MIPS: Add Loongson-3B support

Loongson-3B is a 8-cores processor. In general it looks like there are
two Loongson-3A integrated in one chip: 8 cores are separated into two
groups (two NUMA node), each node has its own local memory.

Of course there are some differences between one Loongson-3B and two
Loongson-3A. E.g., the base addresses of IPI registers of each node are
not the same; Loongson-3A use ChipConfig register to enable/disable
clock, but Loongson-3B use FreqControl register instead.

There are two revision of Loongson-3B, the first revision is called as
Loongson-3B1000, whose frequency is 1GHz and has a PRid 0x6306, the
second revision is called as Loongson-3B1500, whose frequency is 1.5GHz
and has a PRid 0x6307. Both revisions has a bug that clock cannot be
disabled at runtime, but this will be fixed in future.
Signed-off-by: Huacai Chen <chenhc@lemote.com>
Cc: John Crispin <john@phrozen.org>
Cc: Steven J. Hill <Steven.Hill@imgtec.com>
Cc: Aurelien Jarno <aurelien@aurel32.net>
Cc: linux-mips@linux-mips.org
Cc: Fuxin Zhang <zhangfx@lemote.com>
Cc: Zhangjin Wu <wuzhangjin@gmail.com>
Patchwork: https://patchwork.linux-mips.org/patch/7188/Signed-off-by: Ralf Baechle <ralf@linux-mips.org>

arch/mips/include/asm/cpu.h

@@ -233,6 +233,8 @@
 #define PRID_REV_LOONGSON2E	0x0002
 #define PRID_REV_LOONGSON2F	0x0003
 #define PRID_REV_LOONGSON3A	0x0005
+#define PRID_REV_LOONGSON3B_R1	0x0006
+#define PRID_REV_LOONGSON3B_R2	0x0007
 
 /*
  * Older processors used to encode processor version and revision in two

arch/mips/include/asm/mach-loongson/boot_param.h

@@ -163,4 +163,5 @@ struct loongson_system_configuration {
 
 extern struct efi_memory_map_loongson *loongson_memmap;
 extern struct loongson_system_configuration loongson_sysconf;
+extern int cpuhotplug_workaround;
 #endif

arch/mips/include/asm/mach-loongson/loongson.h

@@ -255,6 +255,10 @@ static inline void do_perfcnt_IRQ(void)
 extern u64 loongson_chipcfg[MAX_PACKAGES];
 #define LOONGSON_CHIPCFG(id) (*(volatile u32 *)(loongson_chipcfg[id]))
 
+/* Freq Control register of each physical cpu package, PRid >= Loongson-3B */
+extern u64 loongson_freqctrl[MAX_PACKAGES];
+#define LOONGSON_FREQCTRL(id) (*(volatile u32 *)(loongson_freqctrl[id]))
+
 /* pcimap */
 
 #define LOONGSON_PCIMAP_PCIMAP_LO0	0x0000003f

arch/mips/kernel/cpu-probe.c

@@ -740,6 +740,12 @@ static inline void cpu_probe_legacy(struct cpuinfo_mips *c, unsigned int cpu)
 			__cpu_name[cpu] = "ICT Loongson-3";
 			set_elf_platform(cpu, "loongson3a");
 			break;
+		case PRID_REV_LOONGSON3B_R1:
+		case PRID_REV_LOONGSON3B_R2:
+			c->cputype = CPU_LOONGSON3;
+			__cpu_name[cpu] = "ICT Loongson-3";
+			set_elf_platform(cpu, "loongson3b");
+			break;
 		}
 
 		set_isa(c, MIPS_CPU_ISA_III);

arch/mips/loongson/common/env.c

@@ -28,6 +28,10 @@ struct efi_memory_map_loongson *loongson_memmap;
 struct loongson_system_configuration loongson_sysconf;
 
 u64 loongson_chipcfg[MAX_PACKAGES] = {0xffffffffbfc00180};
+u64 loongson_freqctrl[MAX_PACKAGES];
+
+unsigned long long smp_group[4];
+int cpuhotplug_workaround = 0;
 
