inode.c

linux 内核源代码

		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) */
			inc_nlink(inode);
			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;

	if (dir->i_mode & S_ISGID) {
		gid = dir->i_gid;
		if (S_ISDIR(mode))
			mode |= S_ISGID;
	} else {
		gid = current->fsgid;
	}
	inode = hugetlbfs_get_inode(dir->i_sb, current->fsuid, gid, mode, dev);
	if (inode) {
		dir->i_ctime = dir->i_mtime = CURRENT_TIME;
		d_instantiate(dentry, inode);
		dget(dentry);	/* Extra count - pin the dentry in core */
		error = 0;
	}
	return error;
}

static int hugetlbfs_mkdir(struct inode *dir, struct dentry *dentry, int mode)
{
	int retval = hugetlbfs_mknod(dir, dentry, mode | S_IFDIR, 0);
	if (!retval)
		inc_nlink(dir);
	return retval;
}

static int hugetlbfs_create(struct inode *dir, struct dentry *dentry, int mode, struct nameidata *nd)
{
	return hugetlbfs_mknod(dir, dentry, mode | S_IFREG, 0);
}

static int hugetlbfs_symlink(struct inode *dir,
			struct dentry *dentry, const char *symname)
{
	struct inode *inode;
	int error = -ENOSPC;
	gid_t gid;

	if (dir->i_mode & S_ISGID)
		gid = dir->i_gid;
	else
		gid = current->fsgid;

	inode = hugetlbfs_get_inode(dir->i_sb, current->fsuid,
					gid, S_IFLNK|S_IRWXUGO, 0);
	if (inode) {
		int l = strlen(symname)+1;
		error = page_symlink(inode, symname, l);
		if (!error) {
			d_instantiate(dentry, inode);
			dget(dentry);
		} else
			iput(inode);
	}
	dir->i_ctime = dir->i_mtime = CURRENT_TIME;

	return error;
}

/*
 * mark the head page dirty
 */
static int hugetlbfs_set_page_dirty(struct page *page)
{
	struct page *head = compound_head(page);

	SetPageDirty(head);
	return 0;
}

static int hugetlbfs_statfs(struct dentry *dentry, struct kstatfs *buf)
{
	struct hugetlbfs_sb_info *sbinfo = HUGETLBFS_SB(dentry->d_sb);

	buf->f_type = HUGETLBFS_MAGIC;
	buf->f_bsize = HPAGE_SIZE;
	if (sbinfo) {
		spin_lock(&sbinfo->stat_lock);
		/* If no limits set, just report 0 for max/free/used
		 * blocks, like simple_statfs() */
		if (sbinfo->max_blocks >= 0) {
			buf->f_blocks = sbinfo->max_blocks;
			buf->f_bavail = buf->f_bfree = sbinfo->free_blocks;
			buf->f_files = sbinfo->max_inodes;
			buf->f_ffree = sbinfo->free_inodes;
		}
		spin_unlock(&sbinfo->stat_lock);
	}
	buf->f_namelen = NAME_MAX;
	return 0;
}

static void hugetlbfs_put_super(struct super_block *sb)
{
	struct hugetlbfs_sb_info *sbi = HUGETLBFS_SB(sb);

	if (sbi) {
		sb->s_fs_info = NULL;
		kfree(sbi);
	}
}

static inline int hugetlbfs_dec_free_inodes(struct hugetlbfs_sb_info *sbinfo)
{
	if (sbinfo->free_inodes >= 0) {
		spin_lock(&sbinfo->stat_lock);
		if (unlikely(!sbinfo->free_inodes)) {
			spin_unlock(&sbinfo->stat_lock);
			return 0;
		}
		sbinfo->free_inodes--;
		spin_unlock(&sbinfo->stat_lock);
	}

	return 1;
}

static void hugetlbfs_inc_free_inodes(struct hugetlbfs_sb_info *sbinfo)
{
	if (sbinfo->free_inodes >= 0) {
		spin_lock(&sbinfo->stat_lock);
		sbinfo->free_inodes++;
		spin_unlock(&sbinfo->stat_lock);
	}
}


static struct kmem_cache *hugetlbfs_inode_cachep;

static struct inode *hugetlbfs_alloc_inode(struct super_block *sb)
{
	struct hugetlbfs_sb_info *sbinfo = HUGETLBFS_SB(sb);
	struct hugetlbfs_inode_info *p;

	if (unlikely(!hugetlbfs_dec_free_inodes(sbinfo)))
		return NULL;
	p = kmem_cache_alloc(hugetlbfs_inode_cachep, GFP_KERNEL);
	if (unlikely(!p)) {
		hugetlbfs_inc_free_inodes(sbinfo);
		return NULL;
	}
	return &p->vfs_inode;
}

static void hugetlbfs_destroy_inode(struct inode *inode)
{
	hugetlbfs_inc_free_inodes(HUGETLBFS_SB(inode->i_sb));
	mpol_free_shared_policy(&HUGETLBFS_I(inode)->policy);
	kmem_cache_free(hugetlbfs_inode_cachep, HUGETLBFS_I(inode));
}

