mmap.c

linux下内存管理源代码。。。精、简、强!

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

/* 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.
	 */

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

	free = atomic_read(&buffermem_pages);
	free += atomic_read(&page_cache_size);
	free += nr_free_pages();
	free += nr_swap_pages;
	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(&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(&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 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
}

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;
	struct vm_area_struct * vma;
	int correct_wcount = 0;
	int error;

	if (file && (!file->f_op || !file->f_op->mmap))
		return -ENODEV;

	if ((len = PAGE_ALIGN(len)) == 0)
		return addr;

	if (len > TASK_SIZE || addr > TASK_SIZE-len)
		return -EINVAL;

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

	/* Too many mappings? */
	if (mm->map_count > MAX_MAP_COUNT)
		return -ENOMEM;

	/* mlock MCL_FUTURE? */
	if (mm->def_flags & VM_LOCKED) {
		unsigned long locked = mm->locked_vm << PAGE_SHIFT;
		locked += len;
		if (locked > current->rlim[RLIMIT_MEMLOCK].rlim_cur)
			return -EAGAIN;
	}

	/* Do simple checking here so the lower-level routines won't have
	 * to. we assume access permissions have been handled by the open
	 * of the memory object, so we don't do any here.
	 */
	if (file != NULL) {
		switch (flags & MAP_TYPE) {
		case MAP_SHARED:
			if ((prot & PROT_WRITE) && !(file->f_mode & FMODE_WRITE))
				return -EACCES;

			/* Make sure we don't allow writing to an append-only file.. */
			if (IS_APPEND(file->f_dentry->d_inode) && (file->f_mode & FMODE_WRITE))
				return -EACCES;

			/* make sure there are no mandatory locks on the file. */
			if (locks_verify_locked(file->f_dentry->d_inode))
				return -EAGAIN;

			/* fall through */
		case MAP_PRIVATE:
			if (!(file->f_mode & FMODE_READ))
				return -EACCES;
			break;

		default:
			return -EINVAL;
		}
	}

	/* Obtain the address to map to. we verify (or select) it and ensure
	 * that it represents a valid section of the address space.
	 */
	if (flags & MAP_FIXED) {
		if (addr & ~PAGE_MASK)
			return -EINVAL;
	} else {
		addr = get_unmapped_area(addr, len);
		if (!addr)
			return -ENOMEM;
	}

	/* Determine the object being mapped and call the appropriate
	 * specific mapper. the address has already been validated, but
	 * not unmapped, but the maps are removed from the list.
	 */
	vma = kmem_cache_alloc(vm_area_cachep, SLAB_KERNEL);
	if (!vma)
		return -ENOMEM;

	vma->vm_mm = mm;
	vma->vm_start = addr;
	vma->vm_end = addr + len;
	vma->vm_flags = vm_flags(prot,flags) | mm->def_flags;

	if (file) {
		VM_ClearReadHint(vma);
		vma->vm_raend = 0;

		if (file->f_mode & FMODE_READ)
			vma->vm_flags |= VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC;
		if (flags & MAP_SHARED) {
			vma->vm_flags |= VM_SHARED | VM_MAYSHARE;

			/* This looks strange, but when we don't have the file open
			 * for writing, we can demote the shared mapping to a simpler
			 * private mapping. That also takes care of a security hole
			 * with ptrace() writing to a shared mapping without write
			 * permissions.
			 *
			 * We leave the VM_MAYSHARE bit on, just to get correct output
			 * from /proc/xxx/maps..
			 */
			if (!(file->f_mode & FMODE_WRITE))
				vma->vm_flags &= ~(VM_MAYWRITE | VM_SHARED);
		}
	} else {
		vma->vm_flags |= VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC;
		if (flags & MAP_SHARED)
			vma->vm_flags |= VM_SHARED | VM_MAYSHARE;
	}
	vma->vm_page_prot = protection_map[vma->vm_flags & 0x0f];
	vma->vm_ops = NULL;
	vma->vm_pgoff = pgoff;
	vma->vm_file = NULL;
	vma->vm_private_data = NULL;

	/* Clear old maps */
	error = -ENOMEM;
	if (do_munmap(mm, addr, len))
		goto free_vma;

	/* Check against address space limit. */
	if ((mm->total_vm << PAGE_SHIFT) + len
	    > current->rlim[RLIMIT_AS].rlim_cur)
		goto free_vma;

	/* Private writable mapping? Check memory availability.. */
	if ((vma->vm_flags & (VM_SHARED | VM_WRITE)) == VM_WRITE &&
	    !(flags & MAP_NORESERVE)				 &&
	    !vm_enough_memory(len >> PAGE_SHIFT))
		goto free_vma;

	if (file) {
		if (vma->vm_flags & VM_DENYWRITE) {
			error = deny_write_access(file);
			if (error)
				goto free_vma;
			correct_wcount = 1;
		}
		vma->vm_file = file;
		get_file(file);
		error = file->f_op->mmap(file, vma);
		if (error)
			goto unmap_and_free_vma;
	} else if (flags & MAP_SHARED) {
		error = shmem_zero_setup(vma);
		if (error)
			goto free_vma;
	}

