This is a note to let you know that I've just added the patch titled
sched/fair: Add EAS checks before updating root_domain::overutilized
to the 6.6-stable tree which can be found at:
http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=summary
The filename of the patch is:
sched-fair-add-eas-checks-before-updating-root_domai.patch
and it can be found in the queue-6.6 subdirectory.
If you, or anyone else, feels it should not be added to the stable tree,
please let <stable@xxxxxxxxxxxxxxx> know about it.
commit 44ec23e7d5db53b422621a1e17a8456b5f75abdc
Author: Shrikanth Hegde <sshegde@xxxxxxxxxxxxx>
Date: Thu Mar 7 14:27:23 2024 +0530
sched/fair: Add EAS checks before updating root_domain::overutilized
[ Upstream commit be3a51e68f2f1b17250ce40d8872c7645b7a2991 ]
root_domain::overutilized is only used for EAS(energy aware scheduler)
to decide whether to do load balance or not. It is not used if EAS
not possible.
Currently enqueue_task_fair and task_tick_fair accesses, sometime updates
this field. In update_sd_lb_stats it is updated often. This causes cache
contention due to true sharing and burns a lot of cycles. ::overload and
::overutilized are part of the same cacheline. Updating it often invalidates
the cacheline. That causes access to ::overload to slow down due to
false sharing. Hence add EAS check before accessing/updating this field.
EAS check is optimized at compile time or it is a static branch.
Hence it shouldn't cost much.
With the patch, both enqueue_task_fair and newidle_balance don't show
up as hot routines in perf profile.
6.8-rc4:
7.18% swapper [kernel.vmlinux] [k] enqueue_task_fair
6.78% s [kernel.vmlinux] [k] newidle_balance
+patch:
0.14% swapper [kernel.vmlinux] [k] enqueue_task_fair
0.00% swapper [kernel.vmlinux] [k] newidle_balance
While at it: trace_sched_overutilized_tp expect that second argument to
be bool. So do a int to bool conversion for that.
Fixes: 2802bf3cd936 ("sched/fair: Add over-utilization/tipping point indicator")
Signed-off-by: Shrikanth Hegde <sshegde@xxxxxxxxxxxxx>
Signed-off-by: Ingo Molnar <mingo@xxxxxxxxxx>
Reviewed-by: Qais Yousef <qyousef@xxxxxxxxxxx>
Reviewed-by: Srikar Dronamraju <srikar@xxxxxxxxxxxxx>
Reviewed-by: Vincent Guittot <vincent.guittot@xxxxxxxxxx>
Link: https://lore.kernel.org/r/20240307085725.444486-2-sshegde@xxxxxxxxxxxxx
Signed-off-by: Sasha Levin <sashal@xxxxxxxxxx>
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 397ef27c9bdb1..01b3fc97ddc27 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -6564,22 +6564,42 @@ static inline void hrtick_update(struct rq *rq)
#ifdef CONFIG_SMP
static inline bool cpu_overutilized(int cpu)
{
- unsigned long rq_util_min = uclamp_rq_get(cpu_rq(cpu), UCLAMP_MIN);
- unsigned long rq_util_max = uclamp_rq_get(cpu_rq(cpu), UCLAMP_MAX);
+ unsigned long rq_util_min, rq_util_max;
+
+ if (!sched_energy_enabled())
+ return false;
+
+ rq_util_min = uclamp_rq_get(cpu_rq(cpu), UCLAMP_MIN);
+ rq_util_max = uclamp_rq_get(cpu_rq(cpu), UCLAMP_MAX);
/* Return true only if the utilization doesn't fit CPU's capacity */
return !util_fits_cpu(cpu_util_cfs(cpu), rq_util_min, rq_util_max, cpu);
}
-static inline void update_overutilized_status(struct rq *rq)
+static inline void set_rd_overutilized_status(struct root_domain *rd,
+ unsigned int status)
{
- if (!READ_ONCE(rq->rd->overutilized) && cpu_overutilized(rq->cpu)) {
- WRITE_ONCE(rq->rd->overutilized, SG_OVERUTILIZED);
- trace_sched_overutilized_tp(rq->rd, SG_OVERUTILIZED);
- }
+ if (!sched_energy_enabled())
+ return;
+
+ WRITE_ONCE(rd->overutilized, status);
+ trace_sched_overutilized_tp(rd, !!status);
+}
+
+static inline void check_update_overutilized_status(struct rq *rq)
+{
+ /*
+ * overutilized field is used for load balancing decisions only
+ * if energy aware scheduler is being used
+ */
+ if (!sched_energy_enabled())
+ return;
+
+ if (!READ_ONCE(rq->rd->overutilized) && cpu_overutilized(rq->cpu))
+ set_rd_overutilized_status(rq->rd, SG_OVERUTILIZED);
}
#else
-static inline void update_overutilized_status(struct rq *rq) { }
+static inline void check_update_overutilized_status(struct rq *rq) { }
#endif
/* Runqueue only has SCHED_IDLE tasks enqueued */
@@ -6680,7 +6700,7 @@ enqueue_task_fair(struct rq *rq, struct task_struct *p, int flags)
* and the following generally works well enough in practice.
*/
if (!task_new)
- update_overutilized_status(rq);
+ check_update_overutilized_status(rq);
enqueue_throttle:
assert_list_leaf_cfs_rq(rq);
@@ -10500,19 +10520,14 @@ static inline void update_sd_lb_stats(struct lb_env *env, struct sd_lb_stats *sd
env->fbq_type = fbq_classify_group(&sds->busiest_stat);
if (!env->sd->parent) {
- struct root_domain *rd = env->dst_rq->rd;
-
/* update overload indicator if we are at root domain */
- WRITE_ONCE(rd->overload, sg_status & SG_OVERLOAD);
+ WRITE_ONCE(env->dst_rq->rd->overload, sg_status & SG_OVERLOAD);
/* Update over-utilization (tipping point, U >= 0) indicator */
- WRITE_ONCE(rd->overutilized, sg_status & SG_OVERUTILIZED);
- trace_sched_overutilized_tp(rd, sg_status & SG_OVERUTILIZED);
+ set_rd_overutilized_status(env->dst_rq->rd,
+ sg_status & SG_OVERUTILIZED);
} else if (sg_status & SG_OVERUTILIZED) {
- struct root_domain *rd = env->dst_rq->rd;
-
- WRITE_ONCE(rd->overutilized, SG_OVERUTILIZED);
- trace_sched_overutilized_tp(rd, SG_OVERUTILIZED);
+ set_rd_overutilized_status(env->dst_rq->rd, SG_OVERUTILIZED);
}
update_idle_cpu_scan(env, sum_util);
@@ -12503,7 +12518,7 @@ static void task_tick_fair(struct rq *rq, struct task_struct *curr, int queued)
task_tick_numa(rq, curr);
update_misfit_status(curr, rq);
- update_overutilized_status(task_rq(curr));
+ check_update_overutilized_status(task_rq(curr));
task_tick_core(rq, curr);
}
