filter: bpf_asm: add minimal bpf asm tool

There are a couple of valid use cases for a minimal low-level bpf asm
like tool, for example, using/linking to libpcap is not an option, the
required BPF filters use Linux extensions that are not supported by
libpcap's compiler, a filter might be more complex and not cleanly
implementable with libpcap's compiler, particular filter codes should
be optimized differently than libpcap's internal BPF compiler does,
or for security audits of emitted BPF JIT code for prepared set of BPF
instructions resp. BPF JIT compiler development in general.

Then, in such cases writing such a filter in low-level syntax can be
an good alternative, for example, xt_bpf and cls_bpf users might have
requirements that could result in more complex filter code, or one that
cannot be expressed with libpcap (e.g. different return codes in
cls_bpf for flowids on various BPF code paths).

Moreover, BPF JIT implementors may wish to manually write test cases
in order to verify the resulting JIT image, and thus need low-level
access to BPF code generation as well. Therefore, complete the available
toolchain for BPF with this small bpf_asm helper tool for the tools/net/
directory. These 3 complementary minimal helper tools round up and
facilitate BPF development.

Signed-off-by: Daniel Borkmann <dborkman@redhat.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

4 files changed, 960 insertions, 2 deletions

diff --git a/tools/net/Makefile b/tools/net/Makefile
index 0f30d92..004cd74 100644
--- a/tools/net/Makefile
+++ b/tools/net/Makefile
@@ -1,8 +1,16 @@
 prefix = /usr
 
 CC = gcc
+LEX = flex
+YACC = bison
 
-all : bpf_jit_disasm bpf_dbg
+%.yacc.c: %.y
+	$(YACC) -o $@ -d $<
+
+%.lex.c: %.l
+	$(LEX) -o $@ $<
+
+all : bpf_jit_disasm bpf_dbg bpf_asm
 
 bpf_jit_disasm : CFLAGS = -Wall -O2
 bpf_jit_disasm : LDLIBS = -lopcodes -lbfd -ldl
@@ -12,9 +20,15 @@ bpf_dbg : CFLAGS = -Wall -O2
 bpf_dbg : LDLIBS = -lreadline
 bpf_dbg : bpf_dbg.o
 
+bpf_asm : CFLAGS = -Wall -O2 -I.
+bpf_asm : LDLIBS =
+bpf_asm : bpf_asm.o bpf_exp.yacc.o bpf_exp.lex.o
+bpf_exp.lex.o : bpf_exp.yacc.c
+
 clean :
-	rm -rf *.o bpf_jit_disasm bpf_dbg
+	rm -rf *.o bpf_jit_disasm bpf_dbg bpf_asm bpf_exp.yacc.* bpf_exp.lex.*
 
 install :
 	install bpf_jit_disasm $(prefix)/bin/bpf_jit_disasm
 	install bpf_dbg $(prefix)/bin/bpf_dbg
+	install bpf_asm $(prefix)/bin/bpf_asm
diff --git a/tools/net/bpf_asm.c b/tools/net/bpf_asm.c
new file mode 100644
index 0000000..c15aef0
--- /dev/null
+++ b/tools/net/bpf_asm.c
@@ -0,0 +1,52 @@
+/*
+ * Minimal BPF assembler
+ *
+ * Instead of libpcap high-level filter expressions, it can be quite
+ * useful to define filters in low-level BPF assembler (that is kept
+ * close to Steven McCanne and Van Jacobson's original BPF paper).
+ * In particular for BPF JIT implementors, JIT security auditors, or
+ * just for defining BPF expressions that contain extensions which are
+ * not supported by compilers.
+ *
+ * How to get into it:
+ *
+ * 1) read Documentation/networking/filter.txt
+ * 2) Run `bpf_asm [-c] <filter-prog file>` to translate into binary
+ *    blob that is loadable with xt_bpf, cls_bpf et al. Note: -c will
+ *    pretty print a C-like construct.
+ *
+ * Copyright 2013 Daniel Borkmann <borkmann@redhat.com>
+ * Licensed under the GNU General Public License, version 2.0 (GPLv2)
+ */
+
+#include <stdbool.h>
+#include <stdio.h>
+#include <string.h>
+
+extern void bpf_asm_compile(FILE *fp, bool cstyle);
+
+int main(int argc, char **argv)
+{
+	FILE *fp = stdin;
+	bool cstyle = false;
+	int i;
+
+	for (i = 1; i < argc; i++) {
+		if (!strncmp("-c", argv[i], 2)) {
+			cstyle = true;
+			continue;
+		}
+
+		fp = fopen(argv[i], "r");
+		if (!fp) {
+			fp = stdin;
+			continue;
+		}
+
+		break;
+	}
+
+	bpf_asm_compile(fp, cstyle);
+
+	return 0;
+}
diff --git a/tools/net/bpf_exp.l b/tools/net/bpf_exp.l
new file mode 100644
index 0000000..bf7be77
--- /dev/null
+++ b/tools/net/bpf_exp.l
@@ -0,0 +1,143 @@
+/*
+ * BPF asm code lexer
+ *
+ * This program is free software; you can distribute it and/or modify
+ * it under the terms of the GNU General Public License as published
+ * by the Free Software Foundation; either version 2 of the License,
+ * or (at your option) any later version.
+ *
+ * Syntax kept close to:
+ *
+ * Steven McCanne and Van Jacobson. 1993. The BSD packet filter: a new
+ * architecture for user-level packet capture. In Proceedings of the
+ * USENIX Winter 1993 Conference Proceedings on USENIX Winter 1993
+ * Conference Proceedings (USENIX'93). USENIX Association, Berkeley,
+ * CA, USA, 2-2.
