#include <linux/kernel.h>
#include <linux/mm.h>
+#include <linux/nmi.h>
#include <linux/swap.h>
#include <linux/bootmem.h>
#include <linux/acpi.h>
#include <linux/efi.h>
#include <linux/nodemask.h>
+#include <linux/slab.h>
#include <asm/pgalloc.h>
#include <asm/tlb.h>
#include <asm/meminit.h>
*/
struct early_node_data {
struct ia64_node_data *node_data;
- pg_data_t *pgdat;
unsigned long pernode_addr;
unsigned long pernode_size;
- struct bootmem_data bootmem_data;
unsigned long num_physpages;
+#ifdef CONFIG_ZONE_DMA
unsigned long num_dma_physpages;
+#endif
unsigned long min_pfn;
unsigned long max_pfn;
};
static struct early_node_data mem_data[MAX_NUMNODES] __initdata;
static nodemask_t memory_less_mask __initdata;
+pg_data_t *pgdat_list[MAX_NUMNODES];
+
/*
* To prevent cache aliasing effects, align per-node structures so that they
* start at addresses that are strided by node number.
static int __init build_node_maps(unsigned long start, unsigned long len,
int node)
{
- unsigned long cstart, epfn, end = start + len;
- struct bootmem_data *bdp = &mem_data[node].bootmem_data;
+ unsigned long spfn, epfn, end = start + len;
+ struct bootmem_data *bdp = &bootmem_node_data[node];
epfn = GRANULEROUNDUP(end) >> PAGE_SHIFT;
- cstart = GRANULEROUNDDOWN(start);
+ spfn = GRANULEROUNDDOWN(start) >> PAGE_SHIFT;
if (!bdp->node_low_pfn) {
- bdp->node_boot_start = cstart;
+ bdp->node_min_pfn = spfn;
bdp->node_low_pfn = epfn;
} else {
- bdp->node_boot_start = min(cstart, bdp->node_boot_start);
+ bdp->node_min_pfn = min(spfn, bdp->node_min_pfn);
bdp->node_low_pfn = max(epfn, bdp->node_low_pfn);
}
- min_low_pfn = min(min_low_pfn, bdp->node_boot_start>>PAGE_SHIFT);
- max_low_pfn = max(max_low_pfn, bdp->node_low_pfn);
-
return 0;
}
* acpi_boot_init() (which builds the node_to_cpu_mask array) hasn't been
* called yet. Note that node 0 will also count all non-existent cpus.
*/
-static int __init early_nr_cpus_node(int node)
+static int __meminit early_nr_cpus_node(int node)
{
int cpu, n = 0;
- for (cpu = 0; cpu < NR_CPUS; cpu++)
+ for_each_possible_early_cpu(cpu)
if (node == node_cpuid[cpu].nid)
n++;
* compute_pernodesize - compute size of pernode data
* @node: the node id.
*/
-static unsigned long __init compute_pernodesize(int node)
+static unsigned long __meminit compute_pernodesize(int node)
{
unsigned long pernodesize = 0, cpus;
pernodesize += node * L1_CACHE_BYTES;
pernodesize += L1_CACHE_ALIGN(sizeof(pg_data_t));
pernodesize += L1_CACHE_ALIGN(sizeof(struct ia64_node_data));
+ pernodesize += L1_CACHE_ALIGN(sizeof(pg_data_t));
pernodesize = PAGE_ALIGN(pernodesize);
return pernodesize;
}
#ifdef CONFIG_SMP
int cpu;
- for (cpu = 0; cpu < NR_CPUS; cpu++) {
- if (node == node_cpuid[cpu].nid) {
- memcpy(__va(cpu_data), __phys_per_cpu_start,
- __per_cpu_end - __per_cpu_start);
- __per_cpu_offset[cpu] = (char*)__va(cpu_data) -
- __per_cpu_start;
- cpu_data += PERCPU_PAGE_SIZE;
- }
+ for_each_possible_early_cpu(cpu) {
+ void *src = cpu == 0 ? __cpu0_per_cpu : __phys_per_cpu_start;
+
+ if (node != node_cpuid[cpu].nid)
+ continue;
+
+ memcpy(__va(cpu_data), src, __per_cpu_end - __per_cpu_start);
+ __per_cpu_offset[cpu] = (char *)__va(cpu_data) -
+ __per_cpu_start;
+
+ /*
+ * percpu area for cpu0 is moved from the __init area
+ * which is setup by head.S and used till this point.
