Initial import

8 files changed, 1494 insertions, 0 deletions

diff --git a/arch/mips/loongson/loongson-3/Makefile b/arch/mips/loongson/loongson-3/Makefile
new file mode 100644
index 000000000..622fead5e
--- /dev/null
+++ b/arch/mips/loongson/loongson-3/Makefile
@@ -0,0 +1,10 @@
+#
+# Makefile for Loongson-3 family machines
+#
+obj-y			+= irq.o cop2-ex.o platform.o
+
+obj-$(CONFIG_SMP)	+= smp.o
+
+obj-$(CONFIG_NUMA)	+= numa.o
+
+obj-$(CONFIG_RS780_HPET) += hpet.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 000000000..ea13764d0
--- /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_owned;
+	int fr = !test_thread_flag(TIF_32BIT_FPREGS);
+
+	switch (action) {
+	case CU2_EXCEPTION:
+		preempt_disable();
+		fpu_owned = __is_fpu_owner();
+		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 owned, we needn't init or restore fp */
+		if (!fpu_owned) {
+			set_thread_flag(TIF_USEDFPU);
+			if (!used_math()) {
+				_init_fpu(current->thread.fpu.fcr31);
+				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/hpet.c b/arch/mips/loongson/loongson-3/hpet.c
new file mode 100644
index 000000000..5c21cd3bd
--- /dev/null
+++ b/arch/mips/loongson/loongson-3/hpet.c
@@ -0,0 +1,257 @@
+#include <linux/init.h>
+#include <linux/pci.h>
+#include <linux/percpu.h>
+#include <linux/delay.h>
+#include <linux/spinlock.h>
+#include <linux/interrupt.h>
+
+#include <asm/hpet.h>
+#include <asm/time.h>
+
+#define SMBUS_CFG_BASE		(loongson_sysconf.ht_control_base + 0x0300a000)
+#define SMBUS_PCI_REG40		0x40
+#define SMBUS_PCI_REG64		0x64
+#define SMBUS_PCI_REGB4		0xb4
+
+static DEFINE_SPINLOCK(hpet_lock);
+DEFINE_PER_CPU(struct clock_event_device, hpet_clockevent_device);
+
+static unsigned int smbus_read(int offset)
+{
+	return *(volatile unsigned int *)(SMBUS_CFG_BASE + offset);
+}
+
+static void smbus_write(int offset, int data)
+{
+	*(volatile unsigned int *)(SMBUS_CFG_BASE + offset) = data;
+}
+
+static void smbus_enable(int offset, int bit)
+{
+	unsigned int cfg = smbus_read(offset);
+
+	cfg |= bit;
+	smbus_write(offset, cfg);
+}
+
+static int hpet_read(int offset)
+{
+	return *(volatile unsigned int *)(HPET_MMIO_ADDR + offset);
+}
+
+static void hpet_write(int offset, int data)
+{
+	*(volatile unsigned int *)(HPET_MMIO_ADDR + offset) = data;
+}
+
+static void hpet_start_counter(void)
+{
+	unsigned int cfg = hpet_read(HPET_CFG);
+
+	cfg |= HPET_CFG_ENABLE;
+	hpet_write(HPET_CFG, cfg);
+}
+
+static void hpet_stop_counter(void)
+{
+	unsigned int cfg = hpet_read(HPET_CFG);
+
+	cfg &= ~HPET_CFG_ENABLE;
+	hpet_write(HPET_CFG, cfg);
+}
+
+static void hpet_reset_counter(void)
+{
+	hpet_write(HPET_COUNTER, 0);
+	hpet_write(HPET_COUNTER + 4, 0);
+}
+
+static void hpet_restart_counter(void)
+{
+	hpet_stop_counter();
+	hpet_reset_counter();
+	hpet_start_counter();
+}
+
+static void hpet_enable_legacy_int(void)
+{
+	/* Do nothing on Loongson-3 */
+}
+
+static void hpet_set_mode(enum clock_event_mode mode,
+				struct clock_event_device *evt)
+{
+	int cfg = 0;
+
+	spin_lock(&hpet_lock);
+	switch (mode) {
+	case CLOCK_EVT_MODE_PERIODIC:
+		pr_info("set clock event to periodic mode!\n");
+		/* stop counter */
+		hpet_stop_counter();
+
+		/* enables the timer0 to generate a periodic interrupt */
+		cfg = hpet_read(HPET_T0_CFG);
+		cfg &= ~HPET_TN_LEVEL;
+		cfg |= HPET_TN_ENABLE | HPET_TN_PERIODIC |
+				HPET_TN_SETVAL | HPET_TN_32BIT;
+		hpet_write(HPET_T0_CFG, cfg);
+
+		/* set the comparator */
+		hpet_write(HPET_T0_CMP, HPET_COMPARE_VAL);
+		udelay(1);
+		hpet_write(HPET_T0_CMP, HPET_COMPARE_VAL);
+
+		/* start counter */
+		hpet_start_counter();
+		break;
+	case CLOCK_EVT_MODE_SHUTDOWN:
+	case CLOCK_EVT_MODE_UNUSED:
+		cfg = hpet_read(HPET_T0_CFG);
+		cfg &= ~HPET_TN_ENABLE;
+		hpet_write(HPET_T0_CFG, cfg);
+		break;
+	case CLOCK_EVT_MODE_ONESHOT:
+		pr_info("set clock event to one shot mode!\n");
+		cfg = hpet_read(HPET_T0_CFG);
+		/* set timer0 type
