Stage S-1c: WORD's buffer is per VM; input buffers allotted at VM init, below all compiled code (FABRIC-3.9.0 §8.1)

- The static word_scratch_addr shared by every VM is gone: WORD builds in
  vm->word_buf (257 bytes: count + 255 + NUL). A token over 255 chars is
  refused whole (delimiter restored, >IN unconsumed, vm->error), logged at
  LOG_ERROR and counted -- no more silent cut to 62 chars.
- Pre-existing corruption found by the probe: TIB/>IN/SPAN (and WORD's
  scratch) were allotted lazily at HERE; POST's restore_dict_state(),
  FORGET and COLD rolled HERE below them and compiled the dictionary over
  them (Hera's TIB lay under ACL-RECHECK's body; QUERY/WORD wrote into
  code). Per Captain Bob, all four are now allotted first in both
  vm_init()s (offsets 0-1305); COLD's clamp never goes below them.

Probe (reverted), identical on amd64/aarch64/riscv64: 0 colon bodies inside
the buffers; per-VM isolation; 62/100/255-char tokens full length; 300
refused and counted; interpreter sane after full-width TIB writes.
3-ISA acceptance passes; M7.1a hash and dict_hash set unchanged (here
0xd8 -> 0x5f8).

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
Robert Allan James
2026-09-24 16:21:25 -04:00
co-authored by Claude Opus 5.5
parent a2e3356b2e
commit 316be9fc4b
25 changed files with 73545 additions and 19 deletions
+3
View File
@@ -149,4 +149,7 @@
*/
void register_string_words(VM * vm);
/* S-1c: WORD tokens refused for exceeding a counted string's 255 chars. */
uint32_t string_word_word_refusals(void);
#endif /* STRING_WORDS_H */
+18 -17
View File
@@ -75,9 +75,12 @@ static inline int ensure_input(VM *vm) {
return err;
}
/* Static VM-backed scratch buffer for WORD (allocated on first use) */
#define WORD_SCRATCH_CAP 64
static vaddr_t word_scratch_addr = 0;
/* S-1c: WORD's buffer is per VM now (vm->word_buf, vm_input_ensure()). A
* token too long for a counted string (> 255 chars) is refused, logged and
* counted here -- never silently truncated. */
static uint32_t g_word_too_long;
uint32_t string_word_word_refusals(void) { return g_word_too_long; }
/* Helper function to convert string to number (base-10 only here) */
static int convert_string_to_number(const char *str, size_t len, cell_t *result) {
@@ -248,33 +251,31 @@ void string_word_word(VM *vm) {
while ((size_t) ip < tib_len && tib[ip] != (unsigned char) delimiter) ip++;
size_t end = (size_t) ip;
size_t word_len = end - start;
if (word_len > WORD_SCRATCH_CAP - 2) word_len = WORD_SCRATCH_CAP - 2;
/* Allocate scratch once */
if (word_scratch_addr == 0) {
void *p = vm_allot(vm, WORD_SCRATCH_CAP);
if (!p) {
vm->error = 1;
return;
}
word_scratch_addr = vaddr_from_ptr(vm, p);
if (word_len > WORD_BUFFER_SIZE - 2) {
/* Refused whole: the delimiter goes back on the stack and >IN is
* left where it was, so nothing is consumed. */
g_word_too_long++;
log_message(LOG_ERROR, "WORD: token over 255 chars refused");
vm_push(vm, c);
vm->error = 1;
return;
}
/* Build counted string at scratch */
uint8_t *wb = vm_ptr(vm, word_scratch_addr);
/* Build the counted string in this VM's own WORD buffer */
uint8_t *wb = vm->word_buf;
if (!wb) {
vm->error = 1;
return;
}
wb[0] = (uint8_t) word_len;
if (word_len) memcpy(&wb[1], &tib[start], word_len);
if (word_len + 1 < WORD_SCRATCH_CAP) wb[word_len + 1] = '\0'; /* safety */
wb[word_len + 1] = '\0'; /* safety */
/* Update >IN to char after the delimiter (if any) */
while ((size_t) ip < tib_len && tib[ip] == (unsigned char) delimiter) ip++;
*inp = ip;
vm_push(vm, CELL(word_scratch_addr));
vm_push(vm, CELL(vaddr_from_ptr(vm, wb)));
}
/* >IN ( -- addr ) Input stream pointer cell (VM address) */
+10 -1
View File
@@ -90,7 +90,16 @@ static void reset_vm_state(VM *vm, int cold_start) {
if (cold_start) {
/* In a complete system, this would restore a boot image.
For now we keep a minimal fence by not crushing the base dictionary. */
if (vm->here > 1024) vm->here = 1024;
if (vm->here > 1024) {
/* S-1c: never below the input buffers allotted at vm_init()
* (TIB/>IN/SPAN/WORD buffer end past 1024). */
size_t floor = 1024;
if (vm->word_buf) {
size_t buf_end = (size_t)(vm->word_buf - vm->memory) + WORD_BUFFER_SIZE;
if (buf_end > floor) floor = buf_end;
}
if (vm->here > floor) vm->here = floor;
}
}
system_running = 1;