fault.c

linux-2.4.29操作系统的源码

/*
 *  arch/s390/mm/fault.c
 *
 *  S390 version
 *    Copyright (C) 1999 IBM Deutschland Entwicklung GmbH, IBM Corporation
 *    Author(s): Hartmut Penner ([e-mail])
 *               Ulrich Weigand ([e-mail])
 *
 *  Derived from "arch/i386/mm/fault.c"
 *    Copyright (C) 1995  Linus Torvalds
 */

#include <linux/config.h>
#include <linux/signal.h>
#include <linux/sched.h>
#include <linux/kernel.h>
#include <linux/errno.h>
#include <linux/string.h>
#include <linux/types.h>
#include <linux/ptrace.h>
#include <linux/mman.h>
#include <linux/mm.h>
#include <linux/smp.h>
#include <linux/smp_lock.h>
#include <linux/compatmac.h>
#include <linux/init.h>
#include <linux/console.h>

#include <asm/system.h>
#include <asm/uaccess.h>
#include <asm/pgtable.h>
#include <asm/hardirq.h>

#ifdef CONFIG_SYSCTL
extern int sysctl_userprocess_debug;
#endif

extern void die(const char *,struct pt_regs *,long);

extern spinlock_t timerlist_lock;

/*
 * Unlock any spinlocks which will prevent us from getting the
 * message out (timerlist_lock is acquired through the
 * console unblank code)
 */
void bust_spinlocks(int yes)
{
	spin_lock_init(&timerlist_lock);
	if (yes) {
		oops_in_progress = 1;
	} else {
		int loglevel_save = console_loglevel;
		oops_in_progress = 0;
		console_unblank();
		/*
		 * OK, the message is on the console.  Now we call printk()
		 * without oops_in_progress set so that printk will give klogd
		 * a poke.  Hold onto your hats...
		 */
		console_loglevel = 15;
		printk(" ");
		console_loglevel = loglevel_save;
	}
}

/*
 * Check which address space is addressed by the access
 * register in S390_lowcore.exc_access_id.
 * Returns 1 for user space and 0 for kernel space.
 */
static int __check_access_register(struct pt_regs *regs, int error_code)
{
	int areg = S390_lowcore.exc_access_id;

	if (areg == 0)
		/* Access via access register 0 -> kernel address */
		return 0;
	if (regs && areg < NUM_ACRS && regs->acrs[areg] <= 1)
		/*
		 * access register contains 0 -> kernel address,
		 * access register contains 1 -> user space address
		 */
		return regs->acrs[areg];

	/* Something unhealthy was done with the access registers... */
	die("page fault via unknown access register", regs, error_code);
	do_exit(SIGKILL);
	return 0;
}

/*
 * Check which address space the address belongs to.
 * Returns 1 for user space and 0 for kernel space.
 */
static inline int check_user_space(struct pt_regs *regs, int error_code)
{
	/*
	 * The lowest two bits of S390_lowcore.trans_exc_code indicate
	 * which paging table was used:
	 *   0: Primary Segment Table Descriptor
	 *   1: STD determined via access register
	 *   2: Secondary Segment Table Descriptor
	 *   3: Home Segment Table Descriptor
	 */
	int descriptor = S390_lowcore.trans_exc_code & 3;
	if (descriptor == 1)
		return __check_access_register(regs, error_code);
	return descriptor >> 1;
}

/*
 * Send SIGSEGV to task.  This is an external routine
 * to keep the stack usage of do_page_fault small.
 */
static void force_sigsegv(struct pt_regs *regs, unsigned long error_code,
			  int si_code, unsigned long address)
{
	struct siginfo si;

#if defined(CONFIG_SYSCTL) || defined(CONFIG_PROCESS_DEBUG)
#if defined(CONFIG_SYSCTL)
	if (sysctl_userprocess_debug)
#endif
	{
		printk("User process fault: interruption code 0x%lX\n",
		       error_code);
		printk("failing address: %lX\n", address);
		show_regs(regs);
	}
#endif
	si.si_signo = SIGSEGV;
	si.si_code = si_code;
	si.si_addr = (void *) address;
	force_sig_info(SIGSEGV, &si, current);
}

