Merge branch 'master' of /home/davem/src/GIT/linux-2.6/

18 files changed, 1690 insertions, 881 deletions

diff --git a/arch/x86/mm/Makefile b/arch/x86/mm/Makefile
index d8cc96a2738f..08537747cb58 100644
--- a/arch/x86/mm/Makefile
+++ b/arch/x86/mm/Makefile
@@ -1,6 +1,8 @@
-obj-y	:=  init_$(BITS).o fault.o ioremap.o extable.o pageattr.o mmap.o \
+obj-y	:=  init.o init_$(BITS).o fault.o ioremap.o extable.o pageattr.o mmap.o \
 	    pat.o pgtable.o gup.o
 
+obj-$(CONFIG_SMP)		+= tlb.o
+
 obj-$(CONFIG_X86_32)		+= pgtable_32.o iomap_32.o
 
 obj-$(CONFIG_HUGETLB_PAGE)	+= hugetlbpage.o
diff --git a/arch/x86/mm/extable.c b/arch/x86/mm/extable.c
index 7e8db53528a7..61b41ca3b5a2 100644
--- a/arch/x86/mm/extable.c
+++ b/arch/x86/mm/extable.c
@@ -23,6 +23,12 @@ int fixup_exception(struct pt_regs *regs)
 
 	fixup = search_exception_tables(regs->ip);
 	if (fixup) {
+		/* If fixup is less than 16, it means uaccess error */
+		if (fixup->fixup < 16) {
+			current_thread_info()->uaccess_err = -EFAULT;
+			regs->ip += fixup->fixup;
+			return 1;
+		}
 		regs->ip = fixup->fixup;
 		return 1;
 	}
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index c76ef1d701c9..a03b7279efa0 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -1,73 +1,79 @@
 /*
  *  Copyright (C) 1995  Linus Torvalds
- *  Copyright (C) 2001,2002 Andi Kleen, SuSE Labs.
+ *  Copyright (C) 2001, 2002 Andi Kleen, SuSE Labs.
+ *  Copyright (C) 2008-2009, Red Hat Inc., Ingo Molnar
  */
-
-#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/mmiotrace.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/mmiotrace.h>
+#include <linux/bootmem.h>
 #include <linux/compiler.h>
 #include <linux/highmem.h>
-#include <linux/bootmem.h>		/* for max_low_pfn */
-#include <linux/vmalloc.h>
-#include <linux/module.h>
 #include <linux/kprobes.h>
 #include <linux/uaccess.h>
+#include <linux/vmalloc.h>
+#include <linux/vt_kern.h>
+#include <linux/signal.h>
+#include <linux/kernel.h>
+#include <linux/ptrace.h>
+#include <linux/string.h>
+#include <linux/module.h>
 #include <linux/kdebug.h>
+#include <linux/errno.h>
+#include <linux/magic.h>
+#include <linux/sched.h>
+#include <linux/types.h>
+#include <linux/init.h>
+#include <linux/mman.h>
+#include <linux/tty.h>
+#include <linux/smp.h>
+#include <linux/mm.h>
+
+#include <asm-generic/sections.h>
 
-#include <asm/system.h>
-#include <asm/desc.h>
-#include <asm/segment.h>
-#include <asm/pgalloc.h>
-#include <asm/smp.h>
 #include <asm/tlbflush.h>
+#include <asm/pgalloc.h>
+#include <asm/segment.h>
+#include <asm/system.h>
 #include <asm/proto.h>
-#include <asm-generic/sections.h>
 #include <asm/traps.h>
+#include <asm/desc.h>
 
 /*
- * Page fault error code bits
- *	bit 0 == 0 means no page found, 1 means protection fault
- *	bit 1 == 0 means read, 1 means write
- *	bit 2 == 0 means kernel, 1 means user-mode
- *	bit 3 == 1 means use of reserved bit detected
- *	bit 4 == 1 means fault was an instruction fetch
+ * Page fault error code bits:
+ *
+ *   bit 0 ==	 0: no page found	1: protection fault
+ *   bit 1 ==	 0: read access		1: write access
+ *   bit 2 ==	 0: kernel-mode access	1: user-mode access
+ *   bit 3 ==				1: use of reserved bit detected
+ *   bit 4 ==				1: fault was an instruction fetch
  */
-#define PF_PROT		(1<<0)
-#define PF_WRITE	(1<<1)
-#define PF_USER		(1<<2)
-#define PF_RSVD		(1<<3)
-#define PF_INSTR	(1<<4)
+enum x86_pf_error_code {
+
+	PF_PROT		=		1 << 0,
+	PF_WRITE	=		1 << 1,
+	PF_USER		=		1 << 2,
+	PF_RSVD		=		1 << 3,
+	PF_INSTR	=		1 << 4,
+};
 
+/*
+ * Returns 0 if mmiotrace is disabled, or if the fault is not
+ * handled by mmiotrace:
+ */
 static inline int kmmio_fault(struct pt_regs *regs, unsigned long addr)
 {
-#ifdef CONFIG_MMIOTRACE
 	if (unlikely(is_kmmio_active()))
 		if (kmmio_handler(regs, addr) == 1)
 			return -1;
-#endif
 	return 0;
 }
 
 static inline int notify_page_fault(struct pt_regs *regs)
 {
-#ifdef CONFIG_KPROBES
 	int ret = 0;
 
 	/* kprobe_running() needs smp_processor_id() */
-	if (!user_mode_vm(regs)) {
+	if (kprobes_built_in() && !user_mode_vm(regs)) {
 		preempt_disable();
 		if (kprobe_running() && kprobe_fault_handler(regs, 14))
 			ret = 1;
@@ -75,29 +81,76 @@ static inline int notify_page_fault(struct pt_regs *regs)
 	}
 
 	return ret;
-#else
-	return 0;
-#endif
 }
 
 /*
- * X86_32
- * Sometimes AMD Athlon/Opteron CPUs report invalid exceptions on prefetch.
- * Check that here and ignore it.
+ * Prefetch quirks:
+ *
+ * 32-bit mode:
+ *
+ *   Sometimes AMD Athlon/Opteron CPUs report invalid exceptions on prefetch.
+ *   Check that here and ignore it.
+ *
+ * 64-bit mode:
  *
- * X86_64
- * Sometimes the CPU reports invalid exceptions on prefetch.
- * Check that here and ignore it.
+ *   Sometimes the CPU reports invalid exceptions on prefetch.
+ *   Check that here and ignore it.
  *
- * Opcode checker based on code by Richard Brunner
+ * Opcode checker based on code by Richard Brunner.
  */
-static int is_prefetch(struct pt_regs *regs, unsigned long addr,
-		       unsigned long error_code)
+static inline int
+check_prefetch_opcode(struct pt_regs *regs, unsigned char *instr,
+		      unsigned char opcode, int *prefetch)
 {
+	unsigned char instr_hi = opcode & 0xf0;
+	unsigned char instr_lo = opcode & 0x0f;
+
+	switch (instr_hi) {
+	case 0x20:
+	case 0x30:
+		/*
+		 * Values 0x26,0x2E,0x36,0x3E are valid x86 prefixes.
+		 * In X86_64 long mode, the CPU will signal invalid
+		 * opcode if some of these prefixes are present so
+		 * X86_64 will never get here anyway
+		 */
+		return ((instr_lo & 7) == 0x6);
+#ifdef CONFIG_X86_64
+	case 0x40:
+		/*
+		 * In AMD64 long mode 0x40..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.
+		 */
+		return (!user_mode(regs)) || (regs->cs == __USER_CS);
+#endif
+	case 0x60:
+		/* 0x64 thru 0x67 are valid prefixes in all modes. */
+		return (instr_lo & 0xC) == 0x4;
+	case 0xF0:
+		/* 0xF0, 0xF2, 0xF3 are valid prefixes in all modes. */
+		return !instr_lo || (instr_lo>>1) == 1;
+	case 0x00:
+		/* Prefetch instruction is 0x0F0D or 0x0F18 */
+		if (probe_kernel_address(instr, opcode))
+			return 0;
+
+		*prefetch = (instr_lo == 0xF) &&
+			(opcode == 0x0D || opcode == 0x18);
+		return 0;
+	default:
+		return 0;
+	}
+}
+
+static int
+is_prefetch(struct pt_regs *regs, unsigned long error_code, unsigned long addr)
+{
+	unsigned char *max_instr;
 	unsigned char *instr;
-	int scan_more = 1;
 	int prefetch = 0;
-	unsigned char *max_instr;
 
 	/*
 	 * If it was a exec (instruction fetch) fault on NX page, then
@@ -106,106 +159,170 @@ static int is_prefetch(struct pt_regs *regs, unsigned long addr,
 	if (error_code & PF_INSTR)
 		return 0;
 
-	instr = (unsigned char *)convert_ip_to_linear(current, regs);
+	instr = (void *)convert_ip_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) {
+	while (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 X86_64 long mode, the CPU will signal invalid
-			 * opcode if some of these prefixes are present so
-			 * X86_64 will never get here anyway
-			 */
-			scan_more = ((instr_lo & 7) == 0x6);
+		if (!check_prefetch_opcode(regs, instr, opcode, &prefetch))
 			break;
-#ifdef CONFIG_X86_64
-		case 0x40:
-			/*
-			 * In AMD64 long mode 0x40..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;
-#endif
-		case 0x60:
-			/* 0x64 thru 0x67 are valid prefixes in all modes. */
-			scan_more = (instr_lo & 0xC) == 0x4;
-			break;
-		case 0xF0:
-			/* 0xF0, 0xF2, 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 void force_sig_info_fault(int si_signo, int si_code,
-	unsigned long address, struct task_struct *tsk)
+static void
+force_sig_info_fault(int si_signo, int si_code, unsigned long address,
+		     struct task_struct *tsk)
 {
 	siginfo_t info;
 
-	info.si_signo = si_signo;
-	info.si_errno = 0;
-	info.si_code = si_code;
-	info.si_addr = (void __user *)address;
+	info.si_signo	= si_signo;
+	info.si_errno	= 0;
+	info.si_code	= si_code;
+	info.si_addr	= (void __user *)address;
+
 	force_sig_info(si_signo, &info, tsk);
 }
 
-#ifdef CONFIG_X86_64
-static int bad_address(void *p)
+DEFINE_SPINLOCK(pgd_lock);
+LIST_HEAD(pgd_list);
+
+#ifdef CONFIG_X86_32
+static inline pmd_t *vmalloc_sync_one(pgd_t *pgd, unsigned long address)
 {
-	unsigned long dummy;
-	return probe_kernel_address((unsigned long *)p, dummy);
+	unsigned index = pgd_index(address);
+	pgd_t *pgd_k;
+	pud_t *pud, *pud_k;
+	pmd_t *pmd, *pmd_k;
+
+	pgd += index;
+	pgd_k = init_mm.pgd + index;
+
+	if (!pgd_present(*pgd_k))
+		return NULL;
+
+	/*
+	 * set_pgd(pgd, *pgd_k); here would be useless on PAE
+	 * and redundant with the set_pmd() on non-PAE. As would
+	 * set_pud.
+	 */
+	pud = pud_offset(pgd, address);
+	pud_k = pud_offset(pgd_k, address);
+	if (!pud_present(*pud_k))
+		return NULL;
+
+	pmd = pmd_offset(pud, address);
+	pmd_k = pmd_offset(pud_k, address);
+	if (!pmd_present(*pmd_k))
+		return NULL;
+
+	if (!pmd_present(*pmd)) {
+		set_pmd(pmd, *pmd_k);
+		arch_flush_lazy_mmu_mode();
+	} else {
+		BUG_ON(pmd_page(*pmd) != pmd_page(*pmd_k));
+	}
+
+	return pmd_k;
+}
+
+void vmalloc_sync_all(void)
+{
+	unsigned long address;
+
+	if (SHARED_KERNEL_PMD)
+		return;
+
+	for (address = VMALLOC_START & PMD_MASK;
+	     address >= TASK_SIZE && address < FIXADDR_TOP;
+	     address += PMD_SIZE) {
+
+		unsigned long flags;
+		struct page *page;
+
+		spin_lock_irqsave(&pgd_lock, flags);
+		list_for_each_entry(page, &pgd_list, lru) {
+			if (!vmalloc_sync_one(page_address(page), address))
+				break;
+		}
+		spin_unlock_irqrestore(&pgd_lock, flags);
+	}
+}
+
+/*
+ * 32-bit:
+ *
+ *   Handle a fault on the vmalloc or module mapping area
+ */
+static noinline int vmalloc_fault(unsigned long address)
+{
+	unsigned long pgd_paddr;
+	pmd_t *pmd_k;
+	pte_t *pte_k;
+
+	/* Make sure we are in vmalloc area: */
+	if (!(address >= VMALLOC_START && address < VMALLOC_END))
+		return -1;
+
+	/*
+	 * Synchronize this task's top level page-table
+	 * with the 'reference' page table.
+	 *
+	 * Do _not_ use "current" here. We might be inside
+	 * an interrupt in the middle of a task switch..
+	 */
+	pgd_paddr = read_cr3();
+	pmd_k = vmalloc_sync_one(__va(pgd_paddr), address);
+	if (!pmd_k)
+		return -1;
+
+	pte_k = pte_offset_kernel(pmd_k, address);
+	if (!pte_present(*pte_k))
+		return -1;
+
+	return 0;
+}
+
+/*
+ * Did it hit the DOS screen memory VA from vm86 mode?
+ */
+static inline void
+check_v8086_mode(struct pt_regs *regs, unsigned long address,
+		 struct task_struct *tsk)
+{
+	unsigned long bit;
+
+	if (!v8086_mode(regs))
+		return;
+
+	bit = (address - 0xA0000) >> PAGE_SHIFT;
+	if (bit < 32)
+		tsk->thread.screen_bitmap |= 1 << bit;
 }
-#endif
 
