// SPDX-License-Identifier: GPL-2.0
/*
 * Copyright (C) 2007,2008 Oracle.  All rights reserved.
 */

#include <linux/sched.h>
#include <linux/slab.h>
#include <linux/rbtree.h>
#include <linux/mm.h>
#include "ctree.h"
#include "disk-io.h"
#include "transaction.h"
#include "print-tree.h"
#include "locking.h"
#include "volumes.h"
#include "qgroup.h"
#include "tree-mod-log.h"

static int split_node(struct btrfs_trans_handle *trans, struct btrfs_root
                      *root, struct btrfs_path *path, int level);
static int split_leaf(struct btrfs_trans_handle *trans, struct btrfs_root *root,
                      const struct btrfs_key *ins_key, struct btrfs_path *path,
                      int data_size, int extend);
static int push_node_left(struct btrfs_trans_handle *trans,
                          struct extent_buffer *dst,
                          struct extent_buffer *src, int empty);
static int balance_node_right(struct btrfs_trans_handle *trans,
                              struct extent_buffer *dst_buf,
                              struct extent_buffer *src_buf);
static void del_ptr(struct btrfs_root *root, struct btrfs_path *path,
                    int level, int slot);

static const struct btrfs_csums {
        u16             size;
        const char      name[10];
        const char      driver[12];
} btrfs_csums[] = {
        [BTRFS_CSUM_TYPE_CRC32] = { .size = 4, .name = "crc32c" },
        [BTRFS_CSUM_TYPE_XXHASH] = { .size = 8, .name = "xxhash64" },
        [BTRFS_CSUM_TYPE_SHA256] = { .size = 32, .name = "sha256" },
        [BTRFS_CSUM_TYPE_BLAKE2] = { .size = 32, .name = "blake2b",
                                     .driver = "blake2b-256" },
};

int btrfs_super_csum_size(const struct btrfs_super_block *s)
{
        u16 t = btrfs_super_csum_type(s);
        /*
         * csum type is validated at mount time
         */
        return btrfs_csums[t].size;
}

const char *btrfs_super_csum_name(u16 csum_type)
{
        /* csum type is validated at mount time */
        return btrfs_csums[csum_type].name;
}

/*
 * Return driver name if defined, otherwise the name that's also a valid driver
 * name
 */
const char *btrfs_super_csum_driver(u16 csum_type)
{
        /* csum type is validated at mount time */
        return btrfs_csums[csum_type].driver[0] ?
                btrfs_csums[csum_type].driver :
                btrfs_csums[csum_type].name;
}

size_t __attribute_const__ btrfs_get_num_csums(void)
{
        return ARRAY_SIZE(btrfs_csums);
}

struct btrfs_path *btrfs_alloc_path(void)
{
        return kmem_cache_zalloc(btrfs_path_cachep, GFP_NOFS);
}

/* this also releases the path */
void btrfs_free_path(struct btrfs_path *p)
{
        if (!p)
                return;
        btrfs_release_path(p);
        kmem_cache_free(btrfs_path_cachep, p);
}

/*
 * path release drops references on the extent buffers in the path
 * and it drops any locks held by this path
 *
 * It is safe to call this on paths that no locks or extent buffers held.
 */
noinline void btrfs_release_path(struct btrfs_path *p)
{
        int i;

        for (i = 0; i < BTRFS_MAX_LEVEL; i++) {
                p->slots[i] = 0;
                if (!p->nodes[i])
                        continue;
                if (p->locks[i]) {
                        btrfs_tree_unlock_rw(p->nodes[i], p->locks[i]);
                        p->locks[i] = 0;
                }
                free_extent_buffer(p->nodes[i]);
                p->nodes[i] = NULL;
        }
}

/*
 * safely gets a reference on the root node of a tree.  A lock
 * is not taken, so a concurrent writer may put a different node
 * at the root of the tree.  See btrfs_lock_root_node for the
 * looping required.
 *
 * The extent buffer returned by this has a reference taken, so
 * it won't disappear.  It may stop being the root of the tree
 * at any time because there are no locks held.
 */
struct extent_buffer *btrfs_root_node(struct btrfs_root *root)
{
        struct extent_buffer *eb;

        while (1) {
                rcu_read_lock();
                eb = rcu_dereference(root->node);

                /*
                 * RCU really hurts here, we could free up the root node because
                 * it was COWed but we may not get the new root node yet so do
                 * the inc_not_zero dance and if it doesn't work then
                 * synchronize_rcu and try again.
                 */
                if (atomic_inc_not_zero(&eb->refs)) {
                        rcu_read_unlock();
                        break;
                }
                rcu_read_unlock();
                synchronize_rcu();
        }
        return eb;
}

/*
 * Cowonly root (not-shareable trees, everything not subvolume or reloc roots),
 * just get put onto a simple dirty list.  Transaction walks this list to make
 * sure they get properly updated on disk.
 */
static void add_root_to_dirty_list(struct btrfs_root *root)
{
        struct btrfs_fs_info *fs_info = root->fs_info;

        if (test_bit(BTRFS_ROOT_DIRTY, &root->state) ||
            !test_bit(BTRFS_ROOT_TRACK_DIRTY, &root->state))
                return;

        spin_lock(&fs_info->trans_lock);
        if (!test_and_set_bit(BTRFS_ROOT_DIRTY, &root->state)) {
                /* Want the extent tree to be the last on the list */
                if (root->root_key.objectid == BTRFS_EXTENT_TREE_OBJECTID)
                        list_move_tail(&root->dirty_list,
                                       &fs_info->dirty_cowonly_roots);
                else
                        list_move(&root->dirty_list,
                                  &fs_info->dirty_cowonly_roots);
        }
        spin_unlock(&fs_info->trans_lock);
}

/*
 * used by snapshot creation to make a copy of a root for a tree with
 * a given objectid.  The buffer with the new root node is returned in
 * cow_ret, and this func returns zero on success or a negative error code.
 */
int btrfs_copy_root(struct btrfs_trans_handle *trans,
                      struct btrfs_root *root,
                      struct extent_buffer *buf,
                      struct extent_buffer **cow_ret, u64 new_root_objectid)
{
        struct btrfs_fs_info *fs_info = root->fs_info;
        struct extent_buffer *cow;
        int ret = 0;
        int level;
        struct btrfs_disk_key disk_key;

        WARN_ON(test_bit(BTRFS_ROOT_SHAREABLE, &root->state) &&
                trans->transid != fs_info->running_transaction->transid);
        WARN_ON(test_bit(BTRFS_ROOT_SHAREABLE, &root->state) &&
                trans->transid != root->last_trans);

        level = btrfs_header_level(buf);
        if (level == 0)
                btrfs_item_key(buf, &disk_key, 0);
        else
                btrfs_node_key(buf, &disk_key, 0);

        cow = btrfs_alloc_tree_block(trans, root, 0, new_root_objectid,
                                     &disk_key, level, buf->start, 0,
                                     BTRFS_NESTING_NEW_ROOT);
        if (IS_ERR(cow))
                return PTR_ERR(cow);

        copy_extent_buffer_full(cow, buf);
        btrfs_set_header_bytenr(cow, cow->start);
        btrfs_set_header_generation(cow, trans->transid);
        btrfs_set_header_backref_rev(cow, BTRFS_MIXED_BACKREF_REV);
        btrfs_clear_header_flag(cow, BTRFS_HEADER_FLAG_WRITTEN |
                                     BTRFS_HEADER_FLAG_RELOC);
        if (new_root_objectid == BTRFS_TREE_RELOC_OBJECTID)
                btrfs_set_header_flag(cow, BTRFS_HEADER_FLAG_RELOC);
        else
                btrfs_set_header_owner(cow, new_root_objectid);

        write_extent_buffer_fsid(cow, fs_info->fs_devices->metadata_uuid);

        WARN_ON(btrfs_header_generation(buf) > trans->transid);
        if (new_root_objectid == BTRFS_TREE_RELOC_OBJECTID)
                ret = btrfs_inc_ref(trans, root, cow, 1);
        else
                ret = btrfs_inc_ref(trans, root, cow, 0);
        if (ret) {
                btrfs_tree_unlock(cow);
                free_extent_buffer(cow);
                btrfs_abort_transaction(trans, ret);
                return ret;
        }

        btrfs_mark_buffer_dirty(cow);
        *cow_ret = cow;
        return 0;
}

/*
 * check if the tree block can be shared by multiple trees
 */
int btrfs_block_can_be_shared(struct btrfs_root *root,
                              struct extent_buffer *buf)
{
        /*
         * Tree blocks not in shareable trees and tree roots are never shared.
         * If a block was allocated after the last snapshot and the block was
         * not allocated by tree relocation, we know the block is not shared.
         */
        if (test_bit(BTRFS_ROOT_SHAREABLE, &root->state) &&
            buf != root->node && buf != root->commit_root &&
            (btrfs_header_generation(buf) <=
             btrfs_root_last_snapshot(&root->root_item) ||
             btrfs_header_flag(buf, BTRFS_HEADER_FLAG_RELOC)))
                return 1;

        return 0;
}

static noinline int update_ref_for_cow(struct btrfs_trans_handle *trans,
                                       struct btrfs_root *root,
                                       struct extent_buffer *buf,
                                       struct extent_buffer *cow,
                                       int *last_ref)
{
        struct btrfs_fs_info *fs_info = root->fs_info;
        u64 refs;
        u64 owner;
        u64 flags;
        u64 new_flags = 0;
        int ret;

        /*
         * Backrefs update rules:
         *
         * Always use full backrefs for extent pointers in tree block
         * allocated by tree relocation.
         *
         * If a shared tree block is no longer referenced by its owner
         * tree (btrfs_header_owner(buf) == root->root_key.objectid),
         * use full backrefs for extent pointers in tree block.
         *
         * If a tree block is been relocating
         * (root->root_key.objectid == BTRFS_TREE_RELOC_OBJECTID),
         * use full backrefs for extent pointers in tree block.
         * The reason for this is some operations (such as drop tree)
         * are only allowed for blocks use full backrefs.
         */

        if (btrfs_block_can_be_shared(root, buf)) {
                ret = btrfs_lookup_extent_info(trans, fs_info, buf->start,
                                               btrfs_header_level(buf), 1,
                                               &refs, &flags);
                if (ret)
                        return ret;
                if (refs == 0) {
                        ret = -EROFS;
                        btrfs_handle_fs_error(fs_info, ret, NULL);
                        return ret;
                }
        } else {
                refs = 1;
                if (root->root_key.objectid == BTRFS_TREE_RELOC_OBJECTID ||
                    btrfs_header_backref_rev(buf) < BTRFS_MIXED_BACKREF_REV)
                        flags = BTRFS_BLOCK_FLAG_FULL_BACKREF;
                else
                        flags = 0;
        }

        owner = btrfs_header_owner(buf);
        BUG_ON(owner == BTRFS_TREE_RELOC_OBJECTID &&
               !(flags & BTRFS_BLOCK_FLAG_FULL_BACKREF));

        if (refs > 1) {
                if ((owner == root->root_key.objectid ||
                     root->root_key.objectid == BTRFS_TREE_RELOC_OBJECTID) &&
                    !(flags & BTRFS_BLOCK_FLAG_FULL_BACKREF)) {
                        ret = btrfs_inc_ref(trans, root, buf, 1);
                        if (ret)
                                return ret;

                        if (root->root_key.objectid ==
                            BTRFS_TREE_RELOC_OBJECTID) {
                                ret = btrfs_dec_ref(trans, root, buf, 0);
                                if (ret)
                                        return ret;
                                ret = btrfs_inc_ref(trans, root, cow, 1);
                                if (ret)
                                        return ret;
                        }
                        new_flags |= BTRFS_BLOCK_FLAG_FULL_BACKREF;
                } else {

                        if (root->root_key.objectid ==
                            BTRFS_TREE_RELOC_OBJECTID)
                                ret = btrfs_inc_ref(trans, root, cow, 1);
                        else
                                ret = btrfs_inc_ref(trans, root, cow, 0);
                        if (ret)
                                return ret;
                }
                if (new_flags != 0) {
                        int level = btrfs_header_level(buf);

