diff options
39 files changed, 836 insertions, 1614 deletions
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 38adb2dca1d..0a1fe60037f 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -112,7 +112,14 @@ config MMU def_bool y config ZONE_DMA - def_bool y + bool "DMA memory allocation support" if EXPERT + default y + help + DMA memory allocation support allows devices with less than 32-bit + addressing to allocate within the first 16MB of address space. + Disable if no such devices will be used. + + If unsure, say Y. config SBUS bool @@ -1164,7 +1171,7 @@ comment "NUMA (Summit) requires SMP, 64GB highmem support, ACPI" config AMD_NUMA def_bool y prompt "Old style AMD Opteron NUMA detection" - depends on X86_64 && NUMA && PCI + depends on NUMA && PCI ---help--- Enable AMD NUMA node topology detection. You should say Y here if you have a multi processor AMD system. This uses an old method to @@ -1191,7 +1198,7 @@ config NODES_SPAN_OTHER_NODES config NUMA_EMU bool "NUMA emulation" - depends on X86_64 && NUMA + depends on NUMA ---help--- Enable NUMA emulation. A flat machine will be split into virtual nodes when booted with "numa=fake=N", where N is the @@ -1213,6 +1220,10 @@ config HAVE_ARCH_BOOTMEM def_bool y depends on X86_32 && NUMA +config HAVE_ARCH_ALLOC_REMAP + def_bool y + depends on X86_32 && NUMA + config ARCH_HAVE_MEMORY_PRESENT def_bool y depends on X86_32 && DISCONTIGMEM @@ -1221,13 +1232,9 @@ config NEED_NODE_MEMMAP_SIZE def_bool y depends on X86_32 && (DISCONTIGMEM || SPARSEMEM) -config HAVE_ARCH_ALLOC_REMAP - def_bool y - depends on X86_32 && NUMA - config ARCH_FLATMEM_ENABLE def_bool y - depends on X86_32 && ARCH_SELECT_MEMORY_MODEL && !NUMA + depends on X86_32 && !NUMA config ARCH_DISCONTIGMEM_ENABLE def_bool y @@ -1237,20 +1244,16 @@ config ARCH_DISCONTIGMEM_DEFAULT def_bool y depends on NUMA && X86_32 -config ARCH_PROC_KCORE_TEXT - def_bool y - depends on X86_64 && PROC_KCORE - -config ARCH_SPARSEMEM_DEFAULT - def_bool y - depends on X86_64 - config ARCH_SPARSEMEM_ENABLE def_bool y depends on X86_64 || NUMA || (EXPERIMENTAL && X86_32) || X86_32_NON_STANDARD select SPARSEMEM_STATIC if X86_32 select SPARSEMEM_VMEMMAP_ENABLE if X86_64 +config ARCH_SPARSEMEM_DEFAULT + def_bool y + depends on X86_64 + config ARCH_SELECT_MEMORY_MODEL def_bool y depends on ARCH_SPARSEMEM_ENABLE @@ -1259,6 +1262,10 @@ config ARCH_MEMORY_PROBE def_bool X86_64 depends on MEMORY_HOTPLUG +config ARCH_PROC_KCORE_TEXT + def_bool y + depends on X86_64 && PROC_KCORE + config ILLEGAL_POINTER_VALUE hex default 0 if X86_32 @@ -1693,10 +1700,6 @@ config ARCH_ENABLE_MEMORY_HOTREMOVE def_bool y depends on MEMORY_HOTPLUG -config HAVE_ARCH_EARLY_PFN_TO_NID - def_bool X86_64 - depends on NUMA - config USE_PERCPU_NUMA_NODE_ID def_bool y depends on NUMA diff --git a/arch/x86/include/asm/acpi.h b/arch/x86/include/asm/acpi.h index 12e0e7dd869..416d865eae3 100644 --- a/arch/x86/include/asm/acpi.h +++ b/arch/x86/include/asm/acpi.h @@ -183,8 +183,6 @@ static inline void disable_acpi(void) { } #define ARCH_HAS_POWER_INIT 1 -struct bootnode; - #ifdef CONFIG_ACPI_NUMA extern int acpi_numa; extern int x86_acpi_numa_init(void); diff --git a/arch/x86/include/asm/amd_nb.h b/arch/x86/include/asm/amd_nb.h index 331682231bb..67f87f25761 100644 --- a/arch/x86/include/asm/amd_nb.h +++ b/arch/x86/include/asm/amd_nb.h @@ -11,7 +11,6 @@ struct amd_nb_bus_dev_range { extern const struct pci_device_id amd_nb_misc_ids[]; extern const struct amd_nb_bus_dev_range amd_nb_bus_dev_ranges[]; -struct bootnode; extern bool early_is_amd_nb(u32 value); extern int amd_cache_northbridges(void); diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h index 2b7d573be54..a0c46f06121 100644 --- a/arch/x86/include/asm/apic.h +++ b/arch/x86/include/asm/apic.h @@ -363,7 +363,12 @@ struct apic { */ int (*x86_32_early_logical_apicid)(int cpu); - /* determine CPU -> NUMA node mapping */ + /* + * Optional method called from setup_local_APIC() after logical + * apicid is guaranteed to be known to initialize apicid -> node + * mapping if NUMA initialization hasn't done so already. Don't + * add new users. + */ int (*x86_32_numa_cpu_node)(int cpu); #endif }; @@ -537,8 +542,6 @@ static inline int default_phys_pkg_id(int cpuid_apic, int index_msb) return cpuid_apic >> index_msb; } -extern int default_x86_32_numa_cpu_node(int cpu); - #endif static inline unsigned int diff --git a/arch/x86/include/asm/cpufeature.h b/arch/x86/include/asm/cpufeature.h index 7f2f7b12329..30afb465d48 100644 --- a/arch/x86/include/asm/cpufeature.h +++ b/arch/x86/include/asm/cpufeature.h @@ -208,8 +208,7 @@ extern const char * const x86_power_flags[32]; #define test_cpu_cap(c, bit) \ test_bit(bit, (unsigned long *)((c)->x86_capability)) -#define cpu_has(c, bit) \ - (__builtin_constant_p(bit) && \ +#define REQUIRED_MASK_BIT_SET(bit) \ ( (((bit)>>5)==0 && (1UL<<((bit)&31) & REQUIRED_MASK0)) || \ (((bit)>>5)==1 && (1UL<<((bit)&31) & REQUIRED_MASK1)) || \ (((bit)>>5)==2 && (1UL<<((bit)&31) & REQUIRED_MASK2)) || \ @@ -219,10 +218,16 @@ extern const char * const x86_power_flags[32]; (((bit)>>5)==6 && (1UL<<((bit)&31) & REQUIRED_MASK6)) || \ (((bit)>>5)==7 && (1UL<<((bit)&31) & REQUIRED_MASK7)) || \ (((bit)>>5)==8 && (1UL<<((bit)&31) & REQUIRED_MASK8)) || \ - (((bit)>>5)==9 && (1UL<<((bit)&31) & REQUIRED_MASK9)) ) \ - ? 1 : \ + (((bit)>>5)==9 && (1UL<<((bit)&31) & REQUIRED_MASK9)) ) + +#define cpu_has(c, bit) \ + (__builtin_constant_p(bit) && REQUIRED_MASK_BIT_SET(bit) ? 1 : \ test_cpu_cap(c, bit)) +#define this_cpu_has(bit) \ + (__builtin_constant_p(bit) && REQUIRED_MASK_BIT_SET(bit) ? 1 : \ + x86_this_cpu_test_bit(bit, (unsigned long *)&cpu_info.x86_capability)) + #define boot_cpu_has(bit) cpu_has(&boot_cpu_data, bit) #define set_cpu_cap(c, bit) set_bit(bit, (unsigned long *)((c)->x86_capability)) diff --git a/arch/x86/include/asm/dma.h b/arch/x86/include/asm/dma.h index 057099e5fab..0bdb0c54d9a 100644 --- a/arch/x86/include/asm/dma.h +++ b/arch/x86/include/asm/dma.h @@ -69,22 +69,18 @@ #define MAX_DMA_CHANNELS 8 -#ifdef CONFIG_X86_32 - -/* The maximum address that we can perform a DMA transfer to on this platform */ -#define MAX_DMA_ADDRESS (PAGE_OFFSET + 0x1000000) - -#else - /* 16MB ISA DMA zone */ #define MAX_DMA_PFN ((16 * 1024 * 1024) >> PAGE_SHIFT) /* 4GB broken PCI/AGP hardware bus master zone */ #define MAX_DMA32_PFN ((4UL * 1024 * 1024 * 1024) >> PAGE_SHIFT) +#ifdef CONFIG_X86_32 +/* The maximum address that we can perform a DMA transfer to on this platform */ +#define MAX_DMA_ADDRESS (PAGE_OFFSET + 0x1000000) +#else /* Compat define for old dma zone */ #define MAX_DMA_ADDRESS ((unsigned long)__va(MAX_DMA_PFN << PAGE_SHIFT)) - #endif /* 8237 DMA controllers */ diff --git a/arch/x86/include/asm/mmzone_32.h b/arch/x86/include/asm/mmzone_32.h index 91df7c51806..5e83a416eca 100644 --- a/arch/x86/include/asm/mmzone_32.h +++ b/arch/x86/include/asm/mmzone_32.h @@ -13,31 +13,11 @@ extern struct pglist_data *node_data[]; #define NODE_DATA(nid) (node_data[nid]) #include <asm/numaq.h> -/* summit or generic arch */ -#include <asm/srat.h> - -extern int get_memcfg_numa_flat(void); -/* - * This allows any one NUMA architecture to be compiled - * for, and still fall back to the flat function if it - * fails. - */ -static inline void get_memcfg_numa(void) -{ - - if (get_memcfg_numaq()) - return; - if (get_memcfg_from_srat()) - return; - get_memcfg_numa_flat(); -} extern void resume_map_numa_kva(pgd_t *pgd); #else /* !CONFIG_NUMA */ -#define get_memcfg_numa get_memcfg_numa_flat - static inline void resume_map_numa_kva(pgd_t *pgd) {} #endif /* CONFIG_NUMA */ diff --git a/arch/x86/include/asm/mmzone_64.h b/arch/x86/include/asm/mmzone_64.h index 288b96f815a..b3f88d7867c 100644 --- a/arch/x86/include/asm/mmzone_64.h +++ b/arch/x86/include/asm/mmzone_64.h @@ -4,36 +4,13 @@ #ifndef _ASM_X86_MMZONE_64_H #define _ASM_X86_MMZONE_64_H - #ifdef CONFIG_NUMA #include <linux/mmdebug.h> - #include <asm/smp.h> -/* Simple perfect hash to map physical addresses to node numbers */ -struct memnode { - int shift; - unsigned int mapsize; - s16 *map; - s16 embedded_map[64 - 8]; -} ____cacheline_aligned; /* total size = 128 bytes */ -extern struct memnode memnode; -#define memnode_shift memnode.shift -#define memnodemap memnode.map -#define memnodemapsize memnode.mapsize - extern struct pglist_data *node_data[]; -static inline __attribute__((pure)) int phys_to_nid(unsigned long addr) -{ - unsigned nid; - VIRTUAL_BUG_ON(!memnodemap); - nid = memnodemap[addr >> memnode_shift]; - VIRTUAL_BUG_ON(nid >= MAX_NUMNODES || !node_data[nid]); - return nid; -} - #define NODE_DATA(nid) (node_data[nid]) #define node_start_pfn(nid) (NODE_DATA(nid)->node_start_pfn) diff --git a/arch/x86/include/asm/numa.h b/arch/x86/include/asm/numa.h index a50fc9f493b..bfacd2ccf65 100644 --- a/arch/x86/include/asm/numa.h +++ b/arch/x86/include/asm/numa.h @@ -1,12 +1,24 @@ #ifndef _ASM_X86_NUMA_H #define _ASM_X86_NUMA_H +#include <linux/nodemask.h> + #include <asm/topology.h> #include <asm/apicdef.h> #ifdef CONFIG_NUMA #define NR_NODE_MEMBLKS (MAX_NUMNODES*2) +#define ZONE_ALIGN (1UL << (MAX_ORDER+PAGE_SHIFT)) + +/* + * Too small node sizes may confuse the VM badly. Usually they + * result from BIOS bugs. So dont recognize nodes as standalone + * NUMA entities that have less than this amount of RAM listed: + */ +#define NODE_MIN_SIZE (4*1024*1024) + +extern int numa_off; /* * __apicid_to_node[] stores the raw mapping between physical apicid and @@ -17,15 +29,27 @@ * numa_cpu_node(). */ extern s16 __apicid_to_node[MAX_LOCAL_APIC]; +extern nodemask_t numa_nodes_parsed __initdata; + +extern int __init numa_add_memblk(int nodeid, u64 start, u64 end); +extern void __init numa_set_distance(int from, int to, int distance); static inline void set_apicid_to_node(int apicid, s16 node) { __apicid_to_node[apicid] = node; } + +extern int __cpuinit numa_cpu_node(int cpu); + #else /* CONFIG_NUMA */ static inline void set_apicid_to_node(int apicid, s16 node) { } + +static inline int numa_cpu_node(int cpu) +{ + return NUMA_NO_NODE; +} #endif /* CONFIG_NUMA */ #ifdef CONFIG_X86_32 @@ -37,14 +61,12 @@ static inline void set_apicid_to_node(int apicid, s16 node) #ifdef CONFIG_NUMA extern void __cpuinit numa_set_node(int cpu, int node); extern void __cpuinit numa_clear_node(int cpu); -extern void __init numa_init_array(void); extern void __init init_cpu_to_node(void); extern void __cpuinit numa_add_cpu(int cpu); extern void __cpuinit numa_remove_cpu(int cpu); #else /* CONFIG_NUMA */ static inline void numa_set_node(int cpu, int node) { } static inline void numa_clear_node(int cpu) { } -static inline void numa_init_array(void) { } static inline void init_cpu_to_node(void) { } static inline void numa_add_cpu(int cpu) { } static inline void numa_remove_cpu(int cpu) { } @@ -54,4 +76,10 @@ static inline void numa_remove_cpu(int cpu) { } void debug_cpumask_set_cpu(int cpu, int node, bool enable); #endif +#ifdef CONFIG_NUMA_EMU +#define FAKE_NODE_MIN_SIZE ((u64)32 << 20) +#define FAKE_NODE_MIN_HASH_MASK (~(FAKE_NODE_MIN_SIZE - 1UL)) +void numa_emu_cmdline(char *); +#endif /* CONFIG_NUMA_EMU */ + #endif /* _ASM_X86_NUMA_H */ diff --git a/arch/x86/include/asm/numa_32.h b/arch/x86/include/asm/numa_32.h index c6beed1ef10..e7d6b825474 100644 --- a/arch/x86/include/asm/numa_32.h +++ b/arch/x86/include/asm/numa_32.h @@ -1,16 +1,6 @@ #ifndef _ASM_X86_NUMA_32_H #define _ASM_X86_NUMA_32_H -extern int numa_off; - -extern int pxm_to_nid(int pxm); - -#ifdef CONFIG_NUMA -extern int __cpuinit numa_cpu_node(int cpu); -#else /* CONFIG_NUMA */ -static inline int numa_cpu_node(int cpu) { return NUMA_NO_NODE; } -#endif /* CONFIG_NUMA */ - #ifdef CONFIG_HIGHMEM extern void set_highmem_pages_init(void); #else diff --git a/arch/x86/include/asm/numa_64.h b/arch/x86/include/asm/numa_64.h index 344eb1790b4..0c05f7ae46e 100644 --- a/arch/x86/include/asm/numa_64.h +++ b/arch/x86/include/asm/numa_64.h @@ -1,42 +1,6 @@ #ifndef _ASM_X86_NUMA_64_H #define _ASM_X86_NUMA_64_H -#include <linux/nodemask.h> - -struct bootnode { - u64 start; - u64 end; -}; - -#define ZONE_ALIGN (1UL << (MAX_ORDER+PAGE_SHIFT)) - -extern int numa_off; - extern unsigned long numa_free_all_bootmem(void); -extern void setup_node_bootmem(int nodeid, unsigned long start, - unsigned long end); - -#ifdef CONFIG_NUMA -/* - * Too small node sizes may confuse the VM badly. Usually they - * result from BIOS bugs. So dont recognize nodes as standalone - * NUMA entities that have less than this amount of RAM listed: - */ -#define NODE_MIN_SIZE (4*1024*1024) - -extern nodemask_t numa_nodes_parsed __initdata; - -extern int __cpuinit numa_cpu_node(int cpu); -extern int __init numa_add_memblk(int nodeid, u64 start, u64 end); -extern void __init numa_set_distance(int from, int to, int distance); - -#ifdef CONFIG_NUMA_EMU -#define FAKE_NODE_MIN_SIZE ((u64)32 << 20) -#define FAKE_NODE_MIN_HASH_MASK (~(FAKE_NODE_MIN_SIZE - 1UL)) -void numa_emu_cmdline(char *); -#endif /* CONFIG_NUMA_EMU */ -#else -static inline int numa_cpu_node(int cpu) { return NUMA_NO_NODE; } -#endif #endif /* _ASM_X86_NUMA_64_H */ diff --git a/arch/x86/include/asm/numaq.h b/arch/x86/include/asm/numaq.h index 37c516545ec..c3b3c322fd8 100644 --- a/arch/x86/include/asm/numaq.h +++ b/arch/x86/include/asm/numaq.h @@ -29,7 +29,7 @@ #ifdef CONFIG_X86_NUMAQ extern int found_numaq; -extern int get_memcfg_numaq(void); +extern int numaq_numa_init(void); extern int pci_numaq_init(void); extern void *xquad_portio; @@ -166,11 +166,6 @@ struct sys_cfg_data { void numaq_tsc_disable(void); -#else -static inline int get_memcfg_numaq(void) -{ - return 0; -} #endif /* CONFIG_X86_NUMAQ */ #endif /* _ASM_X86_NUMAQ_H */ diff --git a/arch/x86/include/asm/percpu.h b/arch/x86/include/asm/percpu.h index 751e7f3f705..53278b0dfdf 100644 --- a/arch/x86/include/asm/percpu.h +++ b/arch/x86/include/asm/percpu.h @@ -542,6 +542,33 @@ do { \ old__; \ }) +static __always_inline int x86_this_cpu_constant_test_bit(unsigned int nr, + const unsigned long __percpu *addr) +{ + unsigned long __percpu *a = (unsigned long *)addr + nr / BITS_PER_LONG; + + return ((1UL << (nr % BITS_PER_LONG)) & percpu_read(*a)) != 0; +} + +static inline int x86_this_cpu_variable_test_bit(int nr, + const unsigned long __percpu *addr) +{ + int oldbit; + + asm volatile("bt "__percpu_arg(2)",%1\n\t" + "sbb %0,%0" + : "=r" (oldbit) + : "m" (*(unsigned long *)addr), "Ir" (nr)); + + return oldbit; +} + +#define x86_this_cpu_test_bit(nr, addr) \ + (__builtin_constant_p((nr)) \ + ? x86_this_cpu_constant_test_bit((nr), (addr)) \ + : x86_this_cpu_variable_test_bit((nr), (addr))) + + #include <asm-generic/percpu.h> /* We can use this directly for local CPU (faster). */ diff --git a/arch/x86/include/asm/srat.h b/arch/x86/include/asm/srat.h deleted file mode 100644 index b508d639d1a..00000000000 --- a/arch/x86/include/asm/srat.h +++ /dev/null @@ -1,39 +0,0 @@ -/* - * Some of the code in this file has been gleaned from the 64 bit - * discontigmem support code base. - * - * Copyright (C) 2002, IBM Corp. - * - * All rights reserved. - * - * 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, GOOD TITLE or - * NON INFRINGEMENT. See the GNU General Public License for more - * details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. - * - * Send feedback to Pat Gaughen <gone@us.ibm.com> - */ - -#ifndef _ASM_X86_SRAT_H -#define _ASM_X86_SRAT_H - -#ifdef CONFIG_ACPI_NUMA -extern int get_memcfg_from_srat(void); -#else -static inline int get_memcfg_from_srat(void) -{ - return 0; -} -#endif - -#endif /* _ASM_X86_SRAT_H */ diff --git a/arch/x86/include/asm/topology.h b/arch/x86/include/asm/topology.h index 910a7084f7f..c00692476e9 100644 --- a/arch/x86/include/asm/topology.h +++ b/arch/x86/include/asm/topology.h @@ -93,19 +93,11 @@ extern void setup_node_to_cpumask_map(void); #define pcibus_to_node(bus) __pcibus_to_node(bus) #ifdef CONFIG_X86_32 -extern unsigned long node_start_pfn[]; -extern unsigned long node_end_pfn[]; -extern unsigned long node_remap_size[]; -#define node_has_online_mem(nid) (node_start_pfn[nid] != node_end_pfn[nid]) - # define SD_CACHE_NICE_TRIES 1 # define SD_IDLE_IDX 1 - #else - # define SD_CACHE_NICE_TRIES 2 # define SD_IDLE_IDX 2 - #endif /* sched_domains SD_NODE_INIT for NUMA machines */ diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index ae147126b7b..f92a8e5d1e2 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -505,7 +505,7 @@ static void __cpuinit setup_APIC_timer(void) { struct clock_event_device *levt = &__get_cpu_var(lapic_events); - if (cpu_has(__this_cpu_ptr(&cpu_info), X86_FEATURE_ARAT)) { + if (this_cpu_has(X86_FEATURE_ARAT)) { lapic_clockevent.features &= ~CLOCK_EVT_FEAT_C3STOP; /* Make LAPIC timer preferrable over percpu HPET */ lapic_clockevent.rating = 150; @@ -1237,6 +1237,17 @@ void __cpuinit setup_local_APIC(void) /* always use the value from LDR */ early_per_cpu(x86_cpu_to_logical_apicid, cpu) = logical_smp_processor_id(); + + /* + * Some NUMA implementations (NUMAQ) don't initialize apicid to + * node mapping during NUMA init. Now that logical apicid is + * guaranteed to be known, give it another chance. This is already + * a bit too late - percpu allocation has already happened without + * proper NUMA affinity. + */ + if (apic->x86_32_numa_cpu_node) + set_apicid_to_node(early_per_cpu(x86_cpu_to_apicid, cpu), + apic->x86_32_numa_cpu_node(cpu)); #endif /* @@ -2014,21 +2025,6 @@ void default_init_apic_ldr(void) apic_write(APIC_LDR, val); } -#ifdef CONFIG_X86_32 -int default_x86_32_numa_cpu_node(int cpu) -{ -#ifdef CONFIG_NUMA - int apicid = early_per_cpu(x86_cpu_to_apicid, cpu); - - if (apicid != BAD_APICID) - return __apicid_to_node[apicid]; - return NUMA_NO_NODE; -#else - return 0; -#endif -} -#endif - /* * Power management */ diff --git a/arch/x86/kernel/apic/apic_noop.c b/arch/x86/kernel/apic/apic_noop.c index f1baa2dc087..775b82bc655 100644 --- a/arch/x86/kernel/apic/apic_noop.c +++ b/arch/x86/kernel/apic/apic_noop.c @@ -119,14 +119,6 @@ static void noop_apic_write(u32 reg, u32 v) WARN_ON_ONCE(cpu_has_apic && !disable_apic); } -#ifdef CONFIG_X86_32 -static int noop_x86_32_numa_cpu_node(int cpu) -{ - /* we're always on node 0 */ - return 0; -} -#endif - struct apic apic_noop = { .name = "noop", .probe = noop_probe, @@ -195,6 +187,5 @@ struct apic apic_noop = { #ifdef CONFIG_X86_32 .x86_32_early_logical_apicid = noop_x86_32_early_logical_apicid, - .x86_32_numa_cpu_node = noop_x86_32_numa_cpu_node, #endif }; diff --git a/arch/x86/kernel/apic/bigsmp_32.c b/arch/x86/kernel/apic/bigsmp_32.c index 541a2e43165..d84ac5a584b 100644 --- a/arch/x86/kernel/apic/bigsmp_32.c +++ b/arch/x86/kernel/apic/bigsmp_32.c @@ -253,5 +253,4 @@ struct apic apic_bigsmp = { .safe_wait_icr_idle = native_safe_apic_wait_icr_idle, .x86_32_early_logical_apicid = bigsmp_early_logical_apicid, - .x86_32_numa_cpu_node = default_x86_32_numa_cpu_node, }; diff --git a/arch/x86/kernel/apic/es7000_32.c b/arch/x86/kernel/apic/es7000_32.c index 3e9de4854c5..70533de5bd2 100644 --- a/arch/x86/kernel/apic/es7000_32.c +++ b/arch/x86/kernel/apic/es7000_32.c @@ -510,11 +510,6 @@ static void es7000_setup_apic_routing(void) nr_ioapics, cpumask_bits(es7000_target_cpus())[0]); } -static int es7000_numa_cpu_node(int cpu) -{ - return 0; -} - static int es7000_cpu_present_to_apicid(int mps_cpu) { if (!mps_cpu) @@ -688,7 +683,6 @@ struct apic __refdata apic_es7000_cluster = { .safe_wait_icr_idle = native_safe_apic_wait_icr_idle, .x86_32_early_logical_apicid = es7000_early_logical_apicid, - .x86_32_numa_cpu_node = es7000_numa_cpu_node, }; struct apic __refdata apic_es7000 = { @@ -752,5 +746,4 @@ struct apic __refdata apic_es7000 = { .safe_wait_icr_idle = native_safe_apic_wait_icr_idle, .x86_32_early_logical_apicid = es7000_early_logical_apicid, - .x86_32_numa_cpu_node = es7000_numa_cpu_node, }; diff --git a/arch/x86/kernel/apic/numaq_32.c b/arch/x86/kernel/apic/numaq_32.c index 6273eee5134..30f13319e24 100644 --- a/arch/x86/kernel/apic/numaq_32.c +++ b/arch/x86/kernel/apic/numaq_32.c @@ -48,8 +48,6 @@ #include <asm/e820.h> #include <asm/ipi.h> -#define MB_TO_PAGES(addr) ((addr) << (20 - PAGE_SHIFT)) - int found_numaq; /* @@ -79,31 +77,20 @@ int quad_local_to_mp_bus_id[NR_CPUS/4][4]; static inline void numaq_register_node(int node, struct sys_cfg_data *scd) { struct eachquadmem *eq = scd->eq + node; + u64 start = (u64)(eq->hi_shrd_mem_start - eq->priv_mem_size) << 20; + u64 end = (u64)(eq->hi_shrd_mem_start + eq->hi_shrd_mem_size) << 20; + int ret; - node_set_online(node); - - /* Convert to pages */ - node_start_pfn[node] = - MB_TO_PAGES(eq->hi_shrd_mem_start - eq->priv_mem_size); - - node_end_pfn[node] = - MB_TO_PAGES(eq->hi_shrd_mem_start + eq->hi_shrd_mem_size); - - memblock_x86_register_active_regions(node, node_start_pfn[node], - node_end_pfn[node]); - - memory_present(node, node_start_pfn[node], node_end_pfn[node]); - - node_remap_size[node] = node_memmap_size_bytes(node, - node_start_pfn[node], - node_end_pfn[node]); + node_set(node, numa_nodes_parsed); + ret = numa_add_memblk(node, start, end); + BUG_ON(ret < 0); } /* * Function: smp_dump_qct() * * Description: gets memory layout from the quad config table. This - * function also updates node_online_map with the nodes (quads) present. + * function also updates numa_nodes_parsed with the nodes (quads) present. */ static void __init smp_dump_qct(void) { @@ -112,7 +99,6 @@ static void __init smp_dump_qct(void) scd = (void *)__va(SYS_CFG_DATA_PRIV_ADDR); - nodes_clear(node_online_map); for_each_node(node) { if (scd->quads_present31_0 & (1 << node)) numaq_register_node(node, scd); @@ -282,14 +268,14 @@ static __init void early_check_numaq(void) } } -int __init get_memcfg_numaq(void) +int __init numaq_numa_init(void) { early_check_numaq(); if (!found_numaq) - return 0; + return -ENOENT; smp_dump_qct(); - return 1; + return 0; } #define NUMAQ_APIC_DFR_VALUE (APIC_DFR_CLUSTER) diff --git a/arch/x86/kernel/apic/probe_32.c b/arch/x86/kernel/apic/probe_32.c index fc84c7b6110..6541e471fd9 100644 --- a/arch/x86/kernel/apic/probe_32.c +++ b/arch/x86/kernel/apic/probe_32.c @@ -172,7 +172,6 @@ struct apic apic_default = { .safe_wait_icr_idle = native_safe_apic_wait_icr_idle, .x86_32_early_logical_apicid = default_x86_32_early_logical_apicid, - .x86_32_numa_cpu_node = default_x86_32_numa_cpu_node, }; extern struct apic apic_numaq; diff --git a/arch/x86/kernel/apic/summit_32.c b/arch/x86/kernel/apic/summit_32.c index e4b8059b414..35bcd7d995a 100644 --- a/arch/x86/kernel/apic/summit_32.c +++ b/arch/x86/kernel/apic/summit_32.c @@ -551,5 +551,4 @@ struct apic apic_summit = { .safe_wait_icr_idle = native_safe_apic_wait_icr_idle, .x86_32_early_logical_apicid = summit_early_logical_apicid, - .x86_32_numa_cpu_node = default_x86_32_numa_cpu_node, }; diff --git a/arch/x86/kernel/cpu/mcheck/therm_throt.c b/arch/x86/kernel/cpu/mcheck/therm_throt.c index f5208ff28b5..27c625178bf 100644 --- a/arch/x86/kernel/cpu/mcheck/therm_throt.c +++ b/arch/x86/kernel/cpu/mcheck/therm_throt.c @@ -353,7 +353,6 @@ static void notify_thresholds(__u64 msr_val) static void intel_thermal_interrupt(void) { __u64 msr_val; - struct cpuinfo_x86 *c = &cpu_data(smp_processor_id()); rdmsrl(MSR_IA32_THERM_STATUS, msr_val); @@ -365,19 +364,19 @@ static void intel_thermal_interrupt(void) CORE_LEVEL) != 0) mce_log_therm_throt_event(CORE_THROTTLED | msr_val); - if (cpu_has(c, X86_FEATURE_PLN)) + if (this_cpu_has(X86_FEATURE_PLN)) if (therm_throt_process(msr_val & THERM_STATUS_POWER_LIMIT, POWER_LIMIT_EVENT, CORE_LEVEL) != 0) mce_log_therm_throt_event(CORE_POWER_LIMIT | msr_val); - if (cpu_has(c, X86_FEATURE_PTS)) { + if (this_cpu_has(X86_FEATURE_PTS)) { rdmsrl(MSR_IA32_PACKAGE_THERM_STATUS, msr_val); if (therm_throt_process(msr_val & PACKAGE_THERM_STATUS_PROCHOT, THERMAL_THROTTLING_EVENT, PACKAGE_LEVEL) != 0) mce_log_therm_throt_event(PACKAGE_THROTTLED | msr_val); - if (cpu_has(c, X86_FEATURE_PLN)) + if (this_cpu_has(X86_FEATURE_PLN)) if (therm_throt_process(msr_val & PACKAGE_THERM_STATUS_POWER_LIMIT, POWER_LIMIT_EVENT, diff --git a/arch/x86/kernel/mpparse.c b/arch/x86/kernel/mpparse.c index ef59817357f..6f9bfffb272 100644 --- a/arch/x86/kernel/mpparse.c +++ b/arch/x86/kernel/mpparse.c @@ -715,7 +715,7 @@ static void __init check_irq_src(struct mpc_intsrc *m, int *nr_m_spare) } } -static int +static int __init check_slot(unsigned long mpc_new_phys, unsigned long mpc_new_length, int count) { if (!mpc_new_phys || count <= mpc_new_length) { diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index d46cbe46b7a..88a90a977f8 100644 --- a/arch/x86/kernel/process.c +++ b/arch/x86/kernel/process.c @@ -449,7 +449,7 @@ EXPORT_SYMBOL_GPL(cpu_idle_wait); void mwait_idle_with_hints(unsigned long ax, unsigned long cx) { if (!need_resched()) { - if (cpu_has(__this_cpu_ptr(&cpu_info), X86_FEATURE_CLFLUSH_MONITOR)) + if (this_cpu_has(X86_FEATURE_CLFLUSH_MONITOR)) clflush((void *)¤t_thread_info()->flags); __monitor((void *)¤t_thread_info()->flags, 0, 0); @@ -465,7 +465,7 @@ static void mwait_idle(void) if (!need_resched()) { trace_power_start(POWER_CSTATE, 1, smp_processor_id()); trace_cpu_idle(1, smp_processor_id()); - if (cpu_has(__this_cpu_ptr(&cpu_info), X86_FEATURE_CLFLUSH_MONITOR)) + if (this_cpu_has(X86_FEATURE_CLFLUSH_MONITOR)) clflush((void *)¤t_thread_info()->flags); __monitor((void *)¤t_thread_info()->flags, 0, 0); diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index c2871d3c71b..a3c430bdfb6 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -1332,9 +1332,9 @@ static inline void mwait_play_dead(void) void *mwait_ptr; struct cpuinfo_x86 *c = __this_cpu_ptr(&cpu_info); - if (!