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/kernel.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/ctype.h>
#include <linux/backing-dev.h>
#include <linux/hugetlb.h>
#include <linux/pagevec.h>
#include <linux/parser.h>
#include <linux/mman.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 const struct super_operations hugetlbfs_ops;
static const struct address_space_operations hugetlbfs_aops;
const struct file_operations hugetlbfs_file_operations;
static const struct inode_operations hugetlbfs_dir_inode_operations;
static const 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_AND_WRITEBACK,
};

int sysctl_hugetlb_shm_group;

enum {
	Opt_size, Opt_nr_inodes,
	Opt_mode, Opt_uid, Opt_gid,
	Opt_err,
};

static match_table_t tokens = {
	{Opt_size,	"size=%s"},
	{Opt_nr_inodes,	"nr_inodes=%s"},
	{Opt_mode,	"mode=%o"},
	{Opt_uid,	"uid=%u"},
	{Opt_gid,	"gid=%u"},
	{Opt_err,	NULL},
};

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);
}

static int hugetlbfs_file_mmap(struct file *file, struct vm_area_struct *vma)
{
	struct inode *inode = file->f_path.dentry->d_inode;
	loff_t len, vma_len;
	int ret;

	/*
	 * vma address alignment (but not the pgoff alignment) has
	 * already been checked by prepare_hugepage_range.  If you add
	 * any error returns here, do so after setting VM_HUGETLB, so
	 * is_vm_hugetlb_page tests below unmap_region go the right
	 * way when do_mmap_pgoff unwinds (may be important on powerpc
	 * and ia64).
	 */
	vma->vm_flags |= VM_HUGETLB | VM_RESERVED;
	vma->vm_ops = &hugetlb_vm_ops;

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

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

	mutex_lock(&inode->i_mutex);
	file_accessed(file);

	ret = -ENOMEM;
	len = vma_len + ((loff_t)vma->vm_pgoff << PAGE_SHIFT);

	if (vma->vm_flags & VM_MAYSHARE &&
	    hugetlb_reserve_pages(inode, vma->vm_pgoff >> (HPAGE_SHIFT-PAGE_SHIFT),
				  len >> HPAGE_SHIFT))
		goto out;

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

	return ret;
}

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

#ifndef HAVE_ARCH_HUGETLB_UNMAPPED_AREA
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 (len > TASK_SIZE)
		return -ENOMEM;

	if (flags & MAP_FIXED) {
		if (prepare_hugepage_range(addr, len))
			return -EINVAL;
		return addr;
	}

	if (addr) {
		addr = ALIGN(addr, HPAGE_SIZE);
		vma = find_vma(mm, addr);
		if (TASK_SIZE - len >= addr &&
		    (!vma || addr + len <= vma->vm_start))
			return addr;
	}

	start_addr = mm->free_area_cache;

	if (