mmap.c

ARM 嵌入式 系统 设计与实例开发 实验教材 二源码

/*
 *	linux/mm/mmap.c
 *
 * Written by obz.
 */
#include <linux/slab.h>
#include <linux/shm.h>
#include <linux/mman.h>
#include <linux/pagemap.h>
#include <linux/swap.h>
#include <linux/swapctl.h>
#include <linux/smp_lock.h>
#include <linux/init.h>
#include <linux/file.h>
#include <linux/fs.h>
#include <linux/personality.h>

#include <asm/uaccess.h>
#include <asm/pgalloc.h>
#include <asm/tlb.h>

extern void unmap_page_range(mmu_gather_t *tlb, struct mm_struct *mm, unsigned long start, unsigned long end);

/*
 * WARNING: the debugging will use recursive algorithms so never enable this
 * unless you know what you are doing.
 */
#undef DEBUG_MM_RB

/* description of effects of mapping type and prot in current implementation.
 * this is due to the limited x86 page protection hardware.  The expected
 * behavior is in parens:
 *
 * map_type	prot
 *		PROT_NONE	PROT_READ	PROT_WRITE	PROT_EXEC
 * MAP_SHARED	r: (no) no	r: (yes) yes	r: (no) yes	r: (no) yes
 *		w: (no) no	w: (no) no	w: (yes) yes	w: (no) no
 *		x: (no) no	x: (no) yes	x: (no) yes	x: (yes) yes
 *		
 * MAP_PRIVATE	r: (no) no	r: (yes) yes	r: (no) yes	r: (no) yes
 *		w: (no) no	w: (no) no	w: (copy) copy	w: (no) no
 *		x: (no) no	x: (no) yes	x: (no) yes	x: (yes) yes
 *
 */
pgprot_t protection_map[16] = {
	__P000, __P001, __P010, __P011, __P100, __P101, __P110, __P111,
	__S000, __S001, __S010, __S011, __S100, __S101, __S110, __S111
};

int sysctl_overcommit_memory;

/* Check that a process has enough memory to allocate a
 * new virtual mapping.
 */
int vm_enough_memory(long pages)
{
	/* Stupid algorithm to decide if we have enough memory: while
	 * simple, it hopefully works in most obvious cases.. Easy to
	 * fool it, but this should catch most mistakes.
	 */
	/* 23/11/98 NJC: Somewhat less stupid version of algorithm,
	 * which tries to do "TheRightThing".  Instead of using half of
	 * (buffers+cache), use the minimum values.  Allow an extra 2%
	 * of num_physpages for safety margin.
	 */

	unsigned long free;
	
        /* Sometimes we want to use more memory than we have. */
	if (sysctl_overcommit_memory)
	    return 1;

	/* The page cache contains buffer pages these days.. */
	free = atomic_read(&page_cache_size);
	free += nr_free_pages();
	free += nr_swap_pages;

	/*
	 * This double-counts: the nrpages are both in the page-cache
	 * and in the swapper space. At the same time, this compensates
	 * for the swap-space over-allocation (ie "nr_swap_pages" being
	 * too small.
	 */
	free += swapper_space.nrpages;

	/*
	 * The code below doesn't account for free space in the inode
	 * and dentry slab cache, slab cache fragmentation, inodes and
	 * dentries which will become freeable under VM load, etc.
	 * Lets just hope all these (complex) factors balance out...
	 */
	free += (dentry_stat.nr_unused * sizeof(struct dentry)) >> PAGE_SHIFT;
	free += (inodes_stat.nr_unused * sizeof(struct inode)) >> PAGE_SHIFT;

	return free > pages;
}

/* Remove one vm structure from the inode's i_mapping address space. */
static inline void __remove_shared_vm_struct(struct vm_area_struct *vma)
{
	struct file * file = vma->vm_file;

	if (file) {
		struct inode *inode = file->f_dentry->d_inode;
		if (vma->vm_flags & VM_DENYWRITE)
			atomic_inc(&inode->i_writecount);
		if(vma->vm_next_share)
			vma->vm_next_share->vm_pprev_share = vma->vm_pprev_share;
		*vma->vm_pprev_share = vma->vm_next_share;
	}
}

static inline void remove_shared_vm_struct(struct vm_area_struct *vma)
{
	lock_vma_mappings(vma);
	__remove_shared_vm_struct(vma);
	unlock_vma_mappings(vma);
}

void lock_vma_mappings(struct vm_area_struct *vma)
{
	struct address_space *mapping;

	mapping = NULL;
	if (vma->vm_file)
		mapping = vma->vm_file->f_dentry->d_inode->i_mapping;
	if (mapping)
		spin_lock(&mapping->i_shared_lock);
}

void unlock_vma_mappings(struct vm_area_struct *vma)
{
	struct address_space *mapping;

	mapping = NULL;
	if (vma->vm_file)
		mapping = vma->vm_file->f_dentry->d_inode->i_mapping;
	if (mapping)
		spin_unlock(&mapping->i_shared_lock);
}

