[PATCH V9 11/15] riscv: Add qspinlock support

[guoren@kernel.org]

From: Guo Ren <guoren@linux.alibaba.com>

Enable qspinlock by the requirements mentioned in a8ad07e5240c9
("asm-generic: qspinlock: Indicate the use of mixed-size atomics").

 - RISC-V atomic_*_release()/atomic_*_acquire() are implemented with
   own relaxed version plus acquire/release_fence for RCsc
   synchronization.

 - RISC-V LR/SC pairs could provide a strong/weak forward guarantee
   that depends on micro-architecture. And RISC-V ISA spec has given
   out several limitations to let hardware support strict forward
   guarantee (RISC-V User ISA - 8.3 Eventual Success of
   Store-Conditional Instructions). Some riscv cores such as BOOMv3
   & XiangShan could provide strict & strong forward guarantee (The
   cache line would be kept in an exclusive state for Backoff cycles,
   and only this core's interrupt could break the LR/SC pair).

 - RISC-V provides cheap atomic_fetch_or_acquire() with RCsc.

 - RISC-V only provides relaxed xchg16 to support qspinlock.

Signed-off-by: Guo Ren <guoren@linux.alibaba.com>
Signed-off-by: Guo Ren <guoren@kernel.org>
---
 arch/riscv/Kconfig               | 16 ++++++++++++++++
 arch/riscv/include/asm/Kbuild    |  2 ++
 arch/riscv/include/asm/cmpxchg.h | 24 ++++++++++++++++++++++++
 3 files changed, 42 insertions(+)

diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig
index c3ca23bc6352..8b36a4307d03 100644
--- a/arch/riscv/Kconfig
+++ b/arch/riscv/Kconfig
@@ -359,6 +359,22 @@ config NODES_SHIFT
 	  Specify the maximum number of NUMA Nodes available on the target
 	  system.  Increases memory reserved to accommodate various tables.
 
+choice
+	prompt "RISC-V spinlock type"
+	default RISCV_TICKET_SPINLOCKS
+
+config RISCV_TICKET_SPINLOCKS
+	bool "Using ticket spinlock"
+
+config RISCV_QUEUED_SPINLOCKS
+	bool "Using queued spinlock"
+	depends on SMP && MMU
+	select ARCH_USE_QUEUED_SPINLOCKS
+	help
+	  Make sure your micro arch LL/SC has a strong forward progress guarantee.
+	  Otherwise, stay at ticket-lock.
+endchoice
+
 config RISCV_ALTERNATIVE
 	bool
 	depends on !XIP_KERNEL
diff --git a/arch/riscv/include/asm/Kbuild b/arch/riscv/include/asm/Kbuild
index 504f8b7e72d4..2cce98c7b653 100644
--- a/arch/riscv/include/asm/Kbuild
+++ b/arch/riscv/include/asm/Kbuild
@@ -2,7 +2,9 @@
 generic-y += early_ioremap.h
 generic-y += flat.h
 generic-y += kvm_para.h
+generic-y += mcs_spinlock.h
 generic-y += parport.h
+generic-y += qspinlock.h
 generic-y += spinlock.h
 generic-y += spinlock_types.h
 generic-y += qrwlock.h
diff --git a/arch/riscv/include/asm/cmpxchg.h b/arch/riscv/include/asm/cmpxchg.h
index 4b5fa25f4336..2ba88057db52 100644
--- a/arch/riscv/include/asm/cmpxchg.h
+++ b/arch/riscv/include/asm/cmpxchg.h
@@ -11,12 +11,36 @@
 #include <asm/barrier.h>
 #include <asm/fence.h>
 
+static inline ulong __xchg16_relaxed(ulong new, void *ptr)
+{
+	ulong ret, tmp;
+	ulong shif = ((ulong)ptr & 2) ? 16 : 0;
+	ulong mask = 0xffff << shif;
+	ulong *__ptr = (ulong *)((ulong)ptr & ~2);
+
+	__asm__ __volatile__ (
+		"0:	lr.w %0, %2\n"
+		"	and  %1, %0, %z3\n"
+		"	or   %1, %1, %z4\n"
+		"	sc.w %1, %1, %2\n"
+		"	bnez %1, 0b\n"
+		: "=&r" (ret), "=&r" (tmp), "+A" (*__ptr)
+		: "rJ" (~mask), "rJ" (new << shif)
+		: "memory");
+
+	return (ulong)((ret & mask) >> shif);
+}
+
 #define __xchg_relaxed(ptr, new, size)					\
 ({									\
 	__typeof__(ptr) __ptr = (ptr);					\
 	__typeof__(new) __new = (new);					\
 	__typeof__(*(ptr)) __ret;					\
 	switch (size) {							\
+	case 2:	{							\
+		__ret = (__typeof__(*(ptr)))				\
+			__xchg16_relaxed((ulong)__new, __ptr);		\
+		break;}							\
 	case 4:								\
 		__asm__ __volatile__ (					\
 			"	amoswap.w %0, %2, %1\n"			\
-- 
2.36.1