outaout.c

nasm早期的源代码,比较简单是学习汇编和编译原理的好例子

    } else if (segment == sdata.index) {
        sym->type |= SECT_DATA;
        if (is_global) {
            sym->next = sdata.gsyms;
            sdata.gsyms = sym;
        } else if (!sdata.asym)
            sdata.asym = sym;
    } else if (segment == sbss.index) {
        sym->type |= SECT_BSS;
        if (is_global) {
            sym->next = sbss.gsyms;
            sbss.gsyms = sym;
        } else if (!sbss.asym)
            sbss.asym = sym;
    } else
        sym->type = SYM_GLOBAL;
    if (is_global == 2)
        sym->value = offset;
    else
        sym->value = (sym->type == SYM_GLOBAL ? 0 : offset);

    if (is_global && sym->type != SYM_GLOBAL) {
        /*
         * Global symbol exported _from_ this module. We must check
         * the special text for type information.
         */

        if (special) {
            int n = strcspn(special, " ");

            if (!nasm_strnicmp(special, "function", n))
                sym->type |= SYM_FUNCTION;
            else if (!nasm_strnicmp(special, "data", n) ||
                     !nasm_strnicmp(special, "object", n))
                sym->type |= SYM_DATA;
            else
                error(ERR_NONFATAL, "unrecognised symbol type `%.*s'",
                      n, special);
            if (special[n]) {
                struct tokenval tokval;
                expr *e;
                int fwd = false;
                char *saveme = stdscan_bufptr;  /* bugfix? fbk 8/10/00 */

                if (!bsd) {
                    error(ERR_NONFATAL, "Linux a.out does not support"
                          " symbol size information");
                } else {
                    while (special[n] && isspace(special[n]))
                        n++;
                    /*
                     * We have a size expression; attempt to
                     * evaluate it.
                     */
                    sym->type |= SYM_WITH_SIZE;
                    stdscan_reset();
                    stdscan_bufptr = special + n;
                    tokval.t_type = TOKEN_INVALID;
                    e = evaluate(stdscan, NULL, &tokval, &fwd, 0, error,
                                 NULL);
                    if (fwd) {
                        sym->nextfwd = fwds;
                        fwds = sym;
                        sym->name = nasm_strdup(name);
                    } else if (e) {
                        if (!is_simple(e))
                            error(ERR_NONFATAL, "cannot use relocatable"
                                  " expression as symbol size");
                        else
                            sym->size = reloc_value(e);
                    }
                }
                stdscan_bufptr = saveme;        /* bugfix? fbk 8/10/00 */
            }
            special_used = true;
        }
    }

    /*
     * define the references from external-symbol segment numbers
     * to these symbol records.
     */
    if (segment != NO_SEG && segment != stext.index &&
        segment != sdata.index && segment != sbss.index)
        bsym = raa_write(bsym, segment, nsyms);
    sym->symnum = nsyms;

    nsyms++;
    if (sym->type & SYM_WITH_SIZE)
        nsyms++;                /* and another for the size */

    if (special && !special_used)
        error(ERR_NONFATAL, "no special symbol features supported here");
}

static void aout_add_reloc(struct Section *sect, int32_t segment,
                           int reltype, int bytes)
{
    struct Reloc *r;

    r = *sect->tail = nasm_malloc(sizeof(struct Reloc));
    sect->tail = &r->next;
    r->next = NULL;

    r->address = sect->len;
    r->symbol = (segment == NO_SEG ? -SECT_ABS :
                 segment == stext.index ? -SECT_TEXT :
                 segment == sdata.index ? -SECT_DATA :
                 segment == sbss.index ? -SECT_BSS :
                 raa_read(bsym, segment));
    r->reltype = reltype;
    if (r->symbol >= 0)
        r->reltype |= RELTYPE_SYMFLAG;
    r->bytes = bytes;

    sect->nrelocs++;
}

/*
 * This routine deals with ..got and ..sym relocations: the more
 * complicated kinds. In shared-library writing, some relocations
 * with respect to global symbols must refer to the precise symbol
 * rather than referring to an offset from the base of the section
 * _containing_ the symbol. Such relocations call to this routine,
 * which searches the symbol list for the symbol in question.
 *
 * RELTYPE_GOT references require the _exact_ symbol address to be
 * used; RELTYPE_ABSOLUTE references can be at an offset from the
 * symbol. The boolean argument `exact' tells us this.
 *
 * Return value is the adjusted value of `addr', having become an
 * offset from the symbol rather than the section. Should always be
 * zero when returning from an exact call.
 *
 * Limitation: if you define two symbols at the same place,
 * confusion will occur.
 *
 * Inefficiency: we search, currently, using a linked list which
 * isn't even necessarily sorted.
 */
static int32_t aout_add_gsym_reloc(struct Section *sect,
                                int32_t segment, int32_t offset,
                                int type, int bytes, int exact)
{
    struct Symbol *sym, *sm, *shead;
    struct Reloc *r;

