincent.Renardias@waw.com Mar 20, 1997
 *
 * Added devfs support - Richard Gooch <rgooch@atnf.csiro.au> 16-Jan-1998
 *
 * Handle sparse backing files correctly - Kenn Humborg, Jun 28, 1998
 *
 * Loadable modules and other fixes by AK, 1998
 *
 * Make real block number available to downstream transfer functions, enables
 * CBC (and relatives) mode encryption requiring unique IVs per data block.
 * Reed H. Petty, rhp@draper.net
 *
 * Maximum number of loop devices now dynamic via max_loop module parameter.
 * Russell Kroll <rkroll@exploits.org> 19990701
 *
 * Maximum number of loop devices when compiled-in now selectable by passing
 * max_loop=<1-255> to the kernel on boot.
 * Erik I. Bolsø, <eriki@himolde.no>, Oct 31, 1999
 *
 * Completely rewrite request handling to be make_request_fn style and
 * non blocking, pushing work to a helper thread. Lots of fixes from
 * Al Viro too.
 * Jens Axboe <axboe@suse.de>, Nov 2000
 *
 * Support up to 256 loop devices
 * Heinz Mauelshagen <mge@sistina.com>, Feb 2002
 *
 * Support for falling back on the write file operation when the address space
 * operations write_begin is not available on the backing filesystem.
 * Anton Altaparmakov, 16 Feb 2005
 *
 * Still To Fix:
 * - Advisory locking is ignored here.
 * - Should use an own CAP_* category instead of CAP_SYS_ADMIN
 *
 */

#include <linux/module.h>
#include <linux/moduleparam.h>
#include <linux/sched.h>
#include <linux/fs.h>
#include <linux/file.h>
#include <linux/stat.h>
#include <linux/errno.h>
#include <linux/major.h>
#include <linux/wait.h>
#include <linux/blkdev.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/kthread.h>
#include <linux/splice.h>
#include <linux/sysfs.h>
#include <linux/miscdevice.h>
#include <linux/falloc.h>
#include <linux/uio.h>
#include "loop.h"

#include <linux/uaccess.h>

static DEFINE_IDR(loop_index_idr);
static DEFINE_MUTEX(loop_index_mutex);

static int max_part;
static int part_shift;

static int transfer_xor(struct loop_device *lo, int cmd,
                        struct page *raw_page, unsigned raw_off,
                        struct page *loop_page, unsigned loop_off,
                        int size, sector_t real_block)
{
        char *raw_buf = kmap_atomic(raw_page) + raw_off;
        char *loop_buf = kmap_atomic(loop_page) + loop_off;
        char *in, *out, *key;
        int i, keysize;

        if (cmd == READ) {
                in = raw_buf;
                out = loop_buf;
        } else {
                in = loop_buf;
                out = raw_buf;
        }

        key = lo->lo_encrypt_key;
        keysize = lo->lo_encrypt_key_size;
        for (i = 0; i < size; i++)
                *out++ = *in++ ^ key[(i & 511) % keysize];

        kunmap_atomic(loop_buf);
        kunmap_atomic(raw_buf);
        cond_resched();
        return 0;
}

static int xor_init(struct loop_device *lo, const struct loop_info64 *info)
{
        if (unlikely(info->lo_encrypt_key_size <= 0))
                return -EINVAL;
        return 0;
}

static struct loop_func_table none_funcs = {
        .number = LO_CRYPT_NONE,
}; 

static struct loop_func_table xor_funcs = {
        .number = LO_CRYPT_XOR,
        .transfer = transfer_xor,
        .init = xor_init
}; 

/* xfer_funcs[0] is special - its release function is never called */
static struct loop_func_table *xfer_funcs[MAX_LO_CRYPT] = {
        &none_funcs,
        &xor_funcs
};

static loff_t get_size(loff_t offset, loff_t sizelimit, struct file *file)
{
        loff_t loopsize;

        /* Compute loopsize in bytes */
        loopsize = i_size_read(file->f_mapping->host);
        if (offset > 0)
                loopsize -= offset;
        /* offset is beyond i_size, weird but possible */
        if (loopsize < 0)
                return 0;

        if (sizelimit > 0 && sizelimit < loopsize)
                loopsize = 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;
}

static loff_t get_loop_size(struct loop_device *lo, struct file *file)
{
        return get_size(lo->lo_offset, lo->lo_sizelimit, file);
}

static void __loop_update_dio(struct loop_device *lo, bool dio)
{
        struct file *file = lo->lo_backing_file;
        struct address_space *mapping = file->f_mapping;
        struct inode *inode = mapping->host;
        unsigned short sb_bsize = 0;
        unsigned dio_align = 0;
        bool use_dio;

        if (inode->i_sb->s_bdev) {
                sb_bsize = bdev_logical_block_size(inode->i_sb->s_bdev);
                dio_align = sb_bsize - 1;
        }

        /*
         * 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 the backing device's and the loop
         * needn't transform transfer.
         *
         * TODO: the above condition may be loosed in the future, and
         * direct I/O may be switched runtime at that time because most
         * of requests in sane applications should be PAGE_SIZE aligned
         */
        if (dio) {
                if (queue_logical_block_size(lo->lo_queue) >= sb_bsize &&
                                !(lo->lo_offset & dio_align) &&
                                mapping->a_ops->direct_IO &&
                                !lo->transfer)
                        use_dio = true;
                else
                        use_dio = false;
        } else {
                use_dio = false;
        }

        if (lo->use_dio == use_dio)
                return;

        /* flush dirty pages before changing direct IO */
        vfs_fsync(file, 0);

        /*
         * The flag of LO_FLAGS_DIRECT_IO is handled similarly with
         * LO_FLAGS_READ_ONLY, both are set from kernel, and losetup
         * will get updated by ioctl(LOOP_GET_STATUS)
         */
        blk_mq_freeze_queue(lo->lo_queue);
        lo->use_dio = use_dio;
        if (use_dio)
                lo->lo_flags |= LO_FLAGS_DIRECT_IO;
        else
                lo->lo_flags &= ~LO_FLAGS_DIRECT_IO;
        blk_mq_unfreeze_queue(lo->lo_queue);
}

static int
figure_loop_size(struct loop_device *lo, loff_t offset, loff_t sizelimit)
{
        loff_t size = get_size(offset, sizelimit, lo->lo_backing_file);
        sector_t x = (sector_t)size;
        struct block_device *bdev = lo->lo_device;

        if (unlikely((loff_t)x != size))
                return -EFBIG;
        if (lo->lo_offset != offset)
                lo->lo_offset = offset;
        if (lo->lo_sizelimit != sizelimit)
                lo->lo_sizelimit = sizelimit;
        set_capacity(lo->lo_disk, x);
        bd_set_size(bdev, (loff_t)get_capacity(bdev->bd_disk) << 9);
        /* let user-space know about the new size */
        kobject_uevent(&disk_to_dev(bdev->bd_disk)->kobj, KOBJ_CHANGE);
        return 0;
}

static inline int
lo_do_transfer(struct loop_device *lo, int cmd,
               struct page *rpage, unsigned roffs,
               struct page *lpage, unsigned loffs,
               int size, sector_t rblock)
{
        int ret;

        ret = lo->transfer(lo, cmd, rpage, roffs, lpage, loffs, size, rblock);
        if (likely(!ret))
                return 0;

        printk_ratelimited(KERN_ERR
                "loop: Transfer error at byte offset %llu, length %i.\n",
                (unsigned long long)rblock << 9, size);
        return ret;
}

static int lo_write_bvec(struct file *file, struct bio_vec *bvec, loff_t *ppos)
{
        struct iov_iter i;
        ssize_t bw;

        iov_iter_bvec(&i, ITER_BVEC, bvec, 1, bvec->bv_len);

        file_start_write(file);
        bw = vfs_iter_write(file, &i, ppos, 0);
        file_end_write(file);

        if (likely(bw ==  bvec->bv_len))
                return 0;

        printk_ratelimited(KERN_ERR
                "loop: Write error at byte offset %llu, length %i.\n",
                (unsigned long long)*ppos, bvec->bv_len);
        if (bw >= 0)
                bw = -EIO;
        return bw;
}

static int lo_write_simple(struct loop_device *lo, struct request *rq,
                loff_t pos)
{
        struct bio_vec bvec;
        struct req_iterator iter;
        int ret = 0;

        rq_for_each_segment(bvec, rq, iter) {
                ret = lo_write_bvec(lo->lo_backing_file, &bvec, &pos);
                if (ret < 0)
                        break;
                cond_resched();
        }

        return ret;
}

/*
 * This is the slow, transforming version that needs to double buffer the
 * data as it cannot do the transformations in place without having direct
 * access to the destination pages of the backing file.
 */
static int lo_write_transfer(struct loop_device *lo, struct request *rq,
                loff_t pos)
{
        struct bio_vec bvec, b;
        struct req_iterator iter;
        struct page *page;
        int ret = 0;

        page = alloc_page(GFP_NOIO);
        if (unlikely(!page))
                return -ENOMEM;

        rq_for_each_segment(bvec, rq, iter) {
                ret = lo_do_transfer(lo, WRITE, page, 0, bvec.bv_page,
                        bvec.bv_offset, bvec.bv_len, pos >> 9);
                if (unlikely(ret))
                        break;

                b.bv_page = page;
                b.bv_offset = 0;
                b.bv_len = bvec.bv_len;
                ret = lo_write_bvec(lo->lo_backing_file, &b, &pos);
                if (ret < 0)
                        break;
        }

