On Sun, May 30, 2021 at 12:47PM +0800, Kuan-Ying Lee wrote:
> Add memory corruption identification at bug report for hardware tag-based
> mode. The report shows whether it is "use-after-free" or "out-of-bound"
> error instead of "invalid-access" error. This will make it easier for
> programmers to see the memory corruption problem.
>
> We extend the slab to store five old free pointer tag and free backtrace,
> we can check if the tagged address is in the slab record and make a good
> guess if the object is more like "use-after-free" or "out-of-bound".
> therefore every slab memory corruption can be identified whether it's
> "use-after-free" or "out-of-bound".
>
> Signed-off-by: Kuan-Ying Lee <kylee0686026@xxxxxxxxx>
On a whole this makes sense because SW_TAGS mode supports this, too.
My main complaints are the copy-paste of the SW_TAGS code.
Does it make sense to refactor per my suggestions below?
This is also a question to KASAN maintainers (Andrey, any preference?).
> ---
> lib/Kconfig.kasan | 8 ++++++++
> mm/kasan/hw_tags.c | 25 ++++++++++++++++++++++---
> mm/kasan/kasan.h | 4 ++--
> mm/kasan/report_hw_tags.c | 28 ++++++++++++++++++++++++++++
> 4 files changed, 60 insertions(+), 5 deletions(-)
>
> diff --git a/lib/Kconfig.kasan b/lib/Kconfig.kasan
> index cffc2ebbf185..f7e666b23058 100644
> --- a/lib/Kconfig.kasan
> +++ b/lib/Kconfig.kasan
> @@ -163,6 +163,14 @@ config KASAN_SW_TAGS_IDENTIFY
> (use-after-free or out-of-bounds) at the cost of increased
> memory consumption.
>
> +config KASAN_HW_TAGS_IDENTIFY
> + bool "Enable memory corruption identification"
> + depends on KASAN_HW_TAGS
> + help
> + This option enables best-effort identification of bug type
> + (use-after-free or out-of-bounds) at the cost of increased
> + memory consumption.
Can we rename KASAN_SW_TAGS_IDENTIFY -> KASAN_TAGS_IDENTIFY in a
separate patch and then use that?
Or do we have a problem renaming this options if there are existing
users of it?
> config KASAN_VMALLOC
> bool "Back mappings in vmalloc space with real shadow memory"
> depends on KASAN_GENERIC && HAVE_ARCH_KASAN_VMALLOC
> diff --git a/mm/kasan/hw_tags.c b/mm/kasan/hw_tags.c
> index 4004388b4e4b..b1c6bb116600 100644
> --- a/mm/kasan/hw_tags.c
> +++ b/mm/kasan/hw_tags.c
> @@ -220,22 +220,41 @@ void kasan_set_free_info(struct kmem_cache *cache,
> void *object, u8 tag)
> {
> struct kasan_alloc_meta *alloc_meta;
> + u8 idx = 0;
>
> alloc_meta = kasan_get_alloc_meta(cache, object);
> - if (alloc_meta)
> - kasan_set_track(&alloc_meta->free_track[0], GFP_NOWAIT);
> + if (!alloc_meta)
> + return;
> +
> +#ifdef CONFIG_KASAN_HW_TAGS_IDENTIFY
> + idx = alloc_meta->free_track_idx;
> + alloc_meta->free_pointer_tag[idx] = tag;
> + alloc_meta->free_track_idx = (idx + 1) % KASAN_NR_FREE_STACKS;
> +#endif
> +
> + kasan_set_track(&alloc_meta->free_track[idx], GFP_NOWAIT);
> }
>
> struct kasan_track *kasan_get_free_track(struct kmem_cache *cache,
> void *object, u8 tag)
> {
> struct kasan_alloc_meta *alloc_meta;
> + int i = 0;
>
> alloc_meta = kasan_get_alloc_meta(cache, object);
> if (!alloc_meta)
> return NULL;
>
> - return &alloc_meta->free_track[0];
> +#ifdef CONFIG_KASAN_HW_TAGS_IDENTIFY
> + for (i = 0; i < KASAN_NR_FREE_STACKS; i++) {
> + if (alloc_meta->free_pointer_tag[i] == tag)
> + break;
> + }
> + if (i == KASAN_NR_FREE_STACKS)
> + i = alloc_meta->free_track_idx;
> +#endif
> +
> + return &alloc_meta->free_track[i];
> }
Again, we now have code duplication. These functions are now identical
to the sw_tags.c ones?