+ *
+ * Copyright 2013 Daniel Borkmann <borkmann@redhat.com>
+ * Licensed under the GNU General Public License, version 2.0 (GPLv2)
+ */
+
+%{
+
+#include <stdio.h>
+#include <stdint.h>
+#include <stdlib.h>
+
+#include "bpf_exp.yacc.h"
+
+extern void yyerror(const char *str);
+
+%}
+
+%option align
+%option ecs
+
+%option nounput
+%option noreject
+%option noinput
+%option noyywrap
+
+%option 8bit
+%option caseless
+%option yylineno
+
+%%
+
+"ldb"		{ return OP_LDB; }
+"ldh"		{ return OP_LDH; }
+"ld"		{ return OP_LD; }
+"ldi"		{ return OP_LDI; }
+"ldx"		{ return OP_LDX; }
+"ldxi"		{ return OP_LDXI; }
+"ldxb"		{ return OP_LDXB; }
+"st"		{ return OP_ST; }
+"stx"		{ return OP_STX; }
+"jmp"		{ return OP_JMP; }
+"ja"		{ return OP_JMP; }
+"jeq"		{ return OP_JEQ; }
+"jneq"		{ return OP_JNEQ; }
+"jne"		{ return OP_JNEQ; }
+"jlt"		{ return OP_JLT; }
+"jle"		{ return OP_JLE; }
+"jgt"		{ return OP_JGT; }
+"jge"		{ return OP_JGE; }
+"jset"		{ return OP_JSET; }
+"add"		{ return OP_ADD; }
+"sub"		{ return OP_SUB; }
+"mul"		{ return OP_MUL; }
+"div"		{ return OP_DIV; }
+"mod"		{ return OP_MOD; }
+"neg"		{ return OP_NEG; }
+"and"		{ return OP_AND; }
+"xor"		{ return OP_XOR; }
+"or"		{ return OP_OR; }
+"lsh"		{ return OP_LSH; }
+"rsh"		{ return OP_RSH; }
+"ret"		{ return OP_RET; }
+"tax"		{ return OP_TAX; }
+"txa"		{ return OP_TXA; }
+
+"#"?("len")	{ return K_PKT_LEN; }
+"#"?("proto")	{ return K_PROTO; }
+"#"?("type")	{ return K_TYPE; }
+"#"?("poff")	{ return K_POFF; }
+"#"?("ifidx")	{ return K_IFIDX; }
+"#"?("nla")	{ return K_NLATTR; }
+"#"?("nlan")	{ return K_NLATTR_NEST; }
+"#"?("mark")	{ return K_MARK; }
+"#"?("queue")	{ return K_QUEUE; }
+"#"?("hatype")	{ return K_HATYPE; }
+"#"?("rxhash")	{ return K_RXHASH; }
+"#"?("cpu")	{ return K_CPU; }
+"#"?("vlan_tci") { return K_VLANT; }
+"#"?("vlan_pr")	{ return K_VLANP; }
+
+":"		{ return ':'; }
+","		{ return ','; }
+"#"		{ return '#'; }
+"%"		{ return '%'; }
+"["		{ return '['; }
+"]"		{ return ']'; }
+"("		{ return '('; }
+")"		{ return ')'; }
+"x"		{ return 'x'; }
+"a"		{ return 'a'; }
+"+"		{ return '+'; }
+"M"		{ return 'M'; }
+"*"		{ return '*'; }
+"&"		{ return '&'; }
+
+([0][x][a-fA-F0-9]+) {
+			yylval.number = strtoul(yytext, NULL, 16);
+			return number;
+		}
+([0][b][0-1]+)	{
+			yylval.number = strtol(yytext + 2, NULL, 2);
+			return number;
+		}
+(([0])|([-+]?[1-9][0-9]*)) {
+			yylval.number = strtol(yytext, NULL, 10);
+			return number;
+		}
+([0][0-9]+)	{
+			yylval.number = strtol(yytext + 1, NULL, 8);
+			return number;
+		}
+[a-zA-Z_][a-zA-Z0-9_]+ {
+			yylval.label = strdup(yytext);
+			return label;
+		}
+
+"/*"([^\*]|\*[^/])*"*/"		{ /* NOP */ }
+";"[^\n]*			{ /* NOP */ }
+^#.*				{ /* NOP */ }
+[ \t]+				{ /* NOP */ }
+[ \n]+				{ /* NOP */ }
+
+.		{
+			printf("unknown character \'%s\'", yytext);
+			yyerror("lex unknown character");
+		}
+
+%%
diff --git a/tools/net/bpf_exp.y b/tools/net/bpf_exp.y
new file mode 100644
index 0000000..f524110
--- /dev/null
+++ b/tools/net/bpf_exp.y
@@ -0,0 +1,749 @@
+/*
+ * BPF asm code parser
+ *
+ * This program is free software; you can distribute it and/or modify
+ * it under the terms of the GNU General Public License as published
+ * by the Free Software Foundation; either version 2 of the License,
+ * or (at your option) any later version.
+ *
+ * Syntax kept close to:
+ *
+ * Steven McCanne and Van Jacobson. 1993. The BSD packet filter: a new
+ * architecture for user-level packet capture. In Proceedings of the
+ * USENIX Winter 1993 Conference Proceedings on USENIX Winter 1993
+ * Conference Proceedings (USENIX'93). USENIX Association, Berkeley,
+ * CA, USA, 2-2.
