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

#include <linux/sched.h>
#include <linux/slab.h>
#include <linux/blkdev.h>
#include <linux/list_sort.h>
#include <linux/iversion.h>
#include "ctree.h"
#include "tree-log.h"
#include "disk-io.h"
#include "locking.h"
#include "print-tree.h"
#include "backref.h"
#include "compression.h"
#include "qgroup.h"
#include "inode-map.h"

/* magic values for the inode_only field in btrfs_log_inode:
 *
 * LOG_INODE_ALL means to log everything
 * LOG_INODE_EXISTS means to log just enough to recreate the inode
 * during log replay
 */
#define LOG_INODE_ALL 0
#define LOG_INODE_EXISTS 1
#define LOG_OTHER_INODE 2

/*
 * directory trouble cases
 *
 * 1) on rename or unlink, if the inode being unlinked isn't in the fsync
 * log, we must force a full commit before doing an fsync of the directory
 * where the unlink was done.
 * ---> record transid of last unlink/rename per directory
 *
 * mkdir foo/some_dir
 * normal commit
 * rename foo/some_dir foo2/some_dir
 * mkdir foo/some_dir
 * fsync foo/some_dir/some_file
 *
 * The fsync above will unlink the original some_dir without recording
 * it in its new location (foo2).  After a crash, some_dir will be gone
 * unless the fsync of some_file forces a full commit
 *
 * 2) we must log any new names for any file or dir that is in the fsync
 * log. ---> check inode while renaming/linking.
 *
 * 2a) we must log any new names for any file or dir during rename
 * when the directory they are being removed from was logged.
 * ---> check inode and old parent dir during rename
 *
 *  2a is actually the more important variant.  With the extra logging
 *  a crash might unlink the old name without recreating the new one
 *
 * 3) after a crash, we must go through any directories with a link count
 * of zero and redo the rm -rf
 *
 * mkdir f1/foo
 * normal commit
 * rm -rf f1/foo
 * fsync(f1)
 *
 * The directory f1 was fully removed from the FS, but fsync was never
 * called on f1, only its parent dir.  After a crash the rm -rf must
 * be replayed.  This must be able to recurse down the entire
 * directory tree.  The inode link count fixup code takes care of the
 * ugly details.
 */

/*
 * stages for the tree walking.  The first
 * stage (0) is to only pin down the blocks we find
 * the second stage (1) is to make sure that all the inodes
 * we find in the log are created in the subvolume.
 *
 * The last stage is to deal with directories and links and extents
 * and all the other fun semantics
 */
#define LOG_WALK_PIN_ONLY 0
#define LOG_WALK_REPLAY_INODES 1
#define LOG_WALK_REPLAY_DIR_INDEX 2
#define LOG_WALK_REPLAY_ALL 3

static int btrfs_log_inode(struct btrfs_trans_handle *trans,
                           struct btrfs_root *root, struct btrfs_inode *inode,
                           int inode_only,
                           const loff_t start,
                           const loff_t end,
                           struct btrfs_log_ctx *ctx);
static int link_to_fixup_dir(struct btrfs_trans_handle *trans,
                             struct btrfs_root *root,
                             struct btrfs_path *path, u64 objectid);
static noinline int replay_dir_deletes(struct btrfs_trans_handle *trans,
                                       struct btrfs_root *root,
                                       struct btrfs_root *log,
                                       struct btrfs_path *path,
                                       u64 dirid, int del_all);

/*
 * tree logging is a special write ahead log used to make sure that
 * fsyncs and O_SYNCs can happen without doing full tree commits.
 *
 * Full tree commits are expensive because they require commonly
 * modified blocks to be recowed, creating many dirty pages in the
 * extent tree an 4x-6x higher write load than ext3.
 *
 * Instead of doing a tree commit on every fsync, we use the
 * key ranges and transaction ids to find items for a given file or directory
 * that have changed in this transaction.  Those items are copied into
 * a special tree (one per subvolume root), that tree is written to disk
 * and then the fsync is considered complete.
 *
 * After a crash, items are copied out of the log-tree back into the
 * subvolume tree.  Any file data extents found are recorded in the extent
 * allocation tree, and the log-tree freed.
 *
 * The log tree is read three times, once to pin down all the extents it is
 * using in ram and once, once to create all the inodes logged in the tree
 * and once to do all the other items.
 */

/*
 * start a sub transaction and setup the log tree
 * this increments the log tree writer count to make the people
 * syncing the tree wait for us to finish
 */
static int start_log_trans(struct btrfs_trans_handle *trans,
                           struct btrfs_root *root,
                           struct btrfs_log_ctx *ctx)
{
        struct btrfs_fs_info *fs_info = root->fs_info;
        int ret = 0;

        mutex_lock(&root->log_mutex);

        if (root->log_root) {
                if (btrfs_need_log_full_commit(fs_info, trans)) {
                        ret = -EAGAIN;
                        goto out;
                }

                if (!root->log_start_pid) {
                        clear_bit(BTRFS_ROOT_MULTI_LOG_TASKS, &root->state);
                        root->log_start_pid = current->pid;
                } else if (root->log_start_pid != current->pid) {
                        set_bit(BTRFS_ROOT_MULTI_LOG_TASKS, &root->state);
                }
        } else {
                mutex_lock(&fs_info->tree_log_mutex);
                if (!fs_info->log_root_tree)
                        ret = btrfs_init_log_root_tree(trans, fs_info);
                mutex_unlock(&fs_info->tree_log_mutex);
                if (ret)
                        goto out;

                ret = btrfs_add_log_tree(trans, root);
                if (ret)
                        goto out;

                clear_bit(BTRFS_ROOT_MULTI_LOG_TASKS, &root->state);
                root->log_start_pid = current->pid;
        }

        atomic_inc(&root->log_batch);
        atomic_inc(&root->log_writers);
        if (ctx) {
                int index = root->log_transid % 2;
                list_add_tail(&ctx->list, &root->log_ctxs[index]);
                ctx->log_transid = root->log_transid;
        }

out:
        mutex_unlock(&root->log_mutex);
        return ret;
}

/*
 * returns 0 if there was a log transaction running and we were able
 * to join, or returns -ENOENT if there were not transactions
 * in progress
 */
static int join_running_log_trans(struct btrfs_root *root)
{
        int ret = -ENOENT;

        smp_mb();
        if (!root->log_root)
                return -ENOENT;

        mutex_lock(&root->log_mutex);
        if (root->log_root) {
                ret = 0;
                atomic_inc(&root->log_writers);
        }
        mutex_unlock(&root->log_mutex);
        return ret;
}

/*
 * This either makes the current running log transaction wait
 * until you call btrfs_end_log_trans() or it makes any future
 * log transactions wait until you call btrfs_end_log_trans()
 */
int btrfs_pin_log_trans(struct btrfs_root *root)
{
        int ret = -ENOENT;

        mutex_lock(&root->log_mutex);
        atomic_inc(&root->log_writers);
        mutex_unlock(&root->log_mutex);
        return ret;
}

/*
 * indicate we're done making changes to the log tree
 * and wake up anyone waiting to do a sync
 */
void btrfs_end_log_trans(struct btrfs_root *root)
{
        if (atomic_dec_and_test(&root->log_writers)) {
                /* atomic_dec_and_test implies a barrier */
                cond_wake_up_nomb(&root->log_writer_wait);
        }
}


/*
 * the walk control struct is used to pass state down the chain when
 * processing the log tree.  The stage field tells us which part
 * of the log tree processing we are currently doing.  The others
 * are state fields used for that specific part
 */
struct walk_control {
        /* should we free the extent on disk when done?  This is used
         * at transaction commit time while freeing a log tree
         */
        int free;

        /* should we write out the extent buffer?  This is used
         * while flushing the log tree to disk during a sync
         */
        int write;

        /* should we wait for the extent buffer io to finish?  Also used
         * while flushing the log tree to disk for a sync
         */
        int wait;

        /* pin only walk, we record which extents on disk belong to the
         * log trees
         */
        int pin;

        /* what stage of the replay code we're currently in */
        int stage;

        /* the root we are currently replaying */
        struct btrfs_root *replay_dest;

        /* the trans handle for the current replay */
        struct btrfs_trans_handle *trans;

        /* the function that gets used to process blocks we find in the
         * tree.  Note the extent_buffer might not be up to date when it is
         * passed in, and it must be checked or read if you need the data
         * inside it
         */
        int (*process_func)(struct btrfs_root *log, struct extent_buffer *eb,
                            struct walk_control *wc, u64 gen, int level);
};

/*
 * process_func used to pin down extents, write them or wait on them
 */
static int process_one_buffer(struct btrfs_root *log,
                              struct extent_buffer *eb,
                              struct walk_control *wc, u64 gen, int level)
{
        struct btrfs_fs_info *fs_info = log->fs_info;
        int ret = 0;

        /*
         * If this fs is mixed then we need to be able to process the leaves to
         * pin down any logged extents, so we have to read the block.
         */
        if (btrfs_fs_incompat(fs_info, MIXED_GROUPS)) {
                ret = btrfs_read_buffer(eb, gen, level, NULL);
                if (ret)
                        return ret;
        }

        if (wc->pin)
                ret = btrfs_pin_extent_for_log_replay(fs_info, eb->start,
                                                      eb->len);

        if (!ret && btrfs_buffer_uptodate(eb, gen, 0)) {
                if (wc->pin && btrfs_header_level(eb) == 0)
                        ret = btrfs_exclude_logged_extents(fs_info, eb);
                if (wc->write)
                        btrfs_write_tree_block(eb);
                if (wc->wait)
                        btrfs_wait_tree_block_writeback(eb);
        }
        return ret;
}

/*
 * Item overwrite used by replay and tree logging.  eb, slot and key all refer
 * to the src data we are copying out.
 *
 * root is the tree we are copying into, and path is a scratch
 * path for use in this function (it should be released on entry and
 * will be released on exit).
 *
 * If the key is already in the destination tree the existing item is
 * overwritten.  If the existing item isn't big enough, it is extended.
 * If it is too large, it is truncated.
 *
 * If the key isn't in the destination yet, a new item is inserted.
 */
static noinline int overwrite_item(struct btrfs_trans_handle *trans,
                                   struct btrfs_root *root,
                                   struct btrfs_path *path,
                                   struct extent_buffer *eb, int slot,
                                   struct btrfs_key *key)
{
        struct btrfs_fs_info *fs_info = root->fs_info;
        int ret;
        u32 item_size;
        u64 saved_i_size = 0;
        int save_old_i_size = 0;
        unsigned long src_ptr;
        unsigned long dst_ptr;
        int overwrite_root = 0;
        bool inode_item = key->type == BTRFS_INODE_ITEM_KEY;

        if (root->root_key.objectid != BTRFS_TREE_LOG_OBJECTID)
                overwrite_root = 1;

        item_size = btrfs_item_size_nr(eb, slot);
        src_ptr = btrfs_item_ptr_offset(eb, slot);

        /* look for the key in the destination tree */
        ret = btrfs_search_slot(NULL, root, key, path, 0, 0);
        if (ret < 0)
                return ret;

        if (ret == 0) {
                char *src_copy;
                char *dst_copy;
                u32 dst_size = btrfs_item_size_nr(path->nodes[0],
                                                  path->slots[0]);
                if (dst_size != item_size)
                        goto insert;

                if (item_size == 0) {
                        btrfs_release_path(path);
                        return 0;
                }
                dst_copy = kmalloc(item_size, GFP_NOFS);
                src_copy = kmalloc(item_size, GFP_NOFS);
                if (!dst_copy || !src_copy) {
                        btrfs_release_path(path);
                        kfree(dst_copy);
                        kfree(src_copy);
                        return -ENOMEM;
                }

                read_extent_buffer(eb, src_copy, src_ptr, item_size);

                dst_ptr = btrfs_item_ptr_offset(path->nodes[0], path->slots[0]);
                read_extent_buffer(path->nodes[0], dst_copy, dst_ptr,
                                   item_size);
                ret = memcmp(dst_copy, src_copy, item_size);

                kfree(dst_copy);
                kfree(src_copy);
                /*
                 * they have the same contents, just return, this saves
                 * us from cowing blocks in the destination tree and doing
                 * extra writes that may not have been done by a previous
                 * sync
                 */
                if (ret == 0) {
                        btrfs_release_path(path);
                        return 0;
                }

