[PATCH v6 03/30] objtool: Disassemble code with libopcodes instead of running objdump

[Alexandre Chartre <alexandre.chartre@oracle.com>]

objtool executes the objdump command to disassemble code. Use libopcodes
instead to have more control about the disassembly scope and output.
If libopcodes is not present then objtool is built without disassembly
support.

Signed-off-by: Alexandre Chartre <alexandre.chartre@oracle.com>
---
 tools/objtool/.gitignore              |   2 +
 tools/objtool/Build                   |   3 +-
 tools/objtool/Makefile                |  25 ++++
 tools/objtool/arch/loongarch/decode.c |  12 ++
 tools/objtool/arch/powerpc/decode.c   |  12 ++
 tools/objtool/arch/x86/decode.c       |  12 ++
 tools/objtool/check.c                 |  14 +-
 tools/objtool/disas.c                 | 187 +++++++++++++++++---------
 tools/objtool/include/objtool/arch.h  |   9 ++
 tools/objtool/include/objtool/check.h |   5 +
 tools/objtool/include/objtool/disas.h |  29 ++++
 11 files changed, 238 insertions(+), 72 deletions(-)

diff --git a/tools/objtool/.gitignore b/tools/objtool/.gitignore
index 4faa4dd72f350..759303657bd7c 100644
--- a/tools/objtool/.gitignore
+++ b/tools/objtool/.gitignore
@@ -1,5 +1,7 @@
 # SPDX-License-Identifier: GPL-2.0-only
 arch/x86/lib/inat-tables.c
 /objtool
+feature
+FEATURE-DUMP.objtool
 fixdep
 libsubcmd/
diff --git a/tools/objtool/Build b/tools/objtool/Build
index 17e50a1766d0e..9d1e8f28ef953 100644
--- a/tools/objtool/Build
+++ b/tools/objtool/Build
@@ -7,7 +7,8 @@ objtool-y += special.o
 objtool-y += builtin-check.o
 objtool-y += elf.o
 objtool-y += objtool.o
-objtool-y += disas.o
+
+objtool-$(BUILD_DISAS) += disas.o
 
 objtool-$(BUILD_ORC) += orc_gen.o orc_dump.o
 objtool-$(BUILD_KLP) += builtin-klp.o klp-diff.o klp-post-link.o
diff --git a/tools/objtool/Makefile b/tools/objtool/Makefile
index 021f55b7bd872..df793ca6fc1a1 100644
--- a/tools/objtool/Makefile
+++ b/tools/objtool/Makefile
@@ -70,6 +70,29 @@ OBJTOOL_CFLAGS += $(if $(elfshdr),,-DLIBELF_USE_DEPRECATED)
 # Always want host compilation.
 HOST_OVERRIDES := CC="$(HOSTCC)" LD="$(HOSTLD)" AR="$(HOSTAR)"
 
+#
+# To support disassembly, objtool needs libopcodes which is provided
+# with libbdf (binutils-dev or binutils-devel package).
+#
+FEATURE_USER = .objtool
+FEATURE_TESTS = libbfd disassembler-init-styled
+FEATURE_DISPLAY =
+include $(srctree)/tools/build/Makefile.feature
+
+ifeq ($(feature-disassembler-init-styled), 1)
+	OBJTOOL_CFLAGS += -DDISASM_INIT_STYLED
+endif
+
+BUILD_DISAS := n
+
+ifeq ($(feature-libbfd),1)
+	BUILD_DISAS := y
+	OBJTOOL_CFLAGS += -DDISAS
+	OBJTOOL_LDFLAGS += -lopcodes
+endif
+
+export BUILD_DISAS
+
 AWK = awk
 MKDIR = mkdir
 