+		 * 1 : periodic interrupt
+		 * 0 : non-periodic(oneshot) interrupt
+		 */
+		cfg &= ~HPET_TN_PERIODIC;
+		cfg |= HPET_TN_ENABLE | HPET_TN_32BIT;
+		hpet_write(HPET_T0_CFG, cfg);
+		break;
+	case CLOCK_EVT_MODE_RESUME:
+		hpet_enable_legacy_int();
+		break;
+	}
+	spin_unlock(&hpet_lock);
+}
+
+static int hpet_next_event(unsigned long delta,
+		struct clock_event_device *evt)
+{
+	unsigned int cnt;
+	int res;
+
+	cnt = hpet_read(HPET_COUNTER);
+	cnt += delta;
+	hpet_write(HPET_T0_CMP, cnt);
+
+	res = ((int)(hpet_read(HPET_COUNTER) - cnt) > 0) ? -ETIME : 0;
+	return res;
+}
+
+static irqreturn_t hpet_irq_handler(int irq, void *data)
+{
+	int is_irq;
+	struct clock_event_device *cd;
+	unsigned int cpu = smp_processor_id();
+
+	is_irq = hpet_read(HPET_STATUS);
+	if (is_irq & HPET_T0_IRS) {
+		/* clear the TIMER0 irq status register */
+		hpet_write(HPET_STATUS, HPET_T0_IRS);
+		cd = &per_cpu(hpet_clockevent_device, cpu);
+		cd->event_handler(cd);
+		return IRQ_HANDLED;
+	}
+	return IRQ_NONE;
+}
+
+static struct irqaction hpet_irq = {
+	.handler = hpet_irq_handler,
+	.flags = IRQF_NOBALANCING | IRQF_TIMER,
+	.name = "hpet",
+};
+
+/*
+ * hpet address assignation and irq setting should be done in bios.
+ * but pmon don't do this, we just setup here directly.
+ * The operation under is normal. unfortunately, hpet_setup process
+ * is before pci initialize.
+ *
+ * {
+ *	struct pci_dev *pdev;
+ *
+ *	pdev = pci_get_device(PCI_VENDOR_ID_ATI, PCI_DEVICE_ID_ATI_SBX00_SMBUS, NULL);
+ *	pci_write_config_word(pdev, SMBUS_PCI_REGB4, HPET_ADDR);
+ *
+ *	...
+ * }
+ */
+static void hpet_setup(void)
+{
+	/* set hpet base address */
+	smbus_write(SMBUS_PCI_REGB4, HPET_ADDR);
+
+	/* enable decodeing of access to HPET MMIO*/
+	smbus_enable(SMBUS_PCI_REG40, (1 << 28));
+
+	/* HPET irq enable */
+	smbus_enable(SMBUS_PCI_REG64, (1 << 10));
+
+	hpet_enable_legacy_int();
+}
+
+void __init setup_hpet_timer(void)
+{
+	unsigned int cpu = smp_processor_id();
+	struct clock_event_device *cd;
+
+	hpet_setup();
+
+	cd = &per_cpu(hpet_clockevent_device, cpu);
+	cd->name = "hpet";
+	cd->rating = 320;
+	cd->features = CLOCK_EVT_FEAT_PERIODIC | CLOCK_EVT_FEAT_ONESHOT;
+	cd->set_mode = hpet_set_mode;
+	cd->set_next_event = hpet_next_event;
+	cd->irq = HPET_T0_IRQ;
+	cd->cpumask = cpumask_of(cpu);
+	clockevent_set_clock(cd, HPET_FREQ);
+	cd->max_delta_ns = clockevent_delta2ns(0x7fffffff, cd);
+	cd->min_delta_ns = 5000;
+
+	clockevents_register_device(cd);
+	setup_irq(HPET_T0_IRQ, &hpet_irq);
+	pr_info("hpet clock event device register\n");
+}
+
+static cycle_t hpet_read_counter(struct clocksource *cs)
+{
+	return (cycle_t)hpet_read(HPET_COUNTER);
+}
+
+static void hpet_suspend(struct clocksource *cs)
+{
+}
+
+static void hpet_resume(struct clocksource *cs)
+{
+	hpet_setup();
+	hpet_restart_counter();
+}
+
+static struct clocksource csrc_hpet = {
+	.name = "hpet",
+	/* mips clocksource rating is less than 300, so hpet is better. */
+	.rating = 300,
+	.read = hpet_read_counter,
+	.mask = CLOCKSOURCE_MASK(32),
+	/* oneshot mode work normal with this flag */
+	.flags = CLOCK_SOURCE_IS_CONTINUOUS,
+	.suspend = hpet_suspend,
+	.resume = hpet_resume,
+	.mult = 0,
+	.shift = 10,
+};
+
+int __init init_hpet_clocksource(void)
+{
+	csrc_hpet.mult = clocksource_hz2mult(HPET_FREQ, csrc_hpet.shift);
+	return clocksource_register_hz(&csrc_hpet, HPET_FREQ);
+}
+
+arch_initcall(init_hpet_clocksource);
diff --git a/arch/mips/loongson/loongson-3/irq.c b/arch/mips/loongson/loongson-3/irq.c
new file mode 100644
index 000000000..0f75b6b3d
--- /dev/null
+++ b/arch/mips/loongson/loongson-3/irq.c
@@ -0,0 +1,143 @@
+#include <loongson.h>
+#include <irq.h>
+#include <linux/interrupt.h>
+#include <linux/module.h>
+
+#include <asm/irq_cpu.h>
+#include <asm/i8259.h>
+#include <asm/mipsregs.h>
+
+#include "smp.h"
+
+unsigned int ht_irq[] = {0, 1, 3, 4, 5, 6, 7, 8, 12, 14, 15};