                /*
                 * We need to load the old nbytes into the inode so when we
                 * replay the extents we've logged we get the right nbytes.
                 */
                if (inode_item) {
                        struct btrfs_inode_item *item;
                        u64 nbytes;
                        u32 mode;

                        item = btrfs_item_ptr(path->nodes[0], path->slots[0],
                                              struct btrfs_inode_item);
                        nbytes = btrfs_inode_nbytes(path->nodes[0], item);
                        item = btrfs_item_ptr(eb, slot,
                                              struct btrfs_inode_item);
                        btrfs_set_inode_nbytes(eb, item, nbytes);

                        /*
                         * If this is a directory we need to reset the i_size to
                         * 0 so that we can set it up properly when replaying
                         * the rest of the items in this log.
                         */
                        mode = btrfs_inode_mode(eb, item);
                        if (S_ISDIR(mode))
                                btrfs_set_inode_size(eb, item, 0);
                }
        } else if (inode_item) {
                struct btrfs_inode_item *item;
                u32 mode;

                /*
                 * New inode, set nbytes to 0 so that the nbytes comes out
                 * properly when we replay the extents.
                 */
                item = btrfs_item_ptr(eb, slot, struct btrfs_inode_item);
                btrfs_set_inode_nbytes(eb, item, 0);

                /*
                 * If this is a directory we need to reset the i_size to 0 so
                 * that we can set it up properly when replaying the rest of
                 * the items in this log.
                 */
                mode = btrfs_inode_mode(eb, item);
                if (S_ISDIR(mode))
                        btrfs_set_inode_size(eb, item, 0);
        }
insert:
        btrfs_release_path(path);
        /* try to insert the key into the destination tree */
        path->skip_release_on_error = 1;
        ret = btrfs_insert_empty_item(trans, root, path,
                                      key, item_size);
        path->skip_release_on_error = 0;

        /* make sure any existing item is the correct size */
        if (ret == -EEXIST || ret == -EOVERFLOW) {
                u32 found_size;
                found_size = btrfs_item_size_nr(path->nodes[0],
                                                path->slots[0]);
                if (found_size > item_size)
                        btrfs_truncate_item(fs_info, path, item_size, 1);
                else if (found_size < item_size)
                        btrfs_extend_item(fs_info, path,
                                          item_size - found_size);
        } else if (ret) {
                return ret;
        }
        dst_ptr = btrfs_item_ptr_offset(path->nodes[0],
                                        path->slots[0]);

        /* don't overwrite an existing inode if the generation number
         * was logged as zero.  This is done when the tree logging code
         * is just logging an inode to make sure it exists after recovery.
         *
         * Also, don't overwrite i_size on directories during replay.
         * log replay inserts and removes directory items based on the
         * state of the tree found in the subvolume, and i_size is modified
         * as it goes
         */
        if (key->type == BTRFS_INODE_ITEM_KEY && ret == -EEXIST) {
                struct btrfs_inode_item *src_item;
                struct btrfs_inode_item *dst_item;

                src_item = (struct btrfs_inode_item *)src_ptr;
                dst_item = (struct btrfs_inode_item *)dst_ptr;

                if (btrfs_inode_generation(eb, src_item) == 0) {
                        struct extent_buffer *dst_eb = path->nodes[0];
                        const u64 ino_size = btrfs_inode_size(eb, src_item);

                        /*
                         * For regular files an ino_size == 0 is used only when
                         * logging that an inode exists, as part of a directory
                         * fsync, and the inode wasn't fsynced before. In this
                         * case don't set the size of the inode in the fs/subvol
                         * tree, otherwise we would be throwing valid data away.
                         */
                        if (S_ISREG(btrfs_inode_mode(eb, src_item)) &&
                            S_ISREG(btrfs_inode_mode(dst_eb, dst_item)) &&
                            ino_size != 0) {
                                struct btrfs_map_token token;

                                btrfs_init_map_token(&token);
                                btrfs_set_token_inode_size(dst_eb, dst_item,
                                                           ino_size, &token);
                        }
                        goto no_copy;
                }

                if (overwrite_root &&
                    S_ISDIR(btrfs_inode_mode(eb, src_item)) &&
                    S_ISDIR(btrfs_inode_mode(path->nodes[0], dst_item))) {
                        save_old_i_size = 1;
                        saved_i_size = btrfs_inode_size(path->nodes[0],
                                                        dst_item);
                }
        }

        copy_extent_buffer(path->nodes[0], eb, dst_ptr,
                           src_ptr, item_size);

        if (save_old_i_size) {
                struct btrfs_inode_item *dst_item;
                dst_item = (struct btrfs_inode_item *)dst_ptr;
                btrfs_set_inode_size(path->nodes[0], dst_item, saved_i_size);
        }

        /* make sure the generation is filled in */
        if (key->type == BTRFS_INODE_ITEM_KEY) {
                struct btrfs_inode_item *dst_item;
                dst_item = (struct btrfs_inode_item *)dst_ptr;
                if (btrfs_inode_generation(path->nodes[0], dst_item) == 0) {
                        btrfs_set_inode_generation(path->nodes[0], dst_item,
                                                   trans->transid);
                }
        }
no_copy:
        btrfs_mark_buffer_dirty(path->nodes[0]);
        btrfs_release_path(path);
        return 0;
}

/*
 * simple helper to read an inode off the disk from a given root
 * This can only be called for subvolume roots and not for the log
 */
static noinline struct inode *read_one_inode(struct btrfs_root *root,
                                             u64 objectid)
{
        struct btrfs_key key;
        struct inode *inode;

        key.objectid = objectid;
        key.type = BTRFS_INODE_ITEM_KEY;
        key.offset = 0;
        inode = btrfs_iget(root->fs_info->sb, &key, root, NULL);
        if (IS_ERR(inode)) {
                inode = NULL;
        } else if (is_bad_inode(inode)) {
                iput(inode);
                inode = NULL;
        }
        return inode;
}

/* replays a single extent in 'eb' at 'slot' with 'key' into the
 * subvolume 'root'.  path is released on entry and should be released
 * on exit.
 *
 * extents in the log tree have not been allocated out of the extent
 * tree yet.  So, this completes the allocation, taking a reference
 * as required if the extent already exists or creating a new extent
 * if it isn't in the extent allocation tree yet.
 *
 * The extent is inserted into the file, dropping any existing extents
 * from the file that overlap the new one.
 */
static noinline int replay_one_extent(struct btrfs_trans_handle *trans,
                                      struct btrfs_root *root,
                                      struct btrfs_path *path,
                                      struct extent_buffer *eb, int slot,
                                      struct btrfs_key *key)
{
        struct btrfs_fs_info *fs_info = root->fs_info;
        int found_type;
        u64 extent_end;
        u64 start = key->offset;
        u64 nbytes = 0;
        struct btrfs_file_extent_item *item;
        struct inode *inode = NULL;
        unsigned long size;
        int ret = 0;

        item = btrfs_item_ptr(eb, slot, struct btrfs_file_extent_item);
        found_type = btrfs_file_extent_type(eb, item);

        if (found_type == BTRFS_FILE_EXTENT_REG ||
            found_type == BTRFS_FILE_EXTENT_PREALLOC) {
                nbytes = btrfs_file_extent_num_bytes(eb, item);
                extent_end = start + nbytes;

                /*
                 * We don't add to the inodes nbytes if we are prealloc or a
                 * hole.
                 */
                if (btrfs_file_extent_disk_bytenr(eb, item) == 0)
                        nbytes = 0;
        } else if (found_type == BTRFS_FILE_EXTENT_INLINE) {
                size = btrfs_file_extent_inline_len(eb, slot, item);
                nbytes = btrfs_file_extent_ram_bytes(eb, item);
                extent_end = ALIGN(start + size,
                                   fs_info->sectorsize);
        } else {
                ret = 0;
                goto out;
        }

        inode = read_one_inode(root, key->objectid);
        if (!inode) {
                ret = -EIO;
                goto out;
        }

        /*
         * first check to see if we already have this extent in the
         * file.  This must be done before the btrfs_drop_extents run
         * so we don't try to drop this extent.
         */
        ret = btrfs_lookup_file_extent(trans, root, path,
                        btrfs_ino(BTRFS_I(inode)), start, 0);

        if (ret == 0 &&
            (found_type == BTRFS_FILE_EXTENT_REG ||
             found_type == BTRFS_FILE_EXTENT_PREALLOC)) {
                struct btrfs_file_extent_item cmp1;
                struct btrfs_file_extent_item cmp2;
                struct btrfs_file_extent_item *existing;
                struct extent_buffer *leaf;

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

                read_extent_buffer(eb, &cmp1, (unsigned long)item,
                                   sizeof(cmp1));
                read_extent_buffer(leaf, &cmp2, (unsigned long)existing,
                                   sizeof(cmp2));

                /*
                 * we already have a pointer to this exact extent,
                 * we don't have to do anything
                 */
                if (memcmp(&cmp1, &cmp2, sizeof(cmp1)) == 0) {
                        btrfs_release_path(path);
                        goto out;
                }
        }
        btrfs_release_path(path);

        /* drop any overlapping extents */
        ret = btrfs_drop_extents(trans, root, inode, start, extent_end, 1);
        if (ret)
                goto out;

        if (found_type == BTRFS_FILE_EXTENT_REG ||
            found_type == BTRFS_FILE_EXTENT_PREALLOC) {
                u64 offset;
                unsigned long dest_offset;
                struct btrfs_key ins;

                if (btrfs_file_extent_disk_bytenr(eb, item) == 0 &&
                    btrfs_fs_incompat(fs_info, NO_HOLES))
                        goto update_inode;

                ret = btrfs_insert_empty_item(trans, root, path, key,
                                              sizeof(*item));
                if (ret)
                        goto out;
                dest_offset = btrfs_item_ptr_offset(path->nodes[0],
                                                    path->slots[0]);
                copy_extent_buffer(path->nodes[0], eb, dest_offset,
                                (unsigned long)item,  sizeof(*item));

                ins.objectid = btrfs_file_extent_disk_bytenr(eb, item);
                ins.offset = btrfs_file_extent_disk_num_bytes(eb, item);
                ins.type = BTRFS_EXTENT_ITEM_KEY;
                offset = key->offset - btrfs_file_extent_offset(eb, item);

                /*
                 * Manually record dirty extent, as here we did a shallow
                 * file extent item copy and skip normal backref update,
                 * but modifying extent tree all by ourselves.
                 * So need to manually record dirty extent for qgroup,
                 * as the owner of the file extent changed from log tree
                 * (doesn't affect qgroup) to fs/file tree(affects qgroup)
                 */
                ret = btrfs_qgroup_trace_extent(trans, fs_info,
                                btrfs_file_extent_disk_bytenr(eb, item),
                                btrfs_file_extent_disk_num_bytes(eb, item),
                                GFP_NOFS);
                if (ret < 0)
                        goto out;

                if (ins.objectid > 0) {
                        u64 csum_start;
                        u64 csum_end;
                        LIST_HEAD(ordered_sums);
                        /*
                         * is this extent already allocated in the extent
                         * allocation tree?  If so, just add a reference
                         */
                        ret = btrfs_lookup_data_extent(fs_info, ins.objectid,
                                                ins.offset);
                        if (ret == 0) {
                                ret = btrfs_inc_extent_ref(trans, root,
                                                ins.objectid, ins.offset,
                                                0, root->root_key.objectid,
                                                key->objectid, offset);
                                if (ret)
                                        goto out;
                        } else {
                                /*
                                 * insert the extent pointer in the extent
                                 * allocation tree
                                 */
                                ret = btrfs_alloc_logged_file_extent(trans,
                                                fs_info,
                                                root->root_key.objectid,
                                                key->objectid, offset, &ins);
                                if (ret)
                                        goto out;
                        }
                        btrfs_release_path(path);

