diff options
Diffstat (limited to 'arch/x86_64/mm')
-rw-r--r-- | arch/x86_64/mm/Makefile | 2 | ||||
-rw-r--r-- | arch/x86_64/mm/fault.c | 11 | ||||
-rw-r--r-- | arch/x86_64/mm/init.c | 9 | ||||
-rw-r--r-- | arch/x86_64/mm/ioremap.c | 2 | ||||
-rw-r--r-- | arch/x86_64/mm/numa.c | 60 | ||||
-rw-r--r-- | arch/x86_64/mm/srat.c | 22 |
6 files changed, 63 insertions, 43 deletions
diff --git a/arch/x86_64/mm/Makefile b/arch/x86_64/mm/Makefile index 66c354ad80c..1d232a87f11 100644 --- a/arch/x86_64/mm/Makefile +++ b/arch/x86_64/mm/Makefile @@ -4,7 +4,7 @@ obj-y := init.o fault.o ioremap.o extable.o pageattr.o obj-$(CONFIG_HUGETLB_PAGE) += hugetlbpage.o -obj-$(CONFIG_DISCONTIGMEM) += numa.o +obj-$(CONFIG_NUMA) += numa.o obj-$(CONFIG_K8_NUMA) += k8topology.o obj-$(CONFIG_ACPI_NUMA) += srat.o diff --git a/arch/x86_64/mm/fault.c b/arch/x86_64/mm/fault.c index 57d3ab15a5c..493819e543a 100644 --- a/arch/x86_64/mm/fault.c +++ b/arch/x86_64/mm/fault.c @@ -23,7 +23,6 @@ #include <linux/vt_kern.h> /* For unblank_screen() */ #include <linux/compiler.h> #include <linux/module.h> -#include <linux/kprobes.h> #include <asm/system.h> #include <asm/uaccess.h> @@ -74,7 +73,7 @@ static noinline int is_prefetch(struct pt_regs *regs, unsigned long addr, instr = (unsigned char *)convert_rip_to_linear(current, regs); max_instr = instr + 15; - if ((regs->cs & 3) != 0 && instr >= (unsigned char *)TASK_SIZE) + if (user_mode(regs) && instr >= (unsigned char *)TASK_SIZE) return 0; while (scan_more && instr < max_instr) { @@ -106,7 +105,7 @@ static noinline int is_prefetch(struct pt_regs *regs, unsigned long addr, /* Could check the LDT for lm, but for now it's good enough to assume that long mode only uses well known segments or kernel. */ - scan_more = ((regs->cs & 3) == 0) || (regs->cs == __USER_CS); + scan_more = (!user_mode(regs)) || (regs->cs == __USER_CS); break; case 0x60: @@ -440,13 +439,13 @@ good_area: * the fault. */ switch (handle_mm_fault(mm, vma, address, write)) { - case 1: + case VM_FAULT_MINOR: tsk->min_flt++; break; - case 2: + case VM_FAULT_MAJOR: tsk->maj_flt++; break; - case 0: + case VM_FAULT_SIGBUS: goto do_sigbus; default: goto out_of_memory; diff --git a/arch/x86_64/mm/init.c b/arch/x86_64/mm/init.c index dbe53b4c7e6..72e4b364ed7 100644 --- a/arch/x86_64/mm/init.c +++ b/arch/x86_64/mm/init.c @@ -318,7 +318,7 @@ void zap_low_mappings(void) flush_tlb_all(); } -#ifndef CONFIG_DISCONTIGMEM +#ifndef CONFIG_NUMA void __init paging_init(void) { { @@ -427,13 +427,16 @@ void __init mem_init(void) reservedpages = 0; /* this will put all low memory onto the freelists */ -#ifdef CONFIG_DISCONTIGMEM +#ifdef CONFIG_NUMA totalram_pages += numa_free_all_bootmem(); tmp = 0; /* should count reserved pages here for all nodes */ #else + +#ifdef CONFIG_FLATMEM max_mapnr = end_pfn; if (!mem_map) BUG(); +#endif totalram_pages += free_all_bootmem(); @@ -515,7 +518,7 @@ void free_initrd_mem(unsigned long start, unsigned long end) void __init reserve_bootmem_generic(unsigned long phys, unsigned len) { /* Should check here against the e820 map to avoid double free */ -#ifdef CONFIG_DISCONTIGMEM +#ifdef CONFIG_NUMA int nid = phys_to_nid(phys); reserve_bootmem_node(NODE_DATA(nid), phys, len); #else diff --git a/arch/x86_64/mm/ioremap.c b/arch/x86_64/mm/ioremap.c index 58aac23760e..6972df480d2 100644 --- a/arch/x86_64/mm/ioremap.c +++ b/arch/x86_64/mm/ioremap.c @@ -178,7 +178,7 @@ void __iomem * __ioremap(unsigned long phys_addr, unsigned long size, unsigned l if (phys_addr >= ISA_START_ADDRESS && last_addr < ISA_END_ADDRESS) return (__force void __iomem *)phys_to_virt(phys_addr); -#ifndef CONFIG_DISCONTIGMEM +#ifdef CONFIG_FLATMEM /* * Don't allow anybody to remap normal RAM that we're using.. */ diff --git a/arch/x86_64/mm/numa.c b/arch/x86_64/mm/numa.c index fd9f25d7a6c..70cb2904a90 100644 --- a/arch/x86_64/mm/numa.c +++ b/arch/x86_64/mm/numa.c @@ -36,36 +36,45 @@ int numa_off __initdata; int __init compute_hash_shift(struct node *nodes, int numnodes) { int i; - int shift = 24; - u64 addr; + int shift = 20; + unsigned long addr,maxend=0; - /* When in doubt use brute force. */ - while (shift < 