mem.c 19.7 KB
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 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 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940
/*
 *  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 mmapping 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/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 <linux/export.h>

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

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

static inline unsigned long size_inside_page(unsigned long start,
					     unsigned long size)
{
	unsigned long sz;

	sz = PAGE_SIZE - (start & (PAGE_SIZE - 1));

	return min(sz, size);
}

#ifndef ARCH_HAS_VALID_PHYS_ADDR_RANGE
static inline int valid_phys_addr_range(unsigned long addr, size_t count)
{
	return addr + count <= __pa(high_memory);
}

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

#ifdef CONFIG_STRICT_DEVMEM
static inline int range_is_allowed(unsigned long pfn, unsigned long size)
{
	u64 from = ((u64)pfn) << PAGE_SHIFT;
	u64 to = from + size;
	u64 cursor = from;

	while (cursor < to) {
		if (!devmem_is_allowed(pfn)) {
			printk(KERN_INFO
		"Program %s tried to access /dev/mem between %Lx->%Lx.\n",
				current->comm, from, to);
			return 0;
		}
		cursor += PAGE_SIZE;
		pfn++;
	}
	return 1;
}
#else
static inline int range_is_allowed(unsigned long pfn, unsigned long size)
{
	return 1;
}
#endif

void __weak unxlate_dev_mem_ptr(unsigned long phys, void *addr)
{
}

/*
 * 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 = size_inside_page(p, count);
		if (sz > 0) {
			if (clear_user(buf, sz))
				return -EFAULT;
			buf += sz;
			p += sz;
			count -= sz;
			read += sz;
		}
	}
#endif

	while (count > 0) {
		unsigned long remaining;

		sz = size_inside_page(p, count);

		if (!range_is_allowed(p >> PAGE_SHIFT, count))
			return -EPERM;

		/*
		 * 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 (!ptr)
			return -EFAULT;

		remaining = copy_to_user(buf, ptr, sz);
		unxlate_dev_mem_ptr(p, ptr);
		if (remaining)
			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) {
		sz = size_inside_page(p, count);
		/* Hmm. Do something? */
		buf += sz;
		p += sz;
		count -= sz;
		written += sz;
	}
#endif

	while (count > 0) {
		sz = size_inside_page(p, count);

		if (!range_is_allowed(p >> PAGE_SHIFT, sz))
			return -EPERM;

		/*
		 * 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 (!ptr) {
			if (written)
				break;
			return -EFAULT;
		}

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

		buf += sz;
		p += sz;
		count -= sz;
		written += sz;
	}

	*ppos += written;
	return written;
}

int __weak phys_mem_access_prot_allowed(struct file *file,
	unsigned long pfn, unsigned long size, pgprot_t *vma_prot)
{
	return 1;
}

#ifndef __HAVE_PHYS_MEM_ACCESS_PROT

/*
 * Architectures vary in how they handle caching for addresses
 * outside of main memory.
 *
 */
#ifdef pgprot_noncached
static int uncached_access(struct file *file, unsigned long addr)
{
#if defined(CONFIG_IA64)
	/*
	 * On ia64, we ignore O_DSYNC 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_DSYNC will be done non-cached.
	 */
	if (file->f_flags & O_DSYNC)
		return 1;
	return addr >= __pa(high_memory);
#endif
}
#endif

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 const struct vm_operations_struct mmap_mem_ops = {
#ifdef CONFIG_HAVE_IOREMAP_PROT
	.access = generic_access_phys
#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;

	if (!range_is_allowed(vma->vm_pgoff, size))
		return -EPERM;

	if (!phys_mem_access_prot_allowed(file, vma->vm_pgoff, size,
						&vma->vm_page_prot))
		return -EINVAL;

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

	vma->vm_ops = &mmap_mem_ops;

	/* 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;
}

#ifdef CONFIG_DEVKMEM
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);
}
#endif

#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

#ifdef CONFIG_DEVKMEM
/*
 * 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 */
	int err = 0;

