mirror of
https://github.com/tangerineturtle1/NX2navi.git
synced 2026-11-19 04:19:57 -04:00
Let the first failure report end the run whole when another thread crashes or hits a fatal error beside it.
The platform layer calls the crash handler on every thread that faults, without waiting for the others (win32.c crash_veh, crash_filter), and main.c crash_handler ended any second entry with plat_exit(71) at once. So a second fault during the first report cut it after its first lines, together with its wait for a save Commit (fs_save_crash_wait) and RivaTuner's restore; the audit's probe showed it in 3 of 3 runs. fatal_end had no guard at all and none shared with the crash report: a crash during a FATAL's end wrote a whole crash report whose "FATAL: access violation" became the log's last FATAL line (the one the launcher shows) and replaced code 70 with 71, and a FATAL during a crash report cut it with code 70. dispatch.c rt_ending_enter is the one guard for both ends: the first caller reports and ends the process; the same thread again (a failure inside its own report) ends at once with its own code (crash_handler keeps plat_exit(71), fatal_end plat_terminate(code)); another thread waits in 10 ms sleeps, logging nothing since it may hold the log queue's lock, until the process ends, and after 30 s ends it with 71 should the first report hang. fatal_end calls it first; crash_handler calls it in place of its own busy flag. Reproduced before the change by tests/fatal_exit_check.py's new cases, which failed on the old guards: two faults at once (report lines 2 and 3 missing), a fault during rt_fatal (a crash report after the FATAL) and rt_fatal during a crash report (exit 70, the report cut). They pass now, with the earlier cases and the static check that crash_handler starts with the shared guard; the compile checks pass. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
@@ -59,9 +59,27 @@ void rt_fatal_notes(void) {
|
||||
|
||||
__attribute__((weak)) void fs_save_crash_wait(void) {} // fs_host.c; builds without it (the unit checks) have no saves
|
||||
|
||||
// One end for a failed run. The platform layer calls the crash handler on every thread that faults, without
|
||||
// waiting for the others (platform/win32.c crash_veh, crash_filter), and a fatal error can come beside a crash from
|
||||
// the same bad state (an allocation that failed here, a null pointer read there). The later end cut the first report
|
||||
// where it was, together with its wait for a save Commit and RivaTuner's restore, and its own FATAL line and exit
|
||||
// code replaced the first (the launcher shows the last FATAL). Another thread now waits until the first end is done;
|
||||
// it logs nothing, since it may hold the log queue's lock, which the first report only tries. A first report that
|
||||
// hangs still ends: after 30 s the waiting thread ends the process with the crash report's code.
|
||||
static volatile uint32_t ending_tid; // the thread that reports, 0 before one does
|
||||
|
||||
int rt_ending_enter(void) {
|
||||
uint32_t me = plat_thread_id(), was = 0;
|
||||
if (__atomic_compare_exchange_n(&ending_tid, &was, me, 0, __ATOMIC_ACQ_REL, __ATOMIC_ACQUIRE)) return 1;
|
||||
if (was == me) return 0;
|
||||
for (int i = 0; i < 3000; i++) plat_sleep_ms(10);
|
||||
plat_terminate(71);
|
||||
}
|
||||
|
||||
// The fatal line, the report's notes and what has to be flushed, then the exit with `code`.
|
||||
static void fatal_end(int code, const char *fmt, va_list ap) __attribute__((noreturn));
|
||||
static void fatal_end(int code, const char *fmt, va_list ap) {
|
||||
if (!rt_ending_enter()) plat_terminate(code); // a fatal error inside this thread's own report: no second one
|
||||
rt_log_sync(); // main.c: the lines queued for the log thread, then these, written here
|
||||
rt_log_raw("FATAL: ", 7);
|
||||
rt_vlogf(fmt, ap);
|
||||
|
||||
@@ -62,3 +62,7 @@ void rt_fatal_code(int code, const char *fmt, ...) __attribute__((noreturn, form
|
||||
// needs none. At most four; adding one twice keeps one. rt_fatal_notes runs them, once per process.
|
||||
void rt_fatal_note_add(void (*fn)(void));
|
||||
void rt_fatal_notes(void);
|
||||
// The one end of a failed run: the fatal error (rt_fatal) and the crash report (main.c crash_handler) call it first. 1
|
||||
// for the first caller, which reports and ends the process; 0 for that thread again (a failure inside its own report),
|
||||
// which ends at once with its code; any other thread waits, logging nothing, until the process ends (30 s at most).
|
||||
int rt_ending_enter(void);
|
||||
|
||||
@@ -315,8 +315,9 @@ static volatile int32_t mode_done;
|
||||
static int mode_rc;
|
||||
|
||||
static void crash_handler(const PlatCrash *x) {
|
||||
static volatile int32_t busy;
|
||||
if (plat_xchg32(&busy, 1)) plat_exit(71);
|
||||
// shared with the fatal error's end (dispatch.c rt_ending_enter): another thread's fault or fatal error waits there
|
||||
// while this report is written; a fault inside this thread's own report ends the process at once
|
||||
if (!rt_ending_enter()) plat_exit(71);
|
||||
if (__atomic_load_n(&mode_done, __ATOMIC_ACQUIRE) && x->module) {
|
||||
rt_log("exit: %s (%#x) in %s while the process was ending, after its work was done and saved%s: the run ends "
|
||||
"with its own code %d", x->what, x->code, *x->module ? x->module : "code outside every module",
|
||||
|
||||
Reference in New Issue
Block a user