Date:   Fri, 9 Jun 2017 13:05:06 +0200
From:   Peter Zijlstra <peterz@...radead.org>
To:     Will Deacon <will.deacon@....com>,
        Paul McKenney <paulmck@...ux.vnet.ibm.com>,
        Boqun Feng <boqun.feng@...il.com>
Cc:     linux-kernel@...r.kernel.org, Ingo Molnar <mingo@...nel.org>,
        Thomas Gleixner <tglx@...utronix.de>, vgupta@...opsys.com,
        rkuo@...eaurora.org, james.hogan@...tec.com, jejb@...isc-linux.org,
        davem@...emloft.net, cmetcalf@...lanox.com
Subject: [RFC][PATCH] atomic: Fix atomic_set_release() for 'funny'
 architectures

On Fri, Jun 09, 2017 at 11:24:50AM +0200, Peter Zijlstra wrote:
> +Non RmW ops:
> +
> +The non-RmW ops are (typically) regular LOADs and STOREs and are canonically
> +implemented using READ_ONCE(), WRITE_ONCE(), smp_load_acquire() and
> +smp_store_release() respectively.
> +
> +The one detail to this is that atomic_set() should be observable to the RmW
> +ops. That is:
> +
> +  CPU0						CPU1
> +
> +  val = atomic_read(&X)
> +  do {
> +						atomic_set(&X, 0)
> +	new = val + 1;
> +  } while (!atomic_try_cmpxchg(&X, &val, new));
> +
> +Should cause the cmpxchg to *FAIL* (when @val != 0). This is typically true;
> +on 'normal' platforms; a regular competing STORE will invalidate a LL/SC.
> +
> +The obvious case where this is not so is where we need to implement atomic ops
> +with a spinlock hashtable; the typical solution is to then implement
> +atomic_set() with atomic_xchg().

---
Subject: atomic: Fix atomic_set_release() for 'funny' architectures

Those architectures that have a special atomic_set implementation also
need a special atomic_set_release(), because for the very same reason
WRITE_ONCE() is broken for them, smp_store_release() is too.

The vast majority is architectures that have spinlock hash based atomic
implementation except hexagon which seems to have a hardware 'feature'.

The spinlock based atomics should be SC, that is, none of them appear to
place extra barriers in atomic_cmpxchg() or any of the other SC atomic
primitives and therefore seem to rely on their spinlock implementation
being SC (I did not fully validate all that).

Therefore, the normal atomic_set() is SC and can be used at
atomic_set_release().

Cc: Vineet Gupta <vgupta@...opsys.com>
Cc: Richard Kuo <rkuo@...eaurora.org>
Cc: James Hogan <james.hogan@...tec.com>
Cc: "James E.J. Bottomley" <jejb@...isc-linux.org>
Cc: "David S. Miller" <davem@...emloft.net>
Cc: Chris Metcalf <cmetcalf@...lanox.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@...radead.org>
---
 arch/arc/include/asm/atomic.h         | 2 ++
 arch/hexagon/include/asm/atomic.h     | 2 ++
 arch/metag/include/asm/atomic_lock1.h | 2 ++
 arch/parisc/include/asm/atomic.h      | 2 ++
 arch/sparc/include/asm/atomic_32.h    | 2 ++
 arch/tile/include/asm/atomic_32.h     | 2 ++
 include/asm-generic/atomic64.h        | 2 ++
 7 files changed, 14 insertions(+)

diff --git a/arch/arc/include/asm/atomic.h b/arch/arc/include/asm/atomic.h
index 54b54da6384c..11859287c52a 100644
--- a/arch/arc/include/asm/atomic.h
+++ b/arch/arc/include/asm/atomic.h
@@ -123,6 +123,8 @@ static inline void atomic_set(atomic_t *v, int i)
 	atomic_ops_unlock(flags);
 }
 