        __free_page(page);
        return ret;
}

static int lo_read_simple(struct loop_device *lo, struct request *rq,
                loff_t pos)
{
        struct bio_vec bvec;
        struct req_iterator iter;
        struct iov_iter i;
        ssize_t len;

        rq_for_each_segment(bvec, rq, iter) {
                iov_iter_bvec(&i, ITER_BVEC, &bvec, 1, bvec.bv_len);
                len = vfs_iter_read(lo->lo_backing_file, &i, &pos, 0);
                if (len < 0)
                        return len;

                flush_dcache_page(bvec.bv_page);

                if (len != bvec.bv_len) {
                        struct bio *bio;

                        __rq_for_each_bio(bio, rq)
                                zero_fill_bio(bio);
                        break;
                }
                cond_resched();
        }

        return 0;
}

static int lo_read_transfer(struct loop_device *lo, struct request *rq,
                loff_t pos)
{
        struct bio_vec bvec, b;
        struct req_iterator iter;
        struct iov_iter i;
        struct page *page;
        ssize_t len;
        int ret = 0;

        page = alloc_page(GFP_NOIO);
        if (unlikely(!page))
                return -ENOMEM;

        rq_for_each_segment(bvec, rq, iter) {
                loff_t offset = pos;

                b.bv_page = page;
                b.bv_offset = 0;
                b.bv_len = bvec.bv_len;

                iov_iter_bvec(&i, ITER_BVEC, &b, 1, b.bv_len);
                len = vfs_iter_read(lo->lo_backing_file, &i, &pos, 0);
                if (len < 0) {
                        ret = len;
                        goto out_free_page;
                }

                ret = lo_do_transfer(lo, READ, page, 0, bvec.bv_page,
                        bvec.bv_offset, len, offset >> 9);
                if (ret)
                        goto out_free_page;

                flush_dcache_page(bvec.bv_page);

                if (len != bvec.bv_len) {
                        struct bio *bio;

                        __rq_for_each_bio(bio, rq)
                                zero_fill_bio(bio);
                        break;
                }
        }

        ret = 0;
out_free_page:
        __free_page(page);
        return ret;
}

static int lo_discard(struct loop_device *lo, struct request *rq, loff_t pos)
{
        /*
         * We use punch hole to reclaim the free space used by the
         * image a.k.a. discard. However we do not support discard if
         * encryption is enabled, because it may give an attacker
         * useful information.
         */
        struct file *file = lo->lo_backing_file;
        int mode = FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE;
        int ret;

        if ((!file->f_op->fallocate) || lo->lo_encrypt_key_size) {
                ret = -EOPNOTSUPP;
                goto out;
        }

        ret = file->f_op->fallocate(file, mode, pos, blk_rq_bytes(rq));
        if (unlikely(ret && ret != -EINVAL && ret != -EOPNOTSUPP))
                ret = -EIO;
 out:
        return ret;
}

static int lo_req_flush(struct loop_device *lo, struct request *rq)
{
        struct file *file = lo->lo_backing_file;
        int ret = vfs_fsync(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);

        if (unlikely(req_op(cmd->rq) == REQ_OP_READ && cmd->use_aio &&
                     cmd->ret >= 0 && cmd->ret < blk_rq_bytes(cmd->rq))) {
                struct bio *bio = cmd->rq->bio;

                bio_advance(bio, cmd->ret);
                zero_fill_bio(bio);
        }

        blk_mq_end_request(rq, cmd->ret < 0 ? BLK_STS_IOERR : BLK_STS_OK);
}

static void lo_rw_aio_complete(struct kiocb *iocb, long ret, long ret2)
{
        struct loop_cmd *cmd = container_of(iocb, struct loop_cmd, iocb);

        cmd->ret = ret;
        blk_mq_complete_request(cmd->rq);
}

static int lo_rw_aio(struct loop_device *lo, struct loop_cmd *cmd,
                     loff_t pos, bool rw)
{
        struct iov_iter iter;
        struct bio_vec *bvec;
        struct bio *bio = cmd->rq->bio;
        struct file *file = lo->lo_backing_file;
        int ret;

        /* nomerge for loop request queue */
        WARN_ON(cmd->rq->bio != cmd->rq->biotail);

        bvec = __bvec_iter_bvec(bio->bi_io_vec, bio->bi_iter);
        iov_iter_bvec(&iter, ITER_BVEC | rw, bvec,
                      bio_segments(bio), blk_rq_bytes(cmd->rq));
        /*
         * 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
         */
        iter.iov_offset = bio->bi_iter.bi_bvec_done;

        cmd->iocb.ki_pos = pos;
        cmd->iocb.ki_filp = file;
        cmd->iocb.ki_complete = lo_rw_aio_complete;
        cmd->iocb.ki_flags = IOCB_DIRECT;

        if (rw == WRITE)
                ret = call_write_iter(file, &cmd->iocb, &iter);
        else
                ret = call_read_iter(file, &cmd->iocb, &iter);

        if (ret != -EIOCBQUEUED)
                cmd->iocb.ki_complete(&cmd->iocb, ret, 0);
        return 0;
}

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;

        /*
         * lo_write_simple and lo_read_simple should have been covered
         * by io submit style function like lo_rw_aio(), one blocker
         * is that lo_read_simple() need to call flush_dcache_page after
         * the page is written from kernel, and it isn't easy to handle
         * this in io submit style function which submits all segments
         * of the req at one time. And direct read IO doesn't need to
         * run flush_dcache_page().
         */
        switch (req_op(rq)) {
        case REQ_OP_FLUSH:
                return lo_req_flush(lo, rq);
        case REQ_OP_DISCARD:
        case REQ_OP_WRITE_ZEROES:
                return lo_discard(lo, rq, pos);
        case REQ_OP_WRITE:
                if (lo->transfer)
                        return lo_write_transfer(lo, rq, pos);
                else if (cmd->use_aio)
                        return lo_rw_aio(lo, cmd, pos, WRITE);
                else
                        return lo_write_simple(lo, rq, pos);
        case REQ_OP_READ:
                if (lo->transfer)
                        return lo_read_transfer(lo, rq, pos);
                else if (cmd->use_aio)
                        return lo_rw_aio(lo, cmd, pos, READ);
                else
                        return lo_read_simple(lo, rq, pos);
        default:
                WARN_ON_ONCE(1);
                return -EIO;
                break;
        }
}

struct switch_request {
        struct file *file, *virt_file;
        struct completion wait;
};

static inline void loop_update_dio(struct loop_device *lo)
{
        __loop_update_dio(lo, io_is_direct(lo->lo_backing_file) |
                        lo->use_dio);
}

/*
 * Do the actual switch; called from the BIO completion routine
 */
static void do_loop_switch(struct loop_device *lo, struct switch_request *p)
{
        struct file *file = p->file;
        struct file *old_file = lo->lo_backing_file;
        struct address_space *mapping;

        /* if no new file, only flush of queued bios requested */
        if (!file)
                return;

        mapping = file->f_mapping;
        mapping_set_gfp_mask(old_file->f_mapping, lo->old_gfp_mask);
        lo->lo_backing_file = file;
        lo->lo_backing_virt_file = p->virt_file;
        lo->lo_blocksize = S_ISBLK(mapping->host->i_mode) ?
                mapping->host->i_bdev->bd_block_size : PAGE_SIZE;
        lo->old_gfp_mask = mapping_gfp_mask(mapping);
        mapping_set_gfp_mask(mapping, lo->old_gfp_mask & ~(__GFP_IO|__GFP_FS));
        loop_update_dio(lo);
}

