alpha: Override READ_ONCE() with barriered implementation

Rather then relying on the core code to use smp_read_barrier_depends()
as part of the READ_ONCE() definition, instead override __READ_ONCE()
in the Alpha code so that it generates the required mb() and then
implement smp_load_acquire() using the new macro to avoid redundant
back-to-back barriers from the generic implementation.

Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Paul E. McKenney <paulmck@kernel.org>
Signed-off-by: Will Deacon <will@kernel.org>

arch/alpha/include/asm/barrier.h

@@ -2,64 +2,15 @@
 #ifndef __BARRIER_H
 #define __BARRIER_H
 
-#include <asm/compiler.h>
-
 #define mb()	__asm__ __volatile__("mb": : :"memory")
 #define rmb()	__asm__ __volatile__("mb": : :"memory")
 #define wmb()	__asm__ __volatile__("wmb": : :"memory")
 
-/**
+#define __smp_load_acquire(p)						\
- * read_barrier_depends - Flush all pending reads that subsequents reads
+({									\
- * depend on.
+	compiletime_assert_atomic_type(*p);				\
- *
+	__READ_ONCE(*p);						\
- * No data-dependent reads from memory-like regions are ever reordered
+})
- * over this barrier.  All reads preceding this primitive are guaranteed
- * to access memory (but not necessarily other CPUs' caches) before any
- * reads following this primitive that depend on the data return by
- * any of the preceding reads.  This primitive is much lighter weight than
- * rmb() on most CPUs, and is never heavier weight than is
- * rmb().
- *
- * These ordering constraints are respected by both the local CPU
- * and the compiler.
- *
- * Ordering is not guaranteed by anything other than these primitives,
- * not even by data dependencies.  See the documentation for
- * memory_barrier() for examples and URLs to more information.
- *
- * For example, the following code would force ordering (the initial
- * value of "a" is zero, "b" is one, and "p" is "&a"):
- *
- * <programlisting>
- *	CPU 0				CPU 1
- *
- *	b = 2;
- *	memory_barrier();
- *	p = &b;				q = p;
- *					read_barrier_depends();
- *					d = *q;
- * </programlisting>
- *
- * because the read of "*q" depends on the read of "p" and these
- * two reads are separated by a read_barrier_depends().  However,
- * the following code, with the same initial values for "a" and "b":
- *
- * <programlisting>
- *	CPU 0				CPU 1
- *
- *	a = 2;
- *	memory_barrier();
- *	b = 3;				y = b;
- *					read_barrier_depends();
- *					x = a;
- * </programlisting>
- *
- * does not enforce ordering, since there is no data dependency between
- * the read of "a" and the read of "b".  Therefore, on some CPUs, such
- * as Alpha, "y" could be set to 3 and "x" to 0.  Use rmb()
- * in cases like this where there are no data dependencies.
- */
-#define read_barrier_depends() __asm__ __volatile__("mb": : :"memory")
 
 #ifdef CONFIG_SMP
 #define __ASM_SMP_MB	"\tmb\n"

arch/alpha/include/asm/rwonce.h

@@ -0,0 +1,35 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2019 Google LLC.
+ */
+#ifndef __ASM_RWONCE_H
+#define __ASM_RWONCE_H
+
+#ifdef CONFIG_SMP
+
+#include <asm/barrier.h>
+
+/*
+ * Alpha is apparently daft enough to reorder address-dependent loads
+ * on some CPU implementations. Knock some common sense into it with
+ * a memory barrier in READ_ONCE().
+ *
+ * For the curious, more information about this unusual reordering is
+ * available in chapter 15 of the "perfbook":
+ *
+ *  https://kernel.org/pub/linux/kernel/people/paulmck/perfbook/perfbook.html
+ *
+ */
+#define __READ_ONCE(x)							\
+({									\
+	__unqual_scalar_typeof(x) __x =					\
+		(*(volatile typeof(__x) *)(&(x)));			\
+	mb();								\
+	(typeof(x))__x;							\
+})
+
+#endif /* CONFIG_SMP */
+
+#include <asm-generic/rwonce.h>
+
+#endif /* __ASM_RWONCE_H */