smp.c

优龙2410linux2.6.8内核源代码

/*
 * SMP support for ppc.
 *
 * Written by Cort Dougan ([e-mail]) borrowing a great
 * deal of code from the sparc and intel versions.
 *
 * Copyright (C) 1999 Cort Dougan <[e-mail]>
 *
 * PowerPC-64 Support added by Dave Engebretsen, Peter Bergner, and
 * Mike Corrigan {engebret|bergner|mikec}@us.ibm.com
 *
 *      This program is free software; you can redistribute it and/or
 *      modify it under the terms of the GNU General Public License
 *      as published by the Free Software Foundation; either version
 *      2 of the License, or (at your option) any later version.
 */

#include <linux/config.h>
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/sched.h>
#include <linux/smp.h>
#include <linux/smp_lock.h>
#include <linux/interrupt.h>
#include <linux/kernel_stat.h>
#include <linux/delay.h>
#include <linux/init.h>
#include <linux/spinlock.h>
#include <linux/cache.h>
#include <linux/err.h>
#include <linux/sysdev.h>
#include <linux/cpu.h>

#include <asm/ptrace.h>
#include <asm/atomic.h>
#include <asm/irq.h>
#include <asm/page.h>
#include <asm/pgtable.h>
#include <asm/hardirq.h>
#include <asm/io.h>
#include <asm/prom.h>
#include <asm/smp.h>
#include <asm/naca.h>
#include <asm/paca.h>
#include <asm/iSeries/LparData.h>
#include <asm/iSeries/HvCall.h>
#include <asm/iSeries/HvCallCfg.h>
#include <asm/time.h>
#include <asm/ppcdebug.h>
#include "open_pic.h"
#include <asm/machdep.h>
#include <asm/xics.h>
#include <asm/cputable.h>
#include <asm/system.h>
#include <asm/rtas.h>

int smp_threads_ready;
unsigned long cache_decay_ticks;

cpumask_t cpu_possible_map = CPU_MASK_NONE;
cpumask_t cpu_online_map = CPU_MASK_NONE;
cpumask_t cpu_available_map = CPU_MASK_NONE;
cpumask_t cpu_present_at_boot = CPU_MASK_NONE;

EXPORT_SYMBOL(cpu_online_map);
EXPORT_SYMBOL(cpu_possible_map);

struct smp_ops_t *smp_ops;

static volatile unsigned int cpu_callin_map[NR_CPUS];

extern unsigned char stab_array[];

extern int cpu_idle(void *unused);
void smp_call_function_interrupt(void);
extern long register_vpa(unsigned long flags, unsigned long proc,
			 unsigned long vpa);

/* Low level assembly function used to backup CPU 0 state */
extern void __save_cpu_setup(void);

#ifdef CONFIG_PPC_ISERIES
static unsigned long iSeries_smp_message[NR_CPUS];

void iSeries_smp_message_recv( struct pt_regs * regs )
{
	int cpu = smp_processor_id();
	int msg;

	if ( num_online_cpus() < 2 )
		return;

	for ( msg = 0; msg < 4; ++msg )
		if ( test_and_clear_bit( msg, &iSeries_smp_message[cpu] ) )
			smp_message_recv( msg, regs );
}

static inline void smp_iSeries_do_message(int cpu, int msg)
{
	set_bit(msg, &iSeries_smp_message[cpu]);
	HvCall_sendIPI(&(paca[cpu]));
}

static void smp_iSeries_message_pass(int target, int msg)
{
	int i;

	if (target < NR_CPUS)
		smp_iSeries_do_message(target, msg);
	else {
		for_each_online_cpu(i) {
			if (target == MSG_ALL_BUT_SELF
			    && i == smp_processor_id())
				continue;
			smp_iSeries_do_message(i, msg);
		}
	}
}

static int smp_iSeries_numProcs(void)
{
	unsigned np, i;

	np = 0;
        for (i=0; i < NR_CPUS; ++i) {
                if (paca[i].lppaca.xDynProcStatus < 2) {
			cpu_set(i, cpu_available_map);
			cpu_set(i, cpu_possible_map);
			cpu_set(i, cpu_present_at_boot);
                        ++np;
                }
        }
	return np;
}

static int smp_iSeries_probe(void)
{
	unsigned i;
	unsigned np = 0;

	for (i=0; i < NR_CPUS; ++i) {
		if (paca[i].lppaca.xDynProcStatus < 2) {
			/*paca[i].active = 1;*/
			++np;
		}
	}

	return np;
}

static void smp_iSeries_kick_cpu(int nr)
{
	BUG_ON(nr < 0 || nr >= NR_CPUS);

