13 files changed, 753 insertions, 133 deletions

diff --git a/arch/mips/loongson/Kconfig b/arch/mips/loongson/Kconfig
index e6a86ccc4421..1b91fc6a921b 100644
--- a/arch/mips/loongson/Kconfig
+++ b/arch/mips/loongson/Kconfig
@@ -60,8 +60,8 @@ config LEMOTE_MACH2F
 	  These family machines include fuloong2f mini PC, yeeloong2f notebook,
 	  LingLoong allinone PC and so forth.
 
-config LEMOTE_MACH3A
-	bool "Lemote Loongson 3A family machines"
+config LOONGSON_MACH3X
+	bool "Generic Loongson 3 family machines"
 	select ARCH_SPARSEMEM_ENABLE
 	select GENERIC_ISA_DMA_SUPPORT_BROKEN
 	select BOOT_ELF32
@@ -79,6 +79,7 @@ config LEMOTE_MACH3A
 	select SYS_HAS_EARLY_PRINTK
 	select SYS_SUPPORTS_SMP
 	select SYS_SUPPORTS_HOTPLUG_CPU
+	select SYS_SUPPORTS_NUMA
 	select SYS_SUPPORTS_64BIT_KERNEL
 	select SYS_SUPPORTS_HIGHMEM
 	select SYS_SUPPORTS_LITTLE_ENDIAN
@@ -86,8 +87,8 @@ config LEMOTE_MACH3A
 	select ZONE_DMA32
 	select LEFI_FIRMWARE_INTERFACE
 	help
-		Lemote Loongson 3A family machines utilize the 3A revision of
-		Loongson processor and RS780/SBX00 chipset.
+		Generic Loongson 3 family machines utilize the 3A/3B revision
+		of Loongson processor and RS780/SBX00 chipset.
 endchoice
 
 config CS5536
diff --git a/arch/mips/loongson/Platform b/arch/mips/loongson/Platform
index 6205372b6c2d..0ac20eb84ecc 100644
--- a/arch/mips/loongson/Platform
+++ b/arch/mips/loongson/Platform
@@ -30,4 +30,4 @@ platform-$(CONFIG_MACH_LOONGSON) += loongson/
 cflags-$(CONFIG_MACH_LOONGSON) += -I$(srctree)/arch/mips/include/asm/mach-loongson -mno-branch-likely
 load-$(CONFIG_LEMOTE_FULOONG2E) += 0xffffffff80100000
 load-$(CONFIG_LEMOTE_MACH2F) += 0xffffffff80200000
-load-$(CONFIG_CPU_LOONGSON3) += 0xffffffff80200000
+load-$(CONFIG_LOONGSON_MACH3X) += 0xffffffff80200000
diff --git a/arch/mips/loongson/common/env.c b/arch/mips/loongson/common/env.c
index 0c543eae49bf..f15228550a22 100644
--- a/arch/mips/loongson/common/env.c
+++ b/arch/mips/loongson/common/env.c
@@ -27,6 +27,12 @@ EXPORT_SYMBOL(cpu_clock_freq);
 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 {									\
 	unsigned int tmp __maybe_unused;				\
@@ -77,9 +83,47 @@ void __init prom_init_env(void)
 
 	cpu_clock_freq = ecpu->cpu_clock_freq;
 	loongson_sysconf.cputype = ecpu->cputype;
+	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;
+		loongson_chipcfg[0] = 0x900000001fe00180;
+	}
+
 	loongson_sysconf.nr_cpus = ecpu->nr_cpus;
 	if (ecpu->nr_cpus > NR_CPUS || ecpu->nr_cpus == 0)
 		loongson_sysconf.nr_cpus = NR_CPUS;
+	loongson_sysconf.nr_nodes = (loongson_sysconf.nr_cpus +
+		loongson_sysconf.cores_per_node - 1) /
+		loongson_sysconf.cores_per_node;
 
 	loongson_sysconf.pci_mem_start_addr = eirq_source->pci_mem_start_addr;
 	loongson_sysconf.pci_mem_end_addr = eirq_source->pci_mem_end_addr;
@@ -93,7 +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,
@@ -111,6 +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;
diff --git a/arch/mips/loongson/common/init.c b/arch/mips/loongson/common/init.c
index f37fe5413b73..f6af3aba4c86 100644
--- a/arch/mips/loongson/common/init.c
+++ b/arch/mips/loongson/common/init.c
@@ -30,7 +30,11 @@ void __init prom_init(void)
 	set_io_port_base((unsigned long)
 		ioremap(LOONGSON_PCIIO_BASE, LOONGSON_PCIIO_SIZE));
 
+#ifdef CONFIG_NUMA
+	prom_init_numa_memory();
+#else
 	prom_init_memory();
+#endif
 
 	/*init the uart base address */
 	prom_init_uart_base();
diff --git a/arch/mips/loongson/common/pm.c b/arch/mips/loongson/common/pm.c
index f55e07aee071..a6b67ccfc811 100644
--- a/arch/mips/loongson/common/pm.c
+++ b/arch/mips/loongson/common/pm.c
@@ -79,7 +79,7 @@ int __weak wakeup_loongson(void)
 static void wait_for_wakeup_events(void)
 {
 	while (!wakeup_loongson())
-		LOONGSON_CHIPCFG0 &= ~0x7;
+		LOONGSON_CHIPCFG(0) &= ~0x7;
 }
 
