process.c

linux 内核源代码

/*
 *  Derived from "arch/i386/kernel/process.c"
 *    Copyright (C) 1995  Linus Torvalds
 *
 *  Updated and modified by Cort Dougan ([e-mail]) and
 *  Paul Mackerras ([e-mail])
 *
 *  PowerPC version
 *    Copyright (C) 1995-1996 Gary Thomas ([e-mail])
 *
 *  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/errno.h>
#include <linux/sched.h>
#include <linux/kernel.h>
#include <linux/mm.h>
#include <linux/smp.h>
#include <linux/stddef.h>
#include <linux/unistd.h>
#include <linux/ptrace.h>
#include <linux/slab.h>
#include <linux/user.h>
#include <linux/elf.h>
#include <linux/init.h>
#include <linux/prctl.h>
#include <linux/init_task.h>
#include <linux/module.h>
#include <linux/kallsyms.h>
#include <linux/mqueue.h>
#include <linux/hardirq.h>
#include <linux/utsname.h>

#include <asm/pgtable.h>
#include <asm/uaccess.h>
#include <asm/system.h>
#include <asm/io.h>
#include <asm/processor.h>
#include <asm/mmu.h>
#include <asm/prom.h>
#include <asm/machdep.h>
#include <asm/time.h>
#include <asm/syscalls.h>
#ifdef CONFIG_PPC64
#include <asm/firmware.h>
#endif

extern unsigned long _get_SP(void);

#ifndef CONFIG_SMP
struct task_struct *last_task_used_math = NULL;
struct task_struct *last_task_used_altivec = NULL;
struct task_struct *last_task_used_spe = NULL;
#endif

/*
 * Make sure the floating-point register state in the
 * the thread_struct is up to date for task tsk.
 */
void flush_fp_to_thread(struct task_struct *tsk)
{
	if (tsk->thread.regs) {
		/*
		 * We need to disable preemption here because if we didn't,
		 * another process could get scheduled after the regs->msr
		 * test but before we have finished saving the FP registers
		 * to the thread_struct.  That process could take over the
		 * FPU, and then when we get scheduled again we would store
		 * bogus values for the remaining FP registers.
		 */
		preempt_disable();
		if (tsk->thread.regs->msr & MSR_FP) {
#ifdef CONFIG_SMP
			/*
			 * This should only ever be called for current or
			 * for a stopped child process.  Since we save away
			 * the FP register state on context switch on SMP,
			 * there is something wrong if a stopped child appears
			 * to still have its FP state in the CPU registers.
			 */
			BUG_ON(tsk != current);
#endif
			giveup_fpu(tsk);
		}
		preempt_enable();
	}
}

void enable_kernel_fp(void)
{
	WARN_ON(preemptible());

#ifdef CONFIG_SMP
	if (current->thread.regs && (current->thread.regs->msr & MSR_FP))
		giveup_fpu(current);
	else
		giveup_fpu(NULL);	/* just enables FP for kernel */
#else
	giveup_fpu(last_task_used_math);
#endif /* CONFIG_SMP */
}
EXPORT_SYMBOL(enable_kernel_fp);

int dump_task_fpu(struct task_struct *tsk, elf_fpregset_t *fpregs)
{
	if (!tsk->thread.regs)
		return 0;
	flush_fp_to_thread(current);

	memcpy(fpregs, &tsk->thread.fpr[0], sizeof(*fpregs));

	return 1;
}

#ifdef CONFIG_ALTIVEC
void enable_kernel_altivec(void)
{
	WARN_ON(preemptible());

#ifdef CONFIG_SMP
	if (current->thread.regs && (current->thread.regs->msr & MSR_VEC))
		giveup_altivec(current);
	else
		giveup_altivec(NULL);	/* just enable AltiVec for kernel - force */
#else
	giveup_altivec(last_task_used_altivec);
#endif /* CONFIG_SMP */
}
EXPORT_SYMBOL(enable_kernel_altivec);

