x86_64: move mm

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Ingo Molnar <mingo@elte.hu>

11 files changed, 3315 insertions, 1 deletions

diff --git a/arch/x86/mm/Makefile b/arch/x86/mm/Makefile
index 7317648e658..98329109684 100644
--- a/arch/x86/mm/Makefile
+++ b/arch/x86/mm/Makefile
@@ -1,5 +1,5 @@
 ifeq ($(CONFIG_X86_32),y)
 include ${srctree}/arch/x86/mm/Makefile_32
 else
-include ${srctree}/arch/x86_64/mm/Makefile_64
+include ${srctree}/arch/x86/mm/Makefile_64
 endif
diff --git a/arch/x86/mm/Makefile_64 b/arch/x86/mm/Makefile_64
new file mode 100644
index 00000000000..6bcb47945b8
--- /dev/null
+++ b/arch/x86/mm/Makefile_64
@@ -0,0 +1,10 @@
+#
+# Makefile for the linux x86_64-specific parts of the memory manager.
+#
+
+obj-y	 := init_64.o fault_64.o ioremap_64.o extable_64.o pageattr_64.o mmap_64.o
+obj-$(CONFIG_HUGETLB_PAGE) += hugetlbpage.o
+obj-$(CONFIG_NUMA) += numa_64.o
+obj-$(CONFIG_K8_NUMA) += k8topology_64.o
+obj-$(CONFIG_ACPI_NUMA) += srat_64.o
+
diff --git a/arch/x86/mm/extable_64.c b/arch/x86/mm/extable_64.c
new file mode 100644
index 00000000000..79ac6e7100a
--- /dev/null
+++ b/arch/x86/mm/extable_64.c
@@ -0,0 +1,34 @@
+/*
+ * linux/arch/x86_64/mm/extable.c
+ */
+
+#include <linux/module.h>
+#include <linux/spinlock.h>
+#include <linux/init.h>
+#include <asm/uaccess.h>
+
+/* Simple binary search */
+const struct exception_table_entry *
+search_extable(const struct exception_table_entry *first,
+	       const struct exception_table_entry *last,
+	       unsigned long value)
+{
+	/* Work around a B stepping K8 bug */
+	if ((value >> 32) == 0)
+		value |= 0xffffffffUL << 32; 
+
+        while (first <= last) {
+		const struct exception_table_entry *mid;
+		long diff;
+
+		mid = (last - first) / 2 + first;
+		diff = mid->insn - value;
+                if (diff == 0)
+                        return mid;
+                else if (diff < 0)
+                        first = mid+1;
+                else
+                        last = mid-1;
+        }
+        return NULL;
+}
diff --git a/arch/x86/mm/fault_64.c b/arch/x86/mm/fault_64.c
new file mode 100644
index 00000000000..54816adb8e9
--- /dev/null
+++ b/arch/x86/mm/fault_64.c
@@ -0,0 +1,636 @@
+/*
+ *  linux/arch/x86-64/mm/fault.c
+ *
+ *  Copyright (C) 1995  Linus Torvalds
+ *  Copyright (C) 2001,2002 Andi Kleen, SuSE Labs.
+ */
+
+#include <linux/signal.h>
+#include <linux/sched.h>
+#include <linux/kernel.h>
+#include <linux/errno.h>
+#include <linux/string.h>
+#include <linux/types.h>
+#include <linux/ptrace.h>
+#include <linux/mman.h>
+#include <linux/mm.h>
+#include <linux/smp.h>
+#include <linux/interrupt.h>
+#include <linux/init.h>
+#include <linux/tty.h>
+#include <linux/vt_kern.h>		/* For unblank_screen() */
+#include <linux/compiler.h>
+#include <linux/vmalloc.h>
+#include <linux/module.h>
+#include <linux/kprobes.h>
+#include <linux/uaccess.h>
+#include <linux/kdebug.h>
+
+#include <asm/system.h>
+#include <asm/pgalloc.h>
+#include <asm/smp.h>
+#include <asm/tlbflush.h>
+#include <asm/proto.h>
+#include <asm-generic/sections.h>
+
+/* Page fault error code bits */
+#define PF_PROT	(1<<0)		/* or no page found */
+#define PF_WRITE	(1<<1)
+#define PF_USER	(1<<2)
+#define PF_RSVD	(1<<3)
+#define PF_INSTR	(1<<4)
+
+static ATOMIC_NOTIFIER_HEAD(notify_page_fault_chain);
+
+/* Hook to register for page fault notifications */
+int register_page_fault_notifier(struct notifier_block *nb)
+{
+	vmalloc_sync_all();
+	return atomic_notifier_chain_register(&notify_page_fault_chain, nb);
+}
+EXPORT_SYMBOL_GPL(register_page_fault_notifier);
+
+int unregister_page_fault_notifier(struct notifier_block *nb)
+{
+	return atomic_notifier_chain_unregister(&notify_page_fault_chain, nb);
+}
+EXPORT_SYMBOL_GPL(unregister_page_fault_notifier);
+
+static inline int notify_page_fault(struct pt_regs *regs, long err)
+{
+	struct die_args args = {
+		.regs = regs,
+		.str = "page fault",
+		.err = err,
+		.trapnr = 14,
+		.signr = SIGSEGV
+	};
+	return atomic_notifier_call_chain(&notify_page_fault_chain,
+	                                  DIE_PAGE_FAULT, &args);
+}
+
+/* Sometimes the CPU reports invalid exceptions on prefetch.