 /*
@@ -102,15 +102,15 @@ static void loongson_suspend_enter(void)
 
 	stop_perf_counters();
 
-	cached_cpu_freq = LOONGSON_CHIPCFG0;
+	cached_cpu_freq = LOONGSON_CHIPCFG(0);
 
 	/* Put CPU into wait mode */
-	LOONGSON_CHIPCFG0 &= ~0x7;
+	LOONGSON_CHIPCFG(0) &= ~0x7;
 
 	/* wait for the given events to wakeup cpu from wait mode */
 	wait_for_wakeup_events();
 
-	LOONGSON_CHIPCFG0 = cached_cpu_freq;
+	LOONGSON_CHIPCFG(0) = cached_cpu_freq;
 	mmiowb();
 }
 
diff --git a/arch/mips/loongson/lemote-2f/clock.c b/arch/mips/loongson/lemote-2f/clock.c
index 1eed38e28b1e..a217061beee3 100644
--- a/arch/mips/loongson/lemote-2f/clock.c
+++ b/arch/mips/loongson/lemote-2f/clock.c
@@ -114,9 +114,9 @@ int clk_set_rate(struct clk *clk, unsigned long rate)
 
 	clk->rate = rate;
 
-	regval = LOONGSON_CHIPCFG0;
+	regval = LOONGSON_CHIPCFG(0);
 	regval = (regval & ~0x7) | (pos->driver_data - 1);
-	LOONGSON_CHIPCFG0 = regval;
+	LOONGSON_CHIPCFG(0) = regval;
 
 	return ret;
 }
diff --git a/arch/mips/loongson/lemote-2f/reset.c b/arch/mips/loongson/lemote-2f/reset.c
index 90962a3a1731..79ac694fe744 100644
--- a/arch/mips/loongson/lemote-2f/reset.c
+++ b/arch/mips/loongson/lemote-2f/reset.c
@@ -28,7 +28,7 @@ static void reset_cpu(void)
 	 * reset cpu to full speed, this is needed when enabling cpu frequency
 	 * scalling
 	 */
-	LOONGSON_CHIPCFG0 |= 0x7;
+	LOONGSON_CHIPCFG(0) |= 0x7;
 }
 
 /* reset support for fuloong2f */
diff --git a/arch/mips/loongson/loongson-3/Makefile b/arch/mips/loongson/loongson-3/Makefile
index 70152b252ddc..b4df775b9f30 100644
--- a/arch/mips/loongson/loongson-3/Makefile
+++ b/arch/mips/loongson/loongson-3/Makefile
@@ -1,6 +1,8 @@
 #
 # Makefile for Loongson-3 family machines
 #
-obj-y			+= irq.o
+obj-y			+= irq.o cop2-ex.o
 