    /*
     * First look up the segment to find whether it's text, data,
     * bss or an external symbol.
     */
    shead = NULL;
    if (segment == stext.index)
        shead = stext.gsyms;
    else if (segment == sdata.index)
        shead = sdata.gsyms;
    else if (segment == sbss.index)
        shead = sbss.gsyms;
    if (!shead) {
        if (exact && offset != 0)
            error(ERR_NONFATAL, "unable to find a suitable global symbol"
                  " for this reference");
        else
            aout_add_reloc(sect, segment, type, bytes);
        return offset;
    }

    if (exact) {
        /*
         * Find a symbol pointing _exactly_ at this one.
         */
        for (sym = shead; sym; sym = sym->next)
            if (sym->value == offset)
                break;
    } else {
        /*
         * Find the nearest symbol below this one.
         */
        sym = NULL;
        for (sm = shead; sm; sm = sm->next)
            if (sm->value <= offset && (!sym || sm->value > sym->value))
                sym = sm;
    }
    if (!sym && exact) {
        error(ERR_NONFATAL, "unable to find a suitable global symbol"
              " for this reference");
        return 0;
    }

    r = *sect->tail = nasm_malloc(sizeof(struct Reloc));
    sect->tail = &r->next;
    r->next = NULL;

    r->address = sect->len;
    r->symbol = sym->symnum;
    r->reltype = type | RELTYPE_SYMFLAG;
    r->bytes = bytes;

    sect->nrelocs++;

    return offset - sym->value;
}

/*
 * This routine deals with ..gotoff relocations. These _must_ refer
 * to a symbol, due to a perversity of *BSD's PIC implementation,
 * and it must be a non-global one as well; so we store `asym', the
 * first nonglobal symbol defined in each section, and always work
 * from that. Relocation type is always RELTYPE_GOTOFF.
 *
 * Return value is the adjusted value of `addr', having become an
 * offset from the `asym' symbol rather than the section.
 */
static int32_t aout_add_gotoff_reloc(struct Section *sect, int32_t segment,
                                  int32_t offset, int bytes)
{
    struct Reloc *r;
    struct Symbol *asym;

    /*
     * First look up the segment to find whether it's text, data,
     * bss or an external symbol.
     */
    asym = NULL;
    if (segment == stext.index)
        asym = stext.asym;
    else if (segment == sdata.index)
        asym = sdata.asym;
    else if (segment == sbss.index)
        asym = sbss.asym;
    if (!asym)
        error(ERR_NONFATAL, "`..gotoff' relocations require a non-global"
              " symbol in the section");

    r = *sect->tail = nasm_malloc(sizeof(struct Reloc));
    sect->tail = &r->next;
    r->next = NULL;

    r->address = sect->len;
    r->symbol = asym->symnum;
    r->reltype = RELTYPE_GOTOFF;
    r->bytes = bytes;

    sect->nrelocs++;

    return offset - asym->value;
}

static void aout_out(int32_t segto, const void *data, uint32_t type,
                     int32_t segment, int32_t wrt)
{
    struct Section *s;
    int32_t realbytes = type & OUT_SIZMASK;
    int32_t addr;
    uint8_t mydata[4], *p;

    type &= OUT_TYPMASK;

    /*
     * handle absolute-assembly (structure definitions)
     */
    if (segto == NO_SEG) {
        if (type != OUT_RESERVE)
            error(ERR_NONFATAL, "attempt to assemble code in [ABSOLUTE]"
                  " space");
        return;
    }

    if (segto == stext.index)
        s = &stext;
    else if (segto == sdata.index)
        s = &sdata;
    else if (segto == sbss.index)
        s = NULL;
    else {
        error(ERR_WARNING, "attempt to assemble code in"
              " segment %d: defaulting to `.text'", segto);
        s = &stext;
    }

    if (!s && type != OUT_RESERVE) {
        error(ERR_WARNING, "attempt to initialize memory in the"
              " BSS section: ignored");
        if (type == OUT_REL2ADR)
            realbytes = 2;
        else if (type == OUT_REL4ADR)
            realbytes = 4;
        sbss.len += realbytes;
        return;
    }

    if (type == OUT_RESERVE) {
        if (s) {
            error(ERR_WARNING, "uninitialized space declared in"
                  " %s section: zeroing",
                  (segto == stext.index ? "code" : "data"));
            aout_sect_write(s, NULL, realbytes);
        } else
            sbss.len += realbytes;
    } else if (type == OUT_RAWDATA) {
        if (segment != NO_SEG)
            error(ERR_PANIC, "OUT_RAWDATA with other than NO_SEG");
        aout_sect_write(s, data, realbytes);
    } else if (type == OUT_ADDRESS) {
        addr = *(int32_t *)data;
        if (segment != NO_SEG) {
            if (segment % 2) {
                error(ERR_NONFATAL, "a.out format does not support"
                      " segment base references");
            } else {
                if (wrt == NO_SEG) {
                    aout_add_reloc(s, segment, RELTYPE_ABSOLUTE,
                                   realbytes);
                } else if (!bsd) {
                    error(ERR_NONFATAL,
                          "Linux a.out format does not support"
                          " any use of WRT");
                    wrt = NO_SEG;       /* we can at least _try_ to continue */
                } else if (wrt == aout_gotpc_sect + 1) {
                    is_pic = 0x40;
                    aout_add_reloc(s, segment, RELTYPE_GOTPC, realbytes);
                } else if (wrt == aout_gotoff_sect + 1) {