+
+static void ht_irqdispatch(void)
+{
+	unsigned int i, irq;
+
+	irq = LOONGSON_HT1_INT_VECTOR(0);
+	LOONGSON_HT1_INT_VECTOR(0) = irq; /* Acknowledge the IRQs */
+
+	for (i = 0; i < ARRAY_SIZE(ht_irq); i++) {
+		if (irq & (0x1 << ht_irq[i]))
+			do_IRQ(ht_irq[i]);
+	}
+}
+
+void mach_irq_dispatch(unsigned int pending)
+{
+	if (pending & CAUSEF_IP7)
+		do_IRQ(LOONGSON_TIMER_IRQ);
+#if defined(CONFIG_SMP)
+	else if (pending & CAUSEF_IP6)
+		loongson3_ipi_interrupt(NULL);
+#endif
+	else if (pending & CAUSEF_IP3)
+		ht_irqdispatch();
+	else if (pending & CAUSEF_IP2)
+		do_IRQ(LOONGSON_UART_IRQ);
+	else {
+		pr_err("%s : spurious interrupt\n", __func__);
+		spurious_interrupt();
+	}
+}
+
+static struct irqaction cascade_irqaction = {
+	.handler = no_action,
+	.flags = IRQF_NO_SUSPEND,
+	.name = "cascade",
+};
+
+static inline void mask_loongson_irq(struct irq_data *d)
+{
+	clear_c0_status(0x100 << (d->irq - MIPS_CPU_IRQ_BASE));
+	irq_disable_hazard();
+
+	/* Workaround: UART IRQ may deliver to any core */
+	if (d->irq == LOONGSON_UART_IRQ) {
+		int cpu = smp_processor_id();
+		int node_id = cpu_logical_map(cpu) / loongson_sysconf.cores_per_node;
+		int core_id = cpu_logical_map(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);
+	}
+}
+
+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();
+		int node_id = cpu_logical_map(cpu) / loongson_sysconf.cores_per_node;
+		int core_id = cpu_logical_map(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));
+	irq_enable_hazard();
+}
+
+ /* For MIPS IRQs which shared by all cores */
+static struct irq_chip loongson_irq_chip = {
+	.name		= "Loongson",
+	.irq_ack	= mask_loongson_irq,
+	.irq_mask	= mask_loongson_irq,
+	.irq_mask_ack	= mask_loongson_irq,
+	.irq_unmask	= unmask_loongson_irq,
+	.irq_eoi	= unmask_loongson_irq,
+};
+
+void irq_router_init(void)
+{
+	int i;
+
+	/* route LPC int to cpu core0 int 0 */
+	LOONGSON_INT_ROUTER_LPC =
+		LOONGSON_INT_COREx_INTy(loongson_sysconf.boot_cpu_id, 0);
+	/* route HT1 int0 ~ int7 to cpu core0 INT1*/
+	for (i = 0; i < 8; i++)
+		LOONGSON_INT_ROUTER_HT1(i) =
+			LOONGSON_INT_COREx_INTy(loongson_sysconf.boot_cpu_id, 1);
+	/* enable HT1 interrupt */
+	LOONGSON_HT1_INTN_EN(0) = 0xffffffff;
+	/* enable router interrupt intenset */
+	LOONGSON_INT_ROUTER_INTENSET =
+		LOONGSON_INT_ROUTER_INTEN | (0xffff << 16) | 0x1 << 10;
+}
+
+void __init mach_init_irq(void)
+{
+	clear_c0_status(ST0_IM | ST0_BEV);
+
+	irq_router_init();
+	mips_cpu_irq_init();
+	init_i8259_irqs();
+	irq_set_chip_and_handler(LOONGSON_UART_IRQ,
+			&loongson_irq_chip, handle_level_irq);
+
+	/* setup HT1 irq */
+	setup_irq(LOONGSON_HT1_IRQ, &cascade_irqaction);
+
+	set_c0_status(STATUSF_IP2 | STATUSF_IP6);
+}
+
+#ifdef CONFIG_HOTPLUG_CPU
+
+void fixup_irqs(void)
+{
+	irq_cpu_offline();
+	clear_c0_status(ST0_IM);
+}
+
+#endif
diff --git a/arch/mips/loongson/loongson-3/numa.c b/arch/mips/loongson/loongson-3/numa.c
new file mode 100644
index 000000000..12d14ed48
--- /dev/null
+++ b/arch/mips/loongson/loongson-3/numa.c
@@ -0,0 +1,296 @@
+/*
+ * 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/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];
+EXPORT_SYMBOL(__node_distances);
+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, active_cpu = 0;
+
+	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);
+			cpumask_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;
+
+		if (loongson_sysconf.reserved_cpus_mask & (1<<cpu))
+			continue;
+
+		cpumask_set_cpu(active_cpu, &__node_data[(node)]->cpumask);
+		pr_info("NUMA: set cpumask cpu %d on node %d\n", active_cpu, node);
+
+		active_cpu++;
+	}
+}
+
+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/platform.c b/arch/mips/loongson/loongson-3/platform.c
new file mode 100644
index 000000000..25a97cc0e
--- /dev/null
+++ b/arch/mips/loongson/loongson-3/platform.c
@@ -0,0 +1,43 @@
+/*
+ * Copyright (C) 2009 Lemote Inc.
