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.
259 lines
6.4 KiB
C
259 lines
6.4 KiB
C
/*
|
|
* 620_data_link — end-to-end w6l support for writable globals.
|
|
* Assemble a small .s using DATAW, link it with w6l, run the binary,
|
|
* and verify both that the read returns the global's value and that
|
|
* a store updates it. Also confirms the binary has two PT_LOADs with
|
|
* the right R+X / R+W flags.
|
|
*
|
|
* Inputs without DATAW must still produce the single-PT_LOAD layout
|
|
* — 992 (selfhost w6l .o diff) depends on that invariant.
|
|
*/
|
|
#include <stdio.h>
|
|
#include <stdlib.h>
|
|
#include <string.h>
|
|
#include <stdint.h>
|
|
#include <unistd.h>
|
|
#include <sys/wait.h>
|
|
|
|
#define PT_LOAD 1
|
|
#define PF_X 1
|
|
#define PF_W 2
|
|
#define PF_R 4
|
|
|
|
#pragma pack(push, 1)
|
|
typedef struct {
|
|
uint8_t e_ident[16];
|
|
uint16_t e_type, e_machine;
|
|
uint32_t e_version;
|
|
uint64_t e_entry, e_phoff, e_shoff;
|
|
uint32_t e_flags;
|
|
uint16_t e_ehsize, e_phentsize, e_phnum, e_shentsize, e_shnum, e_shstrndx;
|
|
} Ehdr;
|
|
|
|
typedef struct {
|
|
uint32_t p_type, p_flags;
|
|
uint64_t p_offset, p_vaddr, p_paddr;
|
|
uint64_t p_filesz, p_memsz, p_align;
|
|
} Phdr;
|
|
#pragma pack(pop)
|
|
|
|
static int
|
|
write_file(const char *path, const char *body)
|
|
{
|
|
FILE *f = fopen(path, "wb");
|
|
if (!f) return -1;
|
|
fputs(body, f);
|
|
fclose(f);
|
|
return 0;
|
|
}
|
|
|
|
static int
|
|
slurp(const char *path, uint8_t **out, size_t *outn)
|
|
{
|
|
FILE *f = fopen(path, "rb");
|
|
if (!f) return -1;
|
|
fseek(f, 0, SEEK_END);
|
|
long n = ftell(f);
|
|
fseek(f, 0, SEEK_SET);
|
|
uint8_t *b = malloc((size_t)n);
|
|
if (fread(b, 1, (size_t)n, f) != (size_t)n) {
|
|
free(b);
|
|
fclose(f);
|
|
return -1;
|
|
}
|
|
fclose(f);
|
|
*out = b;
|
|
*outn = (size_t)n;
|
|
return 0;
|
|
}
|
|
|
|
static int
|
|
build(const char *bin, const char *body, const char *exe)
|
|
{
|
|
char src[64], obj[64], cmd[1024];
|
|
snprintf(src, sizeof src, "/tmp/wwt_dl_%d.s", getpid());
|
|
snprintf(obj, sizeof obj, "/tmp/wwt_dl_%d.o", getpid());
|
|
if (write_file(src, body) < 0) return -1;
|
|
|
|
snprintf(cmd, sizeof cmd, "%s/w6a -o %s %s", bin, obj, src);
|
|
if (system(cmd) != 0) { unlink(src); return -1; }
|
|
snprintf(cmd, sizeof cmd, "%s/w6l -o %s %s", bin, exe, obj);
|
|
int rc = system(cmd);
|
|
unlink(src); unlink(obj);
|
|
return rc;
|
|
}
|
|
|
|
static int
|
|
run_exit(const char *exe)
|
|
{
|
|
int rc = system(exe);
|
|
if (rc == -1) return -1;
|
|
if (WIFEXITED(rc)) return WEXITSTATUS(rc);
|
|
return -1;
|
|
}
|
|
|
|
/* Test 1: read a writable global. _start exits with the value stored
|
|
* in `counter` (0x2a == 42). */
|
|
static int
|
|
test_read(const char *bin)
|
|
{
|
|
char exe[64];
|
|
snprintf(exe, sizeof exe, "/tmp/wwt_dl_%d.x1", getpid());
|
|
const char *body =
|
|
"TEXT _start,$0\n"
|
|
"\tMOVQ\tcounter(SB), DI\n"
|
|
"\tMOVQ\t$60, AX\n"
|
|
"\tSYSCALL\n"
|
|
"DATAW counter(SB),\"\\x2a\\x00\\x00\\x00\\x00\\x00\\x00\\x00\"\n";
|
|
if (build(bin, body, exe) != 0) {
|
|
fprintf(stderr, "test_read: build failed\n");
|
|
return -1;
|
|
}
|
|
int rc = run_exit(exe);
|
|
unlink(exe);
|
|
if (rc != 42) {
|
|
fprintf(stderr, "test_read: exit=%d, want 42\n", rc);
|
|
return -1;
|
|
}
|
|
return 0;
|
|
}
|
|
|
|
/* Test 2: store to a writable global, read it back, exit with the new
|
|
* value. Verifies the R+W mapping really is writable. */
|
|
static int
|
|
test_write(const char *bin)
|
|
{
|
|
char exe[64];
|
|
snprintf(exe, sizeof exe, "/tmp/wwt_dl_%d.x2", getpid());
|
|
const char *body =
|
|
"TEXT _start,$0\n"
