#include <linux/ctype.h>
#include <linux/module.h>
#include <linux/nodemask.h>
+#include <linux/sched.h>
#include <asm/e820.h>
#include <asm/proto.h>
struct memnode memnode;
-unsigned char cpu_to_node[NR_CPUS] __read_mostly = {
+int x86_cpu_to_node_map_init[NR_CPUS] = {
[0 ... NR_CPUS-1] = NUMA_NO_NODE
};
-EXPORT_SYMBOL(cpu_to_node);
+void *x86_cpu_to_node_map_early_ptr;
+DEFINE_PER_CPU(int, x86_cpu_to_node_map) = NUMA_NO_NODE;
+EXPORT_PER_CPU_SYMBOL(x86_cpu_to_node_map);
+EXPORT_SYMBOL(x86_cpu_to_node_map_early_ptr);
-unsigned char apicid_to_node[MAX_LOCAL_APIC] __cpuinitdata = {
+s16 apicid_to_node[MAX_LOCAL_APIC] __cpuinitdata = {
[0 ... MAX_LOCAL_APIC-1] = NUMA_NO_NODE
};
-cpumask_t node_to_cpumask[MAX_NUMNODES] __read_mostly;
-EXPORT_SYMBOL(node_to_cpumask);
+cpumask_t node_to_cpumask_map[MAX_NUMNODES] __read_mostly;
+EXPORT_SYMBOL(node_to_cpumask_map);
int numa_off __initdata;
unsigned long __initdata nodemap_addr;
unsigned long addr, end;
int i, res = -1;
- memset(memnodemap, 0xff, memnodemapsize);
+ memset(memnodemap, 0xff, sizeof(s16)*memnodemapsize);
for (i = 0; i < numnodes; i++) {
addr = nodes[i].start;
end = nodes[i].end;
if ((end >> shift) >= memnodemapsize)
return 0;
do {
- if (memnodemap[addr >> shift] != 0xff)
+ if (memnodemap[addr >> shift] != NUMA_NO_NODE)
return -1;
memnodemap[addr >> shift] = i;
addr += (1UL << shift);
static int __init allocate_cachealigned_memnodemap(void)
{
- unsigned long pad, pad_addr;
+ unsigned long addr;
memnodemap = memnode.embedded_map;
- if (memnodemapsize <= 48)
+ if (memnodemapsize <= ARRAY_SIZE(memnode.embedded_map))
return 0;
- pad = L1_CACHE_BYTES - 1;
- pad_addr = 0x8000;
- nodemap_size = pad + memnodemapsize;
- nodemap_addr = find_e820_area(pad_addr, end_pfn<<PAGE_SHIFT,
- nodemap_size);
+ addr = 0x8000;
+ nodemap_size = round_up(sizeof(s16) * memnodemapsize, L1_CACHE_BYTES);
+ nodemap_addr = find_e820_area(addr, end_pfn<<PAGE_SHIFT,
+ nodemap_size, L1_CACHE_BYTES);
if (nodemap_addr == -1UL) {
printk(KERN_ERR
"NUMA: Unable to allocate Memory to Node hash map\n");
nodemap_addr = nodemap_size = 0;
return -1;
}
- pad_addr = (nodemap_addr + pad) & ~pad;
- memnodemap = phys_to_virt(pad_addr);
+ memnodemap = phys_to_virt(nodemap_addr);
+ reserve_early(nodemap_addr, nodemap_addr + nodemap_size, "MEMNODEMAP");
printk(KERN_DEBUG "NUMA: Allocated memnodemap from %lx - %lx\n",
nodemap_addr, nodemap_addr + nodemap_size);
return shift;
}
-#ifdef CONFIG_SPARSEMEM
int early_pfn_to_nid(unsigned long pfn)
{
return phys_to_nid(pfn << PAGE_SHIFT);
}
-#endif
static void * __init early_node_mem(int nodeid, unsigned long start,
- unsigned long end, unsigned long size)
