Linux 存储管理 缺页中断和页面换入

          磁盘中的可执行可执行文件映像（image）一旦初映射到一个进程的虚拟空间，就可以开始执行。由于只有该映像区的开始部分调入内存。因此迟早会执行到那些尚未调入内存的代码。当一个进程访问了一个还没有有效页表项的虚拟地址时（即页表项的P位为0），处理器将产生缺页中断，通知通知操作系统。并将出现缺页的虚拟地址（在CR2寄存器中）和缺页时访问虚存的模式一并传递给Linux的缺页中断服务程序。

          系统初始化时，设定了缺页中断服务程序为do_page_fault():

ENTRY(page_fault)
	pushl $ SYMBOL_NAME(do_page_fault)
	jmp error_code

void __init trap_init(void)
{
#ifdef CONFIG_EISA
	if (isa_readl(0x0FFFD9) == 'E'+('I'<<8)+('S'<<16)+('A'<<24))
		EISA_bus = 1;
#endif

	set_trap_gate(0,÷_error);
	set_trap_gate(1,&debug);
	set_intr_gate(2,&nmi);
	set_system_gate(3,&int3);	/* int3-5 can be called from all */
	set_system_gate(4,&overflow);
	set_system_gate(5,&bounds);
	set_trap_gate(6,&invalid_op);
	set_trap_gate(7,&device_not_available);
	set_trap_gate(8,&double_fault);
	set_trap_gate(9,&coprocessor_segment_overrun);
	set_trap_gate(10,&invalid_TSS);
	set_trap_gate(11,&segment_not_present);
	set_trap_gate(12,&stack_segment);
	set_trap_gate(13,&general_protection);
	set_trap_gate(14,&page_fault);
	set_trap_gate(15,&spurious_interrupt_bug);
	set_trap_gate(16,&coprocessor_error);
	set_trap_gate(17,&alignment_check);
	set_trap_gate(18,&machine_check);
	set_trap_gate(19,&simd_coprocessor_error);

       根据控制寄存器CR2传递的缺页地址，Linux 必须找到用来表示出现缺页的虚拟存储区的vm_area_struct 结构。 搜索进程的vm_area_struct结构时，对搜索时间有严格的限制。为了有效的处理搜索工作，Linux将所有的vm_area_struct 结构通过AVL(Adelson-Velskii and Landis)平衡树连接起来。如果没有找到与缺页相应的vm_area_struct 结构，那么说明进程访问了一个非法存储区，Linux向进程发送信号SIGSEGV. 如果进程没有处理该信号的函数，该进程将被终止。

  

      Linux 接着检测缺页时的访问模式是否合法。如果进程对该页的访问超越权限，例如试图对只允许读操作的而面进行写操作，系统也将向进程发送一个信号，通知进程的存储访问出错。

     经过以上两步检查，可以确定的确是正常的缺页中断。

     Linux 还区分产生缺页中断的页面是在交换空间，还是在磁盘中作为某一可执行文件映像的一部分，进而作出不同的处理。

     这一点通过页表项中的位来区分。如果该页面所对应的页表项是无效的（P=0), 但是非空，说明缺页在交换空间中。否则，页面是某可一执行文件映像的一部分。

      并不是所有的vm_area_struct 结构变量都有完整的一套虚拟存储操作，有些甚至没有nopage操作函数指针。在这种情况下，LInux将使用缺省的操作函数为该虚拟页面找到一物理页帧，同时为其设置一页表项。如果vm_area_struct 结构变量中有nopage 操作函数的话，Linux使用该操作函数。

      Linux 的nopage 函数通常用来调入已被存储映谢的可执行磁盘映像，而且它是利用页面缓存区来将所需映像页调入内存的。

       下面从缺页中断服务入口程序do_page_fault(arch/i386/mm/fault.c) 开始具体分析内核的缺页处理机制：

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

	/* get the address */
	__asm__("movl %%cr2,%0":"=r" (address));

	tsk = current;

	/*
	 * 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.
	 */
	if (address >= TASK_SIZE)
		goto vmalloc_fault;

	mm = tsk->mm;
	info.si_code = SEGV_MAPERR;

