/* 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.
 *
 * It is a *seqlock*, and it has to be a real one, because the reader is the
 * agent's listener thread and the writer is the game thread and neither waits
 * for the other. The counter is odd for exactly as long as a value is being
 * written, so a reader that sees an odd count, or a different count either
 * side of its copy, has read a value that was being overwritten underneath it
 * and reads again. A count of 2k means k complete values; the count the
 * outside world is given is that k, so that the daemon's "has it moved" keeps
 * meaning "is there a new value".
 *
 * The copy is what makes it safe, and the API is shaped around that: a reader
 * gets *bytes of its own*, not a pointer into [result]. The pointer version of
 * this was the bug — it read the generation, then a length, then handed back
 * the buffer itself, and the caller sent it down a socket some time later
 * while the game thread was free to be a hundred bytes into the next value.
 * A seqlock cannot validate a read that happens after it returns. */

#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) {
  /* Odd first, and only then the reset: the counter has to say "in progress"
   * before the buffer stops being the value it used to be.
   *
   * The fence is the half of that a release *store* cannot do. A release store
   * orders what comes before it, not what comes after, so the writes below —
   * and every memcpy in [emit] — would be free to become visible ahead of the
   * odd count, and a reader could see an even count either side of a copy it
   * made while the buffer was being overwritten. Which is the bug this
   * replaced, with more ceremony. So: mark it relaxed, fence, then write.
   *
   * Setting the low bit rather than incrementing, because a [begin] with no
   * [end] is reachable and must not poison the counter for the life of the
   * process. A render thunk that signals is stopped inside this window, and a
   * restart taken from that break transfers past the thunk — [end] never runs.
   * Repairing it here costs nothing in the ordinary case (2k, 2k+1, 2k+2) and
   * means an abandoned write is over as soon as the next evaluation starts,
   * rather than leaving every later read reporting "in progress" forever.
   *
   * What it does not fix, because the buffer cannot: an evaluation that runs
   * while another is stopped mid-render shares this one buffer, so the inner
   * value is the one that survives and the outer thunk, if it is ever resumed,
   * appends to it. That was true before the counter was a seqlock. */
  __atomic_store_n(&generation, generation | 1, __ATOMIC_RELAXED);
  __atomic_thread_fence(__ATOMIC_RELEASE);
  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, and back to even, so a reader that sees the new generation sees the
   * whole value. [| 1] first for the same reason [begin] sets rather than
   * increments: this must land on an even count whatever state an abandoned
   * write left behind. */
  __atomic_store_n(&generation, (generation | 1) + 1, __ATOMIC_RELEASE);
}

/* Copy the current value out, with the counter that says which one it is.
 *
 * Returns 1 having copied a value that was complete for the whole of the copy,
 * 0 if the game thread was in the middle of writing one — in which case [gen]
 * is the last *complete* value's number and [len] is 0, so a caller polling
 * for a new one keeps polling instead of being handed half of it. Spinning
 * here is bounded: the writer is a render thunk between frames, not a loop,
 * and the reader is the listener thread, which has nothing better to do.
 *
 * [cap] is the caller's buffer. A value longer than it is truncated, which is
 * the only failure this can have and is a clamp rather than an overrun; the
 * agent sizes its buffer at RESULT_MAX so it does not arise. */
/* What a caller's buffer has to be for the copy never to be truncated. The
 * bound is declared in one place and asked for rather than written down twice:
 * the agent's buffer and this one agreeing is the whole of "never truncated",
 * and two literals in two files is how that stops being true. */
uint64_t flan_dev_result_cap(void) { return RESULT_MAX; }

int flan_dev_result_read(char *dst, uint64_t cap, uint64_t *gen,
                         uint64_t *len) {
  for (int attempt = 0; attempt < 64; attempt++) {
    uint64_t g1 = __atomic_load_n(&generation, __ATOMIC_ACQUIRE);
    if (g1 & 1) continue;                  /* a write is in progress */
    size_t n = __atomic_load_n(&result_len, __ATOMIC_RELAXED);
    if (n > RESULT_MAX) n = RESULT_MAX;    /* a torn read cannot overrun */
    if ((uint64_t)n > cap) n = (size_t)cap;
    memcpy(dst, result, n);
    /* The copy must be ordered before the second read of the counter, or the
     * check is of a copy the compiler was free to make afterwards. */
    __atomic_thread_fence(__ATOMIC_ACQUIRE);
    if (__atomic_load_n(&generation, __ATOMIC_ACQUIRE) == g1) {
      *gen = g1 / 2;
      *len = (uint64_t)n;
      return 1;
    }
  }
  /* Integer division is the same answer either side of a write in progress:
   * during value k the counter is 2k-1 and k-1 are complete. */
  *gen = __atomic_load_n(&generation, __ATOMIC_ACQUIRE) / 2;
  *len = 0;
  return 0;
}