+ *
+ * Copyright 2013 Daniel Borkmann <borkmann@redhat.com>
+ * Licensed under the GNU General Public License, version 2.0 (GPLv2)
+ */
+
+%{
+
+#include <stdio.h>
+#include <string.h>
+#include <stdint.h>
+#include <stdlib.h>
+#include <stdbool.h>
+#include <unistd.h>
+#include <errno.h>
+#include <assert.h>
+#include <linux/filter.h>
+
+#include "bpf_exp.yacc.h"
+
+enum jmp_type { JTL, JFL, JKL };
+
+extern FILE *yyin;
+extern int yylex(void);
+extern void yyerror(const char *str);
+
+extern void bpf_asm_compile(FILE *fp, bool cstyle);
+static void bpf_set_curr_instr(uint16_t op, uint8_t jt, uint8_t jf, uint32_t k);
+static void bpf_set_curr_label(const char *label);
+static void bpf_set_jmp_label(const char *label, enum jmp_type type);
+
+%}
+
+%union {
+	char *label;
+	uint32_t number;
+}
+
+%token OP_LDB OP_LDH OP_LD OP_LDX OP_ST OP_STX OP_JMP OP_JEQ OP_JGT OP_JGE
+%token OP_JSET OP_ADD OP_SUB OP_MUL OP_DIV OP_AND OP_OR OP_XOR OP_LSH OP_RSH
+%token OP_RET OP_TAX OP_TXA OP_LDXB OP_MOD OP_NEG OP_JNEQ OP_JLT OP_JLE OP_LDI
+%token OP_LDXI
+
+%token K_PKT_LEN K_PROTO K_TYPE K_NLATTR K_NLATTR_NEST K_MARK K_QUEUE K_HATYPE
+%token K_RXHASH K_CPU K_IFIDX K_VLANT K_VLANP K_POFF
+
+%token ':' ',' '[' ']' '(' ')' 'x' 'a' '+' 'M' '*' '&' '#' '%'
+
+%token number label
+
+%type <label> label
+%type <number> number
+
+%%
+
+prog
+	: line
+	| prog line
+	;
+
+line
+	: instr
+	| labelled_instr
+	;
+
+labelled_instr
+	: labelled instr
+	;
+
+instr
+	: ldb
+	| ldh
+	| ld
+	| ldi
+	| ldx
+	| ldxi
+	| st
+	| stx
+	| jmp
+	| jeq
+	| jneq
+	| jlt
+	| jle
+	| jgt
+	| jge
+	| jset
+	| add
+	| sub
+	| mul
+	| div
+	| mod
+	| neg
+	| and
+	| or
+	| xor
+	| lsh
+	| rsh
+	| ret
+	| tax
+	| txa
+	;
+
+labelled
+	: label ':' { bpf_set_curr_label($1); }
+	;
+
+ldb
+	: OP_LDB '[' 'x' '+' number ']' {
+		bpf_set_curr_instr(BPF_LD | BPF_B | BPF_IND, 0, 0, $5); }
+	| OP_LDB '[' '%' 'x' '+' number ']' {
+		bpf_set_curr_instr(BPF_LD | BPF_B | BPF_IND, 0, 0, $6); }
+	| OP_LDB '[' number ']' {
+		bpf_set_curr_instr(BPF_LD | BPF_B | BPF_ABS, 0, 0, $3); }
+	| OP_LDB K_PROTO {
+		bpf_set_curr_instr(BPF_LD | BPF_B | BPF_ABS, 0, 0,
+				   SKF_AD_OFF + SKF_AD_PROTOCOL); }
+	| OP_LDB K_TYPE {
+		bpf_set_curr_instr(BPF_LD | BPF_B | BPF_ABS, 0, 0,
+				   SKF_AD_OFF + SKF_AD_PKTTYPE); }
+	| OP_LDB K_IFIDX {
+		bpf_set_curr_instr(BPF_LD | BPF_B | BPF_ABS, 0, 0,
+				   SKF_AD_OFF + SKF_AD_IFINDEX); }
+	| OP_LDB K_NLATTR {
+		bpf_set_curr_instr(BPF_LD | BPF_B | BPF_ABS, 0, 0,
+				   SKF_AD_OFF + SKF_AD_NLATTR); }
+	| OP_LDB K_NLATTR_NEST {
+		bpf_set_curr_instr(BPF_LD | BPF_B | BPF_ABS, 0, 0,
+				   SKF_AD_OFF + SKF_AD_NLATTR_NEST); }
+	| OP_LDB K_MARK {
+		bpf_set_curr_instr(BPF_LD | BPF_B | BPF_ABS, 0, 0,
+				   SKF_AD_OFF + SKF_AD_MARK); }
+	| OP_LDB K_QUEUE {
+		bpf_set_curr_instr(BPF_LD | BPF_B | BPF_ABS, 0, 0,
+				   SKF_AD_OFF + SKF_AD_QUEUE); }
+	| OP_LDB K_HATYPE {
+		bpf_set_curr_instr(BPF_LD | BPF_B | BPF_ABS, 0, 0,
+				   SKF_AD_OFF + SKF_AD_HATYPE); }
+	| OP_LDB K_RXHASH {
+		bpf_set_curr_instr(BPF_LD | BPF_B | BPF_ABS, 0, 0,
+				   SKF_AD_OFF + SKF_AD_RXHASH); }
+	| OP_LDB K_CPU {
+		bpf_set_curr_instr(BPF_LD | BPF_B | BPF_ABS, 0, 0,
+				   SKF_AD_OFF + SKF_AD_CPU); }
+	| OP_LDB K_VLANT {
+		bpf_set_curr_instr(BPF_LD | BPF_B | BPF_ABS, 0, 0,
+				   SKF_AD_OFF + SKF_AD_VLAN_TAG); }