 obj-$(CONFIG_SMP)	+= smp.o
+
+obj-$(CONFIG_NUMA)	+= numa.o
diff --git a/arch/mips/loongson/loongson-3/cop2-ex.c b/arch/mips/loongson/loongson-3/cop2-ex.c
new file mode 100644
index 000000000000..9182e8d2967c
--- /dev/null
+++ b/arch/mips/loongson/loongson-3/cop2-ex.c
@@ -0,0 +1,63 @@
+/*
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ *
+ * Copyright (C) 2014 Lemote Corporation.
+ *   written by Huacai Chen <chenhc@lemote.com>
+ *
+ * based on arch/mips/cavium-octeon/cpu.c
+ * Copyright (C) 2009 Wind River Systems,
+ *   written by Ralf Baechle <ralf@linux-mips.org>
+ */
+#include <linux/init.h>
+#include <linux/sched.h>
+#include <linux/notifier.h>
+
+#include <asm/fpu.h>
+#include <asm/cop2.h>
+#include <asm/current.h>
+#include <asm/mipsregs.h>
+
+static int loongson_cu2_call(struct notifier_block *nfb, unsigned long action,
+	void *data)
+{
+	int fpu_enabled;
+	int fr = !test_thread_flag(TIF_32BIT_FPREGS);
+
+	switch (action) {
+	case CU2_EXCEPTION:
+		preempt_disable();
+		fpu_enabled = read_c0_status() & ST0_CU1;
+		if (!fr)
+			set_c0_status(ST0_CU1 | ST0_CU2);
+		else
+			set_c0_status(ST0_CU1 | ST0_CU2 | ST0_FR);
+		enable_fpu_hazard();
+		KSTK_STATUS(current) |= (ST0_CU1 | ST0_CU2);
+		if (fr)
+			KSTK_STATUS(current) |= ST0_FR;
+		else
+			KSTK_STATUS(current) &= ~ST0_FR;
+		/* If FPU is enabled, we needn't init or restore fp */
+		if(!fpu_enabled) {
+			set_thread_flag(TIF_USEDFPU);
+			if (!used_math()) {
+				_init_fpu();
+				set_used_math();
+			} else
+				_restore_fp(current);
+		}
+		preempt_enable();
+
+		return NOTIFY_STOP;	/* Don't call default notifier */
+	}
+
+	return NOTIFY_OK;		/* Let default notifier send signals */
+}
+
+static int __init loongson_cu2_setup(void)
+{
+	return cu2_notifier(loongson_cu2_call, 0);
+}
+early_initcall(loongson_cu2_setup);
diff --git a/arch/mips/loongson/loongson-3/irq.c b/arch/mips/loongson/loongson-3/irq.c
index f240828181ff..ca1c62af5188 100644
--- a/arch/mips/loongson/loongson-3/irq.c
+++ b/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));
diff --git a/arch/mips/loongson/loongson-3/numa.c b/arch/mips/loongson/loongson-3/numa.c
new file mode 100644
index 000000000000..ca025a6ba559
--- /dev/null
+++ b/arch/mips/loongson/loongson-3/numa.c
@@ -0,0 +1,291 @@
+/*
+ * Copyright (C) 2010 Loongson Inc. & Lemote Inc. &
+ *                    Insititute of Computing Technology
+ * Author:  Xiang Gao, gaoxiang@ict.ac.cn
+ *          Huacai Chen, chenhc@lemote.com
+ *          Xiaofu Meng, Shuangshuang Zhang
+ *
+ * This program is free software; you can redistribute  it and/or modify it
+ * under  the terms of  the GNU General  Public License as published by the
+ * Free Software Foundation;  either version 2 of the  License, or (at your
+ * option) any later version.
+ */
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/mm.h>
+#include <linux/mmzone.h>
+#include <linux/module.h>
+#include <linux/nodemask.h>
+#include <linux/swap.h>
+#include <linux/memblock.h>
+#include <linux/bootmem.h>
+#include <linux/pfn.h>
+#include <linux/highmem.h>
+#include <asm/page.h>
+#include <asm/pgalloc.h>
+#include <asm/sections.h>
+#include <linux/bootmem.h>
+#include <linux/init.h>
+#include <linux/irq.h>
+#include <asm/bootinfo.h>
+#include <asm/mc146818-time.h>
+#include <asm/time.h>
+#include <asm/wbflush.h>
+#include <boot_param.h>
+
+static struct node_data prealloc__node_data[MAX_NUMNODES];
+unsigned char __node_distances[MAX_NUMNODES][MAX_NUMNODES];
+struct node_data *__node_data[MAX_NUMNODES];
+EXPORT_SYMBOL(__node_data);
+
+static void enable_lpa(void)
+{
+	unsigned long value;
+
+	value = __read_32bit_c0_register($16, 3);
+	value |= 0x00000080;
+	__write_32bit_c0_register($16, 3, value);
+	value = __read_32bit_c0_register($16, 3);
+	pr_info("CP0_Config3: CP0 16.3 (0x%lx)\n", value);
+
+	value = __read_32bit_c0_register($5, 1);
+	value |= 0x20000000;
+	__write_32bit_c0_register($5, 1, value);
+	value = __read_32bit_c0_register($5, 1);
+	pr_info("CP0_PageGrain: CP0 5.1 (0x%lx)\n", value);
+}
+
+static void cpu_node_probe(void)
+{
+	int i;
+
+	nodes_clear(node_possible_map);
+	nodes_clear(node_online_map);
+	for (i = 0; i < loongson_sysconf.nr_nodes; i++) {
+		node_set_state(num_online_nodes(), N_POSSIBLE);
+		node_set_online(num_online_nodes());
+	}
+
+	pr_info("NUMA: Discovered %d cpus on %d nodes\n",
+		loongson_sysconf.nr_cpus, num_online_nodes());
+}
+
+static int __init compute_node_distance(int row, int col)
+{
+	int package_row = row * loongson_sysconf.cores_per_node /
+				loongson_sysconf.cores_per_package;
+	int package_col = col * loongson_sysconf.cores_per_node /
+				loongson_sysconf.cores_per_package;
+
+	if (col == row)
+		return 0;
+	else if (package_row == package_col)
+		return 40;
+	else
+		return 100;
+}
+
+static void __init init_topology_matrix(void)
+{
+	int row, col;
+
+	for (row = 0; row < MAX_NUMNODES; row++)
+		for (col = 0; col < MAX_NUMNODES; col++)
+			__node_distances[row][col] = -1;
+
+	for_each_online_node(row) {
+		for_each_online_node(col) {
+			__node_distances[row][col] =
+				compute_node_distance(row, col);
+		}
+	}
+}
+
+static unsigned long nid_to_addroffset(unsigned int nid)
+{
+	unsigned long result;
+	switch (nid) {
+	case 0:
+	default:
+		result = NODE0_ADDRSPACE_OFFSET;
+		break;
+	case 1:
+		result = NODE1_ADDRSPACE_OFFSET;
+		break;
+	case 2:
+		result = NODE2_ADDRSPACE_OFFSET;
+		break;
+	case 3:
+		result = NODE3_ADDRSPACE_OFFSET;
+		break;
+	}
+	return result;
+}
+
