Hojun-Cho/ww
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

w6a+w6l: DATAR directive for absolute-address relocs in .data

Browse Source 
Unblock literal initialisers for str/slice/struct globals by wiring
an R_X86_64_64 relocation kind through both assembler and static
linker.

w6a:
  - new A_DATAR directive, syntax `DATAR slot+off(SB),target(SB)`,
    records an R_X86_64_64 reloc at slot+off in .data pointing at
    target. The slot must be pre-defined by a prior DATAW;
  - parse_operand learned the `name+disp(SB)` shape so the slot's
    byte offset can be addressed explicitly;
  - Areloc carries a `section` flag (0=.text / 1=.data) and obj.c
    splits the reloc list into .rela.text and .rela.data, emitting
    the latter conditionally with sh_info pointing at .data.

w6l:
  - Lrel grows the same `section` flag; obj.c loads `.rela.data`
    sections into the global reloc list with offsets shifted by
    each input's data_off;
  - pass.c handles R_X86_64_64: target VA is data_va+sym.val for
    in_data symbols (else text_va+sym.val), addend is added, and
    the 8-byte slot is patched in l->data (or l->text).

Inputs without DATAR are unaffected — bootstrap, 991 (selfhost .o
diff) and 992 (selfhost exe diff) keep their byte-identical
output. 520_datar covers the new path: asm a DATAW+DATAR pair,
verify .rela.data has exactly one R_X86_64_64 entry, link, run,
confirm the relocated pointer feeds a 5-byte write that prints
"hello".

Selfhost mirror + w6c emission for str/slice/struct literal init
land in follow-ups.
This commit is contained in:
Hojun-Cho
2026-05-12 12:45:11 +09:00
parent 00d1120441
commit d998425391
11 changed files with 353 additions and 21 deletions
Download Patch File Download Diff File Expand all files Collapse all files