+ unsigned long end, unsigned long size,
+ unsigned long align)
{
- unsigned long mem = find_e820_area(start, end, size);
+ unsigned long mem = find_e820_area(start, end, size, align);
void *ptr;
if (mem != -1L)
return __va(mem);
- ptr = __alloc_bootmem_nopanic(size,
- SMP_CACHE_BYTES, __pa(MAX_DMA_ADDRESS));
+
+ ptr = __alloc_bootmem_nopanic(size, align, __pa(MAX_DMA_ADDRESS));
if (ptr == NULL) {
printk(KERN_ERR "Cannot find %lu bytes in node %d\n",
size, nodeid);
start_pfn = start >> PAGE_SHIFT;
end_pfn = end >> PAGE_SHIFT;
- node_data[nodeid] = early_node_mem(nodeid, start, end, pgdat_size);
+ 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]);
+ printk(KERN_INFO " NODE_DATA [%016lx - %016lx]\n", nodedata_phys,
+ nodedata_phys + pgdat_size - 1);
memset(NODE_DATA(nodeid), 0, sizeof(pg_data_t));
NODE_DATA(nodeid)->bdata = &plat_node_bdata[nodeid];
/* Find a place for the bootmem map */
bootmap_pages = bootmem_bootmap_pages(end_pfn - start_pfn);
bootmap_start = round_up(nodedata_phys + pgdat_size, PAGE_SIZE);
+ /*
+ * SMP_CAHCE_BYTES could be enough, but init_bootmem_node like
+ * to use that to align to PAGE_SIZE
+ */
bootmap = early_node_mem(nodeid, bootmap_start, end,
- bootmap_pages<<PAGE_SHIFT);
+ bootmap_pages<<PAGE_SHIFT, PAGE_SIZE);
if (bootmap == NULL) {
if (nodedata_phys < start || nodedata_phys >= end)
- free_bootmem((unsigned long)node_data[nodeid],
- pgdat_size);
+ free_bootmem(nodedata_phys, pgdat_size);
node_data[nodeid] = NULL;
return;
}
bootmap_start = __pa(bootmap);
- Dprintk("bootmap start %lu pages %lu\n", bootmap_start, bootmap_pages);
bootmap_size = init_bootmem_node(NODE_DATA(nodeid),
bootmap_start >> PAGE_SHIFT,
start_pfn, end_pfn);
+ printk(KERN_INFO " bootmap [%016lx - %016lx] pages %lx\n",
+ bootmap_start, bootmap_start + bootmap_size - 1,
+ bootmap_pages);
+
free_bootmem_with_active_regions(nodeid, end);
- reserve_bootmem_node(NODE_DATA(nodeid), nodedata_phys, pgdat_size);
+ reserve_bootmem_node(NODE_DATA(nodeid), nodedata_phys, pgdat_size,
+ BOOTMEM_DEFAULT);
reserve_bootmem_node(NODE_DATA(nodeid), bootmap_start,
- bootmap_pages<<PAGE_SHIFT);
+ bootmap_pages<<PAGE_SHIFT, BOOTMEM_DEFAULT);
#ifdef CONFIG_ACPI_NUMA
srat_reserve_add_area(nodeid);
#endif
node_set_online(nodeid);
}
-/* Initialize final allocator for a zone */
-void __init setup_node_zones(int nodeid)
-{
- unsigned long start_pfn, end_pfn, memmapsize, limit;
-
- start_pfn = node_start_pfn(nodeid);
- end_pfn = node_end_pfn(nodeid);
-
- Dprintk(KERN_INFO "Setting up memmap for node %d %lx-%lx\n",
- nodeid, start_pfn, end_pfn);
-
- /*
- * Try to allocate mem_map at end to not fill up precious <4GB
- * memory.