/*
 * loop_switch performs the hard work of switching a backing store.
 * First it needs to flush existing IO, it does this by sending a magic
 * BIO down the pipe. The completion of this BIO does the actual switch.
 */
static int loop_switch(struct loop_device *lo, struct file *file,
                       struct file *virt_file)
{
        struct switch_request w;

        w.file = file;
        w.virt_file = virt_file;

        /* freeze queue and wait for completion of scheduled requests */
        blk_mq_freeze_queue(lo->lo_queue);

        /* do the switch action */
        do_loop_switch(lo, &w);

        /* unfreeze */
        blk_mq_unfreeze_queue(lo->lo_queue);

        return 0;
}

/*
 * Helper to flush the IOs in loop, but keeping loop thread running
 */
static int loop_flush(struct loop_device *lo)
{
        /* loop not yet configured, no running thread, nothing to flush */
        if (lo->lo_state != Lo_bound)
                return 0;
        return loop_switch(lo, NULL, NULL);
}

static struct file *loop_real_file(struct file *file)
{
        struct file *f = NULL;

        if (file->f_path.dentry->d_sb->s_op->real_loop)
                f = file->f_path.dentry->d_sb->s_op->real_loop(file);
        return f;
}

static void loop_reread_partitions(struct loop_device *lo,
                                   struct block_device *bdev)
{
        int rc;

        /*
         * bd_mutex has been held already in release path, so don't
         * acquire it if this function is called in such case.
         *
         * If the reread partition isn't from release path, lo_refcnt
         * must be at least one and it can only become zero when the
         * current holder is released.
         */
        if (!atomic_read(&lo->lo_refcnt))
                rc = __blkdev_reread_part(bdev);
        else
                rc = blkdev_reread_part(bdev);
        if (rc)
                pr_warn("%s: partition scan of loop%d (%s) failed (rc=%d)\n",
                        __func__, lo->lo_number, lo->lo_file_name, rc);
}

/*
 * loop_change_fd switched the backing store of a loopback device to
 * a new file. This is useful for operating system installers to free up
 * the original file and in High Availability environments to switch to
 * an alternative location for the content in case of server meltdown.
 * This can only work if the loop device is used read-only, and if the
 * new backing store is the same size and type as the old backing store.
 */
static int loop_change_fd(struct loop_device *lo, struct block_device *bdev,
                          unsigned int arg)
{
        struct file     *file, *old_file;
        struct file     *f, *virt_file = NULL, *old_virt_file;
        struct inode    *inode;
        int             error;

        error = -ENXIO;
        if (lo->lo_state != Lo_bound)
                goto out;

        /* the loop device has to be read-only */
        error = -EINVAL;
        if (!(lo->lo_flags & LO_FLAGS_READ_ONLY))
                goto out;

        error = -EBADF;
        file = fget(arg);
        if (!file)
                goto out;
        f = loop_real_file(file);
        if (f) {
                virt_file = file;
                file = f;
                get_file(file);
        }

        inode = file->f_mapping->host;
        old_file = lo->lo_backing_file;
        old_virt_file = lo->lo_backing_virt_file;

        error = -EINVAL;

        if (!S_ISREG(inode->i_mode) && !S_ISBLK(inode->i_mode))
                goto out_putf;

        /* size of the new backing store needs to be the same */
        if (get_loop_size(lo, file) != get_loop_size(lo, old_file))
                goto out_putf;

        /* and ... switch */
        error = loop_switch(lo, file, virt_file);
        if (error)
                goto out_putf;

        fput(old_file);
        if (old_virt_file)
                fput(old_virt_file);
        if (lo->lo_flags & LO_FLAGS_PARTSCAN)
                loop_reread_partitions(lo, bdev);
        return 0;

 out_putf:
        fput(file);
        if (virt_file)
                fput(virt_file);
 out:
        return error;
}

static inline int is_loop_device(struct file *file)
{
        struct inode *i = file->f_mapping->host;

        return i && S_ISBLK(i->i_mode) && MAJOR(i->i_rdev) == LOOP_MAJOR;
}

/*
 * for AUFS
 * no get/put for file.
 */
struct file *loop_backing_file(struct super_block *sb)
{
        struct file *ret;
        struct loop_device *l;

        ret = NULL;
        if (MAJOR(sb->s_dev) == LOOP_MAJOR) {
                l = sb->s_bdev->bd_disk->private_data;
                ret = l->lo_backing_file;
        }
        return ret;
}
EXPORT_SYMBOL_GPL(loop_backing_file);

/* loop sysfs attributes */

static ssize_t loop_attr_show(struct device *dev, char *page,
                              ssize_t (*callback)(struct loop_device *, char *))
{
        struct gendisk *disk = dev_to_disk(dev);
        struct loop_device *lo = disk->private_data;

        return callback(lo, page);
}

#define LOOP_ATTR_RO(_name)                                             \
static ssize_t loop_attr_##_name##_show(struct loop_device *, char *);  \
static ssize_t loop_attr_do_show_##_name(struct device *d,              \
                                struct device_attribute *attr, char *b) \
{                                                                       \
        return loop_attr_show(d, b, loop_attr_##_name##_show);          \
}                                                                       \
static struct device_attribute loop_attr_##_name =                      \
        __ATTR(_name, S_IRUGO, loop_attr_do_show_##_name, NULL);

static ssize_t loop_attr_backing_file_show(struct loop_device *lo, char *buf)
{
        ssize_t ret;
        char *p = NULL;

        spin_lock_irq(&lo->lo_lock);
        if (lo->lo_backing_file)
                p = file_path(lo->lo_backing_file, buf, PAGE_SIZE - 1);
        spin_unlock_irq(&lo->lo_lock);

        if (IS_ERR_OR_NULL(p))
                ret = PTR_ERR(p);
        else {
                ret = strlen(p);
                memmove(buf, p, ret);
                buf[ret++] = '\n';
                buf[ret] = 0;
        }

        return ret;
}

static ssize_t loop_attr_offset_show(struct loop_device *lo, char *buf)
{
        return sprintf(buf, "%llu\n", (unsigned long long)lo->lo_offset);
}

static ssize_t loop_attr_sizelimit_show(struct loop_device *lo, char *buf)
{
        return sprintf(buf, "%llu\n", (unsigned long long)lo->lo_sizelimit);
}

static ssize_t loop_attr_autoclear_show(struct loop_device *lo, char *buf)
{
        int autoclear = (lo->lo_flags & LO_FLAGS_AUTOCLEAR);

        return sprintf(buf, "%s\n", autoclear ? "1" : "0");
}

static ssize_t loop_attr_partscan_show(struct loop_device *lo, char *buf)
{
        int partscan = (lo->lo_flags & LO_FLAGS_PARTSCAN);

        return sprintf(buf, "%s\n", partscan ? "1" : "0");
}

static ssize_t loop_attr_dio_show(struct loop_device *lo, char *buf)
{
        int dio = (lo->lo_flags & LO_FLAGS_DIRECT_IO);

        return sprintf(buf, "%s\n", dio ? "1" : "0");
}

LOOP_ATTR_RO(backing_file);
LOOP_ATTR_RO(offset);
LOOP_ATTR_RO(sizelimit);
LOOP_ATTR_RO(autoclear);
LOOP_ATTR_RO(partscan);
LOOP_ATTR_RO(dio);

static struct attribute *loop_attrs[] = {
        &loop_attr_backing_file.attr,
        &loop_attr_offset.attr,
        &loop_attr_sizelimit.attr,
        &loop_attr_autoclear.attr,
        &loop_attr_partscan.attr,
        &loop_attr_dio.attr,
        NULL,
};

static struct attribute_group loop_attribute_group = {
        .name = "loop",
        .attrs= loop_attrs,
};

static int loop_sysfs_init(struct loop_device *lo)
{
        return sysfs_create_group(&disk_to_dev(lo->lo_disk)->kobj,
                                  &loop_attribute_group);
}

static void loop_sysfs_exit(struct loop_device *lo)
{
        sysfs_remove_group(&disk_to_dev(lo->lo_disk)->kobj,
                           &loop_attribute_group);
}

static void loop_config_discard(struct loop_device *lo)
{
        struct file *file = lo->lo_backing_file;
        struct inode *inode = file->f_mapping->host;
        struct request_queue *q = lo->lo_queue;

