process-linux-xen.c

xen 3.2.2 源码

/*
 * Architecture-specific setup.
 *
 * Copyright (C) 1998-2003 Hewlett-Packard Co
 *	David Mosberger-Tang <[e-mail]>
 * 04/11/17 Ashok Raj	<[e-mail]> Added CPU Hotplug Support
 */
#ifdef XEN
#include <linux/cpu.h>
#include <linux/notifier.h>
#include <xen/types.h>
#include <xen/lib.h>
#include <xen/symbols.h>
#include <xen/smp.h>
#include <xen/sched.h>
#include <asm/elf.h>
#include <asm/uaccess.h>
#include <asm/processor.h>
#include <asm/ptrace.h>
#include <asm/unwind.h>
#include <asm/sal.h>
#else
#define __KERNEL_SYSCALLS__	/* see <asm/unistd.h> */
#include <linux/config.h>

#include <linux/cpu.h>
#include <linux/pm.h>
#include <linux/elf.h>
#include <linux/errno.h>
#include <linux/kallsyms.h>
#include <linux/kernel.h>
#include <linux/mm.h>
#include <linux/module.h>
#include <linux/notifier.h>
#include <linux/personality.h>
#include <linux/sched.h>
#include <linux/slab.h>
#include <linux/smp_lock.h>
#include <linux/stddef.h>
#include <linux/thread_info.h>
#include <linux/unistd.h>
#include <linux/efi.h>
#include <linux/interrupt.h>
#include <linux/delay.h>
#include <linux/kprobes.h>

#include <asm/cpu.h>
#include <asm/delay.h>
#include <asm/elf.h>
#include <asm/ia32.h>
#include <asm/irq.h>
#include <asm/pgalloc.h>
#include <asm/processor.h>
#include <asm/sal.h>
#include <asm/tlbflush.h>
#include <asm/uaccess.h>
#include <asm/unwind.h>
#include <asm/user.h>

#include "entry.h"

#ifdef CONFIG_PERFMON
# include <asm/perfmon.h>
#endif

#include "sigframe.h"

void (*ia64_mark_idle)(int);
static DEFINE_PER_CPU(unsigned int, cpu_idle_state);

unsigned long boot_option_idle_override = 0;
EXPORT_SYMBOL(boot_option_idle_override);
#endif

void
ia64_do_show_stack (struct unw_frame_info *info, void *arg)
{
	unsigned long ip, sp, bsp;
	char buf[128];			/* don't make it so big that it overflows the stack! */

	printk("\nCall Trace:\n");
	do {
		unw_get_ip(info, &ip);
		if (ip == 0)
			break;

		unw_get_sp(info, &sp);
		unw_get_bsp(info, &bsp);
		snprintf(buf, sizeof(buf),
			 " [<%016lx>] %%s\n"
			 "                                sp=%016lx bsp=%016lx\n",
			 ip, sp, bsp);
		print_symbol(buf, ip);
	} while (unw_unwind(info) >= 0);
}

void
show_stack (struct task_struct *task, unsigned long *sp)
{
	if (!task)
		unw_init_running(ia64_do_show_stack, NULL);
	else {
		struct unw_frame_info info;

		unw_init_from_blocked_task(&info, task);
		ia64_do_show_stack(&info, NULL);
	}
}

void
dump_stack (void)
{
	show_stack(NULL, NULL);
}

EXPORT_SYMBOL(dump_stack);

#ifdef XEN
void
show_registers(struct pt_regs *regs)
#else
void
show_regs (struct pt_regs *regs)
#endif
{
	unsigned long ip = regs->cr_iip + ia64_psr(regs)->ri;

#ifndef XEN
	print_modules();
	printk("\nPid: %d, CPU %d, comm: %20s\n", current->pid, smp_processor_id(), current->comm);
	printk("psr : %016lx ifs : %016lx ip  : [<%016lx>]    %s\n",
	       regs->cr_ipsr, regs->cr_ifs, ip, print_tainted());
#else
	struct vcpu* vcpu = current;
	if (vcpu != NULL) {
		struct domain* d = vcpu->domain;
		printk("d 0x%p domid %d\n", d, d->domain_id);
		printk("vcpu 0x%p vcpu %d\n",
		       vcpu, vcpu->vcpu_id);
	}
	printk("\nCPU %d\n", smp_processor_id());
	printk("psr : %016lx ifs : %016lx ip  : [<%016lx>]\n",
	       regs->cr_ipsr, regs->cr_ifs, ip);
#endif
	print_symbol("ip is at %s\n", ip);
	printk("unat: %016lx pfs : %016lx rsc : %016lx\n",
	       regs->ar_unat, regs->ar_pfs, regs->ar_rsc);
	printk("rnat: %016lx bsps: %016lx pr  : %016lx\n",
	       regs->ar_rnat, regs->ar_bspstore, regs->pr);
	printk("ldrs: %016lx ccv : %016lx fpsr: %016lx\n",
	       regs->loadrs, regs->ar_ccv, regs->ar_fpsr);
	printk("csd : %016lx ssd : %016lx\n", regs->ar_csd, regs->ar_ssd);
	printk("b0  : %016lx b6  : %016lx b7  : %016lx\n", regs->b0, regs->b6, regs->b7);
	printk("f6  : %05lx%016lx f7  : %05lx%016lx\n",
	       regs->f6.u.bits[1], regs->f6.u.bits[0],
	       regs->f7.u.bits[1], regs->f7.u.bits[0]);
	printk("f8  : %05lx%016lx f9  : %05lx%016lx\n",
	       regs->f8.u.bits[1], regs->f8.u.bits[0],
	       regs->f9.u.bits[1], regs->f9.u.bits[0]);
	printk("f10 : %05lx%016lx f11 : %05lx%016lx\n",
	       regs->f10.u.bits[1], regs->f10.u.bits[0],
	       regs->f11.u.bits[1], regs->f11.u.bits[0]);