static const struct address_space_operations hugetlbfs_aops = {
	.readpage	= hugetlbfs_readpage,
	.write_begin	= hugetlbfs_write_begin,
	.write_end	= hugetlbfs_write_end,
	.set_page_dirty	= hugetlbfs_set_page_dirty,
};


static void init_once(struct kmem_cache *cachep, void *foo)
{
	struct hugetlbfs_inode_info *ei = (struct hugetlbfs_inode_info *)foo;

	inode_init_once(&ei->vfs_inode);
}

const struct file_operations hugetlbfs_file_operations = {
	.read			= hugetlbfs_read,
	.mmap			= hugetlbfs_file_mmap,
	.fsync			= simple_sync_file,
	.get_unmapped_area	= hugetlb_get_unmapped_area,
};

static const struct inode_operations hugetlbfs_dir_inode_operations = {
	.create		= hugetlbfs_create,
	.lookup		= simple_lookup,
	.link		= simple_link,
	.unlink		= simple_unlink,
	.symlink	= hugetlbfs_symlink,
	.mkdir		= hugetlbfs_mkdir,
	.rmdir		= simple_rmdir,
	.mknod		= hugetlbfs_mknod,
	.rename		= simple_rename,
	.setattr	= hugetlbfs_setattr,
};

static const struct inode_operations hugetlbfs_inode_operations = {
	.setattr	= hugetlbfs_setattr,
};

static const struct super_operations hugetlbfs_ops = {
	.alloc_inode    = hugetlbfs_alloc_inode,
	.destroy_inode  = hugetlbfs_destroy_inode,
	.statfs		= hugetlbfs_statfs,
	.delete_inode	= hugetlbfs_delete_inode,
	.drop_inode	= hugetlbfs_drop_inode,
	.put_super	= hugetlbfs_put_super,
};

static int
hugetlbfs_parse_options(char *options, struct hugetlbfs_config *pconfig)
{
	char *p, *rest;
	substring_t args[MAX_OPT_ARGS];
	int option;

	if (!options)
		return 0;

	while ((p = strsep(&options, ",")) != NULL) {
		int token;
		if (!*p)
			continue;

		token = match_token(p, tokens, args);
		switch (token) {
		case Opt_uid:
			if (match_int(&args[0], &option))
 				goto bad_val;
			pconfig->uid = option;
			break;

		case Opt_gid:
			if (match_int(&args[0], &option))
 				goto bad_val;
			pconfig->gid = option;
			break;

		case Opt_mode:
			if (match_octal(&args[0], &option))
 				goto bad_val;
			pconfig->mode = option & 0777U;
			break;

		case Opt_size: {
 			unsigned long long size;
			/* memparse() will accept a K/M/G without a digit */
			if (!isdigit(*args[0].from))
				goto bad_val;
			size = memparse(args[0].from, &rest);
			if (*rest == '%') {
				size <<= HPAGE_SHIFT;
				size *= max_huge_pages;
				do_div(size, 100);
			}
			pconfig->nr_blocks = (size >> HPAGE_SHIFT);
			break;
		}

		case Opt_nr_inodes:
			/* memparse() will accept a K/M/G without a digit */
			if (!isdigit(*args[0].from))
				goto bad_val;
			pconfig->nr_inodes = memparse(args[0].from, &rest);
			break;

		default:
			printk(KERN_ERR "hugetlbfs: Bad mount option: \"%s\"\n",
				 p);
			return -EINVAL;
			break;
		}
	}
	return 0;

bad_val:
 	printk(KERN_ERR "hugetlbfs: Bad value '%s' for mount option '%s'\n",
	       args[0].from, p);
 	return 1;
}

static int
hugetlbfs_fill_super(struct super_block *sb, void *data, int silent)
{
	struct inode * inode;
	struct dentry * root;
	int ret;
	struct hugetlbfs_config config;
	struct hugetlbfs_sb_info *sbinfo;

	config.nr_blocks = -1; /* No limit on size by default */
	config.nr_inodes = -1; /* No limit on number of inodes by default */
	config.uid = current->fsuid;
	config.gid = current->fsgid;
	config.mode = 0755;
	ret = hugetlbfs_parse_options(data, &config);
	if (ret)
		return ret;

	sbinfo = kmalloc(sizeof(struct hugetlbfs_sb_info), GFP_KERNEL);
	if (!sbinfo)
		return -ENOMEM;
	sb->s_fs_info = sbinfo;
	spin_lock_init(&sbinfo->stat_lock);
	sbinfo->max_blocks = config.nr_blocks;
	sbinfo->free_blocks = config.nr_blocks;
	sbinfo->max_inodes = config.nr_inodes;
	sbinfo->free_inodes = config.nr_inodes;
	sb->s_maxbytes = MAX_LFS_FILESIZE;
	sb->s_blocksize = HPAGE_SIZE;
	sb->s_blocksize_bits = HPAGE_SHIFT;
	sb->s_magic = HUGETLBFS_MAGIC;
	sb->s_op = &hugetlbfs_ops;
	sb->s_time_gran = 1;
	inode = hugetlbfs_get_inode(sb, config.uid, config.gid,
					S_IFDIR | config.mode, 0);
	if (!inode)
		goto out_free;

