/*
* sparse memory mappings.
*/
-#include <linux/config.h>
#include <linux/mm.h>
#include <linux/mmzone.h>
#include <linux/bootmem.h>
+#include <linux/highmem.h>
#include <linux/module.h>
#include <linux/spinlock.h>
+#include <linux/vmalloc.h>
#include <asm/dma.h>
/*
*/
#ifdef CONFIG_SPARSEMEM_EXTREME
struct mem_section *mem_section[NR_SECTION_ROOTS]
- ____cacheline_maxaligned_in_smp;
+ ____cacheline_internodealigned_in_smp;
#else
struct mem_section mem_section[NR_SECTION_ROOTS][SECTIONS_PER_ROOT]
- ____cacheline_maxaligned_in_smp;
+ ____cacheline_internodealigned_in_smp;
#endif
EXPORT_SYMBOL(mem_section);
+#ifdef NODE_NOT_IN_PAGE_FLAGS
+/*
+ * If we did not store the node number in the page then we have to
+ * do a lookup in the section_to_node_table in order to find which
+ * node the page belongs to.
+ */
+#if MAX_NUMNODES <= 256
+static u8 section_to_node_table[NR_MEM_SECTIONS] __cacheline_aligned;
+#else
+static u16 section_to_node_table[NR_MEM_SECTIONS] __cacheline_aligned;
+#endif
+
+int page_to_nid(struct page *page)
+{
+ return section_to_node_table[page_to_section(page)];
+}
+EXPORT_SYMBOL(page_to_nid);
+
+static void set_section_nid(unsigned long section_nr, int nid)
+{
+ section_to_node_table[section_nr] = nid;
+}
+#else /* !NODE_NOT_IN_PAGE_FLAGS */
+static inline void set_section_nid(unsigned long section_nr, int nid)
+{
+}
+#endif
+
#ifdef CONFIG_SPARSEMEM_EXTREME
-static struct mem_section *sparse_index_alloc(int nid)
+static struct mem_section noinline __init_refok *sparse_index_alloc(int nid)
{
struct mem_section *section = NULL;
unsigned long array_size = SECTIONS_PER_ROOT *
sizeof(struct mem_section);
- section = alloc_bootmem_node(NODE_DATA(nid), array_size);
+ if (slab_is_available())
+ section = kmalloc_node(array_size, GFP_KERNEL, nid);
+ else
+ section = alloc_bootmem_node(NODE_DATA(nid), array_size);
if (section)
memset(section, 0, array_size);
return section;
}
-static int sparse_index_init(unsigned long section_nr, int nid)
+static int __meminit sparse_index_init(unsigned long section_nr, int nid)
{
- static spinlock_t index_init_lock = SPIN_LOCK_UNLOCKED;
+ static DEFINE_SPINLOCK(index_init_lock);
unsigned long root = SECTION_NR_TO_ROOT(section_nr);
struct mem_section *section;
int ret = 0;
unsigned long root_nr;
struct mem_section* root;
- for (root_nr = 0;
- root_nr < NR_MEM_SECTIONS;
- root_nr += SECTIONS_PER_ROOT) {
- root = __nr_to_section(root_nr);
-
+ for (root_nr = 0; root_nr < NR_SECTION_ROOTS; root_nr++) {
+ root = __nr_to_section(root_nr * SECTIONS_PER_ROOT);
if (!root)
continue;
return (root_nr * SECTIONS_PER_ROOT) + (ms - root);
}
+/*
+ * During early boot, before section_mem_map is used for an actual
+ * mem_map, we use section_mem_map to store the section's NUMA
+ * node. This keeps us from having to use another data structure. The
+ * node information is cleared just before we store the real mem_map.
