linux_dsm_epyc7002/include/linux/bpf.h
Alexei Starovoitov f1b9509c2f bpf: Replace prog_raw_tp+btf_id with prog_tracing
The bpf program type raw_tp together with 'expected_attach_type'
was the most appropriate api to indicate BTF-enabled raw_tp programs.
But during development it became apparent that 'expected_attach_type'
cannot be used and new 'attach_btf_id' field had to be introduced.
Which means that the information is duplicated in two fields where
one of them is ignored.
Clean it up by introducing new program type where both
'expected_attach_type' and 'attach_btf_id' fields have
specific meaning.
In the future 'expected_attach_type' will be extended
with other attach points that have similar semantics to raw_tp.
This patch is replacing BTF-enabled BPF_PROG_TYPE_RAW_TRACEPOINT with
prog_type = BPF_RPOG_TYPE_TRACING
expected_attach_type = BPF_TRACE_RAW_TP
attach_btf_id = btf_id of raw tracepoint inside the kernel
Future patches will add
expected_attach_type = BPF_TRACE_FENTRY or BPF_TRACE_FEXIT
where programs have the same input context and the same helpers,
but different attach points.

Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Andrii Nakryiko <andriin@fb.com>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Link: https://lore.kernel.org/bpf/20191030223212.953010-2-ast@kernel.org
2019-10-31 15:16:59 +01:00

1186 lines
37 KiB
C

/* SPDX-License-Identifier: GPL-2.0-only */
/* Copyright (c) 2011-2014 PLUMgrid, http://plumgrid.com
*/
#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>
#include <linux/u64_stats_sync.h>
struct bpf_verifier_env;
struct bpf_verifier_log;
struct perf_event;
struct bpf_prog;
struct bpf_map;
struct sock;
struct seq_file;
struct btf;
struct btf_type;
struct exception_table_entry;
extern struct idr btf_idr;
extern spinlock_t btf_idr_lock;
/* 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);
void *(*map_lookup_elem_sys_only)(struct bpf_map *map, void *key);
/* 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);
int (*map_push_elem)(struct bpf_map *map, void *value, u64 flags);
int (*map_pop_elem)(struct bpf_map *map, void *value);
int (*map_peek_elem)(struct bpf_map *map, void *value);
/* 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);
void (*map_seq_show_elem)(struct bpf_map *map, void *key,
struct seq_file *m);
int (*map_check_btf)(const struct bpf_map *map,
const struct btf *btf,
const struct btf_type *key_type,
const struct btf_type *value_type);
/* Direct value access helpers. */
int (*map_direct_value_addr)(const struct bpf_map *map,
u64 *imm, u32 off);
int (*map_direct_value_meta)(const struct bpf_map *map,
u64 imm, u32 *off);
};
struct bpf_map_memory {
u32 pages;
struct user_struct *user;
};
struct bpf_map {
/* The first two cachelines 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;
int spin_lock_off; /* >=0 valid offset, <0 error */
u32 id;
int numa_node;
u32 btf_key_type_id;
u32 btf_value_type_id;
struct btf *btf;
struct bpf_map_memory memory;
bool unpriv_array;
bool frozen; /* write-once */
/* 48 bytes hole */
/* The 3rd and 4th cacheline with misc members to avoid false sharing
* particularly with refcounting.
*/
atomic_t refcnt ____cacheline_aligned;
atomic_t usercnt;
struct work_struct work;
char name[BPF_OBJ_NAME_LEN];
};
static inline bool map_value_has_spin_lock(const struct bpf_map *map)
{
return map->spin_lock_off >= 0;
}
static inline void check_and_init_map_lock(struct bpf_map *map, void *dst)
{
if (likely(!map_value_has_spin_lock(map)))
return;
*(struct bpf_spin_lock *)(dst + map->spin_lock_off) =
(struct bpf_spin_lock){};
}
/* copy everything but bpf_spin_lock */
static inline void copy_map_value(struct bpf_map *map, void *dst, void *src)
{
if (unlikely(map_value_has_spin_lock(map))) {
u32 off = map->spin_lock_off;
memcpy(dst, src, off);
memcpy(dst + off + sizeof(struct bpf_spin_lock),
src + off + sizeof(struct bpf_spin_lock),
map->value_size - off - sizeof(struct bpf_spin_lock));
} else {
memcpy(dst, src, map->value_size);
}
}
void copy_map_value_locked(struct bpf_map *map, void *dst, void *src,
bool lock_src);
struct bpf_offload_dev;
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);
}
static inline bool bpf_map_offload_neutral(const struct bpf_map *map)
{
return map->map_type == BPF_MAP_TYPE_PERF_EVENT_ARRAY;
}
static inline bool bpf_map_support_seq_show(const struct bpf_map *map)
{
return map->btf && map->ops->map_seq_show_elem;
}
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);
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 */
ARG_PTR_TO_UNINIT_MAP_VALUE, /* pointer to valid memory used to store a map value */