 static void dump_pagetable(unsigned long address)
 {
-#ifdef CONFIG_X86_32
 	__typeof__(pte_val(__pte(0))) page;
 
 	page = read_cr3();
 	page = ((__typeof__(page) *) __va(page))[address >> PGDIR_SHIFT];
+
 #ifdef CONFIG_X86_PAE
 	printk("*pdpt = %016Lx ", page);
 	if ((page >> PAGE_SHIFT) < max_low_pfn
 	    && page & _PAGE_PRESENT) {
 		page &= PAGE_MASK;
 		page = ((__typeof__(page) *) __va(page))[(address >> PMD_SHIFT)
-		                                         & (PTRS_PER_PMD - 1)];
+							& (PTRS_PER_PMD - 1)];
 		printk(KERN_CONT "*pde = %016Lx ", page);
 		page &= ~_PAGE_NX;
 	}
@@ -217,19 +334,145 @@ static void dump_pagetable(unsigned long address)
 	 * We must not directly access the pte in the highpte
 	 * case if the page table is located in highmem.
 	 * And let's rather not kmap-atomic the pte, just in case
-	 * it's allocated already.
+	 * it's allocated already:
 	 */
 	if ((page >> PAGE_SHIFT) < max_low_pfn
 	    && (page & _PAGE_PRESENT)
 	    && !(page & _PAGE_PSE)) {
+
 		page &= PAGE_MASK;
 		page = ((__typeof__(page) *) __va(page))[(address >> PAGE_SHIFT)
-		                                         & (PTRS_PER_PTE - 1)];
+							& (PTRS_PER_PTE - 1)];
 		printk("*pte = %0*Lx ", sizeof(page)*2, (u64)page);
 	}
 
 	printk("\n");
-#else /* CONFIG_X86_64 */
+}
+
+#else /* CONFIG_X86_64: */
+
+void vmalloc_sync_all(void)
+{
+	unsigned long address;
+
+	for (address = VMALLOC_START & PGDIR_MASK; address <= VMALLOC_END;
+	     address += PGDIR_SIZE) {
+
+		const pgd_t *pgd_ref = pgd_offset_k(address);
+		unsigned long flags;
+		struct page *page;
+
+		if (pgd_none(*pgd_ref))
+			continue;
+
+		spin_lock_irqsave(&pgd_lock, flags);
+		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_irqrestore(&pgd_lock, flags);
+	}
+}
+
+/*
+ * 64-bit:
+ *
+ *   Handle a fault on the vmalloc area
+ *
+ * This assumes no large pages in there.
+ */
+static noinline 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;
+
+	/* Make sure we are in vmalloc area: */
+	if (!(address >= VMALLOC_START && address < VMALLOC_END))
+		return -1;
+
+	/*
+	 * 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->active_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 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";
+
+/*
+ * No vm86 mode in 64-bit mode:
+ */
+static inline void
+check_v8086_mode(struct pt_regs *regs, unsigned long address,
+		 struct task_struct *tsk)
+{
+}
+
+static int bad_address(void *p)
+{
+	unsigned long dummy;
+
+	return probe_kernel_address((unsigned long *)p, dummy);
+}
+
+static void dump_pagetable(unsigned long address)
+{
 	pgd_t *pgd;
 	pud_t *pud;
 	pmd_t *pmd;
@@ -238,102 +481,77 @@ static void dump_pagetable(unsigned long address)
 	pgd = (pgd_t *)read_cr3();
 
 	pgd = __va((unsigned long)pgd & PHYSICAL_PAGE_MASK);
+
 	pgd += pgd_index(address);
-	if (bad_address(pgd)) goto bad;
+	if (bad_address(pgd))
+		goto bad;
+
 	printk("PGD %lx ", pgd_val(*pgd));
-	if (!pgd_present(*pgd)) goto ret;
+
+	if (!pgd_present(*pgd))
+		goto out;
 
 	pud = pud_offset(pgd, address);
-	if (bad_address(pud)) goto bad;
+	if (bad_address(pud))
+		goto bad;
+
 	printk("PUD %lx ", pud_val(*pud));
 	if (!pud_present(*pud) || pud_large(*pud))
-		goto ret;
+		goto out;
 
 	pmd = pmd_offset(pud, address);
-	if (bad_address(pmd)) goto bad;
+	if (bad_address(pmd))
+		goto bad;
+
 	printk("PMD %lx ", pmd_val(*pmd));
-	if (!pmd_present(*pmd) || pmd_large(*pmd)) goto ret;
+	if (!pmd_present(*pmd) || pmd_large(*pmd))
+		goto out;
 
 	pte = pte_offset_kernel(pmd, address);
-	if (bad_address(pte)) goto bad;
+	if (bad_address(pte))
+		goto bad;
+
 	printk("PTE %lx", pte_val(*pte));
-ret:
+out:
 	printk("\n");
 	return;
 bad:
 	printk("BAD\n");
-#endif
-}
-
-#ifdef CONFIG_X86_32
-static inline pmd_t *vmalloc_sync_one(pgd_t *pgd, unsigned long address)
-{
-	unsigned index = pgd_index(address);
-	pgd_t *pgd_k;
-	pud_t *pud, *pud_k;
-	pmd_t *pmd, *pmd_k;
-
-	pgd += index;
-	pgd_k = init_mm.pgd + index;
-
-	if (!pgd_present(*pgd_k))
-		return NULL;
-
-	/*
-	 * set_pgd(pgd, *pgd_k); here would be useless on PAE
-	 * and redundant with the set_pmd() on non-PAE. As would
-	 * set_pud.
-	 */
-
-	pud = pud_offset(pgd, address);
-	pud_k = pud_offset(pgd_k, address);
-	if (!pud_present(*pud_k))
-		return NULL;
-
-	pmd = pmd_offset(pud, address);
-	pmd_k = pmd_offset(pud_k, address);
-	if (!pmd_present(*pmd_k))
-		return NULL;
-	if (!pmd_present(*pmd)) {
-		set_pmd(pmd, *pmd_k);
-		arch_flush_lazy_mmu_mode();
-	} else
-		BUG_ON(pmd_page(*pmd) != pmd_page(*pmd_k));
-	return pmd_k;
 }
-#endif
 
-#ifdef CONFIG_X86_64
-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";
-#endif
+#endif /* CONFIG_X86_64 */
 
-/* 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.
-   Does nothing for X86_32
+/*
+ * 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.
+ * Does nothing on 32-bit.
  */
 static int is_errata93(struct pt_regs *regs, unsigned long address)
 {
 #ifdef CONFIG_X86_64
-	static int warned;
+	static int once;
+
 	if (address != regs->ip)
 		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) {
+		if (!once) {
 			printk(errata93_warning);
-			warned = 1;
+			once = 1;
 		}
 		regs->ip = address;
 		return 1;
@@ -343,16 +561,17 @@ static int is_errata93(struct pt_regs *regs, unsigned long address)
 }
 
 /*
- * Work around K8 erratum #100 K8 in compat mode occasionally jumps to illegal
- * addresses >4GB.  We catch this in the page fault handler because these
- * addresses are not reachable. Just detect this case and return.  Any code
+ * Work around K8 erratum #100 K8 in compat mode occasionally jumps
+ * to illegal addresses >4GB.
+ *
+ * We catch this 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.
  */
 static int is_errata100(struct pt_regs *regs, unsigned long address)
 {
 #ifdef CONFIG_X86_64
-	if ((regs->cs == __USER32_CS || (regs->cs & (1<<2))) &&
-	    (address >> 32))
+	if ((regs->cs == __USER32_CS || (regs->cs & (1<<2))) && (address >> 32))
 		return 1;
 #endif
 	return 0;
@@ -362,8 +581,9 @@ static int is_f00f_bug(struct pt_regs *regs, unsigned long address)
 {
 #ifdef CONFIG_X86_F00F_BUG
 	unsigned long nr;
+
 	/*
-	 * Pentium F0 0F C7 C8 bug workaround.
+	 * Pentium F0 0F C7 C8 bug workaround:
 	 */
 	if (boot_cpu_data.f00f_bug) {
 		nr = (address - idt_descr.address) >> 3;
@@ -377,62 +597,277 @@ static int is_f00f_bug(struct pt_regs *regs, unsigned long address)
 	return 0;
 }
 
-static void show_fault_oops(struct pt_regs *regs, unsigned long error_code,
-			    unsigned long address)
+static const char nx_warning[] = KERN_CRIT
+"kernel tried to execute NX-protected page - exploit attempt? (uid: %d)\n";
+
+static void
+show_fault_oops(struct pt_regs *regs, unsigned long error_code,
+		unsigned long address)
 {
-#ifdef CONFIG_X86_32
 	if (!oops_may_print())
 		return;
-#endif
 
-#ifdef CONFIG_X86_PAE
 	if (error_code & PF_INSTR) {
 		unsigned int level;
+
 		pte_t *pte = lookup_address(address, &level);
 
 		if (pte && pte_present(*pte) && !pte_exec(*pte))
-			printk(KERN_CRIT "kernel tried to execute "
-				"NX-protected page - exploit attempt? "
-				"(uid: %d)\n", current_uid());
+			printk(nx_warning, current_uid());
 	}
-#endif
 
 	printk(KERN_ALERT "BUG: unable to handle kernel ");
 	if (address < PAGE_SIZE)
 		printk(KERN_CONT "NULL pointer dereference");
 	else
 		printk(KERN_CONT "paging request");
+
 	printk(KERN_CONT " at %p\n", (void *) address);
 	printk(KERN_ALERT "IP:");
 	printk_address(regs->ip, 1);
+
 	dump_pagetable(address);
 }
 
-#ifdef CONFIG_X86_64
-static noinline void pgtable_bad(unsigned long address, struct pt_regs *regs,
-				 unsigned long error_code)
+static noinline void
+pgtable_bad(struct pt_regs *regs, unsigned long error_code,
+	    unsigned long address)
 {
-	unsigned long flags = oops_begin();
-	int sig = SIGKILL;
 	struct task_struct *tsk;
+	unsigned long flags;
+	int sig;
+
+	flags = oops_begin();
+	tsk = current;
+	sig = SIGKILL;
 
