renegade-project/linux-next
2
0
Fork 0
mirror of https://github.com/edk2-porting/linux-next.git synced 2024-12-25 05:34:00 +08:00
Code
5765f9f66e
linux-next/include/linux/filter.h
Alexei Starovoitov 04fd61ab36 bpf: allow bpf programs to tail-call other bpf programs 
introduce bpf_tail_call(ctx, &jmp_table, index) helper function
which can be used from BPF programs like:
int bpf_prog(struct pt_regs *ctx)
{
  ...
  bpf_tail_call(ctx, &jmp_table, index);
  ...
}
that is roughly equivalent to:
int bpf_prog(struct pt_regs *ctx)
{
  ...
  if (jmp_table[index])
    return (*jmp_table[index])(ctx);
  ...
}
The important detail that it's not a normal call, but a tail call.
The kernel stack is precious, so this helper reuses the current
stack frame and jumps into another BPF program without adding
extra call frame.
It's trivially done in interpreter and a bit trickier in JITs.
In case of x64 JIT the bigger part of generated assembler prologue
is common for all programs, so it is simply skipped while jumping.
Other JITs can do similar prologue-skipping optimization or
do stack unwind before jumping into the next program.

bpf_tail_call() arguments:
ctx - context pointer
jmp_table - one of BPF_MAP_TYPE_PROG_ARRAY maps used as the jump table
index - index in the jump table

Since all BPF programs are idenitified by file descriptor, user space
need to populate the jmp_table with FDs of other BPF programs.
If jmp_table[index] is empty the bpf_tail_call() doesn't jump anywhere
and program execution continues as normal.

New BPF_MAP_TYPE_PROG_ARRAY map type is introduced so that user space can
populate this jmp_table array with FDs of other bpf programs.
Programs can share the same jmp_table array or use multiple jmp_tables.

The chain of tail calls can form unpredictable dynamic loops therefore
tail_call_cnt is used to limit the number of calls and currently is set to 32.

Use cases:
Acked-by: Daniel Borkmann <daniel@iogearbox.net>

==========
- simplify complex programs by splitting them into a sequence of small programs

- dispatch routine
  For tracing and future seccomp the program may be triggered on all system
  calls, but processing of syscall arguments will be different. It's more
  efficient to implement them as:
  int syscall_entry(struct seccomp_data *ctx)
  {
     bpf_tail_call(ctx, &syscall_jmp_table, ctx->nr /* syscall number */);
     ... default: process unknown syscall ...
  }
  int sys_write_event(struct seccomp_data *ctx) {...}
  int sys_read_event(struct seccomp_data *ctx) {...}
  syscall_jmp_table[__NR_write] = sys_write_event;
  syscall_jmp_table[__NR_read] = sys_read_event;

  For networking the program may call into different parsers depending on
  packet format, like:
  int packet_parser(struct __sk_buff *skb)
  {
     ... parse L2, L3 here ...
     __u8 ipproto = load_byte(skb, ... offsetof(struct iphdr, protocol));
     bpf_tail_call(skb, &ipproto_jmp_table, ipproto);
     ... default: process unknown protocol ...
  }
  int parse_tcp(struct __sk_buff *skb) {...}
  int parse_udp(struct __sk_buff *skb) {...}
  ipproto_jmp_table[IPPROTO_TCP] = parse_tcp;
  ipproto_jmp_table[IPPROTO_UDP] = parse_udp;

- for TC use case, bpf_tail_call() allows to implement reclassify-like logic

- bpf_map_update_elem/delete calls into BPF_MAP_TYPE_PROG_ARRAY jump table
  are atomic, so user space can build chains of BPF programs on the fly

Implementation details:
=======================
- high performance of bpf_tail_call() is the goal.
  It could have been implemented without JIT changes as a wrapper on top of
  BPF_PROG_RUN() macro, but with two downsides:
  . all programs would have to pay performance penalty for this feature and
    tail call itself would be slower, since mandatory stack unwind, return,
    stack allocate would be done for every tailcall.
  . tailcall would be limited to programs running preempt_disabled, since
    generic 'void *ctx' doesn't have room for 'tail_call_cnt' and it would
    need to be either global per_cpu variable accessed by helper and by wrapper
    or global variable protected by locks.

  In this implementation x64 JIT bypasses stack unwind and jumps into the
  callee program after prologue.

- bpf_prog_array_compatible() ensures that prog_type of callee and caller
  are the same and JITed/non-JITed flag is the same, since calling JITed
  program from non-JITed is invalid, since stack frames are different.
  Similarly calling kprobe type program from socket type program is invalid.

