Merge branch 'bpftool: Add LLVM as default library for disassembling JIT-ed programs'

Quentin Monnet says:

====================

To disassemble instructions for JIT-ed programs, bpftool has relied on the
libbfd library. This has been problematic in the past: libbfd's interface
is not meant to be stable and has changed several times, hence the
detection of the two related features from the Makefile
(disassembler-four-args and disassembler-init-styled). When it comes to
shipping bpftool, this has also caused issues with several distribution
maintainers unwilling to support the feature (for example, Debian's page
for binutils-dev, libbfd's package, says: "Note that building Debian
packages which depend on the shared libbfd is Not Allowed.").

This patchset adds support for LLVM as the primary library for
disassembling instructions for JIT-ed programs.

We keep libbfd as a fallback. One reason for this is that currently it
works well, we have all we need in terms of features detection in the
Makefile, so it provides a fallback for disassembling JIT-ed programs if
libbfd is installed but LLVM is not. The other reason is that libbfd
supports nfp instruction for Netronome's SmartNICs and can be used to
disassemble offloaded programs, something that LLVM cannot do (Niklas
confirmed that the feature is still in use). However, if libbfd's interface
breaks again in the future, we might reconsider keeping support for it.

v4:
  - Rebase to address a conflict with commit 2c76238eaddd ("bpftool: Add
    "bootstrap" feature to version output").

v3:
  - Extend commit description (patch 6) with notes on llvm-dev and LLVM's
    disassembler stability.

v2:
  - Pass callback when creating the LLVM disassembler, so that the
    branch targets are printed as addresses (instead of byte offsets).
  - Add last commit to "support" other arch with LLVM, although we don't
    know any supported triple yet.
  - Use $(LLVM_CONFIG) instead of llvm-config in Makefile.
  - Pass components to llvm-config --libs to limit the number of
    libraries to pass on the command line, in Makefile.
  - Rebase split of FEATURE_TESTS and FEATURE_DISPLAY in Makefile.
====================

Signed-off-by: Alexei Starovoitov <ast@kernel.org>

1 files changed, 215 insertions, 46 deletions

diff --git a/tools/bpf/bpftool/jit_disasm.c b/tools/bpf/bpftool/jit_disasm.c
index aaf99a0168c9..58a5017034a2 100644
--- a/tools/bpf/bpftool/jit_disasm.c
+++ b/tools/bpf/bpftool/jit_disasm.c
@@ -11,35 +11,151 @@
  * Licensed under the GNU General Public License, version 2.0 (GPLv2)
  */
 
+#ifndef _GNU_SOURCE
 #define _GNU_SOURCE
+#endif
 #include <stdio.h>
 #include <stdarg.h>
 #include <stdint.h>
 #include <stdlib.h>
-#include <assert.h>
 #include <unistd.h>
 #include <string.h>
-#include <bfd.h>
-#include <dis-asm.h>
 #include <sys/stat.h>
 #include <limits.h>
 #include <bpf/libbpf.h>
+
+#ifdef HAVE_LLVM_SUPPORT
+#include <llvm-c/Core.h>
+#include <llvm-c/Disassembler.h>
+#include <llvm-c/Target.h>
+#include <llvm-c/TargetMachine.h>
+#endif
+
+#ifdef HAVE_LIBBFD_SUPPORT
+#include <bfd.h>
+#include <dis-asm.h>
 #include <tools/dis-asm-compat.h>
+#endif
 
 #include "json_writer.h"
 #include "main.h"
 