/*
 * Make sure the VMX/Altivec register state in the
 * the thread_struct is up to date for task tsk.
 */
void flush_altivec_to_thread(struct task_struct *tsk)
{
	if (tsk->thread.regs) {
		preempt_disable();
		if (tsk->thread.regs->msr & MSR_VEC) {
#ifdef CONFIG_SMP
			BUG_ON(tsk != current);
#endif
			giveup_altivec(tsk);
		}
		preempt_enable();
	}
}

int dump_task_altivec(struct task_struct *tsk, elf_vrregset_t *vrregs)
{
	/* ELF_NVRREG includes the VSCR and VRSAVE which we need to save
	 * separately, see below */
	const int nregs = ELF_NVRREG - 2;
	elf_vrreg_t *reg;
	u32 *dest;

	if (tsk == current)
		flush_altivec_to_thread(tsk);

	reg = (elf_vrreg_t *)vrregs;

	/* copy the 32 vr registers */
	memcpy(reg, &tsk->thread.vr[0], nregs * sizeof(*reg));
	reg += nregs;

	/* copy the vscr */
	memcpy(reg, &tsk->thread.vscr, sizeof(*reg));
	reg++;

	/* vrsave is stored in the high 32bit slot of the final 128bits */
	memset(reg, 0, sizeof(*reg));
	dest = (u32 *)reg;
	*dest = tsk->thread.vrsave;

	return 1;
}
#endif /* CONFIG_ALTIVEC */

#ifdef CONFIG_SPE

void enable_kernel_spe(void)
{
	WARN_ON(preemptible());

#ifdef CONFIG_SMP
	if (current->thread.regs && (current->thread.regs->msr & MSR_SPE))
		giveup_spe(current);
	else
		giveup_spe(NULL);	/* just enable SPE for kernel - force */
#else
	giveup_spe(last_task_used_spe);
#endif /* __SMP __ */
}
EXPORT_SYMBOL(enable_kernel_spe);

void flush_spe_to_thread(struct task_struct *tsk)
{
	if (tsk->thread.regs) {
		preempt_disable();
		if (tsk->thread.regs->msr & MSR_SPE) {
#ifdef CONFIG_SMP
			BUG_ON(tsk != current);
#endif
			giveup_spe(tsk);
		}
		preempt_enable();
	}
}

int dump_spe(struct pt_regs *regs, elf_vrregset_t *evrregs)
{
	flush_spe_to_thread(current);
	/* We copy u32 evr[32] + u64 acc + u32 spefscr -> 35 */
	memcpy(evrregs, &current->thread.evr[0], sizeof(u32) * 35);
	return 1;
}
#endif /* CONFIG_SPE */

#ifndef CONFIG_SMP
/*
 * If we are doing lazy switching of CPU state (FP, altivec or SPE),
 * and the current task has some state, discard it.
 */
void discard_lazy_cpu_state(void)
{
	preempt_disable();
	if (last_task_used_math == current)
		last_task_used_math = NULL;
#ifdef CONFIG_ALTIVEC
	if (last_task_used_altivec == current)
		last_task_used_altivec = NULL;
#endif /* CONFIG_ALTIVEC */
#ifdef CONFIG_SPE
	if (last_task_used_spe == current)
		last_task_used_spe = NULL;
#endif
	preempt_enable();
}
#endif /* CONFIG_SMP */

int set_dabr(unsigned long dabr)
{
#ifdef CONFIG_PPC_MERGE		/* XXX for now */
	if (ppc_md.set_dabr)
		return ppc_md.set_dabr(dabr);
#endif

	/* XXX should we have a CPU_FTR_HAS_DABR ? */
#if defined(CONFIG_PPC64) || defined(CONFIG_6xx)
	mtspr(SPRN_DABR, dabr);
#endif
	return 0;
}

#ifdef CONFIG_PPC64
DEFINE_PER_CPU(struct cpu_usage, cpu_usage_array);
#endif

static DEFINE_PER_CPU(unsigned long, current_dabr);

struct task_struct *__switch_to(struct task_struct *prev,
	struct task_struct *new)
{
	struct thread_struct *new_thread, *old_thread;
	unsigned long flags;
	struct task_struct *last;

