LoongArch: Add multi-processor (SMP) support

LoongArch-based procesors have 4, 8 or 16 cores per package. This patch
adds multi-processor (SMP) support for LoongArch.

Reviewed-by: WANG Xuerui <[email protected]>
Reviewed-by: Jiaxun Yang <[email protected]>
Signed-off-by: Huacai Chen <[email protected]>

Author: chenhuacai

arch/loongarch/Kconfig

@@ -64,6 +64,7 @@ config LOONGARCH
 	select GENERIC_LIB_UCMPDI2
 	select GENERIC_PCI_IOMAP
 	select GENERIC_SCHED_CLOCK
+	select GENERIC_SMP_IDLE_THREAD
 	select GENERIC_TIME_VSYSCALL
 	select GPIOLIB
 	select HAVE_ARCH_AUDITSYSCALL
@@ -92,7 +93,7 @@ config LOONGARCH
 	select HAVE_RSEQ
 	select HAVE_SYSCALL_TRACEPOINTS
 	select HAVE_TIF_NOHZ
-	select HAVE_VIRT_CPU_ACCOUNTING_GEN
+	select HAVE_VIRT_CPU_ACCOUNTING_GEN if !SMP
 	select IRQ_FORCED_THREADING
 	select IRQ_LOONGARCH_CPU
 	select MODULES_USE_ELF_RELA if MODULES
@@ -297,6 +298,43 @@ config EFI
 	  This enables the kernel to use EFI runtime services that are
 	  available (such as the EFI variable services).
 
+config SMP
+	bool "Multi-Processing support"
+	help
+	  This enables support for systems with more than one CPU. If you have
+	  a system with only one CPU, say N. If you have a system with more
+	  than one CPU, say Y.
+
+	  If you say N here, the kernel will run on uni- and multiprocessor
+	  machines, but will use only one CPU of a multiprocessor machine. If
+	  you say Y here, the kernel will run on many, but not all,
+	  uniprocessor machines. On a uniprocessor machine, the kernel
+	  will run faster if you say N here.
+
+	  See also the SMP-HOWTO available at <http://www.tldp.org/docs.html#howto>.
+
+	  If you don't know what to do here, say N.
+
+config HOTPLUG_CPU
+	bool "Support for hot-pluggable CPUs"
+	depends on SMP
+	select GENERIC_IRQ_MIGRATION
+	help
+	  Say Y here to allow turning CPUs off and on. CPUs can be
+	  controlled through /sys/devices/system/cpu.
+	  (Note: power management support will enable this option
+	    automatically on SMP systems. )
+	  Say N if you want to disable CPU hotplug.
+
+config NR_CPUS
+	int "Maximum number of CPUs (2-256)"
+	range 2 256
+	depends on SMP
+	default "64"
+	help
+	  This allows you to specify the maximum number of CPUs which this
+	  kernel will support.
+
 config FORCE_MAX_ZONEORDER
 	int "Maximum zone order"
 	range 14 64 if PAGE_SIZE_64KB

arch/loongarch/include/asm/atomic.h

@@ -162,6 +162,7 @@ static inline int arch_atomic_sub_if_positive(int i, atomic_t *v)
 		"	sc.w	%1, %2					\n"
 		"	beq	$zero, %1, 1b				\n"
 		"2:							\n"
+		__WEAK_LLSC_MB
 		: "=&r" (result), "=&r" (temp),
 		  "+" GCC_OFF_SMALL_ASM() (v->counter)
 		: "I" (-i));
@@ -174,6 +175,7 @@ static inline int arch_atomic_sub_if_positive(int i, atomic_t *v)
 		"	sc.w	%1, %2					\n"
 		"	beq	$zero, %1, 1b				\n"
 		"2:							\n"
+		__WEAK_LLSC_MB
 		: "=&r" (result), "=&r" (temp),
 		  "+" GCC_OFF_SMALL_ASM() (v->counter)
 		: "r" (i));
@@ -323,6 +325,7 @@ static inline long arch_atomic64_sub_if_positive(long i, atomic64_t *v)
 		"	sc.d	%1, %2					\n"
 		"	beq	%1, $zero, 1b				\n"
 		"2:							\n"
+		__WEAK_LLSC_MB
 		: "=&r" (result), "=&r" (temp),
 		  "+" GCC_OFF_SMALL_ASM() (v->counter)
 		: "I" (-i));
@@ -335,6 +338,7 @@ static inline long arch_atomic64_sub_if_positive(long i, atomic64_t *v)
 		"	sc.d	%1, %2					\n"
 		"	beq	%1, $zero, 1b				\n"
 		"2:							\n"
+		__WEAK_LLSC_MB
 		: "=&r" (result), "=&r" (temp),
 		  "+" GCC_OFF_SMALL_ASM() (v->counter)
 		: "r" (i));

