/* dev_limits.c — the two fixed-size limits in runtime/flan_dev.c, driven
 * directly.
 *
 * Neither is reachable from a Flan program that behaves. The result buffer
 * only truncates when a renderer emits more than 4K, which no fixture does,
 * and the name table only fills after 4096 distinct run-time-introduced names,
 * which is more forms than the whole corpus has. So both were code nothing had
 * ever run: the first thing either would do in anger is either lose the end of
 * a value or scribble past the end of a static array, and the ellipsis and the
 * abort are the two behaviours that say which.
 *
 * A C main, for the same reason reload_host.c is one: these are C entry points
 * with no Flan spelling, and flan_dev.c is compiled into every build (see
 * build.ml), so linking any Flan program brings them along. The .flan this is
 * linked against therefore has no [main] of its own.
 *
 * One mode per run, chosen by argv, because both of them are one-way: the
 * name table never shrinks and the overflow case aborts the process.
 */

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

void **flan_dev_cell(const char *name);
void flan_dev_result_begin(void);
void flan_dev_emit(const uint8_t *bytes, int64_t len);
void flan_dev_result_end(void);
uint64_t flan_dev_result_cap(void);
int flan_dev_result_read(char *dst, uint64_t cap, uint64_t *gen, uint64_t *len);

/* [flan_dev_result_get] was replaced by a real seqlock, which copies into the
 * caller's buffer rather than handing back a pointer into one being written.
 * The buffer is sized from [flan_dev_result_cap] rather than from CAP below,
 * which is this test's own expectation of the answer: sizing it from the
 * number under test would make a wrong cap copy the wrong amount and agree
 * with itself. */
static char rbuf[1 << 16];

static const char *result_read(uint64_t *gen, uint64_t *len) {
  if (flan_dev_result_cap() > sizeof rbuf) {
    printf("result buffer too small for cap %llu\n",
           (unsigned long long)flan_dev_result_cap());
    exit(2);
  }
  if (!flan_dev_result_read(rbuf, sizeof rbuf, gen, len)) {
    /* Single-threaded here: the writer is this thread, so a failed read means
     * the counter was left odd, not that a write was racing. */
    printf("result read did not settle\n");
    exit(2);
  }
  return rbuf;
}
void flan_rt_init(int32_t argc, char **argv);

void flan_dev_reg_enable(void);
void flan_dev_reg_note(void *base, int64_t bytes, int64_t elem,
                       const char *type, int64_t typelen);
void flan_dev_reg_dead(void *base);
int flan_dev_reg_overflowed(void);
int64_t flan_dev_reg_count(int32_t live_only);
int64_t flan_dev_reg_by_type(int32_t live_only, int64_t *counts,
                             int64_t *bytes, const char **types,
                             int64_t *typelens, int64_t cap, int64_t *unread);

#define CAP 4096

/* Emit more than fits, twice the buffer's worth, and report what came back.
 * What is printed is everything a wrong cap gets wrong: the length, the three
 * characters that say it was truncated, a byte from the middle to show the
 * content up to the cut is the content that was emitted, and the generation
 * counter, which is what a reader waits on and must move exactly once. */
static int cap(void) {
  static uint8_t a[3000], b[3000];
  uint64_t gen0, gen1, len;
  const char *r;

  memset(a, 'a', sizeof a);
  memset(b, 'b', sizeof b);

  r = result_read(&gen0, &len);

  flan_dev_result_begin();
  flan_dev_emit(a, (int64_t)sizeof a);
  /* A negative length is not a huge one: the cast to size_t would make it
   * about 2^64 and the clamp would then be the only thing between it and a
   * memcpy of everything. */
  flan_dev_emit(b, -1);
  flan_dev_emit(b, (int64_t)sizeof b);
  flan_dev_result_end();

  r = result_read(&gen1, &len);
  printf("len %llu\n", (unsigned long long)len);
  printf("tail %.3s\n", len >= 3 ? r + len - 3 : "");
  printf("mid %c\n", len > 3500 ? r[3500] : '?');
  printf("head %c\n", len > 0 ? r[0] : '?');
  printf("gen %llu\n", (unsigned long long)(gen1 - gen0));

