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

tools/net/Makefile

 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

tools/net/bpf_asm.c

+/*
+ * 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;
+}

tools/net/bpf_exp.l

+/*
+ * 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");
+		}
+
+%%