memory hotplug: Hot-add with sparsemem-vmemmap
This patch is to avoid panic when memory hot-add is executed with
sparsemem-vmemmap. Current vmemmap-sparsemem code doesn't support memory
hot-add. Vmemmap must be populated when hot-add. This is for
2.6.23-rc2-mm2.
Todo: # Even if this patch is applied, the message "[xxxx-xxxx] potential
offnode page_structs" is displayed. To allocate memmap on its node,
memmap (and pgdat) must be initialized itself like chicken and
egg relationship.
# vmemmap_unpopulate will be necessary for followings.
- For cancel hot-add due to error.
- For unplug.
Signed-off-by: Yasunori Goto <y-goto@jp.fujitsu.com>
Cc: Andy Whitcroft <apw@shadowen.org>
Cc: Christoph Lameter <clameter@sgi.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 292c686..cc551f0 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1147,7 +1147,7 @@
const char * arch_vma_name(struct vm_area_struct *vma);
-struct page *sparse_early_mem_map_populate(unsigned long pnum, int nid);
+struct page *sparse_mem_map_populate(unsigned long pnum, int nid);
pgd_t *vmemmap_pgd_populate(unsigned long addr, int node);
pud_t *vmemmap_pud_populate(pgd_t *pgd, unsigned long addr, int node);
pmd_t *vmemmap_pmd_populate(pud_t *pud, unsigned long addr, int node);
diff --git a/mm/sparse-vmemmap.c b/mm/sparse-vmemmap.c
index 4f2d485..d3b718b 100644
--- a/mm/sparse-vmemmap.c
+++ b/mm/sparse-vmemmap.c
@@ -137,7 +137,7 @@
return 0;
}
-struct page __init *sparse_early_mem_map_populate(unsigned long pnum, int nid)
+struct page * __meminit sparse_mem_map_populate(unsigned long pnum, int nid)
{
struct page *map = pfn_to_page(pnum * PAGES_PER_SECTION);
int error = vmemmap_populate(map, PAGES_PER_SECTION, nid);
diff --git a/mm/sparse.c b/mm/sparse.c
index 1f4dbb8..08fb14f 100644
--- a/mm/sparse.c
+++ b/mm/sparse.c
@@ -259,7 +259,7 @@
}
#ifndef CONFIG_SPARSEMEM_VMEMMAP
-struct page __init *sparse_early_mem_map_populate(unsigned long pnum, int nid)
+struct page __init *sparse_mem_map_populate(unsigned long pnum, int nid)
{
struct page *map;
@@ -284,7 +284,7 @@
struct mem_section *ms = __nr_to_section(pnum);
int nid = sparse_early_nid(ms);
- map = sparse_early_mem_map_populate(pnum, nid);
+ map = sparse_mem_map_populate(pnum, nid);
if (map)
return map;
@@ -322,6 +322,18 @@
}
#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;
@@ -344,6 +356,12 @@
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 &&
@@ -360,6 +378,7 @@
free_pages((unsigned long)memmap,
get_order(sizeof(struct page) * nr_pages));
}
+#endif /* CONFIG_SPARSEMEM_VMEMMAP */
/*
* returns the number of sections whose mem_maps were properly
@@ -382,7 +401,7 @@
* 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);