	printk("r1  : %016lx r2  : %016lx r3  : %016lx\n", regs->r1, regs->r2, regs->r3);
	printk("r8  : %016lx r9  : %016lx r10 : %016lx\n", regs->r8, regs->r9, regs->r10);
	printk("r11 : %016lx r12 : %016lx r13 : %016lx\n", regs->r11, regs->r12, regs->r13);
	printk("r14 : %016lx r15 : %016lx r16 : %016lx\n", regs->r14, regs->r15, regs->r16);
	printk("r17 : %016lx r18 : %016lx r19 : %016lx\n", regs->r17, regs->r18, regs->r19);
	printk("r20 : %016lx r21 : %016lx r22 : %016lx\n", regs->r20, regs->r21, regs->r22);
	printk("r23 : %016lx r24 : %016lx r25 : %016lx\n", regs->r23, regs->r24, regs->r25);
	printk("r26 : %016lx r27 : %016lx r28 : %016lx\n", regs->r26, regs->r27, regs->r28);
	printk("r29 : %016lx r30 : %016lx r31 : %016lx\n", regs->r29, regs->r30, regs->r31);

#ifndef XEN
	if (user_mode(regs)) {
		/* print the stacked registers */
		unsigned long val, *bsp, ndirty;
		int i, sof, is_nat = 0;

		sof = regs->cr_ifs & 0x7f;	/* size of frame */
		ndirty = (regs->loadrs >> 19);
		bsp = ia64_rse_skip_regs((unsigned long *) regs->ar_bspstore, ndirty);
		for (i = 0; i < sof; ++i) {
			get_user(val, (unsigned long __user *) ia64_rse_skip_regs(bsp, i));
			printk("r%-3u:%c%016lx%s", 32 + i, is_nat ? '*' : ' ', val,
			       ((i == sof - 1) || (i % 3) == 2) ? "\n" : " ");
		}
	} else
#endif
		show_stack(NULL, NULL);
}

#ifndef XEN
void
do_notify_resume_user (sigset_t *oldset, struct sigscratch *scr, long in_syscall)
{
	if (fsys_mode(current, &scr->pt)) {
		/* defer signal-handling etc. until we return to privilege-level 0.  */
		if (!ia64_psr(&scr->pt)->lp)
			ia64_psr(&scr->pt)->lp = 1;
		return;
	}

#ifdef CONFIG_PERFMON
	if (current->thread.pfm_needs_checking)
		pfm_handle_work();
#endif

	/* deal with pending signal delivery */
	if (test_thread_flag(TIF_SIGPENDING))
		ia64_do_signal(oldset, scr, in_syscall);
}

static int pal_halt        = 1;
static int can_do_pal_halt = 1;

static int __init nohalt_setup(char * str)
{
	pal_halt = can_do_pal_halt = 0;
	return 1;
}
__setup("nohalt", nohalt_setup);

void
update_pal_halt_status(int status)
{
	can_do_pal_halt = pal_halt && status;
}

/*
 * We use this if we don't have any better idle routine..
 */
void
default_idle (void)
{
	local_irq_enable();
	while (!need_resched())
		if (can_do_pal_halt)
			safe_halt();
		else
			cpu_relax();
}
#endif

#ifdef CONFIG_HOTPLUG_CPU
/* We don't actually take CPU down, just spin without interrupts. */
#ifndef XEN
static inline void play_dead(void)
#else
void play_dead(void)
#endif
{
	extern void ia64_cpu_local_tick (void);
	unsigned int this_cpu = smp_processor_id();

	/* Ack it */
	__get_cpu_var(cpu_state) = CPU_DEAD;

	max_xtp();
	local_irq_disable();
	ia64_jump_to_sal(&sal_boot_rendez_state[this_cpu]);
	/*
	 * The above is a point of no-return, the processor is
	 * expected to be in SAL loop now.
	 */
	BUG();
}
#else
#ifndef XEN
static inline void play_dead(void)
#else
void play_dead(void)
#endif
{
	BUG();
}
#endif /* CONFIG_HOTPLUG_CPU */

