[tip: sched/urgent] sched/fair: Fix SMT4 group_smt_balance handling

[tip-bot2 for Tim Chen]

The following commit has been merged into the sched/urgent branch of tip:

Commit-ID:     450e749707bc1755f22b505d9cd942d4869dc535
Gitweb:        https://git.kernel.org/tip/450e749707bc1755f22b505d9cd942d4869dc535
Author:        Tim Chen <tim.c.chen@xxxxxxxxxxxxxxx>
AuthorDate:    Thu, 07 Sep 2023 10:42:21 -07:00
Committer:     Ingo Molnar <mingo@xxxxxxxxxx>
CommitterDate: Wed, 13 Sep 2023 15:03:06 +02:00

sched/fair: Fix SMT4 group_smt_balance handling

For SMT4, any group with more than 2 tasks will be marked as
group_smt_balance. Retain the behaviour of group_has_spare by marking
the busiest group as the group which has the least number of idle_cpus.

Also, handle rounding effect of adding (ncores_local + ncores_busy) when
the local is fully idle and busy group imbalance is less than 2 tasks.
Local group should try to pull at least 1 task in this case so imbalance
should be set to 2 instead.

Fixes: fee1759e4f04 ("sched/fair: Determine active load balance for SMT sched groups")
Acked-by: Shrikanth Hegde <sshegde@xxxxxxxxxxxxxxxxxx>
Signed-off-by: Tim Chen <tim.c.chen@xxxxxxxxxxxxxxx>
Signed-off-by: Peter Zijlstra (Intel) <peterz@xxxxxxxxxxxxx>
Signed-off-by: Ingo Molnar <mingo@xxxxxxxxxx>
Link: http://lkml.kernel.org/r/6cd1633036bb6b651af575c32c2a9608a106702c.camel@xxxxxxxxxxxxxxx
---
 kernel/sched/fair.c | 12 +++++++++++-
 1 file changed, 11 insertions(+), 1 deletion(-)

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 33a2b6b..cb22592 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -9580,7 +9580,7 @@ static inline long sibling_imbalance(struct lb_env *env,
 	imbalance /= ncores_local + ncores_busiest;
 
 	/* Take advantage of resource in an empty sched group */
-	if (imbalance == 0 && local->sum_nr_running == 0 &&
+	if (imbalance <= 1 && local->sum_nr_running == 0 &&
 	    busiest->sum_nr_running > 1)
 		imbalance = 2;
 
@@ -9768,6 +9768,15 @@ static bool update_sd_pick_busiest(struct lb_env *env,
 		break;
 
 	case group_smt_balance:
+		/*
+		 * Check if we have spare CPUs on either SMT group to
+		 * choose has spare or fully busy handling.
+		 */
+		if (sgs->idle_cpus != 0 || busiest->idle_cpus != 0)
+			goto has_spare;
+
+		fallthrough;
+
 	case group_fully_busy:
 		/*
 		 * Select the fully busy group with highest avg_load. In
@@ -9807,6 +9816,7 @@ static bool update_sd_pick_busiest(struct lb_env *env,
 			else
 				return true;
 		}
+has_spare:
 
 		/*
 		 * Select not overloaded group with lowest number of idle cpus