* [PATCH 1/2] sched_ext: Don't kick CPUs running higher classes
2026-01-24 9:20 [PATCH 0/2] SCX kick fixes from 6.19 Christian Loehle
@ 2026-01-24 9:20 ` Christian Loehle
2026-01-28 14:18 ` Greg KH
2026-01-24 9:20 ` [PATCH 2/2] sched_ext: Fix SCX_KICK_WAIT to work reliably Christian Loehle
1 sibling, 1 reply; 5+ messages in thread
From: Christian Loehle @ 2026-01-24 9:20 UTC (permalink / raw)
To: stable, tj; +Cc: arighi, void, sched-ext
From: Tejun Heo <tj@kernel.org>
commit a9c1fbbd6dadbaa38c157a07d5d11005460b86b9 upstream.
When a sched_ext scheduler tries to kick a CPU, the CPU may be running a
higher class task. sched_ext has no control over such CPUs. A sched_ext
scheduler couldn't have expected to get access to the CPU after kicking it
anyway. Skip kicking when the target CPU is running a higher class.
Reviewed-by: Andrea Righi <arighi@nvidia.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
---
kernel/sched/ext.c | 11 ++++++++---
1 file changed, 8 insertions(+), 3 deletions(-)
diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c
index 31eda2a56920..3d53b2232937 100644
--- a/kernel/sched/ext.c
+++ b/kernel/sched/ext.c
@@ -5164,18 +5164,23 @@ static bool kick_one_cpu(s32 cpu, struct rq *this_rq, unsigned long *pseqs)
{
struct rq *rq = cpu_rq(cpu);
struct scx_rq *this_scx = &this_rq->scx;
+ const struct sched_class *cur_class;
bool should_wait = false;
unsigned long flags;
raw_spin_rq_lock_irqsave(rq, flags);
+ cur_class = rq->curr->sched_class;
/*
* During CPU hotplug, a CPU may depend on kicking itself to make
- * forward progress. Allow kicking self regardless of online state.
+ * forward progress. Allow kicking self regardless of online state. If
+ * @cpu is running a higher class task, we have no control over @cpu.
+ * Skip kicking.
*/
- if (cpu_online(cpu) || cpu == cpu_of(this_rq)) {
+ if ((cpu_online(cpu) || cpu == cpu_of(this_rq)) &&
+ !sched_class_above(cur_class, &ext_sched_class)) {
if (cpumask_test_cpu(cpu, this_scx->cpus_to_preempt)) {
- if (rq->curr->sched_class == &ext_sched_class)
+ if (cur_class == &ext_sched_class)
rq->curr->scx.slice = 0;
cpumask_clear_cpu(cpu, this_scx->cpus_to_preempt);
}
--
2.34.1
^ permalink raw reply related [flat|nested] 5+ messages in thread* [PATCH 2/2] sched_ext: Fix SCX_KICK_WAIT to work reliably
2026-01-24 9:20 [PATCH 0/2] SCX kick fixes from 6.19 Christian Loehle
2026-01-24 9:20 ` [PATCH 1/2] sched_ext: Don't kick CPUs running higher classes Christian Loehle
@ 2026-01-24 9:20 ` Christian Loehle
1 sibling, 0 replies; 5+ messages in thread
From: Christian Loehle @ 2026-01-24 9:20 UTC (permalink / raw)
To: stable, tj; +Cc: arighi, void, sched-ext, Wen-Fang Liu, Peter Zijlstra
From: Tejun Heo <tj@kernel.org>
commit a379fa1e2cae15d7422b4eead83a6366f2f445cb upstream.
SCX_KICK_WAIT is used to synchronously wait for the target CPU to complete
a reschedule and can be used to implement operations like core scheduling.
This used to be implemented by scx_next_task_picked() incrementing pnt_seq,
which was always called when a CPU picks the next task to run, allowing
SCX_KICK_WAIT to reliably wait for the target CPU to enter the scheduler and
pick the next task.
However, commit b999e365c298 ("sched_ext: Replace scx_next_task_picked()
with switch_class()") replaced scx_next_task_picked() with the
switch_class() callback, which is only called when switching between sched
classes. This broke SCX_KICK_WAIT because pnt_seq would no longer be
reliably incremented unless the previous task was SCX and the next task was
not.
This fix leverages commit 4c95380701f5 ("sched/ext: Fold balance_scx() into
pick_task_scx()") which refactored the pick path making put_prev_task_scx()
the natural place to track task switches for SCX_KICK_WAIT. The fix moves
pnt_seq increment to put_prev_task_scx() and also increments it in
pick_task_scx() to handle cases where the same task is re-selected, whether
by BPF scheduler decision or slice refill. The semantics: If the current
task on the target CPU is SCX, SCX_KICK_WAIT waits until the CPU enters the
scheduling path. This provides sufficient guarantee for use cases like core
scheduling while keeping the operation self-contained within SCX.
v2: - Also increment pnt_seq in pick_task_scx() to handle same-task
re-selection (Andrea Righi).
- Use smp_cond_load_acquire() for the busy-wait loop for better
architecture optimization (Peter Zijlstra).
