/*
* sparse memory mappings.
*/
-#include <linux/config.h>
#include <linux/mm.h>
#include <linux/mmzone.h>
#include <linux/bootmem.h>
#include <linux/spinlock.h>
#include <linux/vmalloc.h>
#include <asm/dma.h>
+#include <asm/pgalloc.h>
+#include <asm/pgtable.h>
/*
* Permanent SPARSEMEM data:
#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);
- if (system_state == SYSTEM_RUNNING)
+ if (slab_is_available())
section = kmalloc_node(array_size, GFP_KERNEL, nid);
else
section = alloc_bootmem_node(NODE_DATA(nid), 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;
/*
* Although written for the SPARSEMEM_EXTREME case, this happens
- * to also work for the flat array case becase
+ * to also work for the flat array case because
* NR_SECTION_ROOTS==NR_MEM_SECTIONS.
*/
int __section_nr(struct mem_section* ms)
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;
}
}
if (nid != early_pfn_to_nid(pfn))
continue;
- if (pfn_valid(pfn))
+ if (pfn_present(pfn))
nr_pages += PAGES_PER_SECTION;
}
return ((struct page *)coded_mem_map) + section_nr_to_pfn(pnum);
}
-static int sparse_init_one_section(struct mem_section *ms,
- unsigned long pnum, struct page *mem_map)
+static int __meminit sparse_init_one_section(struct mem_section *ms,
+ unsigned long pnum, struct page *mem_map,
+ unsigned long *pageblock_bitmap)
{
- if (!valid_section(ms))
+ if (!present_section(ms))
return -EINVAL;
- ms->section_mem_map |= sparse_encode_mem_map(mem_map, pnum);
+ ms->section_mem_map &= ~SECTION_MAP_MASK;
+ ms->section_mem_map |= sparse_encode_mem_map(mem_map, pnum) |
+ SECTION_HAS_MEM_MAP;
+ ms->pageblock_flags = pageblock_bitmap;
return 1;
}
-static struct page *sparse_early_mem_map_alloc(unsigned long pnum)
+static unsigned long usemap_size(void)
{
- struct page *map;
- int nid = early_pfn_to_nid(section_nr_to_pfn(pnum));
+ unsigned long size_bytes;
+ size_bytes = roundup(SECTION_BLOCKFLAGS_BITS, 8) / 8;
+ size_bytes = roundup(size_bytes, sizeof(unsigned long));
+ return size_bytes;
+}
+
+#ifdef CONFIG_MEMORY_HOTPLUG
+static unsigned long *__kmalloc_section_usemap(void)
+{
+ return kmalloc(usemap_size(), GFP_KERNEL);
+}
+#endif /* CONFIG_MEMORY_HOTPLUG */
+
+static unsigned long *sparse_early_usemap_alloc(unsigned long pnum)
+{
+ unsigned long *usemap;
struct mem_section *ms = __nr_to_section(pnum);
+ int nid = sparse_early_nid(ms);
+
+ usemap = alloc_bootmem_node(NODE_DATA(nid), usemap_size());
+ if (usemap)
+ return usemap;
+
+ /* Stupid: suppress gcc warning for SPARSEMEM && !NUMA */
+ nid = 0;
+
+ printk(KERN_WARNING "%s: allocation failed\n", __FUNCTION__);
+ return NULL;
+}
+
+#ifndef CONFIG_SPARSEMEM_VMEMMAP
+struct page __init *sparse_mem_map_populate(unsigned long pnum, int nid)
+{
+ struct page *map;
map = alloc_remap(nid, sizeof(struct page) * PAGES_PER_SECTION);
if (map)
map = alloc_bootmem_node(NODE_DATA(nid),
sizeof(struct page) * PAGES_PER_SECTION);
+ return map;
+}
+#endif /* !CONFIG_SPARSEMEM_VMEMMAP */
+
+struct page __init *sparse_early_mem_map_alloc(unsigned long pnum)
+{
+ struct page *map;
+ struct mem_section *ms = __nr_to_section(pnum);
+ int nid = sparse_early_nid(ms);
+
+ map = sparse_mem_map_populate(pnum, nid);
if (map)
return map;
- printk(KERN_WARNING "%s: allocation failed\n", __FUNCTION__);
+ printk(KERN_ERR "%s: sparsemem memory map backing failed "
+ "some memory will not be available.\n", __FUNCTION__);
ms->section_mem_map = 0;
return NULL;
}
+/*
+ * Allocate the accumulated non-linear sections, allocate a mem_map
+ * for each and record the physical to section mapping.
