/*
 * Copyright (C) 2007 Oracle.  All rights reserved.
 *
 * This program is free software; you can redistribute it and/or
 * modify it under the terms of the GNU General Public
 * License v2 as published by the Free Software Foundation.
 *
 * This program is distributed in the hope that it will be useful,
 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
 * General Public License for more details.
 *
 * You should have received a copy of the GNU General Public
 * License along with this program; if not, write to the
 * Free Software Foundation, Inc., 59 Temple Place - Suite 330,
 * Boston, MA 021110-1307, USA.
 */

#include <linux/kernel.h>
#include <linux/bio.h>
#include <linux/buffer_head.h>
#include <linux/file.h>
#include <linux/fs.h>
#include <linux/fsnotify.h>
#include <linux/pagemap.h>
#include <linux/highmem.h>
#include <linux/time.h>
#include <linux/init.h>
#include <linux/string.h>
#include <linux/backing-dev.h>
#include <linux/mount.h>
#include <linux/mpage.h>
#include <linux/namei.h>
#include <linux/swap.h>
#include <linux/writeback.h>
#include <linux/statfs.h>
#include <linux/compat.h>
#include <linux/bit_spinlock.h>
#include <linux/security.h>
#include <linux/xattr.h>
#include <linux/vmalloc.h>
#include <linux/slab.h>
#include <linux/blkdev.h>
#include <linux/uuid.h>
#include <linux/btrfs.h>
#include <linux/uaccess.h>
#include "ctree.h"
#include "disk-io.h"
#include "transaction.h"
#include "btrfs_inode.h"
#include "print-tree.h"
#include "volumes.h"
#include "locking.h"
#include "inode-map.h"
#include "backref.h"
#include "rcu-string.h"
#include "send.h"
#include "dev-replace.h"
#include "props.h"
#include "sysfs.h"
#include "qgroup.h"
#include "tree-log.h"
#include "compression.h"

#ifdef CONFIG_64BIT
/* If we have a 32-bit userspace and 64-bit kernel, then the UAPI
 * structures are incorrect, as the timespec structure from userspace
 * is 4 bytes too small. We define these alternatives here to teach
 * the kernel about the 32-bit struct packing.
 */
struct btrfs_ioctl_timespec_32 {
        __u64 sec;
        __u32 nsec;
} __attribute__ ((__packed__));

struct btrfs_ioctl_received_subvol_args_32 {
        char    uuid[BTRFS_UUID_SIZE];  /* in */
        __u64   stransid;               /* in */
        __u64   rtransid;               /* out */
        struct btrfs_ioctl_timespec_32 stime; /* in */
        struct btrfs_ioctl_timespec_32 rtime; /* out */
        __u64   flags;                  /* in */
        __u64   reserved[16];           /* in */
} __attribute__ ((__packed__));

#define BTRFS_IOC_SET_RECEIVED_SUBVOL_32 _IOWR(BTRFS_IOCTL_MAGIC, 37, \
                                struct btrfs_ioctl_received_subvol_args_32)
#endif


static int btrfs_clone(struct inode *src, struct inode *inode,
                       u64 off, u64 olen, u64 olen_aligned, u64 destoff,
                       int no_time_update);

/* Mask out flags that are inappropriate for the given type of inode. */
static inline __u32 btrfs_mask_flags(umode_t mode, __u32 flags)
{
        if (S_ISDIR(mode))
                return flags;
        else if (S_ISREG(mode))
                return flags & ~FS_DIRSYNC_FL;
        else
                return flags & (FS_NODUMP_FL | FS_NOATIME_FL);
}

/*
 * Export inode flags to the format expected by the FS_IOC_GETFLAGS ioctl.
 */
static unsigned int btrfs_flags_to_ioctl(unsigned int flags)
{
        unsigned int iflags = 0;

        if (flags & BTRFS_INODE_SYNC)
                iflags |= FS_SYNC_FL;
        if (flags & BTRFS_INODE_IMMUTABLE)
                iflags |= FS_IMMUTABLE_FL;
        if (flags & BTRFS_INODE_APPEND)
                iflags |= FS_APPEND_FL;
        if (flags & BTRFS_INODE_NODUMP)
                iflags |= FS_NODUMP_FL;
        if (flags & BTRFS_INODE_NOATIME)
                iflags |= FS_NOATIME_FL;
        if (flags & BTRFS_INODE_DIRSYNC)
                iflags |= FS_DIRSYNC_FL;
        if (flags & BTRFS_INODE_NODATACOW)
                iflags |= FS_NOCOW_FL;

        if (flags & BTRFS_INODE_NOCOMPRESS)
                iflags |= FS_NOCOMP_FL;
        else if (flags & BTRFS_INODE_COMPRESS)
                iflags |= FS_COMPR_FL;

        return iflags;
}

/*
 * Update inode->i_flags based on the btrfs internal flags.
 */
void btrfs_update_iflags(struct inode *inode)
{
        struct btrfs_inode *ip = BTRFS_I(inode);
        unsigned int new_fl = 0;

        if (ip->flags & BTRFS_INODE_SYNC)
                new_fl |= S_SYNC;
        if (ip->flags & BTRFS_INODE_IMMUTABLE)
                new_fl |= S_IMMUTABLE;
        if (ip->flags & BTRFS_INODE_APPEND)
                new_fl |= S_APPEND;
        if (ip->flags & BTRFS_INODE_NOATIME)
                new_fl |= S_NOATIME;
        if (ip->flags & BTRFS_INODE_DIRSYNC)
                new_fl |= S_DIRSYNC;

        set_mask_bits(&inode->i_flags,
                      S_SYNC | S_APPEND | S_IMMUTABLE | S_NOATIME | S_DIRSYNC,
                      new_fl);
}

/*
 * Inherit flags from the parent inode.
 *
 * Currently only the compression flags and the cow flags are inherited.
 */
void btrfs_inherit_iflags(struct inode *inode, struct inode *dir)
{
        unsigned int flags;

        if (!dir)
                return;

        flags = BTRFS_I(dir)->flags;

        if (flags & BTRFS_INODE_NOCOMPRESS) {
                BTRFS_I(inode)->flags &= ~BTRFS_INODE_COMPRESS;
                BTRFS_I(inode)->flags |= BTRFS_INODE_NOCOMPRESS;
        } else if (flags & BTRFS_INODE_COMPRESS) {
                BTRFS_I(inode)->flags &= ~BTRFS_INODE_NOCOMPRESS;
                BTRFS_I(inode)->flags |= BTRFS_INODE_COMPRESS;
        }

        if (flags & BTRFS_INODE_NODATACOW) {
                BTRFS_I(inode)->flags |= BTRFS_INODE_NODATACOW;
                if (S_ISREG(inode->i_mode))
                        BTRFS_I(inode)->flags |= BTRFS_INODE_NODATASUM;
        }

        btrfs_update_iflags(inode);
}

static int btrfs_ioctl_getflags(struct file *file, void __user *arg)
{
        struct btrfs_inode *ip = BTRFS_I(file_inode(file));
        unsigned int flags = btrfs_flags_to_ioctl(ip->flags);

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

static int check_flags(unsigned int flags)
{
        if (flags & ~(FS_IMMUTABLE_FL | FS_APPEND_FL | \
                      FS_NOATIME_FL | FS_NODUMP_FL | \
                      FS_SYNC_FL | FS_DIRSYNC_FL | \
                      FS_NOCOMP_FL | FS_COMPR_FL |
                      FS_NOCOW_FL))
                return -EOPNOTSUPP;

        if ((flags & FS_NOCOMP_FL) && (flags & FS_COMPR_FL))
                return -EINVAL;

        return 0;
}

static int btrfs_ioctl_setflags(struct file *file, void __user *arg)
{
        struct inode *inode = file_inode(file);
        struct btrfs_inode *ip = BTRFS_I(inode);
        struct btrfs_root *root = ip->root;
        struct btrfs_trans_handle *trans;
        unsigned int flags, oldflags;
        int ret;
        u64 ip_oldflags;
        unsigned int i_oldflags;
        umode_t mode;

        if (!inode_owner_or_capable(inode))
                return -EPERM;

        if (btrfs_root_readonly(root))
                return -EROFS;

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

        ret = check_flags(flags);
        if (ret)
                return ret;

        ret = mnt_want_write_file(file);
        if (ret)
                return ret;

        inode_lock(inode);

        ip_oldflags = ip->flags;
        i_oldflags = inode->i_flags;
        mode = inode->i_mode;

        flags = btrfs_mask_flags(inode->i_mode, flags);
        oldflags = btrfs_flags_to_ioctl(ip->flags);
        if ((flags ^ oldflags) & (FS_APPEND_FL | FS_IMMUTABLE_FL)) {
                if (!capable(CAP_LINUX_IMMUTABLE)) {
                        ret = -EPERM;
                        goto out_unlock;
                }
        }

        if (flags & FS_SYNC_FL)
                ip->flags |= BTRFS_INODE_SYNC;
        else
                ip->flags &= ~BTRFS_INODE_SYNC;
        if (flags & FS_IMMUTABLE_FL)
                ip->flags |= BTRFS_INODE_IMMUTABLE;
        else
                ip->flags &= ~BTRFS_INODE_IMMUTABLE;
        if (flags & FS_APPEND_FL)
                ip->flags |= BTRFS_INODE_APPEND;
        else
                ip->flags &= ~BTRFS_INODE_APPEND;
        if (flags & FS_NODUMP_FL)
                ip->flags |= BTRFS_INODE_NODUMP;
        else
                ip->flags &= ~BTRFS_INODE_NODUMP;
        if (flags & FS_NOATIME_FL)
                ip->flags |= BTRFS_INODE_NOATIME;
        else
                ip->flags &= ~BTRFS_INODE_NOATIME;
        if (flags & FS_DIRSYNC_FL)
                ip->flags |= BTRFS_INODE_DIRSYNC;
        else
                ip->flags &= ~BTRFS_INODE_DIRSYNC;
        if (flags & FS_NOCOW_FL) {
                if (S_ISREG(mode)) {
                        /*
                         * It's safe to turn csums off here, no extents exist.
                         * Otherwise we want the flag to reflect the real COW
                         * status of the file and will not set it.
                         */
                        if (inode->i_size == 0)
                                ip->flags |= BTRFS_INODE_NODATACOW
                                           | BTRFS_INODE_NODATASUM;
                } else {
                        ip->flags |= BTRFS_INODE_NODATACOW;
                }
        } else {
                /*
                 * Revert back under same assumptions as above
                 */
                if (S_ISREG(mode)) {
                        if (inode->i_size == 0)
                                ip->flags &= ~(BTRFS_INODE_NODATACOW
                                             | BTRFS_INODE_NODATASUM);
                } else {
                        ip->flags &= ~BTRFS_INODE_NODATACOW;
                }
        }

        /*
         * The COMPRESS flag can only be changed by users, while the NOCOMPRESS
         * flag may be changed automatically if compression code won't make
         * things smaller.
         */
        if (flags & FS_NOCOMP_FL) {
                ip->flags &= ~BTRFS_INODE_COMPRESS;
                ip->flags |= BTRFS_INODE_NOCOMPRESS;

                ret = btrfs_set_prop(inode, "btrfs.compression", NULL, 0, 0);
                if (ret && ret != -ENODATA)
                        goto out_drop;
        } else if (flags & FS_COMPR_FL) {
                const char *comp;

                ip->flags |= BTRFS_INODE_COMPRESS;
                ip->flags &= ~BTRFS_INODE_NOCOMPRESS;

                if (root->fs_info->compress_type == BTRFS_COMPRESS_LZO)
                        comp = "lzo";
                else
                        comp = "zlib";
                ret = btrfs_set_prop(inode, "btrfs.compression",
                                     comp, strlen(comp), 0);
                if (ret)
                        goto out_drop;