#ifdef CONFIG_SMP
	/* avoid complexity of lazy save/restore of fpu
	 * by just saving it every time we switch out if
	 * this task used the fpu during the last quantum.
	 *
	 * If it tries to use the fpu again, it'll trap and
	 * reload its fp regs.  So we don't have to do a restore
	 * every switch, just a save.
	 *  -- Cort
	 */
	if (prev->thread.regs && (prev->thread.regs->msr & MSR_FP))
		giveup_fpu(prev);
#ifdef CONFIG_ALTIVEC
	/*
	 * If the previous thread used altivec in the last quantum
	 * (thus changing altivec regs) then save them.
	 * We used to check the VRSAVE register but not all apps
	 * set it, so we don't rely on it now (and in fact we need
	 * to save & restore VSCR even if VRSAVE == 0).  -- paulus
	 *
	 * On SMP we always save/restore altivec regs just to avoid the
	 * complexity of changing processors.
	 *  -- Cort
	 */
	if (prev->thread.regs && (prev->thread.regs->msr & MSR_VEC))
		giveup_altivec(prev);
#endif /* CONFIG_ALTIVEC */
#ifdef CONFIG_SPE
	/*
	 * If the previous thread used spe in the last quantum
	 * (thus changing spe regs) then save them.
	 *
	 * On SMP we always save/restore spe regs just to avoid the
	 * complexity of changing processors.
	 */
	if ((prev->thread.regs && (prev->thread.regs->msr & MSR_SPE)))
		giveup_spe(prev);
#endif /* CONFIG_SPE */

#else  /* CONFIG_SMP */
#ifdef CONFIG_ALTIVEC
	/* Avoid the trap.  On smp this this never happens since
	 * we don't set last_task_used_altivec -- Cort
	 */
	if (new->thread.regs && last_task_used_altivec == new)
		new->thread.regs->msr |= MSR_VEC;
#endif /* CONFIG_ALTIVEC */
#ifdef CONFIG_SPE
	/* Avoid the trap.  On smp this this never happens since
	 * we don't set last_task_used_spe
	 */
	if (new->thread.regs && last_task_used_spe == new)
		new->thread.regs->msr |= MSR_SPE;
#endif /* CONFIG_SPE */

#endif /* CONFIG_SMP */

	if (unlikely(__get_cpu_var(current_dabr) != new->thread.dabr)) {
		set_dabr(new->thread.dabr);
		__get_cpu_var(current_dabr) = new->thread.dabr;
	}

	new_thread = &new->thread;
	old_thread = &current->thread;

#ifdef CONFIG_PPC64
	/*
	 * Collect processor utilization data per process
	 */
	if (firmware_has_feature(FW_FEATURE_SPLPAR)) {
		struct cpu_usage *cu = &__get_cpu_var(cpu_usage_array);
		long unsigned start_tb, current_tb;
		start_tb = old_thread->start_tb;
		cu->current_tb = current_tb = mfspr(SPRN_PURR);
		old_thread->accum_tb += (current_tb - start_tb);
		new_thread->start_tb = current_tb;
	}
#endif

	local_irq_save(flags);

	account_system_vtime(current);
	account_process_vtime(current);
	calculate_steal_time();

	last = _switch(old_thread, new_thread);

	local_irq_restore(flags);

	return last;
}

static int instructions_to_print = 16;

static void show_instructions(struct pt_regs *regs)
{
	int i;
	unsigned long pc = regs->nip - (instructions_to_print * 3 / 4 *
			sizeof(int));

	printk("Instruction dump:");

	for (i = 0; i < instructions_to_print; i++) {
		int instr;

		if (!(i % 8))
			printk("\n");

#if !defined(CONFIG_BOOKE)
		/* If executing with the IMMU off, adjust pc rather
		 * than print XXXXXXXX.
		 */
		if (!(regs->msr & MSR_IR))
			pc = (unsigned long)phys_to_virt(pc);
#endif

