fault.c

linux-2.6.15.6

/*
 *  linux/arch/m32r/mm/fault.c
 *
 *  Copyright (c) 2001, 2002  Hitoshi Yamamoto, and H. Kondo
 *  Copyright (c) 2004  Naoto Sugai, NIIBE Yutaka
 *
 *  Some code taken from i386 version.
 *    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/interrupt.h>
#include <linux/init.h>
#include <linux/tty.h>
#include <linux/vt_kern.h>		/* For unblank_screen() */
#include <linux/highmem.h>
#include <linux/module.h>

#include <asm/m32r.h>
#include <asm/system.h>
#include <asm/uaccess.h>
#include <asm/hardirq.h>
#include <asm/mmu_context.h>
#include <asm/tlbflush.h>

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

#ifndef CONFIG_SMP
asmlinkage unsigned int tlb_entry_i_dat;
asmlinkage unsigned int tlb_entry_d_dat;
#define tlb_entry_i tlb_entry_i_dat
#define tlb_entry_d tlb_entry_d_dat
#else
unsigned int tlb_entry_i_dat[NR_CPUS];
unsigned int tlb_entry_d_dat[NR_CPUS];
#define tlb_entry_i tlb_entry_i_dat[smp_processor_id()]
#define tlb_entry_d tlb_entry_d_dat[smp_processor_id()]
#endif

extern void init_tlb(void);

/*
 * Unlock any spinlocks which will prevent us from getting the
 * message out
 */
void bust_spinlocks(int yes)
{
	int loglevel_save = console_loglevel;

	if (yes) {
		oops_in_progress = 1;
		return;
	}
#ifdef CONFIG_VT
	unblank_screen();
#endif
	oops_in_progress = 0;
	/*
	 * 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;		/* NMI oopser may have shut the console up */
	printk(" ");
	console_loglevel = loglevel_save;
}

/*======================================================================*
 * do_page_fault()
 *======================================================================*
 * This routine handles page faults.  It determines the address,
 * and the problem, and then passes it off to one of the appropriate
 * routines.
 *
 * ARGUMENT:
 *  regs       : M32R SP reg.
 *  error_code : See below
 *  address    : M32R MMU MDEVA reg. (Operand ACE)
 *             : M32R BPC reg. (Instruction ACE)
 *
 * error_code :
 *  bit 0 == 0 means no page found, 1 means protection fault
 *  bit 1 == 0 means read, 1 means write
 *  bit 2 == 0 means kernel, 1 means user-mode
 *  bit 3 == 0 means data, 1 means instruction
 *======================================================================*/
#define ACE_PROTECTION		1
#define ACE_WRITE		2
#define ACE_USERMODE		4
#define ACE_INSTRUCTION		8

asmlinkage void do_page_fault(struct pt_regs *regs, unsigned long error_code,
  unsigned long address)
{
	struct task_struct *tsk;
	struct mm_struct *mm;
	struct vm_area_struct * vma;
	unsigned long page, addr;
	int write;
	siginfo_t info;

	/*
	 * If BPSW IE bit enable --> set PSW IE bit
	 */
	if (regs->psw & M32R_PSW_BIE)
		local_irq_enable();

	tsk = current;

	info.si_code = SEGV_MAPERR;

	/*
	 * We fault-in kernel-space virtual memory on-demand. The
	 * 'reference' page table is init_mm.pgd.
	 *
	 * NOTE! We MUST NOT take any locks for this case. We may
	 * be in an interrupt or a critical region, and should
	 * only copy the information from the master page table,
	 * nothing more.
	 *
	 * This verifies that the fault happens in kernel space
	 * (error_code & ACE_USERMODE) == 0, and that the fault was not a
	 * protection error (error_code & ACE_PROTECTION) == 0.
	 */
	if (address >= TASK_SIZE && !(error_code & ACE_USERMODE))
		goto vmalloc_fault;

	mm = tsk->mm;

	/*
	 * If we're in an interrupt or have no user context or are running in an
	 * atomic region then we must not take the fault..
	 */
	if (in_atomic() || !mm)
		goto bad_area_nosemaphore;

