Implement CPU_BUSY_CYCLE() with the ZiHintPause extension

This may help save power but also improves performance in contended
workloads.

kettenis@ helped a lot:
- pointing out the error in my newest diff
- pointing out that the ZiHintPause had been ratified in early 2021
- testing this on his visionfive board

ok kettenis@

libc make -j4 time before
17m39.06s real    22m13.85s user    34m27.88s system
17m35.60s real    22m15.01s user    34m28.51s system
17m40.78s real    22m14.89s user    34m42.91s system
17m40.61s real    22m06.99s user    34m29.58s system
17m42.79s real    22m08.04s user    34m33.19s system
17m39.21s real    22m11.27s user    34m23.18s system
17m32.81s real    22m13.84s user    34m09.67s system

libc make -j4 time after
16m35.48s real    21m57.94s user    32m05.50s system
16m49.10s real    21m58.47s user    32m42.37s system
16m42.16s real    22m00.51s user    32m22.18s system
16m41.54s real    21m53.32s user    32m19.53s system
16m45.42s real    21m52.14s user    32m37.78s system
16m46.55s real    21m58.98s user    32m36.70s system

1 files changed, 3 insertions, 2 deletions

diff --git a/sys/arch/riscv64/include/cpu.h b/sys/arch/riscv64/include/cpu.h
index 20da2ccf689..4c32f35fdff 100644
--- a/sys/arch/riscv64/include/cpu.h
+++ b/sys/arch/riscv64/include/cpu.h
@@ -1,4 +1,4 @@
-/*	$OpenBSD: cpu.h,v 1.11 2022/01/01 14:18:39 kettenis Exp $	*/
+/*	$OpenBSD: cpu.h,v 1.12 2022/06/10 21:34:15 jca Exp $	*/
 
 /*
  * Copyright (c) 2019 Mike Larkin <mlarkin@openbsd.org>
@@ -175,7 +175,8 @@ void	cpu_startclock(void);
 
 #endif /* !MULTIPROCESSOR */
 
-#define CPU_BUSY_CYCLE()	do {} while (0)
+/* Zihintpause ratified extension */
+#define CPU_BUSY_CYCLE()	__asm volatile(".long 0x0100000f" ::: "memory")
 
 #define curpcb		curcpu()->ci_curpcb