	/* Verify that our partition has a processor nr */
	if (paca[nr].lppaca.xDynProcStatus >= 2)
		return;

	/* The processor is currently spinning, waiting
	 * for the cpu_start field to become non-zero
	 * After we set cpu_start, the processor will
	 * continue on to secondary_start in iSeries_head.S
	 */
	paca[nr].cpu_start = 1;
}

static void __devinit smp_iSeries_setup_cpu(int nr)
{
}

static struct smp_ops_t iSeries_smp_ops = {
	.message_pass = smp_iSeries_message_pass,
	.probe        = smp_iSeries_probe,
	.kick_cpu     = smp_iSeries_kick_cpu,
	.setup_cpu    = smp_iSeries_setup_cpu,
};

/* This is called very early. */
void __init smp_init_iSeries(void)
{
	smp_ops = &iSeries_smp_ops;
	systemcfg->processorCount	= smp_iSeries_numProcs();
}
#endif

#ifdef CONFIG_PPC_PSERIES
void smp_openpic_message_pass(int target, int msg)
{
	/* make sure we're sending something that translates to an IPI */
	if ( msg > 0x3 ){
		printk("SMP %d: smp_message_pass: unknown msg %d\n",
		       smp_processor_id(), msg);
		return;
	}
	switch ( target )
	{
	case MSG_ALL:
		openpic_cause_IPI(msg, 0xffffffff);
		break;
	case MSG_ALL_BUT_SELF:
		openpic_cause_IPI(msg,
				  0xffffffff & ~(1 << smp_processor_id()));
		break;
	default:
		openpic_cause_IPI(msg, 1<<target);
		break;
	}
}

static int __init smp_openpic_probe(void)
{
	int nr_cpus;

	nr_cpus = cpus_weight(cpu_possible_map);

	if (nr_cpus > 1)
		openpic_request_IPIs();

	return nr_cpus;
}

static void __devinit smp_openpic_setup_cpu(int cpu)
{
	do_openpic_setup_cpu();
}

#ifdef CONFIG_HOTPLUG_CPU
/* Get state of physical CPU.
 * Return codes:
 *	0	- The processor is in the RTAS stopped state
 *	1	- stop-self is in progress
 *	2	- The processor is not in the RTAS stopped state
 *	-1	- Hardware Error
 *	-2	- Hardware Busy, Try again later.
 */
static int query_cpu_stopped(unsigned int pcpu)
{
	int cpu_status;
	int status, qcss_tok;

	qcss_tok = rtas_token("query-cpu-stopped-state");
	BUG_ON(qcss_tok == RTAS_UNKNOWN_SERVICE);
	status = rtas_call(qcss_tok, 1, 2, &cpu_status, pcpu);
	if (status != 0) {
		printk(KERN_ERR
		       "RTAS query-cpu-stopped-state failed: %i\n", status);
		return status;
	}

	return cpu_status;
}

int __cpu_disable(void)
{
	/* FIXME: go put this in a header somewhere */
	extern void xics_migrate_irqs_away(void);

	systemcfg->processorCount--;

	/*fix boot_cpuid here*/
	if (smp_processor_id() == boot_cpuid)
		boot_cpuid = any_online_cpu(cpu_online_map);

	/* FIXME: abstract this to not be platform specific later on */
	xics_migrate_irqs_away();
	return 0;
}

void __cpu_die(unsigned int cpu)
{
	int tries;
	int cpu_status;
	unsigned int pcpu = get_hard_smp_processor_id(cpu);

	for (tries = 0; tries < 5; tries++) {
		cpu_status = query_cpu_stopped(pcpu);

		if (cpu_status == 0)
			break;
		set_current_state(TASK_UNINTERRUPTIBLE);
		schedule_timeout(HZ);
	}
	if (cpu_status != 0) {
		printk("Querying DEAD? cpu %i (%i) shows %i\n",
		       cpu, pcpu, cpu_status);
	}

	/* Isolation and deallocation are definatly done by
	 * drslot_chrp_cpu.  If they were not they would be
	 * done here.  Change isolate state to Isolate and
	 * change allocation-state to Unusable.
	 */
	paca[cpu].cpu_start = 0;

	/* So we can recognize if it fails to come up next time. */
	cpu_callin_map[cpu] = 0;
}

/* Kill this cpu */
void cpu_die(void)
{
	local_irq_disable();
	/* Some hardware requires clearing the CPPR, while other hardware does not
	 * it is safe either way
	 */
	pSeriesLP_cppr_info(0, 0);
	rtas_stop_self();
	/* Should never get here... */
	BUG();
	for(;;);
}

