outelf64.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

/* outelf.c	output routines for the Netwide Assembler to produce
 *		ELF64 (x86_64 of course) object file format
 *
 * The Netwide Assembler is copyright (C) 1996 Simon Tatham and
 * Julian Hall. All rights reserved. The software is
 * redistributable under the licence given in the file "Licence"
 * distributed in the NASM archive.
 */

#include "compiler.h"

#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <ctype.h>
#include <inttypes.h>

#include "nasm.h"
#include "nasmlib.h"
#include "stdscan.h"
#include "outform.h"

/* Definitions in lieu of elf.h */

#define SHT_PROGBITS 1
#define SHT_RELA	  4		/* Relocation entries with addends */
#define SHT_NOBITS 8
#define SHF_WRITE	     (1 << 0)	/* Writable */
#define SHF_ALLOC	     (1 << 1)	/* Occupies memory during execution */
#define SHF_EXECINSTR	     (1 << 2)	/* Executable */
#define SHN_ABS		0xfff1		/* Associated symbol is absolute */
#define SHN_COMMON	0xfff2		/* Associated symbol is common */
#define R_X86_64_NONE		0	/* No reloc */
#define R_X86_64_64		1	/* Direct 64 bit address */
#define R_X86_64_PC32		2	/* PC relative 32 bit signed */
#define R_X86_64_GOT32		3	/* 32 bit GOT entry */
#define R_X86_64_PLT32		4	/* 32 bit PLT address */
#define R_X86_64_GOTPCREL	9	/* 32 bit signed PC relative */
#define R_X86_64_32		10	/* Direct 32 bit zero extended */
#define R_X86_64_16		12	/* Direct 16 bit zero extended */
#define R_X86_64_PC16		13	/* 16 bit sign extended pc relative */
#define R_X86_64_GOTTPOFF	22	/* 32 bit signed PC relative offset */
#define ET_REL		1		/* Relocatable file */
#define EM_X86_64	62		/* AMD x86-64 architecture */
typedef uint32_t Elf64_Word;
typedef uint64_t Elf64_Xword;
typedef uint64_t Elf64_Addr;
typedef uint64_t Elf64_Off;
typedef struct
{
  Elf64_Word	sh_name;		/* Section name (string tbl index) */
  Elf64_Word	sh_type;		/* Section type */
  Elf64_Xword	sh_flags;		/* Section flags */
  Elf64_Addr	sh_addr;		/* Section virtual addr at execution */
  Elf64_Off	sh_offset;		/* Section file offset */
  Elf64_Xword	sh_size;		/* Section size in bytes */
  Elf64_Word	sh_link;		/* Link to another section */
  Elf64_Word	sh_info;		/* Additional section information */
  Elf64_Xword	sh_addralign;		/* Section alignment */
  Elf64_Xword	sh_entsize;		/* Entry size if section holds table */
} Elf64_Shdr;


#ifdef OF_ELF64


struct Reloc {
    struct Reloc *next;
    int64_t address;               /* relative to _start_ of section */
    int64_t symbol;                /* ELF symbol info thingy */
    int type;                   /* type of relocation */
};

struct Symbol {
    int32_t strpos;                /* string table position of name */
    int32_t section;               /* section ID of the symbol */
    int type;                   /* symbol type */
    int other;                     /* symbol visibility */
    int64_t value;                 /* address, or COMMON variable align */
    int32_t size;                  /* size of symbol */
    int32_t globnum;               /* symbol table offset if global */
    struct Symbol *next;        /* list of globals in each section */
    struct Symbol *nextfwd;     /* list of unresolved-size symbols */
    char *name;                 /* used temporarily if in above list */
};


struct Section {
    struct SAA *data;
    uint32_t len, size, nrelocs;
    int32_t index;
    int type;                   /* SHT_PROGBITS or SHT_NOBITS */
    int align;                  /* alignment: power of two */
    uint32_t flags;        /* section flags */
    char *name;
    struct SAA *rel;
    int32_t rellen;
    struct Reloc *head, **tail;
    struct Symbol *gsyms;       /* global symbols in section */
};

#define SECT_DELTA 32
static struct Section **sects;
static int nsects, sectlen;

#define SHSTR_DELTA 256
static char *shstrtab;
static int shstrtablen, shstrtabsize;

static struct SAA *syms;
static uint32_t nlocals, nglobs;

static int32_t def_seg;

static struct RAA *bsym;

static struct SAA *strs;
static uint32_t strslen;

static FILE *elffp;
static efunc error;
static evalfunc evaluate;

static struct Symbol *fwds;

static char elf_module[FILENAME_MAX];

extern struct ofmt of_elf64;

