MIPS: Add NUMA support for Loongson-3

Multiple Loongson-3A chips can be interconnected with HT0-bus. This is
a CC-NUMA system that every chip (node) has its own local memory and
cache coherency is maintained by hardware. The 64-bit physical memory
address format is as follows:

0x-0000-YZZZ-ZZZZ-ZZZZ

The high 16 bits should be 0, which means the real physical address
supported by Loongson-3 is 48-bit. The "Y" bits is the base address of
each node, which can be also considered as the node-id. The "Z" bits is
the address offset within a node, which means every node has a 44 bits
address space.

Macros XPHYSADDR and MAX_PHYSMEM_BITS are modified unconditionally,
because many other MIPS CPUs have also extended their address spaces.

Signed-off-by: Huacai Chen <[email protected]>
Cc: John Crispin <[email protected]>
Cc: Steven J. Hill <[email protected]>
Cc: Aurelien Jarno <[email protected]>
Cc: [email protected]
Cc: Fuxin Zhang <[email protected]>
Cc: Zhangjin Wu <[email protected]>
Patchwork: https://patchwork.linux-mips.org/patch/7187/
Signed-off-by: Ralf Baechle <[email protected]>

Author: chenhuacai

arch/mips/include/asm/addrspace.h

@@ -52,7 +52,7 @@
  */
 #define CPHYSADDR(a)		((_ACAST32_(a)) & 0x1fffffff)
 #define XPHYSADDR(a)		((_ACAST64_(a)) &			\
-				 _CONST64_(0x000000ffffffffff))
+				 _CONST64_(0x0000ffffffffffff))
 
 #ifdef CONFIG_64BIT
 

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

@@ -146,6 +146,9 @@ struct boot_params {
 
 struct loongson_system_configuration {
 	u32 nr_cpus;
+	u32 nr_nodes;
+	int cores_per_node;
+	int cores_per_package;
 	enum loongson_cpu_type cputype;
 	u64 ht_control_base;
 	u64 pci_mem_start_addr;

arch/mips/include/asm/mach-loongson/kernel-entry-init.h

@@ -0,0 +1,52 @@
+/*
+ * 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) 2005 Embedded Alley Solutions, Inc
+ * Copyright (C) 2005 Ralf Baechle ([email protected])
+ * Copyright (C) 2009 Jiajie Chen ([email protected])
+ * Copyright (C) 2012 Huacai Chen ([email protected])
+ */
+#ifndef __ASM_MACH_LOONGSON_KERNEL_ENTRY_H
+#define __ASM_MACH_LOONGSON_KERNEL_ENTRY_H
+
+/*
+ * Override macros used in arch/mips/kernel/head.S.
+ */
+	.macro	kernel_entry_setup
+#ifdef CONFIG_CPU_LOONGSON3
+	.set	push
+	.set	mips64
+	/* Set LPA on LOONGSON3 config3 */
+	mfc0	t0, $16, 3
+	or	t0, (0x1 << 7)
+	mtc0	t0, $16, 3
+	/* Set ELPA on LOONGSON3 pagegrain */
+	li	t0, (0x1 << 29)
+	mtc0	t0, $5, 1
+	_ehb
+	.set	pop
+#endif
+	.endm
+
+/*
+ * Do SMP slave processor setup.
+ */
+	.macro	smp_slave_setup
+#ifdef CONFIG_CPU_LOONGSON3
+	.set	push
+	.set	mips64
+	/* Set LPA on LOONGSON3 config3 */
+	mfc0	t0, $16, 3
+	or	t0, (0x1 << 7)
+	mtc0	t0, $16, 3
+	/* Set ELPA on LOONGSON3 pagegrain */
+	li	t0, (0x1 << 29)
+	mtc0	t0, $5, 1
+	_ehb
+	.set	pop
+#endif
+	.endm
+
+#endif /* __ASM_MACH_LOONGSON_KERNEL_ENTRY_H */

