linux中的SGI(核间中断)IPI_RESCHEDULE详解

1、SGI中断(核间通信中断)

在gicv2/gicv3中，SGI中断（中断号0-15）是software generate interrupt，用户核间中断。
我们一般将0-7划分给linux中使用，8-15给TEE使用。在smp.c定义了linux中使用的SGI中断。

kernel/arch/arm/kernel/smp.c
enum ipi_msg_type {
IPI_WAKEUP,
IPI_TIMER,
IPI_RESCHEDULE,
IPI_CALL_FUNC,
IPI_CPU_STOP,
IPI_IRQ_WORK,
IPI_COMPLETION,
/*
* CPU_BACKTRACE is special and not included in NR_IPI
* or tracable with trace_ipi_*
/
IPI_CPU_BACKTRACE,
#ifdef CONFIG_TRUSTY
IPI_CUSTOM_FIRST,
IPI_CUSTOM_LAST = 15,
#endif
/
* SGI8-15 can be reserved by secure firmware, and thus may
* not be usable by the kernel. Please keep the above limited
* to at most 8 entries.
*/
};

2、SGI中断的调用流程

（1）、CPU收到IRQ后的处理

当ARM core收到IRQ后，会触发cpu的irq异常，会跳转到linux kernel的irq异常向量表，在该向量表中，会调用gicv2/gicv3的gic_handle_irq函数，在kernel/drivers/irqchip/irq-gic-v3.c中

• irqnr = gic_read_iar() 读gic寄存器获取硬件中断号
• likely(irqnr > 15 && irqnr < 1020) || irqnr >= 8192 这这个条件下处理PPI中断和SPI中断
• if (irqnr < 16) 在这个条件下调用handle_IPI(irqnr, regs)来处理SGI中断

static asmlinkage void __exception_irq_entry gic_handle_irq(struct pt_regs *regs)
{
	u32 irqnr;

	do {
		irqnr = gic_read_iar();

		if (likely(irqnr > 15 && irqnr < 1020) || irqnr >= 8192) {
			int err;

			if (static_key_true(&supports_deactivate))
				gic_write_eoir(irqnr);

			err = handle_domain_irq(gic_data.domain, irqnr, regs);
			if (err) {
				WARN_ONCE(true, "Unexpected interrupt received!\n");
				if (static_key_true(&supports_deactivate)) {
					if (irqnr < 8192)
						gic_write_dir(irqnr);
				} else {
					gic_write_eoir(irqnr);
				}
			}
			continue;
		}
		if (irqnr < 16) {
			gic_write_eoir(irqnr);
			if (static_key_true(&supports_deactivate))
				gic_write_dir(irqnr);
#ifdef CONFIG_SMP
			/*
			 * Unlike GICv2, we don't need an smp_rmb() here.
			 * The control dependency from gic_read_iar to
			 * the ISB in gic_write_eoir is enough to ensure
			 * that any shared data read by handle_IPI will
			 * be read after the ACK.
			 */
			handle_IPI(irqnr, regs);
#else
			WARN_ONCE(true, "Unexpected SGI received!\n");
#endif
			continue;
		}
	} while (irqnr != ICC_IAR1_EL1_SPURIOUS);
}

（2）、处理SGI中断（也叫核间通信中断）

void handle_IPI(int ipinr, struct pt_regs *regs)
{
......
	case IPI_RESCHEDULE:
		scheduler_ipi();
		break;
......
}

（3）、处理IPI_RESCHEDULE中断的操作

void scheduler_ipi(void)
{
	int cpu = smp_processor_id();

	/*
	 * Fold TIF_NEED_RESCHED into the preempt_count; anybody setting
	 * TIF_NEED_RESCHED remotely (for the first time) will also send
	 * this IPI.
	 */
	preempt_fold_need_resched();

	if (llist_empty(&this_rq()->wake_list) && !got_nohz_idle_kick()) {
#ifdef CONFIG_MTK_SCHED_MONITOR
		mt_trace_IPI_start(IPI_RESCHEDULE);
		mt_trace_IPI_end(IPI_RESCHEDULE);
#endif
		return;
	}


	/*
	 * Not all reschedule IPI handlers call irq_enter/irq_exit, since
	 * traditionally all their work was done from the interrupt return
	 * path. Now that we actually do some work, we need to make sure
	 * we do call them.
	 *
	 * Some archs already do call them, luckily irq_enter/exit nest
	 * properly.
	 *
	 * Arguably we should visit all archs and update all handlers,
	 * however a fair share of IPIs are still resched only so this would
	 * somewhat pessimize the simple resched case.
	 */
	irq_enter();
#ifdef CONFIG_MTK_SCHED_MONITOR
	mt_trace_IPI_start(IPI_RESCHEDULE);
#endif
	sched_ttwu_pending();

	/*
	 * Check if someone kicked us for doing the nohz idle load balance.
	 */
	if (unlikely(got_nohz_idle_kick()) && !cpu_isolated(cpu)) {
		this_rq()->idle_balance = 1;
		raise_softirq_irqoff(SCHED_SOFTIRQ);
	}
#ifdef CONFIG_MTK_SCHED_MONITOR
	mt_trace_IPI_end(IPI_RESCHEDULE);
#endif
	irq_exit();
}