[PATCH 4/5] arm64: add smp_vcond_load_relaxed()

[Haris Okanovic <harisokn@amazon.com>]

Implement smp_vcond_load_relaxed() atop __delay_until_ul() on arm64,
to reduce number of busy loops while waiting for a value condition.

This implementation only support unsigned long words. It can be extended
via the enclosed case structure in barrier.h as needed.

Signed-off-by: Haris Okanovic <harisokn@amazon.com>
---
 arch/arm64/include/asm/barrier.h | 18 ++++++++++++++++++
 arch/arm64/lib/delay.c           | 16 ++++++++++++++++
 2 files changed, 34 insertions(+)

diff --git a/arch/arm64/include/asm/barrier.h b/arch/arm64/include/asm/barrier.h
index 1ca947d5c939..188327e3ce72 100644
--- a/arch/arm64/include/asm/barrier.h
+++ b/arch/arm64/include/asm/barrier.h
@@ -203,6 +203,24 @@ do {									\
 	(typeof(*ptr))VAL;						\
 })
 
+extern unsigned long __smp_vcond_load_relaxed_ul(
+	u64 nsecs, unsigned long* addr, unsigned long mask, unsigned long val);
+
+#define smp_vcond_load_relaxed(nsecs, addr, mask, val) ({		\
+	u64 __nsecs = (nsecs);						\
+	typeof(addr) __addr = (addr);					\
+	typeof(*__addr) __mask = (mask);				\
+	typeof(*__addr) __val = (val);					\
+	typeof(*__addr) __cur;						\
+	switch (sizeof(*__addr)) {					\
+	case sizeof(unsigned long):					\
+		__cur = __smp_vcond_load_relaxed_ul(			\
+			__nsecs, __addr, __mask, __val);		\
+		break;							\
+	}								\
+	(__cur);							\
+})
+
 #define smp_cond_load_acquire(ptr, cond_expr)				\
 ({									\
 	typeof(ptr) __PTR = (ptr);					\
diff --git a/arch/arm64/lib/delay.c b/arch/arm64/lib/delay.c
index a7c3040af316..a61a13b04439 100644
--- a/arch/arm64/lib/delay.c
+++ b/arch/arm64/lib/delay.c
@@ -12,6 +12,7 @@
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/timex.h>
+#include <linux/sched/clock.h>
 
 #include <clocksource/arm_arch_timer.h>
 #include <asm/readex.h>
@@ -97,3 +98,18 @@ void __ndelay(unsigned long nsecs)
 	__delay(NSECS_TO_CYCLES(nsecs));
 }
 EXPORT_SYMBOL(__ndelay);
+
+unsigned long __smp_vcond_load_relaxed_ul(
+	u64 nsecs, unsigned long* addr, unsigned long mask, unsigned long val)
+{
+	const u64 start = local_clock_noinstr();
+	const u64 cycles = NSECS_TO_CYCLES(nsecs);
+	unsigned long cur;
+
+	do {
+		cur = __delay_until_ul(cycles, addr, mask, val);
+	} while((cur & mask) != val && local_clock_noinstr() - start < nsecs);
+
+	return cur;
+}
+EXPORT_SYMBOL(__smp_vcond_load_relaxed_ul);
-- 
2.34.1