- */
- memmapsize = sizeof(struct page) * (end_pfn-start_pfn);
- limit = end_pfn << PAGE_SHIFT;
-#ifdef CONFIG_FLAT_NODE_MEM_MAP
- NODE_DATA(nodeid)->node_mem_map =
- __alloc_bootmem_core(NODE_DATA(nodeid)->bdata,
- memmapsize, SMP_CACHE_BYTES,
- round_down(limit - memmapsize, PAGE_SIZE),
- limit);
-#endif
-}
-
/*
* There are unfortunately some poorly designed mainboards around that
* only connect memory to a single CPU. This breaks the 1:1 cpu->node
rr = first_node(node_online_map);
for (i = 0; i < NR_CPUS; i++) {
- if (cpu_to_node(i) != NUMA_NO_NODE)
+ if (early_cpu_to_node(i) != NUMA_NO_NODE)
continue;
numa_set_node(i, rr);
rr = next_node(rr, node_online_map);
int i;
nodes_clear(node_possible_map);
+ nodes_clear(node_online_map);
#ifdef CONFIG_NUMA_EMU
if (cmdline && !numa_emulation(start_pfn, end_pfn))
return;
nodes_clear(node_possible_map);
+ nodes_clear(node_online_map);
#endif
#ifdef CONFIG_ACPI_NUMA
end_pfn << PAGE_SHIFT))
return;
nodes_clear(node_possible_map);
+ nodes_clear(node_online_map);
#endif
#ifdef CONFIG_K8_NUMA
end_pfn<<PAGE_SHIFT))
return;
nodes_clear(node_possible_map);
+ nodes_clear(node_online_map);
#endif
printk(KERN_INFO "%s\n",
numa_off ? "NUMA turned off" : "No NUMA configuration found");
memnode_shift = 63;
memnodemap = memnode.embedded_map;
memnodemap[0] = 0;
- nodes_clear(node_online_map);
node_set_online(0);
node_set(0, node_possible_map);
for (i = 0; i < NR_CPUS; i++)
numa_set_node(i, 0);
- node_to_cpumask[0] = cpumask_of_cpu(0);
+ /* cpumask_of_cpu() may not be available during early startup */
+ memset(&node_to_cpumask_map[0], 0, sizeof(node_to_cpumask_map[0]));
+ cpu_set(0, node_to_cpumask_map[0]);
e820_register_active_regions(0, start_pfn, end_pfn);
setup_node_bootmem(0, start_pfn << PAGE_SHIFT, end_pfn << PAGE_SHIFT);
}
__cpuinit void numa_add_cpu(int cpu)
{
- set_bit(cpu, &node_to_cpumask[cpu_to_node(cpu)]);
+ set_bit(cpu,
+ (unsigned long *)&node_to_cpumask_map[early_cpu_to_node(cpu)]);
}
void __cpuinit numa_set_node(int cpu, int node)
{
+ int *cpu_to_node_map = x86_cpu_to_node_map_early_ptr;
+
cpu_pda(cpu)->nodenumber = node;
- cpu_to_node(cpu) = node;
+
+ if(cpu_to_node_map)
+ cpu_to_node_map[cpu] = node;
+ else if(per_cpu_offset(cpu))
+ per_cpu(x86_cpu_to_node_map, cpu) = node;
+ else
+ Dprintk(KERN_INFO "Setting node for non-present cpu %d\n", cpu);
}
unsigned long __init numa_free_all_bootmem(void)
void __init paging_init(void)
{
unsigned long max_zone_pfns[MAX_NR_ZONES];
- int i;
memset(max_zone_pfns, 0, sizeof(max_zone_pfns));
max_zone_pfns[ZONE_DMA] = MAX_DMA_PFN;
sparse_memory_present_with_active_regions(MAX_NUMNODES);
sparse_init();
- for_each_online_node(i)
- setup_node_zones(i);
-
free_area_init_nodes(max_zone_pfns);
}
int i;
for (i = 0; i < NR_CPUS; i++) {
- u8 apicid = x86_cpu_to_apicid_init[i];
+ int node;
+ u16 apicid = x86_cpu_to_apicid_init[i];
if (apicid == BAD_APICID)
continue;
- if (apicid_to_node[apicid] == NUMA_NO_NODE)
+ node = apicid_to_node[apicid];
+ if (node == NUMA_NO_NODE)
continue;
- numa_set_node(i, apicid_to_node[apicid]);
+ if (!node_online(node))
+ continue;
+ numa_set_node(i, node);
}
}
-#ifdef CONFIG_DISCONTIGMEM
-/*
- * Functions to convert PFNs from/to per node page addresses.
- * These are out of line because they are quite big.
- * They could be all tuned by pre caching more state.
- * Should do that.
- */
-int pfn_valid(unsigned long pfn)
-{
- unsigned nid;
- if (pfn >= num_physpages)
- return 0;
- nid = pfn_to_nid(pfn);
- if (nid == 0xff)
- return 0;
- return pfn >= node_start_pfn(nid) && (pfn) < node_end_pfn(nid);
-}
-EXPORT_SYMBOL(pfn_valid);
-#endif