+ * Author: Wu Zhangjin, wuzhangjin@gmail.com
+ *         Xiang Yu, xiangy@lemote.com
+ *         Chen Huacai, chenhc@lemote.com
+ *
+ * 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/err.h>
+#include <linux/slab.h>
+#include <linux/platform_device.h>
+#include <asm/bootinfo.h>
+#include <boot_param.h>
+#include <loongson_hwmon.h>
+#include <workarounds.h>
+
+static int __init loongson3_platform_init(void)
+{
+	int i;
+	struct platform_device *pdev;
+
+	if (loongson_sysconf.ecname[0] != '\0')
+		platform_device_register_simple(loongson_sysconf.ecname, -1, NULL, 0);
+
+	for (i = 0; i < loongson_sysconf.nr_sensors; i++) {
+		if (loongson_sysconf.sensors[i].type > SENSOR_FAN)
+			continue;
+
+		pdev = kzalloc(sizeof(struct platform_device), GFP_KERNEL);
+		pdev->name = loongson_sysconf.sensors[i].name;
+		pdev->id = loongson_sysconf.sensors[i].id;
+		pdev->dev.platform_data = &loongson_sysconf.sensors[i];
+		platform_device_register(pdev);
+	}
+
+	return 0;
+}
+
+arch_initcall(loongson3_platform_init);
diff --git a/arch/mips/loongson/loongson-3/smp.c b/arch/mips/loongson/loongson-3/smp.c
new file mode 100644
index 000000000..509877c6e
--- /dev/null
+++ b/arch/mips/loongson/loongson-3/smp.c
@@ -0,0 +1,652 @@
+/*
+ * Copyright (C) 2010, 2011, 2012, Lemote, Inc.
+ * Author: Chen Huacai, chenhc@lemote.com
+ *
+ * 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.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ */
+
+#include <linux/init.h>
+#include <linux/cpu.h>
+#include <linux/sched.h>
+#include <linux/smp.h>
+#include <linux/cpufreq.h>
+#include <asm/processor.h>
+#include <asm/time.h>
+#include <asm/clock.h>
+#include <asm/tlbflush.h>
+#include <asm/cacheflush.h>
+#include <loongson.h>
+#include <workarounds.h>
+
+#include "smp.h"
+
+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 */
+#define loongson3_ipi_read64(addr) readq(addr)
+/* write a 32bit value to ipi register */
+#define loongson3_ipi_write32(action, addr)	\
+	do {					\
+		writel(action, addr);		\
+		__wbflush();			\
+	} while (0)
+/* write a 64bit value to ipi register */
+#define loongson3_ipi_write64(action, addr)	\
+	do {					\
+		writeq(action, addr);		\
+		__wbflush();			\
+	} while (0)
+
+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_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_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_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_init(void)
+{
+	ipi_mailbox_buf[0] = (void *)
+		(SMP_CORE_GROUP0_BASE + SMP_CORE0_OFFSET + BUF);
+	ipi_mailbox_buf[1] = (void *)
+		(SMP_CORE_GROUP0_BASE + SMP_CORE1_OFFSET + BUF);
+	ipi_mailbox_buf[2] = (void *)
+		(SMP_CORE_GROUP0_BASE + SMP_CORE2_OFFSET + BUF);
+	ipi_mailbox_buf[3] = (void *)
+		(SMP_CORE_GROUP0_BASE + SMP_CORE3_OFFSET + BUF);
+	ipi_mailbox_buf[4] = (void *)
+		(SMP_CORE_GROUP1_BASE + SMP_CORE0_OFFSET + BUF);
+	ipi_mailbox_buf[5] = (void *)
+		(SMP_CORE_GROUP1_BASE + SMP_CORE1_OFFSET + BUF);
+	ipi_mailbox_buf[6] = (void *)
+		(SMP_CORE_GROUP1_BASE + SMP_CORE2_OFFSET + BUF);
+	ipi_mailbox_buf[7] = (void *)
+		(SMP_CORE_GROUP1_BASE + SMP_CORE3_OFFSET + BUF);
+	ipi_mailbox_buf[8] = (void *)
+		(SMP_CORE_GROUP2_BASE + SMP_CORE0_OFFSET + BUF);
+	ipi_mailbox_buf[9] = (void *)
+		(SMP_CORE_GROUP2_BASE + SMP_CORE1_OFFSET + BUF);
+	ipi_mailbox_buf[10] = (void *)
+		(SMP_CORE_GROUP2_BASE + SMP_CORE2_OFFSET + BUF);
+	ipi_mailbox_buf[11] = (void *)
+		(SMP_CORE_GROUP2_BASE + SMP_CORE3_OFFSET + BUF);
+	ipi_mailbox_buf[12] = (void *)
+		(SMP_CORE_GROUP3_BASE + SMP_CORE0_OFFSET + BUF);