 #define parse_even_earlier(res, option, p)				\
 do {									\
@@ -82,10 +86,32 @@ void __init prom_init_env(void)
 	if (ecpu->cputype == Loongson_3A) {
 		loongson_sysconf.cores_per_node = 4;
 		loongson_sysconf.cores_per_package = 4;
+		smp_group[0] = 0x900000003ff01000;
+		smp_group[1] = 0x900010003ff01000;
+		smp_group[2] = 0x900020003ff01000;
+		smp_group[3] = 0x900030003ff01000;
 		loongson_chipcfg[0] = 0x900000001fe00180;
 		loongson_chipcfg[1] = 0x900010001fe00180;
 		loongson_chipcfg[2] = 0x900020001fe00180;
 		loongson_chipcfg[3] = 0x900030001fe00180;
+		loongson_sysconf.ht_control_base = 0x90000EFDFB000000;
+	} else if (ecpu->cputype == Loongson_3B) {
+		loongson_sysconf.cores_per_node = 4; /* One chip has 2 nodes */
+		loongson_sysconf.cores_per_package = 8;
+		smp_group[0] = 0x900000003ff01000;
+		smp_group[1] = 0x900010003ff05000;
+		smp_group[2] = 0x900020003ff09000;
+		smp_group[3] = 0x900030003ff0d000;
+		loongson_chipcfg[0] = 0x900000001fe00180;
+		loongson_chipcfg[1] = 0x900020001fe00180;
+		loongson_chipcfg[2] = 0x900040001fe00180;
+		loongson_chipcfg[3] = 0x900060001fe00180;
+		loongson_freqctrl[0] = 0x900000001fe001d0;
+		loongson_freqctrl[1] = 0x900020001fe001d0;
+		loongson_freqctrl[2] = 0x900040001fe001d0;
+		loongson_freqctrl[3] = 0x900060001fe001d0;
+		loongson_sysconf.ht_control_base = 0x90001EFDFB000000;
+		cpuhotplug_workaround = 1;
 	} else {
 		loongson_sysconf.cores_per_node = 1;
 		loongson_sysconf.cores_per_package = 1;
@@ -111,7 +137,6 @@ void __init prom_init_env(void)
 	loongson_sysconf.poweroff_addr = boot_p->reset_system.Shutdown;
 	loongson_sysconf.suspend_addr = boot_p->reset_system.DoSuspend;
 
-	loongson_sysconf.ht_control_base = 0x90000EFDFB000000;
 	loongson_sysconf.vgabios_addr = boot_p->efi.smbios.vga_bios;
 	pr_debug("Shutdown Addr: %llx, Restart Addr: %llx, VBIOS Addr: %llx\n",
 		loongson_sysconf.poweroff_addr, loongson_sysconf.restart_addr,
@@ -129,6 +154,10 @@ void __init prom_init_env(void)
 		case PRID_REV_LOONGSON3A:
 			cpu_clock_freq = 900000000;
 			break;
+		case PRID_REV_LOONGSON3B_R1:
+		case PRID_REV_LOONGSON3B_R2:
+			cpu_clock_freq = 1000000000;
+			break;
 		default:
 			cpu_clock_freq = 100000000;
 			break;

arch/mips/loongson/loongson-3/irq.c

@@ -7,6 +7,8 @@
 #include <asm/i8259.h>
 #include <asm/mipsregs.h>
 
+#include "smp.h"
+
 unsigned int ht_irq[] = {1, 3, 4, 5, 6, 7, 8, 12, 14, 15};
 