 	printk(KERN_ALERT "%s: Corrupted page table at address %lx\n",
-	       current->comm, address);
+	       tsk->comm, address);
 	dump_pagetable(address);
-	tsk = current;
-	tsk->thread.cr2 = address;
-	tsk->thread.trap_no = 14;
-	tsk->thread.error_code = error_code;
+
+	tsk->thread.cr2		= address;
+	tsk->thread.trap_no	= 14;
+	tsk->thread.error_code	= error_code;
+
 	if (__die("Bad pagetable", regs, error_code))
 		sig = 0;
+
 	oops_end(flags, regs, sig);
 }
-#endif
+
+static noinline void
+no_context(struct pt_regs *regs, unsigned long error_code,
+	   unsigned long address)
+{
+	struct task_struct *tsk = current;
+	unsigned long *stackend;
+	unsigned long flags;
+	int sig;
+
+	/* Are we prepared to handle this kernel fault? */
+	if (fixup_exception(regs))
+		return;
+
+	/*
+	 * 32-bit:
+	 *
+	 *   Valid to do another page fault here, because if this fault
+	 *   had been triggered by is_prefetch fixup_exception would have
+	 *   handled it.
+	 *
+	 * 64-bit:
+	 *
+	 *   Hall of shame of CPU/BIOS bugs.
+	 */
+	if (is_prefetch(regs, error_code, address))
+		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();
+
+	show_fault_oops(regs, error_code, address);
+
+	stackend = end_of_stack(tsk);
+	if (*stackend != STACK_END_MAGIC)
+		printk(KERN_ALERT "Thread overran stack, or stack corrupted\n");
+
+	tsk->thread.cr2		= address;
+	tsk->thread.trap_no	= 14;
+	tsk->thread.error_code	= error_code;
+
+	sig = SIGKILL;
+	if (__die("Oops", regs, error_code))
+		sig = 0;
+
+	/* Executive summary in case the body of the oops scrolled away */
+	printk(KERN_EMERG "CR2: %016lx\n", address);
+
+	oops_end(flags, regs, sig);
+}
+
+/*
+ * Print out info about fatal segfaults, if the show_unhandled_signals
+ * sysctl is set:
+ */
+static inline void
+show_signal_msg(struct pt_regs *regs, unsigned long error_code,
+		unsigned long address, struct task_struct *tsk)
+{
+	if (!unhandled_signal(tsk, SIGSEGV))
+		return;
+
+	if (!printk_ratelimit())
+		return;
+
+	printk(KERN_CONT "%s%s[%d]: segfault at %lx ip %p sp %p error %lx",
+		task_pid_nr(tsk) > 1 ? KERN_INFO : KERN_EMERG,
+		tsk->comm, task_pid_nr(tsk), address,
+		(void *)regs->ip, (void *)regs->sp, error_code);
+
+	print_vma_addr(KERN_CONT " in ", regs->ip);
+
+	printk(KERN_CONT "\n");
+}
+
+static void
+__bad_area_nosemaphore(struct pt_regs *regs, unsigned long error_code,
+		       unsigned long address, int si_code)
+{
+	struct task_struct *tsk = current;
+
+	/* User mode accesses just cause a SIGSEGV */
+	if (error_code & PF_USER) {
+		/*
+		 * It's possible to have interrupts off here:
+		 */
+		local_irq_enable();
+
+		/*
+		 * Valid to do another page fault here because this one came
+		 * from user space:
+		 */
+		if (is_prefetch(regs, error_code, address))
+			return;
+
+		if (is_errata100(regs, address))
+			return;
+
+		if (unlikely(show_unhandled_signals))
+			show_signal_msg(regs, error_code, address, tsk);
+
+		/* Kernel addresses are always protection faults: */
+		tsk->thread.cr2		= address;
+		tsk->thread.error_code	= error_code | (address >= TASK_SIZE);
+		tsk->thread.trap_no	= 14;
+
+		force_sig_info_fault(SIGSEGV, si_code, address, tsk);
+
+		return;
+	}
+
+	if (is_f00f_bug(regs, address))
+		return;
+
+	no_context(regs, error_code, address);
+}
+
+static noinline void
+bad_area_nosemaphore(struct pt_regs *regs, unsigned long error_code,
+		     unsigned long address)
+{
+	__bad_area_nosemaphore(regs, error_code, address, SEGV_MAPERR);
+}
+
+static void
+__bad_area(struct pt_regs *regs, unsigned long error_code,
+	   unsigned long address, int si_code)
+{
+	struct mm_struct *mm = current->mm;
+
+	/*
+	 * Something tried to access memory that isn't in our memory map..
+	 * Fix it, but check if it's kernel or user first..
+	 */
+	up_read(&mm->mmap_sem);
+
+	__bad_area_nosemaphore(regs, error_code, address, si_code);
+}
+
+static noinline void
+bad_area(struct pt_regs *regs, unsigned long error_code, unsigned long address)
+{
+	__bad_area(regs, error_code, address, SEGV_MAPERR);
+}
+
+static noinline void
+bad_area_access_error(struct pt_regs *regs, unsigned long error_code,
+		      unsigned long address)
+{
+	__bad_area(regs, error_code, address, SEGV_ACCERR);
+}
+
+/* TODO: fixup for "mm-invoke-oom-killer-from-page-fault.patch" */
+static void
+out_of_memory(struct pt_regs *regs, unsigned long error_code,
+	      unsigned long address)
+{
+	/*
+	 * We ran out of memory, call the OOM killer, and return the userspace
+	 * (which will retry the fault, or kill us if we got oom-killed):
+	 */
+	up_read(&current->mm->mmap_sem);
+
+	pagefault_out_of_memory();
+}
+
+static void
+do_sigbus(struct pt_regs *regs, unsigned long error_code, unsigned long address)
+{
+	struct task_struct *tsk = current;
+	struct mm_struct *mm = tsk->mm;
+
+	up_read(&mm->mmap_sem);
+
+	/* Kernel mode? Handle exceptions or die: */
+	if (!(error_code & PF_USER))
+		no_context(regs, error_code, address);
+
+	/* User-space => ok to do another page fault: */
+	if (is_prefetch(regs, error_code, address))
+		return;
+
+	tsk->thread.cr2		= address;
+	tsk->thread.error_code	= error_code;
+	tsk->thread.trap_no	= 14;
+
+	force_sig_info_fault(SIGBUS, BUS_ADRERR, address, tsk);
+}
+
+static noinline void
+mm_fault_error(struct pt_regs *regs, unsigned long error_code,
+	       unsigned long address, unsigned int fault)
+{
+	if (fault & VM_FAULT_OOM) {
+		out_of_memory(regs, error_code, address);
+	} else {
+		if (fault & VM_FAULT_SIGBUS)
+			do_sigbus(regs, error_code, address);
+		else
+			BUG();
+	}
+}
 
 static int spurious_fault_check(unsigned long error_code, pte_t *pte)
 {
 	if ((error_code & PF_WRITE) && !pte_write(*pte))
 		return 0;
+
 	if ((error_code & PF_INSTR) && !pte_exec(*pte))
 		return 0;
 
@@ -440,21 +875,25 @@ static int spurious_fault_check(unsigned long error_code, pte_t *pte)
 }
 
 /*
- * Handle a spurious fault caused by a stale TLB entry.  This allows
- * us to lazily refresh the TLB when increasing the permissions of a
- * kernel page (RO -> RW or NX -> X).  Doing it eagerly is very
- * expensive since that implies doing a full cross-processor TLB
- * flush, even if no stale TLB entries exist on other processors.
+ * Handle a spurious fault caused by a stale TLB entry.
+ *
+ * This allows us to lazily refresh the TLB when increasing the
+ * permissions of a kernel page (RO -> RW or NX -> X).  Doing it
+ * eagerly is very expensive since that implies doing a full
+ * cross-processor TLB flush, even if no stale TLB entries exist
+ * on other processors.
+ *
  * There are no security implications to leaving a stale TLB when
  * increasing the permissions on a page.
  */
-static int spurious_fault(unsigned long address,
-			  unsigned long error_code)
+static noinline int
+spurious_fault(unsigned long error_code, unsigned long address)
 {
 	pgd_t *pgd;
 	pud_t *pud;
 	pmd_t *pmd;
 	pte_t *pte;
+	int ret;
 
 	/* Reserved-bit violation or user access to kernel space? */
 	if (error_code & (PF_USER | PF_RSVD))
@@ -482,127 +921,71 @@ static int spurious_fault(unsigned long address,
 	if (!pte_present(*pte))
 		return 0;
 
-	return spurious_fault_check(error_code, pte);
-}
-
-/*
- * X86_32
- * Handle a fault on the vmalloc or module mapping area
- *
- * X86_64
- * Handle a fault on the vmalloc area
- *
- * This assumes no large pages in there.
- */
-static int vmalloc_fault(unsigned long address)
-{
-#ifdef CONFIG_X86_32
-	unsigned long pgd_paddr;
-	pmd_t *pmd_k;
-	pte_t *pte_k;
-
-	/* Make sure we are in vmalloc area */
-	if (!(address >= VMALLOC_START && address < VMALLOC_END))
-		return -1;
+	ret = spurious_fault_check(error_code, pte);
+	if (!ret)
+		return 0;
 
 	/*
-	 * Synchronize this task's top level page-table
-	 * with the 'reference' page table.
-	 *
-	 * Do _not_ use "current" here. We might be inside
-	 * an interrupt in the middle of a task switch..
+	 * Make sure we have permissions in PMD.
+	 * If not, then there's a bug in the page tables:
 	 */
-	pgd_paddr = read_cr3();
-	pmd_k = vmalloc_sync_one(__va(pgd_paddr), address);
-	if (!pmd_k)
-		return -1;
-	pte_k = pte_offset_kernel(pmd_k, address);
-	if (!pte_present(*pte_k))
-		return -1;
-	return 0;
-#else
-	pgd_t *pgd, *pgd_ref;
-	pud_t *pud, *pud_ref;
-	pmd_t *pmd, *pmd_ref;
-	pte_t *pte, *pte_ref;
+	ret = spurious_fault_check(error_code, (pte_t *) pmd);
+	WARN_ONCE(!ret, "PMD has incorrect permission bits\n");
 
-	/* Make sure we are in vmalloc area */
-	if (!(address >= VMALLOC_START && address < VMALLOC_END))
-		return -1;
+	return ret;
+}
 
-	/* Copy kernel mappings over when needed. This can also
-	   happen within a race in page table update. In the later
-	   case just flush. */
+int show_unhandled_signals = 1;
 
-	pgd = pgd_offset(current->active_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));
+static inline int
+access_error(unsigned long error_code, int write, struct vm_area_struct *vma)
+{
+	if (write) {
+		/* write, present and write, not present: */
+		if (unlikely(!(vma->vm_flags & VM_WRITE)))
+			return 1;
+		return 0;
+	}
 
-	/* Below here mismatches are bugs because these lower tables
-	   are shared */
+	/* read, present: */
+	if (unlikely(error_code & PF_PROT))
+		return 1;
+
+	/* read, not present: */
+	if (unlikely(!(vma->vm_flags & (VM_READ | VM_EXEC | VM_WRITE))))
+		return 1;
 
-	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;
-#endif
 }
 
-int show_unhandled_signals = 1;
+static int fault_in_kernel_space(unsigned long address)
+{
+	return address >= TASK_SIZE_MAX;
+}
 
 /*
  * This routine handles page faults.  It determines the address,
  * and the problem, and then passes it off to one of the appropriate
  * routines.
  */
-#ifdef CONFIG_X86_64
-asmlinkage
-#endif
-void __kprobes do_page_fault(struct pt_regs *regs, unsigned long error_code)
+dotraplinkage 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;
+	struct task_struct *tsk;
 	unsigned long address;
-	int write, si_code;
+	struct mm_struct *mm;
+	int write;
 	int fault;
-#ifdef CONFIG_X86_64
-	unsigned long flags;
-	int sig;
-#endif
 
 	tsk = current;
 	mm = tsk->mm;
+
 	prefetchw(&mm->mmap_sem);
 
-	/* get the address */
+	/* Get the faulting address: */
 	address = read_cr2();
 
-	si_code = SEGV_MAPERR;
-
 	if (unlikely(kmmio_fault(regs, address)))
 		return;
 
@@ -619,319 +1002,147 @@ void __kprobes do_page_fault(struct pt_regs *regs, unsigned long error_code)
 	 * (error_code & 4) == 0, and that the fault was not a
 	 * protection error (error_code & 9) == 0.
 	 */
-#ifdef CONFIG_X86_32
-	if (unlikely(address >= TASK_SIZE)) {
-#else
-	if (unlikely(address >= TASK_SIZE64)) {
-#endif
+	if (unlikely(fault_in_kernel_space(address))) {
 		if (!(error_code & (PF_RSVD|PF_USER|PF_PROT)) &&
 		    vmalloc_fault(address) >= 0)
 			return;
 
-		/* Can handle a stale RO->RW TLB */
-		if (spurious_fault(address, error_code))
+		/* Can handle a stale RO->RW TLB: */
+		if (spurious_fault(error_code, address))
 			return;
 
-		/* kprobes don't want to hook the spurious faults. */
+		/* kprobes don't want to hook the spurious faults: */
 		if (notify_page_fault(regs))
 			return;
 		/*
 		 * Don't take the mm semaphore here. If we fixup a prefetch
-		 * fault we could otherwise deadlock.
+		 * fault we could otherwise deadlock:
 		 */
-		goto bad_area_nosemaphore;
-	}
+		bad_area_nosemaphore(regs, error_code, address);
 
-	/* kprobes don't want to hook the spurious faults. */
-	if (notify_page_fault(regs))
 		return;
+	}
 
+	/* kprobes don't want to hook the spurious faults: */
+	if (unlikely(notify_page_fault(regs)))
+		return;
 	/*
 	 * It's safe to allow irq's after cr2 has been saved and the
 	 * vmalloc fault has been handled.
 	 *
 	 * User-mode registers count as a user access even for any
-	 * potential system fault or CPU buglet.
+	 * potential system fault or CPU buglet:
 	 */
 	if (user_mode_vm(regs)) {
 		local_irq_enable();
 		error_code |= PF_USER;
-	} else if (regs->flags & X86_EFLAGS_IF)
-		local_irq_enable();
+	} else {
+		if (regs->flags & X86_EFLAGS_IF)
+			local_irq_enable();
+	}
 
-#ifdef CONFIG_X86_64
 	if (unlikely(error_code & PF_RSVD))
-		pgtable_bad(address, regs, error_code);
-#endif
+		pgtable_bad(regs, error_code, address);
 
 	/*
-	 * If we're in an interrupt, have no user context or are running in an
-	 * atomic region then we must not take the fault.
+	 * If we're in an interrupt, have no user context or are running
+	 * in an atomic region then we must not take the fault:
 	 */
-	if (unlikely(in_atomic() || !mm))
-		goto bad_area_nosemaphore;
+	if (unlikely(in_atomic() || !mm)) {
+		bad_area_nosemaphore(regs, error_code, address);
+		return;
+	}
 