arch/loongarch/include/asm/barrier.h

@@ -18,6 +18,19 @@
 #define mb()		fast_mb()
 #define iob()		fast_iob()
 
+#define __smp_mb()	__asm__ __volatile__("dbar 0" : : : "memory")
+#define __smp_rmb()	__asm__ __volatile__("dbar 0" : : : "memory")
+#define __smp_wmb()	__asm__ __volatile__("dbar 0" : : : "memory")
+
+#ifdef CONFIG_SMP
+#define __WEAK_LLSC_MB		"	dbar 0  \n"
+#else
+#define __WEAK_LLSC_MB		"		\n"
+#endif
+
+#define __smp_mb__before_atomic()	barrier()
+#define __smp_mb__after_atomic()	barrier()
+
 /**
  * array_index_mask_nospec() - generate a ~0 mask when index < size, 0 otherwise
  * @index: array element index
@@ -46,6 +59,101 @@ static inline unsigned long array_index_mask_nospec(unsigned long index,
 	return mask;
 }
 
+#define __smp_load_acquire(p)							\
+({										\
+	union { typeof(*p) __val; char __c[1]; } __u;				\
+	unsigned long __tmp = 0;							\
+	compiletime_assert_atomic_type(*p);					\
+	switch (sizeof(*p)) {							\
+	case 1:									\
+		*(__u8 *)__u.__c = *(volatile __u8 *)p;				\
+		__smp_mb();							\
+		break;								\
+	case 2:									\
+		*(__u16 *)__u.__c = *(volatile __u16 *)p;			\
+		__smp_mb();							\
+		break;								\
+	case 4:									\
+		__asm__ __volatile__(						\
+		"amor_db.w %[val], %[tmp], %[mem]	\n"				\
+		: [val] "=&r" (*(__u32 *)__u.__c)				\
+		: [mem] "ZB" (*(u32 *) p), [tmp] "r" (__tmp)			\
+		: "memory");							\
+		break;								\
+	case 8:									\
+		__asm__ __volatile__(						\
+		"amor_db.d %[val], %[tmp], %[mem]	\n"				\
+		: [val] "=&r" (*(__u64 *)__u.__c)				\
+		: [mem] "ZB" (*(u64 *) p), [tmp] "r" (__tmp)			\
+		: "memory");							\
+		break;								\
+	}									\
+	(typeof(*p))__u.__val;								\
+})
+
+#define __smp_store_release(p, v)						\
+do {										\
+	union { typeof(*p) __val; char __c[1]; } __u =				\
+		{ .__val = (__force typeof(*p)) (v) };				\
+	unsigned long __tmp;							\
+	compiletime_assert_atomic_type(*p);					\
+	switch (sizeof(*p)) {							\
+	case 1:									\
+		__smp_mb();							\
+		*(volatile __u8 *)p = *(__u8 *)__u.__c;				\
+		break;								\
+	case 2:									\
+		__smp_mb();							\
+		*(volatile __u16 *)p = *(__u16 *)__u.__c;			\
+		break;								\
+	case 4:									\
+		__asm__ __volatile__(						\
+		"amswap_db.w %[tmp], %[val], %[mem]	\n"			\
+		: [mem] "+ZB" (*(u32 *)p), [tmp] "=&r" (__tmp)			\
+		: [val] "r" (*(__u32 *)__u.__c)					\
+		: );								\
+		break;								\