        } else {
                ret = btrfs_set_prop(inode, "btrfs.compression", NULL, 0, 0);
                if (ret && ret != -ENODATA)
                        goto out_drop;
                ip->flags &= ~(BTRFS_INODE_COMPRESS | BTRFS_INODE_NOCOMPRESS);
        }

        trans = btrfs_start_transaction(root, 1);
        if (IS_ERR(trans)) {
                ret = PTR_ERR(trans);
                goto out_drop;
        }

        btrfs_update_iflags(inode);
        inode_inc_iversion(inode);
        inode->i_ctime = current_time(inode);
        ret = btrfs_update_inode(trans, root, inode);

        btrfs_end_transaction(trans, root);
 out_drop:
        if (ret) {
                ip->flags = ip_oldflags;
                inode->i_flags = i_oldflags;
        }

 out_unlock:
        inode_unlock(inode);
        mnt_drop_write_file(file);
        return ret;
}

static int btrfs_ioctl_getversion(struct file *file, int __user *arg)
{
        struct inode *inode = file_inode(file);

        return put_user(inode->i_generation, arg);
}

static noinline int btrfs_ioctl_fitrim(struct file *file, void __user *arg)
{
        struct btrfs_fs_info *fs_info = btrfs_sb(file_inode(file)->i_sb);
        struct btrfs_device *device;
        struct request_queue *q;
        struct fstrim_range range;
        u64 minlen = ULLONG_MAX;
        u64 num_devices = 0;
        u64 total_bytes = btrfs_super_total_bytes(fs_info->super_copy);
        int ret;

        if (!capable(CAP_SYS_ADMIN))
                return -EPERM;

        rcu_read_lock();
        list_for_each_entry_rcu(device, &fs_info->fs_devices->devices,
                                dev_list) {
                if (!device->bdev)
                        continue;
                q = bdev_get_queue(device->bdev);
                if (blk_queue_discard(q)) {
                        num_devices++;
                        minlen = min((u64)q->limits.discard_granularity,
                                     minlen);
                }
        }
        rcu_read_unlock();

        if (!num_devices)
                return -EOPNOTSUPP;
        if (copy_from_user(&range, arg, sizeof(range)))
                return -EFAULT;
        if (range.start > total_bytes ||
            range.len < fs_info->sb->s_blocksize)
                return -EINVAL;

        range.len = min(range.len, total_bytes - range.start);
        range.minlen = max(range.minlen, minlen);
        ret = btrfs_trim_fs(fs_info->tree_root, &range);
        if (ret < 0)
                return ret;

        if (copy_to_user(arg, &range, sizeof(range)))
                return -EFAULT;

        return 0;
}

int btrfs_is_empty_uuid(u8 *uuid)
{
        int i;

        for (i = 0; i < BTRFS_UUID_SIZE; i++) {
                if (uuid[i])
                        return 0;
        }
        return 1;
}

static noinline int create_subvol(struct inode *dir,
                                  struct dentry *dentry,
                                  char *name, int namelen,
                                  u64 *async_transid,
                                  struct btrfs_qgroup_inherit *inherit)
{
        struct btrfs_trans_handle *trans;
        struct btrfs_key key;
        struct btrfs_root_item *root_item;
        struct btrfs_inode_item *inode_item;
        struct extent_buffer *leaf;
        struct btrfs_root *root = BTRFS_I(dir)->root;
        struct btrfs_root *new_root;
        struct btrfs_block_rsv block_rsv;
        struct timespec cur_time = current_time(dir);
        struct inode *inode;
        int ret;
        int err;
        u64 objectid;
        u64 new_dirid = BTRFS_FIRST_FREE_OBJECTID;
        u64 index = 0;
        u64 qgroup_reserved;
        uuid_le new_uuid;

        root_item = kzalloc(sizeof(*root_item), GFP_KERNEL);
        if (!root_item)
                return -ENOMEM;

        ret = btrfs_find_free_objectid(root->fs_info->tree_root, &objectid);
        if (ret)
                goto fail_free;

        /*
         * Don't create subvolume whose level is not zero. Or qgroup will be
         * screwed up since it assumes subvolume qgroup's level to be 0.
         */
        if (btrfs_qgroup_level(objectid)) {
                ret = -ENOSPC;
                goto fail_free;
        }

        btrfs_init_block_rsv(&block_rsv, BTRFS_BLOCK_RSV_TEMP);
        /*
         * The same as the snapshot creation, please see the comment
         * of create_snapshot().
         */
        ret = btrfs_subvolume_reserve_metadata(root, &block_rsv,
                                               8, &qgroup_reserved, false);
        if (ret)
                goto fail_free;

        trans = btrfs_start_transaction(root, 0);
        if (IS_ERR(trans)) {
                ret = PTR_ERR(trans);
                btrfs_subvolume_release_metadata(root, &block_rsv,
                                                 qgroup_reserved);
                goto fail_free;
        }
        trans->block_rsv = &block_rsv;
        trans->bytes_reserved = block_rsv.size;

        ret = btrfs_qgroup_inherit(trans, root->fs_info, 0, objectid, inherit);
        if (ret)
                goto fail;

        leaf = btrfs_alloc_tree_block(trans, root, 0, objectid, NULL, 0, 0, 0);
        if (IS_ERR(leaf)) {
                ret = PTR_ERR(leaf);
                goto fail;
        }

        memset_extent_buffer(leaf, 0, 0, sizeof(struct btrfs_header));
        btrfs_set_header_bytenr(leaf, leaf->start);
        btrfs_set_header_generation(leaf, trans->transid);
        btrfs_set_header_backref_rev(leaf, BTRFS_MIXED_BACKREF_REV);
        btrfs_set_header_owner(leaf, objectid);

        write_extent_buffer(leaf, root->fs_info->fsid, btrfs_header_fsid(),
                            BTRFS_FSID_SIZE);
        write_extent_buffer(leaf, root->fs_info->chunk_tree_uuid,
                            btrfs_header_chunk_tree_uuid(leaf),
                            BTRFS_UUID_SIZE);
        btrfs_mark_buffer_dirty(leaf);

        inode_item = &root_item->inode;
        btrfs_set_stack_inode_generation(inode_item, 1);
        btrfs_set_stack_inode_size(inode_item, 3);
        btrfs_set_stack_inode_nlink(inode_item, 1);
        btrfs_set_stack_inode_nbytes(inode_item, root->nodesize);
        btrfs_set_stack_inode_mode(inode_item, S_IFDIR | 0755);

        btrfs_set_root_flags(root_item, 0);
        btrfs_set_root_limit(root_item, 0);
        btrfs_set_stack_inode_flags(inode_item, BTRFS_INODE_ROOT_ITEM_INIT);

        btrfs_set_root_bytenr(root_item, leaf->start);
        btrfs_set_root_generation(root_item, trans->transid);
        btrfs_set_root_level(root_item, 0);
        btrfs_set_root_refs(root_item, 1);
        btrfs_set_root_used(root_item, leaf->len);
        btrfs_set_root_last_snapshot(root_item, 0);

        btrfs_set_root_generation_v2(root_item,
                        btrfs_root_generation(root_item));
        uuid_le_gen(&new_uuid);
        memcpy(root_item->uuid, new_uuid.b, BTRFS_UUID_SIZE);
        btrfs_set_stack_timespec_sec(&root_item->otime, cur_time.tv_sec);
        btrfs_set_stack_timespec_nsec(&root_item->otime, cur_time.tv_nsec);
        root_item->ctime = root_item->otime;
        btrfs_set_root_ctransid(root_item, trans->transid);
        btrfs_set_root_otransid(root_item, trans->transid);

        btrfs_tree_unlock(leaf);
        free_extent_buffer(leaf);
        leaf = NULL;

        btrfs_set_root_dirid(root_item, new_dirid);

        key.objectid = objectid;
        key.offset = 0;
        key.type = BTRFS_ROOT_ITEM_KEY;
        ret = btrfs_insert_root(trans, root->fs_info->tree_root, &key,
                                root_item);
        if (ret)
                goto fail;

        key.offset = (u64)-1;
        new_root = btrfs_read_fs_root_no_name(root->fs_info, &key);
        if (IS_ERR(new_root)) {
                ret = PTR_ERR(new_root);
                btrfs_abort_transaction(trans, ret);
                goto fail;
        }

        btrfs_record_root_in_trans(trans, new_root);

        ret = btrfs_create_subvol_root(trans, new_root, root, new_dirid);
        if (ret) {
                /* We potentially lose an unused inode item here */
                btrfs_abort_transaction(trans, ret);
                goto fail;
        }

        mutex_lock(&new_root->objectid_mutex);
        new_root->highest_objectid = new_dirid;
        mutex_unlock(&new_root->objectid_mutex);

        /*
         * insert the directory item
         */
        ret = btrfs_set_inode_index(dir, &index);
        if (ret) {
                btrfs_abort_transaction(trans, ret);
                goto fail;
        }

        ret = btrfs_insert_dir_item(trans, root,
                                    name, namelen, dir, &key,
                                    BTRFS_FT_DIR, index);
        if (ret) {
                btrfs_abort_transaction(trans, ret);
                goto fail;
        }

        btrfs_i_size_write(dir, dir->i_size + namelen * 2);
        ret = btrfs_update_inode(trans, root, dir);
        BUG_ON(ret);

        ret = btrfs_add_root_ref(trans, root->fs_info->tree_root,
                                 objectid, root->root_key.objectid,
                                 btrfs_ino(dir), index, name, namelen);
        BUG_ON(ret);

        ret = btrfs_uuid_tree_add(trans, root->fs_info->uuid_root,
                                  root_item->uuid, BTRFS_UUID_KEY_SUBVOL,
                                  objectid);
        if (ret)
                btrfs_abort_transaction(trans, ret);

fail:
        kfree(root_item);
        trans->block_rsv = NULL;
        trans->bytes_reserved = 0;
        btrfs_subvolume_release_metadata(root, &block_rsv, qgroup_reserved);

        if (async_transid) {
                *async_transid = trans->transid;
                err = btrfs_commit_transaction_async(trans, root, 1);
                if (err)
                        err = btrfs_commit_transaction(trans, root);
        } else {
                err = btrfs_commit_transaction(trans, root);
        }
        if (err && !ret)
                ret = err;

        if (!ret) {
                inode = btrfs_lookup_dentry(dir, dentry);
                if (IS_ERR(inode))
                        return PTR_ERR(inode);
                d_instantiate(dentry, inode);
        }
        return ret;

fail_free:
        kfree(root_item);
        return ret;
}

static void btrfs_wait_for_no_snapshoting_writes(struct btrfs_root *root)
{
        s64 writers;
        DEFINE_WAIT(wait);

        do {
                prepare_to_wait(&root->subv_writers->wait, &wait,
                                TASK_UNINTERRUPTIBLE);

                writers = percpu_counter_sum(&root->subv_writers->counter);
                if (writers)
                        schedule();

                finish_wait(&root->subv_writers->wait, &wait);
        } while (writers);
}

static int create_snapshot(struct btrfs_root *root, struct inode *dir,
                           struct dentry *dentry, char *name, int namelen,
                           u64 *async_transid, bool readonly,
                           struct btrfs_qgroup_inherit *inherit)
{
        struct inode *inode;
        struct btrfs_pending_snapshot *pending_snapshot;
        struct btrfs_trans_handle *trans;
        int ret;

        if (!test_bit(BTRFS_ROOT_REF_COWS, &root->state))
                return -EINVAL;

        pending_snapshot = kzalloc(sizeof(*pending_snapshot), GFP_NOFS);
        if (!pending_snapshot)
                return -ENOMEM;

        pending_snapshot->root_item = kzalloc(sizeof(struct btrfs_root_item),
                        GFP_NOFS);
        pending_snapshot->path = btrfs_alloc_path();
        if (!pending_snapshot->root_item || !pending_snapshot->path) {
                ret = -ENOMEM;
                goto free_pending;
        }

        atomic_inc(&root->will_be_snapshoted);
        smp_mb__after_atomic();
        btrfs_wait_for_no_snapshoting_writes(root);

        ret = btrfs_start_delalloc_inodes(root, 0);
        if (ret)
                goto dec_and_free;