 	/*
 	 * 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.  Unfortunately, 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.
+	 * addresses in user space.  All other faults represent errors in
+	 * the kernel and should generate an OOPS.  Unfortunately, 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 possibility 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.
+	 * the source reference check when there is a possibility 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 (unlikely(!down_read_trylock(&mm->mmap_sem))) {
 		if ((error_code & PF_USER) == 0 &&
-		    !search_exception_tables(regs->ip))
-			goto bad_area_nosemaphore;
+		    !search_exception_tables(regs->ip)) {
+			bad_area_nosemaphore(regs, error_code, address);
+			return;
+		}
 		down_read(&mm->mmap_sem);
+	} else {
+		/*
+		 * The above down_read_trylock() might have succeeded in
+		 * which case we'll have missed the might_sleep() from
+		 * down_read():
+		 */
+		might_sleep();
 	}
 
 	vma = find_vma(mm, address);
-	if (!vma)
-		goto bad_area;
-	if (vma->vm_start <= address)
+	if (unlikely(!vma)) {
+		bad_area(regs, error_code, address);
+		return;
+	}
+	if (likely(vma->vm_start <= address))
 		goto good_area;
-	if (!(vma->vm_flags & VM_GROWSDOWN))
-		goto bad_area;
+	if (unlikely(!(vma->vm_flags & VM_GROWSDOWN))) {
+		bad_area(regs, error_code, address);
+		return;
+	}
 	if (error_code & PF_USER) {
 		/*
 		 * Accessing the stack below %sp is always a bug.
 		 * The large cushion allows instructions like enter
-		 * and pusha to work.  ("enter $65535,$31" pushes
+		 * and pusha to work. ("enter $65535, $31" pushes
 		 * 32 pointers and then decrements %sp by 65535.)
 		 */
-		if (address + 65536 + 32 * sizeof(unsigned long) < regs->sp)
-			goto bad_area;
+		if (unlikely(address + 65536 + 32 * sizeof(unsigned long) < regs->sp)) {
+			bad_area(regs, error_code, address);
+			return;
+		}
 	}
-	if (expand_stack(vma, address))
-		goto bad_area;
-/*
- * Ok, we have a good vm_area for this memory access, so
- * we can handle it..
- */
+	if (unlikely(expand_stack(vma, address))) {
+		bad_area(regs, error_code, address);
+		return;
+	}
+
+	/*
+	 * Ok, we have a good vm_area for this memory access, so
+	 * we can handle it..
+	 */
 good_area:
-	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;
+	write = error_code & PF_WRITE;
+
+	if (unlikely(access_error(error_code, write, vma))) {
+		bad_area_access_error(regs, error_code, address);
+		return;
 	}
 
 	/*
 	 * If for any reason at all we couldn't handle the fault,
 	 * make sure we exit gracefully rather than endlessly redo
-	 * the fault.
+	 * 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();
+		mm_fault_error(regs, error_code, address, fault);
+		return;
 	}
+
 	if (fault & VM_FAULT_MAJOR)
 		tsk->maj_flt++;
 	else
 		tsk->min_flt++;
 
-#ifdef CONFIG_X86_32
-	/*
-	 * Did it hit the DOS screen memory VA from vm86 mode?
-	 */
-	if (v8086_mode(regs)) {
-		unsigned long bit = (address - 0xA0000) >> PAGE_SHIFT;
-		if (bit < 32)
-			tsk->thread.screen_bitmap |= 1 << bit;
-	}
-#endif
-	up_read(&mm->mmap_sem);
-	return;
+	check_v8086_mode(regs, address, tsk);
 
-/*
- * 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();
-
-		/*
-		 * Valid to do another page fault here because this one came
-		 * from user space.
-		 */
-		if (is_prefetch(regs, address, error_code))
-			return;
-
-		if (is_errata100(regs, address))
-			return;
-
-		if (show_unhandled_signals && unhandled_signal(tsk, SIGSEGV) &&
-		    printk_ratelimit()) {
-			printk(
-			"%s%s[%d]: segfault at %lx ip %p sp %p error %lx",
-			task_pid_nr(tsk) > 1 ? KERN_INFO : KERN_EMERG,
-			tsk->comm, task_pid_nr(tsk), address,
-			(void *) regs->ip, (void *) regs->sp, error_code);
-			print_vma_addr(" in ", regs->ip);
-			printk("\n");
-		}
-
-		tsk->thread.cr2 = address;
-		/* Kernel addresses are always protection faults */
-		tsk->thread.error_code = error_code | (address >= TASK_SIZE);
-		tsk->thread.trap_no = 14;
-		force_sig_info_fault(SIGSEGV, si_code, address, tsk);
-		return;
-	}
-
-	if (is_f00f_bug(regs, address))
-		return;
-
-no_context:
-	/* Are we prepared to handle this kernel fault?  */
-	if (fixup_exception(regs))
-		return;
-
-	/*
-	 * X86_32
-	 * Valid to do another page fault here, because if this fault
-	 * had been triggered by is_prefetch fixup_exception would have
-	 * handled it.
-	 *
-	 * X86_64
-	 * 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.
- */
-#ifdef CONFIG_X86_32
-	bust_spinlocks(1);
-#else
-	flags = oops_begin();
-#endif
-
-	show_fault_oops(regs, error_code, address);
-
-	tsk->thread.cr2 = address;
-	tsk->thread.trap_no = 14;
-	tsk->thread.error_code = error_code;
-
-#ifdef CONFIG_X86_32
-	die("Oops", regs, error_code);
-	bust_spinlocks(0);
-	do_exit(SIGKILL);
-#else
-	sig = SIGKILL;
-	if (__die("Oops", regs, error_code))
-		sig = 0;
-	/* Executive summary in case the body of the oops scrolled away */
-	printk(KERN_EMERG "CR2: %016lx\n", address);
-	oops_end(flags, regs, sig);
-#endif
-
-out_of_memory:
-	/*
-	 * We ran out of memory, call the OOM killer, and return the userspace
-	 * (which will retry the fault, or kill us if we got oom-killed).
-	 */
-	up_read(&mm->mmap_sem);
-	pagefault_out_of_memory();
-	return;
-
-do_sigbus:
-	up_read(&mm->mmap_sem);
-
-	/* Kernel mode? Handle exceptions or die */
-	if (!(error_code & PF_USER))
-		goto no_context;
-#ifdef CONFIG_X86_32
-	/* User space => ok to do another page fault */
-	if (is_prefetch(regs, address, error_code))
-		return;
-#endif
-	tsk->thread.cr2 = address;
-	tsk->thread.error_code = error_code;
-	tsk->thread.trap_no = 14;
-	force_sig_info_fault(SIGBUS, BUS_ADRERR, address, tsk);
-}
-
-DEFINE_SPINLOCK(pgd_lock);
-LIST_HEAD(pgd_list);
-
-void vmalloc_sync_all(void)
-{
-	unsigned long address;
-
-#ifdef CONFIG_X86_32
-	if (SHARED_KERNEL_PMD)
-		return;
-
-	for (address = VMALLOC_START & PMD_MASK;
-	     address >= TASK_SIZE && address < FIXADDR_TOP;
-	     address += PMD_SIZE) {
-		unsigned long flags;
-		struct page *page;
-
-		spin_lock_irqsave(&pgd_lock, flags);
-		list_for_each_entry(page, &pgd_list, lru) {
-			if (!vmalloc_sync_one(page_address(page),
-					      address))
-				break;
-		}
-		spin_unlock_irqrestore(&pgd_lock, flags);
-	}
-#else /* CONFIG_X86_64 */
-	for (address = VMALLOC_START & PGDIR_MASK; address <= VMALLOC_END;
-	     address += PGDIR_SIZE) {
-		const pgd_t *pgd_ref = pgd_offset_k(address);
-		unsigned long flags;
-		struct page *page;
-
-		if (pgd_none(*pgd_ref))
-			continue;
-		spin_lock_irqsave(&pgd_lock, flags);
-		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_irqrestore(&pgd_lock, flags);
-	}
-#endif
 }
diff --git a/arch/x86/mm/highmem_32.c b/arch/x86/mm/highmem_32.c
index bcc079c282dd..00f127c80b0e 100644
--- a/arch/x86/mm/highmem_32.c
+++ b/arch/x86/mm/highmem_32.c
@@ -1,5 +1,6 @@
 #include <linux/highmem.h>
 #include <linux/module.h>
+#include <linux/swap.h> /* for totalram_pages */
 
 void *kmap(struct page *page)
 {
@@ -156,3 +157,36 @@ EXPORT_SYMBOL(kmap);
 EXPORT_SYMBOL(kunmap);
 EXPORT_SYMBOL(kmap_atomic);
 EXPORT_SYMBOL(kunmap_atomic);
+
+#ifdef CONFIG_NUMA
+void __init set_highmem_pages_init(void)
+{
+	struct zone *zone;
+	int nid;
+
+	for_each_zone(zone) {
+		unsigned long zone_start_pfn, zone_end_pfn;
+
+		if (!is_highmem(zone))
+			continue;
+
+		zone_start_pfn = zone->zone_start_pfn;
+		zone_end_pfn = zone_start_pfn + zone->spanned_pages;
+
+		nid = zone_to_nid(zone);
+		printk(KERN_INFO "Initializing %s for node %d (%08lx:%08lx)\n",
+				zone->name, nid, zone_start_pfn, zone_end_pfn);
+
+		add_highpages_with_active_regions(nid, zone_start_pfn,
+				 zone_end_pfn);
+	}
+	totalram_pages += totalhigh_pages;
+}
+#else
+void __init set_highmem_pages_init(void)
+{
+	add_highpages_with_active_regions(0, highstart_pfn, highend_pfn);
+
+	totalram_pages += totalhigh_pages;
+}
+#endif /* CONFIG_NUMA */
diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c
new file mode 100644
index 000000000000..ce6a722587d8
--- /dev/null
+++ b/arch/x86/mm/init.c
@@ -0,0 +1,49 @@
+#include <linux/swap.h>
+#include <asm/cacheflush.h>
+#include <asm/page.h>
+#include <asm/sections.h>
+#include <asm/system.h>
+
+void free_init_pages(char *what, unsigned long begin, unsigned long end)
+{
+	unsigned long addr = begin;
+
+	if (addr >= end)
+		return;
+
+	/*
+	 * If debugging page accesses then do not free this memory but
+	 * mark them not present - any buggy init-section access will
+	 * create a kernel page fault:
+	 */
+#ifdef CONFIG_DEBUG_PAGEALLOC
+	printk(KERN_INFO "debug: unmapping init memory %08lx..%08lx\n",
+		begin, PAGE_ALIGN(end));
+	set_memory_np(begin, (end - begin) >> PAGE_SHIFT);
+#else
+	/*
+	 * We just marked the kernel text read only above, now that
+	 * we are going to free part of that, we need to make that
+	 * writeable first.
+	 */
+	set_memory_rw(begin, (end - begin) >> PAGE_SHIFT);
+
+	printk(KERN_INFO "Freeing %s: %luk freed\n", what, (end - begin) >> 10);
+
+	for (; addr < end; addr += PAGE_SIZE) {
+		ClearPageReserved(virt_to_page(addr));
+		init_page_count(virt_to_page(addr));
+		memset((void *)(addr & ~(PAGE_SIZE-1)),
+			POISON_FREE_INITMEM, PAGE_SIZE);
+		free_page(addr);
+		totalram_pages++;
+	}
+#endif
+}
+
+void free_initmem(void)
+{
+	free_init_pages("unused kernel memory",
+			(unsigned long)(&__init_begin),
+			(unsigned long)(&__init_end));
+}
diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c
index 2cef05074413..47df0e1bbeb9 100644
--- a/arch/x86/mm/init_32.c
+++ b/arch/x86/mm/init_32.c
@@ -49,9 +49,6 @@
 #include <asm/paravirt.h>
 #include <asm/setup.h>
 #include <asm/cacheflush.h>
-#include <asm/smp.h>
-
-unsigned int __VMALLOC_RESERVE = 128 << 20;
 
 unsigned long max_low_pfn_mapped;
 unsigned long max_pfn_mapped;
@@ -138,6 +135,23 @@ static pte_t * __init one_page_table_init(pmd_t *pmd)
 	return pte_offset_kernel(pmd, 0);
 }
 
+pmd_t * __init populate_extra_pmd(unsigned long vaddr)
+{
+	int pgd_idx = pgd_index(vaddr);
+	int pmd_idx = pmd_index(vaddr);
+
+	return one_md_table_init(swapper_pg_dir + pgd_idx) + pmd_idx;
+}
+
+pte_t * __init populate_extra_pte(unsigned long vaddr)
+{
+	int pte_idx = pte_index(vaddr);
+	pmd_t *pmd;
+
+	pmd = populate_extra_pmd(vaddr);
+	return one_page_table_init(pmd) + pte_idx;
+}
+
 static pte_t *__init page_table_kmap_check(pte_t *pte, pmd_t *pmd,
 					   unsigned long vaddr, pte_t *lastpte)
 {
@@ -470,22 +484,10 @@ void __init add_highpages_with_active_regions(int nid, unsigned long start_pfn,
 	work_with_active_regions(nid, add_highpages_work_fn, &data);
 }
 
-#ifndef CONFIG_NUMA
-static void __init set_highmem_pages_init(void)
-{
-	add_highpages_with_active_regions(0, highstart_pfn, highend_pfn);
-
-	totalram_pages += totalhigh_pages;
-}
-#endif /* !CONFIG_NUMA */
-
 #else
 static inline void permanent_kmaps_init(pgd_t *pgd_base)
 {
 }
-static inline void set_highmem_pages_init(void)
-{
-}
 #endif /* CONFIG_HIGHMEM */
 
 void __init native_pagetable_setup_start(pgd_t *base)
@@ -675,75 +677,97 @@ static int __init parse_highmem(char *arg)
 }
 early_param("highmem", parse_highmem);
 
+#define MSG_HIGHMEM_TOO_BIG \
+	"highmem size (%luMB) is bigger than pages available (%luMB)!\n"
+
+#define MSG_LOWMEM_TOO_SMALL \
+	"highmem size (%luMB) results in <64MB lowmem, ignoring it!\n"
 /*
- * Determine low and high memory ranges:
+ * All of RAM fits into lowmem - but if user wants highmem
+ * artificially via the highmem=x boot parameter then create
+ * it:
  */
-void __init find_low_pfn_range(void)
+void __init lowmem_pfn_init(void)
 {
-	/* it could update max_pfn */
-
 	/* max_low_pfn is 0, we already have early_res support */
-
 	max_low_pfn = max_pfn;
-	if (max_low_pfn > MAXMEM_PFN) {
-		if (highmem_pages == -1)
-			highmem_pages = max_pfn - MAXMEM_PFN;
-		if (highmem_pages + MAXMEM_PFN < max_pfn)
-			max_pfn = MAXMEM_PFN + highmem_pages;
-		if (highmem_pages + MAXMEM_PFN > max_pfn) {
-			printk(KERN_WARNING "only %luMB highmem pages "
-				"available, ignoring highmem size of %uMB.\n",
-				pages_to_mb(max_pfn - MAXMEM_PFN),
+
+	if (highmem_pages == -1)
+		highmem_pages = 0;
+#ifdef CONFIG_HIGHMEM
+	if (highmem_pages >= max_pfn) {
+		printk(KERN_ERR MSG_HIGHMEM_TOO_BIG,
+			pages_to_mb(highmem_pages), pages_to_mb(max_pfn));
+		highmem_pages = 0;
+	}
+	if (highmem_pages) {
+		if (max_low_pfn - highmem_pages < 64*1024*1024/PAGE_SIZE) {
+			printk(KERN_ERR MSG_LOWMEM_TOO_SMALL,
 				pages_to_mb(highmem_pages));
 			highmem_pages = 0;
 		}
-		max_low_pfn = MAXMEM_PFN;
+		max_low_pfn -= highmem_pages;
+	}
+#else
+	if (highmem_pages)
+		printk(KERN_ERR "ignoring highmem size on non-highmem kernel!\n");
+#endif
+}
+
+#define MSG_HIGHMEM_TOO_SMALL \
+	"only %luMB highmem pages available, ignoring highmem size of %luMB!\n"
+
+#define MSG_HIGHMEM_TRIMMED \
+	"Warning: only 4GB will be used. Use a HIGHMEM64G enabled kernel!\n"
+/*
+ * We have more RAM than fits into lowmem - we try to put it into
+ * highmem, also taking the highmem=x boot parameter into account:
+ */
+void __init highmem_pfn_init(void)
+{
+	max_low_pfn = MAXMEM_PFN;
+
+	if (highmem_pages == -1)
+		highmem_pages = max_pfn - MAXMEM_PFN;
+
+	if (highmem_pages + MAXMEM_PFN < max_pfn)
+		max_pfn = MAXMEM_PFN + highmem_pages;
+
+	if (highmem_pages + MAXMEM_PFN > max_pfn) {
+		printk(KERN_WARNING MSG_HIGHMEM_TOO_SMALL,
+			pages_to_mb(max_pfn - MAXMEM_PFN),
+			pages_to_mb(highmem_pages));
+		highmem_pages = 0;
+	}
 #ifndef CONFIG_HIGHMEM
-		/* Maximum memory usable is what is directly addressable */
-		printk(KERN_WARNING "Warning only %ldMB will be used.\n",
-					MAXMEM>>20);
-		if (max_pfn > MAX_NONPAE_PFN)
-			printk(KERN_WARNING
-				 "Use a HIGHMEM64G enabled kernel.\n");
-		else
-			printk(KERN_WARNING "Use a HIGHMEM enabled kernel.\n");
-		max_pfn = MAXMEM_PFN;
+	/* Maximum memory usable is what is directly addressable */
+	printk(KERN_WARNING "Warning only %ldMB will be used.\n", MAXMEM>>20);
+	if (max_pfn > MAX_NONPAE_PFN)
+		printk(KERN_WARNING "Use a HIGHMEM64G enabled kernel.\n");
+	else
+		printk(KERN_WARNING "Use a HIGHMEM enabled kernel.\n");
+	max_pfn = MAXMEM_PFN;
 #else /* !CONFIG_HIGHMEM */
 #ifndef CONFIG_HIGHMEM64G
-		if (max_pfn > MAX_NONPAE_PFN) {
-			max_pfn = MAX_NONPAE_PFN;
-			printk(KERN_WARNING "Warning only 4GB will be used."
-				"Use a HIGHMEM64G enabled kernel.\n");
-		}
+	if (max_pfn > MAX_NONPAE_PFN) {
+		max_pfn = MAX_NONPAE_PFN;
+		printk(KERN_WARNING MSG_HIGHMEM_TRIMMED);
+	}
 #endif /* !CONFIG_HIGHMEM64G */
 #endif /* !CONFIG_HIGHMEM */
-	} else {
-		if (highmem_pages == -1)
-			highmem_pages = 0;
-#ifdef CONFIG_HIGHMEM
-		if (highmem_pages >= max_pfn) {
-			printk(KERN_ERR "highmem size specified (%uMB) is "
-				"bigger than pages available (%luMB)!.\n",
-				pages_to_mb(highmem_pages),
-				pages_to_mb(max_pfn));
-			highmem_pages = 0;
-		}
-		if (highmem_pages) {
-			if (max_low_pfn - highmem_pages <
-			    64*1024*1024/PAGE_SIZE){
-				printk(KERN_ERR "highmem size %uMB results in "
-				"smaller than 64MB lowmem, ignoring it.\n"
-					, pages_to_mb(highmem_pages));
-				highmem_pages = 0;
-			}
-			max_low_pfn -= highmem_pages;
-		}
-#else
-		if (highmem_pages)
-			printk(KERN_ERR "ignoring highmem size on non-highmem"
-					" kernel!\n");
-#endif
-	}
+}
+
+/*
+ * Determine low and high memory ranges:
+ */
+void __init find_low_pfn_range(void)
+{
+	/* it could update max_pfn */
+
+	if (max_pfn <= MAXMEM_PFN)
+		lowmem_pfn_init();
+	else
+		highmem_pfn_init();
 }
 
 #ifndef CONFIG_NEED_MULTIPLE_NODES
@@ -826,10 +850,10 @@ static void __init find_early_table_space(unsigned long end, int use_pse)
 	unsigned long puds, pmds, ptes, tables, start;
 
 	puds = (end + PUD_SIZE - 1) >> PUD_SHIFT;
-	tables = PAGE_ALIGN(puds * sizeof(pud_t));
+	tables = roundup(puds * sizeof(pud_t), PAGE_SIZE);
 
 	pmds = (end + PMD_SIZE - 1) >> PMD_SHIFT;
-	tables += PAGE_ALIGN(pmds * sizeof(pmd_t));
+	tables += roundup(pmds * sizeof(pmd_t), PAGE_SIZE);
 
 	if (use_pse) {
 		unsigned long extra;
@@ -840,10 +864,10 @@ static void __init find_early_table_space(unsigned long end, int use_pse)
 	} else
 		ptes = (end + PAGE_SIZE - 1) >> PAGE_SHIFT;
 
-	tables += PAGE_ALIGN(ptes * sizeof(pte_t));
+	tables += roundup(ptes * sizeof(pte_t), PAGE_SIZE);
 
 	/* for fixmap */
-	tables += PAGE_ALIGN(__end_of_fixed_addresses * sizeof(pte_t));
+	tables += roundup(__end_of_fixed_addresses * sizeof(pte_t), PAGE_SIZE);
 
 	/*
 	 * RED-PEN putting page tables only on node 0 could
@@ -1193,45 +1217,6 @@ void mark_rodata_ro(void)
 }
 #endif
 
-void free_init_pages(char *what, unsigned long begin, unsigned long end)
-{
-#ifdef CONFIG_DEBUG_PAGEALLOC
-	/*
-	 * If debugging page accesses then do not free this memory but
-	 * mark them not present - any buggy init-section access will
-	 * create a kernel page fault:
-	 */
-	printk(KERN_INFO "debug: unmapping init memory %08lx..%08lx\n",
-		begin, PAGE_ALIGN(end));
-	set_memory_np(begin, (end - begin) >> PAGE_SHIFT);
-#else
-	unsigned long addr;
-
-	/*
-	 * We just marked the kernel text read only above, now that
-	 * we are going to free part of that, we need to make that
-	 * writeable first.
-	 */
-	set_memory_rw(begin, (end - begin) >> PAGE_SHIFT);
-
-	for (addr = begin; addr < end; addr += PAGE_SIZE) {
-		ClearPageReserved(virt_to_page(addr));
-		init_page_count(virt_to_page(addr));
-		memset((void *)addr, POISON_FREE_INITMEM, PAGE_SIZE);
-		free_page(addr);
-		totalram_pages++;
-	}
-	printk(KERN_INFO "Freeing %s: %luk freed\n", what, (end - begin) >> 10);
-#endif
-}
-
-void free_initmem(void)
-{
-	free_init_pages("unused kernel memory",
-			(unsigned long)(&__init_begin),
-			(unsigned long)(&__init_end));
-}
-
 #ifdef CONFIG_BLK_DEV_INITRD
 void free_initrd_mem(unsigned long start, unsigned long end)
 {
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index b1352250096e..07f44d491df1 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -168,34 +168,51 @@ static __ref void *spp_getpage(void)
 	return ptr;
 }
 
-void
-set_pte_vaddr_pud(pud_t *pud_page, unsigned long vaddr, pte_t new_pte)
+static pud_t *fill_pud(pgd_t *pgd, unsigned long vaddr)
 {
-	pud_t *pud;
-	pmd_t *pmd;
-	pte_t *pte;
+	if (pgd_none(*pgd)) {
+		pud_t *pud = (pud_t *)spp_getpage();
+		pgd_populate(&init_mm, pgd, pud);
+		if (pud != pud_offset(pgd, 0))
+			printk(KERN_ERR "PAGETABLE BUG #00! %p <-> %p\n",
+			       pud, pud_offset(pgd, 0));
+	}
+	return pud_offset(pgd, vaddr);
+}
 
-	pud = pud_page + pud_index(vaddr);
+static pmd_t *fill_pmd(pud_t *pud, unsigned long vaddr)
+{
 	if (pud_none(*pud)) {
-		pmd = (pmd_t *) spp_getpage();
+		pmd_t *pmd = (pmd_t *) spp_getpage();
 		pud_populate(&init_mm, pud, pmd);
-		if (pmd != pmd_offset(pud, 0)) {
+		if (pmd != pmd_offset(pud, 0))
 			printk(KERN_ERR "PAGETABLE BUG #01! %p <-> %p\n",
-				pmd, pmd_offset(pud, 0));
-			return;
-		}
+			       pmd, pmd_offset(pud, 0));
 	}
-	pmd = pmd_offset(pud, vaddr);
+	return pmd_offset(pud, vaddr);
+}
+
+static pte_t *fill_pte(pmd_t *pmd, unsigned long vaddr)
+{
 	if (pmd_none(*pmd)) {
-		pte = (pte_t *) spp_getpage();
+		pte_t *pte = (pte_t *) spp_getpage();
 		pmd_populate_kernel(&init_mm, pmd, pte);
-		if (pte != pte_offset_kernel(pmd, 0)) {
+		if (pte != pte_offset_kernel(pmd, 0))
 			printk(KERN_ERR "PAGETABLE BUG #02!\n");
-			return;
-		}
 	}
+	return pte_offset_kernel(pmd, vaddr);
+}
+
+void set_pte_vaddr_pud(pud_t *pud_page, unsigned long vaddr, pte_t new_pte)
+{
+	pud_t *pud;
+	pmd_t *pmd;
+	pte_t *pte;
+
+	pud = pud_page + pud_index(vaddr);
+	pmd = fill_pmd(pud, vaddr);
+	pte = fill_pte(pmd, vaddr);
 
-	pte = pte_offset_kernel(pmd, vaddr);
 	set_pte(pte, new_pte);
 
