attrib.c

Go to the documentation of this file.

#include <linux/buffer_head.h>
#include <linux/sched.h>
#include <linux/slab.h>
#include <linux/swap.h>
#include <linux/writeback.h>

#include "attrib.h"
#include "debug.h"
#include "layout.h"
#include "lcnalloc.h"
#include "malloc.h"
#include "mft.h"
#include "ntfs.h"
#include "types.h"

int ntfs_map_runlist_nolock(ntfs_inode *ni, VCN vcn, ntfs_attr_search_ctx *ctx)
{
    VCN end_vcn;
    unsigned long flags;
    ntfs_inode *base_ni;
    MFT_RECORD *m;
    ATTR_RECORD *a;
    runlist_element *rl;
    struct page *put_this_page = NULL;
    int err = 0;
    bool ctx_is_temporary, ctx_needs_reset;
    ntfs_attr_search_ctx old_ctx = { NULL, };

    ntfs_debug("Mapping runlist part containing vcn 0x%llx.",
            (unsigned long long)vcn);
    if (!NInoAttr(ni))
        base_ni = ni;
    else
        base_ni = ni->ext.base_ntfs_ino;
    if (!ctx) {
        ctx_is_temporary = ctx_needs_reset = true;
        m = map_mft_record(base_ni);
        if (IS_ERR(m))
            return PTR_ERR(m);
        ctx = ntfs_attr_get_search_ctx(base_ni, m);
        if (unlikely(!ctx)) {
            err = -ENOMEM;
            goto err_out;
        }
    } else {
        VCN allocated_size_vcn;

        BUG_ON(IS_ERR(ctx->mrec));
        a = ctx->attr;
        BUG_ON(!a->non_resident);
        ctx_is_temporary = false;
        end_vcn = sle64_to_cpu(a->data.non_resident.highest_vcn);
        read_lock_irqsave(&ni->size_lock, flags);
        allocated_size_vcn = ni->allocated_size >>
                ni->vol->cluster_size_bits;
        read_unlock_irqrestore(&ni->size_lock, flags);
        if (!a->data.non_resident.lowest_vcn && end_vcn <= 0)
            end_vcn = allocated_size_vcn - 1;
        /*
         * If we already have the attribute extent containing @vcn in
         * @ctx, no need to look it up again.  We slightly cheat in
         * that if vcn exceeds the allocated size, we will refuse to
         * map the runlist below, so there is definitely no need to get
         * the right attribute extent.
         */
        if (vcn >= allocated_size_vcn || (a->type == ni->type &&
                a->name_length == ni->name_len &&
                !memcmp((u8*)a + le16_to_cpu(a->name_offset),
                ni->name, ni->name_len) &&
                sle64_to_cpu(a->data.non_resident.lowest_vcn)
                <= vcn && end_vcn >= vcn))
            ctx_needs_reset = false;
        else {
            /* Save the old search context. */
            old_ctx = *ctx;
            /*
             * If the currently mapped (extent) inode is not the
             * base inode we will unmap it when we reinitialize the
             * search context which means we need to get a
             * reference to the page containing the mapped mft
             * record so we do not accidentally drop changes to the
             * mft record when it has not been marked dirty yet.
             */
            if (old_ctx.base_ntfs_ino && old_ctx.ntfs_ino !=
                    old_ctx.base_ntfs_ino) {
                put_this_page = old_ctx.ntfs_ino->page;
                page_cache_get(put_this_page);
            }
            /*
             * Reinitialize the search context so we can lookup the
             * needed attribute extent.
             */
            ntfs_attr_reinit_search_ctx(ctx);
            ctx_needs_reset = true;
        }
    }
    if (ctx_needs_reset) {
        err = ntfs_attr_lookup(ni->type, ni->name, ni->name_len,
                CASE_SENSITIVE, vcn, NULL, 0, ctx);
        if (unlikely(err)) {
            if (err == -ENOENT)
                err = -EIO;
            goto err_out;
        }
        BUG_ON(!ctx->attr->non_resident);
    }
    a = ctx->attr;
    /*
     * Only decompress the mapping pairs if @vcn is inside it.  Otherwise
     * we get into problems when we try to map an out of bounds vcn because
     * we then try to map the already mapped runlist fragment and
     * ntfs_mapping_pairs_decompress() fails.
     */
    end_vcn = sle64_to_cpu(a->data.non_resident.highest_vcn) + 1;
    if (unlikely(vcn && vcn >= end_vcn)) {
        err = -ENOENT;
        goto err_out;
    }
    rl = ntfs_mapping_pairs_decompress(ni->vol, a, ni->runlist.rl);
    if (IS_ERR(rl))
        err = PTR_ERR(rl);
    else
        ni->runlist.rl = rl;
err_out:
    if (ctx_is_temporary) {
        if (likely(ctx))
            ntfs_attr_put_search_ctx(ctx);
        unmap_mft_record(base_ni);
    } else if (ctx_needs_reset) {
        /*
         * If there is no attribute list, restoring the search context
         * is accomplished simply by copying the saved context back over
         * the caller supplied context.  If there is an attribute list,
         * things are more complicated as we need to deal with mapping
         * of mft records and resulting potential changes in pointers.
         */
        if (NInoAttrList(base_ni)) {
            /*
             * If the currently mapped (extent) inode is not the
             * one we had before, we need to unmap it and map the
             * old one.
             */
            if (ctx->ntfs_ino != old_ctx.ntfs_ino) {
                /*
                 * If the currently mapped inode is not the
                 * base inode, unmap it.
                 */
                if (ctx->base_ntfs_ino && ctx->ntfs_ino !=
                        ctx->base_ntfs_ino) {
                    unmap_extent_mft_record(ctx->ntfs_ino);
                    ctx->mrec = ctx->base_mrec;
                    BUG_ON(!ctx->mrec);
                }
                /*
                 * If the old mapped inode is not the base
                 * inode, map it.
                 */
                if (old_ctx.base_ntfs_ino &&
                        old_ctx.ntfs_ino !=
                        old_ctx.base_ntfs_ino) {
retry_map:
                    ctx->mrec = map_mft_record(
                            old_ctx.ntfs_ino);
                    /*
                     * Something bad has happened.  If out
                     * of memory retry till it succeeds.
                     * Any other errors are fatal and we
                     * return the error code in ctx->mrec.
                     * Let the caller deal with it...  We
                     * just need to fudge things so the
                     * caller can reinit and/or put the
                     * search context safely.
                     */
                    if (IS_ERR(ctx->mrec)) {
                        if (PTR_ERR(ctx->mrec) ==
                                -ENOMEM) {
                            schedule();
                            goto retry_map;
                        } else
                            old_ctx.ntfs_ino =
                                old_ctx.
                                base_ntfs_ino;
                    }
                }
            }
            /* Update the changed pointers in the saved context. */
            if (ctx->mrec != old_ctx.mrec) {
                if (!IS_ERR(ctx->mrec))
                    old_ctx.attr = (ATTR_RECORD*)(
                            (u8*)ctx->mrec +
                            ((u8*)old_ctx.attr -
                            (u8*)old_ctx.mrec));
                old_ctx.mrec = ctx->mrec;
            }
        }
        /* Restore the search context to the saved one. */
        *ctx = old_ctx;
        /*
         * We drop the reference on the page we took earlier.  In the
         * case that IS_ERR(ctx->mrec) is true this means we might lose
         * some changes to the mft record that had been made between
         * the last time it was marked dirty/written out and now.  This
         * at this stage is not a problem as the mapping error is fatal
         * enough that the mft record cannot be written out anyway and
         * the caller is very likely to shutdown the whole inode
         * immediately and mark the volume dirty for chkdsk to pick up
         * the pieces anyway.
         */
        if (put_this_page)
            page_cache_release(put_this_page);
    }
    return err;
}

int ntfs_map_runlist(ntfs_inode *ni, VCN vcn)
{
    int err = 0;

    down_write(&ni->runlist.lock);
    /* Make sure someone else didn't do the work while we were sleeping. */
    if (likely(ntfs_rl_vcn_to_lcn(ni->runlist.rl, vcn) <=
            LCN_RL_NOT_MAPPED))
        err = ntfs_map_runlist_nolock(ni, vcn, NULL);
    up_write(&ni->runlist.lock);
    return err;
}

LCN ntfs_attr_vcn_to_lcn_nolock(ntfs_inode *ni, const VCN vcn,
        const bool write_locked)
{
    LCN lcn;
    unsigned long flags;
    bool is_retry = false;

    BUG_ON(!ni);
    ntfs_debug("Entering for i_ino 0x%lx, vcn 0x%llx, %s_locked.",
            ni->mft_no, (unsigned long long)vcn,
            write_locked ? "write" : "read");
    BUG_ON(!NInoNonResident(ni));
    BUG_ON(vcn < 0);
    if (!ni->runlist.rl) {
        read_lock_irqsave(&ni->size_lock, flags);
        if (!ni->allocated_size) {
            read_unlock_irqrestore(&ni->size_lock, flags);
            return LCN_ENOENT;
        }
        read_unlock_irqrestore(&ni->size_lock, flags);
    }
retry_remap:
    /* Convert vcn to lcn.  If that fails map the runlist and retry once. */
    lcn = ntfs_rl_vcn_to_lcn(ni->runlist.rl, vcn);
    if (likely(lcn >= LCN_HOLE)) {
        ntfs_debug("Done, lcn 0x%llx.", (long long)lcn);
        return lcn;
    }
    if (lcn != LCN_RL_NOT_MAPPED) {
        if (lcn != LCN_ENOENT)
            lcn = LCN_EIO;
    } else if (!is_retry) {
        int err;

        if (!write_locked) {
            up_read(&ni->runlist.lock);
            down_write(&ni->runlist.lock);
            if (unlikely(ntfs_rl_vcn_to_lcn(ni->runlist.rl, vcn) !=
                    LCN_RL_NOT_MAPPED)) {
                up_write(&ni->runlist.lock);
                down_read(&ni->runlist.lock);
                goto retry_remap;
            }
        }
        err = ntfs_map_runlist_nolock(ni, vcn, NULL);
        if (!write_locked) {
            up_write(&ni->runlist.lock);
            down_read(&ni->runlist.lock);
        }
        if (likely(!err)) {
            is_retry = true;
            goto retry_remap;
        }
        if (err == -ENOENT)
            lcn = LCN_ENOENT;
        else if (err == -ENOMEM)
            lcn = LCN_ENOMEM;
        else
            lcn = LCN_EIO;
    }
    if (lcn != LCN_ENOENT)
        ntfs_error(ni->vol->sb, "Failed with error code %lli.",
                (long long)lcn);
    return lcn;
}

runlist_element *ntfs_attr_find_vcn_nolock(ntfs_inode *ni, const VCN vcn,
        ntfs_attr_search_ctx *ctx)
{
    unsigned long flags;
    runlist_element *rl;
    int err = 0;
    bool is_retry = false;

