// SPDX-License-Identifier: GPL-2.0
/*
 *  linux/fs/ext4/namei.c
 *
 * Copyright (C) 1992, 1993, 1994, 1995
 * Remy Card (card@masi.ibp.fr)
 * Laboratoire MASI - Institut Blaise Pascal
 * Universite Pierre et Marie Curie (Paris VI)
 *
 *  from
 *
 *  linux/fs/minix/namei.c
 *
 *  Copyright (C) 1991, 1992  Linus Torvalds
 *
 *  Big-endian to little-endian byte-swapping/bitmaps by
 *        David S. Miller (davem@caip.rutgers.edu), 1995
 *  Directory entry file type support and forward compatibility hooks
 *      for B-tree directories by Theodore Ts'o (tytso@mit.edu), 1998
 *  Hash Tree Directory indexing (c)
 *      Daniel Phillips, 2001
 *  Hash Tree Directory indexing porting
 *      Christopher Li, 2002
 *  Hash Tree Directory indexing cleanup
 *      Theodore Ts'o, 2002
 */

#include <linux/fs.h>
#include <linux/pagemap.h>
#include <linux/time.h>
#include <linux/fcntl.h>
#include <linux/stat.h>
#include <linux/string.h>
#include <linux/quotaops.h>
#include <linux/buffer_head.h>
#include <linux/bio.h>
#include <linux/iversion.h>
#include <linux/unicode.h>
#include "ext4.h"
#include "ext4_jbd2.h"

#include "xattr.h"
#include "acl.h"

#include <trace/events/ext4.h>
/*
 * define how far ahead to read directories while searching them.
 */
#define NAMEI_RA_CHUNKS  2
#define NAMEI_RA_BLOCKS  4
#define NAMEI_RA_SIZE        (NAMEI_RA_CHUNKS * NAMEI_RA_BLOCKS)

static struct buffer_head *ext4_append(handle_t *handle,
                                        struct inode *inode,
                                        ext4_lblk_t *block)
{
        struct buffer_head *bh;
        int err;

        if (unlikely(EXT4_SB(inode->i_sb)->s_max_dir_size_kb &&
                     ((inode->i_size >> 10) >=
                      EXT4_SB(inode->i_sb)->s_max_dir_size_kb)))
                return ERR_PTR(-ENOSPC);

        *block = inode->i_size >> inode->i_sb->s_blocksize_bits;

        bh = ext4_bread(handle, inode, *block, EXT4_GET_BLOCKS_CREATE);
        if (IS_ERR(bh))
                return bh;
        inode->i_size += inode->i_sb->s_blocksize;
        EXT4_I(inode)->i_disksize = inode->i_size;
        BUFFER_TRACE(bh, "get_write_access");
        err = ext4_journal_get_write_access(handle, inode->i_sb, bh,
                                            EXT4_JTR_NONE);
        if (err) {
                brelse(bh);
                ext4_std_error(inode->i_sb, err);
                return ERR_PTR(err);
        }
        return bh;
}

static int ext4_dx_csum_verify(struct inode *inode,
                               struct ext4_dir_entry *dirent);

/*
 * Hints to ext4_read_dirblock regarding whether we expect a directory
 * block being read to be an index block, or a block containing
 * directory entries (and if the latter, whether it was found via a
 * logical block in an htree index block).  This is used to control
 * what sort of sanity checkinig ext4_read_dirblock() will do on the
 * directory block read from the storage device.  EITHER will means
 * the caller doesn't know what kind of directory block will be read,
 * so no specific verification will be done.
 */
typedef enum {
        EITHER, INDEX, DIRENT, DIRENT_HTREE
} dirblock_type_t;

#define ext4_read_dirblock(inode, block, type) \
        __ext4_read_dirblock((inode), (block), (type), __func__, __LINE__)

static struct buffer_head *__ext4_read_dirblock(struct inode *inode,
                                                ext4_lblk_t block,
                                                dirblock_type_t type,
                                                const char *func,
                                                unsigned int line)
{
        struct buffer_head *bh;
        struct ext4_dir_entry *dirent;
        int is_dx_block = 0;

        if (ext4_simulate_fail(inode->i_sb, EXT4_SIM_DIRBLOCK_EIO))
                bh = ERR_PTR(-EIO);
        else
                bh = ext4_bread(NULL, inode, block, 0);
        if (IS_ERR(bh)) {
                __ext4_warning(inode->i_sb, func, line,
                               "inode #%lu: lblock %lu: comm %s: "
                               "error %ld reading directory block",
                               inode->i_ino, (unsigned long)block,
                               current->comm, PTR_ERR(bh));

                return bh;
        }
        if (!bh && (type == INDEX || type == DIRENT_HTREE)) {
                ext4_error_inode(inode, func, line, block,
                                 "Directory hole found for htree %s block",
                                 (type == INDEX) ? "index" : "leaf");
                return ERR_PTR(-EFSCORRUPTED);
        }
        if (!bh)
                return NULL;
        dirent = (struct ext4_dir_entry *) bh->b_data;
        /* Determine whether or not we have an index block */
        if (is_dx(inode)) {
                if (block == 0)
                        is_dx_block = 1;
                else if (ext4_rec_len_from_disk(dirent->rec_len,
                                                inode->i_sb->s_blocksize) ==
                         inode->i_sb->s_blocksize)
                        is_dx_block = 1;
        }
        if (!is_dx_block && type == INDEX) {
                ext4_error_inode(inode, func, line, block,
                       "directory leaf block found instead of index block");
                brelse(bh);
                return ERR_PTR(-EFSCORRUPTED);
        }
        if (!ext4_has_metadata_csum(inode->i_sb) ||
            buffer_verified(bh))
                return bh;

        /*
         * An empty leaf block can get mistaken for a index block; for
         * this reason, we can only check the index checksum when the
         * caller is sure it should be an index block.
         */
        if (is_dx_block && type == INDEX) {
                if (ext4_dx_csum_verify(inode, dirent) &&
                    !ext4_simulate_fail(inode->i_sb, EXT4_SIM_DIRBLOCK_CRC))
                        set_buffer_verified(bh);
                else {
                        ext4_error_inode_err(inode, func, line, block,
                                             EFSBADCRC,
                                             "Directory index failed checksum");
                        brelse(bh);
                        return ERR_PTR(-EFSBADCRC);
                }
        }
        if (!is_dx_block) {
                if (ext4_dirblock_csum_verify(inode, bh) &&
                    !ext4_simulate_fail(inode->i_sb, EXT4_SIM_DIRBLOCK_CRC))
                        set_buffer_verified(bh);
                else {
                        ext4_error_inode_err(inode, func, line, block,
                                             EFSBADCRC,
                                             "Directory block failed checksum");
                        brelse(bh);
                        return ERR_PTR(-EFSBADCRC);
                }
        }
        return bh;
}

#ifdef DX_DEBUG
#define dxtrace(command) command
#else
#define dxtrace(command)
#endif

struct fake_dirent
{
        __le32 inode;
        __le16 rec_len;
        u8 name_len;
        u8 file_type;
};

struct dx_countlimit
{
        __le16 limit;
        __le16 count;
};

struct dx_entry
{
        __le32 hash;
        __le32 block;
};

/*
 * dx_root_info is laid out so that if it should somehow get overlaid by a
 * dirent the two low bits of the hash version will be zero.  Therefore, the
 * hash version mod 4 should never be 0.  Sincerely, the paranoia department.
 */

struct dx_root
{
        struct fake_dirent dot;
        char dot_name[4];
        struct fake_dirent dotdot;
        char dotdot_name[4];
        struct dx_root_info
        {
                __le32 reserved_zero;
                u8 hash_version;
                u8 info_length; /* 8 */
                u8 indirect_levels;
                u8 unused_flags;
        }
        info;
        struct dx_entry entries[];
};

struct dx_node
{
        struct fake_dirent fake;
        struct dx_entry entries[];
};


struct dx_frame
{
        struct buffer_head *bh;
        struct dx_entry *entries;
        struct dx_entry *at;
};

struct dx_map_entry
{
        u32 hash;
        u16 offs;
        u16 size;
};

/*
 * This goes at the end of each htree block.
 */
struct dx_tail {
        u32 dt_reserved;
        __le32 dt_checksum;     /* crc32c(uuid+inum+dirblock) */
};

static inline ext4_lblk_t dx_get_block(struct dx_entry *entry);
static void dx_set_block(struct dx_entry *entry, ext4_lblk_t value);
static inline unsigned dx_get_hash(struct dx_entry *entry);
static void dx_set_hash(struct dx_entry *entry, unsigned value);
static unsigned dx_get_count(struct dx_entry *entries);
static unsigned dx_get_limit(struct dx_entry *entries);
static void dx_set_count(struct dx_entry *entries, unsigned value);
static void dx_set_limit(struct dx_entry *entries, unsigned value);
static unsigned dx_root_limit(struct inode *dir, unsigned infosize);
static unsigned dx_node_limit(struct inode *dir);
static struct dx_frame *dx_probe(struct ext4_filename *fname,
                                 struct inode *dir,
                                 struct dx_hash_info *hinfo,
                                 struct dx_frame *frame);
static void dx_release(struct dx_frame *frames);
static int dx_make_map(struct inode *dir, struct ext4_dir_entry_2 *de,
                       unsigned blocksize, struct dx_hash_info *hinfo,
                       struct dx_map_entry map[]);
static void dx_sort_map(struct dx_map_entry *map, unsigned count);
static struct ext4_dir_entry_2 *dx_move_dirents(struct inode *dir, char *from,
                                        char *to, struct dx_map_entry *offsets,
                                        int count, unsigned int blocksize);
static struct ext4_dir_entry_2 *dx_pack_dirents(struct inode *dir, char *base,
                                                unsigned int blocksize);
static void dx_insert_block(struct dx_frame *frame,
                                        u32 hash, ext4_lblk_t block);
static int ext4_htree_next_block(struct inode *dir, __u32 hash,
                                 struct dx_frame *frame,
                                 struct dx_frame *frames,
                                 __u32 *start_hash);
static struct buffer_head * ext4_dx_find_entry(struct inode *dir,
                struct ext4_filename *fname,
                struct ext4_dir_entry_2 **res_dir);
static int ext4_dx_add_entry(handle_t *handle, struct ext4_filename *fname,
                             struct inode *dir, struct inode *inode);

/* checksumming functions */
void ext4_initialize_dirent_tail(struct buffer_head *bh,
                                 unsigned int blocksize)
{
        struct ext4_dir_entry_tail *t = EXT4_DIRENT_TAIL(bh->b_data, blocksize);

        memset(t, 0, sizeof(struct ext4_dir_entry_tail));
        t->det_rec_len = ext4_rec_len_to_disk(
                        sizeof(struct ext4_dir_entry_tail), blocksize);
        t->det_reserved_ft = EXT4_FT_DIR_CSUM;
}

/* Walk through a dirent block to find a checksum "dirent" at the tail */
static struct ext4_dir_entry_tail *get_dirent_tail(struct inode *inode,
                                                   struct buffer_head *bh)
{
        struct ext4_dir_entry_tail *t;

#ifdef PARANOID
        struct ext4_dir_entry *d, *top;

        d = (struct ext4_dir_entry *)bh->b_data;
        top = (struct ext4_dir_entry *)(bh->b_data +
                (EXT4_BLOCK_SIZE(inode->i_sb) -
                 sizeof(struct ext4_dir_entry_tail)));
        while (d < top && d->rec_len)
                d = (struct ext4_dir_entry *)(((void *)d) +
                    le16_to_cpu(d->rec_len));

        if (d != top)
                return NULL;

        t = (struct ext4_dir_entry_tail *)d;
#else
        t = EXT4_DIRENT_TAIL(bh->b_data, EXT4_BLOCK_SIZE(inode->i_sb));
#endif

        if (t->det_reserved_zero1 ||
            le16_to_cpu(t->det_rec_len) != sizeof(struct ext4_dir_entry_tail) ||
            t->det_reserved_zero2 ||
            t->det_reserved_ft != EXT4_FT_DIR_CSUM)
                return NULL;

        return t;
}

static __le32 ext4_dirblock_csum(struct inode *inode, void *dirent, int size)
{
        struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
        struct ext4_inode_info *ei = EXT4_I(inode);
        __u32 csum;

        csum = ext4_chksum(sbi, ei->i_csum_seed, (__u8 *)dirent, size);
        return cpu_to_le32(csum);
}

