From mboxrd@z Thu Jan 1 00:00:00 1970 From: Andrea Parri Subject: Re: [PATCH] locking/xchg/alpha: Remove memory barriers from the _local() variants Date: Tue, 27 Feb 2018 21:08:31 +0100 Message-ID: <20180227200830.GA3164@andrea> References: <1519704058-13430-1-git-send-email-parri.andrea@gmail.com> Mime-Version: 1.0 Return-path: DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20161025; h=date:from:to:cc:subject:message-id:references:mime-version :content-disposition:in-reply-to:user-agent; bh=+WTrYJEubfdbZmcWnSF59XvStrPnkxhBbbkALSbgqqA=; b=bM3U5CxlkdBeCOa542EdvvpEmZ919XH4usCcSmjLUUp0czRFgkiJkXO1KFHUK6dFaY rVSSyoKTBe2laCxBnxsnUPguY0Y+3yN19BBZS58kbhDw3koMoFO7JetZconkAPH04oLF Jt73eccN+9egLB8ZPLCoBt4Xut095nr/cSlJ7JLkfj8YQ/mXG2oVENYfTMn+RNt+8nY+ w5dIc2t9ivdJNXwNdfrMWu1HkJ3uYXtwI5GHC6s6rp9HP7Xx2ELzqtCu7hRQKfAP4fA6 6Tty8wH4odX6GwgQNGDH1kiHu8EcbTzjny7o4hyEM9CHRLWti3Xz7oaBvSl2NNHwQXtL GrzQ== Content-Disposition: inline In-Reply-To: <1519704058-13430-1-git-send-email-parri.andrea@gmail.com> Sender: linux-kernel-owner@vger.kernel.org List-ID: Content-Type: text/plain; charset="us-ascii" Content-Transfer-Encoding: 7bit To: Ingo Molnar , Peter Zijlstra Cc: linux-kernel@vger.kernel.org, "Paul E . McKenney" , Alan Stern , Andrew Morton , Ivan Kokshaysky , Linus Torvalds , Matt Turner , Richard Henderson , Thomas Gleixner , linux-alpha@vger.kernel.org, will.deacon@arm.com [+ Will] I'm not sure how this happened; Will, you at least figure as Reported-by: ;-) Andrea On Tue, Feb 27, 2018 at 05:00:58AM +0100, Andrea Parri wrote: > Commits 79d442461df74 ("locking/xchg/alpha: Clean up barrier usage by using > smp_mb() in place of __ASM__MB") and 472e8c55cf662 ("locking/xchg/alpha: > Fix xchg() and cmpxchg() memory ordering bugs") ended up adding unnecessary > barriers to the _local variants, which the previous code took care to avoid. > > Fix them by adding the smp_mb() into the cmpxchg macro rather than into the > ____cmpxchg variants. > > Fixes: 79d442461df74 ("locking/xchg/alpha: Clean up barrier usage by using smp_mb() in place of __ASM__MB") > Fixes: 472e8c55cf662 ("locking/xchg/alpha: Fix xchg() and cmpxchg() memory ordering bugs") > Reported-by: Will Deacon > Signed-off-by: Andrea Parri > Cc: Paul E. McKenney > Cc: Alan Stern > Cc: Andrew Morton > Cc: Ivan Kokshaysky > Cc: Linus Torvalds > Cc: Matt Turner > Cc: Peter Zijlstra > Cc: Richard Henderson > Cc: Thomas Gleixner > Cc: linux-alpha@vger.kernel.org > --- > arch/alpha/include/asm/cmpxchg.h | 20 ++++++++++++++++---- > arch/alpha/include/asm/xchg.h | 27 --------------------------- > 2 files changed, 16 insertions(+), 31 deletions(-) > > diff --git a/arch/alpha/include/asm/cmpxchg.h b/arch/alpha/include/asm/cmpxchg.h > index 8a2b331e43feb..6c7c394524714 100644 > --- a/arch/alpha/include/asm/cmpxchg.h > +++ b/arch/alpha/include/asm/cmpxchg.h > @@ -38,19 +38,31 @@ > #define ____cmpxchg(type, args...) __cmpxchg ##type(args) > #include > > +/* > + * The leading and the trailing memory barriers guarantee that these > + * operations are fully ordered. > + */ > #define xchg(ptr, x) \ > ({ \ > + __typeof__(*(ptr)) __ret; \ > __typeof__(*(ptr)) _x_ = (x); \ > - (__typeof__(*(ptr))) __xchg((ptr), (unsigned long)_x_, \ > - sizeof(*(ptr))); \ > + smp_mb(); \ > + __ret = (__typeof__(*(ptr))) \ > + __xchg((ptr), (unsigned long)_x_, sizeof(*(ptr))); \ > + smp_mb(); \ > + __ret; \ > }) > > #define cmpxchg(ptr, o, n) \ > ({ \ > + __typeof__(*(ptr)) __ret; \ > __typeof__(*(ptr)) _o_ = (o); \ > __typeof__(*(ptr)) _n_ = (n); \ > - (__typeof__(*(ptr))) __cmpxchg((ptr), (unsigned long)_o_, \ > - (unsigned long)_n_, sizeof(*(ptr)));\ > + smp_mb(); \ > + __ret = (__typeof__(*(ptr))) __cmpxchg((ptr), \ > + (unsigned long)_o_, (unsigned long)_n_, sizeof(*(ptr)));\ > + smp_mb(); \ > + __ret; \ > }) > > #define cmpxchg64(ptr, o, n) \ > diff --git a/arch/alpha/include/asm/xchg.h b/arch/alpha/include/asm/xchg.h > index e2b59fac5257d..7adb80c6746ac 100644 > --- a/arch/alpha/include/asm/xchg.h > +++ b/arch/alpha/include/asm/xchg.h > @@ -12,10 +12,6 @@ > * Atomic exchange. > * Since it can be used to implement critical sections > * it must clobber "memory" (also for interrupts in UP). > - * > - * The leading and the trailing memory barriers guarantee that these > - * operations are fully ordered. > - * > */ > > static inline unsigned long > @@ -23,7 +19,6 @@ ____xchg(_u8, volatile char *m, unsigned long val) > { > unsigned long ret, tmp, addr64; > > - smp_mb(); > __asm__ __volatile__( > " andnot %4,7,%3\n" > " insbl %1,%4,%1\n" > @@ -38,7 +33,6 @@ ____xchg(_u8, volatile char *m, unsigned long val) > ".previous" > : "=&r" (ret), "=&r" (val), "=&r" (tmp), "=&r" (addr64) > : "r" ((long)m), "1" (val) : "memory"); > - smp_mb(); > > return ret; > } > @@ -48,7 +42,6 @@ ____xchg(_u16, volatile short *m, unsigned long val) > { > unsigned long ret, tmp, addr64; > > - smp_mb(); > __asm__ __volatile__( > " andnot %4,7,%3\n" > " inswl %1,%4,%1\n" > @@ -63,7 +56,6 @@ ____xchg(_u16, volatile short *m, unsigned long val) > ".previous" > : "=&r" (ret), "=&r" (val), "=&r" (tmp), "=&r" (addr64) > : "r" ((long)m), "1" (val) : "memory"); > - smp_mb(); > > return ret; > } > @@ -73,7 +65,6 @@ ____xchg(_u32, volatile int *m, unsigned long val) > { > unsigned long dummy; > > - smp_mb(); > __asm__ __volatile__( > "1: ldl_l %0,%4\n" > " bis $31,%3,%1\n" > @@ -84,7 +75,6 @@ ____xchg(_u32, volatile int *m, unsigned long val) > ".previous" > : "=&r" (val), "=&r" (dummy), "=m" (*m) > : "rI" (val), "m" (*m) : "memory"); > - smp_mb(); > > return val; > } > @@ -94,7 +84,6 @@ ____xchg(_u64, volatile long *m, unsigned