Kees Cook
c7fea48876
lkdtm: Provide timing tests for atomic_t vs refcount_t
...
While not a crash test, this does provide two tight atomic_t and
refcount_t loops for performance comparisons:
cd /sys/kernel/debug/provoke-crash
perf stat -B -- cat <(echo ATOMIC_TIMING) > DIRECT
perf stat -B -- cat <(echo REFCOUNT_TIMING) > DIRECT
Looking a CPU cycles is the best way to example the fast-path (rather
than instruction counts, since conditional jumps will be executed but
will be negligible due to branch-prediction).
Signed-off-by: Kees Cook <keescook@chromium.org >
2017-07-26 14:38:04 -07:00
..
2015-06-25 17:00:38 -07:00
2017-05-08 17:15:10 -07:00
2017-07-03 23:07:03 +10:00
2017-04-08 18:22:59 +02:00
2017-03-02 08:42:29 +01:00
2017-03-02 08:42:32 +01:00
2017-03-02 08:42:32 +01:00
2017-06-13 15:46:18 +02:00
2017-05-02 23:41:43 +03:00
2017-03-09 11:48:47 -08:00
2017-05-28 10:22:42 -07:00
2017-06-16 11:48:37 -04:00
2017-05-08 17:15:10 -07:00
2015-09-20 19:33:29 -07:00
2015-10-28 10:30:17 +09:00
2016-03-01 16:55:13 -08:00
2017-06-13 16:03:22 +02:00
2017-04-08 17:37:20 +02:00
2017-06-03 19:15:18 +09:00
2015-10-06 12:33:14 +02:00
2016-12-15 12:13:31 +00:00
2017-05-25 18:25:00 +02:00
2017-04-08 18:22:59 +02:00
2017-04-20 12:02:32 +01:00
2017-07-01 16:52:38 -04:00
2016-09-27 12:53:46 +02:00
2015-01-12 05:04:11 -08:00
2015-08-10 08:37:35 +02:00
2017-06-03 19:15:18 +09:00
2017-03-02 08:42:35 +01:00
2015-10-28 10:30:17 +09:00
2017-07-26 14:38:03 -07:00
2017-07-26 14:38:04 -07:00
2017-03-02 08:42:31 +01:00
2016-11-10 15:34:56 +01:00
2017-07-26 14:38:04 -07:00
2016-08-31 13:12:38 +02:00
2017-03-02 08:42:36 +01:00
2017-07-26 14:38:04 -07:00
2017-07-26 14:38:03 -07:00
2016-08-31 15:45:18 +02:00
2017-04-28 10:23:19 -05:00
2016-05-01 14:20:04 -07:00
2015-10-13 22:17:40 -07:00
2017-05-18 17:37:52 +02:00
2017-01-25 11:48:03 +01:00
2017-01-25 11:48:03 +01:00
2015-10-28 10:30:17 +09:00
2015-03-25 11:36:38 +01:00
2017-04-08 18:22:59 +02:00
2017-03-02 08:42:32 +01:00
2015-11-06 17:50:42 -08:00