nommu.c

/*
 *  linux/mm/nommu.c
 *
 *  Replacement code for mm functions to support CPU's that don't
 *  have any form of memory management unit (thus no virtual memory).
 *
 *  See Documentation/nommu-mmap.txt
 *
 *  Copyright (c) 2004-2008 David Howells <dhowells@redhat.com>
 *  Copyright (c) 2000-2003 David McCullough <davidm@snapgear.com>
 *  Copyright (c) 2000-2001 D Jeff Dionne <jeff@uClinux.org>
 *  Copyright (c) 2002      Greg Ungerer <gerg@snapgear.com>
 *  Copyright (c) 2007-2009 Paul Mundt <lethal@linux-sh.org>
 */

#include <linux/module.h>
#include <linux/mm.h>
#include <linux/mman.h>
#include <linux/swap.h>
#include <linux/file.h>
#include <linux/highmem.h>
#include <linux/pagemap.h>
#include <linux/slab.h>
#include <linux/vmalloc.h>
#include <linux/tracehook.h>
#include <linux/blkdev.h>
#include <linux/backing-dev.h>
#include <linux/mount.h>
#include <linux/personality.h>
#include <linux/security.h>
#include <linux/syscalls.h>

#include <asm/uaccess.h>
#include <asm/tlb.h>
#include <asm/tlbflush.h>
#include "internal.h"

static inline __attribute__((format(printf, 1, 2)))
void no_printk(const char *fmt, ...)
{
}

#if 0
#define kenter(FMT, ...) \
	printk(KERN_DEBUG "==> %s("FMT")\n", __func__, ##__VA_ARGS__)
#define kleave(FMT, ...) \
	printk(KERN_DEBUG "<== %s()"FMT"\n", __func__, ##__VA_ARGS__)
#define kdebug(FMT, ...) \
	printk(KERN_DEBUG "xxx" FMT"yyy\n", ##__VA_ARGS__)
#else
#define kenter(FMT, ...) \
	no_printk(KERN_DEBUG "==> %s("FMT")\n", __func__, ##__VA_ARGS__)
#define kleave(FMT, ...) \
	no_printk(KERN_DEBUG "<== %s()"FMT"\n", __func__, ##__VA_ARGS__)
#define kdebug(FMT, ...) \
	no_printk(KERN_DEBUG FMT"\n", ##__VA_ARGS__)
#endif

#include "internal.h"

void *high_memory;
struct page *mem_map;
unsigned long max_mapnr;
unsigned long num_physpages;
struct percpu_counter vm_committed_as;
int sysctl_overcommit_memory = OVERCOMMIT_GUESS; /* heuristic overcommit */
int sysctl_overcommit_ratio = 50; /* default is 50% */
int sysctl_max_map_count = DEFAULT_MAX_MAP_COUNT;
int sysctl_nr_trim_pages = CONFIG_NOMMU_INITIAL_TRIM_EXCESS;
int heap_stack_gap = 0;

/* amount of vm to protect from userspace access */
unsigned long mmap_min_addr = CONFIG_DEFAULT_MMAP_MIN_ADDR;

atomic_long_t mmap_pages_allocated;

EXPORT_SYMBOL(mem_map);
EXPORT_SYMBOL(num_physpages);

/* list of mapped, potentially shareable regions */
static struct kmem_cache *vm_region_jar;
struct rb_root nommu_region_tree = RB_ROOT;
DECLARE_RWSEM(nommu_region_sem);

struct vm_operations_struct generic_file_vm_ops = {
};

/*
 * Handle all mappings that got truncated by a "truncate()"
 * system call.
 *
 * NOTE! We have to be ready to update the memory sharing
 * between the file and the memory map for a potential last
 * incomplete page.  Ugly, but necessary.
 */
int vmtruncate(struct inode *inode, loff_t offset)
{
	struct address_space *mapping = inode->i_mapping;
	unsigned long limit;

	if (inode->i_size < offset)
		goto do_expand;
	i_size_write(inode, offset);

	truncate_inode_pages(mapping, offset);
	goto out_truncate;

do_expand:
	limit = current->signal->rlim[RLIMIT_FSIZE].rlim_cur;
	if (limit != RLIM_INFINITY && offset > limit)
		goto out_sig;
	if (offset > inode->i_sb->s_maxbytes)
		goto out;
	i_size_write(inode, offset);

out_truncate:
	if (inode->i_op->truncate)
		inode->i_op->truncate(inode);
	return 0;
out_sig:
	send_sig(SIGXFSZ, current, 0);
out:
	return -EFBIG;
}

