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>
This commit is contained in:
parent
bf934bed5e
commit
0366017e09
1 changed files with 20 additions and 20 deletions
|
@ -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
|
* - The BPF scheduler is bypassed while the rq is offline and we can always say
|
||||||
* no to the BPF scheduler initiated migrations while offline.
|
* 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);
|
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;
|
return false;
|
||||||
|
}
|
||||||
|
|
||||||
if (unlikely(is_migration_disabled(p)))
|
if (unlikely(is_migration_disabled(p)))
|
||||||
return false;
|
return false;
|
||||||
|
|
||||||
if (!scx_rq_online(rq))
|
if (!scx_rq_online(rq))
|
||||||
return false;
|
return false;
|
||||||
|
|
||||||
return true;
|
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);
|
return move_task_to_local_dsq(p, 0, task_rq, rq);
|
||||||
}
|
}
|
||||||
#else /* CONFIG_SMP */
|
#else /* CONFIG_SMP */
|
||||||
static bool task_can_run_on_remote_rq(struct task_struct *p, struct rq *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 bool consume_remote_task(struct rq *rq, struct scx_dispatch_q *dsq,
|
static inline bool consume_remote_task(struct rq *rq, struct scx_dispatch_q *dsq, struct task_struct *p, struct rq *task_rq) { return false; }
|
||||||
struct task_struct *p, struct rq *task_rq) { return false; }
|
|
||||||
#endif /* CONFIG_SMP */
|
#endif /* CONFIG_SMP */
|
||||||
|
|
||||||
static bool consume_dispatch_q(struct rq *rq, struct scx_dispatch_q *dsq)
|
static bool consume_dispatch_q(struct rq *rq, struct scx_dispatch_q *dsq)
|
||||||
|
@ -2267,7 +2280,7 @@ retry:
|
||||||
return true;
|
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)))
|
if (likely(consume_remote_task(rq, dsq, p, task_rq)))
|
||||||
return true;
|
return true;
|
||||||
goto retry;
|
goto retry;
|
||||||
|
@ -2330,7 +2343,7 @@ dispatch_to_local_dsq(struct rq *rq, u64 dsq_id, struct task_struct *p,
|
||||||
}
|
}
|
||||||
|
|
||||||
#ifdef CONFIG_SMP
|
#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;
|
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);
|
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) {
|
if (src_rq == dst_rq) {
|
||||||
/*
|
/*
|
||||||
* As @p is staying on the same rq, there's no need to
|
* 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 */
|
#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;
|
return DTL_INVALID;
|
||||||
}
|
}
|
||||||
|
|
||||||
|
|
Loading…
Add table
Reference in a new issue