x86_64: SPARSEMEM_VMEMMAP 2M page size support

x86_64 uses 2M page table entries to map its 1-1 kernel space.  We also
implement the virtual memmap using 2M page table entries.  So there is no
additional runtime overhead over FLATMEM, initialisation is slightly more
complex.  As FLATMEM still references memory to obtain the mem_map pointer and
SPARSEMEM_VMEMMAP uses a compile time constant, SPARSEMEM_VMEMMAP should be
superior.

With this SPARSEMEM becomes the most efficient way of handling virt_to_page,
pfn_to_page and friends for UP, SMP and NUMA on x86_64.

[apw@shadowen.org: code resplit, style fixups]
[apw@shadowen.org: vmemmap x86_64: ensure end of section memmap is initialised]
Signed-off-by: Christoph Lameter <clameter@sgi.com>
Signed-off-by: Andy Whitcroft <apw@shadowen.org>
Acked-by: Mel Gorman <mel@csn.ul.ie>
Cc: Andi Kleen <ak@suse.de>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

2 files changed, 46 insertions, 0 deletions

diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index 458893b376f8..7d4fc633a9c9 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -748,3 +748,48 @@ const char *arch_vma_name(struct vm_area_struct *vma)
                 return "[vsyscall]";
         return NULL;
 }
+
+#ifdef CONFIG_SPARSEMEM_VMEMMAP
+/*
+ * Initialise the sparsemem vmemmap using huge-pages at the PMD level.
+ */
+int __meminit vmemmap_populate(struct page *start_page,
+                                                unsigned long size, int node)
+{
+        unsigned long addr = (unsigned long)start_page;
+        unsigned long end = (unsigned long)(start_page + size);
+        unsigned long next;
+        pgd_t *pgd;
+        pud_t *pud;
+        pmd_t *pmd;
+
+        for (; addr < end; addr = next) {
+                next = pmd_addr_end(addr, end);
+
+                pgd = vmemmap_pgd_populate(addr, node);
+                if (!pgd)
+                        return -ENOMEM;
+                pud = vmemmap_pud_populate(pgd, addr, node);
+                if (!pud)
+                        return -ENOMEM;
+
+                pmd = pmd_offset(pud, addr);
+                if (pmd_none(*pmd)) {
+                        pte_t entry;
+                        void *p = vmemmap_alloc_block(PMD_SIZE, node);
+                        if (!p)
+                                return -ENOMEM;
+
+                        entry = pfn_pte(__pa(p) >> PAGE_SHIFT, PAGE_KERNEL);
+                        mk_pte_huge(entry);
+                        set_pmd(pmd, __pmd(pte_val(entry)));
+
+                        printk(KERN_DEBUG " [%lx-%lx] PMD ->%p on node %d\n",
+                                addr, addr + PMD_SIZE - 1, p, node);
+                } else
+                        vmemmap_verify((pte_t *)pmd, node, addr, next);
+        }
+
+        return 0;
+}
+#endif
diff --git a/arch/x86_64/Kconfig b/arch/x86_64/Kconfig
index cf013cb85ea4..8c83dbe4c4d0 100644
--- a/arch/x86_64/Kconfig
+++ b/arch/x86_64/Kconfig
@@ -409,6 +409,7 @@ config ARCH_DISCONTIGMEM_DEFAULT
 config ARCH_SPARSEMEM_ENABLE
         def_bool y
         depends on (NUMA || EXPERIMENTAL)
+        select SPARSEMEM_VMEMMAP_ENABLE
 
 config ARCH_MEMORY_PROBE
         def_bool y