	root = d_alloc_root(inode);
	if (!root) {
		iput(inode);
		goto out_free;
	}
	sb->s_root = root;
	return 0;
out_free:
	kfree(sbinfo);
	return -ENOMEM;
}

int hugetlb_get_quota(struct address_space *mapping, long delta)
{
	int ret = 0;
	struct hugetlbfs_sb_info *sbinfo = HUGETLBFS_SB(mapping->host->i_sb);

	if (sbinfo->free_blocks > -1) {
		spin_lock(&sbinfo->stat_lock);
		if (sbinfo->free_blocks - delta >= 0)
			sbinfo->free_blocks -= delta;
		else
			ret = -ENOMEM;
		spin_unlock(&sbinfo->stat_lock);
	}

	return ret;
}

void hugetlb_put_quota(struct address_space *mapping, long delta)
{
	struct hugetlbfs_sb_info *sbinfo = HUGETLBFS_SB(mapping->host->i_sb);

	if (sbinfo->free_blocks > -1) {
		spin_lock(&sbinfo->stat_lock);
		sbinfo->free_blocks += delta;
		spin_unlock(&sbinfo->stat_lock);
	}
}

static int hugetlbfs_get_sb(struct file_system_type *fs_type,
	int flags, const char *dev_name, void *data, struct vfsmount *mnt)
{
	return get_sb_nodev(fs_type, flags, data, hugetlbfs_fill_super, mnt);
}

static struct file_system_type hugetlbfs_fs_type = {
	.name		= "hugetlbfs",
	.get_sb		= hugetlbfs_get_sb,
	.kill_sb	= kill_litter_super,
};

static struct vfsmount *hugetlbfs_vfsmount;

static int can_do_hugetlb_shm(void)
{
	return likely(capable(CAP_IPC_LOCK) ||
			in_group_p(sysctl_hugetlb_shm_group) ||
			can_do_mlock());
}

struct file *hugetlb_file_setup(const char *name, size_t size)
{
	int error = -ENOMEM;
	struct file *file;
	struct inode *inode;
	struct dentry *dentry, *root;
	struct qstr quick_string;

	if (!hugetlbfs_vfsmount)
		return ERR_PTR(-ENOENT);

	if (!can_do_hugetlb_shm())
		return ERR_PTR(-EPERM);

	if (!user_shm_lock(size, current->user))
		return ERR_PTR(-ENOMEM);

	root = hugetlbfs_vfsmount->mnt_root;
	quick_string.name = name;
	quick_string.len = strlen(quick_string.name);
	quick_string.hash = 0;
	dentry = d_alloc(root, &quick_string);
	if (!dentry)
		goto out_shm_unlock;

	error = -ENOSPC;
	inode = hugetlbfs_get_inode(root->d_sb, current->fsuid,
				current->fsgid, S_IFREG | S_IRWXUGO, 0);
	if (!inode)
		goto out_dentry;

	error = -ENOMEM;
	if (hugetlb_reserve_pages(inode, 0, size >> HPAGE_SHIFT))
		goto out_inode;

	d_instantiate(dentry, inode);
	inode->i_size = size;
	inode->i_nlink = 0;

	error = -ENFILE;
	file = alloc_file(hugetlbfs_vfsmount, dentry,
			FMODE_WRITE | FMODE_READ,
			&hugetlbfs_file_operations);
	if (!file)
		goto out_inode;

	return file;

out_inode:
	iput(inode);
out_dentry:
	dput(dentry);
out_shm_unlock:
	user_shm_unlock(size, current->user);
	return ERR_PTR(error);
}

static int __init init_hugetlbfs_fs(void)
{
	int error;
	struct vfsmount *vfsmount;

	error = bdi_init(&hugetlbfs_backing_dev_info);
	if (error)
		return error;

	hugetlbfs_inode_cachep = kmem_cache_create("hugetlbfs_inode_cache",
					sizeof(struct hugetlbfs_inode_info),
					0, 0, init_once);
	if (hugetlbfs_inode_cachep == NULL)
		goto out2;

	error = register_filesystem(&hugetlbfs_fs_type);
	if (error)
		goto out;

	vfsmount = kern_mount(&hugetlbfs_fs_type);

	if (!IS_ERR(vfsmount)) {
		hugetlbfs_vfsmount = vfsmount;
		return 0;
	}

	error = PTR_ERR(vfsmount);

 out:
	if (error)
		kmem_cache_destroy(hugetlbfs_inode_cachep);
 out2:
	bdi_destroy(&hugetlbfs_backing_dev_info);
	return error;
}

static void __exit exit_hugetlbfs_fs(void)
{
	kmem_cache_destroy(hugetlbfs_inode_cachep);
	unregister_filesystem(&hugetlbfs_fs_type);
	bdi_destroy(&hugetlbfs_backing_dev_info);
}

module_init(init_hugetlbfs_fs)
module_exit(exit_hugetlbfs_fs)

MODULE_LICENSE("GPL");