-static void get_exec_path(char *tpath, size_t size)
+static int oper_count;
+
+#ifdef HAVE_LLVM_SUPPORT
+#define DISASM_SPACER
+
+typedef LLVMDisasmContextRef disasm_ctx_t;
+
+static int printf_json(char *s)
+{
+	s = strtok(s, " \t");
+	jsonw_string_field(json_wtr, "operation", s);
+
+	jsonw_name(json_wtr, "operands");
+	jsonw_start_array(json_wtr);
+	oper_count = 1;
+
+	while ((s = strtok(NULL, " \t,()")) != 0) {
+		jsonw_string(json_wtr, s);
+		oper_count++;
+	}
+	return 0;
+}
+
+/* This callback to set the ref_type is necessary to have the LLVM disassembler
+ * print PC-relative addresses instead of byte offsets for branch instruction
+ * targets.
+ */
+static const char *
+symbol_lookup_callback(__maybe_unused void *disasm_info,
+		       __maybe_unused uint64_t ref_value,
+		       uint64_t *ref_type, __maybe_unused uint64_t ref_PC,
+		       __maybe_unused const char **ref_name)
+{
+	*ref_type = LLVMDisassembler_ReferenceType_InOut_None;
+	return NULL;
+}
+
+static int
+init_context(disasm_ctx_t *ctx, const char *arch,
+	     __maybe_unused const char *disassembler_options,
+	     __maybe_unused unsigned char *image, __maybe_unused ssize_t len)
+{
+	char *triple;
+
+	if (arch)
+		triple = LLVMNormalizeTargetTriple(arch);
+	else
+		triple = LLVMGetDefaultTargetTriple();
+	if (!triple) {
+		p_err("Failed to retrieve triple");
+		return -1;
+	}
+	*ctx = LLVMCreateDisasm(triple, NULL, 0, NULL, symbol_lookup_callback);
+	LLVMDisposeMessage(triple);
+
+	if (!*ctx) {
+		p_err("Failed to create disassembler");
+		return -1;
+	}
+
+	return 0;
+}
+
+static void destroy_context(disasm_ctx_t *ctx)
+{
+	LLVMDisposeMessage(*ctx);
+}
+
+static int
+disassemble_insn(disasm_ctx_t *ctx, unsigned char *image, ssize_t len, int pc)
+{
+	char buf[256];
+	int count;
+
+	count = LLVMDisasmInstruction(*ctx, image + pc, len - pc, pc,
+				      buf, sizeof(buf));
+	if (json_output)
+		printf_json(buf);
+	else
+		printf("%s", buf);
+
+	return count;
+}
+
+int disasm_init(void)
+{
+	LLVMInitializeAllTargetInfos();
+	LLVMInitializeAllTargetMCs();
+	LLVMInitializeAllDisassemblers();
+	return 0;
+}
+#endif /* HAVE_LLVM_SUPPORT */
+
+#ifdef HAVE_LIBBFD_SUPPORT
+#define DISASM_SPACER "\t"
+
+typedef struct {
+	struct disassemble_info *info;
+	disassembler_ftype disassemble;
+	bfd *bfdf;
+} disasm_ctx_t;
+
+static int get_exec_path(char *tpath, size_t size)
 {
 	const char *path = "/proc/self/exe";
 	ssize_t len;
 
 	len = readlink(path, tpath, size - 1);
-	assert(len > 0);
+	if (len <= 0)
+		return -1;
+
 	tpath[len] = 0;
+
+	return 0;
 }
 
-static int oper_count;
 static int printf_json(void *out, const char *fmt, va_list ap)
 {
 	char *s;
@@ -97,37 +213,44 @@ static int fprintf_json_styled(void *out,
 	return r;
 }
 
-void disasm_print_insn(unsigned char *image, ssize_t len, int opcodes,
-		       const char *arch, const char *disassembler_options,
-		       const struct btf *btf,
-		       const struct bpf_prog_linfo *prog_linfo,
-		       __u64 func_ksym, unsigned int func_idx,
-		       bool linum)
+static int init_context(disasm_ctx_t *ctx, const char *arch,
+			const char *disassembler_options,
+			unsigned char *image, ssize_t len)
 {
-	const struct bpf_line_info *linfo = NULL;
-	disassembler_ftype disassemble;
-	struct disassemble_info info;
-	unsigned int nr_skip = 0;
-	int count, i, pc = 0;
+	struct disassemble_info *info;
 	char tpath[PATH_MAX];
 	bfd *bfdf;
 
-	if (!len)
-		return;
-
 	memset(tpath, 0, sizeof(tpath));
-	get_exec_path(tpath, sizeof(tpath));
+	if (get_exec_path(tpath, sizeof(tpath))) {
+		p_err("failed to create disasembler (get_exec_path)");
+		return -1;
+	}
 
-	bfdf = bfd_openr(tpath, NULL);
-	assert(bfdf);
-	assert(bfd_check_format(bfdf, bfd_object));
+	ctx->bfdf = bfd_openr(tpath, NULL);
+	if (!ctx->bfdf) {
+		p_err("failed to create disassembler (bfd_openr)");
+		return -1;
+	}
+	if (!bfd_check_format(ctx->bfdf, bfd_object)) {
+		p_err("failed to create disassembler (bfd_check_format)");
+		goto err_close;
+	}
+	bfdf = ctx->bfdf;
+
+	ctx->info = malloc(sizeof(struct disassemble_info));
+	if (!ctx->info) {
+		p_err("mem alloc failed");
+		goto err_close;
+	}
+	info = ctx->info;
 
 	if (json_output)
-		init_disassemble_info_compat(&info, stdout,
+		init_disassemble_info_compat(info, stdout,
 					     (fprintf_ftype) fprintf_json,
 					     fprintf_json_styled);
 	else
-		init_disassemble_info_compat(&info, stdout,
+		init_disassemble_info_compat(info, stdout,
 					     (fprintf_ftype) fprintf,
 					     fprintf_styled);
 
@@ -139,28 +262,77 @@ void disasm_print_insn(unsigned char *image, ssize_t len, int opcodes,
 			bfdf->arch_info = inf;
 		} else {
 			p_err("No libbfd support for %s", arch);
-			return;
+			goto err_free;
 		}
 	}
 
-	info.arch = bfd_get_arch(bfdf);
-	info.mach = bfd_get_mach(bfdf);
+	info->arch = bfd_get_arch(bfdf);
+	info->mach = bfd_get_mach(bfdf);
 	if (disassembler_options)
-		info.disassembler_options = disassembler_options;
-	info.buffer = image;
-	info.buffer_length = len;
+		info->disassembler_options = disassembler_options;
+	info->buffer = image;
+	info->buffer_length = len;
 
-	disassemble_init_for_target(&info);
+	disassemble_init_for_target(info);
 
 #ifdef DISASM_FOUR_ARGS_SIGNATURE
-	disassemble = disassembler(info.arch,
-				   bfd_big_endian(bfdf),
-				   info.mach,
-				   bfdf);
+	ctx->disassemble = disassembler(info->arch,
+					bfd_big_endian(bfdf),
+					info->mach,
+					bfdf);
 #else
-	disassemble = disassembler(bfdf);
+	ctx->disassemble = disassembler(bfdf);
 #endif
-	assert(disassemble);
+	if (!ctx->disassemble) {
+		p_err("failed to create disassembler");
+		goto err_free;
+	}
+	return 0;
+
+err_free:
+	free(info);
+err_close:
+	bfd_close(ctx->bfdf);
+	return -1;
+}
+
+static void destroy_context(disasm_ctx_t *ctx)
+{
+	free(ctx->info);
+	bfd_close(ctx->bfdf);
+}
+
+static int
+disassemble_insn(disasm_ctx_t *ctx, __maybe_unused unsigned char *image,
+		 __maybe_unused ssize_t len, int pc)
+{
+	return ctx->disassemble(pc, ctx->info);
+}
+
+int disasm_init(void)
+{
+	bfd_init();
+	return 0;
+}
+#endif /* HAVE_LIBBPFD_SUPPORT */
+
+int disasm_print_insn(unsigned char *image, ssize_t len, int opcodes,
+		      const char *arch, const char *disassembler_options,
+		      const struct btf *btf,
+		      const struct bpf_prog_linfo *prog_linfo,
+		      __u64 func_ksym, unsigned int func_idx,
+		      bool linum)
+{
+	const struct bpf_line_info *linfo = NULL;
+	unsigned int nr_skip = 0;
+	int count, i, pc = 0;
+	disasm_ctx_t ctx;
+
+	if (!len)
+		return -1;
+
+	if (init_context(&ctx, arch, disassembler_options, image, len))
+		return -1;
 
 	if (json_output)
 		jsonw_start_array(json_wtr);
@@ -185,10 +357,11 @@ void disasm_print_insn(unsigned char *image, ssize_t len, int opcodes,
 			if (linfo)
 				btf_dump_linfo_plain(btf, linfo, "; ",
 						     linum);
-			printf("%4x:\t", pc);
+			printf("%4x:" DISASM_SPACER, pc);
 		}
 
-		count = disassemble(pc, &info);
+		count = disassemble_insn(&ctx, image, len, pc);
+
 		if (json_output) {
 			/* Operand array, was started in fprintf_json. Before
 			 * that, make sure we have a _null_ value if no operand
@@ -224,11 +397,7 @@ void disasm_print_insn(unsigned char *image, ssize_t len, int opcodes,
 	if (json_output)
 		jsonw_end_array(json_wtr);
 
-	bfd_close(bfdf);
-}
+	destroy_context(&ctx);
 
-int disasm_init(void)
-{
-	bfd_init();
 	return 0;
 }