/*
 * 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/fs.h>
#include <linux/blkdev.h>
#include <linux/scatterlist.h>
#include <linux/swap.h>
#include <linux/radix-tree.h>
#include <linux/writeback.h>
#include <linux/buffer_head.h>
#include <linux/workqueue.h>
#include <linux/kthread.h>
#include <linux/freezer.h>
#include <linux/slab.h>
#include <linux/migrate.h>
#include <linux/ratelimit.h>
#include <linux/uuid.h>
#include <linux/semaphore.h>
#include <asm/unaligned.h>
#include "ctree.h"
#include "disk-io.h"
#include "hash.h"
#include "transaction.h"
#include "btrfs_inode.h"
#include "volumes.h"
#include "print-tree.h"
#include "async-thread.h"
#include "locking.h"
#include "tree-log.h"
#include "free-space-cache.h"
#include "inode-map.h"
#include "check-integrity.h"
#include "rcu-string.h"
#include "dev-replace.h"
#include "raid56.h"
#include "sysfs.h"

#ifdef CONFIG_X86
#include <asm/cpufeature.h>
#endif

static struct extent_io_ops btree_extent_io_ops;
static void end_workqueue_fn(struct btrfs_work *work);
static void free_fs_root(struct btrfs_root *root);
static int btrfs_check_super_valid(struct btrfs_fs_info *fs_info,
                                    int read_only);
static void btrfs_destroy_ordered_operations(struct btrfs_transaction *t,
                                             struct btrfs_root *root);
static void btrfs_destroy_ordered_extents(struct btrfs_root *root);
static int btrfs_destroy_delayed_refs(struct btrfs_transaction *trans,
                                      struct btrfs_root *root);
static void btrfs_destroy_delalloc_inodes(struct btrfs_root *root);
static int btrfs_destroy_marked_extents(struct btrfs_root *root,
                                        struct extent_io_tree *dirty_pages,
                                        int mark);
static int btrfs_destroy_pinned_extent(struct btrfs_root *root,
                                       struct extent_io_tree *pinned_extents);
static int btrfs_cleanup_transaction(struct btrfs_root *root);
static void btrfs_error_commit_super(struct btrfs_root *root);

/*
 * end_io_wq structs are used to do processing in task context when an IO is
 * complete.  This is used during reads to verify checksums, and it is used
 * by writes to insert metadata for new file extents after IO is complete.
 */
struct end_io_wq {
        struct bio *bio;
        bio_end_io_t *end_io;
        void *private;
        struct btrfs_fs_info *info;
        int error;
        int metadata;
        struct list_head list;
        struct btrfs_work work;
};

/*
 * async submit bios are used to offload expensive checksumming
 * onto the worker threads.  They checksum file and metadata bios
 * just before they are sent down the IO stack.
 */
struct async_submit_bio {
        struct inode *inode;
        struct bio *bio;
        struct list_head list;
        extent_submit_bio_hook_t *submit_bio_start;
        extent_submit_bio_hook_t *submit_bio_done;
        int rw;
        int mirror_num;
        unsigned long bio_flags;
        /*
         * bio_offset is optional, can be used if the pages in the bio
         * can't tell us where in the file the bio should go
         */
        u64 bio_offset;
        struct btrfs_work work;
        int error;
};

/*
 * Lockdep class keys for extent_buffer->lock's in this root.  For a given
 * eb, the lockdep key is determined by the btrfs_root it belongs to and
 * the level the eb occupies in the tree.
 *
 * Different roots are used for different purposes and may nest inside each
 * other and they require separate keysets.  As lockdep keys should be
 * static, assign keysets according to the purpose of the root as indicated
 * by btrfs_root->objectid.  This ensures that all special purpose roots
 * have separate keysets.
 *
 * Lock-nesting across peer nodes is always done with the immediate parent
 * node locked thus preventing deadlock.  As lockdep doesn't know this, use
 * subclass to avoid triggering lockdep warning in such cases.
 *
 * The key is set by the readpage_end_io_hook after the buffer has passed
 * csum validation but before the pages are unlocked.  It is also set by
 * btrfs_init_new_buffer on freshly allocated blocks.
 *
 * We also add a check to make sure the highest level of the tree is the
 * same as our lockdep setup here.  If BTRFS_MAX_LEVEL changes, this code
 * needs update as well.
 */
#ifdef CONFIG_DEBUG_LOCK_ALLOC
# if BTRFS_MAX_LEVEL != 8
#  error
# endif

static struct btrfs_lockdep_keyset {
        u64                     id;             /* root objectid */
        const char              *name_stem;     /* lock name stem */
        char                    names[BTRFS_MAX_LEVEL + 1][20];
        struct lock_class_key   keys[BTRFS_MAX_LEVEL + 1];
} btrfs_lockdep_keysets[] = {
        { .id = BTRFS_ROOT_TREE_OBJECTID,       .name_stem = "root"     },
        { .id = BTRFS_EXTENT_TREE_OBJECTID,     .name_stem = "extent"   },
        { .id = BTRFS_CHUNK_TREE_OBJECTID,      .name_stem = "chunk"    },
        { .id = BTRFS_DEV_TREE_OBJECTID,        .name_stem = "dev"      },
        { .id = BTRFS_FS_TREE_OBJECTID,         .name_stem = "fs"       },
        { .id = BTRFS_CSUM_TREE_OBJECTID,       .name_stem = "csum"     },
        { .id = BTRFS_QUOTA_TREE_OBJECTID,      .name_stem = "quota"    },
        { .id = BTRFS_TREE_LOG_OBJECTID,        .name_stem = "log"      },
        { .id = BTRFS_TREE_RELOC_OBJECTID,      .name_stem = "treloc"   },
        { .id = BTRFS_DATA_RELOC_TREE_OBJECTID, .name_stem = "dreloc"   },
        { .id = BTRFS_UUID_TREE_OBJECTID,       .name_stem = "uuid"     },
        { .id = 0,                              .name_stem = "tree"     },
};

void __init btrfs_init_lockdep(void)
{
        int i, j;

        /* initialize lockdep class names */
        for (i = 0; i < ARRAY_SIZE(btrfs_lockdep_keysets); i++) {
                struct btrfs_lockdep_keyset *ks = &btrfs_lockdep_keysets[i];

                for (j = 0; j < ARRAY_SIZE(ks->names); j++)
                        snprintf(ks->names[j], sizeof(ks->names[j]),
                                 "btrfs-%s-%02d", ks->name_stem, j);
        }
}

void btrfs_set_buffer_lockdep_class(u64 objectid, struct extent_buffer *eb,
                                    int level)
{
        struct btrfs_lockdep_keyset *ks;

        BUG_ON(level >= ARRAY_SIZE(ks->keys));

        /* find the matching keyset, id 0 is the default entry */
        for (ks = btrfs_lockdep_keysets; ks->id; ks++)
                if (ks->id == objectid)
                        break;

        lockdep_set_class_and_name(&eb->lock,
                                   &ks->keys[level], ks->names[level]);
}

#endif

/*
 * extents on the btree inode are pretty simple, there's one extent
 * that covers the entire device
 */
static struct extent_map *btree_get_extent(struct inode *inode,
                struct page *page, size_t pg_offset, u64 start, u64 len,
                int create)
{
        struct extent_map_tree *em_tree = &BTRFS_I(inode)->extent_tree;
        struct extent_map *em;
        int ret;

        read_lock(&em_tree->lock);
        em = lookup_extent_mapping(em_tree, start, len);
        if (em) {
                em->bdev =
                        BTRFS_I(inode)->root->fs_info->fs_devices->latest_bdev;
                read_unlock(&em_tree->lock);
                goto out;
        }
        read_unlock(&em_tree->lock);

        em = alloc_extent_map();
        if (!em) {
                em = ERR_PTR(-ENOMEM);
                goto out;
        }
        em->start = 0;
        em->len = (u64)-1;
        em->block_len = (u64)-1;
        em->block_start = 0;
        em->bdev = BTRFS_I(inode)->root->fs_info->fs_devices->latest_bdev;

        write_lock(&em_tree->lock);
        ret = add_extent_mapping(em_tree, em, 0);
        if (ret == -EEXIST) {
                free_extent_map(em);
                em = lookup_extent_mapping(em_tree, start, len);
                if (!em)
                        em = ERR_PTR(-EIO);
        } else if (ret) {
                free_extent_map(em);
                em = ERR_PTR(ret);
        }
        write_unlock(&em_tree->lock);

out:
        return em;
}

u32 btrfs_csum_data(char *data, u32 seed, size_t len)
{
        return btrfs_crc32c(seed, data, len);
}

void btrfs_csum_final(u32 crc, char *result)
{
        put_unaligned_le32(~crc, result);
}

/*
 * compute the csum for a btree block, and either verify it or write it
 * into the csum field of the block.
 */
static int csum_tree_block(struct btrfs_root *root, struct extent_buffer *buf,
                           int verify)
{
        u16 csum_size = btrfs_super_csum_size(root->fs_info->super_copy);
        char *result = NULL;
        unsigned long len;
        unsigned long cur_len;
        unsigned long offset = BTRFS_CSUM_SIZE;
        char *kaddr;
        unsigned long map_start;
        unsigned long map_len;
        int err;
        u32 crc = ~(u32)0;
        unsigned long inline_result;

        len = buf->len - offset;
        while (len > 0) {
                err = map_private_extent_buffer(buf, offset, 32,
                                        &kaddr, &map_start, &map_len);
                if (err)
                        return 1;
                cur_len = min(len, map_len - (offset - map_start));
                crc = btrfs_csum_data(kaddr + offset - map_start,
                                      crc, cur_len);
                len -= cur_len;
                offset += cur_len;
        }
        if (csum_size > sizeof(inline_result)) {
                result = kzalloc(csum_size * sizeof(char), GFP_NOFS);
                if (!result)
                        return 1;
        } else {
                result = (char *)&inline_result;
        }

        btrfs_csum_final(crc, result);

        if (verify) {
                if (memcmp_extent_buffer(buf, result, 0, csum_size)) {
                        u32 val;
                        u32 found = 0;
                        memcpy(&found, result, csum_size);

                        read_extent_buffer(buf, &val, 0, csum_size);
                        printk_ratelimited(KERN_INFO
                                "BTRFS: %s checksum verify failed on %llu wanted %X found %X "
                                "level %d\n",
                                root->fs_info->sb->s_id, buf->start,
                                val, found, btrfs_header_level(buf));
                        if (result != (char *)&inline_result)
                                kfree(result);
                        return 1;
                }
        } else {
                write_extent_buffer(buf, result, 0, csum_size);
        }
        if (result != (char *)&inline_result)
                kfree(result);
        return 0;
}

/*
 * we can't consider a given block up to date unless the transid of the
 * block matches the transid in the parent node's pointer.  This is how we
 * detect blocks that either didn't get written at all or got written
 * in the wrong place.
 */
static int verify_parent_transid(struct extent_io_tree *io_tree,
                                 struct extent_buffer *eb, u64 parent_transid,
                                 int atomic)
{
        struct extent_state *cached_state = NULL;
        int ret;
        bool need_lock = (current->journal_info ==
                          (void *)BTRFS_SEND_TRANS_STUB);

        if (!parent_transid || btrfs_header_generation(eb) == parent_transid)
                return 0;

        if (atomic)
                return -EAGAIN;

        if (need_lock) {
                btrfs_tree_read_lock(eb);
                btrfs_set_lock_blocking_rw(eb, BTRFS_READ_LOCK);
        }

        lock_extent_bits(io_tree, eb->start, eb->start + eb->len - 1,
                         0, &cached_state);
        if (extent_buffer_uptodate(eb) &&
            btrfs_header_generation(eb) == parent_transid) {
                ret = 0;
                goto out;
        }
        printk_ratelimited("parent transid verify failed on %llu wanted %llu "
                       "found %llu\n",
                       eb->start, parent_transid, btrfs_header_generation(eb));
        ret = 1;

        /*
         * Things reading via commit roots that don't have normal protection,
         * like send, can have a really old block in cache that may point at a
         * block that has been free'd and re-allocated.  So don't clear uptodate
         * if we find an eb that is under IO (dirty/writeback) because we could
         * end up reading in the stale data and then writing it back out and
         * making everybody very sad.
         */
        if (!extent_buffer_under_io(eb))
                clear_extent_buffer_uptodate(eb);
out:
        unlock_extent_cached(io_tree, eb->start, eb->start + eb->len - 1,
                             &cached_state, GFP_NOFS);
        btrfs_tree_read_unlock_blocking(eb);
        return ret;
}

/*
 * Return 0 if the superblock checksum type matches the checksum value of that
 * algorithm. Pass the raw disk superblock data.
 */
static int btrfs_check_super_csum(char *raw_disk_sb)
{
        struct btrfs_super_block *disk_sb =
                (struct btrfs_super_block *)raw_disk_sb;
        u16 csum_type = btrfs_super_csum_type(disk_sb);
        int ret = 0;

        if (csum_type == BTRFS_CSUM_TYPE_CRC32) {
                u32 crc = ~(u32)0;
                const int csum_size = sizeof(crc);
                char result[csum_size];

