[PATCH] ppc64: sparsemem memory model

Provide the architecture specific implementation for SPARSEMEM for PPC64
systems.

Signed-off-by: Andy Whitcroft <apw@shadowen.org>
Signed-off-by: Dave Hansen <haveblue@us.ibm.com>
Signed-off-by: Mike Kravetz <kravetz@us.ibm.com> (in part)
Signed-off-by: Martin Bligh <mbligh@aracnet.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

7 files changed, 68 insertions, 21 deletions

diff --git a/arch/ppc64/Kconfig b/arch/ppc64/Kconfig
index c92d48fe06e5..6448231cb106 100644
--- a/arch/ppc64/Kconfig
+++ b/arch/ppc64/Kconfig
@@ -198,6 +198,13 @@ config HMT
           This option enables hardware multithreading on RS64 cpus.
           pSeries systems p620 and p660 have such a cpu type.
 
+config ARCH_SELECT_MEMORY_MODEL
+        def_bool y
+
+config ARCH_FLATMEM_ENABLE
+       def_bool y
+       depends on !NUMA
+
 config ARCH_DISCONTIGMEM_ENABLE
         def_bool y
         depends on SMP && PPC_PSERIES
@@ -209,6 +216,10 @@ config ARCH_DISCONTIGMEM_DEFAULT
 config ARCH_FLATMEM_ENABLE
         def_bool y
 
+config ARCH_SPARSEMEM_ENABLE
+        def_bool y
+        depends on ARCH_DISCONTIGMEM_ENABLE
+
 source "mm/Kconfig"
 
 config HAVE_ARCH_EARLY_PFN_TO_NID
@@ -229,7 +240,7 @@ config NODES_SPAN_OTHER_NODES
 
 config NUMA
         bool "NUMA support"
-        depends on DISCONTIGMEM
+        default y if DISCONTIGMEM || SPARSEMEM
 
 config SCHED_SMT
         bool "SMT (Hyperthreading) scheduler support"
diff --git a/arch/ppc64/kernel/setup.c b/arch/ppc64/kernel/setup.c
index 8e439a817642..9e70ac90dec1 100644
--- a/arch/ppc64/kernel/setup.c
+++ b/arch/ppc64/kernel/setup.c
@@ -1055,6 +1055,7 @@ void __init setup_arch(char **cmdline_p)
 
         /* set up the bootmem stuff with available memory */
         do_init_bootmem();
+        sparse_init();
 
         /* initialize the syscall map in systemcfg */
         setup_syscall_map();
diff --git a/arch/ppc64/mm/Makefile b/arch/ppc64/mm/Makefile
index ac522d57b2a7..3695d00d347f 100644
--- a/arch/ppc64/mm/Makefile
+++ b/arch/ppc64/mm/Makefile
@@ -6,6 +6,6 @@ EXTRA_CFLAGS += -mno-minimal-toc
 
 obj-y := fault.o init.o imalloc.o hash_utils.o hash_low.o tlb.o \
         slb_low.o slb.o stab.o mmap.o
-obj-$(CONFIG_DISCONTIGMEM) += numa.o
+obj-$(CONFIG_NEED_MULTIPLE_NODES) += numa.o
 obj-$(CONFIG_HUGETLB_PAGE) += hugetlbpage.o
 obj-$(CONFIG_PPC_MULTIPLATFORM) += hash_native.o
diff --git a/arch/ppc64/mm/init.c b/arch/ppc64/mm/init.c
index 29dbe084c21f..b50b3a446dbe 100644
--- a/arch/ppc64/mm/init.c
+++ b/arch/ppc64/mm/init.c
@@ -531,7 +531,7 @@ EXPORT_SYMBOL(page_is_ram);
  * Initialize the bootmem system and give it all the memory we
  * have available.
  */
-#ifndef CONFIG_DISCONTIGMEM
+#ifndef CONFIG_NEED_MULTIPLE_NODES
 void __init do_init_bootmem(void)
 {
         unsigned long i;
@@ -553,12 +553,20 @@ void __init do_init_bootmem(void)
 
         max_pfn = max_low_pfn;
 
-        /* add all physical memory to the bootmem map. Also find the first */
+        /* Add all physical memory to the bootmem map, mark each area
+         * present.
+         */
         for (i=0; i < lmb.memory.cnt; i++) {
                 unsigned long physbase, size;
+                unsigned long start_pfn, end_pfn;
 
                 physbase = lmb.memory.region[i].physbase;
                 size = lmb.memory.region[i].size;
+
+                start_pfn = physbase >> PAGE_SHIFT;
+                end_pfn = start_pfn + (size >> PAGE_SHIFT);
+                memory_present(0, start_pfn, end_pfn);
+
                 free_bootmem(physbase, size);
         }
 
@@ -597,7 +605,7 @@ void __init paging_init(void)
         free_area_init_node(0, NODE_DATA(0), zones_size,
                             __pa(PAGE_OFFSET) >> PAGE_SHIFT, zholes_size);
 }
-#endif /* CONFIG_DISCONTIGMEM */
+#endif /* ! CONFIG_NEED_MULTIPLE_NODES */
 
 static struct kcore_list kcore_vmem;
 
