Thread (3 messages) 3 messages, 2 authors, 10d ago

Re: [PATCH v2] module: Extend module_blacklist parameter to built-in modules

From: sashiko-bot@kernel.org
Date: 2026-06-22 14:17:48

Thank you for your contribution! Sashiko AI review found 3 potential issue(s) to consider:
- [Critical] Accessing the .initcall.modnames array during loadable module initialization reads freed .init memory, causing a Use-After-Free.
- [High] Built-in module blacklisting silently bypasses or fails to compile under CONFIG_LTO_CLANG / CONFIG_CFI_CLANG due to function pointer mismatch.
- [Low] Kernel build fails when CONFIG_MODULES is disabled due to missing module_is_blacklisted() definition.
--

commit 5c29fcaa43d56c5e3cb5426f55d85a536519732f
Author: Aaron Tomlin [off-list ref]

module: Extend module_blacklist parameter to built-in modules

This patch extends the module_blacklist parameter to intercept and prevent
the initialization of built-in modules during system boot. It creates a
.initcall.modnames section mapping initcalls to module names, using 32-bit
relative offsets to preserve KASLR.

Link: https://lore.kernel.org/lkml/20260510061301.41341-1-atomlin@atomlin.com/ (local)
quoted hunk ↗ jump to hunk
diff --git a/include/linux/init.h b/include/linux/init.h
index 40331923b9f4a..212f64a07c739 100644
--- a/include/linux/init.h
+++ b/include/linux/init.h
[ ... ]
quoted hunk ↗ jump to hunk
@@ -270,9 +280,26 @@ extern struct module __this_module;
 		__initcall_stub(fn, __iid, id),			\
 		__initcall_name(initcall, __iid, id),		\
 		__initcall_section(__sec, __iid))
+#ifdef CONFIG_HAVE_ARCH_PREL32_RELOCATIONS
+#define ___define_initcall(fn, id, __sec)				\
+	__unique_initcall(fn, id, __sec, __initcall_id(fn));		\
+	asm(".pushsection \".initcall.modnames\", \"a\"\n"		\
+	    ".balign 4\n"						\
+	    ".long " #fn " - .\n"					\
[Severity: High]
When compiled with CONFIG_LTO_CLANG or CONFIG_CFI_CLANG, the kernel wraps
initcalls in an __initcall_stub function, and stores the stub's address in
the initcall array.

Since ___define_initcall explicitly stores the original function's address
here, will initcall_get_modname() fail to match the runtime CFI/LTO stub
address passed by do_one_initcall()?

Also, could using #fn in inline assembly for a static function renamed by
LTO cause an undefined reference link error?
+	    ".long __initcall_modstr_" #fn #id " - .\n"			\
+	    ".popsection\n"						\
+	    ".pushsection .init.rodata, \"a\"\n"			\
+	    "__initcall_modstr_" #fn #id ": .string \"" KBUILD_MODNAME "\"\n" \
+	    ".popsection\n");
[ ... ]
quoted hunk ↗ jump to hunk
diff --git a/include/linux/module.h b/include/linux/module.h
index d80c3ea574726..21668ef1430a5 100644
--- a/include/linux/module.h
+++ b/include/linux/module.h
@@ -754,6 +754,8 @@ void *dereference_module_function_descriptor(struct module *mod, void *ptr);
 int register_module_notifier(struct notifier_block *nb);
 int unregister_module_notifier(struct notifier_block *nb);
 
+extern bool module_is_blacklisted(const char *module_name);
[Severity: Low]
Does this cause a build failure when CONFIG_MODULES is disabled?

The function module_is_blacklisted() is defined in kernel/module/main.c,
but it is declared here unconditionally and called from do_one_initcall()
in init/main.c. If CONFIG_MODULES is disabled, could the linker fail with
an undefined reference?
+
 extern void print_modules(void);
[ ... ]
quoted hunk ↗ jump to hunk
diff --git a/init/main.c b/init/main.c
index b84818ad9685f..ce6d769b99e17 100644
--- a/init/main.c
+++ b/init/main.c
@@ -1365,12 +1365,39 @@ static inline void do_trace_initcall_level(const char *level)
 }
 #endif /* !TRACEPOINTS_ENABLED */
 
+extern struct initcall_modname __start_initcall_modnames[];
+extern struct initcall_modname __stop_initcall_modnames[];
+
+static const char *initcall_get_modname(initcall_t fn)
+{
+	struct initcall_modname *p;
+
+	for (p = __start_initcall_modnames; p < __stop_initcall_modnames; p++) {
+		if (initcall_from_entry(&p->initcall_fn) == fn) {
+#ifdef CONFIG_HAVE_ARCH_PREL32_RELOCATIONS
+			return (const char *)offset_to_ptr(&p->modname_offset);
+#else
+			return p->modname;
+#endif
+		}
+	}
+	return NULL;
+}
+
 int __init_or_module do_one_initcall(initcall_t fn)
 {
 	int count = preempt_count();
 	char msgbuf[64];
+	const char *modname;
 	int ret;
 
+	modname = initcall_get_modname(fn);
[Severity: Critical]
Is there a use-after-free risk here when loading dynamic modules?

The .initcall.modnames section is placed in INIT_DATA_SECTION, mapping it to
.init.data. Memory in the .init.* sections is freed by free_initmem() after
the system boots.

Since do_one_initcall() is marked __init_or_module, it is also called by
do_init_module() whenever a loadable module is initialized after boot:

do_init_module()
  do_one_initcall()
    initcall_get_modname()

Does this unconditionally iterate over the __start_initcall_modnames array
residing in the freed .init.data section?
+	if (modname && module_is_blacklisted(modname)) {
+		pr_info("Skipping initcall for blacklisted built-in module %s\n",
+			modname);
+		return 0;
+	}
+
 	if (initcall_blacklisted(fn))
 		return -EPERM;
-- 
Sashiko AI review · https://sashiko.dev/#/patchset/20260622140259.2974-1-atomlin@atomlin.com?part=1
Keyboard shortcuts
hback out one level
jnext message in thread
kprevious message in thread
ldrill in
Escclose help / fold thread tree
?toggle this help