 static void ht_irqdispatch(void)
@@ -53,9 +55,15 @@ static inline void mask_loongson_irq(struct irq_data *d)
 	/* Workaround: UART IRQ may deliver to any core */
 	if (d->irq == LOONGSON_UART_IRQ) {
 		int cpu = smp_processor_id();
-
-		LOONGSON_INT_ROUTER_INTENCLR = 1 << 10;
-		LOONGSON_INT_ROUTER_LPC = 0x10 + (1<<cpu);
+		int node_id = cpu / loongson_sysconf.cores_per_node;
+		int core_id = cpu % loongson_sysconf.cores_per_node;
+		u64 intenclr_addr = smp_group[node_id] |
+			(u64)(&LOONGSON_INT_ROUTER_INTENCLR);
+		u64 introuter_lpc_addr = smp_group[node_id] |
+			(u64)(&LOONGSON_INT_ROUTER_LPC);
+
+		*(volatile u32 *)intenclr_addr = 1 << 10;
+		*(volatile u8 *)introuter_lpc_addr = 0x10 + (1<<core_id);
 	}
 }
 
@@ -64,9 +72,15 @@ static inline void unmask_loongson_irq(struct irq_data *d)
 	/* Workaround: UART IRQ may deliver to any core */
 	if (d->irq == LOONGSON_UART_IRQ) {
 		int cpu = smp_processor_id();
-
-		LOONGSON_INT_ROUTER_INTENSET = 1 << 10;
-		LOONGSON_INT_ROUTER_LPC = 0x10 + (1<<cpu);
+		int node_id = cpu / loongson_sysconf.cores_per_node;
+		int core_id = cpu % loongson_sysconf.cores_per_node;
+		u64 intenset_addr = smp_group[node_id] |
+			(u64)(&LOONGSON_INT_ROUTER_INTENSET);
+		u64 introuter_lpc_addr = smp_group[node_id] |
+			(u64)(&LOONGSON_INT_ROUTER_LPC);
+
+		*(volatile u32 *)intenset_addr = 1 << 10;
+		*(volatile u8 *)introuter_lpc_addr = 0x10 + (1<<core_id);
 	}
 
 	set_c0_status(0x100 << (d->irq - MIPS_CPU_IRQ_BASE));

arch/mips/loongson/loongson-3/smp.h

 #ifndef __LOONGSON_SMP_H_
 #define __LOONGSON_SMP_H_
 
-/* for Loongson-3A smp support */
+/* for Loongson-3 smp support */
+extern unsigned long long smp_group[4];
 
 /* 4 groups(nodes) in maximum in numa case */
-#define  SMP_CORE_GROUP0_BASE    0x900000003ff01000
-#define  SMP_CORE_GROUP1_BASE    0x900010003ff01000
-#define  SMP_CORE_GROUP2_BASE    0x900020003ff01000
-#define  SMP_CORE_GROUP3_BASE    0x900030003ff01000
+#define SMP_CORE_GROUP0_BASE	(smp_group[0])
+#define SMP_CORE_GROUP1_BASE	(smp_group[1])
+#define SMP_CORE_GROUP2_BASE	(smp_group[2])
+#define SMP_CORE_GROUP3_BASE	(smp_group[3])
 
 /* 4 cores in each group(node) */
-#define  SMP_CORE0_OFFSET  0x000
-#define  SMP_CORE1_OFFSET  0x100
-#define  SMP_CORE2_OFFSET  0x200
-#define  SMP_CORE3_OFFSET  0x300
+#define SMP_CORE0_OFFSET  0x000
+#define SMP_CORE1_OFFSET  0x100
+#define SMP_CORE2_OFFSET  0x200
+#define SMP_CORE3_OFFSET  0x300
 
 /* ipi registers offsets */
-#define  STATUS0  0x00
-#define  EN0      0x04
-#define  SET0     0x08
-#define  CLEAR0   0x0c
-#define  STATUS1  0x10
-#define  MASK1    0x14
-#define  SET1     0x18
-#define  CLEAR1   0x1c
-#define  BUF      0x20
+#define STATUS0  0x00
+#define EN0      0x04
+#define SET0     0x08
+#define CLEAR0   0x0c
+#define STATUS1  0x10
+#define MASK1    0x14
+#define SET1     0x18
+#define CLEAR1   0x1c
+#define BUF      0x20
 
 #endif