                        ret = btrfs_set_disk_extent_flags(trans, buf,
                                                          new_flags, level, 0);
                        if (ret)
                                return ret;
                }
        } else {
                if (flags & BTRFS_BLOCK_FLAG_FULL_BACKREF) {
                        if (root->root_key.objectid ==
                            BTRFS_TREE_RELOC_OBJECTID)
                                ret = btrfs_inc_ref(trans, root, cow, 1);
                        else
                                ret = btrfs_inc_ref(trans, root, cow, 0);
                        if (ret)
                                return ret;
                        ret = btrfs_dec_ref(trans, root, buf, 1);
                        if (ret)
                                return ret;
                }
                btrfs_clean_tree_block(buf);
                *last_ref = 1;
        }
        return 0;
}

/*
 * does the dirty work in cow of a single block.  The parent block (if
 * supplied) is updated to point to the new cow copy.  The new buffer is marked
 * dirty and returned locked.  If you modify the block it needs to be marked
 * dirty again.
 *
 * search_start -- an allocation hint for the new block
 *
 * empty_size -- a hint that you plan on doing more cow.  This is the size in
 * bytes the allocator should try to find free next to the block it returns.
 * This is just a hint and may be ignored by the allocator.
 */
static noinline int __btrfs_cow_block(struct btrfs_trans_handle *trans,
                             struct btrfs_root *root,
                             struct extent_buffer *buf,
                             struct extent_buffer *parent, int parent_slot,
                             struct extent_buffer **cow_ret,
                             u64 search_start, u64 empty_size,
                             enum btrfs_lock_nesting nest)
{
        struct btrfs_fs_info *fs_info = root->fs_info;
        struct btrfs_disk_key disk_key;
        struct extent_buffer *cow;
        int level, ret;
        int last_ref = 0;
        int unlock_orig = 0;
        u64 parent_start = 0;

        if (*cow_ret == buf)
                unlock_orig = 1;

        btrfs_assert_tree_locked(buf);

        WARN_ON(test_bit(BTRFS_ROOT_SHAREABLE, &root->state) &&
                trans->transid != fs_info->running_transaction->transid);
        WARN_ON(test_bit(BTRFS_ROOT_SHAREABLE, &root->state) &&
                trans->transid != root->last_trans);

        level = btrfs_header_level(buf);

        if (level == 0)
                btrfs_item_key(buf, &disk_key, 0);
        else
                btrfs_node_key(buf, &disk_key, 0);

        if ((root->root_key.objectid == BTRFS_TREE_RELOC_OBJECTID) && parent)
                parent_start = parent->start;

        cow = btrfs_alloc_tree_block(trans, root, parent_start,
                                     root->root_key.objectid, &disk_key, level,
                                     search_start, empty_size, nest);
        if (IS_ERR(cow))
                return PTR_ERR(cow);

        /* cow is set to blocking by btrfs_init_new_buffer */

        copy_extent_buffer_full(cow, buf);
        btrfs_set_header_bytenr(cow, cow->start);
        btrfs_set_header_generation(cow, trans->transid);
        btrfs_set_header_backref_rev(cow, BTRFS_MIXED_BACKREF_REV);
        btrfs_clear_header_flag(cow, BTRFS_HEADER_FLAG_WRITTEN |
                                     BTRFS_HEADER_FLAG_RELOC);
        if (root->root_key.objectid == BTRFS_TREE_RELOC_OBJECTID)
                btrfs_set_header_flag(cow, BTRFS_HEADER_FLAG_RELOC);
        else
                btrfs_set_header_owner(cow, root->root_key.objectid);

        write_extent_buffer_fsid(cow, fs_info->fs_devices->metadata_uuid);

        ret = update_ref_for_cow(trans, root, buf, cow, &last_ref);
        if (ret) {
                btrfs_tree_unlock(cow);
                free_extent_buffer(cow);
                btrfs_abort_transaction(trans, ret);
                return ret;
        }

        if (test_bit(BTRFS_ROOT_SHAREABLE, &root->state)) {
                ret = btrfs_reloc_cow_block(trans, root, buf, cow);
                if (ret) {
                        btrfs_tree_unlock(cow);
                        free_extent_buffer(cow);
                        btrfs_abort_transaction(trans, ret);
                        return ret;
                }
        }

        if (buf == root->node) {
                WARN_ON(parent && parent != buf);
                if (root->root_key.objectid == BTRFS_TREE_RELOC_OBJECTID ||
                    btrfs_header_backref_rev(buf) < BTRFS_MIXED_BACKREF_REV)
                        parent_start = buf->start;

                atomic_inc(&cow->refs);
                ret = btrfs_tree_mod_log_insert_root(root->node, cow, true);
                BUG_ON(ret < 0);
                rcu_assign_pointer(root->node, cow);

                btrfs_free_tree_block(trans, root, buf, parent_start,
                                      last_ref);
                free_extent_buffer(buf);
                add_root_to_dirty_list(root);
        } else {
                WARN_ON(trans->transid != btrfs_header_generation(parent));
                btrfs_tree_mod_log_insert_key(parent, parent_slot,
                                              BTRFS_MOD_LOG_KEY_REPLACE, GFP_NOFS);
                btrfs_set_node_blockptr(parent, parent_slot,
                                        cow->start);
                btrfs_set_node_ptr_generation(parent, parent_slot,
                                              trans->transid);
                btrfs_mark_buffer_dirty(parent);
                if (last_ref) {
                        ret = btrfs_tree_mod_log_free_eb(buf);
                        if (ret) {
                                btrfs_tree_unlock(cow);
                                free_extent_buffer(cow);
                                btrfs_abort_transaction(trans, ret);
                                return ret;
                        }
                }
                btrfs_free_tree_block(trans, root, buf, parent_start,
                                      last_ref);
        }
        if (unlock_orig)
                btrfs_tree_unlock(buf);
        free_extent_buffer_stale(buf);
        btrfs_mark_buffer_dirty(cow);
        *cow_ret = cow;
        return 0;
}

static inline int should_cow_block(struct btrfs_trans_handle *trans,
                                   struct btrfs_root *root,
                                   struct extent_buffer *buf)
{
        if (btrfs_is_testing(root->fs_info))
                return 0;

        /* Ensure we can see the FORCE_COW bit */
        smp_mb__before_atomic();

        /*
         * We do not need to cow a block if
         * 1) this block is not created or changed in this transaction;
         * 2) this block does not belong to TREE_RELOC tree;
         * 3) the root is not forced COW.
         *
         * What is forced COW:
         *    when we create snapshot during committing the transaction,
         *    after we've finished copying src root, we must COW the shared
         *    block to ensure the metadata consistency.
         */
        if (btrfs_header_generation(buf) == trans->transid &&
            !btrfs_header_flag(buf, BTRFS_HEADER_FLAG_WRITTEN) &&
            !(root->root_key.objectid != BTRFS_TREE_RELOC_OBJECTID &&
              btrfs_header_flag(buf, BTRFS_HEADER_FLAG_RELOC)) &&
            !test_bit(BTRFS_ROOT_FORCE_COW, &root->state))
                return 0;
        return 1;
}

/*
 * cows a single block, see __btrfs_cow_block for the real work.
 * This version of it has extra checks so that a block isn't COWed more than
 * once per transaction, as long as it hasn't been written yet
 */
noinline int btrfs_cow_block(struct btrfs_trans_handle *trans,
                    struct btrfs_root *root, struct extent_buffer *buf,
                    struct extent_buffer *parent, int parent_slot,
                    struct extent_buffer **cow_ret,
                    enum btrfs_lock_nesting nest)
{
        struct btrfs_fs_info *fs_info = root->fs_info;
        u64 search_start;
        int ret;

        if (test_bit(BTRFS_ROOT_DELETING, &root->state))
                btrfs_err(fs_info,
                        "COW'ing blocks on a fs root that's being dropped");

        if (trans->transaction != fs_info->running_transaction)
                WARN(1, KERN_CRIT "trans %llu running %llu\n",
                       trans->transid,
                       fs_info->running_transaction->transid);

        if (trans->transid != fs_info->generation)
                WARN(1, KERN_CRIT "trans %llu running %llu\n",
                       trans->transid, fs_info->generation);

        if (!should_cow_block(trans, root, buf)) {
                *cow_ret = buf;
                return 0;
        }

        search_start = buf->start & ~((u64)SZ_1G - 1);

        /*
         * Before CoWing this block for later modification, check if it's
         * the subtree root and do the delayed subtree trace if needed.
         *
         * Also We don't care about the error, as it's handled internally.
         */
        btrfs_qgroup_trace_subtree_after_cow(trans, root, buf);
        ret = __btrfs_cow_block(trans, root, buf, parent,
                                 parent_slot, cow_ret, search_start, 0, nest);

        trace_btrfs_cow_block(root, buf, *cow_ret);

        return ret;
}
ALLOW_ERROR_INJECTION(btrfs_cow_block, ERRNO);

/*
 * helper function for defrag to decide if two blocks pointed to by a
 * node are actually close by
 */
static int close_blocks(u64 blocknr, u64 other, u32 blocksize)
{
        if (blocknr < other && other - (blocknr + blocksize) < 32768)
                return 1;
        if (blocknr > other && blocknr - (other + blocksize) < 32768)
                return 1;
        return 0;
}

#ifdef __LITTLE_ENDIAN

/*
 * Compare two keys, on little-endian the disk order is same as CPU order and
 * we can avoid the conversion.
 */
static int comp_keys(const struct btrfs_disk_key *disk_key,
                     const struct btrfs_key *k2)
{
        const struct btrfs_key *k1 = (const struct btrfs_key *)disk_key;

        return btrfs_comp_cpu_keys(k1, k2);
}

#else

/*
 * compare two keys in a memcmp fashion
 */
static int comp_keys(const struct btrfs_disk_key *disk,
                     const struct btrfs_key *k2)
{
        struct btrfs_key k1;

        btrfs_disk_key_to_cpu(&k1, disk);

        return btrfs_comp_cpu_keys(&k1, k2);
}
#endif

/*
 * same as comp_keys only with two btrfs_key's
 */
int __pure btrfs_comp_cpu_keys(const struct btrfs_key *k1, const struct btrfs_key *k2)
{
        if (k1->objectid > k2->objectid)
                return 1;
        if (k1->objectid < k2->objectid)
                return -1;
        if (k1->type > k2->type)
                return 1;
        if (k1->type < k2->type)
                return -1;
        if (k1->offset > k2->offset)
                return 1;
        if (k1->offset < k2->offset)
                return -1;
        return 0;
}

/*
 * this is used by the defrag code to go through all the
 * leaves pointed to by a node and reallocate them so that
 * disk order is close to key order
 */
int btrfs_realloc_node(struct btrfs_trans_handle *trans,
                       struct btrfs_root *root, struct extent_buffer *parent,
                       int start_slot, u64 *last_ret,
                       struct btrfs_key *progress)
{
        struct btrfs_fs_info *fs_info = root->fs_info;
        struct extent_buffer *cur;
        u64 blocknr;
        u64 search_start = *last_ret;
        u64 last_block = 0;
        u64 other;
        u32 parent_nritems;
        int end_slot;
        int i;
        int err = 0;
        u32 blocksize;
        int progress_passed = 0;
        struct btrfs_disk_key disk_key;

        WARN_ON(trans->transaction != fs_info->running_transaction);
        WARN_ON(trans->transid != fs_info->generation);

        parent_nritems = btrfs_header_nritems(parent);
        blocksize = fs_info->nodesize;
        end_slot = parent_nritems - 1;

        if (parent_nritems <= 1)
                return 0;

        for (i = start_slot; i <= end_slot; i++) {
                int close = 1;

                btrfs_node_key(parent, &disk_key, i);
                if (!progress_passed && comp_keys(&disk_key, progress) < 0)
                        continue;

                progress_passed = 1;
                blocknr = btrfs_node_blockptr(parent, i);
                if (last_block == 0)
                        last_block = blocknr;

                if (i > 0) {
                        other = btrfs_node_blockptr(parent, i - 1);
                        close = close_blocks(blocknr, other, blocksize);
                }
                if (!close && i < end_slot) {
                        other = btrfs_node_blockptr(parent, i + 1);
                        close = close_blocks(blocknr, other, blocksize);
                }
                if (close) {
                        last_block = blocknr;
                        continue;
                }

                cur = btrfs_read_node_slot(parent, i);
                if (IS_ERR(cur))
                        return PTR_ERR(cur);
                if (search_start == 0)
                        search_start = last_block;

                btrfs_tree_lock(cur);
                err = __btrfs_cow_block(trans, root, cur, parent, i,
                                        &cur, search_start,
                                        min(16 * blocksize,
                                            (end_slot - i) * blocksize),
                                        BTRFS_NESTING_COW);
                if (err) {
                        btrfs_tree_unlock(cur);
                        free_extent_buffer(cur);
                        break;
                }
                search_start = cur->start;
                last_block = cur->start;
                *last_ret = search_start;
                btrfs_tree_unlock(cur);
                free_extent_buffer(cur);
        }
        return err;
}

