inode.c

来自「Linux Kernel 2.6.9 for OMAP1710」· C语言 代码 · 共 837 行 · 第 1/2 页

/*
 * 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/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 */
	.memory_backed	= 1,	/* Does not contribute to dirty memory */
};

int sysctl_hugetlb_shm_group;

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;
	loff_t len, vma_len;
	int ret;

	if ((vma->vm_flags & (VM_MAYSHARE | VM_WRITE)) == VM_WRITE)
		return -EINVAL;

	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;

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

	down(&inode->i_sem);
	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 = hugetlb_prefault(mapping, vma);
	if (ret)
		goto out;

	if (inode->i_size < len)
		inode->i_size = len;
out:
	up(&inode->i_sem);

	return ret;
}

/*
 * Called under down_write(mmap_sem), page_table_lock is not held
 */

#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;

	if (len & ~HPAGE_MASK)
		return -EINVAL;
	if (len > TASK_SIZE)
		return -ENOMEM;

	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;
	}

	addr = ALIGN(mm->free_area_cache, HPAGE_SIZE);

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

/*
 * Read a page. Again trivial. If it didn't already exist
 * in the page cache, it is zero-filled.
 */
static int hugetlbfs_readpage(struct file *file, struct page * page)
{
	unlock_page(page);
	return -EINVAL;
}

static int hugetlbfs_prepare_write(struct file *file,
			struct page *page, unsigned offset, unsigned to)
{
	return -EINVAL;
}

static int hugetlbfs_commit_write(struct file *file,
			struct page *page, unsigned offset, unsigned to)
{
	return -EINVAL;
}

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);
}

void truncate_huge_page(struct page *page)
{
	clear_page_dirty(page);
	ClearPageUptodate(page);
	remove_from_page_cache(page);
	put_page(page);
}

void truncate_hugepages(struct address_space *mapping, loff_t lstart)
{
	const pgoff_t start = lstart >> HPAGE_SHIFT;
	struct pagevec pvec;
	pgoff_t next;
	int i;

	pagevec_init(&pvec, 0);
	next = start;
	while (1) {
		if (!pagevec_lookup(&pvec, mapping, next, PAGEVEC_SIZE)) {
			if (next == start)
				break;
			next = start;
			continue;
		}

		for (i = 0; i < pagevec_count(&pvec); ++i) {
			struct page *page = pvec.pages[i];

			lock_page(page);
			if (page->index > next)
				next = page->index;
			++next;
			truncate_huge_page(page);
			unlock_page(page);
			hugetlb_put_quota(mapping);
		}
		huge_pagevec_release(&pvec);
	}
	BUG_ON(!lstart && mapping->nrpages);
}

static void hugetlbfs_delete_inode(struct inode *inode)
{
	struct hugetlbfs_sb_info *sbinfo = HUGETLBFS_SB(inode->i_sb);

	hlist_del_init(&inode->i_hash);
	list_del_init(&inode->i_list);
	inode->i_state |= I_FREEING;
	inodes_stat.nr_inodes--;
	spin_unlock(&inode_lock);

	if (inode->i_data.nrpages)
		truncate_hugepages(&inode->i_data, 0);

	security_inode_delete(inode);

	if (sbinfo->free_inodes >= 0) {
		spin_lock(&sbinfo->stat_lock);
		sbinfo->free_inodes++;
		spin_unlock(&sbinfo->stat_lock);
	}

	clear_inode(inode);
	destroy_inode(inode);
}

static void hugetlbfs_forget_inode(struct inode *inode)
{
	struct super_block *super_block = inode->i_sb;
	struct hugetlbfs_sb_info *sbinfo = HUGETLBFS_SB(super_block);

	if (hlist_unhashed(&inode->i_hash))
		goto out_truncate;

	if (!(inode->i_state & (I_DIRTY|I_LOCK))) {
		list_del(&inode->i_list);
		list_add(&inode->i_list, &inode_unused);
	}
	inodes_stat.nr_unused++;
	if (!super_block || (super_block->s_flags & MS_ACTIVE)) {
		spin_unlock(&inode_lock);
		return;
	}

	/* write_inode_now() ? */
	inodes_stat.nr_unused--;
	hlist_del_init(&inode->i_hash);
out_truncate:
	list_del_init(&inode->i_list);
	inode->i_state |= I_FREEING;
	inodes_stat.nr_inodes--;
	spin_unlock(&inode_lock);
	if (inode->i_data.nrpages)
		truncate_hugepages(&inode->i_data, 0);

	if (sbinfo->free_inodes >= 0) {
		spin_lock(&sbinfo->stat_lock);
		sbinfo->free_inodes++;
		spin_unlock(&sbinfo->stat_lock);
	}

	clear_inode(inode);
	destroy_inode(inode);
}

static void hugetlbfs_drop_inode(struct inode *inode)
{
	if (!inode->i_nlink)
		hugetlbfs_delete_inode(inode);
	else
		hugetlbfs_forget_inode(inode);
}

