###### tags: `Linux` `底層` `ARM`

# AArch64 scheduling in Linux
Linux version: 5.8

# schedule
* `kernel\sched\core.c`

asmlinkage __visible void __sched schedule(void)
{
    struct task_struct *tsk = current;

    sched_submit_work(tsk);
    do {
        preempt_disable();
        __schedule(false);
        sched_preempt_enable_no_resched();
    } while (need_resched());
    sched_update_worker(tsk);
}
EXPORT_SYMBOL(schedule);

* `__schedule`:

/*
 * __schedule() is the main scheduler function.
 *
 * The main means of driving the scheduler and thus entering this function are:
 *
 *   1. Explicit blocking: mutex, semaphore, waitqueue, etc.
 *
 *   2. TIF_NEED_RESCHED flag is checked on interrupt and userspace return
 *      paths. For example, see arch/x86/entry_64.S.
 *
 *      To drive preemption between tasks, the scheduler sets the flag in timer
 *      interrupt handler scheduler_tick().
 *
 *   3. Wakeups don't really cause entry into schedule(). They add a
 *      task to the run-queue and that's it.
 *
 *      Now, if the new task added to the run-queue preempts the current
 *      task, then the wakeup sets TIF_NEED_RESCHED and schedule() gets
 *      called on the nearest possible occasion:
 *
 *       - If the kernel is preemptible (CONFIG_PREEMPTION=y):
 *
 *         - in syscall or exception context, at the next outmost
 *           preempt_enable(). (this might be as soon as the wake_up()'s
 *           spin_unlock()!)
 *
 *         - in IRQ context, return from interrupt-handler to
 *           preemptible context
 *
 *       - If the kernel is not preemptible (CONFIG_PREEMPTION is not set)
 *         then at the next:
 *
 *          - cond_resched() call
 *          - explicit schedule() call
 *          - return from syscall or exception to user-space
 *          - return from interrupt-handler to user-space
 *
 * WARNING: must be called with preemption disabled!
 */
static void __sched notrace __schedule(bool preempt)
{
    struct task_struct *prev, *next;
    unsigned long *switch_count;
    unsigned long prev_state;
    struct rq_flags rf;
    struct rq *rq;
    int cpu;

    cpu = smp_processor_id();
    rq = cpu_rq(cpu);
    prev = rq->curr;

    schedule_debug(prev, preempt);

    if (sched_feat(HRTICK))
        hrtick_clear(rq);

    local_irq_disable();
    rcu_note_context_switch(preempt);

    /*
     * Make sure that signal_pending_state()->signal_pending() below
     * can't be reordered with __set_current_state(TASK_INTERRUPTIBLE)
     * done by the caller to avoid the race with signal_wake_up():
     *
     * __set_current_state(@state)        signal_wake_up()
     * schedule()                  set_tsk_thread_flag(p, TIF_SIGPENDING)
     *                      wake_up_state(p, state)
     *   LOCK rq->lock                LOCK p->pi_state
     *   smp_mb__after_spinlock()            smp_mb__after_spinlock()
     *     if (signal_pending_state())        if (p->state & @state)
     *
     * Also, the membarrier system call requires a full memory barrier
     * after coming from user-space, before storing to rq->curr.
     */
    rq_lock(rq, &rf);
    smp_mb__after_spinlock();

    /* Promote REQ to ACT */
    rq->clock_update_flags <<= 1;
    update_rq_clock(rq);

    switch_count = &prev->nivcsw;

    /*
     * We must load prev->state once (task_struct::state is volatile), such
     * that:
     *
     *  - we form a control dependency vs deactivate_task() below.
     *  - ptrace_{,un}freeze_traced() can change ->state underneath us.
     */
    prev_state = prev->state;
    if (!preempt && prev_state) {
        if (signal_pending_state(prev_state, prev)) {
            prev->state = TASK_RUNNING;
        } else {
            prev->sched_contributes_to_load =
                (prev_state & TASK_UNINTERRUPTIBLE) &&
                !(prev_state & TASK_NOLOAD) &&
                !(prev->flags & PF_FROZEN);

            if (prev->sched_contributes_to_load)
                rq->nr_uninterruptible++;