/*
 * search for key in the extent_buffer.  The items start at offset p,
 * and they are item_size apart.  There are 'max' items in p.
 *
 * the slot in the array is returned via slot, and it points to
 * the place where you would insert key if it is not found in
 * the array.
 *
 * slot may point to max if the key is bigger than all of the keys
 */
static noinline int generic_bin_search(struct extent_buffer *eb,
                                       unsigned long p, int item_size,
                                       const struct btrfs_key *key,
                                       int max, int *slot)
{
        int low = 0;
        int high = max;
        int ret;
        const int key_size = sizeof(struct btrfs_disk_key);

        if (low > high) {
                btrfs_err(eb->fs_info,
                 "%s: low (%d) > high (%d) eb %llu owner %llu level %d",
                          __func__, low, high, eb->start,
                          btrfs_header_owner(eb), btrfs_header_level(eb));
                return -EINVAL;
        }

        while (low < high) {
                unsigned long oip;
                unsigned long offset;
                struct btrfs_disk_key *tmp;
                struct btrfs_disk_key unaligned;
                int mid;

                mid = (low + high) / 2;
                offset = p + mid * item_size;
                oip = offset_in_page(offset);

                if (oip + key_size <= PAGE_SIZE) {
                        const unsigned long idx = get_eb_page_index(offset);
                        char *kaddr = page_address(eb->pages[idx]);

                        oip = get_eb_offset_in_page(eb, offset);
                        tmp = (struct btrfs_disk_key *)(kaddr + oip);
                } else {
                        read_extent_buffer(eb, &unaligned, offset, key_size);
                        tmp = &unaligned;
                }

                ret = comp_keys(tmp, key);

                if (ret < 0)
                        low = mid + 1;
                else if (ret > 0)
                        high = mid;
                else {
                        *slot = mid;
                        return 0;
                }
        }
        *slot = low;
        return 1;
}

/*
 * simple bin_search frontend that does the right thing for
 * leaves vs nodes
 */
int btrfs_bin_search(struct extent_buffer *eb, const struct btrfs_key *key,
                     int *slot)
{
        if (btrfs_header_level(eb) == 0)
                return generic_bin_search(eb,
                                          offsetof(struct btrfs_leaf, items),
                                          sizeof(struct btrfs_item),
                                          key, btrfs_header_nritems(eb),
                                          slot);
        else
                return generic_bin_search(eb,
                                          offsetof(struct btrfs_node, ptrs),
                                          sizeof(struct btrfs_key_ptr),
                                          key, btrfs_header_nritems(eb),
                                          slot);
}

static void root_add_used(struct btrfs_root *root, u32 size)
{
        spin_lock(&root->accounting_lock);
        btrfs_set_root_used(&root->root_item,
                            btrfs_root_used(&root->root_item) + size);
        spin_unlock(&root->accounting_lock);
}

static void root_sub_used(struct btrfs_root *root, u32 size)
{
        spin_lock(&root->accounting_lock);
        btrfs_set_root_used(&root->root_item,
                            btrfs_root_used(&root->root_item) - size);
        spin_unlock(&root->accounting_lock);
}

/* given a node and slot number, this reads the blocks it points to.  The
 * extent buffer is returned with a reference taken (but unlocked).
 */
struct extent_buffer *btrfs_read_node_slot(struct extent_buffer *parent,
                                           int slot)
{
        int level = btrfs_header_level(parent);
        struct extent_buffer *eb;
        struct btrfs_key first_key;

        if (slot < 0 || slot >= btrfs_header_nritems(parent))
                return ERR_PTR(-ENOENT);

        BUG_ON(level == 0);

        btrfs_node_key_to_cpu(parent, &first_key, slot);
        eb = read_tree_block(parent->fs_info, btrfs_node_blockptr(parent, slot),
                             btrfs_header_owner(parent),
                             btrfs_node_ptr_generation(parent, slot),
                             level - 1, &first_key);
        if (!IS_ERR(eb) && !extent_buffer_uptodate(eb)) {
                free_extent_buffer(eb);
                eb = ERR_PTR(-EIO);
        }

        return eb;
}

/*
 * node level balancing, used to make sure nodes are in proper order for
 * item deletion.  We balance from the top down, so we have to make sure
 * that a deletion won't leave an node completely empty later on.
 */
static noinline int balance_level(struct btrfs_trans_handle *trans,
                         struct btrfs_root *root,
                         struct btrfs_path *path, int level)
{
        struct btrfs_fs_info *fs_info = root->fs_info;
        struct extent_buffer *right = NULL;
        struct extent_buffer *mid;
        struct extent_buffer *left = NULL;
        struct extent_buffer *parent = NULL;
        int ret = 0;
        int wret;
        int pslot;
        int orig_slot = path->slots[level];
        u64 orig_ptr;

        ASSERT(level > 0);

        mid = path->nodes[level];

        WARN_ON(path->locks[level] != BTRFS_WRITE_LOCK);
        WARN_ON(btrfs_header_generation(mid) != trans->transid);

        orig_ptr = btrfs_node_blockptr(mid, orig_slot);

        if (level < BTRFS_MAX_LEVEL - 1) {
                parent = path->nodes[level + 1];
                pslot = path->slots[level + 1];
        }

        /*
         * deal with the case where there is only one pointer in the root
         * by promoting the node below to a root
         */
        if (!parent) {
                struct extent_buffer *child;

                if (btrfs_header_nritems(mid) != 1)
                        return 0;

                /* promote the child to a root */
                child = btrfs_read_node_slot(mid, 0);
                if (IS_ERR(child)) {
                        ret = PTR_ERR(child);
                        btrfs_handle_fs_error(fs_info, ret, NULL);
                        goto enospc;
                }

                btrfs_tree_lock(child);
                ret = btrfs_cow_block(trans, root, child, mid, 0, &child,
                                      BTRFS_NESTING_COW);
                if (ret) {
                        btrfs_tree_unlock(child);
                        free_extent_buffer(child);
                        goto enospc;
                }

                ret = btrfs_tree_mod_log_insert_root(root->node, child, true);
                BUG_ON(ret < 0);
                rcu_assign_pointer(root->node, child);

                add_root_to_dirty_list(root);
                btrfs_tree_unlock(child);

                path->locks[level] = 0;
                path->nodes[level] = NULL;
                btrfs_clean_tree_block(mid);
                btrfs_tree_unlock(mid);
                /* once for the path */
                free_extent_buffer(mid);

                root_sub_used(root, mid->len);
                btrfs_free_tree_block(trans, root, mid, 0, 1);
                /* once for the root ptr */
                free_extent_buffer_stale(mid);
                return 0;
        }
        if (btrfs_header_nritems(mid) >
            BTRFS_NODEPTRS_PER_BLOCK(fs_info) / 4)
                return 0;

        left = btrfs_read_node_slot(parent, pslot - 1);
        if (IS_ERR(left))
                left = NULL;

        if (left) {
                __btrfs_tree_lock(left, BTRFS_NESTING_LEFT);
                wret = btrfs_cow_block(trans, root, left,
                                       parent, pslot - 1, &left,
                                       BTRFS_NESTING_LEFT_COW);
                if (wret) {
                        ret = wret;
                        goto enospc;
                }
        }

        right = btrfs_read_node_slot(parent, pslot + 1);
        if (IS_ERR(right))
                right = NULL;

        if (right) {
                __btrfs_tree_lock(right, BTRFS_NESTING_RIGHT);
                wret = btrfs_cow_block(trans, root, right,
                                       parent, pslot + 1, &right,
                                       BTRFS_NESTING_RIGHT_COW);
                if (wret) {
                        ret = wret;
                        goto enospc;
                }
        }

        /* first, try to make some room in the middle buffer */
        if (left) {
                orig_slot += btrfs_header_nritems(left);
                wret = push_node_left(trans, left, mid, 1);
                if (wret < 0)
                        ret = wret;
        }

        /*
         * then try to empty the right most buffer into the middle
         */
        if (right) {
                wret = push_node_left(trans, mid, right, 1);
                if (wret < 0 && wret != -ENOSPC)
                        ret = wret;
                if (btrfs_header_nritems(right) == 0) {
                        btrfs_clean_tree_block(right);
                        btrfs_tree_unlock(right);
                        del_ptr(root, path, level + 1, pslot + 1);
                        root_sub_used(root, right->len);
                        btrfs_free_tree_block(trans, root, right, 0, 1);
                        free_extent_buffer_stale(right);
                        right = NULL;
                } else {
                        struct btrfs_disk_key right_key;
                        btrfs_node_key(right, &right_key, 0);
                        ret = btrfs_tree_mod_log_insert_key(parent, pslot + 1,
                                        BTRFS_MOD_LOG_KEY_REPLACE, GFP_NOFS);
                        BUG_ON(ret < 0);

                        btrfs_set_node_key(parent, &right_key, pslot + 1);
                        btrfs_mark_buffer_dirty(parent);
                }
        }
        if (btrfs_header_nritems(mid) == 1) {
                /*
                 * we're not allowed to leave a node with one item in the
                 * tree during a delete.  A deletion from lower in the tree
                 * could try to delete the only pointer in this node.
                 * So, pull some keys from the left.
                 * There has to be a left pointer at this point because
                 * otherwise we would have pulled some pointers from the
                 * right
                 */
                if (!left) {
                        ret = -EROFS;
                        btrfs_handle_fs_error(fs_info, ret, NULL);
                        goto enospc;
                }
                wret = balance_node_right(trans, mid, left);
                if (wret < 0) {
                        ret = wret;
                        goto enospc;
                }
                if (wret == 1) {
                        wret = push_node_left(trans, left, mid, 1);
                        if (wret < 0)
                                ret = wret;
                }
                BUG_ON(wret == 1);
        }
        if (btrfs_header_nritems(mid) == 0) {
                btrfs_clean_tree_block(mid);
                btrfs_tree_unlock(mid);
                del_ptr(root, path, level + 1, pslot);
                root_sub_used(root, mid->len);
                btrfs_free_tree_block(trans, root, mid, 0, 1);
                free_extent_buffer_stale(mid);
                mid = NULL;
        } else {
                /* update the parent key to reflect our changes */
                struct btrfs_disk_key mid_key;
                btrfs_node_key(mid, &mid_key, 0);
                ret = btrfs_tree_mod_log_insert_key(parent, pslot,
                                BTRFS_MOD_LOG_KEY_REPLACE, GFP_NOFS);
                BUG_ON(ret < 0);
                btrfs_set_node_key(parent, &mid_key, pslot);
                btrfs_mark_buffer_dirty(parent);
        }

        /* update the path */
        if (left) {
                if (btrfs_header_nritems(left) > orig_slot) {
                        atomic_inc(&left->refs);
                        /* left was locked after cow */
                        path->nodes[level] = left;
                        path->slots[level + 1] -= 1;
                        path->slots[level] = orig_slot;
                        if (mid) {
                                btrfs_tree_unlock(mid);
                                free_extent_buffer(mid);
                        }
                } else {
                        orig_slot -= btrfs_header_nritems(left);
                        path->slots[level] = orig_slot;
                }
        }
        /* double check we haven't messed things up */
        if (orig_ptr !=
            btrfs_node_blockptr(path->nodes[level], path->slots[level]))
                BUG();
enospc:
        if (right) {
                btrfs_tree_unlock(right);
                free_extent_buffer(right);
        }
        if (left) {
                if (path->nodes[level] != left)
                        btrfs_tree_unlock(left);
                free_extent_buffer(left);
        }
        return ret;
}

