linux-kernel - Re: [PATCH] arm64: fix unreachable code issue with cmpxchg

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives
Hash Suite: Windows password security audit tool. GUI, reports in PDF.
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20190910092324.GI9720@e119886-lin.cambridge.arm.com>
Date:   Tue, 10 Sep 2019 10:23:25 +0100
From:   Andrew Murray <andrew.murray@....com>
To:     Arnd Bergmann <arnd@...db.de>
Cc:     Catalin Marinas <catalin.marinas@....com>,
        Will Deacon <will@...nel.org>,
        Mark Rutland <mark.rutland@....com>,
        linux-arm-kernel@...ts.infradead.org, linux-kernel@...r.kernel.org,
        clang-built-linux@...glegroups.com
Subject: Re: [PATCH] arm64: fix unreachable code issue with cmpxchg

On Mon, Sep 09, 2019 at 10:21:35PM +0200, Arnd Bergmann wrote:
> On arm64 build with clang, sometimes the __cmpxchg_mb is not inlined
> when CONFIG_OPTIMIZE_INLINING is set.
> Clang then fails a compile-time assertion, because it cannot tell at
> compile time what the size of the argument is:
> 
> mm/memcontrol.o: In function `__cmpxchg_mb':
> memcontrol.c:(.text+0x1a4c): undefined reference to `__compiletime_assert_175'
> memcontrol.c:(.text+0x1a4c): relocation truncated to fit: R_AARCH64_CALL26 against undefined symbol `__compiletime_assert_175'
> 
> Mark all of the cmpxchg() style functions as __always_inline to
> ensure that the compiler can see the result.
> 
> Signed-off-by: Arnd Bergmann <arnd@...db.de>
> ---

I was able to reproduce this with the following:

$ git describe HEAD
next-20190904

$ clang --version
Android (5821526 based on r365631) clang version 9.0.6 (https://android.googlesource.com/toolchain/llvm-project 85305eaf1e90ff529d304abac8a979e1d967f0a2) (based on LLVM 9.0.6svn)
Target: x86_64-unknown-linux-gnu
Thread model: posix
InstalledDir: /home/andrewm/android-clang/clang-r365631/bin

$ make O=~/linux-build/ ARCH=arm64 CROSS_COMPILE=aarch64-linux-gnu- CC=clang -j56 allyesconfig Image

(I was unable to reproduce with defconfig+OPTIMIZE_INLINING).

However...

>  arch/arm64/include/asm/cmpxchg.h | 15 ++++++++-------
>  1 file changed, 8 insertions(+), 7 deletions(-)
> 
> diff --git a/arch/arm64/include/asm/cmpxchg.h b/arch/arm64/include/asm/cmpxchg.h
> index a1398f2f9994..fd64dc8a235f 100644
> --- a/arch/arm64/include/asm/cmpxchg.h
> +++ b/arch/arm64/include/asm/cmpxchg.h
> @@ -19,7 +19,7 @@
>   * acquire+release for the latter.
>   */
>  #define __XCHG_CASE(w, sfx, name, sz, mb, nop_lse, acq, acq_lse, rel, cl)	\
> -static inline u##sz __xchg_case_##name##sz(u##sz x, volatile void *ptr)		\
> +static __always_inline u##sz __xchg_case_##name##sz(u##sz x, volatile void *ptr)\

This hunk isn't needed, there is no BUILD_BUG here.


>  {										\
>  	u##sz ret;								\
>  	unsigned long tmp;							\
> @@ -62,7 +62,7 @@ __XCHG_CASE( ,  ,  mb_, 64, dmb ish, nop,  , a, l, "memory")
>  #undef __XCHG_CASE
>  
>  #define __XCHG_GEN(sfx)							\
> -static inline unsigned long __xchg##sfx(unsigned long x,		\
> +static __always_inline  unsigned long __xchg##sfx(unsigned long x,	\
>  					volatile void *ptr,		\
>  					int size)			\
>  {									\
> @@ -103,8 +103,9 @@ __XCHG_GEN(_mb)
>  #define arch_xchg_release(...)	__xchg_wrapper(_rel, __VA_ARGS__)
>  #define arch_xchg(...)		__xchg_wrapper( _mb, __VA_ARGS__)
>  
> -#define __CMPXCHG_CASE(name, sz)			\
> -static inline u##sz __cmpxchg_case_##name##sz(volatile void *ptr,	\
> +#define __CMPXCHG_CASE(name, sz)					\
> +static __always_inline u##sz 						\
> +__cmpxchg_case_##name##sz(volatile void *ptr,				\

This hunk isn't needed, there is no BUILD_BUG here.

>  					      u##sz old,		\
>  					      u##sz new)		\
>  {									\
> @@ -148,7 +149,7 @@ __CMPXCHG_DBL(_mb)
>  #undef __CMPXCHG_DBL
>  
>  #define __CMPXCHG_GEN(sfx)						\
> -static inline unsigned long __cmpxchg##sfx(volatile void *ptr,		\
> +static __always_inline unsigned long __cmpxchg##sfx(volatile void *ptr,	\
>  					   unsigned long old,		\
>  					   unsigned long new,		\
>  					   int size)			\
> @@ -230,7 +231,7 @@ __CMPXCHG_GEN(_mb)
>  })
>  
>  #define __CMPWAIT_CASE(w, sfx, sz)					\
> -static inline void __cmpwait_case_##sz(volatile void *ptr,		\
> +static __always_inline void __cmpwait_case_##sz(volatile void *ptr,	\
>  				       unsigned long val)		\

This hunk isn't needed, there is no BUILD_BUG here.

>  {									\
>  	unsigned long tmp;						\
> @@ -255,7 +256,7 @@ __CMPWAIT_CASE( ,  , 64);
>  #undef __CMPWAIT_CASE
>  
>  #define __CMPWAIT_GEN(sfx)						\
> -static inline void __cmpwait##sfx(volatile void *ptr,			\
> +static __always_inline void __cmpwait##sfx(volatile void *ptr,		\
>  				  unsigned long val,			\
>  				  int size)				\
>  {									\

Alternatively is it possible to replace the BUILD_BUG's with something else?

I think because we use BUILD_BUG at the end of a switch statement, we make
the assumption that size is known at compile time, for this reason we should
ensure the function containing the BUILD_BUG is __always_inline.

Looking across the kernel where BUILD_BUG is used as a default in a switch
statment ($ git grep -B 3 BUILD_BUG\( | grep default), most instances are
within macros, but many are found in an __always_inline function:

arch/x86/kvm/cpuid.h
mm/kasan/generic.c

Though some are not:

include/linux/signal.h
arch/arm64/include/asm/arm_dsu/pmu.h

I wonder if there may be a latent mole ready to whack with pmu.h?

Anyway with just the three remaining hunks:

Reviewed-by: Andrew Murray <andrew.murray@....com>
Tested-by: Andrew Murray <andrew.murray@....com>

> -- 
> 2.20.0
>