flan/runtime/flan_dev.c

/* flan_dev — the part of the host ABI that only a dev build has.
 *
 * A redefinition module reaches the host's functions and globals through
 * symbols the host already exports: a cell for each function, the storage for
 * each global. That covers everything the program was *built* with. It does
 * not cover a name the module introduces — a defn or a defvar typed into the
 * REPL after the process started — because there is no symbol in the host to
 * bind to and ELF cannot grow one.
 *
 * So a name that is new at run time is keyed by string instead. This file is
 * the two lookups that make that work, and deliberately nothing else:
 *
 *   flan_dev_cell(name)              the cell a new function lives in
 *   flan_dev_global(name, size, init) the storage a new global lives in
 *   flan_dev_emit(...)               where an evaluated expression's rendering
 *                                    goes, piece by piece, to be read back
 *
 * Both are idempotent: the second module to mention a name gets what the first
 * one got. That is the whole point. Two modules that each define their own
 * copy of a new function would each call their own, and redefining it would
 * update one of them.
 *
 * The table never moves. A module holds the address of a cell for as long as
 * it is loaded, so a growable table would leave those addresses pointing into
 * a freed allocation. Fixed capacity and a loud failure instead.
 *
 * Never dlclose a module. A cell holds an address inside that module's text,
 * and unloading it leaves every call site pointing at unmapped memory. There
 * is no unload path here on purpose.
 */

#include <stdint.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>

#define FLAN_DEV_MAX 4096

typedef struct {
  const char *name;   /* strdup'd: the module that passed it may go away */
  void       *cell;   /* a function's cell, or a global's storage */
  size_t      size;   /* a global's size; 0 for a function */
} entry;

static entry  table[FLAN_DEV_MAX];
static size_t used;

static void die(const char *what, const char *name) {
  fprintf(stderr, "flan_dev: %s: %s\n", what, name);
  fflush(stderr);
  abort();
}

static entry *find(const char *name) {
  for (size_t i = 0; i < used; i++)
    if (strcmp(table[i].name, name) == 0) return &table[i];
  return NULL;
}

static entry *intern(const char *name) {
  if (used == FLAN_DEV_MAX) die("out of dev name slots", name);
  entry *e = &table[used++];
  e->name = strdup(name);
  if (e->name == NULL) die("out of memory", name);
  e->cell = NULL;
  e->size = 0;
  return e;
}

/* The cell a run-time-introduced function is called through. One indirection
 * more than a function the host was built with, whose cell is a symbol the
 * module can name directly — the compiler picks per name, so the common case
 * stays a single load. */
void **flan_dev_cell(const char *name) {
  entry *e = find(name);
  if (e == NULL) e = intern(name);
  return &e->cell;
}

/* Storage for a run-time-introduced global, allocated once.
 *
 * [init] is its declared initial value, or NULL for all-zero. It is copied on
 * the allocation and ignored on every call after it, which is where "a reload
 * must not reset the program's state" lives: the second module to mention this
 * name is a redefinition, and re-running an initialiser would throw away
 * exactly what the reload exists to preserve. Doing it here rather than by a
 * branch in the caller means the rule cannot be got wrong at one call site.
 *
 * A size mismatch is the layout-drift failure, caught at its first chance: the
 * running process has already laid this memory out, and handing back the old
 * allocation for a differently shaped type means the new body reads fields at
 * the wrong offsets and nothing ever says so. Retyping a var needs a restart. */
void *flan_dev_global(const char *name, uint64_t size, const void *init) {
  entry *e = find(name);
  if (e == NULL) {
    e = intern(name);
    e->cell = calloc(1, size ? (size_t)size : 1);
    if (e->cell == NULL) die("out of memory", name);
    e->size = (size_t)size;
    if (init != NULL && size > 0) memcpy(e->cell, init, (size_t)size);
    return e->cell;
  }
  if (e->size != (size_t)size) die("size changed; restart to retype", name);
  return e->cell;
}