    BUG_ON(!ni);
    ntfs_debug("Entering for i_ino 0x%lx, vcn 0x%llx, with%s ctx.",
            ni->mft_no, (unsigned long long)vcn, ctx ? "" : "out");
    BUG_ON(!NInoNonResident(ni));
    BUG_ON(vcn < 0);
    if (!ni->runlist.rl) {
        read_lock_irqsave(&ni->size_lock, flags);
        if (!ni->allocated_size) {
            read_unlock_irqrestore(&ni->size_lock, flags);
            return ERR_PTR(-ENOENT);
        }
        read_unlock_irqrestore(&ni->size_lock, flags);
    }
retry_remap:
    rl = ni->runlist.rl;
    if (likely(rl && vcn >= rl[0].vcn)) {
        while (likely(rl->length)) {
            if (unlikely(vcn < rl[1].vcn)) {
                if (likely(rl->lcn >= LCN_HOLE)) {
                    ntfs_debug("Done.");
                    return rl;
                }
                break;
            }
            rl++;
        }
        if (likely(rl->lcn != LCN_RL_NOT_MAPPED)) {
            if (likely(rl->lcn == LCN_ENOENT))
                err = -ENOENT;
            else
                err = -EIO;
        }
    }
    if (!err && !is_retry) {
        /*
         * If the search context is invalid we cannot map the unmapped
         * region.
         */
        if (IS_ERR(ctx->mrec))
            err = PTR_ERR(ctx->mrec);
        else {
            /*
             * The @vcn is in an unmapped region, map the runlist
             * and retry.
             */
            err = ntfs_map_runlist_nolock(ni, vcn, ctx);
            if (likely(!err)) {
                is_retry = true;
                goto retry_remap;
            }
        }
        if (err == -EINVAL)
            err = -EIO;
    } else if (!err)
        err = -EIO;
    if (err != -ENOENT)
        ntfs_error(ni->vol->sb, "Failed with error code %i.", err);
    return ERR_PTR(err);
}

static int ntfs_attr_find(const ATTR_TYPE type, const ntfschar *name,
        const u32 name_len, const IGNORE_CASE_BOOL ic,
        const u8 *val, const u32 val_len, ntfs_attr_search_ctx *ctx)
{
    ATTR_RECORD *a;
    ntfs_volume *vol = ctx->ntfs_ino->vol;
    ntfschar *upcase = vol->upcase;
    u32 upcase_len = vol->upcase_len;

    /*
     * Iterate over attributes in mft record starting at @ctx->attr, or the
     * attribute following that, if @ctx->is_first is 'true'.
     */
    if (ctx->is_first) {
        a = ctx->attr;
        ctx->is_first = false;
    } else
        a = (ATTR_RECORD*)((u8*)ctx->attr +
                le32_to_cpu(ctx->attr->length));
    for (;; a = (ATTR_RECORD*)((u8*)a + le32_to_cpu(a->length))) {
        if ((u8*)a < (u8*)ctx->mrec || (u8*)a > (u8*)ctx->mrec +
                le32_to_cpu(ctx->mrec->bytes_allocated))
            break;
        ctx->attr = a;
        if (unlikely(le32_to_cpu(a->type) > le32_to_cpu(type) ||
                a->type == AT_END))
            return -ENOENT;
        if (unlikely(!a->length))
            break;
        if (a->type != type)
            continue;
        /*
         * If @name is present, compare the two names.  If @name is
         * missing, assume we want an unnamed attribute.
         */
        if (!name) {
            /* The search failed if the found attribute is named. */
            if (a->name_length)
                return -ENOENT;
        } else if (!ntfs_are_names_equal(name, name_len,
                (ntfschar*)((u8*)a + le16_to_cpu(a->name_offset)),
                a->name_length, ic, upcase, upcase_len)) {
            register int rc;

            rc = ntfs_collate_names(name, name_len,
                    (ntfschar*)((u8*)a +
                    le16_to_cpu(a->name_offset)),
                    a->name_length, 1, IGNORE_CASE,
                    upcase, upcase_len);
            /*
             * If @name collates before a->name, there is no
             * matching attribute.
             */
            if (rc == -1)
                return -ENOENT;
            /* If the strings are not equal, continue search. */
            if (rc)
                continue;
            rc = ntfs_collate_names(name, name_len,
                    (ntfschar*)((u8*)a +
                    le16_to_cpu(a->name_offset)),
                    a->name_length, 1, CASE_SENSITIVE,
                    upcase, upcase_len);
            if (rc == -1)
                return -ENOENT;
            if (rc)
                continue;
        }
        /*
         * The names match or @name not present and attribute is
         * unnamed.  If no @val specified, we have found the attribute
         * and are done.
         */
        if (!val)
            return 0;
        /* @val is present; compare values. */
        else {
            register int rc;

            rc = memcmp(val, (u8*)a + le16_to_cpu(
                    a->data.resident.value_offset),
                    min_t(u32, val_len, le32_to_cpu(
                    a->data.resident.value_length)));
            /*
             * If @val collates before the current attribute's
             * value, there is no matching attribute.
             */
            if (!rc) {
                register u32 avl;

                avl = le32_to_cpu(
                        a->data.resident.value_length);
                if (val_len == avl)
                    return 0;
                if (val_len < avl)
                    return -ENOENT;
            } else if (rc < 0)
                return -ENOENT;
        }
    }
    ntfs_error(vol->sb, "Inode is corrupt.  Run chkdsk.");
    NVolSetErrors(vol);
    return -EIO;
}

int load_attribute_list(ntfs_volume *vol, runlist *runlist, u8 *al_start,
        const s64 size, const s64 initialized_size)
{
    LCN lcn;
    u8 *al = al_start;
    u8 *al_end = al + initialized_size;
    runlist_element *rl;
    struct buffer_head *bh;
    struct super_block *sb;
    unsigned long block_size;
    unsigned long block, max_block;
    int err = 0;
    unsigned char block_size_bits;

    ntfs_debug("Entering.");
    if (!vol || !runlist || !al || size <= 0 || initialized_size < 0 ||
            initialized_size > size)
        return -EINVAL;
    if (!initialized_size) {
        memset(al, 0, size);
        return 0;
    }
    sb = vol->sb;
    block_size = sb->s_blocksize;
    block_size_bits = sb->s_blocksize_bits;
    down_read(&runlist->lock);
    rl = runlist->rl;
    if (!rl) {
        ntfs_error(sb, "Cannot read attribute list since runlist is "
                "missing.");
        goto err_out;   
    }
    /* Read all clusters specified by the runlist one run at a time. */
    while (rl->length) {
        lcn = ntfs_rl_vcn_to_lcn(rl, rl->vcn);
        ntfs_debug("Reading vcn = 0x%llx, lcn = 0x%llx.",
                (unsigned long long)rl->vcn,
                (unsigned long long)lcn);
        /* The attribute list cannot be sparse. */
        if (lcn < 0) {
            ntfs_error(sb, "ntfs_rl_vcn_to_lcn() failed.  Cannot "
                    "read attribute list.");
            goto err_out;
        }
        block = lcn << vol->cluster_size_bits >> block_size_bits;
        /* Read the run from device in chunks of block_size bytes. */
        max_block = block + (rl->length << vol->cluster_size_bits >>
                block_size_bits);
        ntfs_debug("max_block = 0x%lx.", max_block);
        do {
            ntfs_debug("Reading block = 0x%lx.", block);
            bh = sb_bread(sb, block);
            if (!bh) {
                ntfs_error(sb, "sb_bread() failed. Cannot "
                        "read attribute list.");
                goto err_out;
            }
            if (al + block_size >= al_end)
                goto do_final;
            memcpy(al, bh->b_data, block_size);
            brelse(bh);
            al += block_size;
        } while (++block < max_block);
        rl++;
    }
    if (initialized_size < size) {
initialize:
        memset(al_start + initialized_size, 0, size - initialized_size);
    }
done:
    up_read(&runlist->lock);
    return err;
do_final:
    if (al < al_end) {
        /*
         * Partial block.
         *
         * Note: The attribute list can be smaller than its allocation
         * by multiple clusters.  This has been encountered by at least
         * two people running Windows XP, thus we cannot do any
         * truncation sanity checking here. (AIA)
         */
        memcpy(al, bh->b_data, al_end - al);
        brelse(bh);
        if (initialized_size < size)
            goto initialize;
        goto done;
    }
    brelse(bh);
    /* Real overflow! */
    ntfs_error(sb, "Attribute list buffer overflow. Read attribute list "
            "is truncated.");
err_out:
    err = -EIO;
    goto done;
}