/* Node balancing for insertion.  Here we only split or push nodes around
 * when they are completely full.  This is also done top down, so we
 * have to be pessimistic.
 */
static noinline int push_nodes_for_insert(struct btrfs_trans_handle *trans,
                                          struct btrfs_root *root,
                                          struct btrfs_path *path, int level)
{
        struct btrfs_fs_info *fs_info = root->fs_info;
        struct extent_buffer *right = NULL;
        struct extent_buffer *mid;
        struct extent_buffer *left = NULL;
        struct extent_buffer *parent = NULL;
        int ret = 0;
        int wret;
        int pslot;
        int orig_slot = path->slots[level];

        if (level == 0)
                return 1;

        mid = path->nodes[level];
        WARN_ON(btrfs_header_generation(mid) != trans->transid);

        if (level < BTRFS_MAX_LEVEL - 1) {
                parent = path->nodes[level + 1];
                pslot = path->slots[level + 1];
        }

        if (!parent)
                return 1;

        left = btrfs_read_node_slot(parent, pslot - 1);
        if (IS_ERR(left))
                left = NULL;

        /* first, try to make some room in the middle buffer */
        if (left) {
                u32 left_nr;

                __btrfs_tree_lock(left, BTRFS_NESTING_LEFT);

                left_nr = btrfs_header_nritems(left);
                if (left_nr >= BTRFS_NODEPTRS_PER_BLOCK(fs_info) - 1) {
                        wret = 1;
                } else {
                        ret = btrfs_cow_block(trans, root, left, parent,
                                              pslot - 1, &left,
                                              BTRFS_NESTING_LEFT_COW);
                        if (ret)
                                wret = 1;
                        else {
                                wret = push_node_left(trans, left, mid, 0);
                        }
                }
                if (wret < 0)
                        ret = wret;
                if (wret == 0) {
                        struct btrfs_disk_key disk_key;
                        orig_slot += left_nr;
                        btrfs_node_key(mid, &disk_key, 0);
                        ret = btrfs_tree_mod_log_insert_key(parent, pslot,
                                        BTRFS_MOD_LOG_KEY_REPLACE, GFP_NOFS);
                        BUG_ON(ret < 0);
                        btrfs_set_node_key(parent, &disk_key, pslot);
                        btrfs_mark_buffer_dirty(parent);
                        if (btrfs_header_nritems(left) > orig_slot) {
                                path->nodes[level] = left;
                                path->slots[level + 1] -= 1;
                                path->slots[level] = orig_slot;
                                btrfs_tree_unlock(mid);
                                free_extent_buffer(mid);
                        } else {
                                orig_slot -=
                                        btrfs_header_nritems(left);
                                path->slots[level] = orig_slot;
                                btrfs_tree_unlock(left);
                                free_extent_buffer(left);
                        }
                        return 0;
                }
                btrfs_tree_unlock(left);
                free_extent_buffer(left);
        }
        right = btrfs_read_node_slot(parent, pslot + 1);
        if (IS_ERR(right))
                right = NULL;

        /*
         * then try to empty the right most buffer into the middle
         */
        if (right) {
                u32 right_nr;

                __btrfs_tree_lock(right, BTRFS_NESTING_RIGHT);

                right_nr = btrfs_header_nritems(right);
                if (right_nr >= BTRFS_NODEPTRS_PER_BLOCK(fs_info) - 1) {
                        wret = 1;
                } else {
                        ret = btrfs_cow_block(trans, root, right,
                                              parent, pslot + 1,
                                              &right, BTRFS_NESTING_RIGHT_COW);
                        if (ret)
                                wret = 1;
                        else {
                                wret = balance_node_right(trans, right, mid);
                        }
                }
                if (wret < 0)
                        ret = wret;
                if (wret == 0) {
                        struct btrfs_disk_key disk_key;

                        btrfs_node_key(right, &disk_key, 0);
                        ret = btrfs_tree_mod_log_insert_key(parent, pslot + 1,
                                        BTRFS_MOD_LOG_KEY_REPLACE, GFP_NOFS);
                        BUG_ON(ret < 0);
                        btrfs_set_node_key(parent, &disk_key, pslot + 1);
                        btrfs_mark_buffer_dirty(parent);

                        if (btrfs_header_nritems(mid) <= orig_slot) {
                                path->nodes[level] = right;
                                path->slots[level + 1] += 1;
                                path->slots[level] = orig_slot -
                                        btrfs_header_nritems(mid);
                                btrfs_tree_unlock(mid);
                                free_extent_buffer(mid);
                        } else {
                                btrfs_tree_unlock(right);
                                free_extent_buffer(right);
                        }
                        return 0;
                }
                btrfs_tree_unlock(right);
                free_extent_buffer(right);
        }
        return 1;
}

/*
 * readahead one full node of leaves, finding things that are close
 * to the block in 'slot', and triggering ra on them.
 */
static void reada_for_search(struct btrfs_fs_info *fs_info,
                             struct btrfs_path *path,
                             int level, int slot, u64 objectid)
{
        struct extent_buffer *node;
        struct btrfs_disk_key disk_key;
        u32 nritems;
        u64 search;
        u64 target;
        u64 nread = 0;
        u64 nread_max;
        struct extent_buffer *eb;
        u32 nr;
        u32 blocksize;
        u32 nscan = 0;

        if (level != 1 && path->reada != READA_FORWARD_ALWAYS)
                return;

        if (!path->nodes[level])
                return;

        node = path->nodes[level];

        /*
         * Since the time between visiting leaves is much shorter than the time
         * between visiting nodes, limit read ahead of nodes to 1, to avoid too
         * much IO at once (possibly random).
         */
        if (path->reada == READA_FORWARD_ALWAYS) {
                if (level > 1)
                        nread_max = node->fs_info->nodesize;
                else
                        nread_max = SZ_128K;
        } else {
                nread_max = SZ_64K;
        }

        search = btrfs_node_blockptr(node, slot);
        blocksize = fs_info->nodesize;
        eb = find_extent_buffer(fs_info, search);
        if (eb) {
                free_extent_buffer(eb);
                return;
        }

        target = search;

        nritems = btrfs_header_nritems(node);
        nr = slot;

        while (1) {
                if (path->reada == READA_BACK) {
                        if (nr == 0)
                                break;
                        nr--;
                } else if (path->reada == READA_FORWARD ||
                           path->reada == READA_FORWARD_ALWAYS) {
                        nr++;
                        if (nr >= nritems)
                                break;
                }
                if (path->reada == READA_BACK && objectid) {
                        btrfs_node_key(node, &disk_key, nr);
                        if (btrfs_disk_key_objectid(&disk_key) != objectid)
                                break;
                }
                search = btrfs_node_blockptr(node, nr);
                if (path->reada == READA_FORWARD_ALWAYS ||
                    (search <= target && target - search <= 65536) ||
                    (search > target && search - target <= 65536)) {
                        btrfs_readahead_node_child(node, nr);
                        nread += blocksize;
                }
                nscan++;
                if (nread > nread_max || nscan > 32)
                        break;
        }
}

static noinline void reada_for_balance(struct btrfs_path *path, int level)
{
        struct extent_buffer *parent;
        int slot;
        int nritems;

        parent = path->nodes[level + 1];
        if (!parent)
                return;

        nritems = btrfs_header_nritems(parent);
        slot = path->slots[level + 1];

        if (slot > 0)
                btrfs_readahead_node_child(parent, slot - 1);
        if (slot + 1 < nritems)
                btrfs_readahead_node_child(parent, slot + 1);
}


/*
 * when we walk down the tree, it is usually safe to unlock the higher layers
 * in the tree.  The exceptions are when our path goes through slot 0, because
 * operations on the tree might require changing key pointers higher up in the
 * tree.
 *
 * callers might also have set path->keep_locks, which tells this code to keep
 * the lock if the path points to the last slot in the block.  This is part of
 * walking through the tree, and selecting the next slot in the higher block.
 *
 * lowest_unlock sets the lowest level in the tree we're allowed to unlock.  so
 * if lowest_unlock is 1, level 0 won't be unlocked
 */
static noinline void unlock_up(struct btrfs_path *path, int level,
                               int lowest_unlock, int min_write_lock_level,
                               int *write_lock_level)
{
        int i;
        int skip_level = level;
        int no_skips = 0;
        struct extent_buffer *t;

        for (i = level; i < BTRFS_MAX_LEVEL; i++) {
                if (!path->nodes[i])
                        break;
                if (!path->locks[i])
                        break;
                if (!no_skips && path->slots[i] == 0) {
                        skip_level = i + 1;
                        continue;
                }
                if (!no_skips && path->keep_locks) {
                        u32 nritems;
                        t = path->nodes[i];
                        nritems = btrfs_header_nritems(t);
                        if (nritems < 1 || path->slots[i] >= nritems - 1) {
                                skip_level = i + 1;
                                continue;
                        }
                }
                if (skip_level < i && i >= lowest_unlock)
                        no_skips = 1;

                t = path->nodes[i];
                if (i >= lowest_unlock && i > skip_level) {
                        btrfs_tree_unlock_rw(t, path->locks[i]);
                        path->locks[i] = 0;
                        if (write_lock_level &&
                            i > min_write_lock_level &&
                            i <= *write_lock_level) {
                                *write_lock_level = i - 1;
                        }
                }
        }
}

/*
 * helper function for btrfs_search_slot.  The goal is to find a block
 * in cache without setting the path to blocking.  If we find the block
 * we return zero and the path is unchanged.
 *
 * If we can't find the block, we set the path blocking and do some
 * reada.  -EAGAIN is returned and the search must be repeated.
 */
static int
read_block_for_search(struct btrfs_root *root, struct btrfs_path *p,
                      struct extent_buffer **eb_ret, int level, int slot,
                      const struct btrfs_key *key)
{
        struct btrfs_fs_info *fs_info = root->fs_info;
        u64 blocknr;
        u64 gen;
        struct extent_buffer *tmp;
        struct btrfs_key first_key;
        int ret;
        int parent_level;

        blocknr = btrfs_node_blockptr(*eb_ret, slot);
        gen = btrfs_node_ptr_generation(*eb_ret, slot);
        parent_level = btrfs_header_level(*eb_ret);
        btrfs_node_key_to_cpu(*eb_ret, &first_key, slot);

        tmp = find_extent_buffer(fs_info, blocknr);
        if (tmp) {
                if (p->reada == READA_FORWARD_ALWAYS)
                        reada_for_search(fs_info, p, level, slot, key->objectid);

                /* first we do an atomic uptodate check */
                if (btrfs_buffer_uptodate(tmp, gen, 1) > 0) {
                        /*
                         * Do extra check for first_key, eb can be stale due to
                         * being cached, read from scrub, or have multiple
                         * parents (shared tree blocks).
                         */
                        if (btrfs_verify_level_key(tmp,
                                        parent_level - 1, &first_key, gen)) {
                                free_extent_buffer(tmp);
                                return -EUCLEAN;
                        }
                        *eb_ret = tmp;
                        return 0;
                }

                /* now we're allowed to do a blocking uptodate check */
                ret = btrfs_read_buffer(tmp, gen, parent_level - 1, &first_key);
                if (!ret) {
                        *eb_ret = tmp;
                        return 0;
                }
                free_extent_buffer(tmp);
                btrfs_release_path(p);
                return -EIO;
        }

