mem.c 21.8 KB
Newer Older
L
Linus Torvalds 已提交
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23
/*
 *  linux/drivers/char/mem.c
 *
 *  Copyright (C) 1991, 1992  Linus Torvalds
 *
 *  Added devfs support. 
 *    Jan-11-1998, C. Scott Ananian <cananian@alumni.princeton.edu>
 *  Shared /dev/zero mmaping support, Feb 2000, Kanoj Sarcar <kanoj@sgi.com>
 */

#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/smp_lock.h>
#include <linux/ptrace.h>
#include <linux/device.h>
24 25
#include <linux/highmem.h>
#include <linux/crash_dump.h>
L
Linus Torvalds 已提交
26
#include <linux/backing-dev.h>
27
#include <linux/bootmem.h>
28
#include <linux/pipe_fs_i.h>
29
#include <linux/pfn.h>
L
Linus Torvalds 已提交
30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90

#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__)
	/*
	 * 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__)
	/* 
	 * 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);
#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
91
static inline int valid_phys_addr_range(unsigned long addr, size_t count)
L
Linus Torvalds 已提交
92
{
93
	if (addr + count > __pa(high_memory))
L
Linus Torvalds 已提交
94 95 96 97
		return 0;

	return 1;
}
98

99
static inline int valid_mmap_phys_addr_range(unsigned long pfn, size_t size)
100 101 102
{
	return 1;
}
L
Linus Torvalds 已提交
103 104 105 106 107 108 109 110 111 112 113 114 115
#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;

116
	if (!valid_phys_addr_range(p, count))
L
Linus Torvalds 已提交
117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173
		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;

174
	if (!valid_phys_addr_range(p, count))
L
Linus Torvalds 已提交
175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212
		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) {
213 214 215
			written += sz - copied;
			if (written)
				break;
L
Linus Torvalds 已提交
216 217 218 219 220 221 222 223 224 225 226 227
			return -EFAULT;
		}
		buf += sz;
		p += sz;
		count -= sz;
		written += sz;
	}

	*ppos += written;
	return written;
}

228 229 230 231 232 233 234 235 236 237 238 239 240 241
#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

242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267
#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;
}

/* 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

L
Linus Torvalds 已提交
268 269
static int mmap_mem(struct file * file, struct vm_area_struct * vma)
{
270 271
	size_t size = vma->vm_end - vma->vm_start;

272
	if (!valid_mmap_phys_addr_range(vma->vm_pgoff, size))
273 274
		return -EINVAL;

275 276 277
	if (!private_mapping_ok(vma))
		return -ENOSYS;

278
	vma->vm_page_prot = phys_mem_access_prot(file, vma->vm_pgoff,
279
						 size,
L
Linus Torvalds 已提交
280 281 282 283 284 285
						 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,
286
			    size,
L
Linus Torvalds 已提交
287 288 289 290 291 292 293
			    vma->vm_page_prot))
		return -EAGAIN;
	return 0;
}

static int mmap_kmem(struct file * file, struct vm_area_struct * vma)
{
L
Linus Torvalds 已提交
294 295
	unsigned long pfn;

F
Franck Bui-Huu 已提交
296 297
	/* Turn a pfn offset into an absolute pfn */
	pfn = PFN_DOWN(virt_to_phys((void *)PAGE_OFFSET)) + vma->vm_pgoff;
L
Linus Torvalds 已提交
298

L
Linus Torvalds 已提交
299 300 301 302 303 304 305
	/*
	 * 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.
	 */
L
Linus Torvalds 已提交
306
	if (!pfn_valid(pfn))
L
Linus Torvalds 已提交
307
		return -EIO;
L
Linus Torvalds 已提交
308 309

	vma->vm_pgoff = pfn;
L
Linus Torvalds 已提交
310 311 312
	return mmap_mem(file, vma);
}

313 314 315 316
#ifdef CONFIG_CRASH_DUMP
/*
 * Read memory corresponding to the old kernel.
 */
317
static ssize_t read_oldmem(struct file *file, char __user *buf,
318 319
				size_t count, loff_t *ppos)
{
320 321 322
	unsigned long pfn, offset;
	size_t read = 0, csize;
	int rc = 0;
323

M
Maneesh Soni 已提交
324
	while (count) {
325
		pfn = *ppos / PAGE_SIZE;
326 327
		if (pfn > saved_max_pfn)
			return read;
328