                        if (btrfs_file_extent_compression(eb, item)) {
                                csum_start = ins.objectid;
                                csum_end = csum_start + ins.offset;
                        } else {
                                csum_start = ins.objectid +
                                        btrfs_file_extent_offset(eb, item);
                                csum_end = csum_start +
                                        btrfs_file_extent_num_bytes(eb, item);
                        }

                        ret = btrfs_lookup_csums_range(root->log_root,
                                                csum_start, csum_end - 1,
                                                &ordered_sums, 0);
                        if (ret)
                                goto out;
                        /*
                         * Now delete all existing cums in the csum root that
                         * cover our range. We do this because we can have an
                         * extent that is completely referenced by one file
                         * extent item and partially referenced by another
                         * file extent item (like after using the clone or
                         * extent_same ioctls). In this case if we end up doing
                         * the replay of the one that partially references the
                         * extent first, and we do not do the csum deletion
                         * below, we can get 2 csum items in the csum tree that
                         * overlap each other. For example, imagine our log has
                         * the two following file extent items:
                         *
                         * key (257 EXTENT_DATA 409600)
                         *     extent data disk byte 12845056 nr 102400
                         *     extent data offset 20480 nr 20480 ram 102400
                         *
                         * key (257 EXTENT_DATA 819200)
                         *     extent data disk byte 12845056 nr 102400
                         *     extent data offset 0 nr 102400 ram 102400
                         *
                         * Where the second one fully references the 100K extent
                         * that starts at disk byte 12845056, and the log tree
                         * has a single csum item that covers the entire range
                         * of the extent:
                         *
                         * key (EXTENT_CSUM EXTENT_CSUM 12845056) itemsize 100
                         *
                         * After the first file extent item is replayed, the
                         * csum tree gets the following csum item:
                         *
                         * key (EXTENT_CSUM EXTENT_CSUM 12865536) itemsize 20
                         *
                         * Which covers the 20K sub-range starting at offset 20K
                         * of our extent. Now when we replay the second file
                         * extent item, if we do not delete existing csum items
                         * that cover any of its blocks, we end up getting two
                         * csum items in our csum tree that overlap each other:
                         *
                         * key (EXTENT_CSUM EXTENT_CSUM 12845056) itemsize 100
                         * key (EXTENT_CSUM EXTENT_CSUM 12865536) itemsize 20
                         *
                         * Which is a problem, because after this anyone trying
                         * to lookup up for the checksum of any block of our
                         * extent starting at an offset of 40K or higher, will
                         * end up looking at the second csum item only, which
                         * does not contain the checksum for any block starting
                         * at offset 40K or higher of our extent.
                         */
                        while (!list_empty(&ordered_sums)) {
                                struct btrfs_ordered_sum *sums;
                                sums = list_entry(ordered_sums.next,
                                                struct btrfs_ordered_sum,
                                                list);
                                if (!ret)
                                        ret = btrfs_del_csums(trans, fs_info,
                                                              sums->bytenr,
                                                              sums->len);
                                if (!ret)
                                        ret = btrfs_csum_file_blocks(trans,
                                                fs_info->csum_root, sums);
                                list_del(&sums->list);
                                kfree(sums);
                        }
                        if (ret)
                                goto out;
                } else {
                        btrfs_release_path(path);
                }
        } else if (found_type == BTRFS_FILE_EXTENT_INLINE) {
                /* inline extents are easy, we just overwrite them */
                ret = overwrite_item(trans, root, path, eb, slot, key);
                if (ret)
                        goto out;
        }

        inode_add_bytes(inode, nbytes);
update_inode:
        ret = btrfs_update_inode(trans, root, inode);
out:
        if (inode)
                iput(inode);
        return ret;
}

/*
 * when cleaning up conflicts between the directory names in the
 * subvolume, directory names in the log and directory names in the
 * inode back references, we may have to unlink inodes from directories.
 *
 * This is a helper function to do the unlink of a specific directory
 * item
 */
static noinline int drop_one_dir_item(struct btrfs_trans_handle *trans,
                                      struct btrfs_root *root,
                                      struct btrfs_path *path,
                                      struct btrfs_inode *dir,
                                      struct btrfs_dir_item *di)
{
        struct inode *inode;
        char *name;
        int name_len;
        struct extent_buffer *leaf;
        struct btrfs_key location;
        int ret;

        leaf = path->nodes[0];

        btrfs_dir_item_key_to_cpu(leaf, di, &location);
        name_len = btrfs_dir_name_len(leaf, di);
        name = kmalloc(name_len, GFP_NOFS);
        if (!name)
                return -ENOMEM;

        read_extent_buffer(leaf, name, (unsigned long)(di + 1), name_len);
        btrfs_release_path(path);

        inode = read_one_inode(root, location.objectid);
        if (!inode) {
                ret = -EIO;
                goto out;
        }

        ret = link_to_fixup_dir(trans, root, path, location.objectid);
        if (ret)
                goto out;

        ret = btrfs_unlink_inode(trans, root, dir, BTRFS_I(inode), name,
                        name_len);
        if (ret)
                goto out;
        else
                ret = btrfs_run_delayed_items(trans);
out:
        kfree(name);
        iput(inode);
        return ret;
}

/*
 * helper function to see if a given name and sequence number found
 * in an inode back reference are already in a directory and correctly
 * point to this inode
 */
static noinline int inode_in_dir(struct btrfs_root *root,
                                 struct btrfs_path *path,
                                 u64 dirid, u64 objectid, u64 index,
                                 const char *name, int name_len)
{
        struct btrfs_dir_item *di;
        struct btrfs_key location;
        int match = 0;

        di = btrfs_lookup_dir_index_item(NULL, root, path, dirid,
                                         index, name, name_len, 0);
        if (di && !IS_ERR(di)) {
                btrfs_dir_item_key_to_cpu(path->nodes[0], di, &location);
                if (location.objectid != objectid)
                        goto out;
        } else
                goto out;
        btrfs_release_path(path);

        di = btrfs_lookup_dir_item(NULL, root, path, dirid, name, name_len, 0);
        if (di && !IS_ERR(di)) {
                btrfs_dir_item_key_to_cpu(path->nodes[0], di, &location);
                if (location.objectid != objectid)
                        goto out;
        } else
                goto out;
        match = 1;
out:
        btrfs_release_path(path);
        return match;
}

/*
 * helper function to check a log tree for a named back reference in
 * an inode.  This is used to decide if a back reference that is
 * found in the subvolume conflicts with what we find in the log.
 *
 * inode backreferences may have multiple refs in a single item,
 * during replay we process one reference at a time, and we don't
 * want to delete valid links to a file from the subvolume if that
 * link is also in the log.
 */
static noinline int backref_in_log(struct btrfs_root *log,
                                   struct btrfs_key *key,
                                   u64 ref_objectid,
                                   const char *name, int namelen)
{
        struct btrfs_path *path;
        struct btrfs_inode_ref *ref;
        unsigned long ptr;
        unsigned long ptr_end;
        unsigned long name_ptr;
        int found_name_len;
        int item_size;
        int ret;
        int match = 0;

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

        ret = btrfs_search_slot(NULL, log, key, path, 0, 0);
        if (ret != 0)
                goto out;

        ptr = btrfs_item_ptr_offset(path->nodes[0], path->slots[0]);

        if (key->type == BTRFS_INODE_EXTREF_KEY) {
                if (btrfs_find_name_in_ext_backref(path->nodes[0],
                                                   path->slots[0],
                                                   ref_objectid,
                                                   name, namelen, NULL))
                        match = 1;

                goto out;
        }

        item_size = btrfs_item_size_nr(path->nodes[0], path->slots[0]);
        ptr_end = ptr + item_size;
        while (ptr < ptr_end) {
                ref = (struct btrfs_inode_ref *)ptr;
                found_name_len = btrfs_inode_ref_name_len(path->nodes[0], ref);
                if (found_name_len == namelen) {
                        name_ptr = (unsigned long)(ref + 1);
                        ret = memcmp_extent_buffer(path->nodes[0], name,
                                                   name_ptr, namelen);
                        if (ret == 0) {
                                match = 1;
                                goto out;
                        }
                }
                ptr = (unsigned long)(ref + 1) + found_name_len;
        }
out:
        btrfs_free_path(path);
        return match;
}

static inline int __add_inode_ref(struct btrfs_trans_handle *trans,
                                  struct btrfs_root *root,
                                  struct btrfs_path *path,
                                  struct btrfs_root *log_root,
                                  struct btrfs_inode *dir,
                                  struct btrfs_inode *inode,
                                  u64 inode_objectid, u64 parent_objectid,
                                  u64 ref_index, char *name, int namelen,
                                  int *search_done)
{
        int ret;
        char *victim_name;
        int victim_name_len;
        struct extent_buffer *leaf;
        struct btrfs_dir_item *di;
        struct btrfs_key search_key;
        struct btrfs_inode_extref *extref;

again:
        /* Search old style refs */
        search_key.objectid = inode_objectid;
        search_key.type = BTRFS_INODE_REF_KEY;
        search_key.offset = parent_objectid;
        ret = btrfs_search_slot(NULL, root, &search_key, path, 0, 0);
        if (ret == 0) {
                struct btrfs_inode_ref *victim_ref;
                unsigned long ptr;
                unsigned long ptr_end;

                leaf = path->nodes[0];

                /* are we trying to overwrite a back ref for the root directory
                 * if so, just jump out, we're done
                 */
                if (search_key.objectid == search_key.offset)
                        return 1;

                /* check all the names in this back reference to see
                 * if they are in the log.  if so, we allow them to stay
                 * otherwise they must be unlinked as a conflict
                 */
                ptr = btrfs_item_ptr_offset(leaf, path->slots[0]);
                ptr_end = ptr + btrfs_item_size_nr(leaf, path->slots[0]);
                while (ptr < ptr_end) {
                        victim_ref = (struct btrfs_inode_ref *)ptr;
                        victim_name_len = btrfs_inode_ref_name_len(leaf,
                                                                   victim_ref);
                        victim_name = kmalloc(victim_name_len, GFP_NOFS);
                        if (!victim_name)
                                return -ENOMEM;

                        read_extent_buffer(leaf, victim_name,
                                           (unsigned long)(victim_ref + 1),
                                           victim_name_len);

                        if (!backref_in_log(log_root, &search_key,
                                            parent_objectid,
                                            victim_name,
                                            victim_name_len)) {
                                inc_nlink(&inode->vfs_inode);
                                btrfs_release_path(path);

                                ret = btrfs_unlink_inode(trans, root, dir, inode,
                                                victim_name, victim_name_len);
                                kfree(victim_name);
                                if (ret)
                                        return ret;
                                ret = btrfs_run_delayed_items(trans);
                                if (ret)
                                        return ret;
                                *search_done = 1;
                                goto again;
                        }
                        kfree(victim_name);

                        ptr = (unsigned long)(victim_ref + 1) + victim_name_len;
                }

                /*
                 * NOTE: we have searched root tree and checked the
                 * corresponding ref, it does not need to check again.
                 */
                *search_done = 1;
        }
        btrfs_release_path(path);

