The current "rodata=off" parameter disables read-only kernel mappings
under CONFIG_DEBUG_RODATA:
commit d2aa1acad22f ("mm/init: Add 'rodata=off' boot cmdline parameter
to disable read-only kernel mappings")
This patch is a logical extension to module mappings ie. read-only mappings
at module loading can be disabled even if CONFIG_DEBUG_SET_MODULE_RONX
(mainly for debug use). Please note, however, that it only affects RO/RW
permissions, keeping NX set.
This is the first step to make CONFIG_DEBUG_SET_MODULE_RONX mandatory
(always-on) in the future as CONFIG_DEBUG_RODATA on x86 and arm64.
Suggested-by: and Acked-by: Mark Rutland <[email protected]>
Signed-off-by: AKASHI Takahiro <[email protected]>
Reviewed-by: Kees Cook <[email protected]>
Cc: Rusty Russell <[email protected]>
Cc: Jessica Yu <[email protected]>
---
v3:
* merge if-statements in disable_ro_nx()
v2:
* use CONFIG_DEBUG_RODATA/SET_MODULE_RONX guards better where appropriate
* make "rodata_enabled" variable as __ro_after_init
v1:
* remove RFC's "module_ronx=" and merge it with "rodata="
* always keep NX set if CONFIG_SET_MODULE_RONX
include/linux/init.h | 3 +++
init/main.c | 7 +++++--
kernel/module.c | 20 +++++++++++++++++---
3 files changed, 25 insertions(+), 5 deletions(-)
diff --git a/include/linux/init.h b/include/linux/init.h
index e30104c..885c3e6 100644
--- a/include/linux/init.h
+++ b/include/linux/init.h
@@ -126,6 +126,9 @@ void prepare_namespace(void);
void __init load_default_modules(void);
int __init init_rootfs(void);
+#if defined(CONFIG_DEBUG_RODATA) || defined(CONFIG_DEBUG_SET_MODULE_RONX)
+extern bool rodata_enabled;
+#endif
#ifdef CONFIG_DEBUG_RODATA
void mark_rodata_ro(void);
#endif
diff --git a/init/main.c b/init/main.c
index 2858be7..959a242 100644
--- a/init/main.c
+++ b/init/main.c
@@ -81,6 +81,7 @@
#include <linux/integrity.h>
#include <linux/proc_ns.h>
#include <linux/io.h>
+#include <linux/cache.h>
#include <asm/io.h>
#include <asm/bugs.h>
@@ -914,14 +915,16 @@ static int try_to_run_init_process(const char *init_filename)
static noinline void __init kernel_init_freeable(void);
-#ifdef CONFIG_DEBUG_RODATA
-static bool rodata_enabled = true;
+#if defined(CONFIG_DEBUG_RODATA) || defined(CONFIG_SET_MODULE_RONX)
+bool rodata_enabled __ro_after_init = true;
static int __init set_debug_rodata(char *str)
{
return strtobool(str, &rodata_enabled);
}
__setup("rodata=", set_debug_rodata);
+#endif
+#ifdef CONFIG_DEBUG_RODATA
static void mark_readonly(void)
{
if (rodata_enabled)
diff --git a/kernel/module.c b/kernel/module.c
index f57dd63..6ad4b3f 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -1910,6 +1910,9 @@ static void frob_writable_data(const struct module_layout *layout,
/* livepatching wants to disable read-only so it can frob module. */
void module_disable_ro(const struct module *mod)
{
+ if (!rodata_enabled)
+ return;
+
frob_text(&mod->core_layout, set_memory_rw);
frob_rodata(&mod->core_layout, set_memory_rw);
frob_ro_after_init(&mod->core_layout, set_memory_rw);
@@ -1919,6 +1922,9 @@ void module_disable_ro(const struct module *mod)
void module_enable_ro(const struct module *mod, bool after_init)
{
+ if (!rodata_enabled)
+ return;
+
frob_text(&mod->core_layout, set_memory_ro);
frob_rodata(&mod->core_layout, set_memory_ro);
frob_text(&mod->init_layout, set_memory_ro);
@@ -1951,6 +1957,9 @@ void set_all_modules_text_rw(void)
{
struct module *mod;
+ if (!rodata_enabled)
+ return;
+
mutex_lock(&module_mutex);
list_for_each_entry_rcu(mod, &modules, list) {
if (mod->state == MODULE_STATE_UNFORMED)
@@ -1967,6 +1976,9 @@ void set_all_modules_text_ro(void)
{
struct module *mod;
+ if (!rodata_enabled)
+ return;
+
mutex_lock(&module_mutex);
list_for_each_entry_rcu(mod, &modules, list) {
if (mod->state == MODULE_STATE_UNFORMED)
@@ -1980,10 +1992,12 @@ void set_all_modules_text_ro(void)
static void disable_ro_nx(const struct module_layout *layout)
{
- frob_text(layout, set_memory_rw);
- frob_rodata(layout, set_memory_rw);
+ if (rodata_enabled) {
+ frob_text(layout, set_memory_rw);
+ frob_rodata(layout, set_memory_rw);
+ frob_ro_after_init(layout, set_memory_rw);
+ }
frob_rodata(layout, set_memory_x);
- frob_ro_after_init(layout, set_memory_rw);
frob_ro_after_init(layout, set_memory_x);
frob_writable_data(layout, set_memory_x);
}
--
2.10.0
+++ AKASHI Takahiro [14/11/16 15:15 +0900]:
>The current "rodata=off" parameter disables read-only kernel mappings
>under CONFIG_DEBUG_RODATA:
> commit d2aa1acad22f ("mm/init: Add 'rodata=off' boot cmdline parameter
> to disable read-only kernel mappings")
>
>This patch is a logical extension to module mappings ie. read-only mappings
>at module loading can be disabled even if CONFIG_DEBUG_SET_MODULE_RONX
>(mainly for debug use). Please note, however, that it only affects RO/RW
>permissions, keeping NX set.
