[PATCH] sparsemem hotplug base

Make sparse's initalization be accessible at runtime.  This allows sparse
mappings to be created after boot in a hotplug situation.

This patch is separated from the previous one just to give an indication how
much of the sparse infrastructure is *just* for hotplug memory.

The section_mem_map doesn't really store a pointer.  It stores something that
is convenient to do some math against to get a pointer.  It isn't valid to
just do *section_mem_map, so I don't think it should be stored as a pointer.

There are a couple of things I'd like to store about a section.  First of all,
the fact that it is !NULL does not mean that it is present.  There could be
such a combination where section_mem_map *is* NULL, but the math gets you
properly to a real mem_map.  So, I don't think that check is safe.

Since we're storing 32-bit-aligned structures, we have a few bits in the
bottom of the pointer to play with.  Use one bit to encode whether there's
really a mem_map there, and the other one to tell whether there's a valid
section there.  We need to distinguish between the two because sometimes
there's a gap between when a section is discovered to be present and when we
can get the mem_map for it.

Signed-off-by: Dave Hansen <haveblue@us.ibm.com>
Signed-off-by: Andy Whitcroft <apw@shadowen.org>
Signed-off-by: Jack Steiner <steiner@sgi.com>
Signed-off-by: Bob Picco <bob.picco@hp.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

2 files changed, 74 insertions, 22 deletions

diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 1eb683f9b3af..7ee675ad101e 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -1650,8 +1650,8 @@ void __init memmap_init_zone(unsigned long size, int nid, unsigned long zone,
 		unsigned long start_pfn)
 {
 	struct page *page;
-	int end_pfn = start_pfn + size;
-	int pfn;
+	unsigned long end_pfn = start_pfn + size;
+	unsigned long pfn;
 
 	for (pfn = start_pfn; pfn < end_pfn; pfn++, page++) {
 		if (!early_pfn_valid(pfn))
diff --git a/mm/sparse.c b/mm/sparse.c
index f888385b9e14..b54e304df4a7 100644
--- a/mm/sparse.c
+++ b/mm/sparse.c
@@ -25,7 +25,7 @@ void memory_present(int nid, unsigned long start, unsigned long end)
 	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 = (void *) -1;
+			mem_section[section].section_mem_map = SECTION_MARKED_PRESENT;
 	}
 }
 
@@ -51,6 +51,56 @@ unsigned long __init node_memmap_size_bytes(int nid, unsigned long start_pfn,
 }
 
 /*
+ * Subtle, we encode the real pfn into the mem_map such that
+ * the identity pfn - section_mem_map will return the actual
+ * physical page frame number.
+ */
+static unsigned long sparse_encode_mem_map(struct page *mem_map, unsigned long pnum)
+{
+	return (unsigned long)(mem_map - (section_nr_to_pfn(pnum)));
+}
+
+/*
+ * We need this if we ever free the mem_maps.  While not implemented yet,
+ * this function is included for parity with its sibling.
+ */
+static __attribute((unused))
+struct page *sparse_decode_mem_map(unsigned long coded_mem_map, unsigned long pnum)
+{
+	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)
+{
+	if (!valid_section(ms))
+		return -EINVAL;
+
+	ms->section_mem_map |= sparse_encode_mem_map(mem_map, pnum);
+
+	return 1;
+}
+
+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));
+
+	map = alloc_remap(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)
+		return map;
+
+	printk(KERN_WARNING "%s: allocation failed\n", __FUNCTION__);
+	mem_section[pnum].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.
  */
@@ -58,28 +108,30 @@ void sparse_init(void)
 {
 	unsigned long pnum;
 	struct page *map;
-	int nid;
 
 	for (pnum = 0; pnum < NR_MEM_SECTIONS; pnum++) {
-		if (!mem_section[pnum].section_mem_map)
+		if (!valid_section_nr(pnum))
 			continue;
 
-		nid = early_pfn_to_nid(section_nr_to_pfn(pnum));
-		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);
-		if (!map) {
-			mem_section[pnum].section_mem_map = 0;
-			continue;
-		}
-
-		/*
-		 * Subtle, we encode the real pfn into the mem_map such that
-		 * the identity pfn - section_mem_map will return the actual
-		 * physical page frame number.
-		 */
-		mem_section[pnum].section_mem_map = map -
-						section_nr_to_pfn(pnum);
+		map = sparse_early_mem_map_alloc(pnum);
+		if (map)
+			sparse_init_one_section(&mem_section[pnum], pnum, map);
 	}
 }
+
+/*
+ * 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)
+{
+	struct mem_section *ms = __pfn_to_section(start_pfn);
+
+	if (ms->section_mem_map & SECTION_MARKED_PRESENT)
+		return -EEXIST;
+
+	ms->section_mem_map |= SECTION_MARKED_PRESENT;
+
+	return sparse_init_one_section(ms, pfn_to_section_nr(start_pfn), map);
+}