@@ -103,6 +126,8 @@ clean: $(LIBSUBCMD)-clean
 	$(call QUIET_CLEAN, objtool) $(RM) $(OBJTOOL)
 	$(Q)find $(OUTPUT) -name '*.o' -delete -o -name '\.*.cmd' -delete -o -name '\.*.d' -delete
 	$(Q)$(RM) $(OUTPUT)arch/x86/lib/inat-tables.c $(OUTPUT)fixdep
+	$(Q)$(RM) -- $(OUTPUT)FEATURE-DUMP.objtool
+	$(Q)$(RM) -r -- $(OUTPUT)feature
 
 FORCE:
 
diff --git a/tools/objtool/arch/loongarch/decode.c b/tools/objtool/arch/loongarch/decode.c
index 0115b97c526b8..1de86ebb637d5 100644
--- a/tools/objtool/arch/loongarch/decode.c
+++ b/tools/objtool/arch/loongarch/decode.c
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0-or-later
 #include <string.h>
 #include <objtool/check.h>
+#include <objtool/disas.h>
 #include <objtool/warn.h>
 #include <asm/inst.h>
 #include <asm/orc_types.h>
@@ -414,3 +415,14 @@ unsigned long arch_jump_table_sym_offset(struct reloc *reloc, struct reloc *tabl
 		return reloc->sym->offset + reloc_addend(reloc);
 	}
 }
+
+#ifdef DISAS
+
+int arch_disas_info_init(struct disassemble_info *dinfo)
+{
+	return disas_info_init(dinfo, bfd_arch_loongarch,
+			       bfd_mach_loongarch32, bfd_mach_loongarch64,
+			       NULL);
+}
+
+#endif /* DISAS */
diff --git a/tools/objtool/arch/powerpc/decode.c b/tools/objtool/arch/powerpc/decode.c
index 3a9b748216edc..4f68b402e7855 100644
--- a/tools/objtool/arch/powerpc/decode.c
+++ b/tools/objtool/arch/powerpc/decode.c
@@ -3,6 +3,7 @@
 #include <stdio.h>
 #include <stdlib.h>
 #include <objtool/check.h>
+#include <objtool/disas.h>
 #include <objtool/elf.h>
 #include <objtool/arch.h>
 #include <objtool/warn.h>
@@ -127,3 +128,14 @@ unsigned int arch_reloc_size(struct reloc *reloc)
 		return 8;
 	}
 }
+
+#ifdef DISAS
+
+int arch_disas_info_init(struct disassemble_info *dinfo)
+{
+	return disas_info_init(dinfo, bfd_arch_powerpc,
+			       bfd_mach_ppc, bfd_mach_ppc64,
+			       NULL);
+}
+
+#endif /* DISAS */
diff --git a/tools/objtool/arch/x86/decode.c b/tools/objtool/arch/x86/decode.c
index cc85db7b65a41..83e9c604ce105 100644
--- a/tools/objtool/arch/x86/decode.c
+++ b/tools/objtool/arch/x86/decode.c
@@ -16,6 +16,7 @@
 
 #include <asm/orc_types.h>
 #include <objtool/check.h>
+#include <objtool/disas.h>
 #include <objtool/elf.h>
 #include <objtool/arch.h>
 #include <objtool/warn.h>
@@ -949,3 +950,14 @@ bool arch_absolute_reloc(struct elf *elf, struct reloc *reloc)
 		return false;
 	}
 }
+
+#ifdef DISAS
+
+int arch_disas_info_init(struct disassemble_info *dinfo)
+{
+	return disas_info_init(dinfo, bfd_arch_i386,
+			       bfd_mach_i386_i386, bfd_mach_x86_64,
+			       "att");
+}
+
+#endif /* DISAS */
diff --git a/tools/objtool/check.c b/tools/objtool/check.c
index 5083e47eef08d..de156e91ee8b7 100644
--- a/tools/objtool/check.c
+++ b/tools/objtool/check.c
@@ -4980,8 +4980,6 @@ int check(struct objtool_file *file)
 			goto out;
 	}
 
