mem.c

来自「linux 内核源代码」· C语言 代码 · 共 915 行 · 第 1/2 页

/*
 *  linux/drivers/char/mem.c
 *
 *  Copyright (C) 1991, 1992  Linus Torvalds
 *
 *  Added devfs support. 
 *    Jan-11-1998, C. Scott Ananian <[e-mail]>
 *  Shared /dev/zero mmaping support, Feb 2000, Kanoj Sarcar <[e-mail]>
 */

#include <linux/mm.h>
#include <linux/miscdevice.h>
#include <linux/slab.h>
#include <linux/vmalloc.h>
#include <linux/mman.h>
#include <linux/random.h>
#include <linux/init.h>
#include <linux/raw.h>
#include <linux/tty.h>
#include <linux/capability.h>
#include <linux/ptrace.h>
#include <linux/device.h>
#include <linux/highmem.h>
#include <linux/crash_dump.h>
#include <linux/backing-dev.h>
#include <linux/bootmem.h>
#include <linux/splice.h>
#include <linux/pfn.h>

#include <asm/uaccess.h>
#include <asm/io.h>

#ifdef CONFIG_IA64
# include <linux/efi.h>
#endif

/*
 * Architectures vary in how they handle caching for addresses
 * outside of main memory.
 *
 */
static inline int uncached_access(struct file *file, unsigned long addr)
{
#if defined(__i386__) && !defined(__arch_um__)
	/*
	 * On the PPro and successors, the MTRRs are used to set
	 * memory types for physical addresses outside main memory,
	 * so blindly setting PCD or PWT on those pages is wrong.
	 * For Pentiums and earlier, the surround logic should disable
	 * caching for the high addresses through the KEN pin, but
	 * we maintain the tradition of paranoia in this code.
	 */
	if (file->f_flags & O_SYNC)
		return 1;
 	return !( test_bit(X86_FEATURE_MTRR, boot_cpu_data.x86_capability) ||
		  test_bit(X86_FEATURE_K6_MTRR, boot_cpu_data.x86_capability) ||
		  test_bit(X86_FEATURE_CYRIX_ARR, boot_cpu_data.x86_capability) ||
		  test_bit(X86_FEATURE_CENTAUR_MCR, boot_cpu_data.x86_capability) )
	  && addr >= __pa(high_memory);
#elif defined(__x86_64__) && !defined(__arch_um__)
	/* 
	 * This is broken because it can generate memory type aliases,
	 * which can cause cache corruptions
	 * But it is only available for root and we have to be bug-to-bug
	 * compatible with i386.
	 */
	if (file->f_flags & O_SYNC)
		return 1;
	/* same behaviour as i386. PAT always set to cached and MTRRs control the
	   caching behaviour. 
	   Hopefully a full PAT implementation will fix that soon. */	   
	return 0;
#elif defined(CONFIG_IA64)
	/*
	 * On ia64, we ignore O_SYNC because we cannot tolerate memory attribute aliases.
	 */
	return !(efi_mem_attributes(addr) & EFI_MEMORY_WB);
#elif defined(CONFIG_MIPS)
	{
		extern int __uncached_access(struct file *file,
					     unsigned long addr);

		return __uncached_access(file, addr);
	}
#else
	/*
	 * Accessing memory above the top the kernel knows about or through a file pointer
	 * that was marked O_SYNC will be done non-cached.
	 */
	if (file->f_flags & O_SYNC)
		return 1;
	return addr >= __pa(high_memory);
#endif
}

#ifndef ARCH_HAS_VALID_PHYS_ADDR_RANGE
static inline int valid_phys_addr_range(unsigned long addr, size_t count)
{
	if (addr + count > __pa(high_memory))
		return 0;

	return 1;
}

static inline int valid_mmap_phys_addr_range(unsigned long pfn, size_t size)
{
	return 1;
}
#endif

/*
 * This funcion reads the *physical* memory. The f_pos points directly to the 
 * memory location. 
 */
static ssize_t read_mem(struct file * file, char __user * buf,
			size_t count, loff_t *ppos)
{
	unsigned long p = *ppos;
	ssize_t read, sz;
	char *ptr;

	if (!valid_phys_addr_range(p, count))
		return -EFAULT;
	read = 0;
#ifdef __ARCH_HAS_NO_PAGE_ZERO_MAPPED
	/* we don't have page 0 mapped on sparc and m68k.. */
	if (p < PAGE_SIZE) {
		sz = PAGE_SIZE - p;
		if (sz > count) 
			sz = count; 
		if (sz > 0) {
			if (clear_user(buf, sz))
				return -EFAULT;
			buf += sz; 
			p += sz; 
			count -= sz; 
			read += sz; 
		}
	}
#endif

	while (count > 0) {
		/*
		 * Handle first page in case it's not aligned
		 */
		if (-p & (PAGE_SIZE - 1))
			sz = -p & (PAGE_SIZE - 1);
		else
			sz = PAGE_SIZE;

		sz = min_t(unsigned long, sz, count);