#define SHN_UNDEF 0

#define SYM_SECTION 0x04
#define SYM_GLOBAL 0x10
#define SYM_NOTYPE 0x00
#define SYM_DATA 0x01
#define SYM_FUNCTION 0x02

#define STV_DEFAULT 0
#define STV_INTERNAL 1
#define STV_HIDDEN 2
#define STV_PROTECTED 3

#define GLOBAL_TEMP_BASE 16     /* bigger than any constant sym id */

#define SEG_ALIGN 16            /* alignment of sections in file */
#define SEG_ALIGN_1 (SEG_ALIGN-1)

static const char align_str[SEG_ALIGN] = "";    /* ANSI will pad this with 0s */

#define ELF_MAX_SECTIONS 16     /* really 10, but let's play safe */
static struct ELF_SECTDATA {
    void *data;
    int32_t len;
    bool is_saa;
} *elf_sects;
static int elf_nsect;
static int32_t elf_foffs;

static void elf_write(void);
static void elf_sect_write(struct Section *, const uint8_t *,
                           uint32_t);
static void elf_section_header(int, int, int, void *, bool, int32_t, int, int,
                               int, int);
static void elf_write_sections(void);
static struct SAA *elf_build_symtab(int32_t *, int32_t *);
static struct SAA *elf_build_reltab(int32_t *, struct Reloc *);
static void add_sectname(char *, char *);

/* this stuff is needed for the stabs debugging format */
#define N_SO 0x64               /* ID for main source file */
#define N_SOL 0x84              /* ID for sub-source file */
#define N_BINCL 0x82
#define N_EINCL 0xA2
#define N_SLINE 0x44
#define TY_STABSSYMLIN 0x40     /* ouch */

struct stabentry {
    uint32_t n_strx;
    uint8_t n_type;
    uint8_t n_other;
    uint16_t n_desc;
    uint32_t n_value;
};

struct erel {
    int offset, info;
};

struct symlininfo {
    int offset;
    int section;                /* section index */
    char *name;                 /* shallow-copied pointer of section name */
};

struct linelist {
    struct symlininfo info;
    int line;
    char *filename;
    struct linelist *next;
    struct linelist *last;
};

static struct linelist *stabslines = 0;
static int stabs_immcall = 0;
static int currentline = 0;
static int numlinestabs = 0;
static char *stabs_filename = 0;
static int symtabsection;
static uint8_t *stabbuf = 0, *stabstrbuf = 0, *stabrelbuf = 0;
static int stablen, stabstrlen, stabrellen;

static struct dfmt df_stabs;

void stabs64_init(struct ofmt *, void *, FILE *, efunc);
void stabs64_linenum(const char *filename, int32_t linenumber, int32_t);
void stabs64_deflabel(char *, int32_t, int32_t, int, char *);
void stabs64_directive(const char *, const char *);
void stabs64_typevalue(int32_t);
void stabs64_output(int, void *);
void stabs64_generate(void);
void stabs64_cleanup(void);

/* end of stabs debugging stuff */

/*
 * Special section numbers which are used to define ELF special
 * symbols, which can be used with WRT to provide PIC relocation
 * types.
 */
static int32_t elf_gotpc_sect, elf_gotoff_sect;
static int32_t elf_got_sect, elf_plt_sect;
static int32_t elf_sym_sect;

static void elf_init(FILE * fp, efunc errfunc, ldfunc ldef, evalfunc eval)
{
    maxbits = 64;
    elffp = fp;
    error = errfunc;
    evaluate = eval;
    (void)ldef;                 /* placate optimisers */
    sects = NULL;
    nsects = sectlen = 0;
    syms = saa_init((int32_t)sizeof(struct Symbol));
    nlocals = nglobs = 0;
    bsym = raa_init();
    strs = saa_init(1L);
    saa_wbytes(strs, "\0", 1L);
    saa_wbytes(strs, elf_module, (int32_t)(strlen(elf_module) + 1));
    strslen = 2 + strlen(elf_module);
    shstrtab = NULL;
    shstrtablen = shstrtabsize = 0;;
    add_sectname("", "");

    fwds = NULL;