	/* Can addr have changed??
	 *
	 * Answer: Yes, several device drivers can do it in their
	 *         f_op->mmap method. -DaveM
	 */
	flags = vma->vm_flags;
	addr = vma->vm_start;

	insert_vm_struct(mm, vma);
	if (correct_wcount)
		atomic_inc(&file->f_dentry->d_inode->i_writecount);
	
	mm->total_vm += len >> PAGE_SHIFT;
	if (flags & VM_LOCKED) {
		mm->locked_vm += len >> PAGE_SHIFT;
		make_pages_present(addr, addr + len);
	}
	return addr;

unmap_and_free_vma:
	if (correct_wcount)
		atomic_inc(&file->f_dentry->d_inode->i_writecount);
	vma->vm_file = NULL;
	fput(file);
	/* Undo any partial mapping done by a device driver. */
	flush_cache_range(mm, vma->vm_start, vma->vm_end);
	zap_page_range(mm, vma->vm_start, vma->vm_end - vma->vm_start);
	flush_tlb_range(mm, vma->vm_start, vma->vm_end);
free_vma:
	kmem_cache_free(vm_area_cachep, vma);
	return error;
}

/* Get an address range which is currently unmapped.
 * For mmap() without MAP_FIXED and shmat() with addr=0.
 * Return value 0 means ENOMEM.
 */
#ifndef HAVE_ARCH_UNMAPPED_AREA
unsigned long get_unmapped_area(unsigned long addr, unsigned long len)
{
	struct vm_area_struct * vmm;

	if (len > TASK_SIZE)
		return 0;
	if (!addr)
		addr = TASK_UNMAPPED_BASE;
	addr = PAGE_ALIGN(addr);

	for (vmm = find_vma(current->mm, addr); ; vmm = vmm->vm_next) {
		/* At this point:  (!vmm || addr < vmm->vm_end). */
		if (TASK_SIZE - len < addr)
			return 0;
		if (!vmm || addr + len <= vmm->vm_start)
			return addr;
		addr = vmm->vm_end;
	}
}
#endif

#define vm_avl_empty	(struct vm_area_struct *) NULL

#include "mmap_avl.c"

/* Look up the first VMA which satisfies  addr < vm_end,  NULL if none. */
struct vm_area_struct * find_vma(struct mm_struct * mm, unsigned long addr)
{
	struct vm_area_struct *vma = NULL;

	if (mm) {
		/* Check the cache first. */
		/* (Cache hit rate is typically around 35%.) */
		vma = mm->mmap_cache;
		if (!(vma && vma->vm_end > addr && vma->vm_start <= addr)) {
			if (!mm->mmap_avl) {
				/* Go through the linear list. */
				vma = mm->mmap;
				while (vma && vma->vm_end <= addr)
					vma = vma->vm_next;
			} else {
				/* Then go through the AVL tree quickly. */
				struct vm_area_struct * tree = mm->mmap_avl;
				vma = NULL;
				for (;;) {
					if (tree == vm_avl_empty)
						break;
					if (tree->vm_end > addr) {
						vma = tree;
						if (tree->vm_start <= addr)
							break;
						tree = tree->vm_avl_left;
					} else
						tree = tree->vm_avl_right;
				}
			}
			if (vma)
				mm->mmap_cache = vma;
		}
	}
	return vma;
}

/* Same as find_vma, but also return a pointer to the previous VMA in *pprev. */
struct vm_area_struct * find_vma_prev(struct mm_struct * mm, unsigned long addr,
				      struct vm_area_struct **pprev)
{
	if (mm) {
		if (!mm->mmap_avl) {
			/* Go through the linear list. */
			struct vm_area_struct * prev = NULL;
			struct vm_area_struct * vma = mm->mmap;
			while (vma && vma->vm_end <= addr) {
				prev = vma;
				vma = vma->vm_next;
			}
			*pprev = prev;
			return vma;
		} else {
			/* Go through the AVL tree quickly. */
			struct vm_area_struct * vma = NULL;
			struct vm_area_struct * last_turn_right = NULL;
			struct vm_area_struct * prev = NULL;
			struct vm_area_struct * tree = mm->mmap_avl;
			for (;;) {
				if (tree == vm_avl_empty)
					break;
				if (tree->vm_end > addr) {
					vma = tree;
					prev = last_turn_right;
					if (tree->vm_start <= addr)
						break;
					tree = tree->vm_avl_left;
				} else {
					last_turn_right = tree;
					tree = tree->vm_avl_right;
				}
			}
			if (vma) {
				if (vma->vm_avl_left != vm_avl_empty) {
					prev = vma->vm_avl_left;
					while (prev->vm_avl_right != vm_avl_empty)
						prev = prev->vm_avl_right;
				}
				if ((prev ? prev->vm_next : mm->mmap) != vma)
					printk("find_vma_prev: tree inconsistent with list\n");
				*pprev = prev;