#define warn_no_space_for_csum(inode)                                   \
        __warn_no_space_for_csum((inode), __func__, __LINE__)

static void __warn_no_space_for_csum(struct inode *inode, const char *func,
                                     unsigned int line)
{
        __ext4_warning_inode(inode, func, line,
                "No space for directory leaf checksum. Please run e2fsck -D.");
}

int ext4_dirblock_csum_verify(struct inode *inode, struct buffer_head *bh)
{
        struct ext4_dir_entry_tail *t;

        if (!ext4_has_metadata_csum(inode->i_sb))
                return 1;

        t = get_dirent_tail(inode, bh);
        if (!t) {
                warn_no_space_for_csum(inode);
                return 0;
        }

        if (t->det_checksum != ext4_dirblock_csum(inode, bh->b_data,
                                                  (char *)t - bh->b_data))
                return 0;

        return 1;
}

static void ext4_dirblock_csum_set(struct inode *inode,
                                 struct buffer_head *bh)
{
        struct ext4_dir_entry_tail *t;

        if (!ext4_has_metadata_csum(inode->i_sb))
                return;

        t = get_dirent_tail(inode, bh);
        if (!t) {
                warn_no_space_for_csum(inode);
                return;
        }

        t->det_checksum = ext4_dirblock_csum(inode, bh->b_data,
                                             (char *)t - bh->b_data);
}

int ext4_handle_dirty_dirblock(handle_t *handle,
                               struct inode *inode,
                               struct buffer_head *bh)
{
        ext4_dirblock_csum_set(inode, bh);
        return ext4_handle_dirty_metadata(handle, inode, bh);
}

static struct dx_countlimit *get_dx_countlimit(struct inode *inode,
                                               struct ext4_dir_entry *dirent,
                                               int *offset)
{
        struct ext4_dir_entry *dp;
        struct dx_root_info *root;
        int count_offset;

        if (le16_to_cpu(dirent->rec_len) == EXT4_BLOCK_SIZE(inode->i_sb))
                count_offset = 8;
        else if (le16_to_cpu(dirent->rec_len) == 12) {
                dp = (struct ext4_dir_entry *)(((void *)dirent) + 12);
                if (le16_to_cpu(dp->rec_len) !=
                    EXT4_BLOCK_SIZE(inode->i_sb) - 12)
                        return NULL;
                root = (struct dx_root_info *)(((void *)dp + 12));
                if (root->reserved_zero ||
                    root->info_length != sizeof(struct dx_root_info))
                        return NULL;
                count_offset = 32;
        } else
                return NULL;

        if (offset)
                *offset = count_offset;
        return (struct dx_countlimit *)(((void *)dirent) + count_offset);
}

static __le32 ext4_dx_csum(struct inode *inode, struct ext4_dir_entry *dirent,
                           int count_offset, int count, struct dx_tail *t)
{
        struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
        struct ext4_inode_info *ei = EXT4_I(inode);
        __u32 csum;
        int size;
        __u32 dummy_csum = 0;
        int offset = offsetof(struct dx_tail, dt_checksum);

        size = count_offset + (count * sizeof(struct dx_entry));
        csum = ext4_chksum(sbi, ei->i_csum_seed, (__u8 *)dirent, size);
        csum = ext4_chksum(sbi, csum, (__u8 *)t, offset);
        csum = ext4_chksum(sbi, csum, (__u8 *)&dummy_csum, sizeof(dummy_csum));

        return cpu_to_le32(csum);
}

static int ext4_dx_csum_verify(struct inode *inode,
                               struct ext4_dir_entry *dirent)
{
        struct dx_countlimit *c;
        struct dx_tail *t;
        int count_offset, limit, count;

        if (!ext4_has_metadata_csum(inode->i_sb))
                return 1;

        c = get_dx_countlimit(inode, dirent, &count_offset);
        if (!c) {
                EXT4_ERROR_INODE(inode, "dir seems corrupt?  Run e2fsck -D.");
                return 0;
        }
        limit = le16_to_cpu(c->limit);
        count = le16_to_cpu(c->count);
        if (count_offset + (limit * sizeof(struct dx_entry)) >
            EXT4_BLOCK_SIZE(inode->i_sb) - sizeof(struct dx_tail)) {
                warn_no_space_for_csum(inode);
                return 0;
        }
        t = (struct dx_tail *)(((struct dx_entry *)c) + limit);

        if (t->dt_checksum != ext4_dx_csum(inode, dirent, count_offset,
                                            count, t))
                return 0;
        return 1;
}

static void ext4_dx_csum_set(struct inode *inode, struct ext4_dir_entry *dirent)
{
        struct dx_countlimit *c;
        struct dx_tail *t;
        int count_offset, limit, count;

        if (!ext4_has_metadata_csum(inode->i_sb))
                return;

        c = get_dx_countlimit(inode, dirent, &count_offset);
        if (!c) {
                EXT4_ERROR_INODE(inode, "dir seems corrupt?  Run e2fsck -D.");
                return;
        }
        limit = le16_to_cpu(c->limit);
        count = le16_to_cpu(c->count);
        if (count_offset + (limit * sizeof(struct dx_entry)) >
            EXT4_BLOCK_SIZE(inode->i_sb) - sizeof(struct dx_tail)) {
                warn_no_space_for_csum(inode);
                return;
        }
        t = (struct dx_tail *)(((struct dx_entry *)c) + limit);

        t->dt_checksum = ext4_dx_csum(inode, dirent, count_offset, count, t);
}

static inline int ext4_handle_dirty_dx_node(handle_t *handle,
                                            struct inode *inode,
                                            struct buffer_head *bh)
{
        ext4_dx_csum_set(inode, (struct ext4_dir_entry *)bh->b_data);
        return ext4_handle_dirty_metadata(handle, inode, bh);
}

/*
 * p is at least 6 bytes before the end of page
 */
static inline struct ext4_dir_entry_2 *
ext4_next_entry(struct ext4_dir_entry_2 *p, unsigned long blocksize)
{
        return (struct ext4_dir_entry_2 *)((char *)p +
                ext4_rec_len_from_disk(p->rec_len, blocksize));
}

/*
 * Future: use high four bits of block for coalesce-on-delete flags
 * Mask them off for now.
 */

static inline ext4_lblk_t dx_get_block(struct dx_entry *entry)
{
        return le32_to_cpu(entry->block) & 0x0fffffff;
}

static inline void dx_set_block(struct dx_entry *entry, ext4_lblk_t value)
{
        entry->block = cpu_to_le32(value);
}

static inline unsigned dx_get_hash(struct dx_entry *entry)
{
        return le32_to_cpu(entry->hash);
}

static inline void dx_set_hash(struct dx_entry *entry, unsigned value)
{
        entry->hash = cpu_to_le32(value);
}

static inline unsigned dx_get_count(struct dx_entry *entries)
{
        return le16_to_cpu(((struct dx_countlimit *) entries)->count);
}

static inline unsigned dx_get_limit(struct dx_entry *entries)
{
        return le16_to_cpu(((struct dx_countlimit *) entries)->limit);
}

static inline void dx_set_count(struct dx_entry *entries, unsigned value)
{
        ((struct dx_countlimit *) entries)->count = cpu_to_le16(value);
}

static inline void dx_set_limit(struct dx_entry *entries, unsigned value)
{
        ((struct dx_countlimit *) entries)->limit = cpu_to_le16(value);
}

static inline unsigned dx_root_limit(struct inode *dir, unsigned infosize)
{
        unsigned int entry_space = dir->i_sb->s_blocksize -
                        ext4_dir_rec_len(1, NULL) -
                        ext4_dir_rec_len(2, NULL) - infosize;

        if (ext4_has_metadata_csum(dir->i_sb))
                entry_space -= sizeof(struct dx_tail);
        return entry_space / sizeof(struct dx_entry);
}

static inline unsigned dx_node_limit(struct inode *dir)
{
        unsigned int entry_space = dir->i_sb->s_blocksize -
                        ext4_dir_rec_len(0, dir);

        if (ext4_has_metadata_csum(dir->i_sb))
                entry_space -= sizeof(struct dx_tail);
        return entry_space / sizeof(struct dx_entry);
}

/*
 * Debug
 */
#ifdef DX_DEBUG
static void dx_show_index(char * label, struct dx_entry *entries)
{
        int i, n = dx_get_count (entries);
        printk(KERN_DEBUG "%s index", label);
        for (i = 0; i < n; i++) {
                printk(KERN_CONT " %x->%lu",
                       i ? dx_get_hash(entries + i) : 0,
                       (unsigned long)dx_get_block(entries + i));
        }
        printk(KERN_CONT "\n");
}

struct stats
{
        unsigned names;
        unsigned space;
        unsigned bcount;
};

static struct stats dx_show_leaf(struct inode *dir,
                                struct dx_hash_info *hinfo,
                                struct ext4_dir_entry_2 *de,
                                int size, int show_names)
{
        unsigned names = 0, space = 0;
        char *base = (char *) de;
        struct dx_hash_info h = *hinfo;

        printk("names: ");
        while ((char *) de < base + size)
        {
                if (de->inode)
                {
                        if (show_names)
                        {
#ifdef CONFIG_FS_ENCRYPTION
                                int len;
                                char *name;
                                struct fscrypt_str fname_crypto_str =
                                        FSTR_INIT(NULL, 0);
                                int res = 0;

                                name  = de->name;
                                len = de->name_len;
                                if (!IS_ENCRYPTED(dir)) {
                                        /* Directory is not encrypted */
                                        ext4fs_dirhash(dir, de->name,
                                                de->name_len, &h);
                                        printk("%*.s:(U)%x.%u ", len,
                                               name, h.hash,
                                               (unsigned) ((char *) de
                                                           - base));
                                } else {
                                        struct fscrypt_str de_name =
                                                FSTR_INIT(name, len);

                                        /* Directory is encrypted */
                                        res = fscrypt_fname_alloc_buffer(
                                                len, &fname_crypto_str);
                                        if (res)
                                                printk(KERN_WARNING "Error "
                                                        "allocating crypto "
                                                        "buffer--skipping "
                                                        "crypto\n");
                                        res = fscrypt_fname_disk_to_usr(dir,
                                                0, 0, &de_name,
                                                &fname_crypto_str);
                                        if (res) {
                                                printk(KERN_WARNING "Error "
                                                        "converting filename "
                                                        "from disk to usr"
                                                        "\n");
                                                name = "??";
                                                len = 2;
                                        } else {
                                                name = fname_crypto_str.name;
                                                len = fname_crypto_str.len;
                                        }
                                        if (IS_CASEFOLDED(dir))
                                                h.hash = EXT4_DIRENT_HASH(de);
                                        else
                                                ext4fs_dirhash(dir, de->name,
                                                       de->name_len, &h);
                                        printk("%*.s:(E)%x.%u ", len, name,
                                               h.hash, (unsigned) ((char *) de
                                                                   - base));
                                        fscrypt_fname_free_buffer(
                                                        &fname_crypto_str);
                                }
#else
                                int len = de->name_len;
                                char *name = de->name;
                                ext4fs_dirhash(dir, de->name, de->name_len, &h);
                                printk("%*.s:%x.%u ", len, name, h.hash,
                                       (unsigned) ((char *) de - base));
#endif
                        }
                        space += ext4_dir_rec_len(de->name_len, dir);
                        names++;
                }
                de = ext4_next_entry(de, size);
        }
        printk(KERN_CONT "(%i)\n", names);
        return (struct stats) { names, space, 1 };
}

struct stats dx_show_entries(struct dx_hash_info *hinfo, struct inode *dir,
                             struct dx_entry *entries, int levels)
{
        unsigned blocksize = dir->i_sb->s_blocksize;
        unsigned count = dx_get_count(entries), names = 0, space = 0, i;
        unsigned bcount = 0;
        struct buffer_head *bh;
        printk("%i indexed blocks...\n", count);
        for (i = 0; i < count; i++, entries++)
        {
                ext4_lblk_t block = dx_get_block(entries);
                ext4_lblk_t hash  = i ? dx_get_hash(entries): 0;
                u32 range = i < count - 1? (dx_get_hash(entries + 1) - hash): ~hash;
                struct stats stats;
                printk("%s%3u:%03u hash %8x/%8x ",levels?"":"   ", i, block, hash, range);
                bh = ext4_bread(NULL,dir, block, 0);
                if (!bh || IS_ERR(bh))
                        continue;
                stats = levels?
                   dx_show_entries(hinfo, dir, ((struct dx_node *) bh->b_data)->entries, levels - 1):
                   dx_show_leaf(dir, hinfo, (struct ext4_dir_entry_2 *)
                        bh->b_data, blocksize, 0);
                names += stats.names;
                space += stats.space;
                bcount += stats.bcount;
                brelse(bh);
        }
        if (bcount)
                printk(KERN_DEBUG "%snames %u, fullness %u (%u%%)\n",
                       levels ? "" : "   ", names, space/bcount,
                       (space/bcount)*100/blocksize);
        return (struct stats) { names, space, bcount};
}

/*
 * Linear search cross check
 */
static inline void htree_rep_invariant_check(struct dx_entry *at,
                                             struct dx_entry *target,
                                             u32 hash, unsigned int n)
{
        while (n--) {
                dxtrace(printk(KERN_CONT ","));
                if (dx_get_hash(++at) > hash) {
                        at--;
                        break;
                }
        }
        ASSERT(at == target - 1);
}
#else /* DX_DEBUG */
static inline void htree_rep_invariant_check(struct dx_entry *at,
                                             struct dx_entry *target,
                                             u32 hash, unsigned int n)
{
}
#endif /* DX_DEBUG */