 	/*
@@ -205,8 +222,7 @@ set_pte_vaddr_pud(pud_t *pud_page, unsigned long vaddr, pte_t new_pte)
 	__flush_tlb_one(vaddr);
 }
 
-void
-set_pte_vaddr(unsigned long vaddr, pte_t pteval)
+void set_pte_vaddr(unsigned long vaddr, pte_t pteval)
 {
 	pgd_t *pgd;
 	pud_t *pud_page;
@@ -223,6 +239,24 @@ set_pte_vaddr(unsigned long vaddr, pte_t pteval)
 	set_pte_vaddr_pud(pud_page, vaddr, pteval);
 }
 
+pmd_t * __init populate_extra_pmd(unsigned long vaddr)
+{
+	pgd_t *pgd;
+	pud_t *pud;
+
+	pgd = pgd_offset_k(vaddr);
+	pud = fill_pud(pgd, vaddr);
+	return fill_pmd(pud, vaddr);
+}
+
+pte_t * __init populate_extra_pte(unsigned long vaddr)
+{
+	pmd_t *pmd;
+
+	pmd = populate_extra_pmd(vaddr);
+	return fill_pte(pmd, vaddr);
+}
+
 /*
  * Create large page table mappings for a range of physical addresses.
  */
@@ -947,43 +981,6 @@ void __init mem_init(void)
 		initsize >> 10);
 }
 
-void free_init_pages(char *what, unsigned long begin, unsigned long end)
-{
-	unsigned long addr = begin;
-
-	if (addr >= end)
-		return;
-
-	/*
-	 * If debugging page accesses then do not free this memory but
-	 * mark them not present - any buggy init-section access will
-	 * create a kernel page fault:
-	 */
-#ifdef CONFIG_DEBUG_PAGEALLOC
-	printk(KERN_INFO "debug: unmapping init memory %08lx..%08lx\n",
-		begin, PAGE_ALIGN(end));
-	set_memory_np(begin, (end - begin) >> PAGE_SHIFT);
-#else
-	printk(KERN_INFO "Freeing %s: %luk freed\n", what, (end - begin) >> 10);
-
-	for (; addr < end; addr += PAGE_SIZE) {
-		ClearPageReserved(virt_to_page(addr));
-		init_page_count(virt_to_page(addr));
-		memset((void *)(addr & ~(PAGE_SIZE-1)),
-			POISON_FREE_INITMEM, PAGE_SIZE);
-		free_page(addr);
-		totalram_pages++;
-	}
-#endif
-}
-
-void free_initmem(void)
-{
-	free_init_pages("unused kernel memory",
-			(unsigned long)(&__init_begin),
-			(unsigned long)(&__init_end));
-}
-
 #ifdef CONFIG_DEBUG_RODATA
 const int rodata_test_data = 0xC3;
 EXPORT_SYMBOL_GPL(rodata_test_data);
diff --git a/arch/x86/mm/ioremap.c b/arch/x86/mm/ioremap.c
index f45d5e29a72e..433f7bd4648a 100644
--- a/arch/x86/mm/ioremap.c
+++ b/arch/x86/mm/ioremap.c
@@ -348,7 +348,7 @@ EXPORT_SYMBOL(ioremap_nocache);
  *
  * Must be freed with iounmap.
  */
-void __iomem *ioremap_wc(unsigned long phys_addr, unsigned long size)
+void __iomem *ioremap_wc(resource_size_t phys_addr, unsigned long size)
 {
 	if (pat_enabled)
 		return __ioremap_caller(phys_addr, size, _PAGE_CACHE_WC,
diff --git a/arch/x86/mm/memtest.c b/arch/x86/mm/memtest.c
index 9cab18b0b857..0bcd7883d036 100644
--- a/arch/x86/mm/memtest.c
+++ b/arch/x86/mm/memtest.c
@@ -9,44 +9,44 @@
 
 #include <asm/e820.h>
 
-static void __init memtest(unsigned long start_phys, unsigned long size,
-				 unsigned pattern)
+static u64 patterns[] __initdata = {
+	0,
+	0xffffffffffffffffULL,
+	0x5555555555555555ULL,
+	0xaaaaaaaaaaaaaaaaULL,
+	0x1111111111111111ULL,
+	0x2222222222222222ULL,
+	0x4444444444444444ULL,
+	0x8888888888888888ULL,
+	0x3333333333333333ULL,
+	0x6666666666666666ULL,
+	0x9999999999999999ULL,
+	0xccccccccccccccccULL,
+	0x7777777777777777ULL,
+	0xbbbbbbbbbbbbbbbbULL,
+	0xddddddddddddddddULL,
+	0xeeeeeeeeeeeeeeeeULL,
+	0x7a6c7258554e494cULL, /* yeah ;-) */
+};
+
+static void __init reserve_bad_mem(u64 pattern, u64 start_bad, u64 end_bad)
 {
-	unsigned long i;
-	unsigned long *start;
-	unsigned long start_bad;
-	unsigned long last_bad;
-	unsigned long val;
-	unsigned long start_phys_aligned;
-	unsigned long count;
-	unsigned long incr;
-
-	switch (pattern) {
-	case 0:
-		val = 0UL;
-		break;
-	case 1:
-		val = -1UL;
-		break;
-	case 2:
-#ifdef CONFIG_X86_64
-		val = 0x5555555555555555UL;
-#else
-		val = 0x55555555UL;
-#endif
-		break;
-	case 3:
-#ifdef CONFIG_X86_64
-		val = 0xaaaaaaaaaaaaaaaaUL;
-#else
-		val = 0xaaaaaaaaUL;
-#endif
-		break;
-	default:
-		return;
-	}
+	printk(KERN_INFO "  %016llx bad mem addr %010llx - %010llx reserved\n",
+	       (unsigned long long) pattern,
+	       (unsigned long long) start_bad,
+	       (unsigned long long) end_bad);
+	reserve_early(start_bad, end_bad, "BAD RAM");
+}
 
-	incr = sizeof(unsigned long);
+static void __init memtest(u64 pattern, u64 start_phys, u64 size)
+{
+	u64 i, count;
+	u64 *start;
+	u64 start_bad, last_bad;
+	u64 start_phys_aligned;
+	size_t incr;
+
+	incr = sizeof(pattern);
 	start_phys_aligned = ALIGN(start_phys, incr);
 	count = (size - (start_phys_aligned - start_phys))/incr;
 	start = __va(start_phys_aligned);
@@ -54,25 +54,42 @@ static void __init memtest(unsigned long start_phys, unsigned long size,
 	last_bad = 0;
 
 	for (i = 0; i < count; i++)
-		start[i] = val;
+		start[i] = pattern;
 	for (i = 0; i < count; i++, start++, start_phys_aligned += incr) {
-		if (*start != val) {
-			if (start_phys_aligned == last_bad + incr) {
-				last_bad += incr;
-			} else {
-				if (start_bad) {
-					printk(KERN_CONT "\n  %016lx bad mem addr %010lx - %010lx reserved",
-						val, start_bad, last_bad + incr);
-					reserve_early(start_bad, last_bad + incr, "BAD RAM");
-				}
-				start_bad = last_bad = start_phys_aligned;
-			}
+		if (*start == pattern)
+			continue;
+		if (start_phys_aligned == last_bad + incr) {
+			last_bad += incr;
+			continue;
 		}
+		if (start_bad)
+			reserve_bad_mem(pattern, start_bad, last_bad + incr);
+		start_bad = last_bad = start_phys_aligned;
 	}
-	if (start_bad) {
-		printk(KERN_CONT "\n  %016lx bad mem addr %010lx - %010lx reserved",
-			val, start_bad, last_bad + incr);
-		reserve_early(start_bad, last_bad + incr, "BAD RAM");
+	if (start_bad)
+		reserve_bad_mem(pattern, start_bad, last_bad + incr);
+}
+
+static void __init do_one_pass(u64 pattern, u64 start, u64 end)
+{
+	u64 size = 0;
+
+	while (start < end) {
+		start = find_e820_area_size(start, &size, 1);
+
+		/* done ? */
+		if (start >= end)
+			break;
+		if (start + size > end)
+			size = end - start;
+
+		printk(KERN_INFO "  %010llx - %010llx pattern %016llx\n",
+		       (unsigned long long) start,
+		       (unsigned long long) start + size,
+		       (unsigned long long) cpu_to_be64(pattern));
+		memtest(pattern, start, size);
+
+		start += size;
 	}
 }
 
@@ -90,33 +107,22 @@ early_param("memtest", parse_memtest);
 
 void __init early_memtest(unsigned long start, unsigned long end)
 {
-	u64 t_start, t_size;
-	unsigned pattern;
+	unsigned int i;
+	unsigned int idx = 0;
 
 	if (!memtest_pattern)
 		return;
 
-	printk(KERN_INFO "early_memtest: pattern num %d", memtest_pattern);
-	for (pattern = 0; pattern < memtest_pattern; pattern++) {
-		t_start = start;
-		t_size = 0;
-		while (t_start < end) {
-			t_start = find_e820_area_size(t_start, &t_size, 1);
-
-			/* done ? */
-			if (t_start >= end)
-				break;
-			if (t_start + t_size > end)
-				t_size = end - t_start;
-
-			printk(KERN_CONT "\n  %010llx - %010llx pattern %d",
-				(unsigned long long)t_start,
-				(unsigned long long)t_start + t_size, pattern);
-
-			memtest(t_start, t_size, pattern);
+	printk(KERN_INFO "early_memtest: # of tests: %d\n", memtest_pattern);
+	for (i = 0; i < memtest_pattern; i++) {
+		idx = i % ARRAY_SIZE(patterns);
+		do_one_pass(patterns[idx], start, end);
+	}
 
-			t_start += t_size;
-		}
+	if (idx > 0) {
+		printk(KERN_INFO "early_memtest: wipe out "
+		       "test pattern from memory\n");
+		/* additional test with pattern 0 will do this */
+		do_one_pass(0, start, end);
 	}
-	printk(KERN_CONT "\n");
 }
diff --git a/arch/x86/mm/mmap.c b/arch/x86/mm/mmap.c
index 56fe7124fbec..165829600566 100644
--- a/arch/x86/mm/mmap.c
+++ b/arch/x86/mm/mmap.c
@@ -4,7 +4,7 @@
  * Based on code by Ingo Molnar and Andi Kleen, copyrighted
  * as follows:
  *
- * Copyright 2003-2004 Red Hat Inc., Durham, North Carolina.
+ * Copyright 2003-2009 Red Hat Inc.
  * All Rights Reserved.
  * Copyright 2005 Andi Kleen, SUSE Labs.
  * Copyright 2007 Jiri Kosina, SUSE Labs.
diff --git a/arch/x86/mm/numa_32.c b/arch/x86/mm/numa_32.c
index d1f7439d173c..451fe95a0352 100644
--- a/arch/x86/mm/numa_32.c
+++ b/arch/x86/mm/numa_32.c
@@ -194,7 +194,7 @@ void *alloc_remap(int nid, unsigned long size)
 	size = ALIGN(size, L1_CACHE_BYTES);
 
 	if (!allocation || (allocation + size) >= node_remap_end_vaddr[nid])
-		return 0;
+		return NULL;
 
 	node_remap_alloc_vaddr[nid] += size;
 	memset(allocation, 0, size);
@@ -423,32 +423,6 @@ void __init initmem_init(unsigned long start_pfn,
 	setup_bootmem_allocator();
 }
 
-void __init set_highmem_pages_init(void)
-{
-#ifdef CONFIG_HIGHMEM
-	struct zone *zone;
-	int nid;
-
-	for_each_zone(zone) {
-		unsigned long zone_start_pfn, zone_end_pfn;
-
-		if (!is_highmem(zone))
-			continue;
-
-		zone_start_pfn = zone->zone_start_pfn;
-		zone_end_pfn = zone_start_pfn + zone->spanned_pages;
-
-		nid = zone_to_nid(zone);
-		printk(KERN_INFO "Initializing %s for node %d (%08lx:%08lx)\n",
-				zone->name, nid, zone_start_pfn, zone_end_pfn);
-
-		add_highpages_with_active_regions(nid, zone_start_pfn,
-				 zone_end_pfn);
-	}
-	totalram_pages += totalhigh_pages;
-#endif
-}
-
 #ifdef CONFIG_MEMORY_HOTPLUG
 static int paddr_to_nid(u64 addr)
 {
diff --git a/arch/x86/mm/numa_64.c b/arch/x86/mm/numa_64.c
index f3516da035d1..64c9cf043cdd 100644
--- a/arch/x86/mm/numa_64.c
+++ b/arch/x86/mm/numa_64.c
@@ -20,6 +20,12 @@
 #include <asm/acpi.h>
 #include <asm/k8.h>
 
+#ifdef CONFIG_DEBUG_PER_CPU_MAPS
+# define DBG(x...) printk(KERN_DEBUG x)
+#else
+# define DBG(x...)
+#endif
+
 struct pglist_data *node_data[MAX_NUMNODES] __read_mostly;
 EXPORT_SYMBOL(node_data);
 
