This patch implements the __smp_store_release and __smp_load_acquire barriers using ordered stores
and loads. This avoids the sync instruction present in the generic implementation.
Lightly tested on c8000 and rp3440.
Signed-off-by: Dave Anglin <dave.anglin@xxxxxxxx>
---
diff --git a/arch/parisc/include/asm/barrier.h b/arch/parisc/include/asm/barrier.h
index dbaaca84f27f..a8e0d942c297 100644
--- a/arch/parisc/include/asm/barrier.h
+++ b/arch/parisc/include/asm/barrier.h
@@ -26,6 +26,118 @@
#define __smp_rmb() mb()
#define __smp_wmb() mb()
+#ifdef CONFIG_64BIT
+#define __smp_store_release(p, v) \
+do { \
+ typeof(p) __p = (p); \
+ union { typeof(*p) __val; char __c[1]; } __u = \
+ { .__val = (__force typeof(*p)) (v) }; \
+ compiletime_assert_atomic_type(*p); \
+ switch (sizeof(*p)) { \
+ case 1: \
+ asm volatile("stb,ma %0,0(%1)" \
+ : : "r"(*(__u8 *)__u.__c), "r"(__p) \
+ : "memory"); \
+ break; \
+ case 2: \
+ asm volatile("sth,ma %0,0(%1)" \
+ : : "r"(*(__u16 *)__u.__c), "r"(__p) \
+ : "memory"); \
+ break; \
+ case 4: \
+ asm volatile("stw,ma %0,0(%1)" \
+ : : "r"(*(__u32 *)__u.__c), "r"(__p) \
+ : "memory"); \
+ break; \
+ case 8: \
+ asm volatile("std,ma %0,0(%1)" \
+ : : "r"(*(__u64 *)__u.__c), "r"(__p) \
+ : "memory"); \
+ break; \
+ } \
+} while (0)
+
+#define __smp_load_acquire(p) \
+({ \
+ union { typeof(*p) __val; char __c[1]; } __u; \
+ typeof(p) __p = (p); \
+ compiletime_assert_atomic_type(*p); \
+ switch (sizeof(*p)) { \
+ case 1: \
+ asm volatile("ldb,ma 0(%1),%0" \
+ : "=r"(*(__u8 *)__u.__c) : "r"(__p) \
+ : "memory"); \
+ break; \
+ case 2: \
+ asm volatile("ldh,ma 0(%1),%0" \
+ : "=r"(*(__u16 *)__u.__c) : "r"(__p) \
+ : "memory"); \
+ break; \
+ case 4: \
+ asm volatile("ldw,ma 0(%1),%0" \
+ : "=r"(*(__u32 *)__u.__c) : "r"(__p) \
+ : "memory"); \
+ break; \
+ case 8: \
+ asm volatile("ldd,ma 0(%1),%0" \
+ : "=r"(*(__u64 *)__u.__c) : "r"(__p) \
+ : "memory"); \
+ break; \
+ } \
+ __u.__val; \
+})
+#else
+#define __smp_store_release(p, v) \
+do { \
+ typeof(p) __p = (p); \
+ union { typeof(*p) __val; char __c[1]; } __u = \
+ { .__val = (__force typeof(*p)) (v) }; \
+ compiletime_assert_atomic_type(*p); \
+ switch (sizeof(*p)) { \
+ case 1: \
+ asm volatile("stb,ma %0,0(%1)" \
+ : : "r"(*(__u8 *)__u.__c), "r"(__p) \
+ : "memory"); \
+ break; \
+ case 2: \
+ asm volatile("sth,ma %0,0(%1)" \
+ : : "r"(*(__u16 *)__u.__c), "r"(__p) \
+ : "memory"); \
+ break; \
+ case 4: \
+ asm volatile("stw,ma %0,0(%1)" \
+ : : "r"(*(__u32 *)__u.__c), "r"(__p) \
+ : "memory"); \
+ break; \
+ } \
+} while (0)
+
+#define __smp_load_acquire(p) \
+({ \
+ union { typeof(*p) __val; char __c[1]; } __u; \
+ typeof(p) __p = (p); \
+ compiletime_assert_atomic_type(*p); \
+ switch (sizeof(*p)) { \
+ case 1: \
+ asm volatile("ldb,ma 0(%1),%0" \
+ : "=r"(*(__u8 *)__u.__c) : "r"(__p) \
+ : "memory"); \
+ break; \
+ case 2: \
+ asm volatile("ldh,ma 0(%1),%0" \
+ : "=r"(*(__u16 *)__u.__c) : "r"(__p) \
+ : "memory"); \
+ break; \
+ case 4: \
+ asm volatile("ldw,ma 0(%1),%0" \
+ : "=r"(*(__u32 *)__u.__c) : "r"(__p) \
+ : "memory"); \
+ break; \
+ } \
+ __u.__val; \
+})
+#endif
+
#include <asm-generic/barrier.h>
#endif /* !__ASSEMBLY__ */