+	| OP_LDB K_VLANP {
+		bpf_set_curr_instr(BPF_LD | BPF_B | BPF_ABS, 0, 0,
+				   SKF_AD_OFF + SKF_AD_VLAN_TAG_PRESENT); }
+	| OP_LDB K_POFF {
+		bpf_set_curr_instr(BPF_LD | BPF_B | BPF_ABS, 0, 0,
+				   SKF_AD_OFF + SKF_AD_PAY_OFFSET); }
+	;
+
+ldh
+	: OP_LDH '[' 'x' '+' number ']' {
+		bpf_set_curr_instr(BPF_LD | BPF_H | BPF_IND, 0, 0, $5); }
+	| OP_LDH '[' '%' 'x' '+' number ']' {
+		bpf_set_curr_instr(BPF_LD | BPF_H | BPF_IND, 0, 0, $6); }
+	| OP_LDH '[' number ']' {
+		bpf_set_curr_instr(BPF_LD | BPF_H | BPF_ABS, 0, 0, $3); }
+	| OP_LDH K_PROTO {
+		bpf_set_curr_instr(BPF_LD | BPF_H | BPF_ABS, 0, 0,
+				   SKF_AD_OFF + SKF_AD_PROTOCOL); }
+	| OP_LDH K_TYPE {
+		bpf_set_curr_instr(BPF_LD | BPF_H | BPF_ABS, 0, 0,
+				   SKF_AD_OFF + SKF_AD_PKTTYPE); }
+	| OP_LDH K_IFIDX {
+		bpf_set_curr_instr(BPF_LD | BPF_H | BPF_ABS, 0, 0,
+				   SKF_AD_OFF + SKF_AD_IFINDEX); }
+	| OP_LDH K_NLATTR {
+		bpf_set_curr_instr(BPF_LD | BPF_H | BPF_ABS, 0, 0,
+				   SKF_AD_OFF + SKF_AD_NLATTR); }
+	| OP_LDH K_NLATTR_NEST {
+		bpf_set_curr_instr(BPF_LD | BPF_H | BPF_ABS, 0, 0,
+				   SKF_AD_OFF + SKF_AD_NLATTR_NEST); }
+	| OP_LDH K_MARK {
+		bpf_set_curr_instr(BPF_LD | BPF_H | BPF_ABS, 0, 0,
+				   SKF_AD_OFF + SKF_AD_MARK); }
+	| OP_LDH K_QUEUE {
+		bpf_set_curr_instr(BPF_LD | BPF_H | BPF_ABS, 0, 0,
+				   SKF_AD_OFF + SKF_AD_QUEUE); }
+	| OP_LDH K_HATYPE {
+		bpf_set_curr_instr(BPF_LD | BPF_H | BPF_ABS, 0, 0,
+				   SKF_AD_OFF + SKF_AD_HATYPE); }
+	| OP_LDH K_RXHASH {
+		bpf_set_curr_instr(BPF_LD | BPF_H | BPF_ABS, 0, 0,
+				   SKF_AD_OFF + SKF_AD_RXHASH); }
+	| OP_LDH K_CPU {
+		bpf_set_curr_instr(BPF_LD | BPF_H | BPF_ABS, 0, 0,
+				   SKF_AD_OFF + SKF_AD_CPU); }
+	| OP_LDH K_VLANT {
+		bpf_set_curr_instr(BPF_LD | BPF_H | BPF_ABS, 0, 0,
+				   SKF_AD_OFF + SKF_AD_VLAN_TAG); }
+	| OP_LDH K_VLANP {
+		bpf_set_curr_instr(BPF_LD | BPF_H | BPF_ABS, 0, 0,
+				   SKF_AD_OFF + SKF_AD_VLAN_TAG_PRESENT); }
+	| OP_LDH K_POFF {
+		bpf_set_curr_instr(BPF_LD | BPF_H | BPF_ABS, 0, 0,
+				   SKF_AD_OFF + SKF_AD_PAY_OFFSET); }
+	;
+
+ldi
+	: OP_LDI '#' number {
+		bpf_set_curr_instr(BPF_LD | BPF_IMM, 0, 0, $3); }
+	| OP_LDI number {
+		bpf_set_curr_instr(BPF_LD | BPF_IMM, 0, 0, $2); }
+	;
+
+ld
+	: OP_LD '#' number {
+		bpf_set_curr_instr(BPF_LD | BPF_IMM, 0, 0, $3); }
+	| OP_LD K_PKT_LEN {
+		bpf_set_curr_instr(BPF_LD | BPF_W | BPF_LEN, 0, 0, 0); }
+	| OP_LD K_PROTO {
+		bpf_set_curr_instr(BPF_LD | BPF_W | BPF_ABS, 0, 0,
+				   SKF_AD_OFF + SKF_AD_PROTOCOL); }
+	| OP_LD K_TYPE {
+		bpf_set_curr_instr(BPF_LD | BPF_W | BPF_ABS, 0, 0,
+				   SKF_AD_OFF + SKF_AD_PKTTYPE); }
+	| OP_LD K_IFIDX {
+		bpf_set_curr_instr(BPF_LD | BPF_W | BPF_ABS, 0, 0,
+				   SKF_AD_OFF + SKF_AD_IFINDEX); }
+	| OP_LD K_NLATTR {
+		bpf_set_curr_instr(BPF_LD | BPF_W | BPF_ABS, 0, 0,
+				   SKF_AD_OFF + SKF_AD_NLATTR); }
+	| OP_LD K_NLATTR_NEST {
+		bpf_set_curr_instr(BPF_LD | BPF_W | BPF_ABS, 0, 0,
+				   SKF_AD_OFF + SKF_AD_NLATTR_NEST); }
+	| OP_LD K_MARK {
+		bpf_set_curr_instr(BPF_LD | BPF_W | BPF_ABS, 0, 0,
+				   SKF_AD_OFF + SKF_AD_MARK); }
+	| OP_LD K_QUEUE {
+		bpf_set_curr_instr(BPF_LD | BPF_W | BPF_ABS, 0, 0,
+				   SKF_AD_OFF + SKF_AD_QUEUE); }
+	| OP_LD K_HATYPE {
+		bpf_set_curr_instr(BPF_LD | BPF_W | BPF_ABS, 0, 0,
+				   SKF_AD_OFF + SKF_AD_HATYPE); }
+	| OP_LD K_RXHASH {