        btrfs_wait_ordered_extents(root, -1, 0, (u64)-1);

        btrfs_init_block_rsv(&pending_snapshot->block_rsv,
                             BTRFS_BLOCK_RSV_TEMP);
        /*
         * 1 - parent dir inode
         * 2 - dir entries
         * 1 - root item
         * 2 - root ref/backref
         * 1 - root of snapshot
         * 1 - UUID item
         */
        ret = btrfs_subvolume_reserve_metadata(BTRFS_I(dir)->root,
                                        &pending_snapshot->block_rsv, 8,
                                        &pending_snapshot->qgroup_reserved,
                                        false);
        if (ret)
                goto dec_and_free;

        pending_snapshot->dentry = dentry;
        pending_snapshot->root = root;
        pending_snapshot->readonly = readonly;
        pending_snapshot->dir = dir;
        pending_snapshot->inherit = inherit;

        trans = btrfs_start_transaction(root, 0);
        if (IS_ERR(trans)) {
                ret = PTR_ERR(trans);
                goto fail;
        }

        spin_lock(&root->fs_info->trans_lock);
        list_add(&pending_snapshot->list,
                 &trans->transaction->pending_snapshots);
        spin_unlock(&root->fs_info->trans_lock);
        if (async_transid) {
                *async_transid = trans->transid;
                ret = btrfs_commit_transaction_async(trans,
                                     root->fs_info->extent_root, 1);
                if (ret)
                        ret = btrfs_commit_transaction(trans, root);
        } else {
                ret = btrfs_commit_transaction(trans,
                                               root->fs_info->extent_root);
        }
        if (ret)
                goto fail;

        ret = pending_snapshot->error;
        if (ret)
                goto fail;

        ret = btrfs_orphan_cleanup(pending_snapshot->snap);
        if (ret)
                goto fail;

        inode = btrfs_lookup_dentry(d_inode(dentry->d_parent), dentry);
        if (IS_ERR(inode)) {
                ret = PTR_ERR(inode);
                goto fail;
        }

        d_instantiate(dentry, inode);
        ret = 0;
fail:
        btrfs_subvolume_release_metadata(BTRFS_I(dir)->root,
                                         &pending_snapshot->block_rsv,
                                         pending_snapshot->qgroup_reserved);
dec_and_free:
        if (atomic_dec_and_test(&root->will_be_snapshoted))
                wake_up_atomic_t(&root->will_be_snapshoted);
free_pending:
        kfree(pending_snapshot->root_item);
        btrfs_free_path(pending_snapshot->path);
        kfree(pending_snapshot);

        return ret;
}

/*  copy of may_delete in fs/namei.c()
 *      Check whether we can remove a link victim from directory dir, check
 *  whether the type of victim is right.
 *  1. We can't do it if dir is read-only (done in permission())
 *  2. We should have write and exec permissions on dir
 *  3. We can't remove anything from append-only dir
 *  4. We can't do anything with immutable dir (done in permission())
 *  5. If the sticky bit on dir is set we should either
 *      a. be owner of dir, or
 *      b. be owner of victim, or
 *      c. have CAP_FOWNER capability
 *  6. If the victim is append-only or immutable we can't do anything with
 *     links pointing to it.
 *  7. If we were asked to remove a directory and victim isn't one - ENOTDIR.
 *  8. If we were asked to remove a non-directory and victim isn't one - EISDIR.
 *  9. We can't remove a root or mountpoint.
 * 10. We don't allow removal of NFS sillyrenamed files; it's handled by
 *     nfs_async_unlink().
 */

static int btrfs_may_delete(struct inode *dir, struct dentry *victim, int isdir)
{
        int error;

        if (d_really_is_negative(victim))
                return -ENOENT;

        BUG_ON(d_inode(victim->d_parent) != dir);
        audit_inode_child(dir, victim, AUDIT_TYPE_CHILD_DELETE);

        error = inode_permission(dir, MAY_WRITE | MAY_EXEC);
        if (error)
                return error;
        if (IS_APPEND(dir))
                return -EPERM;
        if (check_sticky(dir, d_inode(victim)) || IS_APPEND(d_inode(victim)) ||
            IS_IMMUTABLE(d_inode(victim)) || IS_SWAPFILE(d_inode(victim)))
                return -EPERM;
        if (isdir) {
                if (!d_is_dir(victim))
                        return -ENOTDIR;
                if (IS_ROOT(victim))
                        return -EBUSY;
        } else if (d_is_dir(victim))
                return -EISDIR;
        if (IS_DEADDIR(dir))
                return -ENOENT;
        if (victim->d_flags & DCACHE_NFSFS_RENAMED)
                return -EBUSY;
        return 0;
}

/* copy of may_create in fs/namei.c() */
static inline int btrfs_may_create(struct inode *dir, struct dentry *child)
{
        if (d_really_is_positive(child))
                return -EEXIST;
        if (IS_DEADDIR(dir))
                return -ENOENT;
        return inode_permission(dir, MAY_WRITE | MAY_EXEC);
}

/*
 * Create a new subvolume below @parent.  This is largely modeled after
 * sys_mkdirat and vfs_mkdir, but we only do a single component lookup
 * inside this filesystem so it's quite a bit simpler.
 */
static noinline int btrfs_mksubvol(struct path *parent,
                                   char *name, int namelen,
                                   struct btrfs_root *snap_src,
                                   u64 *async_transid, bool readonly,
                                   struct btrfs_qgroup_inherit *inherit)
{
        struct inode *dir  = d_inode(parent->dentry);
        struct dentry *dentry;
        int error;

        error = down_write_killable_nested(&dir->i_rwsem, I_MUTEX_PARENT);
        if (error == -EINTR)
                return error;

        dentry = lookup_one_len(name, parent->dentry, namelen);
        error = PTR_ERR(dentry);
        if (IS_ERR(dentry))
                goto out_unlock;

        error = btrfs_may_create(dir, dentry);
        if (error)
                goto out_dput;

        /*
         * even if this name doesn't exist, we may get hash collisions.
         * check for them now when we can safely fail
         */
        error = btrfs_check_dir_item_collision(BTRFS_I(dir)->root,
                                               dir->i_ino, name,
                                               namelen);
        if (error)
                goto out_dput;

        down_read(&BTRFS_I(dir)->root->fs_info->subvol_sem);

        if (btrfs_root_refs(&BTRFS_I(dir)->root->root_item) == 0)
                goto out_up_read;

        if (snap_src) {
                error = create_snapshot(snap_src, dir, dentry, name, namelen,
                                        async_transid, readonly, inherit);
        } else {
                error = create_subvol(dir, dentry, name, namelen,
                                      async_transid, inherit);
        }
        if (!error)
                fsnotify_mkdir(dir, dentry);
out_up_read:
        up_read(&BTRFS_I(dir)->root->fs_info->subvol_sem);
out_dput:
        dput(dentry);
out_unlock:
        inode_unlock(dir);
        return error;
}

/*
 * When we're defragging a range, we don't want to kick it off again
 * if it is really just waiting for delalloc to send it down.
 * If we find a nice big extent or delalloc range for the bytes in the
 * file you want to defrag, we return 0 to let you know to skip this
 * part of the file
 */
static int check_defrag_in_cache(struct inode *inode, u64 offset, u32 thresh)
{
        struct extent_io_tree *io_tree = &BTRFS_I(inode)->io_tree;
        struct extent_map *em = NULL;
        struct extent_map_tree *em_tree = &BTRFS_I(inode)->extent_tree;
        u64 end;

        read_lock(&em_tree->lock);
        em = lookup_extent_mapping(em_tree, offset, PAGE_SIZE);
        read_unlock(&em_tree->lock);

        if (em) {
                end = extent_map_end(em);
                free_extent_map(em);
                if (end - offset > thresh)
                        return 0;
        }
        /* if we already have a nice delalloc here, just stop */
        thresh /= 2;
        end = count_range_bits(io_tree, &offset, offset + thresh,
                               thresh, EXTENT_DELALLOC, 1);
        if (end >= thresh)
                return 0;
        return 1;
}

/*
 * helper function to walk through a file and find extents
 * newer than a specific transid, and smaller than thresh.
 *
 * This is used by the defragging code to find new and small
 * extents
 */
static int find_new_extents(struct btrfs_root *root,
                            struct inode *inode, u64 newer_than,
                            u64 *off, u32 thresh)
{
        struct btrfs_path *path;
        struct btrfs_key min_key;
        struct extent_buffer *leaf;
        struct btrfs_file_extent_item *extent;
        int type;
        int ret;
        u64 ino = btrfs_ino(inode);

        path = btrfs_alloc_path();
        if (!path)
                return -ENOMEM;

        min_key.objectid = ino;
        min_key.type = BTRFS_EXTENT_DATA_KEY;
        min_key.offset = *off;

        while (1) {
                ret = btrfs_search_forward(root, &min_key, path, newer_than);
                if (ret != 0)
                        goto none;
process_slot:
                if (min_key.objectid != ino)
                        goto none;
                if (min_key.type != BTRFS_EXTENT_DATA_KEY)
                        goto none;

                leaf = path->nodes[0];
                extent = btrfs_item_ptr(leaf, path->slots[0],
                                        struct btrfs_file_extent_item);

                type = btrfs_file_extent_type(leaf, extent);
                if (type == BTRFS_FILE_EXTENT_REG &&
                    btrfs_file_extent_num_bytes(leaf, extent) < thresh &&
                    check_defrag_in_cache(inode, min_key.offset, thresh)) {
                        *off = min_key.offset;
                        btrfs_free_path(path);
                        return 0;
                }

                path->slots[0]++;
                if (path->slots[0] < btrfs_header_nritems(leaf)) {
                        btrfs_item_key_to_cpu(leaf, &min_key, path->slots[0]);
                        goto process_slot;
                }

                if (min_key.offset == (u64)-1)
                        goto none;

                min_key.offset++;
                btrfs_release_path(path);
        }
none:
        btrfs_free_path(path);
        return -ENOENT;
}

static struct extent_map *defrag_lookup_extent(struct inode *inode, u64 start)
{
        struct extent_map_tree *em_tree = &BTRFS_I(inode)->extent_tree;
        struct extent_io_tree *io_tree = &BTRFS_I(inode)->io_tree;
        struct extent_map *em;
        u64 len = PAGE_SIZE;

        /*
         * hopefully we have this extent in the tree already, try without
         * the full extent lock
         */
        read_lock(&em_tree->lock);
        em = lookup_extent_mapping(em_tree, start, len);
        read_unlock(&em_tree->lock);

        if (!em) {
                struct extent_state *cached = NULL;
                u64 end = start + len - 1;

                /* get the big lock and read metadata off disk */
                lock_extent_bits(io_tree, start, end, &cached);
                em = btrfs_get_extent(inode, NULL, 0, start, len, 0);
                unlock_extent_cached(io_tree, start, end, &cached, GFP_NOFS);

                if (IS_ERR(em))
                        return NULL;
        }

        return em;
}

static bool defrag_check_next_extent(struct inode *inode, struct extent_map *em)
{
        struct extent_map *next;
        bool ret = true;

        /* this is the last extent */
        if (em->start + em->len >= i_size_read(inode))
                return false;

        next = defrag_lookup_extent(inode, em->start + em->len);
        if (!next || next->block_start >= EXTENT_MAP_LAST_BYTE)
                ret = false;
        else if ((em->block_start + em->block_len == next->block_start) &&
                 (em->block_len > SZ_128K && next->block_len > SZ_128K))
                ret = false;

        free_extent_map(next);
        return ret;
}

static int should_defrag_range(struct inode *inode, u64 start, u32 thresh,
                               u64 *last_len, u64 *skip, u64 *defrag_end,
                               int compress)
{
        struct extent_map *em;
        int ret = 1;
        bool next_mergeable = true;
        bool prev_mergeable = true;

        /*
         * make sure that once we start defragging an extent, we keep on
         * defragging it
         */
        if (start < *defrag_end)
                return 1;

        *skip = 0;

        em = defrag_lookup_extent(inode, start);
        if (!em)
                return 0;