+ * Update ar.k3. This move is ensures that percpu
+ * area for cpu0 is on the correct node and its
+ * virtual address isn't insanely far from other
+ * percpu areas which is important for congruent
+ * percpu allocator.
+ */
+ if (cpu == 0)
+ ia64_set_kr(IA64_KR_PER_CPU_DATA,
+ (unsigned long)cpu_data -
+ (unsigned long)__per_cpu_start);
+
+ cpu_data += PERCPU_PAGE_SIZE;
}
#endif
return cpu_data;
}
+#ifdef CONFIG_SMP
+/**
+ * setup_per_cpu_areas - setup percpu areas
+ *
+ * Arch code has already allocated and initialized percpu areas. All
+ * this function has to do is to teach the determined layout to the
+ * dynamic percpu allocator, which happens to be more complex than
+ * creating whole new ones using helpers.
+ */
+void __init setup_per_cpu_areas(void)
+{
+ struct pcpu_alloc_info *ai;
+ struct pcpu_group_info *uninitialized_var(gi);
+ unsigned int *cpu_map;
+ void *base;
+ unsigned long base_offset;
+ unsigned int cpu;
+ ssize_t static_size, reserved_size, dyn_size;
+ int node, prev_node, unit, nr_units, rc;
+
+ ai = pcpu_alloc_alloc_info(MAX_NUMNODES, nr_cpu_ids);
+ if (!ai)
+ panic("failed to allocate pcpu_alloc_info");
+ cpu_map = ai->groups[0].cpu_map;
+
+ /* determine base */
+ base = (void *)ULONG_MAX;
+ for_each_possible_cpu(cpu)
+ base = min(base,
+ (void *)(__per_cpu_offset[cpu] + __per_cpu_start));
+ base_offset = (void *)__per_cpu_start - base;
+
+ /* build cpu_map, units are grouped by node */
+ unit = 0;
+ for_each_node(node)
+ for_each_possible_cpu(cpu)
+ if (node == node_cpuid[cpu].nid)
+ cpu_map[unit++] = cpu;
+ nr_units = unit;
+
+ /* set basic parameters */
+ static_size = __per_cpu_end - __per_cpu_start;
+ reserved_size = PERCPU_MODULE_RESERVE;
+ dyn_size = PERCPU_PAGE_SIZE - static_size - reserved_size;
+ if (dyn_size < 0)
+ panic("percpu area overflow static=%zd reserved=%zd\n",
+ static_size, reserved_size);
+
+ ai->static_size = static_size;
+ ai->reserved_size = reserved_size;
+ ai->dyn_size = dyn_size;
+ ai->unit_size = PERCPU_PAGE_SIZE;
+ ai->atom_size = PAGE_SIZE;
+ ai->alloc_size = PERCPU_PAGE_SIZE;
+
+ /*
+ * CPUs are put into groups according to node. Walk cpu_map
+ * and create new groups at node boundaries.
+ */
+ prev_node = -1;
+ ai->nr_groups = 0;
+ for (unit = 0; unit < nr_units; unit++) {
+ cpu = cpu_map[unit];
+ node = node_cpuid[cpu].nid;
+
+ if (node == prev_node) {
+ gi->nr_units++;
+ continue;
+ }
+ prev_node = node;
+
+ gi = &ai->groups[ai->nr_groups++];
+ gi->nr_units = 1;
+ gi->base_offset = __per_cpu_offset[cpu] + base_offset;
+ gi->cpu_map = &cpu_map[unit];
+ }
+
+ rc = pcpu_setup_first_chunk(ai, base);
+ if (rc)
+ panic("failed to setup percpu area (err=%d)", rc);
+
+ pcpu_free_alloc_info(ai);
+}
+#endif
+
/**
* fill_pernode - initialize pernode data.
