ppc64: SPARSEMEM_VMEMMAP support

Enable virtual memmap support for SPARSEMEM on PPC64 systems.  Slice a 16th
off the end of the linear mapping space and use that to hold the vmemmap.
Uses the same size mapping as uses in the linear 1:1 kernel mapping.

[pbadari@gmail.com: fix warning]
Signed-off-by: Andy Whitcroft <apw@shadowen.org>
Acked-by: Mel Gorman <mel@csn.ul.ie>
Cc: Christoph Lameter <clameter@sgi.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Signed-off-by: Badari Pulavarty <pbadari@us.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

3 files changed, 76 insertions, 0 deletions

diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index 037664d496d7..5e001ad588a7 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -295,6 +295,7 @@ config ARCH_FLATMEM_ENABLE
 config ARCH_SPARSEMEM_ENABLE
         def_bool y
         depends on PPC64
+        select SPARSEMEM_VMEMMAP_ENABLE
 
 config ARCH_SPARSEMEM_DEFAULT
         def_bool y
diff --git a/arch/powerpc/mm/init_64.c b/arch/powerpc/mm/init_64.c
index fa90f6561b9f..29ed495444f5 100644
--- a/arch/powerpc/mm/init_64.c
+++ b/arch/powerpc/mm/init_64.c
@@ -183,3 +183,70 @@ void pgtable_cache_init(void)
                                                      zero_ctor);
         }
 }
+
+#ifdef CONFIG_SPARSEMEM_VMEMMAP
+/*
+ * Given an address within the vmemmap, determine the pfn of the page that
+ * represents the start of the section it is within.  Note that we have to
+ * do this by hand as the proffered address may not be correctly aligned.
+ * Subtraction of non-aligned pointers produces undefined results.
+ */
+unsigned long __meminit vmemmap_section_start(unsigned long page)
+{
+        unsigned long offset = page - ((unsigned long)(vmemmap));
+
+        /* Return the pfn of the start of the section. */
+        return (offset / sizeof(struct page)) & PAGE_SECTION_MASK;
+}
+
+/*
+ * Check if this vmemmap page is already initialised.  If any section
+ * which overlaps this vmemmap page is initialised then this page is
+ * initialised already.
+ */
+int __meminit vmemmap_populated(unsigned long start, int page_size)
+{
+        unsigned long end = start + page_size;
+
+        for (; start < end; start += (PAGES_PER_SECTION * sizeof(struct page)))
+                if (pfn_valid(vmemmap_section_start(start)))
+                        return 1;
+
+        return 0;
+}
+
+int __meminit vmemmap_populate(struct page *start_page,
+                                        unsigned long nr_pages, int node)
+{
+        unsigned long mode_rw;
+        unsigned long start = (unsigned long)start_page;
+        unsigned long end = (unsigned long)(start_page + nr_pages);
+        unsigned long page_size = 1 << mmu_psize_defs[mmu_linear_psize].shift;
+
+        mode_rw = _PAGE_ACCESSED | _PAGE_DIRTY | _PAGE_COHERENT | PP_RWXX;
+
+        /* Align to the page size of the linear mapping. */
+        start = _ALIGN_DOWN(start, page_size);
+
+        for (; start < end; start += page_size) {
+                int mapped;
+                void *p;
+
+                if (vmemmap_populated(start, page_size))
+                        continue;
+
+                p = vmemmap_alloc_block(page_size, node);
+                if (!p)
+                        return -ENOMEM;
+
+                printk(KERN_WARNING "vmemmap %08lx allocated at %p, "
+                                        "physical %p.\n", start, p, __pa(p));
+
+                mapped = htab_bolt_mapping(start, start + page_size,
+                                        __pa(p), mode_rw, mmu_linear_psize);
+                BUG_ON(mapped < 0);
+        }
+
+        return 0;
+}
+#endif
diff --git a/include/asm-powerpc/pgtable-ppc64.h b/include/asm-powerpc/pgtable-ppc64.h
index 300f9a199bf2..dd4c26dc57d2 100644
--- a/include/asm-powerpc/pgtable-ppc64.h
+++ b/include/asm-powerpc/pgtable-ppc64.h
@@ -68,6 +68,14 @@
 #define USER_REGION_ID          (0UL)
 
 /*
+ * Defines the address of the vmemap area, in the top 16th of the
+ * kernel region.
+ */
+#define VMEMMAP_BASE (ASM_CONST(CONFIG_KERNEL_START) + \
+                                        (0xfUL << (REGION_SHIFT - 4)))
+#define vmemmap ((struct page *)VMEMMAP_BASE)
+
+/*
  * Common bits in a linux-style PTE.  These match the bits in the
  * (hardware-defined) PowerPC PTE as closely as possible. Additional
  * bits may be defined in pgtable-*.h