	/*
	 * If we're in an interrupt or have no user
	 * context, we must not take the fault..
	 */
	if (in_interrupt() || !mm)
		goto no_context;

	down(&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 (error_code & 4) {
		/*
		 * accessing the stack below %esp is always a bug.
		 * The "+ 32" is there due to some instructions (like
		 * pusha) doing post-decrement on the stack and that
		 * doesn't show up until later..
		 */
		if (address + 32 < regs->esp)
			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:
	info.si_code = SEGV_ACCERR;
	write = 0;
	switch (error_code & 3) {
		default:	/* 3: write, present */
#ifdef TEST_VERIFY_AREA
			if (regs->cs == KERNEL_CS)
				printk("WP fault at %08lx\n", regs->eip);
#endif
			/* fall through */
		case 2:		/* write, not present */
			if (!(vma->vm_flags & VM_WRITE))
				goto bad_area;
			write++;
			break;
		case 1:		/* read, present */
			goto bad_area;
		case 0:		/* read, not present */
			if (!(vma->vm_flags & (VM_READ | VM_EXEC)))
				goto bad_area;
	}

	/*
	 * 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, write)) {
	case 1:
		tsk->min_flt++;
		break;
	case 2:
		tsk->maj_flt++;
		break;
	case 0:
		goto do_sigbus;
	default:
		goto out_of_memory;
	}

	/*
	 * Did it hit the DOS screen memory VA from vm86 mode?
	 */
	if (regs->eflags & VM_MASK) {
		unsigned long bit = (address - 0xA0000) >> PAGE_SHIFT;
		if (bit < 32)
			tsk->thread.screen_bitmap |= 1 << bit;
	}
	up(&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(&mm->mmap_sem);

bad_area_nosemaphore:
	/* User mode accesses just cause a SIGSEGV */
	if (error_code & 4) {
		tsk->thread.cr2 = address;
		tsk->thread.error_code = error_code;
		tsk->thread.trap_no = 14;
		info.si_signo = SIGSEGV;
		info.si_errno = 0;
		/* info.si_code has been set above */
		info.si_addr = (void *)address;
		force_sig_info(SIGSEGV, &info, tsk);
		return;
	}

	/*
	 * Pentium F0 0F C7 C8 bug workaround.
	 */
	if (boot_cpu_data.f00f_bug) {
		unsigned long nr;
		
		nr = (address - idt) >> 3;

		if (nr == 6) {
			do_invalid_op(regs, 0);
			return;
		}
	}

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

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

	bust_spinlocks();

	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(" printing eip:\n");
	printk("%08lx\n", regs->eip);
	asm("movl %%cr3,%0":"=r" (page));
	page = ((unsigned long *) __va(page))[address >> 22];
	printk(KERN_ALERT "*pde = %08lx\n", page);
	if (page & 1) {
		page &= PAGE_MASK;
		address &= 0x003ff000;
		page = ((unsigned long *) __va(page))[address >> PAGE_SHIFT];
		printk(KERN_ALERT "*pte = %08lx\n", page);
	}
	die("Oops", regs, error_code);
	do_exit(SIGKILL);

/*
 * We ran out of memory, or some other thing happened to us that made
 * us unable to handle the page fault gracefully.
 */
out_of_memory:
	up(&mm->mmap_sem);
	printk("VM: killing process %s\n", tsk->comm);
	if (error_code & 4)
		do_exit(SIGKILL);
	goto no_context;

do_sigbus:
	up(&mm->mmap_sem);

	/*
	 * Send a sigbus, regardless of whether we were in kernel
	 * or user mode.
	 */
	tsk->thread.cr2 = address;
	tsk->thread.error_code = error_code;
	tsk->thread.trap_no = 14;
	info.si_code = SIGBUS;
	info.si_errno = 0;
	info.si_code = BUS_ADRERR;
	info.si_addr = (void *)address;
	force_sig_info(SIGBUS, &info, tsk);

	/* Kernel mode? Handle exceptions or die */
	if (!(error_code & 4))
		goto no_context;
	return;

vmalloc_fault:
	{
		/*
		 * Synchronize this task's top level page-table
		 * with the 'reference' page table.
		 */
		int offset = __pgd_offset(address);
		pgd_t *pgd, *pgd_k;
		pmd_t *pmd, *pmd_k;

		pgd = tsk->active_mm->pgd + offset;
		pgd_k = init_mm.pgd + offset;

		if (!pgd_present(*pgd)) {
			if (!pgd_present(*pgd_k))
				goto bad_area_nosemaphore;
			set_pgd(pgd, *pgd_k);
			return;
		}

		pmd = pmd_offset(pgd, address);
		pmd_k = pmd_offset(pgd_k, address);

		if (pmd_present(*pmd) || !pmd_present(*pmd_k))
			goto bad_area_nosemaphore;
		set_pmd(pmd, *pmd_k);
		return;
	}
}