/*
 * Probe for a directory leaf block to search.
 *
 * dx_probe can return ERR_BAD_DX_DIR, which means there was a format
 * error in the directory index, and the caller should fall back to
 * searching the directory normally.  The callers of dx_probe **MUST**
 * check for this error code, and make sure it never gets reflected
 * back to userspace.
 */
static struct dx_frame *
dx_probe(struct ext4_filename *fname, struct inode *dir,
         struct dx_hash_info *hinfo, struct dx_frame *frame_in)
{
        unsigned count, indirect;
        struct dx_entry *at, *entries, *p, *q, *m;
        struct dx_root *root;
        struct dx_frame *frame = frame_in;
        struct dx_frame *ret_err = ERR_PTR(ERR_BAD_DX_DIR);
        u32 hash;

        memset(frame_in, 0, EXT4_HTREE_LEVEL * sizeof(frame_in[0]));
        frame->bh = ext4_read_dirblock(dir, 0, INDEX);
        if (IS_ERR(frame->bh))
                return (struct dx_frame *) frame->bh;

        root = (struct dx_root *) frame->bh->b_data;
        if (root->info.hash_version != DX_HASH_TEA &&
            root->info.hash_version != DX_HASH_HALF_MD4 &&
            root->info.hash_version != DX_HASH_LEGACY &&
            root->info.hash_version != DX_HASH_SIPHASH) {
                ext4_warning_inode(dir, "Unrecognised inode hash code %u",
                                   root->info.hash_version);
                goto fail;
        }
        if (ext4_hash_in_dirent(dir)) {
                if (root->info.hash_version != DX_HASH_SIPHASH) {
                        ext4_warning_inode(dir,
                                "Hash in dirent, but hash is not SIPHASH");
                        goto fail;
                }
        } else {
                if (root->info.hash_version == DX_HASH_SIPHASH) {
                        ext4_warning_inode(dir,
                                "Hash code is SIPHASH, but hash not in dirent");
                        goto fail;
                }
        }
        if (fname)
                hinfo = &fname->hinfo;
        hinfo->hash_version = root->info.hash_version;
        if (hinfo->hash_version <= DX_HASH_TEA)
                hinfo->hash_version += EXT4_SB(dir->i_sb)->s_hash_unsigned;
        hinfo->seed = EXT4_SB(dir->i_sb)->s_hash_seed;
        /* hash is already computed for encrypted casefolded directory */
        if (fname && fname_name(fname) &&
                                !(IS_ENCRYPTED(dir) && IS_CASEFOLDED(dir)))
                ext4fs_dirhash(dir, fname_name(fname), fname_len(fname), hinfo);
        hash = hinfo->hash;

        if (root->info.unused_flags & 1) {
                ext4_warning_inode(dir, "Unimplemented hash flags: %#06x",
                                   root->info.unused_flags);
                goto fail;
        }

        indirect = root->info.indirect_levels;
        if (indirect >= ext4_dir_htree_level(dir->i_sb)) {
                ext4_warning(dir->i_sb,
                             "Directory (ino: %lu) htree depth %#06x exceed"
                             "supported value", dir->i_ino,
                             ext4_dir_htree_level(dir->i_sb));
                if (ext4_dir_htree_level(dir->i_sb) < EXT4_HTREE_LEVEL) {
                        ext4_warning(dir->i_sb, "Enable large directory "
                                                "feature to access it");
                }
                goto fail;
        }

        entries = (struct dx_entry *)(((char *)&root->info) +
                                      root->info.info_length);

        if (dx_get_limit(entries) != dx_root_limit(dir,
                                                   root->info.info_length)) {
                ext4_warning_inode(dir, "dx entry: limit %u != root limit %u",
                                   dx_get_limit(entries),
                                   dx_root_limit(dir, root->info.info_length));
                goto fail;
        }

        dxtrace(printk("Look up %x", hash));
        while (1) {
                count = dx_get_count(entries);
                if (!count || count > dx_get_limit(entries)) {
                        ext4_warning_inode(dir,
                                           "dx entry: count %u beyond limit %u",
                                           count, dx_get_limit(entries));
                        goto fail;
                }

                p = entries + 1;
                q = entries + count - 1;
                while (p <= q) {
                        m = p + (q - p) / 2;
                        dxtrace(printk(KERN_CONT "."));
                        if (dx_get_hash(m) > hash)
                                q = m - 1;
                        else
                                p = m + 1;
                }

                htree_rep_invariant_check(entries, p, hash, count - 1);

                at = p - 1;
                dxtrace(printk(KERN_CONT " %x->%u\n",
                               at == entries ? 0 : dx_get_hash(at),
                               dx_get_block(at)));
                frame->entries = entries;
                frame->at = at;
                if (!indirect--)
                        return frame;
                frame++;
                frame->bh = ext4_read_dirblock(dir, dx_get_block(at), INDEX);
                if (IS_ERR(frame->bh)) {
                        ret_err = (struct dx_frame *) frame->bh;
                        frame->bh = NULL;
                        goto fail;
                }
                entries = ((struct dx_node *) frame->bh->b_data)->entries;

                if (dx_get_limit(entries) != dx_node_limit(dir)) {
                        ext4_warning_inode(dir,
                                "dx entry: limit %u != node limit %u",
                                dx_get_limit(entries), dx_node_limit(dir));
                        goto fail;
                }
        }
fail:
        while (frame >= frame_in) {
                brelse(frame->bh);
                frame--;
        }

        if (ret_err == ERR_PTR(ERR_BAD_DX_DIR))
                ext4_warning_inode(dir,
                        "Corrupt directory, running e2fsck is recommended");
        return ret_err;
}

static void dx_release(struct dx_frame *frames)
{
        struct dx_root_info *info;
        int i;
        unsigned int indirect_levels;

        if (frames[0].bh == NULL)
                return;

        info = &((struct dx_root *)frames[0].bh->b_data)->info;
        /* save local copy, "info" may be freed after brelse() */
        indirect_levels = info->indirect_levels;
        for (i = 0; i <= indirect_levels; i++) {
                if (frames[i].bh == NULL)
                        break;
                brelse(frames[i].bh);
                frames[i].bh = NULL;
        }
}

/*
 * This function increments the frame pointer to search the next leaf
 * block, and reads in the necessary intervening nodes if the search
 * should be necessary.  Whether or not the search is necessary is
 * controlled by the hash parameter.  If the hash value is even, then
 * the search is only continued if the next block starts with that
 * hash value.  This is used if we are searching for a specific file.
 *
 * If the hash value is HASH_NB_ALWAYS, then always go to the next block.
 *
 * This function returns 1 if the caller should continue to search,
 * or 0 if it should not.  If there is an error reading one of the
 * index blocks, it will a negative error code.
 *
 * If start_hash is non-null, it will be filled in with the starting
 * hash of the next page.
 */
static int ext4_htree_next_block(struct inode *dir, __u32 hash,
                                 struct dx_frame *frame,
                                 struct dx_frame *frames,
                                 __u32 *start_hash)
{
        struct dx_frame *p;
        struct buffer_head *bh;
        int num_frames = 0;
        __u32 bhash;

        p = frame;
        /*
         * Find the next leaf page by incrementing the frame pointer.
         * If we run out of entries in the interior node, loop around and
         * increment pointer in the parent node.  When we break out of
         * this loop, num_frames indicates the number of interior
         * nodes need to be read.
         */
        while (1) {
                if (++(p->at) < p->entries + dx_get_count(p->entries))
                        break;
                if (p == frames)
                        return 0;
                num_frames++;
                p--;
        }

        /*
         * If the hash is 1, then continue only if the next page has a
         * continuation hash of any value.  This is used for readdir
         * handling.  Otherwise, check to see if the hash matches the
         * desired continuation hash.  If it doesn't, return since
         * there's no point to read in the successive index pages.
         */
        bhash = dx_get_hash(p->at);
        if (start_hash)
                *start_hash = bhash;
        if ((hash & 1) == 0) {
                if ((bhash & ~1) != hash)
                        return 0;
        }
        /*
         * If the hash is HASH_NB_ALWAYS, we always go to the next
         * block so no check is necessary
         */
        while (num_frames--) {
                bh = ext4_read_dirblock(dir, dx_get_block(p->at), INDEX);
                if (IS_ERR(bh))
                        return PTR_ERR(bh);

                p++;
                brelse(p->bh);
                p->bh = bh;
                p->at = p->entries = ((struct dx_node *) bh->b_data)->entries;
        }
        return 1;
}


/*
 * This function fills a red-black tree with information from a
 * directory block.  It returns the number directory entries loaded
 * into the tree.  If there is an error it is returned in err.
 */
static int htree_dirblock_to_tree(struct file *dir_file,
                                  struct inode *dir, ext4_lblk_t block,
                                  struct dx_hash_info *hinfo,
                                  __u32 start_hash, __u32 start_minor_hash)
{
        struct buffer_head *bh;
        struct ext4_dir_entry_2 *de, *top;
        int err = 0, count = 0;
        struct fscrypt_str fname_crypto_str = FSTR_INIT(NULL, 0), tmp_str;
        int csum = ext4_has_metadata_csum(dir->i_sb);

        dxtrace(printk(KERN_INFO "In htree dirblock_to_tree: block %lu\n",
                                                        (unsigned long)block));
        bh = ext4_read_dirblock(dir, block, DIRENT_HTREE);
        if (IS_ERR(bh))
                return PTR_ERR(bh);

        de = (struct ext4_dir_entry_2 *) bh->b_data;
        /* csum entries are not larger in the casefolded encrypted case */
        top = (struct ext4_dir_entry_2 *) ((char *) de +
                                           dir->i_sb->s_blocksize -
                                           ext4_dir_rec_len(0,
                                                           csum ? NULL : dir));
        /* Check if the directory is encrypted */
        if (IS_ENCRYPTED(dir)) {
                err = fscrypt_prepare_readdir(dir);
                if (err < 0) {
                        brelse(bh);
                        return err;
                }
                err = fscrypt_fname_alloc_buffer(EXT4_NAME_LEN,
                                                 &fname_crypto_str);
                if (err < 0) {
                        brelse(bh);
                        return err;
                }
        }

        for (; de < top; de = ext4_next_entry(de, dir->i_sb->s_blocksize)) {
                if (ext4_check_dir_entry(dir, NULL, de, bh,
                                bh->b_data, bh->b_size,
                                (block<<EXT4_BLOCK_SIZE_BITS(dir->i_sb))
                                         + ((char *)de - bh->b_data))) {
                        /* silently ignore the rest of the block */
                        break;
                }
                if (ext4_hash_in_dirent(dir)) {
                        if (de->name_len && de->inode) {
                                hinfo->hash = EXT4_DIRENT_HASH(de);
                                hinfo->minor_hash = EXT4_DIRENT_MINOR_HASH(de);
                        } else {
                                hinfo->hash = 0;
                                hinfo->minor_hash = 0;
                        }
                } else {
                        ext4fs_dirhash(dir, de->name, de->name_len, hinfo);
                }
                if ((hinfo->hash < start_hash) ||
                    ((hinfo->hash == start_hash) &&
                     (hinfo->minor_hash < start_minor_hash)))
                        continue;
                if (de->inode == 0)
                        continue;
                if (!IS_ENCRYPTED(dir)) {
                        tmp_str.name = de->name;
                        tmp_str.len = de->name_len;
                        err = ext4_htree_store_dirent(dir_file,
                                   hinfo->hash, hinfo->minor_hash, de,
                                   &tmp_str);
                } else {
                        int save_len = fname_crypto_str.len;
                        struct fscrypt_str de_name = FSTR_INIT(de->name,
                                                                de->name_len);

                        /* Directory is encrypted */
                        err = fscrypt_fname_disk_to_usr(dir, hinfo->hash,
                                        hinfo->minor_hash, &de_name,
                                        &fname_crypto_str);
                        if (err) {
                                count = err;
                                goto errout;
                        }
                        err = ext4_htree_store_dirent(dir_file,
                                   hinfo->hash, hinfo->minor_hash, de,
                                        &fname_crypto_str);
                        fname_crypto_str.len = save_len;
                }
                if (err != 0) {
                        count = err;
                        goto errout;
                }
                count++;
        }
errout:
        brelse(bh);
        fscrypt_fname_free_buffer(&fname_crypto_str);
        return count;
}