-	free_insns(file);
-
 	if (opts.stats) {
 		printf("nr_insns_visited: %ld\n", nr_insns_visited);
 		printf("nr_cfi: %ld\n", nr_cfi);
@@ -4990,8 +4988,10 @@ int check(struct objtool_file *file)
 	}
 
 out:
-	if (!ret && !warnings)
+	if (!ret && !warnings) {
+		free_insns(file);
 		return 0;
+	}
 
 	if (opts.werror && warnings)
 		ret = 1;
@@ -5000,10 +5000,14 @@ int check(struct objtool_file *file)
 		if (opts.werror && warnings)
 			WARN("%d warning(s) upgraded to errors", warnings);
 		disas_ctx = disas_context_create(file);
-		disas_warned_funcs(disas_ctx);
-		disas_context_destroy(disas_ctx);
+		if (disas_ctx) {
+			disas_warned_funcs(disas_ctx);
+			disas_context_destroy(disas_ctx);
+		}
 	}
 
+	free_insns(file);
+
 	if (opts.backup && make_backup())
 		return 1;
 
diff --git a/tools/objtool/disas.c b/tools/objtool/disas.c
index 7a18e51d43e62..11ac2ec04afc1 100644
--- a/tools/objtool/disas.c
+++ b/tools/objtool/disas.c
@@ -4,18 +4,56 @@
  */
 
 #include <objtool/arch.h>
+#include <objtool/check.h>
 #include <objtool/disas.h>
 #include <objtool/warn.h>
 
+#include <bfd.h>
 #include <linux/string.h>
+#include <tools/dis-asm-compat.h>
 
 struct disas_context {
 	struct objtool_file *file;
+	disassembler_ftype disassembler;
+	struct disassemble_info info;
 };
 
+#define DINFO_FPRINTF(dinfo, ...)	\
+	((*(dinfo)->fprintf_func)((dinfo)->stream, __VA_ARGS__))
+
+/*
+ * Initialize disassemble info arch, mach (32 or 64-bit) and options.
+ */
+int disas_info_init(struct disassemble_info *dinfo,
+		    int arch, int mach32, int mach64,
+		    const char *options)
+{
+	struct disas_context *dctx = dinfo->application_data;
+	struct objtool_file *file = dctx->file;
+
+	dinfo->arch = arch;
+
+	switch (file->elf->ehdr.e_ident[EI_CLASS]) {
+	case ELFCLASS32:
+		dinfo->mach = mach32;
+		break;
+	case ELFCLASS64:
+		dinfo->mach = mach64;
+		break;
+	default:
+		return -1;
+	}
+
+	dinfo->disassembler_options = options;
+
+	return 0;
+}
+
 struct disas_context *disas_context_create(struct objtool_file *file)
 {
 	struct disas_context *dctx;
+	struct disassemble_info *dinfo;
+	int err;
 
 	dctx = malloc(sizeof(*dctx));
 	if (!dctx) {
@@ -24,8 +62,49 @@ struct disas_context *disas_context_create(struct objtool_file *file)
 	}
 
 	dctx->file = file;
+	dinfo = &dctx->info;
+
+	init_disassemble_info_compat(dinfo, stdout,
+				     (fprintf_ftype)fprintf,
+				     fprintf_styled);
+
+	dinfo->read_memory_func = buffer_read_memory;
+	dinfo->application_data = dctx;
+
+	/*
+	 * bfd_openr() is not used to avoid doing ELF data processing
+	 * and caching that has already being done. Here, we just need
+	 * to identify the target file so we call an arch specific
+	 * function to fill some disassemble info (arch, mach).
+	 */
+
+	dinfo->arch = bfd_arch_unknown;
+	dinfo->mach = 0;
+
+	err = arch_disas_info_init(dinfo);
+	if (err || dinfo->arch == bfd_arch_unknown || dinfo->mach == 0) {
+		WARN("failed to init disassembly arch");
+		goto error;
+	}
+
+	dinfo->endian = (file->elf->ehdr.e_ident[EI_DATA] == ELFDATA2MSB) ?
+		BFD_ENDIAN_BIG : BFD_ENDIAN_LITTLE;
+
+	disassemble_init_for_target(dinfo);
+
+	dctx->disassembler = disassembler(dinfo->arch,
+					  dinfo->endian == BFD_ENDIAN_BIG,
+					  dinfo->mach, NULL);
+	if (!dctx->disassembler) {
+		WARN("failed to create disassembler function");
+		goto error;
+	}
 