/* Search all cpu device nodes for an offline logical cpu.  If a
 * device node has a "ibm,my-drc-index" property (meaning this is an
 * LPAR), paranoid-check whether we own the cpu.  For each "thread"
 * of a cpu, if it is offline and has the same hw index as before,
 * grab that in preference.
 */
static unsigned int find_physical_cpu_to_start(unsigned int old_hwindex)
{
	struct device_node *np = NULL;
	unsigned int best = -1U;

	while ((np = of_find_node_by_type(np, "cpu"))) {
		int nr_threads, len;
		u32 *index = (u32 *)get_property(np, "ibm,my-drc-index", NULL);
		u32 *tid = (u32 *)
			get_property(np, "ibm,ppc-interrupt-server#s", &len);

		if (!tid)
			tid = (u32 *)get_property(np, "reg", &len);

		if (!tid)
			continue;

		/* If there is a drc-index, make sure that we own
		 * the cpu.
		 */
		if (index) {
			int state;
			int rc = rtas_get_sensor(9003, *index, &state);
			if (rc != 0 || state != 1)
				continue;
		}

		nr_threads = len / sizeof(u32);

		while (nr_threads--) {
			if (0 == query_cpu_stopped(tid[nr_threads])) {
				best = tid[nr_threads];
				if (best == old_hwindex)
					goto out;
			}
		}
	}
out:
	of_node_put(np);
	return best;
}

/**
 * smp_startup_cpu() - start the given cpu
 *
 * At boot time, there is nothing to do.  At run-time, call RTAS with
 * the appropriate start location, if the cpu is in the RTAS stopped
 * state.
 *
 * Returns:
 *	0	- failure
 *	1	- success
 */
static inline int __devinit smp_startup_cpu(unsigned int lcpu)
{
	int status;
	extern void (*pseries_secondary_smp_init)(unsigned int cpu);
	unsigned long start_here = __pa(pseries_secondary_smp_init);
	unsigned int pcpu;

	/* At boot time the cpus are already spinning in hold
	 * loops, so nothing to do. */
 	if (system_state == SYSTEM_BOOTING)
		return 1;

	pcpu = find_physical_cpu_to_start(get_hard_smp_processor_id(lcpu));
	if (pcpu == -1U) {
		printk(KERN_INFO "No more cpus available, failing\n");
		return 0;
	}

	/* Fixup atomic count: it exited inside IRQ handler. */
	paca[lcpu].__current->thread_info->preempt_count	= 0;

	/* At boot this is done in prom.c. */
	paca[lcpu].hw_cpu_id = pcpu;

	status = rtas_call(rtas_token("start-cpu"), 3, 1, NULL,
			   pcpu, start_here, lcpu);
	if (status != 0) {
		printk(KERN_ERR "start-cpu failed: %i\n", status);
		return 0;
	}
	return 1;
}

static inline void look_for_more_cpus(void)
{
	int num_addr_cell, num_size_cell, len, i, maxcpus;
	struct device_node *np;
	unsigned int *ireg;

	/* Find the property which will tell us about how many CPUs
	 * we're allowed to have. */
	if ((np = find_path_device("/rtas")) == NULL) {
		printk(KERN_ERR "Could not find /rtas in device tree!");
		return;
	}
	num_addr_cell = prom_n_addr_cells(np);
	num_size_cell = prom_n_size_cells(np);

	ireg = (unsigned int *)get_property(np, "ibm,lrdr-capacity", &len);
	if (ireg == NULL) {
		/* FIXME: make sure not marked as lrdr_capable() */
		return;
	}

	maxcpus = ireg[num_addr_cell + num_size_cell];

	/* Double maxcpus for processors which have SMT capability */
	if (cur_cpu_spec->cpu_features & CPU_FTR_SMT)
		maxcpus *= 2;


	if (maxcpus > NR_CPUS) {
		printk(KERN_WARNING
		       "Partition configured for %d cpus, "
		       "operating system maximum is %d.\n", maxcpus, NR_CPUS);
		maxcpus = NR_CPUS;
	} else
		printk(KERN_INFO "Partition configured for %d cpus.\n",
		       maxcpus);

	/* Make those cpus (which might appear later) possible too. */
	for (i = 0; i < maxcpus; i++)
		cpu_set(i, cpu_possible_map);
}
#else /* ... CONFIG_HOTPLUG_CPU */
static inline int __devinit smp_startup_cpu(unsigned int lcpu)
{
	return 1;
}
static inline void look_for_more_cpus(void)
{
}
#endif /* CONFIG_HOTPLUG_CPU */

static void smp_pSeries_kick_cpu(int nr)
{
	BUG_ON(nr < 0 || nr >= NR_CPUS);

	if (!smp_startup_cpu(nr))
		return;