Reported-by: Wen-Fang Liu <liuwenfang@honor.com>
Link: http://lkml.kernel.org/r/228ebd9e6ed3437996dffe15735a9caa@honor.com
Cc: Peter Zijlstra <peterz@infradead.org>
Reviewed-by: Andrea Righi <arighi@nvidia.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
---
kernel/sched/ext.c | 46 +++++++++++++++++++++----------------
kernel/sched/ext_internal.h | 6 +++--
2 files changed, 30 insertions(+), 22 deletions(-)
diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c
index 3d53b2232937..2ff7034841c7 100644
--- a/kernel/sched/ext.c
+++ b/kernel/sched/ext.c
@@ -2306,12 +2306,6 @@ static void switch_class(struct rq *rq, struct task_struct *next)
struct scx_sched *sch = scx_root;
const struct sched_class *next_class = next->sched_class;
- /*
- * Pairs with the smp_load_acquire() issued by a CPU in
- * kick_cpus_irq_workfn() who is waiting for this CPU to perform a
- * resched.
- */
- smp_store_release(&rq->scx.pnt_seq, rq->scx.pnt_seq + 1);
if (!(sch->ops.flags & SCX_OPS_HAS_CPU_PREEMPT))
return;
@@ -2351,6 +2345,10 @@ static void put_prev_task_scx(struct rq *rq, struct task_struct *p,
struct task_struct *next)
{
struct scx_sched *sch = scx_root;
+
+ /* see kick_cpus_irq_workfn() */
+ smp_store_release(&rq->scx.pnt_seq, rq->scx.pnt_seq + 1);
+
update_curr_scx(rq);
/* see dequeue_task_scx() on why we skip when !QUEUED */
@@ -2404,6 +2402,9 @@ static struct task_struct *pick_task_scx(struct rq *rq)
bool keep_prev = rq->scx.flags & SCX_RQ_BAL_KEEP;
bool kick_idle = false;
+ /* see kick_cpus_irq_workfn() */
+ smp_store_release(&rq->scx.pnt_seq, rq->scx.pnt_seq + 1);
+
/*
* WORKAROUND:
*
@@ -5186,8 +5187,12 @@ static bool kick_one_cpu(s32 cpu, struct rq *this_rq, unsigned long *pseqs)
}
if (cpumask_test_cpu(cpu, this_scx->cpus_to_wait)) {
- pseqs[cpu] = rq->scx.pnt_seq;
- should_wait = true;
+ if (cur_class == &ext_sched_class) {
+ pseqs[cpu] = rq->scx.pnt_seq;
+ should_wait = true;
+ } else {
+ cpumask_clear_cpu(cpu, this_scx->cpus_to_wait);
+ }
}
resched_curr(rq);
@@ -5248,18 +5253,19 @@ static void kick_cpus_irq_workfn(struct irq_work *irq_work)
for_each_cpu(cpu, this_scx->cpus_to_wait) {
unsigned long *wait_pnt_seq = &cpu_rq(cpu)->scx.pnt_seq;
- if (cpu != cpu_of(this_rq)) {
- /*
- * Pairs with smp_store_release() issued by this CPU in
- * switch_class() on the resched path.
- *
- * We busy-wait here to guarantee that no other task can
- * be scheduled on our core before the target CPU has
- * entered the resched path.
- */
- while (smp_load_acquire(wait_pnt_seq) == pseqs[cpu])
- cpu_relax();
- }
+ /*
+ * Busy-wait until the task running at the time of kicking is no
+ * longer running. This can be used to implement e.g. core
+ * scheduling.
+ *
+ * smp_cond_load_acquire() pairs with store_releases in
+ * pick_task_scx() and put_prev_task_scx(). The former breaks
+ * the wait if SCX's scheduling path is entered even if the same
+ * task is picked subsequently. The latter is necessary to break
+ * the wait when $cpu is taken by a higher sched class.
+ */
+ if (cpu != cpu_of(this_rq))
+ smp_cond_load_acquire(wait_pnt_seq, VAL != pseqs[cpu]);
cpumask_clear_cpu(cpu, this_scx->cpus_to_wait);
}
diff --git a/kernel/sched/ext_internal.h b/kernel/sched/ext_internal.h
index b3617abed510..601cfae8cc76 100644
--- a/kernel/sched/ext_internal.h
+++ b/kernel/sched/ext_internal.h
@@ -986,8 +986,10 @@ enum scx_kick_flags {
SCX_KICK_PREEMPT = 1LLU << 1,
/*
- * Wait for the CPU to be rescheduled. The scx_bpf_kick_cpu() call will
- * return after the target CPU finishes picking the next task.
+ * The scx_bpf_kick_cpu() call will return after the current SCX task of
+ * the target CPU switches out. This can be used to implement e.g. core
+ * scheduling. This has no effect if the current task on the target CPU
+ * is not on SCX.
*/
SCX_KICK_WAIT = 1LLU << 2,
};
--
2.34.1
^ permalink raw reply related [flat|nested] 5+ messages in thread