[PATCH] sparsemem: record nid during memory present

Record the node id as we mark sections for instantiation.  Use this nid
during instantiation to direct allocations.

Signed-off-by: Andy Whitcroft <apw@shadowen.org>
Cc: Mike Kravetz <kravetz@us.ibm.com>
Cc: Dave Hansen <haveblue@us.ibm.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: Bob Picco <bob.picco@hp.com>
Cc: Jack Steiner <steiner@sgi.com>
Cc: Yasunori Goto <y-goto@jp.fujitsu.com>
Cc: Martin Bligh <mbligh@google.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index e82fc1a52cd06a6890dd95193647e90fec1f677d..d6120fa69116f92399bfeb6951250ac1cc21e4a5 100644 (file)
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -509,6 +509,10 @@ struct mem_section {
         * pages.  However, it is stored with some other magic.
         * (see sparse.c::sparse_init_one_section())
         *
+        * Additionally during early boot we encode node id of
+        * the location of the section here to guide allocation.
+        * (see sparse.c::memory_present())
+        *
         * Making it a UL at least makes someone do a cast
         * before using it wrong.
         */
@@ -548,6 +552,7 @@ extern int __section_nr(struct mem_section* ms);
 #define SECTION_HAS_MEM_MAP    (1UL<<1)
 #define SECTION_MAP_LAST_BIT   (1UL<<2)
 #define SECTION_MAP_MASK       (~(SECTION_MAP_LAST_BIT-1))
+#define SECTION_NID_SHIFT      2
 
 static inline struct page *__section_mem_map_addr(struct mem_section *section)
 {

diff --git a/mm/sparse.c b/mm/sparse.c
index 100040c0dfb6c8e674dada0ed8eb471820e2f75b..e0a3fe48aa3745bebd710ff80d8cad6215dd244d 100644 (file)
--- a/mm/sparse.c
+++ b/mm/sparse.c
@@ -99,6 +99,22 @@ int __section_nr(struct mem_section* ms)
        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)
 {
@@ -113,7 +129,8 @@ void memory_present(int nid, unsigned long start, unsigned long end)
 
                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;
        }
 }
 
@@ -164,6 +181,7 @@ static int sparse_init_one_section(struct mem_section *ms,
        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;
@@ -172,8 +190,8 @@ static int sparse_init_one_section(struct mem_section *ms,
 static struct page *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)