EXPORT_SYMBOL(vmtruncate);

/*
 * Return the total memory allocated for this pointer, not
 * just what the caller asked for.
 *
 * Doesn't have to be accurate, i.e. may have races.
 */
unsigned int kobjsize(const void *objp)
{
	struct page *page;

	/*
	 * If the object we have should not have ksize performed on it,
	 * return size of 0
	 */
	if (!objp || !virt_addr_valid(objp))
		return 0;

	page = virt_to_head_page(objp);

	/*
	 * If the allocator sets PageSlab, we know the pointer came from
	 * kmalloc().
	 */
	if (PageSlab(page))
		return ksize(objp);

	/*
	 * If it's not a compound page, see if we have a matching VMA
	 * region. This test is intentionally done in reverse order,
	 * so if there's no VMA, we still fall through and hand back
	 * PAGE_SIZE for 0-order pages.
	 */
	if (!PageCompound(page)) {
		struct vm_area_struct *vma;

		vma = find_vma(current->mm, (unsigned long)objp);
		if (vma)
			return vma->vm_end - vma->vm_start;
	}

	/*
	 * The ksize() function is only guaranteed to work for pointers
	 * returned by kmalloc(). So handle arbitrary pointers here.
	 */
	return PAGE_SIZE << compound_order(page);
}

int __get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
		     unsigned long start, int len, int flags,
		struct page **pages, struct vm_area_struct **vmas)
{
	struct vm_area_struct *vma;
	unsigned long vm_flags;
	int i;
	int write = !!(flags & GUP_FLAGS_WRITE);
	int force = !!(flags & GUP_FLAGS_FORCE);
	int ignore = !!(flags & GUP_FLAGS_IGNORE_VMA_PERMISSIONS);

	/* calculate required read or write permissions.
	 * - if 'force' is set, we only require the "MAY" flags.
	 */
	vm_flags  = write ? (VM_WRITE | VM_MAYWRITE) : (VM_READ | VM_MAYREAD);
	vm_flags &= force ? (VM_MAYREAD | VM_MAYWRITE) : (VM_READ | VM_WRITE);

	for (i = 0; i < len; i++) {
		vma = find_vma(mm, start);
		if (!vma)
			goto finish_or_fault;

		/* protect what we can, including chardevs */
		if (vma->vm_flags & (VM_IO | VM_PFNMAP) ||
		    (!ignore && !(vm_flags & vma->vm_flags)))
			goto finish_or_fault;

		if (pages) {
			pages[i] = virt_to_page(start);
			if (pages[i])
				page_cache_get(pages[i]);
		}
		if (vmas)
			vmas[i] = vma;
		start += PAGE_SIZE;
	}

	return i;

finish_or_fault:
	return i ? : -EFAULT;
}


/*
 * get a list of pages in an address range belonging to the specified process
 * and indicate the VMA that covers each page
 * - this is potentially dodgy as we may end incrementing the page count of a
 *   slab page or a secondary page from a compound page
 * - don't permit access to VMAs that don't support it, such as I/O mappings
 */
int get_user_pages(struct task_struct *tsk, struct mm_struct *mm,
	unsigned long start, int len, int write, int force,
	struct page **pages, struct vm_area_struct **vmas)
{
	int flags = 0;

	if (write)
		flags |= GUP_FLAGS_WRITE;
	if (force)
		flags |= GUP_FLAGS_FORCE;

	return __get_user_pages(tsk, mm,
				start, len, flags,
				pages, vmas);
}
EXPORT_SYMBOL(get_user_pages);

DEFINE_RWLOCK(vmlist_lock);
struct vm_struct *vmlist;

void vfree(const void *addr)
{
	kfree(addr);
}
EXPORT_SYMBOL(vfree);

void *__vmalloc(unsigned long size, gfp_t gfp_mask, pgprot_t prot)
{
	/*
	 *  You can't specify __GFP_HIGHMEM with kmalloc() since kmalloc()
	 * returns only a logical address.
	 */
	return kmalloc(size, (gfp_mask | __GFP_COMP) & ~__GFP_HIGHMEM);
}
EXPORT_SYMBOL(__vmalloc);

void *vmalloc_user(unsigned long size)
{
	void *ret;