ARG_PTR_TO_MAP_VALUE_OR_NULL, /* pointer to stack used as map value or NULL */
/* 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 */
ARG_PTR_TO_SPIN_LOCK, /* pointer to bpf_spin_lock */
ARG_PTR_TO_SOCK_COMMON, /* pointer to sock_common */
ARG_PTR_TO_INT, /* pointer to int */
ARG_PTR_TO_LONG, /* pointer to long */
ARG_PTR_TO_SOCKET, /* pointer to bpf_sock (fullsock) */
ARG_PTR_TO_BTF_ID, /* pointer to in-kernel struct */
};
/* 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, /* returns a pointer to map elem value */
RET_PTR_TO_MAP_VALUE_OR_NULL, /* returns a pointer to map elem value or NULL */
RET_PTR_TO_SOCKET_OR_NULL, /* returns a pointer to a socket or NULL */
RET_PTR_TO_TCP_SOCK_OR_NULL, /* returns a pointer to a tcp_sock or NULL */
RET_PTR_TO_SOCK_COMMON_OR_NULL, /* returns a pointer to a sock_common 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;
union {
struct {
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;
};
enum bpf_arg_type arg_type[5];
};
u32 *btf_id; /* BTF ids of arguments */
};
/* 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 */
PTR_TO_FLOW_KEYS, /* reg points to bpf_flow_keys */
PTR_TO_SOCKET, /* reg points to struct bpf_sock */
PTR_TO_SOCKET_OR_NULL, /* reg points to struct bpf_sock or NULL */
PTR_TO_SOCK_COMMON, /* reg points to sock_common */
PTR_TO_SOCK_COMMON_OR_NULL, /* reg points to sock_common or NULL */
PTR_TO_TCP_SOCK, /* reg points to struct tcp_sock */
PTR_TO_TCP_SOCK_OR_NULL, /* reg points to struct tcp_sock or NULL */
PTR_TO_TP_BUFFER, /* reg points to a writable raw tp's buffer */
PTR_TO_XDP_SOCK, /* reg points to struct xdp_sock */
PTR_TO_BTF_ID, /* reg points to kernel struct */
};
/* The information passed from prog-specific *_is_valid_access
* back to the verifier.
*/
struct bpf_insn_access_aux {
enum bpf_reg_type reg_type;
union {
int ctx_field_size;
u32 btf_id;
};
struct bpf_verifier_log *log; /* for verbose logs */
};
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);
int (*gen_ld_abs)(const struct bpf_insn *orig,
struct bpf_insn *insn_buf);
u32 (*convert_ctx_access)(enum bpf_access_type type,
const struct bpf_insn *src,
struct bpf_insn *dst,
struct bpf_prog *prog, u32 *target_size);
};
struct bpf_prog_offload_ops {
/* verifier basic callbacks */
int (*insn_hook)(struct bpf_verifier_env *env,
int insn_idx, int prev_insn_idx);
int (*finalize)(struct bpf_verifier_env *env);
/* verifier optimization callbacks (called after .finalize) */
int (*replace_insn)(struct bpf_verifier_env *env, u32 off,
struct bpf_insn *insn);
int (*remove_insns)(struct bpf_verifier_env *env, u32 off, u32 cnt);
/* program management callbacks */
int (*prepare)(struct bpf_prog *prog);
int (*translate)(struct bpf_prog *prog);
void (*destroy)(struct bpf_prog *prog);
};
struct bpf_prog_offload {
struct bpf_prog *prog;
struct net_device *netdev;
struct bpf_offload_dev *offdev;
void *dev_priv;
struct list_head offloads;
bool dev_state;
bool opt_failed;
void *jited_image;
u32 jited_len;
};
enum bpf_cgroup_storage_type {
BPF_CGROUP_STORAGE_SHARED,
BPF_CGROUP_STORAGE_PERCPU,
__BPF_CGROUP_STORAGE_MAX
};
#define MAX_BPF_CGROUP_STORAGE_TYPE __BPF_CGROUP_STORAGE_MAX
/* The longest tracepoint has 12 args.
* See include/trace/bpf_probe.h
*/
#define MAX_BPF_FUNC_ARGS 12
struct bpf_prog_stats {
u64 cnt;
u64 nsecs;
struct u64_stats_sync syncp;
} __aligned(2 * sizeof(u64));
struct bpf_prog_aux {
atomic_t refcnt;
u32 used_map_cnt;
u32 max_ctx_offset;
u32 max_pkt_offset;
u32 max_tp_access;
u32 stack_depth;
u32 id;
u32 func_cnt; /* used by non-func prog as the number of func progs */
u32 func_idx; /* 0 for non-func prog, the index in func array for func prog */
u32 attach_btf_id; /* in-kernel BTF type id to attach to */
bool verifier_zext; /* Zero extensions has been inserted by verifier. */
bool offload_requested;
bool attach_btf_trace; /* true if attaching to BTF-enabled raw tp */
/* BTF_KIND_FUNC_PROTO for valid attach_btf_id */
const struct btf_type *attach_func_proto;
/* function name for valid attach_btf_id */
const char *attach_func_name;
struct bpf_prog **func;
void *jit_data; /* JIT specific data. arch dependent */
struct latch_tree_node ksym_tnode;
struct list_head ksym_lnode;
const struct bpf_prog_ops *ops;
struct bpf_map **used_maps;
struct bpf_prog *prog;
struct user_struct *user;
u64 load_time; /* ns since boottime */
struct bpf_map *cgroup_storage[MAX_BPF_CGROUP_STORAGE_TYPE];
char name[BPF_OBJ_NAME_LEN];
#ifdef CONFIG_SECURITY
void *security;
#endif
struct bpf_prog_offload *offload;
struct btf *btf;
struct bpf_func_info *func_info;
/* bpf_line_info loaded from userspace. linfo->insn_off
* has the xlated insn offset.