/*
 *  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.
 */
asmlinkage unsigned long sys_brk(unsigned long brk)
{
	unsigned long rlim, retval;
	unsigned long newbrk, oldbrk;
	struct mm_struct *mm = current->mm;

	down_write(&mm->mmap_sem);

	if (brk < mm->end_code)
		goto out;
	newbrk = PAGE_ALIGN(brk);
	oldbrk = PAGE_ALIGN(mm->brk);
	if (oldbrk == newbrk)
		goto set_brk;

	/* Always allow shrinking brk. */
	if (brk <= mm->brk) {
		if (!do_munmap(mm, newbrk, oldbrk-newbrk))
			goto set_brk;
		goto out;
	}

	/* Check against rlimit.. */
	rlim = current->rlim[RLIMIT_DATA].rlim_cur;
	if (rlim < RLIM_INFINITY && brk - mm->start_data > rlim)
		goto out;

	/* Check against existing mmap mappings. */
	if (find_vma_intersection(mm, oldbrk, newbrk+PAGE_SIZE))
		goto out;

	/* Check if we have enough memory.. */
	if (!vm_enough_memory((newbrk-oldbrk) >> PAGE_SHIFT))
		goto out;

	/* Ok, looks good - let it rip. */
	if (do_brk(oldbrk, newbrk-oldbrk) != oldbrk)
		goto out;
set_brk:
	mm->brk = brk;
out:
	retval = mm->brk;
	up_write(&mm->mmap_sem);
	return retval;
}

/* Combine the mmap "prot" and "flags" argument into one "vm_flags" used
 * internally. Essentially, translate the "PROT_xxx" and "MAP_xxx" bits
 * into "VM_xxx".
 */
static inline unsigned long calc_vm_flags(unsigned long prot, unsigned long flags)
{
#define _trans(x,bit1,bit2) \
((bit1==bit2)?(x&bit1):(x&bit1)?bit2:0)

	unsigned long prot_bits, flag_bits;
	prot_bits =
		_trans(prot, PROT_READ, VM_READ) |
		_trans(prot, PROT_WRITE, VM_WRITE) |
		_trans(prot, PROT_EXEC, VM_EXEC);
	flag_bits =
		_trans(flags, MAP_GROWSDOWN, VM_GROWSDOWN) |
		_trans(flags, MAP_DENYWRITE, VM_DENYWRITE) |
		_trans(flags, MAP_EXECUTABLE, VM_EXECUTABLE);
	return prot_bits | flag_bits;
#undef _trans
}

#ifdef DEBUG_MM_RB
static int browse_rb(rb_node_t * rb_node) {
	int i = 0;
	if (rb_node) {
		i++;
		i += browse_rb(rb_node->rb_left);
		i += browse_rb(rb_node->rb_right);
	}
	return i;
}

static void validate_mm(struct mm_struct * mm) {
	int bug = 0;
	int i = 0;
	struct vm_area_struct * tmp = mm->mmap;
	while (tmp) {
		tmp = tmp->vm_next;
		i++;
	}
	if (i != mm->map_count)
		printk("map_count %d vm_next %d\n", mm->map_count, i), bug = 1;
	i = browse_rb(mm->mm_rb.rb_node);
	if (i != mm->map_count)
		printk("map_count %d rb %d\n", mm->map_count, i), bug = 1;
	if (bug)
		BUG();
}
#else
#define validate_mm(mm) do { } while (0)
#endif

static struct vm_area_struct * find_vma_prepare(struct mm_struct * mm, unsigned long addr,
						struct vm_area_struct ** pprev,
						rb_node_t *** rb_link, rb_node_t ** rb_parent)
{
	struct vm_area_struct * vma;
	rb_node_t ** __rb_link, * __rb_parent, * rb_prev;

	__rb_link = &mm->mm_rb.rb_node;
	rb_prev = __rb_parent = NULL;
	vma = NULL;

	while (*__rb_link) {
		struct vm_area_struct *vma_tmp;

