[PATCH] sparsemem extreme implementation

With cleanups from Dave Hansen <haveblue@us.ibm.com>

SPARSEMEM_EXTREME makes mem_section a one dimensional array of pointers to
mem_sections.  This two level layout scheme is able to achieve smaller
memory requirements for SPARSEMEM with the tradeoff of an additional shift
and load when fetching the memory section.  The current SPARSEMEM
implementation is a one dimensional array of mem_sections which is the
default SPARSEMEM configuration.  The patch attempts isolates the
implementation details of the physical layout of the sparsemem section
array.

SPARSEMEM_EXTREME requires bootmem to be functioning at the time of
memory_present() calls.  This is not always feasible, so architectures
which do not need it may allocate everything statically by using
SPARSEMEM_STATIC.

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

2 files changed, 33 insertions, 12 deletions

diff --git a/mm/Kconfig b/mm/Kconfig
index fc644c5..4e9937a 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -91,10 +91,23 @@ config HAVE_MEMORY_PRESENT
 	depends on ARCH_HAVE_MEMORY_PRESENT || SPARSEMEM
 
 #
+# SPARSEMEM_EXTREME (which is the default) does some bootmem
+# allocations when memory_present() is called.  If this can not
+# be done on your architecture, select this option.  However,
+# statically allocating the mem_section[] array can potentially
+# consume vast quantities of .bss, so be careful.
+#
+# This option will also potentially produce smaller runtime code
+# with gcc 3.4 and later.
+#
+config SPARSEMEM_STATIC
+	def_bool n
+
+#
 # Architectecture platforms which require a two level mem_section in SPARSEMEM
 # must select this option. This is usually for architecture platforms with
 # an extremely sparse physical address space.
 #
-config ARCH_SPARSEMEM_EXTREME
-	def_bool n
-	depends on SPARSEMEM && 64BIT
+config SPARSEMEM_EXTREME
+	def_bool y
+	depends on SPARSEMEM && !SPARSEMEM_STATIC
diff --git a/mm/sparse.c b/mm/sparse.c
index b2b456b..fa01292 100644
--- a/mm/sparse.c
+++ b/mm/sparse.c
@@ -13,28 +13,36 @@
  *
  * 1) mem_section	- memory sections, mem_map's for valid memory
  */
-#ifdef CONFIG_ARCH_SPARSEMEM_EXTREME
+#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);
+
+static void sparse_alloc_root(unsigned long root, int nid)
+{
+#ifdef CONFIG_SPARSEMEM_EXTREME
+	mem_section[root] = alloc_bootmem_node(NODE_DATA(nid), PAGE_SIZE);
+#endif
+}
 
 static void sparse_index_init(unsigned long section, int nid)
 {
-	unsigned long root = SECTION_TO_ROOT(section);
+	unsigned long root = SECTION_NR_TO_ROOT(section);
 
 	if (mem_section[root])
 		return;
-	mem_section[root] = alloc_bootmem_node(NODE_DATA(nid), PAGE_SIZE);
+
+	sparse_alloc_root(root, nid);
+
 	if (mem_section[root])
 		memset(mem_section[root], 0, PAGE_SIZE);
 	else
 		panic("memory_present: NO MEMORY\n");
 }
-#else
-struct mem_section mem_section[NR_MEM_SECTIONS]
-	____cacheline_maxaligned_in_smp;
-#endif
-EXPORT_SYMBOL(mem_section);
-
 /* Record a memory area against a node. */
 void memory_present(int nid, unsigned long start, unsigned long end)
 {