#ifndef XEN
void cpu_idle_wait(void)
{
	unsigned int cpu, this_cpu = get_cpu();
	cpumask_t map;

	set_cpus_allowed(current, cpumask_of_cpu(this_cpu));
	put_cpu();

	cpus_clear(map);
	for_each_online_cpu(cpu) {
		per_cpu(cpu_idle_state, cpu) = 1;
		cpu_set(cpu, map);
	}

	__get_cpu_var(cpu_idle_state) = 0;

	wmb();
	do {
		ssleep(1);
		for_each_online_cpu(cpu) {
			if (cpu_isset(cpu, map) && !per_cpu(cpu_idle_state, cpu))
				cpu_clear(cpu, map);
		}
		cpus_and(map, map, cpu_online_map);
	} while (!cpus_empty(map));
}
EXPORT_SYMBOL_GPL(cpu_idle_wait);

void __attribute__((noreturn))
cpu_idle (void)
{
	void (*mark_idle)(int) = ia64_mark_idle;

	/* endless idle loop with no priority at all */
	while (1) {
#ifdef CONFIG_SMP
		if (!need_resched())
			min_xtp();
#endif
		while (!need_resched()) {
			void (*idle)(void);

			if (__get_cpu_var(cpu_idle_state))
				__get_cpu_var(cpu_idle_state) = 0;

			rmb();
			if (mark_idle)
				(*mark_idle)(1);

			idle = pm_idle;
			if (!idle)
				idle = default_idle;
			(*idle)();
		}

		if (mark_idle)
			(*mark_idle)(0);

#ifdef CONFIG_SMP
		normal_xtp();
#endif
		schedule();
		check_pgt_cache();
		if (cpu_is_offline(smp_processor_id()))
			play_dead();
	}
}

void
ia64_save_extra (struct task_struct *task)
{
#ifdef CONFIG_PERFMON
	unsigned long info;
#endif

	if ((task->thread.flags & IA64_THREAD_DBG_VALID) != 0)
		ia64_save_debug_regs(&task->thread.dbr[0]);

#ifdef CONFIG_PERFMON
	if ((task->thread.flags & IA64_THREAD_PM_VALID) != 0)
		pfm_save_regs(task);

	info = __get_cpu_var(pfm_syst_info);
	if (info & PFM_CPUINFO_SYST_WIDE)
		pfm_syst_wide_update_task(task, info, 0);
#endif

#ifdef CONFIG_IA32_SUPPORT
	if (IS_IA32_PROCESS(ia64_task_regs(task)))
		ia32_save_state(task);
#endif
}

void
ia64_load_extra (struct task_struct *task)
{
#ifdef CONFIG_PERFMON
	unsigned long info;
#endif

	if ((task->thread.flags & IA64_THREAD_DBG_VALID) != 0)
		ia64_load_debug_regs(&task->thread.dbr[0]);

#ifdef CONFIG_PERFMON
	if ((task->thread.flags & IA64_THREAD_PM_VALID) != 0)
		pfm_load_regs(task);

	info = __get_cpu_var(pfm_syst_info);
	if (info & PFM_CPUINFO_SYST_WIDE) 
		pfm_syst_wide_update_task(task, info, 1);
#endif

#ifdef CONFIG_IA32_SUPPORT
	if (IS_IA32_PROCESS(ia64_task_regs(task)))
		ia32_load_state(task);
#endif
}

/*
 * Copy the state of an ia-64 thread.
 *
 * We get here through the following  call chain:
 *
 *	from user-level:	from kernel:
 *
 *	<clone syscall>	        <some kernel call frames>
 *	sys_clone		   :
 *	do_fork			do_fork
 *	copy_thread		copy_thread
 *
 * This means that the stack layout is as follows:
 *
 *	+---------------------+ (highest addr)
 *	|   struct pt_regs    |
 *	+---------------------+
 *	| struct switch_stack |
 *	+---------------------+
 *	|                     |
 *	|    memory stack     |
 *	|                     | <-- sp (lowest addr)
 *	+---------------------+
 *
 * Observe that we copy the unat values that are in pt_regs and switch_stack.  Spilling an
 * integer to address X causes bit N in ar.unat to be set to the NaT bit of the register,
 * with N=(X & 0x1ff)/8.  Thus, copying the unat value preserves the NaT bits ONLY if the
 * pt_regs structure in the parent is congruent to that of the child, modulo 512.  Since
 * the stack is page aligned and the page size is at least 4KB, this is always the case,
 * so there is nothing to worry about.
 */
int
copy_thread (int nr, unsigned long clone_flags,
	     unsigned long user_stack_base, unsigned long user_stack_size,
	     struct task_struct *p, struct pt_regs *regs)
{
	extern char ia64_ret_from_clone, ia32_ret_from_clone;
	struct switch_stack *child_stack, *stack;
	unsigned long rbs, child_rbs, rbs_size;
	struct pt_regs *child_ptregs;
	int retval = 0;

#ifdef CONFIG_SMP
	/*
	 * For SMP idle threads, fork_by_hand() calls do_fork with
	 * NULL regs.
	 */
	if (!regs)
		return 0;