        /*
         * We use punch hole to reclaim the free space used by the
         * image a.k.a. discard. However we do not support discard if
         * encryption is enabled, because it may give an attacker
         * useful information.
         */
        if ((!file->f_op->fallocate) ||
            lo->lo_encrypt_key_size) {
                q->limits.discard_granularity = 0;
                q->limits.discard_alignment = 0;
                blk_queue_max_discard_sectors(q, 0);
                blk_queue_max_write_zeroes_sectors(q, 0);
                queue_flag_clear_unlocked(QUEUE_FLAG_DISCARD, q);
                return;
        }

        q->limits.discard_granularity = inode->i_sb->s_blocksize;
        q->limits.discard_alignment = 0;

        blk_queue_max_discard_sectors(q, UINT_MAX >> 9);
        blk_queue_max_write_zeroes_sectors(q, UINT_MAX >> 9);
        queue_flag_set_unlocked(QUEUE_FLAG_DISCARD, q);
}

static void loop_unprepare_queue(struct loop_device *lo)
{
        kthread_flush_worker(&lo->worker);
        kthread_stop(lo->worker_task);
}

static int loop_kthread_worker_fn(void *worker_ptr)
{
        current->flags |= PF_LESS_THROTTLE;
        return kthread_worker_fn(worker_ptr);
}

static int loop_prepare_queue(struct loop_device *lo)
{
        kthread_init_worker(&lo->worker);
        lo->worker_task = kthread_run(loop_kthread_worker_fn,
                        &lo->worker, "loop%d", lo->lo_number);
        if (IS_ERR(lo->worker_task))
                return -ENOMEM;
        set_user_nice(lo->worker_task, MIN_NICE);
        return 0;
}

static int loop_set_fd(struct loop_device *lo, fmode_t mode,
                       struct block_device *bdev, unsigned int arg)
{
        struct file     *file, *f, *virt_file = NULL;
        struct inode    *inode;
        struct address_space *mapping;
        unsigned lo_blocksize;
        int             lo_flags = 0;
        int             error;
        loff_t          size;

        /* This is safe, since we have a reference from open(). */
        __module_get(THIS_MODULE);

        error = -EBADF;
        file = fget(arg);
        if (!file)
                goto out;
        f = loop_real_file(file);
        if (f) {
                virt_file = file;
                file = f;
                get_file(file);
        }

        error = -EBUSY;
        if (lo->lo_state != Lo_unbound)
                goto out_putf;

        /* Avoid recursion */
        f = file;
        while (is_loop_device(f)) {
                struct loop_device *l;

                if (f->f_mapping->host->i_bdev == bdev)
                        goto out_putf;

                l = f->f_mapping->host->i_bdev->bd_disk->private_data;
                if (l->lo_state == Lo_unbound) {
                        error = -EINVAL;
                        goto out_putf;
                }
                f = l->lo_backing_file;
        }

        mapping = file->f_mapping;
        inode = mapping->host;

        error = -EINVAL;
        if (!S_ISREG(inode->i_mode) && !S_ISBLK(inode->i_mode))
                goto out_putf;

        if (!(file->f_mode & FMODE_WRITE) || !(mode & FMODE_WRITE) ||
            !file->f_op->write_iter)
                lo_flags |= LO_FLAGS_READ_ONLY;

        lo_blocksize = S_ISBLK(inode->i_mode) ?
                inode->i_bdev->bd_block_size : PAGE_SIZE;

        error = -EFBIG;
        size = get_loop_size(lo, file);
        if ((loff_t)(sector_t)size != size)
                goto out_putf;
        error = loop_prepare_queue(lo);
        if (error)
                goto out_putf;

        error = 0;

        set_device_ro(bdev, (lo_flags & LO_FLAGS_READ_ONLY) != 0);

        lo->use_dio = false;
        lo->lo_blocksize = lo_blocksize;
        lo->lo_device = bdev;
        lo->lo_flags = lo_flags;
        lo->lo_backing_file = file;
        lo->lo_backing_virt_file = virt_file;
        lo->transfer = NULL;
        lo->ioctl = NULL;
        lo->lo_sizelimit = 0;
        lo->old_gfp_mask = mapping_gfp_mask(mapping);
        mapping_set_gfp_mask(mapping, lo->old_gfp_mask & ~(__GFP_IO|__GFP_FS));

        if (!(lo_flags & LO_FLAGS_READ_ONLY) && file->f_op->fsync)
                blk_queue_write_cache(lo->lo_queue, true, false);

        loop_update_dio(lo);
        set_capacity(lo->lo_disk, size);
        bd_set_size(bdev, size << 9);
        loop_sysfs_init(lo);
        /* let user-space know about the new size */
        kobject_uevent(&disk_to_dev(bdev->bd_disk)->kobj, KOBJ_CHANGE);

        set_blocksize(bdev, lo_blocksize);

        lo->lo_state = Lo_bound;
        if (part_shift)
                lo->lo_flags |= LO_FLAGS_PARTSCAN;
        if (lo->lo_flags & LO_FLAGS_PARTSCAN)
                loop_reread_partitions(lo, bdev);

        /* Grab the block_device to prevent its destruction after we
         * put /dev/loopXX inode. Later in loop_clr_fd() we bdput(bdev).
         */
        bdgrab(bdev);
        return 0;

 out_putf:
        fput(file);
        if (virt_file)
                fput(virt_file);
 out:
        /* This is safe: open() is still holding a reference. */
        module_put(THIS_MODULE);
        return error;
}

static int
loop_release_xfer(struct loop_device *lo)
{
        int err = 0;
        struct loop_func_table *xfer = lo->lo_encryption;

        if (xfer) {
                if (xfer->release)
                        err = xfer->release(lo);
                lo->transfer = NULL;
                lo->lo_encryption = NULL;
                module_put(xfer->owner);
        }
        return err;
}

static int
loop_init_xfer(struct loop_device *lo, struct loop_func_table *xfer,
               const struct loop_info64 *i)
{
        int err = 0;

        if (xfer) {
                struct module *owner = xfer->owner;

                if (!try_module_get(owner))
                        return -EINVAL;
                if (xfer->init)
                        err = xfer->init(lo, i);
                if (err)
                        module_put(owner);
                else
                        lo->lo_encryption = xfer;
        }
        return err;
}

static int loop_clr_fd(struct loop_device *lo)
{
        struct file *filp = lo->lo_backing_file;
        struct file *virt_filp = lo->lo_backing_virt_file;
        gfp_t gfp = lo->old_gfp_mask;
        struct block_device *bdev = lo->lo_device;

        if (lo->lo_state != Lo_bound)
                return -ENXIO;

        /*
         * If we've explicitly asked to tear down the loop device,
         * and it has an elevated reference count, set it for auto-teardown when
         * the last reference goes away. This stops $!~#$@ udev from
         * preventing teardown because it decided that it needs to run blkid on
         * the loopback device whenever they appear. xfstests is notorious for
         * failing tests because blkid via udev races with a losetup
         * <dev>/do something like mkfs/losetup -d <dev> causing the losetup -d
         * command to fail with EBUSY.
         */
        if (atomic_read(&lo->lo_refcnt) > 1) {
                lo->lo_flags |= LO_FLAGS_AUTOCLEAR;
                mutex_unlock(&lo->lo_ctl_mutex);
                return 0;
        }

        if (filp == NULL)
                return -EINVAL;

        /* freeze request queue during the transition */
        blk_mq_freeze_queue(lo->lo_queue);

        spin_lock_irq(&lo->lo_lock);
        lo->lo_state = Lo_rundown;
        lo->lo_backing_file = NULL;
        lo->lo_backing_virt_file = NULL;
        spin_unlock_irq(&lo->lo_lock);

        loop_release_xfer(lo);
        lo->transfer = NULL;
        lo->ioctl = NULL;
        lo->lo_device = NULL;
        lo->lo_encryption = NULL;
        lo->lo_offset = 0;
        lo->lo_sizelimit = 0;
        lo->lo_encrypt_key_size = 0;
        memset(lo->lo_encrypt_key, 0, LO_KEY_SIZE);
        memset(lo->lo_crypt_name, 0, LO_NAME_SIZE);
        memset(lo->lo_file_name, 0, LO_NAME_SIZE);
        if (bdev) {
                bdput(bdev);
                invalidate_bdev(bdev);
        }
        set_capacity(lo->lo_disk, 0);
        loop_sysfs_exit(lo);
        if (bdev) {
                bd_set_size(bdev, 0);
                /* let user-space know about this change */
                kobject_uevent(&disk_to_dev(bdev->bd_disk)->kobj, KOBJ_CHANGE);
        }
        mapping_set_gfp_mask(filp->f_mapping, gfp);
        lo->lo_state = Lo_unbound;
        /* This is safe: open() is still holding a reference. */
        module_put(THIS_MODULE);
        blk_mq_unfreeze_queue(lo->lo_queue);

        if (lo->lo_flags & LO_FLAGS_PARTSCAN && bdev)
                loop_reread_partitions(lo, bdev);
        lo->lo_flags = 0;
        if (!part_shift)
                lo->lo_disk->flags |= GENHD_FL_NO_PART_SCAN;
        loop_unprepare_queue(lo);
        mutex_unlock(&lo->lo_ctl_mutex);
        /*
         * Need not hold lo_ctl_mutex to fput backing file.
         * Calling fput holding lo_ctl_mutex triggers a circular
         * lock dependency possibility warning as fput can take
         * bd_mutex which is usually taken before lo_ctl_mutex.
         */
        fput(filp);
        if (virt_filp)
                fput(virt_filp);
        return 0;
}

static int
loop_set_status(struct loop_device *lo, const struct loop_info64 *info)
{
        int err;
        struct loop_func_table *xfer;
        kuid_t uid = current_uid();

        if (lo->lo_encrypt_key_size &&
            !uid_eq(lo->lo_key_owner, uid) &&
            !capable(CAP_SYS_ADMIN))
                return -EPERM;
        if (lo->lo_state != Lo_bound)
                return -ENXIO;
        if ((unsigned int) info->lo_encrypt_key_size > LO_KEY_SIZE)
                return -EINVAL;

        /* I/O need to be drained during transfer transition */
        blk_mq_freeze_queue(lo->lo_queue);

        err = loop_release_xfer(lo);
        if (err)
                goto exit;

        if (info->lo_encrypt_type) {
                unsigned int type = info->lo_encrypt_type;

                if (type >= MAX_LO_CRYPT)
                        return -EINVAL;
                xfer = xfer_funcs[type];
                if (xfer == NULL)
                        return -EINVAL;
        } else
                xfer = NULL;

        err = loop_init_xfer(lo, xfer, info);
        if (err)
                goto exit;

        if (lo->lo_offset != info->lo_offset ||
            lo->lo_sizelimit != info->lo_sizelimit) {
                if (figure_loop_size(lo, info->lo_offset, info->lo_sizelimit)) {
                        err = -EFBIG;
                        goto exit;
                }
        }

        loop_config_discard(lo);

        memcpy(lo->lo_file_name, info->lo_file_name, LO_NAME_SIZE);
        memcpy(lo->lo_crypt_name, info->lo_crypt_name, LO_NAME_SIZE);
        lo->lo_file_name[LO_NAME_SIZE-1] = 0;
        lo->lo_crypt_name[LO_NAME_SIZE-1] = 0;

        if (!xfer)
                xfer = &none_funcs;
        lo->transfer = xfer->transfer;
        lo->ioctl = xfer->ioctl;

        if ((lo->lo_flags & LO_FLAGS_AUTOCLEAR) !=
             (info->lo_flags & LO_FLAGS_AUTOCLEAR))
                lo->lo_flags ^= LO_FLAGS_AUTOCLEAR;

        lo->lo_encrypt_key_size = info->lo_encrypt_key_size;
        lo->lo_init[0] = info->lo_init[0];
        lo->lo_init[1] = info->lo_init[1];
        if (info->lo_encrypt_key_size) {
                memcpy(lo->lo_encrypt_key, info->lo_encrypt_key,
                       info->lo_encrypt_key_size);
                lo->lo_key_owner = uid;
        }

        /* update dio if lo_offset or transfer is changed */
        __loop_update_dio(lo, lo->use_dio);

 exit:
        blk_mq_unfreeze_queue(lo->lo_queue);

        if (!err && (info->lo_flags & LO_FLAGS_PARTSCAN) &&
             !(lo->lo_flags & LO_FLAGS_PARTSCAN)) {
                lo->lo_flags |= LO_FLAGS_PARTSCAN;
                lo->lo_disk->flags &= ~GENHD_FL_NO_PART_SCAN;
                loop_reread_partitions(lo, lo->lo_device);
        }

        return err;
}

static int
loop_get_status(struct loop_device *lo, struct loop_info64 *info)
{
        struct file *file = lo->lo_backing_file;
        struct kstat stat;
        int error;

        if (lo->lo_state != Lo_bound)
                return -ENXIO;
        error = vfs_getattr(&file->f_path, &stat,
                            STATX_INO, AT_STATX_SYNC_AS_STAT);
        if (error)
                return error;
        memset(info, 0, sizeof(*info));
        info->lo_number = lo->lo_number;
        info->lo_device = huge_encode_dev(stat.dev);
        info->lo_inode = stat.ino;
        info->lo_rdevice = huge_encode_dev(lo->lo_device ? stat.rdev : stat.dev);
        info->lo_offset = lo->lo_offset;
        info->lo_sizelimit = lo->lo_sizelimit;
        info->lo_flags = lo->lo_flags;
        memcpy(info->lo_file_name, lo->lo_file_name, LO_NAME_SIZE);
        memcpy(info->lo_crypt_name, lo->lo_crypt_name, LO_NAME_SIZE);
        info->lo_encrypt_type =
                lo->lo_encryption ? lo->lo_encryption->number : 0;
        if (lo->lo_encrypt_key_size && capable(CAP_SYS_ADMIN)) {
                info->lo_encrypt_key_size = lo->lo_encrypt_key_size;
                memcpy(info->lo_encrypt_key, lo->lo_encrypt_key,
                       lo->lo_encrypt_key_size);
        }
        return 0;
}

static void
loop_info64_from_old(const struct loop_info *info, struct loop_info64 *info64)
{
        memset(info64, 0, sizeof(*info64));
        info64->lo_number = info->lo_number;
        info64->lo_device = info->lo_device;
        info64->lo_inode = info->lo_inode;
        info64->lo_rdevice = info->lo_rdevice;
        info64->lo_offset = info->lo_offset;
        info64->lo_sizelimit = 0;
        info64->lo_encrypt_type = info->lo_encrypt_type;
        info64->lo_encrypt_key_size = info->lo_encrypt_key_size;
        info64->lo_flags = info->lo_flags;
        info64->lo_init[0] = info->lo_init[0];
        info64->lo_init[1] = info->lo_init[1];
        if (info->lo_encrypt_type == LO_CRYPT_CRYPTOAPI)
                memcpy(info64->lo_crypt_name, info->lo_name, LO_NAME_SIZE);
        else
                memcpy(info64->lo_file_name, info->lo_name, LO_NAME_SIZE);
        memcpy(info64->lo_encrypt_key, info->lo_encrypt_key, LO_KEY_SIZE);
}

static int
loop_info64_to_old(const struct loop_info64 *info64, struct loop_info *info)
{
        memset(info, 0, sizeof(*info));
        info->lo_number = info64->lo_number;
        info->lo_device = info64->lo_device;
        info->lo_inode = info64->lo_inode;
        info->lo_rdevice = info64->lo_rdevice;
        info->lo_offset = info64->lo_offset;
        info->lo_encrypt_type = info64->lo_encrypt_type;
        info->lo_encrypt_key_size = info64->lo_encrypt_key_size;
        info->lo_flags = info64->lo_flags;
        info->lo_init[0] = info64->lo_init[0];
        info->lo_init[1] = info64->lo_init[1];
        if (info->lo_encrypt_type == LO_CRYPT_CRYPTOAPI)
                memcpy(info->lo_name, info64->lo_crypt_name, LO_NAME_SIZE);
        else
                memcpy(info->lo_name, info64->lo_file_name, LO_NAME_SIZE);
        memcpy(info->lo_encrypt_key, info64->lo_encrypt_key, LO_KEY_SIZE);

        /* error in case values were truncated */
        if (info->lo_device != info64->lo_device ||
            info->lo_rdevice != info64->lo_rdevice ||
            info->lo_inode != info64->lo_inode ||
            info->lo_offset != info64->lo_offset)
                return -EOVERFLOW;

        return 0;
}

static int
loop_set_status_old(struct loop_device *lo, const struct loop_info __user *arg)
{
        struct loop_info info;
        struct loop_info64 info64;

        if (copy_from_user(&info, arg, sizeof (struct loop_info)))
                return -EFAULT;
        loop_info64_from_old(&info, &info64);
        return loop_set_status(lo, &info64);
}

static int
loop_set_status64(struct loop_device *lo, const struct loop_info64 __user *arg)
{
        struct loop_info64 info64;

        if (copy_from_user(&info64, arg, sizeof (struct loop_info64)))
                return -EFAULT;
        return loop_set_status(lo, &info64);
}

static int
loop_get_status_old(struct loop_device *lo, struct loop_info __user *arg) {
        struct loop_info info;
        struct loop_info64 info64;
        int err = 0;

        if (!arg)
                err = -EINVAL;
        if (!err)
                err = loop_get_status(lo, &info64);
        if (!err)
                err = loop_info64_to_old(&info64, &info);
        if (!err && copy_to_user(arg, &info, sizeof(info)))
                err = -EFAULT;

        return err;
}

static int
loop_get_status64(struct loop_device *lo, struct loop_info64 __user *arg) {
        struct loop_info64 info64;
        int err = 0;

        if (!arg)
                err = -EINVAL;
        if (!err)
                err = loop_get_status(lo, &info64);
        if (!err && copy_to_user(arg, &info64, sizeof(info64)))
                err = -EFAULT;

        return err;
}

static int loop_set_capacity(struct loop_device *lo)
{
        if (unlikely(lo->lo_state != Lo_bound))
                return -ENXIO;

        return figure_loop_size(lo, lo->lo_offset, lo->lo_sizelimit);
}

static int loop_set_dio(struct loop_device *lo, unsigned long arg)
{
        int error = -ENXIO;
        if (lo->lo_state != Lo_bound)
                goto out;

        __loop_update_dio(lo, !!arg);
        if (lo->use_dio == !!arg)
                return 0;
        error = -EINVAL;
 out:
        return error;
}

static int lo_ioctl(struct block_device *bdev, fmode_t mode,
        unsigned int cmd, unsigned long arg)
{
        struct loop_device *lo = bdev->bd_disk->private_data;
        int err;

        mutex_lock_nested(&lo->lo_ctl_mutex, 1);
        switch (cmd) {
        case LOOP_SET_FD:
                err = loop_set_fd(lo, mode, bdev, arg);
                break;
        case LOOP_CHANGE_FD:
                err = loop_change_fd(lo, bdev, arg);
                break;
        case LOOP_CLR_FD:
                /* loop_clr_fd would have unlocked lo_ctl_mutex on success */
                err = loop_clr_fd(lo);
                if (!err)
                        goto out_unlocked;
                break;
        case LOOP_SET_STATUS:
                err = -EPERM;
                if ((mode & FMODE_WRITE) || capable(CAP_SYS_ADMIN))
                        err = loop_set_status_old(lo,
                                        (struct loop_info __user *)arg);
                break;
        case LOOP_GET_STATUS:
                err = loop_get_status_old(lo, (struct loop_info __user *) arg);
                break;
        case LOOP_SET_STATUS64:
                err = -EPERM;
                if ((mode & FMODE_WRITE) || capable(CAP_SYS_ADMIN))
                        err = loop_set_status64(lo,
                                        (struct loop_info64 __user *) arg);
                break;
        case LOOP_GET_STATUS64:
                err = loop_get_status64(lo, (struct loop_info64 __user *) arg);
                break;
        case LOOP_SET_CAPACITY:
                err = -EPERM;
                if ((mode & FMODE_WRITE) || capable(CAP_SYS_ADMIN))
                        err = loop_set_capacity(lo);
                break;
        case LOOP_SET_DIRECT_IO:
                err = -EPERM;
                if ((mode & FMODE_WRITE) || capable(CAP_SYS_ADMIN))
                        err = loop_set_dio(lo, arg);
                break;
        default:
                err = lo->ioctl ? lo->ioctl(lo, cmd, arg) : -EINVAL;
        }
        mutex_unlock(&lo->lo_ctl_mutex);

out_unlocked:
        return err;
}

#ifdef CONFIG_COMPAT
struct compat_loop_info {
        compat_int_t    lo_number;      /* ioctl r/o */
        compat_dev_t    lo_device;      /* ioctl r/o */
        compat_ulong_t  lo_inode;       /* ioctl r/o */
        compat_dev_t    lo_rdevice;     /* ioctl r/o */
        compat_int_t    lo_offset;
        compat_int_t    lo_encrypt_type;
        compat_int_t    lo_encrypt_key_size;    /* ioctl w/o */
        compat_int_t    lo_flags;       /* ioctl r/o */
        char            lo_name[LO_NAME_SIZE];
        unsigned char   lo_encrypt_key[LO_KEY_SIZE]; /* ioctl w/o */
        compat_ulong_t  lo_init[2];
        char            reserved[4];
};

/*
 * Transfer 32-bit compatibility structure in userspace to 64-bit loop info
 * - noinlined to reduce stack space usage in main part of driver
 */
static noinline int
loop_info64_from_compat(const struct compat_loop_info __user *arg,
                        struct loop_info64 *info64)
{
        struct compat_loop_info info;

        if (copy_from_user(&info, arg, sizeof(info)))
                return -EFAULT;

        memset(info64, 0, sizeof(*info64));
        info64->lo_number = info.lo_number;
        info64->lo_device = info.lo_device;
        info64->lo_inode = info.lo_inode;
        info64->lo_rdevice = info.lo_rdevice;
        info64->lo_offset = info.lo_offset;
        info64->lo_sizelimit = 0;
        info64->lo_encrypt_type = info.lo_encrypt_type;
        info64->lo_encrypt_key_size = info.lo_encrypt_key_size;
        info64->lo_flags = info.lo_flags;
        info64->lo_init[0] = info.lo_init[0];
        info64->lo_init[1] = info.lo_init[1];
        if (info.lo_encrypt_type == LO_CRYPT_CRYPTOAPI)
                memcpy(info64->lo_crypt_name, info.lo_name, LO_NAME_SIZE);
        else
                memcpy(info64->lo_file_name, info.lo_name, LO_NAME_SIZE);
        memcpy(info64->lo_encrypt_key, info.lo_encrypt_key, LO_KEY_SIZE);
        return 0;
}

/*
 * Transfer 64-bit loop info to 32-bit compatibility structure in userspace
 * - noinlined to reduce stack space usage in main part of driver
 */
static noinline int
loop_info64_to_compat(const struct loop_info64 *info64,
                      struct compat_loop_info __user *arg)
{
        struct compat_loop_info info;

        memset(&info, 0, sizeof(info));
        info.lo_number = info64->lo_number;
        info.lo_device = info64->lo_device;
        info.lo_inode = info64->lo_inode;
        info.lo_rdevice = info64->lo_rdevice;
        info.lo_offset = info64->lo_offset;
        info.lo_encrypt_type = info64->lo_encrypt_type;
        info.lo_encrypt_key_size = info64->lo_encrypt_key_size;
        info.lo_flags = info64->lo_flags;
        info.lo_init[0] = info64->lo_init[0];
        info.lo_init[1] = info64->lo_init[1];
        if (info.lo_encrypt_type == LO_CRYPT_CRYPTOAPI)
                memcpy(info.lo_name, info64->lo_crypt_name, LO_NAME_SIZE);
        else
                memcpy(info.lo_name, info64->lo_file_name, LO_NAME_SIZE);
        memcpy(info.lo_encrypt_key, info64->lo_encrypt_key, LO_KEY_SIZE);

