On Tue, 10 Aug 2021 11:50:32 +0200
Sebastian Andrzej Siewior [off-list ref] wrote:
quoted hunk ↗ jump to hunk
- With lock kcov_remote_lock acquired there is a possible
hash_for_each_safe() and list_for_each() iteration. I don't know what
the limits are here but with a raw_spinlock_t it will contribute to
the maximal latency.
Note, anyone having a kernel with KCOV compiled in, probably doesn't
care about latency ;-) It's like worrying about latency when lockdep is
complied in.
-- Steve