On Mon, Feb 01, 2021 at 08:43PM +0100, Andrey Konovalov wrote:
> Mark all static functions in common.c and kasan.h that are used for
> hardware tag-based KASAN as __always_inline to avoid unnecessary
> function calls.
>
> Signed-off-by: Andrey Konovalov <[email protected]>
Does objtool complain about any of these?
I'm not sure this is unconditionally a good idea. If there isn't a
quantifiable performance bug or case where we cannot call a function,
perhaps we can just let the compiler decide?
More comments below.
> ---
> mm/kasan/common.c | 13 +++++++------
> mm/kasan/kasan.h | 6 +++---
> 2 files changed, 10 insertions(+), 9 deletions(-)
>
> diff --git a/mm/kasan/common.c b/mm/kasan/common.c
> index 5691cca69397..2004ecd6e43c 100644
> --- a/mm/kasan/common.c
> +++ b/mm/kasan/common.c
> @@ -279,7 +279,8 @@ void __kasan_poison_object_data(struct kmem_cache *cache,
> void *object)
> * based on objects indexes, so that objects that are next to each other
> * get different tags.
> */
> -static u8 assign_tag(struct kmem_cache *cache, const void *object, bool init)
> +static __always_inline u8 assign_tag(struct kmem_cache *cache,
> + const void *object, bool init)
This function might be small enough that it's fine.
> {
> if (IS_ENABLED(CONFIG_KASAN_GENERIC))
> return 0xff;
> @@ -321,8 +322,8 @@ void * __must_check __kasan_init_slab_obj(struct
> kmem_cache *cache,
> return (void *)object;
> }
>
> -static bool ____kasan_slab_free(struct kmem_cache *cache, void *object,
> - unsigned long ip, bool quarantine)
> +static __always_inline bool ____kasan_slab_free(struct kmem_cache *cache,
> + void *object, unsigned long ip, bool quarantine)
> {
Because ____kasan_slab_free() is tail-called by __kasan_slab_free() and
__kasan_slab_free_mempool(), there should never be a call (and if there
is we need to figure out why). The additional code-bloat and I-cache
pressure might be worse vs. just a jump. I'd let the compiler decide.
> u8 tag;
> void *tagged_object;
> @@ -366,7 +367,7 @@ bool __kasan_slab_free(struct kmem_cache *cache, void
> *object, unsigned long ip)
> return ____kasan_slab_free(cache, object, ip, true);
> }
>
> -static bool ____kasan_kfree_large(void *ptr, unsigned long ip)
> +static __always_inline bool ____kasan_kfree_large(void *ptr, unsigned long
> ip)
> {
This one is tail-called by __kasan_kfree_large(). The usage in
__kasan_slab_free_mempool() is in an unlikely branch.
> if (ptr != page_address(virt_to_head_page(ptr))) {
> kasan_report_invalid_free(ptr, ip);
> @@ -461,8 +462,8 @@ void * __must_check __kasan_slab_alloc(struct kmem_cache
> *cache,
> return tagged_object;
> }
>
> -static void *____kasan_kmalloc(struct kmem_cache *cache, const void *object,
> - size_t size, gfp_t flags)
> +static __always_inline void *____kasan_kmalloc(struct kmem_cache *cache,
> + const void *object, size_t size, gfp_t flags)
> {
Also only tail-called.
> unsigned long redzone_start;
> unsigned long redzone_end;
> diff --git a/mm/kasan/kasan.h b/mm/kasan/kasan.h
> index 2f7400a3412f..d5fe72747a53 100644
> --- a/mm/kasan/kasan.h
> +++ b/mm/kasan/kasan.h
> @@ -321,7 +321,7 @@ static inline u8 kasan_random_tag(void) { return 0; }
>
> #ifdef CONFIG_KASAN_HW_TAGS
>
> -static inline void kasan_poison(const void *addr, size_t size, u8 value)
> +static __always_inline void kasan_poison(const void *addr, size_t size, u8
> value)
> {
> addr = kasan_reset_tag(addr);
>
> @@ -337,7 +337,7 @@ static inline void kasan_poison(const void *addr, size_t
> size, u8 value)
> hw_set_mem_tag_range((void *)addr, size, value);
> }
>
> -static inline void kasan_unpoison(const void *addr, size_t size)
> +static __always_inline void kasan_unpoison(const void *addr, size_t size)
> {
Not sure about these 2. They should be small, but it's hard to say what
is ideal on which architecture.
> u8 tag = get_tag(addr);
>
> @@ -354,7 +354,7 @@ static inline void kasan_unpoison(const void *addr,
> size_t size)
> hw_set_mem_tag_range((void *)addr, size, tag);
> }
>
> -static inline bool kasan_byte_accessible(const void *addr)
> +static __always_inline bool kasan_byte_accessible(const void *addr)
This function feels like a macro and if the compiler uninlined it, we
could argue it's a bug. But not sure if we need the __always_inline,
unless you've seen this uninlined.
> {
> u8 ptr_tag = get_tag(addr);
> u8 mem_tag = hw_get_mem_tag((void *)addr);
> --
> 2.30.0.365.g02bc693789-goog
>