static int ntfs_external_attr_find(const ATTR_TYPE type,
        const ntfschar *name, const u32 name_len,
        const IGNORE_CASE_BOOL ic, const VCN lowest_vcn,
        const u8 *val, const u32 val_len, ntfs_attr_search_ctx *ctx)
{
    ntfs_inode *base_ni, *ni;
    ntfs_volume *vol;
    ATTR_LIST_ENTRY *al_entry, *next_al_entry;
    u8 *al_start, *al_end;
    ATTR_RECORD *a;
    ntfschar *al_name;
    u32 al_name_len;
    int err = 0;
    static const char *es = " Unmount and run chkdsk.";

    ni = ctx->ntfs_ino;
    base_ni = ctx->base_ntfs_ino;
    ntfs_debug("Entering for inode 0x%lx, type 0x%x.", ni->mft_no, type);
    if (!base_ni) {
        /* First call happens with the base mft record. */
        base_ni = ctx->base_ntfs_ino = ctx->ntfs_ino;
        ctx->base_mrec = ctx->mrec;
    }
    if (ni == base_ni)
        ctx->base_attr = ctx->attr;
    if (type == AT_END)
        goto not_found;
    vol = base_ni->vol;
    al_start = base_ni->attr_list;
    al_end = al_start + base_ni->attr_list_size;
    if (!ctx->al_entry)
        ctx->al_entry = (ATTR_LIST_ENTRY*)al_start;
    /*
     * Iterate over entries in attribute list starting at @ctx->al_entry,
     * or the entry following that, if @ctx->is_first is 'true'.
     */
    if (ctx->is_first) {
        al_entry = ctx->al_entry;
        ctx->is_first = false;
    } else
        al_entry = (ATTR_LIST_ENTRY*)((u8*)ctx->al_entry +
                le16_to_cpu(ctx->al_entry->length));
    for (;; al_entry = next_al_entry) {
        /* Out of bounds check. */
        if ((u8*)al_entry < base_ni->attr_list ||
                (u8*)al_entry > al_end)
            break;  /* Inode is corrupt. */
        ctx->al_entry = al_entry;
        /* Catch the end of the attribute list. */
        if ((u8*)al_entry == al_end)
            goto not_found;
        if (!al_entry->length)
            break;
        if ((u8*)al_entry + 6 > al_end || (u8*)al_entry +
                le16_to_cpu(al_entry->length) > al_end)
            break;
        next_al_entry = (ATTR_LIST_ENTRY*)((u8*)al_entry +
                le16_to_cpu(al_entry->length));
        if (le32_to_cpu(al_entry->type) > le32_to_cpu(type))
            goto not_found;
        if (type != al_entry->type)
            continue;
        /*
         * If @name is present, compare the two names.  If @name is
         * missing, assume we want an unnamed attribute.
         */
        al_name_len = al_entry->name_length;
        al_name = (ntfschar*)((u8*)al_entry + al_entry->name_offset);
        if (!name) {
            if (al_name_len)
                goto not_found;
        } else if (!ntfs_are_names_equal(al_name, al_name_len, name,
                name_len, ic, vol->upcase, vol->upcase_len)) {
            register int rc;

            rc = ntfs_collate_names(name, name_len, al_name,
                    al_name_len, 1, IGNORE_CASE,
                    vol->upcase, vol->upcase_len);
            /*
             * If @name collates before al_name, there is no
             * matching attribute.
             */
            if (rc == -1)
                goto not_found;
            /* If the strings are not equal, continue search. */
            if (rc)
                continue;
            /*
             * FIXME: Reverse engineering showed 0, IGNORE_CASE but
             * that is inconsistent with ntfs_attr_find().  The
             * subsequent rc checks were also different.  Perhaps I
             * made a mistake in one of the two.  Need to recheck
             * which is correct or at least see what is going on...
             * (AIA)
             */
            rc = ntfs_collate_names(name, name_len, al_name,
                    al_name_len, 1, CASE_SENSITIVE,
                    vol->upcase, vol->upcase_len);
            if (rc == -1)
                goto not_found;
            if (rc)
                continue;
        }
        /*
         * The names match or @name not present and attribute is
         * unnamed.  Now check @lowest_vcn.  Continue search if the
         * next attribute list entry still fits @lowest_vcn.  Otherwise
         * we have reached the right one or the search has failed.
         */
        if (lowest_vcn && (u8*)next_al_entry >= al_start        &&
                (u8*)next_al_entry + 6 < al_end         &&
                (u8*)next_al_entry + le16_to_cpu(
                    next_al_entry->length) <= al_end    &&
                sle64_to_cpu(next_al_entry->lowest_vcn) <=
                    lowest_vcn              &&
                next_al_entry->type == al_entry->type       &&
                next_al_entry->name_length == al_name_len   &&
                ntfs_are_names_equal((ntfschar*)((u8*)
                    next_al_entry +
                    next_al_entry->name_offset),
                    next_al_entry->name_length,
                    al_name, al_name_len, CASE_SENSITIVE,
                    vol->upcase, vol->upcase_len))
            continue;
        if (MREF_LE(al_entry->mft_reference) == ni->mft_no) {
            if (MSEQNO_LE(al_entry->mft_reference) != ni->seq_no) {
                ntfs_error(vol->sb, "Found stale mft "
                        "reference in attribute list "
                        "of base inode 0x%lx.%s",
                        base_ni->mft_no, es);
                err = -EIO;
                break;
            }
        } else { /* Mft references do not match. */
            /* If there is a mapped record unmap it first. */
            if (ni != base_ni)
                unmap_extent_mft_record(ni);
            /* Do we want the base record back? */
            if (MREF_LE(al_entry->mft_reference) ==
                    base_ni->mft_no) {
                ni = ctx->ntfs_ino = base_ni;
                ctx->mrec = ctx->base_mrec;
            } else {
                /* We want an extent record. */
                ctx->mrec = map_extent_mft_record(base_ni,
                        le64_to_cpu(
                        al_entry->mft_reference), &ni);
                if (IS_ERR(ctx->mrec)) {
                    ntfs_error(vol->sb, "Failed to map "
                            "extent mft record "
                            "0x%lx of base inode "
                            "0x%lx.%s",
                            MREF_LE(al_entry->
                            mft_reference),
                            base_ni->mft_no, es);
                    err = PTR_ERR(ctx->mrec);
                    if (err == -ENOENT)
                        err = -EIO;
                    /* Cause @ctx to be sanitized below. */
                    ni = NULL;
                    break;
                }
                ctx->ntfs_ino = ni;
            }
            ctx->attr = (ATTR_RECORD*)((u8*)ctx->mrec +
                    le16_to_cpu(ctx->mrec->attrs_offset));
        }
        /*
         * ctx->vfs_ino, ctx->mrec, and ctx->attr now point to the
         * mft record containing the attribute represented by the
         * current al_entry.
         */
        /*
         * We could call into ntfs_attr_find() to find the right
         * attribute in this mft record but this would be less
         * efficient and not quite accurate as ntfs_attr_find() ignores
         * the attribute instance numbers for example which become
         * important when one plays with attribute lists.  Also,
         * because a proper match has been found in the attribute list
         * entry above, the comparison can now be optimized.  So it is
         * worth re-implementing a simplified ntfs_attr_find() here.
         */
        a = ctx->attr;
        /*
         * Use a manual loop so we can still use break and continue
         * with the same meanings as above.
         */
do_next_attr_loop:
        if ((u8*)a < (u8*)ctx->mrec || (u8*)a > (u8*)ctx->mrec +
                le32_to_cpu(ctx->mrec->bytes_allocated))
            break;
        if (a->type == AT_END)
            break;
        if (!a->length)
            break;
        if (al_entry->instance != a->instance)
            goto do_next_attr;
        /*
         * If the type and/or the name are mismatched between the
         * attribute list entry and the attribute record, there is
         * corruption so we break and return error EIO.
         */
        if (al_entry->type != a->type)
            break;
        if (!ntfs_are_names_equal((ntfschar*)((u8*)a +
                le16_to_cpu(a->name_offset)), a->name_length,
                al_name, al_name_len, CASE_SENSITIVE,
                vol->upcase, vol->upcase_len))
            break;
        ctx->attr = a;
        /*
         * If no @val specified or @val specified and it matches, we
         * have found it!
         */
        if (!val || (!a->non_resident && le32_to_cpu(
                a->data.resident.value_length) == val_len &&
                !memcmp((u8*)a +
                le16_to_cpu(a->data.resident.value_offset),
                val, val_len))) {
            ntfs_debug("Done, found.");
            return 0;
        }
do_next_attr:
        /* Proceed to the next attribute in the current mft record. */
        a = (ATTR_RECORD*)((u8*)a + le32_to_cpu(a->length));
        goto do_next_attr_loop;
    }
    if (!err) {
        ntfs_error(vol->sb, "Base inode 0x%lx contains corrupt "
                "attribute list attribute.%s", base_ni->mft_no,
                es);
        err = -EIO;
    }
    if (ni != base_ni) {
        if (ni)
            unmap_extent_mft_record(ni);
        ctx->ntfs_ino = base_ni;
        ctx->mrec = ctx->base_mrec;
        ctx->attr = ctx->base_attr;
    }
    if (err != -ENOMEM)
        NVolSetErrors(vol);
    return err;
not_found:
    /*
     * If we were looking for AT_END, we reset the search context @ctx and
     * use ntfs_attr_find() to seek to the end of the base mft record.
     */
    if (type == AT_END) {
        ntfs_attr_reinit_search_ctx(ctx);
        return ntfs_attr_find(AT_END, name, name_len, ic, val, val_len,
                ctx);
    }
    /*
     * The attribute was not found.  Before we return, we want to ensure
     * @ctx->mrec and @ctx->attr indicate the position at which the
     * attribute should be inserted in the base mft record.  Since we also
     * want to preserve @ctx->al_entry we cannot reinitialize the search
     * context using ntfs_attr_reinit_search_ctx() as this would set
     * @ctx->al_entry to NULL.  Thus we do the necessary bits manually (see
     * ntfs_attr_init_search_ctx() below).  Note, we _only_ preserve
     * @ctx->al_entry as the remaining fields (base_*) are identical to
     * their non base_ counterparts and we cannot set @ctx->base_attr
     * correctly yet as we do not know what @ctx->attr will be set to by
     * the call to ntfs_attr_find() below.
     */
    if (ni != base_ni)
        unmap_extent_mft_record(ni);
    ctx->mrec = ctx->base_mrec;
    ctx->attr = (ATTR_RECORD*)((u8*)ctx->mrec +
            le16_to_cpu(ctx->mrec->attrs_offset));
    ctx->is_first = true;
    ctx->ntfs_ino = base_ni;
    ctx->base_ntfs_ino = NULL;
    ctx->base_mrec = NULL;
    ctx->base_attr = NULL;
    /*
     * In case there are multiple matches in the base mft record, need to
     * keep enumerating until we get an attribute not found response (or
     * another error), otherwise we would keep returning the same attribute
     * over and over again and all programs using us for enumeration would
     * lock up in a tight loop.
     */
    do {
        err = ntfs_attr_find(type, name, name_len, ic, val, val_len,
                ctx);
    } while (!err);
    ntfs_debug("Done, not found.");
    return err;
}