                /*
                 * The super_block structure does not span the whole
                 * BTRFS_SUPER_INFO_SIZE range, we expect that the unused space
                 * is filled with zeros and is included in the checkum.
                 */
                crc = btrfs_csum_data(raw_disk_sb + BTRFS_CSUM_SIZE,
                                crc, BTRFS_SUPER_INFO_SIZE - BTRFS_CSUM_SIZE);
                btrfs_csum_final(crc, result);

                if (memcmp(raw_disk_sb, result, csum_size))
                        ret = 1;

                if (ret && btrfs_super_generation(disk_sb) < 10) {
                        printk(KERN_WARNING
                                "BTRFS: super block crcs don't match, older mkfs detected\n");
                        ret = 0;
                }
        }

        if (csum_type >= ARRAY_SIZE(btrfs_csum_sizes)) {
                printk(KERN_ERR "BTRFS: unsupported checksum algorithm %u\n",
                                csum_type);
                ret = 1;
        }

        return ret;
}

/*
 * helper to read a given tree block, doing retries as required when
 * the checksums don't match and we have alternate mirrors to try.
 */
static int btree_read_extent_buffer_pages(struct btrfs_root *root,
                                          struct extent_buffer *eb,
                                          u64 start, u64 parent_transid)
{
        struct extent_io_tree *io_tree;
        int failed = 0;
        int ret;
        int num_copies = 0;
        int mirror_num = 0;
        int failed_mirror = 0;

        clear_bit(EXTENT_BUFFER_CORRUPT, &eb->bflags);
        io_tree = &BTRFS_I(root->fs_info->btree_inode)->io_tree;
        while (1) {
                ret = read_extent_buffer_pages(io_tree, eb, start,
                                               WAIT_COMPLETE,
                                               btree_get_extent, mirror_num);
                if (!ret) {
                        if (!verify_parent_transid(io_tree, eb,
                                                   parent_transid, 0))
                                break;
                        else
                                ret = -EIO;
                }

                /*
                 * This buffer's crc is fine, but its contents are corrupted, so
                 * there is no reason to read the other copies, they won't be
                 * any less wrong.
                 */
                if (test_bit(EXTENT_BUFFER_CORRUPT, &eb->bflags))
                        break;

                num_copies = btrfs_num_copies(root->fs_info,
                                              eb->start, eb->len);
                if (num_copies == 1)
                        break;

                if (!failed_mirror) {
                        failed = 1;
                        failed_mirror = eb->read_mirror;
                }

                mirror_num++;
                if (mirror_num == failed_mirror)
                        mirror_num++;

                if (mirror_num > num_copies)
                        break;
        }

        if (failed && !ret && failed_mirror)
                repair_eb_io_failure(root, eb, failed_mirror);

        return ret;
}

/*
 * checksum a dirty tree block before IO.  This has extra checks to make sure
 * we only fill in the checksum field in the first page of a multi-page block
 */

static int csum_dirty_buffer(struct btrfs_root *root, struct page *page)
{
        u64 start = page_offset(page);
        u64 found_start;
        struct extent_buffer *eb;

        eb = (struct extent_buffer *)page->private;
        if (page != eb->pages[0])
                return 0;
        found_start = btrfs_header_bytenr(eb);
        if (WARN_ON(found_start != start || !PageUptodate(page)))
                return 0;
        csum_tree_block(root, eb, 0);
        return 0;
}

static int check_tree_block_fsid(struct btrfs_root *root,
                                 struct extent_buffer *eb)
{
        struct btrfs_fs_devices *fs_devices = root->fs_info->fs_devices;
        u8 fsid[BTRFS_UUID_SIZE];
        int ret = 1;

        read_extent_buffer(eb, fsid, btrfs_header_fsid(), BTRFS_FSID_SIZE);
        while (fs_devices) {
                if (!memcmp(fsid, fs_devices->fsid, BTRFS_FSID_SIZE)) {
                        ret = 0;
                        break;
                }
                fs_devices = fs_devices->seed;
        }
        return ret;
}

#define CORRUPT(reason, eb, root, slot)                         \
        btrfs_crit(root->fs_info, "corrupt leaf, %s: block=%llu,"       \
                   "root=%llu, slot=%d", reason,                        \
               btrfs_header_bytenr(eb), root->objectid, slot)

static noinline int check_leaf(struct btrfs_root *root,
                               struct extent_buffer *leaf)
{
        struct btrfs_key key;
        struct btrfs_key leaf_key;
        u32 nritems = btrfs_header_nritems(leaf);
        int slot;

        if (nritems == 0)
                return 0;

        /* Check the 0 item */
        if (btrfs_item_offset_nr(leaf, 0) + btrfs_item_size_nr(leaf, 0) !=
            BTRFS_LEAF_DATA_SIZE(root)) {
                CORRUPT("invalid item offset size pair", leaf, root, 0);
                return -EIO;
        }

        /*
         * Check to make sure each items keys are in the correct order and their
         * offsets make sense.  We only have to loop through nritems-1 because
         * we check the current slot against the next slot, which verifies the
         * next slot's offset+size makes sense and that the current's slot
         * offset is correct.
         */
        for (slot = 0; slot < nritems - 1; slot++) {
                btrfs_item_key_to_cpu(leaf, &leaf_key, slot);
                btrfs_item_key_to_cpu(leaf, &key, slot + 1);

                /* Make sure the keys are in the right order */
                if (btrfs_comp_cpu_keys(&leaf_key, &key) >= 0) {
                        CORRUPT("bad key order", leaf, root, slot);
                        return -EIO;
                }

                /*
                 * Make sure the offset and ends are right, remember that the
                 * item data starts at the end of the leaf and grows towards the
                 * front.
                 */
                if (btrfs_item_offset_nr(leaf, slot) !=
                        btrfs_item_end_nr(leaf, slot + 1)) {
                        CORRUPT("slot offset bad", leaf, root, slot);
                        return -EIO;
                }

                /*
                 * Check to make sure that we don't point outside of the leaf,
                 * just incase all the items are consistent to eachother, but
                 * all point outside of the leaf.
                 */
                if (btrfs_item_end_nr(leaf, slot) >
                    BTRFS_LEAF_DATA_SIZE(root)) {
                        CORRUPT("slot end outside of leaf", leaf, root, slot);
                        return -EIO;
                }
        }

        return 0;
}

static int btree_readpage_end_io_hook(struct btrfs_io_bio *io_bio,
                                      u64 phy_offset, struct page *page,
                                      u64 start, u64 end, int mirror)
{
        u64 found_start;
        int found_level;
        struct extent_buffer *eb;
        struct btrfs_root *root = BTRFS_I(page->mapping->host)->root;
        int ret = 0;
        int reads_done;

        if (!page->private)
                goto out;

        eb = (struct extent_buffer *)page->private;

        /* the pending IO might have been the only thing that kept this buffer
         * in memory.  Make sure we have a ref for all this other checks
         */
        extent_buffer_get(eb);

        reads_done = atomic_dec_and_test(&eb->io_pages);
        if (!reads_done)
                goto err;

        eb->read_mirror = mirror;
        if (test_bit(EXTENT_BUFFER_IOERR, &eb->bflags)) {
                ret = -EIO;
                goto err;
        }

        found_start = btrfs_header_bytenr(eb);
        if (found_start != eb->start) {
                printk_ratelimited(KERN_INFO "BTRFS: bad tree block start "
                               "%llu %llu\n",
                               found_start, eb->start);
                ret = -EIO;
                goto err;
        }
        if (check_tree_block_fsid(root, eb)) {
                printk_ratelimited(KERN_INFO "BTRFS: bad fsid on block %llu\n",
                               eb->start);
                ret = -EIO;
                goto err;
        }
        found_level = btrfs_header_level(eb);
        if (found_level >= BTRFS_MAX_LEVEL) {
                btrfs_info(root->fs_info, "bad tree block level %d",
                           (int)btrfs_header_level(eb));
                ret = -EIO;
                goto err;
        }

        btrfs_set_buffer_lockdep_class(btrfs_header_owner(eb),
                                       eb, found_level);

        ret = csum_tree_block(root, eb, 1);
        if (ret) {
                ret = -EIO;
                goto err;
        }

        /*
         * If this is a leaf block and it is corrupt, set the corrupt bit so
         * that we don't try and read the other copies of this block, just
         * return -EIO.
         */
        if (found_level == 0 && check_leaf(root, eb)) {
                set_bit(EXTENT_BUFFER_CORRUPT, &eb->bflags);
                ret = -EIO;
        }

        if (!ret)
                set_extent_buffer_uptodate(eb);
err:
        if (reads_done &&
            test_and_clear_bit(EXTENT_BUFFER_READAHEAD, &eb->bflags))
                btree_readahead_hook(root, eb, eb->start, ret);

        if (ret) {
                /*
                 * our io error hook is going to dec the io pages
                 * again, we have to make sure it has something
                 * to decrement
                 */
                atomic_inc(&eb->io_pages);
                clear_extent_buffer_uptodate(eb);
        }
        free_extent_buffer(eb);
out:
        return ret;
}

static int btree_io_failed_hook(struct page *page, int failed_mirror)
{
        struct extent_buffer *eb;
        struct btrfs_root *root = BTRFS_I(page->mapping->host)->root;

        eb = (struct extent_buffer *)page->private;
        set_bit(EXTENT_BUFFER_IOERR, &eb->bflags);
        eb->read_mirror = failed_mirror;
        atomic_dec(&eb->io_pages);
        if (test_and_clear_bit(EXTENT_BUFFER_READAHEAD, &eb->bflags))
                btree_readahead_hook(root, eb, eb->start, -EIO);
        return -EIO;    /* we fixed nothing */
}

static void end_workqueue_bio(struct bio *bio, int err)
{
        struct end_io_wq *end_io_wq = bio->bi_private;
        struct btrfs_fs_info *fs_info;

        fs_info = end_io_wq->info;
        end_io_wq->error = err;
        btrfs_init_work(&end_io_wq->work, end_workqueue_fn, NULL, NULL);

        if (bio->bi_rw & REQ_WRITE) {
                if (end_io_wq->metadata == BTRFS_WQ_ENDIO_METADATA)
                        btrfs_queue_work(fs_info->endio_meta_write_workers,
                                         &end_io_wq->work);
                else if (end_io_wq->metadata == BTRFS_WQ_ENDIO_FREE_SPACE)
                        btrfs_queue_work(fs_info->endio_freespace_worker,
                                         &end_io_wq->work);
                else if (end_io_wq->metadata == BTRFS_WQ_ENDIO_RAID56)
                        btrfs_queue_work(fs_info->endio_raid56_workers,
                                         &end_io_wq->work);
                else
                        btrfs_queue_work(fs_info->endio_write_workers,
                                         &end_io_wq->work);
        } else {
                if (end_io_wq->metadata == BTRFS_WQ_ENDIO_RAID56)
                        btrfs_queue_work(fs_info->endio_raid56_workers,
                                         &end_io_wq->work);
                else if (end_io_wq->metadata)
                        btrfs_queue_work(fs_info->endio_meta_workers,
                                         &end_io_wq->work);
                else
                        btrfs_queue_work(fs_info->endio_workers,
                                         &end_io_wq->work);
        }
}

/*
 * For the metadata arg you want
 *
 * 0 - if data
 * 1 - if normal metadta
 * 2 - if writing to the free space cache area
 * 3 - raid parity work
 */
int btrfs_bio_wq_end_io(struct btrfs_fs_info *info, struct bio *bio,
                        int metadata)
{
        struct end_io_wq *end_io_wq;
        end_io_wq = kmalloc(sizeof(*end_io_wq), GFP_NOFS);
        if (!end_io_wq)
                return -ENOMEM;

        end_io_wq->private = bio->bi_private;
        end_io_wq->end_io = bio->bi_end_io;
        end_io_wq->info = info;
        end_io_wq->error = 0;
        end_io_wq->bio = bio;
        end_io_wq->metadata = metadata;

        bio->bi_private = end_io_wq;
        bio->bi_end_io = end_workqueue_bio;
        return 0;
}

unsigned long btrfs_async_submit_limit(struct btrfs_fs_info *info)
{
        unsigned long limit = min_t(unsigned long,
                                    info->thread_pool_size,
                                    info->fs_devices->open_devices);
        return 256 * limit;
}

static void run_one_async_start(struct btrfs_work *work)
{
        struct async_submit_bio *async;
        int ret;

        async = container_of(work, struct  async_submit_bio, work);
        ret = async->submit_bio_start(async->inode, async->rw, async->bio,
                                      async->mirror_num, async->bio_flags,
                                      async->bio_offset);
        if (ret)
                async->error = ret;
}

static void run_one_async_done(struct btrfs_work *work)
{
        struct btrfs_fs_info *fs_info;
        struct async_submit_bio *async;
        int limit;

        async = container_of(work, struct  async_submit_bio, work);
        fs_info = BTRFS_I(async->inode)->root->fs_info;

        limit = btrfs_async_submit_limit(fs_info);
        limit = limit * 2 / 3;

        if (atomic_dec_return(&fs_info->nr_async_submits) < limit &&
            waitqueue_active(&fs_info->async_submit_wait))
                wake_up(&fs_info->async_submit_wait);