@@ -33,6 +39,21 @@ int numa_off __initdata;
 static unsigned long __initdata nodemap_addr;
 static unsigned long __initdata nodemap_size;
 
+DEFINE_PER_CPU(int, node_number) = 0;
+EXPORT_PER_CPU_SYMBOL(node_number);
+
+/*
+ * Map cpu index to node index
+ */
+DEFINE_EARLY_PER_CPU(int, x86_cpu_to_node_map, NUMA_NO_NODE);
+EXPORT_EARLY_PER_CPU_SYMBOL(x86_cpu_to_node_map);
+
+/*
+ * Which logical CPUs are on which nodes
+ */
+cpumask_t *node_to_cpumask_map;
+EXPORT_SYMBOL(node_to_cpumask_map);
+
 /*
  * Given a shift value, try to populate memnodemap[]
  * Returns :
@@ -640,3 +661,199 @@ void __init init_cpu_to_node(void)
 #endif
 
 
+/*
+ * Allocate node_to_cpumask_map based on number of available nodes
+ * Requires node_possible_map to be valid.
+ *
+ * Note: node_to_cpumask() is not valid until after this is done.
+ * (Use CONFIG_DEBUG_PER_CPU_MAPS to check this.)
+ */
+void __init setup_node_to_cpumask_map(void)
+{
+	unsigned int node, num = 0;
+	cpumask_t *map;
+
+	/* setup nr_node_ids if not done yet */
+	if (nr_node_ids == MAX_NUMNODES) {
+		for_each_node_mask(node, node_possible_map)
+			num = node;
+		nr_node_ids = num + 1;
+	}
+
+	/* allocate the map */
+	map = alloc_bootmem_low(nr_node_ids * sizeof(cpumask_t));
+	DBG("node_to_cpumask_map at %p for %d nodes\n", map, nr_node_ids);
+
+	pr_debug("Node to cpumask map at %p for %d nodes\n",
+		 map, nr_node_ids);
+
+	/* node_to_cpumask() will now work */
+	node_to_cpumask_map = map;
+}
+
+void __cpuinit numa_set_node(int cpu, int node)
+{
+	int *cpu_to_node_map = early_per_cpu_ptr(x86_cpu_to_node_map);
+
+	/* early setting, no percpu area yet */
+	if (cpu_to_node_map) {
+		cpu_to_node_map[cpu] = node;
+		return;
+	}
+
+#ifdef CONFIG_DEBUG_PER_CPU_MAPS
+	if (cpu >= nr_cpu_ids || !cpu_possible(cpu)) {
+		printk(KERN_ERR "numa_set_node: invalid cpu# (%d)\n", cpu);
+		dump_stack();
+		return;
+	}
+#endif
+	per_cpu(x86_cpu_to_node_map, cpu) = node;
+
+	if (node != NUMA_NO_NODE)
+		per_cpu(node_number, cpu) = node;
+}
+
+void __cpuinit numa_clear_node(int cpu)
+{
+	numa_set_node(cpu, NUMA_NO_NODE);
+}
+
+#ifndef CONFIG_DEBUG_PER_CPU_MAPS
+
+void __cpuinit numa_add_cpu(int cpu)
+{
+	cpu_set(cpu, node_to_cpumask_map[early_cpu_to_node(cpu)]);
+}
+
+void __cpuinit numa_remove_cpu(int cpu)
+{
+	cpu_clear(cpu, node_to_cpumask_map[early_cpu_to_node(cpu)]);
+}
+
+#else /* CONFIG_DEBUG_PER_CPU_MAPS */
+
+/*
+ * --------- debug versions of the numa functions ---------
+ */
+static void __cpuinit numa_set_cpumask(int cpu, int enable)
+{
+	int node = early_cpu_to_node(cpu);
+	cpumask_t *mask;
+	char buf[64];
+
+	if (node_to_cpumask_map == NULL) {
+		printk(KERN_ERR "node_to_cpumask_map NULL\n");
+		dump_stack();
+		return;
+	}
+
+	mask = &node_to_cpumask_map[node];
+	if (enable)
+		cpu_set(cpu, *mask);
+	else
+		cpu_clear(cpu, *mask);
+
+	cpulist_scnprintf(buf, sizeof(buf), mask);
+	printk(KERN_DEBUG "%s cpu %d node %d: mask now %s\n",
+		enable ? "numa_add_cpu" : "numa_remove_cpu", cpu, node, buf);
+}
+
+void __cpuinit numa_add_cpu(int cpu)
+{
+	numa_set_cpumask(cpu, 1);
+}
+
+void __cpuinit numa_remove_cpu(int cpu)
+{
+	numa_set_cpumask(cpu, 0);
+}
+
+int cpu_to_node(int cpu)
+{
+	if (early_per_cpu_ptr(x86_cpu_to_node_map)) {
+		printk(KERN_WARNING
+			"cpu_to_node(%d): usage too early!\n", cpu);
+		dump_stack();
+		return early_per_cpu_ptr(x86_cpu_to_node_map)[cpu];
+	}
+	return per_cpu(x86_cpu_to_node_map, cpu);
+}
+EXPORT_SYMBOL(cpu_to_node);
+
+/*
+ * Same function as cpu_to_node() but used if called before the
+ * per_cpu areas are setup.
+ */
+int early_cpu_to_node(int cpu)
+{
+	if (early_per_cpu_ptr(x86_cpu_to_node_map))
+		return early_per_cpu_ptr(x86_cpu_to_node_map)[cpu];
+
+	if (!cpu_possible(cpu)) {
+		printk(KERN_WARNING
+			"early_cpu_to_node(%d): no per_cpu area!\n", cpu);
+		dump_stack();
+		return NUMA_NO_NODE;
+	}
+	return per_cpu(x86_cpu_to_node_map, cpu);
+}
+
+
+/* empty cpumask */
+static const cpumask_t cpu_mask_none;
+
+/*
+ * Returns a pointer to the bitmask of CPUs on Node 'node'.
+ */
+const cpumask_t *cpumask_of_node(int node)
+{
+	if (node_to_cpumask_map == NULL) {
+		printk(KERN_WARNING
+			"cpumask_of_node(%d): no node_to_cpumask_map!\n",
+			node);
+		dump_stack();
+		return (const cpumask_t *)&cpu_online_map;
+	}
+	if (node >= nr_node_ids) {
+		printk(KERN_WARNING
+			"cpumask_of_node(%d): node > nr_node_ids(%d)\n",
+			node, nr_node_ids);
+		dump_stack();
+		return &cpu_mask_none;
+	}
+	return &node_to_cpumask_map[node];
+}
+EXPORT_SYMBOL(cpumask_of_node);
+
+/*
+ * Returns a bitmask of CPUs on Node 'node'.
+ *
+ * Side note: this function creates the returned cpumask on the stack
+ * so with a high NR_CPUS count, excessive stack space is used.  The
+ * node_to_cpumask_ptr function should be used whenever possible.
+ */
+cpumask_t node_to_cpumask(int node)
+{
+	if (node_to_cpumask_map == NULL) {
+		printk(KERN_WARNING
+			"node_to_cpumask(%d): no node_to_cpumask_map!\n", node);
+		dump_stack();
+		return cpu_online_map;
+	}
+	if (node >= nr_node_ids) {
+		printk(KERN_WARNING
+			"node_to_cpumask(%d): node > nr_node_ids(%d)\n",
+			node, nr_node_ids);
+		dump_stack();
+		return cpu_mask_none;
+	}
+	return node_to_cpumask_map[node];
+}
+EXPORT_SYMBOL(node_to_cpumask);
+
+/*
+ * --------- end of debug versions of the numa functions ---------
+ */
+
+#endif /* CONFIG_DEBUG_PER_CPU_MAPS */
diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c
index 7233bd7e357b..9c4294986af7 100644
--- a/arch/x86/mm/pageattr.c
+++ b/arch/x86/mm/pageattr.c
@@ -482,6 +482,13 @@ static int split_large_page(pte_t *kpte, unsigned long address)
 	pbase = (pte_t *)page_address(base);
 	paravirt_alloc_pte(&init_mm, page_to_pfn(base));
 	ref_prot = pte_pgprot(pte_clrhuge(*kpte));
+	/*
+	 * If we ever want to utilize the PAT bit, we need to
+	 * update this function to make sure it's converted from
+	 * bit 12 to bit 7 when we cross from the 2MB level to
+	 * the 4K level:
+	 */
+	WARN_ON_ONCE(pgprot_val(ref_prot) & _PAGE_PAT_LARGE);
 
 #ifdef CONFIG_X86_64
 	if (level == PG_LEVEL_1G) {
diff --git a/arch/x86/mm/pat.c b/arch/x86/mm/pat.c
index e0ab173b6974..2ed37158012d 100644
--- a/arch/x86/mm/pat.c
+++ b/arch/x86/mm/pat.c
@@ -31,7 +31,7 @@
 #ifdef CONFIG_X86_PAT
 int __read_mostly pat_enabled = 1;
 
-void __cpuinit pat_disable(char *reason)
+void __cpuinit pat_disable(const char *reason)
 {
 	pat_enabled = 0;
 	printk(KERN_INFO "%s\n", reason);
@@ -43,6 +43,11 @@ static int __init nopat(char *str)
 	return 0;
 }
 early_param("nopat", nopat);
+#else
+static inline void pat_disable(const char *reason)
+{
+	(void)reason;
+}
 #endif
 
 
@@ -79,16 +84,20 @@ void pat_init(void)
 	if (!pat_enabled)
 		return;
 
-	/* Paranoia check. */
-	if (!cpu_has_pat && boot_pat_state) {
-		/*
-		 * If this happens we are on a secondary CPU, but
-		 * switched to PAT on the boot CPU. We have no way to
-		 * undo PAT.
-		 */
-		printk(KERN_ERR "PAT enabled, "
-		       "but not supported by secondary CPU\n");
-		BUG();
+	if (!cpu_has_pat) {
+		if (!boot_pat_state) {
+			pat_disable("PAT not supported by CPU.");
+			return;
+		} else {
+			/*
+			 * If this happens we are on a secondary CPU, but
+			 * switched to PAT on the boot CPU. We have no way to
+			 * undo PAT.
+			 */
+			printk(KERN_ERR "PAT enabled, "
+			       "but not supported by secondary CPU\n");
+			BUG();
+		}
 	}
 
 	/* Set PWT to Write-Combining. All other bits stay the same */
@@ -626,6 +635,33 @@ void unmap_devmem(unsigned long pfn, unsigned long size, pgprot_t vma_prot)
 }
 
 /*
+ * Change the memory type for the physial address range in kernel identity
+ * mapping space if that range is a part of identity map.
+ */
+int kernel_map_sync_memtype(u64 base, unsigned long size, unsigned long flags)
+{
+	unsigned long id_sz;
+
+	if (!pat_enabled || base >= __pa(high_memory))
+		return 0;
+
+	id_sz = (__pa(high_memory) < base + size) ?
+				__pa(high_memory) - base :
+				size;
+
+	if (ioremap_change_attr((unsigned long)__va(base), id_sz, flags) < 0) {
+		printk(KERN_INFO
+			"%s:%d ioremap_change_attr failed %s "
+			"for %Lx-%Lx\n",
+			current->comm, current->pid,
+			cattr_name(flags),
+			base, (unsigned long long)(base + size));
+		return -EINVAL;
+	}
+	return 0;
+}
+
+/*
  * Internal interface to reserve a range of physical memory with prot.
  * Reserved non RAM regions only and after successful reserve_memtype,
  * this func also keeps identity mapping (if any) in sync with this new prot.
@@ -634,7 +670,7 @@ static int reserve_pfn_range(u64 paddr, unsigned long size, pgprot_t *vma_prot,
 				int strict_prot)
 {
 	int is_ram = 0;
-	int id_sz, ret;
+	int ret;
 	unsigned long flags;
 	unsigned long want_flags = (pgprot_val(*vma_prot) & _PAGE_CACHE_MASK);
 
@@ -671,23 +707,8 @@ static int reserve_pfn_range(u64 paddr, unsigned long size, pgprot_t *vma_prot,
 				     flags);
 	}
 
-	/* Need to keep identity mapping in sync */
-	if (paddr >= __pa(high_memory))
-		return 0;
-
-	id_sz = (__pa(high_memory) < paddr + size) ?
-				__pa(high_memory) - paddr :
-				size;
-
-	if (ioremap_change_attr((unsigned long)__va(paddr), id_sz, flags) < 0) {
+	if (kernel_map_sync_memtype(paddr, size, flags) < 0) {
 		free_memtype(paddr, paddr + size);
-		printk(KERN_ERR
-			"%s:%d reserve_pfn_range ioremap_change_attr failed %s "
-			"for %Lx-%Lx\n",
-			current->comm, current->pid,
-			cattr_name(flags),
-			(unsigned long long)paddr,
-			(unsigned long long)(paddr + size));
 		return -EINVAL;
 	}
 	return 0;
diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c
index 86f2ffc43c3d..5b7c7c8464fe 100644
--- a/arch/x86/mm/pgtable.c
+++ b/arch/x86/mm/pgtable.c
@@ -313,6 +313,24 @@ int ptep_clear_flush_young(struct vm_area_struct *vma,
 	return young;
 }
 