* Both the main and sub prog share the same linfo.
* The subprog can access its first linfo by
* using the linfo_idx.
*/
struct bpf_line_info *linfo;
/* jited_linfo is the jited addr of the linfo. It has a
* one to one mapping to linfo:
* jited_linfo[i] is the jited addr for the linfo[i]->insn_off.
* Both the main and sub prog share the same jited_linfo.
* The subprog can access its first jited_linfo by
* using the linfo_idx.
*/
void **jited_linfo;
u32 func_info_cnt;
u32 nr_linfo;
/* subprog can use linfo_idx to access its first linfo and
* jited_linfo.
* main prog always has linfo_idx == 0
*/
u32 linfo_idx;
u32 num_exentries;
struct exception_table_entry *extable;
struct bpf_prog_stats __percpu *stats;
union {
struct work_struct work;
struct rcu_head rcu;
};
};
struct bpf_array {
struct bpf_map map;
u32 elem_size;
u32 index_mask;
/* 'ownership' of prog_array is claimed by the first program that
* is going to use this map or by the first program which FD is stored
* in the map to make sure that all callers and callees have the same
* prog_type and JITed flag
*/
enum bpf_prog_type owner_prog_type;
bool owner_jited;
union {
char value[0] __aligned(8);
void *ptrs[0] __aligned(8);
void __percpu *pptrs[0] __aligned(8);
};
};
#define BPF_COMPLEXITY_LIMIT_INSNS 1000000 /* yes. 1M insns */
#define MAX_TAIL_CALL_CNT 32
#define BPF_F_ACCESS_MASK (BPF_F_RDONLY | \
BPF_F_RDONLY_PROG | \
BPF_F_WRONLY | \
BPF_F_WRONLY_PROG)
#define BPF_MAP_CAN_READ BIT(0)
#define BPF_MAP_CAN_WRITE BIT(1)
static inline u32 bpf_map_flags_to_cap(struct bpf_map *map)
{
u32 access_flags = map->map_flags & (BPF_F_RDONLY_PROG | BPF_F_WRONLY_PROG);
/* Combination of BPF_F_RDONLY_PROG | BPF_F_WRONLY_PROG is
* not possible.
*/
if (access_flags & BPF_F_RDONLY_PROG)
return BPF_MAP_CAN_READ;
else if (access_flags & BPF_F_WRONLY_PROG)
return BPF_MAP_CAN_WRITE;
else
return BPF_MAP_CAN_READ | BPF_MAP_CAN_WRITE;
}
static inline bool bpf_map_flags_access_ok(u32 access_flags)
{
return (access_flags & (BPF_F_RDONLY_PROG | BPF_F_WRONLY_PROG)) !=
(BPF_F_RDONLY_PROG | BPF_F_WRONLY_PROG);
}
struct bpf_event_entry {
struct perf_event *event;
struct file *perf_file;
struct file *map_file;
struct rcu_head rcu;
};
bool bpf_prog_array_compatible(struct bpf_array *array, const struct bpf_prog *fp);
int bpf_prog_calc_tag(struct bpf_prog *fp);
const char *kernel_type_name(u32 btf_type_id);
const struct bpf_func_proto *bpf_get_trace_printk_proto(void);
typedef unsigned long (*bpf_ctx_copy_t)(void *dst, const void *src,
unsigned long off, unsigned long len);
typedef u32 (*bpf_convert_ctx_access_t)(enum bpf_access_type type,
const struct bpf_insn *src,
struct bpf_insn *dst,
struct bpf_prog *prog,
u32 *target_size);
u64 bpf_event_output(struct bpf_map *map, u64 flags, void *meta, u64 meta_size,
void *ctx, u64 ctx_size, bpf_ctx_copy_t ctx_copy);
/* an array of programs to be executed under rcu_lock.
*
* Typical usage:
* ret = BPF_PROG_RUN_ARRAY(&bpf_prog_array, ctx, BPF_PROG_RUN);
*
* the structure returned by bpf_prog_array_alloc() should be populated
* with program pointers and the last pointer must be NULL.
* The user has to keep refcnt on the program and make sure the program
* is removed from the array before bpf_prog_put().
* The 'struct bpf_prog_array *' should only be replaced with xchg()
* since other cpus are walking the array of pointers in parallel.