56
cmd/w6a/obj.c
View File

@@ -111,27 +111,42 @@ typedef struct {
int
a_emit_elf(Asm *a, FILE *f)
{
Buf shstr = {0}, str = {0}, sym = {0}, rela = {0};
Buf shstr = {0}, str = {0}, sym = {0}, rela = {0}, relad = {0};
stput(&shstr, ""); /* idx 0 = empty */
stput(&str, "");
const int has_data = (a->datalen > 0);
int has_data_relocs = 0;
for (Areloc *r = a->relocs; r; r = r->next) {
if (r->section == 1) { has_data_relocs = 1; break; }
}
/* Section indices.
* Without data: 1=.text, 2=.rela.text, 3=.symtab, 4=.strtab, 5=.shstrtab
* With data: 1=.text, 2=.rela.text, 3=.data, 4=.symtab, 5=.strtab, 6=.shstrtab
* Without data, without data-relocs:
* 1=.text, 2=.rela.text, 3=.symtab, 4=.strtab, 5=.shstrtab
* With data, no data-relocs:
* 1=.text, 2=.rela.text, 3=.data, 4=.symtab, 5=.strtab, 6=.shstrtab
* With data + data-relocs:
* 1=.text, 2=.rela.text, 3=.data, 4=.rela.data, 5=.symtab,
* 6=.strtab, 7=.shstrtab
*/
const u16 SH_TEXT = 1;
const u16 SH_DATA = has_data ? 3 : 0;
const u16 SH_SYMTAB = has_data ? 4 : 3;
const u16 SH_STRTAB = has_data ? 5 : 4;
const u16 SH_SHSTR = has_data ? 6 : 5;
const u16 SH_RELAD = (has_data && has_data_relocs) ? 4 : 0;
const u16 SH_SYMTAB = has_data
? (has_data_relocs ? 5 : 4)
: 3;
const u16 SH_STRTAB = (u16)(SH_SYMTAB + 1);
const u16 SH_SHSTR = (u16)(SH_STRTAB + 1);
/* Section name offsets. Append .data's name only when used so the
* .shstrtab buffer stays byte-identical for the no-DATAW case. */
* .shstrtab buffer stays byte-identical for the no-DATAW case.
* Same for .rela.data — only present when data relocs exist. */
u32 shn_text = stput(&shstr, ".text");
u32 shn_rela = stput(&shstr, ".rela.text");
u32 shn_data = has_data ? stput(&shstr, ".data") : 0;
u32 shn_relad = (has_data && has_data_relocs)
? stput(&shstr, ".rela.data") : 0;
u32 shn_symtab = stput(&shstr, ".symtab");
u32 shn_strtab = stput(&shstr, ".strtab");
u32 shn_shstrtab = stput(&shstr, ".shstrtab");
@@ -168,13 +183,14 @@ a_emit_elf(Asm *a, FILE *f)
s->idx = idx++;
}
/* Build relocations */
/* Build relocations — split into two buffers so we can emit
* .rela.text and (conditionally) .rela.data separately. */
for (Areloc *r = a->relocs; r; r = r->next) {
Rela64 re;
re.r_offset = r->off;
re.r_info = ELF64_R_INFO((u64)r->sym->idx, (u64)r->kind);
re.r_addend = r->addend;
bput(&rela, &re, sizeof re);
bput(r->section == 1 ? &relad : &rela, &re, sizeof re);
}
/* Layout offsets in the file */
@@ -182,13 +198,16 @@ a_emit_elf(Asm *a, FILE *f)
u64 off_text = off; off += a->textlen;
u64 off_rela = off; off += rela.n;
u64 off_data = off; if (has_data) off += a->datalen;
u64 off_relad = off; if (has_data && has_data_relocs) off += relad.n;
u64 off_sym = off; off += sym.n;
u64 off_str = off; off += str.n;
u64 off_shstr= off; off += shstr.n;
/* align to 8 */
while (off % 8) off++;
u64 off_shdr = off;
const int NSECT = has_data ? 7 : 6; /* null + reals */
const int NSECT = has_data
? (has_data_relocs ? 8 : 7)
: 6; /* null + reals */
Ehdr eh = {0};
memcpy(eh.e_ident, "\x7f""ELF", 4);
@@ -208,6 +227,7 @@ a_emit_elf(Asm *a, FILE *f)
if (a->textlen) fwrite(a->text, 1, a->textlen, f);
fwrite(rela.p, 1, rela.n, f);
if (has_data) fwrite(a->data, 1, a->datalen, f);
if (has_data && has_data_relocs) fwrite(relad.p, 1, relad.n, f);
fwrite(sym.p, 1, sym.n, f);
fwrite(str.p, 1, str.n, f);
fwrite(shstr.p, 1, shstr.n, f);
@@ -249,6 +269,20 @@ a_emit_elf(Asm *a, FILE *f)
fwrite(&sh, 1, sizeof sh, f);
}
if (has_data && has_data_relocs) {
memset(&sh, 0, sizeof sh);
sh.sh_name = shn_relad;
sh.sh_type = SHT_RELA;
sh.sh_flags = SHF_INFO_LINK;
sh.sh_offset = off_relad;
sh.sh_size = relad.n;
sh.sh_link = SH_SYMTAB;
sh.sh_info = SH_DATA; /* applies to .data */
sh.sh_addralign = 8;
sh.sh_entsize = sizeof(Rela64);
fwrite(&sh, 1, sizeof sh, f);
}
memset(&sh, 0, sizeof sh);
sh.sh_name = shn_symtab;
sh.sh_type = SHT_SYMTAB;
@@ -276,6 +310,6 @@ a_emit_elf(Asm *a, FILE *f)
sh.sh_addralign = 1;
fwrite(&sh, 1, sizeof sh, f);
free(shstr.p); free(str.p); free(sym.p); free(rela.p);
free(shstr.p); free(str.p); free(sym.p); free(rela.p); free(relad.p);
return 0;
}