kernel-ark/include/linux/filter.h
Hagen Paul Pfeifer 01f2f3f6ef net: optimize Berkeley Packet Filter (BPF) processing
Gcc is currenlty not in the ability to optimize the switch statement in
sk_run_filter() because of dense case labels. This patch replace the
OR'd labels with ordered sequenced case labels. The sk_chk_filter()
function is modified to patch/replace the original OPCODES in a
ordered but equivalent form. gcc is now in the ability to transform the
switch statement in sk_run_filter into a jump table of complexity O(1).

Until this patch gcc generates a sequence of conditional branches (O(n) of 567
byte .text segment size (arch x86_64):

7ff: 8b 06                 mov    (%rsi),%eax
801: 66 83 f8 35           cmp    $0x35,%ax
805: 0f 84 d0 02 00 00     je     adb <sk_run_filter+0x31d>
80b: 0f 87 07 01 00 00     ja     918 <sk_run_filter+0x15a>
811: 66 83 f8 15           cmp    $0x15,%ax
815: 0f 84 c5 02 00 00     je     ae0 <sk_run_filter+0x322>
81b: 77 73                 ja     890 <sk_run_filter+0xd2>
81d: 66 83 f8 04           cmp    $0x4,%ax
821: 0f 84 17 02 00 00     je     a3e <sk_run_filter+0x280>
827: 77 29                 ja     852 <sk_run_filter+0x94>
829: 66 83 f8 01           cmp    $0x1,%ax
[...]

With the modification the compiler translate the switch statement into
the following jump table fragment:

7ff: 66 83 3e 2c           cmpw   $0x2c,(%rsi)
803: 0f 87 1f 02 00 00     ja     a28 <sk_run_filter+0x26a>
809: 0f b7 06              movzwl (%rsi),%eax
80c: ff 24 c5 00 00 00 00  jmpq   *0x0(,%rax,8)
813: 44 89 e3              mov    %r12d,%ebx
816: e9 43 03 00 00        jmpq   b5e <sk_run_filter+0x3a0>
81b: 41 89 dc              mov    %ebx,%r12d
81e: e9 3b 03 00 00        jmpq   b5e <sk_run_filter+0x3a0>

Furthermore, I reordered the instructions to reduce cache line misses by
order the most common instruction to the start.

Signed-off-by: Hagen Paul Pfeifer <hagen@jauu.net>
Signed-off-by: David S. Miller <davem@davemloft.net>
2010-06-25 21:33:12 -07:00