* @node: the node id.
{
void *cpu_data;
int cpus = early_nr_cpus_node(node);
- struct bootmem_data *bdp = &mem_data[node].bootmem_data;
+ struct bootmem_data *bdp = &bootmem_node_data[node];
mem_data[node].pernode_addr = pernode;
mem_data[node].pernode_size = pernodesize;
pernode += PERCPU_PAGE_SIZE * cpus;
pernode += node * L1_CACHE_BYTES;
- mem_data[node].pgdat = __va(pernode);
+ pgdat_list[node] = __va(pernode);
pernode += L1_CACHE_ALIGN(sizeof(pg_data_t));
mem_data[node].node_data = __va(pernode);
pernode += L1_CACHE_ALIGN(sizeof(struct ia64_node_data));
- mem_data[node].pgdat->bdata = bdp;
+ pgdat_list[node]->bdata = bdp;
pernode += L1_CACHE_ALIGN(sizeof(pg_data_t));
cpu_data = per_cpu_node_setup(cpu_data, node);
static int __init find_pernode_space(unsigned long start, unsigned long len,
int node)
{
- unsigned long epfn;
+ unsigned long spfn, epfn;
unsigned long pernodesize = 0, pernode, pages, mapsize;
- struct bootmem_data *bdp = &mem_data[node].bootmem_data;
+ struct bootmem_data *bdp = &bootmem_node_data[node];
+ spfn = start >> PAGE_SHIFT;
epfn = (start + len) >> PAGE_SHIFT;
- pages = bdp->node_low_pfn - (bdp->node_boot_start >> PAGE_SHIFT);
+ pages = bdp->node_low_pfn - bdp->node_min_pfn;
mapsize = bootmem_bootmap_pages(pages) << PAGE_SHIFT;
/*
* Make sure this memory falls within this node's usable memory
* since we may have thrown some away in build_maps().
*/
- if (start < bdp->node_boot_start || epfn > bdp->node_low_pfn)
+ if (spfn < bdp->node_min_pfn || epfn > bdp->node_low_pfn)
return 0;
/* Don't setup this node's local space twice... */
static int __init free_node_bootmem(unsigned long start, unsigned long len,
int node)
{
- free_bootmem_node(mem_data[node].pgdat, start, len);
+ free_bootmem_node(pgdat_list[node], start, len);
return 0;
}
int node;
for_each_online_node(node) {
- pg_data_t *pdp = mem_data[node].pgdat;
+ pg_data_t *pdp = pgdat_list[node];
if (node_isset(node, memory_less_mask))
continue;
bdp = pdp->bdata;
/* First the bootmem_map itself */
- pages = bdp->node_low_pfn - (bdp->node_boot_start>>PAGE_SHIFT);
+ pages = bdp->node_low_pfn - bdp->node_min_pfn;
size = bootmem_bootmap_pages(pages) << PAGE_SHIFT;
base = __pa(bdp->node_bootmem_map);
- reserve_bootmem_node(pdp, base, size);
+ reserve_bootmem_node(pdp, base, size, BOOTMEM_DEFAULT);
/* Now the per-node space */
size = mem_data[node].pernode_size;
base = __pa(mem_data[node].pernode_addr);
- reserve_bootmem_node(pdp, base, size);
+ reserve_bootmem_node(pdp, base, size, BOOTMEM_DEFAULT);
+ }
+}
+
+static void __meminit scatter_node_data(void)
+{
+ pg_data_t **dst;
+ int node;
+
+ /*
+ * for_each_online_node() can't be used at here.
+ * node_online_map is not set for hot-added nodes at this time,
+ * because we are halfway through initialization of the new node's
+ * structures. If for_each_online_node() is used, a new node's
+ * pg_data_ptrs will be not initialized. Instead of using it,
+ * pgdat_list[] is checked.