+	ipi_mailbox_buf[13] = (void *)
+		(SMP_CORE_GROUP3_BASE + SMP_CORE1_OFFSET + BUF);
+	ipi_mailbox_buf[14] = (void *)
+		(SMP_CORE_GROUP3_BASE + SMP_CORE2_OFFSET + BUF);
+	ipi_mailbox_buf[15] = (void *)
+		(SMP_CORE_GROUP3_BASE + SMP_CORE3_OFFSET + BUF);
+}
+
+/*
+ * Simple enough, just poke the appropriate ipi register
+ */
+static void loongson3_send_ipi_single(int cpu, unsigned int action)
+{
+	loongson3_ipi_write32((u32)action, ipi_set0_regs[cpu_logical_map(cpu)]);
+}
+
+static void
+loongson3_send_ipi_mask(const struct cpumask *mask, unsigned int action)
+{
+	unsigned int i;
+
+	for_each_cpu(i, mask)
+		loongson3_ipi_write32((u32)action, ipi_set0_regs[cpu_logical_map(i)]);
+}
+
+void loongson3_ipi_interrupt(struct pt_regs *regs)
+{
+	int i, cpu = smp_processor_id();
+	unsigned int action, c0count;
+
+	/* Load the ipi register to figure out what we're supposed to do */
+	action = loongson3_ipi_read32(ipi_status0_regs[cpu_logical_map(cpu)]);
+
+	/* Clear the ipi register to clear the interrupt */
+	loongson3_ipi_write32((u32)action, ipi_clear0_regs[cpu_logical_map(cpu)]);
+
+	if (action & SMP_RESCHEDULE_YOURSELF)
+		scheduler_ipi();
+
+	if (action & SMP_CALL_FUNCTION)
+		smp_call_function_interrupt();
+
+	if (action & SMP_ASK_C0COUNT) {
+		BUG_ON(cpu != 0);
+		c0count = read_c0_count();
+		for (i = 1; i < num_possible_cpus(); i++)
+			per_cpu(core0_c0count, i) = c0count;
+	}
+}
+
+#define MAX_LOOPS 1111
+/*
+ * SMP init and finish on secondary CPUs
+ */
+static void loongson3_init_secondary(void)
+{
+	int i;
+	uint32_t initcount;
+	unsigned int cpu = smp_processor_id();
+	unsigned int imask = STATUSF_IP7 | STATUSF_IP6 |
+			     STATUSF_IP3 | STATUSF_IP2;
+
+	/* Set interrupt mask, but don't enable */
+	change_c0_status(ST0_IM, imask);
+
+	for (i = 0; i < num_possible_cpus(); i++)
+		loongson3_ipi_write32(0xffffffff, ipi_en0_regs[cpu_logical_map(i)]);
+
+	per_cpu(cpu_state, cpu) = CPU_ONLINE;
+	cpu_data[cpu].core =
+		cpu_logical_map(cpu) % loongson_sysconf.cores_per_package;
+	cpu_data[cpu].package =
+		cpu_logical_map(cpu) / loongson_sysconf.cores_per_package;
+
+	i = 0;
+	__this_cpu_write(core0_c0count, 0);
+	loongson3_send_ipi_single(0, SMP_ASK_C0COUNT);
+	while (!__this_cpu_read(core0_c0count)) {
+		i++;
+		cpu_relax();
+	}
+
+	if (i > MAX_LOOPS)
+		i = MAX_LOOPS;
+	initcount = __this_cpu_read(core0_c0count) + i;
+	write_c0_count(initcount);
+}
+
+static void loongson3_smp_finish(void)
+{
+	int cpu = smp_processor_id();
+
+	write_c0_compare(read_c0_count() + mips_hpt_frequency/HZ);
+	local_irq_enable();
+	loongson3_ipi_write64(0,
+			(void *)(ipi_mailbox_buf[cpu_logical_map(cpu)]+0x0));
+	pr_info("CPU#%d finished, CP0_ST=%x\n",
+			smp_processor_id(), read_c0_status());
+}
+
+static void __init loongson3_smp_setup(void)
+{
+	int i = 0, num = 0; /* i: physical id, num: logical id */
+
+	init_cpu_possible(cpu_none_mask);
+
+	/* For unified kernel, NR_CPUS is the maximum possible value,
+	 * loongson_sysconf.nr_cpus is the really present value */
+	while (i < loongson_sysconf.nr_cpus) {
+		if (loongson_sysconf.reserved_cpus_mask & (1<<i)) {
+			/* Reserved physical CPU cores */
+			__cpu_number_map[i] = -1;
+		} else {
+			__cpu_number_map[i] = num;
+			__cpu_logical_map[num] = i;
+			set_cpu_possible(num, true);
+			num++;
+		}
+		i++;
+	}
+	pr_info("Detected %i available CPU(s)\n", num);
+
+	while (num < loongson_sysconf.nr_cpus) {
+		__cpu_logical_map[num] = -1;
+		num++;
+	}
+
+	ipi_set0_regs_init();
+	ipi_clear0_regs_init();
+	ipi_status0_regs_init();
+	ipi_en0_regs_init();