+static void __init szmem(unsigned int node)
+{
+	u32 i, mem_type;
+	static unsigned long num_physpages = 0;
+	u64 node_id, node_psize, start_pfn, end_pfn, mem_start, mem_size;
+
+	/* Parse memory information and activate */
+	for (i = 0; i < loongson_memmap->nr_map; i++) {
+		node_id = loongson_memmap->map[i].node_id;
+		if (node_id != node)
+			continue;
+
+		mem_type = loongson_memmap->map[i].mem_type;
+		mem_size = loongson_memmap->map[i].mem_size;
+		mem_start = loongson_memmap->map[i].mem_start;
+
+		switch (mem_type) {
+		case SYSTEM_RAM_LOW:
+			start_pfn = ((node_id << 44) + mem_start) >> PAGE_SHIFT;
+			node_psize = (mem_size << 20) >> PAGE_SHIFT;
+			end_pfn  = start_pfn + node_psize;
+			num_physpages += node_psize;
+			pr_info("Node%d: mem_type:%d, mem_start:0x%llx, mem_size:0x%llx MB\n",
+				(u32)node_id, mem_type, mem_start, mem_size);
+			pr_info("       start_pfn:0x%llx, end_pfn:0x%llx, num_physpages:0x%lx\n",
+				start_pfn, end_pfn, num_physpages);
+			add_memory_region((node_id << 44) + mem_start,
+				(u64)mem_size << 20, BOOT_MEM_RAM);
+			memblock_add_node(PFN_PHYS(start_pfn),
+				PFN_PHYS(end_pfn - start_pfn), node);
+			break;
+		case SYSTEM_RAM_HIGH:
+			start_pfn = ((node_id << 44) + mem_start) >> PAGE_SHIFT;
+			node_psize = (mem_size << 20) >> PAGE_SHIFT;
+			end_pfn  = start_pfn + node_psize;
+			num_physpages += node_psize;
+			pr_info("Node%d: mem_type:%d, mem_start:0x%llx, mem_size:0x%llx MB\n",
+				(u32)node_id, mem_type, mem_start, mem_size);
+			pr_info("       start_pfn:0x%llx, end_pfn:0x%llx, num_physpages:0x%lx\n",
+				start_pfn, end_pfn, num_physpages);
+			add_memory_region((node_id << 44) + mem_start,
+				(u64)mem_size << 20, BOOT_MEM_RAM);
+			memblock_add_node(PFN_PHYS(start_pfn),
+				PFN_PHYS(end_pfn - start_pfn), node);
+			break;
+		case MEM_RESERVED:
+			pr_info("Node%d: mem_type:%d, mem_start:0x%llx, mem_size:0x%llx MB\n",
+				(u32)node_id, mem_type, mem_start, mem_size);
+			add_memory_region((node_id << 44) + mem_start,
+				(u64)mem_size << 20, BOOT_MEM_RESERVED);
+			memblock_reserve(((node_id << 44) + mem_start),
+				mem_size << 20);
+			break;
+		}
+	}
+}
+
+static void __init node_mem_init(unsigned int node)
+{
+	unsigned long bootmap_size;
+	unsigned long node_addrspace_offset;
+	unsigned long start_pfn, end_pfn, freepfn;
+
+	node_addrspace_offset = nid_to_addroffset(node);
+	pr_info("Node%d's addrspace_offset is 0x%lx\n",
+			node, node_addrspace_offset);
+
+	get_pfn_range_for_nid(node, &start_pfn, &end_pfn);
+	freepfn = start_pfn;
+	if (node == 0)
+		freepfn = PFN_UP(__pa_symbol(&_end)); /* kernel end address */
+	pr_info("Node%d: start_pfn=0x%lx, end_pfn=0x%lx, freepfn=0x%lx\n",
+		node, start_pfn, end_pfn, freepfn);
+
+	__node_data[node] = prealloc__node_data + node;
+
+	NODE_DATA(node)->bdata = &bootmem_node_data[node];
+	NODE_DATA(node)->node_start_pfn = start_pfn;
+	NODE_DATA(node)->node_spanned_pages = end_pfn - start_pfn;
+
+	bootmap_size = init_bootmem_node(NODE_DATA(node), freepfn,
+					start_pfn, end_pfn);
+	free_bootmem_with_active_regions(node, end_pfn);
+	if (node == 0) /* used by finalize_initrd() */
+		max_low_pfn = end_pfn;
+
+	/* This is reserved for the kernel and bdata->node_bootmem_map */
+	reserve_bootmem_node(NODE_DATA(node), start_pfn << PAGE_SHIFT,
+		((freepfn - start_pfn) << PAGE_SHIFT) + bootmap_size,
+		BOOTMEM_DEFAULT);
+
+	if (node == 0 && node_end_pfn(0) >= (0xffffffff >> PAGE_SHIFT)) {
+		/* Reserve 0xff800000~0xffffffff for RS780E integrated GPU */
+		reserve_bootmem_node(NODE_DATA(node),
+				(node_addrspace_offset | 0xff800000),
+				8 << 20, BOOTMEM_DEFAULT);
+	}
+
+	sparse_memory_present_with_active_regions(node);
+}
+
+static __init void prom_meminit(void)
+{
+	unsigned int node, cpu;
+
+	cpu_node_probe();
+	init_topology_matrix();
+
+	for (node = 0; node < loongson_sysconf.nr_nodes; node++) {
+		if (node_online(node)) {
+			szmem(node);
+			node_mem_init(node);
+			cpus_clear(__node_data[(node)]->cpumask);
+		}
+	}
+	for (cpu = 0; cpu < loongson_sysconf.nr_cpus; cpu++) {
+		node = cpu / loongson_sysconf.cores_per_node;
+		if (node >= num_online_nodes())
+			node = 0;
+		pr_info("NUMA: set cpumask cpu %d on node %d\n", cpu, node);
+		cpu_set(cpu, __node_data[(node)]->cpumask);
+	}
+}
+
+void __init paging_init(void)
+{
+	unsigned node;
+	unsigned long zones_size[MAX_NR_ZONES] = {0, };
+
+	pagetable_init();
+
+	for_each_online_node(node) {
+		unsigned long  start_pfn, end_pfn;
+
+		get_pfn_range_for_nid(node, &start_pfn, &end_pfn);
+
+		if (end_pfn > max_low_pfn)
+			max_low_pfn = end_pfn;
+	}
+#ifdef CONFIG_ZONE_DMA32
+	zones_size[ZONE_DMA32] = MAX_DMA32_PFN;
+#endif
+	zones_size[ZONE_NORMAL] = max_low_pfn;
+	free_area_init_nodes(zones_size);
+}
+
+void __init mem_init(void)
+{
+	high_memory = (void *) __va(get_num_physpages() << PAGE_SHIFT);
+	free_all_bootmem();
+	setup_zero_pages();	/* This comes from node 0 */
+	mem_init_print_info(NULL);
+}
+
+/* All PCI device belongs to logical Node-0 */
+int pcibus_to_node(struct pci_bus *bus)
+{
+	return 0;
+}
+EXPORT_SYMBOL(pcibus_to_node);
+
+void __init prom_init_numa_memory(void)
+{
+	enable_lpa();
+	prom_meminit();
+}
+EXPORT_SYMBOL(prom_init_numa_memory);
diff --git a/arch/mips/loongson/loongson-3/smp.c b/arch/mips/loongson/loongson-3/smp.c
index 1e8894020ea5..74e827b4ec8f 100644
--- a/arch/mips/loongson/loongson-3/smp.c
+++ b/arch/mips/loongson/loongson-3/smp.c
@@ -31,6 +31,12 @@
 DEFINE_PER_CPU(int, cpu_state);
 DEFINE_PER_CPU(uint32_t, core0_c0count);
 