329 330 331 332 333
		offset = (unsigned long)(*ppos % PAGE_SIZE);
		if (count > PAGE_SIZE - offset)
			csize = PAGE_SIZE - offset;
		else
			csize = count;
334

335 336 337
		rc = copy_oldmem_page(pfn, buf, csize, offset, 1);
		if (rc < 0)
			return rc;
338 339 340 341 342 343 344 345 346
		buf += csize;
		*ppos += csize;
		read += csize;
		count -= csize;
	}
	return read;
}
#endif

L
Linus Torvalds 已提交
347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479
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;
		realp += sz;
		count -= sz;
		written += sz;
	}
#endif

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

		copied = copy_from_user(ptr, buf, sz);
		if (copied) {
480 481 482
			written += sz - copied;
			if (written)
				break;
L
Linus Torvalds 已提交
483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535
			return -EFAULT;
		}
		buf += sz;
		p += sz;
		realp += sz;
		count -= sz;
		written += sz;
	}

	*ppos += written;
	return written;
}


/*
 * This function writes to the *virtual* memory as seen by the kernel.
 */
static ssize_t write_kmem(struct file * file, const char __user * buf, 
			  size_t count, loff_t *ppos)
{
	unsigned long p = *ppos;
	ssize_t wrote = 0;
	ssize_t virtr = 0;
	ssize_t written;
	char * kbuf; /* k-addr because vwrite() takes vmlist_lock rwlock */

	if (p < (unsigned long) high_memory) {

		wrote = count;
		if (count > (unsigned long) high_memory - p)
			wrote = (unsigned long) high_memory - p;

		written = do_write_kmem((void*)p, p, buf, wrote, ppos);
		if (written != wrote)
			return written;
		wrote = written;
		p += wrote;
		buf += wrote;
		count -= wrote;
	}

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

			if (len > PAGE_SIZE)
				len = PAGE_SIZE;
			if (len) {
				written = copy_from_user(kbuf, buf, len);
				if (written) {
536 537
					if (wrote + virtr)
						break;
L
Linus Torvalds 已提交
538
					free_page((unsigned long)kbuf);
539
					return -EFAULT;
L
Linus Torvalds 已提交
540 541 542 543 544 545 546 547 548 549 550 551 552 553 554
				}
			}
			len = vwrite(kbuf, (char *)p, len);
			count -= len;
			buf += len;
			virtr += len;
			p += len;
		}
		free_page((unsigned long)kbuf);
	}

 	*ppos = p;
 	return virtr + wrote;
}

555
#if (defined(CONFIG_ISA) || defined(CONFIG_PCI)) && !defined(__mc68000__)
L
Linus Torvalds 已提交
556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583
static ssize_t read_port(struct file * file, char __user * buf,
			 size_t count, loff_t *ppos)
{
	unsigned long i = *ppos;
	char __user *tmp = buf;

	if (!access_ok(VERIFY_WRITE, buf, count))
		return -EFAULT; 
	while (count-- > 0 && i < 65536) {
		if (__put_user(inb(i),tmp) < 0) 
			return -EFAULT;  
		i++;
		tmp++;
	}
	*ppos = i;
	return tmp-buf;
}

static ssize_t write_port(struct file * file, const char __user * buf,
			  size_t count, loff_t *ppos)
{
	unsigned long i = *ppos;
	const char __user * tmp = buf;

	if (!access_ok(VERIFY_READ,buf,count))
		return -EFAULT;
	while (count-- > 0 && i < 65536) {
		char c;
584 585 586
		if (__get_user(c, tmp)) {
			if (tmp > buf)
				break;
L
Linus Torvalds 已提交
587
			return -EFAULT; 
588
		}
L
Linus Torvalds 已提交
589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609
		outb(c,i);
		i++;
		tmp++;
	}
	*ppos = i;
	return tmp-buf;
}
#endif

static ssize_t read_null(struct file * file, char __user * buf,
			 size_t count, loff_t *ppos)
{
	return 0;
}

static ssize_t write_null(struct file * file, const char __user * buf,
			  size_t count, loff_t *ppos)
{
	return count;
}

610 611 612 613 614 615 616 617 618 619 620 621
static int pipe_to_null(struct pipe_inode_info *info, struct pipe_buffer *buf,
			struct splice_desc *sd)
{
	return sd->len;
}

static ssize_t splice_write_null(struct pipe_inode_info *pipe,struct file *out,
				 loff_t *ppos, size_t len, unsigned int flags)
{
	return splice_from_pipe(pipe, out, ppos, len, flags, pipe_to_null);
}

