powerpc/64s: Make POWER10 and later use pause_short in cpu_relax loops

We want to move away from using SMT priority updates for cpu_relax, and
use a 'wait' instruction which is similar to x86. As well as being a
much better fit for what everybody else uses and tests with, priority
nops are stateful which is nasty (interrupts have to consider they might
be taken at a different priority), and they're expensive to execute,
similar to a mtSPR which can effect other threads in the pipe.

This has shown to give results that are less affected by code alignment
on benchmarks that cause a lot of spin waiting (e.g., rwsem contention
on unixbench filesystem benchmarks) on POWER10.

QEMU TCG only supports this instruction correctly since v7.1, versions
without the fix may cause hangs whne running POWER10 CPUs.
Reviewed-by: Segher Boessenkool <segher@kernel.crashing.org>
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
[mpe: Fix checkpatch warnings RE the macros]
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20220920122259.363092-2-npiggin@gmail.com

arch/powerpc/include/asm/processor.h

@@ -355,11 +355,23 @@ static inline unsigned long __pack_fe01(unsigned int fpmode)
 
 #ifdef CONFIG_PPC64
 
-#define spin_begin()	HMT_low()
-
-#define spin_cpu_relax()	barrier()
-
-#define spin_end()	HMT_medium()
+#define spin_begin()							\
+	asm volatile(ASM_FTR_IFCLR(					\
+		"or 1,1,1", /* HMT_LOW */				\
+		"nop", /* v3.1 uses pause_short in cpu_relax instead */	\
+		%0) :: "i" (CPU_FTR_ARCH_31) : "memory")
+
+#define spin_cpu_relax()						\
+	asm volatile(ASM_FTR_IFCLR(					\
+		"nop", /* Before v3.1 use priority nops in spin_begin/end */ \
+		PPC_WAIT(2, 0),	/* aka pause_short */			\
+		%0) :: "i" (CPU_FTR_ARCH_31) : "memory")
+
+#define spin_end()							\
+	asm volatile(ASM_FTR_IFCLR(					\
+		"or 2,2,2", /* HMT_MEDIUM */				\
+		"nop",							\
+		%0) :: "i" (CPU_FTR_ARCH_31) : "memory")
 
 #endif
 

arch/powerpc/include/asm/vdso/processor.h

@@ -22,7 +22,13 @@
 #endif
 
 #ifdef CONFIG_PPC64
-#define cpu_relax()	do { HMT_low(); HMT_medium(); barrier(); } while (0)
+#define cpu_relax()							\
+	asm volatile(ASM_FTR_IFCLR(					\
+		/* Pre-POWER10 uses low ; medium priority nops */	\
+		"or 1,1,1 ; or 2,2,2",					\
+		/* POWER10 onward uses pause_short (wait 2,0) */	\
+		PPC_WAIT(2, 0),						\
+		%0) :: "i" (CPU_FTR_ARCH_31) : "memory")
 #else
 #define cpu_relax()	barrier()
 #endif