+   Check that here and ignore.
+   Opcode checker based on code by Richard Brunner */
+static noinline int is_prefetch(struct pt_regs *regs, unsigned long addr,
+				unsigned long error_code)
+{ 
+	unsigned char *instr;
+	int scan_more = 1;
+	int prefetch = 0; 
+	unsigned char *max_instr;
+
+	/* If it was a exec fault ignore */
+	if (error_code & PF_INSTR)
+		return 0;
+	
+	instr = (unsigned char __user *)convert_rip_to_linear(current, regs);
+	max_instr = instr + 15;
+
+	if (user_mode(regs) && instr >= (unsigned char *)TASK_SIZE)
+		return 0;
+
+	while (scan_more && instr < max_instr) { 
+		unsigned char opcode;
+		unsigned char instr_hi;
+		unsigned char instr_lo;
+
+		if (probe_kernel_address(instr, opcode))
+			break; 
+
+		instr_hi = opcode & 0xf0; 
+		instr_lo = opcode & 0x0f; 
+		instr++;
+
+		switch (instr_hi) { 
+		case 0x20:
+		case 0x30:
+			/* Values 0x26,0x2E,0x36,0x3E are valid x86
+			   prefixes.  In long mode, the CPU will signal
+			   invalid opcode if some of these prefixes are
+			   present so we will never get here anyway */
+			scan_more = ((instr_lo & 7) == 0x6);
+			break;
+			
+		case 0x40:
+			/* In AMD64 long mode, 0x40 to 0x4F are valid REX prefixes
+			   Need to figure out under what instruction mode the
+			   instruction was issued ... */
+			/* Could check the LDT for lm, but for now it's good
+			   enough to assume that long mode only uses well known
+			   segments or kernel. */
+			scan_more = (!user_mode(regs)) || (regs->cs == __USER_CS);
+			break;
+			
+		case 0x60:
+			/* 0x64 thru 0x67 are valid prefixes in all modes. */
+			scan_more = (instr_lo & 0xC) == 0x4;
+			break;		
+		case 0xF0:
+			/* 0xF0, 0xF2, and 0xF3 are valid prefixes in all modes. */
+			scan_more = !instr_lo || (instr_lo>>1) == 1;
+			break;			
+		case 0x00:
+			/* Prefetch instruction is 0x0F0D or 0x0F18 */
+			scan_more = 0;
+			if (probe_kernel_address(instr, opcode))
+				break;
+			prefetch = (instr_lo == 0xF) &&
+				(opcode == 0x0D || opcode == 0x18);
+			break;			
+		default:
+			scan_more = 0;
+			break;
+		} 
+	}
+	return prefetch;
+}
+
+static int bad_address(void *p) 
+{ 
+	unsigned long dummy;
+	return probe_kernel_address((unsigned long *)p, dummy);
+} 
+
+void dump_pagetable(unsigned long address)
+{
+	pgd_t *pgd;
+	pud_t *pud;
+	pmd_t *pmd;
+	pte_t *pte;
+
+	pgd = (pgd_t *)read_cr3();
+
+	pgd = __va((unsigned long)pgd & PHYSICAL_PAGE_MASK); 
+	pgd += pgd_index(address);
+	if (bad_address(pgd)) goto bad;
+	printk("PGD %lx ", pgd_val(*pgd));
+	if (!pgd_present(*pgd)) goto ret; 
+
+	pud = pud_offset(pgd, address);
+	if (bad_address(pud)) goto bad;
+	printk("PUD %lx ", pud_val(*pud));
+	if (!pud_present(*pud))	goto ret;
+
+	pmd = pmd_offset(pud, address);
+	if (bad_address(pmd)) goto bad;
+	printk("PMD %lx ", pmd_val(*pmd));
+	if (!pmd_present(*pmd))	goto ret;	 
+
+	pte = pte_offset_kernel(pmd, address);
+	if (bad_address(pte)) goto bad;
+	printk("PTE %lx", pte_val(*pte)); 
+ret:
+	printk("\n");
+	return;
+bad:
+	printk("BAD\n");
+}
+
+static const char errata93_warning[] = 
+KERN_ERR "******* Your BIOS seems to not contain a fix for K8 errata #93\n"
+KERN_ERR "******* Working around it, but it may cause SEGVs or burn power.\n"
+KERN_ERR "******* Please consider a BIOS update.\n"
+KERN_ERR "******* Disabling USB legacy in the BIOS may also help.\n";
+
+/* Workaround for K8 erratum #93 & buggy BIOS.