+	ipi_mailbox_buf_init();
+	cpu_data[0].core = cpu_logical_map(0) % loongson_sysconf.cores_per_package;
+	cpu_data[0].package = cpu_logical_map(0) / loongson_sysconf.cores_per_package;
+}
+
+static void __init loongson3_prepare_cpus(unsigned int max_cpus)
+{
+	init_cpu_present(cpu_possible_mask);
+	per_cpu(cpu_state, smp_processor_id()) = CPU_ONLINE;
+}
+
+/*
+ * Setup the PC, SP, and GP of a secondary processor and start it runing!
+ */
+static void loongson3_boot_secondary(int cpu, struct task_struct *idle)
+{
+	unsigned long startargs[4];
+
+	pr_info("Booting CPU#%d...\n", cpu);
+
+	/* startargs[] are initial PC, SP and GP for secondary CPU */
+	startargs[0] = (unsigned long)&smp_bootstrap;
+	startargs[1] = (unsigned long)__KSTK_TOS(idle);
+	startargs[2] = (unsigned long)task_thread_info(idle);
+	startargs[3] = 0;
+
+	pr_debug("CPU#%d, func_pc=%lx, sp=%lx, gp=%lx\n",
+			cpu, startargs[0], startargs[1], startargs[2]);
+
+	loongson3_ipi_write64(startargs[3],
+			(void *)(ipi_mailbox_buf[cpu_logical_map(cpu)]+0x18));
+	loongson3_ipi_write64(startargs[2],
+			(void *)(ipi_mailbox_buf[cpu_logical_map(cpu)]+0x10));
+	loongson3_ipi_write64(startargs[1],
+			(void *)(ipi_mailbox_buf[cpu_logical_map(cpu)]+0x8));
+	loongson3_ipi_write64(startargs[0],
+			(void *)(ipi_mailbox_buf[cpu_logical_map(cpu)]+0x0));
+}
+
+#ifdef CONFIG_HOTPLUG_CPU
+
+static int loongson3_cpu_disable(void)
+{
+	unsigned long flags;
+	unsigned int cpu = smp_processor_id();
+
+	if (cpu == 0)
+		return -EBUSY;
+
+	set_cpu_online(cpu, false);
+	cpumask_clear_cpu(cpu, &cpu_callin_map);
+	local_irq_save(flags);
+	fixup_irqs();
+	local_irq_restore(flags);
+	flush_cache_all();
+	local_flush_tlb_all();
+
+	return 0;
+}
+
+
+static void loongson3_cpu_die(unsigned int cpu)
+{
+	while (per_cpu(cpu_state, cpu) != CPU_DEAD)
+		cpu_relax();
+
+	mb();
+}
+
+/* To shutdown a core in Loongson 3, the target core should go to CKSEG1 and
+ * flush all L1 entries at first. Then, another core (usually Core 0) can
+ * safely disable the clock of the target core. loongson3_play_dead() is
+ * called via CKSEG1 (uncached and unmmaped) */
+static void loongson3a_play_dead(int *state_addr)
+{
+	register int val;
+	register long cpuid, core, node, count;
+	register void *addr, *base, *initfunc;
+
+	__asm__ __volatile__(
+		"   .set push                     \n"
+		"   .set noreorder                \n"
+		"   li %[addr], 0x80000000        \n" /* KSEG0 */
+		"1: cache 0, 0(%[addr])           \n" /* flush L1 ICache */
+		"   cache 0, 1(%[addr])           \n"
+		"   cache 0, 2(%[addr])           \n"
+		"   cache 0, 3(%[addr])           \n"
+		"   cache 1, 0(%[addr])           \n" /* flush L1 DCache */
+		"   cache 1, 1(%[addr])           \n"
+		"   cache 1, 2(%[addr])           \n"
+		"   cache 1, 3(%[addr])           \n"
+		"   addiu %[sets], %[sets], -1    \n"
+		"   bnez  %[sets], 1b             \n"
+		"   addiu %[addr], %[addr], 0x20  \n"
+		"   li    %[val], 0x7             \n" /* *state_addr = CPU_DEAD; */
+		"   sw    %[val], (%[state_addr]) \n"
+		"   sync                          \n"
+		"   cache 21, (%[state_addr])     \n" /* flush entry of *state_addr */
+		"   .set pop                      \n"
+		: [addr] "=&r" (addr), [val] "=&r" (val)
+		: [state_addr] "r" (state_addr),
+		  [sets] "r" (cpu_data[smp_processor_id()].dcache.sets));
+
+	__asm__ __volatile__(
+		"   .set push                         \n"
+		"   .set noreorder                    \n"
+		"   .set mips64                       \n"
+		"   mfc0  %[cpuid], $15, 1            \n"