+		bpf_set_curr_instr(BPF_LD | BPF_W | BPF_ABS, 0, 0,
+				   SKF_AD_OFF + SKF_AD_RXHASH); }
+	| OP_LD K_CPU {
+		bpf_set_curr_instr(BPF_LD | BPF_W | BPF_ABS, 0, 0,
+				   SKF_AD_OFF + SKF_AD_CPU); }
+	| OP_LD K_VLANT {
+		bpf_set_curr_instr(BPF_LD | BPF_W | BPF_ABS, 0, 0,
+				   SKF_AD_OFF + SKF_AD_VLAN_TAG); }
+	| OP_LD K_VLANP {
+		bpf_set_curr_instr(BPF_LD | BPF_W | BPF_ABS, 0, 0,
+				   SKF_AD_OFF + SKF_AD_VLAN_TAG_PRESENT); }
+	| OP_LD K_POFF {
+		bpf_set_curr_instr(BPF_LD | BPF_W | BPF_ABS, 0, 0,
+				   SKF_AD_OFF + SKF_AD_PAY_OFFSET); }
+	| OP_LD 'M' '[' number ']' {
+		bpf_set_curr_instr(BPF_LD | BPF_MEM, 0, 0, $4); }
+	| OP_LD '[' 'x' '+' number ']' {
+		bpf_set_curr_instr(BPF_LD | BPF_W | BPF_IND, 0, 0, $5); }
+	| OP_LD '[' '%' 'x' '+' number ']' {
+		bpf_set_curr_instr(BPF_LD | BPF_W | BPF_IND, 0, 0, $6); }
+	| OP_LD '[' number ']' {
+		bpf_set_curr_instr(BPF_LD | BPF_W | BPF_ABS, 0, 0, $3); }
+	;
+
+ldxi
+	: OP_LDXI '#' number {
+		bpf_set_curr_instr(BPF_LDX | BPF_IMM, 0, 0, $3); }
+	| OP_LDXI number {
+		bpf_set_curr_instr(BPF_LDX | BPF_IMM, 0, 0, $2); }
+	;
+
+ldx
+	: OP_LDX '#' number {
+		bpf_set_curr_instr(BPF_LDX | BPF_IMM, 0, 0, $3); }
+	| OP_LDX K_PKT_LEN {
+		bpf_set_curr_instr(BPF_LDX | BPF_W | BPF_LEN, 0, 0, 0); }
+	| OP_LDX 'M' '[' number ']' {
+		bpf_set_curr_instr(BPF_LDX | BPF_MEM, 0, 0, $4); }
+	| OP_LDXB number '*' '(' '[' number ']' '&' number ')' {
+		if ($2 != 4 || $9 != 0xf) {
+			fprintf(stderr, "ldxb offset not supported!\n");
+			exit(0);
+		} else {
+			bpf_set_curr_instr(BPF_LDX | BPF_MSH | BPF_B, 0, 0, $6); } }
+	| OP_LDX number '*' '(' '[' number ']' '&' number ')' {
+		if ($2 != 4 || $9 != 0xf) {
+			fprintf(stderr, "ldxb offset not supported!\n");
+			exit(0);
+		} else {
+			bpf_set_curr_instr(BPF_LDX | BPF_MSH | BPF_B, 0, 0, $6); } }
+	;
+
+st
+	: OP_ST 'M' '[' number ']' {
+		bpf_set_curr_instr(BPF_ST, 0, 0, $4); }
+	;
+
+stx
+	: OP_STX 'M' '[' number ']' {
+		bpf_set_curr_instr(BPF_STX, 0, 0, $4); }
+	;
+
+jmp
+	: OP_JMP label {
+		bpf_set_jmp_label($2, JKL);
+		bpf_set_curr_instr(BPF_JMP | BPF_JA, 0, 0, 0); }
+	;
+
+jeq
+	: OP_JEQ '#' number ',' label ',' label {
+		bpf_set_jmp_label($5, JTL);
+		bpf_set_jmp_label($7, JFL);
+		bpf_set_curr_instr(BPF_JMP | BPF_JEQ | BPF_K, 0, 0, $3); }
+	| OP_JEQ 'x' ',' label ',' label {
+		bpf_set_jmp_label($4, JTL);
+		bpf_set_jmp_label($6, JFL);
+		bpf_set_curr_instr(BPF_JMP | BPF_JEQ | BPF_X, 0, 0, 0); }
+	| OP_JEQ '%' 'x' ',' label ',' label {
+		bpf_set_jmp_label($5, JTL);
+		bpf_set_jmp_label($7, JFL);
+		bpf_set_curr_instr(BPF_JMP | BPF_JEQ | BPF_X, 0, 0, 0); }
+	| OP_JEQ '#' number ',' label {
+		bpf_set_jmp_label($5, JTL);
+		bpf_set_curr_instr(BPF_JMP | BPF_JEQ | BPF_K, 0, 0, $3); }
+	| OP_JEQ 'x' ',' label {
+		bpf_set_jmp_label($4, JTL);
+		bpf_set_curr_instr(BPF_JMP | BPF_JEQ | BPF_X, 0, 0, 0); }
+	| OP_JEQ '%' 'x' ',' label {
+		bpf_set_jmp_label($5, JTL);
+		bpf_set_curr_instr(BPF_JMP | BPF_JEQ | BPF_X, 0, 0, 0); }
+	;
+
+jneq
+	: OP_JNEQ '#' number ',' label {
+		bpf_set_jmp_label($5, JFL);
+		bpf_set_curr_instr(BPF_JMP | BPF_JEQ | BPF_K, 0, 0, $3); }
+	| OP_JNEQ 'x' ',' label {
+		bpf_set_jmp_label($4, JFL);
+		bpf_set_curr_instr(BPF_JMP | BPF_JEQ | BPF_X, 0, 0, 0); }
+	| OP_JNEQ '%' 'x' ',' label {
+		bpf_set_jmp_label($5, JFL);