            /*
             * __schedule()            ttwu()
             *   prev_state = prev->state;    if (p->on_rq && ...)
             *   if (prev_state)            goto out;
             *     p->on_rq = 0;          smp_acquire__after_ctrl_dep();
             *                  p->state = TASK_WAKING
             *
             * Where __schedule() and ttwu() have matching control dependencies.
             *
             * After this, schedule() must not care about p->state any more.
             */
            deactivate_task(rq, prev, DEQUEUE_SLEEP | DEQUEUE_NOCLOCK);

            if (prev->in_iowait) {
                atomic_inc(&rq->nr_iowait);
                delayacct_blkio_start();
            }
        }
        switch_count = &prev->nvcsw;
    }

    next = pick_next_task(rq, prev, &rf);
    clear_tsk_need_resched(prev);
    clear_preempt_need_resched();

    if (likely(prev != next)) {
        rq->nr_switches++;
        /*
         * RCU users of rcu_dereference(rq->curr) may not see
         * changes to task_struct made by pick_next_task().
         */
        RCU_INIT_POINTER(rq->curr, next);
        /*
         * The membarrier system call requires each architecture
         * to have a full memory barrier after updating
         * rq->curr, before returning to user-space.
         *
         * Here are the schemes providing that barrier on the
         * various architectures:
         * - mm ? switch_mm() : mmdrop() for x86, s390, sparc, PowerPC.
         *   switch_mm() rely on membarrier_arch_switch_mm() on PowerPC.
         * - finish_lock_switch() for weakly-ordered
         *   architectures where spin_unlock is a full barrier,
         * - switch_to() for arm64 (weakly-ordered, spin_unlock
         *   is a RELEASE barrier),
         */
        ++*switch_count;

        psi_sched_switch(prev, next, !task_on_rq_queued(prev));

        trace_sched_switch(preempt, prev, next);

        /* Also unlocks the rq: */
        rq = context_switch(rq, prev, next, &rf);
    } else {
        rq->clock_update_flags &= ~(RQCF_ACT_SKIP|RQCF_REQ_SKIP);
        rq_unlock_irq(rq, &rf);
    }

    balance_callback(rq);
}

* 註解講述呼叫 `schedule` 的時機, 其中第二點為在 interrupt return 或 userspace return 的過程會呼叫到, 並提到了要驅動 scheduler, 要設定 timer, 使其定期呼叫 `scheduler_tick()` 去計時, 一段時間過後就設定 `TIF_NEED_RESCHED` 使其在第二點所述過程中被重新排程

# IRQ handler
* `arch/arm64/kernel/entry.S`
* `el1_irq`

SYM_CODE_START_LOCAL_NOALIGN(el1_irq)
    kernel_entry 1
    gic_prio_irq_setup pmr=x20, tmp=x1
    enable_da_f

    ...

    irq_handler

#ifdef CONFIG_PREEMPTION
    ldr    x24, [tsk, #TSK_TI_PREEMPT]    // get preempt count
alternative_if ARM64_HAS_IRQ_PRIO_MASKING
    /*
     * DA_F were cleared at start of handling. If anything is set in DAIF,
     * we come back from an NMI, so skip preemption
     */
    mrs    x0, daif
    orr    x24, x24, x0
alternative_else_nop_endif
    cbnz    x24, 1f                // preempt count != 0 || NMI return path
    bl    arm64_preempt_schedule_irq    // irq en/disable is done inside
1:
#endif
    
    ...

    kernel_exit 1
SYM_CODE_END(el1_irq)

* 可以看到在結束 irq_handler 後, 在 `kernel_exit` 之前 (內部會呼叫 eret 從 exception context 返回), 有一段判斷是否要呼叫 `arm64_preempt_schedule_irq` 的邏輯

# arm64_preempt_schedule_irq
* `arch/arm64/kernel/process.c`:

asmlinkage void __sched arm64_preempt_schedule_irq(void)
{
    lockdep_assert_irqs_disabled();

    /*
     * Preempting a task from an IRQ means we leave copies of PSTATE
     * on the stack. cpufeature's enable calls may modify PSTATE, but
     * resuming one of these preempted tasks would undo those changes.
     *
     * Only allow a task to be preempted once cpufeatures have been
     * enabled.
     */
    if (system_capabilities_finalized())
        preempt_schedule_irq();
}

# preempt_schedule_irq
* `kernel/sched/core.c`:

/*
 * This is the entry point to schedule() from kernel preemption
 * off of irq context.
 * Note, that this is called and return with irqs disabled. This will
 * protect us against recursive calling from irq.
 */
asmlinkage __visible void __sched preempt_schedule_irq(void)
{
    enum ctx_state prev_state;

    /* Catch callers which need to be fixed */
    BUG_ON(preempt_count() || !irqs_disabled());

    prev_state = exception_enter();

    do {
        preempt_disable();
        local_irq_enable();
        __schedule(true);
        local_irq_disable();
        sched_preempt_enable_no_resched();
    } while (need_resched());

    exception_exit(prev_state);
}

* 與 `schedule` 類似, 幾個差別:
* 在執行 `__schedule` 時啟用中斷, 由於進入此函數時, 中斷是關閉的, 要另外打開
* 多了 `exception_enter`、`exception_exit` 的部分