        /* error in case values were truncated */
        if (info.lo_device != info64->lo_device ||
            info.lo_rdevice != info64->lo_rdevice ||
            info.lo_inode != info64->lo_inode ||
            info.lo_offset != info64->lo_offset ||
            info.lo_init[0] != info64->lo_init[0] ||
            info.lo_init[1] != info64->lo_init[1])
                return -EOVERFLOW;

        if (copy_to_user(arg, &info, sizeof(info)))
                return -EFAULT;
        return 0;
}

static int
loop_set_status_compat(struct loop_device *lo,
                       const struct compat_loop_info __user *arg)
{
        struct loop_info64 info64;
        int ret;

        ret = loop_info64_from_compat(arg, &info64);
        if (ret < 0)
                return ret;
        return loop_set_status(lo, &info64);
}

static int
loop_get_status_compat(struct loop_device *lo,
                       struct compat_loop_info __user *arg)
{
        struct loop_info64 info64;
        int err = 0;

        if (!arg)
                err = -EINVAL;
        if (!err)
                err = loop_get_status(lo, &info64);
        if (!err)
                err = loop_info64_to_compat(&info64, arg);
        return err;
}

static int lo_compat_ioctl(struct block_device *bdev, fmode_t mode,
                           unsigned int cmd, unsigned long arg)
{
        struct loop_device *lo = bdev->bd_disk->private_data;
        int err;

        switch(cmd) {
        case LOOP_SET_STATUS:
                mutex_lock(&lo->lo_ctl_mutex);
                err = loop_set_status_compat(
                        lo, (const struct compat_loop_info __user *) arg);
                mutex_unlock(&lo->lo_ctl_mutex);
                break;
        case LOOP_GET_STATUS:
                mutex_lock(&lo->lo_ctl_mutex);
                err = loop_get_status_compat(
                        lo, (struct compat_loop_info __user *) arg);
                mutex_unlock(&lo->lo_ctl_mutex);
                break;
        case LOOP_SET_CAPACITY:
        case LOOP_CLR_FD:
        case LOOP_GET_STATUS64:
        case LOOP_SET_STATUS64:
                arg = (unsigned long) compat_ptr(arg);
        case LOOP_SET_FD:
        case LOOP_CHANGE_FD:
                err = lo_ioctl(bdev, mode, cmd, arg);
                break;
        default:
                err = -ENOIOCTLCMD;
                break;
        }
        return err;
}
#endif

static int lo_open(struct block_device *bdev, fmode_t mode)
{
        struct loop_device *lo;
        int err = 0;

        mutex_lock(&loop_index_mutex);
        lo = bdev->bd_disk->private_data;
        if (!lo) {
                err = -ENXIO;
                goto out;
        }

        atomic_inc(&lo->lo_refcnt);
out:
        mutex_unlock(&loop_index_mutex);
        return err;
}

static void __lo_release(struct loop_device *lo)
{
        int err;

        if (atomic_dec_return(&lo->lo_refcnt))
                return;

        mutex_lock(&lo->lo_ctl_mutex);
        if (lo->lo_flags & LO_FLAGS_AUTOCLEAR) {
                /*
                 * In autoclear mode, stop the loop thread
                 * and remove configuration after last close.
                 */
                err = loop_clr_fd(lo);
                if (!err)
                        return;
        } else {
                /*
                 * Otherwise keep thread (if running) and config,
                 * but flush possible ongoing bios in thread.
                 */
                loop_flush(lo);
        }

        mutex_unlock(&lo->lo_ctl_mutex);
}

static void lo_release(struct gendisk *disk, fmode_t mode)
{
        mutex_lock(&loop_index_mutex);
        __lo_release(disk->private_data);
        mutex_unlock(&loop_index_mutex);
}

static const struct block_device_operations lo_fops = {
        .owner =        THIS_MODULE,
        .open =         lo_open,
        .release =      lo_release,
        .ioctl =        lo_ioctl,
#ifdef CONFIG_COMPAT
        .compat_ioctl = lo_compat_ioctl,
#endif
};

/*
 * And now the modules code and kernel interface.
 */
static int max_loop;
module_param(max_loop, int, S_IRUGO);
MODULE_PARM_DESC(max_loop, "Maximum number of loop devices");
module_param(max_part, int, S_IRUGO);
MODULE_PARM_DESC(max_part, "Maximum number of partitions per loop device");
MODULE_LICENSE("GPL");
MODULE_ALIAS_BLOCKDEV_MAJOR(LOOP_MAJOR);

int loop_register_transfer(struct loop_func_table *funcs)
{
        unsigned int n = funcs->number;

        if (n >= MAX_LO_CRYPT || xfer_funcs[n])
                return -EINVAL;
        xfer_funcs[n] = funcs;
        return 0;
}

static int unregister_transfer_cb(int id, void *ptr, void *data)
{
        struct loop_device *lo = ptr;
        struct loop_func_table *xfer = data;

        mutex_lock(&lo->lo_ctl_mutex);
        if (lo->lo_encryption == xfer)
                loop_release_xfer(lo);
        mutex_unlock(&lo->lo_ctl_mutex);
        return 0;
}

int loop_unregister_transfer(int number)
{
        unsigned int n = number;
        struct loop_func_table *xfer;

        if (n == 0 || n >= MAX_LO_CRYPT || (xfer = xfer_funcs[n]) == NULL)
                return -EINVAL;

        xfer_funcs[n] = NULL;
        idr_for_each(&loop_index_idr, &unregister_transfer_cb, xfer);
        return 0;
}

EXPORT_SYMBOL(loop_register_transfer);
EXPORT_SYMBOL(loop_unregister_transfer);

static blk_status_t loop_queue_rq(struct blk_mq_hw_ctx *hctx,
                const struct blk_mq_queue_data *bd)
{
        struct loop_cmd *cmd = blk_mq_rq_to_pdu(bd->rq);
        struct loop_device *lo = cmd->rq->q->queuedata;

        blk_mq_start_request(bd->rq);

        if (lo->lo_state != Lo_bound)
                return BLK_STS_IOERR;

        switch (req_op(cmd->rq)) {
        case REQ_OP_FLUSH:
        case REQ_OP_DISCARD:
        case REQ_OP_WRITE_ZEROES:
                cmd->use_aio = false;
                break;
        default:
                cmd->use_aio = lo->use_dio;
                break;
        }

        kthread_queue_work(&lo->worker, &cmd->work);

        return BLK_STS_OK;
}

static void loop_handle_cmd(struct loop_cmd *cmd)
{
        const bool write = op_is_write(req_op(cmd->rq));
        struct loop_device *lo = cmd->rq->q->queuedata;
        int ret = 0;

        if (write && (lo->lo_flags & LO_FLAGS_READ_ONLY)) {
                ret = -EIO;
                goto failed;
        }

        ret = do_req_filebacked(lo, cmd->rq);
 failed:
        /* complete non-aio request */
        if (!cmd->use_aio || ret) {
                cmd->ret = ret ? -EIO : 0;
                blk_mq_complete_request(cmd->rq);
        }
}

static void loop_queue_work(struct kthread_work *work)
{
        struct loop_cmd *cmd =
                container_of(work, struct loop_cmd, work);

        loop_handle_cmd(cmd);
}

static int loop_init_request(struct blk_mq_tag_set *set, struct request *rq,
                unsigned int hctx_idx, unsigned int numa_node)
{
        struct loop_cmd *cmd = blk_mq_rq_to_pdu(rq);

        cmd->rq = rq;
        kthread_init_work(&cmd->work, loop_queue_work);

        return 0;
}

static const struct blk_mq_ops loop_mq_ops = {
        .queue_rq       = loop_queue_rq,
        .init_request   = loop_init_request,
        .complete       = lo_complete_rq,
};

static int loop_add(struct loop_device **l, int i)
{
        struct loop_device *lo;
        struct gendisk *disk;
        int err;

        err = -ENOMEM;
        lo = kzalloc(sizeof(*lo), GFP_KERNEL);
        if (!lo)
                goto out;

        lo->lo_state = Lo_unbound;

        /* allocate id, if @id >= 0, we're requesting that specific id */
        if (i >= 0) {
                err = idr_alloc(&loop_index_idr, lo, i, i + 1, GFP_KERNEL);
                if (err == -ENOSPC)
                        err = -EEXIST;
        } else {
                err = idr_alloc(&loop_index_idr, lo, 0, 0, GFP_KERNEL);
        }
        if (err < 0)
                goto out_free_dev;
        i = err;

        err = -ENOMEM;
        lo->tag_set.ops = &loop_mq_ops;
        lo->tag_set.nr_hw_queues = 1;
        lo->tag_set.queue_depth = 128;
        lo->tag_set.numa_node = NUMA_NO_NODE;
        lo->tag_set.cmd_size = sizeof(struct loop_cmd);
        lo->tag_set.flags = BLK_MQ_F_SHOULD_MERGE | BLK_MQ_F_SG_MERGE;
        lo->tag_set.driver_data = lo;

        err = blk_mq_alloc_tag_set(&lo->tag_set);
        if (err)
                goto out_free_idr;

        lo->lo_queue = blk_mq_init_queue(&lo->tag_set);
        if (IS_ERR_OR_NULL(lo->lo_queue)) {
                err = PTR_ERR(lo->lo_queue);
                goto out_cleanup_tags;
        }
        lo->lo_queue->queuedata = lo;

        /*
         * It doesn't make sense to enable merge because the I/O
         * submitted to backing file is handled page by page.
         */
        queue_flag_set_unlocked(QUEUE_FLAG_NOMERGES, lo->lo_queue);

        err = -ENOMEM;
        disk = lo->lo_disk = alloc_disk(1 << part_shift);
        if (!disk)
                goto out_free_queue;