+		bpf_set_curr_instr(BPF_JMP | BPF_JEQ | BPF_X, 0, 0, 0); }
+	;
+
+jlt
+	: OP_JLT '#' number ',' label {
+		bpf_set_jmp_label($5, JFL);
+		bpf_set_curr_instr(BPF_JMP | BPF_JGE | BPF_K, 0, 0, $3); }
+	| OP_JLT 'x' ',' label {
+		bpf_set_jmp_label($4, JFL);
+		bpf_set_curr_instr(BPF_JMP | BPF_JGE | BPF_X, 0, 0, 0); }
+	| OP_JLT '%' 'x' ',' label {
+		bpf_set_jmp_label($5, JFL);
+		bpf_set_curr_instr(BPF_JMP | BPF_JGE | BPF_X, 0, 0, 0); }
+	;
+
+jle
+	: OP_JLE '#' number ',' label {
+		bpf_set_jmp_label($5, JFL);
+		bpf_set_curr_instr(BPF_JMP | BPF_JGT | BPF_K, 0, 0, $3); }
+	| OP_JLE 'x' ',' label {
+		bpf_set_jmp_label($4, JFL);
+		bpf_set_curr_instr(BPF_JMP | BPF_JGT | BPF_X, 0, 0, 0); }
+	| OP_JLE '%' 'x' ',' label {
+		bpf_set_jmp_label($5, JFL);
+		bpf_set_curr_instr(BPF_JMP | BPF_JGT | BPF_X, 0, 0, 0); }
+	;
+
+jgt
+	: OP_JGT '#' number ',' label ',' label {
+		bpf_set_jmp_label($5, JTL);
+		bpf_set_jmp_label($7, JFL);
+		bpf_set_curr_instr(BPF_JMP | BPF_JGT | BPF_K, 0, 0, $3); }
+	| OP_JGT 'x' ',' label ',' label {
+		bpf_set_jmp_label($4, JTL);
+		bpf_set_jmp_label($6, JFL);
+		bpf_set_curr_instr(BPF_JMP | BPF_JGT | BPF_X, 0, 0, 0); }
+	| OP_JGT '%' 'x' ',' label ',' label {
+		bpf_set_jmp_label($5, JTL);
+		bpf_set_jmp_label($7, JFL);
+		bpf_set_curr_instr(BPF_JMP | BPF_JGT | BPF_X, 0, 0, 0); }
+	| OP_JGT '#' number ',' label {
+		bpf_set_jmp_label($5, JTL);
+		bpf_set_curr_instr(BPF_JMP | BPF_JGT | BPF_K, 0, 0, $3); }
+	| OP_JGT 'x' ',' label {
+		bpf_set_jmp_label($4, JTL);
+		bpf_set_curr_instr(BPF_JMP | BPF_JGT | BPF_X, 0, 0, 0); }
+	| OP_JGT '%' 'x' ',' label {
+		bpf_set_jmp_label($5, JTL);
+		bpf_set_curr_instr(BPF_JMP | BPF_JGT | BPF_X, 0, 0, 0); }
+	;
+
+jge
+	: OP_JGE '#' number ',' label ',' label {
+		bpf_set_jmp_label($5, JTL);
+		bpf_set_jmp_label($7, JFL);
+		bpf_set_curr_instr(BPF_JMP | BPF_JGE | BPF_K, 0, 0, $3); }
+	| OP_JGE 'x' ',' label ',' label {
+		bpf_set_jmp_label($4, JTL);
+		bpf_set_jmp_label($6, JFL);
+		bpf_set_curr_instr(BPF_JMP | BPF_JGE | BPF_X, 0, 0, 0); }
+	| OP_JGE '%' 'x' ',' label ',' label {
+		bpf_set_jmp_label($5, JTL);
+		bpf_set_jmp_label($7, JFL);
+		bpf_set_curr_instr(BPF_JMP | BPF_JGE | BPF_X, 0, 0, 0); }
+	| OP_JGE '#' number ',' label {
+		bpf_set_jmp_label($5, JTL);
+		bpf_set_curr_instr(BPF_JMP | BPF_JGE | BPF_K, 0, 0, $3); }
+	| OP_JGE 'x' ',' label {
+		bpf_set_jmp_label($4, JTL);
+		bpf_set_curr_instr(BPF_JMP | BPF_JGE | BPF_X, 0, 0, 0); }
+	| OP_JGE '%' 'x' ',' label {
+		bpf_set_jmp_label($5, JTL);
+		bpf_set_curr_instr(BPF_JMP | BPF_JGE | BPF_X, 0, 0, 0); }
+	;
+
+jset
+	: OP_JSET '#' number ',' label ',' label {
+		bpf_set_jmp_label($5, JTL);
+		bpf_set_jmp_label($7, JFL);
+		bpf_set_curr_instr(BPF_JMP | BPF_JSET | BPF_K, 0, 0, $3); }
+	| OP_JSET 'x' ',' label ',' label {
+		bpf_set_jmp_label($4, JTL);
+		bpf_set_jmp_label($6, JFL);
+		bpf_set_curr_instr(BPF_JMP | BPF_JSET | BPF_X, 0, 0, 0); }
+	| OP_JSET '%' 'x' ',' label ',' label {
+		bpf_set_jmp_label($5, JTL);
+		bpf_set_jmp_label($7, JFL);
+		bpf_set_curr_instr(BPF_JMP | BPF_JSET | BPF_X, 0, 0, 0); }
+	| OP_JSET '#' number ',' label {
+		bpf_set_jmp_label($5, JTL);
+		bpf_set_curr_instr(BPF_JMP | BPF_JSET | BPF_K, 0, 0, $3); }
+	| OP_JSET 'x' ',' label {
+		bpf_set_jmp_label($4, JTL);
+		bpf_set_curr_instr(BPF_JMP | BPF_JSET | BPF_X, 0, 0, 0); }