        /* Same search but for extended refs */
        extref = btrfs_lookup_inode_extref(NULL, root, path, name, namelen,
                                           inode_objectid, parent_objectid, 0,
                                           0);
        if (!IS_ERR_OR_NULL(extref)) {
                u32 item_size;
                u32 cur_offset = 0;
                unsigned long base;
                struct inode *victim_parent;

                leaf = path->nodes[0];

                item_size = btrfs_item_size_nr(leaf, path->slots[0]);
                base = btrfs_item_ptr_offset(leaf, path->slots[0]);

                while (cur_offset < item_size) {
                        extref = (struct btrfs_inode_extref *)(base + cur_offset);

                        victim_name_len = btrfs_inode_extref_name_len(leaf, extref);

                        if (btrfs_inode_extref_parent(leaf, extref) != parent_objectid)
                                goto next;

                        victim_name = kmalloc(victim_name_len, GFP_NOFS);
                        if (!victim_name)
                                return -ENOMEM;
                        read_extent_buffer(leaf, victim_name, (unsigned long)&extref->name,
                                           victim_name_len);

                        search_key.objectid = inode_objectid;
                        search_key.type = BTRFS_INODE_EXTREF_KEY;
                        search_key.offset = btrfs_extref_hash(parent_objectid,
                                                              victim_name,
                                                              victim_name_len);
                        ret = 0;
                        if (!backref_in_log(log_root, &search_key,
                                            parent_objectid, victim_name,
                                            victim_name_len)) {
                                ret = -ENOENT;
                                victim_parent = read_one_inode(root,
                                                parent_objectid);
                                if (victim_parent) {
                                        inc_nlink(&inode->vfs_inode);
                                        btrfs_release_path(path);

                                        ret = btrfs_unlink_inode(trans, root,
                                                        BTRFS_I(victim_parent),
                                                        inode,
                                                        victim_name,
                                                        victim_name_len);
                                        if (!ret)
                                                ret = btrfs_run_delayed_items(
                                                                  trans);
                                }
                                iput(victim_parent);
                                kfree(victim_name);
                                if (ret)
                                        return ret;
                                *search_done = 1;
                                goto again;
                        }
                        kfree(victim_name);
next:
                        cur_offset += victim_name_len + sizeof(*extref);
                }
                *search_done = 1;
        }
        btrfs_release_path(path);

        /* look for a conflicting sequence number */
        di = btrfs_lookup_dir_index_item(trans, root, path, btrfs_ino(dir),
                                         ref_index, name, namelen, 0);
        if (di && !IS_ERR(di)) {
                ret = drop_one_dir_item(trans, root, path, dir, di);
                if (ret)
                        return ret;
        }
        btrfs_release_path(path);

        /* look for a conflicing name */
        di = btrfs_lookup_dir_item(trans, root, path, btrfs_ino(dir),
                                   name, namelen, 0);
        if (di && !IS_ERR(di)) {
                ret = drop_one_dir_item(trans, root, path, dir, di);
                if (ret)
                        return ret;
        }
        btrfs_release_path(path);

        return 0;
}

static int extref_get_fields(struct extent_buffer *eb, unsigned long ref_ptr,
                             u32 *namelen, char **name, u64 *index,
                             u64 *parent_objectid)
{
        struct btrfs_inode_extref *extref;

        extref = (struct btrfs_inode_extref *)ref_ptr;

        *namelen = btrfs_inode_extref_name_len(eb, extref);
        *name = kmalloc(*namelen, GFP_NOFS);
        if (*name == NULL)
                return -ENOMEM;

        read_extent_buffer(eb, *name, (unsigned long)&extref->name,
                           *namelen);

        if (index)
                *index = btrfs_inode_extref_index(eb, extref);
        if (parent_objectid)
                *parent_objectid = btrfs_inode_extref_parent(eb, extref);

        return 0;
}

static int ref_get_fields(struct extent_buffer *eb, unsigned long ref_ptr,
                          u32 *namelen, char **name, u64 *index)
{
        struct btrfs_inode_ref *ref;

        ref = (struct btrfs_inode_ref *)ref_ptr;

        *namelen = btrfs_inode_ref_name_len(eb, ref);
        *name = kmalloc(*namelen, GFP_NOFS);
        if (*name == NULL)
                return -ENOMEM;

        read_extent_buffer(eb, *name, (unsigned long)(ref + 1), *namelen);

        if (index)
                *index = btrfs_inode_ref_index(eb, ref);

        return 0;
}

/*
 * Take an inode reference item from the log tree and iterate all names from the
 * inode reference item in the subvolume tree with the same key (if it exists).
 * For any name that is not in the inode reference item from the log tree, do a
 * proper unlink of that name (that is, remove its entry from the inode
 * reference item and both dir index keys).
 */
static int unlink_old_inode_refs(struct btrfs_trans_handle *trans,
                                 struct btrfs_root *root,
                                 struct btrfs_path *path,
                                 struct btrfs_inode *inode,
                                 struct extent_buffer *log_eb,
                                 int log_slot,
                                 struct btrfs_key *key)
{
        int ret;
        unsigned long ref_ptr;
        unsigned long ref_end;
        struct extent_buffer *eb;

again:
        btrfs_release_path(path);
        ret = btrfs_search_slot(NULL, root, key, path, 0, 0);
        if (ret > 0) {
                ret = 0;
                goto out;
        }
        if (ret < 0)
                goto out;

        eb = path->nodes[0];
        ref_ptr = btrfs_item_ptr_offset(eb, path->slots[0]);
        ref_end = ref_ptr + btrfs_item_size_nr(eb, path->slots[0]);
        while (ref_ptr < ref_end) {
                char *name = NULL;
                int namelen;
                u64 parent_id;

                if (key->type == BTRFS_INODE_EXTREF_KEY) {
                        ret = extref_get_fields(eb, ref_ptr, &namelen, &name,
                                                NULL, &parent_id);
                } else {
                        parent_id = key->offset;
                        ret = ref_get_fields(eb, ref_ptr, &namelen, &name,
                                             NULL);
                }
                if (ret)
                        goto out;

                if (key->type == BTRFS_INODE_EXTREF_KEY)
                        ret = btrfs_find_name_in_ext_backref(log_eb, log_slot,
                                                             parent_id, name,
                                                             namelen, NULL);
                else
                        ret = btrfs_find_name_in_backref(log_eb, log_slot, name,
                                                         namelen, NULL);

                if (!ret) {
                        struct inode *dir;

                        btrfs_release_path(path);
                        dir = read_one_inode(root, parent_id);
                        if (!dir) {
                                ret = -ENOENT;
                                kfree(name);
                                goto out;
                        }
                        ret = btrfs_unlink_inode(trans, root, BTRFS_I(dir),
                                                 inode, name, namelen);
                        kfree(name);
                        iput(dir);
                        if (ret)
                                goto out;
                        goto again;
                }

                kfree(name);
                ref_ptr += namelen;
                if (key->type == BTRFS_INODE_EXTREF_KEY)
                        ref_ptr += sizeof(struct btrfs_inode_extref);
                else
                        ref_ptr += sizeof(struct btrfs_inode_ref);
        }
        ret = 0;
 out:
        btrfs_release_path(path);
        return ret;
}

/*
 * replay one inode back reference item found in the log tree.
 * eb, slot and key refer to the buffer and key found in the log tree.
 * root is the destination we are replaying into, and path is for temp
 * use by this function.  (it should be released on return).
 */
static noinline int add_inode_ref(struct btrfs_trans_handle *trans,
                                  struct btrfs_root *root,
                                  struct btrfs_root *log,
                                  struct btrfs_path *path,
                                  struct extent_buffer *eb, int slot,
                                  struct btrfs_key *key)
{
        struct inode *dir = NULL;
        struct inode *inode = NULL;
        unsigned long ref_ptr;
        unsigned long ref_end;
        char *name = NULL;
        int namelen;
        int ret;
        int search_done = 0;
        int log_ref_ver = 0;
        u64 parent_objectid;
        u64 inode_objectid;
        u64 ref_index = 0;
        int ref_struct_size;

        ref_ptr = btrfs_item_ptr_offset(eb, slot);
        ref_end = ref_ptr + btrfs_item_size_nr(eb, slot);

        if (key->type == BTRFS_INODE_EXTREF_KEY) {
                struct btrfs_inode_extref *r;

                ref_struct_size = sizeof(struct btrfs_inode_extref);
                log_ref_ver = 1;
                r = (struct btrfs_inode_extref *)ref_ptr;
                parent_objectid = btrfs_inode_extref_parent(eb, r);
        } else {
                ref_struct_size = sizeof(struct btrfs_inode_ref);
                parent_objectid = key->offset;
        }
        inode_objectid = key->objectid;

        /*
         * it is possible that we didn't log all the parent directories
         * for a given inode.  If we don't find the dir, just don't
         * copy the back ref in.  The link count fixup code will take
         * care of the rest
         */
        dir = read_one_inode(root, parent_objectid);
        if (!dir) {
                ret = -ENOENT;
                goto out;
        }

        inode = read_one_inode(root, inode_objectid);
        if (!inode) {
                ret = -EIO;
                goto out;
        }

        while (ref_ptr < ref_end) {
                if (log_ref_ver) {
                        ret = extref_get_fields(eb, ref_ptr, &namelen, &name,
                                                &ref_index, &parent_objectid);
                        /*
                         * parent object can change from one array
                         * item to another.
                         */
                        if (!dir)
                                dir = read_one_inode(root, parent_objectid);
                        if (!dir) {
                                ret = -ENOENT;
                                goto out;
                        }
                } else {
                        ret = ref_get_fields(eb, ref_ptr, &namelen, &name,
                                             &ref_index);
                }
                if (ret)
                        goto out;

                /* if we already have a perfect match, we're done */
                if (!inode_in_dir(root, path, btrfs_ino(BTRFS_I(dir)),
                                        btrfs_ino(BTRFS_I(inode)), ref_index,
                                        name, namelen)) {
                        /*
                         * look for a conflicting back reference in the
                         * metadata. if we find one we have to unlink that name
                         * of the file before we add our new link.  Later on, we
                         * overwrite any existing back reference, and we don't
                         * want to create dangling pointers in the directory.
                         */

                        if (!search_done) {
                                ret = __add_inode_ref(trans, root, path, log,
                                                      BTRFS_I(dir),
                                                      BTRFS_I(inode),
                                                      inode_objectid,
                                                      parent_objectid,
                                                      ref_index, name, namelen,
                                                      &search_done);
                                if (ret) {
                                        if (ret == 1)
                                                ret = 0;
                                        goto out;
                                }
                        }

                        /* insert our name */
                        ret = btrfs_add_link(trans, BTRFS_I(dir),
                                        BTRFS_I(inode),
                                        name, namelen, 0, ref_index);
                        if (ret)
                                goto out;

                        btrfs_update_inode(trans, root, inode);
                }

                ref_ptr = (unsigned long)(ref_ptr + ref_struct_size) + namelen;
                kfree(name);
                name = NULL;
                if (log_ref_ver) {
                        iput(dir);
                        dir = NULL;
                }
        }

        /*
         * Before we overwrite the inode reference item in the subvolume tree
         * with the item from the log tree, we must unlink all names from the
         * parent directory that are in the subvolume's tree inode reference
         * item, otherwise we end up with an inconsistent subvolume tree where
         * dir index entries exist for a name but there is no inode reference
         * item with the same name.
         */
        ret = unlink_old_inode_refs(trans, root, path, BTRFS_I(inode), eb, slot,
                                    key);
        if (ret)
                goto out;