+static void *ipi_set0_regs[16];
+static void *ipi_clear0_regs[16];
+static void *ipi_status0_regs[16];
+static void *ipi_en0_regs[16];
+static void *ipi_mailbox_buf[16];
+
 /* read a 32bit value from ipi register */
 #define loongson3_ipi_read32(addr) readl(addr)
 /* read a 64bit value from ipi register */
@@ -48,100 +54,185 @@ DEFINE_PER_CPU(uint32_t, core0_c0count);
 		__wbflush();			\
 	} while (0)
 
-static void *ipi_set0_regs[] = {
-	(void *)(SMP_CORE_GROUP0_BASE + SMP_CORE0_OFFSET + SET0),
-	(void *)(SMP_CORE_GROUP0_BASE + SMP_CORE1_OFFSET + SET0),
-	(void *)(SMP_CORE_GROUP0_BASE + SMP_CORE2_OFFSET + SET0),
-	(void *)(SMP_CORE_GROUP0_BASE + SMP_CORE3_OFFSET + SET0),
-	(void *)(SMP_CORE_GROUP1_BASE + SMP_CORE0_OFFSET + SET0),
-	(void *)(SMP_CORE_GROUP1_BASE + SMP_CORE1_OFFSET + SET0),
-	(void *)(SMP_CORE_GROUP1_BASE + SMP_CORE2_OFFSET + SET0),
-	(void *)(SMP_CORE_GROUP1_BASE + SMP_CORE3_OFFSET + SET0),
-	(void *)(SMP_CORE_GROUP2_BASE + SMP_CORE0_OFFSET + SET0),
-	(void *)(SMP_CORE_GROUP2_BASE + SMP_CORE1_OFFSET + SET0),
-	(void *)(SMP_CORE_GROUP2_BASE + SMP_CORE2_OFFSET + SET0),
-	(void *)(SMP_CORE_GROUP2_BASE + SMP_CORE3_OFFSET + SET0),
-	(void *)(SMP_CORE_GROUP3_BASE + SMP_CORE0_OFFSET + SET0),
-	(void *)(SMP_CORE_GROUP3_BASE + SMP_CORE1_OFFSET + SET0),
-	(void *)(SMP_CORE_GROUP3_BASE + SMP_CORE2_OFFSET + SET0),
-	(void *)(SMP_CORE_GROUP3_BASE + SMP_CORE3_OFFSET + SET0),
-};
+static void ipi_set0_regs_init(void)
+{
+	ipi_set0_regs[0] = (void *)
+		(SMP_CORE_GROUP0_BASE + SMP_CORE0_OFFSET + SET0);
+	ipi_set0_regs[1] = (void *)
+		(SMP_CORE_GROUP0_BASE + SMP_CORE1_OFFSET + SET0);
+	ipi_set0_regs[2] = (void *)
+		(SMP_CORE_GROUP0_BASE + SMP_CORE2_OFFSET + SET0);
+	ipi_set0_regs[3] = (void *)
+		(SMP_CORE_GROUP0_BASE + SMP_CORE3_OFFSET + SET0);
+	ipi_set0_regs[4] = (void *)
+		(SMP_CORE_GROUP1_BASE + SMP_CORE0_OFFSET + SET0);
+	ipi_set0_regs[5] = (void *)
+		(SMP_CORE_GROUP1_BASE + SMP_CORE1_OFFSET + SET0);
+	ipi_set0_regs[6] = (void *)
+		(SMP_CORE_GROUP1_BASE + SMP_CORE2_OFFSET + SET0);
+	ipi_set0_regs[7] = (void *)
+		(SMP_CORE_GROUP1_BASE + SMP_CORE3_OFFSET + SET0);
+	ipi_set0_regs[8] = (void *)
+		(SMP_CORE_GROUP2_BASE + SMP_CORE0_OFFSET + SET0);
+	ipi_set0_regs[9] = (void *)
+		(SMP_CORE_GROUP2_BASE + SMP_CORE1_OFFSET + SET0);
+	ipi_set0_regs[10] = (void *)
+		(SMP_CORE_GROUP2_BASE + SMP_CORE2_OFFSET + SET0);
+	ipi_set0_regs[11] = (void *)
+		(SMP_CORE_GROUP2_BASE + SMP_CORE3_OFFSET + SET0);
+	ipi_set0_regs[12] = (void *)
+		(SMP_CORE_GROUP3_BASE + SMP_CORE0_OFFSET + SET0);
+	ipi_set0_regs[13] = (void *)
+		(SMP_CORE_GROUP3_BASE + SMP_CORE1_OFFSET + SET0);
+	ipi_set0_regs[14] = (void *)
+		(SMP_CORE_GROUP3_BASE + SMP_CORE2_OFFSET + SET0);
+	ipi_set0_regs[15] = (void *)
+		(SMP_CORE_GROUP3_BASE + SMP_CORE3_OFFSET + SET0);
+}
 
