efDataPreprocessing memoryCall.h 李海忠 commit at 2020-09-15

efDataPreprocessing/dataSharedMemory/memoryCall.h

@@ -23,3 +23,202 @@
 
 /*
  * On ARM, ordinary assignment (str instruction) doesn't clear the local
+ * strex/ldrex monitor on some implementations. The reason we can use it for
+ * atomic_set() is the clrex or dummy strex done on every exception return.
+ */
+#define atomic_read(v)	(*(volatile int *)&(v)->counter)
+#define atomic_set(v,i)	(((v)->counter) = (i))
+
+#if __LINUX_ARM_ARCH__ >= 6
+
+/*
+ * ARMv6 UP and SMP safe atomic ops.  We use load exclusive and
+ * store exclusive to ensure that these are atomic.  We may loop
+ * to ensure that the update happens.
+ */
+static inline void atomic_add(int i, atomic_t *v)
+{
+	unsigned long tmp;
+	int result;
+
+	__asm__ __volatile__("@ atomic_add\n"
+"1:	ldrex	%0, [%3]\n"
+"	add	%0, %0, %4\n"
+"	strex	%1, %0, [%3]\n"
+"	teq	%1, #0\n"
+"	bne	1b"
+	: "=&r" (result), "=&r" (tmp), "+Qo" (v->counter)
+	: "r" (&v->counter), "Ir" (i)
+	: "cc");
+}
+
+static inline int atomic_add_return(int i, atomic_t *v)
+{
+	unsigned long tmp;
+	int result;
+
+	smp_mb();
+
+	__asm__ __volatile__("@ atomic_add_return\n"
+"1:	ldrex	%0, [%3]\n"
+"	add	%0, %0, %4\n"
+"	strex	%1, %0, [%3]\n"
+"	teq	%1, #0\n"
+"	bne	1b"
+	: "=&r" (result), "=&r" (tmp), "+Qo" (v->counter)
+	: "r" (&v->counter), "Ir" (i)
+	: "cc");
+
+	smp_mb();
+
+	return result;
+}
+
+static inline void atomic_sub(int i, atomic_t *v)
+{
+	unsigned long tmp;
+	int result;
+
+	__asm__ __volatile__("@ atomic_sub\n"
+"1:	ldrex	%0, [%3]\n"
+"	sub	%0, %0, %4\n"
+"	strex	%1, %0, [%3]\n"
+"	teq	%1, #0\n"
+"	bne	1b"
+	: "=&r" (result), "=&r" (tmp), "+Qo" (v->counter)
+	: "r" (&v->counter), "Ir" (i)
+	: "cc");
+}
+
+static inline int atomic_sub_return(int i, atomic_t *v)
+{
+	unsigned long tmp;
+	int result;
+
+	smp_mb();
+
+	__asm__ __volatile__("@ atomic_sub_return\n"
+"1:	ldrex	%0, [%3]\n"
+"	sub	%0, %0, %4\n"
+"	strex	%1, %0, [%3]\n"
+"	teq	%1, #0\n"
+"	bne	1b"
+	: "=&r" (result), "=&r" (tmp), "+Qo" (v->counter)
+	: "r" (&v->counter), "Ir" (i)
+	: "cc");
+
+	smp_mb();
+
+	return result;
+}
+
+static inline int atomic_cmpxchg(atomic_t *ptr, int old, int new)
+{
+	unsigned long oldval, res;
+
+	smp_mb();
+
+	do {
+		__asm__ __volatile__("@ atomic_cmpxchg\n"
+		"ldrex	%1, [%3]\n"
+		"mov	%0, #0\n"
+		"teq	%1, %4\n"
+		"strexeq %0, %5, [%3]\n"
+		    : "=&r" (res), "=&r" (oldval), "+Qo" (ptr->counter)
+		    : "r" (&ptr->counter), "Ir" (old), "r" (new)
+		    : "cc");
+	} while (res);
+
+	smp_mb();
+
+	return oldval;
+}
+
+static inline void atomic_clear_mask(unsigned long mask, unsigned long *addr)
+{
+	unsigned long tmp, tmp2;
+
+	__asm__ __volatile__("@ atomic_clear_mask\n"
+"1:	ldrex	%0, [%3]\n"
+"	bic	%0, %0, %4\n"
+"	strex	%1, %0, [%3]\n"
+"	teq	%1, #0\n"
+"	bne	1b"
+	: "=&r" (tmp), "=&r" (tmp2), "+Qo" (*addr)
+	: "r" (addr), "Ir" (mask)
+	: "cc");
+}
+
+#else /* ARM_ARCH_6 */
+
+#ifdef CONFIG_SMP
+#error SMP not supported on pre-ARMv6 CPUs
+#endif
+
+static inline int atomic_add_return(int i, atomic_t *v)
+{
+	unsigned long flags;
+	int val;
+
+	raw_local_irq_save(flags);
+	val = v->counter;
+	v->counter = val += i;
+	raw_local_irq_restore(flags);
+
+	return val;
+}
+#define atomic_add(i, v)	(void) atomic_add_return(i, v)
+
+static inline int atomic_sub_return(int i, atomic_t *v)
+{
+	unsigned long flags;
+	int val;
+
+	raw_local_irq_save(flags);
+	val = v->counter;
+	v->counter = val -= i;
+	raw_local_irq_restore(flags);
+
+	return val;
+}
+#define atomic_sub(i, v)	(void) atomic_sub_return(i, v)
+
+static inline int atomic_cmpxchg(atomic_t *v, int old, int new)
+{
+	int ret;
+	unsigned long flags;
+
+	raw_local_irq_save(flags);
+	ret = v->counter;
+	if (likely(ret == old))
+		v->counter = new;
+	raw_local_irq_restore(flags);
+
+	return ret;
+}
+
+static inline void atomic_clear_mask(unsigned long mask, unsigned long *addr)
+{
+	unsigned long flags;
+
+	raw_local_irq_save(flags);
+	*addr &= ~mask;
+	raw_local_irq_restore(flags);
+}
+
+#endif /* __LINUX_ARM_ARCH__ */
+
+#define atomic_xchg(v, new) (xchg(&((v)->counter), new))
+
+static inline int __atomic_add_unless(atomic_t *v, int a, int u)
+{
+	int c, old;
+
+	c = atomic_read(v);
+	while (c != u && (old = atomic_cmpxchg((v), c, c + a)) != c)
+		c = old;
+	return c;
+}
+
+#define atomic_inc(v)		atomic_add(1, v)
+#define atomic_dec(v)		atomic_sub(1, v)