        /* finally write the back reference in the inode */
        ret = overwrite_item(trans, root, path, eb, slot, key);
out:
        btrfs_release_path(path);
        kfree(name);
        iput(dir);
        iput(inode);
        return ret;
}

static int insert_orphan_item(struct btrfs_trans_handle *trans,
                              struct btrfs_root *root, u64 ino)
{
        int ret;

        ret = btrfs_insert_orphan_item(trans, root, ino);
        if (ret == -EEXIST)
                ret = 0;

        return ret;
}

static int count_inode_extrefs(struct btrfs_root *root,
                struct btrfs_inode *inode, struct btrfs_path *path)
{
        int ret = 0;
        int name_len;
        unsigned int nlink = 0;
        u32 item_size;
        u32 cur_offset = 0;
        u64 inode_objectid = btrfs_ino(inode);
        u64 offset = 0;
        unsigned long ptr;
        struct btrfs_inode_extref *extref;
        struct extent_buffer *leaf;

        while (1) {
                ret = btrfs_find_one_extref(root, inode_objectid, offset, path,
                                            &extref, &offset);
                if (ret)
                        break;

                leaf = path->nodes[0];
                item_size = btrfs_item_size_nr(leaf, path->slots[0]);
                ptr = btrfs_item_ptr_offset(leaf, path->slots[0]);
                cur_offset = 0;

                while (cur_offset < item_size) {
                        extref = (struct btrfs_inode_extref *) (ptr + cur_offset);
                        name_len = btrfs_inode_extref_name_len(leaf, extref);

                        nlink++;

                        cur_offset += name_len + sizeof(*extref);
                }

                offset++;
                btrfs_release_path(path);
        }
        btrfs_release_path(path);

        if (ret < 0 && ret != -ENOENT)
                return ret;
        return nlink;
}

static int count_inode_refs(struct btrfs_root *root,
                        struct btrfs_inode *inode, struct btrfs_path *path)
{
        int ret;
        struct btrfs_key key;
        unsigned int nlink = 0;
        unsigned long ptr;
        unsigned long ptr_end;
        int name_len;
        u64 ino = btrfs_ino(inode);

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

        while (1) {
                ret = btrfs_search_slot(NULL, root, &key, path, 0, 0);
                if (ret < 0)
                        break;
                if (ret > 0) {
                        if (path->slots[0] == 0)
                                break;
                        path->slots[0]--;
                }
process_slot:
                btrfs_item_key_to_cpu(path->nodes[0], &key,
                                      path->slots[0]);
                if (key.objectid != ino ||
                    key.type != BTRFS_INODE_REF_KEY)
                        break;
                ptr = btrfs_item_ptr_offset(path->nodes[0], path->slots[0]);
                ptr_end = ptr + btrfs_item_size_nr(path->nodes[0],
                                                   path->slots[0]);
                while (ptr < ptr_end) {
                        struct btrfs_inode_ref *ref;

                        ref = (struct btrfs_inode_ref *)ptr;
                        name_len = btrfs_inode_ref_name_len(path->nodes[0],
                                                            ref);
                        ptr = (unsigned long)(ref + 1) + name_len;
                        nlink++;
                }

                if (key.offset == 0)
                        break;
                if (path->slots[0] > 0) {
                        path->slots[0]--;
                        goto process_slot;
                }
                key.offset--;
                btrfs_release_path(path);
        }
        btrfs_release_path(path);

        return nlink;
}

/*
 * There are a few corners where the link count of the file can't
 * be properly maintained during replay.  So, instead of adding
 * lots of complexity to the log code, we just scan the backrefs
 * for any file that has been through replay.
 *
 * The scan will update the link count on the inode to reflect the
 * number of back refs found.  If it goes down to zero, the iput
 * will free the inode.
 */
static noinline int fixup_inode_link_count(struct btrfs_trans_handle *trans,
                                           struct btrfs_root *root,
                                           struct inode *inode)
{
        struct btrfs_path *path;
        int ret;
        u64 nlink = 0;
        u64 ino = btrfs_ino(BTRFS_I(inode));

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

        ret = count_inode_refs(root, BTRFS_I(inode), path);
        if (ret < 0)
                goto out;

        nlink = ret;

        ret = count_inode_extrefs(root, BTRFS_I(inode), path);
        if (ret < 0)
                goto out;

        nlink += ret;

        ret = 0;

        if (nlink != inode->i_nlink) {
                set_nlink(inode, nlink);
                btrfs_update_inode(trans, root, inode);
        }
        BTRFS_I(inode)->index_cnt = (u64)-1;

        if (inode->i_nlink == 0) {
                if (S_ISDIR(inode->i_mode)) {
                        ret = replay_dir_deletes(trans, root, NULL, path,
                                                 ino, 1);
                        if (ret)
                                goto out;
                }
                ret = insert_orphan_item(trans, root, ino);
        }

out:
        btrfs_free_path(path);
        return ret;
}

static noinline int fixup_inode_link_counts(struct btrfs_trans_handle *trans,
                                            struct btrfs_root *root,
                                            struct btrfs_path *path)
{
        int ret;
        struct btrfs_key key;
        struct inode *inode;

        key.objectid = BTRFS_TREE_LOG_FIXUP_OBJECTID;
        key.type = BTRFS_ORPHAN_ITEM_KEY;
        key.offset = (u64)-1;
        while (1) {
                ret = btrfs_search_slot(trans, root, &key, path, -1, 1);
                if (ret < 0)
                        break;

                if (ret == 1) {
                        if (path->slots[0] == 0)
                                break;
                        path->slots[0]--;
                }

                btrfs_item_key_to_cpu(path->nodes[0], &key, path->slots[0]);
                if (key.objectid != BTRFS_TREE_LOG_FIXUP_OBJECTID ||
                    key.type != BTRFS_ORPHAN_ITEM_KEY)
                        break;

                ret = btrfs_del_item(trans, root, path);
                if (ret)
                        goto out;

                btrfs_release_path(path);
                inode = read_one_inode(root, key.offset);
                if (!inode)
                        return -EIO;

                ret = fixup_inode_link_count(trans, root, inode);
                iput(inode);
                if (ret)
                        goto out;

                /*
                 * fixup on a directory may create new entries,
                 * make sure we always look for the highset possible
                 * offset
                 */
                key.offset = (u64)-1;
        }
        ret = 0;
out:
        btrfs_release_path(path);
        return ret;
}


/*
 * record a given inode in the fixup dir so we can check its link
 * count when replay is done.  The link count is incremented here
 * so the inode won't go away until we check it
 */
static noinline int link_to_fixup_dir(struct btrfs_trans_handle *trans,
                                      struct btrfs_root *root,
                                      struct btrfs_path *path,
                                      u64 objectid)
{
        struct btrfs_key key;
        int ret = 0;
        struct inode *inode;

        inode = read_one_inode(root, objectid);
        if (!inode)
                return -EIO;

        key.objectid = BTRFS_TREE_LOG_FIXUP_OBJECTID;
        key.type = BTRFS_ORPHAN_ITEM_KEY;
        key.offset = objectid;

        ret = btrfs_insert_empty_item(trans, root, path, &key, 0);

        btrfs_release_path(path);
        if (ret == 0) {
                if (!inode->i_nlink)
                        set_nlink(inode, 1);
                else
                        inc_nlink(inode);
                ret = btrfs_update_inode(trans, root, inode);
        } else if (ret == -EEXIST) {
                ret = 0;
        } else {
                BUG(); /* Logic Error */
        }
        iput(inode);

        return ret;
}

/*
 * when replaying the log for a directory, we only insert names
 * for inodes that actually exist.  This means an fsync on a directory
 * does not implicitly fsync all the new files in it
 */
static noinline int insert_one_name(struct btrfs_trans_handle *trans,
                                    struct btrfs_root *root,
                                    u64 dirid, u64 index,
                                    char *name, int name_len,
                                    struct btrfs_key *location)
{
        struct inode *inode;
        struct inode *dir;
        int ret;

        inode = read_one_inode(root, location->objectid);
        if (!inode)
                return -ENOENT;

        dir = read_one_inode(root, dirid);
        if (!dir) {
                iput(inode);
                return -EIO;
        }

        ret = btrfs_add_link(trans, BTRFS_I(dir), BTRFS_I(inode), name,
                        name_len, 1, index);

        /* FIXME, put inode into FIXUP list */

        iput(inode);
        iput(dir);
        return ret;
}

/*
 * Return true if an inode reference exists in the log for the given name,
 * inode and parent inode.
 */
static bool name_in_log_ref(struct btrfs_root *log_root,
                            const char *name, const int name_len,
                            const u64 dirid, const u64 ino)
{
        struct btrfs_key search_key;

        search_key.objectid = ino;
        search_key.type = BTRFS_INODE_REF_KEY;
        search_key.offset = dirid;
        if (backref_in_log(log_root, &search_key, dirid, name, name_len))
                return true;

        search_key.type = BTRFS_INODE_EXTREF_KEY;
        search_key.offset = btrfs_extref_hash(dirid, name, name_len);
        if (backref_in_log(log_root, &search_key, dirid, name, name_len))
                return true;

        return false;
}

/*
 * take a single entry in a log directory item and replay it into
 * the subvolume.
 *
 * if a conflicting item exists in the subdirectory already,
 * the inode it points to is unlinked and put into the link count
 * fix up tree.
 *
 * If a name from the log points to a file or directory that does
 * not exist in the FS, it is skipped.  fsyncs on directories
 * do not force down inodes inside that directory, just changes to the
 * names or unlinks in a directory.
 *
 * Returns < 0 on error, 0 if the name wasn't replayed (dentry points to a
 * non-existing inode) and 1 if the name was replayed.
 */
static noinline int replay_one_name(struct btrfs_trans_handle *trans,
                                    struct btrfs_root *root,
                                    struct btrfs_path *path,
                                    struct extent_buffer *eb,
                                    struct btrfs_dir_item *di,
                                    struct btrfs_key *key)
{
        char *name;
        int name_len;
        struct btrfs_dir_item *dst_di;
        struct btrfs_key found_key;
        struct btrfs_key log_key;
        struct inode *dir;
        u8 log_type;
        int exists;
        int ret = 0;
        bool update_size = (key->type == BTRFS_DIR_INDEX_KEY);
        bool name_added = false;

        dir = read_one_inode(root, key->objectid);
        if (!dir)
                return -EIO;

        name_len = btrfs_dir_name_len(eb, di);
        name = kmalloc(name_len, GFP_NOFS);
        if (!name) {
                ret = -ENOMEM;
                goto out;
        }

        log_type = btrfs_dir_type(eb, di);
        read_extent_buffer(eb, name, (unsigned long)(di + 1),
                   name_len);

        btrfs_dir_item_key_to_cpu(eb, di, &log_key);
        exists = btrfs_lookup_inode(trans, root, path, &log_key, 0);
        if (exists == 0)
                exists = 1;
        else
                exists = 0;
        btrfs_release_path(path);

        if (key->type == BTRFS_DIR_ITEM_KEY) {
                dst_di = btrfs_lookup_dir_item(trans, root, path, key->objectid,
                                       name, name_len, 1);
        } else if (key->type == BTRFS_DIR_INDEX_KEY) {
                dst_di = btrfs_lookup_dir_index_item(trans, root, path,
                                                     key->objectid,
                                                     key->offset, name,
                                                     name_len, 1);
        } else {
                /* Corruption */
                ret = -EINVAL;
                goto out;
        }
        if (IS_ERR_OR_NULL(dst_di)) {
                /* we need a sequence number to insert, so we only
                 * do inserts for the BTRFS_DIR_INDEX_KEY types
                 */
                if (key->type != BTRFS_DIR_INDEX_KEY)
                        goto out;
                goto insert;
        }

        btrfs_dir_item_key_to_cpu(path->nodes[0], dst_di, &found_key);
        /* the existing item matches the logged item */
        if (found_key.objectid == log_key.objectid &&
            found_key.type == log_key.type &&
            found_key.offset == log_key.offset &&
            btrfs_dir_type(path->nodes[0], dst_di) == log_type) {
                update_size = false;
                goto out;
        }