        /* If an error occured we just want to clean up the bio and move on */
        if (async->error) {
                bio_endio(async->bio, async->error);
                return;
        }

        async->submit_bio_done(async->inode, async->rw, async->bio,
                               async->mirror_num, async->bio_flags,
                               async->bio_offset);
}

static void run_one_async_free(struct btrfs_work *work)
{
        struct async_submit_bio *async;

        async = container_of(work, struct  async_submit_bio, work);
        kfree(async);
}

int btrfs_wq_submit_bio(struct btrfs_fs_info *fs_info, struct inode *inode,
                        int rw, struct bio *bio, int mirror_num,
                        unsigned long bio_flags,
                        u64 bio_offset,
                        extent_submit_bio_hook_t *submit_bio_start,
                        extent_submit_bio_hook_t *submit_bio_done)
{
        struct async_submit_bio *async;

        async = kmalloc(sizeof(*async), GFP_NOFS);
        if (!async)
                return -ENOMEM;

        async->inode = inode;
        async->rw = rw;
        async->bio = bio;
        async->mirror_num = mirror_num;
        async->submit_bio_start = submit_bio_start;
        async->submit_bio_done = submit_bio_done;

        btrfs_init_work(&async->work, run_one_async_start,
                        run_one_async_done, run_one_async_free);

        async->bio_flags = bio_flags;
        async->bio_offset = bio_offset;

        async->error = 0;

        atomic_inc(&fs_info->nr_async_submits);

        if (rw & REQ_SYNC)
                btrfs_set_work_high_priority(&async->work);

        btrfs_queue_work(fs_info->workers, &async->work);

        while (atomic_read(&fs_info->async_submit_draining) &&
              atomic_read(&fs_info->nr_async_submits)) {
                wait_event(fs_info->async_submit_wait,
                           (atomic_read(&fs_info->nr_async_submits) == 0));
        }

        return 0;
}

static int btree_csum_one_bio(struct bio *bio)
{
        struct bio_vec *bvec;
        struct btrfs_root *root;
        int i, ret = 0;

        bio_for_each_segment_all(bvec, bio, i) {
                root = BTRFS_I(bvec->bv_page->mapping->host)->root;
                ret = csum_dirty_buffer(root, bvec->bv_page);
                if (ret)
                        break;
        }

        return ret;
}

static int __btree_submit_bio_start(struct inode *inode, int rw,
                                    struct bio *bio, int mirror_num,
                                    unsigned long bio_flags,
                                    u64 bio_offset)
{
        /*
         * when we're called for a write, we're already in the async
         * submission context.  Just jump into btrfs_map_bio
         */
        return btree_csum_one_bio(bio);
}

static int __btree_submit_bio_done(struct inode *inode, int rw, struct bio *bio,
                                 int mirror_num, unsigned long bio_flags,
                                 u64 bio_offset)
{
        int ret;

        /*
         * when we're called for a write, we're already in the async
         * submission context.  Just jump into btrfs_map_bio
         */
        ret = btrfs_map_bio(BTRFS_I(inode)->root, rw, bio, mirror_num, 1);
        if (ret)
                bio_endio(bio, ret);
        return ret;
}

static int check_async_write(struct inode *inode, unsigned long bio_flags)
{
        if (bio_flags & EXTENT_BIO_TREE_LOG)
                return 0;
#ifdef CONFIG_X86
        if (cpu_has_xmm4_2)
                return 0;
#endif
        return 1;
}

static int btree_submit_bio_hook(struct inode *inode, int rw, struct bio *bio,
                                 int mirror_num, unsigned long bio_flags,
                                 u64 bio_offset)
{
        int async = check_async_write(inode, bio_flags);
        int ret;

        if (!(rw & REQ_WRITE)) {
                /*
                 * called for a read, do the setup so that checksum validation
                 * can happen in the async kernel threads
                 */
                ret = btrfs_bio_wq_end_io(BTRFS_I(inode)->root->fs_info,
                                          bio, 1);
                if (ret)
                        goto out_w_error;
                ret = btrfs_map_bio(BTRFS_I(inode)->root, rw, bio,
                                    mirror_num, 0);
        } else if (!async) {
                ret = btree_csum_one_bio(bio);
                if (ret)
                        goto out_w_error;
                ret = btrfs_map_bio(BTRFS_I(inode)->root, rw, bio,
                                    mirror_num, 0);
        } else {
                /*
                 * kthread helpers are used to submit writes so that
                 * checksumming can happen in parallel across all CPUs
                 */
                ret = btrfs_wq_submit_bio(BTRFS_I(inode)->root->fs_info,
                                          inode, rw, bio, mirror_num, 0,
                                          bio_offset,
                                          __btree_submit_bio_start,
                                          __btree_submit_bio_done);
        }

        if (ret) {
out_w_error:
                bio_endio(bio, ret);
        }
        return ret;
}

#ifdef CONFIG_MIGRATION
static int btree_migratepage(struct address_space *mapping,
                        struct page *newpage, struct page *page,
                        enum migrate_mode mode)
{
        /*
         * we can't safely write a btree page from here,
         * we haven't done the locking hook
         */
        if (PageDirty(page))
                return -EAGAIN;
        /*
         * Buffers may be managed in a filesystem specific way.
         * We must have no buffers or drop them.
         */
        if (page_has_private(page) &&
            !try_to_release_page(page, GFP_KERNEL))
                return -EAGAIN;
        return migrate_page(mapping, newpage, page, mode);
}
#endif


static int btree_writepages(struct address_space *mapping,
                            struct writeback_control *wbc)
{
        struct btrfs_fs_info *fs_info;
        int ret;

        if (wbc->sync_mode == WB_SYNC_NONE) {

                if (wbc->for_kupdate)
                        return 0;

                fs_info = BTRFS_I(mapping->host)->root->fs_info;
                /* this is a bit racy, but that's ok */
                ret = percpu_counter_compare(&fs_info->dirty_metadata_bytes,
                                             BTRFS_DIRTY_METADATA_THRESH);
                if (ret < 0)
                        return 0;
        }
        return btree_write_cache_pages(mapping, wbc);
}

static int btree_readpage(struct file *file, struct page *page)
{
        struct extent_io_tree *tree;
        tree = &BTRFS_I(page->mapping->host)->io_tree;

        return extent_read_full_page(tree, page, btree_get_extent, 0);
}

static int btree_releasepage(struct page *page, gfp_t gfp_flags)
{
        if (PageWriteback(page) || PageDirty(page))
                return 0;

        return try_release_extent_buffer(page);
}

static void btree_invalidatepage(struct page *page, unsigned int offset,
                                 unsigned int length)
{
        struct extent_io_tree *tree;
        tree = &BTRFS_I(page->mapping->host)->io_tree;
        extent_invalidatepage(tree, page, offset);
        btree_releasepage(page, GFP_NOFS);
        if (PagePrivate(page)) {
                btrfs_warn(BTRFS_I(page->mapping->host)->root->fs_info,
                           "page private not zero on page %llu",
                           (unsigned long long)page_offset(page));
                ClearPagePrivate(page);
                set_page_private(page, 0);
                page_cache_release(page);
        }
}

static int btree_set_page_dirty(struct page *page)
{
#ifdef DEBUG
        struct extent_buffer *eb;

        BUG_ON(!PagePrivate(page));
        eb = (struct extent_buffer *)page->private;
        BUG_ON(!eb);
        BUG_ON(!test_bit(EXTENT_BUFFER_DIRTY, &eb->bflags));
        BUG_ON(!atomic_read(&eb->refs));
        btrfs_assert_tree_locked(eb);
#endif
        return __set_page_dirty_nobuffers(page);
}

static const struct address_space_operations btree_aops = {
        .readpage       = btree_readpage,
        .writepages     = btree_writepages,
        .releasepage    = btree_releasepage,
        .invalidatepage = btree_invalidatepage,
#ifdef CONFIG_MIGRATION
        .migratepage    = btree_migratepage,
#endif
        .set_page_dirty = btree_set_page_dirty,
};

int readahead_tree_block(struct btrfs_root *root, u64 bytenr, u32 blocksize,
                         u64 parent_transid)
{
        struct extent_buffer *buf = NULL;
        struct inode *btree_inode = root->fs_info->btree_inode;
        int ret = 0;

        buf = btrfs_find_create_tree_block(root, bytenr, blocksize);
        if (!buf)
                return 0;
        read_extent_buffer_pages(&BTRFS_I(btree_inode)->io_tree,
                                 buf, 0, WAIT_NONE, btree_get_extent, 0);
        free_extent_buffer(buf);
        return ret;
}

int reada_tree_block_flagged(struct btrfs_root *root, u64 bytenr, u32 blocksize,
                         int mirror_num, struct extent_buffer **eb)
{
        struct extent_buffer *buf = NULL;
        struct inode *btree_inode = root->fs_info->btree_inode;
        struct extent_io_tree *io_tree = &BTRFS_I(btree_inode)->io_tree;
        int ret;

        buf = btrfs_find_create_tree_block(root, bytenr, blocksize);
        if (!buf)
                return 0;

        set_bit(EXTENT_BUFFER_READAHEAD, &buf->bflags);

        ret = read_extent_buffer_pages(io_tree, buf, 0, WAIT_PAGE_LOCK,
                                       btree_get_extent, mirror_num);
        if (ret) {
                free_extent_buffer(buf);
                return ret;
        }

        if (test_bit(EXTENT_BUFFER_CORRUPT, &buf->bflags)) {
                free_extent_buffer(buf);
                return -EIO;
        } else if (extent_buffer_uptodate(buf)) {
                *eb = buf;
        } else {
                free_extent_buffer(buf);
        }
        return 0;
}

struct extent_buffer *btrfs_find_tree_block(struct btrfs_root *root,
                                            u64 bytenr, u32 blocksize)
{
        return find_extent_buffer(root->fs_info, bytenr);
}

struct extent_buffer *btrfs_find_create_tree_block(struct btrfs_root *root,
                                                 u64 bytenr, u32 blocksize)
{
        return alloc_extent_buffer(root->fs_info, bytenr, blocksize);
}


int btrfs_write_tree_block(struct extent_buffer *buf)
{
        return filemap_fdatawrite_range(buf->pages[0]->mapping, buf->start,
                                        buf->start + buf->len - 1);
}

int btrfs_wait_tree_block_writeback(struct extent_buffer *buf)
{
        return filemap_fdatawait_range(buf->pages[0]->mapping,
                                       buf->start, buf->start + buf->len - 1);
}

struct extent_buffer *read_tree_block(struct btrfs_root *root, u64 bytenr,
                                      u32 blocksize, u64 parent_transid)
{
        struct extent_buffer *buf = NULL;
        int ret;

        buf = btrfs_find_create_tree_block(root, bytenr, blocksize);
        if (!buf)
                return NULL;

        ret = btree_read_extent_buffer_pages(root, buf, 0, parent_transid);
        if (ret) {
                free_extent_buffer(buf);
                return NULL;
        }
        return buf;

}

void clean_tree_block(struct btrfs_trans_handle *trans, struct btrfs_root *root,
                      struct extent_buffer *buf)
{
        struct btrfs_fs_info *fs_info = root->fs_info;

        if (btrfs_header_generation(buf) ==
            fs_info->running_transaction->transid) {
                btrfs_assert_tree_locked(buf);

                if (test_and_clear_bit(EXTENT_BUFFER_DIRTY, &buf->bflags)) {
                        __percpu_counter_add(&fs_info->dirty_metadata_bytes,
                                             -buf->len,
                                             fs_info->dirty_metadata_batch);
                        /* ugh, clear_extent_buffer_dirty needs to lock the page */
                        btrfs_set_lock_blocking(buf);
                        clear_extent_buffer_dirty(buf);
                }
        }
}

static struct btrfs_subvolume_writers *btrfs_alloc_subvolume_writers(void)
{
        struct btrfs_subvolume_writers *writers;
        int ret;

        writers = kmalloc(sizeof(*writers), GFP_NOFS);
        if (!writers)
                return ERR_PTR(-ENOMEM);

        ret = percpu_counter_init(&writers->counter, 0);
        if (ret < 0) {
                kfree(writers);
                return ERR_PTR(ret);
        }

        init_waitqueue_head(&writers->wait);
        return writers;
}

static void
btrfs_free_subvolume_writers(struct btrfs_subvolume_writers *writers)
{
        percpu_counter_destroy(&writers->counter);
        kfree(writers);
}

static void __setup_root(u32 nodesize, u32 leafsize, u32 sectorsize,
                         u32 stripesize, struct btrfs_root *root,
                         struct btrfs_fs_info *fs_info,
                         u64 objectid)
{
        root->node = NULL;
        root->commit_root = NULL;
        root->sectorsize = sectorsize;
        root->nodesize = nodesize;
        root->leafsize = leafsize;
        root->stripesize = stripesize;
        root->ref_cows = 0;
        root->track_dirty = 0;
        root->in_radix = 0;
        root->orphan_item_inserted = 0;
        root->orphan_cleanup_state = 0;

        root->objectid = objectid;
        root->last_trans = 0;
        root->highest_objectid = 0;
        root->nr_delalloc_inodes = 0;
        root->nr_ordered_extents = 0;
        root->name = NULL;
        root->inode_tree = RB_ROOT;
        INIT_RADIX_TREE(&root->delayed_nodes_tree, GFP_ATOMIC);
        root->block_rsv = NULL;
        root->orphan_block_rsv = NULL;