	ret = __vmalloc(size, GFP_KERNEL | __GFP_HIGHMEM | __GFP_ZERO,
			PAGE_KERNEL);
	if (ret) {
		struct vm_area_struct *vma;

		down_write(&current->mm->mmap_sem);
		vma = find_vma(current->mm, (unsigned long)ret);
		if (vma)
			vma->vm_flags |= VM_USERMAP;
		up_write(&current->mm->mmap_sem);
	}

	return ret;
}
EXPORT_SYMBOL(vmalloc_user);

struct page *vmalloc_to_page(const void *addr)
{
	return virt_to_page(addr);
}
EXPORT_SYMBOL(vmalloc_to_page);

unsigned long vmalloc_to_pfn(const void *addr)
{
	return page_to_pfn(virt_to_page(addr));
}
EXPORT_SYMBOL(vmalloc_to_pfn);

long vread(char *buf, char *addr, unsigned long count)
{
	memcpy(buf, addr, count);
	return count;
}

long vwrite(char *buf, char *addr, unsigned long count)
{
	/* Don't allow overflow */
	if ((unsigned long) addr + count < count)
		count = -(unsigned long) addr;

	memcpy(addr, buf, count);
	return(count);
}

/*
 *	vmalloc  -  allocate virtually continguos memory
 *
 *	@size:		allocation size
 *
 *	Allocate enough pages to cover @size from the page level
 *	allocator and map them into continguos kernel virtual space.
 *
 *	For tight control over page level allocator and protection flags
 *	use __vmalloc() instead.
 */
void *vmalloc(unsigned long size)
{
       return __vmalloc(size, GFP_KERNEL | __GFP_HIGHMEM, PAGE_KERNEL);
}
EXPORT_SYMBOL(vmalloc);

void *vmalloc_node(unsigned long size, int node)
{
	return vmalloc(size);
}
EXPORT_SYMBOL(vmalloc_node);

#ifndef PAGE_KERNEL_EXEC
# define PAGE_KERNEL_EXEC PAGE_KERNEL
#endif

/**
 *	vmalloc_exec  -  allocate virtually contiguous, executable memory
 *	@size:		allocation size
 *
 *	Kernel-internal function to allocate enough pages to cover @size
 *	the page level allocator and map them into contiguous and
 *	executable kernel virtual space.
 *
 *	For tight control over page level allocator and protection flags
 *	use __vmalloc() instead.
 */

void *vmalloc_exec(unsigned long size)
{
	return __vmalloc(size, GFP_KERNEL | __GFP_HIGHMEM, PAGE_KERNEL_EXEC);
}

/**
 * vmalloc_32  -  allocate virtually contiguous memory (32bit addressable)
 *	@size:		allocation size
 *
 *	Allocate enough 32bit PA addressable pages to cover @size from the
 *	page level allocator and map them into continguos kernel virtual space.
 */
void *vmalloc_32(unsigned long size)
{
	return __vmalloc(size, GFP_KERNEL, PAGE_KERNEL);
}
EXPORT_SYMBOL(vmalloc_32);

/**
 * vmalloc_32_user - allocate zeroed virtually contiguous 32bit memory
 *	@size:		allocation size
 *
 * The resulting memory area is 32bit addressable and zeroed so it can be
 * mapped to userspace without leaking data.
 *
 * VM_USERMAP is set on the corresponding VMA so that subsequent calls to
 * remap_vmalloc_range() are permissible.
 */
void *vmalloc_32_user(unsigned long size)
{
	/*
	 * We'll have to sort out the ZONE_DMA bits for 64-bit,
	 * but for now this can simply use vmalloc_user() directly.
	 */
	return vmalloc_user(size);
}
EXPORT_SYMBOL(vmalloc_32_user);

void *vmap(struct page **pages, unsigned int count, unsigned long flags, pgprot_t prot)
{
	BUG();
	return NULL;
}
EXPORT_SYMBOL(vmap);

void vunmap(const void *addr)
{
	BUG();
}
EXPORT_SYMBOL(vunmap);

void *vm_map_ram(struct page **pages, unsigned int count, int node, pgprot_t prot)
{
	BUG();
	return NULL;
}
EXPORT_SYMBOL(vm_map_ram);

void vm_unmap_ram(const void *mem, unsigned int count)
{
	BUG();
}
EXPORT_SYMBOL(vm_unmap_ram);

void vm_unmap_aliases(void)
{
}
EXPORT_SYMBOL_GPL(vm_unmap_aliases);