/*
 * This function fills a red-black tree with information from a
 * directory.  We start scanning the directory in hash order, starting
 * at start_hash and start_minor_hash.
 *
 * This function returns the number of entries inserted into the tree,
 * or a negative error code.
 */
int ext4_htree_fill_tree(struct file *dir_file, __u32 start_hash,
                         __u32 start_minor_hash, __u32 *next_hash)
{
        struct dx_hash_info hinfo;
        struct ext4_dir_entry_2 *de;
        struct dx_frame frames[EXT4_HTREE_LEVEL], *frame;
        struct inode *dir;
        ext4_lblk_t block;
        int count = 0;
        int ret, err;
        __u32 hashval;
        struct fscrypt_str tmp_str;

        dxtrace(printk(KERN_DEBUG "In htree_fill_tree, start hash: %x:%x\n",
                       start_hash, start_minor_hash));
        dir = file_inode(dir_file);
        if (!(ext4_test_inode_flag(dir, EXT4_INODE_INDEX))) {
                if (ext4_hash_in_dirent(dir))
                        hinfo.hash_version = DX_HASH_SIPHASH;
                else
                        hinfo.hash_version =
                                        EXT4_SB(dir->i_sb)->s_def_hash_version;
                if (hinfo.hash_version <= DX_HASH_TEA)
                        hinfo.hash_version +=
                                EXT4_SB(dir->i_sb)->s_hash_unsigned;
                hinfo.seed = EXT4_SB(dir->i_sb)->s_hash_seed;
                if (ext4_has_inline_data(dir)) {
                        int has_inline_data = 1;
                        count = ext4_inlinedir_to_tree(dir_file, dir, 0,
                                                       &hinfo, start_hash,
                                                       start_minor_hash,
                                                       &has_inline_data);
                        if (has_inline_data) {
                                *next_hash = ~0;
                                return count;
                        }
                }
                count = htree_dirblock_to_tree(dir_file, dir, 0, &hinfo,
                                               start_hash, start_minor_hash);
                *next_hash = ~0;
                return count;
        }
        hinfo.hash = start_hash;
        hinfo.minor_hash = 0;
        frame = dx_probe(NULL, dir, &hinfo, frames);
        if (IS_ERR(frame))
                return PTR_ERR(frame);

        /* Add '.' and '..' from the htree header */
        if (!start_hash && !start_minor_hash) {
                de = (struct ext4_dir_entry_2 *) frames[0].bh->b_data;
                tmp_str.name = de->name;
                tmp_str.len = de->name_len;
                err = ext4_htree_store_dirent(dir_file, 0, 0,
                                              de, &tmp_str);
                if (err != 0)
                        goto errout;
                count++;
        }
        if (start_hash < 2 || (start_hash ==2 && start_minor_hash==0)) {
                de = (struct ext4_dir_entry_2 *) frames[0].bh->b_data;
                de = ext4_next_entry(de, dir->i_sb->s_blocksize);
                tmp_str.name = de->name;
                tmp_str.len = de->name_len;
                err = ext4_htree_store_dirent(dir_file, 2, 0,
                                              de, &tmp_str);
                if (err != 0)
                        goto errout;
                count++;
        }

        while (1) {
                if (fatal_signal_pending(current)) {
                        err = -ERESTARTSYS;
                        goto errout;
                }
                cond_resched();
                block = dx_get_block(frame->at);
                ret = htree_dirblock_to_tree(dir_file, dir, block, &hinfo,
                                             start_hash, start_minor_hash);
                if (ret < 0) {
                        err = ret;
                        goto errout;
                }
                count += ret;
                hashval = ~0;
                ret = ext4_htree_next_block(dir, HASH_NB_ALWAYS,
                                            frame, frames, &hashval);
                *next_hash = hashval;
                if (ret < 0) {
                        err = ret;
                        goto errout;
                }
                /*
                 * Stop if:  (a) there are no more entries, or
                 * (b) we have inserted at least one entry and the
                 * next hash value is not a continuation
                 */
                if ((ret == 0) ||
                    (count && ((hashval & 1) == 0)))
                        break;
        }
        dx_release(frames);
        dxtrace(printk(KERN_DEBUG "Fill tree: returned %d entries, "
                       "next hash: %x\n", count, *next_hash));
        return count;
errout:
        dx_release(frames);
        return (err);
}

static inline int search_dirblock(struct buffer_head *bh,
                                  struct inode *dir,
                                  struct ext4_filename *fname,
                                  unsigned int offset,
                                  struct ext4_dir_entry_2 **res_dir)
{
        return ext4_search_dir(bh, bh->b_data, dir->i_sb->s_blocksize, dir,
                               fname, offset, res_dir);
}

/*
 * Directory block splitting, compacting
 */

/*
 * Create map of hash values, offsets, and sizes, stored at end of block.
 * Returns number of entries mapped.
 */
static int dx_make_map(struct inode *dir, struct ext4_dir_entry_2 *de,
                       unsigned blocksize, struct dx_hash_info *hinfo,
                       struct dx_map_entry *map_tail)
{
        int count = 0;
        char *base = (char *) de;
        struct dx_hash_info h = *hinfo;

        while ((char *) de < base + blocksize) {
                if (de->name_len && de->inode) {
                        if (ext4_hash_in_dirent(dir))
                                h.hash = EXT4_DIRENT_HASH(de);
                        else
                                ext4fs_dirhash(dir, de->name, de->name_len, &h);
                        map_tail--;
                        map_tail->hash = h.hash;
                        map_tail->offs = ((char *) de - base)>>2;
                        map_tail->size = le16_to_cpu(de->rec_len);
                        count++;
                        cond_resched();
                }
                /* XXX: do we need to check rec_len == 0 case? -Chris */
                de = ext4_next_entry(de, blocksize);
        }
        return count;
}

/* Sort map by hash value */
static void dx_sort_map (struct dx_map_entry *map, unsigned count)
{
        struct dx_map_entry *p, *q, *top = map + count - 1;
        int more;
        /* Combsort until bubble sort doesn't suck */
        while (count > 2) {
                count = count*10/13;
                if (count - 9 < 2) /* 9, 10 -> 11 */
                        count = 11;
                for (p = top, q = p - count; q >= map; p--, q--)
                        if (p->hash < q->hash)
                                swap(*p, *q);
        }
        /* Garden variety bubble sort */
        do {
                more = 0;
                q = top;
                while (q-- > map) {
                        if (q[1].hash >= q[0].hash)
                                continue;
                        swap(*(q+1), *q);
                        more = 1;
                }
        } while(more);
}

static void dx_insert_block(struct dx_frame *frame, u32 hash, ext4_lblk_t block)
{
        struct dx_entry *entries = frame->entries;
        struct dx_entry *old = frame->at, *new = old + 1;
        int count = dx_get_count(entries);

        ASSERT(count < dx_get_limit(entries));
        ASSERT(old < entries + count);
        memmove(new + 1, new, (char *)(entries + count) - (char *)(new));
        dx_set_hash(new, hash);
        dx_set_block(new, block);
        dx_set_count(entries, count + 1);
}

#ifdef CONFIG_UNICODE
/*
 * Test whether a case-insensitive directory entry matches the filename
 * being searched for.  If quick is set, assume the name being looked up
 * is already in the casefolded form.
 *
 * Returns: 0 if the directory entry matches, more than 0 if it
 * doesn't match or less than zero on error.
 */
static int ext4_ci_compare(const struct inode *parent, const struct qstr *name,
                           u8 *de_name, size_t de_name_len, bool quick)
{
        const struct super_block *sb = parent->i_sb;
        const struct unicode_map *um = sb->s_encoding;
        struct fscrypt_str decrypted_name = FSTR_INIT(NULL, de_name_len);
        struct qstr entry = QSTR_INIT(de_name, de_name_len);
        int ret;

        if (IS_ENCRYPTED(parent)) {
                const struct fscrypt_str encrypted_name =
                                FSTR_INIT(de_name, de_name_len);

                decrypted_name.name = kmalloc(de_name_len, GFP_KERNEL);
                if (!decrypted_name.name)
                        return -ENOMEM;
                ret = fscrypt_fname_disk_to_usr(parent, 0, 0, &encrypted_name,
                                                &decrypted_name);
                if (ret < 0)
                        goto out;
                entry.name = decrypted_name.name;
                entry.len = decrypted_name.len;
        }

        if (quick)
                ret = utf8_strncasecmp_folded(um, name, &entry);
        else
                ret = utf8_strncasecmp(um, name, &entry);
        if (ret < 0) {
                /* Handle invalid character sequence as either an error
                 * or as an opaque byte sequence.
                 */
                if (sb_has_strict_encoding(sb))
                        ret = -EINVAL;
                else if (name->len != entry.len)
                        ret = 1;
                else
                        ret = !!memcmp(name->name, entry.name, entry.len);
        }
out:
        kfree(decrypted_name.name);
        return ret;
}

int ext4_fname_setup_ci_filename(struct inode *dir, const struct qstr *iname,
                                  struct ext4_filename *name)
{
        struct fscrypt_str *cf_name = &name->cf_name;
        struct dx_hash_info *hinfo = &name->hinfo;
        int len;

        if (!IS_CASEFOLDED(dir) || !dir->i_sb->s_encoding ||
            (IS_ENCRYPTED(dir) && !fscrypt_has_encryption_key(dir))) {
                cf_name->name = NULL;
                return 0;
        }

        cf_name->name = kmalloc(EXT4_NAME_LEN, GFP_NOFS);
        if (!cf_name->name)
                return -ENOMEM;

        len = utf8_casefold(dir->i_sb->s_encoding,
                            iname, cf_name->name,
                            EXT4_NAME_LEN);
        if (len <= 0) {
                kfree(cf_name->name);
                cf_name->name = NULL;
        }
        cf_name->len = (unsigned) len;
        if (!IS_ENCRYPTED(dir))
                return 0;

        hinfo->hash_version = DX_HASH_SIPHASH;
        hinfo->seed = NULL;
        if (cf_name->name)
                ext4fs_dirhash(dir, cf_name->name, cf_name->len, hinfo);
        else
                ext4fs_dirhash(dir, iname->name, iname->len, hinfo);
        return 0;
}
#endif

/*
 * Test whether a directory entry matches the filename being searched for.
 *
 * Return: %true if the directory entry matches, otherwise %false.
 */
static bool ext4_match(struct inode *parent,
                              const struct ext4_filename *fname,
                              struct ext4_dir_entry_2 *de)
{
        struct fscrypt_name f;

        if (!de->inode)
                return false;

        f.usr_fname = fname->usr_fname;
        f.disk_name = fname->disk_name;
#ifdef CONFIG_FS_ENCRYPTION
        f.crypto_buf = fname->crypto_buf;
#endif

#ifdef CONFIG_UNICODE
        if (parent->i_sb->s_encoding && IS_CASEFOLDED(parent) &&
            (!IS_ENCRYPTED(parent) || fscrypt_has_encryption_key(parent))) {
                if (fname->cf_name.name) {
                        struct qstr cf = {.name = fname->cf_name.name,
                                          .len = fname->cf_name.len};
                        if (IS_ENCRYPTED(parent)) {
                                if (fname->hinfo.hash != EXT4_DIRENT_HASH(de) ||
                                        fname->hinfo.minor_hash !=
                                                EXT4_DIRENT_MINOR_HASH(de)) {

                                        return 0;
                                }
                        }
                        return !ext4_ci_compare(parent, &cf, de->name,
                                                        de->name_len, true);
                }
                return !ext4_ci_compare(parent, fname->usr_fname, de->name,
                                                de->name_len, false);
        }
#endif

        return fscrypt_match_name(&f, de->name, de->name_len);
}

/*
 * Returns 0 if not found, -1 on failure, and 1 on success
 */
int ext4_search_dir(struct buffer_head *bh, char *search_buf, int buf_size,
                    struct inode *dir, struct ext4_filename *fname,
                    unsigned int offset, struct ext4_dir_entry_2 **res_dir)
{
        struct ext4_dir_entry_2 * de;
        char * dlimit;
        int de_len;

        de = (struct ext4_dir_entry_2 *)search_buf;
        dlimit = search_buf + buf_size;
        while ((char *) de < dlimit) {
                /* this code is executed quadratically often */
                /* do minimal checking `by hand' */
                if ((char *) de + de->name_len <= dlimit &&
                    ext4_match(dir, fname, de)) {
                        /* found a match - just to be sure, do
                         * a full check */
                        if (ext4_check_dir_entry(dir, NULL, de, bh, search_buf,
                                                 buf_size, offset))
                                return -1;
                        *res_dir = de;
                        return 1;
                }
                /* prevent looping on a bad block */
                de_len = ext4_rec_len_from_disk(de->rec_len,
                                                dir->i_sb->s_blocksize);
                if (de_len <= 0)
                        return -1;
                offset += de_len;
                de = (struct ext4_dir_entry_2 *) ((char *) de + de_len);
        }
        return 0;
}

static int is_dx_internal_node(struct inode *dir, ext4_lblk_t block,
                               struct ext4_dir_entry *de)
{
        struct super_block *sb = dir->i_sb;

        if (!is_dx(dir))
                return 0;
        if (block == 0)
                return 1;
        if (de->inode == 0 &&
            ext4_rec_len_from_disk(de->rec_len, sb->s_blocksize) ==
                        sb->s_blocksize)
                return 1;
        return 0;
}