	/*
	 * The processor is currently spinning, waiting for the
	 * cpu_start field to become non-zero After we set cpu_start,
	 * the processor will continue on to secondary_start
	 */
	paca[nr].cpu_start = 1;
}
#endif /* CONFIG_PPC_PSERIES */

static void __init smp_space_timers(unsigned int max_cpus)
{
	int i;
	unsigned long offset = tb_ticks_per_jiffy / max_cpus;
	unsigned long previous_tb = paca[boot_cpuid].next_jiffy_update_tb;

	for_each_cpu(i) {
		if (i != boot_cpuid) {
			paca[i].next_jiffy_update_tb =
				previous_tb + offset;
			previous_tb = paca[i].next_jiffy_update_tb;
		}
	}
}

#ifdef CONFIG_PPC_PSERIES
void vpa_init(int cpu)
{
	unsigned long flags;

	/* Register the Virtual Processor Area (VPA) */
	flags = 1UL << (63 - 18);
	register_vpa(flags, cpu, __pa((unsigned long)&(paca[cpu].lppaca)));
}

static inline void smp_xics_do_message(int cpu, int msg)
{
	set_bit(msg, &xics_ipi_message[cpu].value);
	mb();
	xics_cause_IPI(cpu);
}

static void smp_xics_message_pass(int target, int msg)
{
	unsigned int i;

	if (target < NR_CPUS) {
		smp_xics_do_message(target, msg);
	} else {
		for_each_online_cpu(i) {
			if (target == MSG_ALL_BUT_SELF
			    && i == smp_processor_id())
				continue;
			smp_xics_do_message(i, msg);
		}
	}
}

extern void xics_request_IPIs(void);

static int __init smp_xics_probe(void)
{
#ifdef CONFIG_SMP
	xics_request_IPIs();
#endif

	return cpus_weight(cpu_possible_map);
}

static void __devinit smp_xics_setup_cpu(int cpu)
{
	if (cpu != boot_cpuid)
		xics_setup_cpu();
}

static spinlock_t timebase_lock = SPIN_LOCK_UNLOCKED;
static unsigned long timebase = 0;

static void __devinit pSeries_give_timebase(void)
{
	spin_lock(&timebase_lock);
	rtas_call(rtas_token("freeze-time-base"), 0, 1, NULL);
	timebase = get_tb();
	spin_unlock(&timebase_lock);

	while (timebase)
		barrier();
	rtas_call(rtas_token("thaw-time-base"), 0, 1, NULL);
}

static void __devinit pSeries_take_timebase(void)
{
	while (!timebase)
		barrier();
	spin_lock(&timebase_lock);
	set_tb(timebase >> 32, timebase & 0xffffffff);
	timebase = 0;
	spin_unlock(&timebase_lock);
}

static struct smp_ops_t pSeries_openpic_smp_ops = {
	.message_pass	= smp_openpic_message_pass,
	.probe		= smp_openpic_probe,
	.kick_cpu	= smp_pSeries_kick_cpu,
	.setup_cpu	= smp_openpic_setup_cpu,
};

static struct smp_ops_t pSeries_xics_smp_ops = {
	.message_pass	= smp_xics_message_pass,
	.probe		= smp_xics_probe,
	.kick_cpu	= smp_pSeries_kick_cpu,
	.setup_cpu	= smp_xics_setup_cpu,
};

/* This is called very early */
void __init smp_init_pSeries(void)
{

	if (naca->interrupt_controller == IC_OPEN_PIC)
		smp_ops = &pSeries_openpic_smp_ops;
	else
		smp_ops = &pSeries_xics_smp_ops;

	/* Non-lpar has additional take/give timebase */
	if (systemcfg->platform == PLATFORM_PSERIES) {
		smp_ops->give_timebase = pSeries_give_timebase;
		smp_ops->take_timebase = pSeries_take_timebase;
	}
}
#endif

void smp_local_timer_interrupt(struct pt_regs * regs)
{
	if (!--(get_paca()->prof_counter)) {
		update_process_times(user_mode(regs));
		(get_paca()->prof_counter)=get_paca()->prof_multiplier;
	}
}

void smp_message_recv(int msg, struct pt_regs *regs)
{
	switch(msg) {
	case PPC_MSG_CALL_FUNCTION:
		smp_call_function_interrupt();
		break;
	case PPC_MSG_RESCHEDULE: 
		/* XXX Do we have to do this? */
		set_need_resched();
		break;
#if 0
	case PPC_MSG_MIGRATE_TASK: