selftests/bpf: extract utility function for BPF disassembly

struct bpf_insn *disasm_insn(struct bpf_insn *insn, char *buf, size_t buf_sz);

  Disassembles instruction 'insn' to a text buffer 'buf'.
  Removes insn->code hex prefix added by kernel disassembly routine.
  Returns a pointer to the next instruction
  (increments insn by either 1 or 2).

Acked-by: Andrii Nakryiko <andrii@kernel.org>
Signed-off-by: Eduard Zingerman <eddyz87@gmail.com>
Link: https://lore.kernel.org/r/20240722233844.1406874-5-eddyz87@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>

tools/testing/selftests/bpf/Makefile

@@ -661,6 +661,7 @@ TRUNNER_EXTRA_SOURCES := test_progs.c		\
 			 test_loader.c		\
 			 xsk.c			\
 			 disasm.c		\
+			 disasm_helpers.c	\
 			 json_writer.c 		\
 			 flow_dissector_load.h	\
 			 ip_check_defrag_frags.h

tools/testing/selftests/bpf/disasm_helpers.c

@@ -0,0 +1,51 @@
+// SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause)
+
+#include <bpf/bpf.h>
+#include "disasm.h"
+
+struct print_insn_context {
+	char *buf;
+	size_t sz;
+};
+
+static void print_insn_cb(void *private_data, const char *fmt, ...)
+{
+	struct print_insn_context *ctx = private_data;
+	va_list args;
+
+	va_start(args, fmt);
+	vsnprintf(ctx->buf, ctx->sz, fmt, args);
+	va_end(args);
+}
+
+struct bpf_insn *disasm_insn(struct bpf_insn *insn, char *buf, size_t buf_sz)
+{
+	struct print_insn_context ctx = {
+		.buf = buf,
+		.sz = buf_sz,
+	};
+	struct bpf_insn_cbs cbs = {
+		.cb_print	= print_insn_cb,
+		.private_data	= &ctx,
+	};
+	char *tmp, *pfx_end, *sfx_start;
+	bool double_insn;
+	int len;
+
+	print_bpf_insn(&cbs, insn, true);
+	/* We share code with kernel BPF disassembler, it adds '(FF) ' prefix
+	 * for each instruction (FF stands for instruction `code` byte).
+	 * Remove the prefix inplace, and also simplify call instructions.
+	 * E.g.: "(85) call foo#10" -> "call foo".
+	 * Also remove newline in the end (the 'max(strlen(buf) - 1, 0)' thing).
+	 */
+	pfx_end = buf + 5;
+	sfx_start = buf + max((int)strlen(buf) - 1, 0);
+	if (strncmp(pfx_end, "call ", 5) == 0 && (tmp = strrchr(buf, '#')))
+		sfx_start = tmp;
+	len = sfx_start - pfx_end;
+	memmove(buf, pfx_end, len);
+	buf[len] = 0;
+	double_insn = insn->code == (BPF_LD | BPF_IMM | BPF_DW);
+	return insn + (double_insn ? 2 : 1);
+}

tools/testing/selftests/bpf/disasm_helpers.h

@@ -0,0 +1,12 @@
+/* SPDX-License-Identifier: (LGPL-2.1 OR BSD-2-Clause) */
+
+#ifndef __DISASM_HELPERS_H
+#define __DISASM_HELPERS_H
+
+#include <stdlib.h>
+
+struct bpf_insn;
+
+struct bpf_insn *disasm_insn(struct bpf_insn *insn, char *buf, size_t buf_sz);
+
+#endif /* __DISASM_HELPERS_H */

tools/testing/selftests/bpf/prog_tests/ctx_rewrite.c

@@ -10,7 +10,8 @@
 #include "bpf/btf.h"
 #include "bpf_util.h"
 #include "linux/filter.h"
-#include "disasm.h"
+#include "linux/kernel.h"
+#include "disasm_helpers.h"
 
 #define MAX_PROG_TEXT_SZ (32 * 1024)
 
@@ -628,63 +629,6 @@ static bool match_pattern(struct btf *btf, char *pattern, char *text, char *reg_
 	return false;
 }
 
-static void print_insn(void *private_data, const char *fmt, ...)
-{
-	va_list args;
-
-	va_start(args, fmt);
-	vfprintf((FILE *)private_data, fmt, args);
-	va_end(args);
-}
-
-/* Disassemble instructions to a stream */
-static void print_xlated(FILE *out, struct bpf_insn *insn, __u32 len)
-{
-	const struct bpf_insn_cbs cbs = {
-		.cb_print	= print_insn,
-		.cb_call	= NULL,
-		.cb_imm		= NULL,
-		.private_data	= out,
-	};
-	bool double_insn = false;
-	int i;
-
-	for (i = 0; i < len; i++) {
-		if (double_insn) {
-			double_insn = false;
-			continue;
-		}
-
-		double_insn = insn[i].code == (BPF_LD | BPF_IMM | BPF_DW);
-		print_bpf_insn(&cbs, insn + i, true);
-	}
-}
-
-/* We share code with kernel BPF disassembler, it adds '(FF) ' prefix
- * for each instruction (FF stands for instruction `code` byte).
- * This function removes the prefix inplace for each line in `str`.
- */
-static void remove_insn_prefix(char *str, int size)
-{
-	const int prefix_size = 5;
-
-	int write_pos = 0, read_pos = prefix_size;
-	int len = strlen(str);
-	char c;
-
-	size = min(size, len);
-
-	while (read_pos < size) {
-		c = str[read_pos++];
-		if (c == 0)
-			break;
-		str[write_pos++] = c;
-		if (c == '\n')
-			read_pos += prefix_size;
-	}
-	str[write_pos] = 0;
-}
-
 struct prog_info {
 	char *prog_kind;
 	enum bpf_prog_type prog_type;
@@ -699,9 +643,10 @@ static void match_program(struct btf *btf,
 			  char *reg_map[][2],
 			  bool skip_first_insn)
 {
-	struct bpf_insn *buf = NULL;
+	struct bpf_insn *buf = NULL, *insn, *insn_end;
 	int err = 0, prog_fd = 0;
 	FILE *prog_out = NULL;
+	char insn_buf[64];
 	char *text = NULL;
 	__u32 cnt = 0;
 
@@ -739,12 +684,13 @@ static void match_program(struct btf *btf,
 		PRINT_FAIL("Can't open memory stream\n");
 		goto out;
 	}
-	if (skip_first_insn)
-		print_xlated(prog_out, buf + 1, cnt - 1);
-	else
-		print_xlated(prog_out, buf, cnt);
+	insn_end = buf + cnt;
+	insn = buf + (skip_first_insn ? 1 : 0);
+	while (insn < insn_end) {
+		insn = disasm_insn(insn, insn_buf, sizeof(insn_buf));
+		fprintf(prog_out, "%s\n", insn_buf);
+	}
 	fclose(prog_out);
-	remove_insn_prefix(text, MAX_PROG_TEXT_SZ);
 
 	ASSERT_TRUE(match_pattern(btf, pattern, text, reg_map),
 		    pinfo->prog_kind);

tools/testing/selftests/bpf/testing_helpers.c

@@ -7,6 +7,7 @@
 #include <errno.h>
 #include <bpf/bpf.h>
 #include <bpf/libbpf.h>
+#include "disasm.h"
 #include "test_progs.h"
 #include "testing_helpers.h"
 #include <linux/membarrier.h>