        /*
         * reduce lock contention at high levels
         * of the btree by dropping locks before
         * we read.  Don't release the lock on the current
         * level because we need to walk this node to figure
         * out which blocks to read.
         */
        btrfs_unlock_up_safe(p, level + 1);

        if (p->reada != READA_NONE)
                reada_for_search(fs_info, p, level, slot, key->objectid);

        ret = -EAGAIN;
        tmp = read_tree_block(fs_info, blocknr, root->root_key.objectid,
                              gen, parent_level - 1, &first_key);
        if (!IS_ERR(tmp)) {
                /*
                 * If the read above didn't mark this buffer up to date,
                 * it will never end up being up to date.  Set ret to EIO now
                 * and give up so that our caller doesn't loop forever
                 * on our EAGAINs.
                 */
                if (!extent_buffer_uptodate(tmp))
                        ret = -EIO;
                free_extent_buffer(tmp);
        } else {
                ret = PTR_ERR(tmp);
        }

        btrfs_release_path(p);
        return ret;
}

/*
 * helper function for btrfs_search_slot.  This does all of the checks
 * for node-level blocks and does any balancing required based on
 * the ins_len.
 *
 * If no extra work was required, zero is returned.  If we had to
 * drop the path, -EAGAIN is returned and btrfs_search_slot must
 * start over
 */
static int
setup_nodes_for_search(struct btrfs_trans_handle *trans,
                       struct btrfs_root *root, struct btrfs_path *p,
                       struct extent_buffer *b, int level, int ins_len,
                       int *write_lock_level)
{
        struct btrfs_fs_info *fs_info = root->fs_info;
        int ret = 0;

        if ((p->search_for_split || ins_len > 0) && btrfs_header_nritems(b) >=
            BTRFS_NODEPTRS_PER_BLOCK(fs_info) - 3) {

                if (*write_lock_level < level + 1) {
                        *write_lock_level = level + 1;
                        btrfs_release_path(p);
                        return -EAGAIN;
                }

                reada_for_balance(p, level);
                ret = split_node(trans, root, p, level);

                b = p->nodes[level];
        } else if (ins_len < 0 && btrfs_header_nritems(b) <
                   BTRFS_NODEPTRS_PER_BLOCK(fs_info) / 2) {

                if (*write_lock_level < level + 1) {
                        *write_lock_level = level + 1;
                        btrfs_release_path(p);
                        return -EAGAIN;
                }

                reada_for_balance(p, level);
                ret = balance_level(trans, root, p, level);
                if (ret)
                        return ret;

                b = p->nodes[level];
                if (!b) {
                        btrfs_release_path(p);
                        return -EAGAIN;
                }
                BUG_ON(btrfs_header_nritems(b) == 1);
        }
        return ret;
}

int btrfs_find_item(struct btrfs_root *fs_root, struct btrfs_path *path,
                u64 iobjectid, u64 ioff, u8 key_type,
                struct btrfs_key *found_key)
{
        int ret;
        struct btrfs_key key;
        struct extent_buffer *eb;

        ASSERT(path);
        ASSERT(found_key);

        key.type = key_type;
        key.objectid = iobjectid;
        key.offset = ioff;

        ret = btrfs_search_slot(NULL, fs_root, &key, path, 0, 0);
        if (ret < 0)
                return ret;

        eb = path->nodes[0];
        if (ret && path->slots[0] >= btrfs_header_nritems(eb)) {
                ret = btrfs_next_leaf(fs_root, path);
                if (ret)
                        return ret;
                eb = path->nodes[0];
        }

        btrfs_item_key_to_cpu(eb, found_key, path->slots[0]);
        if (found_key->type != key.type ||
                        found_key->objectid != key.objectid)
                return 1;

        return 0;
}

static struct extent_buffer *btrfs_search_slot_get_root(struct btrfs_root *root,
                                                        struct btrfs_path *p,
                                                        int write_lock_level)
{
        struct btrfs_fs_info *fs_info = root->fs_info;
        struct extent_buffer *b;
        int root_lock;
        int level = 0;

        /* We try very hard to do read locks on the root */
        root_lock = BTRFS_READ_LOCK;

        if (p->search_commit_root) {
                /*
                 * The commit roots are read only so we always do read locks,
                 * and we always must hold the commit_root_sem when doing
                 * searches on them, the only exception is send where we don't
                 * want to block transaction commits for a long time, so
                 * we need to clone the commit root in order to avoid races
                 * with transaction commits that create a snapshot of one of
                 * the roots used by a send operation.
                 */
                if (p->need_commit_sem) {
                        down_read(&fs_info->commit_root_sem);
                        b = btrfs_clone_extent_buffer(root->commit_root);
                        up_read(&fs_info->commit_root_sem);
                        if (!b)
                                return ERR_PTR(-ENOMEM);

                } else {
                        b = root->commit_root;
                        atomic_inc(&b->refs);
                }
                level = btrfs_header_level(b);
                /*
                 * Ensure that all callers have set skip_locking when
                 * p->search_commit_root = 1.
                 */
                ASSERT(p->skip_locking == 1);

                goto out;
        }

        if (p->skip_locking) {
                b = btrfs_root_node(root);
                level = btrfs_header_level(b);
                goto out;
        }

        /*
         * If the level is set to maximum, we can skip trying to get the read
         * lock.
         */
        if (write_lock_level < BTRFS_MAX_LEVEL) {
                /*
                 * We don't know the level of the root node until we actually
                 * have it read locked
                 */
                b = btrfs_read_lock_root_node(root);
                level = btrfs_header_level(b);
                if (level > write_lock_level)
                        goto out;

                /* Whoops, must trade for write lock */
                btrfs_tree_read_unlock(b);
                free_extent_buffer(b);
        }

        b = btrfs_lock_root_node(root);
        root_lock = BTRFS_WRITE_LOCK;

        /* The level might have changed, check again */
        level = btrfs_header_level(b);

out:
        p->nodes[level] = b;
        if (!p->skip_locking)
                p->locks[level] = root_lock;
        /*
         * Callers are responsible for dropping b's references.
         */
        return b;
}


/*
 * btrfs_search_slot - look for a key in a tree and perform necessary
 * modifications to preserve tree invariants.
 *
 * @trans:      Handle of transaction, used when modifying the tree
 * @p:          Holds all btree nodes along the search path
 * @root:       The root node of the tree
 * @key:        The key we are looking for
 * @ins_len:    Indicates purpose of search:
 *              >0  for inserts it's size of item inserted (*)
 *              <0  for deletions
 *               0  for plain searches, not modifying the tree
 *
 *              (*) If size of item inserted doesn't include
 *              sizeof(struct btrfs_item), then p->search_for_extension must
 *              be set.
 * @cow:        boolean should CoW operations be performed. Must always be 1
 *              when modifying the tree.
 *
 * If @ins_len > 0, nodes and leaves will be split as we walk down the tree.
 * If @ins_len < 0, nodes will be merged as we walk down the tree (if possible)
 *
 * If @key is found, 0 is returned and you can find the item in the leaf level
 * of the path (level 0)
 *
 * If @key isn't found, 1 is returned and the leaf level of the path (level 0)
 * points to the slot where it should be inserted
 *
 * If an error is encountered while searching the tree a negative error number
 * is returned
 */
int btrfs_search_slot(struct btrfs_trans_handle *trans, struct btrfs_root *root,
                      const struct btrfs_key *key, struct btrfs_path *p,
                      int ins_len, int cow)
{
        struct extent_buffer *b;
        int slot;
        int ret;
        int err;
        int level;
        int lowest_unlock = 1;
        /* everything at write_lock_level or lower must be write locked */
        int write_lock_level = 0;
        u8 lowest_level = 0;
        int min_write_lock_level;
        int prev_cmp;

        lowest_level = p->lowest_level;
        WARN_ON(lowest_level && ins_len > 0);
        WARN_ON(p->nodes[0] != NULL);
        BUG_ON(!cow && ins_len);

        if (ins_len < 0) {
                lowest_unlock = 2;

                /* when we are removing items, we might have to go up to level
                 * two as we update tree pointers  Make sure we keep write
                 * for those levels as well
                 */
                write_lock_level = 2;
        } else if (ins_len > 0) {
                /*
                 * for inserting items, make sure we have a write lock on
                 * level 1 so we can update keys
                 */
                write_lock_level = 1;
        }

        if (!cow)
                write_lock_level = -1;

        if (cow && (p->keep_locks || p->lowest_level))
                write_lock_level = BTRFS_MAX_LEVEL;

        min_write_lock_level = write_lock_level;

again:
        prev_cmp = -1;
        b = btrfs_search_slot_get_root(root, p, write_lock_level);
        if (IS_ERR(b)) {
                ret = PTR_ERR(b);
                goto done;
        }

        while (b) {
                int dec = 0;

                level = btrfs_header_level(b);

                if (cow) {
                        bool last_level = (level == (BTRFS_MAX_LEVEL - 1));

                        /*
                         * if we don't really need to cow this block
                         * then we don't want to set the path blocking,
                         * so we test it here
                         */
                        if (!should_cow_block(trans, root, b))
                                goto cow_done;

                        /*
                         * must have write locks on this node and the
                         * parent
                         */
                        if (level > write_lock_level ||
                            (level + 1 > write_lock_level &&
                            level + 1 < BTRFS_MAX_LEVEL &&
                            p->nodes[level + 1])) {
                                write_lock_level = level + 1;
                                btrfs_release_path(p);
                                goto again;
                        }

                        if (last_level)
                                err = btrfs_cow_block(trans, root, b, NULL, 0,
                                                      &b,
                                                      BTRFS_NESTING_COW);
                        else
                                err = btrfs_cow_block(trans, root, b,
                                                      p->nodes[level + 1],
                                                      p->slots[level + 1], &b,
                                                      BTRFS_NESTING_COW);
                        if (err) {
                                ret = err;
                                goto done;
                        }
                }
cow_done:
                p->nodes[level] = b;
                /*
                 * Leave path with blocking locks to avoid massive
                 * lock context switch, this is made on purpose.
                 */

                /*
                 * we have a lock on b and as long as we aren't changing
                 * the tree, there is no way to for the items in b to change.
                 * It is safe to drop the lock on our parent before we
                 * go through the expensive btree search on b.
                 *
                 * If we're inserting or deleting (ins_len != 0), then we might
                 * be changing slot zero, which may require changing the parent.
                 * So, we can't drop the lock until after we know which slot
                 * we're operating on.
                 */
                if (!ins_len && !p->keep_locks) {
                        int u = level + 1;

                        if (u < BTRFS_MAX_LEVEL && p->locks[u]) {
                                btrfs_tree_unlock_rw(p->nodes[u], p->locks[u]);
                                p->locks[u] = 0;
                        }
                }

                /*
                 * If btrfs_bin_search returns an exact match (prev_cmp == 0)
                 * we can safely assume the target key will always be in slot 0
                 * on lower levels due to the invariants BTRFS' btree provides,
                 * namely that a btrfs_key_ptr entry always points to the
                 * lowest key in the child node, thus we can skip searching
                 * lower levels
                 */
                if (prev_cmp == 0) {
                        slot = 0;
                        ret = 0;
                } else {
                        ret = btrfs_bin_search(b, key, &slot);
                        prev_cmp = ret;
                        if (ret < 0)
                                goto done;
                }

                if (level == 0) {
                        p->slots[level] = slot;
                        /*
                         * Item key already exists. In this case, if we are
                         * allowed to insert the item (for example, in dir_item
                         * case, item key collision is allowed), it will be
                         * merged with the original item. Only the item size
                         * grows, no new btrfs item will be added. If
                         * search_for_extension is not set, ins_len already
                         * accounts the size btrfs_item, deduct it here so leaf
                         * space check will be correct.
                         */
                        if (ret == 0 && ins_len > 0 && !p->search_for_extension) {
                                ASSERT(ins_len >= sizeof(struct btrfs_item));
                                ins_len -= sizeof(struct btrfs_item);
                        }
                        if (ins_len > 0 &&
                            btrfs_leaf_free_space(b) < ins_len) {
                                if (write_lock_level < 1) {
                                        write_lock_level = 1;
                                        btrfs_release_path(p);
                                        goto again;
                                }

                                err = split_leaf(trans, root, key,
                                                 p, ins_len, ret == 0);

                                BUG_ON(err > 0);
                                if (err) {
                                        ret = err;
                                        goto done;
                                }
                        }
                        if (!p->search_for_split)
                                unlock_up(p, level, lowest_unlock,
                                          min_write_lock_level, NULL);
                        goto done;
                }
                if (ret && slot > 0) {
                        dec = 1;
                        slot--;
                }
                p->slots[level] = slot;
                err = setup_nodes_for_search(trans, root, p, b, level, ins_len,
                                             &write_lock_level);
                if (err == -EAGAIN)
                        goto again;
                if (err) {
                        ret = err;
                        goto done;
                }
                b = p->nodes[level];
                slot = p->slots[level];

