From 0366017e0973a52245787e972c8ac68a88692bba Mon Sep 17 00:00:00 2001
From: Tejun Heo <tj@kernel.org>
Date: Fri, 30 Aug 2024 00:51:40 -1000
Subject: [PATCH] sched_ext: Use task_can_run_on_remote_rq() test in
dispatch_to_local_dsq()
When deciding whether a task can be migrated to a CPU,
dispatch_to_local_dsq() was open-coding p->cpus_allowed and scx_rq_online()
tests instead of using task_can_run_on_remote_rq(). This had two problems.
- It was missing is_migration_disabled() check and thus could try to migrate
a task which shouldn't leading to assertion and scheduling failures.
- It was testing p->cpus_ptr directly instead of using task_allowed_on_cpu()
and thus failed to consider ISA compatibility.
Update dispatch_to_local_dsq() to use task_can_run_on_remote_rq():
- Move scx_ops_error() triggering into task_can_run_on_remote_rq().
- When migration isn't allowed, fall back to the global DSQ instead of the
source DSQ by returning DTL_INVALID. This is both simpler and an overall
better behavior.
Signed-off-by: Tejun Heo <tj@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Acked-by: David Vernet <void@manifault.com>
---
kernel/sched/ext.c | 40 ++++++++++++++++++++--------------------
1 file changed, 20 insertions(+), 20 deletions(-)
diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c
index 57f30b1604db9..33e13dfa32e08 100644
--- a/kernel/sched/ext.c
+++ b/kernel/sched/ext.c
@@ -2203,16 +2203,30 @@ static void consume_local_task(struct rq *rq, struct scx_dispatch_q *dsq,
* - The BPF scheduler is bypassed while the rq is offline and we can always say
* no to the BPF scheduler initiated migrations while offline.
*/
-static bool task_can_run_on_remote_rq(struct task_struct *p, struct rq *rq)
+static bool task_can_run_on_remote_rq(struct task_struct *p, struct rq *rq,
+ bool trigger_error)
{
int cpu = cpu_of(rq);
- if (!task_allowed_on_cpu(p, cpu))
+ /*
+ * We don't require the BPF scheduler to avoid dispatching to offline
+ * CPUs mostly for convenience but also because CPUs can go offline
+ * between scx_bpf_dispatch() calls and here. Trigger error iff the
+ * picked CPU is outside the allowed mask.
+ */
+ if (!task_allowed_on_cpu(p, cpu)) {
+ if (trigger_error)
+ scx_ops_error("SCX_DSQ_LOCAL[_ON] verdict target cpu %d not allowed for %s[%d]",
+ cpu_of(rq), p->comm, p->pid);
return false;
+ }
+
if (unlikely(is_migration_disabled(p)))
return false;
+
if (!scx_rq_online(rq))
return false;
+
return true;
}
@@ -2240,9 +2254,8 @@ static bool consume_remote_task(struct rq *rq, struct scx_dispatch_q *dsq,
return move_task_to_local_dsq(p, 0, task_rq, rq);
}
#else /* CONFIG_SMP */
-static bool task_can_run_on_remote_rq(struct task_struct *p, struct rq *rq) { return false; }
-static bool consume_remote_task(struct rq *rq, struct scx_dispatch_q *dsq,
- struct task_struct *p, struct rq *task_rq) { return false; }
+static inline bool task_can_run_on_remote_rq(struct task_struct *p, struct rq *rq, bool trigger_error) { return false; }
+static inline bool consume_remote_task(struct rq *rq, struct scx_dispatch_q *dsq, struct task_struct *p, struct rq *task_rq) { return false; }
#endif /* CONFIG_SMP */
static bool consume_dispatch_q(struct rq *rq, struct scx_dispatch_q *dsq)
@@ -2267,7 +2280,7 @@ static bool consume_dispatch_q(struct rq *rq, struct scx_dispatch_q *dsq)
return true;
}
- if (task_can_run_on_remote_rq(p, rq)) {
+ if (task_can_run_on_remote_rq(p, rq, false)) {
if (likely(consume_remote_task(rq, dsq, p, task_rq)))
return true;
goto retry;
@@ -2330,7 +2343,7 @@ dispatch_to_local_dsq(struct rq *rq, u64 dsq_id, struct task_struct *p,
}
#ifdef CONFIG_SMP
- if (cpumask_test_cpu(cpu_of(dst_rq), p->cpus_ptr)) {
+ if (likely(task_can_run_on_remote_rq(p, dst_rq, true))) {
bool dsp;
/*
@@ -2355,17 +2368,6 @@ dispatch_to_local_dsq(struct rq *rq, u64 dsq_id, struct task_struct *p,
raw_spin_rq_lock(src_rq);
}
- /*
- * We don't require the BPF scheduler to avoid dispatching to
- * offline CPUs mostly for convenience but also because CPUs can
- * go offline between scx_bpf_dispatch() calls and here. If @p
- * is destined to an offline CPU, queue it on its current CPU
- * instead, which should always be safe. As this is an allowed
- * behavior, don't trigger an ops error.
- */
- if (!scx_rq_online(dst_rq))
- dst_rq = src_rq;
-
if (src_rq == dst_rq) {
/*
* As @p is staying on the same rq, there's no need to
@@ -2399,8 +2401,6 @@ dispatch_to_local_dsq(struct rq *rq, u64 dsq_id, struct task_struct *p,
}
#endif /* CONFIG_SMP */
- scx_ops_error("SCX_DSQ_LOCAL[_ON] verdict target cpu %d not allowed for %s[%d]",
- cpu_of(dst_rq), p->comm, p->pid);
return DTL_INVALID;
}
--
GitLab