L
Linus Torvalds 已提交
622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641
#ifdef CONFIG_MMU
/*
 * For fun, we are using the MMU for this.
 */
static inline size_t read_zero_pagealigned(char __user * buf, size_t size)
{
	struct mm_struct *mm;
	struct vm_area_struct * vma;
	unsigned long addr=(unsigned long)buf;

	mm = current->mm;
	/* Oops, this was forgotten before. -ben */
	down_read(&mm->mmap_sem);

	/* For private mappings, just map in zero pages. */
	for (vma = find_vma(mm, addr); vma; vma = vma->vm_next) {
		unsigned long count;

		if (vma->vm_start > addr || (vma->vm_flags & VM_WRITE) == 0)
			goto out_up;
642
		if (vma->vm_flags & (VM_SHARED | VM_HUGETLB))
L
Linus Torvalds 已提交
643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776
			break;
		count = vma->vm_end - addr;
		if (count > size)
			count = size;

		zap_page_range(vma, addr, count, NULL);
        	zeromap_page_range(vma, addr, count, PAGE_COPY);

		size -= count;
		buf += count;
		addr += count;
		if (size == 0)
			goto out_up;
	}

	up_read(&mm->mmap_sem);
	
	/* The shared case is hard. Let's do the conventional zeroing. */ 
	do {
		unsigned long unwritten = clear_user(buf, PAGE_SIZE);
		if (unwritten)
			return size + unwritten - PAGE_SIZE;
		cond_resched();
		buf += PAGE_SIZE;
		size -= PAGE_SIZE;
	} while (size);

	return size;
out_up:
	up_read(&mm->mmap_sem);
	return size;
}

static ssize_t read_zero(struct file * file, char __user * buf, 
			 size_t count, loff_t *ppos)
{
	unsigned long left, unwritten, written = 0;

	if (!count)
		return 0;

	if (!access_ok(VERIFY_WRITE, buf, count))
		return -EFAULT;

	left = count;

	/* do we want to be clever? Arbitrary cut-off */
	if (count >= PAGE_SIZE*4) {
		unsigned long partial;

		/* How much left of the page? */
		partial = (PAGE_SIZE-1) & -(unsigned long) buf;
		unwritten = clear_user(buf, partial);
		written = partial - unwritten;
		if (unwritten)
			goto out;
		left -= partial;
		buf += partial;
		unwritten = read_zero_pagealigned(buf, left & PAGE_MASK);
		written += (left & PAGE_MASK) - unwritten;
		if (unwritten)
			goto out;
		buf += left & PAGE_MASK;
		left &= ~PAGE_MASK;
	}
	unwritten = clear_user(buf, left);
	written += left - unwritten;
out:
	return written ? written : -EFAULT;
}

static int mmap_zero(struct file * file, struct vm_area_struct * vma)
{
	if (vma->vm_flags & VM_SHARED)
		return shmem_zero_setup(vma);
	if (zeromap_page_range(vma, vma->vm_start, vma->vm_end - vma->vm_start, vma->vm_page_prot))
		return -EAGAIN;
	return 0;
}
#else /* CONFIG_MMU */
static ssize_t read_zero(struct file * file, char * buf, 
			 size_t count, loff_t *ppos)
{
	size_t todo = count;

	while (todo) {
		size_t chunk = todo;

		if (chunk > 4096)
			chunk = 4096;	/* Just for latency reasons */
		if (clear_user(buf, chunk))
			return -EFAULT;
		buf += chunk;
		todo -= chunk;
		cond_resched();
	}
	return count;
}

static int mmap_zero(struct file * file, struct vm_area_struct * vma)
{
	return -ENOSYS;
}
#endif /* CONFIG_MMU */

static ssize_t write_full(struct file * file, const char __user * buf,
			  size_t count, loff_t *ppos)
{
	return -ENOSPC;
}

/*
 * Special lseek() function for /dev/null and /dev/zero.  Most notably, you
 * can fopen() both devices with "a" now.  This was previously impossible.
 * -- SRB.
 */

static loff_t null_lseek(struct file * file, loff_t offset, int orig)
{
	return file->f_pos = 0;
}

