smp.c

优龙2410linux2.6.8内核源代码

		/* spare */
		break;
#endif
#ifdef CONFIG_DEBUGGER
	case PPC_MSG_DEBUGGER_BREAK:
		debugger_ipi(regs);
		break;
#endif
	default:
		printk("SMP %d: smp_message_recv(): unknown msg %d\n",
		       smp_processor_id(), msg);
		break;
	}
}

void smp_send_reschedule(int cpu)
{
	smp_ops->message_pass(cpu, PPC_MSG_RESCHEDULE);
}

#ifdef CONFIG_DEBUGGER
void smp_send_debugger_break(int cpu)
{
	smp_ops->message_pass(cpu, PPC_MSG_DEBUGGER_BREAK);
}
#endif

static void stop_this_cpu(void *dummy)
{
	local_irq_disable();
	while (1)
		;
}

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

/*
 * Structure and data for smp_call_function(). This is designed to minimise
 * static memory requirements. It also looks cleaner.
 * Stolen from the i386 version.
 */
static spinlock_t call_lock __cacheline_aligned_in_smp = SPIN_LOCK_UNLOCKED;

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

/* delay of at least 8 seconds on 1GHz cpu */
#define SMP_CALL_TIMEOUT (1UL << (30 + 3))

/*
 * This function sends a 'generic call function' IPI to all other CPUs
 * in the system.
 *
 * [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.
 */
int smp_call_function (void (*func) (void *info), void *info, int nonatomic,
		       int wait)
{ 
	struct call_data_struct data;
	int ret = -1, cpus;
	unsigned long timeout;

	/* 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);

	spin_lock(&call_lock);
	/* Must grab online cpu count with preempt disabled, otherwise
	 * it can change. */
	cpus = num_online_cpus() - 1;
	if (!cpus) {
		ret = 0;
		goto out;
	}

	call_data = &data;
	wmb();
	/* Send a message to all other CPUs and wait for them to respond */
	smp_ops->message_pass(MSG_ALL_BUT_SELF, PPC_MSG_CALL_FUNCTION);

	/* Wait for response */
	timeout = SMP_CALL_TIMEOUT;
	while (atomic_read(&data.started) != cpus) {
		HMT_low();
		if (--timeout == 0) {
			printk("smp_call_function on cpu %d: other cpus not "
			       "responding (%d)\n", smp_processor_id(),
			       atomic_read(&data.started));
			debugger(NULL);
			goto out;
		}
	}

	if (wait) {
		timeout = SMP_CALL_TIMEOUT;
		while (atomic_read(&data.finished) != cpus) {
			HMT_low();
			if (--timeout == 0) {
				printk("smp_call_function on cpu %d: other "
				       "cpus not finishing (%d/%d)\n",
				       smp_processor_id(),
				       atomic_read(&data.finished),
				       atomic_read(&data.started));
				debugger(NULL);
				goto out;
			}
		}
	}

	ret = 0;

out:
	call_data = NULL;
	HMT_medium();
	spin_unlock(&call_lock);
	return ret;
}

void smp_call_function_interrupt(void)
{
	void (*func) (void *info);
	void *info;
	int wait;

	/* call_data will be NULL if the sender timed out while
	 * waiting on us to receive the call.
	 */
	if (!call_data)
		return;

	func = call_data->func;
	info = call_data->info;
	wait = call_data->wait;

	if (!wait)
		smp_mb__before_atomic_inc();

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

extern unsigned long decr_overclock;
extern struct gettimeofday_struct do_gtod;

struct thread_info *current_set[NR_CPUS];

DECLARE_PER_CPU(unsigned int, pvr);

static void __devinit smp_store_cpu_info(int id)
{
	per_cpu(pvr, id) = _get_PVR();
}

static void __init smp_create_idle(unsigned int cpu)
{
	struct pt_regs regs;
	struct task_struct *p;

	/* create a process for the processor */
	/* only regs.msr is actually used, and 0 is OK for it */
	memset(&regs, 0, sizeof(struct pt_regs));
	p = copy_process(CLONE_VM | CLONE_IDLETASK,
			 0, &regs, 0, NULL, NULL);
	if (IS_ERR(p))
		panic("failed fork for CPU %u: %li", cpu, PTR_ERR(p));

	wake_up_forked_process(p);
	init_idle(p, cpu);
	unhash_process(p);

	paca[cpu].__current = p;
	current_set[cpu] = p->thread_info;
}

void __init smp_prepare_cpus(unsigned int max_cpus)
{
	unsigned int cpu;