- jump table is implemented as BPF_MAP_TYPE_PROG_ARRAY to reuse 'map'
  abstraction, its user space API and all of verifier logic.
  It's in the existing arraymap.c file, since several functions are
  shared with regular array map.

Signed-off-by: Alexei Starovoitov <ast@plumgrid.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
2015-05-21 17:07:59 -04:00

501 lines
13 KiB
C
Raw Blame History

/*
* Linux Socket Filter Data Structures
*/
#ifndef __LINUX_FILTER_H__
#define __LINUX_FILTER_H__
#include <stdarg.h>
#include <linux/atomic.h>
#include <linux/compat.h>
#include <linux/skbuff.h>
#include <linux/linkage.h>
#include <linux/printk.h>
#include <linux/workqueue.h>
#include <asm/cacheflush.h>
#include <uapi/linux/filter.h>
#include <uapi/linux/bpf.h>
struct sk_buff;
struct sock;
struct seccomp_data;
struct bpf_prog_aux;
/* ArgX, context and stack frame pointer register positions. Note,
* Arg1, Arg2, Arg3, etc are used as argument mappings of function
* calls in BPF_CALL instruction.
*/
#define BPF_REG_ARG1 BPF_REG_1
#define BPF_REG_ARG2 BPF_REG_2
#define BPF_REG_ARG3 BPF_REG_3
#define BPF_REG_ARG4 BPF_REG_4
#define BPF_REG_ARG5 BPF_REG_5
#define BPF_REG_CTX BPF_REG_6
#define BPF_REG_FP BPF_REG_10
/* Additional register mappings for converted user programs. */
#define BPF_REG_A BPF_REG_0
#define BPF_REG_X BPF_REG_7
#define BPF_REG_TMP BPF_REG_8
/* BPF program can access up to 512 bytes of stack space. */
#define MAX_BPF_STACK 512
/* Helper macros for filter block array initializers. */
/* ALU ops on registers, bpf_add|sub|...: dst_reg += src_reg */
#define BPF_ALU64_REG(OP, DST, SRC) \
((struct bpf_insn) { \
.code = BPF_ALU64 | BPF_OP(OP) | BPF_X, \
.dst_reg = DST, \
.src_reg = SRC, \
.off = 0, \
.imm = 0 })
#define BPF_ALU32_REG(OP, DST, SRC) \
((struct bpf_insn) { \
.code = BPF_ALU | BPF_OP(OP) | BPF_X, \
.dst_reg = DST, \
.src_reg = SRC, \
.off = 0, \
.imm = 0 })
/* ALU ops on immediates, bpf_add|sub|...: dst_reg += imm32 */
#define BPF_ALU64_IMM(OP, DST, IMM) \
((struct bpf_insn) { \
.code = BPF_ALU64 | BPF_OP(OP) | BPF_K, \
.dst_reg = DST, \
.src_reg = 0, \
.off = 0, \
.imm = IMM })
#define BPF_ALU32_IMM(OP, DST, IMM) \
((struct bpf_insn) { \
.code = BPF_ALU | BPF_OP(OP) | BPF_K, \
.dst_reg = DST, \
.src_reg = 0, \
.off = 0, \
.imm = IMM })
/* Endianess conversion, cpu_to_{l,b}e(), {l,b}e_to_cpu() */
#define BPF_ENDIAN(TYPE, DST, LEN) \
((struct bpf_insn) { \
.code = BPF_ALU | BPF_END | BPF_SRC(TYPE), \
.dst_reg = DST, \
.src_reg = 0, \
.off = 0, \
.imm = LEN })
/* Short form of mov, dst_reg = src_reg */
#define BPF_MOV64_REG(DST, SRC) \
((struct bpf_insn) { \
.code = BPF_ALU64 | BPF_MOV | BPF_X, \
.dst_reg = DST, \
.src_reg = SRC, \
.off = 0, \
.imm = 0 })
#define BPF_MOV32_REG(DST, SRC) \
((struct bpf_insn) { \
.code = BPF_ALU | BPF_MOV | BPF_X, \
.dst_reg = DST, \
.src_reg = SRC, \
.off = 0, \
.imm = 0 })
/* Short form of mov, dst_reg = imm32 */
#define BPF_MOV64_IMM(DST, IMM) \
((struct bpf_insn) { \
.code = BPF_ALU64 | BPF_MOV | BPF_K, \
.dst_reg = DST, \
.src_reg = 0, \
.off = 0, \
.imm = IMM })