+	| OP_JSET '%' 'x' ',' label {
+		bpf_set_jmp_label($5, JTL);
+		bpf_set_curr_instr(BPF_JMP | BPF_JSET | BPF_X, 0, 0, 0); }
+	;
+
+add
+	: OP_ADD '#' number {
+		bpf_set_curr_instr(BPF_ALU | BPF_ADD | BPF_K, 0, 0, $3); }
+	| OP_ADD 'x' {
+		bpf_set_curr_instr(BPF_ALU | BPF_ADD | BPF_X, 0, 0, 0); }
+	| OP_ADD '%' 'x' {
+		bpf_set_curr_instr(BPF_ALU | BPF_ADD | BPF_X, 0, 0, 0); }
+	;
+
+sub
+	: OP_SUB '#' number {
+		bpf_set_curr_instr(BPF_ALU | BPF_SUB | BPF_K, 0, 0, $3); }
+	| OP_SUB 'x' {
+		bpf_set_curr_instr(BPF_ALU | BPF_SUB | BPF_X, 0, 0, 0); }
+	| OP_SUB '%' 'x' {
+		bpf_set_curr_instr(BPF_ALU | BPF_SUB | BPF_X, 0, 0, 0); }
+	;
+
+mul
+	: OP_MUL '#' number {
+		bpf_set_curr_instr(BPF_ALU | BPF_MUL | BPF_K, 0, 0, $3); }
+	| OP_MUL 'x' {
+		bpf_set_curr_instr(BPF_ALU | BPF_MUL | BPF_X, 0, 0, 0); }
+	| OP_MUL '%' 'x' {
+		bpf_set_curr_instr(BPF_ALU | BPF_MUL | BPF_X, 0, 0, 0); }
+	;
+
+div
+	: OP_DIV '#' number {
+		bpf_set_curr_instr(BPF_ALU | BPF_DIV | BPF_K, 0, 0, $3); }
+	| OP_DIV 'x' {
+		bpf_set_curr_instr(BPF_ALU | BPF_DIV | BPF_X, 0, 0, 0); }
+	| OP_DIV '%' 'x' {
+		bpf_set_curr_instr(BPF_ALU | BPF_DIV | BPF_X, 0, 0, 0); }
+	;
+
+mod
+	: OP_MOD '#' number {
+		bpf_set_curr_instr(BPF_ALU | BPF_MOD | BPF_K, 0, 0, $3); }
+	| OP_MOD 'x' {
+		bpf_set_curr_instr(BPF_ALU | BPF_MOD | BPF_X, 0, 0, 0); }
+	| OP_MOD '%' 'x' {
+		bpf_set_curr_instr(BPF_ALU | BPF_MOD | BPF_X, 0, 0, 0); }
+	;
+
+neg
+	: OP_NEG {
+		bpf_set_curr_instr(BPF_ALU | BPF_NEG, 0, 0, 0); }
+	;
+
+and
+	: OP_AND '#' number {
+		bpf_set_curr_instr(BPF_ALU | BPF_AND | BPF_K, 0, 0, $3); }
+	| OP_AND 'x' {
+		bpf_set_curr_instr(BPF_ALU | BPF_AND | BPF_X, 0, 0, 0); }
+	| OP_AND '%' 'x' {
+		bpf_set_curr_instr(BPF_ALU | BPF_AND | BPF_X, 0, 0, 0); }
+	;
+
+or
+	: OP_OR '#' number {
+		bpf_set_curr_instr(BPF_ALU | BPF_OR | BPF_K, 0, 0, $3); }
+	| OP_OR 'x' {
+		bpf_set_curr_instr(BPF_ALU | BPF_OR | BPF_X, 0, 0, 0); }
+	| OP_OR '%' 'x' {
+		bpf_set_curr_instr(BPF_ALU | BPF_OR | BPF_X, 0, 0, 0); }
+	;
+
+xor
+	: OP_XOR '#' number {
+		bpf_set_curr_instr(BPF_ALU | BPF_XOR | BPF_K, 0, 0, $3); }
+	| OP_XOR 'x' {
+		bpf_set_curr_instr(BPF_ALU | BPF_XOR | BPF_X, 0, 0, 0); }
+	| OP_XOR '%' 'x' {
+		bpf_set_curr_instr(BPF_ALU | BPF_XOR | BPF_X, 0, 0, 0); }
+	;
+
+lsh
+	: OP_LSH '#' number {
+		bpf_set_curr_instr(BPF_ALU | BPF_LSH | BPF_K, 0, 0, $3); }
+	| OP_LSH 'x' {
+		bpf_set_curr_instr(BPF_ALU | BPF_LSH | BPF_X, 0, 0, 0); }
+	| OP_LSH '%' 'x' {
+		bpf_set_curr_instr(BPF_ALU | BPF_LSH | BPF_X, 0, 0, 0); }
+	;
+
+rsh
+	: OP_RSH '#' number {
+		bpf_set_curr_instr(BPF_ALU | BPF_RSH | BPF_K, 0, 0, $3); }
+	| OP_RSH 'x' {
+		bpf_set_curr_instr(BPF_ALU | BPF_RSH | BPF_X, 0, 0, 0); }
+	| OP_RSH '%' 'x' {
+		bpf_set_curr_instr(BPF_ALU | BPF_RSH | BPF_X, 0, 0, 0); }
+	;
+
+ret
+	: OP_RET 'a' {
+		bpf_set_curr_instr(BPF_RET | BPF_A, 0, 0, 0); }
+	| OP_RET '%' 'a' {
+		bpf_set_curr_instr(BPF_RET | BPF_A, 0, 0, 0); }
+	| OP_RET 'x' {
+		bpf_set_curr_instr(BPF_RET | BPF_X, 0, 0, 0); }
+	| OP_RET '%' 'x' {
+		bpf_set_curr_instr(BPF_RET | BPF_X, 0, 0, 0); }
+	| OP_RET '#' number {
+		bpf_set_curr_instr(BPF_RET | BPF_K, 0, 0, $3); }
+	;
+
+tax
+	: OP_TAX {
+		bpf_set_curr_instr(BPF_MISC | BPF_TAX, 0, 0, 0); }
+	;
+
+txa
+	: OP_TXA {
+		bpf_set_curr_instr(BPF_MISC | BPF_TXA, 0, 0, 0); }
+	;
+
+%%
+
+static int curr_instr = 0;