/*
 * The memory devices use the full 32/64 bits of the offset, and so we cannot
 * check against negative addresses: they are ok. The return value is weird,
 * though, in that case (0).
 *
 * also note that seeking relative to the "end of file" isn't supported:
 * it has no meaning, so it returns -EINVAL.
 */
static loff_t memory_lseek(struct file * file, loff_t offset, int orig)
{
	loff_t ret;

777
	mutex_lock(&file->f_dentry->d_inode->i_mutex);
L
Linus Torvalds 已提交
778 779 780 781 782 783 784 785 786 787 788 789 790 791
	switch (orig) {
		case 0:
			file->f_pos = offset;
			ret = file->f_pos;
			force_successful_syscall_return();
			break;
		case 1:
			file->f_pos += offset;
			ret = file->f_pos;
			force_successful_syscall_return();
			break;
		default:
			ret = -EINVAL;
	}
792
	mutex_unlock(&file->f_dentry->d_inode->i_mutex);
L
Linus Torvalds 已提交
793 794 795 796 797 798 799 800 801 802 803 804 805 806
	return ret;
}

static int open_port(struct inode * inode, struct file * filp)
{
	return capable(CAP_SYS_RAWIO) ? 0 : -EPERM;
}

#define zero_lseek	null_lseek
#define full_lseek      null_lseek
#define write_zero	write_null
#define read_full       read_zero
#define open_mem	open_port
#define open_kmem	open_mem
807
#define open_oldmem	open_mem
L
Linus Torvalds 已提交
808

809
static const struct file_operations mem_fops = {
L
Linus Torvalds 已提交
810 811 812 813 814
	.llseek		= memory_lseek,
	.read		= read_mem,
	.write		= write_mem,
	.mmap		= mmap_mem,
	.open		= open_mem,
815
	.get_unmapped_area = get_unmapped_area_mem,
L
Linus Torvalds 已提交
816 817
};

818
static const struct file_operations kmem_fops = {
L
Linus Torvalds 已提交
819 820 821 822 823
	.llseek		= memory_lseek,
	.read		= read_kmem,
	.write		= write_kmem,
	.mmap		= mmap_kmem,
	.open		= open_kmem,
824
	.get_unmapped_area = get_unmapped_area_mem,
L
Linus Torvalds 已提交
825 826
};

827
static const struct file_operations null_fops = {
L
Linus Torvalds 已提交
828 829 830
	.llseek		= null_lseek,
	.read		= read_null,
	.write		= write_null,
831
	.splice_write	= splice_write_null,
L
Linus Torvalds 已提交
832 833
};

834
#if (defined(CONFIG_ISA) || defined(CONFIG_PCI)) && !defined(__mc68000__)
835
static const struct file_operations port_fops = {
L
Linus Torvalds 已提交
836 837 838 839 840 841 842
	.llseek		= memory_lseek,
	.read		= read_port,
	.write		= write_port,
	.open		= open_port,
};
#endif

843
static const struct file_operations zero_fops = {
L
Linus Torvalds 已提交
844 845 846 847 848 849
	.llseek		= zero_lseek,
	.read		= read_zero,
	.write		= write_zero,
	.mmap		= mmap_zero,
};

850 851 852 853
/*
 * capabilities for /dev/zero
 * - permits private mappings, "copies" are taken of the source of zeros
 */
L
Linus Torvalds 已提交
854 855 856 857
static struct backing_dev_info zero_bdi = {
	.capabilities	= BDI_CAP_MAP_COPY,
};

858
static const struct file_operations full_fops = {
L
Linus Torvalds 已提交
859 860 861 862 863
	.llseek		= full_lseek,
	.read		= read_full,
	.write		= write_full,
};

864
#ifdef CONFIG_CRASH_DUMP
865
static const struct file_operations oldmem_fops = {
866 867 868 869 870
	.read	= read_oldmem,
	.open	= open_oldmem,
};
#endif

L
Linus Torvalds 已提交
871 872 873 874
static ssize_t kmsg_write(struct file * file, const char __user * buf,
			  size_t count, loff_t *ppos)
{
	char *tmp;
875
	ssize_t ret;
L
Linus Torvalds 已提交
876 877 878 879 880 881 882 883

	tmp = kmalloc(count + 1, GFP_KERNEL);
	if (tmp == NULL)
		return -ENOMEM;
	ret = -EFAULT;
	if (!copy_from_user(tmp, buf, count)) {
		tmp[count] = 0;
		ret = printk("%s", tmp);
884 885 886
		if (ret > count)
			/* printk can add a prefix */
			ret = count;
L
Linus Torvalds 已提交
887 888 889 890 891
	}
	kfree(tmp);
	return ret;
}