        INIT_LIST_HEAD(&root->dirty_list);
        INIT_LIST_HEAD(&root->root_list);
        INIT_LIST_HEAD(&root->delalloc_inodes);
        INIT_LIST_HEAD(&root->delalloc_root);
        INIT_LIST_HEAD(&root->ordered_extents);
        INIT_LIST_HEAD(&root->ordered_root);
        INIT_LIST_HEAD(&root->logged_list[0]);
        INIT_LIST_HEAD(&root->logged_list[1]);
        spin_lock_init(&root->orphan_lock);
        spin_lock_init(&root->inode_lock);
        spin_lock_init(&root->delalloc_lock);
        spin_lock_init(&root->ordered_extent_lock);
        spin_lock_init(&root->accounting_lock);
        spin_lock_init(&root->log_extents_lock[0]);
        spin_lock_init(&root->log_extents_lock[1]);
        mutex_init(&root->objectid_mutex);
        mutex_init(&root->log_mutex);
        mutex_init(&root->ordered_extent_mutex);
        mutex_init(&root->delalloc_mutex);
        init_waitqueue_head(&root->log_writer_wait);
        init_waitqueue_head(&root->log_commit_wait[0]);
        init_waitqueue_head(&root->log_commit_wait[1]);
        INIT_LIST_HEAD(&root->log_ctxs[0]);
        INIT_LIST_HEAD(&root->log_ctxs[1]);
        atomic_set(&root->log_commit[0], 0);
        atomic_set(&root->log_commit[1], 0);
        atomic_set(&root->log_writers, 0);
        atomic_set(&root->log_batch, 0);
        atomic_set(&root->orphan_inodes, 0);
        atomic_set(&root->refs, 1);
        atomic_set(&root->will_be_snapshoted, 0);
        root->log_transid = 0;
        root->log_transid_committed = -1;
        root->last_log_commit = 0;
        if (fs_info)
                extent_io_tree_init(&root->dirty_log_pages,
                                     fs_info->btree_inode->i_mapping);

        memset(&root->root_key, 0, sizeof(root->root_key));
        memset(&root->root_item, 0, sizeof(root->root_item));
        memset(&root->defrag_progress, 0, sizeof(root->defrag_progress));
        memset(&root->root_kobj, 0, sizeof(root->root_kobj));
        if (fs_info)
                root->defrag_trans_start = fs_info->generation;
        else
                root->defrag_trans_start = 0;
        init_completion(&root->kobj_unregister);
        root->defrag_running = 0;
        root->root_key.objectid = objectid;
        root->anon_dev = 0;

        spin_lock_init(&root->root_item_lock);
}

static struct btrfs_root *btrfs_alloc_root(struct btrfs_fs_info *fs_info)
{
        struct btrfs_root *root = kzalloc(sizeof(*root), GFP_NOFS);
        if (root)
                root->fs_info = fs_info;
        return root;
}

#ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS
/* Should only be used by the testing infrastructure */
struct btrfs_root *btrfs_alloc_dummy_root(void)
{
        struct btrfs_root *root;

        root = btrfs_alloc_root(NULL);
        if (!root)
                return ERR_PTR(-ENOMEM);
        __setup_root(4096, 4096, 4096, 4096, root, NULL, 1);
        root->dummy_root = 1;

        return root;
}
#endif

struct btrfs_root *btrfs_create_tree(struct btrfs_trans_handle *trans,
                                     struct btrfs_fs_info *fs_info,
                                     u64 objectid)
{
        struct extent_buffer *leaf;
        struct btrfs_root *tree_root = fs_info->tree_root;
        struct btrfs_root *root;
        struct btrfs_key key;
        int ret = 0;
        uuid_le uuid;

        root = btrfs_alloc_root(fs_info);
        if (!root)
                return ERR_PTR(-ENOMEM);

        __setup_root(tree_root->nodesize, tree_root->leafsize,
                     tree_root->sectorsize, tree_root->stripesize,
                     root, fs_info, objectid);
        root->root_key.objectid = objectid;
        root->root_key.type = BTRFS_ROOT_ITEM_KEY;
        root->root_key.offset = 0;

        leaf = btrfs_alloc_free_block(trans, root, root->leafsize,
                                      0, objectid, NULL, 0, 0, 0);
        if (IS_ERR(leaf)) {
                ret = PTR_ERR(leaf);
                leaf = NULL;
                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);
        root->node = leaf;

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

        root->commit_root = btrfs_root_node(root);
        root->track_dirty = 1;


        root->root_item.flags = 0;
        root->root_item.byte_limit = 0;
        btrfs_set_root_bytenr(&root->root_item, leaf->start);
        btrfs_set_root_generation(&root->root_item, trans->transid);
        btrfs_set_root_level(&root->root_item, 0);
        btrfs_set_root_refs(&root->root_item, 1);
        btrfs_set_root_used(&root->root_item, leaf->len);
        btrfs_set_root_last_snapshot(&root->root_item, 0);
        btrfs_set_root_dirid(&root->root_item, 0);
        uuid_le_gen(&uuid);
        memcpy(root->root_item.uuid, uuid.b, BTRFS_UUID_SIZE);
        root->root_item.drop_level = 0;

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

        btrfs_tree_unlock(leaf);

        return root;

fail:
        if (leaf) {
                btrfs_tree_unlock(leaf);
                free_extent_buffer(leaf);
        }
        kfree(root);

        return ERR_PTR(ret);
}

static struct btrfs_root *alloc_log_tree(struct btrfs_trans_handle *trans,
                                         struct btrfs_fs_info *fs_info)
{
        struct btrfs_root *root;
        struct btrfs_root *tree_root = fs_info->tree_root;
        struct extent_buffer *leaf;

        root = btrfs_alloc_root(fs_info);
        if (!root)
                return ERR_PTR(-ENOMEM);

        __setup_root(tree_root->nodesize, tree_root->leafsize,
                     tree_root->sectorsize, tree_root->stripesize,
                     root, fs_info, BTRFS_TREE_LOG_OBJECTID);

        root->root_key.objectid = BTRFS_TREE_LOG_OBJECTID;
        root->root_key.type = BTRFS_ROOT_ITEM_KEY;
        root->root_key.offset = BTRFS_TREE_LOG_OBJECTID;
        /*
         * log trees do not get reference counted because they go away
         * before a real commit is actually done.  They do store pointers
         * to file data extents, and those reference counts still get
         * updated (along with back refs to the log tree).
         */
        root->ref_cows = 0;

        leaf = btrfs_alloc_free_block(trans, root, root->leafsize, 0,
                                      BTRFS_TREE_LOG_OBJECTID, NULL,
                                      0, 0, 0);
        if (IS_ERR(leaf)) {
                kfree(root);
                return ERR_CAST(leaf);
        }

        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, BTRFS_TREE_LOG_OBJECTID);
        root->node = leaf;

        write_extent_buffer(root->node, root->fs_info->fsid,
                            btrfs_header_fsid(), BTRFS_FSID_SIZE);
        btrfs_mark_buffer_dirty(root->node);
        btrfs_tree_unlock(root->node);
        return root;
}

int btrfs_init_log_root_tree(struct btrfs_trans_handle *trans,
                             struct btrfs_fs_info *fs_info)
{
        struct btrfs_root *log_root;

        log_root = alloc_log_tree(trans, fs_info);
        if (IS_ERR(log_root))
                return PTR_ERR(log_root);
        WARN_ON(fs_info->log_root_tree);
        fs_info->log_root_tree = log_root;
        return 0;
}

int btrfs_add_log_tree(struct btrfs_trans_handle *trans,
                       struct btrfs_root *root)
{
        struct btrfs_root *log_root;
        struct btrfs_inode_item *inode_item;

        log_root = alloc_log_tree(trans, root->fs_info);
        if (IS_ERR(log_root))
                return PTR_ERR(log_root);

        log_root->last_trans = trans->transid;
        log_root->root_key.offset = root->root_key.objectid;

        inode_item = &log_root->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->leafsize);
        btrfs_set_stack_inode_mode(inode_item, S_IFDIR | 0755);

        btrfs_set_root_node(&log_root->root_item, log_root->node);

        WARN_ON(root->log_root);
        root->log_root = log_root;
        root->log_transid = 0;
        root->log_transid_committed = -1;
        root->last_log_commit = 0;
        return 0;
}

static struct btrfs_root *btrfs_read_tree_root(struct btrfs_root *tree_root,
                                               struct btrfs_key *key)
{
        struct btrfs_root *root;
        struct btrfs_fs_info *fs_info = tree_root->fs_info;
        struct btrfs_path *path;
        u64 generation;
        u32 blocksize;
        int ret;

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

        root = btrfs_alloc_root(fs_info);
        if (!root) {
                ret = -ENOMEM;
                goto alloc_fail;
        }

        __setup_root(tree_root->nodesize, tree_root->leafsize,
                     tree_root->sectorsize, tree_root->stripesize,
                     root, fs_info, key->objectid);

        ret = btrfs_find_root(tree_root, key, path,
                              &root->root_item, &root->root_key);
        if (ret) {
                if (ret > 0)
                        ret = -ENOENT;
                goto find_fail;
        }

        generation = btrfs_root_generation(&root->root_item);
        blocksize = btrfs_level_size(root, btrfs_root_level(&root->root_item));
        root->node = read_tree_block(root, btrfs_root_bytenr(&root->root_item),
                                     blocksize, generation);
        if (!root->node) {
                ret = -ENOMEM;
                goto find_fail;
        } else if (!btrfs_buffer_uptodate(root->node, generation, 0)) {
                ret = -EIO;
                goto read_fail;
        }
        root->commit_root = btrfs_root_node(root);
out:
        btrfs_free_path(path);
        return root;

read_fail:
        free_extent_buffer(root->node);
find_fail:
        kfree(root);
alloc_fail:
        root = ERR_PTR(ret);
        goto out;
}

struct btrfs_root *btrfs_read_fs_root(struct btrfs_root *tree_root,
                                      struct btrfs_key *location)
{
        struct btrfs_root *root;

        root = btrfs_read_tree_root(tree_root, location);
        if (IS_ERR(root))
                return root;

        if (root->root_key.objectid != BTRFS_TREE_LOG_OBJECTID) {
                root->ref_cows = 1;
                btrfs_check_and_init_root_item(&root->root_item);
        }

        return root;
}

int btrfs_init_fs_root(struct btrfs_root *root)
{
        int ret;
        struct btrfs_subvolume_writers *writers;

        root->free_ino_ctl = kzalloc(sizeof(*root->free_ino_ctl), GFP_NOFS);
        root->free_ino_pinned = kzalloc(sizeof(*root->free_ino_pinned),
                                        GFP_NOFS);
        if (!root->free_ino_pinned || !root->free_ino_ctl) {
                ret = -ENOMEM;
                goto fail;
        }

        writers = btrfs_alloc_subvolume_writers();
        if (IS_ERR(writers)) {
                ret = PTR_ERR(writers);
                goto fail;
        }
        root->subv_writers = writers;

        btrfs_init_free_ino_ctl(root);
        spin_lock_init(&root->cache_lock);
        init_waitqueue_head(&root->cache_wait);

        ret = get_anon_bdev(&root->anon_dev);
        if (ret)
                goto free_writers;
        return 0;

free_writers:
        btrfs_free_subvolume_writers(root->subv_writers);
fail:
        kfree(root->free_ino_ctl);
        kfree(root->free_ino_pinned);
        return ret;
}

static struct btrfs_root *btrfs_lookup_fs_root(struct btrfs_fs_info *fs_info,
                                               u64 root_id)
{
        struct btrfs_root *root;

        spin_lock(&fs_info->fs_roots_radix_lock);
        root = radix_tree_lookup(&fs_info->fs_roots_radix,
                                 (unsigned long)root_id);
        spin_unlock(&fs_info->fs_roots_radix_lock);
        return root;
}

int btrfs_insert_fs_root(struct btrfs_fs_info *fs_info,
                         struct btrfs_root *root)
{
        int ret;

        ret = radix_tree_preload(GFP_NOFS & ~__GFP_HIGHMEM);
        if (ret)
                return ret;

        spin_lock(&fs_info->fs_roots_radix_lock);
        ret = radix_tree_insert(&fs_info->fs_roots_radix,
                                (unsigned long)root->root_key.objectid,
                                root);
        if (ret == 0)
                root->in_radix = 1;
        spin_unlock(&fs_info->fs_roots_radix_lock);
        radix_tree_preload_end();

        return ret;
}

struct btrfs_root *btrfs_get_fs_root(struct btrfs_fs_info *fs_info,
                                     struct btrfs_key *location,
                                     bool check_ref)
{
        struct btrfs_root *root;
        int ret;

