smp.c

linux-2.6.15.6

	if (!cpu_isset(cpu, flush_cpumask))
		goto out;
		/* 
		 * This was a BUG() but until someone can quote me the
		 * line from the intel manual that guarantees an IPI to
		 * multiple CPUs is retried _only_ on the erroring CPUs
		 * its staying as a return
		 *
		 * BUG();
		 */
		 
	if (flush_mm == per_cpu(cpu_tlbstate, cpu).active_mm) {
		if (per_cpu(cpu_tlbstate, cpu).state == TLBSTATE_OK) {
			if (flush_va == FLUSH_ALL)
				local_flush_tlb();
			else
				__flush_tlb_one(flush_va);
		} else
			leave_mm(cpu);
	}
	ack_APIC_irq();
	smp_mb__before_clear_bit();
	cpu_clear(cpu, flush_cpumask);
	smp_mb__after_clear_bit();
out:
	put_cpu_no_resched();
}

static void flush_tlb_others(cpumask_t cpumask, struct mm_struct *mm,
						unsigned long va)
{
	/*
	 * A couple of (to be removed) sanity checks:
	 *
	 * - current CPU must not be in mask
	 * - mask must exist :)
	 */
	BUG_ON(cpus_empty(cpumask));
	BUG_ON(cpu_isset(smp_processor_id(), cpumask));
	BUG_ON(!mm);

	/* If a CPU which we ran on has gone down, OK. */
	cpus_and(cpumask, cpumask, cpu_online_map);
	if (cpus_empty(cpumask))
		return;

	/*
	 * i'm not happy about this global shared spinlock in the
	 * MM hot path, but we'll see how contended it is.
	 * Temporarily this turns IRQs off, so that lockups are
	 * detected by the NMI watchdog.
	 */
	spin_lock(&tlbstate_lock);
	
	flush_mm = mm;
	flush_va = va;
#if NR_CPUS <= BITS_PER_LONG
	atomic_set_mask(cpumask, &flush_cpumask);
#else
	{
		int k;
		unsigned long *flush_mask = (unsigned long *)&flush_cpumask;
		unsigned long *cpu_mask = (unsigned long *)&cpumask;
		for (k = 0; k < BITS_TO_LONGS(NR_CPUS); ++k)
			atomic_set_mask(cpu_mask[k], &flush_mask[k]);
	}
#endif
	/*
	 * We have to send the IPI only to
	 * CPUs affected.
	 */
	send_IPI_mask(cpumask, INVALIDATE_TLB_VECTOR);

	while (!cpus_empty(flush_cpumask))
		/* nothing. lockup detection does not belong here */
		mb();

	flush_mm = NULL;
	flush_va = 0;
	spin_unlock(&tlbstate_lock);
}
	
void flush_tlb_current_task(void)
{
	struct mm_struct *mm = current->mm;
	cpumask_t cpu_mask;

	preempt_disable();
	cpu_mask = mm->cpu_vm_mask;
	cpu_clear(smp_processor_id(), cpu_mask);

	local_flush_tlb();
	if (!cpus_empty(cpu_mask))
		flush_tlb_others(cpu_mask, mm, FLUSH_ALL);
	preempt_enable();
}

void flush_tlb_mm (struct mm_struct * mm)
{
	cpumask_t cpu_mask;

	preempt_disable();
	cpu_mask = mm->cpu_vm_mask;
	cpu_clear(smp_processor_id(), cpu_mask);

	if (current->active_mm == mm) {
		if (current->mm)
			local_flush_tlb();
		else
			leave_mm(smp_processor_id());
	}
	if (!cpus_empty(cpu_mask))
		flush_tlb_others(cpu_mask, mm, FLUSH_ALL);

	preempt_enable();
}

void flush_tlb_page(struct vm_area_struct * vma, unsigned long va)
{
	struct mm_struct *mm = vma->vm_mm;
	cpumask_t cpu_mask;

	preempt_disable();
	cpu_mask = mm->cpu_vm_mask;
	cpu_clear(smp_processor_id(), cpu_mask);

	if (current->active_mm == mm) {
		if(current->mm)
			__flush_tlb_one(va);
		 else
		 	leave_mm(smp_processor_id());
	}

	if (!cpus_empty(cpu_mask))
		flush_tlb_others(cpu_mask, mm, va);

	preempt_enable();
}
EXPORT_SYMBOL(flush_tlb_page);

static void do_flush_tlb_all(void* info)
{
	unsigned long cpu = smp_processor_id();

