2913 lines · 67.8 KB · C
RawDownload
// SPDX-License-Identifier: GPL-2.0-only/* Copyright (c) 2011-2014 PLUMgrid, http://plumgrid.com */#include <linux/bpf.h>#include <linux/bpf_trace.h>#include <linux/bpf_lirc.h>#include <linux/btf.h>#include <linux/syscalls.h>#include <linux/slab.h>#include <linux/sched/signal.h>#include <linux/vmalloc.h>#include <linux/mmzone.h>#include <linux/anon_inodes.h>#include <linux/fdtable.h>#include <linux/file.h>#include <linux/fs.h>#include <linux/license.h>#include <linux/filter.h>#include <linux/version.h>#include <linux/kernel.h>#include <linux/idr.h>#include <linux/cred.h>#include <linux/timekeeping.h>#include <linux/ctype.h>#include <linux/nospec.h> #define IS_FD_ARRAY(map) ((map)->map_type == BPF_MAP_TYPE_PROG_ARRAY || \			   (map)->map_type == BPF_MAP_TYPE_PERF_EVENT_ARRAY || \			   (map)->map_type == BPF_MAP_TYPE_CGROUP_ARRAY || \			   (map)->map_type == BPF_MAP_TYPE_ARRAY_OF_MAPS)#define IS_FD_HASH(map) ((map)->map_type == BPF_MAP_TYPE_HASH_OF_MAPS)#define IS_FD_MAP(map) (IS_FD_ARRAY(map) || IS_FD_HASH(map)) #define BPF_OBJ_FLAG_MASK   (BPF_F_RDONLY | BPF_F_WRONLY) DEFINE_PER_CPU(int, bpf_prog_active);static DEFINE_IDR(prog_idr);static DEFINE_SPINLOCK(prog_idr_lock);static DEFINE_IDR(map_idr);static DEFINE_SPINLOCK(map_idr_lock); int sysctl_unprivileged_bpf_disabled __read_mostly; static const struct bpf_map_ops * const bpf_map_types[] = {#define BPF_PROG_TYPE(_id, _ops)#define BPF_MAP_TYPE(_id, _ops) \	[_id] = &_ops,#include <linux/bpf_types.h>#undef BPF_PROG_TYPE#undef BPF_MAP_TYPE}; /* * 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 don't know about yet. * * There is a ToCToU between this function call and the following * copy_from_user() call. However, this is not a concern since this function is * meant to be a future-proofing of bits. */int bpf_check_uarg_tail_zero(void __user *uaddr,			     size_t expected_size,			     size_t actual_size){	unsigned char __user *addr;	unsigned char __user *end;	unsigned char val;	int err; 	if (unlikely(actual_size > PAGE_SIZE))	/* silly large */		return -E2BIG; 	if (unlikely(!access_ok(uaddr, actual_size)))		return -EFAULT; 	if (actual_size <= expected_size)		return 0; 	addr = uaddr + expected_size;	end  = uaddr + actual_size; 	for (; addr < end; addr++) {		err = get_user(val, addr);		if (err)			return err;		if (val)			return -E2BIG;	} 	return 0;} const struct bpf_map_ops bpf_map_offload_ops = {	.map_alloc = bpf_map_offload_map_alloc,	.map_free = bpf_map_offload_map_free,	.map_check_btf = map_check_no_btf,}; static struct bpf_map *find_and_alloc_map(union bpf_attr *attr){	const struct bpf_map_ops *ops;	u32 type = attr->map_type;	struct bpf_map *map;	int err; 	if (type >= ARRAY_SIZE(bpf_map_types))		return ERR_PTR(-EINVAL);	type = array_index_nospec(type, ARRAY_SIZE(bpf_map_types));	ops = bpf_map_types[type];	if (!ops)		return ERR_PTR(-EINVAL); 	if (ops->map_alloc_check) {		err = ops->map_alloc_check(attr);		if (err)			return ERR_PTR(err);	}	if (attr->map_ifindex)		ops = &bpf_map_offload_ops;	map = ops->map_alloc(attr);	if (IS_ERR(map))		return map;	map->ops = ops;	map->map_type = type;	return map;} void *bpf_map_area_alloc(size_t size, int numa_node){	/* We really just want to fail instead of triggering OOM killer	 * under memory pressure, therefore we set __GFP_NORETRY to kmalloc,	 * which is used for lower order allocation requests.	 *	 * It has been observed that higher order allocation requests done by	 * vmalloc with __GFP_NORETRY being set might fail due to not trying	 * to reclaim memory from the page cache, thus we set	 * __GFP_RETRY_MAYFAIL to avoid such situations.	 */ 	const gfp_t flags = __GFP_NOWARN | __GFP_ZERO;	void *area; 	if (size <= (PAGE_SIZE << PAGE_ALLOC_COSTLY_ORDER)) {		area = kmalloc_node(size, GFP_USER | __GFP_NORETRY | flags,				    numa_node);		if (area != NULL)			return area;	} 	return __vmalloc_node_flags_caller(size, numa_node,					   GFP_KERNEL | __GFP_RETRY_MAYFAIL |					   flags, __builtin_return_address(0));} void bpf_map_area_free(void *area){	kvfree(area);} static u32 bpf_map_flags_retain_permanent(u32 flags){	/* Some map creation flags are not tied to the map object but	 * rather to the map fd instead, so they have no meaning upon	 * map object inspection since multiple file descriptors with	 * different (access) properties can exist here. Thus, given	 * this has zero meaning for the map itself, lets clear these	 * from here.	 */	return flags & ~(BPF_F_RDONLY | BPF_F_WRONLY);} void bpf_map_init_from_attr(struct bpf_map *map, union bpf_attr *attr){	map->map_type = attr->map_type;	map->key_size = attr->key_size;	map->value_size = attr->value_size;	map->max_entries = attr->max_entries;	map->map_flags = bpf_map_flags_retain_permanent(attr->map_flags);	map->numa_node = bpf_map_attr_numa_node(attr);} static int bpf_charge_memlock(struct user_struct *user, u32 pages){	unsigned long memlock_limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT; 	if (atomic_long_add_return(pages, &user->locked_vm) > memlock_limit) {		atomic_long_sub(pages, &user->locked_vm);		return -EPERM;	}	return 0;} static void bpf_uncharge_memlock(struct user_struct *user, u32 pages){	if (user)		atomic_long_sub(pages, &user->locked_vm);} int bpf_map_charge_init(struct bpf_map_memory *mem, size_t size){	u32 pages = round_up(size, PAGE_SIZE) >> PAGE_SHIFT;	struct user_struct *user;	int ret; 	if (size >= U32_MAX - PAGE_SIZE)		return -E2BIG; 	user = get_current_user();	ret = bpf_charge_memlock(user, pages);	if (ret) {		free_uid(user);		return ret;	} 	mem->pages = pages;	mem->user = user; 	return 0;} void bpf_map_charge_finish(struct bpf_map_memory *mem){	bpf_uncharge_memlock(mem->user, mem->pages);	free_uid(mem->user);} void bpf_map_charge_move(struct bpf_map_memory *dst,			 struct bpf_map_memory *src){	*dst = *src; 	/* Make sure src will not be used for the redundant uncharging. */	memset(src, 0, sizeof(struct bpf_map_memory));} int bpf_map_charge_memlock(struct bpf_map *map, u32 pages){	int ret; 	ret = bpf_charge_memlock(map->memory.user, pages);	if (ret)		return ret;	map->memory.pages += pages;	return ret;} void bpf_map_uncharge_memlock(struct bpf_map *map, u32 pages){	bpf_uncharge_memlock(map->memory.user, pages);	map->memory.pages -= pages;} static int bpf_map_alloc_id(struct bpf_map *map){	int id; 	idr_preload(GFP_KERNEL);	spin_lock_bh(&map_idr_lock);	id = idr_alloc_cyclic(&map_idr, map, 1, INT_MAX, GFP_ATOMIC);	if (id > 0)		map->id = id;	spin_unlock_bh(&map_idr_lock);	idr_preload_end(); 	if (WARN_ON_ONCE(!id))		return -ENOSPC; 	return id > 0 ? 0 : id;} void bpf_map_free_id(struct bpf_map *map, bool do_idr_lock){	unsigned long flags; 	/* Offloaded maps are removed from the IDR store when their device	 * disappears - even if someone holds an fd to them they are unusable,	 * the memory is gone, all ops will fail; they are simply waiting for	 * refcnt to drop to be freed.	 */	if (!map->id)		return; 	if (do_idr_lock)		spin_lock_irqsave(&map_idr_lock, flags);	else		__acquire(&map_idr_lock); 	idr_remove(&map_idr, map->id);	map->id = 0; 	if (do_idr_lock)		spin_unlock_irqrestore(&map_idr_lock, flags);	else		__release(&map_idr_lock);} /* called from workqueue */static void bpf_map_free_deferred(struct work_struct *work){	struct bpf_map *map = container_of(work, struct bpf_map, work);	struct bpf_map_memory mem; 	bpf_map_charge_move(&mem, &map->memory);	security_bpf_map_free(map);	/* implementation dependent freeing */	map->ops->map_free(map);	bpf_map_charge_finish(&mem);} static void bpf_map_put_uref(struct bpf_map *map){	if (atomic_dec_and_test(&map->usercnt)) {		if (map->ops->map_release_uref)			map->ops->map_release_uref(map);	}} /* decrement map refcnt and schedule it for freeing via workqueue * (unrelying