static ulong csd_lock_timeout = 5000; /* CSD lock timeout in milliseconds. */
module_param(csd_lock_timeout, ulong, 0444);
+static int panic_on_ipistall; /* CSD panic timeout in milliseconds, 300000 for five minutes. */
+module_param(panic_on_ipistall, int, 0444);
static atomic_t csd_bug_count = ATOMIC_INIT(0);
}
ts2 = sched_clock();
+ /* How long since we last checked for a stuck CSD lock.*/
ts_delta = ts2 - *ts1;
if (likely(ts_delta <= csd_lock_timeout_ns || csd_lock_timeout_ns == 0))
return false;
else
cpux = cpu;
cpu_cur_csd = smp_load_acquire(&per_cpu(cur_csd, cpux)); /* Before func and info. */
+ /* How long since this CSD lock was stuck. */
+ ts_delta = ts2 - ts0;
pr_alert("csd: %s non-responsive CSD lock (#%d) on CPU#%d, waiting %llu ns for CPU#%02d %pS(%ps).\n",
- firsttime ? "Detected" : "Continued", *bug_id, raw_smp_processor_id(), ts2 - ts0,
+ firsttime ? "Detected" : "Continued", *bug_id, raw_smp_processor_id(), ts_delta,
cpu, csd->func, csd->info);
+ /*
+ * If the CSD lock is still stuck after 5 minutes, it is unlikely
+ * to become unstuck. Use a signed comparison to avoid triggering
+ * on underflows when the TSC is out of sync between sockets.
+ */
+ BUG_ON(panic_on_ipistall > 0 && (s64)ts_delta > ((s64)panic_on_ipistall * NSEC_PER_MSEC));
if (cpu_cur_csd && csd != cpu_cur_csd) {
pr_alert("\tcsd: CSD lock (#%d) handling prior %pS(%ps) request.\n",
*bug_id, READ_ONCE(per_cpu(cur_csd_func, cpux)),