+ */
+ for_each_node(node) {
+ if (pgdat_list[node]) {
+ dst = LOCAL_DATA_ADDR(pgdat_list[node])->pg_data_ptrs;
+ memcpy(dst, pgdat_list, sizeof(pgdat_list));
+ }
}
}
*/
static void __init initialize_pernode_data(void)
{
- pg_data_t *pgdat_list[MAX_NUMNODES];
int cpu, node;
- for_each_online_node(node)
- pgdat_list[node] = mem_data[node].pgdat;
+ scatter_node_data();
- /* Copy the pg_data_t list to each node and init the node field */
- for_each_online_node(node) {
- memcpy(mem_data[node].node_data->pg_data_ptrs, pgdat_list,
- sizeof(pgdat_list));
- }
#ifdef CONFIG_SMP
/* Set the node_data pointer for each per-cpu struct */
- for (cpu = 0; cpu < NR_CPUS; cpu++) {
+ for_each_possible_early_cpu(cpu) {
node = node_cpuid[cpu].nid;
- per_cpu(cpu_info, cpu).node_data = mem_data[node].node_data;
+ per_cpu(ia64_cpu_info, cpu).node_data =
+ mem_data[node].node_data;
}
#else
{
cpu = 0;
node = node_cpuid[cpu].nid;
cpu0_cpu_info = (struct cpuinfo_ia64 *)(__phys_per_cpu_start +
- ((char *)&per_cpu__cpu_info - __per_cpu_start));
+ ((char *)&ia64_cpu_info - __per_cpu_start));
cpu0_cpu_info->node_data = mem_data[node].node_data;
}
#endif /* CONFIG_SMP */
if (bestnode == -1)
bestnode = anynode;
- ptr = __alloc_bootmem_node(mem_data[bestnode].pgdat, pernodesize,
+ ptr = __alloc_bootmem_node(pgdat_list[bestnode], pernodesize,
PERCPU_PAGE_SIZE, __pa(MAX_DMA_ADDRESS));
return ptr;
return;
}
-#ifdef CONFIG_SPARSEMEM
-/**
- * register_sparse_mem - notify SPARSEMEM that this memory range exists.
- * @start: physical start of range
- * @end: physical end of range
- * @arg: unused
- *
- * Simply calls SPARSEMEM to register memory section(s).
- */
-static int __init register_sparse_mem(unsigned long start, unsigned long end,
- void *arg)
-{
- int nid;
-
- start = __pa(start) >> PAGE_SHIFT;
- end = __pa(end) >> PAGE_SHIFT;
- nid = early_pfn_to_nid(start);
- memory_present(nid, start, end);
-
- return 0;
-}
-
-static void __init arch_sparse_init(void)
-{
- efi_memmap_walk(register_sparse_mem, NULL);
- sparse_init();
-}
-#else
-#define arch_sparse_init() do {} while (0)
-#endif
-
/**
* find_memory - walk the EFI memory map and setup the bootmem allocator
*
/* These actually end up getting called by call_pernode_memory() */
efi_memmap_walk(filter_rsvd_memory, build_node_maps);
efi_memmap_walk(filter_rsvd_memory, find_pernode_space);
+ efi_memmap_walk(find_max_min_low_pfn, NULL);
for_each_online_node(node)
- if (mem_data[node].bootmem_data.node_low_pfn) {
+ if (bootmem_node_data[node].node_low_pfn) {
node_clear(node, memory_less_mask);
mem_data[node].min_pfn = ~0UL;
}
+
+ efi_memmap_walk(filter_memory, register_active_ranges);
+
/*
* Initialize the boot memory maps in reverse order since that's
* what the bootmem allocator expects
else if (node_isset(node, memory_less_mask))
continue;
- bdp = &mem_data[node].bootmem_data;
+ bdp = &bootmem_node_data[node];
pernode = mem_data[node].pernode_addr;
pernodesize = mem_data[node].pernode_size;
map = pernode + pernodesize;
- init_bootmem_node(mem_data[node].pgdat,