+   BIOS SMM functions are required to use a specific workaround
+   to avoid corruption of the 64bit RIP register on C stepping K8. 
+   A lot of BIOS that didn't get tested properly miss this. 
+   The OS sees this as a page fault with the upper 32bits of RIP cleared.
+   Try to work around it here.
+   Note we only handle faults in kernel here. */
+
+static int is_errata93(struct pt_regs *regs, unsigned long address) 
+{
+	static int warned;
+	if (address != regs->rip)
+		return 0;
+	if ((address >> 32) != 0) 
+		return 0;
+	address |= 0xffffffffUL << 32;
+	if ((address >= (u64)_stext && address <= (u64)_etext) || 
+	    (address >= MODULES_VADDR && address <= MODULES_END)) { 
+		if (!warned) {
+			printk(errata93_warning); 		
+			warned = 1;
+		}
+		regs->rip = address;
+		return 1;
+	}
+	return 0;
+} 
+
+static noinline void pgtable_bad(unsigned long address, struct pt_regs *regs,
+				 unsigned long error_code)
+{
+	unsigned long flags = oops_begin();
+	struct task_struct *tsk;
+
+	printk(KERN_ALERT "%s: Corrupted page table at address %lx\n",
+	       current->comm, address);
+	dump_pagetable(address);
+	tsk = current;
+	tsk->thread.cr2 = address;
+	tsk->thread.trap_no = 14;
+	tsk->thread.error_code = error_code;
+	__die("Bad pagetable", regs, error_code);
+	oops_end(flags);
+	do_exit(SIGKILL);
+}
+
+/*
+ * Handle a fault on the vmalloc area
+ *
+ * This assumes no large pages in there.
+ */
+static int vmalloc_fault(unsigned long address)
+{
+	pgd_t *pgd, *pgd_ref;
+	pud_t *pud, *pud_ref;
+	pmd_t *pmd, *pmd_ref;
+	pte_t *pte, *pte_ref;
+
+	/* Copy kernel mappings over when needed. This can also
+	   happen within a race in page table update. In the later
+	   case just flush. */
+
+	pgd = pgd_offset(current->mm ?: &init_mm, address);
+	pgd_ref = pgd_offset_k(address);
+	if (pgd_none(*pgd_ref))
+		return -1;
+	if (pgd_none(*pgd))
+		set_pgd(pgd, *pgd_ref);
+	else
+		BUG_ON(pgd_page_vaddr(*pgd) != pgd_page_vaddr(*pgd_ref));
+
+	/* Below here mismatches are bugs because these lower tables
+	   are shared */
+
+	pud = pud_offset(pgd, address);
+	pud_ref = pud_offset(pgd_ref, address);
+	if (pud_none(*pud_ref))
+		return -1;
+	if (pud_none(*pud) || pud_page_vaddr(*pud) != pud_page_vaddr(*pud_ref))
+		BUG();
+	pmd = pmd_offset(pud, address);
+	pmd_ref = pmd_offset(pud_ref, address);
+	if (pmd_none(*pmd_ref))
+		return -1;
+	if (pmd_none(*pmd) || pmd_page(*pmd) != pmd_page(*pmd_ref))
+		BUG();
+	pte_ref = pte_offset_kernel(pmd_ref, address);
+	if (!pte_present(*pte_ref))
+		return -1;
+	pte = pte_offset_kernel(pmd, address);
+	/* Don't use pte_page here, because the mappings can point
+	   outside mem_map, and the NUMA hash lookup cannot handle
+	   that. */
+	if (!pte_present(*pte) || pte_pfn(*pte) != pte_pfn(*pte_ref))
+		BUG();
+	return 0;
+}
+
+static int page_fault_trace;
+int show_unhandled_signals = 1;
+
+/*
+ * This routine handles page faults.  It determines the address,
+ * and the problem, and then passes it off to one of the appropriate
+ * routines.
+ */
+asmlinkage void __kprobes do_page_fault(struct pt_regs *regs,
+					unsigned long error_code)
+{
+	struct task_struct *tsk;
+	struct mm_struct *mm;
+	struct vm_area_struct * vma;
+	unsigned long address;
+	const struct exception_table_entry *fixup;
+	int write, fault;
+	unsigned long flags;
+	siginfo_t info;
+
+	tsk = current;
+	mm = tsk->mm;
+	prefetchw(&mm->mmap_sem);
+
+	/* get the address */
+	address = read_cr2();
+
+	info.si_code = SEGV_MAPERR;
+
+
+	/*
+	 * We fault-in kernel-space virtual memory on-demand. The
+	 * 'reference' page table is init_mm.pgd.
+	 *
+	 * NOTE! We MUST NOT take any locks for this case. We may
+	 * be in an interrupt or a critical region, and should
+	 * only copy the information from the master page table,
+	 * nothing more.