 	return dctx;
+
+error:
+	free(dctx);
+	return NULL;
 }
 
 void disas_context_destroy(struct disas_context *dctx)
@@ -33,86 +112,62 @@ void disas_context_destroy(struct disas_context *dctx)
 	free(dctx);
 }
 
-/* 'funcs' is a space-separated list of function names */
-static void disas_funcs(const char *funcs)
+/*
+ * Disassemble a single instruction. Return the size of the instruction.
+ */
+static size_t disas_insn(struct disas_context *dctx,
+			 struct instruction *insn)
 {
-	const char *objdump_str, *cross_compile;
-	int size, ret;
-	char *cmd;
-
-	cross_compile = getenv("CROSS_COMPILE");
-	if (!cross_compile)
-		cross_compile = "";
-
-	objdump_str = "%sobjdump -wdr %s | gawk -M -v _funcs='%s' '"
-			"BEGIN { split(_funcs, funcs); }"
-			"/^$/ { func_match = 0; }"
-			"/<.*>:/ { "
-				"f = gensub(/.*<(.*)>:/, \"\\\\1\", 1);"
-				"for (i in funcs) {"
-					"if (funcs[i] == f) {"
-						"func_match = 1;"
-						"base = strtonum(\"0x\" $1);"
-						"break;"
-					"}"
-				"}"
-			"}"
-			"{"
-				"if (func_match) {"
-					"addr = strtonum(\"0x\" $1);"
-					"printf(\"%%04x \", addr - base);"
-					"print;"
-				"}"
-			"}' 1>&2";
-
-	/* fake snprintf() to calculate the size */
-	size = snprintf(NULL, 0, objdump_str, cross_compile, objname, funcs) + 1;
-	if (size <= 0) {
-		WARN("objdump string size calculation failed");
-		return;
+	disassembler_ftype disasm = dctx->disassembler;
+	struct disassemble_info *dinfo = &dctx->info;
+
+	if (insn->type == INSN_NOP) {
+		DINFO_FPRINTF(dinfo, "nop%d", insn->len);
+		return insn->len;
 	}
 
-	cmd = malloc(size);
+	/*
+	 * Set the disassembler buffer to read data from the section
+	 * containing the instruction to disassemble.
+	 */
+	dinfo->buffer = insn->sec->data->d_buf;
+	dinfo->buffer_vma = 0;
+	dinfo->buffer_length = insn->sec->sh.sh_size;
 
-	/* real snprintf() */
-	snprintf(cmd, size, objdump_str, cross_compile, objname, funcs);
-	ret = system(cmd);
-	if (ret) {
-		WARN("disassembly failed: %d", ret);
-		return;
+	return disasm(insn->offset, &dctx->info);
+}
+
+/*
+ * Disassemble a function.
+ */
+static void disas_func(struct disas_context *dctx, struct symbol *func)
+{
+	struct instruction *insn;
+	size_t addr;
+
+	printf("%s:\n", func->name);
+	sym_for_each_insn(dctx->file, func, insn) {
+		addr = insn->offset;
+		printf(" %6lx:  %s+0x%-6lx      ",
+		       addr, func->name, addr - func->offset);
+		disas_insn(dctx, insn);
+		printf("\n");
 	}
+	printf("\n");
 }
 