        /* this will cover holes, and inline extents */
        if (em->block_start >= EXTENT_MAP_LAST_BYTE) {
                ret = 0;
                goto out;
        }

        if (!*defrag_end)
                prev_mergeable = false;

        next_mergeable = defrag_check_next_extent(inode, em);
        /*
         * we hit a real extent, if it is big or the next extent is not a
         * real extent, don't bother defragging it
         */
        if (!compress && (*last_len == 0 || *last_len >= thresh) &&
            (em->len >= thresh || (!next_mergeable && !prev_mergeable)))
                ret = 0;
out:
        /*
         * last_len ends up being a counter of how many bytes we've defragged.
         * every time we choose not to defrag an extent, we reset *last_len
         * so that the next tiny extent will force a defrag.
         *
         * The end result of this is that tiny extents before a single big
         * extent will force at least part of that big extent to be defragged.
         */
        if (ret) {
                *defrag_end = extent_map_end(em);
        } else {
                *last_len = 0;
                *skip = extent_map_end(em);
                *defrag_end = 0;
        }

        free_extent_map(em);
        return ret;
}

/*
 * it doesn't do much good to defrag one or two pages
 * at a time.  This pulls in a nice chunk of pages
 * to COW and defrag.
 *
 * It also makes sure the delalloc code has enough
 * dirty data to avoid making new small extents as part
 * of the defrag
 *
 * It's a good idea to start RA on this range
 * before calling this.
 */
static int cluster_pages_for_defrag(struct inode *inode,
                                    struct page **pages,
                                    unsigned long start_index,
                                    unsigned long num_pages)
{
        unsigned long file_end;
        u64 isize = i_size_read(inode);
        u64 page_start;
        u64 page_end;
        u64 page_cnt;
        int ret;
        int i;
        int i_done;
        struct btrfs_ordered_extent *ordered;
        struct extent_state *cached_state = NULL;
        struct extent_io_tree *tree;
        gfp_t mask = btrfs_alloc_write_mask(inode->i_mapping);

        file_end = (isize - 1) >> PAGE_SHIFT;
        if (!isize || start_index > file_end)
                return 0;

        page_cnt = min_t(u64, (u64)num_pages, (u64)file_end - start_index + 1);

        ret = btrfs_delalloc_reserve_space(inode,
                        start_index << PAGE_SHIFT,
                        page_cnt << PAGE_SHIFT);
        if (ret)
                return ret;
        i_done = 0;
        tree = &BTRFS_I(inode)->io_tree;

        /* step one, lock all the pages */
        for (i = 0; i < page_cnt; i++) {
                struct page *page;
again:
                page = find_or_create_page(inode->i_mapping,
                                           start_index + i, mask);
                if (!page)
                        break;

                page_start = page_offset(page);
                page_end = page_start + PAGE_SIZE - 1;
                while (1) {
                        lock_extent_bits(tree, page_start, page_end,
                                         &cached_state);
                        ordered = btrfs_lookup_ordered_extent(inode,
                                                              page_start);
                        unlock_extent_cached(tree, page_start, page_end,
                                             &cached_state, GFP_NOFS);
                        if (!ordered)
                                break;

                        unlock_page(page);
                        btrfs_start_ordered_extent(inode, ordered, 1);
                        btrfs_put_ordered_extent(ordered);
                        lock_page(page);
                        /*
                         * we unlocked the page above, so we need check if
                         * it was released or not.
                         */
                        if (page->mapping != inode->i_mapping) {
                                unlock_page(page);
                                put_page(page);
                                goto again;
                        }
                }

                if (!PageUptodate(page)) {
                        btrfs_readpage(NULL, page);
                        lock_page(page);
                        if (!PageUptodate(page)) {
                                unlock_page(page);
                                put_page(page);
                                ret = -EIO;
                                break;
                        }
                }

                if (page->mapping != inode->i_mapping) {
                        unlock_page(page);
                        put_page(page);
                        goto again;
                }

                pages[i] = page;
                i_done++;
        }
        if (!i_done || ret)
                goto out;

        if (!(inode->i_sb->s_flags & MS_ACTIVE))
                goto out;

        /*
         * so now we have a nice long stream of locked
         * and up to date pages, lets wait on them
         */
        for (i = 0; i < i_done; i++)
                wait_on_page_writeback(pages[i]);

        page_start = page_offset(pages[0]);
        page_end = page_offset(pages[i_done - 1]) + PAGE_SIZE;

        lock_extent_bits(&BTRFS_I(inode)->io_tree,
                         page_start, page_end - 1, &cached_state);
        clear_extent_bit(&BTRFS_I(inode)->io_tree, page_start,
                          page_end - 1, EXTENT_DIRTY | EXTENT_DELALLOC |
                          EXTENT_DO_ACCOUNTING | EXTENT_DEFRAG, 0, 0,
                          &cached_state, GFP_NOFS);

        if (i_done != page_cnt) {
                spin_lock(&BTRFS_I(inode)->lock);
                BTRFS_I(inode)->outstanding_extents++;
                spin_unlock(&BTRFS_I(inode)->lock);
                btrfs_delalloc_release_space(inode,
                                start_index << PAGE_SHIFT,
                                (page_cnt - i_done) << PAGE_SHIFT);
        }


        set_extent_defrag(&BTRFS_I(inode)->io_tree, page_start, page_end - 1,
                          &cached_state);

        unlock_extent_cached(&BTRFS_I(inode)->io_tree,
                             page_start, page_end - 1, &cached_state,
                             GFP_NOFS);

        for (i = 0; i < i_done; i++) {
                clear_page_dirty_for_io(pages[i]);
                ClearPageChecked(pages[i]);
                set_page_extent_mapped(pages[i]);
                set_page_dirty(pages[i]);
                unlock_page(pages[i]);
                put_page(pages[i]);
        }
        return i_done;
out:
        for (i = 0; i < i_done; i++) {
                unlock_page(pages[i]);
                put_page(pages[i]);
        }
        btrfs_delalloc_release_space(inode,
                        start_index << PAGE_SHIFT,
                        page_cnt << PAGE_SHIFT);
        return ret;

}

int btrfs_defrag_file(struct inode *inode, struct file *file,
                      struct btrfs_ioctl_defrag_range_args *range,
                      u64 newer_than, unsigned long max_to_defrag)
{
        struct btrfs_root *root = BTRFS_I(inode)->root;
        struct file_ra_state *ra = NULL;
        unsigned long last_index;
        u64 isize = i_size_read(inode);
        u64 last_len = 0;
        u64 skip = 0;
        u64 defrag_end = 0;
        u64 newer_off = range->start;
        unsigned long i;
        unsigned long ra_index = 0;
        int ret;
        int defrag_count = 0;
        int compress_type = BTRFS_COMPRESS_ZLIB;
        u32 extent_thresh = range->extent_thresh;
        unsigned long max_cluster = SZ_256K >> PAGE_SHIFT;
        unsigned long cluster = max_cluster;
        u64 new_align = ~((u64)SZ_128K - 1);
        struct page **pages = NULL;

        if (isize == 0)
                return 0;

        if (range->start >= isize)
                return -EINVAL;

        if (range->flags & BTRFS_DEFRAG_RANGE_COMPRESS) {
                if (range->compress_type > BTRFS_COMPRESS_TYPES)
                        return -EINVAL;
                if (range->compress_type)
                        compress_type = range->compress_type;
        }

        if (extent_thresh == 0)
                extent_thresh = SZ_256K;

        /*
         * if we were not given a file, allocate a readahead
         * context
         */
        if (!file) {
                ra = kzalloc(sizeof(*ra), GFP_NOFS);
                if (!ra)
                        return -ENOMEM;
                file_ra_state_init(ra, inode->i_mapping);
        } else {
                ra = &file->f_ra;
        }

        pages = kmalloc_array(max_cluster, sizeof(struct page *),
                        GFP_NOFS);
        if (!pages) {
                ret = -ENOMEM;
                goto out_ra;
        }

        /* find the last page to defrag */
        if (range->start + range->len > range->start) {
                last_index = min_t(u64, isize - 1,
                         range->start + range->len - 1) >> PAGE_SHIFT;
        } else {
                last_index = (isize - 1) >> PAGE_SHIFT;
        }

        if (newer_than) {
                ret = find_new_extents(root, inode, newer_than,
                                       &newer_off, SZ_64K);
                if (!ret) {
                        range->start = newer_off;
                        /*
                         * we always align our defrag to help keep
                         * the extents in the file evenly spaced
                         */
                        i = (newer_off & new_align) >> PAGE_SHIFT;
                } else
                        goto out_ra;
        } else {
                i = range->start >> PAGE_SHIFT;
        }
        if (!max_to_defrag)
                max_to_defrag = last_index - i + 1;

        /*
         * make writeback starts from i, so the defrag range can be
         * written sequentially.
         */
        if (i < inode->i_mapping->writeback_index)
                inode->i_mapping->writeback_index = i;

        while (i <= last_index && defrag_count < max_to_defrag &&
               (i < DIV_ROUND_UP(i_size_read(inode), PAGE_SIZE))) {
                /*
                 * make sure we stop running if someone unmounts
                 * the FS
                 */
                if (!(inode->i_sb->s_flags & MS_ACTIVE))
                        break;

                if (btrfs_defrag_cancelled(root->fs_info)) {
                        btrfs_debug(root->fs_info, "defrag_file cancelled");
                        ret = -EAGAIN;
                        break;
                }

                if (!should_defrag_range(inode, (u64)i << PAGE_SHIFT,
                                         extent_thresh, &last_len, &skip,
                                         &defrag_end, range->flags &
                                         BTRFS_DEFRAG_RANGE_COMPRESS)) {
                        unsigned long next;
                        /*
                         * the should_defrag function tells us how much to skip
                         * bump our counter by the suggested amount
                         */
                        next = DIV_ROUND_UP(skip, PAGE_SIZE);
                        i = max(i + 1, next);
                        continue;
                }

                if (!newer_than) {
                        cluster = (PAGE_ALIGN(defrag_end) >>
                                   PAGE_SHIFT) - i;
                        cluster = min(cluster, max_cluster);
                } else {
                        cluster = max_cluster;
                }

                if (i + cluster > ra_index) {
                        ra_index = max(i, ra_index);
                        btrfs_force_ra(inode->i_mapping, ra, file, ra_index,
                                       cluster);
                        ra_index += cluster;
                }

                inode_lock(inode);
                if (range->flags & BTRFS_DEFRAG_RANGE_COMPRESS)
                        BTRFS_I(inode)->force_compress = compress_type;
                ret = cluster_pages_for_defrag(inode, pages, i, cluster);
                if (ret < 0) {
                        inode_unlock(inode);
                        goto out_ra;
                }

                defrag_count += ret;
                balance_dirty_pages_ratelimited(inode->i_mapping);
                inode_unlock(inode);

                if (newer_than) {
                        if (newer_off == (u64)-1)
                                break;

                        if (ret > 0)
                                i += ret;

                        newer_off = max(newer_off + 1,
                                        (u64)i << PAGE_SHIFT);