  /* And a short value after a truncated one: the flag has to be cleared by
   * [begin] or every later render ends in an ellipsis it did not earn. */
  flan_dev_result_begin();
  flan_dev_emit((const uint8_t *)"12", 2);
  flan_dev_result_end();
  r = result_read(&gen1, &len);
  printf("again %.*s\n", (int)len, r);
  return 0;
}

/* Fill the name table and then ask for one more. The table is fixed and never
 * moves — a module holds the address of a cell for as long as it is loaded —
 * so the only honest answer past the end is to stop. */
static int names(void) {
  char buf[32];
  for (int i = 0; i < CAP; i++) {
    snprintf(buf, sizeof buf, "n%d", i);
    if (flan_dev_cell(buf) == NULL) {
      printf("null cell at %d\n", i);
      return 1;
    }
  }
  /* Distinct names, all of them: a table that deduplicated wrongly would not
   * be full here and the line below would not abort. */
  printf("interned %d\n", CAP);
  fflush(stdout);
  (void)flan_dev_cell("one-too-many");
  printf("survived\n");
  return 0;
}


/* ── A table full of live blocks, read while it is being written ─────
 *
 * The shape of the bug this pins, which is worth writing down because the
 * mode looks like a stress test and is not one. A compaction reclaims dead
 * entries. The trigger used to be "three quarters full" and nothing else, so a
 * program holding more than three quarters of the table live compacted on
 * every single allocation, for ever, reclaiming nothing each time. Each
 * compaction holds the table-wide epoch odd from end to end, a listing retries
 * eight times and each retry meets another one, and [flan_dev_reg_by_type]
 * used to answer that with zero rows — "nothing is held", about a program
 * holding three thousand blocks. It was measured at 198 wrong answers in 200.
 *
 * So: 3100 live blocks, which is over the old three-quarter mark and under the
 * 4096 the table holds, one thread noting allocations as fast as it can, and
 * this thread asking the leak question two hundred times. The count printed is
 * how many of those answers were right. Nothing here is timing-dependent in
 * the direction that matters — a wrong answer is a wrong answer on any
 * machine, and the fixed table means "right" is a number this file knows.
 *
 * The blocks are fake addresses rather than real allocations. The registry is
 * told about a block, it never reads one, and 3100 real mallocs would only be
 * measuring the allocator. */
enum { REG_LIVE = 3100, REG_ASKS = 200 };

static volatile int reg_stop;

/* The writer: re-note blocks that are already in the table, which is what a
 * game loop overwriting its own allocations looks like from in here, and is
 * the path that takes the compaction branch. The addresses are the ones
 * already recorded, so the live count does not move and the table never
 * fills. */
static void *reg_writer(void *arg) {
  int64_t n = 0;
  (void)arg;
  while (!reg_stop) {
    for (int i = 0; i < REG_LIVE && !reg_stop; i++) {
      void *p = (void *)(uintptr_t)(0x100000 + (uintptr_t)i * 64);
      flan_dev_reg_note(p, 64, 8, "Enemy", 5);
      n++;
    }
  }
  return (void *)(uintptr_t)n;
}

static int regfull(void) {
  enum { ROWS = 16 };
  int64_t counts[ROWS], bytes[ROWS], typelens[ROWS], unread;
  const char *types[ROWS];
  pthread_t w;
  int right = 0, refused = 0, wrong = 0, zero = 0;

  flan_dev_reg_enable();
  for (int i = 0; i < REG_LIVE; i++) {
    void *p = (void *)(uintptr_t)(0x100000 + (uintptr_t)i * 64);
    flan_dev_reg_note(p, 64, 8, "Enemy", 5);
  }
  printf("live %lld\n", (long long)flan_dev_reg_count(1));

  if (pthread_create(&w, NULL, reg_writer, NULL) != 0) {
    printf("no writer thread\n");
    return 2;
  }
  for (int a = 0; a < REG_ASKS; a++) {
    int64_t n = flan_dev_reg_by_type(1, counts, bytes, types, typelens, ROWS,
                                     &unread);
    /* One type, 3100 blocks of it. Any other answer is this table described as
       something it is not — and zero rows is the specific lie, because it is
       the answer a program that had freed everything would get. */
    if (n < 0) refused++;
    else if (n == 0) zero++;
    else if (n == 1 && counts[0] == REG_LIVE) right++;
    else wrong++;
  }
  reg_stop = 1;
  pthread_join(w, NULL);

  printf("right %d\n", right);
  printf("zero %d\n", zero);
  printf("wrong %d\n", wrong);
  printf("refused %d\n", refused);
  return 0;
}