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

@@ -0,0 +1,53 @@
+/*
+ * Copyright (C) 2010 Loongson Inc. & Lemote Inc. &
+ *                    Insititute of Computing Technology
+ * Author:  Xiang Gao, [email protected]
+ *          Huacai Chen, [email protected]
+ *          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.
+ */
+#ifndef _ASM_MACH_MMZONE_H
+#define _ASM_MACH_MMZONE_H
+
+#include <boot_param.h>
+#define NODE_ADDRSPACE_SHIFT 44
+#define NODE0_ADDRSPACE_OFFSET 0x000000000000UL
+#define NODE1_ADDRSPACE_OFFSET 0x100000000000UL
+#define NODE2_ADDRSPACE_OFFSET 0x200000000000UL
+#define NODE3_ADDRSPACE_OFFSET 0x300000000000UL
+
+#define pa_to_nid(addr)  (((addr) & 0xf00000000000) >> NODE_ADDRSPACE_SHIFT)
+
+#define LEVELS_PER_SLICE 128
+
+struct slice_data {
+	unsigned long irq_enable_mask[2];
+	int level_to_irq[LEVELS_PER_SLICE];
+};
+
+struct hub_data {
+	cpumask_t	h_cpus;
+	unsigned long slice_map;
+	unsigned long irq_alloc_mask[2];
+	struct slice_data slice[2];
+};
+
+struct node_data {
+	struct pglist_data pglist;
+	struct hub_data hub;
+	cpumask_t cpumask;
+};
+
+extern struct node_data *__node_data[];
+
+#define NODE_DATA(n)		(&__node_data[(n)]->pglist)
+#define hub_data(n)		(&__node_data[(n)]->hub)
+
+extern void setup_zero_pages(void);
+extern void __init prom_init_numa_memory(void);
+
+#endif /* _ASM_MACH_MMZONE_H */

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

@@ -0,0 +1,23 @@
+#ifndef _ASM_MACH_TOPOLOGY_H
+#define _ASM_MACH_TOPOLOGY_H
+
+#ifdef CONFIG_NUMA
+
+#define cpu_to_node(cpu)	((cpu) >> 2)
+#define parent_node(node)	(node)
+#define cpumask_of_node(node)	(&__node_data[(node)]->cpumask)
+
+struct pci_bus;
+extern int pcibus_to_node(struct pci_bus *);
+
+#define cpumask_of_pcibus(bus)	(cpu_online_mask)
+
+extern unsigned char __node_distances[MAX_NUMNODES][MAX_NUMNODES];
+
+#define node_distance(from, to)	(__node_distances[(from)][(to)])
+
+#endif
+
+#include <asm-generic/topology.h>
+
+#endif /* _ASM_MACH_TOPOLOGY_H */

arch/mips/include/asm/sparsemem.h

@@ -11,7 +11,7 @@
 #else
 # define SECTION_SIZE_BITS	28
 #endif
-#define MAX_PHYSMEM_BITS	35
+#define MAX_PHYSMEM_BITS	48
 
 #endif /* CONFIG_SPARSEMEM */
 #endif /* _MIPS_SPARSEMEM_H */

arch/mips/kernel/setup.c

@@ -282,7 +282,7 @@ static unsigned long __init init_initrd(void)
  * Initialize the bootmem allocator. It also setup initrd related data
  * if needed.
  */
-#ifdef CONFIG_SGI_IP27
+#if defined(CONFIG_SGI_IP27) || (defined(CONFIG_CPU_LOONGSON3) && defined(CONFIG_NUMA))
 
 static void __init bootmem_init(void)
 {

arch/mips/loongson/Kconfig

@@ -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

arch/mips/loongson/common/env.c

@@ -80,17 +80,24 @@ 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;
 		loongson_chipcfg[0] = 0x900000001fe00180;
 		loongson_chipcfg[1] = 0x900010001fe00180;
 		loongson_chipcfg[2] = 0x900020001fe00180;
 		loongson_chipcfg[3] = 0x900030001fe00180;
 	} 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;

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();