#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 <asm/e820.h>
#include <asm/setup.h>
#include <asm/mmzone.h>
#include <bios_ebda.h>
-struct pglist_data *node_data[MAX_NUMNODES];
+struct pglist_data *node_data[MAX_NUMNODES] __read_mostly;
+EXPORT_SYMBOL(node_data);
bootmem_data_t node0_bdata;
/*
* populated the following initialisation.
*
* 1) node_online_map - the map of all nodes configured (online) in the system
- * 2) physnode_map - the mapping between a pfn and owning node
- * 3) node_start_pfn - the starting page frame number for a node
+ * 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;
+
+#ifdef CONFIG_DISCONTIGMEM
/*
+ * 4) physnode_map - the mapping between a pfn and owning node
* physnode_map keeps track of the physical memory layout of a generic
* numa node on a 256Mb break (each element of the array will
* represent 256Mb of memory and will be marked by the node id. so,
* physnode_map[4-7] = 1;
* physnode_map[8- ] = -1;
*/
-s8 physnode_map[MAX_ELEMENTS] = { [0 ... (MAX_ELEMENTS - 1)] = -1};
+s8 physnode_map[MAX_ELEMENTS] __read_mostly = { [0 ... (MAX_ELEMENTS - 1)] = -1};
+EXPORT_SYMBOL(physnode_map);
+
+void memory_present(int nid, unsigned long start, unsigned long end)
+{
+ unsigned long pfn;
+
+ printk(KERN_INFO "Node: %d, start_pfn: %ld, end_pfn: %ld\n",
+ nid, start, end);
+ printk(KERN_DEBUG " Setting physnode_map array to node %d for pfns:\n", nid);
+ printk(KERN_DEBUG " ");
+ for (pfn = start; pfn < end; pfn += PAGES_PER_ELEMENT) {
+ physnode_map[pfn / PAGES_PER_ELEMENT] = nid;
+ printk("%ld ", pfn);
+ }
+ printk("\n");
+}
+
+unsigned long node_memmap_size_bytes(int nid, unsigned long start_pfn,
+ unsigned long end_pfn)
+{
+ unsigned long nr_pages = end_pfn - start_pfn;
-unsigned long node_start_pfn[MAX_NUMNODES];
-unsigned long node_end_pfn[MAX_NUMNODES];
+ if (!nr_pages)
+ return 0;
+
+ return (nr_pages + 1) * sizeof(struct page);
+}
+#endif
extern unsigned long find_max_low_pfn(void);
extern void find_max_pfn(void);
-extern void one_highpage_init(struct page *, int, int);
+extern void add_one_highpage_init(struct page *, int, int);
extern struct e820map e820;
extern unsigned long init_pg_tables_end;
void *node_remap_start_vaddr[MAX_NUMNODES];
void set_pmd_pfn(unsigned long vaddr, unsigned long pfn, pgprot_t flags);
+void *node_remap_end_vaddr[MAX_NUMNODES];
+void *node_remap_alloc_vaddr[MAX_NUMNODES];
+
/*
* FLAT - support for basic PC memory model with discontig enabled, essentially
* a single node with all available processors in it with a flat
find_max_pfn();
node_start_pfn[0] = 0;
node_end_pfn[0] = max_pfn;
+ memory_present(0, 0, max_pfn);
/* Indicate there is one node available. */
nodes_clear(node_online_map);
BUG();
}
+/* Find the owning node for a pfn. */
+int early_pfn_to_nid(unsigned long pfn)
+{
+ int nid;
+
+ for_each_node(nid) {
+ if (node_end_pfn[nid] == 0)
+ break;
+ if (node_start_pfn[nid] <= pfn && node_end_pfn[nid] >= pfn)
+ return nid;
+ }
+
+ return 0;
+}
+
/*
* 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
*/
static void __init allocate_pgdat(int nid)
{
- if (nid)
+ if (nid && node_has_online_mem(nid))
NODE_DATA(nid) = (pg_data_t *)node_remap_start_vaddr[nid];
else {
NODE_DATA(nid) = (pg_data_t *)(__va(min_low_pfn << PAGE_SHIFT));
min_low_pfn += PFN_UP(sizeof(pg_data_t));
- memset(NODE_DATA(nid), 0, sizeof(pg_data_t));
}
}
-/*
- * Register fully available low RAM pages with the bootmem allocator.
