myxce/src/scheduler/testsuite/test_sim_cache_clear_isolation.c

/*
 * test_sim_cache_clear_isolation.c - scheduler-allocation spec, task 5.2
 * round 2 (Req 7.2 regression, mandated by the round-1 review that
 * REJECTED this task for a CRITICAL memory-corruption defect).
 *
 * ── The bug this guards against ──────────────────────────────────────────
 * core_begin_session_internal() (core_session.c) is reached from BOTH
 * driver.c's xce_sched_driver_run_normal_mode_round() (a real
 * xce_scheduler_t*, which HAS an unsatisfiable_cache field, scheduler.h)
 * and sim_loop.c's sched_sim_driver_run() (a structurally different
 * xce_sched_sim_driver_t*, sim.h -- Req 5 AC 17 "Simulation isolation" --
 * which has NO unsatisfiable_cache field at all). Round 1 called
 * alloc_cache.c's real, strong cache_clear(xce_scheduler_t*) via a
 * same-named WEAK fallback declared in core_session.c, relying on
 * link-time weak/strong symbol resolution. Since that resolution picks
 * ONE winner for the whole binary (not per call site), BOTH the driver.c
 * call (correct) and the sim_loop.c call (WRONG -- there is no cache to
 * clear) resolved to the same real cache_clear(xce_scheduler_t*), which
 * reinterpreted whatever field sits at unsatisfiable_cache's byte offset
 * in xce_sched_sim_driver_t as a kvtab_t* and clobbered it. That offset is
 * `alt_events_file` (sim.h) -- a live FILE* every --sim-alt-events run
 * depends on. Empirically confirmed by this task's round-1 reviewer, and
 * reproduced by this exact test file before round 2's fix (see this
 * task's own Status Report for the before/after run).
 *
 * ── The fix this proves ──────────────────────────────────────────────────
 * core_begin_session_internal() now calls a driver-registered hook
 * (core->cache_clear_cb, core.h's xce_core_cache_clear_cb_t) ONLY if
 * non-NULL, instead of calling cache_clear() unconditionally.
 * sim_loop.c never calls xce_core_set_cache_clear_cb() -- a simulation-
 * mode xce_sched_core_t's hook therefore stays NULL (xce_sched_core_
 * init()'s memset() default), and core_begin_session_internal() treats
 * NULL as "this driver has no cache to clear" and skips the call
 * entirely. This test constructs a real xce_sched_sim_driver_t, points
 * alt_events_file at a real, open FILE*, deliberately does NOT register
 * any cache_clear_cb (mirroring production sim_loop.c exactly), calls the
 * REAL xce_core_begin_session() (core_session.c's public entry point),
 * and asserts alt_events_file is bit-for-bit unchanged across the call.
 *
 * ── Link technique ───────────────────────────────────────────────────────
 * Same technique as the sibling test_core_session_cache_clear.c (round 1):
 * this fixture's meson.build entry lists core.c/core_clock.c/
 * core_session.c/decision.c/alloc_cache.c as genuinely SEPARATE compiled
 * sources rather than white-box #include-ing them, specifically so
 * alloc_cache.c's real, strong cache_clear(xce_scheduler_t*) IS present
 * in this binary -- if a future regression reintroduced an unconditional
 * call to it, this test would still catch it (a white-box #include of
 * core_session.c alone, without also linking alloc_cache.c, could not
 * have caught round 1's bug at all -- that is exactly why round 1's bug
 * was invisible to the existing suite).
 *
 * kill_sched_* / plugin_unregister / sched_worker_release_host_ctx stubs
 * below are identical, for identical reasons, to test_core_session_
 * cache_clear.c's own (see that file's header comment).
 */
#include <errno.h>
#include <stdint.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>

#include <unity/unity.h>

#include "sched/alloc_cache.h"
#include "sim.h"

void kill_sched_job(void* arg) { (void)arg; }
void kill_sched_queue(void* arg) { (void)arg; }
void kill_sched_worker(void* arg) { (void)arg; }
void kill_sched_user(void* arg) { (void)arg; }
void kill_sched_project(void* arg) { (void)arg; }
void kill_sched_resval(xce_val_t* val) { (void)val; }
void plugin_unregister(void* arg) { (void)arg; }

/* sched_worker_release_host_ctx (resource.c) is outside this test's linked
 * source set (only core.c/core_clock.c/core_session.c/decision.c/
 * alloc_cache.c, meson.build) -- this fixture never adds a worker, so it
 * is never actually invoked at runtime either. */
void sched_worker_release_host_ctx(xce_sched_worker_t* w) { (void)w; }

void setUp(void) { return; }
void tearDown(void) { return; }

/*
 * THE Observable this regression guards (Req 7.2, round-2 review
 * requirement): a simulation-mode xce_sched_core_t, which never registers
 * a cache_clear_cb, must never have any of its sibling xce_sched_sim_
 * driver_t fields touched by xce_core_begin_session() -- even with the
 * real, strong alloc_cache.c cache_clear(xce_scheduler_t*) linked into
 * the very same binary.
 */
static void test_sim_begin_session_never_corrupts_alt_events_file(void)
{
    xce_sched_sim_driver_t sim;
    FILE*                  f;
    int                    rc;

    memset(&sim, 0, sizeof(sim));

    rc = xce_sched_core_init(&(sim.core));
    TEST_ASSERT_EQUAL_INT(0, rc);

    /* A real, live FILE* -- exactly what a --sim-alt-events run holds
     * here in production. tmpfile() needs no cleanup path/permissions
     * setup and is auto-removed on fclose()/process exit. */
    f = tmpfile();
    TEST_ASSERT_NOT_NULL(f);
    sim.alt_events_file = f;

    /* Deliberately NOT calling xce_core_set_cache_clear_cb() here --
     * mirrors sim_loop.c exactly, which never registers this hook (Req 5
     * AC 17 "Simulation isolation": sim mode has no cache to clear). This
     * is the crux of the regression: before round 2's fix,
     * core_begin_session_internal() called cache_clear() unconditionally,
     * so linking alloc_cache.c's real, strong cache_clear(xce_scheduler_t*)
     * into this binary was enough to corrupt alt_events_file below even
     * though nothing here ever asked for a cache to be cleared. */
    rc = xce_core_begin_session(&(sim.core));
    TEST_ASSERT_EQUAL_INT(0, rc);

    TEST_ASSERT_EQUAL_PTR_MESSAGE(
        f, sim.alt_events_file,
        "xce_core_begin_session() corrupted xce_sched_sim_driver_t's "
        "alt_events_file -- core_begin_session_internal() must treat a "
        "NULL cache_clear_cb as a true no-op (Req 7.2 round 2), never "
        "fall through to alloc_cache.c's xce_scheduler_t*-typed "
        "cache_clear() for a simulation-mode core");

    rc = xce_core_end_session(&(sim.core));
    TEST_ASSERT_EQUAL_INT(0, rc);

    fclose(f);
}

int main(void)
{
    UNITY_BEGIN();
    RUN_TEST(test_sim_begin_session_never_corrupts_alt_events_file);
    return UNITY_END();
}