On Fri, Dec 20, 2024 at 04:11:37PM +0100, Andrea Righi wrote: > Add a comments to clarify about the usage of cpumask_intersects(). > > Moreover, update scx_select_cpu_dfl() description clarifying that the > final step of the idle selection logic involves searching for any idle > CPU in the system that the task can use. > > Signed-off-by: Andrea Righi <arighi@xxxxxxxxxx> Reviewed-by: Yury Norov <yury.norov@xxxxxxxxx> > --- > kernel/sched/ext_idle.c | 6 ++++++ > 1 file changed, 6 insertions(+) > > diff --git a/kernel/sched/ext_idle.c b/kernel/sched/ext_idle.c > index dedd39febc88..4952e2793304 100644 > --- a/kernel/sched/ext_idle.c > +++ b/kernel/sched/ext_idle.c > @@ -52,6 +52,10 @@ static bool test_and_clear_cpu_idle(int cpu) > * scx_pick_idle_cpu() can get caught in an infinite loop as > * @cpu is never cleared from idle_masks.smt. Ensure that @cpu > * is eventually cleared. > + * > + * NOTE: Use cpumask_intersects() and cpumask_test_cpu() to > + * reduce memory writes, which may help alleviate cache > + * coherence pressure. > */ > if (cpumask_intersects(smt, idle_masks.smt)) > cpumask_andnot(idle_masks.smt, idle_masks.smt, smt); > @@ -280,6 +284,8 @@ static void update_selcpu_topology(void) > * 4. Pick a CPU within the same NUMA node, if enabled: > * - choose a CPU from the same NUMA node to reduce memory access latency. > * > + * 5. Pick any idle CPU usable by the task. > + * > * Step 3 and 4 are performed only if the system has, respectively, multiple > * LLC domains / multiple NUMA nodes (see scx_selcpu_topo_llc and > * scx_selcpu_topo_numa). > -- > 2.47.1