+static struct sock_filter out[BPF_MAXINSNS];
+static const char **labels, **labels_jt, **labels_jf, **labels_k;
+
+static void bpf_assert_max(void)
+{
+	if (curr_instr >= BPF_MAXINSNS) {
+		fprintf(stderr, "only max %u insns allowed!\n", BPF_MAXINSNS);
+		exit(0);
+	}
+}
+
+static void bpf_set_curr_instr(uint16_t code, uint8_t jt, uint8_t jf,
+			       uint32_t k)
+{
+	bpf_assert_max();
+	out[curr_instr].code = code;
+	out[curr_instr].jt = jt;
+	out[curr_instr].jf = jf;
+	out[curr_instr].k = k;
+	curr_instr++;
+}
+
+static void bpf_set_curr_label(const char *label)
+{
+	bpf_assert_max();
+        labels[curr_instr] = label;
+}
+
+static void bpf_set_jmp_label(const char *label, enum jmp_type type)
+{
+	bpf_assert_max();
+	switch (type) {
+	case JTL:
+		labels_jt[curr_instr] = label;
+		break;
+	case JFL:
+		labels_jf[curr_instr] = label;
+		break;
+	case JKL:
+		labels_k[curr_instr] = label;
+		break;
+	}
+}
+
+static int bpf_find_insns_offset(const char *label)
+{
+	int i, max = curr_instr, ret = -ENOENT;
+
+	for (i = 0; i < max; i++) {
+		if (labels[i] && !strcmp(label, labels[i])) {
+			ret = i;
+			break;
+		}
+	}
+
+	if (ret == -ENOENT) {
+		fprintf(stderr, "no such label \'%s\'!\n", label);
+		exit(0);
+	}
+
+	return ret;
+}
+
+static void bpf_stage_1_insert_insns(void)
+{
+	yyparse();
+}
+
+static void bpf_reduce_k_jumps(void)
+{
+	int i;
+
+	for (i = 0; i < curr_instr; i++) {
+		if (labels_k[i]) {
+			int off = bpf_find_insns_offset(labels_k[i]);
+			out[i].k = (uint32_t) (off - i - 1);
+		}
+	}
+}
+
+static void bpf_reduce_jt_jumps(void)
+{
+	int i;
+
+	for (i = 0; i < curr_instr; i++) {
+		if (labels_jt[i]) {
+			int off = bpf_find_insns_offset(labels_jt[i]);
+			out[i].jt = (uint8_t) (off - i -1);
+		}
+	}
+}
+
+static void bpf_reduce_jf_jumps(void)
+{
+	int i;
+
+	for (i = 0; i < curr_instr; i++) {
+		if (labels_jf[i]) {
+			int off = bpf_find_insns_offset(labels_jf[i]);
+			out[i].jf = (uint8_t) (off - i - 1);
+		}
+	}
+}
+
+static void bpf_stage_2_reduce_labels(void)
+{
+	bpf_reduce_k_jumps();
+	bpf_reduce_jt_jumps();
+	bpf_reduce_jf_jumps();
+}
+
+static void bpf_pretty_print_c(void)
+{
+	int i;
+
+	for (i = 0; i < curr_instr; i++)
+		printf("{ %#04x, %2u, %2u, %#010x },\n", out[i].code,
+		       out[i].jt, out[i].jf, out[i].k);
+}
+
+static void bpf_pretty_print(void)
+{
+	int i;
+
+	printf("%u,", curr_instr);
+	for (i = 0; i < curr_instr; i++)
+		printf("%u %u %u %u,", out[i].code,
+		       out[i].jt, out[i].jf, out[i].k);
+	printf("\n");
+}
+
+static void bpf_init(void)
+{
+	memset(out, 0, sizeof(out));
+
+	labels = calloc(BPF_MAXINSNS, sizeof(*labels));
+	assert(labels);
+	labels_jt = calloc(BPF_MAXINSNS, sizeof(*labels_jt));
+	assert(labels_jt);
+	labels_jf = calloc(BPF_MAXINSNS, sizeof(*labels_jf));
+	assert(labels_jf);
+	labels_k = calloc(BPF_MAXINSNS, sizeof(*labels_k));
+	assert(labels_k);
+}
+
+static void bpf_destroy(void)
+{
+	free(labels);
+	free(labels_jt);
+	free(labels_jf);
+	free(labels_k);
+}
+
+void bpf_asm_compile(FILE *fp, bool cstyle)
+{
+	yyin = fp;
+
+	bpf_init();
+	bpf_stage_1_insert_insns();
+	bpf_stage_2_reduce_labels();
+	bpf_destroy();
+
+	if (cstyle)
+		bpf_pretty_print_c();
+	else
+		bpf_pretty_print();
+
+	if (fp != stdin)
+		fclose(yyin);
+}
+
+void yyerror(const char *str)
+{
+	exit(1);
+}