[PATCH v4 15/22] objtool: Prevent kCFI hashes from being decoded as instructions

[Josh Poimboeuf]

On arm64 with CONFIG_CFI=y, Clang places a 4-byte kCFI type hash
immediately before each address-taken function entry.  Since these
hashes are in the text section, objtool tries to decode them, leading to
unpredictable results (e.g., ""unannotated intra-function call").

arm64 toolchains use mapping symbols to annotate boundaries between code
and data.  Use those to just mark such "instructions" as NOP so objtool
ignores them.

Signed-off-by: Josh Poimboeuf <jpoimboe at kernel.org>
---
 tools/objtool/check.c               | 14 ++++++++++++++
 tools/objtool/include/objtool/elf.h | 23 +++++++++++++++++++++++
 2 files changed, 37 insertions(+)

diff --git a/tools/objtool/check.c b/tools/objtool/check.c
index c034676e1b8c7..79b9e2b5d96de 100644
--- a/tools/objtool/check.c
+++ b/tools/objtool/check.c
@@ -430,6 +430,8 @@ static int decode_instructions(struct objtool_file *file)
 
 	for_each_sec(file->elf, sec) {
 		struct instruction *insns = NULL;
+		struct symbol *map_sym;
+		bool is_data = false;
 		u8 prev_len = 0;
 		u8 idx = 0;
 
@@ -456,6 +458,8 @@ static int decode_instructions(struct objtool_file *file)
 		if (!strcmp(sec->name, ".init.text") && !opts.module)
 			sec->init = true;
 
+		map_sym = list_first_entry(&sec->symbol_list, struct symbol, list);
+
 		for (offset = 0; offset < sec_size(sec); offset += insn->len) {
 			if (!insns || idx == INSN_CHUNK_MAX) {
 				insns = calloc(INSN_CHUNK_SIZE, sizeof(*insn));
@@ -480,6 +484,16 @@ static int decode_instructions(struct objtool_file *file)
 
 			prev_len = insn->len;
 
+			/* Use mapping symbols to skip data in text sections */
+			sec_for_each_sym_from(sec, map_sym) {
+				if (map_sym->offset > offset)
+					break;
+				if (is_mapping_sym(map_sym))
+					is_data = is_data_mapping_sym(map_sym);
+			}
+			if (is_data)
+				insn->type = INSN_NOP;
+
 			/*
 			 * By default, "ud2" is a dead end unless otherwise
 			 * annotated, because GCC 7 inserts it for certain
diff --git a/tools/objtool/include/objtool/elf.h b/tools/objtool/include/objtool/elf.h
index 5cba96c6392cb..796d154d447b6 100644
--- a/tools/objtool/include/objtool/elf.h
+++ b/tools/objtool/include/objtool/elf.h
@@ -296,6 +296,26 @@ static inline bool is_notype_sym(struct symbol *sym)
 	return sym->type == STT_NOTYPE;
 }
 
+/*
+ * ARM64 mapping symbols ($d, $x, $a, __pi_$d, etc) which mark transitions
+ * between code and data.
+ */
+static inline bool is_mapping_sym(struct symbol *sym)
+{
+	return is_notype_sym(sym) && strchr(sym->name, '$');
+}
+
+static inline bool is_data_mapping_sym(struct symbol *sym)
+{
+	const char *dollar;
+
+	if (!is_mapping_sym(sym))
+		return false;
+
+	dollar = strchr(sym->name, '$');
+	return dollar && dollar[1] == 'd';
+}
+
 static inline bool is_global_sym(struct symbol *sym)
 {
 	return sym->bind == STB_GLOBAL;
@@ -508,6 +528,9 @@ static inline void set_sym_next_reloc(struct reloc *reloc, struct reloc *next)
 #define sec_for_each_sym(sec, sym)					\
 	list_for_each_entry(sym, &sec->symbol_list, list)
 
+#define sec_for_each_sym_from(sec, sym)					\
+	list_for_each_entry_from(sym, &sec->symbol_list, list)
+
 #define sec_prev_sym(sym)						\
 	sym->sec && sym->list.prev != &sym->sec->symbol_list ?		\
 	list_prev_entry(sym, list) : NULL
-- 
2.54.0