        /*
         * don't drop the conflicting directory entry if the inode
         * for the new entry doesn't exist
         */
        if (!exists)
                goto out;

        ret = drop_one_dir_item(trans, root, path, BTRFS_I(dir), dst_di);
        if (ret)
                goto out;

        if (key->type == BTRFS_DIR_INDEX_KEY)
                goto insert;
out:
        btrfs_release_path(path);
        if (!ret && update_size) {
                btrfs_i_size_write(BTRFS_I(dir), dir->i_size + name_len * 2);
                ret = btrfs_update_inode(trans, root, dir);
        }
        kfree(name);
        iput(dir);
        if (!ret && name_added)
                ret = 1;
        return ret;

insert:
        if (name_in_log_ref(root->log_root, name, name_len,
                            key->objectid, log_key.objectid)) {
                /* The dentry will be added later. */
                ret = 0;
                update_size = false;
                goto out;
        }
        btrfs_release_path(path);
        ret = insert_one_name(trans, root, key->objectid, key->offset,
                              name, name_len, &log_key);
        if (ret && ret != -ENOENT && ret != -EEXIST)
                goto out;
        if (!ret)
                name_added = true;
        update_size = false;
        ret = 0;
        goto out;
}

/*
 * find all the names in a directory item and reconcile them into
 * the subvolume.  Only BTRFS_DIR_ITEM_KEY types will have more than
 * one name in a directory item, but the same code gets used for
 * both directory index types
 */
static noinline int replay_one_dir_item(struct btrfs_trans_handle *trans,
                                        struct btrfs_root *root,
                                        struct btrfs_path *path,
                                        struct extent_buffer *eb, int slot,
                                        struct btrfs_key *key)
{
        int ret = 0;
        u32 item_size = btrfs_item_size_nr(eb, slot);
        struct btrfs_dir_item *di;
        int name_len;
        unsigned long ptr;
        unsigned long ptr_end;
        struct btrfs_path *fixup_path = NULL;

        ptr = btrfs_item_ptr_offset(eb, slot);
        ptr_end = ptr + item_size;
        while (ptr < ptr_end) {
                di = (struct btrfs_dir_item *)ptr;
                name_len = btrfs_dir_name_len(eb, di);
                ret = replay_one_name(trans, root, path, eb, di, key);
                if (ret < 0)
                        break;
                ptr = (unsigned long)(di + 1);
                ptr += name_len;

                /*
                 * If this entry refers to a non-directory (directories can not
                 * have a link count > 1) and it was added in the transaction
                 * that was not committed, make sure we fixup the link count of
                 * the inode it the entry points to. Otherwise something like
                 * the following would result in a directory pointing to an
                 * inode with a wrong link that does not account for this dir
                 * entry:
                 *
                 * mkdir testdir
                 * touch testdir/foo
                 * touch testdir/bar
                 * sync
                 *
                 * ln testdir/bar testdir/bar_link
                 * ln testdir/foo testdir/foo_link
                 * xfs_io -c "fsync" testdir/bar
                 *
                 * <power failure>
                 *
                 * mount fs, log replay happens
                 *
                 * File foo would remain with a link count of 1 when it has two
                 * entries pointing to it in the directory testdir. This would
                 * make it impossible to ever delete the parent directory has
                 * it would result in stale dentries that can never be deleted.
                 */
                if (ret == 1 && btrfs_dir_type(eb, di) != BTRFS_FT_DIR) {
                        struct btrfs_key di_key;

                        if (!fixup_path) {
                                fixup_path = btrfs_alloc_path();
                                if (!fixup_path) {
                                        ret = -ENOMEM;
                                        break;
                                }
                        }

                        btrfs_dir_item_key_to_cpu(eb, di, &di_key);
                        ret = link_to_fixup_dir(trans, root, fixup_path,
                                                di_key.objectid);
                        if (ret)
                                break;
                }
                ret = 0;
        }
        btrfs_free_path(fixup_path);
        return ret;
}

/*
 * directory replay has two parts.  There are the standard directory
 * items in the log copied from the subvolume, and range items
 * created in the log while the subvolume was logged.
 *
 * The range items tell us which parts of the key space the log
 * is authoritative for.  During replay, if a key in the subvolume
 * directory is in a logged range item, but not actually in the log
 * that means it was deleted from the directory before the fsync
 * and should be removed.
 */
static noinline int find_dir_range(struct btrfs_root *root,
                                   struct btrfs_path *path,
                                   u64 dirid, int key_type,

                                   u64 *start_ret, u64 *end_ret)
{
        struct btrfs_key key;
        u64 found_end;
        struct btrfs_dir_log_item *item;
        int ret;
        int nritems;

        if (*start_ret == (u64)-1)
                return 1;

        key.objectid = dirid;
        key.type = key_type;
        key.offset = *start_ret;

        ret = btrfs_search_slot(NULL, root, &key, path, 0, 0);
        if (ret < 0)
                goto out;
        if (ret > 0) {
                if (path->slots[0] == 0)
                        goto out;
                path->slots[0]--;
        }
        if (ret != 0)
                btrfs_item_key_to_cpu(path->nodes[0], &key, path->slots[0]);

        if (key.type != key_type || key.objectid != dirid) {
                ret = 1;
                goto next;
        }
        item = btrfs_item_ptr(path->nodes[0], path->slots[0],
                              struct btrfs_dir_log_item);
        found_end = btrfs_dir_log_end(path->nodes[0], item);

        if (*start_ret >= key.offset && *start_ret <= found_end) {
                ret = 0;
                *start_ret = key.offset;
                *end_ret = found_end;
                goto out;
        }
        ret = 1;
next:
        /* check the next slot in the tree to see if it is a valid item */
        nritems = btrfs_header_nritems(path->nodes[0]);
        path->slots[0]++;
        if (path->slots[0] >= nritems) {
                ret = btrfs_next_leaf(root, path);
                if (ret)
                        goto out;
        }

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

        if (key.type != key_type || key.objectid != dirid) {
                ret = 1;
                goto out;
        }
        item = btrfs_item_ptr(path->nodes[0], path->slots[0],
                              struct btrfs_dir_log_item);
        found_end = btrfs_dir_log_end(path->nodes[0], item);
        *start_ret = key.offset;
        *end_ret = found_end;
        ret = 0;
out:
        btrfs_release_path(path);
        return ret;
}

/*
 * this looks for a given directory item in the log.  If the directory
 * item is not in the log, the item is removed and the inode it points
 * to is unlinked
 */
static noinline int check_item_in_log(struct btrfs_trans_handle *trans,
                                      struct btrfs_root *root,
                                      struct btrfs_root *log,
                                      struct btrfs_path *path,
                                      struct btrfs_path *log_path,
                                      struct inode *dir,
                                      struct btrfs_key *dir_key)
{
        int ret;
        struct extent_buffer *eb;
        int slot;
        u32 item_size;
        struct btrfs_dir_item *di;
        struct btrfs_dir_item *log_di;
        int name_len;
        unsigned long ptr;
        unsigned long ptr_end;
        char *name;
        struct inode *inode;
        struct btrfs_key location;

again:
        eb = path->nodes[0];
        slot = path->slots[0];
        item_size = btrfs_item_size_nr(eb, slot);
        ptr = btrfs_item_ptr_offset(eb, slot);
        ptr_end = ptr + item_size;
        while (ptr < ptr_end) {
                di = (struct btrfs_dir_item *)ptr;
                name_len = btrfs_dir_name_len(eb, di);
                name = kmalloc(name_len, GFP_NOFS);
                if (!name) {
                        ret = -ENOMEM;
                        goto out;
                }
                read_extent_buffer(eb, name, (unsigned long)(di + 1),
                                  name_len);
                log_di = NULL;
                if (log && dir_key->type == BTRFS_DIR_ITEM_KEY) {
                        log_di = btrfs_lookup_dir_item(trans, log, log_path,
                                                       dir_key->objectid,
                                                       name, name_len, 0);
                } else if (log && dir_key->type == BTRFS_DIR_INDEX_KEY) {
                        log_di = btrfs_lookup_dir_index_item(trans, log,
                                                     log_path,
                                                     dir_key->objectid,
                                                     dir_key->offset,
                                                     name, name_len, 0);
                }
                if (!log_di || (IS_ERR(log_di) && PTR_ERR(log_di) == -ENOENT)) {
                        btrfs_dir_item_key_to_cpu(eb, di, &location);
                        btrfs_release_path(path);
                        btrfs_release_path(log_path);
                        inode = read_one_inode(root, location.objectid);
                        if (!inode) {
                                kfree(name);
                                return -EIO;
                        }

                        ret = link_to_fixup_dir(trans, root,
                                                path, location.objectid);
                        if (ret) {
                                kfree(name);
                                iput(inode);
                                goto out;
                        }

                        inc_nlink(inode);
                        ret = btrfs_unlink_inode(trans, root, BTRFS_I(dir),
                                        BTRFS_I(inode), name, name_len);
                        if (!ret)
                                ret = btrfs_run_delayed_items(trans);
                        kfree(name);
                        iput(inode);
                        if (ret)
                                goto out;

                        /* there might still be more names under this key
                         * check and repeat if required
                         */
                        ret = btrfs_search_slot(NULL, root, dir_key, path,
                                                0, 0);
                        if (ret == 0)
                                goto again;
                        ret = 0;
                        goto out;
                } else if (IS_ERR(log_di)) {
                        kfree(name);
                        return PTR_ERR(log_di);
                }
                btrfs_release_path(log_path);
                kfree(name);

                ptr = (unsigned long)(di + 1);
                ptr += name_len;
        }
        ret = 0;
out:
        btrfs_release_path(path);
        btrfs_release_path(log_path);
        return ret;
}

static int replay_xattr_deletes(struct btrfs_trans_handle *trans,
                              struct btrfs_root *root,
                              struct btrfs_root *log,
                              struct btrfs_path *path,
                              const u64 ino)
{
        struct btrfs_key search_key;
        struct btrfs_path *log_path;
        int i;
        int nritems;
        int ret;

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

        search_key.objectid = ino;
        search_key.type = BTRFS_XATTR_ITEM_KEY;
        search_key.offset = 0;
again:
        ret = btrfs_search_slot(NULL, root, &search_key, path, 0, 0);
        if (ret < 0)
                goto out;
process_leaf:
        nritems = btrfs_header_nritems(path->nodes[0]);
        for (i = path->slots[0]; i < nritems; i++) {
                struct btrfs_key key;
                struct btrfs_dir_item *di;
                struct btrfs_dir_item *log_di;
                u32 total_size;
                u32 cur;

                btrfs_item_key_to_cpu(path->nodes[0], &key, i);
                if (key.objectid != ino || key.type != BTRFS_XATTR_ITEM_KEY) {
                        ret = 0;
                        goto out;
                }

                di = btrfs_item_ptr(path->nodes[0], i, struct btrfs_dir_item);
                total_size = btrfs_item_size_nr(path->nodes[0], i);
                cur = 0;
                while (cur < total_size) {
                        u16 name_len = btrfs_dir_name_len(path->nodes[0], di);
                        u16 data_len = btrfs_dir_data_len(path->nodes[0], di);
                        u32 this_len = sizeof(*di) + name_len + data_len;
                        char *name;

                        name = kmalloc(name_len, GFP_NOFS);
                        if (!name) {
                                ret = -ENOMEM;
                                goto out;
                        }
                        read_extent_buffer(path->nodes[0], name,
                                           (unsigned long)(di + 1), name_len);

