linux/kernel/bpf/syscall.c

/* Copyright (c) 2011-2014 PLUMgrid, http://plumgrid.com
 *
 * This program is free software; you can redistribute it and/or
 * modify it under the terms of version 2 of the GNU General Public
 * License as published by the Free Software Foundation.
 *
 * This program is distributed in the hope that it will be useful, but
 * WITHOUT ANY WARRANTY; without even the implied warranty of
 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
 * General Public License for more details.
 */
#include <linux/bpf.h>
#include <linux/syscalls.h>
#include <linux/slab.h>
#include <linux/anon_inodes.h>

static LIST_HEAD(bpf_map_types);

static struct bpf_map *find_and_alloc_map(union bpf_attr *attr)
{
	struct bpf_map_type_list *tl;
	struct bpf_map *map;

	list_for_each_entry(tl, &bpf_map_types, list_node) {
		if (tl->type == attr->map_type) {
			map = tl->ops->map_alloc(attr);
			if (IS_ERR(map))
				return map;
			map->ops = tl->ops;
			map->map_type = attr->map_type;
			return map;
		}
	}
	return ERR_PTR(-EINVAL);
}

/* boot time registration of different map implementations */
void bpf_register_map_type(struct bpf_map_type_list *tl)
{
	list_add(&tl->list_node, &bpf_map_types);
}

/* called from workqueue */
static void bpf_map_free_deferred(struct work_struct *work)
{
	struct bpf_map *map = container_of(work, struct bpf_map, work);

	/* implementation dependent freeing */
	map->ops->map_free(map);
}

/* decrement map refcnt and schedule it for freeing via workqueue
 * (unrelying map implementation ops->map_free() might sleep)
 */
void bpf_map_put(struct bpf_map *map)
{
	if (atomic_dec_and_test(&map->refcnt)) {
		INIT_WORK(&map->work, bpf_map_free_deferred);
		schedule_work(&map->work);
	}
}

static int bpf_map_release(struct inode *inode, struct file *filp)
{
	struct bpf_map *map = filp->private_data;

	bpf_map_put(map);
	return 0;
}

static const struct file_operations bpf_map_fops = {
	.release = bpf_map_release,
};

/* helper macro to check that unused fields 'union bpf_attr' are zero */
#define CHECK_ATTR(CMD) \
	memchr_inv((void *) &attr->CMD##_LAST_FIELD + \
		   sizeof(attr->CMD##_LAST_FIELD), 0, \
		   sizeof(*attr) - \
		   offsetof(union bpf_attr, CMD##_LAST_FIELD) - \
		   sizeof(attr->CMD##_LAST_FIELD)) != NULL

#define BPF_MAP_CREATE_LAST_FIELD max_entries
/* called via syscall */
static int map_create(union bpf_attr *attr)
{
	struct bpf_map *map;
	int err;

	err = CHECK_ATTR(BPF_MAP_CREATE);
	if (err)
		return -EINVAL;

	/* find map type and init map: hashtable vs rbtree vs bloom vs ... */
	map = find_and_alloc_map(attr);
	if (IS_ERR(map))
		return PTR_ERR(map);

	atomic_set(&map->refcnt, 1);

	err = anon_inode_getfd("bpf-map", &bpf_map_fops, map, O_RDWR | O_CLOEXEC);

	if (err < 0)
		/* failed to allocate fd */
		goto free_map;

	return err;

free_map:
	map->ops->map_free(map);
	return err;
}

SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, size)
{
	union bpf_attr attr = {};
	int err;

	/* the syscall is limited to root temporarily. This restriction will be
	 * lifted when security audit is clean. Note that eBPF+tracing must have
	 * this restriction, since it may pass kernel data to user space
	 */
	if (!capable(CAP_SYS_ADMIN))
		return -EPERM;

	if (!access_ok(VERIFY_READ, uattr, 1))
		return -EFAULT;

	if (size > PAGE_SIZE)	/* silly large */
		return -E2BIG;

	/* If we're handed a bigger struct than we know of,
	 * ensure all the unknown bits are 0 - i.e. new
	 * user-space does not rely on any kernel feature
	 * extensions we dont know about yet.
	 */
	if (size > sizeof(attr)) {
		unsigned char __user *addr;
		unsigned char __user *end;
		unsigned char val;

		addr = (void __user *)uattr + sizeof(attr);
		end  = (void __user *)uattr + size;

		for (; addr < end; addr++) {
			err = get_user(val, addr);
			if (err)
				return err;
			if (val)
				return -E2BIG;
		}
		size = sizeof(attr);
	}

	/* copy attributes from user space, may be less than sizeof(bpf_attr) */
	if (copy_from_user(&attr, uattr, size) != 0)
		return -EFAULT;

	switch (cmd) {
	case BPF_MAP_CREATE:
		err = map_create(&attr);
		break;
	default:
		err = -EINVAL;
		break;
	}

	return err;
}