/*
 *      __ext4_find_entry()
 *
 * finds an entry in the specified directory with the wanted name. It
 * returns the cache buffer in which the entry was found, and the entry
 * itself (as a parameter - res_dir). It does NOT read the inode of the
 * entry - you'll have to do that yourself if you want to.
 *
 * The returned buffer_head has ->b_count elevated.  The caller is expected
 * to brelse() it when appropriate.
 */
static struct buffer_head *__ext4_find_entry(struct inode *dir,
                                             struct ext4_filename *fname,
                                             struct ext4_dir_entry_2 **res_dir,
                                             int *inlined)
{
        struct super_block *sb;
        struct buffer_head *bh_use[NAMEI_RA_SIZE];
        struct buffer_head *bh, *ret = NULL;
        ext4_lblk_t start, block;
        const u8 *name = fname->usr_fname->name;
        size_t ra_max = 0;      /* Number of bh's in the readahead
                                   buffer, bh_use[] */
        size_t ra_ptr = 0;      /* Current index into readahead
                                   buffer */
        ext4_lblk_t  nblocks;
        int i, namelen, retval;

        *res_dir = NULL;
        sb = dir->i_sb;
        namelen = fname->usr_fname->len;
        if (namelen > EXT4_NAME_LEN)
                return NULL;

        if (ext4_has_inline_data(dir)) {
                int has_inline_data = 1;
                ret = ext4_find_inline_entry(dir, fname, res_dir,
                                             &has_inline_data);
                if (has_inline_data) {
                        if (inlined)
                                *inlined = 1;
                        goto cleanup_and_exit;
                }
        }

        if ((namelen <= 2) && (name[0] == '.') &&
            (name[1] == '.' || name[1] == '\0')) {
                /*
                 * "." or ".." will only be in the first block
                 * NFS may look up ".."; "." should be handled by the VFS
                 */
                block = start = 0;
                nblocks = 1;
                goto restart;
        }
        if (is_dx(dir)) {
                ret = ext4_dx_find_entry(dir, fname, res_dir);
                /*
                 * On success, or if the error was file not found,
                 * return.  Otherwise, fall back to doing a search the
                 * old fashioned way.
                 */
                if (!IS_ERR(ret) || PTR_ERR(ret) != ERR_BAD_DX_DIR)
                        goto cleanup_and_exit;
                dxtrace(printk(KERN_DEBUG "ext4_find_entry: dx failed, "
                               "falling back\n"));
                ret = NULL;
        }
        nblocks = dir->i_size >> EXT4_BLOCK_SIZE_BITS(sb);
        if (!nblocks) {
                ret = NULL;
                goto cleanup_and_exit;
        }
        start = EXT4_I(dir)->i_dir_start_lookup;
        if (start >= nblocks)
                start = 0;
        block = start;
restart:
        do {
                /*
                 * We deal with the read-ahead logic here.
                 */
                cond_resched();
                if (ra_ptr >= ra_max) {
                        /* Refill the readahead buffer */
                        ra_ptr = 0;
                        if (block < start)
                                ra_max = start - block;
                        else
                                ra_max = nblocks - block;
                        ra_max = min(ra_max, ARRAY_SIZE(bh_use));
                        retval = ext4_bread_batch(dir, block, ra_max,
                                                  false /* wait */, bh_use);
                        if (retval) {
                                ret = ERR_PTR(retval);
                                ra_max = 0;
                                goto cleanup_and_exit;
                        }
                }
                if ((bh = bh_use[ra_ptr++]) == NULL)
                        goto next;
                wait_on_buffer(bh);
                if (!buffer_uptodate(bh)) {
                        EXT4_ERROR_INODE_ERR(dir, EIO,
                                             "reading directory lblock %lu",
                                             (unsigned long) block);
                        brelse(bh);
                        ret = ERR_PTR(-EIO);
                        goto cleanup_and_exit;
                }
                if (!buffer_verified(bh) &&
                    !is_dx_internal_node(dir, block,
                                         (struct ext4_dir_entry *)bh->b_data) &&
                    !ext4_dirblock_csum_verify(dir, bh)) {
                        EXT4_ERROR_INODE_ERR(dir, EFSBADCRC,
                                             "checksumming directory "
                                             "block %lu", (unsigned long)block);
                        brelse(bh);
                        ret = ERR_PTR(-EFSBADCRC);
                        goto cleanup_and_exit;
                }
                set_buffer_verified(bh);
                i = search_dirblock(bh, dir, fname,
                            block << EXT4_BLOCK_SIZE_BITS(sb), res_dir);
                if (i == 1) {
                        EXT4_I(dir)->i_dir_start_lookup = block;
                        ret = bh;
                        goto cleanup_and_exit;
                } else {
                        brelse(bh);
                        if (i < 0)
                                goto cleanup_and_exit;
                }
        next:
                if (++block >= nblocks)
                        block = 0;
        } while (block != start);

        /*
         * If the directory has grown while we were searching, then
         * search the last part of the directory before giving up.
         */
        block = nblocks;
        nblocks = dir->i_size >> EXT4_BLOCK_SIZE_BITS(sb);
        if (block < nblocks) {
                start = 0;
                goto restart;
        }

cleanup_and_exit:
        /* Clean up the read-ahead blocks */
        for (; ra_ptr < ra_max; ra_ptr++)
                brelse(bh_use[ra_ptr]);
        return ret;
}

static struct buffer_head *ext4_find_entry(struct inode *dir,
                                           const struct qstr *d_name,
                                           struct ext4_dir_entry_2 **res_dir,
                                           int *inlined)
{
        int err;
        struct ext4_filename fname;
        struct buffer_head *bh;

        err = ext4_fname_setup_filename(dir, d_name, 1, &fname);
        if (err == -ENOENT)
                return NULL;
        if (err)
                return ERR_PTR(err);

        bh = __ext4_find_entry(dir, &fname, res_dir, inlined);

        ext4_fname_free_filename(&fname);
        return bh;
}

static struct buffer_head *ext4_lookup_entry(struct inode *dir,
                                             struct dentry *dentry,
                                             struct ext4_dir_entry_2 **res_dir)
{
        int err;
        struct ext4_filename fname;
        struct buffer_head *bh;

        err = ext4_fname_prepare_lookup(dir, dentry, &fname);
        generic_set_encrypted_ci_d_ops(dentry);
        if (err == -ENOENT)
                return NULL;
        if (err)
                return ERR_PTR(err);

        bh = __ext4_find_entry(dir, &fname, res_dir, NULL);

        ext4_fname_free_filename(&fname);
        return bh;
}

static struct buffer_head * ext4_dx_find_entry(struct inode *dir,
                        struct ext4_filename *fname,
                        struct ext4_dir_entry_2 **res_dir)
{
        struct super_block * sb = dir->i_sb;
        struct dx_frame frames[EXT4_HTREE_LEVEL], *frame;
        struct buffer_head *bh;
        ext4_lblk_t block;
        int retval;

#ifdef CONFIG_FS_ENCRYPTION
        *res_dir = NULL;
#endif
        frame = dx_probe(fname, dir, NULL, frames);
        if (IS_ERR(frame))
                return (struct buffer_head *) frame;
        do {
                block = dx_get_block(frame->at);
                bh = ext4_read_dirblock(dir, block, DIRENT_HTREE);
                if (IS_ERR(bh))
                        goto errout;

                retval = search_dirblock(bh, dir, fname,
                                         block << EXT4_BLOCK_SIZE_BITS(sb),
                                         res_dir);
                if (retval == 1)
                        goto success;
                brelse(bh);
                if (retval == -1) {
                        bh = ERR_PTR(ERR_BAD_DX_DIR);
                        goto errout;
                }

                /* Check to see if we should continue to search */
                retval = ext4_htree_next_block(dir, fname->hinfo.hash, frame,
                                               frames, NULL);
                if (retval < 0) {
                        ext4_warning_inode(dir,
                                "error %d reading directory index block",
                                retval);
                        bh = ERR_PTR(retval);
                        goto errout;
                }
        } while (retval == 1);

        bh = NULL;
errout:
        dxtrace(printk(KERN_DEBUG "%s not found\n", fname->usr_fname->name));
success:
        dx_release(frames);
        return bh;
}

static struct dentry *ext4_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags)
{
        struct inode *inode;
        struct ext4_dir_entry_2 *de;
        struct buffer_head *bh;

        if (dentry->d_name.len > EXT4_NAME_LEN)
                return ERR_PTR(-ENAMETOOLONG);

        bh = ext4_lookup_entry(dir, dentry, &de);
        if (IS_ERR(bh))
                return ERR_CAST(bh);
        inode = NULL;
        if (bh) {
                __u32 ino = le32_to_cpu(de->inode);
                brelse(bh);
                if (!ext4_valid_inum(dir->i_sb, ino)) {
                        EXT4_ERROR_INODE(dir, "bad inode number: %u", ino);
                        return ERR_PTR(-EFSCORRUPTED);
                }
                if (unlikely(ino == dir->i_ino)) {
                        EXT4_ERROR_INODE(dir, "'%pd' linked to parent dir",
                                         dentry);
                        return ERR_PTR(-EFSCORRUPTED);
                }
                inode = ext4_iget(dir->i_sb, ino, EXT4_IGET_NORMAL);
                if (inode == ERR_PTR(-ESTALE)) {
                        EXT4_ERROR_INODE(dir,
                                         "deleted inode referenced: %u",
                                         ino);
                        return ERR_PTR(-EFSCORRUPTED);
                }
                if (!IS_ERR(inode) && IS_ENCRYPTED(dir) &&
                    (S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode)) &&
                    !fscrypt_has_permitted_context(dir, inode)) {
                        ext4_warning(inode->i_sb,
                                     "Inconsistent encryption contexts: %lu/%lu",
                                     dir->i_ino, inode->i_ino);
                        iput(inode);
                        return ERR_PTR(-EPERM);
                }
        }

#ifdef CONFIG_UNICODE
        if (!inode && IS_CASEFOLDED(dir)) {
                /* Eventually we want to call d_add_ci(dentry, NULL)
                 * for negative dentries in the encoding case as
                 * well.  For now, prevent the negative dentry
                 * from being cached.
                 */
                return NULL;
        }
#endif
        return d_splice_alias(inode, dentry);
}


struct dentry *ext4_get_parent(struct dentry *child)
{
        __u32 ino;
        struct ext4_dir_entry_2 * de;
        struct buffer_head *bh;

        bh = ext4_find_entry(d_inode(child), &dotdot_name, &de, NULL);
        if (IS_ERR(bh))
                return ERR_CAST(bh);
        if (!bh)
                return ERR_PTR(-ENOENT);
        ino = le32_to_cpu(de->inode);
        brelse(bh);

        if (!ext4_valid_inum(child->d_sb, ino)) {
                EXT4_ERROR_INODE(d_inode(child),
                                 "bad parent inode number: %u", ino);
                return ERR_PTR(-EFSCORRUPTED);
        }

        return d_obtain_alias(ext4_iget(child->d_sb, ino, EXT4_IGET_NORMAL));
}

/*
 * Move count entries from end of map between two memory locations.
 * Returns pointer to last entry moved.
 */
static struct ext4_dir_entry_2 *
dx_move_dirents(struct inode *dir, char *from, char *to,
                struct dx_map_entry *map, int count,
                unsigned blocksize)
{
        unsigned rec_len = 0;

        while (count--) {
                struct ext4_dir_entry_2 *de = (struct ext4_dir_entry_2 *)
                                                (from + (map->offs<<2));
                rec_len = ext4_dir_rec_len(de->name_len, dir);

                memcpy (to, de, rec_len);
                ((struct ext4_dir_entry_2 *) to)->rec_len =
                                ext4_rec_len_to_disk(rec_len, blocksize);

                /* wipe dir_entry excluding the rec_len field */
                de->inode = 0;
                memset(&de->name_len, 0, ext4_rec_len_from_disk(de->rec_len,
                                                                blocksize) -
                                         offsetof(struct ext4_dir_entry_2,
                                                                name_len));

                map++;
                to += rec_len;
        }
        return (struct ext4_dir_entry_2 *) (to - rec_len);
}

/*
 * Compact each dir entry in the range to the minimal rec_len.
 * Returns pointer to last entry in range.
 */
static struct ext4_dir_entry_2 *dx_pack_dirents(struct inode *dir, char *base,
                                                        unsigned int blocksize)
{
        struct ext4_dir_entry_2 *next, *to, *prev, *de = (struct ext4_dir_entry_2 *) base;
        unsigned rec_len = 0;

        prev = to = de;
        while ((char*)de < base + blocksize) {
                next = ext4_next_entry(de, blocksize);
                if (de->inode && de->name_len) {
                        rec_len = ext4_dir_rec_len(de->name_len, dir);
                        if (de > to)
                                memmove(to, de, rec_len);
                        to->rec_len = ext4_rec_len_to_disk(rec_len, blocksize);
                        prev = to;
                        to = (struct ext4_dir_entry_2 *) (((char *) to) + rec_len);
                }
                de = next;
        }
        return prev;
}

