[PATCH] csky: Add qspinlock support

[PATCH] csky: Add qspinlock support

[guoren]

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").

C-SKY only has "ldex/stex" for all atomic operations. So csky give a
strong forward guarantee for "ldex/stex." That means when ldex grabbed
the cache line into $L1, it would block other cores from snooping the
address with several cycles. The atomic_fetch_add & xchg16 has the same
forward guarantee level in C-SKY.

Qspinlock has better code size and performance in a fast path.

Signed-off-by: Guo Ren <guoren@linux.alibaba.com>
Signed-off-by: Guo Ren <guoren@kernel.org>
---
 arch/csky/Kconfig                      |  1 +
 arch/csky/include/asm/Kbuild           |  4 ++--
 arch/csky/include/asm/cmpxchg.h        | 20 ++++++++++++++++++++
 arch/csky/include/asm/spinlock.h       | 12 ++++++++++++
 arch/csky/include/asm/spinlock_types.h |  9 +++++++++
 5 files changed, 44 insertions(+), 2 deletions(-)
 create mode 100644 arch/csky/include/asm/spinlock.h
 create mode 100644 arch/csky/include/asm/spinlock_types.h

diff --git a/arch/csky/Kconfig b/arch/csky/Kconfig
index 41d7d614f7a2..333def12faef 100644
--- a/arch/csky/Kconfig
+++ b/arch/csky/Kconfig
@@ -8,6 +8,7 @@ config CSKY
 	select ARCH_HAS_SYNC_DMA_FOR_DEVICE
 	select ARCH_USE_BUILTIN_BSWAP
 	select ARCH_USE_QUEUED_RWLOCKS
+	select ARCH_USE_QUEUED_SPINLOCKS
 	select ARCH_WANT_FRAME_POINTERS if !CPU_CK610 && $(cc-option,-mbacktrace)
 	select ARCH_WANT_DEFAULT_TOPDOWN_MMAP_LAYOUT
 	select COMMON_CLK
diff --git a/arch/csky/include/asm/Kbuild b/arch/csky/include/asm/Kbuild
index 103207a58f97..1117c28cb7e8 100644
--- a/arch/csky/include/asm/Kbuild
+++ b/arch/csky/include/asm/Kbuild
@@ -3,10 +3,10 @@ generic-y += asm-offsets.h
 generic-y += extable.h
 generic-y += gpio.h
 generic-y += kvm_para.h
-generic-y += spinlock.h
-generic-y += spinlock_types.h
+generic-y += mcs_spinlock.h
 generic-y += qrwlock.h
 generic-y += qrwlock_types.h
+generic-y += qspinlock.h
 generic-y += parport.h
 generic-y += user.h
 generic-y += vmlinux.lds.h
diff --git a/arch/csky/include/asm/cmpxchg.h b/arch/csky/include/asm/cmpxchg.h
index 5b8faccd65e4..5f693fadb56c 100644
--- a/arch/csky/include/asm/cmpxchg.h
+++ b/arch/csky/include/asm/cmpxchg.h
@@ -15,6 +15,26 @@ extern void __bad_xchg(void);
 	__typeof__(*(ptr)) __ret;				\
 	unsigned long tmp;					\
 	switch (size) {						\
+	case 2: {						\
+		u32 ret;					\
+		u32 shif = ((ulong)__ptr & 2) ? 16 : 0;		\
+		u32 mask = 0xffff << shif;			\
+		__ptr = (__typeof__(ptr))((ulong)__ptr & ~2);	\
+		__asm__ __volatile__ (				\
+			"1:	ldex.w %0, (%4)\n"		\
+			"	and    %1, %0, %2\n"		\
+			"	or     %1, %1, %3\n"		\
+			"	stex.w %1, (%4)\n"		\
+			"	bez    %1, 1b\n"		\
+			: "=&r" (ret), "=&r" (tmp)		\
+			: "r" (~mask),				\
+			  "r" ((u32)__new << shif),		\
+			  "r" (__ptr)				\
+			: "memory");				\
+		__ret = (__typeof__(*(ptr)))			\
+			((ret & mask) >> shif);			\
+		break;						\
+	}							\
 	case 4:							\
 		asm volatile (					\
 		"1:	ldex.w		%0, (%3) \n"		\
diff --git a/arch/csky/include/asm/spinlock.h b/arch/csky/include/asm/spinlock.h
new file mode 100644
index 000000000000..83a2005341f5
--- /dev/null
+++ b/arch/csky/include/asm/spinlock.h
@@ -0,0 +1,12 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef __ASM_CSKY_SPINLOCK_H
+#define __ASM_CSKY_SPINLOCK_H
+
+#include <asm/qspinlock.h>
+#include <asm/qrwlock.h>
+
+/* See include/linux/spinlock.h */
+#define smp_mb__after_spinlock()	smp_mb()
+
+#endif /* __ASM_CSKY_SPINLOCK_H */
diff --git a/arch/csky/include/asm/spinlock_types.h b/arch/csky/include/asm/spinlock_types.h
new file mode 100644
index 000000000000..75bdf3af80ba
--- /dev/null
+++ b/arch/csky/include/asm/spinlock_types.h
@@ -0,0 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef __ASM_CSKY_SPINLOCK_TYPES_H
+#define __ASM_CSKY_SPINLOCK_TYPES_H
+
+#include <asm-generic/qspinlock_types.h>
+#include <asm-generic/qrwlock_types.h>
+
+#endif /* __ASM_CSKY_SPINLOCK_TYPES_H */
-- 
2.36.1