/*
 * Implement a stub for vmalloc_sync_all() if the architecture chose not to
 * have one.
 */
void  __attribute__((weak)) vmalloc_sync_all(void)
{
}

int vm_insert_page(struct vm_area_struct *vma, unsigned long addr,
		   struct page *page)
{
	return -EINVAL;
}
EXPORT_SYMBOL(vm_insert_page);

/*
 *  sys_brk() for the most part doesn't need the global kernel
 *  lock, except when an application is doing something nasty
 *  like trying to un-brk an area that has already been mapped
 *  to a regular file.  in this case, the unmapping will need
 *  to invoke file system routines that need the global lock.
 */
SYSCALL_DEFINE1(brk, unsigned long, brk)
{
	struct mm_struct *mm = current->mm;

	if (brk < mm->start_brk || brk > mm->context.end_brk)
		return mm->brk;

	if (mm->brk == brk)
		return mm->brk;

	/*
	 * Always allow shrinking brk
	 */
	if (brk <= mm->brk) {
		mm->brk = brk;
		return brk;
	}

	/*
	 * Ok, looks good - let it rip.
	 */
	return mm->brk = brk;
}

/*
 * initialise the VMA and region record slabs
 */
void __init mmap_init(void)
{
	int ret;

	ret = percpu_counter_init(&vm_committed_as, 0);
	VM_BUG_ON(ret);
	vm_region_jar = KMEM_CACHE(vm_region, SLAB_PANIC);
}

/*
 * validate the region tree
 * - the caller must hold the region lock
 */
#ifdef CONFIG_DEBUG_NOMMU_REGIONS
static noinline void validate_nommu_regions(void)
{
	struct vm_region *region, *last;
	struct rb_node *p, *lastp;

	lastp = rb_first(&nommu_region_tree);
	if (!lastp)
		return;

	last = rb_entry(lastp, struct vm_region, vm_rb);
	BUG_ON(unlikely(last->vm_end <= last->vm_start));
	BUG_ON(unlikely(last->vm_top < last->vm_end));

	while ((p = rb_next(lastp))) {
		region = rb_entry(p, struct vm_region, vm_rb);
		last = rb_entry(lastp, struct vm_region, vm_rb);

		BUG_ON(unlikely(region->vm_end <= region->vm_start));
		BUG_ON(unlikely(region->vm_top < region->vm_end));
		BUG_ON(unlikely(region->vm_start < last->vm_top));

		lastp = p;
	}
}
#else
static void validate_nommu_regions(void)
{
}
#endif

/*
 * add a region into the global tree
 */
static void add_nommu_region(struct vm_region *region)
{
	struct vm_region *pregion;
	struct rb_node **p, *parent;

	validate_nommu_regions();

	parent = NULL;
	p = &nommu_region_tree.rb_node;
	while (*p) {
		parent = *p;
		pregion = rb_entry(parent, struct vm_region, vm_rb);
		if (region->vm_start < pregion->vm_start)
			p = &(*p)->rb_left;
		else if (region->vm_start > pregion->vm_start)
			p = &(*p)->rb_right;
		else if (pregion == region)
			return;
		else
			BUG();
	}

	rb_link_node(&region->vm_rb, parent, p);
	rb_insert_color(&region->vm_rb, &nommu_region_tree);

	validate_nommu_regions();
}

/*
 * delete a region from the global tree
 */
static void delete_nommu_region(struct vm_region *region)
{
	BUG_ON(!nommu_region_tree.rb_node);

	validate_nommu_regions();
	rb_erase(&region->vm_rb, &nommu_region_tree);
	validate_nommu_regions();
}

/*
 * free a contiguous series of pages
 */
static void free_page_series(unsigned long from, unsigned long to)
{
	for (; from < to; from += PAGE_SIZE) {
		struct page *page = virt_to_page(from);

		kdebug("- free %lx", from);
		atomic_long_dec(&mmap_pages_allocated);
		if (page_count(page) != 1)
			kdebug("free page %p: refcount not one: %d",
			       page, page_count(page));
		put_page(page);
	}
}

/*
 * release a reference to a region
 * - the caller must hold the region semaphore for writing, which this releases
 * - the region may not have been added to the tree yet, in which case vm_top
 *   will equal vm_start
 */
static void __put_nommu_region(struct vm_region *region)
	__releases(nommu_region_sem)
{
	kenter("%p{%d}", region, atomic_read(&region->vm_usage));