*/
struct bpf_prog_array_item {
struct bpf_prog *prog;
struct bpf_cgroup_storage *cgroup_storage[MAX_BPF_CGROUP_STORAGE_TYPE];
};
struct bpf_prog_array {
struct rcu_head rcu;
struct bpf_prog_array_item items[0];
};
struct bpf_prog_array *bpf_prog_array_alloc(u32 prog_cnt, gfp_t flags);
void bpf_prog_array_free(struct bpf_prog_array *progs);
int bpf_prog_array_length(struct bpf_prog_array *progs);
bool bpf_prog_array_is_empty(struct bpf_prog_array *array);
int bpf_prog_array_copy_to_user(struct bpf_prog_array *progs,
__u32 __user *prog_ids, u32 cnt);
void bpf_prog_array_delete_safe(struct bpf_prog_array *progs,
struct bpf_prog *old_prog);
int bpf_prog_array_copy_info(struct bpf_prog_array *array,
u32 *prog_ids, u32 request_cnt,
u32 *prog_cnt);
int bpf_prog_array_copy(struct bpf_prog_array *old_array,
struct bpf_prog *exclude_prog,
struct bpf_prog *include_prog,
struct bpf_prog_array **new_array);
#define __BPF_PROG_RUN_ARRAY(array, ctx, func, check_non_null) \
({ \
struct bpf_prog_array_item *_item; \
struct bpf_prog *_prog; \
struct bpf_prog_array *_array; \
u32 _ret = 1; \
preempt_disable(); \
rcu_read_lock(); \
_array = rcu_dereference(array); \
if (unlikely(check_non_null && !_array))\
goto _out; \
_item = &_array->items[0]; \
while ((_prog = READ_ONCE(_item->prog))) { \
bpf_cgroup_storage_set(_item->cgroup_storage); \
_ret &= func(_prog, ctx); \
_item++; \
} \
_out: \
rcu_read_unlock(); \
preempt_enable(); \
_ret; \
})
/* To be used by __cgroup_bpf_run_filter_skb for EGRESS BPF progs
* so BPF programs can request cwr for TCP packets.
*
* Current cgroup skb programs can only return 0 or 1 (0 to drop the
* packet. This macro changes the behavior so the low order bit
* indicates whether the packet should be dropped (0) or not (1)
* and the next bit is a congestion notification bit. This could be
* used by TCP to call tcp_enter_cwr()
*
* Hence, new allowed return values of CGROUP EGRESS BPF programs are:
* 0: drop packet
* 1: keep packet
* 2: drop packet and cn
* 3: keep packet and cn
*
* This macro then converts it to one of the NET_XMIT or an error
* code that is then interpreted as drop packet (and no cn):
* 0: NET_XMIT_SUCCESS skb should be transmitted
* 1: NET_XMIT_DROP skb should be dropped and cn
* 2: NET_XMIT_CN skb should be transmitted and cn
* 3: -EPERM skb should be dropped
*/
#define BPF_PROG_CGROUP_INET_EGRESS_RUN_ARRAY(array, ctx, func) \
({ \
struct bpf_prog_array_item *_item; \
struct bpf_prog *_prog; \
struct bpf_prog_array *_array; \
u32 ret; \
u32 _ret = 1; \
u32 _cn = 0; \
preempt_disable(); \
rcu_read_lock(); \
_array = rcu_dereference(array); \
_item = &_array->items[0]; \
while ((_prog = READ_ONCE(_item->prog))) { \
bpf_cgroup_storage_set(_item->cgroup_storage); \
ret = func(_prog, ctx); \
_ret &= (ret & 1); \
_cn |= (ret & 2); \
_item++; \
} \
rcu_read_unlock(); \
preempt_enable(); \
if (_ret) \
_ret = (_cn ? NET_XMIT_CN : NET_XMIT_SUCCESS); \
else \
_ret = (_cn ? NET_XMIT_DROP : -EPERM); \
_ret; \
})
#define BPF_PROG_RUN_ARRAY(array, ctx, func) \
__BPF_PROG_RUN_ARRAY(array, ctx, func, false)
#define BPF_PROG_RUN_ARRAY_CHECK(array, ctx, func) \
__BPF_PROG_RUN_ARRAY(array, ctx, func, true)
#ifdef CONFIG_BPF_SYSCALL
DECLARE_PER_CPU(int, bpf_prog_active);
extern const struct file_operations bpf_map_fops;
extern const struct file_operations bpf_prog_fops;
#define BPF_PROG_TYPE(_id, _name) \
extern const struct bpf_prog_ops _name ## _prog_ops; \
extern const struct bpf_verifier_ops _name ## _verifier_ops;
#define BPF_MAP_TYPE(_id, _ops) \
extern const struct bpf_map_ops _ops;
#include <linux/bpf_types.h>
#undef BPF_PROG_TYPE
#undef BPF_MAP_TYPE
extern const struct bpf_prog_ops bpf_offload_prog_ops;
extern const struct bpf_verifier_ops tc_cls_act_analyzer_ops;
extern const struct bpf_verifier_ops xdp_analyzer_ops;
struct bpf_prog *bpf_prog_get(u32 ufd);
struct bpf_prog *bpf_prog_get_type_dev(u32 ufd, enum bpf_prog_type type,
bool attach_drv);
struct bpf_prog * __must_check bpf_prog_add(struct bpf_prog *prog, int i);
