path: root/include/linux/bpf.h

/* 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.
 */
#ifndef _LINUX_BPF_H
#define _LINUX_BPF_H 1

#include <uapi/linux/bpf.h>

#include <linux/workqueue.h>
#include <linux/file.h>
#include <linux/percpu.h>
#include <linux/err.h>
#include <linux/rbtree_latch.h>
#include <linux/numa.h>
#include <linux/wait.h>

struct bpf_verifier_env;
struct perf_event;
struct bpf_prog;
struct bpf_map;
struct sock;

/* map is generic key/value storage optionally accesible by eBPF programs */
struct bpf_map_ops {
	/* funcs callable from userspace (via syscall) */
	int (*map_alloc_check)(union bpf_attr *attr);
	struct bpf_map *(*map_alloc)(union bpf_attr *attr);
	void (*map_release)(struct bpf_map *map, struct file *map_file);
	void (*map_free)(struct bpf_map *map);
	int (*map_get_next_key)(struct bpf_map *map, void *key, void *next_key);
	void (*map_release_uref)(struct bpf_map *map);

	/* funcs callable from userspace and from eBPF programs */
	void *(*map_lookup_elem)(struct bpf_map *map, void *key);
	int (*map_update_elem)(struct bpf_map *map, void *key, void *value, u64 flags);
	int (*map_delete_elem)(struct bpf_map *map, void *key);

	/* funcs called by prog_array and perf_event_array map */
	void *(*map_fd_get_ptr)(struct bpf_map *map, struct file *map_file,
				int fd);
	void (*map_fd_put_ptr)(void *ptr);
	u32 (*map_gen_lookup)(struct bpf_map *map, struct bpf_insn *insn_buf);
	u32 (*map_fd_sys_lookup_elem)(void *ptr);
};

struct bpf_map {
	/* 1st cacheline with read-mostly members of which some
	 * are also accessed in fast-path (e.g. ops, max_entries).
	 */
	const struct bpf_map_ops *ops ____cacheline_aligned;
	struct bpf_map *inner_map_meta;
#ifdef CONFIG_SECURITY
	void *security;
#endif
	enum bpf_map_type map_type;
	u32 key_size;
	u32 value_size;
	u32 max_entries;
	u32 map_flags;
	u32 pages;
	u32 id;
	int numa_node;
	bool unpriv_array;
	/* 7 bytes hole */

	/* 2nd cacheline with misc members to avoid false sharing
	 * particularly with refcounting.
	 */
	struct user_struct *user ____cacheline_aligned;
	atomic_t refcnt;
	atomic_t usercnt;
	struct work_struct work;
	char name[BPF_OBJ_NAME_LEN];
};

struct bpf_offloaded_map;

struct bpf_map_dev_ops {
	int (*map_get_next_key)(struct bpf_offloaded_map *map,
				void *key, void *next_key);
	int (*map_lookup_elem)(struct bpf_offloaded_map *map,
			       void *key, void *value);
	int (*map_update_elem)(struct bpf_offloaded_map *map,
			       void *key, void *value, u64 flags);
	int (*map_delete_elem)(struct bpf_offloaded_map *map, void *key);
};

struct bpf_offloaded_map {
	struct bpf_map map;
	struct net_device *netdev;
	const struct bpf_map_dev_ops *dev_ops;
	void *dev_priv;
	struct list_head offloads;
};

static inline struct bpf_offloaded_map *map_to_offmap(struct bpf_map *map)
{
	return container_of(map, struct bpf_offloaded_map, map);
}

extern const struct bpf_map_ops bpf_map_offload_ops;

/* function argument constraints */
enum bpf_arg_type {
	ARG_DONTCARE = 0,	/* unused argument in helper function */

	/* the following constraints used to prototype
	 * bpf_map_lookup/update/delete_elem() functions
	 */
	ARG_CONST_MAP_PTR,	/* const argument used as pointer to bpf_map */
	ARG_PTR_TO_MAP_KEY,	/* pointer to stack used as map key */
	ARG_PTR_TO_MAP_VALUE,	/* pointer to stack used as map value */