	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) {
			sz = size_inside_page(p, low_count);
			if (clear_user(buf, sz))
				return -EFAULT;
			buf += sz;
			p += sz;
			read += sz;
			low_count -= sz;
			count -= sz;
		}
#endif
		while (low_count > 0) {
			sz = size_inside_page(p, 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) {
			sz = size_inside_page(p, count);
			if (!is_vmalloc_or_module_addr((void *)p)) {
				err = -ENXIO;
				break;
			}
			sz = vread(kbuf, (char *)p, sz);
			if (!sz)
				break;
			if (copy_to_user(buf, kbuf, sz)) {
				err = -EFAULT;
				break;
			}
			count -= sz;
			buf += sz;
			read += sz;
			p += sz;
		}
		free_page((unsigned long)kbuf);
	}
	*ppos = p;
	return read ? read : err;
}


static ssize_t do_write_kmem(unsigned long p, 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 (p < PAGE_SIZE) {
		sz = size_inside_page(p, count);
		/* Hmm. Do something? */
		buf += sz;
		p += sz;
		count -= sz;
		written += sz;
	}
#endif

	while (count > 0) {
		char *ptr;

		sz = size_inside_page(p, 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((char *)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;
}

/*
 * 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;
	char * kbuf; /* k-addr because vwrite() takes vmlist_lock rwlock */
	int err = 0;

	if (p < (unsigned long) high_memory) {
		unsigned long to_write = min_t(unsigned long, count,
					       (unsigned long)high_memory - p);
		wrote = do_write_kmem(p, buf, to_write, ppos);
		if (wrote != to_write)
			return wrote;
		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) {
			unsigned long sz = size_inside_page(p, count);
			unsigned long n;

			if (!is_vmalloc_or_module_addr((void *)p)) {
				err = -ENXIO;
				break;
			}
			n = copy_from_user(kbuf, buf, sz);
			if (n) {
				err = -EFAULT;
				break;
			}
			vwrite(kbuf, (char *)p, sz);
			count -= sz;
			buf += sz;
			virtr += sz;
			p += sz;
		}
		free_page((unsigned long)kbuf);
	}

	*ppos = p;
	return virtr + wrote ? : err;
}
#endif

#ifdef CONFIG_DEVPORT
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;
		if (__get_user(c, tmp)) {
			if (tmp > buf)
				break;
			return -EFAULT;
		}
		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;
}

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);
}

static ssize_t read_zero(struct file *file, char __user *buf,
			 size_t count, loff_t *ppos)
{
	size_t written;

	if (!count)
		return 0;

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

	written = 0;
	while (count) {
		unsigned long unwritten;
		size_t chunk = count;

		if (chunk > PAGE_SIZE)
			chunk = PAGE_SIZE;	/* Just for latency reasons */
		unwritten = __clear_user(buf, chunk);
		written += chunk - unwritten;
		if (unwritten)
			break;
		if (signal_pending(current))
			return written ? written : -ERESTARTSYS;
		buf += chunk;
		count -= chunk;
		cond_resched();
	}
	return written ? written : -EFAULT;
}

static int mmap_zero(struct file *file, struct vm_area_struct *vma)
{
#ifndef CONFIG_MMU
	return -ENOSYS;
#endif
	if (vma->vm_flags & VM_SHARED)
		return shmem_zero_setup(vma);
	return 0;
}

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;

	mutex_lock(&file->f_path.dentry->d_inode->i_mutex);
	switch (orig) {
	case SEEK_CUR:
		offset += file->f_pos;
	case SEEK_SET:
		/* to avoid userland mistaking f_pos=-9 as -EBADF=-9 */
		if ((unsigned long long)offset >= ~0xFFFULL) {
			ret = -EOVERFLOW;
			break;
		}
		file->f_pos = offset;
		ret = file->f_pos;
		force_successful_syscall_return();
		break;
	default:
		ret = -EINVAL;
	}
	mutex_unlock(&file->f_path.dentry->d_inode->i_mutex);
	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
#define open_oldmem	open_mem

static const struct file_operations mem_fops = {
	.llseek		= memory_lseek,
	.read		= read_mem,
	.write		= write_mem,
	.mmap		= mmap_mem,
	.open		= open_mem,
	.get_unmapped_area = get_unmapped_area_mem,
};

#ifdef CONFIG_DEVKMEM
static const struct file_operations kmem_fops = {
	.llseek		= memory_lseek,
	.read		= read_kmem,
	.write		= write_kmem,
	.mmap		= mmap_kmem,
	.open		= open_kmem,
	.get_unmapped_area = get_unmapped_area_mem,
};
#endif

static const struct file_operations null_fops = {
	.llseek		= null_lseek,
	.read		= read_null,
	.write		= write_null,
	.splice_write	= splice_write_null,
};

#ifdef CONFIG_DEVPORT
static const struct file_operations port_fops = {
	.llseek		= memory_lseek,
	.read		= read_port,
	.write		= write_port,
	.open		= open_port,
};
#endif

static const struct file_operations zero_fops = {
	.llseek		= zero_lseek,
	.read		= read_zero,
	.write		= write_zero,
	.mmap		= mmap_zero,
};