(cpu_has(c, X86_FEATURE_MWAIT) && mwait_usable(c))) + if (!this_cpu_has(X86_FEATURE_MWAIT) && mwait_usable(c)) return; - if (!cpu_has(__this_cpu_ptr(&cpu_info), X86_FEATURE_CLFLSH)) + if (!this_cpu_has(X86_FEATURE_CLFLSH)) return; if (__this_cpu_read(cpu_info.cpuid_level) < CPUID_MWAIT_LEAF) return; diff --git a/arch/x86/mm/Makefile b/arch/x86/mm/Makefile index 3e608edf995..3d11327c9ab 100644 --- a/arch/x86/mm/Makefile +++ b/arch/x86/mm/Makefile @@ -23,8 +23,8 @@ mmiotrace-y := kmmio.o pf_in.o mmio-mod.o obj-$(CONFIG_MMIOTRACE_TEST) += testmmiotrace.o obj-$(CONFIG_NUMA) += numa.o numa_$(BITS).o -obj-$(CONFIG_AMD_NUMA) += amdtopology_64.o -obj-$(CONFIG_ACPI_NUMA) += srat_$(BITS).o +obj-$(CONFIG_AMD_NUMA) += amdtopology.o +obj-$(CONFIG_ACPI_NUMA) += srat.o obj-$(CONFIG_NUMA_EMU) += numa_emulation.o obj-$(CONFIG_HAVE_MEMBLOCK) += memblock.o diff --git a/arch/x86/mm/amdtopology_64.c b/arch/x86/mm/amdtopology.c index 0919c26820d..5247d01329c 100644 --- a/arch/x86/mm/amdtopology_64.c +++ b/arch/x86/mm/amdtopology.c @@ -12,6 +12,7 @@ #include <linux/module.h> #include <linux/nodemask.h> #include <linux/memblock.h> +#include <linux/bootmem.h> #include <asm/io.h> #include <linux/pci_ids.h> @@ -69,10 +70,10 @@ static __init void early_get_boot_cpu_id(void) int __init amd_numa_init(void) { - unsigned long start = PFN_PHYS(0); - unsigned long end = PFN_PHYS(max_pfn); + u64 start = PFN_PHYS(0); + u64 end = PFN_PHYS(max_pfn); unsigned numnodes; - unsigned long prevbase; + u64 prevbase; int i, j, nb; u32 nodeid, reg; unsigned int bits, cores, apicid_base; @@ -95,7 +96,7 @@ int __init amd_numa_init(void) prevbase = 0; for (i = 0; i < 8; i++) { - unsigned long base, limit; + u64 base, limit; base = read_pci_config(0, nb, 1, 0x40 + i*8); limit = read_pci_config(0, nb, 1, 0x44 + i*8); @@ -107,18 +108,18 @@ int __init amd_numa_init(void) continue; } if (nodeid >= numnodes) { - pr_info("Ignoring excess node %d (%lx:%lx)\n", nodeid, + pr_info("Ignoring excess node %d (%Lx:%Lx)\n", nodeid, base, limit); continue; } if (!limit) { - pr_info("Skipping node entry %d (base %lx)\n", + pr_info("Skipping node entry %d (base %Lx)\n", i, base); continue; } if ((base >> 8) & 3 || (limit >> 8) & 3) { - pr_err("Node %d using interleaving mode %lx/%lx\n", + pr_err("Node %d using interleaving mode %Lx/%Lx\n", nodeid, (base >> 8) & 3, (limit >> 8) & 3); return -EINVAL; } @@ -150,19 +151,19 @@ int __init amd_numa_init(void) continue; } if (limit < base) { - pr_err("Node %d bogus settings %lx-%lx.\n", + pr_err("Node %d bogus settings %Lx-%Lx.\n", nodeid, base, limit); continue; } /* Could sort here, but pun for now. Should not happen anyroads. */ if (prevbase > base) { - pr_err("Node map not sorted %lx,%lx\n", + pr_err("Node map not sorted %Lx,%Lx\n", prevbase, base); return -EINVAL; } - pr_info("Node %d MemBase %016lx Limit %016lx\n", + pr_info("Node %d MemBase %016Lx Limit %016Lx\n", nodeid, base, limit); prevbase = base; diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c index 80088f99419..29f7c6d9817 100644 --- a/arch/x86/mm/init_32.c +++ b/arch/x86/mm/init_32.c @@ -678,8 +678,10 @@ static void __init zone_sizes_init(void) { unsigned long max_zone_pfns[MAX_NR_ZONES]; memset(max_zone_pfns, 0, sizeof(max_zone_pfns)); +#ifdef CONFIG_ZONE_DMA max_zone_pfns[ZONE_DMA] = virt_to_phys((char *)MAX_DMA_ADDRESS) >> PAGE_SHIFT; +#endif max_zone_pfns[ZONE_NORMAL] = max_low_pfn; #ifdef CONFIG_HIGHMEM max_zone_pfns[ZONE_HIGHMEM] = highend_pfn; @@ -716,6 +718,7 @@ void __init paging_init(void) * NOTE: at this point the bootmem allocator is fully available. */ olpc_dt_build_devicetree(); + sparse_memory_present_with_active_regions(MAX_NUMNODES); sparse_init(); zone_sizes_init(); } diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c index 79423358728..d865c4aeec5 100644 --- a/arch/x86/mm/init_64.c +++ b/arch/x86/mm/init_64.c @@ -616,7 +616,9 @@ void __init paging_init(void) unsigned long max_zone_pfns[MAX_NR_ZONES]; memset(max_zone_pfns, 0, sizeof(max_zone_pfns)); +#ifdef CONFIG_ZONE_DMA max_zone_pfns[ZONE_DMA] = MAX_DMA_PFN; +#endif max_zone_pfns[ZONE_DMA32] = MAX_DMA32_PFN; max_zone_pfns[ZONE_NORMAL] = max_pfn; @@ -679,14 +681,6 @@ int arch_add_memory(int nid, u64 start, u64 size) } EXPORT_SYMBOL_GPL(arch_add_memory); -#if !defined(CONFIG_ACPI_NUMA) && defined(CONFIG_NUMA) -int memory_add_physaddr_to_nid(u64 start) -{ - return 0; -} -EXPORT_SYMBOL_GPL(memory_add_physaddr_to_nid); -#endif - #endif /* CONFIG_MEMORY_HOTPLUG */ static struct kcore_list kcore_vsyscall; diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c index 0369843511d..be1ef574ce9 100644 --- a/arch/x86/mm/ioremap.c +++ b/arch/x86/mm/ioremap.c @@ -91,13 +91,6 @@ static void __iomem *__ioremap_caller(resource_size_t phys_addr, return (__force void __iomem *)phys_to_virt(phys_addr); /* - * Check if the request spans more than any BAR in the iomem resource - * tree. - */ - WARN_ONCE(iomem_map_sanity_check(phys_addr, size), - KERN_INFO "Info: mapping multiple BARs. Your kernel is fine."); - - /* * Don't allow anybody to remap normal RAM that we're using.. */ last_pfn = last_addr >> PAGE_SHIFT; @@ -170,6 +163,13 @@ static void __iomem *__ioremap_caller(resource_size_t phys_addr, ret_addr = (void __iomem *) (vaddr + offset); mmiotrace_ioremap(unaligned_phys_addr, unaligned_size, ret_addr); + /* + * Check if the request spans more than any BAR in the iomem resource + * tree. + */ + WARN_ONCE(iomem_map_sanity_check(unaligned_phys_addr, unaligned_size), + KERN_INFO "Info: mapping multiple BARs. Your kernel is fine."); + return ret_addr; err_free_area: free_vm_area(area); diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c index 745258dfc4d..f5510d889a2 100644 --- a/arch/x86/mm/numa.c +++ b/arch/x86/mm/numa.c @@ -1,11 +1,39 @@ /* Common code for 32 and 64-bit NUMA */ -#include <linux/topology.h> -#include <linux/module.h> +#include <linux/kernel.h> +#include <linux/mm.h> +#include <linux/string.h> +#include <linux/init.h> #include <linux/bootmem.h> -#include <asm/numa.h> +#include <linux/memblock.h> +#include <linux/mmzone.h> +#include <linux/ctype.h> +#include <linux/module.h> +#include <linux/nodemask.h> +#include <linux/sched.h> +#include <linux/topology.h> + +#include <asm/e820.h> +#include <asm/proto.h> +#include <asm/dma.h> #include <asm/acpi.h> +#include <asm/amd_nb.h> + +#include "numa_internal.h" int __initdata numa_off; +nodemask_t numa_nodes_parsed __initdata; + +struct pglist_data *node_data[MAX_NUMNODES] __read_mostly; +EXPORT_SYMBOL(node_data); + +static struct numa_meminfo numa_meminfo +#ifndef CONFIG_MEMORY_HOTPLUG +__initdata +#endif +; + +static int numa_distance_cnt; +static u8 *numa_distance; static __init int numa_setup(char *opt) { @@ -32,6 +60,15 @@ s16 __apicid_to_node[MAX_LOCAL_APIC] __cpuinitdata = { [0 ... MAX_LOCAL_APIC-1] = NUMA_NO_NODE }; +int __cpuinit numa_cpu_node(int cpu) +{ + int apicid = early_per_cpu(x86_cpu_to_apicid, cpu); + + if (apicid != BAD_APICID) + return __apicid_to_node[apicid]; + return NUMA_NO_NODE; +} + cpumask_var_t node_to_cpumask_map[MAX_NUMNODES]; EXPORT_SYMBOL(node_to_cpumask_map); @@ -95,6 +132,407 @@ void __init setup_node_to_cpumask_map(void) pr_debug("Node to cpumask map for %d nodes\n", nr_node_ids); } +static int __init numa_add_memblk_to(int nid, u64 start, u64 end, + struct numa_meminfo *mi) +{ + /* ignore zero length blks */ + if (start == end) + return 0; + + /* whine about and ignore invalid blks */ + if (start > end || nid < 0 || nid >= MAX_NUMNODES) { + pr_warning("NUMA: Warning: invalid memblk node %d (%Lx-%Lx)\n", + nid, start, end); + return 0; + } + + if (mi->nr_blks >= NR_NODE_MEMBLKS) { + pr_err("NUMA: too many memblk ranges\n"); + return -EINVAL; + } + + mi->blk[mi->nr_blks].start = start; + mi->blk[mi->nr_blks].end = end; + mi->blk[mi->nr_blks].nid = nid; + mi->nr_blks++; + return 0; +} + +/** + * numa_remove_memblk_from - Remove one numa_memblk from a numa_meminfo + * @idx: Index of memblk to remove + * @mi: numa_meminfo to remove memblk from + * + * Remove @idx'th numa_memblk from @mi by shifting @mi->blk[] and + * decrementing @mi->nr_blks. + */ +void __init numa_remove_memblk_from(int idx, struct numa_meminfo *mi) +{ + mi->nr_blks--; + memmove(&mi->blk[idx], &mi->blk[idx + 1], + (mi->nr_blks - idx) * sizeof(mi->blk[0])); +} + +/** + * numa_add_memblk - Add one numa_memblk to numa_meminfo + * @nid: NUMA node ID of the new memblk + * @start: Start address of the new memblk + * @end: End address of the new memblk + * + * Add a new memblk to the default numa_meminfo. + * + * RETURNS: + * 0 on success, -errno on failure. + */ +int __init numa_add_memblk(int nid, u64 start, u64 end) +{ + return numa_add_memblk_to(nid, start, end, &numa_meminfo); +} + +/* Initialize NODE_DATA for a node on the local memory */ +static void __init setup_node_data(int nid, u64 start, u64 end) +{ + const u64 nd_low = PFN_PHYS(MAX_DMA_PFN); + const u64 nd_high = PFN_PHYS(max_pfn_mapped); + const size_t nd_size = roundup(sizeof(pg_data_t), PAGE_SIZE); + bool remapped = false; + u64 nd_pa; + void *nd; + int tnid; + + /* + * Don't confuse VM with a node that doesn't have the + * minimum amount of memory: + */ + if (end && (end - start) < NODE_MIN_SIZE) + return; + + /* initialize remap allocator before aligning to ZONE_ALIGN */ + init_alloc_remap(nid, start, end); + + start = roundup(start, ZONE_ALIGN); + + printk(KERN_INFO "Initmem setup node %d %016Lx-%016Lx\n", + nid, start, end); + + /* + * Allocate node data. Try remap allocator first, node-local + * memory and then any node. Never allocate in DMA zone. + */ + nd = alloc_remap(nid, nd_size); + if (nd) { + nd_pa = __pa(nd); + remapped = true; + } else { + nd_pa = memblock_x86_find_in_range_node(nid, nd_low, nd_high, + nd_size, SMP_CACHE_BYTES); + if (nd_pa == MEMBLOCK_ERROR) + nd_pa = memblock_find_in_range(nd_low, nd_high, + nd_size, SMP_CACHE_BYTES); + if (nd_pa == MEMBLOCK_ERROR) { + pr_err("Cannot find %zu bytes in node %d\n", + nd_size, nid); + return; + } + memblock_x86_reserve_range(nd_pa, nd_pa + nd_size, "NODE_DATA"); + nd = __va(nd_pa); + } + + /* report and initialize */ + printk(KERN_INFO " NODE_DATA [%016Lx - %016Lx]%s\n", + nd_pa, nd_pa + nd_size - 1, remapped ? " (remapped)" : ""); + tnid = early_pfn_to_nid(nd_pa >> PAGE_SHIFT); + if (!remapped && tnid != nid) + printk(KERN_INFO " NODE_DATA(%d) on node %d\n", nid, tnid); + + node_data[nid] = nd; + memset(NODE_DATA(nid), 0, sizeof(pg_data_t)); + NODE_DATA(nid)->node_id = nid; + NODE_DATA(nid)->node_start_pfn = start >> PAGE_SHIFT; + NODE_DATA(nid)->node_spanned_pages = (end - start) >> PAGE_SHIFT; + + node_set_online(nid); +} + +/** + * numa_cleanup_meminfo - Cleanup a numa_meminfo + * @mi: numa_meminfo to clean up + * + * Sanitize @mi by merging and removing unncessary memblks. Also check for + * conflicts and clear unused memblks. + * + * RETURNS: + * 0 on success, -errno on failure. + */ +int __init numa_cleanup_meminfo(struct numa_meminfo *mi) +{ + const u64 low = 0; + const u64 high = PFN_PHYS(max_pfn); + int i, j, k; + + /* first, trim all entries */ + for (i = 0; i < mi->nr_blks; i++) { + struct numa_memblk *bi = &mi->blk[i]; + + /* make sure all blocks are inside the limits */ + bi->start = max(bi->start, low); + bi->end = min(bi->end, high); + + /* and there's no empty block */ + if (bi->start >= bi->end) + numa_remove_memblk_from(i--, mi); + } + + /* merge neighboring / overlapping entries */ + for (i = 0; i < mi->nr_blks; i++) { + struct numa_memblk *bi = &mi->blk[i]; + + for (j = i + 1; j < mi->nr_blks; j++) { + struct numa_memblk *bj = &mi->blk[j]; + u64 start, end; + + /* + * See whether there are overlapping blocks. Whine + * about but allow overlaps of the same nid. They + * will be merged below. + */ + if (bi->end > bj->start && bi->start < bj->end) { + if (bi->nid != bj->nid) { + pr_err("NUMA: node %d (%Lx-%Lx) overlaps with node %d (%Lx-%Lx)\n", + bi->nid, bi->start, bi->end, + bj->nid, bj->start, bj->end); + return -EINVAL; + } + pr_warning("NUMA: Warning: node %d (%Lx-%Lx) overlaps with itself (%Lx-%Lx)\n", + bi->nid, bi->start, bi->end, + bj->start, bj->end); + } + + /* + * Join together blocks on the same node, holes + * between which don't overlap with memory on other + * nodes. + */ + if (bi->nid != bj->nid) + continue; + start = min(bi->start, bj->start); + end = max(bi->end, bj->end); + for (k = 0; k < mi->nr_blks; k++) { + struct numa_memblk *bk = &mi->blk[k]; + + if (bi->nid == bk->nid) + continue; + if (start < bk->end && end > bk->start) + break; + } + if (k < mi->nr_blks) + continue; + printk(KERN_INFO "NUMA: Node %d [%Lx,%Lx) + [%Lx,%Lx) -> [%Lx,%Lx)\n", + bi->nid, bi->start, bi->end, bj->start, bj->end, + start, end); + bi->start = start; + bi->end = end; + numa_remove_memblk_from(j--, mi); + } + } + + /* clear unused ones */ + for (i = mi->nr_blks; i < ARRAY_SIZE(mi->blk); i++) { + mi->blk[i].start = mi->blk[i].end = 0; + mi->blk[i].nid = NUMA_NO_NODE; + } + + return 0; +} + +/* + * Set nodes, which have memory in @mi, in *@nodemask. + */ +static void __init numa_nodemask_from_meminfo(nodemask_t *nodemask, + const struct numa_meminfo *mi) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(mi->blk); i++) + if (mi->blk[i].start != mi->blk[i].end && + mi->blk[i].nid != NUMA_NO_NODE) + node_set(mi->blk[i].nid, *nodemask); +} + +/** + * numa_reset_distance - Reset NUMA distance table + * + * The current table is freed. The next numa_set_distance() call will + * create a new one. + */ +void __init numa_reset_distance(void) +{ + size_t size = numa_distance_cnt * numa_distance_cnt * sizeof(numa_distance[0]); + + /* numa_distance could be 1LU marking allocation failure, test cnt */ + if (numa_distance_cnt) + memblock_x86_free_range(__pa(numa_distance), + __pa(numa_distance) + size); + numa_distance_cnt = 0; + numa_distance = NULL; /* enable table creation */ +} + +static int __init numa_alloc_distance(void) +{ + nodemask_t nodes_parsed; + size_t size; + int i, j, cnt = 0; + u64 phys; + + /* size the new table and allocate it */ + nodes_parsed = numa_nodes_parsed; + numa_nodemask_from_meminfo(&nodes_parsed, &numa_meminfo); + + for_each_node_mask(i, nodes_parsed) + cnt = i; + cnt++; + size = cnt * cnt * sizeof(numa_distance[0]); + + phys = memblock_find_in_range(0, PFN_PHYS(max_pfn_mapped), + size, PAGE_SIZE); + if (phys == MEMBLOCK_ERROR) { + pr_warning("NUMA: Warning: can't allocate distance table!\n"); + /* don't retry until explicitly reset */ + numa_distance = (void *)1LU; + return -ENOMEM; + } + memblock_x86_reserve_range(phys, phys + size, "NUMA DIST"); + + numa_distance = __va(phys); + numa_distance_cnt = cnt; + + /* fill with the default distances */ + for (i = 0; i < cnt; i++) + for (j = 0; j < cnt; j++) + numa_distance[i * cnt + j] = i == j ? + LOCAL_DISTANCE : REMOTE_DISTANCE; + printk(KERN_DEBUG "NUMA: Initialized distance table, cnt=%d\n", cnt); + + return 0; +} + +/** + * numa_set_distance - Set NUMA distance from one NUMA to another + * @from: the 'from' node to set distance + * @to: the 'to' node to set distance + * @distance: NUMA distance + * + * Set the distance from node @from to @to to @distance. If distance table + * doesn't exist, one which is large enough to accommodate all the currently + * known nodes will be created. + * + * If such table cannot be allocated, a warning is printed and further + * calls are ignored until the distance table is reset with + * numa_reset_distance(). + * + * If @from or @to is higher than the highest known node at the time of + * table creation or @distance doesn't make sense, the call is ignored. + * This is to allow simplification of specific NUMA config implementations. + */ +void __init numa_set_distance(int from, int to, int distance) +{ + if (!numa_distance && numa_alloc_distance() < 0) + return; + + if (from >= numa_distance_cnt || to >= numa_distance_cnt) { + printk_once(KERN_DEBUG "NUMA: Debug: distance out of bound, from=%d to=%d distance=%d\n", + from, to, distance); + return; + } + + if ((u8)distance != distance || + (from == to && distance != LOCAL_DISTANCE)) { + pr_warn_once("NUMA: Warning: invalid distance parameter, from=%d to=%d distance=%d\n", + from, to, distance); + return; + } + + numa_distance[from * numa_distance_cnt + to] = distance; +} + +int __node_distance(int from, int to) +{ + if (from >= numa_distance_cnt || to >= numa_distance_cnt) + return from == to ? LOCAL_DISTANCE : REMOTE_DISTANCE; + return numa_distance[from * numa_distance_cnt + to]; +} +EXPORT_SYMBOL(__node_distance); + +/* + * Sanity check to catch more bad NUMA configurations (they are amazingly + * common). Make sure the nodes cover all memory. + */ +static bool __init numa_meminfo_cover_memory(const struct numa_meminfo *mi) +{ + u64 numaram, e820ram; + int i; + + numaram = 0; + for (i = 0; i < mi->nr_blks; i++) { + u64 s = mi->blk[i].start >> PAGE_SHIFT; + u64 e = mi->blk[i].end >> PAGE_SHIFT; + numaram += e - s; + numaram -= __absent_pages_in_range(mi->blk[i].nid, s, e); + if ((s64)numaram < 0) + numaram = 0; + } + + e820ram = max_pfn - (memblock_x86_hole_size(0, + PFN_PHYS(max_pfn)) >> PAGE_SHIFT); + /* We seem to lose 3 pages somewhere. Allow 1M of slack. */ + if ((s64)(e820ram - numaram) >= (1 << (20 - PAGE_SHIFT))) { + printk(KERN_ERR "NUMA: nodes only cover %LuMB of your %LuMB e820 RAM. Not used.\n", + (numaram << PAGE_SHIFT) >> 20, + (e820ram << PAGE_SHIFT) >> 20); + return false; + } + return true; +} + +static int __init numa_register_memblks(struct numa_meminfo *mi) +{ + int i, nid; + + /* Account for nodes with cpus and no memory */ + node_possible_map = numa_nodes_parsed; + numa_nodemask_from_meminfo(&node_possible_map, mi); + if (WARN_ON(nodes_empty(node_possible_map))) + return -EINVAL; + + for (i = 0; i < mi->nr_blks; i++) + memblock_x86_register_active_regions(mi->blk[i].nid, + mi->blk[i].start >> PAGE_SHIFT, + mi->blk[i].end >> PAGE_SHIFT); + + /* for out of order entries */ + sort_node_map(); + if (!numa_meminfo_cover_memory(mi)) + return -EINVAL; + + /* Finally register nodes. */ + for_each_node_mask(nid, node_possible_map) { + u64 start = PFN_PHYS(max_pfn); + u64 end = 0; + + for (i = 0; i < mi->nr_blks; i++) { + if (nid != mi->blk[i].nid) + continue; + start = min(mi->blk[i].start, start); + end = max(mi->blk[i].end, end); + } + + if (start < end) + setup_node_data(nid, start, end); + } + + return 0; +} + /* * There are unfortunately some poorly designed mainboards around that * only connect memory to a single CPU. This breaks the 1:1 cpu->node @@ -102,7 +540,7 @@ void __init setup_node_to_cpumask_map(void) * as the number of CPUs is not known yet. We round robin the existing * nodes. */ -void __init numa_init_array(void) +static void __init numa_init_array(void) { int rr, i; @@ -117,6 +555,95 @@ void __init numa_init_array(void) } } +static int __init numa_init(int (*init_func)(void)) +{ + int i; + int ret; + + for (i = 0; i < MAX_LOCAL_APIC; i++) + set_apicid_to_node(i, NUMA_NO_NODE); + + nodes_clear(numa_nodes_parsed); + nodes_clear(node_possible_map); + nodes_clear(node_online_map); + memset(&numa_meminfo, 0, sizeof(numa_meminfo)); + remove_all_active_ranges(); + numa_reset_distance(); + + ret = init_func(); + if (ret < 0) + return ret; + ret = numa_cleanup_meminfo(&numa_meminfo); + if (ret < 0) + return ret; + + numa_emulation(&numa_meminfo, numa_distance_cnt); + + ret = numa_register_memblks(&numa_meminfo); + if (ret < 0) + return ret; + + for (i = 0; i < nr_cpu_ids; i++) { + int nid = early_cpu_to_node(i); + + if (nid == NUMA_NO_NODE) + continue; + if (!node_online(nid)) + numa_clear_node(i); + } + numa_init_array(); + return 0; +} + +/** + * dummy_numa_init - Fallback dummy NUMA init + * + * Used if there's no underlying NUMA architecture, NUMA initialization + * fails, or NUMA is disabled on the command line. + * + * Must online at least one node and add memory blocks that cover all + * allowed memory. This function must not fail. + */ +static int __init dummy_numa_init(void) +{ + printk(KERN_INFO "%s\n", + numa_off ? "NUMA turned off" : "No NUMA configuration found"); + printk(KERN_INFO "Faking a node at %016Lx-%016Lx\n", + 0LLU, PFN_PHYS(max_pfn)); + + node_set(0, numa_nodes_parsed); + numa_add_memblk(0, 0, PFN_PHYS(max_pfn)); + + return 0; +} + +/** + * x86_numa_init - Initialize NUMA + * + * Try each configured NUMA initialization method until one succeeds. The + * last fallback is dummy single node config encomapssing whole memory and + * never fails. + */ +void __init x86_numa_init(void) +{ + if (!numa_off) { +#ifdef CONFIG_X86_NUMAQ + if (!numa_init(numaq_numa_init)) + return; +#endif +#ifdef CONFIG_ACPI_NUMA + if (!numa_init(x86_acpi_numa_init)) + return; +#endif +#ifdef CONFIG_AMD_NUMA + if (!numa_init(amd_numa_init)) + return; +#endif + } + + numa_init(dummy_numa_init); +} + static __init int find_near_online_node(int node) { int n, val; @@ -282,3 +809,18 @@ const struct cpumask *cpumask_of_node(int node) EXPORT_SYMBOL(cpumask_of_node); #endif /* !CONFIG_DEBUG_PER_CPU_MAPS */ + +#ifdef CONFIG_MEMORY_HOTPLUG +int memory_add_physaddr_to_nid(u64 start) +{ + struct numa_meminfo *mi = &numa_meminfo; + int nid = mi->blk[0].nid; + int i; + + for (i = 0; i < mi->nr_blks; i++) + if (mi->blk[i].start <= start && mi->blk[i].end > start) + nid = mi->blk[i].nid; + return nid; +} +EXPORT_SYMBOL_GPL(memory_add_physaddr_to_nid); +#endif diff --git a/arch/x86/mm/numa_32.c b/arch/x86/mm/numa_32.c index bde3906420d..849a975d3fa 100644 --- a/arch/x86/mm/numa_32.c +++ b/arch/x86/mm/numa_32.c @@ -22,39 +22,11 @@ * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. */ -#include <linux/mm.h> #include <linux/bootmem.h> #include <linux/memblock.h> -#include <linux/mmzone.h> -#include <linux/highmem.h> -#include <linux/initrd.h> -#include <linux/nodemask.h> #include <linux/module.h> -#include <linux/kexec.h> -#include <linux/pfn.h> -#include <linux/swap.h> -#include <linux/acpi.h> - -#include <asm/e820.h> -#include <asm/setup.h> -#include <asm/mmzone.h> -#include <asm/bios_ebda.h> -#include <asm/proto.h> - -struct pglist_data *node_data[MAX_NUMNODES] __read_mostly; -EXPORT_SYMBOL(node_data); - -/* - * numa interface - we expect the numa architecture specific code to have - * populated the following initialisation. - * - * 1) node_online_map - the map of all nodes configured (online) in the system - * 2) node_start_pfn - the starting page frame number for a node - * 3) node_end_pfn - the ending page fram number for a node - */ -unsigned long node_start_pfn[MAX_NUMNODES] __read_mostly; -unsigned long node_end_pfn[MAX_NUMNODES] __read_mostly; +#include "numa_internal.h" #ifdef CONFIG_DISCONTIGMEM /* @@ -99,108 +71,46 @@ unsigned long node_memmap_size_bytes(int nid, unsigned long start_pfn, } #endif -extern unsigned long find_max_low_pfn(void); extern unsigned long highend_pfn, highstart_pfn; #define LARGE_PAGE_BYTES (PTRS_PER_PTE * PAGE_SIZE) -unsigned long node_remap_size[MAX_NUMNODES]; static void *node_remap_start_vaddr[MAX_NUMNODES]; void set_pmd_pfn(unsigned long vaddr, unsigned long pfn, pgprot_t flags); -static unsigned long kva_start_pfn; -static unsigned long kva_pages; - -int __cpuinit numa_cpu_node(int cpu) -{ - return apic->x86_32_numa_cpu_node(cpu); -} - -/* - * FLAT - support for basic PC memory model with discontig enabled, essentially - * a single node with all available processors in it with a flat - * memory map. - */ -int __init get_memcfg_numa_flat(void) -{ - printk(KERN_DEBUG "NUMA - single node, flat memory mode\n"); - - node_start_pfn[0] = 0; - node_end_pfn[0] = max_pfn; - memblock_x86_register_active_regions(0, 0, max_pfn); - memory_present(0, 0, max_pfn); - node_remap_size[0] = node_memmap_size_bytes(0, 0, max_pfn); - - /* Indicate there is one node available. */ - nodes_clear(node_online_map); - node_set_online(0); - return 1; -} - -/* - * Find the highest page frame number we have available for the node - */ -static void __init propagate_e820_map_node(int nid) -{ - if (node_end_pfn[nid] > max_pfn) - node_end_pfn[nid] = max_pfn; - /* - * if a user has given mem=XXXX, then we need to make sure - * that the node _starts_ before that, too, not just ends - */ - if (node_start_pfn[nid] > max_pfn) - node_start_pfn[nid] = max_pfn; - BUG_ON(node_start_pfn[nid] > node_end_pfn[nid]); -} - -/* - * Allocate memory for the pg_data_t for this node via a crude pre-bootmem - * method. For node zero take this from the bottom of memory, for - * subsequent nodes place them at node_remap_start_vaddr which contains - * node local data in physically node local memory. See setup_memory() - * for details. - */ -static void __init allocate_pgdat(int nid) -{ - char buf[16]; - - if (node_has_online_mem(nid) && node_remap_start_vaddr[nid]) - NODE_DATA(nid) = (pg_data_t *)node_remap_start_vaddr[nid]; - else { - unsigned long pgdat_phys; - pgdat_phys = memblock_find_in_range(min_low_pfn<<PAGE_SHIFT, - max_pfn_mapped<<PAGE_SHIFT, - sizeof(pg_data_t), - PAGE_SIZE); - NODE_DATA(nid) = (pg_data_t *)(pfn_to_kaddr(pgdat_phys>>PAGE_SHIFT)); - memset(buf, 0, sizeof(buf)); - sprintf(buf, "NODE_DATA %d", nid); - memblock_x86_reserve_range(pgdat_phys, pgdat_phys + sizeof(pg_data_t), buf); - } - printk(KERN_DEBUG "allocate_pgdat: node %d NODE_DATA %08lx\n", - nid, (unsigned long)NODE_DATA(nid)); -} - /* - * In the DISCONTIGMEM and SPARSEMEM memory model, a portion of the kernel - * virtual address space (KVA) is reserved and portions of nodes are mapped - * using it. This is to allow node-local memory to be allocated for - * structures that would normally require ZONE_NORMAL. The memory is - * allocated with alloc_remap() and callers should be prepared to allocate - * from the bootmem allocator instead. + * Remap memory allocator */ static unsigned long node_remap_start_pfn[MAX_NUMNODES]; static void *node_remap_end_vaddr[MAX_NUMNODES]; static void *node_remap_alloc_vaddr[MAX_NUMNODES]; -static unsigned long node_remap_offset[MAX_NUMNODES]; +/** + * alloc_remap - Allocate remapped memory + * @nid: NUMA node to allocate memory from + * @size: The size of allocation + * + * Allocate @size bytes from the remap area of NUMA node @nid. The + * size of the remap area is predetermined by init_alloc_remap() and + * only the callers considered there should call this function. For + * more info, please read the comment on top of init_alloc_remap(). + * + * The caller must be ready to handle allocation failure from this + * function and fall back to regular memory allocator in such cases. + * + * CONTEXT: + * Single CPU early boot context. + * + * RETURNS: + * Pointer to the allocated memory on success, %NULL on failure. + */ void *alloc_remap(int nid, unsigned long size) { void *allocation = node_remap_alloc_vaddr[nid]; size = ALIGN(size, L1_CACHE_BYTES); - if (!allocation || (allocation + size) >= node_remap_end_vaddr[nid]) + if (!allocation || (allocation + size) > node_remap_end_vaddr[nid]) return NULL; node_remap_alloc_vaddr[nid] += size; @@ -209,26 +119,6 @@ void *alloc_remap(int nid, unsigned long size) return allocation; } -static void __init remap_numa_kva(void) -{ - void *vaddr; - unsigned long pfn; - int node; - - for_each_online_node(node) { - printk(KERN_DEBUG "remap_numa_kva: node %d\n", node); - for (pfn=0; pfn < node_remap_size[node]; pfn += PTRS_PER_PTE) { - vaddr = node_remap_start_vaddr[node]+(pfn<<PAGE_SHIFT); - printk(KERN_DEBUG "remap_numa_kva: %08lx to pfn %08lx\n", - (unsigned long)vaddr, - node_remap_start_pfn[node] + pfn); - set_pmd_pfn((ulong) vaddr, - node_remap_start_pfn[node] + pfn, - PAGE_KERNEL_LARGE); - } - } -} - #ifdef CONFIG_HIBERNATION /** * resume_map_numa_kva - add KVA mapping to the temporary page tables created @@ -240,15 +130,16 @@ void resume_map_numa_kva(pgd_t *pgd_base) int node; for_each_online_node(node) { - unsigned long start_va, start_pfn, size, pfn; + unsigned long start_va, start_pfn, nr_pages, pfn; start_va = (unsigned long)node_remap_start_vaddr[node]; start_pfn = node_remap_start_pfn[node]; - size = node_remap_size[node]; + nr_pages = (node_remap_end_vaddr[node] - + node_remap_start_vaddr[node]) >> PAGE_SHIFT; printk(KERN_DEBUG "%s: node %d\n", __func__, node); - for (pfn = 0; pfn < size; pfn += PTRS_PER_PTE) { + for (pfn = 0; pfn < nr_pages; pfn += PTRS_PER_PTE) { unsigned long vaddr = start_va + (pfn << PAGE_SHIFT); pgd_t *pgd = pgd_base + pgd_index(vaddr); pud_t *pud = pud_offset(pgd, vaddr); @@ -264,132 +155,89 @@ void resume_map_numa_kva(pgd_t *pgd_base) } #endif -static __init unsigned long calculate_numa_remap_pages(void) +/** + * init_alloc_remap - Initialize remap allocator for a NUMA node + * @nid: NUMA node to initizlie remap allocator for + * + * NUMA nodes may end up without any lowmem. As allocating pgdat and + * memmap on a different node with lowmem is inefficient, a special + * remap allocator is implemented which can be used by alloc_remap(). + * + * For each node, the amount of memory which will be necessary for + * pgdat and memmap is calculated and two memory areas of the size are + * allocated - one in the node and the other in lowmem; then, the area + * in the node is remapped to the lowmem area. + * + * As pgdat and memmap must be allocated in lowmem anyway, this + * doesn't waste lowmem address space; however, the actual lowmem + * which gets remapped over is wasted. The amount shouldn't be + * problematic on machines this feature will be used. + * + * Initialization failure isn't fatal. alloc_remap() is used + * opportunistically and the callers will fall back to other memory + * allocation mechanisms on failure. + */ +void __init init_alloc_remap(int nid, u64 start, u64 end) { - int nid; - unsigned long size, reserve_pages = 0; - - for_each_online_node(nid) { - u64 node_kva_target; - u64 node_kva_final; - - /* - * The acpi/srat node info can show hot-add memroy zones - * where memory could be added but not currently present. - */ - printk(KERN_DEBUG "node %d pfn: [%lx - %lx]\n", - nid, node_start_pfn[nid], node_end_pfn[nid]); - if (node_start_pfn[nid] > max_pfn) - continue; - if (!node_end_pfn[nid]) - continue; - if (node_end_pfn[nid] > max_pfn) - node_end_pfn[nid] = max_pfn; - - /* ensure the remap includes space for the pgdat. */ - size = node_remap_size[nid] + sizeof(pg_data_t); - - /* convert size to large (pmd size) pages, rounding up */ - size = (size + LARGE_PAGE_BYTES - 1) / LARGE_PAGE_BYTES; - /* now the roundup is correct, convert to PAGE_SIZE pages */ - size = size * PTRS_PER_PTE; - - node_kva_target = round_down(node_end_pfn[nid] - size, - PTRS_PER_PTE); - node_kva_target <<= PAGE_SHIFT; - do { - node_kva_final = memblock_find_in_range(node_kva_target, - ((u64)node_end_pfn[nid])<<PAGE_SHIFT, - ((u64)size)<<PAGE_SHIFT, - LARGE_PAGE_BYTES); - node_kva_target -= LARGE_PAGE_BYTES; - } while (node_kva_final == MEMBLOCK_ERROR && - (node_kva_target>>PAGE_SHIFT) > (node_start_pfn[nid])); - - if (node_kva_final == MEMBLOCK_ERROR) - panic("Can not get kva ram\n"); - - node_remap_size[nid] = size; - node_remap_offset[nid] = reserve_pages; - reserve_pages += size; - printk(KERN_DEBUG "Reserving %ld pages of KVA for lmem_map of" - " node %d at %llx\n", - size, nid, node_kva_final>>PAGE_SHIFT); - - /* - * prevent kva address below max_low_pfn want it on system - * with less memory later. - * layout will be: KVA address , KVA RAM - * - * we are supposed to only record the one less then max_low_pfn - * but we could have some hole in high memory, and it will only - * check page_is_ram(pfn) && !page_is_reserved_early(pfn) to decide - * to use it as free. - * So memblock_x86_reserve_range here, hope we don't run out of that array - */ - memblock_x86_reserve_range(node_kva_final, - node_kva_final+(((u64)size)<<PAGE_SHIFT), - "KVA RAM"); - - node_remap_start_pfn[nid] = node_kva_final>>PAGE_SHIFT; - } - printk(KERN_INFO "Reserving total of %lx pages for numa KVA remap\n", - reserve_pages); - return reserve_pages; -} + unsigned long start_pfn = start >> PAGE_SHIFT; + unsigned long end_pfn = end >> PAGE_SHIFT; + unsigned long size, pfn; + u64 node_pa, remap_pa; + void *remap_va; -static void init_remap_allocator(int nid) -{ - node_remap_start_vaddr[nid] = pfn_to_kaddr( - kva_start_pfn + node_remap_offset[nid]); - node_remap_end_vaddr[nid] = node_remap_start_vaddr[nid] + - (node_remap_size[nid] * PAGE_SIZE); - node_remap_alloc_vaddr[nid] = node_remap_start_vaddr[nid] + - ALIGN(sizeof(pg_data_t), PAGE_SIZE); - - printk(KERN_DEBUG "node %d will remap to vaddr %08lx - %08lx\n", nid, - (ulong) node_remap_start_vaddr[nid], - (ulong) node_remap_end_vaddr[nid]); + /* + * The acpi/srat node info can show hot-add memroy zones where + * memory could be added but not currently present. + */ + printk(KERN_DEBUG "node %d pfn: [%lx - %lx]\n", + nid, start_pfn, end_pfn); + + /* calculate the necessary space aligned to large page size */ + size = node_memmap_size_bytes(nid, start_pfn, end_pfn); + size += ALIGN(sizeof(pg_data_t), PAGE_SIZE); + size = ALIGN(size, LARGE_PAGE_BYTES); + + /* allocate node memory and the lowmem remap area */ + node_pa = memblock_find_in_range(start, end, size, LARGE_PAGE_BYTES); + if (node_pa == MEMBLOCK_ERROR) { + pr_warning("remap_alloc: failed to allocate %lu bytes for node %d\n", + size, nid); + return; + } + memblock_x86_reserve_range(node_pa, node_pa + size, "KVA RAM"); + + remap_pa = memblock_find_in_range(min_low_pfn << PAGE_SHIFT, + max_low_pfn << PAGE_SHIFT, + size, LARGE_PAGE_BYTES); + if (remap_pa == MEMBLOCK_ERROR) { + pr_warning("remap_alloc: failed to allocate %lu bytes remap area for node %d\n", + size, nid); + memblock_x86_free_range(node_pa, node_pa + size); + return; + } + memblock_x86_reserve_range(remap_pa, remap_pa + size, "KVA PG"); + remap_va = phys_to_virt(remap_pa); + + /* perform actual remap */ + for (pfn = 0; pfn < size >> PAGE_SHIFT; pfn += PTRS_PER_PTE) + set_pmd_pfn((unsigned long)remap_va + (pfn << PAGE_SHIFT), + (node_pa >> PAGE_SHIFT) + pfn, + PAGE_KERNEL_LARGE); + + /* initialize remap allocator parameters */ + node_remap_start_pfn[nid] = node_pa >> PAGE_SHIFT; + node_remap_start_vaddr[nid] = remap_va; + node_remap_end_vaddr[nid] = remap_va + size; + node_remap_alloc_vaddr[nid] = remap_va; + + printk(KERN_DEBUG "remap_alloc: node %d [%08llx-%08llx) -> [%p-%p)\n", + nid, node_pa, node_pa + size, remap_va, remap_va + size); } void __init initmem_init(void) { - int nid; - long kva_target_pfn; - - /* - * When mapping a NUMA machine we allocate the node_mem_map arrays - * from node local memory. They are then mapped directly into KVA - * between zone normal and vmalloc space. Calculate the size of - * this space and use it to adjust the boundary between ZONE_NORMAL - * and ZONE_HIGHMEM. - */ - - get_memcfg_numa(); - numa_init_array(); - - kva_pages = roundup(calculate_numa_remap_pages(), PTRS_PER_PTE); + x86_numa_init(); - kva_target_pfn = round_down(max_low_pfn - kva_pages, PTRS_PER_PTE); - do { - kva_start_pfn = memblock_find_in_range(kva_target_pfn<<PAGE_SHIFT, - max_low_pfn<<PAGE_SHIFT, - kva_pages<<PAGE_SHIFT, - PTRS_PER_PTE<<PAGE_SHIFT) >> PAGE_SHIFT; - kva_target_pfn -= PTRS_PER_PTE; - } while (kva_start_pfn == MEMBLOCK_ERROR && kva_target_pfn > min_low_pfn); - - if (kva_start_pfn == MEMBLOCK_ERROR) - panic("Can not get kva space\n"); - - printk(KERN_INFO "kva_start_pfn ~ %lx max_low_pfn ~ %lx\n", - kva_start_pfn, max_low_pfn); - printk(KERN_INFO "max_pfn = %lx\n", max_pfn); - - /* avoid clash with initrd */ - memblock_x86_reserve_range(kva_start_pfn<<PAGE_SHIFT, - (kva_start_pfn + kva_pages)<<PAGE_SHIFT, - "KVA PG"); #ifdef CONFIG_HIGHMEM highstart_pfn = highend_pfn = max_pfn; if (max_pfn > max_low_pfn) @@ -409,51 +257,9 @@ void __init initmem_init(void) printk(KERN_DEBUG "Low memory ends at vaddr %08lx\n", (ulong) pfn_to_kaddr(max_low_pfn)); - for_each_online_node(nid) { - init_remap_allocator(nid); - - allocate_pgdat(nid); - } - remap_numa_kva(); printk(KERN_DEBUG "High memory starts at vaddr %08lx\n", (ulong) pfn_to_kaddr(highstart_pfn)); - for_each_online_node(nid) - propagate_e820_map_node(nid); - - for_each_online_node(nid) { - memset(NODE_DATA(nid), 0, sizeof(struct pglist_data)); - NODE_DATA(nid)->node_id = nid; - } setup_bootmem_allocator(); } - -#ifdef CONFIG_MEMORY_HOTPLUG -static int paddr_to_nid(u64 addr) -{ - int nid; - unsigned long pfn = PFN_DOWN(addr); - - for_each_node(nid) - if (node_start_pfn[nid] <= pfn && - pfn < node_end_pfn[nid]) - return nid; - - return -1; -} - -/* - * This function is used to ask node id BEFORE memmap and mem_section's - * initialization (pfn_to_nid() can't be used yet). - * If _PXM is not defined on ACPI's DSDT, node id must be found by this. - */ -int memory_add_physaddr_to_nid(u64 addr) -{ - int nid = paddr_to_nid(addr); - return (nid >= 0) ? nid : 0; -} - -EXPORT_SYMBOL_GPL(memory_add_physaddr_to_nid); -#endif - diff --git a/arch/x86/mm/numa_64.c b/arch/x86/mm/numa_64.c index 85b52fc0308..dd27f401f0a 100644 --- a/arch/x86/mm/numa_64.c +++ b/arch/x86/mm/numa_64.c @@ -2,646 +2,13 @@ * Generic VM initialization for x86-64 NUMA setups. * Copyright 2002,2003 Andi Kleen, SuSE Labs. */ -#include <linux/kernel.h> -#include <linux/mm.h> -#include <linux/string.h> -#include <linux/init.h> #include <linux/bootmem.h> -#include <linux/memblock.h> -#include <linux/mmzone.h> -#include <linux/ctype.h> -#include <linux/module.h> -#include <linux/nodemask.h> -#include <linux/sched.h> -#include <linux/acpi.h> - -#include <asm/e820.h> -#include <asm/proto.h> -#include <asm/dma.h> -#include <asm/acpi.h> -#include <asm/amd_nb.h> #include "numa_internal.h" -struct pglist_data *node_data[MAX_NUMNODES] __read_mostly; -EXPORT_SYMBOL(node_data); - -nodemask_t numa_nodes_parsed __initdata; - -struct memnode memnode; - -static unsigned long __initdata nodemap_addr; -static unsigned long __initdata nodemap_size; - -static struct numa_meminfo numa_meminfo __initdata; - -static int numa_distance_cnt; -static u8 *numa_distance; - -/* - * Given a shift value, try to populate memnodemap[] - * Returns : - * 1 if OK - * 0 if memnodmap[] too small (of shift too small) - * -1 if node overlap or lost ram (shift too big) - */ -static int __init populate_memnodemap(const struct numa_meminfo *mi, int shift) -{ - unsigned long addr, end; - int i, res = -1; - - memset(memnodemap, 0xff, sizeof(s16)*memnodemapsize); - for (i = 0; i < mi->nr_blks; i++) { - addr = mi->blk[i].start; - end = mi->blk[i].end; - if (addr >= end) - continue; - if ((end >> shift) >= memnodemapsize) - return 0; - do { - if (memnodemap[addr >> shift] != NUMA_NO_NODE) - return -1; - memnodemap[addr >> shift] = mi->blk[i].nid; - addr += (1UL << shift); - } while (addr < end); - res = 1; - } - return res; -} - -static int __init allocate_cachealigned_memnodemap(void) -{ - unsigned long addr; - - memnodemap = memnode.embedded_map; - if (memnodemapsize <= ARRAY_SIZE(memnode.embedded_map)) - return 0; - - addr = 0x8000; - nodemap_size = roundup(sizeof(s16) * memnodemapsize, L1_CACHE_BYTES); - nodemap_addr = memblock_find_in_range(addr, get_max_mapped(), - nodemap_size, L1_CACHE_BYTES); - if (nodemap_addr == MEMBLOCK_ERROR) { - printk(KERN_ERR - "NUMA: Unable to allocate Memory to Node hash map\n"); - nodemap_addr = nodemap_size = 0; - return -1; - } - memnodemap = phys_to_virt(nodemap_addr); - memblock_x86_reserve_range(nodemap_addr, nodemap_addr + nodemap_size, "MEMNODEMAP"); - - printk(KERN_DEBUG "NUMA: Allocated memnodemap from %lx - %lx\n", - nodemap_addr, nodemap_addr + nodemap_size); - return 0; -} - -/* - * The LSB of all start and end addresses in the node map is the value of the - * maximum possible shift. - */ -static int __init extract_lsb_from_nodes(const struct numa_meminfo *mi) -{ - int i, nodes_used = 0; - unsigned long start, end; - unsigned long bitfield = 0, memtop = 0; - - for (i = 0; i < mi->nr_blks; i++) { - start = mi->blk[i].start; - end = mi->blk[i].end; - if (start >= end) - continue; - bitfield |= start; - nodes_used++; - if (end > memtop) - memtop = end; - } - if (nodes_used <= 1) - i = 63; - else - i = find_first_bit(&bitfield, sizeof(unsigned long)*8); - memnodemapsize = (memtop >> i)+1; - return i; -} - -static int __init compute_hash_shift(const struct numa_meminfo *mi) -{ - int shift; - - shift = extract_lsb_from_nodes(mi); - if (allocate_cachealigned_memnodemap()) - return -1; - printk(KERN_DEBUG "NUMA: Using %d for the hash shift.\n", - shift); - - if (populate_memnodemap(mi, shift) != 1) { - printk(KERN_INFO "Your memory is not aligned you need to " - "rebuild your kernel with a bigger NODEMAPSIZE " - "shift=%d\n", shift); - return -1; - } - return shift; -} - -int __meminit __early_pfn_to_nid(unsigned long pfn) -{ - return phys_to_nid(pfn << PAGE_SHIFT); -} - -static void * __init early_node_mem(int nodeid, unsigned long start, - unsigned long end, unsigned long size, - unsigned long align) -{ - unsigned long mem; - - /* - * put it on high as possible - * something will go with NODE_DATA - */ - if (start < (MAX_DMA_PFN<<PAGE_SHIFT)) - start = MAX_DMA_PFN<<PAGE_SHIFT; - if (start < (MAX_DMA32_PFN<<PAGE_SHIFT) && - end > (MAX_DMA32_PFN<<PAGE_SHIFT)) - start = MAX_DMA32_PFN<<PAGE_SHIFT; - mem = memblock_x86_find_in_range_node(nodeid, start, end, size, align); - if (mem != MEMBLOCK_ERROR) - return __va(mem); - - /* extend the search scope */ - end = max_pfn_mapped << PAGE_SHIFT; - start = MAX_DMA_PFN << PAGE_SHIFT; - mem = memblock_find_in_range(start, end, size, align); - if (mem != MEMBLOCK_ERROR) - return __va(mem); - - printk(KERN_ERR "Cannot find %lu bytes in node %d\n", - size, nodeid); - - return NULL; -} - -static int __init numa_add_memblk_to(int nid, u64 start, u64 end, - struct numa_meminfo *mi) -{ - /* ignore zero length blks */ - if (start == end) - return 0; - - /* whine about and ignore invalid blks */ - if (start > end || nid < 0 || nid >= MAX_NUMNODES) { - pr_warning("NUMA: Warning: invalid memblk node %d (%Lx-%Lx)\n", - nid, start, end); - return 0; - } - - if (mi->nr_blks >= NR_NODE_MEMBLKS) { - pr_err("NUMA: too many memblk ranges\n"); - return -EINVAL; - } - - mi->blk[mi->nr_blks].start = start; - mi->blk[mi->nr_blks].end = end; - mi->blk[mi->nr_blks].nid = nid; - mi->nr_blks++; - return 0; -} - -/** - * numa_remove_memblk_from - Remove one numa_memblk from a numa_meminfo - * @idx: Index of memblk to remove - * @mi: numa_meminfo to remove memblk from - * - * Remove @idx'th numa_memblk from @mi by shifting @mi->blk[] and - * decrementing @mi->nr_blks. - */ -void __init numa_remove_memblk_from(int idx, struct numa_meminfo *mi) -{ - mi->nr_blks--; - memmove(&mi->blk[idx], &mi->blk[idx + 1], - (mi->nr_blks - idx) * sizeof(mi->blk[0])); -} - -/** - * numa_add_memblk - Add one numa_memblk to numa_meminfo - * @nid: NUMA node ID of the new memblk - * @start: Start address of the new memblk - * @end: End address of the new memblk - * - * Add a new memblk to the default numa_meminfo. - * - * RETURNS: - * 0 on success, -errno on failure. - */ -int __init numa_add_memblk(int nid, u64 start, u64 end) -{ - return numa_add_memblk_to(nid, start, end, &numa_meminfo); -} - -/* Initialize bootmem allocator for a node */ -void __init -setup_node_bootmem(int nodeid, unsigned long start, unsigned long end) -{ - unsigned long start_pfn, last_pfn, nodedata_phys; - const int pgdat_size = roundup(sizeof(pg_data_t), PAGE_SIZE); - int nid; - - if (!end) - return; - - /* - * Don't confuse VM with a node that doesn't have the - * minimum amount of memory: - */ - if (end && (end - start) < NODE_MIN_SIZE) - return; - - start = roundup(start, ZONE_ALIGN); - - printk(KERN_INFO "Initmem setup node %d %016lx-%016lx\n", nodeid, - start, end); - - start_pfn = start >> PAGE_SHIFT; - last_pfn = end >> PAGE_SHIFT; - - node_data[nodeid] = early_node_mem(nodeid, start, end, pgdat_size, - SMP_CACHE_BYTES); - if (node_data[nodeid] == NULL) - return; - nodedata_phys = __pa(node_data[nodeid]); - memblock_x86_reserve_range(nodedata_phys, nodedata_phys + pgdat_size, "NODE_DATA"); - printk(KERN_INFO " NODE_DATA [%016lx - %016lx]\n", nodedata_phys, - nodedata_phys + pgdat_size - 1); - nid = phys_to_nid(nodedata_phys); - if (nid != nodeid) - printk(KERN_INFO " NODE_DATA(%d) on node %d\n", nodeid, nid); - - memset(NODE_DATA(nodeid), 0, sizeof(pg_data_t)); - NODE_DATA(nodeid)->node_id = nodeid; - NODE_DATA(nodeid)->node_start_pfn = start_pfn; - NODE_DATA(nodeid)->node_spanned_pages = last_pfn - start_pfn; - - node_set_online(nodeid); -} - -/** - * numa_cleanup_meminfo - Cleanup a numa_meminfo - * @mi: numa_meminfo to clean up - * - * Sanitize @mi by merging and removing unncessary memblks. Also check for - * conflicts and clear unused memblks. - * - * RETURNS: - * 0 on success, -errno on failure. - */ -int __init numa_cleanup_meminfo(struct numa_meminfo *mi) -{ - const u64 low = 0; - const u64 high = (u64)max_pfn << PAGE_SHIFT; - int i, j, k; - - for (i = 0; i < mi->nr_blks; i++) { - struct numa_memblk *bi = &mi->blk[i]; - - /* make sure all blocks are inside the limits */ - bi->start = max(bi->start, low); - bi->end = min(bi->end, high); - - /* and there's no empty block */ - if (bi->start >= bi->end) { - numa_remove_memblk_from(i--, mi); - continue; - } - - for (j = i + 1; j < mi->nr_blks; j++) { - struct numa_memblk *bj = &mi->blk[j]; - unsigned long start, end; - - /* - * See whether there are overlapping blocks. Whine - * about but allow overlaps of the same nid. They - * will be merged below. - */ - if (bi->end > bj->start && bi->start < bj->end) { - if (bi->nid != bj->nid) { - pr_err("NUMA: node %d (%Lx-%Lx) overlaps with node %d (%Lx-%Lx)\n", - bi->nid, bi->start, bi->end, - bj->nid, bj->start, bj->end); - return -EINVAL; - } - pr_warning("NUMA: Warning: node %d (%Lx-%Lx) overlaps with itself (%Lx-%Lx)\n", - bi->nid, bi->start, bi->end, - bj->start, bj->end); - } - - /* - * Join together blocks on the same node, holes - * between which don't overlap with memory on other - * nodes. - */ - if (bi->nid != bj->nid) - continue; - start = max(min(bi->start, bj->start), low); - end = min(max(bi->end, bj->end), high); - for (k = 0; k < mi->nr_blks; k++) { - struct numa_memblk *bk = &mi->blk[k]; - - if (bi->nid == bk->nid) - continue; - if (start < bk->end && end > bk->start) - break; - } - if (k < mi->nr_blks) - continue; - printk(KERN_INFO "NUMA: Node %d [%Lx,%Lx) + [%Lx,%Lx) -> [%lx,%lx)\n", - bi->nid, bi->start, bi->end, bj->start, bj->end, - start, end); - bi->start = start; - bi->end = end; - numa_remove_memblk_from(j--, mi); - } - } - - for (i = mi->nr_blks; i < ARRAY_SIZE(mi->blk); i++) { - mi->blk[i].start = mi->blk[i].end = 0; - mi->blk[i].nid = NUMA_NO_NODE; - } - - return 0; -} - -/* - * Set nodes, which have memory in @mi, in *@nodemask. - */ -static void __init numa_nodemask_from_meminfo(nodemask_t *nodemask, - const struct numa_meminfo *mi) -{ - int i; - - for (i = 0; i < ARRAY_SIZE(mi->blk); i++) - if (mi->blk[i].start != mi->blk[i].end && - mi->blk[i].nid != NUMA_NO_NODE) - node_set(mi->blk[i].nid, *nodemask); -} - -/** - * numa_reset_distance - Reset NUMA distance table - * - * The current table is freed. The next numa_set_distance() call will - * create a new one. - */ -void __init numa_reset_distance(void) -{ - size_t size = numa_distance_cnt * numa_distance_cnt * sizeof(numa_distance[0]); - - /* numa_distance could be 1LU marking allocation failure, test cnt */ - if (numa_distance_cnt) - memblock_x86_free_range(__pa(numa_distance), - __pa(numa_distance) + size); - numa_distance_cnt = 0; - numa_distance = NULL; /* enable table creation */ -} - -static int __init numa_alloc_distance(void) -{ - nodemask_t nodes_parsed; - size_t size; - int i, j, cnt = 0; - u64 phys; - - /* size the new table and allocate it */ - nodes_parsed = numa_nodes_parsed; - numa_nodemask_from_meminfo(&nodes_parsed, &numa_meminfo); - - for_each_node_mask(i, nodes_parsed) - cnt = i; - cnt++; - size = cnt * cnt * sizeof(numa_distance[0]); - - phys = memblock_find_in_range(0, (u64)max_pfn_mapped << PAGE_SHIFT, - size, PAGE_SIZE); - if (phys == MEMBLOCK_ERROR) { - pr_warning("NUMA: Warning: can't allocate distance table!