map implementation ops->map_free() might sleep) */static void __bpf_map_put(struct bpf_map *map, bool do_idr_lock){	if (atomic_dec_and_test(&map->refcnt)) {		/* bpf_map_free_id() must be called first */		bpf_map_free_id(map, do_idr_lock);		btf_put(map->btf);		INIT_WORK(&map->work, bpf_map_free_deferred);		schedule_work(&map->work);	}} void bpf_map_put(struct bpf_map *map){	__bpf_map_put(map, true);}EXPORT_SYMBOL_GPL(bpf_map_put); void bpf_map_put_with_uref(struct bpf_map *map){	bpf_map_put_uref(map);	bpf_map_put(map);} static int bpf_map_release(struct inode *inode, struct file *filp){	struct bpf_map *map = filp->private_data; 	if (map->ops->map_release)		map->ops->map_release(map, filp); 	bpf_map_put_with_uref(map);	return 0;} static fmode_t map_get_sys_perms(struct bpf_map *map, struct fd f){	fmode_t mode = f.file->f_mode; 	/* Our file permissions may have been overridden by global	 * map permissions facing syscall side.	 */	if (READ_ONCE(map->frozen))		mode &= ~FMODE_CAN_WRITE;	return mode;} #ifdef CONFIG_PROC_FSstatic void bpf_map_show_fdinfo(struct seq_file *m, struct file *filp){	const struct bpf_map *map = filp->private_data;	const struct bpf_array *array;	u32 owner_prog_type = 0;	u32 owner_jited = 0; 	if (map->map_type == BPF_MAP_TYPE_PROG_ARRAY) {		array = container_of(map, struct bpf_array, map);		owner_prog_type = array->owner_prog_type;		owner_jited = array->owner_jited;	} 	seq_printf(m,		   "map_type:\t%u\n"		   "key_size:\t%u\n"		   "value_size:\t%u\n"		   "max_entries:\t%u\n"		   "map_flags:\t%#x\n"		   "memlock:\t%llu\n"		   "map_id:\t%u\n"		   "frozen:\t%u\n",		   map->map_type,		   map->key_size,		   map->value_size,		   map->max_entries,		   map->map_flags,		   map->memory.pages * 1ULL << PAGE_SHIFT,		   map->id,		   READ_ONCE(map->frozen)); 	if (owner_prog_type) {		seq_printf(m, "owner_prog_type:\t%u\n",			   owner_prog_type);		seq_printf(m, "owner_jited:\t%u\n",			   owner_jited);	}}#endif static ssize_t bpf_dummy_read(struct file *filp, char __user *buf, size_t siz,			      loff_t *ppos){	/* We need this handler such that alloc_file() enables	 * f_mode with FMODE_CAN_READ.	 */	return -EINVAL;} static ssize_t bpf_dummy_write(struct file *filp, const char __user *buf,			       size_t siz, loff_t *ppos){	/* We need this handler such that alloc_file() enables	 * f_mode with FMODE_CAN_WRITE.	 */	return -EINVAL;} const struct file_operations bpf_map_fops = {#ifdef CONFIG_PROC_FS	.show_fdinfo	= bpf_map_show_fdinfo,#endif	.release	= bpf_map_release,	.read		= bpf_dummy_read,	.write		= bpf_dummy_write,}; int bpf_map_new_fd(struct bpf_map *map, int flags){	int ret; 	ret = security_bpf_map(map, OPEN_FMODE(flags));	if (ret < 0)		return ret; 	return anon_inode_getfd("bpf-map", &bpf_map_fops, map,				flags | O_CLOEXEC);} int bpf_get_file_flag(int flags){	if ((flags & BPF_F_RDONLY) && (flags & BPF_F_WRONLY))		return -EINVAL;	if (flags & BPF_F_RDONLY)		return O_RDONLY;	if (flags & BPF_F_WRONLY)		return O_WRONLY;	return O_RDWR;} /* 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 /* dst and src must have at least BPF_OBJ_NAME_LEN number of bytes. * Return 0 on success and < 0 on error. */static int bpf_obj_name_cpy(char *dst, const char *src){	const char *end = src + BPF_OBJ_NAME_LEN; 	memset(dst, 0, BPF_OBJ_NAME_LEN);	/* Copy all isalnum(), '_' and '.' chars. */	while (src < end && *src) {		if (!isalnum(*src) &&		    *src != '_' && *src != '.')			return -EINVAL;		*dst++ = *src++;	} 	/* No '\0' found in BPF_OBJ_NAME_LEN number of bytes */	if (src == end)		return -EINVAL; 	return 0;} int map_check_no_btf(const struct bpf_map *map,		     const struct btf *btf,		     const struct btf_type *key_type,		     const struct btf_type *value_type){	return -ENOTSUPP;} static int map_check_btf(struct bpf_map *map, const struct btf *btf,			 u32 btf_key_id, u32 btf_value_id){

Lines 1–500 of 2913.