    elf_gotpc_sect = seg_alloc();
    ldef("..gotpc", elf_gotpc_sect + 1, 0L, NULL, false, false, &of_elf64,
         error);
    elf_gotoff_sect = seg_alloc();
    ldef("..gotoff", elf_gotoff_sect + 1, 0L, NULL, false, false, &of_elf64,
         error);
    elf_got_sect = seg_alloc();
    ldef("..got", elf_got_sect + 1, 0L, NULL, false, false, &of_elf64,
         error);
    elf_plt_sect = seg_alloc();
    ldef("..plt", elf_plt_sect + 1, 0L, NULL, false, false, &of_elf64,
         error);
    elf_sym_sect = seg_alloc();
    ldef("..sym", elf_sym_sect + 1, 0L, NULL, false, false, &of_elf64,
         error);

    def_seg = seg_alloc();
}

static void elf_cleanup(int debuginfo)
{
    struct Reloc *r;
    int i;

    (void)debuginfo;

    elf_write();
    fclose(elffp);
    for (i = 0; i < nsects; i++) {
        if (sects[i]->type != SHT_NOBITS)
            saa_free(sects[i]->data);
        if (sects[i]->head)
            saa_free(sects[i]->rel);
        while (sects[i]->head) {
            r = sects[i]->head;
            sects[i]->head = sects[i]->head->next;
            nasm_free(r);
        }
    }
    nasm_free(sects);
    saa_free(syms);
    raa_free(bsym);
    saa_free(strs);
    if (of_elf64.current_dfmt) {
        of_elf64.current_dfmt->cleanup();
    }
}

static void add_sectname(char *firsthalf, char *secondhalf)
{
    int len = strlen(firsthalf) + strlen(secondhalf);
    while (shstrtablen + len + 1 > shstrtabsize)
        shstrtab = nasm_realloc(shstrtab, (shstrtabsize += SHSTR_DELTA));
    strcpy(shstrtab + shstrtablen, firsthalf);
    strcat(shstrtab + shstrtablen, secondhalf);
    shstrtablen += len + 1;
}

static int elf_make_section(char *name, int type, int flags, int align)
{
    struct Section *s;

    s = nasm_malloc(sizeof(*s));

    if (type != SHT_NOBITS)
        s->data = saa_init(1L);
    s->head = NULL;
    s->tail = &s->head;
    s->len = s->size = 0;
    s->nrelocs = 0;
    if (!strcmp(name, ".text"))
        s->index = def_seg;
    else
        s->index = seg_alloc();
    add_sectname("", name);
    s->name = nasm_malloc(1 + strlen(name));
    strcpy(s->name, name);
    s->type = type;
    s->flags = flags;
    s->align = align;
    s->gsyms = NULL;

    if (nsects >= sectlen)
        sects =
            nasm_realloc(sects, (sectlen += SECT_DELTA) * sizeof(*sects));
    sects[nsects++] = s;

    return nsects - 1;
}

static int32_t elf_section_names(char *name, int pass, int *bits)
{
    char *p;
    int flags_and, flags_or, type, align, i;

    /*
     * Default is 64 bits.
     */
    if (!name) {
        *bits = 64;
        return def_seg;
    }

    p = name;
    while (*p && !isspace(*p))
        p++;
    if (*p)
        *p++ = '\0';
    flags_and = flags_or = type = align = 0;

    while (*p && isspace(*p))
        p++;
    while (*p) {
        char *q = p;
        while (*p && !isspace(*p))
            p++;
        if (*p)
            *p++ = '\0';
        while (*p && isspace(*p))
            p++;

        if (!nasm_strnicmp(q, "align=", 6)) {
            align = atoi(q + 6);
            if (align == 0)
                align = 1;
            if ((align - 1) & align) {  /* means it's not a power of two */
                error(ERR_NONFATAL, "section alignment %d is not"
                      " a power of two", align);
                align = 1;
            }
        } else if (!nasm_stricmp(q, "alloc")) {
            flags_and |= SHF_ALLOC;
            flags_or |= SHF_ALLOC;
        } else if (!nasm_stricmp(q, "noalloc")) {
            flags_and |= SHF_ALLOC;
            flags_or &= ~SHF_ALLOC;
        } else if (!nasm_stricmp(q, "exec")) {
            flags_and |= SHF_EXECINSTR;
            flags_or |= SHF_EXECINSTR;
        } else if (!nasm_stricmp(q, "noexec")) {
            flags_and |= SHF_EXECINSTR;
            flags_or &= ~SHF_EXECINSTR;
        } else if (!nasm_stricmp(q, "write")) {
            flags_and |= SHF_WRITE;
            flags_or |= SHF_WRITE;