@@ -628,7 +636,7 @@ module_init(setup_kcore);
 
 void __init mem_init(void)
 {
-#ifdef CONFIG_DISCONTIGMEM
+#ifdef CONFIG_NEED_MULTIPLE_NODES
         int nid;
 #endif
         pg_data_t *pgdat;
@@ -639,7 +647,7 @@ void __init mem_init(void)
         num_physpages = max_low_pfn;    /* RAM is assumed contiguous */
         high_memory = (void *) __va(max_low_pfn * PAGE_SIZE);
 
-#ifdef CONFIG_DISCONTIGMEM
+#ifdef CONFIG_NEED_MULTIPLE_NODES
         for_each_online_node(nid) {
                 if (NODE_DATA(nid)->node_spanned_pages != 0) {
                         printk("freeing bootmem node %x\n", nid);
diff --git a/include/asm-ppc64/mmzone.h b/include/asm-ppc64/mmzone.h
index ecc4b07507d6..ed473f4b0152 100644
--- a/include/asm-ppc64/mmzone.h
+++ b/include/asm-ppc64/mmzone.h
@@ -10,9 +10,20 @@
 #include <linux/config.h>
 #include <asm/smp.h>
 
-#ifdef CONFIG_DISCONTIGMEM
+/* generic non-linear memory support:
+ *
+ * 1) we will not split memory into more chunks than will fit into the
+ *    flags field of the struct page
+ */
+
+
+#ifdef CONFIG_NEED_MULTIPLE_NODES
 
 extern struct pglist_data *node_data[];
+/*
+ * Return a pointer to the node data for node n.
+ */
+#define NODE_DATA(nid)          (node_data[nid])
 
 /*
  * Following are specific to this numa platform.
@@ -47,30 +58,27 @@ static inline int pa_to_nid(unsigned long pa)
         return nid;
 }
 
-#define pfn_to_nid(pfn)         pa_to_nid((pfn) << PAGE_SHIFT)
-
-/*
- * Return a pointer to the node data for node n.
- */
-#define NODE_DATA(nid)          (node_data[nid])
-
 #define node_localnr(pfn, nid)  ((pfn) - NODE_DATA(nid)->node_start_pfn)
 
 /*
  * Following are macros that each numa implmentation must define.
  */
 
-/*
- * Given a kernel address, find the home node of the underlying memory.
- */
-#define kvaddr_to_nid(kaddr)    pa_to_nid(__pa(kaddr))
-
 #define node_start_pfn(nid)     (NODE_DATA(nid)->node_start_pfn)
 #define node_end_pfn(nid)       (NODE_DATA(nid)->node_end_pfn)
 
 #define local_mapnr(kvaddr) \
         ( (__pa(kvaddr) >> PAGE_SHIFT) - node_start_pfn(kvaddr_to_nid(kvaddr)) 
 
+#ifdef CONFIG_DISCONTIGMEM
+
+/*
+ * Given a kernel address, find the home node of the underlying memory.
+ */
+#define kvaddr_to_nid(kaddr)    pa_to_nid(__pa(kaddr))
+
+#define pfn_to_nid(pfn)         pa_to_nid((unsigned long)(pfn) << PAGE_SHIFT)
+
 /* Written this way to avoid evaluating arguments twice */
 #define discontigmem_pfn_to_page(pfn) \
 ({ \
@@ -91,6 +99,8 @@ static inline int pa_to_nid(unsigned long pa)
 
 #endif /* CONFIG_DISCONTIGMEM */
 
+#endif /* CONFIG_NEED_MULTIPLE_NODES */
+
 #ifdef CONFIG_HAVE_ARCH_EARLY_PFN_TO_NID
 #define early_pfn_to_nid(pfn)  pa_to_nid(((unsigned long)pfn) << PAGE_SHIFT)
 #endif
diff --git a/include/asm-ppc64/page.h b/include/asm-ppc64/page.h
index 257d87eb7c34..a5893a305a09 100644
--- a/include/asm-ppc64/page.h
+++ b/include/asm-ppc64/page.h
@@ -217,7 +217,8 @@ extern u64 ppc64_pft_size;		/* Log 2 of page table size */
 #define page_to_pfn(page)       discontigmem_page_to_pfn(page)
 #define pfn_to_page(pfn)        discontigmem_pfn_to_page(pfn)
 #define pfn_valid(pfn)          discontigmem_pfn_valid(pfn)
-#else
+#endif
+#ifdef CONFIG_FLATMEM
 #define pfn_to_page(pfn)        (mem_map + (pfn))
 #define page_to_pfn(page)       ((unsigned long)((page) - mem_map))
 #define pfn_valid(pfn)          ((pfn) < max_mapnr)
diff --git a/include/asm-ppc64/sparsemem.h b/include/asm-ppc64/sparsemem.h
new file mode 100644
index 000000000000..c5bd47e57f17
--- /dev/null
+++ b/include/asm-ppc64/sparsemem.h
@@ -0,0 +1,16 @@
+#ifndef _ASM_PPC64_SPARSEMEM_H
+#define _ASM_PPC64_SPARSEMEM_H 1
+
+#ifdef CONFIG_SPARSEMEM
+/*
+ * SECTION_SIZE_BITS            2^N: how big each section will be
+ * MAX_PHYSADDR_BITS            2^N: how much physical address space we have
+ * MAX_PHYSMEM_BITS             2^N: how much memory we can have in that space
+ */
+#define SECTION_SIZE_BITS       24
+#define MAX_PHYSADDR_BITS       38
+#define MAX_PHYSMEM_BITS        36
+
+#endif /* CONFIG_SPARSEMEM */
+
+#endif /* _ASM_PPC64_SPARSEMEM_H */