long val) > { > unsigned long dummy; > > - smp_mb(); > __asm__ __volatile__( > "1: ldq_l %0,%4\n" > " bis $31,%3,%1\n" > @@ -105,7 +94,6 @@ ____xchg(_u64, volatile long *m, unsigned long val) > ".previous" > : "=&r" (val), "=&r" (dummy), "=m" (*m) > : "rI" (val), "m" (*m) : "memory"); > - smp_mb(); > > return val; > } > @@ -135,13 +123,6 @@ ____xchg(, volatile void *ptr, unsigned long x, int size) > * Atomic compare and exchange. Compare OLD with MEM, if identical, > * store NEW in MEM. Return the initial value in MEM. Success is > * indicated by comparing RETURN with OLD. > - * > - * The leading and the trailing memory barriers guarantee that these > - * operations are fully ordered. > - * > - * The trailing memory barrier is placed in SMP unconditionally, in > - * order to guarantee that dependency ordering is preserved when a > - * dependency is headed by an unsuccessful operation. > */ > > static inline unsigned long > @@ -149,7 +130,6 @@ ____cmpxchg(_u8, volatile char *m, unsigned char old, unsigned char new) > { > unsigned long prev, tmp, cmp, addr64; > > - smp_mb(); > __asm__ __volatile__( > " andnot %5,7,%4\n" > " insbl %1,%5,%1\n" > @@ -167,7 +147,6 @@ ____cmpxchg(_u8, volatile char *m, unsigned char old, unsigned char new) > ".previous" > : "=&r" (prev), "=&r" (new), "=&r" (tmp), "=&r" (cmp), "=&r" (addr64) > : "r" ((long)m), "Ir" (old), "1" (new) : "memory"); > - smp_mb(); > > return prev; > } > @@ -177,7 +156,6 @@ ____cmpxchg(_u16, volatile short *m, unsigned short old, unsigned short new) > { > unsigned long prev, tmp, cmp, addr64; > > - smp_mb(); > __asm__ __volatile__( > " andnot %5,7,%4\n" > " inswl %1,%5,%1\n" > @@ -195,7 +173,6 @@ ____cmpxchg(_u16, volatile short *m, unsigned short old, unsigned short new) > ".previous" > : "=&r" (prev), "=&r" (new), "=&r" (tmp), "=&r" (cmp), "=&r" (addr64) > : "r" ((long)m), "Ir" (old), "1" (new) : "memory"); > - smp_mb(); > > return prev; > } > @@ -205,7 +182,6 @@ ____cmpxchg(_u32, volatile int *m, int old, int new) > { > unsigned long prev, cmp; > > - smp_mb(); > __asm__ __volatile__( > "1: ldl_l %0,%5\n" > " cmpeq %0,%3,%1\n" > @@ -219,7 +195,6 @@ ____cmpxchg(_u32, volatile int *m, int old, int new) > ".previous" > : "=&r"(prev), "=&r"(cmp), "=m"(*m) > : "r"((long) old), "r"(new), "m"(*m) : "memory"); > - smp_mb(); > > return prev; > } > @@ -229,7 +204,6 @@ ____cmpxchg(_u64, volatile long *m, unsigned long old, unsigned long new) > { > unsigned long prev, cmp; > > - smp_mb(); > __asm__ __volatile__( > "1: ldq_l %0,%5\n" > " cmpeq %0,%3,%1\n" > @@ -243,7 +217,6 @@ ____cmpxchg(_u64, volatile long *m, unsigned long old, unsigned long new) > ".previous" > : "=&r"(prev), "=&r"(cmp), "=m"(*m) > : "r"((long) old), "r"(new), "m"(*m) : "memory"); > - smp_mb(); > > return prev; > } > -- > 2.7.4 >