mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git
synced 2026-06-21 15:43:21 +02:00
John Stultz
7a3a6bfbd6
Historically, the prev value from __schedule() was the rq->curr. This prev value is passed down through numerous functions, and used in the class scheduler implementations. The fact that prev was on_cpu until the end of __schedule(), meant it was stable across the rq lock drops that the class->balance() implementations often do. However, with proxy-exec, the prev passed to functions called by __schedule() is rq->donor, which may not be the same as rq->curr and may not be on_cpu, this makes the prev value potentially unstable across rq lock drops. A recently found issue with proxy-exec, is when we begin doing return migration from try_to_wake_up(), its possible we may be waking up the rq->donor. When we do this, we proxy_resched_idle() to put_prev_set_next() setting the rq->donor to rq->idle, allowing the rq->donor to be return migrated and allowed to run. This however runs into trouble, as on another cpu we might be in the middle of calling __schedule(). Conceptually the rq lock is held for the majority of the time, but in calling prev_balance() its possible the class->balance() handler call may briefly drop the rq lock. This opens a window for try_to_wake_up() to wake and return migrate the rq->donor before the class logic reacquires the rq lock. Unfortunately prev_balance() pass in a prev argument, to which we pass rq->donor. However this prev value can now become stale and incorrect across a rq lock drop. So, to correct this, rework the prev_balance() call so that it does not take a "prev" argument. Signed-off-by: John Stultz <jstultz@google.com> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Link: https://patch.msgid.link/20260512025635.2840817-2-jstultz@google.com
120 lines
2.6 KiB
C
120 lines
2.6 KiB
C
// SPDX-License-Identifier: GPL-2.0
|
|
/*
|
|
* stop-task scheduling class.
|
|
*
|
|
* The stop task is the highest priority task in the system, it preempts
|
|
* everything and will be preempted by nothing.
|
|
*
|
|
* See kernel/stop_machine.c
|
|
*/
|
|
#include "sched.h"
|
|
|
|
static int
|
|
select_task_rq_stop(struct task_struct *p, int cpu, int flags)
|
|
{
|
|
return task_cpu(p); /* stop tasks as never migrate */
|
|
}
|
|
|
|
static int
|
|
balance_stop(struct rq *rq, struct rq_flags *rf)
|
|
{
|
|
return sched_stop_runnable(rq);
|
|
}
|
|
|
|
static void
|
|
wakeup_preempt_stop(struct rq *rq, struct task_struct *p, int flags)
|
|
{
|
|
/* we're never preempted */
|
|
}
|
|
|
|
static void set_next_task_stop(struct rq *rq, struct task_struct *stop, bool first)
|
|
{
|
|
stop->se.exec_start = rq_clock_task(rq);
|
|
}
|
|
|
|
static struct task_struct *pick_task_stop(struct rq *rq, struct rq_flags *rf)
|
|
{
|
|
if (!sched_stop_runnable(rq))
|
|
return NULL;
|
|
|
|
return rq->stop;
|
|
}
|
|
|
|
static void
|
|
enqueue_task_stop(struct rq *rq, struct task_struct *p, int flags)
|
|
{
|
|
add_nr_running(rq, 1);
|
|
}
|
|
|
|
static bool
|
|
dequeue_task_stop(struct rq *rq, struct task_struct *p, int flags)
|
|
{
|
|
sub_nr_running(rq, 1);
|
|
return true;
|
|
}
|
|
|
|
static void yield_task_stop(struct rq *rq)
|
|
{
|
|
BUG(); /* the stop task should never yield, its pointless. */
|
|
}
|
|
|
|
static void put_prev_task_stop(struct rq *rq, struct task_struct *prev, struct task_struct *next)
|
|
{
|
|
update_curr_common(rq);
|
|
}
|
|
|
|
/*
|
|
* scheduler tick hitting a task of our scheduling class.
|
|
*
|
|
* NOTE: This function can be called remotely by the tick offload that
|
|
* goes along full dynticks. Therefore no local assumption can be made
|
|
* and everything must be accessed through the @rq and @curr passed in
|
|
* parameters.
|
|
*/
|
|
static void task_tick_stop(struct rq *rq, struct task_struct *curr, int queued)
|
|
{
|
|
}
|
|
|
|
static void switching_to_stop(struct rq *rq, struct task_struct *p)
|
|
{
|
|
BUG(); /* its impossible to change to this class */
|
|
}
|
|
|
|
static void
|
|
prio_changed_stop(struct rq *rq, struct task_struct *p, u64 oldprio)
|
|
{
|
|
if (p->prio == oldprio)
|
|
return;
|
|
|
|
BUG(); /* how!?, what priority? */
|
|
}
|
|
|
|
static void update_curr_stop(struct rq *rq)
|
|
{
|
|
}
|
|
|
|
/*
|
|
* Simple, special scheduling class for the per-CPU stop tasks:
|
|
*/
|
|
DEFINE_SCHED_CLASS(stop) = {
|
|
.enqueue_task = enqueue_task_stop,
|
|
.dequeue_task = dequeue_task_stop,
|
|
.yield_task = yield_task_stop,
|
|
|
|
.wakeup_preempt = wakeup_preempt_stop,
|
|
|
|
.pick_task = pick_task_stop,
|
|
.put_prev_task = put_prev_task_stop,
|
|
.set_next_task = set_next_task_stop,
|
|
|
|
.balance = balance_stop,
|
|
.select_task_rq = select_task_rq_stop,
|
|
.set_cpus_allowed = set_cpus_allowed_common,
|
|
|
|
.task_tick = task_tick_stop,
|
|
|
|
.prio_changed = prio_changed_stop,
|
|
.switching_to = switching_to_stop,
|
|
.update_curr = update_curr_stop,
|
|
};
|