LoongArch: Add qspinlock support

On NUMA system, the performance of qspinlock is better than generic
spinlock. Below is the UnixBench test results on a 8 nodes (4 cores
per node, 32 cores in total) machine.

A. With generic spinlock:

System Benchmarks Index Values               BASELINE       RESULT    INDEX
Dhrystone 2 using register variables         116700.0  449574022.5  38523.9
Double-Precision Whetstone                       55.0      85190.4  15489.2
Execl Throughput                                 43.0      14696.2   3417.7
File Copy 1024 bufsize 2000 maxblocks          3960.0     143157.8    361.5
File Copy 256 bufsize 500 maxblocks            1655.0      37631.8    227.4
File Copy 4096 bufsize 8000 maxblocks          5800.0     444814.2    766.9
Pipe Throughput                               12440.0    5047490.7   4057.5
Pipe-based Context Switching                   4000.0    2021545.7   5053.9
Process Creation                                126.0      23829.8   1891.3
Shell Scripts (1 concurrent)                     42.4      33756.7   7961.5
Shell Scripts (8 concurrent)                      6.0       4062.9   6771.5
System Call Overhead                          15000.0    2479748.6   1653.2
                                                                   ========
System Benchmarks Index Score                                        2955.6

B. With qspinlock:

System Benchmarks Index Values               BASELINE       RESULT    INDEX
Dhrystone 2 using register variables         116700.0  449467876.9  38514.8
Double-Precision Whetstone                       55.0      85174.6  15486.3
Execl Throughput                                 43.0      14769.1   3434.7
File Copy 1024 bufsize 2000 maxblocks          3960.0     146150.5    369.1
File Copy 256 bufsize 500 maxblocks            1655.0      37496.8    226.6
File Copy 4096 bufsize 8000 maxblocks          5800.0     447527.0    771.6
Pipe Throughput                               12440.0    5175989.2   4160.8
Pipe-based Context Switching                   4000.0    2207747.8   5519.4
Process Creation                                126.0      25125.5   1994.1
Shell Scripts (1 concurrent)                     42.4      33461.2   7891.8
Shell Scripts (8 concurrent)                      6.0       4024.7   6707.8
System Call Overhead                          15000.0    2917278.6   1944.9
                                                                   ========
System Benchmarks Index Score                                        3040.1
Signed-off-by: Rui Wang <wangrui@loongson.cn>
Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>

arch/loongarch/Kconfig

@@ -51,6 +51,7 @@ config LOONGARCH
 	select ARCH_USE_BUILTIN_BSWAP
 	select ARCH_USE_CMPXCHG_LOCKREF
 	select ARCH_USE_QUEUED_RWLOCKS
+	select ARCH_USE_QUEUED_SPINLOCKS
 	select ARCH_WANT_DEFAULT_TOPDOWN_MMAP_LAYOUT
 	select ARCH_WANT_LD_ORPHAN_WARN
 	select ARCH_WANTS_NO_INSTR

arch/loongarch/include/asm/Kbuild

 # SPDX-License-Identifier: GPL-2.0
 generic-y += dma-contiguous.h
 generic-y += export.h
+generic-y += mcs_spinlock.h
 generic-y += parport.h
 generic-y += early_ioremap.h
 generic-y += qrwlock.h
-generic-y += qrwlock_types.h
-generic-y += spinlock.h
-generic-y += spinlock_types.h
+generic-y += qspinlock.h
 generic-y += rwsem.h
 generic-y += segment.h
 generic-y += user.h

arch/loongarch/include/asm/spinlock.h

+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2020-2022 Loongson Technology Corporation Limited
+ */
+#ifndef _ASM_SPINLOCK_H
+#define _ASM_SPINLOCK_H
+
+#include <asm/processor.h>
+#include <asm/qspinlock.h>
+#include <asm/qrwlock.h>
+
+#endif /* _ASM_SPINLOCK_H */

arch/loongarch/include/asm/spinlock_types.h

+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2020-2022 Loongson Technology Corporation Limited
+ */
+#ifndef _ASM_SPINLOCK_TYPES_H
+#define _ASM_SPINLOCK_TYPES_H
+
+#include <asm-generic/qspinlock_types.h>
+#include <asm-generic/qrwlock_types.h>
+
+#endif