                /*
                 * Slot 0 is special, if we change the key we have to update
                 * the parent pointer which means we must have a write lock on
                 * the parent
                 */
                if (slot == 0 && ins_len && write_lock_level < level + 1) {
                        write_lock_level = level + 1;
                        btrfs_release_path(p);
                        goto again;
                }

                unlock_up(p, level, lowest_unlock, min_write_lock_level,
                          &write_lock_level);

                if (level == lowest_level) {
                        if (dec)
                                p->slots[level]++;
                        goto done;
                }

                err = read_block_for_search(root, p, &b, level, slot, key);
                if (err == -EAGAIN)
                        goto again;
                if (err) {
                        ret = err;
                        goto done;
                }

                if (!p->skip_locking) {
                        level = btrfs_header_level(b);
                        if (level <= write_lock_level) {
                                btrfs_tree_lock(b);
                                p->locks[level] = BTRFS_WRITE_LOCK;
                        } else {
                                btrfs_tree_read_lock(b);
                                p->locks[level] = BTRFS_READ_LOCK;
                        }
                        p->nodes[level] = b;
                }
        }
        ret = 1;
done:
        if (ret < 0 && !p->skip_release_on_error)
                btrfs_release_path(p);
        return ret;
}
ALLOW_ERROR_INJECTION(btrfs_search_slot, ERRNO);

/*
 * Like btrfs_search_slot, this looks for a key in the given tree. It uses the
 * current state of the tree together with the operations recorded in the tree
 * modification log to search for the key in a previous version of this tree, as
 * denoted by the time_seq parameter.
 *
 * Naturally, there is no support for insert, delete or cow operations.
 *
 * The resulting path and return value will be set up as if we called
 * btrfs_search_slot at that point in time with ins_len and cow both set to 0.
 */
int btrfs_search_old_slot(struct btrfs_root *root, const struct btrfs_key *key,
                          struct btrfs_path *p, u64 time_seq)
{
        struct btrfs_fs_info *fs_info = root->fs_info;
        struct extent_buffer *b;
        int slot;
        int ret;
        int err;
        int level;
        int lowest_unlock = 1;
        u8 lowest_level = 0;

        lowest_level = p->lowest_level;
        WARN_ON(p->nodes[0] != NULL);

        if (p->search_commit_root) {
                BUG_ON(time_seq);
                return btrfs_search_slot(NULL, root, key, p, 0, 0);
        }

again:
        b = btrfs_get_old_root(root, time_seq);
        if (!b) {
                ret = -EIO;
                goto done;
        }
        level = btrfs_header_level(b);
        p->locks[level] = BTRFS_READ_LOCK;

        while (b) {
                int dec = 0;

                level = btrfs_header_level(b);
                p->nodes[level] = b;

                /*
                 * we have a lock on b and as long as we aren't changing
                 * the tree, there is no way to for the items in b to change.
                 * It is safe to drop the lock on our parent before we
                 * go through the expensive btree search on b.
                 */
                btrfs_unlock_up_safe(p, level + 1);

                ret = btrfs_bin_search(b, key, &slot);
                if (ret < 0)
                        goto done;

                if (level == 0) {
                        p->slots[level] = slot;
                        unlock_up(p, level, lowest_unlock, 0, NULL);
                        goto done;
                }

                if (ret && slot > 0) {
                        dec = 1;
                        slot--;
                }
                p->slots[level] = slot;
                unlock_up(p, level, lowest_unlock, 0, NULL);

                if (level == lowest_level) {
                        if (dec)
                                p->slots[level]++;
                        goto done;
                }

                err = read_block_for_search(root, p, &b, level, slot, key);
                if (err == -EAGAIN)
                        goto again;
                if (err) {
                        ret = err;
                        goto done;
                }

                level = btrfs_header_level(b);
                btrfs_tree_read_lock(b);
                b = btrfs_tree_mod_log_rewind(fs_info, p, b, time_seq);
                if (!b) {
                        ret = -ENOMEM;
                        goto done;
                }
                p->locks[level] = BTRFS_READ_LOCK;
                p->nodes[level] = b;
        }
        ret = 1;
done:
        if (ret < 0)
                btrfs_release_path(p);

        return ret;
}

/*
 * helper to use instead of search slot if no exact match is needed but
 * instead the next or previous item should be returned.
 * When find_higher is true, the next higher item is returned, the next lower
 * otherwise.
 * When return_any and find_higher are both true, and no higher item is found,
 * return the next lower instead.
 * When return_any is true and find_higher is false, and no lower item is found,
 * return the next higher instead.
 * It returns 0 if any item is found, 1 if none is found (tree empty), and
 * < 0 on error
 */
int btrfs_search_slot_for_read(struct btrfs_root *root,
                               const struct btrfs_key *key,
                               struct btrfs_path *p, int find_higher,
                               int return_any)
{
        int ret;
        struct extent_buffer *leaf;

again:
        ret = btrfs_search_slot(NULL, root, key, p, 0, 0);
        if (ret <= 0)
                return ret;
        /*
         * a return value of 1 means the path is at the position where the
         * item should be inserted. Normally this is the next bigger item,
         * but in case the previous item is the last in a leaf, path points
         * to the first free slot in the previous leaf, i.e. at an invalid
         * item.
         */
        leaf = p->nodes[0];

        if (find_higher) {
                if (p->slots[0] >= btrfs_header_nritems(leaf)) {
                        ret = btrfs_next_leaf(root, p);
                        if (ret <= 0)
                                return ret;
                        if (!return_any)
                                return 1;
                        /*
                         * no higher item found, return the next
                         * lower instead
                         */
                        return_any = 0;
                        find_higher = 0;
                        btrfs_release_path(p);
                        goto again;
                }
        } else {
                if (p->slots[0] == 0) {
                        ret = btrfs_prev_leaf(root, p);
                        if (ret < 0)
                                return ret;
                        if (!ret) {
                                leaf = p->nodes[0];
                                if (p->slots[0] == btrfs_header_nritems(leaf))
                                        p->slots[0]--;
                                return 0;
                        }
                        if (!return_any)
                                return 1;
                        /*
                         * no lower item found, return the next
                         * higher instead
                         */
                        return_any = 0;
                        find_higher = 1;
                        btrfs_release_path(p);
                        goto again;
                } else {
                        --p->slots[0];
                }
        }
        return 0;
}

/*
 * adjust the pointers going up the tree, starting at level
 * making sure the right key of each node is points to 'key'.
 * This is used after shifting pointers to the left, so it stops
 * fixing up pointers when a given leaf/node is not in slot 0 of the
 * higher levels
 *
 */
static void fixup_low_keys(struct btrfs_path *path,
                           struct btrfs_disk_key *key, int level)
{
        int i;
        struct extent_buffer *t;
        int ret;

        for (i = level; i < BTRFS_MAX_LEVEL; i++) {
                int tslot = path->slots[i];

                if (!path->nodes[i])
                        break;
                t = path->nodes[i];
                ret = btrfs_tree_mod_log_insert_key(t, tslot,
                                BTRFS_MOD_LOG_KEY_REPLACE, GFP_ATOMIC);
                BUG_ON(ret < 0);
                btrfs_set_node_key(t, key, tslot);
                btrfs_mark_buffer_dirty(path->nodes[i]);
                if (tslot != 0)
                        break;
        }
}

/*
 * update item key.
 *
 * This function isn't completely safe. It's the caller's responsibility
 * that the new key won't break the order
 */
void btrfs_set_item_key_safe(struct btrfs_fs_info *fs_info,
                             struct btrfs_path *path,
                             const struct btrfs_key *new_key)
{
        struct btrfs_disk_key disk_key;
        struct extent_buffer *eb;
        int slot;

        eb = path->nodes[0];
        slot = path->slots[0];
        if (slot > 0) {
                btrfs_item_key(eb, &disk_key, slot - 1);
                if (unlikely(comp_keys(&disk_key, new_key) >= 0)) {
                        btrfs_crit(fs_info,
                "slot %u key (%llu %u %llu) new key (%llu %u %llu)",
                                   slot, btrfs_disk_key_objectid(&disk_key),
                                   btrfs_disk_key_type(&disk_key),
                                   btrfs_disk_key_offset(&disk_key),
                                   new_key->objectid, new_key->type,
                                   new_key->offset);
                        btrfs_print_leaf(eb);
                        BUG();
                }
        }
        if (slot < btrfs_header_nritems(eb) - 1) {
                btrfs_item_key(eb, &disk_key, slot + 1);
                if (unlikely(comp_keys(&disk_key, new_key) <= 0)) {
                        btrfs_crit(fs_info,
                "slot %u key (%llu %u %llu) new key (%llu %u %llu)",
                                   slot, btrfs_disk_key_objectid(&disk_key),
                                   btrfs_disk_key_type(&disk_key),
                                   btrfs_disk_key_offset(&disk_key),
                                   new_key->objectid, new_key->type,
                                   new_key->offset);
                        btrfs_print_leaf(eb);
                        BUG();
                }
        }

        btrfs_cpu_key_to_disk(&disk_key, new_key);
        btrfs_set_item_key(eb, &disk_key, slot);
        btrfs_mark_buffer_dirty(eb);
        if (slot == 0)
                fixup_low_keys(path, &disk_key, 1);
}

/*
 * Check key order of two sibling extent buffers.
 *
 * Return true if something is wrong.
 * Return false if everything is fine.
 *
 * Tree-checker only works inside one tree block, thus the following
 * corruption can not be detected by tree-checker:
 *
 * Leaf @left                   | Leaf @right
 * --------------------------------------------------------------
 * | 1 | 2 | 3 | 4 | 5 | f6 |   | 7 | 8 |
 *
 * Key f6 in leaf @left itself is valid, but not valid when the next
 * key in leaf @right is 7.
 * This can only be checked at tree block merge time.
 * And since tree checker has ensured all key order in each tree block
 * is correct, we only need to bother the last key of @left and the first
 * key of @right.
 */
static bool check_sibling_keys(struct extent_buffer *left,
                               struct extent_buffer *right)
{
        struct btrfs_key left_last;
        struct btrfs_key right_first;
        int level = btrfs_header_level(left);
        int nr_left = btrfs_header_nritems(left);
        int nr_right = btrfs_header_nritems(right);

        /* No key to check in one of the tree blocks */
        if (!nr_left || !nr_right)
                return false;

        if (level) {
                btrfs_node_key_to_cpu(left, &left_last, nr_left - 1);
                btrfs_node_key_to_cpu(right, &right_first, 0);
        } else {
                btrfs_item_key_to_cpu(left, &left_last, nr_left - 1);
                btrfs_item_key_to_cpu(right, &right_first, 0);
        }

        if (btrfs_comp_cpu_keys(&left_last, &right_first) >= 0) {
                btrfs_crit(left->fs_info,
"bad key order, sibling blocks, left last (%llu %u %llu) right first (%llu %u %llu)",
                           left_last.objectid, left_last.type,
                           left_last.offset, right_first.objectid,
                           right_first.type, right_first.offset);
                return true;
        }
        return false;
}

/*
 * try to push data from one node into the next node left in the
 * tree.
 *
 * returns 0 if some ptrs were pushed left, < 0 if there was some horrible
 * error, and > 0 if there was no room in the left hand block.
 */
static int push_node_left(struct btrfs_trans_handle *trans,
                          struct extent_buffer *dst,
                          struct extent_buffer *src, int empty)
{
        struct btrfs_fs_info *fs_info = trans->fs_info;
        int push_items = 0;
        int src_nritems;
        int dst_nritems;
        int ret = 0;

        src_nritems = btrfs_header_nritems(src);
        dst_nritems = btrfs_header_nritems(dst);
        push_items = BTRFS_NODEPTRS_PER_BLOCK(fs_info) - dst_nritems;
        WARN_ON(btrfs_header_generation(src) != trans->transid);
        WARN_ON(btrfs_header_generation(dst) != trans->transid);

        if (!empty && src_nritems <= 8)
                return 1;

        if (push_items <= 0)
                return 1;

        if (empty) {
                push_items = min(src_nritems, push_items);
                if (push_items < src_nritems) {
                        /* leave at least 8 pointers in the node if
                         * we aren't going to empty it
                         */
                        if (src_nritems - push_items < 8) {
                                if (push_items <= 8)
                                        return 1;
                                push_items -= 8;
                        }
                }
        } else
                push_items = min(src_nritems - 8, push_items);