|
|
"\tMOVQ\t$99, AX\n"
|
|
"\tMOVQ\tAX, counter(SB)\n"
|
|
"\tMOVQ\tcounter(SB), DI\n"
|
|
"\tMOVQ\t$60, AX\n"
|
|
"\tSYSCALL\n"
|
|
"DATAW counter(SB),\"\\x00\\x00\\x00\\x00\\x00\\x00\\x00\\x00\"\n";
|
|
if (build(bin, body, exe) != 0) {
|
|
fprintf(stderr, "test_write: build failed\n");
|
|
return -1;
|
|
}
|
|
int rc = run_exit(exe);
|
|
unlink(exe);
|
|
if (rc != 99) {
|
|
fprintf(stderr, "test_write: exit=%d, want 99\n", rc);
|
|
return -1;
|
|
}
|
|
return 0;
|
|
}
|
|
|
|
/* Test 3: structurally inspect the linked ELF — two PT_LOADs, the
|
|
* first R+X and the second R+W. Catches regressions where the layout
|
|
* is right but the flags or count are off. */
|
|
static int
|
|
test_two_loads(const char *bin)
|
|
{
|
|
char exe[64];
|
|
snprintf(exe, sizeof exe, "/tmp/wwt_dl_%d.x3", getpid());
|
|
const char *body =
|
|
"TEXT _start,$0\n"
|
|
"\tMOVQ\tcounter(SB), AX\n"
|
|
"\tMOVQ\t$60, AX\n"
|
|
"\tMOVQ\t$0, DI\n"
|
|
"\tSYSCALL\n"
|
|
"DATAW counter(SB),\"\\x01\\x00\\x00\\x00\\x00\\x00\\x00\\x00\"\n";
|
|
if (build(bin, body, exe) != 0) {
|
|
fprintf(stderr, "test_two_loads: build failed\n");
|
|
return -1;
|
|
}
|
|
uint8_t *buf = NULL;
|
|
size_t n = 0;
|
|
if (slurp(exe, &buf, &n) < 0) {
|
|
fprintf(stderr, "test_two_loads: cannot read exe\n");
|
|
unlink(exe);
|
|
return -1;
|
|
}
|
|
unlink(exe);
|
|
|
|
const Ehdr *eh = (const Ehdr *)buf;
|
|
int rc = 0;
|
|
if (eh->e_phnum != 2) {
|
|
fprintf(stderr, "test_two_loads: e_phnum=%u, want 2\n", eh->e_phnum);
|
|
rc = -1;
|
|
goto out;
|
|
}
|
|
const Phdr *ph = (const Phdr *)(buf + eh->e_phoff);
|
|
int saw_rx = 0, saw_rw = 0;
|
|
for (int i = 0; i < 2; i++) {
|
|
if (ph[i].p_type != PT_LOAD) {
|
|
fprintf(stderr, "test_two_loads: ph[%d] not PT_LOAD\n", i);
|
|
rc = -1;
|
|
continue;
|
|
}
|
|
if (ph[i].p_flags == (PF_R | PF_X)) saw_rx = 1;
|
|
else if (ph[i].p_flags == (PF_R | PF_W)) saw_rw = 1;
|
|
else {
|
|
fprintf(stderr, "test_two_loads: ph[%d] flags=0x%x\n",
|
|
i, ph[i].p_flags);
|
|
rc = -1;
|
|
}
|
|
}
|
|
if (!saw_rx) { fprintf(stderr, "test_two_loads: missing R+X\n"); rc = -1; }
|
|
if (!saw_rw) { fprintf(stderr, "test_two_loads: missing R+W\n"); rc = -1; }
|
|
out:
|
|
free(buf);
|
|
return rc;
|
|
}
|
|
|
|
/* Test 4: an input without DATAW still produces a single PT_LOAD.
|
|
* 992 (selfhost w6l .o diff) depends on this byte-level invariant. */
|
|
static int
|
|
test_no_data_single_load(const char *bin)
|
|
{
|
|
char exe[64];
|
|
snprintf(exe, sizeof exe, "/tmp/wwt_dl_%d.x4", getpid());
|
|
const char *body =
|
|
"TEXT _start,$0\n"
|
|
"\tMOVQ\t$60, AX\n"
|
|
"\tMOVQ\t$0, DI\n"
|
|
"\tSYSCALL\n";
|
|
if (build(bin, body, exe) != 0) {
|
|
fprintf(stderr, "test_no_data_single_load: build failed\n");
|
|
return -1;
|
|
}
|
|
uint8_t *buf = NULL;
|
|
size_t n = 0;
|
|
if (slurp(exe, &buf, &n) < 0) {
|
|
fprintf(stderr, "test_no_data_single_load: cannot read exe\n");
|
|
unlink(exe);
|
|
return -1;
|
|
}
|
|
unlink(exe);
|
|
int rc = 0;
|
|
const Ehdr *eh = (const Ehdr *)buf;
|
|
if (eh->e_phnum != 1) {
|
|
fprintf(stderr, "test_no_data_single_load: e_phnum=%u, want 1\n",
|
|
eh->e_phnum);
|
|
rc = -1;
|
|
}
|
|
free(buf);
|
|
return rc;
|
|
}
|
|
|
|
int
|
|
main(void)
|
|
{
|
|
const char *bin = getenv("BIN");
|
|
if (!bin) bin = "out/bin";
|
|
int fail = 0;
|
|
if (test_read(bin) != 0) fail++;
|
|
if (test_write(bin) != 0) fail++;
|
|
if (test_two_loads(bin) != 0) fail++;
|
|
if (test_no_data_single_load(bin) != 0) fail++;
|
|
if (fail) {
|
|
fprintf(stderr, "data_link: %d/4 subtests failed\n", fail);
|
|
return 1;
|
|
}
|
|
printf("data_link: 4/4 ok\n");
|
|
return 0;
|
|
}
|