        if (location->objectid == BTRFS_ROOT_TREE_OBJECTID)
                return fs_info->tree_root;
        if (location->objectid == BTRFS_EXTENT_TREE_OBJECTID)
                return fs_info->extent_root;
        if (location->objectid == BTRFS_CHUNK_TREE_OBJECTID)
                return fs_info->chunk_root;
        if (location->objectid == BTRFS_DEV_TREE_OBJECTID)
                return fs_info->dev_root;
        if (location->objectid == BTRFS_CSUM_TREE_OBJECTID)
                return fs_info->csum_root;
        if (location->objectid == BTRFS_QUOTA_TREE_OBJECTID)
                return fs_info->quota_root ? fs_info->quota_root :
                                             ERR_PTR(-ENOENT);
        if (location->objectid == BTRFS_UUID_TREE_OBJECTID)
                return fs_info->uuid_root ? fs_info->uuid_root :
                                            ERR_PTR(-ENOENT);
again:
        root = btrfs_lookup_fs_root(fs_info, location->objectid);
        if (root) {
                if (check_ref && btrfs_root_refs(&root->root_item) == 0)
                        return ERR_PTR(-ENOENT);
                return root;
        }

        root = btrfs_read_fs_root(fs_info->tree_root, location);
        if (IS_ERR(root))
                return root;

        if (check_ref && btrfs_root_refs(&root->root_item) == 0) {
                ret = -ENOENT;
                goto fail;
        }

        ret = btrfs_init_fs_root(root);
        if (ret)
                goto fail;

        ret = btrfs_find_item(fs_info->tree_root, NULL, BTRFS_ORPHAN_OBJECTID,
                        location->objectid, BTRFS_ORPHAN_ITEM_KEY, NULL);
        if (ret < 0)
                goto fail;
        if (ret == 0)
                root->orphan_item_inserted = 1;

        ret = btrfs_insert_fs_root(fs_info, root);
        if (ret) {
                if (ret == -EEXIST) {
                        free_fs_root(root);
                        goto again;
                }
                goto fail;
        }
        return root;
fail:
        free_fs_root(root);
        return ERR_PTR(ret);
}

static int btrfs_congested_fn(void *congested_data, int bdi_bits)
{
        struct btrfs_fs_info *info = (struct btrfs_fs_info *)congested_data;
        int ret = 0;
        struct btrfs_device *device;
        struct backing_dev_info *bdi;

        rcu_read_lock();
        list_for_each_entry_rcu(device, &info->fs_devices->devices, dev_list) {
                if (!device->bdev)
                        continue;
                bdi = blk_get_backing_dev_info(device->bdev);
                if (bdi && bdi_congested(bdi, bdi_bits)) {
                        ret = 1;
                        break;
                }
        }
        rcu_read_unlock();
        return ret;
}

/*
 * If this fails, caller must call bdi_destroy() to get rid of the
 * bdi again.
 */
static int setup_bdi(struct btrfs_fs_info *info, struct backing_dev_info *bdi)
{
        int err;

        bdi->capabilities = BDI_CAP_MAP_COPY;
        err = bdi_setup_and_register(bdi, "btrfs", BDI_CAP_MAP_COPY);
        if (err)
                return err;

        bdi->ra_pages   = default_backing_dev_info.ra_pages;
        bdi->congested_fn       = btrfs_congested_fn;
        bdi->congested_data     = info;
        return 0;
}

/*
 * called by the kthread helper functions to finally call the bio end_io
 * functions.  This is where read checksum verification actually happens
 */
static void end_workqueue_fn(struct btrfs_work *work)
{
        struct bio *bio;
        struct end_io_wq *end_io_wq;
        int error;

        end_io_wq = container_of(work, struct end_io_wq, work);
        bio = end_io_wq->bio;

        error = end_io_wq->error;
        bio->bi_private = end_io_wq->private;
        bio->bi_end_io = end_io_wq->end_io;
        kfree(end_io_wq);
        bio_endio_nodec(bio, error);
}

static int cleaner_kthread(void *arg)
{
        struct btrfs_root *root = arg;
        int again;

        do {
                again = 0;

                /* Make the cleaner go to sleep early. */
                if (btrfs_need_cleaner_sleep(root))
                        goto sleep;

                if (!mutex_trylock(&root->fs_info->cleaner_mutex))
                        goto sleep;

                /*
                 * Avoid the problem that we change the status of the fs
                 * during the above check and trylock.
                 */
                if (btrfs_need_cleaner_sleep(root)) {
                        mutex_unlock(&root->fs_info->cleaner_mutex);
                        goto sleep;
                }

                btrfs_run_delayed_iputs(root);
                again = btrfs_clean_one_deleted_snapshot(root);
                mutex_unlock(&root->fs_info->cleaner_mutex);

                /*
                 * The defragger has dealt with the R/O remount and umount,
                 * needn't do anything special here.
                 */
                btrfs_run_defrag_inodes(root->fs_info);
sleep:
                if (!try_to_freeze() && !again) {
                        set_current_state(TASK_INTERRUPTIBLE);
                        if (!kthread_should_stop())
                                schedule();
                        __set_current_state(TASK_RUNNING);
                }
        } while (!kthread_should_stop());
        return 0;
}

static int transaction_kthread(void *arg)
{
        struct btrfs_root *root = arg;
        struct btrfs_trans_handle *trans;
        struct btrfs_transaction *cur;
        u64 transid;
        unsigned long now;
        unsigned long delay;
        bool cannot_commit;

        do {
                cannot_commit = false;
                delay = HZ * root->fs_info->commit_interval;
                mutex_lock(&root->fs_info->transaction_kthread_mutex);

                spin_lock(&root->fs_info->trans_lock);
                cur = root->fs_info->running_transaction;
                if (!cur) {
                        spin_unlock(&root->fs_info->trans_lock);
                        goto sleep;
                }

                now = get_seconds();
                if (cur->state < TRANS_STATE_BLOCKED &&
                    (now < cur->start_time ||
                     now - cur->start_time < root->fs_info->commit_interval)) {
                        spin_unlock(&root->fs_info->trans_lock);
                        delay = HZ * 5;
                        goto sleep;
                }
                transid = cur->transid;
                spin_unlock(&root->fs_info->trans_lock);

                /* If the file system is aborted, this will always fail. */
                trans = btrfs_attach_transaction(root);
                if (IS_ERR(trans)) {
                        if (PTR_ERR(trans) != -ENOENT)
                                cannot_commit = true;
                        goto sleep;
                }
                if (transid == trans->transid) {
                        btrfs_commit_transaction(trans, root);
                } else {
                        btrfs_end_transaction(trans, root);
                }
sleep:
                wake_up_process(root->fs_info->cleaner_kthread);
                mutex_unlock(&root->fs_info->transaction_kthread_mutex);

                if (unlikely(test_bit(BTRFS_FS_STATE_ERROR,
                                      &root->fs_info->fs_state)))
                        btrfs_cleanup_transaction(root);
                if (!try_to_freeze()) {
                        set_current_state(TASK_INTERRUPTIBLE);
                        if (!kthread_should_stop() &&
                            (!btrfs_transaction_blocked(root->fs_info) ||
                             cannot_commit))
                                schedule_timeout(delay);
                        __set_current_state(TASK_RUNNING);
                }
        } while (!kthread_should_stop());
        return 0;
}

/*
 * this will find the highest generation in the array of
 * root backups.  The index of the highest array is returned,
 * or -1 if we can't find anything.
 *
 * We check to make sure the array is valid by comparing the
 * generation of the latest  root in the array with the generation
 * in the super block.  If they don't match we pitch it.
 */
static int find_newest_super_backup(struct btrfs_fs_info *info, u64 newest_gen)
{
        u64 cur;
        int newest_index = -1;
        struct btrfs_root_backup *root_backup;
        int i;

        for (i = 0; i < BTRFS_NUM_BACKUP_ROOTS; i++) {
                root_backup = info->super_copy->super_roots + i;
                cur = btrfs_backup_tree_root_gen(root_backup);
                if (cur == newest_gen)
                        newest_index = i;
        }

        /* check to see if we actually wrapped around */
        if (newest_index == BTRFS_NUM_BACKUP_ROOTS - 1) {
                root_backup = info->super_copy->super_roots;
                cur = btrfs_backup_tree_root_gen(root_backup);
                if (cur == newest_gen)
                        newest_index = 0;
        }
        return newest_index;
}


/*
 * find the oldest backup so we know where to store new entries
 * in the backup array.  This will set the backup_root_index
 * field in the fs_info struct
 */
static void find_oldest_super_backup(struct btrfs_fs_info *info,
                                     u64 newest_gen)
{
        int newest_index = -1;

        newest_index = find_newest_super_backup(info, newest_gen);
        /* if there was garbage in there, just move along */
        if (newest_index == -1) {
                info->backup_root_index = 0;
        } else {
                info->backup_root_index = (newest_index + 1) % BTRFS_NUM_BACKUP_ROOTS;
        }
}

/*
 * copy all the root pointers into the super backup array.
 * this will bump the backup pointer by one when it is
 * done
 */
static void backup_super_roots(struct btrfs_fs_info *info)
{
        int next_backup;
        struct btrfs_root_backup *root_backup;
        int last_backup;

        next_backup = info->backup_root_index;
        last_backup = (next_backup + BTRFS_NUM_BACKUP_ROOTS - 1) %
                BTRFS_NUM_BACKUP_ROOTS;

        /*
         * just overwrite the last backup if we're at the same generation
         * this happens only at umount
         */
        root_backup = info->super_for_commit->super_roots + last_backup;
        if (btrfs_backup_tree_root_gen(root_backup) ==
            btrfs_header_generation(info->tree_root->node))
                next_backup = last_backup;

        root_backup = info->super_for_commit->super_roots + next_backup;

        /*
         * make sure all of our padding and empty slots get zero filled
         * regardless of which ones we use today
         */
        memset(root_backup, 0, sizeof(*root_backup));

        info->backup_root_index = (next_backup + 1) % BTRFS_NUM_BACKUP_ROOTS;

        btrfs_set_backup_tree_root(root_backup, info->tree_root->node->start);
        btrfs_set_backup_tree_root_gen(root_backup,
                               btrfs_header_generation(info->tree_root->node));

        btrfs_set_backup_tree_root_level(root_backup,
                               btrfs_header_level(info->tree_root->node));

        btrfs_set_backup_chunk_root(root_backup, info->chunk_root->node->start);
        btrfs_set_backup_chunk_root_gen(root_backup,
                               btrfs_header_generation(info->chunk_root->node));
        btrfs_set_backup_chunk_root_level(root_backup,
                               btrfs_header_level(info->chunk_root->node));

        btrfs_set_backup_extent_root(root_backup, info->extent_root->node->start);
        btrfs_set_backup_extent_root_gen(root_backup,
                               btrfs_header_generation(info->extent_root->node));
        btrfs_set_backup_extent_root_level(root_backup,
                               btrfs_header_level(info->extent_root->node));

        /*
         * we might commit during log recovery, which happens before we set
         * the fs_root.  Make sure it is valid before we fill it in.
         */
        if (info->fs_root && info->fs_root->node) {
                btrfs_set_backup_fs_root(root_backup,
                                         info->fs_root->node->start);
                btrfs_set_backup_fs_root_gen(root_backup,
                               btrfs_header_generation(info->fs_root->node));
                btrfs_set_backup_fs_root_level(root_backup,
                               btrfs_header_level(info->fs_root->node));
        }

        btrfs_set_backup_dev_root(root_backup, info->dev_root->node->start);
        btrfs_set_backup_dev_root_gen(root_backup,
                               btrfs_header_generation(info->dev_root->node));
        btrfs_set_backup_dev_root_level(root_backup,
                                       btrfs_header_level(info->dev_root->node));

        btrfs_set_backup_csum_root(root_backup, info->csum_root->node->start);
        btrfs_set_backup_csum_root_gen(root_backup,
                               btrfs_header_generation(info->csum_root->node));
        btrfs_set_backup_csum_root_level(root_backup,
                               btrfs_header_level(info->csum_root->node));

        btrfs_set_backup_total_bytes(root_backup,
                             btrfs_super_total_bytes(info->super_copy));
        btrfs_set_backup_bytes_used(root_backup,
                             btrfs_super_bytes_used(info->super_copy));
        btrfs_set_backup_num_devices(root_backup,
                             btrfs_super_num_devices(info->super_copy));

        /*
         * if we don't copy this out to the super_copy, it won't get remembered
         * for the next commit
         */
        memcpy(&info->super_copy->super_roots,
               &info->super_for_commit->super_roots,
               sizeof(*root_backup) * BTRFS_NUM_BACKUP_ROOTS);
}

/*
 * this copies info out of the root backup array and back into
 * the in-memory super block.  It is meant to help iterate through
 * the array, so you send it the number of backups you've already
 * tried and the last backup index you used.