void bpf_prog_sub(struct bpf_prog *prog, int i);
struct bpf_prog * __must_check bpf_prog_inc(struct bpf_prog *prog);
struct bpf_prog * __must_check bpf_prog_inc_not_zero(struct bpf_prog *prog);
void bpf_prog_put(struct bpf_prog *prog);
int __bpf_prog_charge(struct user_struct *user, u32 pages);
void __bpf_prog_uncharge(struct user_struct *user, u32 pages);
void bpf_prog_free_id(struct bpf_prog *prog, bool do_idr_lock);
void bpf_map_free_id(struct bpf_map *map, bool do_idr_lock);
struct bpf_map *bpf_map_get_with_uref(u32 ufd);
struct bpf_map *__bpf_map_get(struct fd f);
struct bpf_map * __must_check bpf_map_inc(struct bpf_map *map, bool uref);
struct bpf_map * __must_check bpf_map_inc_not_zero(struct bpf_map *map,
bool uref);
void bpf_map_put_with_uref(struct bpf_map *map);
void bpf_map_put(struct bpf_map *map);
int bpf_map_charge_memlock(struct bpf_map *map, u32 pages);
void bpf_map_uncharge_memlock(struct bpf_map *map, u32 pages);
int bpf_map_charge_init(struct bpf_map_memory *mem, size_t size);
void bpf_map_charge_finish(struct bpf_map_memory *mem);
void bpf_map_charge_move(struct bpf_map_memory *dst,
struct bpf_map_memory *src);
void *bpf_map_area_alloc(size_t size, int numa_node);
void bpf_map_area_free(void *base);
void bpf_map_init_from_attr(struct bpf_map *map, union bpf_attr *attr);
extern int sysctl_unprivileged_bpf_disabled;
int bpf_map_new_fd(struct bpf_map *map, int flags);
int bpf_prog_new_fd(struct bpf_prog *prog);
int bpf_obj_pin_user(u32 ufd, const char __user *pathname);
int bpf_obj_get_user(const char __user *pathname, int flags);
int bpf_percpu_hash_copy(struct bpf_map *map, void *key, void *value);
int bpf_percpu_array_copy(struct bpf_map *map, void *key, void *value);
int bpf_percpu_hash_update(struct bpf_map *map, void *key, void *value,
u64 flags);
int bpf_percpu_array_update(struct bpf_map *map, void *key, void *value,
u64 flags);
int bpf_stackmap_copy(struct bpf_map *map, void *key, void *value);
int bpf_fd_array_map_update_elem(struct bpf_map *map, struct file *map_file,
void *key, void *value, u64 map_flags);
int bpf_fd_array_map_lookup_elem(struct bpf_map *map, void *key, u32 *value);
int bpf_fd_htab_map_update_elem(struct bpf_map *map, struct file *map_file,
void *key, void *value, u64 map_flags);
int bpf_fd_htab_map_lookup_elem(struct bpf_map *map, void *key, u32 *value);
int bpf_get_file_flag(int flags);
int bpf_check_uarg_tail_zero(void __user *uaddr, size_t expected_size,
size_t actual_size);
/* memcpy that is used with 8-byte aligned pointers, power-of-8 size and
* forced to use 'long' read/writes to try to atomically copy long counters.
* Best-effort only. No barriers here, since it _will_ race with concurrent
* updates from BPF programs. Called from bpf syscall and mostly used with
* size 8 or 16 bytes, so ask compiler to inline it.
*/
static inline void bpf_long_memcpy(void *dst, const void *src, u32 size)
{
const long *lsrc = src;
long *ldst = dst;
size /= sizeof(long);
while (size--)
*ldst++ = *lsrc++;
}
/* verify correctness of eBPF program */
int bpf_check(struct bpf_prog **fp, union bpf_attr *attr,
union bpf_attr __user *uattr);
void bpf_patch_call_args(struct bpf_insn *insn, u32 stack_depth);
/* Map specifics */
struct xdp_buff;
struct sk_buff;
struct bpf_dtab_netdev *__dev_map_lookup_elem(struct bpf_map *map, u32 key);
struct bpf_dtab_netdev *__dev_map_hash_lookup_elem(struct bpf_map *map, u32 key);
void __dev_map_flush(struct bpf_map *map);
int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_buff *xdp,
struct net_device *dev_rx);
int dev_map_generic_redirect(struct bpf_dtab_netdev *dst, struct sk_buff *skb,
struct bpf_prog *xdp_prog);
struct bpf_cpu_map_entry *__cpu_map_lookup_elem(struct bpf_map *map, u32 key);
void __cpu_map_flush(struct bpf_map *map);
int cpu_map_enqueue(struct bpf_cpu_map_entry *rcpu, struct xdp_buff *xdp,
struct net_device *dev_rx);
/* Return map's numa specified by userspace */
static inline int bpf_map_attr_numa_node(const union bpf_attr *attr)
{
return (attr->map_flags & BPF_F_NUMA_NODE) ?