+/*
+ * Disassemble all warned functions.
+ */
 void disas_warned_funcs(struct disas_context *dctx)
 {
 	struct symbol *sym;
-	char *funcs = NULL, *tmp;
 
 	if (!dctx)
 		return;
 
 	for_each_sym(dctx->file->elf, sym) {
-		if (sym->warned) {
-			if (!funcs) {
-				funcs = malloc(strlen(sym->name) + 1);
-				if (!funcs) {
-					ERROR_GLIBC("malloc");
-					return;
-				}
-				strcpy(funcs, sym->name);
-			} else {
-				tmp = malloc(strlen(funcs) + strlen(sym->name) + 2);
-				if (!tmp) {
-					ERROR_GLIBC("malloc");
-					return;
-				}
-				sprintf(tmp, "%s %s", funcs, sym->name);
-				free(funcs);
-				funcs = tmp;
-			}
-		}
+		if (sym->warned)
+			disas_func(dctx, sym);
 	}
-
-	if (funcs)
-		disas_funcs(funcs);
 }
diff --git a/tools/objtool/include/objtool/arch.h b/tools/objtool/include/objtool/arch.h
index d89f8b5ec14e3..18c0e69ee6170 100644
--- a/tools/objtool/include/objtool/arch.h
+++ b/tools/objtool/include/objtool/arch.h
@@ -103,4 +103,13 @@ bool arch_absolute_reloc(struct elf *elf, struct reloc *reloc);
 unsigned int arch_reloc_size(struct reloc *reloc);
 unsigned long arch_jump_table_sym_offset(struct reloc *reloc, struct reloc *table);
 
+#ifdef DISAS
+
+#include <bfd.h>
+#include <dis-asm.h>
+
+int arch_disas_info_init(struct disassemble_info *dinfo);
+
+#endif /* DISAS */
+
 #endif /* _ARCH_H */
diff --git a/tools/objtool/include/objtool/check.h b/tools/objtool/include/objtool/check.h
index d73b0c3ae1ee3..674f57466d125 100644
--- a/tools/objtool/include/objtool/check.h
+++ b/tools/objtool/include/objtool/check.h
@@ -127,4 +127,9 @@ struct instruction *next_insn_same_sec(struct objtool_file *file, struct instruc
 	     insn && insn->sec == _sec;					\
 	     insn = next_insn_same_sec(file, insn))
 
+#define sym_for_each_insn(file, sym, insn)				\
+	for (insn = find_insn(file, sym->sec, sym->offset);		\
+	     insn && insn->offset < sym->offset + sym->len;		\
+	     insn = next_insn_same_sec(file, insn))
+
 #endif /* _CHECK_H */
diff --git a/tools/objtool/include/objtool/disas.h b/tools/objtool/include/objtool/disas.h
index 5c543b69fc612..3ec3ce2e4e6f0 100644
--- a/tools/objtool/include/objtool/disas.h
+++ b/tools/objtool/include/objtool/disas.h
@@ -7,8 +7,37 @@
 #define _DISAS_H
 
 struct disas_context;
+struct disassemble_info;
+
+#ifdef DISAS
+
 struct disas_context *disas_context_create(struct objtool_file *file);
 void disas_context_destroy(struct disas_context *dctx);
 void disas_warned_funcs(struct disas_context *dctx);
+int disas_info_init(struct disassemble_info *dinfo,
+		    int arch, int mach32, int mach64,
+		    const char *options);
+
+#else /* DISAS */
+
+#include <objtool/warn.h>
+
+static inline struct disas_context *disas_context_create(struct objtool_file *file)
+{
+	WARN("Rebuild with libopcodes for disassembly support");
+	return NULL;
+}
+
+static inline void disas_context_destroy(struct disas_context *dctx) {}
+static inline void disas_warned_funcs(struct disas_context *dctx) {}
+
+static inline int disas_info_init(struct disassemble_info *dinfo,
+				  int arch, int mach32, int mach64,
+				  const char *options)
+{
+	return -1;
+}
+
+#endif /* DISAS */
 
 #endif /* _DISAS_H */
-- 
2.43.5