#define BPF_MOV32_IMM(DST, IMM) \
((struct bpf_insn) { \
.code = BPF_ALU | BPF_MOV | BPF_K, \
.dst_reg = DST, \
.src_reg = 0, \
.off = 0, \
.imm = IMM })
/* BPF_LD_IMM64 macro encodes single 'load 64-bit immediate' insn */
#define BPF_LD_IMM64(DST, IMM) \
BPF_LD_IMM64_RAW(DST, 0, IMM)
#define BPF_LD_IMM64_RAW(DST, SRC, IMM) \
((struct bpf_insn) { \
.code = BPF_LD | BPF_DW | BPF_IMM, \
.dst_reg = DST, \
.src_reg = SRC, \
.off = 0, \
.imm = (__u32) (IMM) }), \
((struct bpf_insn) { \
.code = 0, /* zero is reserved opcode */ \
.dst_reg = 0, \
.src_reg = 0, \
.off = 0, \
.imm = ((__u64) (IMM)) >> 32 })
/* pseudo BPF_LD_IMM64 insn used to refer to process-local map_fd */
#define BPF_LD_MAP_FD(DST, MAP_FD) \
BPF_LD_IMM64_RAW(DST, BPF_PSEUDO_MAP_FD, MAP_FD)
/* Short form of mov based on type, BPF_X: dst_reg = src_reg, BPF_K: dst_reg = imm32 */
#define BPF_MOV64_RAW(TYPE, DST, SRC, IMM) \
((struct bpf_insn) { \
.code = BPF_ALU64 | BPF_MOV | BPF_SRC(TYPE), \
.dst_reg = DST, \
.src_reg = SRC, \
.off = 0, \
.imm = IMM })
#define BPF_MOV32_RAW(TYPE, DST, SRC, IMM) \
((struct bpf_insn) { \
.code = BPF_ALU | BPF_MOV | BPF_SRC(TYPE), \
.dst_reg = DST, \
.src_reg = SRC, \
.off = 0, \
.imm = IMM })
/* Direct packet access, R0 = *(uint *) (skb->data + imm32) */
#define BPF_LD_ABS(SIZE, IMM) \
((struct bpf_insn) { \
.code = BPF_LD | BPF_SIZE(SIZE) | BPF_ABS, \
.dst_reg = 0, \
.src_reg = 0, \
.off = 0, \
.imm = IMM })
/* Indirect packet access, R0 = *(uint *) (skb->data + src_reg + imm32) */
#define BPF_LD_IND(SIZE, SRC, IMM) \
((struct bpf_insn) { \
.code = BPF_LD | BPF_SIZE(SIZE) | BPF_IND, \
.dst_reg = 0, \
.src_reg = SRC, \
.off = 0, \
.imm = IMM })
/* Memory load, dst_reg = *(uint *) (src_reg + off16) */
#define BPF_LDX_MEM(SIZE, DST, SRC, OFF) \
((struct bpf_insn) { \
.code = BPF_LDX | BPF_SIZE(SIZE) | BPF_MEM, \
.dst_reg = DST, \
.src_reg = SRC, \
.off = OFF, \
.imm = 0 })
/* Memory store, *(uint *) (dst_reg + off16) = src_reg */
#define BPF_STX_MEM(SIZE, DST, SRC, OFF) \
((struct bpf_insn) { \
.code = BPF_STX | BPF_SIZE(SIZE) | BPF_MEM, \
.dst_reg = DST, \
.src_reg = SRC, \
.off = OFF, \
.imm = 0 })
/* Atomic memory add, *(uint *)(dst_reg + off16) += src_reg */
#define BPF_STX_XADD(SIZE, DST, SRC, OFF) \
((struct bpf_insn) { \
.code = BPF_STX | BPF_SIZE(SIZE) | BPF_XADD, \
.dst_reg = DST, \
.src_reg = SRC, \
.off = OFF, \
.imm = 0 })
/* Memory store, *(uint *) (dst_reg + off16) = imm32 */
#define BPF_ST_MEM(SIZE, DST, OFF, IMM) \
((struct bpf_insn) { \
.code = BPF_ST | BPF_SIZE(SIZE) | BPF_MEM, \
.dst_reg = DST, \
.src_reg = 0, \
.off = OFF, \
.imm = IMM })
/* Conditional jumps against registers, if (dst_reg 'op' src_reg) goto pc + off16 */
#define BPF_JMP_REG(OP, DST, SRC, OFF) \
((struct bpf_insn) { \
.code = BPF_JMP | BPF_OP(OP) | BPF_X, \
.dst_reg = DST, \
.src_reg = SRC, \
.off = OFF, \
.imm = 0 })
/* Conditional jumps against immediates, if (dst_reg 'op' imm32) goto pc + off16 */
#define BPF_JMP_IMM(OP, DST, IMM, OFF) \
((struct bpf_insn) { \
.code = BPF_JMP | BPF_OP(OP) | BPF_K, \
.dst_reg = DST, \
.src_reg = 0, \
.off = OFF, \
.imm = IMM })