	BUG_ON(!nommu_region_tree.rb_node);

	if (atomic_dec_and_test(&region->vm_usage)) {
		if (region->vm_top > region->vm_start)
			delete_nommu_region(region);
		up_write(&nommu_region_sem);

		if (region->vm_file)
			fput(region->vm_file);

		/* IO memory and memory shared directly out of the pagecache
		 * from ramfs/tmpfs mustn't be released here */
		if (region->vm_flags & VM_MAPPED_COPY) {
			kdebug("free series");
			free_page_series(region->vm_start, region->vm_top);
		}
		kmem_cache_free(vm_region_jar, region);
	} else {
		up_write(&nommu_region_sem);
	}
}

/*
 * release a reference to a region
 */
static void put_nommu_region(struct vm_region *region)
{
	down_write(&nommu_region_sem);
	__put_nommu_region(region);
}

/*
 * add a VMA into a process's mm_struct in the appropriate place in the list
 * and tree and add to the address space's page tree also if not an anonymous
 * page
 * - should be called with mm->mmap_sem held writelocked
 */
static void add_vma_to_mm(struct mm_struct *mm, struct vm_area_struct *vma)
{
	struct vm_area_struct *pvma, **pp;
	struct address_space *mapping;
	struct rb_node **p, *parent;

	kenter(",%p", vma);

	BUG_ON(!vma->vm_region);

	mm->map_count++;
	vma->vm_mm = mm;

	/* add the VMA to the mapping */
	if (vma->vm_file) {
		mapping = vma->vm_file->f_mapping;

		flush_dcache_mmap_lock(mapping);
		vma_prio_tree_insert(vma, &mapping->i_mmap);
		flush_dcache_mmap_unlock(mapping);
	}

	/* add the VMA to the tree */
	parent = NULL;
	p = &mm->mm_rb.rb_node;
	while (*p) {
		parent = *p;
		pvma = rb_entry(parent, struct vm_area_struct, vm_rb);

		/* sort by: start addr, end addr, VMA struct addr in that order
		 * (the latter is necessary as we may get identical VMAs) */
		if (vma->vm_start < pvma->vm_start)
			p = &(*p)->rb_left;
		else if (vma->vm_start > pvma->vm_start)
			p = &(*p)->rb_right;
		else if (vma->vm_end < pvma->vm_end)
			p = &(*p)->rb_left;
		else if (vma->vm_end > pvma->vm_end)
			p = &(*p)->rb_right;
		else if (vma < pvma)
			p = &(*p)->rb_left;
		else if (vma > pvma)
			p = &(*p)->rb_right;
		else
			BUG();
	}

	rb_link_node(&vma->vm_rb, parent, p);
	rb_insert_color(&vma->vm_rb, &mm->mm_rb);

	/* add VMA to the VMA list also */
	for (pp = &mm->mmap; (pvma = *pp); pp = &(*pp)->vm_next) {
		if (pvma->vm_start > vma->vm_start)
			break;
		if (pvma->vm_start < vma->vm_start)
			continue;
		if (pvma->vm_end < vma->vm_end)
			break;
	}

	vma->vm_next = *pp;
	*pp = vma;
}

/*
 * delete a VMA from its owning mm_struct and address space
 */
static void delete_vma_from_mm(struct vm_area_struct *vma)
{
	struct vm_area_struct **pp;
	struct address_space *mapping;
	struct mm_struct *mm = vma->vm_mm;

	kenter("%p", vma);

	mm->map_count--;
	if (mm->mmap_cache == vma)
		mm->mmap_cache = NULL;

	/* remove the VMA from the mapping */
	if (vma->vm_file) {
		mapping = vma->vm_file->f_mapping;

		flush_dcache_mmap_lock(mapping);
		vma_prio_tree_remove(vma, &mapping->i_mmap);
		flush_dcache_mmap_unlock(mapping);
	}