+	case 8:									\
+		__asm__ __volatile__(						\
+		"amswap_db.d %[tmp], %[val], %[mem]	\n"			\
+		: [mem] "+ZB" (*(u64 *)p), [tmp] "=&r" (__tmp)			\
+		: [val] "r" (*(__u64 *)__u.__c)					\
+		: );								\
+		break;								\
+	}									\
+} while (0)
+
+#define __smp_store_mb(p, v)							\
+do {										\
+	union { typeof(p) __val; char __c[1]; } __u =				\
+		{ .__val = (__force typeof(p)) (v) };				\
+	unsigned long __tmp;							\
+	switch (sizeof(p)) {							\
+	case 1:									\
+		*(volatile __u8 *)&p = *(__u8 *)__u.__c;			\
+		__smp_mb();							\
+		break;								\
+	case 2:									\
+		*(volatile __u16 *)&p = *(__u16 *)__u.__c;			\
+		__smp_mb();							\
+		break;								\
+	case 4:									\
+		__asm__ __volatile__(						\
+		"amswap_db.w %[tmp], %[val], %[mem]	\n"			\
+		: [mem] "+ZB" (*(u32 *)&p), [tmp] "=&r" (__tmp)			\
+		: [val] "r" (*(__u32 *)__u.__c)					\
+		: );								\
+		break;								\
+	case 8:									\
+		__asm__ __volatile__(						\
+		"amswap_db.d %[tmp], %[val], %[mem]	\n"			\
+		: [mem] "+ZB" (*(u64 *)&p), [tmp] "=&r" (__tmp)			\
+		: [val] "r" (*(__u64 *)__u.__c)					\
+		: );								\
+		break;								\
+	}									\
+} while (0)
+
 #include <asm-generic/barrier.h>
 
 #endif /* __ASM_BARRIER_H */

arch/loongarch/include/asm/cmpxchg.h

@@ -59,6 +59,7 @@ static inline unsigned long __xchg(volatile void *ptr, unsigned long x,
 	"	" st "	$t0, %1				\n"		\
 	"	beq	$zero, $t0, 1b			\n"		\
 	"2:						\n"		\
+	__WEAK_LLSC_MB							\
 	: "=&r" (__ret), "=ZB"(*m)					\
 	: "ZB"(*m), "Jr" (old), "Jr" (new)				\
 	: "t0", "memory");						\

arch/loongarch/include/asm/futex.h

@@ -86,6 +86,7 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr, u32 oldval, u32 newv
 	"2:	sc.w	$t0, %2					\n"
 	"	beq	$zero, $t0, 1b				\n"
 	"3:							\n"
+	__WEAK_LLSC_MB
 	"	.section .fixup,\"ax\"				\n"
 	"4:	li.d	%0, %6					\n"
 	"	b	3b					\n"

arch/loongarch/include/asm/hardirq.h

@@ -21,4 +21,6 @@ typedef struct {
 
 DECLARE_PER_CPU_ALIGNED(irq_cpustat_t, irq_stat);
 
+#define __ARCH_IRQ_STAT
+
 #endif /* _ASM_HARDIRQ_H */

arch/loongarch/include/asm/irq.h

@@ -125,6 +125,8 @@ extern struct irq_domain *pch_lpc_domain;
 extern struct irq_domain *pch_msi_domain[MAX_IO_PICS];
 extern struct irq_domain *pch_pic_domain[MAX_IO_PICS];
 
+extern irqreturn_t loongson3_ipi_interrupt(int irq, void *dev);
+
 #include <asm-generic/irq.h>
 
 #endif /* _ASM_IRQ_H */