		__rb_parent = *__rb_link;
		vma_tmp = rb_entry(__rb_parent, struct vm_area_struct, vm_rb);

		if (vma_tmp->vm_end > addr) {
			vma = vma_tmp;
			if (vma_tmp->vm_start <= addr)
				return vma;
			__rb_link = &__rb_parent->rb_left;
		} else {
			rb_prev = __rb_parent;
			__rb_link = &__rb_parent->rb_right;
		}
	}

	*pprev = NULL;
	if (rb_prev)
		*pprev = rb_entry(rb_prev, struct vm_area_struct, vm_rb);
	*rb_link = __rb_link;
	*rb_parent = __rb_parent;
	return vma;
}

static inline void __vma_link_list(struct mm_struct * mm, struct vm_area_struct * vma, struct vm_area_struct * prev,
				   rb_node_t * rb_parent)
{
	if (prev) {
		vma->vm_next = prev->vm_next;
		prev->vm_next = vma;
	} else {
		mm->mmap = vma;
		if (rb_parent)
			vma->vm_next = rb_entry(rb_parent, struct vm_area_struct, vm_rb);
		else
			vma->vm_next = NULL;
	}
}

static inline void __vma_link_rb(struct mm_struct * mm, struct vm_area_struct * vma,
				 rb_node_t ** rb_link, rb_node_t * rb_parent)
{
	rb_link_node(&vma->vm_rb, rb_parent, rb_link);
	rb_insert_color(&vma->vm_rb, &mm->mm_rb);
}

static inline void __vma_link_file(struct vm_area_struct * vma)
{
	struct file * file;

	file = vma->vm_file;
	if (file) {
		struct inode * inode = file->f_dentry->d_inode;
		struct address_space *mapping = inode->i_mapping;
		struct vm_area_struct **head;

		if (vma->vm_flags & VM_DENYWRITE)
			atomic_dec(&inode->i_writecount);

		head = &mapping->i_mmap;
		if (vma->vm_flags & VM_SHARED)
			head = &mapping->i_mmap_shared;
      
		/* insert vma into inode's share list */
		if((vma->vm_next_share = *head) != NULL)
			(*head)->vm_pprev_share = &vma->vm_next_share;
		*head = vma;
		vma->vm_pprev_share = head;
	}
}

static void __vma_link(struct mm_struct * mm, struct vm_area_struct * vma,  struct vm_area_struct * prev,
		       rb_node_t ** rb_link, rb_node_t * rb_parent)
{
	__vma_link_list(mm, vma, prev, rb_parent);
	__vma_link_rb(mm, vma, rb_link, rb_parent);
	__vma_link_file(vma);
}

static inline void vma_link(struct mm_struct * mm, struct vm_area_struct * vma, struct vm_area_struct * prev,
			    rb_node_t ** rb_link, rb_node_t * rb_parent)
{
	lock_vma_mappings(vma);
	spin_lock(&mm->page_table_lock);
	__vma_link(mm, vma, prev, rb_link, rb_parent);
	spin_unlock(&mm->page_table_lock);
	unlock_vma_mappings(vma);

	mm->map_count++;
	validate_mm(mm);
}

static int vma_merge(struct mm_struct * mm, struct vm_area_struct * prev,
		     rb_node_t * rb_parent, unsigned long addr, unsigned long end, unsigned long vm_flags)
{
	spinlock_t * lock = &mm->page_table_lock;
	if (!prev) {
		prev = rb_entry(rb_parent, struct vm_area_struct, vm_rb);
		goto merge_next;
	}
	if (prev->vm_end == addr && can_vma_merge(prev, vm_flags)) {
		struct vm_area_struct * next;

		spin_lock(lock);
		prev->vm_end = end;
		next = prev->vm_next;
		if (next && prev->vm_end == next->vm_start && can_vma_merge(next, vm_flags)) {
			prev->vm_end = next->vm_end;
			__vma_unlink(mm, next, prev);
			spin_unlock(lock);

			mm->map_count--;
			kmem_cache_free(vm_area_cachep, next);
			return 1;
		}
		spin_unlock(lock);
		return 1;
	}

	prev = prev->vm_next;
	if (prev) {
 merge_next:
		if (!can_vma_merge(prev, vm_flags))
			return 0;
		if (end == prev->vm_start) {
			spin_lock(lock);
			prev->vm_start = addr;
			spin_unlock(lock);
			return 1;
		}
	}

	return 0;
}

unsigned long do_mmap_pgoff(struct file * file, unsigned long addr, unsigned long len,
	unsigned long prot, unsigned long flags, unsigned long pgoff)
{
	struct mm_struct * mm = current->mm;