	/* remove from the MM's tree and list */
	rb_erase(&vma->vm_rb, &mm->mm_rb);
	for (pp = &mm->mmap; *pp; pp = &(*pp)->vm_next) {
		if (*pp == vma) {
			*pp = vma->vm_next;
			break;
		}
	}

	vma->vm_mm = NULL;
}

/*
 * destroy a VMA record
 */
static void delete_vma(struct mm_struct *mm, struct vm_area_struct *vma)
{
	kenter("%p", vma);
	if (vma->vm_ops && vma->vm_ops->close)
		vma->vm_ops->close(vma);
	if (vma->vm_file) {
		fput(vma->vm_file);
		if (vma->vm_flags & VM_EXECUTABLE)
			removed_exe_file_vma(mm);
	}
	put_nommu_region(vma->vm_region);
	kmem_cache_free(vm_area_cachep, vma);
}

/*
 * look up the first VMA in which addr resides, NULL if none
 * - should be called with mm->mmap_sem at least held readlocked
 */
struct vm_area_struct *find_vma(struct mm_struct *mm, unsigned long addr)
{
	struct vm_area_struct *vma;
	struct rb_node *n = mm->mm_rb.rb_node;

	/* check the cache first */
	vma = mm->mmap_cache;
	if (vma && vma->vm_start <= addr && vma->vm_end > addr)
		return vma;

	/* trawl the tree (there may be multiple mappings in which addr
	 * resides) */
	for (n = rb_first(&mm->mm_rb); n; n = rb_next(n)) {
		vma = rb_entry(n, struct vm_area_struct, vm_rb);
		if (vma->vm_start > addr)
			return NULL;
		if (vma->vm_end > addr) {
			mm->mmap_cache = vma;
			return vma;
		}
	}

	return NULL;
}
EXPORT_SYMBOL(find_vma);

/*
 * find a VMA
 * - we don't extend stack VMAs under NOMMU conditions
 */
struct vm_area_struct *find_extend_vma(struct mm_struct *mm, unsigned long addr)
{
	return find_vma(mm, addr);
}

/*
 * expand a stack to a given address
 * - not supported under NOMMU conditions
 */
int expand_stack(struct vm_area_struct *vma, unsigned long address)
{
	return -ENOMEM;
}

/*
 * look up the first VMA exactly that exactly matches addr
 * - should be called with mm->mmap_sem at least held readlocked
 */
static struct vm_area_struct *find_vma_exact(struct mm_struct *mm,
					     unsigned long addr,
					     unsigned long len)
{
	struct vm_area_struct *vma;
	struct rb_node *n = mm->mm_rb.rb_node;
	unsigned long end = addr + len;

	/* check the cache first */
	vma = mm->mmap_cache;
	if (vma && vma->vm_start == addr && vma->vm_end == end)
		return vma;

	/* trawl the tree (there may be multiple mappings in which addr
	 * resides) */
	for (n = rb_first(&mm->mm_rb); n; n = rb_next(n)) {
		vma = rb_entry(n, struct vm_area_struct, vm_rb);
		if (vma->vm_start < addr)
			continue;
		if (vma->vm_start > addr)
			return NULL;
		if (vma->vm_end == end) {
			mm->mmap_cache = vma;
			return vma;
		}
	}

	return NULL;
}

/*
 * determine whether a mapping should be permitted and, if so, what sort of
 * mapping we're capable of supporting
 */
static int validate_mmap_request(struct file *file,
				 unsigned long addr,
				 unsigned long len,
				 unsigned long prot,
				 unsigned long flags,
				 unsigned long pgoff,
				 unsigned long *_capabilities)
{
	unsigned long capabilities, rlen;
	unsigned long reqprot = prot;
	int ret;

	/* do the simple checks first */
	if (flags & MAP_FIXED || addr) {
		printk(KERN_DEBUG
		       "%d: Can't do fixed-address/overlay mmap of RAM\n",
		       current->pid);
		return -EINVAL;
	}

	if ((flags & MAP_TYPE) != MAP_PRIVATE &&
	    (flags & MAP_TYPE) != MAP_SHARED)
		return -EINVAL;

	if (!len)
		return -EINVAL;

	/* Careful about overflows.. */
	rlen = PAGE_ALIGN(len);
	if (!rlen || rlen > TASK_SIZE)
		return -ENOMEM;

	/* offset overflow? */
	if ((pgoff + (rlen >> PAGE_SHIFT)) < pgoff)
		return -EOVERFLOW;

	if (file) {
		/* validate file mapping requests */
		struct address_space *mapping;

		/* files must support mmap */
		if (!file->f_op || !file->f_op->mmap)
			return -ENODEV;

