Hojun-Cho
38e0b6510a
Second step toward top-level mutable `let`. The static path now loads .data PROGBITS sections from input .o files, page-aligns them after .text, and emits a second PT_LOAD (R+W) covering them. Relocations targeting data symbols compute against the data VA; text→text displacements still cancel the absolute VAs and stay correct. Inputs without any .data keep the original single-PT_LOAD layout byte-for-byte — 992 (selfhost w6l .o diff) and 995 (self-rebuild) depend on that invariant. Dynamic-link path (-l/-L) rejects .data for now with a clear error; folding writable globals into the existing R+W segment alongside .got.plt/.dynamic is a follow-up.
98 lines
2.7 KiB
C
98 lines
2.7 KiB
C
/*
|
|
* pass.c — resolution + relocation. After all objects are loaded:
|
|
*
|
|
* l_resolve : check that every symbol referenced by a relocation
|
|
* is defined somewhere. Errors get logged.
|
|
* l_relocate: with the final virtual base address known, walk the
|
|
* relocation list and patch the .text bytes in place.
|
|
*
|
|
* Supported relocation kinds: PC32 (2), PLT32 (4). Both are PC-relative
|
|
* 32-bit displacements; for static linking PLT32 collapses to PC32.
|
|
*/
|
|
#include "l.h"
|
|
#include <stdio.h>
|
|
#include <string.h>
|
|
|
|
#define R_X86_64_PC32 2
|
|
#define R_X86_64_PLT32 4
|
|
|
|
int
|
|
l_resolve(Lnk *l)
|
|
{
|
|
/* Initialise dynamic-linking fields. plt_idx and dynsym_idx
|
|
* default to -1; l_intern sets is_dyn/dyn_lib to 0/NULL via
|
|
* calloc, but we make the invariants explicit here for clarity. */
|
|
for (Lsym *s = l->syms; s; s = s->next) {
|
|
s->plt_idx = -1;
|
|
s->dynsym_idx = -1;
|
|
}
|
|
|
|
/* Promote each undefined sym that some Lso exports to "dynamic"
|
|
* and hand it a PLT slot. Order is the iteration order over the
|
|
* relocation list; that determines slot numbering and is stable
|
|
* across runs (rels are pushed onto the head as objects load). */
|
|
for (Lrel *r = l->rels; r; r = r->next) {
|
|
if (r->sym == NULL || r->sym->defined) continue;
|
|
if (r->sym->is_dyn) continue; /* already promoted */
|
|
for (Lso *so = l->sos; so; so = so->next) {
|
|
const char *ver = NULL;
|
|
if (l_so_provides_v(so, r->sym->name, &ver)) {
|
|
r->sym->is_dyn = 1;
|
|
r->sym->dyn_lib = so;
|
|
r->sym->dyn_version = ver; /* may be NULL */
|
|
r->sym->plt_idx = l->dyn_n++;
|
|
break;
|
|
}
|
|
}
|
|
}
|
|
|
|
/* What remains undefined truly is undefined. */
|
|
for (Lrel *r = l->rels; r; r = r->next) {
|
|
if (r->sym == NULL) continue;
|
|
if (!r->sym->defined && !r->sym->is_dyn) {
|
|
fprintf(stderr, "w6l: undefined reference to '%s'\n",
|
|
r->sym->name);
|
|
l->errs++;
|
|
}
|
|
}
|
|
return l->errs;
|
|
}
|
|
|
|
static void
|
|
patch_u32(u8 *p, u32 v)
|
|
{
|
|
p[0] = (u8)(v & 0xff);
|
|
p[1] = (u8)((v >> 8) & 0xff);
|
|
p[2] = (u8)((v >> 16) & 0xff);
|
|
p[3] = (u8)((v >> 24) & 0xff);
|
|
}
|
|
|
|
int
|
|
l_relocate(Lnk *l, u64 text_va, u64 data_va)
|
|
{
|
|
for (Lrel *r = l->rels; r; r = r->next) {
|
|
if (r->sym == NULL) continue;
|
|
/* Dynamic syms are patched later, in l_emit_elf, once the
|
|
* PLT's virtual address is known. */
|
|
if (r->sym->is_dyn) continue;
|
|
if (!r->sym->defined) continue;
|
|
switch (r->kind) {
|
|
case R_X86_64_PC32:
|
|
case R_X86_64_PLT32: {
|
|
u64 site = text_va + r->off;
|
|
u64 sym_va = r->sym->in_data
|
|
? data_va + r->sym->val
|
|
: text_va + r->sym->val;
|
|
i64 rel = (i64)sym_va - (i64)site + r->addend;
|
|
patch_u32(l->text + r->off, (u32)(i32)rel);
|
|
break;
|
|
}
|
|
default:
|
|
fprintf(stderr, "w6l: unsupported reloc kind %d\n",
|
|
r->kind);
|
|
l->errs++;
|
|
}
|
|
}
|
|
return l->errs;
|
|
}
|