Re: [PATCH] MIPS: Compare __SYNC_loongson3_war against 0

From: Nick Desaulniers
Date: Thu Jan 14 2021 - 12:50:05 EST


On Thu, Jan 14, 2021 at 9:34 AM Nathan Chancellor
<natechancellor@xxxxxxxxx> wrote:
>
> When building with clang when CONFIG_CPU_LOONGSON3_WORKAROUNDS is
> enabled:
>
> In file included from lib/errseq.c:4:
> In file included from ./include/linux/atomic.h:7:
> ./arch/mips/include/asm/atomic.h:52:1: warning: converting the result of
> '<<' to a boolean always evaluates to true
> [-Wtautological-constant-compare]
> ATOMIC_OPS(atomic64, s64)
> ^
> ./arch/mips/include/asm/atomic.h:40:9: note: expanded from macro
> 'ATOMIC_OPS'
> return cmpxchg(&v->counter, o, n);
> ^
> ./arch/mips/include/asm/cmpxchg.h:194:7: note: expanded from macro
> 'cmpxchg'
> if (!__SYNC_loongson3_war)
> ^
> ./arch/mips/include/asm/sync.h:147:34: note: expanded from macro
> '__SYNC_loongson3_war'
> # define __SYNC_loongson3_war (1 << 31)
> ^
>
> While it is not wrong that the result of this shift is always true in a
> boolean context, it is not a problem here. Regardless, the warning is
> really noisy so rather than making the shift a boolean implicitly, use
> it in an equality comparison so the shift is used as an integer value.
>
> Fixes: 4d1dbfe6cbec ("MIPS: atomic: Emit Loongson3 sync workarounds within asm")
> Fixes: a91f2a1dba44 ("MIPS: cmpxchg: Omit redundant barriers for Loongson3")
> Reported-by: kernel test robot <lkp@xxxxxxxxx>
> Signed-off-by: Nathan Chancellor <natechancellor@xxxxxxxxx>

Acked-by: Nick Desaulniers <ndesaulniers@xxxxxxxxxx>

> ---
> arch/mips/include/asm/atomic.h | 2 +-
> arch/mips/include/asm/cmpxchg.h | 6 +++---
> 2 files changed, 4 insertions(+), 4 deletions(-)
>
> diff --git a/arch/mips/include/asm/atomic.h b/arch/mips/include/asm/atomic.h
> index f904084fcb1f..27ad76791539 100644
> --- a/arch/mips/include/asm/atomic.h
> +++ b/arch/mips/include/asm/atomic.h
> @@ -248,7 +248,7 @@ static __inline__ int pfx##_sub_if_positive(type i, pfx##_t * v) \
> * bltz that can branch to code outside of the LL/SC loop. As \
> * such, we don't need to emit another barrier here. \
> */ \
> - if (!__SYNC_loongson3_war) \
> + if (__SYNC_loongson3_war == 0) \
> smp_mb__after_atomic(); \
> \
> return result; \
> diff --git a/arch/mips/include/asm/cmpxchg.h b/arch/mips/include/asm/cmpxchg.h
> index 5b0b3a6777ea..ed8f3f3c4304 100644
> --- a/arch/mips/include/asm/cmpxchg.h
> +++ b/arch/mips/include/asm/cmpxchg.h
> @@ -99,7 +99,7 @@ unsigned long __xchg(volatile void *ptr, unsigned long x, int size)
> * contains a completion barrier prior to the LL, so we don't \
> * need to emit an extra one here. \
> */ \
> - if (!__SYNC_loongson3_war) \
> + if (__SYNC_loongson3_war == 0) \
> smp_mb__before_llsc(); \
> \
> __res = (__typeof__(*(ptr))) \
> @@ -191,7 +191,7 @@ unsigned long __cmpxchg(volatile void *ptr, unsigned long old,
> * contains a completion barrier prior to the LL, so we don't \
> * need to emit an extra one here. \
> */ \
> - if (!__SYNC_loongson3_war) \
> + if (__SYNC_loongson3_war == 0) \
> smp_mb__before_llsc(); \
> \
> __res = cmpxchg_local((ptr), (old), (new)); \
> @@ -201,7 +201,7 @@ unsigned long __cmpxchg(volatile void *ptr, unsigned long old,
> * contains a completion barrier after the SC, so we don't \
> * need to emit an extra one here. \
> */ \
> - if (!__SYNC_loongson3_war) \
> + if (__SYNC_loongson3_war == 0) \
> smp_llsc_mb(); \
> \
> __res; \
>
> base-commit: 7c53f6b671f4aba70ff15e1b05148b10d58c2837

^ is this "base-commit" something you manually added, or can git
format generate that?

--
Thanks,
~Nick Desaulniers