>
>This is the first step to make CONFIG_DEBUG_SET_MODULE_RONX mandatory
>(always-on) in the future as CONFIG_DEBUG_RODATA on x86 and arm64.
>
>Suggested-by: and Acked-by: Mark Rutland <[email protected]>
>Signed-off-by: AKASHI Takahiro <[email protected]>
>Reviewed-by: Kees Cook <[email protected]>
>Cc: Rusty Russell <[email protected]>
Hi Rusty, could I get an (n)ack for this patch? :-)
Thanks!
Jessica
Jessica Yu <[email protected]> writes:
> +++ AKASHI Takahiro [14/11/16 15:15 +0900]:
>>The current "rodata=off" parameter disables read-only kernel mappings
>>under CONFIG_DEBUG_RODATA:
>> commit d2aa1acad22f ("mm/init: Add 'rodata=off' boot cmdline parameter
>> to disable read-only kernel mappings")
>>
>>This patch is a logical extension to module mappings ie. read-only mappings
>>at module loading can be disabled even if CONFIG_DEBUG_SET_MODULE_RONX
>>(mainly for debug use). Please note, however, that it only affects RO/RW
>>permissions, keeping NX set.
>>
>>This is the first step to make CONFIG_DEBUG_SET_MODULE_RONX mandatory
>>(always-on) in the future as CONFIG_DEBUG_RODATA on x86 and arm64.
>>
>>Suggested-by: and Acked-by: Mark Rutland <[email protected]>
>>Signed-off-by: AKASHI Takahiro <[email protected]>
>>Reviewed-by: Kees Cook <[email protected]>
>>Cc: Rusty Russell <[email protected]>
>
> Hi Rusty, could I get an (n)ack for this patch? :-)
Acked-by: Rusty Russell <[email protected]>
Cheers,
Rusty.
Hi Akashi,
your patch "module: extend 'rodata=off' boot cmdline parameter to module
mappings" showed up in linux-next today, and I noticed a small error in it.
The first modified #ifdef is fine, the second one, however, has a spelling
mistake in it: the CONFIG_ variable should be CONFIG_DEBUG_SET_MODULE_RONX
instead of CONFIG_SET_MODULE_RONX (note the missing DEBUG).
I noticed it by running 'scripts/checkkconfigsymbols -f --force -f
next-20161124..next-20161128', which is essentialy diffing the last two
linux-next releases and looks for undefined/unknown Kconfig symbols.
You can also run the script on single commits with -c to test them.
Best regards,
Andreas
On Mon, Nov 28, 2016 at 08:59:40AM +0100, Andreas Ziegler wrote:
> Hi Akashi,
>
> your patch "module: extend 'rodata=off' boot cmdline parameter to module
> mappings" showed up in linux-next today, and I noticed a small error in it.
>
> The first modified #ifdef is fine, the second one, however, has a spelling
> mistake in it: the CONFIG_ variable should be CONFIG_DEBUG_SET_MODULE_RONX
> instead of CONFIG_SET_MODULE_RONX (note the missing DEBUG).
Thank you for pointing this out.
(I didn't notice it because DEBUG_RODATA is always on on arm64.)
Rusty, Jessica, should I submit v4 to correct it?
-Takahiro AKASHI
> I noticed it by running 'scripts/checkkconfigsymbols -f --force -f
> next-20161124..next-20161128', which is essentialy diffing the last two
> linux-next releases and looks for undefined/unknown Kconfig symbols.
> You can also run the script on single commits with -c to test them.
>
> Best regards,
>
> Andreas
+++ AKASHI Takahiro [28/11/16 18:18 +0900]:
>On Mon, Nov 28, 2016 at 08:59:40AM +0100, Andreas Ziegler wrote:
>> Hi Akashi,
>>
>> your patch "module: extend 'rodata=off' boot cmdline parameter to module
>> mappings" showed up in linux-next today, and I noticed a small error in it.
>>
>> The first modified #ifdef is fine, the second one, however, has a spelling
>> mistake in it: the CONFIG_ variable should be CONFIG_DEBUG_SET_MODULE_RONX
>> instead of CONFIG_SET_MODULE_RONX (note the missing DEBUG).
>
>Thank you for pointing this out.
>(I didn't notice it because DEBUG_RODATA is always on on arm64.)
>
>Rusty, Jessica, should I submit v4 to correct it?
Andreas, Akashi -
The typo has been fixed with Arnd's patch:
http://lkml.kernel.org/r/[email protected]
Thanks for finding the issue!
Jessica