\n"); - /* don't retry until explicitly reset */ - numa_distance = (void *)1LU; - return -ENOMEM; - } - memblock_x86_reserve_range(phys, phys + size, "NUMA DIST"); - - numa_distance = __va(phys); - numa_distance_cnt = cnt; - - /* fill with the default distances */ - for (i = 0; i < cnt; i++) - for (j = 0; j < cnt; j++) - numa_distance[i * cnt + j] = i == j ? - LOCAL_DISTANCE : REMOTE_DISTANCE; - printk(KERN_DEBUG "NUMA: Initialized distance table, cnt=%d\n", cnt); - - return 0; -} - -/** - * numa_set_distance - Set NUMA distance from one NUMA to another - * @from: the 'from' node to set distance - * @to: the 'to' node to set distance - * @distance: NUMA distance - * - * Set the distance from node @from to @to to @distance. If distance table - * doesn't exist, one which is large enough to accommodate all the currently - * known nodes will be created. - * - * If such table cannot be allocated, a warning is printed and further - * calls are ignored until the distance table is reset with - * numa_reset_distance(). - * - * If @from or @to is higher than the highest known node at the time of - * table creation or @distance doesn't make sense, the call is ignored. - * This is to allow simplification of specific NUMA config implementations. - */ -void __init numa_set_distance(int from, int to, int distance) -{ - if (!numa_distance && numa_alloc_distance() < 0) - return; - - if (from >= numa_distance_cnt || to >= numa_distance_cnt) { - printk_once(KERN_DEBUG "NUMA: Debug: distance out of bound, from=%d to=%d distance=%d\n", - from, to, distance); - return; - } - - if ((u8)distance != distance || - (from == to && distance != LOCAL_DISTANCE)) { - pr_warn_once("NUMA: Warning: invalid distance parameter, from=%d to=%d distance=%d\n", - from, to, distance); - return; - } - - numa_distance[from * numa_distance_cnt + to] = distance; -} - -int __node_distance(int from, int to) -{ - if (from >= numa_distance_cnt || to >= numa_distance_cnt) - return from == to ? LOCAL_DISTANCE : REMOTE_DISTANCE; - return numa_distance[from * numa_distance_cnt + to]; -} -EXPORT_SYMBOL(__node_distance); - -/* - * Sanity check to catch more bad NUMA configurations (they are amazingly - * common). Make sure the nodes cover all memory. - */ -static bool __init numa_meminfo_cover_memory(const struct numa_meminfo *mi) -{ - unsigned long numaram, e820ram; - int i; - - numaram = 0; - for (i = 0; i < mi->nr_blks; i++) { - unsigned long s = mi->blk[i].start >> PAGE_SHIFT; - unsigned long e = mi->blk[i].end >> PAGE_SHIFT; - numaram += e - s; - numaram -= __absent_pages_in_range(mi->blk[i].nid, s, e); - if ((long)numaram < 0) - numaram = 0; - } - - e820ram = max_pfn - (memblock_x86_hole_size(0, - max_pfn << PAGE_SHIFT) >> PAGE_SHIFT); - /* We seem to lose 3 pages somewhere. Allow 1M of slack. */ - if ((long)(e820ram - numaram) >= (1 << (20 - PAGE_SHIFT))) { - printk(KERN_ERR "NUMA: nodes only cover %luMB of your %luMB e820 RAM. Not used.\n", - (numaram << PAGE_SHIFT) >> 20, - (e820ram << PAGE_SHIFT) >> 20); - return false; - } - return true; -} - -static int __init numa_register_memblks(struct numa_meminfo *mi) -{ - int i, nid; - - /* Account for nodes with cpus and no memory */ - node_possible_map = numa_nodes_parsed; - numa_nodemask_from_meminfo(&node_possible_map, mi); - if (WARN_ON(nodes_empty(node_possible_map))) - return -EINVAL; - - memnode_shift = compute_hash_shift(mi); - if (memnode_shift < 0) { - printk(KERN_ERR "NUMA: No NUMA node hash function found. Contact maintainer\n"); - return -EINVAL; - } - - for (i = 0; i < mi->nr_blks; i++) - memblock_x86_register_active_regions(mi->blk[i].nid, - mi->blk[i].start >> PAGE_SHIFT, - mi->blk[i].end >> PAGE_SHIFT); - - /* for out of order entries */ - sort_node_map(); - if (!numa_meminfo_cover_memory(mi)) - return -EINVAL; - - /* Finally register nodes. */ - for_each_node_mask(nid, node_possible_map) { - u64 start = (u64)max_pfn << PAGE_SHIFT; - u64 end = 0; - - for (i = 0; i < mi->nr_blks; i++) { - if (nid != mi->blk[i].nid) - continue; - start = min(mi->blk[i].start, start); - end = max(mi->blk[i].end, end); - } - - if (start < end) - setup_node_bootmem(nid, start, end); - } - - return 0; -} - -/** - * dummy_numma_init - Fallback dummy NUMA init - * - * Used if there's no underlying NUMA architecture, NUMA initialization - * fails, or NUMA is disabled on the command line. - * - * Must online at least one node and add memory blocks that cover all - * allowed memory. This function must not fail. - */ -static int __init dummy_numa_init(void) -{ - printk(KERN_INFO "%s\n", - numa_off ? "NUMA turned off" : "No NUMA configuration found"); - printk(KERN_INFO "Faking a node at %016lx-%016lx\n", - 0LU, max_pfn << PAGE_SHIFT); - - node_set(0, numa_nodes_parsed); - numa_add_memblk(0, 0, (u64)max_pfn << PAGE_SHIFT); - - return 0; -} - -static int __init numa_init(int (*init_func)(void)) -{ - int i; - int ret; - - for (i = 0; i < MAX_LOCAL_APIC; i++) - set_apicid_to_node(i, NUMA_NO_NODE); - - nodes_clear(numa_nodes_parsed); - nodes_clear(node_possible_map); - nodes_clear(node_online_map); - memset(&numa_meminfo, 0, sizeof(numa_meminfo)); - remove_all_active_ranges(); - numa_reset_distance(); - - ret = init_func(); - if (ret < 0) - return ret; - ret = numa_cleanup_meminfo(&numa_meminfo); - if (ret < 0) - return ret; - - numa_emulation(&numa_meminfo, numa_distance_cnt); - - ret = numa_register_memblks(&numa_meminfo); - if (ret < 0) - return ret; - - for (i = 0; i < nr_cpu_ids; i++) { - int nid = early_cpu_to_node(i); - - if (nid == NUMA_NO_NODE) - continue; - if (!node_online(nid)) - numa_clear_node(i); - } - numa_init_array(); - return 0; -} - void __init initmem_init(void) { - int ret; - - if (!numa_off) { -#ifdef CONFIG_ACPI_NUMA - ret = numa_init(x86_acpi_numa_init); - if (!ret) - return; -#endif -#ifdef CONFIG_AMD_NUMA - ret = numa_init(amd_numa_init); - if (!ret) - return; -#endif - } - - numa_init(dummy_numa_init); + x86_numa_init(); } unsigned long __init numa_free_all_bootmem(void) @@ -656,12 +23,3 @@ unsigned long __init numa_free_all_bootmem(void) return pages; } - -int __cpuinit numa_cpu_node(int cpu) -{ - int apicid = early_per_cpu(x86_cpu_to_apicid, cpu); - - if (apicid != BAD_APICID) - return __apicid_to_node[apicid]; - return NUMA_NO_NODE; -} diff --git a/arch/x86/mm/numa_emulation.c b/arch/x86/mm/numa_emulation.c index de84cc14037..d0ed086b624 100644 --- a/arch/x86/mm/numa_emulation.c +++ b/arch/x86/mm/numa_emulation.c @@ -5,6 +5,7 @@ #include <linux/errno.h> #include <linux/topology.h> #include <linux/memblock.h> +#include <linux/bootmem.h> #include <asm/dma.h> #include "numa_internal.h" @@ -84,7 +85,13 @@ static int __init split_nodes_interleave(struct numa_meminfo *ei, nr_nodes = MAX_NUMNODES; } - size = (max_addr - addr - memblock_x86_hole_size(addr, max_addr)) / nr_nodes; + /* + * Calculate target node size. x86_32 freaks on __udivdi3() so do + * the division in ulong number of pages and convert back. + */ + size = max_addr - addr - memblock_x86_hole_size(addr, max_addr); + size = PFN_PHYS((unsigned long)(size >> PAGE_SHIFT) / nr_nodes); + /* * Calculate the number of big nodes that can be allocated as a result * of consolidating the remainder. @@ -226,7 +233,7 @@ static int __init split_nodes_size_interleave(struct numa_meminfo *ei, */ while (nodes_weight(physnode_mask)) { for_each_node_mask(i, physnode_mask) { - u64 dma32_end = MAX_DMA32_PFN << PAGE_SHIFT; + u64 dma32_end = PFN_PHYS(MAX_DMA32_PFN); u64 start, limit, end; int phys_blk; @@ -298,7 +305,7 @@ void __init numa_emulation(struct numa_meminfo *numa_meminfo, int numa_dist_cnt) { static struct numa_meminfo ei __initdata; static struct numa_meminfo pi __initdata; - const u64 max_addr = max_pfn << PAGE_SHIFT; + const u64 max_addr = PFN_PHYS(max_pfn); u8 *phys_dist = NULL; size_t phys_size = numa_dist_cnt * numa_dist_cnt * sizeof(phys_dist[0]); int max_emu_nid, dfl_phys_nid; @@ -342,8 +349,7 @@ void __init numa_emulation(struct numa_meminfo *numa_meminfo, int numa_dist_cnt) if (numa_dist_cnt) { u64 phys; - phys = memblock_find_in_range(0, - (u64)max_pfn_mapped << PAGE_SHIFT, + phys = memblock_find_in_range(0, PFN_PHYS(max_pfn_mapped), phys_size, PAGE_SIZE); if (phys == MEMBLOCK_ERROR) { pr_warning("NUMA: Warning: can't allocate copy of distance table, disabling emulation\n"); diff --git a/arch/x86/mm/numa_internal.h b/arch/x86/mm/numa_internal.h index ef2d97377d7..7178c3afe05 100644 --- a/arch/x86/mm/numa_internal.h +++ b/arch/x86/mm/numa_internal.h @@ -19,6 +19,14 @@ void __init numa_remove_memblk_from(int idx, struct numa_meminfo *mi); int __init numa_cleanup_meminfo(struct numa_meminfo *mi); void __init numa_reset_distance(void); +void __init x86_numa_init(void); + +#ifdef CONFIG_X86_64 +static inline void init_alloc_remap(int nid, u64 start, u64 end) { } +#else +void __init init_alloc_remap(int nid, u64 start, u64 end); +#endif + #ifdef CONFIG_NUMA_EMU void __init numa_emulation(struct numa_meminfo *numa_meminfo, int numa_dist_cnt); diff --git a/arch/x86/mm/srat_64.c b/arch/x86/mm/srat.c index 8e9d3394f6d..81dbfdeb080 100644 --- a/arch/x86/mm/srat_64.c +++ b/arch/x86/mm/srat.c @@ -26,8 +26,6 @@ int acpi_numa __initdata; -static struct bootnode nodes_add[MAX_NUMNODES]; - static __init int setup_node(int pxm) { return acpi_map_pxm_to_node(pxm); @@ -37,7 +35,6 @@ static __init void bad_srat(void) { printk(KERN_ERR "SRAT: SRAT not used.