 *
 * this returns -1 when it has tried all the backups
 */
static noinline int next_root_backup(struct btrfs_fs_info *info,
                                     struct btrfs_super_block *super,
                                     int *num_backups_tried, int *backup_index)
{
        struct btrfs_root_backup *root_backup;
        int newest = *backup_index;

        if (*num_backups_tried == 0) {
                u64 gen = btrfs_super_generation(super);

                newest = find_newest_super_backup(info, gen);
                if (newest == -1)
                        return -1;

                *backup_index = newest;
                *num_backups_tried = 1;
        } else if (*num_backups_tried == BTRFS_NUM_BACKUP_ROOTS) {
                /* we've tried all the backups, all done */
                return -1;
        } else {
                /* jump to the next oldest backup */
                newest = (*backup_index + BTRFS_NUM_BACKUP_ROOTS - 1) %
                        BTRFS_NUM_BACKUP_ROOTS;
                *backup_index = newest;
                *num_backups_tried += 1;
        }
        root_backup = super->super_roots + newest;

        btrfs_set_super_generation(super,
                                   btrfs_backup_tree_root_gen(root_backup));
        btrfs_set_super_root(super, btrfs_backup_tree_root(root_backup));
        btrfs_set_super_root_level(super,
                                   btrfs_backup_tree_root_level(root_backup));
        btrfs_set_super_bytes_used(super, btrfs_backup_bytes_used(root_backup));

        /*
         * fixme: the total bytes and num_devices need to match or we should
         * need a fsck
         */
        btrfs_set_super_total_bytes(super, btrfs_backup_total_bytes(root_backup));
        btrfs_set_super_num_devices(super, btrfs_backup_num_devices(root_backup));
        return 0;
}

/* helper to cleanup workers */
static void btrfs_stop_all_workers(struct btrfs_fs_info *fs_info)
{
        btrfs_destroy_workqueue(fs_info->fixup_workers);
        btrfs_destroy_workqueue(fs_info->delalloc_workers);
        btrfs_destroy_workqueue(fs_info->workers);
        btrfs_destroy_workqueue(fs_info->endio_workers);
        btrfs_destroy_workqueue(fs_info->endio_meta_workers);
        btrfs_destroy_workqueue(fs_info->endio_raid56_workers);
        btrfs_destroy_workqueue(fs_info->rmw_workers);
        btrfs_destroy_workqueue(fs_info->endio_meta_write_workers);
        btrfs_destroy_workqueue(fs_info->endio_write_workers);
        btrfs_destroy_workqueue(fs_info->endio_freespace_worker);
        btrfs_destroy_workqueue(fs_info->submit_workers);
        btrfs_destroy_workqueue(fs_info->delayed_workers);
        btrfs_destroy_workqueue(fs_info->caching_workers);
        btrfs_destroy_workqueue(fs_info->readahead_workers);
        btrfs_destroy_workqueue(fs_info->flush_workers);
        btrfs_destroy_workqueue(fs_info->qgroup_rescan_workers);
}

static void free_root_extent_buffers(struct btrfs_root *root)
{
        if (root) {
                free_extent_buffer(root->node);
                free_extent_buffer(root->commit_root);
                root->node = NULL;
                root->commit_root = NULL;
        }
}

/* helper to cleanup tree roots */
static void free_root_pointers(struct btrfs_fs_info *info, int chunk_root)
{
        free_root_extent_buffers(info->tree_root);

        free_root_extent_buffers(info->dev_root);
        free_root_extent_buffers(info->extent_root);
        free_root_extent_buffers(info->csum_root);
        free_root_extent_buffers(info->quota_root);
        free_root_extent_buffers(info->uuid_root);
        if (chunk_root)
                free_root_extent_buffers(info->chunk_root);
}

static void del_fs_roots(struct btrfs_fs_info *fs_info)
{
        int ret;
        struct btrfs_root *gang[8];
        int i;

        while (!list_empty(&fs_info->dead_roots)) {
                gang[0] = list_entry(fs_info->dead_roots.next,
                                     struct btrfs_root, root_list);
                list_del(&gang[0]->root_list);

                if (gang[0]->in_radix) {
                        btrfs_drop_and_free_fs_root(fs_info, gang[0]);
                } else {
                        free_extent_buffer(gang[0]->node);
                        free_extent_buffer(gang[0]->commit_root);
                        btrfs_put_fs_root(gang[0]);
                }
        }

        while (1) {
                ret = radix_tree_gang_lookup(&fs_info->fs_roots_radix,
                                             (void **)gang, 0,
                                             ARRAY_SIZE(gang));
                if (!ret)
                        break;
                for (i = 0; i < ret; i++)
                        btrfs_drop_and_free_fs_root(fs_info, gang[i]);
        }

        if (test_bit(BTRFS_FS_STATE_ERROR, &fs_info->fs_state)) {
                btrfs_free_log_root_tree(NULL, fs_info);
                btrfs_destroy_pinned_extent(fs_info->tree_root,
                                            fs_info->pinned_extents);
        }
}

int open_ctree(struct super_block *sb,
               struct btrfs_fs_devices *fs_devices,
               char *options)
{
        u32 sectorsize;
        u32 nodesize;
        u32 leafsize;
        u32 blocksize;
        u32 stripesize;
        u64 generation;
        u64 features;
        struct btrfs_key location;
        struct buffer_head *bh;
        struct btrfs_super_block *disk_super;
        struct btrfs_fs_info *fs_info = btrfs_sb(sb);
        struct btrfs_root *tree_root;
        struct btrfs_root *extent_root;
        struct btrfs_root *csum_root;
        struct btrfs_root *chunk_root;
        struct btrfs_root *dev_root;
        struct btrfs_root *quota_root;
        struct btrfs_root *uuid_root;
        struct btrfs_root *log_tree_root;
        int ret;
        int err = -EINVAL;
        int num_backups_tried = 0;
        int backup_index = 0;
        int max_active;
        int flags = WQ_MEM_RECLAIM | WQ_FREEZABLE | WQ_UNBOUND;
        bool create_uuid_tree;
        bool check_uuid_tree;

        tree_root = fs_info->tree_root = btrfs_alloc_root(fs_info);
        chunk_root = fs_info->chunk_root = btrfs_alloc_root(fs_info);
        if (!tree_root || !chunk_root) {
                err = -ENOMEM;
                goto fail;
        }

        ret = init_srcu_struct(&fs_info->subvol_srcu);
        if (ret) {
                err = ret;
                goto fail;
        }

        ret = setup_bdi(fs_info, &fs_info->bdi);
        if (ret) {
                err = ret;
                goto fail_srcu;
        }

        ret = percpu_counter_init(&fs_info->dirty_metadata_bytes, 0);
        if (ret) {
                err = ret;
                goto fail_bdi;
        }
        fs_info->dirty_metadata_batch = PAGE_CACHE_SIZE *
                                        (1 + ilog2(nr_cpu_ids));

        ret = percpu_counter_init(&fs_info->delalloc_bytes, 0);
        if (ret) {
                err = ret;
                goto fail_dirty_metadata_bytes;
        }

        ret = percpu_counter_init(&fs_info->bio_counter, 0);
        if (ret) {
                err = ret;
                goto fail_delalloc_bytes;
        }

        fs_info->btree_inode = new_inode(sb);
        if (!fs_info->btree_inode) {
                err = -ENOMEM;
                goto fail_bio_counter;
        }

        mapping_set_gfp_mask(fs_info->btree_inode->i_mapping, GFP_NOFS);

        INIT_RADIX_TREE(&fs_info->fs_roots_radix, GFP_ATOMIC);
        INIT_RADIX_TREE(&fs_info->buffer_radix, GFP_ATOMIC);
        INIT_LIST_HEAD(&fs_info->trans_list);
        INIT_LIST_HEAD(&fs_info->dead_roots);
        INIT_LIST_HEAD(&fs_info->delayed_iputs);
        INIT_LIST_HEAD(&fs_info->delalloc_roots);
        INIT_LIST_HEAD(&fs_info->caching_block_groups);
        spin_lock_init(&fs_info->delalloc_root_lock);
        spin_lock_init(&fs_info->trans_lock);
        spin_lock_init(&fs_info->fs_roots_radix_lock);
        spin_lock_init(&fs_info->delayed_iput_lock);
        spin_lock_init(&fs_info->defrag_inodes_lock);
        spin_lock_init(&fs_info->free_chunk_lock);
        spin_lock_init(&fs_info->tree_mod_seq_lock);
        spin_lock_init(&fs_info->super_lock);
        spin_lock_init(&fs_info->buffer_lock);
        rwlock_init(&fs_info->tree_mod_log_lock);
        mutex_init(&fs_info->reloc_mutex);
        mutex_init(&fs_info->delalloc_root_mutex);
        seqlock_init(&fs_info->profiles_lock);

        init_completion(&fs_info->kobj_unregister);
        INIT_LIST_HEAD(&fs_info->dirty_cowonly_roots);
        INIT_LIST_HEAD(&fs_info->space_info);
        INIT_LIST_HEAD(&fs_info->tree_mod_seq_list);
        btrfs_mapping_init(&fs_info->mapping_tree);
        btrfs_init_block_rsv(&fs_info->global_block_rsv,
                             BTRFS_BLOCK_RSV_GLOBAL);
        btrfs_init_block_rsv(&fs_info->delalloc_block_rsv,
                             BTRFS_BLOCK_RSV_DELALLOC);
        btrfs_init_block_rsv(&fs_info->trans_block_rsv, BTRFS_BLOCK_RSV_TRANS);
        btrfs_init_block_rsv(&fs_info->chunk_block_rsv, BTRFS_BLOCK_RSV_CHUNK);
        btrfs_init_block_rsv(&fs_info->empty_block_rsv, BTRFS_BLOCK_RSV_EMPTY);
        btrfs_init_block_rsv(&fs_info->delayed_block_rsv,
                             BTRFS_BLOCK_RSV_DELOPS);
        atomic_set(&fs_info->nr_async_submits, 0);
        atomic_set(&fs_info->async_delalloc_pages, 0);
        atomic_set(&fs_info->async_submit_draining, 0);
        atomic_set(&fs_info->nr_async_bios, 0);
        atomic_set(&fs_info->defrag_running, 0);
        atomic64_set(&fs_info->tree_mod_seq, 0);
        fs_info->sb = sb;
        fs_info->max_inline = 8192 * 1024;
        fs_info->metadata_ratio = 0;
        fs_info->defrag_inodes = RB_ROOT;
        fs_info->free_chunk_space = 0;
        fs_info->tree_mod_log = RB_ROOT;
        fs_info->commit_interval = BTRFS_DEFAULT_COMMIT_INTERVAL;
        fs_info->avg_delayed_ref_runtime = div64_u64(NSEC_PER_SEC, 64);
        /* readahead state */
        INIT_RADIX_TREE(&fs_info->reada_tree, GFP_NOFS & ~__GFP_WAIT);
        spin_lock_init(&fs_info->reada_lock);

        fs_info->thread_pool_size = min_t(unsigned long,
                                          num_online_cpus() + 2, 8);

        INIT_LIST_HEAD(&fs_info->ordered_roots);
        spin_lock_init(&fs_info->ordered_root_lock);
        fs_info->delayed_root = kmalloc(sizeof(struct btrfs_delayed_root),
                                        GFP_NOFS);
        if (!fs_info->delayed_root) {
                err = -ENOMEM;
                goto fail_iput;
        }
        btrfs_init_delayed_root(fs_info->delayed_root);

        mutex_init(&fs_info->scrub_lock);
        atomic_set(&fs_info->scrubs_running, 0);
        atomic_set(&fs_info->scrub_pause_req, 0);
        atomic_set(&fs_info->scrubs_paused, 0);
        atomic_set(&fs_info->scrub_cancel_req, 0);
        init_waitqueue_head(&fs_info->replace_wait);
        init_waitqueue_head(&fs_info->scrub_pause_wait);
        fs_info->scrub_workers_refcnt = 0;
#ifdef CONFIG_BTRFS_FS_CHECK_INTEGRITY
        fs_info->check_integrity_print_mask = 0;
#endif

        spin_lock_init(&fs_info->balance_lock);
        mutex_init(&fs_info->balance_mutex);
        atomic_set(&fs_info->balance_running, 0);
        atomic_set(&fs_info->balance_pause_req, 0);
        atomic_set(&fs_info->balance_cancel_req, 0);
        fs_info->balance_ctl = NULL;
        init_waitqueue_head(&fs_info->balance_wait_q);

        sb->s_blocksize = 4096;
        sb->s_blocksize_bits = blksize_bits(4096);
        sb->s_bdi = &fs_info->bdi;

        fs_info->btree_inode->i_ino = BTRFS_BTREE_INODE_OBJECTID;
        set_nlink(fs_info->btree_inode, 1);
        /*
         * we set the i_size on the btree inode to the max possible int.
         * the real end of the address space is determined by all of
         * the devices in the system
         */
        fs_info->btree_inode->i_size = OFFSET_MAX;
        fs_info->btree_inode->i_mapping->a_ops = &btree_aops;
        fs_info->btree_inode->i_mapping->backing_dev_info = &fs_info->bdi;

        RB_CLEAR_NODE(&BTRFS_I(fs_info->btree_inode)->rb_node);
        extent_io_tree_init(&BTRFS_I(fs_info->btree_inode)->io_tree,
                             fs_info->btree_inode->i_mapping);
        BTRFS_I(fs_info->btree_inode)->io_tree.track_uptodate = 0;
        extent_map_tree_init(&BTRFS_I(fs_info->btree_inode)->extent_tree);

        BTRFS_I(fs_info->btree_inode)->io_tree.ops = &btree_extent_io_ops;

