diff options
| -rw-r--r-- | arch/x86/Kconfig | 30 | ||||
| -rw-r--r-- | arch/x86/include/asm/cpufeature.h | 13 | ||||
| -rw-r--r-- | arch/x86/include/asm/mmzone_64.h | 23 | ||||
| -rw-r--r-- | arch/x86/include/asm/percpu.h | 27 | ||||
| -rw-r--r-- | arch/x86/include/asm/topology.h | 1 | ||||
| -rw-r--r-- | arch/x86/kernel/apic/apic.c | 2 | ||||
| -rw-r--r-- | arch/x86/kernel/apic/numaq_32.c | 4 | ||||
| -rw-r--r-- | arch/x86/kernel/cpu/mcheck/therm_throt.c | 7 | ||||
| -rw-r--r-- | arch/x86/kernel/mpparse.c | 2 | ||||
| -rw-r--r-- | arch/x86/kernel/process.c | 4 | ||||
| -rw-r--r-- | arch/x86/kernel/smpboot.c | 4 | ||||
| -rw-r--r-- | arch/x86/mm/ioremap.c | 14 | ||||
| -rw-r--r-- | arch/x86/mm/numa_32.c | 268 | ||||
| -rw-r--r-- | arch/x86/mm/numa_64.c | 131 | ||||
| -rw-r--r-- | arch/x86/mm/srat_32.c | 1 | ||||
| -rw-r--r-- | drivers/acpi/processor_throttling.c | 32 |
16 files changed, 189 insertions, 374 deletions
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index cc6c53a95bfd..8db4fbf30b59 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -1223,6 +1223,10 @@ 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 @@ -1231,13 +1235,9 @@ 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 @@ -1247,20 +1247,16 @@ 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 @@ -1269,6 +1265,10 @@ 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 @@ -1703,10 +1703,6 @@ 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/cpufeature.h b/arch/x86/include/asm/cpufeature.h index 91f3e087cf21..50c0d30e676d 100644 --- a/arch/x86/include/asm/cpufeature.h +++ b/arch/x86/include/asm/cpufeature.h @@ -207,8 +207,7 @@ 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)) || \ @@ -218,10 +217,16 @@ 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/mmzone_64.h b/arch/x86/include/asm/mmzone_64.h index 288b96f815a6..b3f88d7867c7 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/percpu.h b/arch/x86/include/asm/percpu.h index d475b4398d8b..76042d981596 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/topology.h b/arch/x86/include/asm/topology.h index 910a7084f7f2..8dba76972fd7 100644 --- a/arch/x86/include/asm/topology.h +++ b/arch/x86/include/asm/topology.h @@ -95,7 +95,6 @@ extern void setup_node_to_cpumask_map(void); #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 diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index fabf01eff771..2bc503bf9e99 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; diff --git a/arch/x86/kernel/apic/numaq_32.c b/arch/x86/kernel/apic/numaq_32.c index 6273eee5134b..0aced70815f0 100644 --- a/arch/x86/kernel/apic/numaq_32.c +++ b/arch/x86/kernel/apic/numaq_32.c @@ -93,10 +93,6 @@ static inline void numaq_register_node(int node, struct sys_cfg_data *scd) 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]); } /* diff --git a/arch/x86/kernel/cpu/mcheck/therm_throt.c b/arch/x86/kernel/cpu/mcheck/therm_throt.c index 6f8c5e9da97f..6b0f4cde7a22 100644 --- a/arch/x86/kernel/cpu/mcheck/therm_throt.c +++ b/arch/x86/kernel/cpu/mcheck/therm_throt.c @@ -355,7 +355,6 @@ 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); @@ -367,19 +366,19 @@ 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 5a532ce646bf..f1b27181de04 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) { int ret = 0; diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c index d46cbe46b7ab..88a90a977f8e 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 c2871d3c71b6..a3c430bdfb60 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/ioremap.c b/arch/x86/mm/ioremap.c index 0369843511dc..be1ef574ce9a 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_32.c b/arch/x86/mm/numa_32.c index bde3906420df..c757c0a3b529 100644 --- a/arch/x86/mm/numa_32.c +++ b/arch/x86/mm/numa_32.c @@ -104,13 +104,9 @@ 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); @@ -129,7 +125,6 @@ int __init get_memcfg_numa_flat(void) 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); @@ -164,9 +159,8 @@ 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 { + NODE_DATA(nid) = alloc_remap(nid, ALIGN(sizeof(pg_data_t), PAGE_SIZE)); + if (!NODE_DATA(nid)) { unsigned long pgdat_phys; pgdat_phys = memblock_find_in_range(min_low_pfn<<PAGE_SHIFT, max_pfn_mapped<<PAGE_SHIFT, @@ -182,25 +176,38 @@ static void __init allocate_pgdat(int 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 +216,6 @@ 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 +227,16 @@ 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 +252,102 @@ 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. + */ +static __init void init_alloc_remap(int nid) { - int nid; - unsigned long size, reserve_pages = 0; + unsigned long size, pfn; + u64 node_pa, remap_pa; + void *remap_va; - 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; -} + /* + * 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) + return; + if (!node_end_pfn[nid]) + return; + if (node_end_pfn[nid] > max_pfn) + node_end_pfn[nid] = max_pfn; -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]); + /* calculate the necessary space aligned to large page size */ + size = node_memmap_size_bytes(nid, node_start_pfn[nid], + min(node_end_pfn[nid], max_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(node_start_pfn[nid] << PAGE_SHIFT, + (u64)node_end_pfn[nid] << PAGE_SHIFT, + 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); - - 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); + for_each_online_node(nid) + init_alloc_remap(nid); - /* 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) @@ -409,12 +367,8 @@ 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); - + for_each_online_node(nid) allocate_pgdat(nid); - } - remap_numa_kva(); printk(KERN_DEBUG "High memory starts at vaddr %08lx\n", (ulong) pfn_to_kaddr(highstart_pfn)); diff --git a/arch/x86/mm/numa_64.c b/arch/x86/mm/numa_64.c index 85b52fc03084..a96767cb068f 100644 --- a/arch/x86/mm/numa_64.c +++ b/arch/x86/mm/numa_64.c @@ -28,125 +28,10 @@ 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) @@ -270,7 +155,7 @@ setup_node_bootmem(int nodeid, unsigned long start, unsigned long end) 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); + nid = early_pfn_to_nid(nodedata_phys >> PAGE_SHIFT); if (nid != nodeid) printk(KERN_INFO " NODE_DATA(%d) on node %d\n", nodeid, nid); @@ -527,12 +412,6 @@ static int __init numa_register_memblks(struct numa_meminfo *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, @@ -626,17 +505,13 @@ static int __init numa_init(int (*init_func)(void)) void __init initmem_init(void) { - int ret; - if (!numa_off) { #ifdef CONFIG_ACPI_NUMA - ret = numa_init(x86_acpi_numa_init); - if (!ret) + if (!numa_init(x86_acpi_numa_init)) return; #endif #ifdef CONFIG_AMD_NUMA - ret = numa_init(amd_numa_init); - if (!ret) + if (!numa_init(amd_numa_init)) return; #endif } diff --git a/arch/x86/mm/srat_32.c b/arch/x86/mm/srat_32.c index 364f36bdfad8..ae20046a9e98 100644 --- a/arch/x86/mm/srat_32.c +++ b/arch/x86/mm/srat_32.c @@ -278,7 +278,6 @@ int __init get_memcfg_from_srat(void) 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: diff --git a/drivers/acpi/processor_throttling.c b/drivers/acpi/processor_throttling.c index ad3501739563..605a2954ef17 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", |