		/*
		 * On ia64 if a page has been mapped somewhere as
		 * uncached, then it must also be accessed uncached
		 * by the kernel or data corruption may occur
		 */
		ptr = xlate_dev_mem_ptr(p);

		if (copy_to_user(buf, ptr, sz))
			return -EFAULT;
		buf += sz;
		p += sz;
		count -= sz;
		read += sz;
	}

	*ppos += read;
	return read;
}

static ssize_t write_mem(struct file * file, const char __user * buf, 
			 size_t count, loff_t *ppos)
{
	unsigned long p = *ppos;
	ssize_t written, sz;
	unsigned long copied;
	void *ptr;

	if (!valid_phys_addr_range(p, count))
		return -EFAULT;

	written = 0;

#ifdef __ARCH_HAS_NO_PAGE_ZERO_MAPPED
	/* we don't have page 0 mapped on sparc and m68k.. */
	if (p < PAGE_SIZE) {
		unsigned long sz = PAGE_SIZE - p;
		if (sz > count)
			sz = count;
		/* Hmm. Do something? */
		buf += sz;
		p += sz;
		count -= sz;
		written += sz;
	}
#endif

	while (count > 0) {
		/*
		 * Handle first page in case it's not aligned
		 */
		if (-p & (PAGE_SIZE - 1))
			sz = -p & (PAGE_SIZE - 1);
		else
			sz = PAGE_SIZE;

		sz = min_t(unsigned long, sz, count);

		/*
		 * On ia64 if a page has been mapped somewhere as
		 * uncached, then it must also be accessed uncached
		 * by the kernel or data corruption may occur
		 */
		ptr = xlate_dev_mem_ptr(p);

		copied = copy_from_user(ptr, buf, sz);
		if (copied) {
			written += sz - copied;
			if (written)
				break;
			return -EFAULT;
		}
		buf += sz;
		p += sz;
		count -= sz;
		written += sz;
	}

	*ppos += written;
	return written;
}

#ifndef __HAVE_PHYS_MEM_ACCESS_PROT
static pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn,
				     unsigned long size, pgprot_t vma_prot)
{
#ifdef pgprot_noncached
	unsigned long offset = pfn << PAGE_SHIFT;

	if (uncached_access(file, offset))
		return pgprot_noncached(vma_prot);
#endif
	return vma_prot;
}
#endif

#ifndef CONFIG_MMU
static unsigned long get_unmapped_area_mem(struct file *file,
					   unsigned long addr,
					   unsigned long len,
					   unsigned long pgoff,
					   unsigned long flags)
{
	if (!valid_mmap_phys_addr_range(pgoff, len))
		return (unsigned long) -EINVAL;
	return pgoff << PAGE_SHIFT;
}

/* can't do an in-place private mapping if there's no MMU */
static inline int private_mapping_ok(struct vm_area_struct *vma)
{
	return vma->vm_flags & VM_MAYSHARE;
}
#else
#define get_unmapped_area_mem	NULL

static inline int private_mapping_ok(struct vm_area_struct *vma)
{
	return 1;
}
#endif

static int mmap_mem(struct file * file, struct vm_area_struct * vma)
{
	size_t size = vma->vm_end - vma->vm_start;

	if (!valid_mmap_phys_addr_range(vma->vm_pgoff, size))
		return -EINVAL;

	if (!private_mapping_ok(vma))
		return -ENOSYS;

	vma->vm_page_prot = phys_mem_access_prot(file, vma->vm_pgoff,
						 size,
						 vma->vm_page_prot);

	/* Remap-pfn-range will mark the range VM_IO and VM_RESERVED */
	if (remap_pfn_range(vma,
			    vma->vm_start,
			    vma->vm_pgoff,
			    size,
			    vma->vm_page_prot))
		return -EAGAIN;
	return 0;
}

static int mmap_kmem(struct file * file, struct vm_area_struct * vma)
{
	unsigned long pfn;