/* Function call */
#define BPF_EMIT_CALL(FUNC) \
((struct bpf_insn) { \
.code = BPF_JMP | BPF_CALL, \
.dst_reg = 0, \
.src_reg = 0, \
.off = 0, \
.imm = ((FUNC) - __bpf_call_base) })
/* Raw code statement block */
#define BPF_RAW_INSN(CODE, DST, SRC, OFF, IMM) \
((struct bpf_insn) { \
.code = CODE, \
.dst_reg = DST, \
.src_reg = SRC, \
.off = OFF, \
.imm = IMM })
/* Program exit */
#define BPF_EXIT_INSN() \
((struct bpf_insn) { \
.code = BPF_JMP | BPF_EXIT, \
.dst_reg = 0, \
.src_reg = 0, \
.off = 0, \
.imm = 0 })
/* Internal classic blocks for direct assignment */
#define __BPF_STMT(CODE, K) \
((struct sock_filter) BPF_STMT(CODE, K))
#define __BPF_JUMP(CODE, K, JT, JF) \
((struct sock_filter) BPF_JUMP(CODE, K, JT, JF))
#define bytes_to_bpf_size(bytes) \
({ \
int bpf_size = -EINVAL; \
\
if (bytes == sizeof(u8)) \
bpf_size = BPF_B; \
else if (bytes == sizeof(u16)) \
bpf_size = BPF_H; \
else if (bytes == sizeof(u32)) \
bpf_size = BPF_W; \
else if (bytes == sizeof(u64)) \
bpf_size = BPF_DW; \
\
bpf_size; \
})
/* Macro to invoke filter function. */
#define SK_RUN_FILTER(filter, ctx) \
(*filter->prog->bpf_func)(ctx, filter->prog->insnsi)
#ifdef CONFIG_COMPAT
/* A struct sock_filter is architecture independent. */
struct compat_sock_fprog {
u16 len;
compat_uptr_t filter; /* struct sock_filter * */
};
#endif
struct sock_fprog_kern {
u16 len;
struct sock_filter *filter;
};
struct bpf_binary_header {
unsigned int pages;
u8 image[];
};
struct bpf_prog {
u16 pages; /* Number of allocated pages */
bool jited; /* Is our filter JIT'ed? */
bool gpl_compatible; /* Is our filter GPL compatible? */
u32 len; /* Number of filter blocks */
enum bpf_prog_type type; /* Type of BPF program */
struct bpf_prog_aux *aux; /* Auxiliary fields */
struct sock_fprog_kern *orig_prog; /* Original BPF program */
unsigned int (*bpf_func)(const struct sk_buff *skb,
const struct bpf_insn *filter);
/* Instructions for interpreter */
union {
struct sock_filter insns[0];
struct bpf_insn insnsi[0];
};
};
struct sk_filter {
atomic_t refcnt;
struct rcu_head rcu;
struct bpf_prog *prog;
};
#define BPF_PROG_RUN(filter, ctx) (*filter->bpf_func)(ctx, filter->insnsi)
static inline unsigned int bpf_prog_size(unsigned int proglen)
{
return max(sizeof(struct bpf_prog),
offsetof(struct bpf_prog, insns[proglen]));
}
#define bpf_classic_proglen(fprog) (fprog->len * sizeof(fprog->filter[0]))
#ifdef CONFIG_DEBUG_SET_MODULE_RONX
static inline void bpf_prog_lock_ro(struct bpf_prog *fp)
{
set_memory_ro((unsigned long)fp, fp->pages);
}
static inline void bpf_prog_unlock_ro(struct bpf_prog *fp)
{
set_memory_rw((unsigned long)fp, fp->pages);
}
#else
static inline void bpf_prog_lock_ro(struct bpf_prog *fp)
{
}
static inline void bpf_prog_unlock_ro(struct bpf_prog *fp)
{
}
#endif /* CONFIG_DEBUG_SET_MODULE_RONX */
int sk_filter(struct sock *sk, struct sk_buff *skb);
int bpf_prog_select_runtime(struct bpf_prog *fp);
void bpf_prog_free(struct bpf_prog *fp);
struct bpf_prog *bpf_prog_alloc(unsigned int size, gfp_t gfp_extra_flags);
struct bpf_prog *bpf_prog_realloc(struct bpf_prog *fp_old, unsigned int size,