+#define atomic_set_release(v, i)	atomic_set((v), (i))
+
 #endif
 
 /*
diff --git a/arch/hexagon/include/asm/atomic.h b/arch/hexagon/include/asm/atomic.h
index a62ba368b27d..fb3dfb2a667e 100644
--- a/arch/hexagon/include/asm/atomic.h
+++ b/arch/hexagon/include/asm/atomic.h
@@ -42,6 +42,8 @@ static inline void atomic_set(atomic_t *v, int new)
 	);
 }
 
+#define atomic_set_release(v, i)	atomic_set((v), (i))
+
 /**
  * atomic_read - reads a word, atomically
  * @v: pointer to atomic value
diff --git a/arch/metag/include/asm/atomic_lock1.h b/arch/metag/include/asm/atomic_lock1.h
index 6c1380a8a0d4..eee779f26cc4 100644
--- a/arch/metag/include/asm/atomic_lock1.h
+++ b/arch/metag/include/asm/atomic_lock1.h
@@ -37,6 +37,8 @@ static inline int atomic_set(atomic_t *v, int i)
 	return i;
 }
 
+#define atomic_set_release(v, i) atomic_set((v), (i))
+
 #define ATOMIC_OP(op, c_op)						\
 static inline void atomic_##op(int i, atomic_t *v)			\
 {									\
diff --git a/arch/parisc/include/asm/atomic.h b/arch/parisc/include/asm/atomic.h
index 5394b9c5f914..17b98a87e5e2 100644
--- a/arch/parisc/include/asm/atomic.h
+++ b/arch/parisc/include/asm/atomic.h
@@ -65,6 +65,8 @@ static __inline__ void atomic_set(atomic_t *v, int i)
 	_atomic_spin_unlock_irqrestore(v, flags);
 }
 
+#define atomic_set_release(v, i)	atomic_set((v), (i))
+
 static __inline__ int atomic_read(const atomic_t *v)
 {
 	return READ_ONCE((v)->counter);
diff --git a/arch/sparc/include/asm/atomic_32.h b/arch/sparc/include/asm/atomic_32.h
index ee3f11c43cda..7643e979e333 100644
--- a/arch/sparc/include/asm/atomic_32.h
+++ b/arch/sparc/include/asm/atomic_32.h
@@ -29,6 +29,8 @@ int atomic_xchg(atomic_t *, int);
 int __atomic_add_unless(atomic_t *, int, int);
 void atomic_set(atomic_t *, int);
 
+#define atomic_set_release(v, i)	atomic_set((v), (i))
+
 #define atomic_read(v)          ACCESS_ONCE((v)->counter)
 
 #define atomic_add(i, v)	((void)atomic_add_return( (int)(i), (v)))
diff --git a/arch/tile/include/asm/atomic_32.h b/arch/tile/include/asm/atomic_32.h
index a93774255136..53a423e7cb92 100644
--- a/arch/tile/include/asm/atomic_32.h
+++ b/arch/tile/include/asm/atomic_32.h
@@ -101,6 +101,8 @@ static inline void atomic_set(atomic_t *v, int n)
 	_atomic_xchg(&v->counter, n);
 }
 
+#define atomic_set_release(v, i)	atomic_set((v), (i))
+
 /* A 64bit atomic type */
 
 typedef struct {
diff --git a/include/asm-generic/atomic64.h b/include/asm-generic/atomic64.h
index dad68bf46c77..8d28eb010d0d 100644
--- a/include/asm-generic/atomic64.h
+++ b/include/asm-generic/atomic64.h
@@ -21,6 +21,8 @@ typedef struct {
 extern long long atomic64_read(const atomic64_t *v);
 extern void	 atomic64_set(atomic64_t *v, long long i);
 
+#define atomic64_set_release(v, i)	atomic64_set((v), (i))
+
 #define ATOMIC64_OP(op)							\
 extern void	 atomic64_##op(long long a, atomic64_t *v);
 

Powered by blists - more mailing lists