attr->numa_node : NUMA_NO_NODE;
}
struct bpf_prog *bpf_prog_get_type_path(const char *name, enum bpf_prog_type type);
int array_map_alloc_check(union bpf_attr *attr);
int bpf_prog_test_run_xdp(struct bpf_prog *prog, const union bpf_attr *kattr,
union bpf_attr __user *uattr);
int bpf_prog_test_run_skb(struct bpf_prog *prog, const union bpf_attr *kattr,
union bpf_attr __user *uattr);
int bpf_prog_test_run_flow_dissector(struct bpf_prog *prog,
const union bpf_attr *kattr,
union bpf_attr __user *uattr);
bool btf_ctx_access(int off, int size, enum bpf_access_type type,
const struct bpf_prog *prog,
struct bpf_insn_access_aux *info);
int btf_struct_access(struct bpf_verifier_log *log,
const struct btf_type *t, int off, int size,
enum bpf_access_type atype,
u32 *next_btf_id);
u32 btf_resolve_helper_id(struct bpf_verifier_log *log, void *, int);
#else /* !CONFIG_BPF_SYSCALL */
static inline struct bpf_prog *bpf_prog_get(u32 ufd)
{
return ERR_PTR(-EOPNOTSUPP);
}
static inline struct bpf_prog *bpf_prog_get_type_dev(u32 ufd,
enum bpf_prog_type type,
bool attach_drv)
{
return ERR_PTR(-EOPNOTSUPP);
}
static inline struct bpf_prog * __must_check bpf_prog_add(struct bpf_prog *prog,
int i)
{
return ERR_PTR(-EOPNOTSUPP);
}
static inline void bpf_prog_sub(struct bpf_prog *prog, int i)
{
}
static inline void bpf_prog_put(struct bpf_prog *prog)
{
}
static inline struct bpf_prog * __must_check bpf_prog_inc(struct bpf_prog *prog)
{
return ERR_PTR(-EOPNOTSUPP);
}
static inline struct bpf_prog *__must_check
bpf_prog_inc_not_zero(struct bpf_prog *prog)
{
return ERR_PTR(-EOPNOTSUPP);
}
static inline int __bpf_prog_charge(struct user_struct *user, u32 pages)
{
return 0;
}
static inline void __bpf_prog_uncharge(struct user_struct *user, u32 pages)
{
}
static inline int bpf_obj_get_user(const char __user *pathname, int flags)
{
return -EOPNOTSUPP;
}
static inline struct net_device *__dev_map_lookup_elem(struct bpf_map *map,
u32 key)
{
return NULL;
}
static inline struct net_device *__dev_map_hash_lookup_elem(struct bpf_map *map,
u32 key)
{
return NULL;
}
static inline void __dev_map_flush(struct bpf_map *map)
{
}
struct xdp_buff;
struct bpf_dtab_netdev;
static inline
int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_buff *xdp,
struct net_device *dev_rx)
{
return 0;
}
struct sk_buff;
static inline int dev_map_generic_redirect(struct bpf_dtab_netdev *dst,
struct sk_buff *skb,
struct bpf_prog *xdp_prog)
{
return 0;
}
static inline
struct bpf_cpu_map_entry *__cpu_map_lookup_elem(struct bpf_map *map, u32 key)
{
return NULL;
}
static inline void __cpu_map_flush(struct bpf_map *map)
{
}
static inline int cpu_map_enqueue(struct bpf_cpu_map_entry *rcpu,
struct xdp_buff *xdp,
struct net_device *dev_rx)
{
return 0;
}
static inline struct bpf_prog *bpf_prog_get_type_path(const char *name,
enum bpf_prog_type type)
{
return ERR_PTR(-EOPNOTSUPP);
}
static inline int bpf_prog_test_run_xdp(struct bpf_prog *prog,
const union bpf_attr *kattr,
union bpf_attr __user *uattr)
{
return -ENOTSUPP;
}
static inline int bpf_prog_test_run_skb(struct bpf_prog *prog,
const union bpf_attr *kattr,
union bpf_attr __user *uattr)
{
return -ENOTSUPP;
}
static inline int bpf_prog_test_run_flow_dissector(struct bpf_prog *prog,
const union bpf_attr *kattr,
union bpf_attr __user *uattr)
{
return -ENOTSUPP;
}
#endif /* CONFIG_BPF_SYSCALL */
static inline struct bpf_prog *bpf_prog_get_type(u32 ufd,
enum bpf_prog_type type)
{
return bpf_prog_get_type_dev(ufd, type, false);
}
bool bpf_prog_get_ok(struct bpf_prog *, enum bpf_prog_type *, bool);
int bpf_prog_offload_compile(struct bpf_prog *prog);
void bpf_prog_offload_destroy(struct bpf_prog *prog);
int bpf_prog_offload_info_fill(struct bpf_prog_info *info,
struct bpf_prog *prog);
int bpf_map_offload_info_fill(struct bpf_map_info *info, struct bpf_map *map);
int bpf_map_offload_lookup_elem(struct bpf_map *map, void *key, void *value);