	/* the following constraints used to prototype bpf_memcmp() and other
	 * functions that access data on eBPF program stack
	 */
	ARG_PTR_TO_MEM,		/* pointer to valid memory (stack, packet, map value) */
	ARG_PTR_TO_MEM_OR_NULL, /* pointer to valid memory or NULL */
	ARG_PTR_TO_UNINIT_MEM,	/* pointer to memory does not need to be initialized,
				 * helper function must fill all bytes or clear
				 * them in error case.
				 */

	ARG_CONST_SIZE,		/* number of bytes accessed from memory */
	ARG_CONST_SIZE_OR_ZERO,	/* number of bytes accessed from memory or 0 */

	ARG_PTR_TO_CTX,		/* pointer to context */
	ARG_ANYTHING,		/* any (initialized) argument is ok */
};

/* type of values returned from helper functions */
enum bpf_return_type {
	RET_INTEGER,			/* function returns integer */
	RET_VOID,			/* function doesn't return anything */
	RET_PTR_TO_MAP_VALUE_OR_NULL,	/* returns a pointer to map elem value or NULL */
};

/* eBPF function prototype used by verifier to allow BPF_CALLs from eBPF programs
 * to in-kernel helper functions and for adjusting imm32 field in BPF_CALL
 * instructions after verifying
 */
struct bpf_func_proto {
	u64 (*func)(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5);
	bool gpl_only;
	bool pkt_access;
	enum bpf_return_type ret_type;
	enum bpf_arg_type arg1_type;
	enum bpf_arg_type arg2_type;
	enum bpf_arg_type arg3_type;
	enum bpf_arg_type arg4_type;
	enum bpf_arg_type arg5_type;
};

/* bpf_context is intentionally undefined structure. Pointer to bpf_context is
 * the first argument to eBPF programs.
 * For socket filters: 'struct bpf_context *' == 'struct sk_buff *'
 */
struct bpf_context;

enum bpf_access_type {
	BPF_READ = 1,
	BPF_WRITE = 2
};

/* types of values stored in eBPF registers */
/* Pointer types represent:
 * pointer
 * pointer + imm
 * pointer + (u16) var
 * pointer + (u16) var + imm
 * if (range > 0) then [ptr, ptr + range - off) is safe to access
 * if (id > 0) means that some 'var' was added
 * if (off > 0) means that 'imm' was added
 */
enum bpf_reg_type {
	NOT_INIT = 0,		 /* nothing was written into register */
	SCALAR_VALUE,		 /* reg doesn't contain a valid pointer */
	PTR_TO_CTX,		 /* reg points to bpf_context */
	CONST_PTR_TO_MAP,	 /* reg points to struct bpf_map */
	PTR_TO_MAP_VALUE,	 /* reg points to map element value */
	PTR_TO_MAP_VALUE_OR_NULL,/* points to map elem value or NULL */
	PTR_TO_STACK,		 /* reg == frame_pointer + offset */
	PTR_TO_PACKET_META,	 /* skb->data - meta_len */
	PTR_TO_PACKET,		 /* reg points to skb->data */
	PTR_TO_PACKET_END,	 /* skb->data + headlen */
};

/* The information passed from prog-specific *_is_valid_access
 * back to the verifier.
 */
struct bpf_insn_access_aux {
	enum bpf_reg_type reg_type;
	int ctx_field_size;
};

static inline void
bpf_ctx_record_field_size(struct bpf_insn_access_aux *aux, u32 size)
{
	aux->ctx_field_size = size;
}

struct bpf_prog_ops {
	int (*test_run)(struct bpf_prog *prog, const union bpf_attr *kattr,
			union bpf_attr __user *uattr);
};

struct bpf_verifier_ops {
	/* return eBPF function prototype for verification */
	const struct bpf_func_proto *
	(*get_func_proto)(enum bpf_func_id func_id,
			  const struct bpf_prog *prog);

	/* return true if 'size' wide access at offset 'off' within bpf_context
	 * with 'type' (read or write) is allowed
	 */
	bool (*is_valid_access)(int off, int size, enum bpf_access_type type,
				const struct bpf_prog *prog,
				struct bpf_insn_access_aux *info);
	int (*gen_prologue)(struct bpf_insn *insn, bool direct_write,
			    const struct bpf_prog *prog);
	u32 (*convert_ctx_access)(enum bpf_access_type