diff options
Diffstat (limited to 'arch/alpha')
| -rw-r--r-- | arch/alpha/include/asm/atomic.h | 16 | ||||
| -rw-r--r-- | arch/alpha/include/asm/barrier.h | 59 | ||||
| -rw-r--r-- | arch/alpha/include/asm/pgtable.h | 10 | ||||
| -rw-r--r-- | arch/alpha/include/asm/rwonce.h | 35 |
4 files changed, 53 insertions, 67 deletions
diff --git a/arch/alpha/include/asm/atomic.h b/arch/alpha/include/asm/atomic.h index e2093994fd0d..e41c113c6688 100644 --- a/arch/alpha/include/asm/atomic.h +++ b/arch/alpha/include/asm/atomic.h @@ -16,10 +16,10 @@ /* * To ensure dependency ordering is preserved for the _relaxed and - * _release atomics, an smp_read_barrier_depends() is unconditionally - * inserted into the _relaxed variants, which are used to build the - * barriered versions. Avoid redundant back-to-back fences in the - * _acquire and _fence versions. + * _release atomics, an smp_mb() is unconditionally inserted into the + * _relaxed variants, which are used to build the barriered versions. + * Avoid redundant back-to-back fences in the _acquire and _fence + * versions. */ #define __atomic_acquire_fence() #define __atomic_post_full_fence() @@ -69,7 +69,7 @@ static inline int atomic_##op##_return_relaxed(int i, atomic_t *v) \ ".previous" \ :"=&r" (temp), "=m" (v->counter), "=&r" (result) \ :"Ir" (i), "m" (v->counter) : "memory"); \ - smp_read_barrier_depends(); \ + smp_mb(); \ return result; \ } @@ -87,7 +87,7 @@ static inline int atomic_fetch_##op##_relaxed(int i, atomic_t *v) \ ".previous" \ :"=&r" (temp), "=m" (v->counter), "=&r" (result) \ :"Ir" (i), "m" (v->counter) : "memory"); \ - smp_read_barrier_depends(); \ + smp_mb(); \ return result; \ } @@ -122,7 +122,7 @@ static __inline__ s64 atomic64_##op##_return_relaxed(s64 i, atomic64_t * v) \ ".previous" \ :"=&r" (temp), "=m" (v->counter), "=&r" (result) \ :"Ir" (i), "m" (v->counter) : "memory"); \ - smp_read_barrier_depends(); \ + smp_mb(); \ return result; \ } @@ -140,7 +140,7 @@ static __inline__ s64 atomic64_fetch_##op##_relaxed(s64 i, atomic64_t * v) \ ".previous" \ :"=&r" (temp), "=m" (v->counter), "=&r" (result) \ :"Ir" (i), "m" (v->counter) : "memory"); \ - smp_read_barrier_depends(); \ + smp_mb(); \ return result; \ } diff --git a/arch/alpha/include/asm/barrier.h b/arch/alpha/include/asm/barrier.h index 92ec486a4f9e..c56bfffc9918 100644 --- a/arch/alpha/include/asm/barrier.h +++ b/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") -/** - * read_barrier_depends - Flush all pending reads that subsequents reads - * depend on. - * - * 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") +#define __smp_load_acquire(p) \ +({ \ + compiletime_assert_atomic_type(*p); \ + __READ_ONCE(*p); \ +}) #ifdef CONFIG_SMP #define __ASM_SMP_MB "\tmb\n" diff --git a/arch/alpha/include/asm/pgtable.h b/arch/alpha/include/asm/pgtable.h index 162c17b2631f..660b14ce1317 100644 --- a/arch/alpha/include/asm/pgtable.h +++ b/arch/alpha/include/asm/pgtable.h @@ -277,9 +277,9 @@ extern inline pte_t pte_mkdirty(pte_t pte) { pte_val(pte) |= __DIRTY_BITS; retur extern inline pte_t pte_mkyoung(pte_t pte) { pte_val(pte) |= __ACCESS_BITS; return pte; } /* - * The smp_read_barrier_depends() in the following functions are required to - * order the load of *dir (the pointer in the top level page table) with any - * subsequent load of the returned pmd_t *ret (ret is data dependent on *dir). + * The smp_rmb() in the following functions are required to order the load of + * *dir (the pointer in the top level page table) with any subsequent load of + * the returned pmd_t *ret (ret is data dependent on *dir). * * If this ordering is not enforced, the CPU might load an older value of * *ret, which may be uninitialized data. See mm/memory.c:__pte_alloc for @@ -293,7 +293,7 @@ extern inline pte_t pte_mkyoung(pte_t pte) { pte_val(pte) |= __ACCESS_BITS; retu extern inline pmd_t * pmd_offset(pud_t * dir, unsigned long address) { pmd_t *ret = (pmd_t *) pud_page_vaddr(*dir) + ((address >> PMD_SHIFT) & (PTRS_PER_PAGE - 1)); - smp_read_barrier_depends(); /* see above */ + smp_rmb(); /* see above */ return ret; } #define pmd_offset pmd_offset @@ -303,7 +303,7 @@ extern inline pte_t * pte_offset_kernel(pmd_t * dir, unsigned long address) { pte_t *ret = (pte_t *) pmd_page_vaddr(*dir) + ((address >> PAGE_SHIFT) & (PTRS_PER_PAGE - 1)); - smp_read_barrier_depends(); /* see above */ + smp_rmb(); /* see above */ return ret; } #define pte_offset_kernel pte_offset_kernel diff --git a/arch/alpha/include/asm/rwonce.h b/arch/alpha/include/asm/rwonce.h new file mode 100644 index 000000000000..35542bcf92b3 --- /dev/null +++ b/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 */ |