int bpf_map_offload_update_elem(struct bpf_map *map,
void *key, void *value, u64 flags);
int bpf_map_offload_delete_elem(struct bpf_map *map, void *key);
int bpf_map_offload_get_next_key(struct bpf_map *map,
void *key, void *next_key);
bool bpf_offload_prog_map_match(struct bpf_prog *prog, struct bpf_map *map);
struct bpf_offload_dev *
bpf_offload_dev_create(const struct bpf_prog_offload_ops *ops, void *priv);
void bpf_offload_dev_destroy(struct bpf_offload_dev *offdev);
void *bpf_offload_dev_priv(struct bpf_offload_dev *offdev);
int bpf_offload_dev_netdev_register(struct bpf_offload_dev *offdev,
struct net_device *netdev);
void bpf_offload_dev_netdev_unregister(struct bpf_offload_dev *offdev,
struct net_device *netdev);
bool bpf_offload_dev_match(struct bpf_prog *prog, struct net_device *netdev);
#if defined(CONFIG_NET) && defined(CONFIG_BPF_SYSCALL)
int bpf_prog_offload_init(struct bpf_prog *prog, union bpf_attr *attr);
static inline bool bpf_prog_is_dev_bound(const struct bpf_prog_aux *aux)
{
return aux->offload_requested;
}
static inline bool bpf_map_is_dev_bound(struct bpf_map *map)
{
return unlikely(map->ops == &bpf_map_offload_ops);
}
struct bpf_map *bpf_map_offload_map_alloc(union bpf_attr *attr);
void bpf_map_offload_map_free(struct bpf_map *map);
#else
static inline int bpf_prog_offload_init(struct bpf_prog *prog,
union bpf_attr *attr)
{
return -EOPNOTSUPP;
}
static inline bool bpf_prog_is_dev_bound(struct bpf_prog_aux *aux)
{
return false;
}
static inline bool bpf_map_is_dev_bound(struct bpf_map *map)
{
return false;
}
static inline struct bpf_map *bpf_map_offload_map_alloc(union bpf_attr *attr)
{
return ERR_PTR(-EOPNOTSUPP);
}
static inline void bpf_map_offload_map_free(struct bpf_map *map)
{
}
#endif /* CONFIG_NET && CONFIG_BPF_SYSCALL */
#if defined(CONFIG_BPF_STREAM_PARSER)
int sock_map_prog_update(struct bpf_map *map, struct bpf_prog *prog, u32 which);
int sock_map_get_from_fd(const union bpf_attr *attr, struct bpf_prog *prog);
#else
static inline int sock_map_prog_update(struct bpf_map *map,
struct bpf_prog *prog, u32 which)
{
return -EOPNOTSUPP;
}
static inline int sock_map_get_from_fd(const union bpf_attr *attr,
struct bpf_prog *prog)
{
return -EINVAL;
}
#endif
#if defined(CONFIG_XDP_SOCKETS)
struct xdp_sock;
struct xdp_sock *__xsk_map_lookup_elem(struct bpf_map *map, u32 key);
int __xsk_map_redirect(struct bpf_map *map, struct xdp_buff *xdp,
struct xdp_sock *xs);
void __xsk_map_flush(struct bpf_map *map);
#else
struct xdp_sock;
static inline struct xdp_sock *__xsk_map_lookup_elem(struct bpf_map *map,
u32 key)
{
return NULL;
}
static inline int __xsk_map_redirect(struct bpf_map *map, struct xdp_buff *xdp,
struct xdp_sock *xs)
{
return -EOPNOTSUPP;
}
static inline void __xsk_map_flush(struct bpf_map *map)
{
}
#endif
#if defined(CONFIG_INET) && defined(CONFIG_BPF_SYSCALL)
void bpf_sk_reuseport_detach(struct sock *sk);
int bpf_fd_reuseport_array_lookup_elem(struct bpf_map *map, void *key,
void *value);
int bpf_fd_reuseport_array_update_elem(struct bpf_map *map, void *key,
void *value, u64 map_flags);
#else
static inline void bpf_sk_reuseport_detach(struct sock *sk)
{
}
#ifdef CONFIG_BPF_SYSCALL
static inline int bpf_fd_reuseport_array_lookup_elem(struct bpf_map *map,
void *key, void *value)
{
return -EOPNOTSUPP;
}
static inline int bpf_fd_reuseport_array_update_elem(struct bpf_map *map,
void *key, void *value,
u64 map_flags)
{
return -EOPNOTSUPP;
}
#endif /* CONFIG_BPF_SYSCALL */
#endif /* defined(CONFIG_INET) && defined(CONFIG_BPF_SYSCALL) */
/* verifier prototypes for helper functions called from eBPF programs */
extern const struct bpf_func_proto bpf_map_lookup_elem_proto;
extern const struct bpf_func_proto bpf_map_update_elem_proto;
extern const struct bpf_func_proto bpf_map_delete_elem_proto;
extern const struct bpf_func_proto bpf_map_push_elem_proto;
extern const struct bpf_func_proto bpf_map_pop_elem_proto;
extern const struct bpf_func_proto bpf_map_peek_elem_proto;
extern const struct bpf_func_proto bpf_get_prandom_u32_proto;
extern const struct bpf_func_proto bpf_get_smp_processor_id_proto;
extern const struct bpf_func_proto bpf_get_numa_node_id_proto;
extern const struct bpf_func_proto bpf_tail_call_proto;
extern const struct bpf_func_proto bpf_ktime_get_ns_proto;
extern const struct bpf_func_proto bpf_get_current_pid_tgid_proto;
extern const struct bpf_func_proto bpf_get_current_uid_gid_proto;
extern const struct bpf_func_proto bpf_get_current_comm_proto;
extern const struct bpf_func_proto bpf_get_stackid_proto;
extern const struct bpf_func_proto bpf_get_stack_proto;
extern const struct bpf_func_proto bpf_sock_map_update_proto;
extern const struct bpf_func_proto bpf_sock_hash_update_proto;
extern const struct bpf_func_proto bpf_get_current_cgroup_id_proto;
extern const struct bpf_func_proto bpf_msg_redirect_hash_proto;
extern const struct bpf_func_proto bpf_msg_redirect_map_proto;
extern const struct bpf_func_proto bpf_sk_redirect_hash_proto;
extern const struct bpf_func_proto bpf_sk_redirect_map_proto;
extern const struct bpf_func_proto bpf_spin_lock_proto;
extern const struct bpf_func_proto bpf_spin_unlock_proto;
extern const struct bpf_func_proto bpf_get_local_storage_proto;
extern const struct bpf_func_proto bpf_strtol_proto;
extern const struct bpf_func_proto bpf_strtoul_proto;
extern const struct bpf_func_proto bpf_tcp_sock_proto;
/* Shared helpers among cBPF and eBPF. */
void bpf_user_rnd_init_once(void);
u64 bpf_user_rnd_u32(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5);
#if defined(CONFIG_NET)
bool bpf_sock_common_is_valid_access(int off, int size,
enum bpf_access_type type,
struct bpf_insn_access_aux *info);
bool bpf_sock_is_valid_access(int off, int size, enum bpf_access_type type,
struct bpf_insn_access_aux *info);
u32 bpf_sock_convert_ctx_access(enum bpf_access_type type,
const struct bpf_insn *si,
struct bpf_insn *insn_buf,
struct bpf_prog *prog,
u32 *target_size);
#else
static inline bool bpf_sock_common_is_valid_access(int off, int size,
enum bpf_access_type type,
struct bpf_insn_access_aux *info)
{
return false;
}
static inline bool bpf_sock_is_valid_access(int off, int size,
enum bpf_access_type type,
struct bpf_insn_access_aux *info)
{
return false;
}
static inline u32 bpf_sock_convert_ctx_access(enum bpf_access_type type,
const struct bpf_insn *si,
struct bpf_insn *insn_buf,
struct bpf_prog *prog,
u32 *target_size)
{
return 0;
}
#endif
#ifdef CONFIG_INET
bool bpf_tcp_sock_is_valid_access(int off, int size, enum bpf_access_type type,
struct bpf_insn_access_aux *info);
u32 bpf_tcp_sock_convert_ctx_access(enum bpf_access_type type,
const struct bpf_insn *si,
struct bpf_insn *insn_buf,
struct bpf_prog *prog,
u32 *target_size);
bool bpf_xdp_sock_is_valid_access(int off, int size, enum bpf_access_type type,
struct bpf_insn_access_aux *info);
u32 bpf_xdp_sock_convert_ctx_access(enum bpf_access_type type,
const struct bpf_insn *si,
struct bpf_insn *insn_buf,
struct bpf_prog *prog,
u32 *target_size);
#else
static inline bool bpf_tcp_sock_is_valid_access(int off, int size,
enum bpf_access_type type,
struct bpf_insn_access_aux *info)
{
return false;
}
static inline u32 bpf_tcp_sock_convert_ctx_access(enum bpf_access_type type,
const struct bpf_insn *si,
struct bpf_insn *insn_buf,
struct bpf_prog *prog,
u32 *target_size)
{
return 0;
}
static inline bool bpf_xdp_sock_is_valid_access(int off, int size,
enum bpf_access_type type,
struct bpf_insn_access_aux *info)
{
return false;
}
static inline u32 bpf_xdp_sock_convert_ctx_access(enum bpf_access_type type,
const struct bpf_insn *si,
struct bpf_insn *insn_buf,
struct bpf_prog *prog,
u32 *target_size)
{
return 0;
}
#endif /* CONFIG_INET */
#endif /* _LINUX_BPF_H */