/*
 * Split a full leaf block to make room for a new dir entry.
 * Allocate a new block, and move entries so that they are approx. equally full.
 * Returns pointer to de in block into which the new entry will be inserted.
 */
static struct ext4_dir_entry_2 *do_split(handle_t *handle, struct inode *dir,
                        struct buffer_head **bh,struct dx_frame *frame,
                        struct dx_hash_info *hinfo)
{
        unsigned blocksize = dir->i_sb->s_blocksize;
        unsigned count, continued;
        struct buffer_head *bh2;
        ext4_lblk_t newblock;
        u32 hash2;
        struct dx_map_entry *map;
        char *data1 = (*bh)->b_data, *data2;
        unsigned split, move, size;
        struct ext4_dir_entry_2 *de = NULL, *de2;
        int     csum_size = 0;
        int     err = 0, i;

        if (ext4_has_metadata_csum(dir->i_sb))
                csum_size = sizeof(struct ext4_dir_entry_tail);

        bh2 = ext4_append(handle, dir, &newblock);
        if (IS_ERR(bh2)) {
                brelse(*bh);
                *bh = NULL;
                return (struct ext4_dir_entry_2 *) bh2;
        }

        BUFFER_TRACE(*bh, "get_write_access");
        err = ext4_journal_get_write_access(handle, dir->i_sb, *bh,
                                            EXT4_JTR_NONE);
        if (err)
                goto journal_error;

        BUFFER_TRACE(frame->bh, "get_write_access");
        err = ext4_journal_get_write_access(handle, dir->i_sb, frame->bh,
                                            EXT4_JTR_NONE);
        if (err)
                goto journal_error;

        data2 = bh2->b_data;

        /* create map in the end of data2 block */
        map = (struct dx_map_entry *) (data2 + blocksize);
        count = dx_make_map(dir, (struct ext4_dir_entry_2 *) data1,
                             blocksize, hinfo, map);
        map -= count;
        dx_sort_map(map, count);
        /* Ensure that neither split block is over half full */
        size = 0;
        move = 0;
        for (i = count-1; i >= 0; i--) {
                /* is more than half of this entry in 2nd half of the block? */
                if (size + map[i].size/2 > blocksize/2)
                        break;
                size += map[i].size;
                move++;
        }
        /*
         * map index at which we will split
         *
         * If the sum of active entries didn't exceed half the block size, just
         * split it in half by count; each resulting block will have at least
         * half the space free.
         */
        if (i > 0)
                split = count - move;
        else
                split = count/2;

        hash2 = map[split].hash;
        continued = hash2 == map[split - 1].hash;
        dxtrace(printk(KERN_INFO "Split block %lu at %x, %i/%i\n",
                        (unsigned long)dx_get_block(frame->at),
                                        hash2, split, count-split));

        /* Fancy dance to stay within two buffers */
        de2 = dx_move_dirents(dir, data1, data2, map + split, count - split,
                              blocksize);
        de = dx_pack_dirents(dir, data1, blocksize);
        de->rec_len = ext4_rec_len_to_disk(data1 + (blocksize - csum_size) -
                                           (char *) de,
                                           blocksize);
        de2->rec_len = ext4_rec_len_to_disk(data2 + (blocksize - csum_size) -
                                            (char *) de2,
                                            blocksize);
        if (csum_size) {
                ext4_initialize_dirent_tail(*bh, blocksize);
                ext4_initialize_dirent_tail(bh2, blocksize);
        }

        dxtrace(dx_show_leaf(dir, hinfo, (struct ext4_dir_entry_2 *) data1,
                        blocksize, 1));
        dxtrace(dx_show_leaf(dir, hinfo, (struct ext4_dir_entry_2 *) data2,
                        blocksize, 1));

        /* Which block gets the new entry? */
        if (hinfo->hash >= hash2) {
                swap(*bh, bh2);

                de = de2;
        }
        dx_insert_block(frame, hash2 + continued, newblock);
        err = ext4_handle_dirty_dirblock(handle, dir, bh2);
        if (err)
                goto journal_error;
        err = ext4_handle_dirty_dx_node(handle, dir, frame->bh);
        if (err)
                goto journal_error;
        brelse(bh2);
        dxtrace(dx_show_index("frame", frame->entries));
        return de;

journal_error:
        brelse(*bh);
        brelse(bh2);
        *bh = NULL;
        ext4_std_error(dir->i_sb, err);
        return ERR_PTR(err);
}

int ext4_find_dest_de(struct inode *dir, struct inode *inode,
                      struct buffer_head *bh,
                      void *buf, int buf_size,
                      struct ext4_filename *fname,
                      struct ext4_dir_entry_2 **dest_de)
{
        struct ext4_dir_entry_2 *de;
        unsigned short reclen = ext4_dir_rec_len(fname_len(fname), dir);
        int nlen, rlen;
        unsigned int offset = 0;
        char *top;

        de = (struct ext4_dir_entry_2 *)buf;
        top = buf + buf_size - reclen;
        while ((char *) de <= top) {
                if (ext4_check_dir_entry(dir, NULL, de, bh,
                                         buf, buf_size, offset))
                        return -EFSCORRUPTED;
                if (ext4_match(dir, fname, de))
                        return -EEXIST;
                nlen = ext4_dir_rec_len(de->name_len, dir);
                rlen = ext4_rec_len_from_disk(de->rec_len, buf_size);
                if ((de->inode ? rlen - nlen : rlen) >= reclen)
                        break;
                de = (struct ext4_dir_entry_2 *)((char *)de + rlen);
                offset += rlen;
        }
        if ((char *) de > top)
                return -ENOSPC;

        *dest_de = de;
        return 0;
}

void ext4_insert_dentry(struct inode *dir,
                        struct inode *inode,
                        struct ext4_dir_entry_2 *de,
                        int buf_size,
                        struct ext4_filename *fname)
{

        int nlen, rlen;

        nlen = ext4_dir_rec_len(de->name_len, dir);
        rlen = ext4_rec_len_from_disk(de->rec_len, buf_size);
        if (de->inode) {
                struct ext4_dir_entry_2 *de1 =
                        (struct ext4_dir_entry_2 *)((char *)de + nlen);
                de1->rec_len = ext4_rec_len_to_disk(rlen - nlen, buf_size);
                de->rec_len = ext4_rec_len_to_disk(nlen, buf_size);
                de = de1;
        }
        de->file_type = EXT4_FT_UNKNOWN;
        de->inode = cpu_to_le32(inode->i_ino);
        ext4_set_de_type(inode->i_sb, de, inode->i_mode);
        de->name_len = fname_len(fname);
        memcpy(de->name, fname_name(fname), fname_len(fname));
        if (ext4_hash_in_dirent(dir)) {
                struct dx_hash_info *hinfo = &fname->hinfo;

                EXT4_DIRENT_HASHES(de)->hash = cpu_to_le32(hinfo->hash);
                EXT4_DIRENT_HASHES(de)->minor_hash =
                                                cpu_to_le32(hinfo->minor_hash);
        }
}

/*
 * Add a new entry into a directory (leaf) block.  If de is non-NULL,
 * it points to a directory entry which is guaranteed to be large
 * enough for new directory entry.  If de is NULL, then
 * add_dirent_to_buf will attempt search the directory block for
 * space.  It will return -ENOSPC if no space is available, and -EIO
 * and -EEXIST if directory entry already exists.
 */
static int add_dirent_to_buf(handle_t *handle, struct ext4_filename *fname,
                             struct inode *dir,
                             struct inode *inode, struct ext4_dir_entry_2 *de,
                             struct buffer_head *bh)
{
        unsigned int    blocksize = dir->i_sb->s_blocksize;
        int             csum_size = 0;
        int             err, err2;

        if (ext4_has_metadata_csum(inode->i_sb))
                csum_size = sizeof(struct ext4_dir_entry_tail);

        if (!de) {
                err = ext4_find_dest_de(dir, inode, bh, bh->b_data,
                                        blocksize - csum_size, fname, &de);
                if (err)
                        return err;
        }
        BUFFER_TRACE(bh, "get_write_access");
        err = ext4_journal_get_write_access(handle, dir->i_sb, bh,
                                            EXT4_JTR_NONE);
        if (err) {
                ext4_std_error(dir->i_sb, err);
                return err;
        }

        /* By now the buffer is marked for journaling */
        ext4_insert_dentry(dir, inode, de, blocksize, fname);

        /*
         * XXX shouldn't update any times until successful
         * completion of syscall, but too many callers depend
         * on this.
         *
         * XXX similarly, too many callers depend on
         * ext4_new_inode() setting the times, but error
         * recovery deletes the inode, so the worst that can
         * happen is that the times are slightly out of date
         * and/or different from the directory change time.
         */
        dir->i_mtime = dir->i_ctime = current_time(dir);
        ext4_update_dx_flag(dir);
        inode_inc_iversion(dir);
        err2 = ext4_mark_inode_dirty(handle, dir);
        BUFFER_TRACE(bh, "call ext4_handle_dirty_metadata");
        err = ext4_handle_dirty_dirblock(handle, dir, bh);
        if (err)
                ext4_std_error(dir->i_sb, err);
        return err ? err : err2;
}

/*
 * This converts a one block unindexed directory to a 3 block indexed
 * directory, and adds the dentry to the indexed directory.
 */
static int make_indexed_dir(handle_t *handle, struct ext4_filename *fname,
                            struct inode *dir,
                            struct inode *inode, struct buffer_head *bh)
{
        struct buffer_head *bh2;
        struct dx_root  *root;
        struct dx_frame frames[EXT4_HTREE_LEVEL], *frame;
        struct dx_entry *entries;
        struct ext4_dir_entry_2 *de, *de2;
        char            *data2, *top;
        unsigned        len;
        int             retval;
        unsigned        blocksize;
        ext4_lblk_t  block;
        struct fake_dirent *fde;
        int csum_size = 0;

        if (ext4_has_metadata_csum(inode->i_sb))
                csum_size = sizeof(struct ext4_dir_entry_tail);

        blocksize =  dir->i_sb->s_blocksize;
        dxtrace(printk(KERN_DEBUG "Creating index: inode %lu\n", dir->i_ino));
        BUFFER_TRACE(bh, "get_write_access");
        retval = ext4_journal_get_write_access(handle, dir->i_sb, bh,
                                               EXT4_JTR_NONE);
        if (retval) {
                ext4_std_error(dir->i_sb, retval);
                brelse(bh);
                return retval;
        }
        root = (struct dx_root *) bh->b_data;

        /* The 0th block becomes the root, move the dirents out */
        fde = &root->dotdot;
        de = (struct ext4_dir_entry_2 *)((char *)fde +
                ext4_rec_len_from_disk(fde->rec_len, blocksize));
        if ((char *) de >= (((char *) root) + blocksize)) {
                EXT4_ERROR_INODE(dir, "invalid rec_len for '..'");
                brelse(bh);
                return -EFSCORRUPTED;
        }
        len = ((char *) root) + (blocksize - csum_size) - (char *) de;

        /* Allocate new block for the 0th block's dirents */
        bh2 = ext4_append(handle, dir, &block);
        if (IS_ERR(bh2)) {
                brelse(bh);
                return PTR_ERR(bh2);
        }
        ext4_set_inode_flag(dir, EXT4_INODE_INDEX);
        data2 = bh2->b_data;

        memcpy(data2, de, len);
        memset(de, 0, len); /* wipe old data */
        de = (struct ext4_dir_entry_2 *) data2;
        top = data2 + len;
        while ((char *)(de2 = ext4_next_entry(de, blocksize)) < top)
                de = de2;
        de->rec_len = ext4_rec_len_to_disk(data2 + (blocksize - csum_size) -
                                           (char *) de, blocksize);

        if (csum_size)
                ext4_initialize_dirent_tail(bh2, blocksize);

        /* Initialize the root; the dot dirents already exist */
        de = (struct ext4_dir_entry_2 *) (&root->dotdot);
        de->rec_len = ext4_rec_len_to_disk(
                        blocksize - ext4_dir_rec_len(2, NULL), blocksize);
        memset (&root->info, 0, sizeof(root->info));
        root->info.info_length = sizeof(root->info);
        if (ext4_hash_in_dirent(dir))
                root->info.hash_version = DX_HASH_SIPHASH;
        else
                root->info.hash_version =
                                EXT4_SB(dir->i_sb)->s_def_hash_version;

        entries = root->entries;
        dx_set_block(entries, 1);
        dx_set_count(entries, 1);
        dx_set_limit(entries, dx_root_limit(dir, sizeof(root->info)));

        /* Initialize as for dx_probe */
        fname->hinfo.hash_version = root->info.hash_version;
        if (fname->hinfo.hash_version <= DX_HASH_TEA)
                fname->hinfo.hash_version += EXT4_SB(dir->i_sb)->s_hash_unsigned;
        fname->hinfo.seed = EXT4_SB(dir->i_sb)->s_hash_seed;

        /* casefolded encrypted hashes are computed on fname setup */
        if (!ext4_hash_in_dirent(dir))
                ext4fs_dirhash(dir, fname_name(fname),
                                fname_len(fname), &fname->hinfo);

        memset(frames, 0, sizeof(frames));
        frame = frames;
        frame->entries = entries;
        frame->at = entries;
        frame->bh = bh;

        retval = ext4_handle_dirty_dx_node(handle, dir, frame->bh);
        if (retval)
                goto out_frames;
        retval = ext4_handle_dirty_dirblock(handle, dir, bh2);
        if (retval)
                goto out_frames;

        de = do_split(handle,dir, &bh2, frame, &fname->hinfo);
        if (IS_ERR(de)) {
                retval = PTR_ERR(de);
                goto out_frames;
        }

        retval = add_dirent_to_buf(handle, fname, dir, inode, de, bh2);
out_frames:
        /*
         * Even if the block split failed, we have to properly write
         * out all the changes we did so far. Otherwise we can end up
         * with corrupted filesystem.
         */
        if (retval)
                ext4_mark_inode_dirty(handle, dir);
        dx_release(frames);
        brelse(bh2);
        return retval;
}

/*
 *      ext4_add_entry()
 *
 * adds a file entry to the specified directory, using the same
 * semantics as ext4_find_entry(). It returns NULL if it failed.
 *
 * NOTE!! The inode part of 'de' is left at 0 - which means you
 * may not sleep between calling this and putting something into
 * the entry, as someone else might have used it while you slept.
 */
static int ext4_add_entry(handle_t *handle, struct dentry *dentry,
                          struct inode *inode)
{
        struct inode *dir = d_inode(dentry->d_parent);
        struct buffer_head *bh = NULL;
        struct ext4_dir_entry_2 *de;
        struct super_block *sb;
        struct ext4_filename fname;
        int     retval;
        int     dx_fallback=0;
        unsigned blocksize;
        ext4_lblk_t block, blocks;
        int     csum_size = 0;

        if (ext4_has_metadata_csum(inode->i_sb))
                csum_size = sizeof(struct ext4_dir_entry_tail);

        sb = dir->i_sb;
        blocksize = sb->s_blocksize;
        if (!dentry->d_name.len)
                return -EINVAL;

        if (fscrypt_is_nokey_name(dentry))
                return -ENOKEY;

#ifdef CONFIG_UNICODE
        if (sb_has_strict_encoding(sb) && IS_CASEFOLDED(dir) &&
            sb->s_encoding && utf8_validate(sb->s_encoding, &dentry->d_name))
                return -EINVAL;
#endif

        retval = ext4_fname_setup_filename(dir, &dentry->d_name, 0, &fname);
        if (retval)
                return retval;

        if (ext4_has_inline_data(dir)) {
                retval = ext4_try_add_inline_entry(handle, &fname, dir, inode);
                if (retval < 0)
                        goto out;
                if (retval == 1) {
                        retval = 0;
                        goto out;
                }
        }

        if (is_dx(dir)) {
                retval = ext4_dx_add_entry(handle, &fname, dir, inode);
                if (!retval || (retval != ERR_BAD_DX_DIR))
                        goto out;
                /* Can we just ignore htree data? */
                if (ext4_has_metadata_csum(sb)) {
                        EXT4_ERROR_INODE(dir,
                                "Directory has corrupted htree index.");
                        retval = -EFSCORRUPTED;
                        goto out;
                }
                ext4_clear_inode_flag(dir, EXT4_INODE_INDEX);
                dx_fallback++;
                retval = ext4_mark_inode_dirty(handle, dir);
                if (unlikely(retval))
                        goto out;
        }
        blocks = dir->i_size >> sb->s_blocksize_bits;
        for (block = 0; block < blocks; block++) {
                bh = ext4_read_dirblock(dir, block, DIRENT);
                if (bh == NULL) {
                        bh = ext4_bread(handle, dir, block,
                                        EXT4_GET_BLOCKS_CREATE);
                        goto add_to_new_block;
                }
                if (IS_ERR(bh)) {
                        retval = PTR_ERR(bh);
                        bh = NULL;
                        goto out;
                }
                retval = add_dirent_to_buf(handle, &fname, dir, inode,
                                           NULL, bh);
                if (retval != -ENOSPC)
                        goto out;

                if (blocks == 1 && !dx_fallback &&
                    ext4_has_feature_dir_index(sb)) {
                        retval = make_indexed_dir(handle, &fname, dir,
                                                  inode, bh);
                        bh = NULL; /* make_indexed_dir releases bh */
                        goto out;
                }
                brelse(bh);
        }
        bh = ext4_append(handle, dir, &block);
add_to_new_block:
        if (IS_ERR(bh)) {
                retval = PTR_ERR(bh);
                bh = NULL;
                goto out;
        }
        de = (struct ext4_dir_entry_2 *) bh->b_data;
        de->inode = 0;
        de->rec_len = ext4_rec_len_to_disk(blocksize - csum_size, blocksize);

        if (csum_size)
                ext4_initialize_dirent_tail(bh, blocksize);

        retval = add_dirent_to_buf(handle, &fname, dir, inode, de, bh);
out:
        ext4_fname_free_filename(&fname);
        brelse(bh);
        if (retval == 0)
                ext4_set_inode_state(inode, EXT4_STATE_NEWENTRY);
        return retval;
}

/*
 * Returns 0 for success, or a negative error value
 */
static int ext4_dx_add_entry(handle_t *handle, struct ext4_filename *fname,
                             struct inode *dir, struct inode *inode)
{
        struct dx_frame frames[EXT4_HTREE_LEVEL], *frame;
        struct dx_entry *entries, *at;
        struct buffer_head *bh;
        struct super_block *sb = dir->i_sb;
        struct ext4_dir_entry_2 *de;
        int restart;
        int err;

again:
        restart = 0;
        frame = dx_probe(fname, dir, NULL, frames);
        if (IS_ERR(frame))
                return PTR_ERR(frame);
        entries = frame->entries;
        at = frame->at;
        bh = ext4_read_dirblock(dir, dx_get_block(frame->at), DIRENT_HTREE);
        if (IS_ERR(bh)) {
                err = PTR_ERR(bh);
                bh = NULL;
                goto cleanup;
        }

        BUFFER_TRACE(bh, "get_write_access");
        err = ext4_journal_get_write_access(handle, sb, bh, EXT4_JTR_NONE);
        if (err)
                goto journal_error;

        err = add_dirent_to_buf(handle, fname, dir, inode, NULL, bh);
        if (err != -ENOSPC)
                goto cleanup;

        err = 0;
        /* Block full, should compress but for now just split */
        dxtrace(printk(KERN_DEBUG "using %u of %u node entries\n",
                       dx_get_count(entries), dx_get_limit(entries)));
        /* Need to split index? */
        if (dx_get_count(entries) == dx_get_limit(entries)) {
                ext4_lblk_t newblock;
                int levels = frame - frames + 1;
                unsigned int icount;
                int add_level = 1;
                struct dx_entry *entries2;
                struct dx_node *node2;
                struct buffer_head *bh2;

                while (frame > frames) {
                        if (dx_get_count((frame - 1)->entries) <
                            dx_get_limit((frame - 1)->entries)) {
                                add_level = 0;
                                break;
                        }
                        frame--; /* split higher index block */
                        at = frame->at;
                        entries = frame->entries;
                        restart = 1;
                }
                if (add_level && levels == ext4_dir_htree_level(sb)) {
                        ext4_warning(sb, "Directory (ino: %lu) index full, "
                                         "reach max htree level :%d",
                                         dir->i_ino, levels);
                        if (ext4_dir_htree_level(sb) < EXT4_HTREE_LEVEL) {
                                ext4_warning(sb, "Large directory feature is "
                                                 "not enabled on this "
                                                 "filesystem");
                        }
                        err = -ENOSPC;
                        goto cleanup;
                }
                icount = dx_get_count(entries);
                bh2 = ext4_append(handle, dir, &newblock);
                if (IS_ERR(bh2)) {
                        err = PTR_ERR(bh2);
                        goto cleanup;
                }
                node2 = (struct dx_node *)(bh2->b_data);
                entries2 = node2->entries;
                memset(&node2->fake, 0, sizeof(struct fake_dirent));
                node2->fake.rec_len = ext4_rec_len_to_disk(sb->s_blocksize,
                                                           sb->s_blocksize);
                BUFFER_TRACE(frame->bh, "get_write_access");
                err = ext4_journal_get_write_access(handle, sb, frame->bh,
                                                    EXT4_JTR_NONE);
                if (err)
                        goto journal_error;
                if (!add_level) {
                        unsigned icount1 = icount/2, icount2 = icount - icount1;
                        unsigned hash2 = dx_get_hash(entries + icount1);
                        dxtrace(printk(KERN_DEBUG "Split index %i/%i\n",
                                       icount1, icount2));

                        BUFFER_TRACE(frame->bh, "get_write_access"); /* index root */
                        err = ext4_journal_get_write_access(handle, sb,
                                                            (frame - 1)->bh,
                                                            EXT4_JTR_NONE);
                        if (err)
                                goto journal_error;

                        memcpy((char *) entries2, (char *) (entries + icount1),
                               icount2 * sizeof(struct dx_entry));
                        dx_set_count(entries, icount1);
                        dx_set_count(entries2, icount2);
                        dx_set_limit(entries2, dx_node_limit(dir));

                        /* Which index block gets the new entry? */
                        if (at - entries >= icount1) {
                                frame->at = at - entries - icount1 + entries2;
                                frame->entries = entries = entries2;
                                swap(frame->bh, bh2);
                        }
                        dx_insert_block((frame - 1), hash2, newblock);
                        dxtrace(dx_show_index("node", frame->entries));
                        dxtrace(dx_show_index("node",
                               ((struct dx_node *) bh2->b_data)->entries));
                        err = ext4_handle_dirty_dx_node(handle, dir, bh2);
                        if (err)
                                goto journal_error;
                        brelse (bh2);
                        err = ext4_handle_dirty_dx_node(handle, dir,
                                                   (frame - 1)->bh);
                        if (err)
                                goto journal_error;
                        err = ext4_handle_dirty_dx_node(handle, dir,
                                                        frame->bh);
                        if (restart || err)
                                goto journal_error;
                } else {
                        struct dx_root *dxroot;
                        memcpy((char *) entries2, (char *) entries,
                               icount * sizeof(struct dx_entry));
                        dx_set_limit(entries2, dx_node_limit(dir));

                        /* Set up root */
                        dx_set_count(entries, 1);
                        dx_set_block(entries + 0, newblock);
                        dxroot = (struct dx_root *)frames[0].bh->b_data;
                        dxroot->info.indirect_levels += 1;
                        dxtrace(printk(KERN_DEBUG
                                       "Creating %d level index...\n",
                                       dxroot->info.indirect_levels));
                        err = ext4_handle_dirty_dx_node(handle, dir, frame->bh);
                        if (err)
                                goto journal_error;
                        err = ext4_handle_dirty_dx_node(handle, dir, bh2);
                        brelse(bh2);
                        restart = 1;
                        goto journal_error;
                }
        }
        de = do_split(handle, dir, &bh, frame, &fname->hinfo);
        if (IS_ERR(de)) {
                err = PTR_ERR(de);
                goto cleanup;
        }
        err = add_dirent_to_buf(handle, fname, dir, inode, de, bh);
        goto cleanup;

journal_error:
        ext4_std_error(dir->i_sb, err); /* this is a no-op if err == 0 */
cleanup:
        brelse(bh);
        dx_release(frames);
        /* @restart is true means htree-path has been changed, we need to
         * repeat dx_probe() to find out valid htree-path
         */
        if (restart && err == 0)
                goto again;
        return err;
}

/*
 * ext4_generic_delete_entry deletes a directory entry by merging it
 * with the previous entry
 */
int ext4_generic_delete_entry(struct inode *dir,
                              struct ext4_dir_entry_2 *de_del,
                              struct buffer_head *bh,
                              void *entry_buf,
                              int buf_size,
                              int csum_size)
{
        struct ext4_dir_entry_2 *de, *pde;
        unsigned int blocksize = dir->i_sb->s_blocksize;
        int i;

        i = 0;
        pde = NULL;
        de = (struct ext4_dir_entry_2 *)entry_buf;
        while (i < buf_size - csum_size) {
                if (ext4_check_dir_entry(dir, NULL, de, bh,
                                         entry_buf, buf_size, i))
                        return -EFSCORRUPTED;
                if (de == de_del)  {
                        if (pde) {
                                pde->rec_len = ext4_rec_len_to_disk(
                                        ext4_rec_len_from_disk(pde->rec_len,
                                                               blocksize) +
                                        ext4_rec_len_from_disk(de->rec_len,
                                                               blocksize),
                                        blocksize);

                                /* wipe entire dir_entry */
                                memset(de, 0, ext4_rec_len_from_disk(de->rec_len,
                                                                blocksize));
                        } else {
                                /* wipe dir_entry excluding the rec_len field */
                                de->inode = 0;
                                memset(&de->name_len, 0,
                                        ext4_rec_len_from_disk(de->rec_len,
                                                                blocksize) -
                                        offsetof(struct ext4_dir_entry_2,
                                                                name_len));
                        }

                        inode_inc_iversion(dir);
                        return 0;
                }
                i += ext4_rec_len_from_disk(de->rec_len, blocksize);
                pde = de;
                de = ext4_next_entry(de, blocksize);
        }
        return -ENOENT;
}

static int ext4_delete_entry(handle_t *handle,
                             struct inode *dir,
                             struct ext4_dir_entry_2 *de_del,
                             struct buffer_head *bh)
{
        int err, csum_size = 0;

        if (ext4_has_inline_data(dir)) {
                int has_inline_data = 1;
                err = ext4_delete_inline_entry(handle, dir, de_del, bh,
                                               &has_inline_data);
                if (has_inline_data)
                        return err;
        }

        if (ext4_has_metadata_csum(dir->i_sb))
                csum_size = sizeof(struct ext4_dir_entry_tail);

        BUFFER_TRACE(bh, "get_write_access");
        err = ext4_journal_get_write_access(handle, dir->i_sb, bh,
                                            EXT4_JTR_NONE);
        if (unlikely(err))
                goto out;

        err = ext4_generic_delete_entry(dir, de_del, bh, bh->b_data,
                                        dir->i_sb->s_blocksize, csum_size);
        if (err)
                goto out;

        BUFFER_TRACE(bh, "call ext4_handle_dirty_metadata");
        err = ext4_handle_dirty_dirblock(handle, dir, bh);
        if (unlikely(err))
                goto out;

        return 0;
out:
        if (err != -ENOENT)
                ext4_std_error(dir->i_sb, err);
        return err;
}

/*
 * Set directory link count to 1 if nlinks > EXT4_LINK_MAX, or if nlinks == 2
 * since this indicates that nlinks count was previously 1 to avoid overflowing
 * the 16-bit i_links_count field on disk.  Directories with i_nlink == 1 mean
 * that subdirectory link counts are not being maintained accurately.
 *
 * The caller has already checked for i_nlink overflow in case the DIR_LINK
 * feature is not enabled and returned -EMLINK.  The is_dx() check is a proxy
 * for checking S_ISDIR(inode) (since the INODE_INDEX feature will not be set
 * on regular files) and to avoid creating huge/slow non-HTREE directories.
 */
static void ext4_inc_count(struct inode *inode)
{
        inc_nlink(inode);
        if (is_dx(inode) &&
            (inode->i_nlink > EXT4_LINK_MAX || inode->i_nlink == 2))
                set_nlink(inode, 1);
}

/*
 * If a directory had nlink == 1, then we should let it be 1. This indicates
 * directory has >EXT4_LINK_MAX subdirs.
 */
static void ext4_dec_count(struct inode *inode)
{
        if (!S_ISDIR(inode->i_mode) || inode->i_nlink > 2)
                drop_nlink(inode);
}


/*
 * Add non-directory inode to a directory. On success, the inode reference is
 * consumed by dentry is instantiation. This is also indicated by clearing of
 * *inodep pointer. On failure, the caller is responsible for dropping the
 * inode reference in the safe context.
 */
static int ext4_add_nondir(handle_t *handle,
                struct dentry *dentry, struct inode **inodep)
{
        struct inode *dir = d_inode(dentry->d_parent);
        struct inode *inode = *inodep;
        int err = ext4_add_entry(handle, dentry, inode);
        if (!err) {
                err = ext4_mark_inode_dirty(handle, inode);
                if (IS_DIRSYNC(dir))
                        ext4_handle_sync(handle);
                d_instantiate_new(dentry, inode);
                *inodep = NULL;
                return err;
        }
        drop_nlink(inode);
        ext4_orphan_add(handle, inode);
        unlock_new_inode(inode);
        return err;
}

/*
 * By the time this is called, we already have created
 * the directory cache entry for the new file, but it
 * is so far negative - it has no inode.
 *
 * If the create succeeds, we fill in the inode information
 * with d_instantiate().
 */
static int ext4_create(struct user_namespace *mnt_userns, struct inode *dir,
                       struct dentry *dentry, umode_t mode, bool excl)
{
        handle_t *handle;
        struct inode *inode;
        int err, credits, retries = 0;

        err = dquot_initialize(dir);
        if (err)
                return err;

        credits = (EXT4_DATA_TRANS_BLOCKS(dir->i_sb) +
                   EXT4_INDEX_EXTRA_TRANS_BLOCKS + 3);
retry:
        inode = ext4_new_inode_start_handle(mnt_userns, dir, mode, &dentry->d_name,
                                            0, NULL, EXT4_HT_DIR, credits);
        handle = ext4_journal_current_handle();
        err = PTR_ERR(inode);
        if (!IS_ERR(inode)) {
                inode->i_op = &ext4_file_inode_operations;
                inode->i_fop = &ext4_file_operations;
                ext4_set_aops(inode);
                err = ext4_add_nondir(handle, dentry, &inode);
                if (!err)
                        ext4_fc_track_create(handle, dentry);
        }
        if (handle)
                ext4_journal_stop(handle);
        if (!IS_ERR_OR_NULL(inode))
                iput(inode);
        if (err == -ENOSPC && ext4_should_retry_alloc(dir->i_sb, &retries))
                goto retry;
        return err;
}

static int ext4_mknod(struct user_namespace *mnt_userns, struct inode *dir,
                      struct dentry *dentry, umode_t mode, dev_t rdev)
{
        handle_t *handle;
        struct inode *inode;
        int err, credits, retries = 0;

        err = dquot_initialize(dir);
        if (err)
                return err;

        credits = (EXT4_DATA_TRANS_BLOCKS(dir->i_sb) +
                   EXT4_INDEX_EXTRA_TRANS_BLOCKS + 3);
retry:
        inode = ext4_new_inode_start_handle(mnt_userns, dir, mode, &dentry->d_name,
                                            0, NULL, EXT4_HT_DIR, credits);
        handle = ext4_journal_current_handle();
        err = PTR_ERR(inode);
        if (!IS_ERR(inode)) {
                init_special_inode(inode, inode->i_mode, rdev);
                inode->i_op = &ext4_special_inode_operations;
                err = ext4_add_nondir(handle, dentry, &inode);
                if (!err)
                        ext4_fc_track_create(handle, dentry);
        }
        if (handle)
                ext4_journal_stop(handle);
        if (!IS_ERR_OR_NULL(inode))
                iput(inode);
        if (err == -ENOSPC && ext4_should_retry_alloc(dir->i_sb, &retries))
                goto retry;
        return err;
}

static int ext4_tmpfile(struct user_namespace *mnt_userns, struct inode *dir,
                        struct dentry *dentry, umode_t mode)
{
        handle_t *handle;
        struct inode *inode;
        int err, retries = 0;

        err = dquot_initialize(dir);
        if (err)
                return err;

retry:
        inode = ext4_new_inode_start_handle(mnt_userns, dir, mode,
                                            NULL, 0, NULL,
                                            EXT4_HT_DIR,
                        EXT4_MAXQUOTAS_INIT_BLOCKS(dir->i_sb) +
                          4 + EXT4_XATTR_TRANS_BLOCKS);
        handle = ext4_journal_current_handle();
        err = PTR_ERR(inode);
        if (!IS_ERR(inode)) {
                inode->i_op = &ext4_file_inode_operations;
                inode->i_fop = &ext4_file_operations;
                ext4_set_aops(inode);
                d_tmpfile(dentry, inode);
                err = ext4_orphan_add(handle, inode);
                if (err)
                        goto err_unlock_inode;
                mark_inode_dirty(inode);
                unlock_new_inode(inode);
        }
        if (handle)
                ext4_journal_stop(handle);
        if (err == -ENOSPC && ext4_should_retry_alloc(dir->i_sb, &retries))
                goto retry;
        return err;
err_unlock_inode:
        ext4_journal_stop(handle);
        unlock_new_inode(inode);
        return err;
}

struct ext4_dir_entry_2 *ext4_init_dot_dotdot(struct inode *inode,
                          struct ext4_dir_entry_2 *de,
                          int blocksize, int csum_size,
                          unsigned int parent_ino, int dotdot_real_len)
{
        de->inode = cpu_to_le32(inode->i_ino);
        de->name_len = 1;
        de->rec_len = ext4_rec_len_to_disk(ext4_dir_rec_len(de->name_len, NULL),
                                           blocksize);
        strcpy(de->name, ".");
        ext4_set_de_type(inode->i_sb, de, S_IFDIR);

        de = ext4_next_entry(de, blocksize);
        de->inode = cpu_to_le32(parent_ino);
        de->name_len = 2;
        if (!dotdot_real_len)
                de->rec_len = ext4_rec_len_to_disk(blocksize -
                                        (csum_size + ext4_dir_rec_len(1, NULL)),
                                        blocksize);
        else
                de->rec_len = ext4_rec_len_to_disk(
                                        ext4_dir_rec_len(de->name_len, NULL),
                                        blocksize);
        strcpy(de->name, "..");
        ext4_set_de_type(inode->i_sb, de, S_IFDIR);

        return ext4_next_entry(de, blocksize);
}

int ext4_init_new_dir(handle_t *handle, struct inode *dir,
                             struct inode *inode)
{
        struct buffer_head *dir_block = NULL;
        struct ext4_dir_entry_2 *de;
        ext4_lblk_t block = 0;
        unsigned int blocksize = dir->i_sb->s_blocksize;
        int csum_size = 0;
        int err;

        if (ext4_has_metadata_csum(dir->i_sb))
                csum_size = sizeof(struct ext4_dir_entry_tail);

        if (ext4_test_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA)) {
                err = ext4_try_create_inline_dir(handle, dir, inode);
                if (err < 0 && err != -ENOSPC)
                        goto out;
                if (!err)
                        goto out;
        }

        inode->i_size = 0;
        dir_block = ext4_append(handle, inode, &block);
        if (IS_ERR(dir_block))
                return PTR_ERR(dir_block);
        de = (struct ext4_dir_entry_2 *)dir_block->b_data;
        ext4_init_dot_dotdot(inode, de, blocksize, csum_size, dir->i_ino, 0);
        set_nlink(inode, 2);
        if (csum_size)
                ext4_initialize_dirent_tail(dir_block, blocksize);

        BUFFER_TRACE(dir_block, "call ext4_handle_dirty_metadata");
        err = ext4_handle_dirty_dirblock(handle, inode, dir_block);
        if (err)
                goto out;
        set_buffer_verified(dir_block);
out:
        brelse(dir_block);
        return err;
}

static int ext4_mkdir(struct user_namespace *mnt_userns, struct inode *dir,
                      struct dentry *dentry, umode_t mode)
{
        handle_t *handle;
        struct inode *inode;
        int err, err2 = 0, credits, retries = 0;

        if (EXT4_DIR_LINK_MAX(dir))
                return -EMLINK;

        err = dquot_initialize(dir);
        if (err)
                return err;

        credits = (EXT4_DATA_TRANS_BLOCKS(dir->i_sb) +
                   EXT4_INDEX_EXTRA_TRANS_BLOCKS + 3);
retry:
        inode = ext4_new_inode_start_handle(mnt_userns, dir, S_IFDIR | mode,
                                            &dentry->d_name,
                                            0, NULL, EXT4_HT_DIR, credits);
        handle = ext4_journal_current_handle();
        err = PTR_ERR(inode);
        if (IS_ERR(inode))
                goto out_stop;

        inode->i_op = &ext4_dir_inode_operations;
        inode->i_fop = &ext4_dir_operations;
        err = ext4_init_new_dir(handle, dir, inode);
        if (err)
                goto out_clear_inode;
        err = ext4_mark_inode_dirty(handle, inode);
        if (!err)
                err = ext4_add_entry(handle, dentry, inode);
        if (err) {
out_clear_inode:
                clear_nlink(inode);
                ext4_orphan_add(handle, inode);
                unlock_new_inode(inode);
                err2 = ext4_mark_inode_dirty(handle, inode);
                if (unlikely(err2))
                        err = err2;
                ext4_journal_stop(handle);
                iput(inode);
                goto out_retry;
        }
        ext4_inc_count(dir);

        ext4_update_dx_flag(dir);
        err = ext4_mark_inode_dirty(handle, dir);
        if (err)
                goto out_clear_inode;
        d_instantiate_new(dentry, inode);
        ext4_fc_track_create(handle, dentry);
        if (IS_DIRSYNC(dir))
                ext4_handle_sync(handle);

out_stop:
        if (handle)
                ext4_journal_stop(handle);
out_retry:
        if (err == -ENOSPC && ext4_should_retry_alloc(dir->i_sb, &retries))
                goto retry;
        return err;
}

/*
 * routine to check that the specified directory is empty (for rmdir)
 */
bool ext4_empty_dir(struct inode *inode)
{
        unsigned int offset;
        struct buffer_head *bh;
        struct ext4_dir_entry_2 *de;
        struct super_block *sb;

        if (ext4_has_inline_data(inode)) {
                int has_inline_data = 1;
                int ret;

                ret = empty_inline_dir(inode, &has_inline_data);
                if (has_inline_data)
                        return ret;
        }

        sb = inode->i_sb;
        if (inode->i_size < ext4_dir_rec_len(1, NULL) +
                                        ext4_dir_rec_len(2, NULL)) {
                EXT4_ERROR_INODE(inode, "invalid size");
                return true;