+ */
+void __init sparse_init(void)
+{
+ unsigned long pnum;
+ struct page *map;
+ unsigned long *usemap;
+
+ for (pnum = 0; pnum < NR_MEM_SECTIONS; pnum++) {
+ if (!present_section_nr(pnum))
+ continue;
+
+ map = sparse_early_mem_map_alloc(pnum);
+ if (!map)
+ continue;
+
+ usemap = sparse_early_usemap_alloc(pnum);
+ if (!usemap)
+ continue;
+
+ sparse_init_one_section(__nr_to_section(pnum), pnum, map,
+ usemap);
+ }
+}
+
+#ifdef CONFIG_MEMORY_HOTPLUG
+#ifdef CONFIG_SPARSEMEM_VMEMMAP
+static inline struct page *kmalloc_section_memmap(unsigned long pnum, int nid,
+ unsigned long nr_pages)
+{
+ /* This will make the necessary allocations eventually. */
+ return sparse_mem_map_populate(pnum, nid);
+}
+static void __kfree_section_memmap(struct page *memmap, unsigned long nr_pages)
+{
+ return; /* XXX: Not implemented yet */
+}
+#else
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, get_order(memmap_size));
+ page = alloc_pages(GFP_KERNEL|__GFP_NOWARN, get_order(memmap_size));
if (page)
goto got_map_page;
return ret;
}
+static inline struct page *kmalloc_section_memmap(unsigned long pnum, int nid,
+ unsigned long nr_pages)
+{
+ return __kmalloc_section_memmap(nr_pages);
+}
+
static int vaddr_in_vmalloc_area(void *addr)
{
if (addr >= (void *)VMALLOC_START &&
free_pages((unsigned long)memmap,
get_order(sizeof(struct page) * nr_pages));
}
-
-/*
- * Allocate the accumulated non-linear sections, allocate a mem_map
- * for each and record the physical to section mapping.
- */
-void sparse_init(void)
-{
- unsigned long pnum;
- struct page *map;
-
- for (pnum = 0; pnum < NR_MEM_SECTIONS; pnum++) {
- if (!valid_section_nr(pnum))
- continue;
-
- map = sparse_early_mem_map_alloc(pnum);
- if (!map)
- continue;
- sparse_init_one_section(__nr_to_section(pnum), pnum, map);
- }
-}
+#endif /* CONFIG_SPARSEMEM_VMEMMAP */
/*
* returns the number of sections whose mem_maps were properly
struct pglist_data *pgdat = zone->zone_pgdat;
struct mem_section *ms;
struct page *memmap;
+ unsigned long *usemap;
unsigned long flags;
int ret;
* plus, it does a kmalloc
*/
sparse_index_init(section_nr, pgdat->node_id);
- memmap = __kmalloc_section_memmap(nr_pages);
+ memmap = kmalloc_section_memmap(section_nr, pgdat->node_id, nr_pages);
+ usemap = __kmalloc_section_usemap();
pgdat_resize_lock(pgdat, &flags);
ret = -EEXIST;
goto out;
}
+
+ if (!usemap) {
+ ret = -ENOMEM;
+ goto out;
+ }
ms->section_mem_map |= SECTION_MARKED_PRESENT;
- ret = sparse_init_one_section(ms, section_nr, memmap);
+ ret = sparse_init_one_section(ms, section_nr, memmap, usemap);
out:
pgdat_resize_unlock(pgdat, &flags);
__kfree_section_memmap(memmap, nr_pages);
return ret;
}
+#endif