int ntfs_attr_lookup(const ATTR_TYPE type, const ntfschar *name,
        const u32 name_len, const IGNORE_CASE_BOOL ic,
        const VCN lowest_vcn, const u8 *val, const u32 val_len,
        ntfs_attr_search_ctx *ctx)
{
    ntfs_inode *base_ni;

    ntfs_debug("Entering.");
    BUG_ON(IS_ERR(ctx->mrec));
    if (ctx->base_ntfs_ino)
        base_ni = ctx->base_ntfs_ino;
    else
        base_ni = ctx->ntfs_ino;
    /* Sanity check, just for debugging really. */
    BUG_ON(!base_ni);
    if (!NInoAttrList(base_ni) || type == AT_ATTRIBUTE_LIST)
        return ntfs_attr_find(type, name, name_len, ic, val, val_len,
                ctx);
    return ntfs_external_attr_find(type, name, name_len, ic, lowest_vcn,
            val, val_len, ctx);
}

static inline void ntfs_attr_init_search_ctx(ntfs_attr_search_ctx *ctx,
        ntfs_inode *ni, MFT_RECORD *mrec)
{
    *ctx = (ntfs_attr_search_ctx) {
        .mrec = mrec,
        /* Sanity checks are performed elsewhere. */
        .attr = (ATTR_RECORD*)((u8*)mrec +
                le16_to_cpu(mrec->attrs_offset)),
        .is_first = true,
        .ntfs_ino = ni,
    };
}

void ntfs_attr_reinit_search_ctx(ntfs_attr_search_ctx *ctx)
{
    if (likely(!ctx->base_ntfs_ino)) {
        /* No attribute list. */
        ctx->is_first = true;
        /* Sanity checks are performed elsewhere. */
        ctx->attr = (ATTR_RECORD*)((u8*)ctx->mrec +
                le16_to_cpu(ctx->mrec->attrs_offset));
        /*
         * This needs resetting due to ntfs_external_attr_find() which
         * can leave it set despite having zeroed ctx->base_ntfs_ino.
         */
        ctx->al_entry = NULL;
        return;
    } /* Attribute list. */
    if (ctx->ntfs_ino != ctx->base_ntfs_ino)
        unmap_extent_mft_record(ctx->ntfs_ino);
    ntfs_attr_init_search_ctx(ctx, ctx->base_ntfs_ino, ctx->base_mrec);
    return;
}

ntfs_attr_search_ctx *ntfs_attr_get_search_ctx(ntfs_inode *ni, MFT_RECORD *mrec)
{
    ntfs_attr_search_ctx *ctx;

    ctx = kmem_cache_alloc(ntfs_attr_ctx_cache, GFP_NOFS);
    if (ctx)
        ntfs_attr_init_search_ctx(ctx, ni, mrec);
    return ctx;
}

void ntfs_attr_put_search_ctx(ntfs_attr_search_ctx *ctx)
{
    if (ctx->base_ntfs_ino && ctx->ntfs_ino != ctx->base_ntfs_ino)
        unmap_extent_mft_record(ctx->ntfs_ino);
    kmem_cache_free(ntfs_attr_ctx_cache, ctx);
    return;
}

#ifdef NTFS_RW

static ATTR_DEF *ntfs_attr_find_in_attrdef(const ntfs_volume *vol,
        const ATTR_TYPE type)
{
    ATTR_DEF *ad;

    BUG_ON(!vol->attrdef);
    BUG_ON(!type);
    for (ad = vol->attrdef; (u8*)ad - (u8*)vol->attrdef <
            vol->attrdef_size && ad->type; ++ad) {
        /* We have not found it yet, carry on searching. */
        if (likely(le32_to_cpu(ad->type) < le32_to_cpu(type)))
            continue;
        /* We found the attribute; return it. */
        if (likely(ad->type == type))
            return ad;
        /* We have gone too far already.  No point in continuing. */
        break;
    }
    /* Attribute not found. */
    ntfs_debug("Attribute type 0x%x not found in $AttrDef.",
            le32_to_cpu(type));
    return NULL;
}

int ntfs_attr_size_bounds_check(const ntfs_volume *vol, const ATTR_TYPE type,
        const s64 size)
{
    ATTR_DEF *ad;

    BUG_ON(size < 0);
    /*
     * $ATTRIBUTE_LIST has a maximum size of 256kiB, but this is not
     * listed in $AttrDef.
     */
    if (unlikely(type == AT_ATTRIBUTE_LIST && size > 256 * 1024))
        return -ERANGE;
    /* Get the $AttrDef entry for the attribute @type. */
    ad = ntfs_attr_find_in_attrdef(vol, type);
    if (unlikely(!ad))
        return -ENOENT;
    /* Do the bounds check. */
    if (((sle64_to_cpu(ad->min_size) > 0) &&
            size < sle64_to_cpu(ad->min_size)) ||
            ((sle64_to_cpu(ad->max_size) > 0) && size >
            sle64_to_cpu(ad->max_size)))
        return -ERANGE;
    return 0;
}

int ntfs_attr_can_be_non_resident(const ntfs_volume *vol, const ATTR_TYPE type)
{
    ATTR_DEF *ad;

    /* Find the attribute definition record in $AttrDef. */
    ad = ntfs_attr_find_in_attrdef(vol, type);
    if (unlikely(!ad))
        return -ENOENT;
    /* Check the flags and return the result. */
    if (ad->flags & ATTR_DEF_RESIDENT)
        return -EPERM;
    return 0;
}

int ntfs_attr_can_be_resident(const ntfs_volume *vol, const ATTR_TYPE type)
{
    if (type == AT_INDEX_ALLOCATION)
        return -EPERM;
    return 0;
}

int ntfs_attr_record_resize(MFT_RECORD *m, ATTR_RECORD *a, u32 new_size)
{
    ntfs_debug("Entering for new_size %u.", new_size);
    /* Align to 8 bytes if it is not already done. */
    if (new_size & 7)
        new_size = (new_size + 7) & ~7;
    /* If the actual attribute length has changed, move things around. */
    if (new_size != le32_to_cpu(a->length)) {
        u32 new_muse = le32_to_cpu(m->bytes_in_use) -
                le32_to_cpu(a->length) + new_size;
        /* Not enough space in this mft record. */
        if (new_muse > le32_to_cpu(m->bytes_allocated))
            return -ENOSPC;
        /* Move attributes following @a to their new location. */
        memmove((u8*)a + new_size, (u8*)a + le32_to_cpu(a->length),
                le32_to_cpu(m->bytes_in_use) - ((u8*)a -
                (u8*)m) - le32_to_cpu(a->length));
        /* Adjust @m to reflect the change in used space. */
        m->bytes_in_use = cpu_to_le32(new_muse);
        /* Adjust @a to reflect the new size. */
        if (new_size >= offsetof(ATTR_REC, length) + sizeof(a->length))
            a->length = cpu_to_le32(new_size);
    }
    return 0;
}

int ntfs_resident_attr_value_resize(MFT_RECORD *m, ATTR_RECORD *a,
        const u32 new_size)
{
    u32 old_size;

    /* Resize the resident part of the attribute record. */
    if (ntfs_attr_record_resize(m, a,
            le16_to_cpu(a->data.resident.value_offset) + new_size))
        return -ENOSPC;
    /*
     * The resize succeeded!  If we made the attribute value bigger, clear
     * the area between the old size and @new_size.
     */
    old_size = le32_to_cpu(a->data.resident.value_length);
    if (new_size > old_size)
        memset((u8*)a + le16_to_cpu(a->data.resident.value_offset) +
                old_size, 0, new_size - old_size);
    /* Finally update the length of the attribute value. */
    a->data.resident.value_length = cpu_to_le32(new_size);
    return 0;
}

int ntfs_attr_make_non_resident(ntfs_inode *ni, const u32 data_size)
{
    s64 new_size;
    struct inode *vi = VFS_I(ni);
    ntfs_volume *vol = ni->vol;
    ntfs_inode *base_ni;
    MFT_RECORD *m;
    ATTR_RECORD *a;
    ntfs_attr_search_ctx *ctx;
    struct page *page;
    runlist_element *rl;
    u8 *kaddr;
    unsigned long flags;
    int mp_size, mp_ofs, name_ofs, arec_size, err, err2;
    u32 attr_size;
    u8 old_res_attr_flags;