205 lines
4.9 KiB
C

/*
* Linux Socket Filter Data Structures
*/
#ifndef __LINUX_FILTER_H__
#define __LINUX_FILTER_H__
#include <linux/compiler.h>
#include <linux/types.h>
#ifdef __KERNEL__
#include <asm/atomic.h>
#endif
/*
* Current version of the filter code architecture.
*/
#define BPF_MAJOR_VERSION 1
#define BPF_MINOR_VERSION 1
/*
* Try and keep these values and structures similar to BSD, especially
* the BPF code definitions which need to match so you can share filters
*/
struct sock_filter { /* Filter block */
__u16 code; /* Actual filter code */
__u8 jt; /* Jump true */
__u8 jf; /* Jump false */
__u32 k; /* Generic multiuse field */
};
struct sock_fprog { /* Required for SO_ATTACH_FILTER. */
unsigned short len; /* Number of filter blocks */
struct sock_filter __user *filter;
};
/*
* Instruction classes
*/
#define BPF_CLASS(code) ((code) & 0x07)
#define BPF_LD 0x00
#define BPF_LDX 0x01
#define BPF_ST 0x02
#define BPF_STX 0x03
#define BPF_ALU 0x04
#define BPF_JMP 0x05
#define BPF_RET 0x06
#define BPF_MISC 0x07
/* ld/ldx fields */
#define BPF_SIZE(code) ((code) & 0x18)
#define BPF_W 0x00
#define BPF_H 0x08
#define BPF_B 0x10
#define BPF_MODE(code) ((code) & 0xe0)
#define BPF_IMM 0x00
#define BPF_ABS 0x20
#define BPF_IND 0x40
#define BPF_MEM 0x60
#define BPF_LEN 0x80
#define BPF_MSH 0xa0
/* alu/jmp fields */
#define BPF_OP(code) ((code) & 0xf0)
#define BPF_ADD 0x00
#define BPF_SUB 0x10
#define BPF_MUL 0x20
#define BPF_DIV 0x30
#define BPF_OR 0x40
#define BPF_AND 0x50
#define BPF_LSH 0x60
#define BPF_RSH 0x70
#define BPF_NEG 0x80
#define BPF_JA 0x00
#define BPF_JEQ 0x10
#define BPF_JGT 0x20
#define BPF_JGE 0x30
#define BPF_JSET 0x40
#define BPF_SRC(code) ((code) & 0x08)
#define BPF_K 0x00
#define BPF_X 0x08
/* ret - BPF_K and BPF_X also apply */
#define BPF_RVAL(code) ((code) & 0x18)
#define BPF_A 0x10
/* misc */
#define BPF_MISCOP(code) ((code) & 0xf8)
#define BPF_TAX 0x00
#define BPF_TXA 0x80
enum {
BPF_S_RET_K = 0,
BPF_S_RET_A,
BPF_S_ALU_ADD_K,
BPF_S_ALU_ADD_X,
BPF_S_ALU_SUB_K,
BPF_S_ALU_SUB_X,
BPF_S_ALU_MUL_K,
BPF_S_ALU_MUL_X,
BPF_S_ALU_DIV_X,
BPF_S_ALU_AND_K,
BPF_S_ALU_AND_X,
BPF_S_ALU_OR_K,
BPF_S_ALU_OR_X,
BPF_S_ALU_LSH_K,
BPF_S_ALU_LSH_X,
BPF_S_ALU_RSH_K,
BPF_S_ALU_RSH_X,
BPF_S_ALU_NEG,
BPF_S_LD_W_ABS,
BPF_S_LD_H_ABS,
BPF_S_LD_B_ABS,
BPF_S_LD_W_LEN,
BPF_S_LD_W_IND,
BPF_S_LD_H_IND,
BPF_S_LD_B_IND,
BPF_S_LD_IMM,
BPF_S_LDX_W_LEN,
BPF_S_LDX_B_MSH,
BPF_S_LDX_IMM,
BPF_S_MISC_TAX,
BPF_S_MISC_TXA,
BPF_S_ALU_DIV_K,
BPF_S_LD_MEM,
BPF_S_LDX_MEM,
BPF_S_ST,
BPF_S_STX,
BPF_S_JMP_JA,
BPF_S_JMP_JEQ_K,
BPF_S_JMP_JEQ_X,
BPF_S_JMP_JGE_K,
BPF_S_JMP_JGE_X,
BPF_S_JMP_JGT_K,
BPF_S_JMP_JGT_X,
BPF_S_JMP_JSET_K,
BPF_S_JMP_JSET_X,
};
#ifndef BPF_MAXINSNS
#define BPF_MAXINSNS 4096
#endif
/*
* Macros for filter block array initializers.
*/
#ifndef BPF_STMT
#define BPF_STMT(code, k) { (unsigned short)(code), 0, 0, k }
#endif
#ifndef BPF_JUMP
#define BPF_JUMP(code, k, jt, jf) { (unsigned short)(code), jt, jf, k }
#endif
/*
* Number of scratch memory words for: BPF_ST and BPF_STX
*/
#define BPF_MEMWORDS 16
/* RATIONALE. Negative offsets are invalid in BPF.
We use them to reference ancillary data.
Unlike introduction new instructions, it does not break
existing compilers/optimizers.
*/
#define SKF_AD_OFF (-0x1000)
#define SKF_AD_PROTOCOL 0
#define SKF_AD_PKTTYPE 4
#define SKF_AD_IFINDEX 8
#define SKF_AD_NLATTR 12
#define SKF_AD_NLATTR_NEST 16
#define SKF_AD_MARK 20
#define SKF_AD_QUEUE 24
#define SKF_AD_HATYPE 28
#define SKF_AD_MAX 32
#define SKF_NET_OFF (-0x100000)
#define SKF_LL_OFF (-0x200000)
#ifdef __KERNEL__
struct sk_filter
{
atomic_t refcnt;
unsigned int len; /* Number of filter blocks */
struct rcu_head rcu;
struct sock_filter insns[0];
};
static inline unsigned int sk_filter_len(const struct sk_filter *fp)
{
return fp->len * sizeof(struct sock_filter) + sizeof(*fp);
}
struct sk_buff;
struct sock;
extern int sk_filter(struct sock *sk, struct sk_buff *skb);
extern unsigned int sk_run_filter(struct sk_buff *skb,
struct sock_filter *filter, int flen);
extern int sk_attach_filter(struct sock_fprog *fprog, struct sock *sk);
extern int sk_detach_filter(struct sock *sk);
extern int sk_chk_filter(struct sock_filter *filter, int flen);
#endif /* __KERNEL__ */
#endif /* __LINUX_FILTER_H__ */