/*
 * capabilities for /dev/zero
 * - permits private mappings, "copies" are taken of the source of zeros
 * - no writeback happens
 */
static struct backing_dev_info zero_bdi = {
	.name		= "char/mem",
	.capabilities	= BDI_CAP_MAP_COPY | BDI_CAP_NO_ACCT_AND_WRITEBACK,
};

static const struct file_operations full_fops = {
	.llseek		= full_lseek,
	.read		= read_full,
	.write		= write_full,
};

#ifdef CONFIG_CRASH_DUMP
static const struct file_operations oldmem_fops = {
	.read	= read_oldmem,
	.open	= open_oldmem,
	.llseek = default_llseek,
};
#endif

static ssize_t kmsg_writev(struct kiocb *iocb, const struct iovec *iv,
			   unsigned long count, loff_t pos)
{
	char *line, *p;
	int i;
	ssize_t ret = -EFAULT;
	size_t len = iov_length(iv, count);

	line = kmalloc(len + 1, GFP_KERNEL);
	if (line == NULL)
		return -ENOMEM;

	/*
	 * copy all vectors into a single string, to ensure we do
	 * not interleave our log line with other printk calls
	 */
	p = line;
	for (i = 0; i < count; i++) {
		if (copy_from_user(p, iv[i].iov_base, iv[i].iov_len))
			goto out;
		p += iv[i].iov_len;
	}
	p[0] = '\0';

	ret = printk("%s", line);
	/* printk can add a prefix */
	if (ret > len)
		ret = len;
out:
	kfree(line);
	return ret;
}

static const struct file_operations kmsg_fops = {
	.aio_write = kmsg_writev,
	.llseek = noop_llseek,
};

static const struct memdev {
	const char *name;
	umode_t mode;
	const struct file_operations *fops;
	struct backing_dev_info *dev_info;
} devlist[] = {
	 [1] = { "mem", 0, &mem_fops, &directly_mappable_cdev_bdi },
#ifdef CONFIG_DEVKMEM
	 [2] = { "kmem", 0, &kmem_fops, &directly_mappable_cdev_bdi },
#endif
	 [3] = { "null", 0666, &null_fops, NULL },
#ifdef CONFIG_DEVPORT
	 [4] = { "port", 0, &port_fops, NULL },
#endif
	 [5] = { "zero", 0666, &zero_fops, &zero_bdi },
	 [7] = { "full", 0666, &full_fops, NULL },
	 [8] = { "random", 0666, &random_fops, NULL },
	 [9] = { "urandom", 0666, &urandom_fops, NULL },
	[11] = { "kmsg", 0, &kmsg_fops, NULL },
#ifdef CONFIG_CRASH_DUMP
	[12] = { "oldmem", 0, &oldmem_fops, NULL },
#endif
};

static int memory_open(struct inode *inode, struct file *filp)
{
	int minor;
	const struct memdev *dev;

	minor = iminor(inode);
	if (minor >= ARRAY_SIZE(devlist))
		return -ENXIO;

	dev = &devlist[minor];
	if (!dev->fops)
		return -ENXIO;

	filp->f_op = dev->fops;
	if (dev->dev_info)
		filp->f_mapping->backing_dev_info = dev->dev_info;

	/* Is /dev/mem or /dev/kmem ? */
	if (dev->dev_info == &directly_mappable_cdev_bdi)
		filp->f_mode |= FMODE_UNSIGNED_OFFSET;

	if (dev->fops->open)
		return dev->fops->open(inode, filp);

	return 0;
}

static const struct file_operations memory_fops = {
	.open = memory_open,
	.llseek = noop_llseek,
};

static char *mem_devnode(struct device *dev, umode_t *mode)
{
	if (mode && devlist[MINOR(dev->devt)].mode)
		*mode = devlist[MINOR(dev->devt)].mode;
	return NULL;
}

static struct class *mem_class;

static int __init chr_dev_init(void)
{
	int minor;
	int err;

	err = bdi_init(&zero_bdi);
	if (err)
		return err;

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

	mem_class = class_create(THIS_MODULE, "mem");
	if (IS_ERR(mem_class))
		return PTR_ERR(mem_class);

	mem_class->devnode = mem_devnode;
	for (minor = 1; minor < ARRAY_SIZE(devlist); minor++) {
		if (!devlist[minor].name)
			continue;
		device_create(mem_class, NULL, MKDEV(MEM_MAJOR, minor),
			      NULL, devlist[minor].name);
	}

	return tty_init();
}

fs_initcall(chr_dev_init);