        /* dst is the left eb, src is the middle eb */
        if (check_sibling_keys(dst, src)) {
                ret = -EUCLEAN;
                btrfs_abort_transaction(trans, ret);
                return ret;
        }
        ret = btrfs_tree_mod_log_eb_copy(dst, src, dst_nritems, 0, push_items);
        if (ret) {
                btrfs_abort_transaction(trans, ret);
                return ret;
        }
        copy_extent_buffer(dst, src,
                           btrfs_node_key_ptr_offset(dst_nritems),
                           btrfs_node_key_ptr_offset(0),
                           push_items * sizeof(struct btrfs_key_ptr));

        if (push_items < src_nritems) {
                /*
                 * Don't call btrfs_tree_mod_log_insert_move() here, key removal
                 * was already fully logged by btrfs_tree_mod_log_eb_copy() above.
                 */
                memmove_extent_buffer(src, btrfs_node_key_ptr_offset(0),
                                      btrfs_node_key_ptr_offset(push_items),
                                      (src_nritems - push_items) *
                                      sizeof(struct btrfs_key_ptr));
        }
        btrfs_set_header_nritems(src, src_nritems - push_items);
        btrfs_set_header_nritems(dst, dst_nritems + push_items);
        btrfs_mark_buffer_dirty(src);
        btrfs_mark_buffer_dirty(dst);

        return ret;
}

/*
 * try to push data from one node into the next node right in the
 * tree.
 *
 * returns 0 if some ptrs were pushed, < 0 if there was some horrible
 * error, and > 0 if there was no room in the right hand block.
 *
 * this will  only push up to 1/2 the contents of the left node over
 */
static int balance_node_right(struct btrfs_trans_handle *trans,
                              struct extent_buffer *dst,
                              struct extent_buffer *src)
{
        struct btrfs_fs_info *fs_info = trans->fs_info;
        int push_items = 0;
        int max_push;
        int src_nritems;
        int dst_nritems;
        int ret = 0;

        WARN_ON(btrfs_header_generation(src) != trans->transid);
        WARN_ON(btrfs_header_generation(dst) != trans->transid);

        src_nritems = btrfs_header_nritems(src);
        dst_nritems = btrfs_header_nritems(dst);
        push_items = BTRFS_NODEPTRS_PER_BLOCK(fs_info) - dst_nritems;
        if (push_items <= 0)
                return 1;

        if (src_nritems < 4)
                return 1;

        max_push = src_nritems / 2 + 1;
        /* don't try to empty the node */
        if (max_push >= src_nritems)
                return 1;

        if (max_push < push_items)
                push_items = max_push;

        /* dst is the right eb, src is the middle eb */
        if (check_sibling_keys(src, dst)) {
                ret = -EUCLEAN;
                btrfs_abort_transaction(trans, ret);
                return ret;
        }
        ret = btrfs_tree_mod_log_insert_move(dst, push_items, 0, dst_nritems);
        BUG_ON(ret < 0);
        memmove_extent_buffer(dst, btrfs_node_key_ptr_offset(push_items),
                                      btrfs_node_key_ptr_offset(0),
                                      (dst_nritems) *
                                      sizeof(struct btrfs_key_ptr));

        ret = btrfs_tree_mod_log_eb_copy(dst, src, 0, src_nritems - push_items,
                                         push_items);
        if (ret) {
                btrfs_abort_transaction(trans, ret);
                return ret;
        }
        copy_extent_buffer(dst, src,
                           btrfs_node_key_ptr_offset(0),
                           btrfs_node_key_ptr_offset(src_nritems - push_items),
                           push_items * sizeof(struct btrfs_key_ptr));

        btrfs_set_header_nritems(src, src_nritems - push_items);
        btrfs_set_header_nritems(dst, dst_nritems + push_items);

        btrfs_mark_buffer_dirty(src);
        btrfs_mark_buffer_dirty(dst);

        return ret;
}

/*
 * helper function to insert a new root level in the tree.
 * A new node is allocated, and a single item is inserted to
 * point to the existing root
 *
 * returns zero on success or < 0 on failure.
 */
static noinline int insert_new_root(struct btrfs_trans_handle *trans,
                           struct btrfs_root *root,
                           struct btrfs_path *path, int level)
{
        struct btrfs_fs_info *fs_info = root->fs_info;
        u64 lower_gen;
        struct extent_buffer *lower;
        struct extent_buffer *c;
        struct extent_buffer *old;
        struct btrfs_disk_key lower_key;
        int ret;

        BUG_ON(path->nodes[level]);
        BUG_ON(path->nodes[level-1] != root->node);

        lower = path->nodes[level-1];
        if (level == 1)
                btrfs_item_key(lower, &lower_key, 0);
        else
                btrfs_node_key(lower, &lower_key, 0);

        c = btrfs_alloc_tree_block(trans, root, 0, root->root_key.objectid,
                                   &lower_key, level, root->node->start, 0,
                                   BTRFS_NESTING_NEW_ROOT);
        if (IS_ERR(c))
                return PTR_ERR(c);

        root_add_used(root, fs_info->nodesize);

        btrfs_set_header_nritems(c, 1);
        btrfs_set_node_key(c, &lower_key, 0);
        btrfs_set_node_blockptr(c, 0, lower->start);
        lower_gen = btrfs_header_generation(lower);
        WARN_ON(lower_gen != trans->transid);

        btrfs_set_node_ptr_generation(c, 0, lower_gen);

        btrfs_mark_buffer_dirty(c);

        old = root->node;
        ret = btrfs_tree_mod_log_insert_root(root->node, c, false);
        BUG_ON(ret < 0);
        rcu_assign_pointer(root->node, c);

        /* the super has an extra ref to root->node */
        free_extent_buffer(old);

        add_root_to_dirty_list(root);
        atomic_inc(&c->refs);
        path->nodes[level] = c;
        path->locks[level] = BTRFS_WRITE_LOCK;
        path->slots[level] = 0;
        return 0;
}

/*
 * worker function to insert a single pointer in a node.
 * the node should have enough room for the pointer already
 *
 * slot and level indicate where you want the key to go, and
 * blocknr is the block the key points to.
 */
static void insert_ptr(struct btrfs_trans_handle *trans,
                       struct btrfs_path *path,
                       struct btrfs_disk_key *key, u64 bytenr,
                       int slot, int level)
{
        struct extent_buffer *lower;
        int nritems;
        int ret;

        BUG_ON(!path->nodes[level]);
        btrfs_assert_tree_locked(path->nodes[level]);
        lower = path->nodes[level];
        nritems = btrfs_header_nritems(lower);
        BUG_ON(slot > nritems);
        BUG_ON(nritems == BTRFS_NODEPTRS_PER_BLOCK(trans->fs_info));
        if (slot != nritems) {
                if (level) {
                        ret = btrfs_tree_mod_log_insert_move(lower, slot + 1,
                                        slot, nritems - slot);
                        BUG_ON(ret < 0);
                }
                memmove_extent_buffer(lower,
                              btrfs_node_key_ptr_offset(slot + 1),
                              btrfs_node_key_ptr_offset(slot),
                              (nritems - slot) * sizeof(struct btrfs_key_ptr));
        }
        if (level) {
                ret = btrfs_tree_mod_log_insert_key(lower, slot,
                                            BTRFS_MOD_LOG_KEY_ADD, GFP_NOFS);
                BUG_ON(ret < 0);
        }
        btrfs_set_node_key(lower, key, slot);
        btrfs_set_node_blockptr(lower, slot, bytenr);
        WARN_ON(trans->transid == 0);
        btrfs_set_node_ptr_generation(lower, slot, trans->transid);
        btrfs_set_header_nritems(lower, nritems + 1);
        btrfs_mark_buffer_dirty(lower);
}

/*
 * split the node at the specified level in path in two.
 * The path is corrected to point to the appropriate node after the split
 *
 * Before splitting this tries to make some room in the node by pushing
 * left and right, if either one works, it returns right away.
 *
 * returns 0 on success and < 0 on failure
 */
static noinline int split_node(struct btrfs_trans_handle *trans,
                               struct btrfs_root *root,
                               struct btrfs_path *path, int level)
{
        struct btrfs_fs_info *fs_info = root->fs_info;
        struct extent_buffer *c;
        struct extent_buffer *split;
        struct btrfs_disk_key disk_key;
        int mid;
        int ret;
        u32 c_nritems;

        c = path->nodes[level];
        WARN_ON(btrfs_header_generation(c) != trans->transid);
        if (c == root->node) {
                /*
                 * trying to split the root, lets make a new one
                 *
                 * tree mod log: We don't log_removal old root in
                 * insert_new_root, because that root buffer will be kept as a
                 * normal node. We are going to log removal of half of the
                 * elements below with btrfs_tree_mod_log_eb_copy(). We're
                 * holding a tree lock on the buffer, which is why we cannot
                 * race with other tree_mod_log users.
                 */
                ret = insert_new_root(trans, root, path, level + 1);
                if (ret)
                        return ret;
        } else {
                ret = push_nodes_for_insert(trans, root, path, level);
                c = path->nodes[level];
                if (!ret && btrfs_header_nritems(c) <
                    BTRFS_NODEPTRS_PER_BLOCK(fs_info) - 3)
                        return 0;
                if (ret < 0)
                        return ret;
        }

        c_nritems = btrfs_header_nritems(c);
        mid = (c_nritems + 1) / 2;
        btrfs_node_key(c, &disk_key, mid);

        split = btrfs_alloc_tree_block(trans, root, 0, root->root_key.objectid,
                                       &disk_key, level, c->start, 0,
                                       BTRFS_NESTING_SPLIT);
        if (IS_ERR(split))
                return PTR_ERR(split);

        root_add_used(root, fs_info->nodesize);
        ASSERT(btrfs_header_level(c) == level);

        ret = btrfs_tree_mod_log_eb_copy(split, c, 0, mid, c_nritems - mid);
        if (ret) {
                btrfs_abort_transaction(trans, ret);
                return ret;
        }
        copy_extent_buffer(split, c,
                           btrfs_node_key_ptr_offset(0),
                           btrfs_node_key_ptr_offset(mid),
                           (c_nritems - mid) * sizeof(struct btrfs_key_ptr));
        btrfs_set_header_nritems(split, c_nritems - mid);
        btrfs_set_header_nritems(c, mid);

        btrfs_mark_buffer_dirty(c);
        btrfs_mark_buffer_dirty(split);

        insert_ptr(trans, path, &disk_key, split->start,
                   path->slots[level + 1] + 1, level + 1);

        if (path->slots[level] >= mid) {
                path->slots[level] -= mid;
                btrfs_tree_unlock(c);
                free_extent_buffer(c);
                path->nodes[level] = split;
                path->slots[level + 1] += 1;
        } else {
                btrfs_tree_unlock(split);
                free_extent_buffer(split);
        }
        return 0;
}

/*
 * how many bytes are required to store the items in a leaf.  start
 * and nr indicate which items in the leaf to check.  This totals up the
 * space used both by the item structs and the item data
 */
static int leaf_space_used(struct extent_buffer *l, int start, int nr)
{
        struct btrfs_item *start_item;
        struct btrfs_item *end_item;
        int data_len;
        int nritems = btrfs_header_nritems(l);
        int end = min(nritems, start + nr) - 1;

        if (!nr)
                return 0;
        start_item = btrfs_item_nr(start);
        end_item = btrfs_item_nr(end);
        data_len = btrfs_item_offset(l, start_item) +
                   btrfs_item_size(l, start_item);
        data_len = data_len - btrfs_item_offset(l, end_item);
        data_len += sizeof(struct btrfs_item) * nr;
        WARN_ON(data_len < 0);
        return data_len;
}

/*
 * The space between the end of the leaf items and
 * the start of the leaf data.  IOW, how much room
 * the leaf has left for both items and data
 */
noinline int btrfs_leaf_free_space(struct extent_buffer *leaf)
{
        struct btrfs_fs_info *fs_info = leaf->fs_info;
        int nritems = btrfs_header_nritems(leaf);
        int ret;

        ret = BTRFS_LEAF_DATA_SIZE(fs_info) - leaf_space_used(leaf, 0, nritems);
        if (ret < 0) {
                btrfs_crit(fs_info,
                           "leaf free space ret %d, leaf data size %lu, used %d nritems %d",
                           ret,
                           (unsigned long) BTRFS_LEAF_DATA_SIZE(fs_info),
                           leaf_space_used(leaf, 0, nritems), nritems);
        }
        return ret;
}