        /*
         * Disable partition scanning by default. The in-kernel partition
         * scanning can be requested individually per-device during its
         * setup. Userspace can always add and remove partitions from all
         * devices. The needed partition minors are allocated from the
         * extended minor space, the main loop device numbers will continue
         * to match the loop minors, regardless of the number of partitions
         * used.
         *
         * If max_part is given, partition scanning is globally enabled for
         * all loop devices. The minors for the main loop devices will be
         * multiples of max_part.
         *
         * Note: Global-for-all-devices, set-only-at-init, read-only module
         * parameteters like 'max_loop' and 'max_part' make things needlessly
         * complicated, are too static, inflexible and may surprise
         * userspace tools. Parameters like this in general should be avoided.
         */
        if (!part_shift)
                disk->flags |= GENHD_FL_NO_PART_SCAN;
        disk->flags |= GENHD_FL_EXT_DEVT;
        mutex_init(&lo->lo_ctl_mutex);
        atomic_set(&lo->lo_refcnt, 0);
        lo->lo_number           = i;
        spin_lock_init(&lo->lo_lock);
        disk->major             = LOOP_MAJOR;
        disk->first_minor       = i << part_shift;
        disk->fops              = &lo_fops;
        disk->private_data      = lo;
        disk->queue             = lo->lo_queue;
        sprintf(disk->disk_name, "loop%d", i);
        add_disk(disk);
        *l = lo;
        return lo->lo_number;

out_free_queue:
        blk_cleanup_queue(lo->lo_queue);
out_cleanup_tags:
        blk_mq_free_tag_set(&lo->tag_set);
out_free_idr:
        idr_remove(&loop_index_idr, i);
out_free_dev:
        kfree(lo);
out:
        return err;
}

static void loop_remove(struct loop_device *lo)
{
        blk_cleanup_queue(lo->lo_queue);
        del_gendisk(lo->lo_disk);
        blk_mq_free_tag_set(&lo->tag_set);
        put_disk(lo->lo_disk);
        kfree(lo);
}

static int find_free_cb(int id, void *ptr, void *data)
{
        struct loop_device *lo = ptr;
        struct loop_device **l = data;

        if (lo->lo_state == Lo_unbound) {
                *l = lo;
                return 1;
        }
        return 0;
}

static int loop_lookup(struct loop_device **l, int i)
{
        struct loop_device *lo;
        int ret = -ENODEV;

        if (i < 0) {
                int err;

                err = idr_for_each(&loop_index_idr, &find_free_cb, &lo);
                if (err == 1) {
                        *l = lo;
                        ret = lo->lo_number;
                }
                goto out;
        }

        /* lookup and return a specific i */
        lo = idr_find(&loop_index_idr, i);
        if (lo) {
                *l = lo;
                ret = lo->lo_number;
        }
out:
        return ret;
}

static struct kobject *loop_probe(dev_t dev, int *part, void *data)
{
        struct loop_device *lo;
        struct kobject *kobj;
        int err;

        mutex_lock(&loop_index_mutex);
        err = loop_lookup(&lo, MINOR(dev) >> part_shift);
        if (err < 0)
                err = loop_add(&lo, MINOR(dev) >> part_shift);
        if (err < 0)
                kobj = NULL;
        else
                kobj = get_disk(lo->lo_disk);
        mutex_unlock(&loop_index_mutex);

        *part = 0;
        return kobj;
}

static long loop_control_ioctl(struct file *file, unsigned int cmd,
                               unsigned long parm)
{
        struct loop_device *lo;
        int ret = -ENOSYS;

        mutex_lock(&loop_index_mutex);
        switch (cmd) {
        case LOOP_CTL_ADD:
                ret = loop_lookup(&lo, parm);
                if (ret >= 0) {
                        ret = -EEXIST;
                        break;
                }
                ret = loop_add(&lo, parm);
                break;
        case LOOP_CTL_REMOVE:
                ret = loop_lookup(&lo, parm);
                if (ret < 0)
                        break;
                mutex_lock(&lo->lo_ctl_mutex);
                if (lo->lo_state != Lo_unbound) {
                        ret = -EBUSY;
                        mutex_unlock(&lo->lo_ctl_mutex);
                        break;
                }
                if (atomic_read(&lo->lo_refcnt) > 0) {
                        ret = -EBUSY;
                        mutex_unlock(&lo->lo_ctl_mutex);
                        break;
                }
                lo->lo_disk->private_data = NULL;
                mutex_unlock(&lo->lo_ctl_mutex);
                idr_remove(&loop_index_idr, lo->lo_number);
                loop_remove(lo);
                break;
        case LOOP_CTL_GET_FREE:
                ret = loop_lookup(&lo, -1);
                if (ret >= 0)
                        break;
                ret = loop_add(&lo, -1);
        }
        mutex_unlock(&loop_index_mutex);

        return ret;
}

static const struct file_operations loop_ctl_fops = {
        .open           = nonseekable_open,
        .unlocked_ioctl = loop_control_ioctl,
        .compat_ioctl   = loop_control_ioctl,
        .owner          = THIS_MODULE,
        .llseek         = noop_llseek,
};

static struct miscdevice loop_misc = {
        .minor          = LOOP_CTRL_MINOR,
        .name           = "loop-control",
        .fops           = &loop_ctl_fops,
};

MODULE_ALIAS_MISCDEV(LOOP_CTRL_MINOR);
MODULE_ALIAS("devname:loop-control");

static int __init loop_init(void)
{
        int i, nr;
        unsigned long range;
        struct loop_device *lo;
        int err;

        err = misc_register(&loop_misc);
        if (err < 0)
                return err;

        part_shift = 0;
        if (max_part > 0) {
                part_shift = fls(max_part);

                /*
                 * Adjust max_part according to part_shift as it is exported
                 * to user space so that user can decide correct minor number
                 * if [s]he want to create more devices.
                 *
                 * Note that -1 is required because partition 0 is reserved
                 * for the whole disk.
                 */
                max_part = (1UL << part_shift) - 1;
        }

        if ((1UL << part_shift) > DISK_MAX_PARTS) {
                err = -EINVAL;
                goto misc_out;
        }

        if (max_loop > 1UL << (MINORBITS - part_shift)) {
                err = -EINVAL;
                goto misc_out;
        }

        /*
         * If max_loop is specified, create that many devices upfront.
         * This also becomes a hard limit. If max_loop is not specified,
         * create CONFIG_BLK_DEV_LOOP_MIN_COUNT loop devices at module
         * init time. Loop devices can be requested on-demand with the
         * /dev/loop-control interface, or be instantiated by accessing
         * a 'dead' device node.
         */
        if (max_loop) {
                nr = max_loop;
                range = max_loop << part_shift;
        } else {
                nr = CONFIG_BLK_DEV_LOOP_MIN_COUNT;
                range = 1UL << MINORBITS;
        }

        if (register_blkdev(LOOP_MAJOR, "loop")) {
                err = -EIO;
                goto misc_out;
        }

        blk_register_region(MKDEV(LOOP_MAJOR, 0), range,
                                  THIS_MODULE, loop_probe, NULL, NULL);

        /* pre-create number of devices given by config or max_loop */
        mutex_lock(&loop_index_mutex);
        for (i = 0; i < nr; i++)
                loop_add(&lo, i);
        mutex_unlock(&loop_index_mutex);

        printk(KERN_INFO "loop: module loaded\n");
        return 0;

misc_out:
        misc_deregister(&loop_misc);
        return err;
}

static int loop_exit_cb(int id, void *ptr, void *data)
{
        struct loop_device *lo = ptr;

        loop_remove(lo);
        return 0;
}

static void __exit loop_exit(void)
{
        unsigned long range;

        range = max_loop ? max_loop << part_shift : 1UL << MINORBITS;

        idr_for_each(&loop_index_idr, &loop_exit_cb, NULL);
        idr_destroy(&loop_index_idr);

        blk_unregister_region(MKDEV(LOOP_MAJOR, 0), range);
        unregister_blkdev(LOOP_MAJOR, "loop");

        misc_deregister(&loop_misc);
}

module_init(loop_init);
module_exit(loop_exit);

#ifndef MODULE
static int __init max_loop_setup(char *str)
{
        max_loop = simple_strtol(str, NULL, 0);
        return 1;
}

__setup("max_loop=", max_loop_setup);
#endif