	__flush_tlb_all();
	if (per_cpu(cpu_tlbstate, cpu).state == TLBSTATE_LAZY)
		leave_mm(cpu);
}

void flush_tlb_all(void)
{
	on_each_cpu(do_flush_tlb_all, NULL, 1, 1);
}

/*
 * this function sends a 'reschedule' IPI to another CPU.
 * it goes straight through and wastes no time serializing
 * anything. Worst case is that we lose a reschedule ...
 */
void smp_send_reschedule(int cpu)
{
	WARN_ON(cpu_is_offline(cpu));
	send_IPI_mask(cpumask_of_cpu(cpu), RESCHEDULE_VECTOR);
}

/*
 * Structure and data for smp_call_function(). This is designed to minimise
 * static memory requirements. It also looks cleaner.
 */
static DEFINE_SPINLOCK(call_lock);

struct call_data_struct {
	void (*func) (void *info);
	void *info;
	atomic_t started;
	atomic_t finished;
	int wait;
};

void lock_ipi_call_lock(void)
{
	spin_lock_irq(&call_lock);
}

void unlock_ipi_call_lock(void)
{
	spin_unlock_irq(&call_lock);
}

static struct call_data_struct * call_data;

/*
 * this function sends a 'generic call function' IPI to all other CPUs
 * in the system.
 */

int smp_call_function (void (*func) (void *info), void *info, int nonatomic,
			int wait)
/*
 * [SUMMARY] Run a function on all other CPUs.
 * <func> The function to run. This must be fast and non-blocking.
 * <info> An arbitrary pointer to pass to the function.
 * <nonatomic> currently unused.
 * <wait> If true, wait (atomically) until function has completed on other CPUs.
 * [RETURNS] 0 on success, else a negative status code. Does not return until
 * remote CPUs are nearly ready to execute <<func>> or are or have executed.
 *
 * You must not call this function with disabled interrupts or from a
 * hardware interrupt handler or from a bottom half handler.
 */
{
	struct call_data_struct data;
	int cpus;

	/* Holding any lock stops cpus from going down. */
	spin_lock(&call_lock);
	cpus = num_online_cpus() - 1;
	if (!cpus) {
		spin_unlock(&call_lock);
		return 0;
	}

	/* Can deadlock when called with interrupts disabled */
	WARN_ON(irqs_disabled());

	data.func = func;
	data.info = info;
	atomic_set(&data.started, 0);
	data.wait = wait;
	if (wait)
		atomic_set(&data.finished, 0);

	call_data = &data;
	mb();
	
	/* Send a message to all other CPUs and wait for them to respond */
	send_IPI_allbutself(CALL_FUNCTION_VECTOR);

	/* Wait for response */
	while (atomic_read(&data.started) != cpus)
		cpu_relax();

	if (wait)
		while (atomic_read(&data.finished) != cpus)
			cpu_relax();
	spin_unlock(&call_lock);

	return 0;
}
EXPORT_SYMBOL(smp_call_function);

static void stop_this_cpu (void * dummy)
{
	/*
	 * Remove this CPU:
	 */
	cpu_clear(smp_processor_id(), cpu_online_map);
	local_irq_disable();
	disable_local_APIC();
	if (cpu_data[smp_processor_id()].hlt_works_ok)
		for(;;) halt();
	for (;;);
}

/*
 * this function calls the 'stop' function on all other CPUs in the system.
 */

void smp_send_stop(void)
{
	smp_call_function(stop_this_cpu, NULL, 1, 0);

	local_irq_disable();
	disable_local_APIC();
	local_irq_enable();
}

/*
 * Reschedule call back. Nothing to do,
 * all the work is done automatically when
 * we return from the interrupt.
 */
fastcall void smp_reschedule_interrupt(struct pt_regs *regs)
{
	ack_APIC_irq();
}

fastcall void smp_call_function_interrupt(struct pt_regs *regs)
{
	void (*func) (void *info) = call_data->func;
	void *info = call_data->info;
	int wait = call_data->wait;

	ack_APIC_irq();
	/*
	 * Notify initiating CPU that I've grabbed the data and am
	 * about to execute the function
	 */
	mb();
	atomic_inc(&call_data->started);
	/*
	 * At this point the info structure may be out of scope unless wait==1
	 */
	irq_enter();
	(*func)(info);
	irq_exit();

	if (wait) {
		mb();
		atomic_inc(&call_data->finished);
	}
}