                        ret = find_new_extents(root, inode, newer_than,
                                               &newer_off, SZ_64K);
                        if (!ret) {
                                range->start = newer_off;
                                i = (newer_off & new_align) >> PAGE_SHIFT;
                        } else {
                                break;
                        }
                } else {
                        if (ret > 0) {
                                i += ret;
                                last_len += ret << PAGE_SHIFT;
                        } else {
                                i++;
                                last_len = 0;
                        }
                }
        }

        if ((range->flags & BTRFS_DEFRAG_RANGE_START_IO)) {
                filemap_flush(inode->i_mapping);
                if (test_bit(BTRFS_INODE_HAS_ASYNC_EXTENT,
                             &BTRFS_I(inode)->runtime_flags))
                        filemap_flush(inode->i_mapping);
        }

        if ((range->flags & BTRFS_DEFRAG_RANGE_COMPRESS)) {
                /* the filemap_flush will queue IO into the worker threads, but
                 * we have to make sure the IO is actually started and that
                 * ordered extents get created before we return
                 */
                atomic_inc(&root->fs_info->async_submit_draining);
                while (atomic_read(&root->fs_info->nr_async_submits) ||
                      atomic_read(&root->fs_info->async_delalloc_pages)) {
                        wait_event(root->fs_info->async_submit_wait,
                           (atomic_read(&root->fs_info->nr_async_submits) == 0 &&
                            atomic_read(&root->fs_info->async_delalloc_pages) == 0));
                }
                atomic_dec(&root->fs_info->async_submit_draining);
        }

        if (range->compress_type == BTRFS_COMPRESS_LZO) {
                btrfs_set_fs_incompat(root->fs_info, COMPRESS_LZO);
        }

        ret = defrag_count;

out_ra:
        if (range->flags & BTRFS_DEFRAG_RANGE_COMPRESS) {
                inode_lock(inode);
                BTRFS_I(inode)->force_compress = BTRFS_COMPRESS_NONE;
                inode_unlock(inode);
        }
        if (!file)
                kfree(ra);
        kfree(pages);
        return ret;
}

static noinline int btrfs_ioctl_resize(struct file *file,
                                        void __user *arg)
{
        u64 new_size;
        u64 old_size;
        u64 devid = 1;
        struct btrfs_root *root = BTRFS_I(file_inode(file))->root;
        struct btrfs_ioctl_vol_args *vol_args;
        struct btrfs_trans_handle *trans;
        struct btrfs_device *device = NULL;
        char *sizestr;
        char *retptr;
        char *devstr = NULL;
        int ret = 0;
        int mod = 0;

        if (!capable(CAP_SYS_ADMIN))
                return -EPERM;

        ret = mnt_want_write_file(file);
        if (ret)
                return ret;

        if (atomic_xchg(&root->fs_info->mutually_exclusive_operation_running,
                        1)) {
                mnt_drop_write_file(file);
                return BTRFS_ERROR_DEV_EXCL_RUN_IN_PROGRESS;
        }

        mutex_lock(&root->fs_info->volume_mutex);
        vol_args = memdup_user(arg, sizeof(*vol_args));
        if (IS_ERR(vol_args)) {
                ret = PTR_ERR(vol_args);
                goto out;
        }

        vol_args->name[BTRFS_PATH_NAME_MAX] = '\0';

        sizestr = vol_args->name;
        devstr = strchr(sizestr, ':');
        if (devstr) {
                sizestr = devstr + 1;
                *devstr = '\0';
                devstr = vol_args->name;
                ret = kstrtoull(devstr, 10, &devid);
                if (ret)
                        goto out_free;
                if (!devid) {
                        ret = -EINVAL;
                        goto out_free;
                }
                btrfs_info(root->fs_info, "resizing devid %llu", devid);
        }

        device = btrfs_find_device(root->fs_info, devid, NULL, NULL);
        if (!device) {
                btrfs_info(root->fs_info, "resizer unable to find device %llu",
                       devid);
                ret = -ENODEV;
                goto out_free;
        }

        if (!device->writeable) {
                btrfs_info(root->fs_info,
                           "resizer unable to apply on readonly device %llu",
                       devid);
                ret = -EPERM;
                goto out_free;
        }

        if (!strcmp(sizestr, "max"))
                new_size = device->bdev->bd_inode->i_size;
        else {
                if (sizestr[0] == '-') {
                        mod = -1;
                        sizestr++;
                } else if (sizestr[0] == '+') {
                        mod = 1;
                        sizestr++;
                }
                new_size = memparse(sizestr, &retptr);
                if (*retptr != '\0' || new_size == 0) {
                        ret = -EINVAL;
                        goto out_free;
                }
        }

        if (device->is_tgtdev_for_dev_replace) {
                ret = -EPERM;
                goto out_free;
        }

        old_size = btrfs_device_get_total_bytes(device);

        if (mod < 0) {
                if (new_size > old_size) {
                        ret = -EINVAL;
                        goto out_free;
                }
                new_size = old_size - new_size;
        } else if (mod > 0) {
                if (new_size > ULLONG_MAX - old_size) {
                        ret = -ERANGE;
                        goto out_free;
                }
                new_size = old_size + new_size;
        }

        if (new_size < SZ_256M) {
                ret = -EINVAL;
                goto out_free;
        }
        if (new_size > device->bdev->bd_inode->i_size) {
                ret = -EFBIG;
                goto out_free;
        }

        new_size = div_u64(new_size, root->sectorsize);
        new_size *= root->sectorsize;

        btrfs_info_in_rcu(root->fs_info, "new size for %s is %llu",
                      rcu_str_deref(device->name), new_size);

        if (new_size > old_size) {
                trans = btrfs_start_transaction(root, 0);
                if (IS_ERR(trans)) {
                        ret = PTR_ERR(trans);
                        goto out_free;
                }
                ret = btrfs_grow_device(trans, device, new_size);
                btrfs_commit_transaction(trans, root);
        } else if (new_size < old_size) {
                ret = btrfs_shrink_device(device, new_size);
        } /* equal, nothing need to do */

out_free:
        kfree(vol_args);
out:
        mutex_unlock(&root->fs_info->volume_mutex);
        atomic_set(&root->fs_info->mutually_exclusive_operation_running, 0);
        mnt_drop_write_file(file);
        return ret;
}

static noinline int btrfs_ioctl_snap_create_transid(struct file *file,
                                char *name, unsigned long fd, int subvol,
                                u64 *transid, bool readonly,
                                struct btrfs_qgroup_inherit *inherit)
{
        int namelen;
        int ret = 0;

        if (!S_ISDIR(file_inode(file)->i_mode))
                return -ENOTDIR;

        ret = mnt_want_write_file(file);
        if (ret)
                goto out;

        namelen = strlen(name);
        if (strchr(name, '/')) {
                ret = -EINVAL;
                goto out_drop_write;
        }

        if (name[0] == '.' &&
           (namelen == 1 || (name[1] == '.' && namelen == 2))) {
                ret = -EEXIST;
                goto out_drop_write;
        }

        if (subvol) {
                ret = btrfs_mksubvol(&file->f_path, name, namelen,
                                     NULL, transid, readonly, inherit);
        } else {
                struct fd src = fdget(fd);
                struct inode *src_inode;
                if (!src.file) {
                        ret = -EINVAL;
                        goto out_drop_write;
                }

                src_inode = file_inode(src.file);
                if (src_inode->i_sb != file_inode(file)->i_sb) {
                        btrfs_info(BTRFS_I(file_inode(file))->root->fs_info,
                                   "Snapshot src from another FS");
                        ret = -EXDEV;
                } else if (!inode_owner_or_capable(src_inode)) {
                        /*
                         * Subvolume creation is not restricted, but snapshots
                         * are limited to own subvolumes only
                         */
                        ret = -EPERM;
                } else {
                        ret = btrfs_mksubvol(&file->f_path, name, namelen,
                                             BTRFS_I(src_inode)->root,
                                             transid, readonly, inherit);
                }
                fdput(src);
        }
out_drop_write:
        mnt_drop_write_file(file);
out:
        return ret;
}

static noinline int btrfs_ioctl_snap_create(struct file *file,
                                            void __user *arg, int subvol)
{
        struct btrfs_ioctl_vol_args *vol_args;
        int ret;

        if (!S_ISDIR(file_inode(file)->i_mode))
                return -ENOTDIR;

        vol_args = memdup_user(arg, sizeof(*vol_args));
        if (IS_ERR(vol_args))
                return PTR_ERR(vol_args);
        vol_args->name[BTRFS_PATH_NAME_MAX] = '\0';

        ret = btrfs_ioctl_snap_create_transid(file, vol_args->name,
                                              vol_args->fd, subvol,
                                              NULL, false, NULL);

        kfree(vol_args);
        return ret;
}

static noinline int btrfs_ioctl_snap_create_v2(struct file *file,
                                               void __user *arg, int subvol)
{
        struct btrfs_ioctl_vol_args_v2 *vol_args;
        int ret;
        u64 transid = 0;
        u64 *ptr = NULL;
        bool readonly = false;
        struct btrfs_qgroup_inherit *inherit = NULL;

        if (!S_ISDIR(file_inode(file)->i_mode))
                return -ENOTDIR;

        vol_args = memdup_user(arg, sizeof(*vol_args));
        if (IS_ERR(vol_args))
                return PTR_ERR(vol_args);
        vol_args->name[BTRFS_SUBVOL_NAME_MAX] = '\0';

        if (vol_args->flags &
            ~(BTRFS_SUBVOL_CREATE_ASYNC | BTRFS_SUBVOL_RDONLY |
              BTRFS_SUBVOL_QGROUP_INHERIT)) {
                ret = -EOPNOTSUPP;
                goto free_args;
        }

        if (vol_args->flags & BTRFS_SUBVOL_CREATE_ASYNC)
                ptr = &transid;
        if (vol_args->flags & BTRFS_SUBVOL_RDONLY)
                readonly = true;
        if (vol_args->flags & BTRFS_SUBVOL_QGROUP_INHERIT) {
                if (vol_args->size > PAGE_SIZE) {
                        ret = -EINVAL;
                        goto free_args;
                }
                inherit = memdup_user(vol_args->qgroup_inherit, vol_args->size);
                if (IS_ERR(inherit)) {
                        ret = PTR_ERR(inherit);
                        goto free_args;
                }
        }

        ret = btrfs_ioctl_snap_create_transid(file, vol_args->name,
                                              vol_args->fd, subvol, ptr,
                                              readonly, inherit);
        if (ret)
                goto free_inherit;

        if (ptr && copy_to_user(arg +
                                offsetof(struct btrfs_ioctl_vol_args_v2,
                                        transid),
                                ptr, sizeof(*ptr)))
                ret = -EFAULT;

free_inherit:
        kfree(inherit);
free_args:
        kfree(vol_args);
        return ret;
}

static noinline int btrfs_ioctl_subvol_getflags(struct file *file,
                                                void __user *arg)
{
        struct inode *inode = file_inode(file);
        struct btrfs_root *root = BTRFS_I(inode)->root;
        int ret = 0;
        u64 flags = 0;

        if (btrfs_ino(inode) != BTRFS_FIRST_FREE_OBJECTID)
                return -EINVAL;

        down_read(&root->fs_info->subvol_sem);
        if (btrfs_root_readonly(root))
                flags |= BTRFS_SUBVOL_RDONLY;
        up_read(&root->fs_info->subvol_sem);

        if (copy_to_user(arg, &flags, sizeof(flags)))
                ret = -EFAULT;

        return ret;
}

static noinline int btrfs_ioctl_subvol_setflags(struct file *file,
                                              void __user *arg)
{
        struct inode *inode = file_inode(file);
        struct btrfs_root *root = BTRFS_I(inode)->root;
        struct btrfs_trans_handle *trans;
        u64 root_flags;
        u64 flags;
        int ret = 0;

        if (!inode_owner_or_capable(inode))
                return -EPERM;

        ret = mnt_want_write_file(file);
        if (ret)
                goto out;

        if (btrfs_ino(inode) != BTRFS_FIRST_FREE_OBJECTID) {
                ret = -EINVAL;
                goto out_drop_write;
        }

        if (copy_from_user(&flags, arg, sizeof(flags))) {
                ret = -EFAULT;
                goto out_drop_write;
        }

        if (flags & BTRFS_SUBVOL_CREATE_ASYNC) {
                ret = -EINVAL;
                goto out_drop_write;
        }

        if (flags & ~BTRFS_SUBVOL_RDONLY) {
                ret = -EOPNOTSUPP;
                goto out_drop_write;
        }

        down_write(&root->fs_info->subvol_sem);