/* ── The dead count the compaction trigger reads ─────────────────────
 *
 * [regfull] above proves a table of live blocks stops compacting. This proves
 * the other half still does, which is the failure that would be silent: the
 * trigger now asks how many entries are dead, four places maintain that number
 * — a death, an arena's free-all, a dead slot being written over, and the sweep
 * itself, which drops all of them — and a count that drifted low would simply
 * stop reclaiming. Nothing would crash. The table would pin at its cap, the
 * overflow flag would come on, and every listing from then on would be a floor
 * quietly described as a count.
 *
 * So: three thousand blocks that stay live, and a pool of six hundred noted and
 * freed over and over on top of them. Used passes the three-quarter mark, the
 * dead pass the reclaim floor several times over the run, and the sweep runs.
 * The assertion that catches a drifted count is the last one — a table that
 * never reclaimed would have overflowed long before this returns. */
enum { CHURN_LIVE = 3000, CHURN_POOL = 600, CHURN_PASSES = 8 };

static void *churn_addr(int i) {
  return (void *)(uintptr_t)(0x800000 + (uintptr_t)i * 64);
}

static int regchurn(void) {
  enum { ROWS = 16 };
  int64_t counts[ROWS], bytes[ROWS], typelens[ROWS], unread, n;
  const char *types[ROWS];

  flan_dev_reg_enable();
  for (int i = 0; i < CHURN_LIVE; i++)
    flan_dev_reg_note(churn_addr(i), 64, 8, "Enemy", 5);
  /* Noted and freed on top of the live set. A note landing on the slot of a
   * block that died is the decrement; the free is the increment; the sweep in
   * between is the reset. */
  for (int pass = 0; pass < CHURN_PASSES; pass++)
    for (int i = 0; i < CHURN_POOL; i++) {
      void *p = churn_addr(CHURN_LIVE + i);
      flan_dev_reg_note(p, 32, 4, "Bullet", 6);
      flan_dev_reg_dead(p);
    }

  printf("live %lld\n", (long long)flan_dev_reg_count(1));
  n = flan_dev_reg_by_type(1, counts, bytes, types, typelens, ROWS, &unread);
  printf("rows %lld\n", (long long)n);
  printf("blocks %lld\n", (long long)(n == 1 ? counts[0] : -1));
  /* The one that catches a dead count that drifted: a table that stopped
     reclaiming fills, and a full table is a floor for the rest of the run. */
  printf("overflowed %d\n", flan_dev_reg_overflowed());
  return 0;
}

/* And a table that really is full, which is the case the trigger above must
 * not paper over: 4096 live blocks and nothing dead anywhere, then one more.
 * The note is dropped — that is the standing decision, and dying because a
 * diagnostic ran out of room would be worse — and what is checked here is that
 * the drop is *said*, once, rather than only being discoverable by asking the
 * flag. A second and third dropped note must add nothing. */
static int regoverflow(void) {
  flan_dev_reg_enable();
  for (int i = 0; i < CAP; i++)
    flan_dev_reg_note((void *)(uintptr_t)(0x2000000 + (uintptr_t)i * 64), 64, 8,
                      "Enemy", 5);
  printf("live %lld\n", (long long)flan_dev_reg_count(1));
  printf("overflowed %d\n", flan_dev_reg_overflowed());
  fflush(stdout);
  for (int i = 0; i < 3; i++)
    flan_dev_reg_note((void *)(uintptr_t)(0x9000000 + (uintptr_t)i * 64), 64, 8,
                      "Latecomer", 9);
  printf("overflowed %d\n", flan_dev_reg_overflowed());
  printf("live %lld\n", (long long)flan_dev_reg_count(1));
  return 0;
}