-static void *ipi_clear0_regs[] = {
-	(void *)(SMP_CORE_GROUP0_BASE + SMP_CORE0_OFFSET + CLEAR0),
-	(void *)(SMP_CORE_GROUP0_BASE + SMP_CORE1_OFFSET + CLEAR0),
-	(void *)(SMP_CORE_GROUP0_BASE + SMP_CORE2_OFFSET + CLEAR0),
-	(void *)(SMP_CORE_GROUP0_BASE + SMP_CORE3_OFFSET + CLEAR0),
-	(void *)(SMP_CORE_GROUP1_BASE + SMP_CORE0_OFFSET + CLEAR0),
-	(void *)(SMP_CORE_GROUP1_BASE + SMP_CORE1_OFFSET + CLEAR0),
-	(void *)(SMP_CORE_GROUP1_BASE + SMP_CORE2_OFFSET + CLEAR0),
-	(void *)(SMP_CORE_GROUP1_BASE + SMP_CORE3_OFFSET + CLEAR0),
-	(void *)(SMP_CORE_GROUP2_BASE + SMP_CORE0_OFFSET + CLEAR0),
-	(void *)(SMP_CORE_GROUP2_BASE + SMP_CORE1_OFFSET + CLEAR0),
-	(void *)(SMP_CORE_GROUP2_BASE + SMP_CORE2_OFFSET + CLEAR0),
-	(void *)(SMP_CORE_GROUP2_BASE + SMP_CORE3_OFFSET + CLEAR0),
-	(void *)(SMP_CORE_GROUP3_BASE + SMP_CORE0_OFFSET + CLEAR0),
-	(void *)(SMP_CORE_GROUP3_BASE + SMP_CORE1_OFFSET + CLEAR0),
-	(void *)(SMP_CORE_GROUP3_BASE + SMP_CORE2_OFFSET + CLEAR0),
-	(void *)(SMP_CORE_GROUP3_BASE + SMP_CORE3_OFFSET + CLEAR0),
-};
+static void ipi_clear0_regs_init(void)
+{
+	ipi_clear0_regs[0] = (void *)
+		(SMP_CORE_GROUP0_BASE + SMP_CORE0_OFFSET + CLEAR0);
+	ipi_clear0_regs[1] = (void *)
+		(SMP_CORE_GROUP0_BASE + SMP_CORE1_OFFSET + CLEAR0);
+	ipi_clear0_regs[2] = (void *)
+		(SMP_CORE_GROUP0_BASE + SMP_CORE2_OFFSET + CLEAR0);
+	ipi_clear0_regs[3] = (void *)
+		(SMP_CORE_GROUP0_BASE + SMP_CORE3_OFFSET + CLEAR0);
+	ipi_clear0_regs[4] = (void *)
+		(SMP_CORE_GROUP1_BASE + SMP_CORE0_OFFSET + CLEAR0);
+	ipi_clear0_regs[5] = (void *)
+		(SMP_CORE_GROUP1_BASE + SMP_CORE1_OFFSET + CLEAR0);
+	ipi_clear0_regs[6] = (void *)
+		(SMP_CORE_GROUP1_BASE + SMP_CORE2_OFFSET + CLEAR0);
+	ipi_clear0_regs[7] = (void *)
+		(SMP_CORE_GROUP1_BASE + SMP_CORE3_OFFSET + CLEAR0);
+	ipi_clear0_regs[8] = (void *)
+		(SMP_CORE_GROUP2_BASE + SMP_CORE0_OFFSET + CLEAR0);
+	ipi_clear0_regs[9] = (void *)
+		(SMP_CORE_GROUP2_BASE + SMP_CORE1_OFFSET + CLEAR0);
+	ipi_clear0_regs[10] = (void *)
+		(SMP_CORE_GROUP2_BASE + SMP_CORE2_OFFSET + CLEAR0);
+	ipi_clear0_regs[11] = (void *)
+		(SMP_CORE_GROUP2_BASE + SMP_CORE3_OFFSET + CLEAR0);
+	ipi_clear0_regs[12] = (void *)
+		(SMP_CORE_GROUP3_BASE + SMP_CORE0_OFFSET + CLEAR0);
+	ipi_clear0_regs[13] = (void *)
+		(SMP_CORE_GROUP3_BASE + SMP_CORE1_OFFSET + CLEAR0);
+	ipi_clear0_regs[14] = (void *)
+		(SMP_CORE_GROUP3_BASE + SMP_CORE2_OFFSET + CLEAR0);
+	ipi_clear0_regs[15] = (void *)
+		(SMP_CORE_GROUP3_BASE + SMP_CORE3_OFFSET + CLEAR0);
+}
 