        /* nothing to do */
        if (!!(flags & BTRFS_SUBVOL_RDONLY) == btrfs_root_readonly(root))
                goto out_drop_sem;

        root_flags = btrfs_root_flags(&root->root_item);
        if (flags & BTRFS_SUBVOL_RDONLY) {
                btrfs_set_root_flags(&root->root_item,
                                     root_flags | BTRFS_ROOT_SUBVOL_RDONLY);
        } else {
                /*
                 * Block RO -> RW transition if this subvolume is involved in
                 * send
                 */
                spin_lock(&root->root_item_lock);
                if (root->send_in_progress == 0) {
                        btrfs_set_root_flags(&root->root_item,
                                     root_flags & ~BTRFS_ROOT_SUBVOL_RDONLY);
                        spin_unlock(&root->root_item_lock);
                } else {
                        spin_unlock(&root->root_item_lock);
                        btrfs_warn(root->fs_info,
                        "Attempt to set subvolume %llu read-write during send",
                                        root->root_key.objectid);
                        ret = -EPERM;
                        goto out_drop_sem;
                }
        }

        trans = btrfs_start_transaction(root, 1);
        if (IS_ERR(trans)) {
                ret = PTR_ERR(trans);
                goto out_reset;
        }

        ret = btrfs_update_root(trans, root->fs_info->tree_root,
                                &root->root_key, &root->root_item);

        btrfs_commit_transaction(trans, root);
out_reset:
        if (ret)
                btrfs_set_root_flags(&root->root_item, root_flags);
out_drop_sem:
        up_write(&root->fs_info->subvol_sem);
out_drop_write:
        mnt_drop_write_file(file);
out:
        return ret;
}

/*
 * helper to check if the subvolume references other subvolumes
 */
static noinline int may_destroy_subvol(struct btrfs_root *root)
{
        struct btrfs_path *path;
        struct btrfs_dir_item *di;
        struct btrfs_key key;
        u64 dir_id;
        int ret;

        path = btrfs_alloc_path();
        if (!path)
                return -ENOMEM;

        /* Make sure this root isn't set as the default subvol */
        dir_id = btrfs_super_root_dir(root->fs_info->super_copy);
        di = btrfs_lookup_dir_item(NULL, root->fs_info->tree_root, path,
                                   dir_id, "default", 7, 0);
        if (di && !IS_ERR(di)) {
                btrfs_dir_item_key_to_cpu(path->nodes[0], di, &key);
                if (key.objectid == root->root_key.objectid) {
                        ret = -EPERM;
                        btrfs_err(root->fs_info,
                                  "deleting default subvolume %llu is not allowed",
                                  key.objectid);
                        goto out;
                }
                btrfs_release_path(path);
        }

        key.objectid = root->root_key.objectid;
        key.type = BTRFS_ROOT_REF_KEY;
        key.offset = (u64)-1;

        ret = btrfs_search_slot(NULL, root->fs_info->tree_root,
                                &key, path, 0, 0);
        if (ret < 0)
                goto out;
        BUG_ON(ret == 0);

        ret = 0;
        if (path->slots[0] > 0) {
                path->slots[0]--;
                btrfs_item_key_to_cpu(path->nodes[0], &key, path->slots[0]);
                if (key.objectid == root->root_key.objectid &&
                    key.type == BTRFS_ROOT_REF_KEY)
                        ret = -ENOTEMPTY;
        }
out:
        btrfs_free_path(path);
        return ret;
}

static noinline int key_in_sk(struct btrfs_key *key,
                              struct btrfs_ioctl_search_key *sk)
{
        struct btrfs_key test;
        int ret;

        test.objectid = sk->min_objectid;
        test.type = sk->min_type;
        test.offset = sk->min_offset;

        ret = btrfs_comp_cpu_keys(key, &test);
        if (ret < 0)
                return 0;

        test.objectid = sk->max_objectid;
        test.type = sk->max_type;
        test.offset = sk->max_offset;

        ret = btrfs_comp_cpu_keys(key, &test);
        if (ret > 0)
                return 0;
        return 1;
}

static noinline int copy_to_sk(struct btrfs_path *path,
                               struct btrfs_key *key,
                               struct btrfs_ioctl_search_key *sk,
                               size_t *buf_size,
                               char __user *ubuf,
                               unsigned long *sk_offset,
                               int *num_found)
{
        u64 found_transid;
        struct extent_buffer *leaf;
        struct btrfs_ioctl_search_header sh;
        struct btrfs_key test;
        unsigned long item_off;
        unsigned long item_len;
        int nritems;
        int i;
        int slot;
        int ret = 0;

        leaf = path->nodes[0];
        slot = path->slots[0];
        nritems = btrfs_header_nritems(leaf);

        if (btrfs_header_generation(leaf) > sk->max_transid) {
                i = nritems;
                goto advance_key;
        }
        found_transid = btrfs_header_generation(leaf);

        for (i = slot; i < nritems; i++) {
                item_off = btrfs_item_ptr_offset(leaf, i);
                item_len = btrfs_item_size_nr(leaf, i);

                btrfs_item_key_to_cpu(leaf, key, i);
                if (!key_in_sk(key, sk))
                        continue;

                if (sizeof(sh) + item_len > *buf_size) {
                        if (*num_found) {
                                ret = 1;

                                goto out;
                        }

                        /*
                         * return one empty item back for v1, which does not
                         * handle -EOVERFLOW
                         */

                        *buf_size = sizeof(sh) + item_len;
                        item_len = 0;
                        ret = -EOVERFLOW;
                }

                if (sizeof(sh) + item_len + *sk_offset > *buf_size) {
                        ret = 1;
                        goto out;
                }

                sh.objectid = key->objectid;
                sh.offset = key->offset;
                sh.type = key->type;
                sh.len = item_len;
                sh.transid = found_transid;

                /* copy search result header */
                if (copy_to_user(ubuf + *sk_offset, &sh, sizeof(sh))) {
                        ret = -EFAULT;
                        goto out;
                }

                *sk_offset += sizeof(sh);

                if (item_len) {
                        char __user *up = ubuf + *sk_offset;
                        /* copy the item */
                        if (read_extent_buffer_to_user(leaf, up,
                                                       item_off, item_len)) {
                                ret = -EFAULT;
                                goto out;
                        }

                        *sk_offset += item_len;
                }
                (*num_found)++;

                if (ret) /* -EOVERFLOW from above */
                        goto out;

                if (*num_found >= sk->nr_items) {
                        ret = 1;
                        goto out;
                }
        }
advance_key:
        ret = 0;
        test.objectid = sk->max_objectid;
        test.type = sk->max_type;
        test.offset = sk->max_offset;
        if (btrfs_comp_cpu_keys(key, &test) >= 0)
                ret = 1;
        else if (key->offset < (u64)-1)
                key->offset++;
        else if (key->type < (u8)-1) {
                key->offset = 0;
                key->type++;
        } else if (key->objectid < (u64)-1) {
                key->offset = 0;
                key->type = 0;
                key->objectid++;
        } else
                ret = 1;
out:
        /*
         *  0: all items from this leaf copied, continue with next
         *  1: * more items can be copied, but unused buffer is too small
         *     * all items were found
         *     Either way, it will stops the loop which iterates to the next
         *     leaf
         *  -EOVERFLOW: item was to large for buffer
         *  -EFAULT: could not copy extent buffer back to userspace
         */
        return ret;
}

static noinline int search_ioctl(struct inode *inode,
                                 struct btrfs_ioctl_search_key *sk,
                                 size_t *buf_size,
                                 char __user *ubuf)
{
        struct btrfs_root *root;
        struct btrfs_key key;
        struct btrfs_path *path;
        struct btrfs_fs_info *info = BTRFS_I(inode)->root->fs_info;
        int ret;
        int num_found = 0;
        unsigned long sk_offset = 0;

        if (*buf_size < sizeof(struct btrfs_ioctl_search_header)) {
                *buf_size = sizeof(struct btrfs_ioctl_search_header);
                return -EOVERFLOW;
        }

        path = btrfs_alloc_path();
        if (!path)
                return -ENOMEM;

        if (sk->tree_id == 0) {
                /* search the root of the inode that was passed */
                root = BTRFS_I(inode)->root;
        } else {
                key.objectid = sk->tree_id;
                key.type = BTRFS_ROOT_ITEM_KEY;
                key.offset = (u64)-1;
                root = btrfs_read_fs_root_no_name(info, &key);
                if (IS_ERR(root)) {
                        btrfs_free_path(path);
                        return -ENOENT;
                }
        }

        key.objectid = sk->min_objectid;
        key.type = sk->min_type;
        key.offset = sk->min_offset;

        while (1) {
                ret = btrfs_search_forward(root, &key, path, sk->min_transid);
                if (ret != 0) {
                        if (ret > 0)
                                ret = 0;
                        goto err;
                }
                ret = copy_to_sk(path, &key, sk, buf_size, ubuf,
                                 &sk_offset, &num_found);
                btrfs_release_path(path);
                if (ret)
                        break;

        }
        if (ret > 0)
                ret = 0;
err:
        sk->nr_items = num_found;
        btrfs_free_path(path);
        return ret;
}

static noinline int btrfs_ioctl_tree_search(struct file *file,
                                           void __user *argp)
{
        struct btrfs_ioctl_search_args __user *uargs;
        struct btrfs_ioctl_search_key sk;
        struct inode *inode;
        int ret;
        size_t buf_size;

        if (!capable(CAP_SYS_ADMIN))
                return -EPERM;

        uargs = (struct btrfs_ioctl_search_args __user *)argp;

        if (copy_from_user(&sk, &uargs->key, sizeof(sk)))
                return -EFAULT;

        buf_size = sizeof(uargs->buf);

        inode = file_inode(file);
        ret = search_ioctl(inode, &sk, &buf_size, uargs->buf);

        /*
         * In the origin implementation an overflow is handled by returning a
         * search header with a len of zero, so reset ret.
         */
        if (ret == -EOVERFLOW)
                ret = 0;

        if (ret == 0 && copy_to_user(&uargs->key, &sk, sizeof(sk)))
                ret = -EFAULT;
        return ret;
}

static noinline int btrfs_ioctl_tree_search_v2(struct file *file,
                                               void __user *argp)
{
        struct btrfs_ioctl_search_args_v2 __user *uarg;
        struct btrfs_ioctl_search_args_v2 args;
        struct inode *inode;
        int ret;
        size_t buf_size;
        const size_t buf_limit = SZ_16M;

        if (!capable(CAP_SYS_ADMIN))
                return -EPERM;

        /* copy search header and buffer size */
        uarg = (struct btrfs_ioctl_search_args_v2 __user *)argp;
        if (copy_from_user(&args, uarg, sizeof(args)))
                return -EFAULT;

        buf_size = args.buf_size;

        if (buf_size < sizeof(struct btrfs_ioctl_search_header))
                return -EOVERFLOW;

        /* limit result size to 16MB */
        if (buf_size > buf_limit)
                buf_size = buf_limit;

        inode = file_inode(file);
        ret = search_ioctl(inode, &args.key, &buf_size,
                           (char *)(&uarg->buf[0]));
        if (ret == 0 && copy_to_user(&uarg->key, &args.key, sizeof(args.key)))
                ret = -EFAULT;
        else if (ret == -EOVERFLOW &&
                copy_to_user(&uarg->buf_size, &buf_size, sizeof(buf_size)))
                ret = -EFAULT;

        return ret;
}

/*
 * Search INODE_REFs to identify path name of 'dirid' directory
 * in a 'tree_id' tree. and sets path name to 'name'.
 */
static noinline int btrfs_search_path_in_tree(struct btrfs_fs_info *info,
                                u64 tree_id, u64 dirid, char *name)
{
        struct btrfs_root *root;
        struct btrfs_key key;
        char *ptr;
        int ret = -1;
        int slot;
        int len;
        int total_len = 0;
        struct btrfs_inode_ref *iref;
        struct extent_buffer *l;
        struct btrfs_path *path;

        if (dirid == BTRFS_FIRST_FREE_OBJECTID) {
                name[0]='\0';
                return 0;
        }

        path = btrfs_alloc_path();
        if (!path)
                return -ENOMEM;

        ptr = &name[BTRFS_INO_LOOKUP_PATH_MAX];

        key.objectid = tree_id;
        key.type = BTRFS_ROOT_ITEM_KEY;
        key.offset = (u64)-1;
        root = btrfs_read_fs_root_no_name(info, &key);
        if (IS_ERR(root)) {
                btrfs_err(info, "could not find root %llu", tree_id);
                ret = -ENOENT;
                goto out;
        }

        key.objectid = dirid;
        key.type = BTRFS_INODE_REF_KEY;
        key.offset = (u64)-1;

        while (1) {
                ret = btrfs_search_slot(NULL, root, &key, path, 0, 0);
                if (ret < 0)
                        goto out;
                else if (ret > 0) {
                        ret = btrfs_previous_item(root, path, dirid,
                                                  BTRFS_INODE_REF_KEY);
                        if (ret < 0)
                                goto out;
                        else if (ret > 0) {
                                ret = -ENOENT;
                                goto out;
                        }
                }

                l = path->nodes[0];
                slot = path->slots[0];
                btrfs_item_key_to_cpu(l, &key, slot);

                iref = btrfs_item_ptr(l, slot, struct btrfs_inode_ref);
                len = btrfs_inode_ref_name_len(l, iref);
                ptr -= len + 1;
                total_len += len + 1;
                if (ptr < name) {
                        ret = -ENAMETOOLONG;
                        goto out;
                }