gfp_t gfp_extra_flags);
void __bpf_prog_free(struct bpf_prog *fp);
static inline void bpf_prog_unlock_free(struct bpf_prog *fp)
{
bpf_prog_unlock_ro(fp);
__bpf_prog_free(fp);
}
typedef int (*bpf_aux_classic_check_t)(struct sock_filter *filter,
unsigned int flen);
int bpf_prog_create(struct bpf_prog **pfp, struct sock_fprog_kern *fprog);
int bpf_prog_create_from_user(struct bpf_prog **pfp, struct sock_fprog *fprog,
bpf_aux_classic_check_t trans);
void bpf_prog_destroy(struct bpf_prog *fp);
int sk_attach_filter(struct sock_fprog *fprog, struct sock *sk);
int sk_attach_bpf(u32 ufd, struct sock *sk);
int sk_detach_filter(struct sock *sk);
int sk_get_filter(struct sock *sk, struct sock_filter __user *filter,
unsigned int len);
bool sk_filter_charge(struct sock *sk, struct sk_filter *fp);
void sk_filter_uncharge(struct sock *sk, struct sk_filter *fp);
u64 __bpf_call_base(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5);
void bpf_int_jit_compile(struct bpf_prog *fp);
#ifdef CONFIG_BPF_JIT
typedef void (*bpf_jit_fill_hole_t)(void *area, unsigned int size);
struct bpf_binary_header *
bpf_jit_binary_alloc(unsigned int proglen, u8 **image_ptr,
unsigned int alignment,
bpf_jit_fill_hole_t bpf_fill_ill_insns);
void bpf_jit_binary_free(struct bpf_binary_header *hdr);
void bpf_jit_compile(struct bpf_prog *fp);
void bpf_jit_free(struct bpf_prog *fp);
static inline void bpf_jit_dump(unsigned int flen, unsigned int proglen,
u32 pass, void *image)
{
pr_err("flen=%u proglen=%u pass=%u image=%pK\n",
flen, proglen, pass, image);
if (image)
print_hex_dump(KERN_ERR, "JIT code: ", DUMP_PREFIX_OFFSET,
16, 1, image, proglen, false);
}
#else
static inline void bpf_jit_compile(struct bpf_prog *fp)
{
}
static inline void bpf_jit_free(struct bpf_prog *fp)
{
bpf_prog_unlock_free(fp);
}
#endif /* CONFIG_BPF_JIT */
#define BPF_ANC BIT(15)
static inline u16 bpf_anc_helper(const struct sock_filter *ftest)
{
BUG_ON(ftest->code & BPF_ANC);
switch (ftest->code) {
case BPF_LD | BPF_W | BPF_ABS:
case BPF_LD | BPF_H | BPF_ABS:
case BPF_LD | BPF_B | BPF_ABS:
#define BPF_ANCILLARY(CODE) case SKF_AD_OFF + SKF_AD_##CODE: \
return BPF_ANC | SKF_AD_##CODE
switch (ftest->k) {
BPF_ANCILLARY(PROTOCOL);
BPF_ANCILLARY(PKTTYPE);
BPF_ANCILLARY(IFINDEX);
BPF_ANCILLARY(NLATTR);
BPF_ANCILLARY(NLATTR_NEST);
BPF_ANCILLARY(MARK);
BPF_ANCILLARY(QUEUE);
BPF_ANCILLARY(HATYPE);
BPF_ANCILLARY(RXHASH);
BPF_ANCILLARY(CPU);
BPF_ANCILLARY(ALU_XOR_X);
BPF_ANCILLARY(VLAN_TAG);
BPF_ANCILLARY(VLAN_TAG_PRESENT);
BPF_ANCILLARY(PAY_OFFSET);
BPF_ANCILLARY(RANDOM);
BPF_ANCILLARY(VLAN_TPID);
}
/* Fallthrough. */
default:
return ftest->code;
}
}
void *bpf_internal_load_pointer_neg_helper(const struct sk_buff *skb,
int k, unsigned int size);
static inline void *bpf_load_pointer(const struct sk_buff *skb, int k,
unsigned int size, void *buffer)
{
if (k >= 0)
return skb_header_pointer(skb, k, size, buffer);
return bpf_internal_load_pointer_neg_helper(skb, k, size);
}
static inline int bpf_tell_extensions(void)
{
return SKF_AD_MAX;
}
#endif /* __LINUX_FILTER_H__ */
View Git Blame Copy Permalink