path: root/fs/hugetlbfs/inode.c

/*
 * hugetlbpage-backed filesystem.  Based on ramfs.
 *
 * William Irwin, 2002
 *
 * Copyright (C) 2002 Linus Torvalds.
 */

#include <linux/module.h>
#include <linux/thread_info.h>
#include <asm/current.h>
#include <linux/sched.h>		/* remove ASAP */
#include <linux/fs.h>
#include <linux/mount.h>
#include <linux/file.h>
#include <linux/writeback.h>
#include <linux/pagemap.h>
#include <linux/highmem.h>
#include <linux/init.h>
#include <linux/string.h>
#include <linux/capability.h>
#include <linux/backing-dev.h>
#include <linux/hugetlb.h>
#include <linux/pagevec.h>
#include <linux/quotaops.h>
#include <linux/slab.h>
#include <linux/dnotify.h>
#include <linux/statfs.h>
#include <linux/security.h>

#include <asm/uaccess.h>

/* some random number */
#define HUGETLBFS_MAGIC	0x958458f6

static struct super_operations hugetlbfs_ops;
static struct address_space_operations hugetlbfs_aops;
struct file_operations hugetlbfs_file_operations;
static struct inode_operations hugetlbfs_dir_inode_operations;
static struct inode_operations hugetlbfs_inode_operations;

static struct backing_dev_info hugetlbfs_backing_dev_info = {
	.ra_pages	= 0,	/* No readahead */
	.capabilities	= BDI_CAP_NO_ACCT_DIRTY | BDI_CAP_NO_WRITEBACK,
};

int sysctl_hugetlb_shm_group;

static void huge_pagevec_release(struct pagevec *pvec)
{
	int i;

	for (i = 0; i < pagevec_count(pvec); ++i)
		put_page(pvec->pages[i]);

	pagevec_reinit(pvec);
}

/*
 * huge_pages_needed tries to determine the number of new huge pages that
 * will be required to fully populate this VMA.  This will be equal to
 * the size of the VMA in huge pages minus the number of huge pages
 * (covered by this VMA) that are found in the page cache.
 *
 * Result is in bytes to be compatible with is_hugepage_mem_enough()
 */
static unsigned long
huge_pages_needed(struct address_space *mapping, struct vm_area_struct *vma)
{
	int i;
	struct pagevec pvec;
	unsigned long start = vma->vm_start;
	unsigned long end = vma->vm_end;
	unsigned long hugepages = (end - start) >> HPAGE_SHIFT;
	pgoff_t next = vma->vm_pgoff;
	pgoff_t endpg = next + ((end - start) >> PAGE_SHIFT);

	pagevec_init(&pvec, 0);
	while (next < endpg) {
		if (!pagevec_lookup(&pvec, mapping, next, PAGEVEC_SIZE))
			break;
		for (i = 0; i < pagevec_count(&pvec); i++) {
			struct page *page = pvec.pages[i];
			if (page->index > next)
				next = page->index;
			if (page->index >= endpg)
				break;
			next++;
			hugepages--;
		}
		huge_pagevec_release(&pvec);
	}
	return hugepages << HPAGE_SHIFT;
}

static int hugetlbfs_file_mmap(struct file *file, struct vm_area_struct *vma)
{
	struct inode *inode = file->f_dentry->d_inode;
	struct address_space *mapping = inode->i_mapping;
	unsigned long bytes;
	loff_t len, vma_len;
	int ret;

	if (vma->vm_pgoff & (HPAGE_SIZE / PAGE_SIZE - 1))
		return -EINVAL;

	if (vma->vm_start & ~HPAGE_MASK)
		return -EINVAL;

	if (vma->vm_end & ~HPAGE_MASK)
		return -EINVAL;

	if (vma->vm_end - vma->vm_start < HPAGE_SIZE)
		return -EINVAL;

	bytes = huge_pages_needed(mapping, vma);
	if (!is_hugepage_mem_enough(bytes))
		return -ENOMEM;

	vma_len = (loff_t)(vma->vm_end - vma->vm_start);

	mutex_lock(&inode->i_mutex);
	file_accessed(file);
	vma->vm_flags |= VM_HUGETLB | VM_RESERVED;
	vma->vm_ops = &hugetlb_vm_ops;

	ret = -ENOMEM;
	len = vma_len + ((loff_t)vma->vm_pgoff << PAGE_SHIFT);
	if (!(vma->vm_flags & VM_WRITE) && len > inode->i_size)
		goto out;

	ret = 0;
	hugetlb_prefault_arch_hook(vma->vm_mm);
	if (inode->i_size < len)
		inode->i_size = len;
out:
	mutex_unlock(&inode->i_mutex);

	return ret;
}

/*
 * Called under down_write(mmap_sem).
 */

#ifdef HAVE_ARCH_HUGETLB_UNMAPPED_AREA
unsigned long hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
		unsigned long len, unsigned long pgoff, unsigned long flags);
#else
static unsigned long
hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
		unsigned long len, unsigned long pgoff, unsigned long flags)
{
	struct mm_struct *mm = current->mm;
	struct vm_area_struct *vma;
	unsigned long start_addr;

	if (len & ~HPAGE_MASK)
		return -EINVAL;
	if (</