-static void *ipi_status0_regs[] = {
-	(void *)(SMP_CORE_GROUP0_BASE + SMP_CORE0_OFFSET + STATUS0),
-	(void *)(SMP_CORE_GROUP0_BASE + SMP_CORE1_OFFSET + STATUS0),
-	(void *)(SMP_CORE_GROUP0_BASE + SMP_CORE2_OFFSET + STATUS0),
-	(void *)(SMP_CORE_GROUP0_BASE + SMP_CORE3_OFFSET + STATUS0),
-	(void *)(SMP_CORE_GROUP1_BASE + SMP_CORE0_OFFSET + STATUS0),
-	(void *)(SMP_CORE_GROUP1_BASE + SMP_CORE1_OFFSET + STATUS0),
-	(void *)(SMP_CORE_GROUP1_BASE + SMP_CORE2_OFFSET + STATUS0),
-	(void *)(SMP_CORE_GROUP1_BASE + SMP_CORE3_OFFSET + STATUS0),
-	(void *)(SMP_CORE_GROUP2_BASE + SMP_CORE0_OFFSET + STATUS0),
-	(void *)(SMP_CORE_GROUP2_BASE + SMP_CORE1_OFFSET + STATUS0),
-	(void *)(SMP_CORE_GROUP2_BASE + SMP_CORE2_OFFSET + STATUS0),
-	(void *)(SMP_CORE_GROUP2_BASE + SMP_CORE3_OFFSET + STATUS0),
-	(void *)(SMP_CORE_GROUP3_BASE + SMP_CORE0_OFFSET + STATUS0),
-	(void *)(SMP_CORE_GROUP3_BASE + SMP_CORE1_OFFSET + STATUS0),
-	(void *)(SMP_CORE_GROUP3_BASE + SMP_CORE2_OFFSET + STATUS0),
-	(void *)(SMP_CORE_GROUP3_BASE + SMP_CORE3_OFFSET + STATUS0),
-};
+static void ipi_status0_regs_init(void)
+{
+	ipi_status0_regs[0] = (void *)
+		(SMP_CORE_GROUP0_BASE + SMP_CORE0_OFFSET + STATUS0);
+	ipi_status0_regs[1] = (void *)
+		(SMP_CORE_GROUP0_BASE + SMP_CORE1_OFFSET + STATUS0);
+	ipi_status0_regs[2] = (void *)
+		(SMP_CORE_GROUP0_BASE + SMP_CORE2_OFFSET + STATUS0);
+	ipi_status0_regs[3] = (void *)
+		(SMP_CORE_GROUP0_BASE + SMP_CORE3_OFFSET + STATUS0);
+	ipi_status0_regs[4] = (void *)
+		(SMP_CORE_GROUP1_BASE + SMP_CORE0_OFFSET + STATUS0);
+	ipi_status0_regs[5] = (void *)
+		(SMP_CORE_GROUP1_BASE + SMP_CORE1_OFFSET + STATUS0);
+	ipi_status0_regs[6] = (void *)
+		(SMP_CORE_GROUP1_BASE + SMP_CORE2_OFFSET + STATUS0);
+	ipi_status0_regs[7] = (void *)
+		(SMP_CORE_GROUP1_BASE + SMP_CORE3_OFFSET + STATUS0);
+	ipi_status0_regs[8] = (void *)
+		(SMP_CORE_GROUP2_BASE + SMP_CORE0_OFFSET + STATUS0);
+	ipi_status0_regs[9] = (void *)
+		(SMP_CORE_GROUP2_BASE + SMP_CORE1_OFFSET + STATUS0);
+	ipi_status0_regs[10] = (void *)
+		(SMP_CORE_GROUP2_BASE + SMP_CORE2_OFFSET + STATUS0);
+	ipi_status0_regs[11] = (void *)
+		(SMP_CORE_GROUP2_BASE + SMP_CORE3_OFFSET + STATUS0);
+	ipi_status0_regs[12] = (void *)
+		(SMP_CORE_GROUP3_BASE + SMP_CORE0_OFFSET + STATUS0);
+	ipi_status0_regs[13] = (void *)
+		(SMP_CORE_GROUP3_BASE + SMP_CORE1_OFFSET + STATUS0);
+	ipi_status0_regs[14] = (void *)
+		(SMP_CORE_GROUP3_BASE + SMP_CORE2_OFFSET + STATUS0);
+	ipi_status0_regs[15] = (void *)
+		(SMP_CORE_GROUP3_BASE + SMP_CORE3_OFFSET + STATUS0);
+}
 