+	 *
+	 * This verifies that the fault happens in kernel space
+	 * (error_code & 4) == 0, and that the fault was not a
+	 * protection error (error_code & 9) == 0.
+	 */
+	if (unlikely(address >= TASK_SIZE64)) {
+		/*
+		 * Don't check for the module range here: its PML4
+		 * is always initialized because it's shared with the main
+		 * kernel text. Only vmalloc may need PML4 syncups.
+		 */
+		if (!(error_code & (PF_RSVD|PF_USER|PF_PROT)) &&
+		      ((address >= VMALLOC_START && address < VMALLOC_END))) {
+			if (vmalloc_fault(address) >= 0)
+				return;
+		}
+		if (notify_page_fault(regs, error_code) == NOTIFY_STOP)
+			return;
+		/*
+		 * Don't take the mm semaphore here. If we fixup a prefetch
+		 * fault we could otherwise deadlock.
+		 */
+		goto bad_area_nosemaphore;
+	}
+
+	if (notify_page_fault(regs, error_code) == NOTIFY_STOP)
+		return;
+
+	if (likely(regs->eflags & X86_EFLAGS_IF))
+		local_irq_enable();
+
+	if (unlikely(page_fault_trace))
+		printk("pagefault rip:%lx rsp:%lx cs:%lu ss:%lu address %lx error %lx\n",
+		       regs->rip,regs->rsp,regs->cs,regs->ss,address,error_code); 
+
+	if (unlikely(error_code & PF_RSVD))
+		pgtable_bad(address, regs, error_code);
+
+	/*
+	 * If we're in an interrupt or have no user
+	 * context, we must not take the fault..
+	 */
+	if (unlikely(in_atomic() || !mm))
+		goto bad_area_nosemaphore;
+
+	/*
+	 * User-mode registers count as a user access even for any
+	 * potential system fault or CPU buglet.
+	 */
+	if (user_mode_vm(regs))
+		error_code |= PF_USER;
+
+ again:
+	/* When running in the kernel we expect faults to occur only to
+	 * addresses in user space.  All other faults represent errors in the
+	 * kernel and should generate an OOPS.  Unfortunatly, in the case of an
+	 * erroneous fault occurring in a code path which already holds mmap_sem
+	 * we will deadlock attempting to validate the fault against the
+	 * address space.  Luckily the kernel only validly references user
+	 * space from well defined areas of code, which are listed in the
+	 * exceptions table.
+	 *
+	 * As the vast majority of faults will be valid we will only perform
+	 * the source reference check when there is a possibilty of a deadlock.
+	 * Attempt to lock the address space, if we cannot we then validate the
+	 * source.  If this is invalid we can skip the address space check,
+	 * thus avoiding the deadlock.
+	 */
+	if (!down_read_trylock(&mm->mmap_sem)) {
+		if ((error_code & PF_USER) == 0 &&
+		    !search_exception_tables(regs->rip))
+			goto bad_area_nosemaphore;
+		down_read(&mm->mmap_sem);
+	}
+
+	vma = find_vma(mm, address);
+	if (!vma)
+		goto bad_area;
+	if (likely(vma->vm_start <= address))
+		goto good_area;
+	if (!(vma->vm_flags & VM_GROWSDOWN))
+		goto bad_area;
+	if (error_code & 4) {
+		/* Allow userspace just enough access below the stack pointer
+		 * to let the 'enter' instruction work.
+		 */
+		if (address + 65536 + 32 * sizeof(unsigned long) < regs->rsp)
+			goto bad_area;
+	}
+	if (expand_stack(vma, address))
+		goto bad_area;
+/*
+ * Ok, we have a good vm_area for this memory access, so
+ * we can handle it..
+ */
+good_area:
+	info.si_code = SEGV_ACCERR;
+	write = 0;
+	switch (error_code & (PF_PROT|PF_WRITE)) {
+		default:	/* 3: write, present */
+			/* fall through */
+		case PF_WRITE:		/* write, not present */
+			if (!(vma->vm_flags & VM_WRITE))
+				goto bad_area;
+			write++;
+			break;
+		case PF_PROT:		/* read, present */
+			goto bad_area;
+		case 0:			/* read, not present */
+			if (!(vma->vm_flags & (VM_READ | VM_EXEC | VM_WRITE)))
+				goto bad_area;
+	}
+
+	/*
+	 * If for any reason at all we couldn't handle the fault,
+	 * make sure we exit gracefully rather than endlessly redo
+	 * the fault.
+	 */
+	fault = handle_mm_fault(mm, vma, address, write);
+	if (unlikely(fault & VM_FAULT_ERROR)) {
+		if (fault & VM_FAULT_OOM)
+			goto out_of_memory;
+		else if (fault & VM_FAULT_SIGBUS)
+			goto do_sigbus;
+		BUG();
+	}
+	if (fault & VM_FAULT_MAJOR)
+		tsk->maj_flt++;
+	else
+		tsk->min_flt++;
+	up_read(&mm->mmap_sem);
+	return;
+
+/*
+ * Something tried to access memory that isn't in our memory map..
+ * Fix it, but check if it's kernel or user first..
+ */
+bad_area:
+	up_read(&mm->mmap_sem);
+
+bad_area_nosemaphore:
+	/* User mode accesses just cause a SIGSEGV */
+	if (error_code & PF_USER) {
+
+		/*
+		 * It's possible to have interrupts off here.
+		 */
+		local_irq_enable();
+
+		if (is_prefetch(regs, address, error_code))
+			return;
+
+		/* Work around K8 erratum #100 K8 in compat mode
+		   occasionally jumps to illegal addresses >4GB.  We
+		   catch this here in the page fault handler because
+		   these addresses are not reachable. Just detect this
+		   case and return.  Any code segment in LDT is
+		   compatibility mode. */
+		if ((regs->cs == __USER32_CS || (regs->cs & (1<<2))) &&
+		    (address >> 32))
+			return;
+
+		if (show_unhandled_signals && unhandled_signal(tsk, SIGSEGV) &&
+		    printk_ratelimit()) {
+			printk(
+		       "%s%s[%d]: segfault at %016lx rip %016lx rsp %016lx error %lx\n",
+					tsk->pid > 1 ? KERN_INFO : KERN_EMERG,
+					tsk->comm, tsk->pid, address, regs->rip,
+					regs->rsp, error_code);
+		}
+       
+		tsk->thread.cr2 = address;
+		/* Kernel addresses are always protection faults */
+		tsk->thread.error_code = error_code | (address >= TASK_SIZE);
+		tsk->thread.trap_no = 14;
+		info.si_signo = SIGSEGV;
+		info.si_errno = 0;
+		/* info.si_code has been set above */
+		info.si_addr = (void __user *)address;
+		force_sig_info(SIGSEGV, &info, tsk);
+		return;
+	}
+
+no_context:
+	
+	/* Are we prepared to handle this kernel fault?  */
+	fixup = search_exception_tables(regs->rip);
+	if (fixup) {
+		regs->rip = fixup->fixup;
+		return;
+	}
+
+	/* 
+	 * Hall of shame of CPU/BIOS bugs.
+	 */
+
+ 	if (is_prefetch(regs, address, error_code))
+ 		return;
+
+	if (is_errata93(regs, address))
+		return; 
+
+/*
+ * Oops. The kernel tried to access some bad page. We'll have to
+ * terminate things with extreme prejudice.
+ */
+
+	flags = oops_begin();
+
+	if (address < PAGE_SIZE)
+		printk(KERN_ALERT "Unable to handle kernel NULL pointer dereference");
+	else
+		printk(KERN_ALERT "Unable to handle kernel paging request");
+	printk(" at %016lx RIP: \n" KERN_ALERT,address);
+	printk_address(regs->rip);
+	dump_pagetable(address);
+	tsk->thread.cr2 = address;
+	tsk->thread.trap_no = 14;
+	tsk->thread.error_code = error_code;
+	__die("Oops", regs, error_code);
+	/* Executive summary in case the body of the oops scrolled away */
+	printk(KERN_EMERG "CR2: %016lx\n", address);
+	oops_end(flags);
+	do_exit(SIGKILL);
+
+/*
+ * We ran out of memory, or some other thing happened to us that made
+ * us unable to handle the page fault gracefully.
+ */
+out_of_memory:
+	up_read(&mm->mmap_sem);
+	if (is_init(current)) {
+		yield();
+		goto again;
+	}
+	printk("VM: killing process %s\n", tsk->comm);
+	if (error_code & 4)
+		do_group_exit(SIGKILL);
+	goto no_context;
+
+do_sigbus:
+	up_read(&mm->mmap_sem);
+
+	/* Kernel mode? Handle exceptions or die */
+	if (!(error_code & PF_USER))
+		goto no_context;
+
+	tsk->thread.cr2 = address;
+	tsk->thread.error_code = error_code;
+	tsk->thread.trap_no = 14;
+	info.si_signo = SIGBUS;
+	info.si_errno = 0;
+	info.si_code = BUS_ADRERR;
+	info.si_addr = (void __user *)address;
+	force_sig_info(SIGBUS, &info, tsk);
+	return;
+}
+
+DEFINE_SPINLOCK(pgd_lock);
+LIST_HEAD(pgd_list);
+
+void vmalloc_sync_all(void)
+{
+	/* Note that races in the updates of insync and start aren't 
+	   problematic:
+	   insync can only get set bits added, and updates to start are only
+	   improving performance (without affecting correctness if undone). */
+	static DECLARE_BITMAP(insync, PTRS_PER_PGD);
+	static unsigned long start = VMALLOC_START & PGDIR_MASK;
+	unsigned long address;
+
+	for (address = start; address <= VMALLOC_END; address += PGDIR_SIZE) {
+		if (!test_bit(pgd_index(address), insync)) {
+			const pgd_t *pgd_ref = pgd_offset_k(address);
+			struct page *page;
+
+			if (pgd_none(*pgd_ref))
+				continue;
+			spin_lock(&pgd_lock);
+			list_for_each_entry(page, &pgd_list, lru) {
+				pgd_t *pgd;
+				pgd = (pgd_t *)page_address(page) + pgd_index(address);
+				if (pgd_none(*pgd))
+					set_pgd(pgd, *pgd_ref);
+				else
+					BUG_ON(pgd_page_vaddr(*pgd) != pgd_page_vaddr(*pgd_ref));
+			}
+			spin_unlock(&pgd_lock);
+			set_bit(pgd_index(address), insync);
+		}
+		if (address == start)
+			start = address + PGDIR_SIZE;
+	}
+	/* Check that there is no need to do the same for the modules area. */
+	BUILD_BUG_ON(!(MODULES_VADDR > __START_KERNEL));
+	BUILD_BUG_ON(!(((MODULES_END - 1) & PGDIR_MASK) == 
+				(__START_KERNEL & PGDIR_MASK)));
+}
+
+static int __init enable_pagefaulttrace(char *str)
+{
+	page_fault_trace = 1;
+	return 1;
+}
+__setup("pagefaulttrace", enable_pagefaulttrace);
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
new file mode 100644
index 00000000000..458893b376f
--- /dev/null
+++ b/arch/x86/mm/init_64.c
@@ -0,0 +1,750 @@
+/*
+ *  linux/arch/x86_64/mm/init.c
+ *
+ *  Copyright (C) 1995  Linus Torvalds
+ *  Copyright (C) 2000  Pavel Machek <pavel@suse.cz>
+ *  Copyright (C) 2002,2003 Andi Kleen <ak@suse.de>
+ */
+
+#include <linux/signal.h>
+#include <linux/sched.h>
+#include <linux/kernel.h>
+#include <linux/errno.h>
+#include <linux/string.h>
+#include <linux/types.h>
+#include <linux/ptrace.h>
+#include <linux/mman.h>
+#include <linux/mm.h>
+#include <linux/swap.h>
+#include <linux/smp.h>
+#include <linux/init.h>
+#include <linux/pagemap.h>
+#include <linux/bootmem.h>
+#include <linux/proc_fs.h>
+#include <linux/pci.h>
+#include <linux/pfn.h>
+#include <linux/poison.h>
+#include <linux/dma-mapping.h>
+#include <linux/module.h>
+#include <linux/memory_hotplug.h>
+#include <linux/nmi.h>
+
+#include <asm/processor.h>
+#include <asm/system.h>
+#include <asm/uaccess.h>
+#include <asm/pgtable.h>
+#include <asm/pgalloc.h>
+#include <asm/dma.h>
+#include <asm/fixmap.h>
+#include <asm/e820.h>
+#include <asm/apic.h>
+#include <asm/tlb.h>
+#include <asm/mmu_context.h>
+#include <asm/proto.h>
+#include <asm/smp.h>
+#include <asm/sections.h>
+
+#ifndef Dprintk
+#define Dprintk(x...)
+#endif
+
+const struct dma_mapping_ops* dma_ops;
+EXPORT_SYMBOL(dma_ops);
+
+static unsigned long dma_reserve __initdata;
+
+DEFINE_PER_CPU(struct mmu_gather, mmu_gathers);
+
+/*
+ * NOTE: pagetable_init alloc all the fixmap pagetables contiguous on the
+ * physical space so we can cache the place of the first one and move
+ * around without checking the pgd every time.
+ */
+
+void show_mem(void)
+{
+	long i, total = 0, reserved = 0;
+	long shared = 0, cached = 0;
+	pg_data_t *pgdat;
+	struct page *page;
+
+	printk(KERN_INFO "Mem-info:\n");
+	show_free_areas();
+	printk(KERN_INFO "Free swap:       %6ldkB\n", nr_swap_pages<<(PAGE_SHIFT-10));
+
+	for_each_online_pgdat(pgdat) {
+               for (i = 0; i < pgdat->node_spanned_pages; ++i) {
+			/* this loop can take a while with 256 GB and 4k pages
+			   so update the NMI watchdog */
+			if (unlikely(i % MAX_ORDER_NR_PAGES == 0)) {
+				touch_nmi_watchdog();
+			}
+			if (!pfn_valid(pgdat->node_start_pfn + i))
+				continue;
+			page = pfn_to_page(pgdat->node_start_pfn + i);
+			total++;
+			if (PageReserved(page))
+				reserved++;
+			else if (PageSwapCache(page))
+				cached++;
+			else if (page_count(page))
+				shared += page_count(page) - 1;
+               }
+	}
+	printk(KERN_INFO "%lu pages of RAM\n", total);
+	printk(KERN_INFO "%lu reserved pages\n",reserved);
+	printk(KERN_INFO "%lu pages shared\n",shared);
+	printk(KERN_INFO "%lu pages swap cached\n",cached);
+}
+
+int after_bootmem;
+
+static __init void *spp_getpage(void)
+{ 
+	void *ptr;
+	if (after_bootmem)
+		ptr = (void *) get_zeroed_page(GFP_ATOMIC); 
+	else
+		ptr = alloc_bootmem_pages(PAGE_SIZE);
+	if (!ptr || ((unsigned long)ptr & ~PAGE_MASK))
+		panic("set_pte_phys: cannot allocate page data %s\n", after_bootmem?"after bootmem":"");
+
+	Dprintk("spp_getpage %p\n", ptr);
+	return ptr;
+} 
+
+static __init void set_pte_phys(unsigned long vaddr,
+			 unsigned long phys, pgprot_t prot)
+{
+	pgd_t *pgd;
+	pud_t *pud;
+	pmd_t *pmd;
+	pte_t *pte, new_pte;
+
+	Dprintk("set_pte_phys %lx to %lx\n", vaddr, phys);
+
+	pgd = pgd_offset_k(vaddr);
+	if (pgd_none(*pgd)) {
+		printk("PGD FIXMAP MISSING, it should be setup in head.S!\n");
+		return;
+	}
+	pud = pud_offset(pgd, vaddr);
+	if (pud_none(*pud)) {
+		pmd = (pmd_t *) spp_getpage(); 
+		set_pud(pud, __pud(__pa(pmd) | _KERNPG_TABLE | _PAGE_USER));
+		if (pmd != pmd_offset(pud, 0)) {
+			printk("PAGETABLE BUG #01! %p <-> %p\n", pmd, pmd_offset(pud,0));
+			return;
+		}
+	}
+	pmd = pmd_offset(pud, vaddr);
+	if (pmd_none(*pmd)) {
+		pte = (pte_t *) spp_getpage();
+		set_pmd(pmd, __pmd(__pa(pte) | _KERNPG_TABLE | _PAGE_USER));
+		if (pte != pte_offset_kernel(pmd, 0)) {
+			printk("PAGETABLE BUG #02!\n");
+			return;
+		}
+	}
+	new_pte = pfn_pte(phys >> PAGE_SHIFT, prot);
+
+	pte = pte_offset_kernel(pmd, vaddr);
+	if (!pte_none(*pte) &&
+	    pte_val(*pte) != (pte_val(new_pte) & __supported_pte_mask))
+		pte_ERROR(*pte);
+	set_pte(pte, new_pte);
+
+	/*
+	 * It's enough to flush this one mapping.
+	 * (PGE mappings get flushed as well)
+	 */
+	__flush_tlb_one(vaddr);
+}
+
+/* NOTE: this is meant to be run only at boot */
+void __init 
+__set_fixmap (enum fixed_addresses idx, unsigned long phys, pgprot_t prot)
+{
+	unsigned long address = __fix_to_virt(idx);
+
+	if (idx >= __end_of_fixed_addresses) {
+		printk("Invalid __set_fixmap\n");
+		return;
+	}
+	set_pte_phys(address, phys, prot);
+}
+
+unsigned long __meminitdata table_start, table_end;
+
+static __meminit void *alloc_low_page(unsigned long *phys)
+{ 
+	unsigned long pfn = table_end++;
+	void *adr;
+
+	if (after_bootmem) {
+		adr = (void *)get_zeroed_page(GFP_ATOMIC);
+		*phys = __pa(adr);
+		return adr;
+	}
+
+	if (pfn >= end_pfn) 
+		panic("alloc_low_page: ran out of memory"); 
+
+	adr = early_ioremap(pfn * PAGE_SIZE, PAGE_SIZE);
+	memset(adr, 0, PAGE_SIZE);
+	*phys  = pfn * PAGE_SIZE;
+	return adr;
+}
+
+static __meminit void unmap_low_page(void *adr)
+{ 
+
+	if (after_bootmem)
+		return;
+
+	early_iounmap(adr, PAGE_SIZE);
+} 
+
+/* Must run before zap_low_mappings */
+__meminit void *early_ioremap(unsigned long addr, unsigned long size)
+{
+	unsigned long vaddr;
+	pmd_t *pmd, *last_pmd;
+	int i, pmds;
+
+	pmds = ((addr & ~PMD_MASK) + size + ~PMD_MASK) / PMD_SIZE;
+	vaddr = __START_KERNEL_map;
+	pmd = level2_kernel_pgt;
+	last_pmd = level2_kernel_pgt + PTRS_PER_PMD - 1;
+	for (; pmd <= last_pmd; pmd++, vaddr += PMD_SIZE) {
+		for (i = 0; i < pmds; i++) {
+			if (pmd_present(pmd[i]))
+				goto next;
+		}
+		vaddr += addr & ~PMD_MASK;
+		addr &= PMD_MASK;
+		for (i = 0; i < pmds; i++, addr += PMD_SIZE)
+			set_pmd(pmd + i,__pmd(addr | _KERNPG_TABLE | _PAGE_PSE));
+		__flush_tlb();
+		return (void *)vaddr;
+	next:
+		;
+	}
+	printk("early_ioremap(0x%lx, %lu) failed\n", addr, size);
+	return NULL;
+}
+
+/* To avoid virtual aliases later */
+__meminit void early_iounmap(void *addr, unsigned long size)
+{
+	unsigned long vaddr;
+	pmd_t *pmd;
+	int i, pmds;
+
+	vaddr = (unsigned long)addr;
+	pmds = ((vaddr & ~PMD_MASK) + size + ~PMD_MASK) / PMD_SIZE;
+	pmd = level2_kernel_pgt + pmd_index(vaddr);
+	for (i = 0; i < pmds; i++)
+		pmd_clear(pmd + i);
+	__flush_tlb();
+}
+
+static void __meminit
+phys_pmd_init(pmd_t *pmd_page, unsigned long address, unsigned long end)
+{
+	int i = pmd_index(address);
+
+	for (; i < PTRS_PER_PMD; i++, address += PMD_SIZE) {
+		unsigned long entry;
+		pmd_t *pmd = pmd_page + pmd_index(address);
+
+		if (address >= end) {
+			if (!after_bootmem)
+				for (; i < PTRS_PER_PMD; i++, pmd++)
+					set_pmd(pmd, __pmd(0));
+			break;
+		}
+
+		if (pmd_val(*pmd))
+			continue;
+
+		entry = _PAGE_NX|_PAGE_PSE|_KERNPG_TABLE|_PAGE_GLOBAL|address;
+		entry &= __supported_pte_mask;
+		set_pmd(pmd, __pmd(entry));
+	}
+}
+
+static void __meminit
+phys_pmd_update(pud_t *pud, unsigned long address, unsigned long end)
+{
+	pmd_t *pmd = pmd_offset(pud,0);
+	spin_lock(&init_mm.page_table_lock);
+	phys_pmd_init(pmd, address, end);
+	spin_unlock(&init_mm.page_table_lock);
+	__flush_tlb_all();
+}
+
+static void __meminit phys_pud_init(pud_t *pud_page, unsigned long addr, unsigned long end)
+{ 
+	int i = pud_index(addr);
+
+
+	for (; i < PTRS_PER_PUD; i++, addr = (addr & PUD_MASK) + PUD_SIZE ) {
+		unsigned long pmd_phys;
+		pud_t *pud = pud_page + pud_index(addr);
+		pmd_t *pmd;
+
+		if (addr >= end)
+			break;
+
+		if (!after_bootmem && !e820_any_mapped(addr,addr+PUD_SIZE,0)) {
+			set_pud(pud, __pud(0)); 
+			continue;
+		} 
+
+		if (pud_val(*pud)) {
+			phys_pmd_update(pud, addr, end);
+			continue;
+		}
+
+		pmd = alloc_low_page(&pmd_phys);
+		spin_lock(&init_mm.page_table_lock);
+		set_pud(pud, __pud(pmd_phys | _KERNPG_TABLE));
+		phys_pmd_init(pmd, addr, end);
+		spin_unlock(&init_mm.page_table_lock);
+		unmap_low_page(pmd);
+	}
+	__flush_tlb();
+} 
+
+static void __init find_early_table_space(unsigned long end)
+{
+	unsigned long puds, pmds, tables, start;
+
+	puds = (end + PUD_SIZE - 1) >> PUD_SHIFT;
+	pmds = (end + PMD_SIZE - 1) >> PMD_SHIFT;
+	tables = round_up(puds * sizeof(pud_t), PAGE_SIZE) +
+		 round_up(pmds * sizeof(pmd_t), PAGE_SIZE);
+
+ 	/* RED-PEN putting page tables only on node 0 could
+ 	   cause a hotspot and fill up ZONE_DMA. The page tables
+ 	   need roughly 0.5KB per GB. */
+ 	start = 0x8000;
+ 	table_start = find_e820_area(start, end, tables);
+	if (table_start == -1UL)
+		panic("Cannot find space for the kernel page tables");
+
+	table_start >>= PAGE_SHIFT;
+	table_end = table_start;
+
+	early_printk("kernel direct mapping tables up to %lx @ %lx-%lx\n",
+		end, table_start << PAGE_SHIFT,
+		(table_start << PAGE_SHIFT) + tables);
+}
+
+/* Setup the direct mapping of the physical memory at PAGE_OFFSET.
+   This runs before bootmem is initialized and gets pages directly from the 
+   physical memory. To access them they are temporarily mapped. */
+void __meminit init_memory_mapping(unsigned long start, unsigned long end)
+{ 
+	unsigned long next; 
+
+	Dprintk("init_memory_mapping\n");
+
+	/* 
+	 * Find space for the kernel direct mapping tables.
+	 * Later we should allocate these tables in the local node of the memory
+	 * mapped.  Unfortunately this is done currently before the nodes are 
+	 * discovered.
+	 */
+	if (!after_bootmem)
+		find_early_table_space(end);
+