                *(ptr + len) = '/';
                read_extent_buffer(l, ptr, (unsigned long)(iref + 1), len);

                if (key.offset == BTRFS_FIRST_FREE_OBJECTID)
                        break;

                btrfs_release_path(path);
                key.objectid = key.offset;
                key.offset = (u64)-1;
                dirid = key.objectid;
        }
        memmove(name, ptr, total_len);
        name[total_len] = '\0';
        ret = 0;
out:
        btrfs_free_path(path);
        return ret;
}

static noinline int btrfs_ioctl_ino_lookup(struct file *file,
                                           void __user *argp)
{
         struct btrfs_ioctl_ino_lookup_args *args;
         struct inode *inode;
        int ret = 0;

        args = memdup_user(argp, sizeof(*args));
        if (IS_ERR(args))
                return PTR_ERR(args);

        inode = file_inode(file);

        /*
         * Unprivileged query to obtain the containing subvolume root id. The
         * path is reset so it's consistent with btrfs_search_path_in_tree.
         */
        if (args->treeid == 0)
                args->treeid = BTRFS_I(inode)->root->root_key.objectid;

        if (args->objectid == BTRFS_FIRST_FREE_OBJECTID) {
                args->name[0] = 0;
                goto out;
        }

        if (!capable(CAP_SYS_ADMIN)) {
                ret = -EPERM;
                goto out;
        }

        ret = btrfs_search_path_in_tree(BTRFS_I(inode)->root->fs_info,
                                        args->treeid, args->objectid,
                                        args->name);

out:
        if (ret == 0 && copy_to_user(argp, args, sizeof(*args)))
                ret = -EFAULT;

        kfree(args);
        return ret;
}

static noinline int btrfs_ioctl_snap_destroy(struct file *file,
                                             void __user *arg)
{
        struct dentry *parent = file->f_path.dentry;
        struct dentry *dentry;
        struct inode *dir = d_inode(parent);
        struct inode *inode;
        struct btrfs_root *root = BTRFS_I(dir)->root;
        struct btrfs_root *dest = NULL;
        struct btrfs_ioctl_vol_args *vol_args;
        struct btrfs_trans_handle *trans;
        struct btrfs_block_rsv block_rsv;
        u64 root_flags;
        u64 qgroup_reserved;
        int namelen;
        int ret;
        int err = 0;

        if (!S_ISDIR(dir->i_mode))
                return -ENOTDIR;

        vol_args = memdup_user(arg, sizeof(*vol_args));
        if (IS_ERR(vol_args))
                return PTR_ERR(vol_args);

        vol_args->name[BTRFS_PATH_NAME_MAX] = '\0';
        namelen = strlen(vol_args->name);
        if (strchr(vol_args->name, '/') ||
            strncmp(vol_args->name, "..", namelen) == 0) {
                err = -EINVAL;
                goto out;
        }

        err = mnt_want_write_file(file);
        if (err)
                goto out;


        err = down_write_killable_nested(&dir->i_rwsem, I_MUTEX_PARENT);
        if (err == -EINTR)
                goto out_drop_write;
        dentry = lookup_one_len(vol_args->name, parent, namelen);
        if (IS_ERR(dentry)) {
                err = PTR_ERR(dentry);
                goto out_unlock_dir;
        }

        if (d_really_is_negative(dentry)) {
                err = -ENOENT;
                goto out_dput;
        }

        inode = d_inode(dentry);
        dest = BTRFS_I(inode)->root;
        if (!capable(CAP_SYS_ADMIN)) {
                /*
                 * Regular user.  Only allow this with a special mount
                 * option, when the user has write+exec access to the
                 * subvol root, and when rmdir(2) would have been
                 * allowed.
                 *
                 * Note that this is _not_ check that the subvol is
                 * empty or doesn't contain data that we wouldn't
                 * otherwise be able to delete.
                 *
                 * Users who want to delete empty subvols should try
                 * rmdir(2).
                 */
                err = -EPERM;
                if (!btrfs_test_opt(root->fs_info, USER_SUBVOL_RM_ALLOWED))
                        goto out_dput;

                /*
                 * Do not allow deletion if the parent dir is the same
                 * as the dir to be deleted.  That means the ioctl
                 * must be called on the dentry referencing the root
                 * of the subvol, not a random directory contained
                 * within it.
                 */
                err = -EINVAL;
                if (root == dest)
                        goto out_dput;

                err = inode_permission(inode, MAY_WRITE | MAY_EXEC);
                if (err)
                        goto out_dput;
        }

        /* check if subvolume may be deleted by a user */
        err = btrfs_may_delete(dir, dentry, 1);
        if (err)
                goto out_dput;

        if (btrfs_ino(inode) != BTRFS_FIRST_FREE_OBJECTID) {
                err = -EINVAL;
                goto out_dput;
        }

        inode_lock(inode);

        /*
         * Don't allow to delete a subvolume with send in progress. This is
         * inside the i_mutex so the error handling that has to drop the bit
         * again is not run concurrently.
         */
        spin_lock(&dest->root_item_lock);
        root_flags = btrfs_root_flags(&dest->root_item);
        if (dest->send_in_progress == 0) {
                btrfs_set_root_flags(&dest->root_item,
                                root_flags | BTRFS_ROOT_SUBVOL_DEAD);
                spin_unlock(&dest->root_item_lock);
        } else {
                spin_unlock(&dest->root_item_lock);
                btrfs_warn(root->fs_info,
                        "Attempt to delete subvolume %llu during send",
                        dest->root_key.objectid);
                err = -EPERM;
                goto out_unlock_inode;
        }

        down_write(&root->fs_info->subvol_sem);

        err = may_destroy_subvol(dest);
        if (err)
                goto out_up_write;

        btrfs_init_block_rsv(&block_rsv, BTRFS_BLOCK_RSV_TEMP);
        /*
         * One for dir inode, two for dir entries, two for root
         * ref/backref.
         */
        err = btrfs_subvolume_reserve_metadata(root, &block_rsv,
                                               5, &qgroup_reserved, true);
        if (err)
                goto out_up_write;

        trans = btrfs_start_transaction(root, 0);
        if (IS_ERR(trans)) {
                err = PTR_ERR(trans);
                goto out_release;
        }
        trans->block_rsv = &block_rsv;
        trans->bytes_reserved = block_rsv.size;

        btrfs_record_snapshot_destroy(trans, dir);

        ret = btrfs_unlink_subvol(trans, root, dir,
                                dest->root_key.objectid,
                                dentry->d_name.name,
                                dentry->d_name.len);
        if (ret) {
                err = ret;
                btrfs_abort_transaction(trans, ret);
                goto out_end_trans;
        }

        btrfs_record_root_in_trans(trans, dest);

        memset(&dest->root_item.drop_progress, 0,
                sizeof(dest->root_item.drop_progress));
        dest->root_item.drop_level = 0;
        btrfs_set_root_refs(&dest->root_item, 0);

        if (!test_and_set_bit(BTRFS_ROOT_ORPHAN_ITEM_INSERTED, &dest->state)) {
                ret = btrfs_insert_orphan_item(trans,
                                        root->fs_info->tree_root,
                                        dest->root_key.objectid);
                if (ret) {
                        btrfs_abort_transaction(trans, ret);
                        err = ret;
                        goto out_end_trans;
                }
        }

        ret = btrfs_uuid_tree_rem(trans, root->fs_info->uuid_root,
                                  dest->root_item.uuid, BTRFS_UUID_KEY_SUBVOL,
                                  dest->root_key.objectid);
        if (ret && ret != -ENOENT) {
                btrfs_abort_transaction(trans, ret);
                err = ret;
                goto out_end_trans;
        }
        if (!btrfs_is_empty_uuid(dest->root_item.received_uuid)) {
                ret = btrfs_uuid_tree_rem(trans, root->fs_info->uuid_root,
                                          dest->root_item.received_uuid,
                                          BTRFS_UUID_KEY_RECEIVED_SUBVOL,
                                          dest->root_key.objectid);
                if (ret && ret != -ENOENT) {
                        btrfs_abort_transaction(trans, ret);
                        err = ret;
                        goto out_end_trans;
                }
        }

out_end_trans:
        trans->block_rsv = NULL;
        trans->bytes_reserved = 0;
        ret = btrfs_end_transaction(trans, root);
        if (ret && !err)
                err = ret;
        inode->i_flags |= S_DEAD;
out_release:
        btrfs_subvolume_release_metadata(root, &block_rsv, qgroup_reserved);
out_up_write:
        up_write(&root->fs_info->subvol_sem);
        if (err) {
                spin_lock(&dest->root_item_lock);
                root_flags = btrfs_root_flags(&dest->root_item);
                btrfs_set_root_flags(&dest->root_item,
                                root_flags & ~BTRFS_ROOT_SUBVOL_DEAD);
                spin_unlock(&dest->root_item_lock);
        }
out_unlock_inode:
        inode_unlock(inode);
        if (!err) {
                d_invalidate(dentry);
                btrfs_invalidate_inodes(dest);
                d_delete(dentry);
                ASSERT(dest->send_in_progress == 0);