- */
-static void __init register_bootmem_low_pages(unsigned long system_max_low_pfn)
+void *alloc_remap(int nid, unsigned long size)
{
- int i;
+ void *allocation = node_remap_alloc_vaddr[nid];
- for (i = 0; i < e820.nr_map; i++) {
- unsigned long curr_pfn, last_pfn, size;
- /*
- * Reserve usable low memory
- */
- if (e820.map[i].type != E820_RAM)
- continue;
- /*
- * We are rounding up the start address of usable memory:
- */
- curr_pfn = PFN_UP(e820.map[i].addr);
- if (curr_pfn >= system_max_low_pfn)
- continue;
- /*
- * ... and at the end of the usable range downwards:
- */
- last_pfn = PFN_DOWN(e820.map[i].addr + e820.map[i].size);
+ size = ALIGN(size, L1_CACHE_BYTES);
- if (last_pfn > system_max_low_pfn)
- last_pfn = system_max_low_pfn;
+ if (!allocation || (allocation + size) >= node_remap_end_vaddr[nid])
+ return 0;
- /*
- * .. finally, did all the rounding and playing
- * around just make the area go away?
- */
- if (last_pfn <= curr_pfn)
- continue;
+ node_remap_alloc_vaddr[nid] += size;
+ memset(allocation, 0, size);
- size = last_pfn - curr_pfn;
- free_bootmem_node(NODE_DATA(0), PFN_PHYS(curr_pfn), PFN_PHYS(size));
- }
+ return allocation;
}
void __init remap_numa_kva(void)
int node;
for_each_online_node(node) {
- if (node == 0)
- continue;
for (pfn=0; pfn < node_remap_size[node]; pfn += PTRS_PER_PTE) {
vaddr = node_remap_start_vaddr[node]+(pfn<<PAGE_SHIFT);
set_pmd_pfn((ulong) vaddr,
{
int nid;
unsigned long size, reserve_pages = 0;
+ unsigned long pfn;
for_each_online_node(nid) {
- if (nid == 0)
+ /*
+ * The acpi/srat node info can show hot-add memroy zones
+ * where memory could be added but not currently present.
+ */
+ if (node_start_pfn[nid] > max_pfn)
continue;
- /* calculate the size of the mem_map needed in bytes */
- size = (node_end_pfn[nid] - node_start_pfn[nid] + 1)
- * sizeof(struct page) + sizeof(pg_data_t);
+ 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;
+
+ /*
+ * Validate the region we are allocating only contains valid
+ * pages.
+ */
+ for (pfn = node_end_pfn[nid] - size;
+ pfn < node_end_pfn[nid]; pfn++)
+ if (!page_is_ram(pfn))
+ break;
+
+ if (pfn != node_end_pfn[nid])
+ size = 0;
+
printk("Reserving %ld pages of KVA for lmem_map of node %d\n",
size, nid);
node_remap_size[nid] = size;
- reserve_pages += size;
node_remap_offset[nid] = reserve_pages;
+ reserve_pages += size;
printk("Shrinking node %d from %ld pages to %ld pages\n",
nid, node_end_pfn[nid], node_end_pfn[nid] - size);
+
+ if (node_end_pfn[nid] & (PTRS_PER_PTE-1)) {
+ /*
+ * Align node_end_pfn[] and node_remap_start_pfn[] to
+ * pmd boundary. remap_numa_kva will barf otherwise.
+ */
+ printk("Shrinking node %d further by %ld pages for proper alignment\n",
+ nid, node_end_pfn[nid] & (PTRS_PER_PTE-1));
+ size += node_end_pfn[nid] & (PTRS_PER_PTE-1);
+ }
+
node_end_pfn[nid] -= size;
node_remap_start_pfn[nid] = node_end_pfn[nid];
}
return reserve_pages;
}
-/*
- * workaround for Dell systems that neglect to reserve EBDA
- */
-static void __init reserve_ebda_region_node(void)
-{
- unsigned int addr;
- addr = get_bios_ebda();
- if (addr)
- reserve_bootmem_node(NODE_DATA(0), addr, PAGE_SIZE);
-}
-
+extern void setup_bootmem_allocator(void);
unsigned long __init setup_memory(void)
{
int nid;
- unsigned long bootmap_size, system_start_pfn, system_max_low_pfn;
- unsigned long reserve_pages, pfn;
+ unsigned long system_start_pfn, system_max_low_pfn;
+ unsigned long reserve_pages;
/*
* When mapping a NUMA machine we allocate the node_mem_map arrays
* this space and use it to adjust the boundry between ZONE_NORMAL
* and ZONE_HIGHMEM.
