[PATCH V6 2/2] 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>
Cc: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Waiman Long <longman@redhat.com>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Palmer Dabbelt <palmer@rivosinc.com>
---
 arch/riscv/Kconfig               |  8 ++++++++
 arch/riscv/include/asm/Kbuild    |  2 ++
 arch/riscv/include/asm/cmpxchg.h | 17 +++++++++++++++++
 3 files changed, 27 insertions(+)

diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig
index 32ffef9f6e5b..e1b57cb89189 100644
--- a/arch/riscv/Kconfig
+++ b/arch/riscv/Kconfig
@@ -333,6 +333,14 @@ config NODES_SHIFT
 	  Specify the maximum number of NUMA Nodes available on the target
 	  system.  Increases memory reserved to accommodate various tables.
 
+config RISCV_USE_QUEUED_SPINLOCKS
+	bool "Using queued spinlock instead of ticket-lock"
+	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.
+
 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 12debce235e5..492104d45a23 100644
--- a/arch/riscv/include/asm/cmpxchg.h
+++ b/arch/riscv/include/asm/cmpxchg.h
@@ -17,6 +17,23 @@
 	__typeof__(new) __new = (new);					\
 	__typeof__(*(ptr)) __ret;					\
 	switch (size) {							\
+	case 2: { 							\
+		u32 temp;						\
+		u32 shif = ((ulong)__ptr & 2) ? 16 : 0;			\
+		u32 mask = 0xffff << shif;				\
+		__ptr = (__typeof__(ptr))((ulong)__ptr & ~(ulong)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" (temp), "+A" (*__ptr)	\
+			: "rJ" (~mask), "rJ" (__new << shif)		\
+			: "memory");					\
+		__ret = (__ret & mask) >> shif;				\
+		break;							\
+	}								\
 	case 4:								\
 		__asm__ __volatile__ (					\
 			"	amoswap.w %0, %2, %1\n"			\
-- 
2.36.1