                        log_di = btrfs_lookup_xattr(NULL, log, log_path, ino,
                                                    name, name_len, 0);
                        btrfs_release_path(log_path);
                        if (!log_di) {
                                /* Doesn't exist in log tree, so delete it. */
                                btrfs_release_path(path);
                                di = btrfs_lookup_xattr(trans, root, path, ino,
                                                        name, name_len, -1);
                                kfree(name);
                                if (IS_ERR(di)) {
                                        ret = PTR_ERR(di);
                                        goto out;
                                }
                                ASSERT(di);
                                ret = btrfs_delete_one_dir_name(trans, root,
                                                                path, di);
                                if (ret)
                                        goto out;
                                btrfs_release_path(path);
                                search_key = key;
                                goto again;
                        }
                        kfree(name);
                        if (IS_ERR(log_di)) {
                                ret = PTR_ERR(log_di);
                                goto out;
                        }
                        cur += this_len;
                        di = (struct btrfs_dir_item *)((char *)di + this_len);
                }
        }
        ret = btrfs_next_leaf(root, path);
        if (ret > 0)
                ret = 0;
        else if (ret == 0)
                goto process_leaf;
out:
        btrfs_free_path(log_path);
        btrfs_release_path(path);
        return ret;
}


/*
 * deletion replay happens before we copy any new directory items
 * out of the log or out of backreferences from inodes.  It
 * scans the log to find ranges of keys that log is authoritative for,
 * and then scans the directory to find items in those ranges that are
 * not present in the log.
 *
 * Anything we don't find in the log is unlinked and removed from the
 * directory.
 */
static noinline int replay_dir_deletes(struct btrfs_trans_handle *trans,
                                       struct btrfs_root *root,
                                       struct btrfs_root *log,
                                       struct btrfs_path *path,
                                       u64 dirid, int del_all)
{
        u64 range_start;
        u64 range_end;
        int key_type = BTRFS_DIR_LOG_ITEM_KEY;
        int ret = 0;
        struct btrfs_key dir_key;
        struct btrfs_key found_key;
        struct btrfs_path *log_path;
        struct inode *dir;

        dir_key.objectid = dirid;
        dir_key.type = BTRFS_DIR_ITEM_KEY;
        log_path = btrfs_alloc_path();
        if (!log_path)
                return -ENOMEM;

        dir = read_one_inode(root, dirid);
        /* it isn't an error if the inode isn't there, that can happen
         * because we replay the deletes before we copy in the inode item
         * from the log
         */
        if (!dir) {
                btrfs_free_path(log_path);
                return 0;
        }
again:
        range_start = 0;
        range_end = 0;
        while (1) {
                if (del_all)
                        range_end = (u64)-1;
                else {
                        ret = find_dir_range(log, path, dirid, key_type,
                                             &range_start, &range_end);
                        if (ret != 0)
                                break;
                }

                dir_key.offset = range_start;
                while (1) {
                        int nritems;
                        ret = btrfs_search_slot(NULL, root, &dir_key, path,
                                                0, 0);
                        if (ret < 0)
                                goto out;

                        nritems = btrfs_header_nritems(path->nodes[0]);
                        if (path->slots[0] >= nritems) {
                                ret = btrfs_next_leaf(root, path);
                                if (ret == 1)
                                        break;
                                else if (ret < 0)
                                        goto out;
                        }
                        btrfs_item_key_to_cpu(path->nodes[0], &found_key,
                                              path->slots[0]);
                        if (found_key.objectid != dirid ||
                            found_key.type != dir_key.type)
                                goto next_type;

                        if (found_key.offset > range_end)
                                break;

                        ret = check_item_in_log(trans, root, log, path,
                                                log_path, dir,
                                                &found_key);
                        if (ret)
                                goto out;
                        if (found_key.offset == (u64)-1)
                                break;
                        dir_key.offset = found_key.offset + 1;
                }
                btrfs_release_path(path);
                if (range_end == (u64)-1)
                        break;
                range_start = range_end + 1;
        }

next_type:
        ret = 0;
        if (key_type == BTRFS_DIR_LOG_ITEM_KEY) {
                key_type = BTRFS_DIR_LOG_INDEX_KEY;
                dir_key.type = BTRFS_DIR_INDEX_KEY;
                btrfs_release_path(path);
                goto again;
        }
out:
        btrfs_release_path(path);
        btrfs_free_path(log_path);
        iput(dir);
        return ret;
}

/*
 * the process_func used to replay items from the log tree.  This
 * gets called in two different stages.  The first stage just looks
 * for inodes and makes sure they are all copied into the subvolume.
 *
 * The second stage copies all the other item types from the log into
 * the subvolume.  The two stage approach is slower, but gets rid of
 * lots of complexity around inodes referencing other inodes that exist
 * only in the log (references come from either directory items or inode
 * back refs).
 */
static int replay_one_buffer(struct btrfs_root *log, struct extent_buffer *eb,
                             struct walk_control *wc, u64 gen, int level)
{
        int nritems;
        struct btrfs_path *path;
        struct btrfs_root *root = wc->replay_dest;
        struct btrfs_key key;
        int i;
        int ret;

        ret = btrfs_read_buffer(eb, gen, level, NULL);
        if (ret)
                return ret;

        level = btrfs_header_level(eb);

        if (level != 0)
                return 0;

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

        nritems = btrfs_header_nritems(eb);
        for (i = 0; i < nritems; i++) {
                btrfs_item_key_to_cpu(eb, &key, i);

                /* inode keys are done during the first stage */
                if (key.type == BTRFS_INODE_ITEM_KEY &&
                    wc->stage == LOG_WALK_REPLAY_INODES) {
                        struct btrfs_inode_item *inode_item;
                        u32 mode;

                        inode_item = btrfs_item_ptr(eb, i,
                                            struct btrfs_inode_item);
                        ret = replay_xattr_deletes(wc->trans, root, log,
                                                   path, key.objectid);
                        if (ret)
                                break;
                        mode = btrfs_inode_mode(eb, inode_item);
                        if (S_ISDIR(mode)) {
                                ret = replay_dir_deletes(wc->trans,
                                         root, log, path, key.objectid, 0);
                                if (ret)
                                        break;
                        }
                        ret = overwrite_item(wc->trans, root, path,
                                             eb, i, &key);
                        if (ret)
                                break;

                        /*
                         * Before replaying extents, truncate the inode to its
                         * size. We need to do it now and not after log replay
                         * because before an fsync we can have prealloc extents
                         * added beyond the inode's i_size. If we did it after,
                         * through orphan cleanup for example, we would drop
                         * those prealloc extents just after replaying them.
                         */
                        if (S_ISREG(mode)) {
                                struct inode *inode;
                                u64 from;

                                inode = read_one_inode(root, key.objectid);
                                if (!inode) {
                                        ret = -EIO;
                                        break;
                                }
                                from = ALIGN(i_size_read(inode),
                                             root->fs_info->sectorsize);
                                ret = btrfs_drop_extents(wc->trans, root, inode,
                                                         from, (u64)-1, 1);
                                /*
                                 * If the nlink count is zero here, the iput
                                 * will free the inode.  We bump it to make
                                 * sure it doesn't get freed until the link
                                 * count fixup is done.
                                 */
                                if (!ret) {
                                        if (inode->i_nlink == 0)
                                                inc_nlink(inode);
                                        /* Update link count and nbytes. */
                                        ret = btrfs_update_inode(wc->trans,
                                                                 root, inode);
                                }
                                iput(inode);
                                if (ret)
                                        break;
                        }

                        ret = link_to_fixup_dir(wc->trans, root,
                                                path, key.objectid);
                        if (ret)
                                break;
                }

                if (key.type == BTRFS_DIR_INDEX_KEY &&
                    wc->stage == LOG_WALK_REPLAY_DIR_INDEX) {
                        ret = replay_one_dir_item(wc->trans, root, path,
                                                  eb, i, &key);
                        if (ret)
                                break;
                }

                if (wc->stage < LOG_WALK_REPLAY_ALL)
                        continue;

                /* these keys are simply copied */
                if (key.type == BTRFS_XATTR_ITEM_KEY) {
                        ret = overwrite_item(wc->trans, root, path,
                                             eb, i, &key);
                        if (ret)
                                break;
                } else if (key.type == BTRFS_INODE_REF_KEY ||
                           key.type == BTRFS_INODE_EXTREF_KEY) {
                        ret = add_inode_ref(wc->trans, root, log, path,
                                            eb, i, &key);
                        if (ret && ret != -ENOENT)
                                break;
                        ret = 0;
                } else if (key.type == BTRFS_EXTENT_DATA_KEY) {
                        ret = replay_one_extent(wc->trans, root, path,
                                                eb, i, &key);
                        if (ret)
                                break;
                } else if (key.type == BTRFS_DIR_ITEM_KEY) {
                        ret = replay_one_dir_item(wc->trans, root, path,
                                                  eb, i, &key);
                        if (ret)
                                break;
                }
        }
        btrfs_free_path(path);
        return ret;
}

static noinline int walk_down_log_tree(struct btrfs_trans_handle *trans,
                                   struct btrfs_root *root,
                                   struct btrfs_path *path, int *level,
                                   struct walk_control *wc)
{
        struct btrfs_fs_info *fs_info = root->fs_info;
        u64 root_owner;
        u64 bytenr;
        u64 ptr_gen;
        struct extent_buffer *next;
        struct extent_buffer *cur;
        struct extent_buffer *parent;
        u32 blocksize;
        int ret = 0;

        WARN_ON(*level < 0);
        WARN_ON(*level >= BTRFS_MAX_LEVEL);

        while (*level > 0) {
                struct btrfs_key first_key;

                WARN_ON(*level < 0);
                WARN_ON(*level >= BTRFS_MAX_LEVEL);
                cur = path->nodes[*level];

                WARN_ON(btrfs_header_level(cur) != *level);

                if (path->slots[*level] >=
                    btrfs_header_nritems(cur))
                        break;

                bytenr = btrfs_node_blockptr(cur, path->slots[*level]);
                ptr_gen = btrfs_node_ptr_generation(cur, path->slots[*level]);
                btrfs_node_key_to_cpu(cur, &first_key, path->slots[*level]);
                blocksize = fs_info->nodesize;

                parent = path->nodes[*level];
                root_owner = btrfs_header_owner(parent);

                next = btrfs_find_create_tree_block(fs_info, bytenr);
                if (IS_ERR(next))
                        return PTR_ERR(next);

                if (*level == 1) {
                        ret = wc->process_func(root, next, wc, ptr_gen,
                                               *level - 1);
                        if (ret) {
                                free_extent_buffer(next);
                                return ret;
                        }

                        path->slots[*level]++;
                        if (wc->free) {
                                ret = btrfs_read_buffer(next, ptr_gen,
                                                        *level - 1, &first_key);
                                if (ret) {
                                        free_extent_buffer(next);
                                        return ret;
                                }

                                if (trans) {
                                        btrfs_tree_lock(next);
                                        btrfs_set_lock_blocking(next);
                                        clean_tree_block(fs_info, next);
                                        btrfs_wait_tree_block_writeback(next);
                                        btrfs_tree_unlock(next);
                                } else {
                                        if (test_and_clear_bit(EXTENT_BUFFER_DIRTY, &next->bflags))
                                                clear_extent_buffer_dirty(next);
                                }

                                WARN_ON(root_owner !=
                                        BTRFS_TREE_LOG_OBJECTID);
                                ret = btrfs_free_and_pin_reserved_extent(
                                                        fs_info, bytenr,
                                                        blocksize);
                                if (ret) {
                                        free_extent_buffer(next);
                                        return ret;
                                }
                        }
                        free_extent_buffer(next);
                        continue;
                }
                ret = btrfs_read_buffer(next, ptr_gen, *level - 1, &first_key);
                if (ret) {
                        free_extent_buffer(next);
                        return ret;
                }

                WARN_ON(*level <= 0);
                if (path->nodes[*level-1])
                        free_extent_buffer(path->nodes[*level-1]);
                path->nodes[*level-1] = next;
                *level = btrfs_header_level(next);
                path->slots[*level] = 0;
                cond_resched();
        }
        WARN_ON(*level < 0);
        WARN_ON(*level >= BTRFS_MAX_LEVEL);

        path->slots[*level] = btrfs_header_nritems(path->nodes[*level]);

        cond_resched();
        return 0;
}

static noinline int walk_up_log_tree(struct btrfs_trans_handle *trans,
                                 struct btrfs_root *root,
                                 struct btrfs_path *path, int *level,
                                 struct walk_control *wc)
{
        struct btrfs_fs_info *fs_info = root->fs_info;
        u64 root_owner;
        int i;
        int slot;
        int ret;

        for (i = *level; i < BTRFS_MAX_LEVEL - 1 && path->nodes[i]; i++) {
                slot = path->slots[i];
                if (slot + 1 < btrfs_header_nritems(path->nodes[i])) {
                        path->slots[i]++;
                        *level = i;
                        WARN_ON(*level == 0);
                        return 0;
                } else {
                        struct extent_buffer *parent;
                        if (path->nodes[*level] == root->node)
                                parent = path->nodes[*level];
                        else
                                parent = path->nodes[*level + 1];

                        root_owner = btrfs_header_owner(parent);
                        ret = wc->process_func(root, path->nodes[*level], wc,
                                 btrfs_header_generation(path->nodes[*level]),
                                 *level);
                        if (ret)
                                return ret;

                        if (wc->free) {
                                struct extent_buffer *next;

                                next = path->nodes[*level];

                                if (trans) {
                                        btrfs_tree_lock(next);
                                        btrfs_set_lock_blocking(next);
                                        clean_tree_block(fs_info, next);
                                        btrfs_wait_tree_block_writeback(next);
                                        btrfs_tree_unlock(next);
                                } else {
                                        if (test_and_clear_bit(EXTENT_BUFFER_DIRTY, &next->bflags))
                                                clear_extent_buffer_dirty(next);
                                }

                                WARN_ON(root_owner != BTRFS_TREE_LOG_OBJECTID);
                                ret = btrfs_free_and_pin_reserved_extent(
                                                fs_info,
                                                path->nodes[*level]->start,
                                                path->nodes[*level]->len);
                                if (ret)
                                        return ret;
                        }
                        free_extent_buffer(path->nodes[*level]);
                        path->nodes[*level] = NULL;
                        *level = i + 1;
                }
        }
        return 1;
}

/*
 * drop the reference count on the tree rooted at 'snap'.  This traverses
 * the tree freeing any blocks that have a ref count of zero after being
 * decremented.
 */
static int walk_log_tree(struct btrfs_trans_handle *trans,
                         struct btrfs_root *log, struct walk_control *wc)
{
        struct btrfs_fs_info *fs_info = log->fs_info;
        int ret = 0;
        int wret;
        int level;
        struct btrfs_path *path;
        int orig_level;

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

        level = btrfs_header_level(log->node);
        orig_level = level;
        path->nodes[level] = log->node;
        extent_buffer_get(log->node);
        path->slots[level] = 0;

        while (1) {
                wret = walk_down_log_tree(trans, log, path, &level, wc);
                if (wret > 0)
                        break;
                if (wret < 0) {
                        ret = wret;
                        goto out;
                }

                wret = walk_up_log_tree(trans, log, path, &level, wc);
                if (wret > 0)
                        break;
                if (wret < 0) {
                        ret = wret;
                        goto out;
                }
        }

        /* was the root node processed? if not, catch it here */
        if (path->nodes[orig_level]) {
                ret = wc->process_func(log, path->nodes[orig_level], wc,
                         btrfs_header_generation(path->nodes[orig_level]),
                         orig_level);
                if (ret)
                        goto out;
                if (wc->free) {
                        struct extent_buffer *next;

                        next = path->nodes[orig_level];

                        if (trans) {
                                btrfs_tree_lock(next);
                                btrfs_set_lock_blocking(next);
                                clean_tree_block(fs_info, next);
                                btrfs_wait_tree_block_writeback(next);
                                btrfs_tree_unlock(next);
                        } else {
                                if (test_and_clear_bit(EXTENT_BUFFER_DIRTY, &next->bflags))
                                        clear_extent_buffer_dirty(next);
                        }

                        WARN_ON(log->root_key.objectid !=
                                BTRFS_TREE_LOG_OBJECTID);
                        ret = btrfs_free_and_pin_reserved_extent(fs_info,
                                                        next->start, next->len);
                        if (ret)
                                goto out;
                }
        }

out:
        btrfs_free_path(path);
        return ret;
}

/*
 * helper function to update the item for a given subvolumes log root
 * in the tree of log roots
 */
static int update_log_root(struct btrfs_trans_handle *trans,
                           struct btrfs_root *log)
{
        struct btrfs_fs_info *fs_info = log->fs_info;
        int ret;

        if (log->log_transid == 1) {
                /* insert root item on the first sync */
                ret = btrfs_insert_root(trans, fs_info->log_root_tree,
                                &log->root_key, &log->root_item);
        } else {
                ret = btrfs_update_root(trans, fs_info->log_root_tree,
                                &log->root_key, &log->root_item);
        }
        return ret;
}

static void wait_log_commit(struct btrfs_root *root, int transid)
{
        DEFINE_WAIT(wait);
        int index = transid % 2;

        /*
         * we only allow two pending log transactions at a time,
         * so we know that if ours is more than 2 older than the
         * current transaction, we're done
         */
        for (;;) {
                prepare_to_wait(&root->log_commit_wait[index],
                                &wait, TASK_UNINTERRUPTIBLE);

                if (!(root->log_transid_committed < transid &&
                      atomic_read(&root->log_commit[index])))
                        break;

                mutex_unlock(&root->log_mutex);
                schedule();
                mutex_lock(&root->log_mutex);
        }
        finish_wait(&root->log_commit_wait[index], &wait);
}

static void wait_for_writer(struct btrfs_root *root)
{
        DEFINE_WAIT(wait);

        for (;;) {
                prepare_to_wait(&root->log_writer_wait, &wait,
                                TASK_UNINTERRUPTIBLE);
                if (!atomic_read(&root->log_writers))
                        break;

                mutex_unlock(&root->log_mutex);
                schedule();
                mutex_lock(&root->log_mutex);
        }
        finish_wait(&root->log_writer_wait, &wait);
}

static inline void btrfs_remove_log_ctx(struct btrfs_root *root,
                                        struct btrfs_log_ctx *ctx)
{
        if (!ctx)
                return;

        mutex_lock(&root->log_mutex);
        list_del_init(&ctx->list);
        mutex_unlock(&root->log_mutex);
}

/* 
 * Invoked in log mutex context, or be sure there is no other task which
 * can access the list.
 */
static inline void btrfs_remove_all_log_ctxs(struct btrfs_root *root,
                                             int index, int error)
{
        struct btrfs_log_ctx *ctx;
        struct btrfs_log_ctx *safe;

        list_for_each_entry_safe(ctx, safe, &root->log_ctxs[index], list) {
                list_del_init(&ctx->list);
                ctx->log_ret = error;
        }

        INIT_LIST_HEAD(&root->log_ctxs[index]);
}

/*
 * btrfs_sync_log does sends a given tree log down to the disk and
 * updates the super blocks to record it.  When this call is done,
 * you know that any inodes previously logged are safely on disk only
 * if it returns 0.
 *
 * Any other return value means you need to call btrfs_commit_transaction.
 * Some of the edge cases for fsyncing directories that have had unlinks
 * or renames done in the past mean that sometimes the only safe
 * fsync is to commit the whole FS.  When btrfs_sync_log returns -EAGAIN,
 * that has happened.
 */
int btrfs_sync_log(struct btrfs_trans_handle *trans,
                   struct btrfs_root *root, struct btrfs_log_ctx *ctx)
{
        int index1;
        int index2;
        int mark;
        int ret;
        struct btrfs_fs_info *fs_info = root->fs_info;
        struct btrfs_root *log = root->log_root;
        struct btrfs_root *log_root_tree = fs_info->log_root_tree;
        int log_transid = 0;
        struct btrfs_log_ctx root_log_ctx;
        struct blk_plug plug;

        mutex_lock(&root->log_mutex);
        log_transid = ctx->log_transid;
        if (root->log_transid_committed >= log_transid) {
                mutex_unlock(&root->log_mutex);
                return ctx->log_ret;
        }

        index1 = log_transid % 2;
        if (atomic_read(&root->log_commit[index1])) {
                wait_log_commit(root, log_transid);
                mutex_unlock(&root->log_mutex);
                return ctx->log_ret;
        }
        ASSERT(log_transid == root->log_transid);
        atomic_set(&root->log_commit[index1], 1);

        /* wait for previous tree log sync to complete */
        if (atomic_read(&root->log_commit[(index1 + 1) % 2]))
                wait_log_commit(root, log_transid - 1);

        while (1) {
                int batch = atomic_read(&root->log_batch);
                /* when we're on an ssd, just kick the log commit out */
                if (!btrfs_test_opt(fs_info, SSD) &&
                    test_bit(BTRFS_ROOT_MULTI_LOG_TASKS, &root->state)) {
                        mutex_unlock(&root->log_mutex);
                        schedule_timeout_uninterruptible(1);
                        mutex_lock(&root->log_mutex);
                }
                wait_for_writer(root);
                if (batch == atomic_read(&root->log_batch))
                        break;
        }

        /* bail out if we need to do a full commit */
        if (btrfs_need_log_full_commit(fs_info, trans)) {
                ret = -EAGAIN;
                btrfs_free_logged_extents(log, log_transid);
                mutex_unlock(&root->log_mutex);
                goto out;
        }

        if (log_transid % 2 == 0)
                mark = EXTENT_DIRTY;
        else
                mark = EXTENT_NEW;

        /* we start IO on  all the marked extents here, but we don't actually
         * wait for them until later.
         */
        blk_start_plug(&plug);
        ret = btrfs_write_marked_extents(fs_info, &log->dirty_log_pages, mark);
        if (ret) {
                blk_finish_plug(&plug);
                btrfs_abort_transaction(trans, ret);
                btrfs_free_logged_extents(log, log_transid);
                btrfs_set_log_full_commit(fs_info, trans);
                mutex_unlock(&root->log_mutex);
                goto out;
        }

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

        root->log_transid++;
        log->log_transid = root->log_transid;
        root->log_start_pid = 0;
        /*
         * IO has been started, blocks of the log tree have WRITTEN flag set
         * in their headers. new modifications of the log will be written to
         * new positions. so it's safe to allow log writers to go in.
         */
        mutex_unlock(&root->log_mutex);

        btrfs_init_log_ctx(&root_log_ctx, NULL);

        mutex_lock(&log_root_tree->log_mutex);
        atomic_inc(&log_root_tree->log_batch);
        atomic_inc(&log_root_tree->log_writers);

        index2 = log_root_tree->log_transid % 2;
        list_add_tail(&root_log_ctx.list, &log_root_tree->log_ctxs[index2]);
        root_log_ctx.log_transid = log_root_tree->log_transid;

        mutex_unlock(&log_root_tree->log_mutex);

        ret = update_log_root(trans, log);

        mutex_lock(&log_root_tree->log_mutex);
        if (atomic_dec_and_test(&log_root_tree->log_writers)) {
                /* atomic_dec_and_test implies a barrier */
                cond_wake_up_nomb(&log_root_tree->log_writer_wait);
        }

        if (ret) {
                if (!list_empty(&root_log_ctx.list))
                        list_del_init(&root_log_ctx.list);

                blk_finish_plug(&plug);
                btrfs_set_log_full_commit(fs_info, trans);

                if (ret != -ENOSPC) {
                        btrfs_abort_transaction(trans, ret);