		/* work out if what we've got could possibly be shared
		 * - we support chardevs that provide their own "memory"
		 * - we support files/blockdevs that are memory backed
		 */
		mapping = file->f_mapping;
		if (!mapping)
			mapping = file->f_path.dentry->d_inode->i_mapping;

		capabilities = 0;
		if (mapping && mapping->backing_dev_info)
			capabilities = mapping->backing_dev_info->capabilities;

		if (!capabilities) {
			/* no explicit capabilities set, so assume some
			 * defaults */
			switch (file->f_path.dentry->d_inode->i_mode & S_IFMT) {
			case S_IFREG:
			case S_IFBLK:
				capabilities = BDI_CAP_MAP_COPY;
				break;

			case S_IFCHR:
				capabilities =
					BDI_CAP_MAP_DIRECT |
					BDI_CAP_READ_MAP |
					BDI_CAP_WRITE_MAP;
				break;

			default:
				return -EINVAL;
			}
		}

		/* eliminate any capabilities that we can't support on this
		 * device */
		if (!file->f_op->get_unmapped_area)
			capabilities &= ~BDI_CAP_MAP_DIRECT;
		if (!file->f_op->read)
			capabilities &= ~BDI_CAP_MAP_COPY;

		if (flags & MAP_SHARED) {
			/* do checks for writing, appending and locking */
			if ((prot & PROT_WRITE) &&
			    !(file->f_mode & FMODE_WRITE))
				return -EACCES;

			if (IS_APPEND(file->f_path.dentry->d_inode) &&
			    (file->f_mode & FMODE_WRITE))
				return -EACCES;

			if (locks_verify_locked(file->f_path.dentry->d_inode))
				return -EAGAIN;

			if (!(capabilities & BDI_CAP_MAP_DIRECT))
				return -ENODEV;

			if (((prot & PROT_READ)  && !(capabilities & BDI_CAP_READ_MAP))  ||
			    ((prot & PROT_WRITE) && !(capabilities & BDI_CAP_WRITE_MAP)) ||
			    ((prot & PROT_EXEC)  && !(capabilities & BDI_CAP_EXEC_MAP))
			    ) {
				printk("MAP_SHARED not completely supported on !MMU\n");
				return -EINVAL;
			}

			/* we mustn't privatise shared mappings */
			capabilities &= ~BDI_CAP_MAP_COPY;
		}
		else {
			/* we're going to read the file into private memory we
			 * allocate */
			if (!(capabilities & BDI_CAP_MAP_COPY))
				return -ENODEV;

			/* we don't permit a private writable mapping to be
			 * shared with the backing device */
			if (prot & PROT_WRITE)
				capabilities &= ~BDI_CAP_MAP_DIRECT;
		}

		/* handle executable mappings and implied executable
		 * mappings */
		if (file->f_path.mnt->mnt_flags & MNT_NOEXEC) {
			if (prot & PROT_EXEC)
				return -EPERM;
		}
		else if ((prot & PROT_READ) && !(prot & PROT_EXEC)) {
			/* handle implication of PROT_EXEC by PROT_READ */
			if (current->personality & READ_IMPLIES_EXEC) {
				if (capabilities & BDI_CAP_EXEC_MAP)
					prot |= PROT_EXEC;
			}
		}
		else if ((prot & PROT_READ) &&
			 (prot & PROT_EXEC) &&
			 !(capabilities & BDI_CAP_EXEC_MAP)
			 ) {
			/* backing file is not executable, try to copy */
			capabilities &= ~BDI_CAP_MAP_DIRECT;
		}
	}
	else {
		/* anonymous mappings are always memory backed and can be
		 * privately mapped
		 */
		capabilities = BDI_CAP_MAP_COPY;

		/* handle PROT_EXEC implication by PROT_READ */
		if ((prot & PROT_READ) &&
		    (current->personality & READ_IMPLIES_EXEC))
			prot |= PROT_EXEC;
	}

	/* allow the security API to have its say */
	ret = security_file_mmap(file, reqprot, prot, flags, addr, 0);
	if (ret < 0)
		return ret;

	/* looks okay */
	*_capabilities = capabilities;
	return 0;
}

/*
 * we've determined that we can make the mapping, now translate what we
 * now know into VMA flags
 */
static unsigned long determine_vm_flags(struct file *file,
					unsigned long prot,
					unsigned long flags,
					unsigned long capabilities)
{
	unsigned long vm_flags;

	vm_flags = calc_vm_prot_bits(prot) | calc_vm_flag_bits(flags);
	vm_flags |= VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC;