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: NChristoph Lameter <clameter@sgi.com>
Signed-off-by: NAndy Whitcroft <apw@shadowen.org>
Acked-by: NMel Gorman <mel@csn.ul.ie>
Cc: Andi Kleen <ak@suse.de>
Cc: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

Documentation/x86_64/mm.txt

@@ -9,6 +9,7 @@ ffff800000000000 - ffff80ffffffffff (=40 bits) guard hole
 ffff810000000000 - ffffc0ffffffffff (=46 bits) direct mapping of all phys. memory
 ffffc10000000000 - ffffc1ffffffffff (=40 bits) hole
 ffffc20000000000 - ffffe1ffffffffff (=45 bits) vmalloc/ioremap space
+ffffe20000000000 - ffffe2ffffffffff (=40 bits) virtual memory map (1TB)
 ... unused hole ...
 ffffffff80000000 - ffffffff82800000 (=40 MB)   kernel text mapping, from phys 0
 ... unused hole ...

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

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

include/asm-x86/page_64.h

@@ -134,6 +134,7 @@ extern unsigned long __phys_addr(unsigned long);
 	 VM_READ | VM_WRITE | VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC)
 
 #define __HAVE_ARCH_GATE_AREA 1	
+#define vmemmap ((struct page *)VMEMMAP_START)
 
 #include <asm-generic/memory_model.h>
 #include <asm-generic/page.h>

include/asm-x86/pgtable_64.h

@@ -137,6 +137,7 @@ static inline pte_t ptep_get_and_clear_full(struct mm_struct *mm, unsigned long
 #define MAXMEM		 _AC(0x3fffffffffff, UL)
 #define VMALLOC_START    _AC(0xffffc20000000000, UL)
 #define VMALLOC_END      _AC(0xffffe1ffffffffff, UL)
+#define VMEMMAP_START	 _AC(0xffffe20000000000, UL)
 #define MODULES_VADDR    _AC(0xffffffff88000000, UL)
 #define MODULES_END      _AC(0xfffffffffff00000, UL)
 #define MODULES_LEN   (MODULES_END - MODULES_VADDR)