	/* Turn a kernel-virtual address into a physical page frame */
	pfn = __pa((u64)vma->vm_pgoff << PAGE_SHIFT) >> PAGE_SHIFT;

	/*
	 * RED-PEN: on some architectures there is more mapped memory
	 * than available in mem_map which pfn_valid checks
	 * for. Perhaps should add a new macro here.
	 *
	 * RED-PEN: vmalloc is not supported right now.
	 */
	if (!pfn_valid(pfn))
		return -EIO;

	vma->vm_pgoff = pfn;
	return mmap_mem(file, vma);
}

#ifdef CONFIG_CRASH_DUMP
/*
 * Read memory corresponding to the old kernel.
 */
static ssize_t read_oldmem(struct file *file, char __user *buf,
				size_t count, loff_t *ppos)
{
	unsigned long pfn, offset;
	size_t read = 0, csize;
	int rc = 0;

	while (count) {
		pfn = *ppos / PAGE_SIZE;
		if (pfn > saved_max_pfn)
			return read;

		offset = (unsigned long)(*ppos % PAGE_SIZE);
		if (count > PAGE_SIZE - offset)
			csize = PAGE_SIZE - offset;
		else
			csize = count;

		rc = copy_oldmem_page(pfn, buf, csize, offset, 1);
		if (rc < 0)
			return rc;
		buf += csize;
		*ppos += csize;
		read += csize;
		count -= csize;
	}
	return read;
}
#endif

extern long vread(char *buf, char *addr, unsigned long count);
extern long vwrite(char *buf, char *addr, unsigned long count);

/*
 * This function reads the *virtual* memory as seen by the kernel.
 */
static ssize_t read_kmem(struct file *file, char __user *buf, 
			 size_t count, loff_t *ppos)
{
	unsigned long p = *ppos;
	ssize_t low_count, read, sz;
	char * kbuf; /* k-addr because vread() takes vmlist_lock rwlock */

	read = 0;
	if (p < (unsigned long) high_memory) {
		low_count = count;
		if (count > (unsigned long) high_memory - p)
			low_count = (unsigned long) high_memory - p;

#ifdef __ARCH_HAS_NO_PAGE_ZERO_MAPPED
		/* we don't have page 0 mapped on sparc and m68k.. */
		if (p < PAGE_SIZE && low_count > 0) {
			size_t tmp = PAGE_SIZE - p;
			if (tmp > low_count) tmp = low_count;
			if (clear_user(buf, tmp))
				return -EFAULT;
			buf += tmp;
			p += tmp;
			read += tmp;
			low_count -= tmp;
			count -= tmp;
		}
#endif
		while (low_count > 0) {
			/*
			 * Handle first page in case it's not aligned
			 */
			if (-p & (PAGE_SIZE - 1))
				sz = -p & (PAGE_SIZE - 1);
			else
				sz = PAGE_SIZE;

			sz = min_t(unsigned long, sz, low_count);

			/*
			 * On ia64 if a page has been mapped somewhere as
			 * uncached, then it must also be accessed uncached
			 * by the kernel or data corruption may occur
			 */
			kbuf = xlate_dev_kmem_ptr((char *)p);

			if (copy_to_user(buf, kbuf, sz))
				return -EFAULT;
			buf += sz;
			p += sz;
			read += sz;
			low_count -= sz;
			count -= sz;
		}
	}

	if (count > 0) {
		kbuf = (char *)__get_free_page(GFP_KERNEL);
		if (!kbuf)
			return -ENOMEM;
		while (count > 0) {
			int len = count;

			if (len > PAGE_SIZE)
				len = PAGE_SIZE;
			len = vread(kbuf, (char *)p, len);
			if (!len)
				break;
			if (copy_to_user(buf, kbuf, len)) {
				free_page((unsigned long)kbuf);
				return -EFAULT;
			}
			count -= len;
			buf += len;
			read += len;
			p += len;
		}
		free_page((unsigned long)kbuf);
	}
 	*ppos = p;
 	return read;
}


static inline ssize_t
do_write_kmem(void *p, unsigned long realp, const char __user * buf,
	      size_t count, loff_t *ppos)
{
	ssize_t written, sz;
	unsigned long copied;

	written = 0;
#ifdef __ARCH_HAS_NO_PAGE_ZERO_MAPPED
	/* we don't have page 0 mapped on sparc and m68k.. */
	if (realp < PAGE_SIZE) {
		unsigned long sz = PAGE_SIZE - realp;
		if (sz > count)
			sz = count;
		/* Hmm. Do something? */
		buf += sz;
		p += sz;