+ init_bootmem_node(pgdat_list[node],
map>>PAGE_SHIFT,
- bdp->node_boot_start>>PAGE_SHIFT,
+ bdp->node_min_pfn,
bdp->node_low_pfn);
}
int cpu;
static int first_time = 1;
-
- if (smp_processor_id() != 0)
- return __per_cpu_start + __per_cpu_offset[smp_processor_id()];
-
if (first_time) {
first_time = 0;
- for (cpu = 0; cpu < NR_CPUS; cpu++)
+ for_each_possible_early_cpu(cpu)
per_cpu(local_per_cpu_offset, cpu) = __per_cpu_offset[cpu];
}
unsigned long total_present = 0;
pg_data_t *pgdat;
- printk("Mem-info:\n");
+ printk(KERN_INFO "Mem-info:\n");
show_free_areas();
- printk("Free swap: %6ldkB\n", nr_swap_pages<<(PAGE_SHIFT-10));
+ printk(KERN_INFO "Node memory in pages:\n");
for_each_online_pgdat(pgdat) {
unsigned long present;
unsigned long flags;
int shared = 0, cached = 0, reserved = 0;
- printk("Node ID: %d\n", pgdat->node_id);
pgdat_resize_lock(pgdat, &flags);
present = pgdat->node_present_pages;
for(i = 0; i < pgdat->node_spanned_pages; i++) {
struct page *page;
+ if (unlikely(i % MAX_ORDER_NR_PAGES == 0))
+ touch_nmi_watchdog();
if (pfn_valid(pgdat->node_start_pfn + i))
page = pfn_to_page(pgdat->node_start_pfn + i);
- else
+ else {
+ i = vmemmap_find_next_valid_pfn(pgdat->node_id,
+ i) - 1;
continue;
+ }
if (PageReserved(page))
reserved++;
else if (PageSwapCache(page))
total_reserved += reserved;
total_cached += cached;
total_shared += shared;
- printk("\t%ld pages of RAM\n", present);
- printk("\t%d reserved pages\n", reserved);
- printk("\t%d pages shared\n", shared);
- printk("\t%d pages swap cached\n", cached);
+ printk(KERN_INFO "Node %4d: RAM: %11ld, rsvd: %8d, "
+ "shrd: %10d, swpd: %10d\n", pgdat->node_id,
+ present, reserved, shared, cached);
}
- printk("%ld pages of RAM\n", total_present);
- printk("%d reserved pages\n", total_reserved);
- printk("%d pages shared\n", total_shared);
- printk("%d pages swap cached\n", total_cached);
- printk("Total of %ld pages in page table cache\n",
- pgtable_quicklist_total_size());
- printk("%d free buffer pages\n", nr_free_buffer_pages());
+ printk(KERN_INFO "%ld pages of RAM\n", total_present);
+ printk(KERN_INFO "%d reserved pages\n", total_reserved);
+ printk(KERN_INFO "%d pages shared\n", total_shared);
+ printk(KERN_INFO "%d pages swap cached\n", total_cached);
+ printk(KERN_INFO "Total of %ld pages in page table cache\n",
+ quicklist_total_size());
+ printk(KERN_INFO "%d free buffer pages\n", nr_free_buffer_pages());
}
/**
unsigned long end = start + len;
mem_data[node].num_physpages += len >> PAGE_SHIFT;
+#ifdef CONFIG_ZONE_DMA
if (start <= __pa(MAX_DMA_ADDRESS))
mem_data[node].num_dma_physpages +=
(min(end, __pa(MAX_DMA_ADDRESS)) - start) >>PAGE_SHIFT;
+#endif
start = GRANULEROUNDDOWN(start);
- start = ORDERROUNDDOWN(start);
end = GRANULEROUNDUP(end);
mem_data[node].max_pfn = max(mem_data[node].max_pfn,
end >> PAGE_SHIFT);
void __init paging_init(void)
{
unsigned long max_dma;
- unsigned long zones_size[MAX_NR_ZONES];
- unsigned long zholes_size[MAX_NR_ZONES];
unsigned long pfn_offset = 0;