                /* the last ref */
                if (dest->ino_cache_inode) {
                        iput(dest->ino_cache_inode);
                        dest->ino_cache_inode = NULL;
                }
        }
out_dput:
        dput(dentry);
out_unlock_dir:
        inode_unlock(dir);
out_drop_write:
        mnt_drop_write_file(file);
out:
        kfree(vol_args);
        return err;
}

static int btrfs_ioctl_defrag(struct file *file, void __user *argp)
{
        struct inode *inode = file_inode(file);
        struct btrfs_root *root = BTRFS_I(inode)->root;
        struct btrfs_ioctl_defrag_range_args *range;
        int ret;

        ret = mnt_want_write_file(file);
        if (ret)
                return ret;

        if (btrfs_root_readonly(root)) {
                ret = -EROFS;
                goto out;
        }

        switch (inode->i_mode & S_IFMT) {
        case S_IFDIR:
                if (!capable(CAP_SYS_ADMIN)) {
                        ret = -EPERM;
                        goto out;
                }
                ret = btrfs_defrag_root(root);
                if (ret)
                        goto out;
                ret = btrfs_defrag_root(root->fs_info->extent_root);
                break;
        case S_IFREG:
                if (!(file->f_mode & FMODE_WRITE)) {
                        ret = -EINVAL;
                        goto out;
                }

                range = kzalloc(sizeof(*range), GFP_KERNEL);
                if (!range) {
                        ret = -ENOMEM;
                        goto out;
                }

                if (argp) {
                        if (copy_from_user(range, argp,
                                           sizeof(*range))) {
                                ret = -EFAULT;
                                kfree(range);
                                goto out;
                        }
                        /* compression requires us to start the IO */
                        if ((range->flags & BTRFS_DEFRAG_RANGE_COMPRESS)) {
                                range->flags |= BTRFS_DEFRAG_RANGE_START_IO;
                                range->extent_thresh = (u32)-1;
                        }
                } else {
                        /* the rest are all set to zero by kzalloc */
                        range->len = (u64)-1;
                }
                ret = btrfs_defrag_file(file_inode(file), file,
                                        range, 0, 0);
                if (ret > 0)
                        ret = 0;
                kfree(range);
                break;
        default:
                ret = -EINVAL;
        }
out:
        mnt_drop_write_file(file);
        return ret;
}

static long btrfs_ioctl_add_dev(struct btrfs_root *root, void __user *arg)
{
        struct btrfs_ioctl_vol_args *vol_args;
        int ret;

        if (!capable(CAP_SYS_ADMIN))
                return -EPERM;

        if (atomic_xchg(&root->fs_info->mutually_exclusive_operation_running,
                        1)) {
                return BTRFS_ERROR_DEV_EXCL_RUN_IN_PROGRESS;
        }

        mutex_lock(&root->fs_info->volume_mutex);
        vol_args = memdup_user(arg, sizeof(*vol_args));
        if (IS_ERR(vol_args)) {
                ret = PTR_ERR(vol_args);
                goto out;
        }

        vol_args->name[BTRFS_PATH_NAME_MAX] = '\0';
        ret = btrfs_init_new_device(root, vol_args->name);

        if (!ret)
                btrfs_info(root->fs_info, "disk added %s",vol_args->name);

        kfree(vol_args);
out:
        mutex_unlock(&root->fs_info->volume_mutex);
        atomic_set(&root->fs_info->mutually_exclusive_operation_running, 0);
        return ret;
}

static long btrfs_ioctl_rm_dev_v2(struct file *file, void __user *arg)
{
        struct btrfs_root *root = BTRFS_I(file_inode(file))->root;
        struct btrfs_ioctl_vol_args_v2 *vol_args;
        int ret;

        if (!capable(CAP_SYS_ADMIN))
                return -EPERM;

        ret = mnt_want_write_file(file);
        if (ret)
                return ret;

        vol_args = memdup_user(arg, sizeof(*vol_args));
        if (IS_ERR(vol_args)) {
                ret = PTR_ERR(vol_args);
                goto err_drop;
        }

        /* Check for compatibility reject unknown flags */
        if (vol_args->flags & ~BTRFS_VOL_ARG_V2_FLAGS_SUPPORTED)
                return -EOPNOTSUPP;

        if (atomic_xchg(&root->fs_info->mutually_exclusive_operation_running,
                        1)) {
                ret = BTRFS_ERROR_DEV_EXCL_RUN_IN_PROGRESS;
                goto out;
        }

        mutex_lock(&root->fs_info->volume_mutex);
        if (vol_args->flags & BTRFS_DEVICE_SPEC_BY_ID) {
                ret = btrfs_rm_device(root, NULL, vol_args->devid);
        } else {
                vol_args->name[BTRFS_SUBVOL_NAME_MAX] = '\0';
                ret = btrfs_rm_device(root, vol_args->name, 0);
        }
        mutex_unlock(&root->fs_info->volume_mutex);
        atomic_set(&root->fs_info->mutually_exclusive_operation_running, 0);

        if (!ret) {
                if (vol_args->flags & BTRFS_DEVICE_SPEC_BY_ID)
                        btrfs_info(root->fs_info, "device deleted: id %llu",
                                        vol_args->devid);
                else
                        btrfs_info(root->fs_info, "device deleted: %s",
                                        vol_args->name);
        }
out:
        kfree(vol_args);
err_drop:
        mnt_drop_write_file(file);
        return ret;
}

static long btrfs_ioctl_rm_dev(struct file *file, void __user *arg)
{
        struct btrfs_root *root = BTRFS_I(file_inode(file))->root;
        struct btrfs_ioctl_vol_args *vol_args;
        int ret;

        if (!capable(CAP_SYS_ADMIN))
                return -EPERM;

        ret = mnt_want_write_file(file);
        if (ret)
                return ret;

        if (atomic_xchg(&root->fs_info->mutually_exclusive_operation_running,
                        1)) {
                ret = BTRFS_ERROR_DEV_EXCL_RUN_IN_PROGRESS;
                goto out_drop_write;
        }

        vol_args = memdup_user(arg, sizeof(*vol_args));
        if (IS_ERR(vol_args)) {
                ret = PTR_ERR(vol_args);
                goto out;
        }

        vol_args->name[BTRFS_PATH_NAME_MAX] = '\0';
        mutex_lock(&root->fs_info->volume_mutex);
        ret = btrfs_rm_device(root, vol_args->name, 0);
        mutex_unlock(&root->fs_info->volume_mutex);

        if (!ret)
                btrfs_info(root->fs_info, "disk deleted %s",vol_args->name);
        kfree(vol_args);
out:
        atomic_set(&root->fs_info->mutually_exclusive_operation_running, 0);
out_drop_write:
        mnt_drop_write_file(file);

        return ret;
}

static long btrfs_ioctl_fs_info(struct btrfs_root *root, void __user *arg)
{
        struct btrfs_ioctl_fs_info_args *fi_args;
        struct btrfs_device *device;
        struct btrfs_fs_devices *fs_devices = root->fs_info->fs_devices;
        int ret = 0;

        fi_args = kzalloc(sizeof(*fi_args), GFP_KERNEL);
        if (!fi_args)
                return -ENOMEM;

        mutex_lock(&fs_devices->device_list_mutex);
        fi_args->num_devices = fs_devices->num_devices;
        memcpy(&fi_args->fsid, root->fs_info->fsid, sizeof(fi_args->fsid));

        list_for_each_entry(device, &fs_devices->devices, dev_list) {
                if (device->devid > fi_args->max_id)
                        fi_args->max_id = device->devid;
        }
        mutex_unlock(&fs_devices->device_list_mutex);

        fi_args->nodesize = root->fs_info->super_copy->nodesize;
        fi_args->sectorsize = root->fs_info->super_copy->sectorsize;
        fi_args->clone_alignment = root->fs_info->super_copy->sectorsize;

        if (copy_to_user(arg, fi_args, sizeof(*fi_args)))
                ret = -EFAULT;

        kfree(fi_args);
        return ret;
}

static long btrfs_ioctl_dev_info(struct btrfs_root *root, void __user *arg)
{
        struct btrfs_ioctl_dev_info_args *di_args;
        struct btrfs_device *dev;
        struct btrfs_fs_devices *fs_devices = root->fs_info->fs_devices;
        int ret = 0;
        char *s_uuid = NULL;

        di_args = memdup_user(arg, sizeof(*di_args));
        if (IS_ERR(di_args))
                return PTR_ERR(di_args);

        if (!btrfs_is_empty_uuid(di_args->uuid))
                s_uuid = di_args->uuid;

        mutex_lock(&fs_devices->device_list_mutex);
        dev = btrfs_find_device(root->fs_info, di_args->devid, s_uuid, NULL);

        if (!dev) {
                ret = -ENODEV;
                goto out;
        }

        di_args->devid = dev->devid;
        di_args->bytes_used = btrfs_device_get_bytes_used(dev);
        di_args->total_bytes = btrfs_device_get_total_bytes(dev);
        memcpy(di_args->uuid, dev->uuid, sizeof(di_args->uuid));
        if (dev->name) {
                struct rcu_string *name;

                rcu_read_lock();
                name = rcu_dereference(dev->name);
                strncpy(di_args->path, name->str, sizeof(di_args->path));
                rcu_read_unlock();
                di_args->path[sizeof(di_args->path) - 1] = 0;
        } else {
                di_args->path[0] = '\0';
        }

out:
        mutex_unlock(&fs_devices->device_list_mutex);
        if (ret == 0 && copy_to_user(arg, di_args, sizeof(*di_args)))
                ret = -EFAULT;

        kfree(di_args);
        return ret;
}

static struct page *extent_same_get_page(struct inode *inode, pgoff_t index)
{
        struct page *page;

        page = grab_cache_page(inode->i_mapping, index);
        if (!page)
                return ERR_PTR(-ENOMEM);

        if (!PageUptodate(page)) {
                int ret;

                ret = btrfs_readpage(NULL, page);
                if (ret)
                        return ERR_PTR(ret);
                lock_page(page);
                if (!PageUptodate(page)) {
                        unlock_page(page);
                        put_page(page);
                        return ERR_PTR(-EIO);
                }
                if (page->mapping != inode->i_mapping) {
                        unlock_page(page);
                        put_page(page);
                        return ERR_PTR(-EAGAIN);
                }
        }

        return page;
}

static int gather_extent_pages(struct inode *inode, struct page **pages,
                               int num_pages, u64 off)
{
        int i;
        pgoff_t index = off >> PAGE_SHIFT;

        for (i = 0; i < num_pages; i++) {
again:
                pages[i] = extent_same_get_page(inode, index + i);
                if (IS_ERR(pages[i])) {
                        int err = PTR_ERR(pages[i]);

                        if (err == -EAGAIN)
                                goto again;
                        pages[i] = NULL;
                        return err;
                }
        }
        return 0;
}

static int lock_extent_range(struct inode *inode, u64 off, u64 len,
                             bool retry_range_locking)
{
        /*
         * Do any pending delalloc/csum calculations on inode, one way or
         * another, and lock file content.
         * The locking order is:
         *
         *   1) pages
         *   2) range in the inode's io tree
         */
        while (1) {
                struct btrfs_ordered_extent *ordered;
                lock_extent(&BTRFS_I(inode)->io_tree, off, off + len - 1);
                ordered = btrfs_lookup_first_ordered_extent(inode,
                                                            off + len - 1);
                if ((!ordered ||
                     ordered->file_offset + ordered->len <= off ||
                     ordered->file_offset >= off + len) &&
                    !test_range_bit(&BTRFS_I(inode)->io_tree, off,
                                    off + len - 1, EXTENT_DELALLOC, 0, NULL)) {
                        if (ordered)
                                btrfs_put_ordered_extent(ordered);
                        break;
                }
                unlock_extent(&BTRFS_I(inode)->io_tree, off, off + len - 1);
                if (ordered)
                        btrfs_put_ordered_extent(ordered);
                if (!retry_range_locking)
                        return -EAGAIN;
                btrfs_wait_ordered_range(inode, off, len);
        }
        return 0;
}

static void btrfs_double_inode_unlock(struct inode *inode1, struct inode *inode2)
{
        inode_unlock(inode1);
        inode_unlock(inode2);
}

static void btrfs_double_inode_lock(struct inode *inode1, struct inode *inode2)
{
        if (inode1 < inode2)
                swap(inode1, inode2);

        inode_lock_nested(inode1, I_MUTEX_PARENT);
        inode_lock_nested(inode2, I_MUTEX_CHILD);
}

static void btrfs_double_extent_unlock(struct inode *inode1, u64 loff1,
                                      struct inode *inode2, u64 loff2, u64 len)
{
        unlock_extent(&BTRFS_I(inode1)->io_tree, loff1, loff1 + len - 1);
        unlock_extent(&BTRFS_I(inode2)->io_tree, loff2, loff2 + len - 1);
}

static int btrfs_double_extent_lock(struct inode *inode1, u64 loff1,
                                    struct inode *inode2, u64 loff2, u64 len,
                                    bool retry_range_locking)
{
        int ret;

        if (inode1 < inode2) {
                swap(inode1, inode2);
                swap(loff1, loff2);
        }
        ret = lock_extent_range(inode1, loff1, len, retry_range_locking);
        if (ret)
                return ret;
        ret = lock_extent_range(inode2, loff2, len, retry_range_locking);
        if (ret)
                unlock_extent(&BTRFS_I(inode1)->io_tree, loff1,
                              loff1 + len - 1);
        return ret;
}

struct cmp_pages {
        int             num_pages;
        struct page     **src_pages;
        struct page     **dst_pages;
};

static void btrfs_cmp_data_free(struct cmp_pages *cmp)