*/
+ find_max_pfn();
get_memcfg_numa();
- /* Fill in the physnode_map */
- for_each_online_node(nid) {
- printk("Node: %d, start_pfn: %ld, end_pfn: %ld\n",
- nid, node_start_pfn[nid], node_end_pfn[nid]);
- printk(" Setting physnode_map array to node %d for pfns:\n ",
- nid);
- for (pfn = node_start_pfn[nid]; pfn < node_end_pfn[nid];
- pfn += PAGES_PER_ELEMENT) {
- physnode_map[pfn / PAGES_PER_ELEMENT] = nid;
- printk("%ld ", pfn);
- }
- printk("\n");
- }
-
reserve_pages = calculate_numa_remap_pages();
/* partially used pages are not usable - thus round upwards */
system_start_pfn = min_low_pfn = PFN_UP(init_pg_tables_end);
- find_max_pfn();
system_max_low_pfn = max_low_pfn = find_max_low_pfn() - reserve_pages;
printk("reserve_pages = %ld find_max_low_pfn() ~ %ld\n",
reserve_pages, max_low_pfn + reserve_pages);
(ulong) pfn_to_kaddr(max_low_pfn));
for_each_online_node(nid) {
node_remap_start_vaddr[nid] = pfn_to_kaddr(
- (highstart_pfn + reserve_pages) - node_remap_offset[nid]);
+ highstart_pfn + node_remap_offset[nid]);
+ /* Init the node remap allocator */
+ 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);
+
allocate_pgdat(nid);
printk ("node %d will remap to vaddr %08lx - %08lx\n", nid,
(ulong) node_remap_start_vaddr[nid],
- (ulong) pfn_to_kaddr(highstart_pfn + reserve_pages
- - node_remap_offset[nid] + node_remap_size[nid]));
+ (ulong) pfn_to_kaddr(highstart_pfn
+ + node_remap_offset[nid] + node_remap_size[nid]));
}
printk("High memory starts at vaddr %08lx\n",
(ulong) pfn_to_kaddr(highstart_pfn));
for_each_online_node(nid)
find_max_pfn_node(nid);
+ memset(NODE_DATA(0), 0, sizeof(struct pglist_data));
NODE_DATA(0)->bdata = &node0_bdata;
-
- /*
- * Initialize the boot-time allocator (with low memory only):
- */
- bootmap_size = init_bootmem_node(NODE_DATA(0), min_low_pfn, 0, system_max_low_pfn);
-
- register_bootmem_low_pages(system_max_low_pfn);
-
- /*
- * Reserve the bootmem bitmap itself as well. We do this in two
- * steps (first step was init_bootmem()) because this catches
- * the (very unlikely) case of us accidentally initializing the
- * bootmem allocator with an invalid RAM area.
- */
- reserve_bootmem_node(NODE_DATA(0), HIGH_MEMORY, (PFN_PHYS(min_low_pfn) +
- bootmap_size + PAGE_SIZE-1) - (HIGH_MEMORY));
-
- /*
- * reserve physical page 0 - it's a special BIOS page on many boxes,
- * enabling clean reboots, SMP operation, laptop functions.
- */
- reserve_bootmem_node(NODE_DATA(0), 0, PAGE_SIZE);
-
- /*
- * But first pinch a few for the stack/trampoline stuff
- * FIXME: Don't need the extra page at 4K, but need to fix
- * trampoline before removing it. (see the GDT stuff)
- */
- reserve_bootmem_node(NODE_DATA(0), PAGE_SIZE, PAGE_SIZE);
-
- /* reserve EBDA region, it's a 4K region */
- reserve_ebda_region_node();
-
-#ifdef CONFIG_ACPI_SLEEP
- /*
- * Reserve low memory region for sleep support.
- */
- acpi_reserve_bootmem();
-#endif
-
- /*
- * Find and reserve possible boot-time SMP configuration:
- */
- find_smp_config();
-
-#ifdef CONFIG_BLK_DEV_INITRD
- if (LOADER_TYPE && INITRD_START) {
- if (INITRD_START + INITRD_SIZE <= (system_max_low_pfn << PAGE_SHIFT)) {
- reserve_bootmem_node(NODE_DATA(0), INITRD_START, INITRD_SIZE);
- initrd_start =
- INITRD_START ? INITRD_START + PAGE_OFFSET : 0;
- initrd_end = initrd_start+INITRD_SIZE;
- }
- else {
- printk(KERN_ERR "initrd extends beyond end of memory "
- "(0x%08lx > 0x%08lx)\ndisabling initrd\n",
- INITRD_START + INITRD_SIZE,
- system_max_low_pfn << PAGE_SHIFT);
- initrd_start = 0;
- }
- }
-#endif
- return system_max_low_pfn;
+ setup_bootmem_allocator();
+ return max_low_pfn;
}
void __init zone_sizes_init(void)
{
int nid;
- /*
- * Insert nodes into pgdat_list backward so they appear in order.