Does it make sense to also move them in a preparatory patch to a new
'tags.c'?
> #if IS_ENABLED(CONFIG_KASAN_KUNIT_TEST)
> diff --git a/mm/kasan/kasan.h b/mm/kasan/kasan.h
> index 8f450bc28045..41b47f456130 100644
> --- a/mm/kasan/kasan.h
> +++ b/mm/kasan/kasan.h
> @@ -153,7 +153,7 @@ struct kasan_track {
> depot_stack_handle_t stack;
> };
>
> -#ifdef CONFIG_KASAN_SW_TAGS_IDENTIFY
> +#if defined(CONFIG_KASAN_SW_TAGS_IDENTIFY) || defined(CONFIG_KASAN_HW_TAGS_IDENTIFY)
> #define KASAN_NR_FREE_STACKS 5
> #else
> #define KASAN_NR_FREE_STACKS 1
> @@ -170,7 +170,7 @@ struct kasan_alloc_meta {
> #else
> struct kasan_track free_track[KASAN_NR_FREE_STACKS];
> #endif
> -#ifdef CONFIG_KASAN_SW_TAGS_IDENTIFY
> +#if defined(CONFIG_KASAN_SW_TAGS_IDENTIFY) || defined(CONFIG_KASAN_HW_TAGS_IDENTIFY)
> u8 free_pointer_tag[KASAN_NR_FREE_STACKS];
> u8 free_track_idx;
> #endif
> diff --git a/mm/kasan/report_hw_tags.c b/mm/kasan/report_hw_tags.c
> index 42b2168755d6..d77109b85a09 100644
> --- a/mm/kasan/report_hw_tags.c
> +++ b/mm/kasan/report_hw_tags.c
> @@ -14,9 +14,37 @@
> #include <linux/types.h>
>
> #include "kasan.h"
> +#include "../slab.h"
>
> const char *kasan_get_bug_type(struct kasan_access_info *info)
> {
> +#ifdef CONFIG_KASAN_HW_TAGS_IDENTIFY
> + struct kasan_alloc_meta *alloc_meta;
> + struct kmem_cache *cache;
> + struct page *page;
> + const void *addr;
> + void *object;
> + u8 tag;
> + int i;
> +
> + tag = get_tag(info->access_addr);
> + addr = kasan_reset_tag(info->access_addr);
> + page = kasan_addr_to_page(addr);
> + if (page && PageSlab(page)) {
> + cache = page->slab_cache;
> + object = nearest_obj(cache, page, (void *)addr);
> + alloc_meta = kasan_get_alloc_meta(cache, object);
> +
> + if (alloc_meta) {
> + for (i = 0; i < KASAN_NR_FREE_STACKS; i++) {
> + if (alloc_meta->free_pointer_tag[i] == tag)
> + return "use-after-free";
> + }
> + }
> + return "out-of-bounds";
> + }
> +
> +#endif
> return "invalid-access";
> }
This function is an almost copy-paste of what we have in
report_sw_tags.c. Does it make sense to try and share this code or would
it complicate things?
I imagine we could have a header report_tags.h, which defines a static
const char *kasan_try_get_bug_type(..), and simply returns NULL if it
couldn't identify it:
#if defined(CONFIG_KASAN_SW_TAGS_IDENTIFY) || defined(CONFIG_KASAN_HW_TAGS_IDENTIFY)
static const char *kasan_try_get_bug_type(struct kasan_access_info *info)
{
... the code above ...
return NULL;
}
#else
static const char *kasan_try_get_bug_type(struct kasan_access_info *info) { return NULL; }
#endif
Thanks,
-- Marco