/* ── The value of an evaluated expression ──────────────────────────── */

/* C-x C-e compiles a thunk that renders one expression and emits it here, a
 * piece at a time. It is not written to stdout: stdout belongs to the program,
 * it is in the hot path for anything that prints, and a dev-only feature must
 * not put a branch in it. The daemon reads this back over the agent's socket.
 *
 * Emitting piece by piece rather than returning one string is what makes a
 * composite renderer possible at all — a struct is its fields with punctuation
 * between them, and concatenating that in the generated IR would mean an
 * allocator the language does not have.
 *
 * The output bound lives here and nowhere else. A slice of a million elements
 * renders with a loop the compiler cannot bound, so [emit] truncates and
 * [end] says so with an ellipsis. One place enforcing it means no renderer has
 * to carry a budget.
 *
 * [generation] is what makes the read safe without a handshake. The thunk runs
 * on the game thread at a frame boundary, whenever that happens to be; the
 * daemon waits for the counter to move rather than guessing it has. */

#define RESULT_MAX 4096
static char     result[RESULT_MAX];
static size_t   result_len;
static int      result_full;
static uint64_t generation;

void flan_dev_result_begin(void) {
  result_len = 0;
  result_full = 0;
}

void flan_dev_emit(const uint8_t *bytes, int64_t len) {
  size_t n = len < 0 ? 0 : (size_t)len;
  if (result_len + n > RESULT_MAX) {
    n = RESULT_MAX - result_len;
    result_full = 1;
  }
  memcpy(result + result_len, bytes, n);
  result_len += n;
}

static void emit_cstr(const char *s) {
  flan_dev_emit((const uint8_t *)s, (int64_t)strlen(s));
}

/* Rendered in C so that u64 is not a lie: the language's own i64->bytes is
 * signed, and anything past 2^63 would come back negative. */
void flan_dev_emit_u64(uint64_t x) {
  char buf[32];
  snprintf(buf, sizeof buf, "%llu", (unsigned long long)x);
  emit_cstr(buf);
}

void flan_dev_emit_i64(int64_t x) {
  char buf[32];
  snprintf(buf, sizeof buf, "%lld", (long long)x);
  emit_cstr(buf);
}

void flan_dev_emit_f64(double x) {
  char buf[64];
  snprintf(buf, sizeof buf, "%g", x);
  emit_cstr(buf);
}

/* Quoted and escaped, in C, because doing it in the generated IR would be a
 * loop per string and the language has no allocator to build the result in.
 * A string whose content is not escaped does not round-trip and reads as a
 * framing bug rather than as the value it is. */
void flan_dev_emit_str(const uint8_t *bytes, int64_t len) {
  size_t n = len < 0 ? 0 : (size_t)len;
  emit_cstr("\"");
  for (size_t i = 0; i < n; i++) {
    unsigned char c = bytes[i];
    switch (c) {
      case '"':  emit_cstr("\\\""); break;
      case '\\': emit_cstr("\\\\"); break;
      case '\n': emit_cstr("\\n"); break;
      case '\t': emit_cstr("\\t"); break;
      case '\r': emit_cstr("\\r"); break;
      default:
        if (c < 0x20) {
          char buf[8];
          snprintf(buf, sizeof buf, "\\x%02x", c);
          emit_cstr(buf);
        } else {
          flan_dev_emit(&c, 1);
        }
    }
  }
  emit_cstr("\"");
}

void flan_dev_result_end(void) {
  if (result_full) {
    /* Room is made for it rather than assumed: the buffer is full by
     * definition when this fires. */
    const char *ell = "...";
    size_t k = strlen(ell);
    if (result_len > RESULT_MAX - k) result_len = RESULT_MAX - k;
    memcpy(result + result_len, ell, k);
    result_len += k;
  }
  /* Last, so a reader that sees the new generation sees the whole value. */
  __atomic_store_n(&generation, generation + 1, __ATOMIC_RELEASE);
}

const char *flan_dev_result_get(uint64_t *gen, uint64_t *len) {
  *gen = __atomic_load_n(&generation, __ATOMIC_ACQUIRE);
  *len = (uint64_t)result_len;
  return result;
}