        BTRFS_I(fs_info->btree_inode)->root = tree_root;
        memset(&BTRFS_I(fs_info->btree_inode)->location, 0,
               sizeof(struct btrfs_key));
        set_bit(BTRFS_INODE_DUMMY,
                &BTRFS_I(fs_info->btree_inode)->runtime_flags);
        btrfs_insert_inode_hash(fs_info->btree_inode);

        spin_lock_init(&fs_info->block_group_cache_lock);
        fs_info->block_group_cache_tree = RB_ROOT;
        fs_info->first_logical_byte = (u64)-1;

        extent_io_tree_init(&fs_info->freed_extents[0],
                             fs_info->btree_inode->i_mapping);
        extent_io_tree_init(&fs_info->freed_extents[1],
                             fs_info->btree_inode->i_mapping);
        fs_info->pinned_extents = &fs_info->freed_extents[0];
        fs_info->do_barriers = 1;


        mutex_init(&fs_info->ordered_operations_mutex);
        mutex_init(&fs_info->ordered_extent_flush_mutex);
        mutex_init(&fs_info->tree_log_mutex);
        mutex_init(&fs_info->chunk_mutex);
        mutex_init(&fs_info->transaction_kthread_mutex);
        mutex_init(&fs_info->cleaner_mutex);
        mutex_init(&fs_info->volume_mutex);
        init_rwsem(&fs_info->commit_root_sem);
        init_rwsem(&fs_info->cleanup_work_sem);
        init_rwsem(&fs_info->subvol_sem);
        sema_init(&fs_info->uuid_tree_rescan_sem, 1);
        fs_info->dev_replace.lock_owner = 0;
        atomic_set(&fs_info->dev_replace.nesting_level, 0);
        mutex_init(&fs_info->dev_replace.lock_finishing_cancel_unmount);
        mutex_init(&fs_info->dev_replace.lock_management_lock);
        mutex_init(&fs_info->dev_replace.lock);

        spin_lock_init(&fs_info->qgroup_lock);
        mutex_init(&fs_info->qgroup_ioctl_lock);
        fs_info->qgroup_tree = RB_ROOT;
        INIT_LIST_HEAD(&fs_info->dirty_qgroups);
        fs_info->qgroup_seq = 1;
        fs_info->quota_enabled = 0;
        fs_info->pending_quota_state = 0;
        fs_info->qgroup_ulist = NULL;
        mutex_init(&fs_info->qgroup_rescan_lock);

        btrfs_init_free_cluster(&fs_info->meta_alloc_cluster);
        btrfs_init_free_cluster(&fs_info->data_alloc_cluster);

        init_waitqueue_head(&fs_info->transaction_throttle);
        init_waitqueue_head(&fs_info->transaction_wait);
        init_waitqueue_head(&fs_info->transaction_blocked_wait);
        init_waitqueue_head(&fs_info->async_submit_wait);

        ret = btrfs_alloc_stripe_hash_table(fs_info);
        if (ret) {
                err = ret;
                goto fail_alloc;
        }

        __setup_root(4096, 4096, 4096, 4096, tree_root,
                     fs_info, BTRFS_ROOT_TREE_OBJECTID);

        invalidate_bdev(fs_devices->latest_bdev);

        /*
         * Read super block and check the signature bytes only
         */
        bh = btrfs_read_dev_super(fs_devices->latest_bdev);
        if (!bh) {
                err = -EINVAL;
                goto fail_alloc;
        }

        /*
         * We want to check superblock checksum, the type is stored inside.
         * Pass the whole disk block of size BTRFS_SUPER_INFO_SIZE (4k).
         */
        if (btrfs_check_super_csum(bh->b_data)) {
                printk(KERN_ERR "BTRFS: superblock checksum mismatch\n");
                err = -EINVAL;
                goto fail_alloc;
        }

        /*
         * super_copy is zeroed at allocation time and we never touch the
         * following bytes up to INFO_SIZE, the checksum is calculated from
         * the whole block of INFO_SIZE
         */
        memcpy(fs_info->super_copy, bh->b_data, sizeof(*fs_info->super_copy));
        memcpy(fs_info->super_for_commit, fs_info->super_copy,
               sizeof(*fs_info->super_for_commit));
        brelse(bh);

        memcpy(fs_info->fsid, fs_info->super_copy->fsid, BTRFS_FSID_SIZE);

        ret = btrfs_check_super_valid(fs_info, sb->s_flags & MS_RDONLY);
        if (ret) {
                printk(KERN_ERR "BTRFS: superblock contains fatal errors\n");
                err = -EINVAL;
                goto fail_alloc;
        }

        disk_super = fs_info->super_copy;
        if (!btrfs_super_root(disk_super))
                goto fail_alloc;

        /* check FS state, whether FS is broken. */
        if (btrfs_super_flags(disk_super) & BTRFS_SUPER_FLAG_ERROR)
                set_bit(BTRFS_FS_STATE_ERROR, &fs_info->fs_state);

        /*
         * run through our array of backup supers and setup
         * our ring pointer to the oldest one
         */
        generation = btrfs_super_generation(disk_super);
        find_oldest_super_backup(fs_info, generation);

        /*
         * In the long term, we'll store the compression type in the super
         * block, and it'll be used for per file compression control.
         */
        fs_info->compress_type = BTRFS_COMPRESS_ZLIB;

        ret = btrfs_parse_options(tree_root, options);
        if (ret) {
                err = ret;
                goto fail_alloc;
        }

        features = btrfs_super_incompat_flags(disk_super) &
                ~BTRFS_FEATURE_INCOMPAT_SUPP;
        if (features) {
                printk(KERN_ERR "BTRFS: couldn't mount because of "
                       "unsupported optional features (%Lx).\n",
                       features);
                err = -EINVAL;
                goto fail_alloc;
        }

        if (btrfs_super_leafsize(disk_super) !=
            btrfs_super_nodesize(disk_super)) {
                printk(KERN_ERR "BTRFS: couldn't mount because metadata "
                       "blocksizes don't match.  node %d leaf %d\n",
                       btrfs_super_nodesize(disk_super),
                       btrfs_super_leafsize(disk_super));
                err = -EINVAL;
                goto fail_alloc;
        }
        if (btrfs_super_leafsize(disk_super) > BTRFS_MAX_METADATA_BLOCKSIZE) {
                printk(KERN_ERR "BTRFS: couldn't mount because metadata "
                       "blocksize (%d) was too large\n",
                       btrfs_super_leafsize(disk_super));
                err = -EINVAL;
                goto fail_alloc;
        }

        features = btrfs_super_incompat_flags(disk_super);
        features |= BTRFS_FEATURE_INCOMPAT_MIXED_BACKREF;
        if (tree_root->fs_info->compress_type == BTRFS_COMPRESS_LZO)
                features |= BTRFS_FEATURE_INCOMPAT_COMPRESS_LZO;

        if (features & BTRFS_FEATURE_INCOMPAT_SKINNY_METADATA)
                printk(KERN_ERR "BTRFS: has skinny extents\n");

        /*
         * flag our filesystem as having big metadata blocks if
         * they are bigger than the page size
         */
        if (btrfs_super_leafsize(disk_super) > PAGE_CACHE_SIZE) {
                if (!(features & BTRFS_FEATURE_INCOMPAT_BIG_METADATA))
                        printk(KERN_INFO "BTRFS: flagging fs with big metadata feature\n");
                features |= BTRFS_FEATURE_INCOMPAT_BIG_METADATA;
        }

        nodesize = btrfs_super_nodesize(disk_super);
        leafsize = btrfs_super_leafsize(disk_super);
        sectorsize = btrfs_super_sectorsize(disk_super);
        stripesize = btrfs_super_stripesize(disk_super);
        fs_info->dirty_metadata_batch = leafsize * (1 + ilog2(nr_cpu_ids));
        fs_info->delalloc_batch = sectorsize * 512 * (1 + ilog2(nr_cpu_ids));

        /*
         * mixed block groups end up with duplicate but slightly offset
         * extent buffers for the same range.  It leads to corruptions
         */
        if ((features & BTRFS_FEATURE_INCOMPAT_MIXED_GROUPS) &&
            (sectorsize != leafsize)) {
                printk(KERN_WARNING "BTRFS: unequal leaf/node/sector sizes "
                                "are not allowed for mixed block groups on %s\n",
                                sb->s_id);
                goto fail_alloc;
        }

        /*
         * Needn't use the lock because there is no other task which will
         * update the flag.
         */
        btrfs_set_super_incompat_flags(disk_super, features);

        features = btrfs_super_compat_ro_flags(disk_super) &
                ~BTRFS_FEATURE_COMPAT_RO_SUPP;
        if (!(sb->s_flags & MS_RDONLY) && features) {
                printk(KERN_ERR "BTRFS: couldn't mount RDWR because of "
                       "unsupported option features (%Lx).\n",
                       features);
                err = -EINVAL;
                goto fail_alloc;
        }

        max_active = fs_info->thread_pool_size;

        fs_info->workers =
                btrfs_alloc_workqueue("worker", flags | WQ_HIGHPRI,
                                      max_active, 16);

        fs_info->delalloc_workers =
                btrfs_alloc_workqueue("delalloc", flags, max_active, 2);

        fs_info->flush_workers =
                btrfs_alloc_workqueue("flush_delalloc", flags, max_active, 0);

        fs_info->caching_workers =
                btrfs_alloc_workqueue("cache", flags, max_active, 0);

        /*
         * a higher idle thresh on the submit workers makes it much more
         * likely that bios will be send down in a sane order to the
         * devices
         */
        fs_info->submit_workers =
                btrfs_alloc_workqueue("submit", flags,
                                      min_t(u64, fs_devices->num_devices,
                                            max_active), 64);

        fs_info->fixup_workers =
                btrfs_alloc_workqueue("fixup", flags, 1, 0);

        /*
         * endios are largely parallel and should have a very
         * low idle thresh
         */
        fs_info->endio_workers =
                btrfs_alloc_workqueue("endio", flags, max_active, 4);
        fs_info->endio_meta_workers =
                btrfs_alloc_workqueue("endio-meta", flags, max_active, 4);
        fs_info->endio_meta_write_workers =
                btrfs_alloc_workqueue("endio-meta-write", flags, max_active, 2);
        fs_info->endio_raid56_workers =
                btrfs_alloc_workqueue("endio-raid56", flags, max_active, 4);
        fs_info->rmw_workers =
                btrfs_alloc_workqueue("rmw", flags, max_active, 2);
        fs_info->endio_write_workers =
                btrfs_alloc_workqueue("endio-write", flags, max_active, 2);
        fs_info->endio_freespace_worker =
                btrfs_alloc_workqueue("freespace-write", flags, max_active, 0);
        fs_info->delayed_workers =
                btrfs_alloc_workqueue("delayed-meta", flags, max_active, 0);
        fs_info->readahead_workers =
                btrfs_alloc_workqueue("readahead", flags, max_active, 2);
        fs_info->qgroup_rescan_workers =
                btrfs_alloc_workqueue("qgroup-rescan", flags, 1, 0);

        if (!(fs_info->workers && fs_info->delalloc_workers &&
              fs_info->submit_workers && fs_info->flush_workers &&
              fs_info->endio_workers && fs_info->endio_meta_workers &&
              fs_info->endio_meta_write_workers &&
              fs_info->endio_write_workers && fs_info->endio_raid56_workers &&
              fs_info->endio_freespace_worker && fs_info->rmw_workers &&
              fs_info->caching_workers && fs_info->readahead_workers &&
              fs_info->fixup_workers && fs_info->delayed_workers &&
              fs_info->qgroup_rescan_workers)) {
                err = -ENOMEM;
                goto fail_sb_buffer;
        }

        fs_info->bdi.ra_pages *= btrfs_super_num_devices(disk_super);
        fs_info->bdi.ra_pages = max(fs_info->bdi.ra_pages,
                                    4 * 1024 * 1024 / PAGE_CACHE_SIZE);

        tree_root->nodesize = nodesize;
        tree_root->leafsize = leafsize;
        tree_root->sectorsize = sectorsize;
        tree_root->stripesize = stripesize;

        sb->s_blocksize = sectorsize;
        sb->s_blocksize_bits = blksize_bits(sectorsize);

        if (btrfs_super_magic(disk_super) != BTRFS_MAGIC) {
                printk(KERN_INFO "BTRFS: valid FS not found on %s\n", sb->s_id);
                goto fail_sb_buffer;
        }

        if (sectorsize != PAGE_SIZE) {
                printk(KERN_WARNING "BTRFS: Incompatible sector size(%lu) "
                       "found on %s\n", (unsigned long)sectorsize, sb->s_id);
                goto fail_sb_buffer;
        }

        mutex_lock(&fs_info->chunk_mutex);
        ret = btrfs_read_sys_array(tree_root);
        mutex_unlock(&fs_info->chunk_mutex);
        if (ret) {
                printk(KERN_WARNING "BTRFS: failed to read the system "
                       "array on %s\n", sb->s_id);
                goto fail_sb_buffer;
        }

        blocksize = btrfs_level_size(tree_root,
                                     btrfs_super_chunk_root_level(disk_super));
        generation = btrfs_super_chunk_root_generation(disk_super);