    /* Check that the attribute is allowed to be non-resident. */
    err = ntfs_attr_can_be_non_resident(vol, ni->type);
    if (unlikely(err)) {
        if (err == -EPERM)
            ntfs_debug("Attribute is not allowed to be "
                    "non-resident.");
        else
            ntfs_debug("Attribute not defined on the NTFS "
                    "volume!");
        return err;
    }
    /*
     * FIXME: Compressed and encrypted attributes are not supported when
     * writing and we should never have gotten here for them.
     */
    BUG_ON(NInoCompressed(ni));
    BUG_ON(NInoEncrypted(ni));
    /*
     * The size needs to be aligned to a cluster boundary for allocation
     * purposes.
     */
    new_size = (data_size + vol->cluster_size - 1) &
            ~(vol->cluster_size - 1);
    if (new_size > 0) {
        /*
         * Will need the page later and since the page lock nests
         * outside all ntfs locks, we need to get the page now.
         */
        page = find_or_create_page(vi->i_mapping, 0,
                mapping_gfp_mask(vi->i_mapping));
        if (unlikely(!page))
            return -ENOMEM;
        /* Start by allocating clusters to hold the attribute value. */
        rl = ntfs_cluster_alloc(vol, 0, new_size >>
                vol->cluster_size_bits, -1, DATA_ZONE, true);
        if (IS_ERR(rl)) {
            err = PTR_ERR(rl);
            ntfs_debug("Failed to allocate cluster%s, error code "
                    "%i.", (new_size >>
                    vol->cluster_size_bits) > 1 ? "s" : "",
                    err);
            goto page_err_out;
        }
    } else {
        rl = NULL;
        page = NULL;
    }
    /* Determine the size of the mapping pairs array. */
    mp_size = ntfs_get_size_for_mapping_pairs(vol, rl, 0, -1);
    if (unlikely(mp_size < 0)) {
        err = mp_size;
        ntfs_debug("Failed to get size for mapping pairs array, error "
                "code %i.", err);
        goto rl_err_out;
    }
    down_write(&ni->runlist.lock);
    if (!NInoAttr(ni))
        base_ni = ni;
    else
        base_ni = ni->ext.base_ntfs_ino;
    m = map_mft_record(base_ni);
    if (IS_ERR(m)) {
        err = PTR_ERR(m);
        m = NULL;
        ctx = NULL;
        goto err_out;
    }
    ctx = ntfs_attr_get_search_ctx(base_ni, m);
    if (unlikely(!ctx)) {
        err = -ENOMEM;
        goto err_out;
    }
    err = ntfs_attr_lookup(ni->type, ni->name, ni->name_len,
            CASE_SENSITIVE, 0, NULL, 0, ctx);
    if (unlikely(err)) {
        if (err == -ENOENT)
            err = -EIO;
        goto err_out;
    }
    m = ctx->mrec;
    a = ctx->attr;
    BUG_ON(NInoNonResident(ni));
    BUG_ON(a->non_resident);
    /*
     * Calculate new offsets for the name and the mapping pairs array.
     */
    if (NInoSparse(ni) || NInoCompressed(ni))
        name_ofs = (offsetof(ATTR_REC,
                data.non_resident.compressed_size) +
                sizeof(a->data.non_resident.compressed_size) +
                7) & ~7;
    else
        name_ofs = (offsetof(ATTR_REC,
                data.non_resident.compressed_size) + 7) & ~7;
    mp_ofs = (name_ofs + a->name_length * sizeof(ntfschar) + 7) & ~7;
    /*
     * Determine the size of the resident part of the now non-resident
     * attribute record.
     */
    arec_size = (mp_ofs + mp_size + 7) & ~7;
    /*
     * If the page is not uptodate bring it uptodate by copying from the
     * attribute value.
     */
    attr_size = le32_to_cpu(a->data.resident.value_length);
    BUG_ON(attr_size != data_size);
    if (page && !PageUptodate(page)) {
        kaddr = kmap_atomic(page);
        memcpy(kaddr, (u8*)a +
                le16_to_cpu(a->data.resident.value_offset),
                attr_size);
        memset(kaddr + attr_size, 0, PAGE_CACHE_SIZE - attr_size);
        kunmap_atomic(kaddr);
        flush_dcache_page(page);
        SetPageUptodate(page);
    }
    /* Backup the attribute flag. */
    old_res_attr_flags = a->data.resident.flags;
    /* Resize the resident part of the attribute record. */
    err = ntfs_attr_record_resize(m, a, arec_size);
    if (unlikely(err))
        goto err_out;
    /*
     * Convert the resident part of the attribute record to describe a
     * non-resident attribute.
     */
    a->non_resident = 1;
    /* Move the attribute name if it exists and update the offset. */
    if (a->name_length)
        memmove((u8*)a + name_ofs, (u8*)a + le16_to_cpu(a->name_offset),
                a->name_length * sizeof(ntfschar));
    a->name_offset = cpu_to_le16(name_ofs);
    /* Setup the fields specific to non-resident attributes. */
    a->data.non_resident.lowest_vcn = 0;
    a->data.non_resident.highest_vcn = cpu_to_sle64((new_size - 1) >>
            vol->cluster_size_bits);
    a->data.non_resident.mapping_pairs_offset = cpu_to_le16(mp_ofs);
    memset(&a->data.non_resident.reserved, 0,
            sizeof(a->data.non_resident.reserved));
    a->data.non_resident.allocated_size = cpu_to_sle64(new_size);
    a->data.non_resident.data_size =
            a->data.non_resident.initialized_size =
            cpu_to_sle64(attr_size);
    if (NInoSparse(ni) || NInoCompressed(ni)) {
        a->data.non_resident.compression_unit = 0;
        if (NInoCompressed(ni) || vol->major_ver < 3)
            a->data.non_resident.compression_unit = 4;
        a->data.non_resident.compressed_size =
                a->data.non_resident.allocated_size;
    } else
        a->data.non_resident.compression_unit = 0;
    /* Generate the mapping pairs array into the attribute record. */
    err = ntfs_mapping_pairs_build(vol, (u8*)a + mp_ofs,
            arec_size - mp_ofs, rl, 0, -1, NULL);
    if (unlikely(err)) {
        ntfs_debug("Failed to build mapping pairs, error code %i.",
                err);
        goto undo_err_out;
    }
    /* Setup the in-memory attribute structure to be non-resident. */
    ni->runlist.rl = rl;
    write_lock_irqsave(&ni->size_lock, flags);
    ni->allocated_size = new_size;
    if (NInoSparse(ni) || NInoCompressed(ni)) {
        ni->itype.compressed.size = ni->allocated_size;
        if (a->data.non_resident.compression_unit) {
            ni->itype.compressed.block_size = 1U << (a->data.
                    non_resident.compression_unit +
                    vol->cluster_size_bits);
            ni->itype.compressed.block_size_bits =
                    ffs(ni->itype.compressed.block_size) -
                    1;
            ni->itype.compressed.block_clusters = 1U <<
                    a->data.non_resident.compression_unit;
        } else {
            ni->itype.compressed.block_size = 0;
            ni->itype.compressed.block_size_bits = 0;
            ni->itype.compressed.block_clusters = 0;
        }
        vi->i_blocks = ni->itype.compressed.size >> 9;
    } else
        vi->i_blocks = ni->allocated_size >> 9;
    write_unlock_irqrestore(&ni->size_lock, flags);
    /*
     * This needs to be last since the address space operations ->readpage
     * and ->writepage can run concurrently with us as they are not
     * serialized on i_mutex.  Note, we are not allowed to fail once we flip
     * this switch, which is another reason to do this last.
     */
    NInoSetNonResident(ni);
    /* Mark the mft record dirty, so it gets written back. */
    flush_dcache_mft_record_page(ctx->ntfs_ino);
    mark_mft_record_dirty(ctx->ntfs_ino);
    ntfs_attr_put_search_ctx(ctx);
    unmap_mft_record(base_ni);
    up_write(&ni->runlist.lock);
    if (page) {
        set_page_dirty(page);
        unlock_page(page);
        mark_page_accessed(page);
        page_cache_release(page);
    }
    ntfs_debug("Done.");
    return 0;
undo_err_out:
    /* Convert the attribute back into a resident attribute. */
    a->non_resident = 0;
    /* Move the attribute name if it exists and update the offset. */
    name_ofs = (offsetof(ATTR_RECORD, data.resident.reserved) +
            sizeof(a->data.resident.reserved) + 7) & ~7;
    if (a->name_length)
        memmove((u8*)a + name_ofs, (u8*)a + le16_to_cpu(a->name_offset),
                a->name_length * sizeof(ntfschar));
    mp_ofs = (name_ofs + a->name_length * sizeof(ntfschar) + 7) & ~7;
    a->name_offset = cpu_to_le16(name_ofs);
    arec_size = (mp_ofs + attr_size + 7) & ~7;
    /* Resize the resident part of the attribute record. */
    err2 = ntfs_attr_record_resize(m, a, arec_size);
    if (unlikely(err2)) {
        /*
         * This cannot happen (well if memory corruption is at work it
         * could happen in theory), but deal with it as well as we can.
         * If the old size is too small, truncate the attribute,
         * otherwise simply give it a larger allocated size.
         * FIXME: Should check whether chkdsk complains when the
         * allocated size is much bigger than the resident value size.
         */
        arec_size = le32_to_cpu(a->length);
        if ((mp_ofs + attr_size) > arec_size) {
            err2 = attr_size;
            attr_size = arec_size - mp_ofs;
            ntfs_error(vol->sb, "Failed to undo partial resident "
                    "to non-resident attribute "
                    "conversion.  Truncating inode 0x%lx, "
                    "attribute type 0x%x from %i bytes to "
                    "%i bytes to maintain metadata "
                    "consistency.  THIS MEANS YOU ARE "
                    "LOSING %i BYTES DATA FROM THIS %s.",
                    vi->i_ino,
                    (unsigned)le32_to_cpu(ni->type),
                    err2, attr_size, err2 - attr_size,
                    ((ni->type == AT_DATA) &&
                    !ni->name_len) ? "FILE": "ATTRIBUTE");
            write_lock_irqsave(&ni->size_lock, flags);
            ni->initialized_size = attr_size;
            i_size_write(vi, attr_size);
            write_unlock_irqrestore(&ni->size_lock, flags);
        }
    }
    /* Setup the fields specific to resident attributes. */
    a->data.resident.value_length = cpu_to_le32(attr_size);
    a->data.resident.value_offset = cpu_to_le16(mp_ofs);
    a->data.resident.flags = old_res_attr_flags;
    memset(&a->data.resident.reserved, 0,
            sizeof(a->data.resident.reserved));
    /* Copy the data from the page back to the attribute value. */
    if (page) {
        kaddr = kmap_atomic(page);
        memcpy((u8*)a + mp_ofs, kaddr, attr_size);
        kunmap_atomic(kaddr);
    }
    /* Setup the allocated size in the ntfs inode in case it changed. */
    write_lock_irqsave(&ni->size_lock, flags);
    ni->allocated_size = arec_size - mp_ofs;
    write_unlock_irqrestore(&ni->size_lock, flags);
    /* Mark the mft record dirty, so it gets written back. */
    flush_dcache_mft_record_page(ctx->ntfs_ino);
    mark_mft_record_dirty(ctx->ntfs_ino);
err_out:
    if (ctx)
        ntfs_attr_put_search_ctx(ctx);
    if (m)
        unmap_mft_record(base_ni);
    ni->runlist.rl = NULL;
    up_write(&ni->runlist.lock);
rl_err_out:
    if (rl) {
        if (ntfs_cluster_free_from_rl(vol, rl) < 0) {
            ntfs_error(vol->sb, "Failed to release allocated "
                    "cluster(s) in error code path.  Run "
                    "chkdsk to recover the lost "
                    "cluster(s).");
            NVolSetErrors(vol);
        }
        ntfs_free(rl);
page_err_out:
        unlock_page(page);
        page_cache_release(page);
    }
    if (err == -EINVAL)
        err = -EIO;
    return err;
}

