[RFC PATCH v4 14/37] objtool: check: Support data in text section

[Chen Zhongjin <chenzhongjin@huawei.com>]

From: Julien Thierry <jthierry@redhat.com>

Assembly code can mix code and data in text sections through the use
of SYM_DATA_*() macros. Skip the content of these symbols when decoding
instructions of text sections.

Signed-off-by: Julien Thierry <jthierry@redhat.com>
Signed-off-by: Chen Zhongjin <chenzhongjin@huawei.com>
---
 tools/objtool/check.c               | 19 +++++++++++++++++--
 tools/objtool/elf.c                 | 14 ++++++++++++++
 tools/objtool/include/objtool/elf.h |  1 +
 3 files changed, 32 insertions(+), 2 deletions(-)

diff --git a/tools/objtool/check.c b/tools/objtool/check.c
index ae75e88c4885..52978b8f2ae9 100644
--- a/tools/objtool/check.c
+++ b/tools/objtool/check.c
@@ -356,7 +356,7 @@ static int decode_instructions(struct objtool_file *file)
 {
 	struct section *sec;
 	struct symbol *func;
-	unsigned long offset;
+	unsigned long offset, next_offset;
 	struct instruction *insn;
 	int ret;
 
@@ -374,7 +374,14 @@ static int decode_instructions(struct objtool_file *file)
 		    !strcmp(sec->name, ".entry.text"))
 			sec->noinstr = true;
 
-		for (offset = 0; offset < sec->sh.sh_size; offset += insn->len) {
+		for (offset = 0; offset < sec->sh.sh_size; offset = next_offset) {
+			struct symbol *obj_sym = find_object_containing(sec, offset);
+			if (obj_sym) {
+				/* This is data in the middle of text section, skip it */
+				next_offset = obj_sym->offset + obj_sym->len;
+				continue;
+			}
+
 			insn = malloc(sizeof(*insn));
 			if (!insn) {
 				WARN("malloc failed");
@@ -407,6 +414,14 @@ static int decode_instructions(struct objtool_file *file)
 			hash_add(file->insn_hash, &insn->hash, sec_offset_hash(sec, insn->offset));
 			list_add_tail(&insn->list, &file->insn_list);
 			nr_insns++;
+
+			/* This case is rare, but can cause infinite loop */
+			if (!insn->len) {
+				WARN("zero instruction length");
+				return -1;
+			}
+
+			next_offset = offset + insn->len;
 		}
 
 		list_for_each_entry(func, &sec->symbol_list, list) {
diff --git a/tools/objtool/elf.c b/tools/objtool/elf.c
index d7b99a737496..5b35d89b54d4 100644
--- a/tools/objtool/elf.c
+++ b/tools/objtool/elf.c
@@ -236,6 +236,20 @@ struct symbol *find_func_containing(struct section *sec, unsigned long offset)
 	return NULL;
 }
 
+struct symbol *find_object_containing(struct section *sec, unsigned long offset)
+{
+	struct rb_node *node;
+
+	rb_for_each(node, &offset, &sec->symbol_tree, symbol_by_offset) {
+		struct symbol *s = rb_entry(node, struct symbol, node);
+
+		if (s->type == STT_OBJECT)
+			return s;
+	}
+
+	return NULL;
+}
+
 struct symbol *find_symbol_by_name(const struct elf *elf, const char *name)
 {
 	struct symbol *sym;
diff --git a/tools/objtool/include/objtool/elf.h b/tools/objtool/include/objtool/elf.h
index 22ba7e2b816e..52ecf1e23cb6 100644
--- a/tools/objtool/include/objtool/elf.h
+++ b/tools/objtool/include/objtool/elf.h
@@ -157,6 +157,7 @@ struct reloc *find_reloc_by_dest(const struct elf *elf, struct section *sec, uns
 struct reloc *find_reloc_by_dest_range(const struct elf *elf, struct section *sec,
 				     unsigned long offset, unsigned int len);
 struct symbol *find_func_containing(struct section *sec, unsigned long offset);
+struct symbol *find_object_containing(struct section *sec, unsigned long offset);
 
 #define for_each_sec(file, sec)						\
 	list_for_each_entry(sec, &file->elf->sections, list)
-- 
2.17.1