	/* When running in the kernel we expect faults to occur only to
	 * addresses in user space.  All other faults represent errors in the
	 * kernel and should generate an OOPS.  Unfortunatly, in the case of an
	 * erroneous fault occuring in a code path which already holds mmap_sem
	 * we will deadlock attempting to validate the fault against the
	 * address space.  Luckily the kernel only validly references user
	 * space from well defined areas of code, which are listed in the
	 * exceptions table.
	 *
	 * As the vast majority of faults will be valid we will only perform
	 * the source reference check when there is a possibilty of a deadlock.
	 * Attempt to lock the address space, if we cannot we then validate the
	 * source.  If this is invalid we can skip the address space check,
	 * thus avoiding the deadlock.
	 */
	if (!down_read_trylock(&mm->mmap_sem)) {
		if ((error_code & ACE_USERMODE) == 0 &&
		    !search_exception_tables(regs->psw))
			goto bad_area_nosemaphore;
		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 0
	if (error_code & ACE_USERMODE) {
		/*
		 * accessing the stack below "spu" is always a bug.
		 * The "+ 4" is there due to the push instruction
		 * doing pre-decrement on the stack and that
		 * doesn't show up until later..
		 */
		if (address + 4 < regs->spu)
			goto bad_area;
	}
#endif
	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:
	info.si_code = SEGV_ACCERR;
	write = 0;
	switch (error_code & (ACE_WRITE|ACE_PROTECTION)) {
		default:	/* 3: write, present */
			/* fall through */
		case ACE_WRITE:	/* write, not present */
			if (!(vma->vm_flags & VM_WRITE))
				goto bad_area;
			write++;
			break;
		case ACE_PROTECTION:	/* read, present */
		case 0:		/* read, not present */
			if (!(vma->vm_flags & (VM_READ | VM_EXEC)))
				goto bad_area;
	}

	/*
	 * For instruction access exception, check if the area is executable
	 */
	if ((error_code & ACE_INSTRUCTION) && !(vma->vm_flags & VM_EXEC))
	  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.
	 */
	addr = (address & PAGE_MASK);
	set_thread_fault_code(error_code);
	switch (handle_mm_fault(mm, vma, addr, write)) {
		case VM_FAULT_MINOR:
			tsk->min_flt++;
			break;
		case VM_FAULT_MAJOR:
			tsk->maj_flt++;
			break;
		case VM_FAULT_SIGBUS:
			goto do_sigbus;
		case VM_FAULT_OOM:
			goto out_of_memory;
		default:
			BUG();
	}
	set_thread_fault_code(0);
	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);

bad_area_nosemaphore:
	/* User mode accesses just cause a SIGSEGV */
	if (error_code & ACE_USERMODE) {
		tsk->thread.address = address;
		tsk->thread.error_code = error_code | (address >= TASK_SIZE);
		tsk->thread.trap_no = 14;
		info.si_signo = SIGSEGV;
		info.si_errno = 0;
		/* info.si_code has been set above */
		info.si_addr = (void __user *)address;
		force_sig_info(SIGSEGV, &info, tsk);
		return;
	}

no_context:
	/* Are we prepared to handle this kernel fault?  */
	if (fixup_exception(regs))
		return;

/*
 * Oops. The kernel tried to access some bad page. We'll have to
 * terminate things with extreme prejudice.
 */

	bust_spinlocks(1);

	if (address < PAGE_SIZE)
		printk(KERN_ALERT "Unable to handle kernel NULL pointer dereference");
	else
		printk(KERN_ALERT "Unable to handle kernel paging request");
	printk(" at virtual address %08lx\n",address);
	printk(KERN_ALERT " printing bpc:\n");
	printk("%08lx\n", regs->bpc);
	page = *(unsigned long *)MPTB;
	page = ((unsigned long *) page)[address >> PGDIR_SHIFT];
	printk(KERN_ALERT "*pde = %08lx\n", page);
	if (page & _PAGE_PRESENT) {
		page &= PAGE_MASK;
		address &= 0x003ff000;
		page = ((unsigned long *) __va(page))[address >> PAGE_SHIFT];
		printk(KERN_ALERT "*pte = %08lx\n", page);
	}