s64 ntfs_attr_extend_allocation(ntfs_inode *ni, s64 new_alloc_size,
        const s64 new_data_size, const s64 data_start)
{
    VCN vcn;
    s64 ll, allocated_size, start = data_start;
    struct inode *vi = VFS_I(ni);
    ntfs_volume *vol = ni->vol;
    ntfs_inode *base_ni;
    MFT_RECORD *m;
    ATTR_RECORD *a;
    ntfs_attr_search_ctx *ctx;
    runlist_element *rl, *rl2;
    unsigned long flags;
    int err, mp_size;
    u32 attr_len = 0; /* Silence stupid gcc warning. */
    bool mp_rebuilt;

#ifdef DEBUG
    read_lock_irqsave(&ni->size_lock, flags);
    allocated_size = ni->allocated_size;
    read_unlock_irqrestore(&ni->size_lock, flags);
    ntfs_debug("Entering for i_ino 0x%lx, attribute type 0x%x, "
            "old_allocated_size 0x%llx, "
            "new_allocated_size 0x%llx, new_data_size 0x%llx, "
            "data_start 0x%llx.", vi->i_ino,
            (unsigned)le32_to_cpu(ni->type),
            (unsigned long long)allocated_size,
            (unsigned long long)new_alloc_size,
            (unsigned long long)new_data_size,
            (unsigned long long)start);
#endif
retry_extend:
    /*
     * For non-resident attributes, @start and @new_size need to be aligned
     * to cluster boundaries for allocation purposes.
     */
    if (NInoNonResident(ni)) {
        if (start > 0)
            start &= ~(s64)vol->cluster_size_mask;
        new_alloc_size = (new_alloc_size + vol->cluster_size - 1) &
                ~(s64)vol->cluster_size_mask;
    }
    BUG_ON(new_data_size >= 0 && new_data_size > new_alloc_size);
    /* Check if new size is allowed in $AttrDef. */
    err = ntfs_attr_size_bounds_check(vol, ni->type, new_alloc_size);
    if (unlikely(err)) {
        /* Only emit errors when the write will fail completely. */
        read_lock_irqsave(&ni->size_lock, flags);
        allocated_size = ni->allocated_size;
        read_unlock_irqrestore(&ni->size_lock, flags);
        if (start < 0 || start >= allocated_size) {
            if (err == -ERANGE) {
                ntfs_error(vol->sb, "Cannot extend allocation "
                        "of inode 0x%lx, attribute "
                        "type 0x%x, because the new "
                        "allocation would exceed the "
                        "maximum allowed size for "
                        "this attribute type.",
                        vi->i_ino, (unsigned)
                        le32_to_cpu(ni->type));
            } else {
                ntfs_error(vol->sb, "Cannot extend allocation "
                        "of inode 0x%lx, attribute "
                        "type 0x%x, because this "
                        "attribute type is not "
                        "defined on the NTFS volume.  "
                        "Possible corruption!  You "
                        "should run chkdsk!",
                        vi->i_ino, (unsigned)
                        le32_to_cpu(ni->type));
            }
        }
        /* Translate error code to be POSIX conformant for write(2). */
        if (err == -ERANGE)
            err = -EFBIG;
        else
            err = -EIO;
        return err;
    }
    if (!NInoAttr(ni))
        base_ni = ni;
    else
        base_ni = ni->ext.base_ntfs_ino;
    /*
     * We will be modifying both the runlist (if non-resident) and the mft
     * record so lock them both down.
     */
    down_write(&ni->runlist.lock);
    m = map_mft_record(base_ni);
    if (IS_ERR(m)) {
        err = PTR_ERR(m);
        m = NULL;
        ctx = NULL;
        goto err_out;
    }
    ctx = ntfs_attr_get_search_ctx(base_ni, m);
    if (unlikely(!ctx)) {
        err = -ENOMEM;
        goto err_out;
    }
    read_lock_irqsave(&ni->size_lock, flags);
    allocated_size = ni->allocated_size;
    read_unlock_irqrestore(&ni->size_lock, flags);
    /*
     * If non-resident, seek to the last extent.  If resident, there is
     * only one extent, so seek to that.
     */
    vcn = NInoNonResident(ni) ? allocated_size >> vol->cluster_size_bits :
            0;
    /*
     * Abort if someone did the work whilst we waited for the locks.  If we
     * just converted the attribute from resident to non-resident it is
     * likely that exactly this has happened already.  We cannot quite
     * abort if we need to update the data size.
     */
    if (unlikely(new_alloc_size <= allocated_size)) {
        ntfs_debug("Allocated size already exceeds requested size.");
        new_alloc_size = allocated_size;
        if (new_data_size < 0)
            goto done;
        /*
         * We want the first attribute extent so that we can update the
         * data size.
         */
        vcn = 0;
    }
    err = ntfs_attr_lookup(ni->type, ni->name, ni->name_len,
            CASE_SENSITIVE, vcn, NULL, 0, ctx);
    if (unlikely(err)) {
        if (err == -ENOENT)
            err = -EIO;
        goto err_out;
    }
    m = ctx->mrec;
    a = ctx->attr;
    /* Use goto to reduce indentation. */
    if (a->non_resident)
        goto do_non_resident_extend;
    BUG_ON(NInoNonResident(ni));
    /* The total length of the attribute value. */
    attr_len = le32_to_cpu(a->data.resident.value_length);
    /*
     * Extend the attribute record to be able to store the new attribute
     * size.  ntfs_attr_record_resize() will not do anything if the size is
     * not changing.
     */
    if (new_alloc_size < vol->mft_record_size &&
            !ntfs_attr_record_resize(m, a,
            le16_to_cpu(a->data.resident.value_offset) +
            new_alloc_size)) {
        /* The resize succeeded! */
        write_lock_irqsave(&ni->size_lock, flags);
        ni->allocated_size = le32_to_cpu(a->length) -
                le16_to_cpu(a->data.resident.value_offset);
        write_unlock_irqrestore(&ni->size_lock, flags);
        if (new_data_size >= 0) {
            BUG_ON(new_data_size < attr_len);
            a->data.resident.value_length =
                    cpu_to_le32((u32)new_data_size);
        }
        goto flush_done;
    }
    /*
     * We have to drop all the locks so we can call
     * ntfs_attr_make_non_resident().  This could be optimised by try-
     * locking the first page cache page and only if that fails dropping
     * the locks, locking the page, and redoing all the locking and
     * lookups.  While this would be a huge optimisation, it is not worth
     * it as this is definitely a slow code path.
     */
    ntfs_attr_put_search_ctx(ctx);
    unmap_mft_record(base_ni);
    up_write(&ni->runlist.lock);
    /*
     * Not enough space in the mft record, try to make the attribute
     * non-resident and if successful restart the extension process.
     */
    err = ntfs_attr_make_non_resident(ni, attr_len);
    if (likely(!err))
        goto retry_extend;
    /*
     * Could not make non-resident.  If this is due to this not being
     * permitted for this attribute type or there not being enough space,
     * try to make other attributes non-resident.  Otherwise fail.
     */
    if (unlikely(err != -EPERM && err != -ENOSPC)) {
        /* Only emit errors when the write will fail completely. */
        read_lock_irqsave(&ni->size_lock, flags);
        allocated_size = ni->allocated_size;
        read_unlock_irqrestore(&ni->size_lock, flags);
        if (start < 0 || start >= allocated_size)
            ntfs_error(vol->sb, "Cannot extend allocation of "
                    "inode 0x%lx, attribute type 0x%x, "
                    "because the conversion from resident "
                    "to non-resident attribute failed "
                    "with error code %i.", vi->i_ino,
                    (unsigned)le32_to_cpu(ni->type), err);
        if (err != -ENOMEM)
            err = -EIO;
        goto conv_err_out;
    }
    /* TODO: Not implemented from here, abort. */
    read_lock_irqsave(&ni->size_lock, flags);
    allocated_size = ni->allocated_size;
    read_unlock_irqrestore(&ni->size_lock, flags);
    if (start < 0 || start >= allocated_size) {
        if (err == -ENOSPC)
            ntfs_error(vol->sb, "Not enough space in the mft "
                    "record/on disk for the non-resident "
                    "attribute value.  This case is not "
                    "implemented yet.");
        else /* if (err == -EPERM) */
            ntfs_error(vol->sb, "This attribute type may not be "
                    "non-resident.  This case is not "
                    "implemented yet.");
    }
    err = -EOPNOTSUPP;
    goto conv_err_out;
#if 0
    // TODO: Attempt to make other attributes non-resident.
    if (!err)
        goto do_resident_extend;
    /*
     * Both the attribute list attribute and the standard information
     * attribute must remain in the base inode.  Thus, if this is one of
     * these attributes, we have to try to move other attributes out into
     * extent mft records instead.
     */
    if (ni->type == AT_ATTRIBUTE_LIST ||
            ni->type == AT_STANDARD_INFORMATION) {
        // TODO: Attempt to move other attributes into extent mft
        // records.
        err = -EOPNOTSUPP;
        if (!err)
            goto do_resident_extend;
        goto err_out;
    }
    // TODO: Attempt to move this attribute to an extent mft record, but
    // only if it is not already the only attribute in an mft record in
    // which case there would be nothing to gain.
    err = -EOPNOTSUPP;
    if (!err)
        goto do_resident_extend;
    /* There is nothing we can do to make enough space. )-: */
    goto err_out;
#endif
do_non_resident_extend:
    BUG_ON(!NInoNonResident(ni));
    if (new_alloc_size == allocated_size) {
        BUG_ON(vcn);
        goto alloc_done;
    }
    /*
     * If the data starts after the end of the old allocation, this is a
     * $DATA attribute and sparse attributes are enabled on the volume and
     * for this inode, then create a sparse region between the old
     * allocated size and the start of the data.  Otherwise simply proceed
     * with filling the whole space between the old allocated size and the
     * new allocated size with clusters.
     */
    if ((start >= 0 && start <= allocated_size) || ni->type != AT_DATA ||
            !NVolSparseEnabled(vol) || NInoSparseDisabled(ni))
        goto skip_sparse;
    // TODO: This is not implemented yet.  We just fill in with real
    // clusters for now...
    ntfs_debug("Inserting holes is not-implemented yet.  Falling back to "
            "allocating real clusters instead.");
skip_sparse:
    rl = ni->runlist.rl;
    if (likely(rl)) {
        /* Seek to the end of the runlist. */
        while (rl->length)
            rl++;
    }
    /* If this attribute extent is not mapped, map it now. */
    if (unlikely(!rl || rl->lcn == LCN_RL_NOT_MAPPED ||
            (rl->lcn == LCN_ENOENT && rl > ni->runlist.rl &&
            (rl-1)->lcn == LCN_RL_NOT_MAPPED))) {
        if (!rl && !allocated_size)
            goto first_alloc;
        rl = ntfs_mapping_pairs_decompress(vol, a, ni->runlist.rl);
        if (IS_ERR(rl)) {
            err = PTR_ERR(rl);
            if (start < 0 || start >= allocated_size)
                ntfs_error(vol->sb, "Cannot extend allocation "
                        "of inode 0x%lx, attribute "
                        "type 0x%x, because the "
                        "mapping of a runlist "
                        "fragment failed with error "
                        "code %i.", vi->i_ino,
                        (unsigned)le32_to_cpu(ni->type),
                        err);
            if (err != -ENOMEM)
                err = -EIO;
            goto err_out;
        }
        ni->runlist.rl = rl;
        /* Seek to the end of the runlist. */
        while (rl->length)
