Linux kernel mirror (for testing)
git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git
kernel
os
linux
clocksource: Improve randomness in clocksource_verify_choose_cpus()
The current algorithm of picking a random CPU works OK for dense online
cpumask, but if cpumask is non-dense, the distribution of picked CPUs
is skewed.
For example, on 8-CPU board with CPUs 4-7 offlined, the probability of
selecting CPU 0 is 5/8. Accordingly, cpus 1, 2 and 3 are chosen with
probability 1/8 each. The proper algorithm should pick each online CPU
with probability 1/4.
Switch it to cpumask_random(), which has better statistical
characteristics.
CC: Andrew Morton <akpm@linux-foundation.org>
Acked-by: John Stultz <jstultz@google.com>
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: "Yury Norov [NVIDIA]" <yury.norov@gmail.com>
+1
-4
+1
-4
kernel/time/clocksource.c
+1
-4
kernel/time/clocksource.c
···
342
342
* CPUs that are currently online.
343
343
*/
344
344
for (i = 1; i < n; i++) {
345
-
cpu = get_random_u32_below(nr_cpu_ids);
346
-
cpu = cpumask_next(cpu - 1, cpu_online_mask);
347
-
if (cpu >= nr_cpu_ids)
348
-
cpu = cpumask_first(cpu_online_mask);
345
+
cpu = cpumask_random(cpu_online_mask);
349
346
if (!WARN_ON_ONCE(cpu >= nr_cpu_ids))
350
347
cpumask_set_cpu(cpu, &cpus_chosen);
351
348
}