        __setup_root(nodesize, leafsize, sectorsize, stripesize,
                     chunk_root, fs_info, BTRFS_CHUNK_TREE_OBJECTID);

        chunk_root->node = read_tree_block(chunk_root,
                                           btrfs_super_chunk_root(disk_super),
                                           blocksize, generation);
        if (!chunk_root->node ||
            !test_bit(EXTENT_BUFFER_UPTODATE, &chunk_root->node->bflags)) {
                printk(KERN_WARNING "BTRFS: failed to read chunk root on %s\n",
                       sb->s_id);
                goto fail_tree_roots;
        }
        btrfs_set_root_node(&chunk_root->root_item, chunk_root->node);
        chunk_root->commit_root = btrfs_root_node(chunk_root);

        read_extent_buffer(chunk_root->node, fs_info->chunk_tree_uuid,
           btrfs_header_chunk_tree_uuid(chunk_root->node), BTRFS_UUID_SIZE);

        ret = btrfs_read_chunk_tree(chunk_root);
        if (ret) {
                printk(KERN_WARNING "BTRFS: failed to read chunk tree on %s\n",
                       sb->s_id);
                goto fail_tree_roots;
        }

        /*
         * keep the device that is marked to be the target device for the
         * dev_replace procedure
         */
        btrfs_close_extra_devices(fs_info, fs_devices, 0);

        if (!fs_devices->latest_bdev) {
                printk(KERN_CRIT "BTRFS: failed to read devices on %s\n",
                       sb->s_id);
                goto fail_tree_roots;
        }

retry_root_backup:
        blocksize = btrfs_level_size(tree_root,
                                     btrfs_super_root_level(disk_super));
        generation = btrfs_super_generation(disk_super);

        tree_root->node = read_tree_block(tree_root,
                                          btrfs_super_root(disk_super),
                                          blocksize, generation);
        if (!tree_root->node ||
            !test_bit(EXTENT_BUFFER_UPTODATE, &tree_root->node->bflags)) {
                printk(KERN_WARNING "BTRFS: failed to read tree root on %s\n",
                       sb->s_id);

                goto recovery_tree_root;
        }

        btrfs_set_root_node(&tree_root->root_item, tree_root->node);
        tree_root->commit_root = btrfs_root_node(tree_root);
        btrfs_set_root_refs(&tree_root->root_item, 1);

        location.objectid = BTRFS_EXTENT_TREE_OBJECTID;
        location.type = BTRFS_ROOT_ITEM_KEY;
        location.offset = 0;

        extent_root = btrfs_read_tree_root(tree_root, &location);
        if (IS_ERR(extent_root)) {
                ret = PTR_ERR(extent_root);
                goto recovery_tree_root;
        }
        extent_root->track_dirty = 1;
        fs_info->extent_root = extent_root;

        location.objectid = BTRFS_DEV_TREE_OBJECTID;
        dev_root = btrfs_read_tree_root(tree_root, &location);
        if (IS_ERR(dev_root)) {
                ret = PTR_ERR(dev_root);
                goto recovery_tree_root;
        }
        dev_root->track_dirty = 1;
        fs_info->dev_root = dev_root;
        btrfs_init_devices_late(fs_info);

        location.objectid = BTRFS_CSUM_TREE_OBJECTID;
        csum_root = btrfs_read_tree_root(tree_root, &location);
        if (IS_ERR(csum_root)) {
                ret = PTR_ERR(csum_root);
                goto recovery_tree_root;
        }
        csum_root->track_dirty = 1;
        fs_info->csum_root = csum_root;

        location.objectid = BTRFS_QUOTA_TREE_OBJECTID;
        quota_root = btrfs_read_tree_root(tree_root, &location);
        if (!IS_ERR(quota_root)) {
                quota_root->track_dirty = 1;
                fs_info->quota_enabled = 1;
                fs_info->pending_quota_state = 1;
                fs_info->quota_root = quota_root;
        }

        location.objectid = BTRFS_UUID_TREE_OBJECTID;
        uuid_root = btrfs_read_tree_root(tree_root, &location);
        if (IS_ERR(uuid_root)) {
                ret = PTR_ERR(uuid_root);
                if (ret != -ENOENT)
                        goto recovery_tree_root;
                create_uuid_tree = true;
                check_uuid_tree = false;
        } else {
                uuid_root->track_dirty = 1;
                fs_info->uuid_root = uuid_root;
                create_uuid_tree = false;
                check_uuid_tree =
                    generation != btrfs_super_uuid_tree_generation(disk_super);
        }

        fs_info->generation = generation;
        fs_info->last_trans_committed = generation;

        ret = btrfs_recover_balance(fs_info);
        if (ret) {
                printk(KERN_WARNING "BTRFS: failed to recover balance\n");
                goto fail_block_groups;
        }

        ret = btrfs_init_dev_stats(fs_info);
        if (ret) {
                printk(KERN_ERR "BTRFS: failed to init dev_stats: %d\n",
                       ret);
                goto fail_block_groups;
        }

        ret = btrfs_init_dev_replace(fs_info);
        if (ret) {
                pr_err("BTRFS: failed to init dev_replace: %d\n", ret);
                goto fail_block_groups;
        }

        btrfs_close_extra_devices(fs_info, fs_devices, 1);

        ret = btrfs_sysfs_add_one(fs_info);
        if (ret) {
                pr_err("BTRFS: failed to init sysfs interface: %d\n", ret);
                goto fail_block_groups;
        }

        ret = btrfs_init_space_info(fs_info);
        if (ret) {
                printk(KERN_ERR "BTRFS: Failed to initial space info: %d\n", ret);
                goto fail_sysfs;
        }

        ret = btrfs_read_block_groups(extent_root);
        if (ret) {
                printk(KERN_ERR "BTRFS: Failed to read block groups: %d\n", ret);
                goto fail_sysfs;
        }
        fs_info->num_tolerated_disk_barrier_failures =
                btrfs_calc_num_tolerated_disk_barrier_failures(fs_info);
        if (fs_info->fs_devices->missing_devices >
             fs_info->num_tolerated_disk_barrier_failures &&
            !(sb->s_flags & MS_RDONLY)) {
                printk(KERN_WARNING "BTRFS: "
                        "too many missing devices, writeable mount is not allowed\n");
                goto fail_sysfs;
        }

        fs_info->cleaner_kthread = kthread_run(cleaner_kthread, tree_root,
                                               "btrfs-cleaner");
        if (IS_ERR(fs_info->cleaner_kthread))
                goto fail_sysfs;

        fs_info->transaction_kthread = kthread_run(transaction_kthread,
                                                   tree_root,
                                                   "btrfs-transaction");
        if (IS_ERR(fs_info->transaction_kthread))
                goto fail_cleaner;

        if (!btrfs_test_opt(tree_root, SSD) &&
            !btrfs_test_opt(tree_root, NOSSD) &&
            !fs_info->fs_devices->rotating) {
                printk(KERN_INFO "BTRFS: detected SSD devices, enabling SSD "
                       "mode\n");
                btrfs_set_opt(fs_info->mount_opt, SSD);
        }

        /* Set the real inode map cache flag */
        if (btrfs_test_opt(tree_root, CHANGE_INODE_CACHE))
                btrfs_set_opt(tree_root->fs_info->mount_opt, INODE_MAP_CACHE);

#ifdef CONFIG_BTRFS_FS_CHECK_INTEGRITY
        if (btrfs_test_opt(tree_root, CHECK_INTEGRITY)) {
                ret = btrfsic_mount(tree_root, fs_devices,
                                    btrfs_test_opt(tree_root,
                                        CHECK_INTEGRITY_INCLUDING_EXTENT_DATA) ?
                                    1 : 0,
                                    fs_info->check_integrity_print_mask);
                if (ret)
                        printk(KERN_WARNING "BTRFS: failed to initialize"
                               " integrity check module %s\n", sb->s_id);
        }
#endif
        ret = btrfs_read_qgroup_config(fs_info);
        if (ret)
                goto fail_trans_kthread;

        /* do not make disk changes in broken FS */
        if (btrfs_super_log_root(disk_super) != 0) {
                u64 bytenr = btrfs_super_log_root(disk_super);

                if (fs_devices->rw_devices == 0) {
                        printk(KERN_WARNING "BTRFS: log replay required "
                               "on RO media\n");
                        err = -EIO;
                        goto fail_qgroup;
                }
                blocksize =
                     btrfs_level_size(tree_root,
                                      btrfs_super_log_root_level(disk_super));

                log_tree_root = btrfs_alloc_root(fs_info);
                if (!log_tree_root) {
                        err = -ENOMEM;
                        goto fail_qgroup;
                }

                __setup_root(nodesize, leafsize, sectorsize, stripesize,
                             log_tree_root, fs_info, BTRFS_TREE_LOG_OBJECTID);

                log_tree_root->node = read_tree_block(tree_root, bytenr,
                                                      blocksize,
                                                      generation + 1);
                if (!log_tree_root->node ||
                    !extent_buffer_uptodate(log_tree_root->node)) {
                        printk(KERN_ERR "BTRFS: failed to read log tree\n");
                        free_extent_buffer(log_tree_root->node);
                        kfree(log_tree_root);
                        goto fail_qgroup;
                }
                /* returns with log_tree_root freed on success */
                ret = btrfs_recover_log_trees(log_tree_root);
                if (ret) {
                        btrfs_error(tree_root->fs_info, ret,
                                    "Failed to recover log tree");
                        free_extent_buffer(log_tree_root->node);
                        kfree(log_tree_root);
                        goto fail_qgroup;
                }

                if (sb->s_flags & MS_RDONLY) {
                        ret = btrfs_commit_super(tree_root);
                        if (ret)
                                goto fail_qgroup;
                }
        }

        ret = btrfs_find_orphan_roots(tree_root);
        if (ret)
                goto fail_qgroup;

        if (!(sb->s_flags & MS_RDONLY)) {
                ret = btrfs_cleanup_fs_roots(fs_info);
                if (ret)
                        goto fail_qgroup;

                ret = btrfs_recover_relocation(tree_root);
                if (ret < 0) {
                        printk(KERN_WARNING
                               "BTRFS: failed to recover relocation\n");
                        err = -EINVAL;
                        goto fail_qgroup;
                }
        }

        location.objectid = BTRFS_FS_TREE_OBJECTID;
        location.type = BTRFS_ROOT_ITEM_KEY;
        location.offset = 0;

        fs_info->fs_root = btrfs_read_fs_root_no_name(fs_info, &location);
        if (IS_ERR(fs_info->fs_root)) {
                err = PTR_ERR(fs_info->fs_root);
                goto fail_qgroup;
        }

        if (sb->s_flags & MS_RDONLY)
                return 0;

        down_read(&fs_info->cleanup_work_sem);
        if ((ret = btrfs_orphan_cleanup(fs_info->fs_root)) ||
            (ret = btrfs_orphan_cleanup(fs_info->tree_root))) {
                up_read(&fs_info->cleanup_work_sem);
                close_ctree(tree_root);
                return ret;
        }
        up_read(&fs_info->cleanup_work_sem);

        ret = btrfs_resume_balance_async(fs_info);
        if (ret) {
                printk(KERN_WARNING "BTRFS: failed to resume balance\n");
                close_ctree(tree_root);
                return ret;
        }

        ret = btrfs_resume_dev_replace_async(fs_info);
        if (ret) {
                pr_warn("BTRFS: failed to resume dev_replace\n");
                close_ctree(tree_root);
                return ret;
        }

        btrfs_qgroup_rescan_resume(fs_info);

        if (create_uuid_tree) {
                pr_info("BTRFS: creating UUID tree\n");
                ret = btrfs_create_uuid_tree(fs_info);
                if (ret) {
                        pr_warn("BTRFS: failed to create the UUID tree %d\n",
                                ret);
                        close_ctree(tree_root);
                        return ret;
                }
        } else if (check_uuid_tree ||
                   btrfs_test_opt(tree_root, RESCAN_UUID_TREE)) {
                pr_info("BTRFS: checking UUID tree\n");
                ret = btrfs_check_uuid_tree(fs_info);
                if (ret) {
                        pr_warn("BTRFS: failed to check the UUID tree %d\n",
                                ret);
                        close_ctree(tree_root);
                        return ret;
                }
        } else {
                fs_info->update_uuid_tree_gen = 1;
        }

        return 0;

fail_qgroup:
        btrfs_free_qgroup_config(fs_info);
fail_trans_kthread:
        kthread_stop(fs_info->transaction_kthread);
        btrfs_cleanup_transaction(fs_info->tree_root);
        del_fs_roots(fs_info);
fail_cleaner:
        kthread_stop(fs_info->cleaner_kthread);

        /*
         * make sure we're done with the btree inode before we stop our
         * kthreads
         */
        filemap_write_and_wait(fs_info->btree_inode->i_mapping);

fail_sysfs:
        btrfs_sysfs_remove_one(fs_info);

fail_block_groups:
        btrfs_put_block_group_cache(fs_info);
        btrfs_free_block_groups(fs_info);

fail_tree_roots:
        free_root_pointers(fs_info, 1);
        invalidate_inode_pages2(fs_info->btree_inode->i_mapping);

fail_sb_buffer:
        btrfs_stop_all_workers(fs_info);
fail_alloc:
fail_iput:
        btrfs_mapping_tree_free(&fs_info->mapping_tree);

        iput(fs_info->btree_inode);
fail_bio_counter:
        percpu_counter_destroy(&fs_info->bio_counter);
fail_delalloc_bytes:
        percpu_counter_destroy(&fs_info->delalloc_bytes);