            rl++;
    }
    /*
     * We now know the runlist of the last extent is mapped and @rl is at
     * the end of the runlist.  We want to begin allocating clusters
     * starting at the last allocated cluster to reduce fragmentation.  If
     * there are no valid LCNs in the attribute we let the cluster
     * allocator choose the starting cluster.
     */
    /* If the last LCN is a hole or simillar seek back to last real LCN. */
    while (rl->lcn < 0 && rl > ni->runlist.rl)
        rl--;
first_alloc:
    // FIXME: Need to implement partial allocations so at least part of the
    // write can be performed when start >= 0.  (Needed for POSIX write(2)
    // conformance.)
    rl2 = ntfs_cluster_alloc(vol, allocated_size >> vol->cluster_size_bits,
            (new_alloc_size - allocated_size) >>
            vol->cluster_size_bits, (rl && (rl->lcn >= 0)) ?
            rl->lcn + rl->length : -1, DATA_ZONE, true);
    if (IS_ERR(rl2)) {
        err = PTR_ERR(rl2);
        if (start < 0 || start >= allocated_size)
            ntfs_error(vol->sb, "Cannot extend allocation of "
                    "inode 0x%lx, attribute type 0x%x, "
                    "because the allocation of clusters "
                    "failed with error code %i.", vi->i_ino,
                    (unsigned)le32_to_cpu(ni->type), err);
        if (err != -ENOMEM && err != -ENOSPC)
            err = -EIO;
        goto err_out;
    }
    rl = ntfs_runlists_merge(ni->runlist.rl, rl2);
    if (IS_ERR(rl)) {
        err = PTR_ERR(rl);
        if (start < 0 || start >= allocated_size)
            ntfs_error(vol->sb, "Cannot extend allocation of "
                    "inode 0x%lx, attribute type 0x%x, "
                    "because the runlist merge failed "
                    "with error code %i.", vi->i_ino,
                    (unsigned)le32_to_cpu(ni->type), err);
        if (err != -ENOMEM)
            err = -EIO;
        if (ntfs_cluster_free_from_rl(vol, rl2)) {
            ntfs_error(vol->sb, "Failed to release allocated "
                    "cluster(s) in error code path.  Run "
                    "chkdsk to recover the lost "
                    "cluster(s).");
            NVolSetErrors(vol);
        }
        ntfs_free(rl2);
        goto err_out;
    }
    ni->runlist.rl = rl;
    ntfs_debug("Allocated 0x%llx clusters.", (long long)(new_alloc_size -
            allocated_size) >> vol->cluster_size_bits);
    /* Find the runlist element with which the attribute extent starts. */
    ll = sle64_to_cpu(a->data.non_resident.lowest_vcn);
    rl2 = ntfs_rl_find_vcn_nolock(rl, ll);
    BUG_ON(!rl2);
    BUG_ON(!rl2->length);
    BUG_ON(rl2->lcn < LCN_HOLE);
    mp_rebuilt = false;
    /* Get the size for the new mapping pairs array for this extent. */
    mp_size = ntfs_get_size_for_mapping_pairs(vol, rl2, ll, -1);
    if (unlikely(mp_size <= 0)) {
        err = mp_size;
        if (start < 0 || start >= allocated_size)
            ntfs_error(vol->sb, "Cannot extend allocation of "
                    "inode 0x%lx, attribute type 0x%x, "
                    "because determining the size for the "
                    "mapping pairs failed with error code "
                    "%i.", vi->i_ino,
                    (unsigned)le32_to_cpu(ni->type), err);
        err = -EIO;
        goto undo_alloc;
    }
    /* Extend the attribute record to fit the bigger mapping pairs array. */
    attr_len = le32_to_cpu(a->length);
    err = ntfs_attr_record_resize(m, a, mp_size +
            le16_to_cpu(a->data.non_resident.mapping_pairs_offset));
    if (unlikely(err)) {
        BUG_ON(err != -ENOSPC);
        // TODO: Deal with this by moving this extent to a new mft
        // record or by starting a new extent in a new mft record,
        // possibly by extending this extent partially and filling it
        // and creating a new extent for the remainder, or by making
        // other attributes non-resident and/or by moving other
        // attributes out of this mft record.
        if (start < 0 || start >= allocated_size)
            ntfs_error(vol->sb, "Not enough space in the mft "
                    "record for the extended attribute "
                    "record.  This case is not "
                    "implemented yet.");
        err = -EOPNOTSUPP;
        goto undo_alloc;
    }
    mp_rebuilt = true;
    /* Generate the mapping pairs array directly into the attr record. */
    err = ntfs_mapping_pairs_build(vol, (u8*)a +
            le16_to_cpu(a->data.non_resident.mapping_pairs_offset),
            mp_size, rl2, ll, -1, NULL);
    if (unlikely(err)) {
        if (start < 0 || start >= allocated_size)
            ntfs_error(vol->sb, "Cannot extend allocation of "
                    "inode 0x%lx, attribute type 0x%x, "
                    "because building the mapping pairs "
                    "failed with error code %i.", vi->i_ino,
                    (unsigned)le32_to_cpu(ni->type), err);
        err = -EIO;
        goto undo_alloc;
    }
    /* Update the highest_vcn. */
    a->data.non_resident.highest_vcn = cpu_to_sle64((new_alloc_size >>
            vol->cluster_size_bits) - 1);
    /*
     * We now have extended the allocated size of the attribute.  Reflect
     * this in the ntfs_inode structure and the attribute record.
     */
    if (a->data.non_resident.lowest_vcn) {
        /*
         * We are not in the first attribute extent, switch to it, but
         * first ensure the changes will make it to disk later.
         */
        flush_dcache_mft_record_page(ctx->ntfs_ino);
        mark_mft_record_dirty(ctx->ntfs_ino);
        ntfs_attr_reinit_search_ctx(ctx);
        err = ntfs_attr_lookup(ni->type, ni->name, ni->name_len,
                CASE_SENSITIVE, 0, NULL, 0, ctx);
        if (unlikely(err))
            goto restore_undo_alloc;
        /* @m is not used any more so no need to set it. */
        a = ctx->attr;
    }
    write_lock_irqsave(&ni->size_lock, flags);
    ni->allocated_size = new_alloc_size;
    a->data.non_resident.allocated_size = cpu_to_sle64(new_alloc_size);
    /*
     * FIXME: This would fail if @ni is a directory, $MFT, or an index,
     * since those can have sparse/compressed set.  For example can be
     * set compressed even though it is not compressed itself and in that
     * case the bit means that files are to be created compressed in the
     * directory...  At present this is ok as this code is only called for
     * regular files, and only for their $DATA attribute(s).
     * FIXME: The calculation is wrong if we created a hole above.  For now
     * it does not matter as we never create holes.
     */
    if (NInoSparse(ni) || NInoCompressed(ni)) {
        ni->itype.compressed.size += new_alloc_size - allocated_size;
        a->data.non_resident.compressed_size =
                cpu_to_sle64(ni->itype.compressed.size);
        vi->i_blocks = ni->itype.compressed.size >> 9;
    } else
        vi->i_blocks = new_alloc_size >> 9;
    write_unlock_irqrestore(&ni->size_lock, flags);
alloc_done:
    if (new_data_size >= 0) {
        BUG_ON(new_data_size <
                sle64_to_cpu(a->data.non_resident.data_size));
        a->data.non_resident.data_size = cpu_to_sle64(new_data_size);
    }
flush_done:
    /* Ensure the changes make it to disk. */
    flush_dcache_mft_record_page(ctx->ntfs_ino);
    mark_mft_record_dirty(ctx->ntfs_ino);
done:
    ntfs_attr_put_search_ctx(ctx);
    unmap_mft_record(base_ni);
    up_write(&ni->runlist.lock);
    ntfs_debug("Done, new_allocated_size 0x%llx.",
            (unsigned long long)new_alloc_size);
    return new_alloc_size;
restore_undo_alloc:
    if (start < 0 || start >= allocated_size)
        ntfs_error(vol->sb, "Cannot complete extension of allocation "
                "of inode 0x%lx, attribute type 0x%x, because "
                "lookup of first attribute extent failed with "
                "error code %i.", vi->i_ino,
                (unsigned)le32_to_cpu(ni->type), err);
    if (err == -ENOENT)
        err = -EIO;
    ntfs_attr_reinit_search_ctx(ctx);
    if (ntfs_attr_lookup(ni->type, ni->name, ni->name_len, CASE_SENSITIVE,
            allocated_size >> vol->cluster_size_bits, NULL, 0,
            ctx)) {
        ntfs_error(vol->sb, "Failed to find last attribute extent of "
                "attribute in error code path.  Run chkdsk to "
                "recover.");
        write_lock_irqsave(&ni->size_lock, flags);
        ni->allocated_size = new_alloc_size;
        /*
         * FIXME: This would fail if @ni is a directory...  See above.
         * FIXME: The calculation is wrong if we created a hole above.
         * For now it does not matter as we never create holes.
         */
        if (NInoSparse(ni) || NInoCompressed(ni)) {
            ni->itype.compressed.size += new_alloc_size -
                    allocated_size;
            vi->i_blocks = ni->itype.compressed.size >> 9;
        } else
            vi->i_blocks = new_alloc_size >> 9;
        write_unlock_irqrestore(&ni->size_lock, flags);
        ntfs_attr_put_search_ctx(ctx);
        unmap_mft_record(base_ni);
        up_write(&ni->runlist.lock);
        /*
         * The only thing that is now wrong is the allocated size of the
         * base attribute extent which chkdsk should be able to fix.
         */
        NVolSetErrors(vol);
        return err;
    }
    ctx->attr->data.non_resident.highest_vcn = cpu_to_sle64(
            (allocated_size >> vol->cluster_size_bits) - 1);
undo_alloc:
    ll = allocated_size >> vol->cluster_size_bits;
    if (ntfs_cluster_free(ni, ll, -1, ctx) < 0) {
        ntfs_error(vol->sb, "Failed to release allocated cluster(s) "
                "in error code path.  Run chkdsk to recover "
                "the lost cluster(s).");
        NVolSetErrors(vol);
    }
    m = ctx->mrec;
    a = ctx->attr;
    /*
     * If the runlist truncation fails and/or the search context is no
     * longer valid, we cannot resize the attribute record or build the
     * mapping pairs array thus we mark the inode bad so that no access to
     * the freed clusters can happen.
     */
    if (ntfs_rl_truncate_nolock(vol, &ni->runlist, ll) || IS_ERR(m)) {
        ntfs_error(vol->sb, "Failed to %s in error code path.  Run "
                "chkdsk to recover.", IS_ERR(m) ?
                "restore attribute search context" :
                "truncate attribute runlist");
        NVolSetErrors(vol);
    } else if (mp_rebuilt) {
        if (ntfs_attr_record_resize(m, a, attr_len)) {
            ntfs_error(vol->sb, "Failed to restore attribute "
                    "record in error code path.  Run "
                    "chkdsk to recover.");
            NVolSetErrors(vol);
        } else /* if (success) */ {
            if (ntfs_mapping_pairs_build(vol, (u8*)a + le16_to_cpu(
                    a->data.non_resident.
                    mapping_pairs_offset), attr_len -
                    le16_to_cpu(a->data.non_resident.
                    mapping_pairs_offset), rl2, ll, -1,
                    NULL)) {
                ntfs_error(vol->sb, "Failed to restore "
                        "mapping pairs array in error "
                        "code path.  Run chkdsk to "
                        "recover.");
                NVolSetErrors(vol);
            }
            flush_dcache_mft_record_page(ctx->ntfs_ino);
            mark_mft_record_dirty(ctx->ntfs_ino);
        }
    }
err_out:
    if (ctx)
        ntfs_attr_put_search_ctx(ctx);
    if (m)
        unmap_mft_record(base_ni);
    up_write(&ni->runlist.lock);
conv_err_out:
    ntfs_debug("Failed.  Returning error code %i.", err);
    return err;
}