892
static const struct file_operations kmsg_fops = {
L
Linus Torvalds 已提交
893 894 895 896 897 898 899 900
	.write =	kmsg_write,
};

static int memory_open(struct inode * inode, struct file * filp)
{
	switch (iminor(inode)) {
		case 1:
			filp->f_op = &mem_fops;
901 902
			filp->f_mapping->backing_dev_info =
				&directly_mappable_cdev_bdi;
L
Linus Torvalds 已提交
903 904 905
			break;
		case 2:
			filp->f_op = &kmem_fops;
906 907
			filp->f_mapping->backing_dev_info =
				&directly_mappable_cdev_bdi;
L
Linus Torvalds 已提交
908 909 910 911
			break;
		case 3:
			filp->f_op = &null_fops;
			break;
912
#if (defined(CONFIG_ISA) || defined(CONFIG_PCI)) && !defined(__mc68000__)
L
Linus Torvalds 已提交
913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932
		case 4:
			filp->f_op = &port_fops;
			break;
#endif
		case 5:
			filp->f_mapping->backing_dev_info = &zero_bdi;
			filp->f_op = &zero_fops;
			break;
		case 7:
			filp->f_op = &full_fops;
			break;
		case 8:
			filp->f_op = &random_fops;
			break;
		case 9:
			filp->f_op = &urandom_fops;
			break;
		case 11:
			filp->f_op = &kmsg_fops;
			break;
933 934 935 936 937
#ifdef CONFIG_CRASH_DUMP
		case 12:
			filp->f_op = &oldmem_fops;
			break;
#endif
L
Linus Torvalds 已提交
938 939 940 941 942 943 944 945
		default:
			return -ENXIO;
	}
	if (filp->f_op && filp->f_op->open)
		return filp->f_op->open(inode,filp);
	return 0;
}

946
static const struct file_operations memory_fops = {
L
Linus Torvalds 已提交
947 948 949 950 951 952 953
	.open		= memory_open,	/* just a selector for the real open */
};

static const struct {
	unsigned int		minor;
	char			*name;
	umode_t			mode;
954
	const struct file_operations	*fops;
L
Linus Torvalds 已提交
955 956 957 958
} devlist[] = { /* list of minor devices */
	{1, "mem",     S_IRUSR | S_IWUSR | S_IRGRP, &mem_fops},
	{2, "kmem",    S_IRUSR | S_IWUSR | S_IRGRP, &kmem_fops},
	{3, "null",    S_IRUGO | S_IWUGO,           &null_fops},
959
#if (defined(CONFIG_ISA) || defined(CONFIG_PCI)) && !defined(__mc68000__)
L
Linus Torvalds 已提交
960 961 962 963 964 965 966
	{4, "port",    S_IRUSR | S_IWUSR | S_IRGRP, &port_fops},
#endif
	{5, "zero",    S_IRUGO | S_IWUGO,           &zero_fops},
	{7, "full",    S_IRUGO | S_IWUGO,           &full_fops},
	{8, "random",  S_IRUGO | S_IWUSR,           &random_fops},
	{9, "urandom", S_IRUGO | S_IWUSR,           &urandom_fops},
	{11,"kmsg",    S_IRUGO | S_IWUSR,           &kmsg_fops},
967 968 969
#ifdef CONFIG_CRASH_DUMP
	{12,"oldmem",    S_IRUSR | S_IWUSR | S_IRGRP, &oldmem_fops},
#endif
L
Linus Torvalds 已提交
970 971
};

972
static struct class *mem_class;
L
Linus Torvalds 已提交
973 974 975 976 977 978 979 980

static int __init chr_dev_init(void)
{
	int i;

	if (register_chrdev(MEM_MAJOR,"mem",&memory_fops))
		printk("unable to get major %d for memory devs\n", MEM_MAJOR);

981
	mem_class = class_create(THIS_MODULE, "mem");
982
	for (i = 0; i < ARRAY_SIZE(devlist); i++)
983 984
		class_device_create(mem_class, NULL,
					MKDEV(MEM_MAJOR, devlist[i].minor),
L
Linus Torvalds 已提交
985 986 987 988 989 990
					NULL, devlist[i].name);
	
	return 0;
}

fs_initcall(chr_dev_init);