linux_dsm_epyc7002/include/linux/bpf.h
Alexei Starovoitov 557c0c6e7d bpf: convert stackmap to pre-allocation
It was observed that calling bpf_get_stackid() from a kprobe inside
slub or from spin_unlock causes similar deadlock as with hashmap,
therefore convert stackmap to use pre-allocated memory.

The call_rcu is no longer feasible mechanism, since delayed freeing
causes bpf_get_stackid() to fail unpredictably when number of actual
stacks is significantly less than user requested max_entries.
Since elements are no longer freed into slub, we can push elements into
freelist immediately and let them be recycled.
However the very unlikley race between user space map_lookup() and
program-side recycling is possible:
     cpu0                          cpu1
     ----                          ----
user does lookup(stackidX)
starts copying ips into buffer
                                   delete(stackidX)
                                   calls bpf_get_stackid()
				   which recyles the element and
                                   overwrites with new stack trace

To avoid user space seeing a partial stack trace consisting of two
merged stack traces, do bucket = xchg(, NULL); copy; xchg(,bucket);
to preserve consistent stack trace delivery to user space.
Now we can move memset(,0) of left-over element value from critical
path of bpf_get_stackid() into slow-path of user space lookup.
Also disallow lookup() from bpf program, since it's useless and
program shouldn't be messing with collected stack trace.

Note that similar race between user space lookup and kernel side updates
is also present in hashmap, but it's not a new race. bpf programs were
always allowed to modify hash and array map elements while user space
is copying them.

Fixes: d5a3b1f691 ("bpf: introduce BPF_MAP_TYPE_STACK_TRACE")
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
2016-03-08 15:28:31 -05:00

254 lines
8.0 KiB
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.
*/
#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>
struct bpf_map;
/* map is generic key/value storage optionally accesible by eBPF programs */
struct bpf_map_ops {
/* funcs callable from userspace (via syscall) */
struct bpf_map *(*map_alloc)(union bpf_attr *attr);
void (*map_free)(struct bpf_map *);
int (*map_get_next_key)(struct bpf_map *map, void *key, void *next_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);
/* funcs called by prog_array and perf_event_array map */
void *(*map_fd_get_ptr) (struct bpf_map *map, int fd);
void (*map_fd_put_ptr) (void *ptr);
};
struct bpf_map {
atomic_t refcnt;
enum bpf_map_type map_type;
u32 key_size;
u32 value_size;
u32 max_entries;
u32 map_flags;
u32 pages;
struct user_struct *user;
const struct bpf_map_ops *ops;
struct work_struct work;
atomic_t usercnt;
};
struct bpf_map_type_list {
struct list_head list_node;
const struct bpf_map_ops *ops;
enum bpf_map_type type;
};
/* 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_STACK, /* any pointer to eBPF program stack */
ARG_CONST_STACK_SIZE, /* number of bytes accessed from stack */
ARG_CONST_STACK_SIZE_OR_ZERO, /* number of bytes accessed from stack 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;
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
};
struct bpf_prog;
struct bpf_verifier_ops {
/* return eBPF function prototype for verification */
const struct bpf_func_proto *(*get_func_proto)(enum bpf_func_id func_id);
/* 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);
u32 (*convert_ctx_access)(enum bpf_access_type type, int dst_reg,
int src_reg, int ctx_off,
struct bpf_insn *insn, struct bpf_prog *prog);
};
struct bpf_prog_type_list {
struct list_head list_node;
const struct bpf_verifier_ops *ops;
enum bpf_prog_type type;
};
struct bpf_prog_aux {
atomic_t refcnt;
u32 used_map_cnt;
const struct bpf_verifier_ops *ops;
struct bpf_map **used_maps;
struct bpf_prog *prog;
struct user_struct *user;
union {
struct work_struct work;
struct rcu_head rcu;
};
};
struct bpf_array {
struct bpf_map map;
u32 elem_size;
/* '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 MAX_TAIL_CALL_CNT 32
u64 bpf_tail_call(u64 ctx, u64 r2, u64 index, u64 r4, u64 r5);
void bpf_fd_array_map_clear(struct bpf_map *map);
bool bpf_prog_array_compatible(struct bpf_array *array, const struct bpf_prog *fp);
const struct bpf_func_proto *bpf_get_trace_printk_proto(void);
#ifdef CONFIG_BPF_SYSCALL
DECLARE_PER_CPU(int, bpf_prog_active);
void bpf_register_prog_type(struct bpf_prog_type_list *tl);
void bpf_register_map_type(struct bpf_map_type_list *tl);
struct bpf_prog *bpf_prog_get(u32 ufd);
void bpf_prog_put(struct bpf_prog *prog);
void bpf_prog_put_rcu(struct bpf_prog *prog);
struct bpf_map *bpf_map_get_with_uref(u32 ufd);
struct bpf_map *__bpf_map_get(struct fd f);
void bpf_map_inc(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_precharge_memlock(u32 pages);
extern int sysctl_unprivileged_bpf_disabled;
int bpf_map_new_fd(struct bpf_map *map);
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 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);
/* 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);
#else
static inline void bpf_register_prog_type(struct bpf_prog_type_list *tl)
{
}
static inline struct bpf_prog *bpf_prog_get(u32 ufd)
{
return ERR_PTR(-EOPNOTSUPP);
}
static inline void bpf_prog_put(struct bpf_prog *prog)
{
}
#endif /* 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_get_prandom_u32_proto;
extern const struct bpf_func_proto bpf_get_smp_processor_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_skb_vlan_push_proto;
extern const struct bpf_func_proto bpf_skb_vlan_pop_proto;
extern const struct bpf_func_proto bpf_get_stackid_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);
#endif /* _LINUX_BPF_H */