+		"   andi  %[cpuid], 0x3ff             \n"
+		"   dli   %[base], 0x900000003ff01000 \n"
+		"   andi  %[core], %[cpuid], 0x3      \n"
+		"   sll   %[core], 8                  \n" /* get core id */
+		"   or    %[base], %[base], %[core]   \n"
+		"   andi  %[node], %[cpuid], 0xc      \n"
+		"   dsll  %[node], 42                 \n" /* get node id */
+		"   or    %[base], %[base], %[node]   \n"
+		"1: li    %[count], 0x100             \n" /* wait for init loop */
+		"2: bnez  %[count], 2b                \n" /* limit mailbox access */
+		"   addiu %[count], -1                \n"
+		"   ld    %[initfunc], 0x20(%[base])  \n" /* get PC via mailbox */
+		"   beqz  %[initfunc], 1b             \n"
+		"   nop                               \n"
+		"   ld    $sp, 0x28(%[base])          \n" /* get SP via mailbox */
+		"   ld    $gp, 0x30(%[base])          \n" /* get GP via mailbox */
+		"   ld    $a1, 0x38(%[base])          \n"
+		"   jr    %[initfunc]                 \n" /* jump to initial PC */
+		"   nop                               \n"
+		"   .set pop                          \n"
+		: [core] "=&r" (core), [node] "=&r" (node),
+		  [base] "=&r" (base), [cpuid] "=&r" (cpuid),
+		  [count] "=&r" (count), [initfunc] "=&r" (initfunc)
+		: /* No Input */
+		: "a1");
+}
+
+static void loongson3b_play_dead(int *state_addr)
+{
+	register int val;
+	register long cpuid, core, node, count;
+	register void *addr, *base, *initfunc;
+
+	__asm__ __volatile__(
+		"   .set push                     \n"
+		"   .set noreorder                \n"
+		"   li %[addr], 0x80000000        \n" /* KSEG0 */
+		"1: cache 0, 0(%[addr])           \n" /* flush L1 ICache */
+		"   cache 0, 1(%[addr])           \n"
+		"   cache 0, 2(%[addr])           \n"
+		"   cache 0, 3(%[addr])           \n"
+		"   cache 1, 0(%[addr])           \n" /* flush L1 DCache */
+		"   cache 1, 1(%[addr])           \n"
+		"   cache 1, 2(%[addr])           \n"
+		"   cache 1, 3(%[addr])           \n"
+		"   addiu %[sets], %[sets], -1    \n"
+		"   bnez  %[sets], 1b             \n"
+		"   addiu %[addr], %[addr], 0x20  \n"
+		"   li    %[val], 0x7             \n" /* *state_addr = CPU_DEAD; */
+		"   sw    %[val], (%[state_addr]) \n"
+		"   sync                          \n"
+		"   cache 21, (%[state_addr])     \n" /* flush entry of *state_addr */
+		"   .set pop                      \n"
+		: [addr] "=&r" (addr), [val] "=&r" (val)
+		: [state_addr] "r" (state_addr),
+		  [sets] "r" (cpu_data[smp_processor_id()].dcache.sets));
+
+	__asm__ __volatile__(
+		"   .set push                         \n"
+		"   .set noreorder                    \n"
+		"   .set mips64                       \n"
+		"   mfc0  %[cpuid], $15, 1            \n"
+		"   andi  %[cpuid], 0x3ff             \n"
+		"   dli   %[base], 0x900000003ff01000 \n"
+		"   andi  %[core], %[cpuid], 0x3      \n"
+		"   sll   %[core], 8                  \n" /* get core id */
+		"   or    %[base], %[base], %[core]   \n"
+		"   andi  %[node], %[cpuid], 0xc      \n"
+		"   dsll  %[node], 42                 \n" /* get node id */
+		"   or    %[base], %[base], %[node]   \n"
+		"   dsrl  %[node], 30                 \n" /* 15:14 */
+		"   or    %[base], %[base], %[node]   \n"
+		"1: li    %[count], 0x100             \n" /* wait for init loop */
+		"2: bnez  %[count], 2b                \n" /* limit mailbox access */
+		"   addiu %[count], -1                \n"
+		"   ld    %[initfunc], 0x20(%[base])  \n" /* get PC via mailbox */
+		"   beqz  %[initfunc], 1b             \n"
+		"   nop                               \n"
