diff --git a/arch/mips/include/asm/addrspace.h b/arch/mips/include/asm/addrspace.h index 3f745459fdb58ee53e228a71cb27a737db4f7800..3b0e51d5a613f70ff667916540d98bba2e87ae6f 100644 --- a/arch/mips/include/asm/addrspace.h +++ b/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 diff --git a/arch/mips/include/asm/mach-loongson/boot_param.h b/arch/mips/include/asm/mach-loongson/boot_param.h index 829a7ec185fbb8271d815a777ba24a5fbe2410fd..8b06c96cce1f535cf3cf0bd6928bd586cede7751 100644 --- a/arch/mips/include/asm/mach-loongson/boot_param.h +++ b/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; diff --git a/arch/mips/include/asm/mach-loongson/kernel-entry-init.h b/arch/mips/include/asm/mach-loongson/kernel-entry-init.h new file mode 100644 index 0000000000000000000000000000000000000000..df5fca8eeb80a591cf03aa0332c39315ce2e04cf --- /dev/null +++ b/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 (ralf@linux-mips.org) + * Copyright (C) 2009 Jiajie Chen (chenjiajie@cse.buaa.edu.cn) + * Copyright (C) 2012 Huacai Chen (chenhc@lemote.com) + */ +#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 */ diff --git a/arch/mips/include/asm/mach-loongson/mmzone.h b/arch/mips/include/asm/mach-loongson/mmzone.h new file mode 100644 index 0000000000000000000000000000000000000000..37c08a27b4f00a338d46d1fdbef718eac62809f1 --- /dev/null +++ b/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, 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. + */ +#ifndef _ASM_MACH_MMZONE_H +#define _ASM_MACH_MMZONE_H + +#include +#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 */ diff --git a/arch/mips/include/asm/mach-loongson/topology.h b/arch/mips/include/asm/mach-loongson/topology.h new file mode 100644 index 0000000000000000000000000000000000000000..5598ba77d2efed283e03b364862e4a42ca8e54a7 --- /dev/null +++ b/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 + +#endif /* _ASM_MACH_TOPOLOGY_H */ diff --git a/arch/mips/include/asm/sparsemem.h b/arch/mips/include/asm/sparsemem.h index d2da53c2c2f8eaf2419e7cc41ad33192b15dc60c..b1071c1e54f53cb22fe59cff721757a1bdcbc3ee 100644 --- a/arch/mips/include/asm/sparsemem.h +++ b/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 */ diff --git a/arch/mips/kernel/setup.c b/arch/mips/kernel/setup.c index 2f01201b158cd353abc0d8b5cee5c6b376bc6772..7c1fe2b42d405fed3c1ca5c61a3bfe743af7a6c3 100644 --- a/arch/mips/kernel/setup.c +++ b/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) { diff --git a/arch/mips/loongson/Kconfig b/arch/mips/loongson/Kconfig index e6a86ccc4421221bea100d9a7915a9332fd157e5..a14a50d009d41b74df184df02c67cf450e50af66 100644 --- a/arch/mips/loongson/Kconfig +++ b/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 diff --git a/arch/mips/loongson/common/env.c b/arch/mips/loongson/common/env.c index dc592412f764e5f78e7c27a83729af061b9a0ed8..33a13b9e436c79bd15c159a1267da8a59c80685e 100644 --- a/arch/mips/loongson/common/env.c +++ b/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; diff --git a/arch/mips/loongson/common/init.c b/arch/mips/loongson/common/init.c index f37fe5413b7305d17c38bcc057e66686948b53b5..f6af3aba4c86a5501ee5fad615f04d6e67d8bcbc 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/loongson-3/Makefile b/arch/mips/loongson/loongson-3/Makefile index 70152b252ddc196800774bd85e571e4173072600..471b0f2af0793ec5388078bce22ed2e3fae8c9e1 100644 --- a/arch/mips/loongson/loongson-3/Makefile +++ b/arch/mips/loongson/loongson-3/Makefile @@ -4,3 +4,5 @@ obj-y += irq.o obj-$(CONFIG_SMP) += smp.o + +obj-$(CONFIG_NUMA) += numa.o diff --git a/arch/mips/loongson/loongson-3/numa.c b/arch/mips/loongson/loongson-3/numa.c new file mode 100644 index 0000000000000000000000000000000000000000..ca025a6ba559bbe644e555290af2a617fd90d9ce --- /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 +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +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 3c320e709e91885719e9c93f0ff8e6a59ef00bf6..ed0e2d0f87abade2955098648805f1fb0b232655 100644 --- a/arch/mips/loongson/loongson-3/smp.c +++ b/arch/mips/loongson/loongson-3/smp.c @@ -203,6 +203,8 @@ static void loongson3_init_secondary(void) for (i = 0; i < loongson_sysconf.nr_cpus; i++) loongson3_ipi_write32(0xffffffff, ipi_en0_regs[i]); + cpu_data[cpu].package = cpu / loongson_sysconf.cores_per_package; + cpu_data[cpu].core = cpu % loongson_sysconf.cores_per_package; per_cpu(cpu_state, cpu) = CPU_ONLINE; i = 0; @@ -394,17 +396,19 @@ static int loongson3_cpu_callback(struct notifier_block *nfb, unsigned long action, void *hcpu) { unsigned int cpu = (unsigned long)hcpu; + uint64_t core_id = cpu_data[cpu].core; + uint64_t package_id = cpu_data[cpu].package; switch (action) { case CPU_POST_DEAD: case CPU_POST_DEAD_FROZEN: pr_info("Disable clock for CPU#%d\n", cpu); - LOONGSON_CHIPCFG(0) &= ~(1 << (12 + cpu)); + LOONGSON_CHIPCFG(package_id) &= ~(1 << (12 + core_id)); break; case CPU_UP_PREPARE: case CPU_UP_PREPARE_FROZEN: pr_info("Enable clock for CPU#%d\n", cpu); - LOONGSON_CHIPCFG(0) |= 1 << (12 + cpu); + LOONGSON_CHIPCFG(package_id) |= 1 << (12 + core_id); break; }