/*
 * This routine handles page faults.  It determines the address,
 * and the problem, and then passes it off to one of the appropriate
 * routines.
 *
 * error_code:
 *   04       Protection           ->  Write-Protection  (suprression)
 *   10       Segment translation  ->  Not present       (nullification)
 *   11       Page translation     ->  Not present       (nullification)
 */
extern inline void do_exception(struct pt_regs *regs, unsigned long error_code)
{
        struct task_struct *tsk;
        struct mm_struct *mm;
        struct vm_area_struct * vma;
        unsigned long address;
	int user_address;
        unsigned long fixup;
	int si_code = SEGV_MAPERR;

        tsk = current;
        mm = tsk->mm;
	
	/* 
         * Check for low-address protection.  This needs to be treated
	 * as a special case because the translation exception code 
	 * field is not guaranteed to contain valid data in this case.
	 */
	if (error_code == 4 && !(S390_lowcore.trans_exc_code & 4)) {

		/* Low-address protection hit in kernel mode means 
		   NULL pointer write access in kernel mode.  */
 		if (!(regs->psw.mask & PSW_PROBLEM_STATE)) {
			address = 0;
			user_address = 0;
			goto no_context;
		}

		/* Low-address protection hit in user mode 'cannot happen'.  */
		die ("Low-address protection", regs, error_code);
        	do_exit(SIGKILL);
	}

        /* 
         * get the failing address 
         * more specific the segment and page table portion of 
         * the address 
         */
        address = S390_lowcore.trans_exc_code&0x7ffff000;
	user_address = check_user_space(regs, error_code);

	/*
	 * Verify that the fault happened in user space, that
	 * we are not in an interrupt and that there is a 
	 * user context.
	 */
        if (user_address == 0 || in_interrupt() || !mm)
                goto no_context;

	/*
	 * When we get here, the fault happened in the current
	 * task's user address space, so we can switch on the
	 * interrupts again and then search the VMAs
	 */
	__sti();

        down_read(&mm->mmap_sem);

        vma = find_vma(mm, address);
        if (!vma)
                goto bad_area;
        if (vma->vm_start <= address) 
                goto good_area;
        if (!(vma->vm_flags & VM_GROWSDOWN))
                goto bad_area;
        if (expand_stack(vma, address))
                goto bad_area;
/*
 * Ok, we have a good vm_area for this memory access, so
 * we can handle it..
 */
good_area:
	si_code = SEGV_ACCERR;
	if (error_code != 4) {
		/* page not present, check vm flags */
		if (!(vma->vm_flags & (VM_READ | VM_EXEC | VM_WRITE)))
			goto bad_area;
	} else {
		if (!(vma->vm_flags & VM_WRITE))
			goto bad_area;
	}

survive:
	/*
	 * If for any reason at all we couldn't handle the fault,
	 * make sure we exit gracefully rather than endlessly redo
	 * the fault.
	 */
	switch (handle_mm_fault(mm, vma, address, error_code == 4)) {
	case 1:
		tsk->min_flt++;
		break;
	case 2:
		tsk->maj_flt++;
		break;
	case 0:
		goto do_sigbus;
	default:
		goto out_of_memory;
	}

        up_read(&mm->mmap_sem);
        return;

/*
 * Something tried to access memory that isn't in our memory map..
 * Fix it, but check if it's kernel or user first..
 */
bad_area:
        up_read(&mm->mmap_sem);

        /* User mode accesses just cause a SIGSEGV */
        if (regs->psw.mask & PSW_PROBLEM_STATE) {
                tsk->thread.prot_addr = address;
                tsk->thread.trap_no = error_code;
		force_sigsegv(regs, error_code, si_code, address);
                return;
	}

no_context:
        /* Are we prepared to handle this kernel fault?  */
        if ((fixup = search_exception_table(regs->psw.addr)) != 0) {
                regs->psw.addr = fixup;
                return;
        }

/*
 * Oops. The kernel tried to access some bad page. We'll have to
 * terminate things with extreme prejudice.
 */
        if (user_address == 0)
                printk(KERN_ALERT "Unable to handle kernel pointer dereference"
        	       " at virtual kernel address %08lx\n", address);
        else
                printk(KERN_ALERT "Unable to handle kernel paging request"
		       " at virtual user address %08lx\n", address);