+ */
+static inline unsigned long sparse_encode_early_nid(int nid)
+{
+ return (nid << SECTION_NID_SHIFT);
+}
+
+static inline int sparse_early_nid(struct mem_section *section)
+{
+ return (section->section_mem_map >> SECTION_NID_SHIFT);
+}
+
/* Record a memory area against a node. */
-void memory_present(int nid, unsigned long start, unsigned long end)
+void __init memory_present(int nid, unsigned long start, unsigned long end)
{
unsigned long pfn;
struct mem_section *ms;
sparse_index_init(section, nid);
+ set_section_nid(section, nid);
ms = __nr_to_section(section);
if (!ms->section_mem_map)
- ms->section_mem_map = SECTION_MARKED_PRESENT;
+ ms->section_mem_map = sparse_encode_early_nid(nid) |
+ SECTION_MARKED_PRESENT;
}
}
return ((struct page *)coded_mem_map) + section_nr_to_pfn(pnum);
}
-static int sparse_init_one_section(struct mem_section *ms,
+static int __meminit sparse_init_one_section(struct mem_section *ms,
unsigned long pnum, struct page *mem_map)
{
if (!valid_section(ms))
return -EINVAL;
+ ms->section_mem_map &= ~SECTION_MAP_MASK;
ms->section_mem_map |= sparse_encode_mem_map(mem_map, pnum);
return 1;
}
-static struct page *sparse_early_mem_map_alloc(unsigned long pnum)
+__attribute__((weak)) __init
+void *alloc_bootmem_high_node(pg_data_t *pgdat, unsigned long size)
+{
+ return NULL;
+}
+
+static struct page __init *sparse_early_mem_map_alloc(unsigned long pnum)
{
struct page *map;
- int nid = early_pfn_to_nid(section_nr_to_pfn(pnum));
struct mem_section *ms = __nr_to_section(pnum);
+ int nid = sparse_early_nid(ms);
map = alloc_remap(nid, sizeof(struct page) * PAGES_PER_SECTION);
if (map)
return map;
+ map = alloc_bootmem_high_node(NODE_DATA(nid),
+ sizeof(struct page) * PAGES_PER_SECTION);
+ if (map)
+ return map;
+
map = alloc_bootmem_node(NODE_DATA(nid),
sizeof(struct page) * PAGES_PER_SECTION);
if (map)
* Allocate the accumulated non-linear sections, allocate a mem_map
* for each and record the physical to section mapping.
*/
-void sparse_init(void)
+void __init sparse_init(void)
{
unsigned long pnum;
struct page *map;
}
}
+#ifdef CONFIG_MEMORY_HOTPLUG
+static struct page *__kmalloc_section_memmap(unsigned long nr_pages)
+{
+ struct page *page, *ret;
+ unsigned long memmap_size = sizeof(struct page) * nr_pages;
+
+ page = alloc_pages(GFP_KERNEL|__GFP_NOWARN, get_order(memmap_size));
+ if (page)
+ goto got_map_page;
+
+ ret = vmalloc(memmap_size);
+ if (ret)
+ goto got_map_ptr;
+
+ return NULL;
+got_map_page:
+ ret = (struct page *)pfn_to_kaddr(page_to_pfn(page));
+got_map_ptr:
+ memset(ret, 0, memmap_size);
+
+ return ret;
+}
+
+static int vaddr_in_vmalloc_area(void *addr)
+{
+ if (addr >= (void *)VMALLOC_START &&
+ addr < (void *)VMALLOC_END)
+ return 1;
+ return 0;
+}
+
+static void __kfree_section_memmap(struct page *memmap, unsigned long nr_pages)
+{
+ if (vaddr_in_vmalloc_area(memmap))
+ vfree(memmap);
+ else
+ free_pages((unsigned long)memmap,
+ get_order(sizeof(struct page) * nr_pages));
+}
+
/*
* returns the number of sections whose mem_maps were properly
* set. If this is <=0, then that means that the passed-in
* map was not consumed and must be freed.
*/
-int sparse_add_one_section(unsigned long start_pfn, int nr_pages, struct page *map)
+int sparse_add_one_section(struct zone *zone, unsigned long start_pfn,
+ int nr_pages)
{
- struct mem_section *ms = __pfn_to_section(start_pfn);
+ unsigned long section_nr = pfn_to_section_nr(start_pfn);
+ struct pglist_data *pgdat = zone->zone_pgdat;
+ struct mem_section *ms;
+ struct page *memmap;
+ unsigned long flags;
+ int ret;
- if (ms->section_mem_map & SECTION_MARKED_PRESENT)
- return -EEXIST;
+ /*
+ * no locking for this, because it does its own
+ * plus, it does a kmalloc
+ */
+ sparse_index_init(section_nr, pgdat->node_id);
+ memmap = __kmalloc_section_memmap(nr_pages);
+
+ pgdat_resize_lock(pgdat, &flags);
+ ms = __pfn_to_section(start_pfn);
+ if (ms->section_mem_map & SECTION_MARKED_PRESENT) {
+ ret = -EEXIST;
+ goto out;
+ }
ms->section_mem_map |= SECTION_MARKED_PRESENT;
- return sparse_init_one_section(ms, pfn_to_section_nr(start_pfn), map);
+ ret = sparse_init_one_section(ms, section_nr, memmap);
+
+out:
+ pgdat_resize_unlock(pgdat, &flags);
+ if (ret <= 0)
+ __kfree_section_memmap(memmap, nr_pages);
+ return ret;
}
+#endif