-static void *ipi_en0_regs[] = {
-	(void *)(SMP_CORE_GROUP0_BASE + SMP_CORE0_OFFSET + EN0),
-	(void *)(SMP_CORE_GROUP0_BASE + SMP_CORE1_OFFSET + EN0),
-	(void *)(SMP_CORE_GROUP0_BASE + SMP_CORE2_OFFSET + EN0),
-	(void *)(SMP_CORE_GROUP0_BASE + SMP_CORE3_OFFSET + EN0),
-	(void *)(SMP_CORE_GROUP1_BASE + SMP_CORE0_OFFSET + EN0),
-	(void *)(SMP_CORE_GROUP1_BASE + SMP_CORE1_OFFSET + EN0),
-	(void *)(SMP_CORE_GROUP1_BASE + SMP_CORE2_OFFSET + EN0),
-	(void *)(SMP_CORE_GROUP1_BASE + SMP_CORE3_OFFSET + EN0),
-	(void *)(SMP_CORE_GROUP2_BASE + SMP_CORE0_OFFSET + EN0),
-	(void *)(SMP_CORE_GROUP2_BASE + SMP_CORE1_OFFSET + EN0),
-	(void *)(SMP_CORE_GROUP2_BASE + SMP_CORE2_OFFSET + EN0),
-	(void *)(SMP_CORE_GROUP2_BASE + SMP_CORE3_OFFSET + EN0),
-	(void *)(SMP_CORE_GROUP3_BASE + SMP_CORE0_OFFSET + EN0),
-	(void *)(SMP_CORE_GROUP3_BASE + SMP_CORE1_OFFSET + EN0),
-	(void *)(SMP_CORE_GROUP3_BASE + SMP_CORE2_OFFSET + EN0),
-	(void *)(SMP_CORE_GROUP3_BASE + SMP_CORE3_OFFSET + EN0),
-};
+static void ipi_en0_regs_init(void)
+{
+	ipi_en0_regs[0] = (void *)
+		(SMP_CORE_GROUP0_BASE + SMP_CORE0_OFFSET + EN0);
+	ipi_en0_regs[1] = (void *)
+		(SMP_CORE_GROUP0_BASE + SMP_CORE1_OFFSET + EN0);
+	ipi_en0_regs[2] = (void *)
+		(SMP_CORE_GROUP0_BASE + SMP_CORE2_OFFSET + EN0);
+	ipi_en0_regs[3] = (void *)
+		(SMP_CORE_GROUP0_BASE + SMP_CORE3_OFFSET + EN0);
+	ipi_en0_regs[4] = (void *)
+		(SMP_CORE_GROUP1_BASE + SMP_CORE0_OFFSET + EN0);
+	ipi_en0_regs[5] = (void *)
+		(SMP_CORE_GROUP1_BASE + SMP_CORE1_OFFSET + EN0);
+	ipi_en0_regs[6] = (void *)
+		(SMP_CORE_GROUP1_BASE + SMP_CORE2_OFFSET + EN0);
+	ipi_en0_regs[7] = (void *)
+		(SMP_CORE_GROUP1_BASE + SMP_CORE3_OFFSET + EN0);
+	ipi_en0_regs[8] = (void *)
+		(SMP_CORE_GROUP2_BASE + SMP_CORE0_OFFSET + EN0);
+	ipi_en0_regs[9] = (void *)
+		(SMP_CORE_GROUP2_BASE + SMP_CORE1_OFFSET + EN0);
+	ipi_en0_regs[10] = (void *)
+		(SMP_CORE_GROUP2_BASE + SMP_CORE2_OFFSET + EN0);
+	ipi_en0_regs[11] = (void *)
+		(SMP_CORE_GROUP2_BASE + SMP_CORE3_OFFSET + EN0);
+	ipi_en0_regs[12] = (void *)
+		(SMP_CORE_GROUP3_BASE + SMP_CORE0_OFFSET + EN0);
+	ipi_en0_regs[13] = (void *)
+		(SMP_CORE_GROUP3_BASE + SMP_CORE1_OFFSET + EN0);
+	ipi_en0_regs[14] = (void *)
+		(SMP_CORE_GROUP3_BASE + SMP_CORE2_OFFSET + EN0);
+	ipi_en0_regs[15] = (void *)
+		(SMP_CORE_GROUP3_BASE + SMP_CORE3_OFFSET + EN0);
+}
 
-static void *ipi_mailbox_buf[] = {
-	(void *)(SMP_CORE_GROUP0_BASE + SMP_CORE0_OFFSET + BUF),
-	(void *)(SMP_CORE_GROUP0_BASE + SMP_CORE1_OFFSET + BUF),
-	(void *)(SMP_CORE_GROUP0_BASE + SMP_CORE2_OFFSET + BUF),
-	(void *)(SMP_CORE_GROUP0_BASE + SMP_CORE3_OFFSET + BUF),
-	(void *)(SMP_CORE_GROUP1_BASE + SMP_CORE0_OFFSET + BUF),
-	(void *)(SMP_CORE_GROUP1_BASE + SMP_CORE1_OFFSET + BUF),
-	(void *)(SMP_CORE_GROUP1_BASE + SMP_CORE2_OFFSET + BUF),
-	(void *)(SMP_CORE_GROUP1_BASE + SMP_CORE3_OFFSET + BUF),
-	(void *)(SMP_CORE_GROUP2_BASE + SMP_CORE0_OFFSET + BUF),
-	(void *)(SMP_CORE_GROUP2_BASE + SMP_CORE1_OFFSET + BUF),
-	(void *)(SMP_CORE_GROUP2_BASE + SMP_CORE2_OFFSET + BUF),
-	(void *)(SMP_CORE_GROUP2_BASE + SMP_CORE3_OFFSET + BUF),
-	(void *)(SMP_CORE_GROUP3_BASE + SMP_CORE0_OFFSET + BUF),
-	(void *)(SMP_CORE_GROUP3_BASE + SMP_CORE1_OFFSET + BUF),
-	(void *)(SMP_CORE_GROUP3_BASE + SMP_CORE2_OFFSET + BUF),
-	(void *)(SMP_CORE_GROUP3_BASE + SMP_CORE3_OFFSET + BUF),
-};
+static void ipi_mailbox_buf_init(void)
+{
+	ipi_mailbox_buf[0] = (