kevin/linux
1
Fork 0
Code

locking/csd-lock: Use backoff for repeated reports of same incident

Browse Source 
Currently, the CSD-lock diagnostics in CONFIG_CSD_LOCK_WAIT_DEBUG=y
kernels are emitted at five-second intervals.  Although this has proven
to be a good time interval for the first diagnostic, if the target CPU
keeps interrupts disabled for way longer than five seconds, the ratio
of useful new information to pointless repetition increases considerably.

Therefore, back off the time period for repeated reports of the same
incident, increasing linearly with the number of reports and logarithmicly
with the number of online CPUs.

[ paulmck: Apply Dan Carpenter feedback. ]

Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
Cc: Imran Khan <imran.f.khan@oracle.com>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Leonardo Bras <leobras@redhat.com>
Cc: "Peter Zijlstra (Intel)" <peterz@infradead.org>
Cc: Rik van Riel <riel@surriel.com>
Reviewed-by: Rik van Riel <riel@surriel.com>
Signed-off-by: Neeraj Upadhyay <neeraj.upadhyay@kernel.org>
This commit is contained in:
Paul E. McKenney 2024-07-02 14:32:20 -07:00 committed by Neeraj Upadhyay
parent ac9d45544c
commit d40760d681
1 changed files with 7 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

10
kernel/smp.c
View File

@ -226,7 +226,7 @@ bool csd_lock_is_stuck(void)
* the CSD_TYPE_SYNC/ASYNC types provide the destination CPU, * the CSD_TYPE_SYNC/ASYNC types provide the destination CPU,
* so waiting on other types gets much less information. * so waiting on other types gets much less information.
*/ */
static bool csd_lock_wait_toolong(call_single_data_t *csd, u64 ts0, u64 *ts1, int *bug_id) static bool csd_lock_wait_toolong(call_single_data_t *csd, u64 ts0, u64 *ts1, int *bug_id, unsigned long *nmessages)
{ {
int cpu = -1; int cpu = -1;
int cpux; int cpux;
@ -249,7 +249,9 @@ static bool csd_lock_wait_toolong(call_single_data_t *csd, u64 ts0, u64 *ts1, in
ts2 = sched_clock(); ts2 = sched_clock();
/* How long since we last checked for a stuck CSD lock.*/ /* How long since we last checked for a stuck CSD lock.*/
ts_delta = ts2 - *ts1; ts_delta = ts2 - *ts1;
if (likely(ts_delta <= csd_lock_timeout_ns || csd_lock_timeout_ns == 0)) if (likely(ts_delta <= csd_lock_timeout_ns * (*nmessages + 1) *
(!*nmessages ? 1 : (ilog2(num_online_cpus()) / 2 + 1)) ||
csd_lock_timeout_ns == 0))
return false; return false;
firsttime = !*bug_id; firsttime = !*bug_id;
@ -266,6 +268,7 @@ static bool csd_lock_wait_toolong(call_single_data_t *csd, u64 ts0, u64 *ts1, in
pr_alert("csd: %s non-responsive CSD lock (#%d) on CPU#%d, waiting %lld ns for CPU#%02d %pS(%ps).\n", pr_alert("csd: %s non-responsive CSD lock (#%d) on CPU#%d, waiting %lld ns for CPU#%02d %pS(%ps).\n",
firsttime ? "Detected" : "Continued", *bug_id, raw_smp_processor_id(), (s64)ts_delta, firsttime ? "Detected" : "Continued", *bug_id, raw_smp_processor_id(), (s64)ts_delta,
cpu, csd->func, csd->info); cpu, csd->func, csd->info);
(*nmessages)++;
if (firsttime) if (firsttime)
atomic_inc(&n_csd_lock_stuck); atomic_inc(&n_csd_lock_stuck);
/* /*
@ -306,12 +309,13 @@ static bool csd_lock_wait_toolong(call_single_data_t *csd, u64 ts0, u64 *ts1, in
*/ */
static void __csd_lock_wait(call_single_data_t *csd) static void __csd_lock_wait(call_single_data_t *csd)
{ {
unsigned long nmessages = 0;
int bug_id = 0; int bug_id = 0;
u64 ts0, ts1; u64 ts0, ts1;
ts1 = ts0 = sched_clock(); ts1 = ts0 = sched_clock();
for (;;) { for (;;) {
if (csd_lock_wait_toolong(csd, ts0, &ts1, &bug_id)) if (csd_lock_wait_toolong(csd, ts0, &ts1, &bug_id, &nmessages))
break; break;
cpu_relax(); cpu_relax();
} }