\n"); acpi_numa = -1; - memset(nodes_add, 0, sizeof(nodes_add)); } static __init inline int srat_disabled(void) @@ -131,73 +128,17 @@ acpi_numa_processor_affinity_init(struct acpi_srat_cpu_affinity *pa) pxm, apic_id, node); } -#ifdef CONFIG_MEMORY_HOTPLUG_SPARSE +#ifdef CONFIG_MEMORY_HOTPLUG static inline int save_add_info(void) {return 1;} #else static inline int save_add_info(void) {return 0;} #endif -/* - * Update nodes_add[] - * This code supports one contiguous hot add area per node - */ -static void __init -update_nodes_add(int node, unsigned long start, unsigned long end) -{ - unsigned long s_pfn = start >> PAGE_SHIFT; - unsigned long e_pfn = end >> PAGE_SHIFT; - int changed = 0; - struct bootnode *nd = &nodes_add[node]; - - /* I had some trouble with strange memory hotadd regions breaking - the boot. Be very strict here and reject anything unexpected. - If you want working memory hotadd write correct SRATs. - - The node size check is a basic sanity check to guard against - mistakes */ - if ((signed long)(end - start) < NODE_MIN_SIZE) { - printk(KERN_ERR "SRAT: Hotplug area too small\n"); - return; - } - - /* This check might be a bit too strict, but I'm keeping it for now. */ - if (absent_pages_in_range(s_pfn, e_pfn) != e_pfn - s_pfn) { - printk(KERN_ERR - "SRAT: Hotplug area %lu -> %lu has existing memory\n", - s_pfn, e_pfn); - return; - } - - /* Looks good */ - - if (nd->start == nd->end) { - nd->start = start; - nd->end = end; - changed = 1; - } else { - if (nd->start == end) { - nd->start = start; - changed = 1; - } - if (nd->end == start) { - nd->end = end; - changed = 1; - } - if (!changed) - printk(KERN_ERR "SRAT: Hotplug zone not continuous. Partly ignored\n"); - } - - if (changed) { - node_set(node, numa_nodes_parsed); - printk(KERN_INFO "SRAT: hot plug zone found %Lx - %Lx\n", - nd->start, nd->end); - } -} /* Callback for parsing of the Proximity Domain <-> Memory Area mappings */ void __init acpi_numa_memory_affinity_init(struct acpi_srat_mem_affinity *ma) { - unsigned long start, end; + u64 start, end; int node, pxm; if (srat_disabled()) @@ -226,11 +167,8 @@ acpi_numa_memory_affinity_init(struct acpi_srat_mem_affinity *ma) return; } - printk(KERN_INFO "SRAT: Node %u PXM %u %lx-%lx\n", node, pxm, + printk(KERN_INFO "SRAT: Node %u PXM %u %Lx-%Lx\n", node, pxm, start, end); - - if (ma->flags & ACPI_SRAT_MEM_HOT_PLUGGABLE) - update_nodes_add(node, start, end); } void __init acpi_numa_arch_fixup(void) {} @@ -244,17 +182,3 @@ int __init x86_acpi_numa_init(void) return ret; return srat_disabled() ? -EINVAL : 0; } - -#if defined(CONFIG_MEMORY_HOTPLUG_SPARSE) || defined(CONFIG_ACPI_HOTPLUG_MEMORY) -int memory_add_physaddr_to_nid(u64 start) -{ - int i, ret = 0; - - for_each_node(i) - if (nodes_add[i].start <= start && nodes_add[i].end > start) - ret = i; - - return ret; -} -EXPORT_SYMBOL_GPL(memory_add_physaddr_to_nid); -#endif diff --git a/arch/x86/mm/srat_32.c b/arch/x86/mm/srat_32.c deleted file mode 100644 index 364f36bdfad..00000000000 --- a/arch/x86/mm/srat_32.c +++ /dev/null @@ -1,288 +0,0 @@ -/* - * Some of the code in this file has been gleaned from the 64 bit - * discontigmem support code base. - * - * Copyright (C) 2002, IBM Corp. - * - * All rights reserved. - * - * 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, GOOD TITLE or - * NON INFRINGEMENT. See the GNU General Public License for more - * details. - * - * You should have received a copy of the GNU General Public License - * along with this program; if not, write to the Free Software - * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. - * - * Send feedback to Pat Gaughen <gone@us.ibm.com> - */ -#include <linux/mm.h> -#include <linux/bootmem.h> -#include <linux/memblock.h> -#include <linux/mmzone.h> -#include <linux/acpi.h> -#include <linux/nodemask.h> -#include <asm/srat.h> -#include <asm/topology.h> -#include <asm/smp.h> -#include <asm/e820.h> - -/* - * proximity macros and definitions - */ -#define NODE_ARRAY_INDEX(x) ((x) / 8) /* 8 bits/char */ -#define NODE_ARRAY_OFFSET(x) ((x) % 8) /* 8 bits/char */ -#define BMAP_SET(bmap, bit) ((bmap)[NODE_ARRAY_INDEX(bit)] |= 1 << NODE_ARRAY_OFFSET(bit)) -#define BMAP_TEST(bmap, bit) ((bmap)[NODE_ARRAY_INDEX(bit)] & (1 << NODE_ARRAY_OFFSET(bit))) -/* bitmap length; _PXM is at most 255 */ -#define PXM_BITMAP_LEN (MAX_PXM_DOMAINS / 8) -static u8 __initdata pxm_bitmap[PXM_BITMAP_LEN]; /* bitmap of proximity domains */ - -#define MAX_CHUNKS_PER_NODE 3 -#define MAXCHUNKS (MAX_CHUNKS_PER_NODE * MAX_NUMNODES) -struct node_memory_chunk_s { - unsigned long start_pfn; - unsigned long end_pfn; - u8 pxm; // proximity domain of node - u8 nid; // which cnode contains this chunk? - u8 bank; // which mem bank on this node -}; -static struct node_memory_chunk_s __initdata node_memory_chunk[MAXCHUNKS]; - -static int __initdata num_memory_chunks; /* total number of memory chunks */ -static u8 __initdata apicid_to_pxm[MAX_LOCAL_APIC]; - -int acpi_numa __initdata; - -static __init void bad_srat(void) -{ - printk(KERN_ERR "SRAT: SRAT not used.\n"); - acpi_numa = -1; - num_memory_chunks = 0; -} - -static __init inline int srat_disabled(void) -{ - return numa_off || acpi_numa < 0; -} - -/* Identify CPU proximity domains */ -void __init -acpi_numa_processor_affinity_init(struct acpi_srat_cpu_affinity *cpu_affinity) -{ - if (srat_disabled()) - return; - if (cpu_affinity->header.length != - sizeof(struct acpi_srat_cpu_affinity)) { - bad_srat(); - return; - } - - if ((cpu_affinity->flags & ACPI_SRAT_CPU_ENABLED) == 0) - return; /* empty entry */ - - /* mark this node as "seen" in node bitmap */ - BMAP_SET(pxm_bitmap, cpu_affinity->proximity_domain_lo); - - /* don't need to check apic_id here, because it is always 8 bits */ - apicid_to_pxm[cpu_affinity->apic_id] = cpu_affinity->proximity_domain_lo; - - printk(KERN_DEBUG "CPU %02x in proximity domain %02x\n", - cpu_affinity->apic_id, cpu_affinity->proximity_domain_lo); -} - -/* - * Identify memory proximity domains and hot-remove capabilities. - * Fill node memory chunk list structure. - */ -void __init -acpi_numa_memory_affinity_init(struct acpi_srat_mem_affinity *memory_affinity) -{ - unsigned long long paddr, size; - unsigned long start_pfn, end_pfn; - u8 pxm; - struct node_memory_chunk_s *p, *q, *pend; - - if (srat_disabled()) - return; - if (memory_affinity->header.length != - sizeof(struct acpi_srat_mem_affinity)) { - bad_srat(); - return; - } - - if ((memory_affinity->flags & ACPI_SRAT_MEM_ENABLED) == 0) - return; /* empty entry */ - - pxm = memory_affinity->proximity_domain & 0xff; - - /* mark this node as "seen" in node bitmap */ - BMAP_SET(pxm_bitmap, pxm); - - /* calculate info for memory chunk structure */ - paddr = memory_affinity->base_address; - size = memory_affinity->length; - - start_pfn = paddr >> PAGE_SHIFT; - end_pfn = (paddr + size) >> PAGE_SHIFT; - - - if (num_memory_chunks >= MAXCHUNKS) { - printk(KERN_WARNING "Too many mem chunks in SRAT." - " Ignoring %lld MBytes at %llx\n", - size/(1024*1024), paddr); - return; - } - - /* Insertion sort based on base address */ - pend = &node_memory_chunk[num_memory_chunks]; - for (p = &node_memory_chunk[0]; p < pend; p++) { - if (start_pfn < p->start_pfn) - break; - } - if (p < pend) { - for (q = pend; q >= p; q--) - *(q + 1) = *q; - } - p->start_pfn = start_pfn; - p->end_pfn = end_pfn; - p->pxm = pxm; - - num_memory_chunks++; - - printk(KERN_DEBUG "Memory range %08lx to %08lx" - " in proximity domain %02x %s\n", - start_pfn, end_pfn, - pxm, - ((memory_affinity->flags & ACPI_SRAT_MEM_HOT_PLUGGABLE) ? - "enabled and removable" : "enabled" ) ); -} - -/* Callback for SLIT parsing */ -void __init acpi_numa_slit_init(struct acpi_table_slit *slit) -{ -} - -void acpi_numa_arch_fixup(void) -{ -} -/* - * The SRAT table always lists ascending addresses, so can always - * assume that the first "start" address that you see is the real - * start of the node, and that the current "end" address is after - * the previous one. - */ -static __init int node_read_chunk(int nid, struct node_memory_chunk_s *memory_chunk) -{ - /* - * Only add present memory as told by the e820. - * There is no guarantee from the SRAT that the memory it - * enumerates is present at boot time because it represents - * *possible* memory hotplug areas the same as normal RAM. - */ - if (memory_chunk->start_pfn >= max_pfn) { - printk(KERN_INFO "Ignoring SRAT pfns: %08lx - %08lx\n", - memory_chunk->start_pfn, memory_chunk->end_pfn); - return -1; - } - if (memory_chunk->nid != nid) - return -1; - - if (!node_has_online_mem(nid)) - node_start_pfn[nid] = memory_chunk->start_pfn; - - if (node_start_pfn[nid] > memory_chunk->start_pfn) - node_start_pfn[nid] = memory_chunk->start_pfn; - - if (node_end_pfn[nid] < memory_chunk->end_pfn) - node_end_pfn[nid] = memory_chunk->end_pfn; - - return 0; -} - -int __init get_memcfg_from_srat(void) -{ - int i, j, nid; - - if (srat_disabled()) - goto out_fail; - - if (acpi_numa_init() < 0) - goto out_fail; - - if (num_memory_chunks == 0) { - printk(KERN_DEBUG - "could not find any ACPI SRAT memory areas.\n"); - goto out_fail; - } - - /* Calculate total number of nodes in system from PXM bitmap and create - * a set of sequential node IDs starting at zero. (ACPI doesn't seem - * to specify the range of _PXM values.) - */ - /* - * MCD - we no longer HAVE to number nodes sequentially. PXM domain - * numbers could go as high as 256, and MAX_NUMNODES for i386 is typically - * 32, so we will continue numbering them in this manner until MAX_NUMNODES - * approaches MAX_PXM_DOMAINS for i386. - */ - nodes_clear(node_online_map); - for (i = 0; i < MAX_PXM_DOMAINS; i++) { - if (BMAP_TEST(pxm_bitmap, i)) { - int nid = acpi_map_pxm_to_node(i); - node_set_online(nid); - } - } - BUG_ON(num_online_nodes() == 0); - - /* set cnode id in memory chunk structure */ - for (i = 0; i < num_memory_chunks; i++) - node_memory_chunk[i].nid = pxm_to_node(node_memory_chunk[i].pxm); - - printk(KERN_DEBUG "pxm bitmap: "); - for (i = 0; i < sizeof(pxm_bitmap); i++) { - printk(KERN_CONT "%02x ", pxm_bitmap[i]); - } - printk(KERN_CONT "\n"); - printk(KERN_DEBUG "Number of logical nodes in system = %d\n", - num_online_nodes()); - printk(KERN_DEBUG "Number of memory chunks in system = %d\n", - num_memory_chunks); - - for (i = 0; i < MAX_LOCAL_APIC; i++) - set_apicid_to_node(i, pxm_to_node(apicid_to_pxm[i])); - - for (j = 0; j < num_memory_chunks; j++){ - struct node_memory_chunk_s * chunk = &node_memory_chunk[j]; - printk(KERN_DEBUG - "chunk %d nid %d start_pfn %08lx end_pfn %08lx\n", - j, chunk->nid, chunk->start_pfn, chunk->end_pfn); - if (node_read_chunk(chunk->nid, chunk)) - continue; - - memblock_x86_register_active_regions(chunk->nid, chunk->start_pfn, - min(chunk->end_pfn, max_pfn)); - } - /* for out of order entries in SRAT */ - sort_node_map(); - - for_each_online_node(nid) { - unsigned long start = node_start_pfn[nid]; - unsigned long end = min(node_end_pfn[nid], max_pfn); - - memory_present(nid, start, end); - node_remap_size[nid] = node_memmap_size_bytes(nid, start, end); - } - return 1; -out_fail: - printk(KERN_DEBUG "failed to get NUMA memory information from SRAT" - " table\n"); - return 0; -} diff --git a/drivers/acpi/processor_throttling.c b/drivers/acpi/processor_throttling.c index ad350173956..605a2954ef1 100644 --- a/drivers/acpi/processor_throttling.c +++ b/drivers/acpi/processor_throttling.c @@ -710,20 +710,14 @@ static int acpi_processor_get_throttling_fadt(struct acpi_processor *pr) } #ifdef CONFIG_X86 -static int acpi_throttling_rdmsr(struct acpi_processor *pr, - u64 *value) +static int acpi_throttling_rdmsr(u64 *value) { - struct cpuinfo_x86 *c; u64 msr_high, msr_low; - unsigned int cpu; u64 msr = 0; int ret = -1; - cpu = pr->id; - c = &cpu_data(cpu); - - if ((c->x86_vendor != X86_VENDOR_INTEL) || - !cpu_has(c, X86_FEATURE_ACPI)) { + if ((this_cpu_read(cpu_info.x86_vendor) != X86_VENDOR_INTEL) || + !this_cpu_has(X86_FEATURE_ACPI)) { printk(KERN_ERR PREFIX "HARDWARE addr space,NOT supported yet\n"); } else { @@ -738,18 +732,13 @@ static int acpi_throttling_rdmsr(struct acpi_processor *pr, return ret; } -static int acpi_throttling_wrmsr(struct acpi_processor *pr, u64 value) +static int acpi_throttling_wrmsr(u64 value) { - struct cpuinfo_x86 *c; - unsigned int cpu; int ret = -1; u64 msr; - cpu = pr->id; - c = &cpu_data(cpu); - - if ((c->x86_vendor != X86_VENDOR_INTEL) || - !cpu_has(c, X86_FEATURE_ACPI)) { + if ((this_cpu_read(cpu_info.x86_vendor) != X86_VENDOR_INTEL) || + !this_cpu_has(X86_FEATURE_ACPI)) { printk(KERN_ERR PREFIX "HARDWARE addr space,NOT supported yet\n"); } else { @@ -761,15 +750,14 @@ static int acpi_throttling_wrmsr(struct acpi_processor *pr, u64 value) return ret; } #else -static int acpi_throttling_rdmsr(struct acpi_processor *pr, - u64 *value) +static int acpi_throttling_rdmsr(u64 *value) { printk(KERN_ERR PREFIX "HARDWARE addr space,NOT supported yet\n"); return -1; } -static int acpi_throttling_wrmsr(struct acpi_processor *pr, u64 value) +static int acpi_throttling_wrmsr(u64 value) { printk(KERN_ERR PREFIX "HARDWARE addr space,NOT supported yet\n"); @@ -801,7 +789,7 @@ static int acpi_read_throttling_status(struct acpi_processor *pr, ret = 0; break; case ACPI_ADR_SPACE_FIXED_HARDWARE: - ret = acpi_throttling_rdmsr(pr, value); + ret = acpi_throttling_rdmsr(value); break; default: printk(KERN_ERR PREFIX "Unknown addr space %d\n", @@ -834,7 +822,7 @@ static int acpi_write_throttling_state(struct acpi_processor *pr, ret = 0; break; case ACPI_ADR_SPACE_FIXED_HARDWARE: - ret = acpi_throttling_wrmsr(pr, value); + ret = acpi_throttling_wrmsr(value); break; default: printk(KERN_ERR PREFIX "Unknown addr space %d\n", |