- * Clobber node 0's links and NULL out pgdat_list before starting.
- */
- pgdat_list = NULL;
- for (nid = MAX_NUMNODES - 1; nid >= 0; nid--) {
- if (!node_online(nid))
- continue;
- if (nid)
- memset(NODE_DATA(nid), 0, sizeof(pg_data_t));
- NODE_DATA(nid)->pgdat_next = pgdat_list;
- pgdat_list = NODE_DATA(nid);
- }
for_each_online_node(nid) {
unsigned long zones_size[MAX_NR_ZONES] = {0, 0, 0};
max_dma = virt_to_phys((char *)MAX_DMA_ADDRESS) >> PAGE_SHIFT;
- if (start > low) {
+ if (node_has_online_mem(nid)){
+ if (start > low) {
#ifdef CONFIG_HIGHMEM
- BUG_ON(start > high);
- zones_size[ZONE_HIGHMEM] = high - start;
+ BUG_ON(start > high);
+ zones_size[ZONE_HIGHMEM] = high - start;
#endif
- } else {
- if (low < max_dma)
- zones_size[ZONE_DMA] = low;
- else {
- BUG_ON(max_dma > low);
- BUG_ON(low > high);
- zones_size[ZONE_DMA] = max_dma;
- zones_size[ZONE_NORMAL] = low - max_dma;
+ } else {
+ if (low < max_dma)
+ zones_size[ZONE_DMA] = low;
+ else {
+ BUG_ON(max_dma > low);
+ BUG_ON(low > high);
+ zones_size[ZONE_DMA] = max_dma;
+ zones_size[ZONE_NORMAL] = low - max_dma;
#ifdef CONFIG_HIGHMEM
- zones_size[ZONE_HIGHMEM] = high - low;
+ zones_size[ZONE_HIGHMEM] = high - low;
#endif
+ }
}
}
+
zholes_size = get_zholes_size(nid);
- /*
- * We let the lmem_map for node 0 be allocated from the
- * normal bootmem allocator, but other nodes come from the
- * remapped KVA area - mbligh
- */
- if (!nid)
- free_area_init_node(nid, NODE_DATA(nid),
- zones_size, start, zholes_size);
- else {
- unsigned long lmem_map;
- lmem_map = (unsigned long)node_remap_start_vaddr[nid];
- lmem_map += sizeof(pg_data_t) + PAGE_SIZE - 1;
- lmem_map &= PAGE_MASK;
- NODE_DATA(nid)->node_mem_map = (struct page *)lmem_map;
- free_area_init_node(nid, NODE_DATA(nid), zones_size,
- start, zholes_size);
- }
+
+ free_area_init_node(nid, NODE_DATA(nid), zones_size, start,
+ zholes_size);
}
return;
}
{
#ifdef CONFIG_HIGHMEM
struct zone *zone;
+ struct page *page;
for_each_zone(zone) {
- unsigned long node_pfn, node_high_size, zone_start_pfn;
- struct page * zone_mem_map;
-
+ unsigned long node_pfn, zone_start_pfn, zone_end_pfn;
+
if (!is_highmem(zone))
continue;
- printk("Initializing %s for node %d\n", zone->name,
- zone->zone_pgdat->node_id);
-
- node_high_size = zone->spanned_pages;
- zone_mem_map = zone->zone_mem_map;
zone_start_pfn = zone->zone_start_pfn;
+ zone_end_pfn = zone_start_pfn + zone->spanned_pages;
- for (node_pfn = 0; node_pfn < node_high_size; node_pfn++) {
- one_highpage_init((struct page *)(zone_mem_map + node_pfn),
- zone_start_pfn + node_pfn, bad_ppro);
+ printk("Initializing %s for node %d (%08lx:%08lx)\n",
+ zone->name, zone->zone_pgdat->node_id,
+ zone_start_pfn, zone_end_pfn);
+
+ for (node_pfn = zone_start_pfn; node_pfn < zone_end_pfn; node_pfn++) {
+ if (!pfn_valid(node_pfn))
+ continue;
+ page = pfn_to_page(node_pfn);
+ add_one_highpage_init(page, node_pfn, bad_ppro);
}
}
totalram_pages += totalhigh_pages;
#endif
}
-
-void __init set_max_mapnr_init(void)
-{
-#ifdef CONFIG_HIGHMEM
- num_physpages = highend_pfn;
-#else
- num_physpages = max_low_pfn;
-#endif
-}
git://git.onelab.eu / linux-2.6.git / blobdiff