	/* 
	 * setup_cpu may need to be called on the boot cpu. We havent
	 * spun any cpus up but lets be paranoid.
	 */
	BUG_ON(boot_cpuid != smp_processor_id());

	/* Fixup boot cpu */
	smp_store_cpu_info(boot_cpuid);
	cpu_callin_map[boot_cpuid] = 1;
	paca[boot_cpuid].prof_counter = 1;
	paca[boot_cpuid].prof_multiplier = 1;

#ifndef CONFIG_PPC_ISERIES
	paca[boot_cpuid].next_jiffy_update_tb = tb_last_stamp = get_tb();

	/*
	 * Should update do_gtod.stamp_xsec.
	 * For now we leave it which means the time can be some
	 * number of msecs off until someone does a settimeofday()
	 */
	do_gtod.tb_orig_stamp = tb_last_stamp;

	look_for_more_cpus();
#endif

	max_cpus = smp_ops->probe();
 
	/* Backup CPU 0 state if necessary */
	__save_cpu_setup();

	smp_space_timers(max_cpus);

	for_each_cpu(cpu)
		if (cpu != boot_cpuid)
			smp_create_idle(cpu);
}

void __devinit smp_prepare_boot_cpu(void)
{
	BUG_ON(smp_processor_id() != boot_cpuid);

	/* cpu_possible is set up in prom.c */
	cpu_set(boot_cpuid, cpu_online_map);

	paca[boot_cpuid].__current = current;
	current_set[boot_cpuid] = current->thread_info;
}

int __devinit __cpu_up(unsigned int cpu)
{
	int c;

	/* At boot, don't bother with non-present cpus -JSCHOPP */
	if (system_state == SYSTEM_BOOTING && !cpu_present_at_boot(cpu))
		return -ENOENT;

	paca[cpu].prof_counter = 1;
	paca[cpu].prof_multiplier = 1;
	paca[cpu].default_decr = tb_ticks_per_jiffy / decr_overclock;

	if (!(cur_cpu_spec->cpu_features & CPU_FTR_SLB)) {
		void *tmp;

		/* maximum of 48 CPUs on machines with a segment table */
		if (cpu >= 48)
			BUG();

		tmp = &stab_array[PAGE_SIZE * cpu];
		memset(tmp, 0, PAGE_SIZE); 
		paca[cpu].stab_addr = (unsigned long)tmp;
		paca[cpu].stab_real = virt_to_abs(tmp);
	}

	/* The information for processor bringup must
	 * be written out to main store before we release
	 * the processor.
	 */
	mb();

	/* wake up cpus */
	smp_ops->kick_cpu(cpu);

	/*
	 * wait to see if the cpu made a callin (is actually up).
	 * use this value that I found through experimentation.
	 * -- Cort
	 */
	if (system_state == SYSTEM_BOOTING)
		for (c = 5000; c && !cpu_callin_map[cpu]; c--)
			udelay(100);
#ifdef CONFIG_HOTPLUG_CPU
	else
		/*
		 * CPUs can take much longer to come up in the
		 * hotplug case.  Wait five seconds.
		 */
		for (c = 25; c && !cpu_callin_map[cpu]; c--) {
			set_current_state(TASK_UNINTERRUPTIBLE);
			schedule_timeout(HZ/5);
		}
#endif

	if (!cpu_callin_map[cpu]) {
		printk("Processor %u is stuck.\n", cpu);
		return -ENOENT;
	}

	printk("Processor %u found.\n", cpu);

	if (smp_ops->give_timebase)
		smp_ops->give_timebase();

	/* Wait until cpu puts itself in the online map */
	while (!cpu_online(cpu))
		cpu_relax();

	return 0;
}

extern unsigned int default_distrib_server;
/* Activate a secondary processor. */
int __devinit start_secondary(void *unused)
{
	unsigned int cpu = smp_processor_id();

	atomic_inc(&init_mm.mm_count);
	current->active_mm = &init_mm;

	smp_store_cpu_info(cpu);
	set_dec(paca[cpu].default_decr);
	cpu_callin_map[cpu] = 1;

	smp_ops->setup_cpu(cpu);
	if (smp_ops->take_timebase)
		smp_ops->take_timebase();

#ifdef CONFIG_PPC_PSERIES
	if (cur_cpu_spec->firmware_features & FW_FEATURE_SPLPAR) {
		vpa_init(cpu); 
	}

#ifdef CONFIG_IRQ_ALL_CPUS
	/* Put the calling processor into the GIQ.  This is really only
	 * necessary from a secondary thread as the OF start-cpu interface
	 * performs this function for us on primary threads.
	 */
	/* TODO: 9005 is #defined in rtas-proc.c -- move to a header */
	rtas_set_indicator(9005, default_distrib_server, 1);
#endif
#endif

	spin_lock(&call_lock);
	cpu_set(cpu, cpu_online_map);
	spin_unlock(&call_lock);

	local_irq_enable();

	return cpu_idle(NULL);
}

int setup_profiling_timer(unsigned int multiplier)
{
	return 0;
}

void __init smp_cpus_done(unsigned int max_cpus)
{
	cpumask_t old_mask;

	/* We want the setup_cpu() here to be called from CPU 0, but our
	 * init thread may have been "borrowed" by another CPU in the meantime
	 * se we pin us down to CPU 0 for a short while
	 */
	old_mask = current->cpus_allowed;
	set_cpus_allowed(current, cpumask_of_cpu(boot_cpuid));
	
	smp_ops->setup_cpu(boot_cpuid);

	/* XXX fix this, xics currently relies on it - Anton */
	smp_threads_ready = 1;

	set_cpus_allowed(current, old_mask);
}

#ifdef CONFIG_SCHED_SMT
#ifdef CONFIG_NUMA
static struct sched_group sched_group_cpus[NR_CPUS];
static struct sched_group sched_group_phys[NR_CPUS];
static struct sched_group sched_group_nodes[MAX_NUMNODES];
static DEFINE_PER_CPU(struct sched_domain, cpu_domains);
static DEFINE_PER_CPU(struct sched_domain, phys_domains);
static DEFINE_PER_CPU(struct sched_domain, node_domains);
__init void arch_init_sched_domains(void)
{
	int i;
	struct sched_group *first = NULL, *last = NULL;

	/* Set up domains */
	for_each_cpu(i) {
		struct sched_domain *cpu_domain = &per_cpu(cpu_domains, i);
		struct sched_domain *phys_domain = &per_cpu(phys_domains, i);
		struct sched_domain *node_domain = &per_cpu(node_domains, i);
		int node = cpu_to_node(i);
		cpumask_t nodemask = node_to_cpumask(node);
		cpumask_t my_cpumask = cpumask_of_cpu(i);
		cpumask_t sibling_cpumask = cpumask_of_cpu(i ^ 0x1);

		*cpu_domain = SD_SIBLING_INIT;
		if (cur_cpu_spec->cpu_features & CPU_FTR_SMT)
			cpus_or(cpu_domain->span, my_cpumask, sibling_cpumask);
		else
			cpu_domain->span = my_cpumask;
		cpu_domain->parent = phys_domain;
		cpu_domain->groups = &sched_group_cpus[i];

		*phys_domain = SD_CPU_INIT;
		phys_domain->span = nodemask;
		phys_domain->parent = node_domain;
		phys_domain->groups = &sched_group_phys[first_cpu(cpu_domain->span)];

		*node_domain = SD_NODE_INIT;
		node_domain->span = cpu_possible_map;
		node_domain->groups = &sched_group_nodes[node];
	}

	/* Set up CPU (sibling) groups */
	for_each_cpu(i) {
		struct sched_domain *cpu_domain = &per_cpu(cpu_domains, i);
		int j;
		first = last = NULL;

		if (i != first_cpu(cpu_domain->span))
			continue;

		for_each_cpu_mask(j, cpu_domain->span) {
			struct sched_group *cpu = &sched_group_cpus[j];

			cpus_clear(cpu->cpumask);
			cpu_set(j, cpu->cpumask);
			cpu->cpu_power = SCHED_LOAD_SCALE;

			if (!first)
				first = cpu;
			if (last)
				last->next = cpu;
			last = cpu;
		}
		last->next = first;
	}

	for (i = 0; i < MAX_NUMNODES; i++) {
		int j;
		cpumask_t nodemask;
		struct sched_group *node = &sched_group_nodes[i];
		cpumask_t node_cpumask = node_to_cpumask(i);
		cpus_and(nodemask, node_cpumask, cpu_possible_map);

		if (cpus_empty(nodemask))
			continue;

		first = last = NULL;
		/* Set up physical groups */
		for_each_cpu_mask(j, nodemask) {
			struct sched_domain *cpu_domain = &per_cpu(cpu_domains, j);
			struct sched_group *cpu = &sched_group_phys[j];

			if (j != first_cpu(cpu_domain->span))
				continue;

			cpu->cpumask = cpu_domain->span;
			/*
			 * Make each extra sibling increase power by 10% of
			 * the basic CPU. This is very arbitrary.
			 */
			cpu->cpu_power = SCHED_LOAD_SCALE + SCHED_LOAD_SCALE*(cpus_weight(cpu->cpumask)-1) / 10;
			node->cpu_power += cpu->cpu_power;

			if (!first)
				first = cpu;
			if (last)
				last->next = cpu;
			last = cpu;
		}
		last->next = first;
	}

	/* Set up nodes */
	first = last = NULL;
	for (i = 0; i < MAX_NUMNODES; i++) {
		struct sched_group *cpu = &sched_group_nodes[i];
		cpumask_t nodemask;
		cpumask_t node_cpumask = node_to_cpumask(i);
		cpus_and(nodemask, node_cpumask, cpu_possible_map);

		if (cpus_empty(nodemask))
			continue;

		cpu->cpumask = nodemask;
		/* ->cpu_power already setup */

		if (!first)
			first = cpu;
		if (last)
			last->next = cpu;
		last = cpu;
	}
	last->next = first;

	mb();
	for_each_cpu(i) {
		struct sched_domain *cpu_domain = &per_cpu(cpu_domains, i);
		cpu_attach_domain(cpu_domain, i);
	}
}
#else /* !CONFIG_NUMA */
static struct sched_group sched_group_cpus[NR_CPUS];
static struct sched_group sched_group_phys[NR_CPUS];
static DEFINE_PER_CPU(struct sched_domain, cpu_domains);
static DEFINE_PER_CPU(struct sched_domain, phys_domains);
__init void arch_init_sched_domains(void)
{
	int i;
	struct sched_group *first = NULL, *last = NULL;

	/* Set up domains */
	for_each_cpu(i) {
		struct sched_domain *cpu_domain = &per_cpu(cpu_domains, i);
		struct sched_domain *phys_domain = &per_cpu(phys_domains, i);
		cpumask_t my_cpumask = cpumask_of_cpu(i);
		cpumask_t sibling_cpumask = cpumask_of_cpu(i ^ 0x1);

		*cpu_domain = SD_SIBLING_INIT;
		if (cur_cpu_spec->cpu_features & CPU_FTR_SMT)
			cpus_or(cpu_domain->span, my_cpumask, sibling_cpumask);
		else
			cpu_domain->span = my_cpumask;
		cpu_domain->parent = phys_domain;
		cpu_domain->groups = &sched_group_cpus[i];

		*phys_domain = SD_CPU_INIT;
		phys_domain->span = cpu_possible_map;
		phys_domain->groups = &sched_group_phys[first_cpu(cpu_domain->span)];
	}

	/* Set up CPU (sibling) groups */
	for_each_cpu(i) {
		struct sched_domain *cpu_domain = &per_cpu(cpu_domains, i);
		int j;
		first = last = NULL;

		if (i != first_cpu(cpu_domain->span))
			continue;

		for_each_cpu_mask(j, cpu_domain->span) {
			struct sched_group *cpu = &sched_group_cpus[j];

			cpus_clear(cpu->cpumask);
			cpu_set(j, cpu->cpumask);
			cpu->cpu_power = SCHED_LOAD_SCALE;

			if (!first)
				first = cpu;
			if (last)
				last->next = cpu;
			last = cpu;
		}
		last->next = first;
	}

	first = last = NULL;
	/* Set up physical groups */
	for_each_cpu(i) {
		struct sched_domain *cpu_domain = &per_cpu(cpu_domains, i);
		struct sched_group *cpu = &sched_group_phys[i];

		if (i != first_cpu(cpu_domain->span))
			continue;

		cpu->cpumask = cpu_domain->span;
		/* See SMT+NUMA setup for comment */
		cpu->cpu_power = SCHED_LOAD_SCALE + SCHED_LOAD_SCALE*(cpus_weight(cpu->cpumask)-1) / 10;

		if (!first)
			first = cpu;
		if (last)
			last->next = cpu;
		last = cpu;
	}
	last->next = first;

	mb();
	for_each_cpu(i) {
		struct sched_domain *cpu_domain = &per_cpu(cpu_domains, i);
		cpu_attach_domain(cpu_domain, i);
	}
}
#endif /* CONFIG_NUMA */
#endif /* CONFIG_SCHED_SMT */