/* ── The shadow stack ───────────────────────────────────────────────── */

/* plan.org's "Dev vs release builds" has had *Frames: shadow stack* in the dev
 * column since the beginning. This is it, and it exists for one reason: the
 * more a break loop can show, the less often a real debugger is needed. A
 * stopped program that cannot say where it is sends someone to lldb.
 *
 * Native unwinding would be the other route and is deliberately not taken:
 * plan.org lowers every non-local exit explicitly rather than through platform
 * unwinding, so there is no .eh_frame walk to borrow, and a frame pointer walk
 * gives addresses that only DWARF can turn back into names. A pushed record
 * carries the name itself, is the same on wasm32 as it is here, and needs no
 * agreement with the optimiser about what a frame looks like.
 *
 * The compiler emits the push and the pop inline (emit.ml, [emit_fn]) rather
 * than calling in here: this is on every call in a dev build, and a call to
 * record a call would double the thing being measured.
 *
 * A plain global, not a _Thread_local. It matches what the handler stack and
 * the restart stack in flan_rt.c already assume — one thread runs Flan; the
 * listener thread runs C and the loader and never enters a Flan body. If the
 * language ever grows threads this becomes thread-local and the compiler's
 * two stores become TLS-relative, which is the only change.
 *
 * Nothing in here walks the chain while the game thread is running. The break
 * loop snapshots it on the stopped thread, exactly as it snapshots the restart
 * list and for exactly the same reason: a chain read by another thread is a
 * chain that can be popped underneath the reader. The accessors below are the
 * snapshot's, and take the frame they were given rather than re-reading the
 * head. */

typedef struct {
  const char *name;     /* the Flan name, qualified; not NUL-terminated */
  int64_t     namelen;
  const char *loc;      /* file:line:col, as Loc spells it */
  int64_t     loclen;
  int32_t     nslots;
  /* What the two ends compare about a frame's slots, from
     [Emit.slot_fingerprint]: a hash over every slot's name and the spelling of
     its type. The frame carries the one belonging to the body it was compiled
     from; the daemon recomputes it from the body it now holds, and a
     difference means the frame is running a superseded body. A count alone
     cannot see a rename, which is the case this exists for. */
  int32_t     slotsig;
} flan_fninfo;

typedef struct flan_frame {
  struct flan_frame *prev;
  const flan_fninfo *info;
  /* One entry per slot, each null until the binding that fills that slot has
   * run — so "not bound yet at the point this frame stopped" is a null and
   * needs no liveness analysis to work out. Null altogether for a function
   * with no named slot, and in a release build there is no frame at all.
   * Read through [flan_dev_frame_slot], which is where the bound is checked. */
  void     **slots;
} flan_frame;

/* The compiler names this symbol directly. A redefinition module reaches it
 * the same way it reaches any other host global — through the dynamic symbol
 * table, which [--dev] links with -rdynamic. */
flan_frame *flan_frame_head;

/* [i] counts from the innermost. NULL past the end, which is how a caller
 * learns the depth without a second walk. */
void *flan_dev_frame_at(int32_t i) {
  flan_frame *f = flan_frame_head;
  while (f != NULL && i > 0) { f = f->prev; i--; }
  return f;
}

int32_t flan_dev_frame_count(void) {
  int32_t n = 0;
  for (flan_frame *f = flan_frame_head; f != NULL; f = f->prev) {
    n++;
    if (n > 100000) break;   /* a corrupt chain says so rather than hanging */
  }
  return n;
}

const char *flan_dev_frame_name(const void *frame, int64_t *len) {
  const flan_frame *f = frame;
  if (f == NULL || f->info == NULL) { *len = 0; return NULL; }
  *len = f->info->namelen;
  return f->info->name;
}

const char *flan_dev_frame_loc(const void *frame, int64_t *len) {
  const flan_frame *f = frame;
  if (f == NULL || f->info == NULL) { *len = 0; return NULL; }
  *len = f->info->loclen;
  return f->info->loc;
}

int32_t flan_dev_frame_nslots(const void *frame) {
  const flan_frame *f = frame;
  return (f == NULL || f->info == NULL) ? 0 : f->info->nslots;
}

/* The fingerprint of the body this frame was compiled from. Zero for a frame
 * with no description, which is the same "nothing to compare" a zero slot
 * count already means. */
int32_t flan_dev_frame_slotsig(const void *frame) {
  const flan_frame *f = frame;
  return (f == NULL || f->info == NULL) ? 0 : f->info->slotsig;
}

/* Where slot [i] of this frame lives, or NULL — which means one of three
 * things, all of which are "there is nothing to read here": this build records
 * no slots, the index is not one of them, or the binding that fills it had not
 * run when the frame stopped. A caller renders what it is given and refuses
 * what it is not; nothing here guesses. */
void *flan_dev_frame_slot(const void *frame, int32_t i) {
  const flan_frame *f = frame;
  if (f == NULL || f->info == NULL || f->slots == NULL) return NULL;
  if (i < 0 || i >= f->info->nslots) return NULL;
  return f->slots[i];
}