/*
 * test_netio_arm_failure.c — libxce-failover: a poll-arm failure must fail LOUD.
 *
 * Root cause (bug-646): endpoint_update_epoll() swallowed iomgr_update_poll()
 * (EPOLL_CTL_MOD) failures — it logged "rc1=-1 < 0" but returned 0 and left the
 * poll interest unarmed.  On the synchronous client send path (endpoint_enq),
 * a failed arm meant the request bytes were never flushed, no reply ever
 * arrived, and the caller blocked forever in cbuf_get() while a perfectly
 * healthy io_worker slept in epoll_wait().  (EPOLL_CTL_MOD fails with ENOENT
 * when the fd is no longer registered — e.g. after a failed reconnect.)
 *
 * Contract under test: when the poll interest cannot be armed, endpoint_enq()
 * must (1) return a negative, RETRIABLE error so the caller propagates it
 * (request.c senders return it; the client failover loop rotates — bug-650),
 * and (2) must NOT synchronously invoke the endpoint's err_handler.  endpoint_enq
 * runs on the caller's thread, which may already hold a lock the err_handler
 * needs (the controller's primary_heartbeat_fn holds ha->lock and
 * vote_ep_err_handler re-acquires it → self-deadlock, bug-652).  The real
 * teardown stays on the io_worker thread, off the next epoll error event.
 */

#define _GNU_SOURCE
#include <errno.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <sys/socket.h>
#include <unistd.h>

#include <unity/unity.h>
#include "netio.h"

/* ── err_handler invocation tracker ──────────────────────────────── */

static int g_err_count = 0;

static int err_handler_stub(void *ep)
{
    (void)ep;
    g_err_count++;
    return 0;
}

/*
 * Arming EPOLL_CTL_MOD on an fd that was never EPOLL_CTL_ADD'd fails with
 * ENOENT — the exact post-failed-reconnect condition.  endpoint_enq() must
 * surface it (negative rc) WITHOUT calling the err_handler (no re-entrancy).
 */
static void test_enq_arm_failure_is_loud_no_errhandler(void)
{
    iomgr_t iomgr;
    memset(&iomgr, 0, sizeof(iomgr));
    TEST_ASSERT_EQUAL_INT(0, iomgr_init(&iomgr));

    endpoint_t *ep = endpoint_get();
    TEST_ASSERT_NOT_NULL(ep);

    /* A real socket fd that is NOT registered in iomgr's epoll: EPOLL_CTL_MOD
     * on it fails with ENOENT, mirroring a send after a failed reconnect. */
    ep->fd = socket(AF_INET, SOCK_STREAM, 0);
    TEST_ASSERT_TRUE(ep->fd >= 0);
    ep->iomgr              = &iomgr;
    ep->ssl_handshake_done = 1; /* past handshake: calc_flags arms EPOLLIN     */
    ep->flags              = 0; /* force flags != calc_flags → iomgr_update_poll */
    endpoint_set_err_handler(ep, (err_handler_t)err_handler_stub);

    g_err_count = 0;

    /* One packet on the outq so there is real outbound work to strand. The
     * endpoint owns it after enq; endpoint_fini drains it via outq_item_killer. */
    io_packet_t *pkt = (io_packet_t *)calloc(1, sizeof(*pkt));
    TEST_ASSERT_NOT_NULL(pkt);

    int rc = endpoint_enq(ep, &pkt->link);

    /* Loud failure (negative, retriable) so the caller propagates and rotates —
     * but the err_handler must NOT be invoked from this synchronous send path
     * (re-entrancy would self-deadlock the controller, bug-652). */
    TEST_ASSERT_TRUE(rc < 0);
    TEST_ASSERT_EQUAL_INT(0, g_err_count);

    endpoint_fini(ep);
    free(ep);
    close(iomgr.epoll_fd);
    printf("test_enq_arm_failure_is_loud_no_errhandler: PASS\n");
}

/* ── suite entry point ───────────────────────────────────────────── */

void test_netio_arm_failure(void)
{
    printf("\n>> netio poll-arm failure tests\n\n");

    RUN_TEST(test_enq_arm_failure_is_loud_no_errhandler);
}