		/* We use __get_user here *only* to avoid an OOPS on a
		 * bad address because the pc *should* only be a
		 * kernel address.
		 */
		if (!__kernel_text_address(pc) ||
		     __get_user(instr, (unsigned int __user *)pc)) {
			printk("XXXXXXXX ");
		} else {
			if (regs->nip == pc)
				printk("<%08x> ", instr);
			else
				printk("%08x ", instr);
		}

		pc += sizeof(int);
	}

	printk("\n");
}

static struct regbit {
	unsigned long bit;
	const char *name;
} msr_bits[] = {
	{MSR_EE,	"EE"},
	{MSR_PR,	"PR"},
	{MSR_FP,	"FP"},
	{MSR_ME,	"ME"},
	{MSR_IR,	"IR"},
	{MSR_DR,	"DR"},
	{0,		NULL}
};

static void printbits(unsigned long val, struct regbit *bits)
{
	const char *sep = "";

	printk("<");
	for (; bits->bit; ++bits)
		if (val & bits->bit) {
			printk("%s%s", sep, bits->name);
			sep = ",";
		}
	printk(">");
}

#ifdef CONFIG_PPC64
#define REG		"%016lx"
#define REGS_PER_LINE	4
#define LAST_VOLATILE	13
#else
#define REG		"%08lx"
#define REGS_PER_LINE	8
#define LAST_VOLATILE	12
#endif

void show_regs(struct pt_regs * regs)
{
	int i, trap;

	printk("NIP: "REG" LR: "REG" CTR: "REG"\n",
	       regs->nip, regs->link, regs->ctr);
	printk("REGS: %p TRAP: %04lx   %s  (%s)\n",
	       regs, regs->trap, print_tainted(), init_utsname()->release);
	printk("MSR: "REG" ", regs->msr);
	printbits(regs->msr, msr_bits);
	printk("  CR: %08lx  XER: %08lx\n", regs->ccr, regs->xer);
	trap = TRAP(regs);
	if (trap == 0x300 || trap == 0x600)
#if defined(CONFIG_4xx) || defined(CONFIG_BOOKE)
		printk("DEAR: "REG", ESR: "REG"\n", regs->dar, regs->dsisr);
#else
		printk("DAR: "REG", DSISR: "REG"\n", regs->dar, regs->dsisr);
#endif
	printk("TASK = %p[%d] '%s' THREAD: %p",
	       current, task_pid_nr(current), current->comm, task_thread_info(current));

#ifdef CONFIG_SMP
	printk(" CPU: %d", smp_processor_id());
#endif /* CONFIG_SMP */

	for (i = 0;  i < 32;  i++) {
		if ((i % REGS_PER_LINE) == 0)
			printk("\n" KERN_INFO "GPR%02d: ", i);
		printk(REG " ", regs->gpr[i]);
		if (i == LAST_VOLATILE && !FULL_REGS(regs))
			break;
	}
	printk("\n");
#ifdef CONFIG_KALLSYMS
	/*
	 * Lookup NIP late so we have the best change of getting the
	 * above info out without failing
	 */
	printk("NIP ["REG"] ", regs->nip);
	print_symbol("%s\n", regs->nip);
	printk("LR ["REG"] ", regs->link);
	print_symbol("%s\n", regs->link);
#endif
	show_stack(current, (unsigned long *) regs->gpr[1]);
	if (!user_mode(regs))
		show_instructions(regs);
}

void exit_thread(void)
{
	discard_lazy_cpu_state();
}

void flush_thread(void)
{
#ifdef CONFIG_PPC64
	struct thread_info *t = current_thread_info();

	if (test_ti_thread_flag(t, TIF_ABI_PENDING)) {
		clear_ti_thread_flag(t, TIF_ABI_PENDING);
		if (test_ti_thread_flag(t, TIF_32BIT))
			clear_ti_thread_flag(t, TIF_32BIT);
		else
			set_ti_thread_flag(t, TIF_32BIT);
	}
#endif

	discard_lazy_cpu_state();

	if (current->thread.dabr) {
		current->thread.dabr = 0;
		set_dabr(0);
	}
}

void
release_thread(struct task_struct *t)
{
}

/*
 * This gets called before we allocate a new thread and copy
 * the current task into it.