int ntfs_attr_set(ntfs_inode *ni, const s64 ofs, const s64 cnt, const u8 val)
{
    ntfs_volume *vol = ni->vol;
    struct address_space *mapping;
    struct page *page;
    u8 *kaddr;
    pgoff_t idx, end;
    unsigned start_ofs, end_ofs, size;

    ntfs_debug("Entering for ofs 0x%llx, cnt 0x%llx, val 0x%hx.",
            (long long)ofs, (long long)cnt, val);
    BUG_ON(ofs < 0);
    BUG_ON(cnt < 0);
    if (!cnt)
        goto done;
    /*
     * FIXME: Compressed and encrypted attributes are not supported when
     * writing and we should never have gotten here for them.
     */
    BUG_ON(NInoCompressed(ni));
    BUG_ON(NInoEncrypted(ni));
    mapping = VFS_I(ni)->i_mapping;
    /* Work out the starting index and page offset. */
    idx = ofs >> PAGE_CACHE_SHIFT;
    start_ofs = ofs & ~PAGE_CACHE_MASK;
    /* Work out the ending index and page offset. */
    end = ofs + cnt;
    end_ofs = end & ~PAGE_CACHE_MASK;
    /* If the end is outside the inode size return -ESPIPE. */
    if (unlikely(end > i_size_read(VFS_I(ni)))) {
        ntfs_error(vol->sb, "Request exceeds end of attribute.");
        return -ESPIPE;
    }
    end >>= PAGE_CACHE_SHIFT;
    /* If there is a first partial page, need to do it the slow way. */
    if (start_ofs) {
        page = read_mapping_page(mapping, idx, NULL);
        if (IS_ERR(page)) {
            ntfs_error(vol->sb, "Failed to read first partial "
                    "page (error, index 0x%lx).", idx);
            return PTR_ERR(page);
        }
        /*
         * If the last page is the same as the first page, need to
         * limit the write to the end offset.
         */
        size = PAGE_CACHE_SIZE;
        if (idx == end)
            size = end_ofs;
        kaddr = kmap_atomic(page);
        memset(kaddr + start_ofs, val, size - start_ofs);
        flush_dcache_page(page);
        kunmap_atomic(kaddr);
        set_page_dirty(page);
        page_cache_release(page);
        balance_dirty_pages_ratelimited(mapping);
        cond_resched();
        if (idx == end)
            goto done;
        idx++;
    }
    /* Do the whole pages the fast way. */
    for (; idx < end; idx++) {
        /* Find or create the current page.  (The page is locked.) */
        page = grab_cache_page(mapping, idx);
        if (unlikely(!page)) {
            ntfs_error(vol->sb, "Insufficient memory to grab "
                    "page (index 0x%lx).", idx);
            return -ENOMEM;
        }
        kaddr = kmap_atomic(page);
        memset(kaddr, val, PAGE_CACHE_SIZE);
        flush_dcache_page(page);
        kunmap_atomic(kaddr);
        /*
         * If the page has buffers, mark them uptodate since buffer
         * state and not page state is definitive in 2.6 kernels.
         */
        if (page_has_buffers(page)) {
            struct buffer_head *bh, *head;

            bh = head = page_buffers(page);
            do {
                set_buffer_uptodate(bh);
            } while ((bh = bh->b_this_page) != head);
        }
        /* Now that buffers are uptodate, set the page uptodate, too. */
        SetPageUptodate(page);
        /*
         * Set the page and all its buffers dirty and mark the inode
         * dirty, too.  The VM will write the page later on.
         */
        set_page_dirty(page);
        /* Finally unlock and release the page. */
        unlock_page(page);
        page_cache_release(page);
        balance_dirty_pages_ratelimited(mapping);
        cond_resched();
    }
    /* If there is a last partial page, need to do it the slow way. */
    if (end_ofs) {
        page = read_mapping_page(mapping, idx, NULL);
        if (IS_ERR(page)) {
            ntfs_error(vol->sb, "Failed to read last partial page "
                    "(error, index 0x%lx).", idx);
            return PTR_ERR(page);
        }
        kaddr = kmap_atomic(page);
        memset(kaddr, val, end_ofs);
        flush_dcache_page(page);
        kunmap_atomic(kaddr);
        set_page_dirty(page);
        page_cache_release(page);
        balance_dirty_pages_ratelimited(mapping);
        cond_resched();
    }
done:
    ntfs_debug("Done.");
    return 0;
}

#endif /* NTFS_RW */