/* ── A listing taken while the table is actually being rearranged ────
 *
 * [regfull] is a table of live blocks, where the fix is that no compaction
 * runs at all. This is the other race: a writer churning hard enough that
 * compactions do run, under a reader asking the leak question through them.
 *
 * What it pins is not a rate. Rates here are the machine's, and the counts
 * printed are deliberately the two that cannot come out any other way on any
 * machine: [zero], an answer of no rows, which is the original lie and the one
 * shape a program holding three thousand blocks must never produce; and
 * [low], a count that is neither right nor a refusal, which is what a torn
 * read or a walk that straddled a compaction would produce. Right-versus-
 * refused is the interesting number and it is printed rather than asserted,
 * because a refusal is an honest answer and how often it comes up is the
 * writer's business. It moves a lot: on the machine this was written on, the
 * paced retry turned 8 right in 200 into 200 in 200 at one churn rate and
 * changed nothing at all at another.
 *
 * The throttle is a spin and not a sleep because the whole interesting range
 * is under nanosleep's floor of tens of microseconds. */
enum { RACE_LIVE = 3000, RACE_ASKS = 200, RACE_SPIN = 1000 };

static volatile int race_stop;

static void *race_writer(void *arg) {
  long long i = 0;
  (void)arg;
  while (!race_stop) {
    /* Noted and freed, which is what makes the dead count climb and the
     * compaction actually run — the difference from [regfull]'s writer, which
     * re-notes live blocks and therefore never earns a sweep. */
    void *p = (void *)(uintptr_t)(0x40000000 + (uintptr_t)(i % 100000) * 64);
    flan_dev_reg_note(p, 32, 4, "Bullet", 6);
    flan_dev_reg_dead(p);
    for (volatile long k = 0; k < RACE_SPIN; k++) { }
    i++;
  }
  return NULL;
}

static int regrace(void) {
  enum { ROWS = 16 };
  int64_t counts[ROWS], bytes[ROWS], typelens[ROWS], unread;
  const char *types[ROWS];
  pthread_t w;
  int right = 0, refused = 0, zero = 0, low = 0;

  flan_dev_reg_enable();
  for (int i = 0; i < RACE_LIVE; i++)
    flan_dev_reg_note((void *)(uintptr_t)(0x100000 + (uintptr_t)i * 64), 64, 8,
                      "Enemy", 5);
  if (pthread_create(&w, NULL, race_writer, NULL) != 0) {
    printf("no writer thread\n");
    return 2;
  }
  for (int a = 0; a < RACE_ASKS; a++) {
    int64_t n =
        flan_dev_reg_by_type(1, counts, bytes, types, typelens, ROWS, &unread);
    if (n < 0) refused++;
    else if (n == 0) zero++;
    else {
      int64_t enemies = 0;
      for (int64_t j = 0; j < n && j < ROWS; j++)
        if (typelens[j] == 5) enemies = counts[j];
      if (enemies == RACE_LIVE) right++; else low++;
    }
  }
  race_stop = 1;
  pthread_join(w, NULL);

  printf("zero %d\n", zero);
  printf("low %d\n", low);
  printf("answered %d refused %d\n", right, refused);
  return 0;
}

int main(int argc, char **argv) {
  flan_rt_init(argc, argv);
  if (argc < 2) {
    fprintf(stderr,
            "usage: %s cap|names|regfull|regchurn|regrace|regoverflow\n",
            argv[0]);
    return 2;
  }
  if (strcmp(argv[1], "cap") == 0) return cap();
  if (strcmp(argv[1], "names") == 0) return names();
  if (strcmp(argv[1], "regfull") == 0) return regfull();
  if (strcmp(argv[1], "regchurn") == 0) return regchurn();
  if (strcmp(argv[1], "regrace") == 0) return regrace();
  if (strcmp(argv[1], "regoverflow") == 0) return regoverflow();
  fprintf(stderr, "unknown mode %s\n", argv[1]);
  return 2;
}