/*
 * min slot controls the lowest index we're willing to push to the
 * right.  We'll push up to and including min_slot, but no lower
 */
static noinline int __push_leaf_right(struct btrfs_path *path,
                                      int data_size, int empty,
                                      struct extent_buffer *right,
                                      int free_space, u32 left_nritems,
                                      u32 min_slot)
{
        struct btrfs_fs_info *fs_info = right->fs_info;
        struct extent_buffer *left = path->nodes[0];
        struct extent_buffer *upper = path->nodes[1];
        struct btrfs_map_token token;
        struct btrfs_disk_key disk_key;
        int slot;
        u32 i;
        int push_space = 0;
        int push_items = 0;
        struct btrfs_item *item;
        u32 nr;
        u32 right_nritems;
        u32 data_end;
        u32 this_item_size;

        if (empty)
                nr = 0;
        else
                nr = max_t(u32, 1, min_slot);

        if (path->slots[0] >= left_nritems)
                push_space += data_size;

        slot = path->slots[1];
        i = left_nritems - 1;
        while (i >= nr) {
                item = btrfs_item_nr(i);

                if (!empty && push_items > 0) {
                        if (path->slots[0] > i)
                                break;
                        if (path->slots[0] == i) {
                                int space = btrfs_leaf_free_space(left);

                                if (space + push_space * 2 > free_space)
                                        break;
                        }
                }

                if (path->slots[0] == i)
                        push_space += data_size;

                this_item_size = btrfs_item_size(left, item);
                if (this_item_size + sizeof(*item) + push_space > free_space)
                        break;

                push_items++;
                push_space += this_item_size + sizeof(*item);
                if (i == 0)
                        break;
                i--;
        }

        if (push_items == 0)
                goto out_unlock;

        WARN_ON(!empty && push_items == left_nritems);

        /* push left to right */
        right_nritems = btrfs_header_nritems(right);

        push_space = btrfs_item_end_nr(left, left_nritems - push_items);
        push_space -= leaf_data_end(left);

        /* make room in the right data area */
        data_end = leaf_data_end(right);
        memmove_extent_buffer(right,
                              BTRFS_LEAF_DATA_OFFSET + data_end - push_space,
                              BTRFS_LEAF_DATA_OFFSET + data_end,
                              BTRFS_LEAF_DATA_SIZE(fs_info) - data_end);

        /* copy from the left data area */
        copy_extent_buffer(right, left, BTRFS_LEAF_DATA_OFFSET +
                     BTRFS_LEAF_DATA_SIZE(fs_info) - push_space,
                     BTRFS_LEAF_DATA_OFFSET + leaf_data_end(left),
                     push_space);

        memmove_extent_buffer(right, btrfs_item_nr_offset(push_items),
                              btrfs_item_nr_offset(0),
                              right_nritems * sizeof(struct btrfs_item));

        /* copy the items from left to right */
        copy_extent_buffer(right, left, btrfs_item_nr_offset(0),
                   btrfs_item_nr_offset(left_nritems - push_items),
                   push_items * sizeof(struct btrfs_item));

        /* update the item pointers */
        btrfs_init_map_token(&token, right);
        right_nritems += push_items;
        btrfs_set_header_nritems(right, right_nritems);
        push_space = BTRFS_LEAF_DATA_SIZE(fs_info);
        for (i = 0; i < right_nritems; i++) {
                item = btrfs_item_nr(i);
                push_space -= btrfs_token_item_size(&token, item);
                btrfs_set_token_item_offset(&token, item, push_space);
        }

        left_nritems -= push_items;
        btrfs_set_header_nritems(left, left_nritems);

        if (left_nritems)
                btrfs_mark_buffer_dirty(left);
        else
                btrfs_clean_tree_block(left);

        btrfs_mark_buffer_dirty(right);

        btrfs_item_key(right, &disk_key, 0);
        btrfs_set_node_key(upper, &disk_key, slot + 1);
        btrfs_mark_buffer_dirty(upper);

        /* then fixup the leaf pointer in the path */
        if (path->slots[0] >= left_nritems) {
                path->slots[0] -= left_nritems;
                if (btrfs_header_nritems(path->nodes[0]) == 0)
                        btrfs_clean_tree_block(path->nodes[0]);
                btrfs_tree_unlock(path->nodes[0]);
                free_extent_buffer(path->nodes[0]);
                path->nodes[0] = right;
                path->slots[1] += 1;
        } else {
                btrfs_tree_unlock(right);
                free_extent_buffer(right);
        }
        return 0;

out_unlock:
        btrfs_tree_unlock(right);
        free_extent_buffer(right);
        return 1;
}

/*
 * push some data in the path leaf to the right, trying to free up at
 * least data_size bytes.  returns zero if the push worked, nonzero otherwise
 *
 * returns 1 if the push failed because the other node didn't have enough
 * room, 0 if everything worked out and < 0 if there were major errors.
 *
 * this will push starting from min_slot to the end of the leaf.  It won't
 * push any slot lower than min_slot
 */
static int push_leaf_right(struct btrfs_trans_handle *trans, struct btrfs_root
                           *root, struct btrfs_path *path,
                           int min_data_size, int data_size,
                           int empty, u32 min_slot)
{
        struct extent_buffer *left = path->nodes[0];
        struct extent_buffer *right;
        struct extent_buffer *upper;
        int slot;
        int free_space;
        u32 left_nritems;
        int ret;

        if (!path->nodes[1])
                return 1;

        slot = path->slots[1];
        upper = path->nodes[1];
        if (slot >= btrfs_header_nritems(upper) - 1)
                return 1;

        btrfs_assert_tree_locked(path->nodes[1]);

        right = btrfs_read_node_slot(upper, slot + 1);
        /*
         * slot + 1 is not valid or we fail to read the right node,
         * no big deal, just return.
         */
        if (IS_ERR(right))
                return 1;

        __btrfs_tree_lock(right, BTRFS_NESTING_RIGHT);

        free_space = btrfs_leaf_free_space(right);
        if (free_space < data_size)
                goto out_unlock;

        /* cow and double check */
        ret = btrfs_cow_block(trans, root, right, upper,
                              slot + 1, &right, BTRFS_NESTING_RIGHT_COW);
        if (ret)
                goto out_unlock;

        free_space = btrfs_leaf_free_space(right);
        if (free_space < data_size)
                goto out_unlock;

        left_nritems = btrfs_header_nritems(left);
        if (left_nritems == 0)
                goto out_unlock;

        if (check_sibling_keys(left, right)) {
                ret = -EUCLEAN;
                btrfs_tree_unlock(right);
                free_extent_buffer(right);
                return ret;
        }
        if (path->slots[0] == left_nritems && !empty) {
                /* Key greater than all keys in the leaf, right neighbor has
                 * enough room for it and we're not emptying our leaf to delete
                 * it, therefore use right neighbor to insert the new item and
                 * no need to touch/dirty our left leaf. */
                btrfs_tree_unlock(left);
                free_extent_buffer(left);
                path->nodes[0] = right;
                path->slots[0] = 0;
                path->slots[1]++;
                return 0;
        }

        return __push_leaf_right(path, min_data_size, empty,
                                right, free_space, left_nritems, min_slot);
out_unlock:
        btrfs_tree_unlock(right);
        free_extent_buffer(right);
        return 1;
}

/*
 * push some data in the path leaf to the left, trying to free up at
 * least data_size bytes.  returns zero if the push worked, nonzero otherwise
 *
 * max_slot can put a limit on how far into the leaf we'll push items.  The
 * item at 'max_slot' won't be touched.  Use (u32)-1 to make us do all the
 * items
 */
static noinline int __push_leaf_left(struct btrfs_path *path, int data_size,
                                     int empty, struct extent_buffer *left,
                                     int free_space, u32 right_nritems,
                                     u32 max_slot)
{
        struct btrfs_fs_info *fs_info = left->fs_info;
        struct btrfs_disk_key disk_key;
        struct extent_buffer *right = path->nodes[0];
        int i;
        int push_space = 0;
        int push_items = 0;
        struct btrfs_item *item;
        u32 old_left_nritems;
        u32 nr;
        int ret = 0;
        u32 this_item_size;
        u32 old_left_item_size;
        struct btrfs_map_token token;

        if (empty)
                nr = min(right_nritems, max_slot);
        else
                nr = min(right_nritems - 1, max_slot);

        for (i = 0; i < nr; i++) {
                item = btrfs_item_nr(i);

                if (!empty && push_items > 0) {
                        if (path->slots[0] < i)
                                break;
                        if (path->slots[0] == i) {
                                int space = btrfs_leaf_free_space(right);

                                if (space + push_space * 2 > free_space)
                                        break;
                        }
                }

                if (path->slots[0] == i)
                        push_space += data_size;

                this_item_size = btrfs_item_size(right, item);
                if (this_item_size + sizeof(*item) + push_space > free_space)
                        break;

                push_items++;
                push_space += this_item_size + sizeof(*item);
        }

        if (push_items == 0) {
                ret = 1;
                goto out;
        }
        WARN_ON(!empty && push_items == btrfs_header_nritems(right));

        /* push data from right to left */
        copy_extent_buffer(left, right,
                           btrfs_item_nr_offset(btrfs_header_nritems(left)),
                           btrfs_item_nr_offset(0),
                           push_items * sizeof(struct btrfs_item));

        push_space = BTRFS_LEAF_DATA_SIZE(fs_info) -
                     btrfs_item_offset_nr(right, push_items - 1);

        copy_extent_buffer(left, right, BTRFS_LEAF_DATA_OFFSET +
                     leaf_data_end(left) - push_space,
                     BTRFS_LEAF_DATA_OFFSET +
                     btrfs_item_offset_nr(right, push_items - 1),
                     push_space);
        old_left_nritems = btrfs_header_nritems(left);
        BUG_ON(old_left_nritems <= 0);

        btrfs_init_map_token(&token, left);
        old_left_item_size = btrfs_item_offset_nr(left, old_left_nritems - 1);
        for (i = old_left_nritems; i < old_left_nritems + push_items; i++) {
                u32 ioff;

                item = btrfs_item_nr(i);

                ioff = btrfs_token_item_offset(&token, item);
                btrfs_set_token_item_offset(&token, item,
                      ioff - (BTRFS_LEAF_DATA_SIZE(fs_info) - old_left_item_size));
        }
        btrfs_set_header_nritems(left, old_left_nritems + push_items);

        /* fixup right node */
        if (push_items > right_nritems)
                WARN(1, KERN_CRIT "push items %d nr %u\n", push_items,
                       right_nritems);

        if (push_items < right_nritems) {
                push_space = btrfs_item_offset_nr(right, push_items - 1) -
                                                  leaf_data_end(right);
                memmove_extent_buffer(right, BTRFS_LEAF_DATA_OFFSET +
                                      BTRFS_LEAF_DATA_SIZE(fs_info) - push_space,
                                      BTRFS_LEAF_DATA_OFFSET +
                                      leaf_data_end(right), push_space);

                memmove_extent_buffer(right, btrfs_item_nr_offset(0),
                              btrfs_item_nr_offset(push_items),
                             (btrfs_header_nritems(right) - push_items) *
                             sizeof(struct btrfs_item));
        }

        btrfs_init_map_token(&token, right);
        right_nritems -= push_items;
        btrfs_set_header_nritems(right, right_nritems);
        push_space = BTRFS_LEAF_DATA_SIZE(fs_info);
        for (i = 0; i < right_nritems; i++) {
                item = btrfs_item_nr(i);

                push_space = push_space - btrfs_token_item_size(&token, item);
                btrfs_set_token_item_offset(&token, item, push_space);
        }

        btrfs_mark_buffer_dirty(left);
        if (right_nritems)
                btrfs_mark_buffer_dirty(right);
        else
                btrfs_clean_tree_block(right);

        btrfs_item_key(right, &disk_key, 0);
        fixup_low_keys(path, &disk_key, 1);

        /* then fixup the leaf pointer in the path */
        if (path->slots[0] < push_items) {