#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>
/*
*
* 1) mem_section - memory sections, mem_map's for valid memory
*/
-struct mem_section mem_section[NR_MEM_SECTIONS];
+#ifdef CONFIG_SPARSEMEM_EXTREME
+struct mem_section *mem_section[NR_SECTION_ROOTS]
+ ____cacheline_maxaligned_in_smp;
+#else
+struct mem_section mem_section[NR_SECTION_ROOTS][SECTIONS_PER_ROOT]
+ ____cacheline_maxaligned_in_smp;
+#endif
EXPORT_SYMBOL(mem_section);
+#ifdef CONFIG_SPARSEMEM_EXTREME
+static struct mem_section *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 (section)
+ memset(section, 0, array_size);
+
+ return section;
+}
+
+static int sparse_index_init(unsigned long section_nr, int nid)
+{
+ static spinlock_t index_init_lock = SPIN_LOCK_UNLOCKED;
+ unsigned long root = SECTION_NR_TO_ROOT(section_nr);
+ struct mem_section *section;
+ int ret = 0;
+
+ if (mem_section[root])
+ return -EEXIST;
+
+ section = sparse_index_alloc(nid);
+ /*
+ * This lock keeps two different sections from
+ * reallocating for the same index
+ */
+ spin_lock(&index_init_lock);
+
+ if (mem_section[root]) {
+ ret = -EEXIST;
+ goto out;
+ }
+
+ mem_section[root] = section;
+out:
+ spin_unlock(&index_init_lock);
+ return ret;
+}
+#else /* !SPARSEMEM_EXTREME */
+static inline int sparse_index_init(unsigned long section_nr, int nid)
+{
+ return 0;
+}
+#endif
+
+/*
+ * Although written for the SPARSEMEM_EXTREME case, this happens
+ * to also work for the flat array case becase
+ * 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);
+
+ if (!root)
+ continue;
+
+ if ((ms >= root) && (ms < (root + SECTIONS_PER_ROOT)))
+ break;
+ }
+
+ return (root_nr * SECTIONS_PER_ROOT) + (ms - root);
+}
+
/* Record a memory area against a node. */
void memory_present(int nid, unsigned long start, unsigned long end)
{
start &= PAGE_SECTION_MASK;
for (pfn = start; pfn < end; pfn += PAGES_PER_SECTION) {
unsigned long section = pfn_to_section_nr(pfn);
- if (!mem_section[section].section_mem_map)
- mem_section[section].section_mem_map = SECTION_MARKED_PRESENT;
+ struct mem_section *ms;
+
+ sparse_index_init(section, nid);
+
+ ms = __nr_to_section(section);
+ if (!ms->section_mem_map)
+ ms->section_mem_map = SECTION_MARKED_PRESENT;
}
}
{
struct page *map;
int nid = early_pfn_to_nid(section_nr_to_pfn(pnum));
+ struct mem_section *ms = __nr_to_section(pnum);
map = alloc_remap(nid, sizeof(struct page) * PAGES_PER_SECTION);
if (map)
return map;
printk(KERN_WARNING "%s: allocation failed\n", __FUNCTION__);
- mem_section[pnum].section_mem_map = 0;
+ ms->section_mem_map = 0;
+ return NULL;
+}
+
+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));
+ 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));
}
/*
continue;
map = sparse_early_mem_map_alloc(pnum);
- if (map)
- sparse_init_one_section(&mem_section[pnum], pnum, map);
+ if (!map)
+ continue;
+ sparse_init_one_section(__nr_to_section(pnum), pnum, map);
}
}
* 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);
+
+ if (ret <= 0)
+ __kfree_section_memmap(memmap, nr_pages);
+out:
+ pgdat_resize_unlock(pgdat, &flags);
+ return ret;
}