+		"   ld    $sp, 0x28(%[base])          \n" /* get SP via mailbox */
+		"   ld    $gp, 0x30(%[base])          \n" /* get GP via mailbox */
+		"   ld    $a1, 0x38(%[base])          \n"
+		"   jr    %[initfunc]                 \n" /* jump to initial PC */
+		"   nop                               \n"
+		"   .set pop                          \n"
+		: [core] "=&r" (core), [node] "=&r" (node),
+		  [base] "=&r" (base), [cpuid] "=&r" (cpuid),
+		  [count] "=&r" (count), [initfunc] "=&r" (initfunc)
+		: /* No Input */
+		: "a1");
+}
+
+void play_dead(void)
+{
+	int *state_addr;
+	unsigned int cpu = smp_processor_id();
+	void (*play_dead_at_ckseg1)(int *);
+
+	idle_task_exit();
+	switch (loongson_sysconf.cputype) {
+	case Loongson_3A:
+	default:
+		play_dead_at_ckseg1 =
+			(void *)CKSEG1ADDR((unsigned long)loongson3a_play_dead);
+		break;
+	case Loongson_3B:
+		play_dead_at_ckseg1 =
+			(void *)CKSEG1ADDR((unsigned long)loongson3b_play_dead);
+		break;
+	}
+	state_addr = &per_cpu(cpu_state, cpu);
+	mb();
+	play_dead_at_ckseg1(state_addr);
+}
+
+void loongson3_disable_clock(int cpu)
+{
+	uint64_t core_id = cpu_data[cpu].core;
+	uint64_t package_id = cpu_data[cpu].package;
+
+	if (loongson_sysconf.cputype == Loongson_3A) {
+		LOONGSON_CHIPCFG(package_id) &= ~(1 << (12 + core_id));
+	} else if (loongson_sysconf.cputype == Loongson_3B) {
+		if (!(loongson_sysconf.workarounds & WORKAROUND_CPUHOTPLUG))
+			LOONGSON_FREQCTRL(package_id) &= ~(1 << (core_id * 4 + 3));
+	}
+}
+
+void loongson3_enable_clock(int cpu)
+{
+	uint64_t core_id = cpu_data[cpu].core;
+	uint64_t package_id = cpu_data[cpu].package;
+
+	if (loongson_sysconf.cputype == Loongson_3A) {
+		LOONGSON_CHIPCFG(package_id) |= 1 << (12 + core_id);
+	} else if (loongson_sysconf.cputype == Loongson_3B) {
+		if (!(loongson_sysconf.workarounds & WORKAROUND_CPUHOTPLUG))
+			LOONGSON_FREQCTRL(package_id) |= 1 << (core_id * 4 + 3);
+	}
+}
+
+#define CPU_POST_DEAD_FROZEN	(CPU_POST_DEAD | CPU_TASKS_FROZEN)
+static int loongson3_cpu_callback(struct notifier_block *nfb,
+	unsigned long action, void *hcpu)
+{
+	unsigned int cpu = (unsigned long)hcpu;
+
+	switch (action) {
+	case CPU_POST_DEAD:
+	case CPU_POST_DEAD_FROZEN:
+		pr_info("Disable clock for CPU#%d\n", cpu);
+		loongson3_disable_clock(cpu);
+		break;
+	case CPU_UP_PREPARE:
+	case CPU_UP_PREPARE_FROZEN:
+		pr_info("Enable clock for CPU#%d\n", cpu);
+		loongson3_enable_clock(cpu);
+		break;
+	}
+
+	return NOTIFY_OK;
+}
+
+static int register_loongson3_notifier(void)
+{
+	hotcpu_notifier(loongson3_cpu_callback, 0);
+	return 0;
+}
+early_initcall(register_loongson3_notifier);
+
+#endif
+
+struct plat_smp_ops loongson3_smp_ops = {
+	.send_ipi_single = loongson3_send_ipi_single,
+	.send_ipi_mask = loongson3_send_ipi_mask,
+	.init_secondary = loongson3_init_secondary,
+	.smp_finish = loongson3_smp_finish,
+	.boot_secondary = loongson3_boot_secondary,
+	.smp_setup = loongson3_smp_setup,
+	.prepare_cpus = loongson3_prepare_cpus,
+#ifdef CONFIG_HOTPLUG_CPU
+	.cpu_disable = loongson3_cpu_disable,
+	.cpu_die = loongson3_cpu_die,
+#endif
+};
diff --git a/arch/mips/loongson/loongson-3/smp.h b/arch/mips/loongson/loongson-3/smp.h
new file mode 100644
index 000000000..d98ff654b
--- /dev/null
+++ b/arch/mips/loongson/loongson-3/smp.h
@@ -0,0 +1,30 @@
+#ifndef __LOONGSON_SMP_H_
+#define __LOONGSON_SMP_H_
+
+/* 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	(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
+
+/* 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
+
+#endif