48) { - memset(memnodemap,0xff,sizeof(*memnodemap) * NODEMAPSIZE); - for (i = 0; i < numnodes; i++) { - if (nodes[i].start == nodes[i].end) - continue; - for (addr = nodes[i].start; - addr < nodes[i].end; - addr += (1UL << shift)) { - if (memnodemap[addr >> shift] != 0xff && - memnodemap[addr >> shift] != i) { - printk(KERN_INFO - "node %d shift %d addr %Lx conflict %d\n", - i, shift, addr, memnodemap[addr>>shift]); - goto next; - } - memnodemap[addr >> shift] = i; + for (i = 0; i < numnodes; i++) + if ((nodes[i].start != nodes[i].end) && (nodes[i].end > maxend)) + maxend = nodes[i].end; + + while ((1UL << shift) < (maxend / NODEMAPSIZE)) + shift++; + + printk (KERN_DEBUG"Using %d for the hash shift. Max adder is %lx \n", + shift,maxend); + memset(memnodemap,0xff,sizeof(*memnodemap) * NODEMAPSIZE); + for (i = 0; i < numnodes; i++) { + if (nodes[i].start == nodes[i].end) + continue; + for (addr = nodes[i].start; + addr < nodes[i].end; + addr += (1UL << shift)) { + if (memnodemap[addr >> shift] != 0xff) { + printk(KERN_INFO + "Your memory is not aligned you need to rebuild your kernel " + "with a bigger NODEMAPSIZE shift=%d adder=%lu\n", + shift,addr); + return -1; } + memnodemap[addr >> shift] = i; } - return shift; - next: - shift++; } - memset(memnodemap,0,sizeof(*memnodemap) * NODEMAPSIZE); - return -1; + return shift; } +#ifdef CONFIG_SPARSEMEM +int early_pfn_to_nid(unsigned long pfn) +{ + return phys_to_nid(pfn << PAGE_SHIFT); +} +#endif + /* Initialize bootmem allocator for a node */ void __init setup_node_bootmem(int nodeid, unsigned long start, unsigned long end) { @@ -80,6 +89,7 @@ void __init setup_node_bootmem(int nodeid, unsigned long start, unsigned long en start_pfn = start >> PAGE_SHIFT; end_pfn = end >> PAGE_SHIFT; + memory_present(nodeid, start_pfn, end_pfn); nodedata_phys = find_e820_area(start, end, pgdat_size); if (nodedata_phys == -1L) panic("Cannot find memory pgdat in node %d\n", nodeid); @@ -243,7 +253,7 @@ void __init numa_initmem_init(unsigned long start_pfn, unsigned long end_pfn) setup_node_bootmem(0, start_pfn << PAGE_SHIFT, end_pfn << PAGE_SHIFT); } -__init void numa_add_cpu(int cpu) +__cpuinit void numa_add_cpu(int cpu) { /* BP is initialized elsewhere */ if (cpu) diff --git a/arch/x86_64/mm/srat.c b/arch/x86_64/mm/srat.c index 5d01b31472e..8e3d097a9dd 100644 --- a/arch/x86_64/mm/srat.c +++ b/arch/x86_64/mm/srat.c @@ -20,6 +20,9 @@ static struct acpi_table_slit *acpi_slit; +/* Internal processor count */ +static unsigned int __initdata num_processors = 0; + static nodemask_t nodes_parsed __initdata; static nodemask_t nodes_found __initdata; static struct node nodes[MAX_NUMNODES] __initdata; @@ -101,16 +104,18 @@ acpi_numa_processor_affinity_init(struct acpi_table_processor_affinity *pa) bad_srat(); return; } - if (pa->apic_id >= NR_CPUS) { - printk(KERN_ERR "SRAT: lapic %u too large.\n", - pa->apic_id); + if (num_processors >= NR_CPUS) { + printk(KERN_ERR "SRAT: Processor #%d (lapic %u) INVALID. (Max ID: %d).\n", + num_processors, pa->apic_id, NR_CPUS); bad_srat(); return; } - cpu_to_node[pa->apic_id] = node; + cpu_to_node[num_processors] = node; acpi_numa = 1; - printk(KERN_INFO "SRAT: PXM %u -> APIC %u -> Node %u\n", - pxm, pa->apic_id, node); + printk(KERN_INFO "SRAT: PXM %u -> APIC %u -> CPU %u -> Node %u\n", + pxm, pa->apic_id, num_processors, node); + + num_processors++; } /* Callback for parsing of the Proximity Domain <-> Memory Area mappings */ @@ -124,7 +129,6 @@ acpi_numa_memory_affinity_init(struct acpi_table_memory_affinity *ma) if (srat_disabled() || ma->flags.enabled == 0) return; - /* hotplug bit is ignored for now */ pxm = ma->proximity_domain; node = setup_node(pxm); if (node < 0) { @@ -134,6 +138,10 @@ acpi_numa_memory_affinity_init(struct acpi_table_memory_affinity *ma) } start = ma->base_addr_lo | ((u64)ma->base_addr_hi << 32); end = start + (ma->length_lo | ((u64)ma->length_hi << 32)); + /* It is fine to add this area to the nodes data it will be used later*/ + if (ma->flags.hot_pluggable == 1) + printk(KERN_INFO "SRAT: hot plug zone found %lx - %lx \n", + start, end); i = conflicting_nodes(start, end); if (i >= 0) { printk(KERN_ERR |