/*
 * h_pgoff is in HPAGE_SIZE units.
 * vma->vm_pgoff is in PAGE_SIZE units.
 */
static inline void
hugetlb_vmtruncate_list(struct prio_tree_root *root, unsigned long h_pgoff)
{
	struct vm_area_struct *vma;
	struct prio_tree_iter iter;

	vma_prio_tree_foreach(vma, &iter, root, h_pgoff, ULONG_MAX) {
		unsigned long h_vm_pgoff;
		unsigned long v_length;
		unsigned long v_offset;

		h_vm_pgoff = vma->vm_pgoff >> (HPAGE_SHIFT - PAGE_SHIFT);
		v_offset = (h_pgoff - h_vm_pgoff) << HPAGE_SHIFT;
		/*
		 * Is this VMA fully outside the truncation point?
		 */
		if (h_vm_pgoff >= h_pgoff)
			v_offset = 0;

		v_length = vma->vm_end - vma->vm_start;

		zap_hugepage_range(vma,
				vma->vm_start + v_offset,
				v_length - v_offset);
	}
}

/*
 * Expanding truncates are not allowed.
 */
static int hugetlb_vmtruncate(struct inode *inode, loff_t offset)
{
	unsigned long pgoff;
	struct address_space *mapping = inode->i_mapping;

	if (offset > inode->i_size)
		return -EINVAL;

	BUG_ON(offset & ~HPAGE_MASK);
	pgoff = offset >> HPAGE_SHIFT;

	inode->i_size = offset;
	spin_lock(&mapping->i_mmap_lock);
	if (!prio_tree_empty(&mapping->i_mmap))
		hugetlb_vmtruncate_list(&mapping->i_mmap, pgoff);
	spin_unlock(&mapping->i_mmap_lock);
	truncate_hugepages(mapping, offset);
	return 0;
}

static int hugetlbfs_setattr(struct dentry *dentry, struct iattr *attr)
{
	struct inode *inode = dentry->d_inode;
	int error;
	unsigned int ia_valid = attr->ia_valid;

	BUG_ON(!inode);

	error = inode_change_ok(inode, attr);
	if (error)
		goto out;

	if (ia_valid & ATTR_SIZE) {
		error = -EINVAL;
		if (!(attr->ia_size & ~HPAGE_MASK))
			error = hugetlb_vmtruncate(inode, attr->ia_size);
		if (error)
			goto out;
		attr->ia_valid &= ~ATTR_SIZE;
	}
	error = inode_setattr(inode, attr);
out:
	return error;
}

static struct inode *hugetlbfs_get_inode(struct super_block *sb, uid_t uid, 
					gid_t gid, int mode, dev_t dev)
{
	struct inode *inode;
	struct hugetlbfs_sb_info *sbinfo = HUGETLBFS_SB(sb);

	if (sbinfo->free_inodes >= 0) {
		spin_lock(&sbinfo->stat_lock);
		if (!sbinfo->free_inodes) {
			spin_unlock(&sbinfo->stat_lock);
			return NULL;
		}
		sbinfo->free_inodes--;
		spin_unlock(&sbinfo->stat_lock);
	}

	inode = new_inode(sb);
	if (inode) {
		struct hugetlbfs_inode_info *info;
		inode->i_mode = mode;
		inode->i_uid = uid;
		inode->i_gid = gid;
		inode->i_blksize = HPAGE_SIZE;
		inode->i_blocks = 0;
		inode->i_mapping->a_ops = &hugetlbfs_aops;
		inode->i_mapping->backing_dev_info =&hugetlbfs_backing_dev_info;
		inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME;
		info = HUGETLBFS_I(inode);
		mpol_shared_policy_init(&info->policy);
		switch (mode & S_IFMT) {
		default:
			init_special_inode(inode, mode, dev);
			break;
		case S_IFREG:
			inode->i_op = &hugetlbfs_inode_operations;
			inode->i_fop = &hugetlbfs_file_operations;
			break;
		case S_IFDIR:
			inode->i_op = &hugetlbfs_dir_inode_operations;
			inode->i_fop = &simple_dir_operations;

			/* directory inodes start off with i_nlink == 2 (for "." entry) */
			inode->i_nlink++;
			break;
		case S_IFLNK:
			inode->i_op = &page_symlink_inode_operations;
			break;
		}
	}
	return inode;
}

/*
 * File creation. Allocate an inode, and we're done..
 */
static int hugetlbfs_mknod(struct inode *dir,
			struct dentry *dentry, int mode, dev_t dev)
{
	struct inode *inode;
	int error = -ENOSPC;
	gid_t gid;