kbuild: check static EXPORT_SYMBOL* by script instead of modpost

The 'static' specifier and EXPORT_SYMBOL() are an odd combination.

Commit 15bfc2348d ("modpost: check for static EXPORT_SYMBOL*
functions") tried to detect it, but this check has false negatives.

Here is the sample code.

  Makefile:

    obj-y += foo1.o foo2.o

  foo1.c:

    #include <linux/export.h>
    static void foo(void) {}
    EXPORT_SYMBOL(foo);

  foo2.c:

    void foo(void) {}

foo1.c exports the static symbol 'foo', but modpost cannot catch it
because it is fooled by foo2.c, which has a global symbol with the
same name.

s->is_static is cleared if a global symbol with the same name is found
somewhere, but EXPORT_SYMBOL() and the global symbol do not necessarily
belong to the same compilation unit.

This check should be done per compilation unit, but I do not know how
to do it in modpost. modpost runs against vmlinux.o or modules, which
merges multiple objects, then forgets their origin.

modpost cannot parse individual objects because they may not be ELF but
LLVM IR when CONFIG_LTO_CLANG=y.

Add a simple bash script to parse the output from ${NM}. This works for
CONFIG_LTO_CLANG=y because llvm-nm can dump symbols of LLVM IR files.

Revert 15bfc2348d.

Signed-off-by: Masahiro Yamada <masahiroy@kernel.org>
Reviewed-by: Nick Desaulniers <ndesaulniers@google.com>
Tested-by: Nathan Chancellor <nathan@kernel.org>
Tested-by: Sedat Dilek <sedat.dilek@gmail.com> # LLVM-14 (x86-64)

scripts/Makefile.build

@@ -249,9 +249,12 @@ cmd_gen_ksymdeps = \
 	$(CONFIG_SHELL) $(srctree)/scripts/gen_ksymdeps.sh $@ >> $(dot-target).cmd
 endif
 
+cmd_check_local_export = $(srctree)/scripts/check-local-export $@
+
 define rule_cc_o_c
 	$(call cmd_and_fixdep,cc_o_c)
 	$(call cmd,gen_ksymdeps)
+	$(call cmd,check_local_export)
 	$(call cmd,checksrc)
 	$(call cmd,checkdoc)
 	$(call cmd,gen_objtooldep)
@@ -262,6 +265,7 @@ endef
 define rule_as_o_S
 	$(call cmd_and_fixdep,as_o_S)
 	$(call cmd,gen_ksymdeps)
+	$(call cmd,check_local_export)
 	$(call cmd,gen_objtooldep)
 	$(call cmd,gen_symversions_S)
 endef

scripts/check-local-export

@@ -0,0 +1,65 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0-only
+#
+# Copyright (C) 2022 Masahiro Yamada <masahiroy@kernel.org>
+#
+# Exit with error if a local exported symbol is found.
+# EXPORT_SYMBOL should be used for global symbols.
+
+set -e
+
+declare -A symbol_types
+declare -a export_symbols
+
+exit_code=0
+
+while read value type name
+do
+	# Skip the line if the number of fields is less than 3.
+	#
+	# case 1)
+	#   For undefined symbols, the first field (value) is empty.
+	#   The outout looks like this:
+	#     "                 U _printk"
+	#   It is unneeded to record undefined symbols.
+	#
+	# case 2)
+	#   For Clang LTO, llvm-nm outputs a line with type 't' but empty name:
+	#     "---------------- t"
+	if [[ -z ${name} ]]; then
+		continue
+	fi
+
+	# save (name, type) in the associative array
+	symbol_types[${name}]=${type}
+
+	# append the exported symbol to the array
+	if [[ ${name} == __ksymtab_* ]]; then
+		export_symbols+=(${name#__ksymtab_})
+	fi
+
+	# If there is no symbol in the object, ${NM} (both GNU nm and llvm-nm)
+	# shows 'no symbols' diagnostic (but exits with 0). It is harmless and
+	# hidden by '2>/dev/null'. However, it suppresses real error messages
+	# as well. Add a hand-crafted error message here.
+	#
+	# Use --quiet instead of 2>/dev/null when we upgrade the minimum version
+	# of binutils to 2.37, llvm to 13.0.0.
+	#
+	# Then, the following line will be really simple:
+	#   done < <(${NM} --quiet ${1})
+done < <(${NM} ${1} 2>/dev/null || { echo "${0}: ${NM} failed" >&2; false; } )
+
+# Catch error in the process substitution
+wait $!
+
+for name in "${export_symbols[@]}"
+do
+	# nm(3) says "If lowercase, the symbol is usually local"
+	if [[ ${symbol_types[$name]} =~ [a-z] ]]; then
+		echo "$@: error: local symbol '${name}' was exported" >&2
+		exit_code=1
+	fi
+done
+
+exit ${exit_code}

scripts/mod/modpost.c

@@ -212,7 +212,6 @@ struct symbol {
 	unsigned int crc;
 	bool crc_valid;
 	bool weak;
-	bool is_static;		/* true if symbol is not global */
 	bool is_gpl_only;	/* exported by EXPORT_SYMBOL_GPL */
 	char name[];
 };
@@ -242,7 +241,7 @@ static struct symbol *alloc_symbol(const char *name)
 
 	memset(s, 0, sizeof(*s));
 	strcpy(s->name, name);
-	s->is_static = true;
+
 	return s;
 }
 
@@ -2064,20 +2063,6 @@ static void read_symbols(const char *modname)
 					     sym_get_data(&info, sym));
 	}
 
-	// check for static EXPORT_SYMBOL_* functions && global vars
-	for (sym = info.symtab_start; sym < info.symtab_stop; sym++) {
-		unsigned char bind = ELF_ST_BIND(sym->st_info);
-
-		if (bind == STB_GLOBAL || bind == STB_WEAK) {
-			struct symbol *s =
-				find_symbol(remove_dot(info.strtab +
-						       sym->st_name));
-
-			if (s)
-				s->is_static = false;
-		}
-	}
-
 	check_sec_ref(modname, &info);
 
 	if (!mod->is_vmlinux) {
@@ -2507,7 +2492,6 @@ static void read_dump(const char *fname)
 			mod->from_dump = true;
 		}
 		s = sym_add_exported(symname, mod, gpl_only);
-		s->is_static = false;
 		sym_set_crc(s, crc);
 		sym_update_namespace(symname, namespace);
 	}
@@ -2572,7 +2556,6 @@ int main(int argc, char **argv)
 	char *missing_namespace_deps = NULL;
 	char *dump_write = NULL, *files_source = NULL;
 	int opt;
-	int n;
 	LIST_HEAD(dump_lists);
 	struct dump_list *dl, *dl2;
 
@@ -2648,15 +2631,6 @@ int main(int argc, char **argv)
 	if (sec_mismatch_count && !sec_mismatch_warn_only)
 		error("Section mismatches detected.\n"
 		      "Set CONFIG_SECTION_MISMATCH_WARN_ONLY=y to allow them.\n");
-	for (n = 0; n < SYMBOL_HASH_SIZE; n++) {
-		struct symbol *s;
-
-		for (s = symbolhash[n]; s; s = s->next) {
-			if (s->is_static)
-				error("\"%s\" [%s] is a static EXPORT_SYMBOL\n",
-				      s->name, s->module->name);
-		}
-	}
 
 	if (nr_unresolved > MAX_UNRESOLVED_REPORTS)
 		warn("suppressed %u unresolved symbol warnings because there were too many)\n",