+ unsigned long max_pfn = 0;
int node;
+ unsigned long max_zone_pfns[MAX_NR_ZONES];
max_dma = virt_to_phys((void *) MAX_DMA_ADDRESS) >> PAGE_SHIFT;
- arch_sparse_init();
-
efi_memmap_walk(filter_rsvd_memory, count_node_pages);
+ sparse_memory_present_with_active_regions(MAX_NUMNODES);
+ sparse_init();
+
#ifdef CONFIG_VIRTUAL_MEM_MAP
- vmalloc_end -= PAGE_ALIGN(max_low_pfn * sizeof(struct page));
- vmem_map = (struct page *) vmalloc_end;
+ VMALLOC_END -= PAGE_ALIGN(ALIGN(max_low_pfn, MAX_ORDER_NR_PAGES) *
+ sizeof(struct page));
+ vmem_map = (struct page *) VMALLOC_END;
efi_memmap_walk(create_mem_map_page_table, NULL);
printk("Virtual mem_map starts at 0x%p\n", vmem_map);
#endif
for_each_online_node(node) {
- memset(zones_size, 0, sizeof(zones_size));
- memset(zholes_size, 0, sizeof(zholes_size));
-
num_physpages += mem_data[node].num_physpages;
-
- if (mem_data[node].min_pfn >= max_dma) {
- /* All of this node's memory is above ZONE_DMA */
- zones_size[ZONE_NORMAL] = mem_data[node].max_pfn -
- mem_data[node].min_pfn;
- zholes_size[ZONE_NORMAL] = mem_data[node].max_pfn -
- mem_data[node].min_pfn -
- mem_data[node].num_physpages;
- } else if (mem_data[node].max_pfn < max_dma) {
- /* All of this node's memory is in ZONE_DMA */
- zones_size[ZONE_DMA] = mem_data[node].max_pfn -
- mem_data[node].min_pfn;
- zholes_size[ZONE_DMA] = mem_data[node].max_pfn -
- mem_data[node].min_pfn -
- mem_data[node].num_dma_physpages;
- } else {
- /* This node has memory in both zones */
- zones_size[ZONE_DMA] = max_dma -
- mem_data[node].min_pfn;
- zholes_size[ZONE_DMA] = zones_size[ZONE_DMA] -
- mem_data[node].num_dma_physpages;
- zones_size[ZONE_NORMAL] = mem_data[node].max_pfn -
- max_dma;
- zholes_size[ZONE_NORMAL] = zones_size[ZONE_NORMAL] -
- (mem_data[node].num_physpages -
- mem_data[node].num_dma_physpages);
- }
-
pfn_offset = mem_data[node].min_pfn;
#ifdef CONFIG_VIRTUAL_MEM_MAP
NODE_DATA(node)->node_mem_map = vmem_map + pfn_offset;
#endif
- free_area_init_node(node, NODE_DATA(node), zones_size,
- pfn_offset, zholes_size);
+ if (mem_data[node].max_pfn > max_pfn)
+ max_pfn = mem_data[node].max_pfn;
}
+ memset(max_zone_pfns, 0, sizeof(max_zone_pfns));
+#ifdef CONFIG_ZONE_DMA
+ max_zone_pfns[ZONE_DMA] = max_dma;
+#endif
+ max_zone_pfns[ZONE_NORMAL] = max_pfn;
+ free_area_init_nodes(max_zone_pfns);
+
zero_page_memmap_ptr = virt_to_page(ia64_imva(empty_zero_page));
}
+
+#ifdef CONFIG_MEMORY_HOTPLUG
+pg_data_t *arch_alloc_nodedata(int nid)
+{
+ unsigned long size = compute_pernodesize(nid);
+
+ return kzalloc(size, GFP_KERNEL);
+}
+
+void arch_free_nodedata(pg_data_t *pgdat)
+{
+ kfree(pgdat);
+}
+
+void arch_refresh_nodedata(int update_node, pg_data_t *update_pgdat)
+{
+ pgdat_list[update_node] = update_pgdat;
+ scatter_node_data();
+}
+#endif
+
+#ifdef CONFIG_SPARSEMEM_VMEMMAP
+int __meminit vmemmap_populate(struct page *start_page,
+ unsigned long size, int node)
+{
+ return vmemmap_populate_basepages(start_page, size, node);
+}
+#endif
git://ftp.safe.ca / safe / jmp / linux-2.6 / blobdiff