+/**
+ * reserve_top_address - reserves a hole in the top of kernel address space
+ * @reserve - size of hole to reserve
+ *
+ * Can be used to relocate the fixmap area and poke a hole in the top
+ * of kernel address space to make room for a hypervisor.
+ */
+void __init reserve_top_address(unsigned long reserve)
+{
+#ifdef CONFIG_X86_32
+	BUG_ON(fixmaps_set > 0);
+	printk(KERN_INFO "Reserving virtual address space above 0x%08x\n",
+	       (int)-reserve);
+	__FIXADDR_TOP = -reserve - PAGE_SIZE;
+	__VMALLOC_RESERVE += reserve;
+#endif
+}
+
 int fixmaps_set;
 
 void __native_set_fixmap(enum fixed_addresses idx, pte_t pte)
diff --git a/arch/x86/mm/pgtable_32.c b/arch/x86/mm/pgtable_32.c
index 0951db9ee519..f2e477c91c1b 100644
--- a/arch/x86/mm/pgtable_32.c
+++ b/arch/x86/mm/pgtable_32.c
@@ -20,6 +20,8 @@
 #include <asm/tlb.h>
 #include <asm/tlbflush.h>
 
+unsigned int __VMALLOC_RESERVE = 128 << 20;
+
 /*
  * Associate a virtual page frame with a given physical page frame 
  * and protection flags for that frame.
@@ -97,22 +99,6 @@ void set_pmd_pfn(unsigned long vaddr, unsigned long pfn, pgprot_t flags)
 unsigned long __FIXADDR_TOP = 0xfffff000;
 EXPORT_SYMBOL(__FIXADDR_TOP);
 
-/**
- * reserve_top_address - reserves a hole in the top of kernel address space
- * @reserve - size of hole to reserve
- *
- * Can be used to relocate the fixmap area and poke a hole in the top
- * of kernel address space to make room for a hypervisor.
- */
-void __init reserve_top_address(unsigned long reserve)
-{
-	BUG_ON(fixmaps_set > 0);
-	printk(KERN_INFO "Reserving virtual address space above 0x%08x\n",
-	       (int)-reserve);
-	__FIXADDR_TOP = -reserve - PAGE_SIZE;
-	__VMALLOC_RESERVE += reserve;
-}
-
 /*
  * vmalloc=size forces the vmalloc area to be exactly 'size'
  * bytes. This can be used to increase (or decrease) the
diff --git a/arch/x86/mm/srat_64.c b/arch/x86/mm/srat_64.c
index 09737c8af074..574c8bc95ef0 100644
--- a/arch/x86/mm/srat_64.c
+++ b/arch/x86/mm/srat_64.c
@@ -20,7 +20,8 @@
 #include <asm/proto.h>
 #include <asm/numa.h>
 #include <asm/e820.h>
-#include <asm/genapic.h>
+#include <asm/apic.h>
+#include <asm/uv/uv.h>
 
 int acpi_numa __initdata;
 
diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
new file mode 100644
index 000000000000..a654d59e4483
--- /dev/null
+++ b/arch/x86/mm/tlb.c
@@ -0,0 +1,295 @@
+#include <linux/init.h>
+
+#include <linux/mm.h>
+#include <linux/spinlock.h>
+#include <linux/smp.h>
+#include <linux/interrupt.h>
+#include <linux/module.h>
+
+#include <asm/tlbflush.h>
+#include <asm/mmu_context.h>
+#include <asm/apic.h>
+#include <asm/uv/uv.h>
+
+DEFINE_PER_CPU_SHARED_ALIGNED(struct tlb_state, cpu_tlbstate)
+			= { &init_mm, 0, };
+
+/*
+ *	Smarter SMP flushing macros.
+ *		c/o Linus Torvalds.
+ *
+ *	These mean you can really definitely utterly forget about
+ *	writing to user space from interrupts. (Its not allowed anyway).
+ *
+ *	Optimizations Manfred Spraul <manfred@colorfullife.com>
+ *
+ *	More scalable flush, from Andi Kleen
+ *
+ *	To avoid global state use 8 different call vectors.
+ *	Each CPU uses a specific vector to trigger flushes on other
+ *	CPUs. Depending on the received vector the target CPUs look into
+ *	the right array slot for the flush data.
+ *
+ *	With more than 8 CPUs they are hashed to the 8 available
+ *	vectors. The limited global vector space forces us to this right now.
+ *	In future when interrupts are split into per CPU domains this could be
+ *	fixed, at the cost of triggering multiple IPIs in some cases.
+ */
+
+union smp_flush_state {
+	struct {
+		struct mm_struct *flush_mm;
+		unsigned long flush_va;
+		spinlock_t tlbstate_lock;
+		DECLARE_BITMAP(flush_cpumask, NR_CPUS);
+	};
+	char pad[CONFIG_X86_INTERNODE_CACHE_BYTES];
+} ____cacheline_internodealigned_in_smp;
+
+/* State is put into the per CPU data section, but padded
+   to a full cache line because other CPUs can access it and we don't
+   want false sharing in the per cpu data segment. */
+static union smp_flush_state flush_state[NUM_INVALIDATE_TLB_VECTORS];
+
+/*
+ * We cannot call mmdrop() because we are in interrupt context,
+ * instead update mm->cpu_vm_mask.
+ */
+void leave_mm(int cpu)
+{
+	if (percpu_read(cpu_tlbstate.state) == TLBSTATE_OK)
+		BUG();
+	cpu_clear(cpu, percpu_read(cpu_tlbstate.active_mm)->cpu_vm_mask);
+	load_cr3(swapper_pg_dir);
+}
+EXPORT_SYMBOL_GPL(leave_mm);
+
+/*
+ *
+ * The flush IPI assumes that a thread switch happens in this order:
+ * [cpu0: the cpu that switches]
+ * 1) switch_mm() either 1a) or 1b)
+ * 1a) thread switch to a different mm
+ * 1a1) cpu_clear(cpu, old_mm->cpu_vm_mask);
+ *	Stop ipi delivery for the old mm. This is not synchronized with
+ *	the other cpus, but smp_invalidate_interrupt ignore flush ipis
+ *	for the wrong mm, and in the worst case we perform a superfluous
+ *	tlb flush.
+ * 1a2) set cpu mmu_state to TLBSTATE_OK
+ *	Now the smp_invalidate_interrupt won't call leave_mm if cpu0
+ *	was in lazy tlb mode.
+ * 1a3) update cpu active_mm
+ *	Now cpu0 accepts tlb flushes for the new mm.
+ * 1a4) cpu_set(cpu, new_mm->cpu_vm_mask);
+ *	Now the other cpus will send tlb flush ipis.
+ * 1a4) change cr3.
+ * 1b) thread switch without mm change
+ *	cpu active_mm is correct, cpu0 already handles
+ *	flush ipis.
+ * 1b1) set cpu mmu_state to TLBSTATE_OK
+ * 1b2) test_and_set the cpu bit in cpu_vm_mask.
+ *	Atomically set the bit [other cpus will start sending flush ipis],
+ *	and test the bit.
+ * 1b3) if the bit was 0: leave_mm was called, flush the tlb.
+ * 2) switch %%esp, ie current
+ *
+ * The interrupt must handle 2 special cases:
+ * - cr3 is changed before %%esp, ie. it cannot use current->{active_,}mm.
+ * - the cpu performs speculative tlb reads, i.e. even if the cpu only
+ *   runs in kernel space, the cpu could load tlb entries for user space
+ *   pages.
+ *
+ * The good news is that cpu mmu_state is local to each cpu, no
+ * write/read ordering problems.
+ */
+
+/*
+ * TLB flush IPI:
+ *
+ * 1) Flush the tlb entries if the cpu uses the mm that's being flushed.
+ * 2) Leave the mm if we are in the lazy tlb mode.
+ *
+ * Interrupts are disabled.
+ */
+
+/*
+ * FIXME: use of asmlinkage is not consistent.  On x86_64 it's noop
+ * but still used for documentation purpose but the usage is slightly
+ * inconsistent.  On x86_32, asmlinkage is regparm(0) but interrupt
+ * entry calls in with the first parameter in %eax.  Maybe define
+ * intrlinkage?
+ */
+#ifdef CONFIG_X86_64
+asmlinkage
+#endif
+void smp_invalidate_interrupt(struct pt_regs *regs)
+{
+	unsigned int cpu;
+	unsigned int sender;
+	union smp_flush_state *f;
+
+	cpu = smp_processor_id();
+	/*
+	 * orig_rax contains the negated interrupt vector.
+	 * Use that to determine where the sender put the data.
+	 */
+	sender = ~regs->orig_ax - INVALIDATE_TLB_VECTOR_START;
+	f = &flush_state[sender];
+
+	if (!cpumask_test_cpu(cpu, to_cpumask(f->flush_cpumask)))
+		goto out;
+		/*
+		 * This was a BUG() but until someone can quote me the
+		 * line from the intel manual that guarantees an IPI to
+		 * multiple CPUs is retried _only_ on the erroring CPUs
+		 * its staying as a return
+		 *
+		 * BUG();
+		 */
+
+	if (f->flush_mm == percpu_read(cpu_tlbstate.active_mm)) {
+		if (percpu_read(cpu_tlbstate.state) == TLBSTATE_OK) {
+			if (f->flush_va == TLB_FLUSH_ALL)
+				local_flush_tlb();
+			else
+				__flush_tlb_one(f->flush_va);
+		} else
+			leave_mm(cpu);
+	}
+out:
+	ack_APIC_irq();
+	smp_mb__before_clear_bit();
+	cpumask_clear_cpu(cpu, to_cpumask(f->flush_cpumask));
+	smp_mb__after_clear_bit();
+	inc_irq_stat(irq_tlb_count);
+}
+
+static void flush_tlb_others_ipi(const struct cpumask *cpumask,
+				 struct mm_struct *mm, unsigned long va)
+{
+	unsigned int sender;
+	union smp_flush_state *f;
+
+	/* Caller has disabled preemption */
+	sender = smp_processor_id() % NUM_INVALIDATE_TLB_VECTORS;
+	f = &flush_state[sender];
+
+	/*
+	 * Could avoid this lock when
+	 * num_online_cpus() <= NUM_INVALIDATE_TLB_VECTORS, but it is
+	 * probably not worth checking this for a cache-hot lock.
+	 */
+	spin_lock(&f->tlbstate_lock);
+
+	f->flush_mm = mm;
+	f->flush_va = va;
+	cpumask_andnot(to_cpumask(f->flush_cpumask),
+		       cpumask, cpumask_of(smp_processor_id()));
+
+	/*
+	 * Make the above memory operations globally visible before
+	 * sending the IPI.
+	 */
+	smp_mb();
+	/*
+	 * We have to send the IPI only to
+	 * CPUs affected.
+	 */
+	apic->send_IPI_mask(to_cpumask(f->flush_cpumask),
+		      INVALIDATE_TLB_VECTOR_START + sender);
+
+	while (!cpumask_empty(to_cpumask(f->flush_cpumask)))
+		cpu_relax();
+
+	f->flush_mm = NULL;
+	f->flush_va = 0;
+	spin_unlock(&f->tlbstate_lock);
+}
+
+void native_flush_tlb_others(const struct cpumask *cpumask,
+			     struct mm_struct *mm, unsigned long va)
+{
+	if (is_uv_system()) {
+		unsigned int cpu;
+
+		cpu = get_cpu();
+		cpumask = uv_flush_tlb_others(cpumask, mm, va, cpu);
+		if (cpumask)
+			flush_tlb_others_ipi(cpumask, mm, va);
+		put_cpu();
+		return;
+	}
+	flush_tlb_others_ipi(cpumask, mm, va);
+}
+
+static int __cpuinit init_smp_flush(void)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(flush_state); i++)
+		spin_lock_init(&flush_state[i].tlbstate_lock);
+
+	return 0;
+}
+core_initcall(init_smp_flush);
+
+void flush_tlb_current_task(void)
+{
+	struct mm_struct *mm = current->mm;
+
+	preempt_disable();
+
+	local_flush_tlb();
+	if (cpumask_any_but(&mm->cpu_vm_mask, smp_processor_id()) < nr_cpu_ids)
+		flush_tlb_others(&mm->cpu_vm_mask, mm, TLB_FLUSH_ALL);
+	preempt_enable();
+}
+
+void flush_tlb_mm(struct mm_struct *mm)
+{
+	preempt_disable();
+
+	if (current->active_mm == mm) {
+		if (current->mm)
+			local_flush_tlb();
+		else
+			leave_mm(smp_processor_id());
+	}
+	if (cpumask_any_but(&mm->cpu_vm_mask, smp_processor_id()) < nr_cpu_ids)
+		flush_tlb_others(&mm->cpu_vm_mask, mm, TLB_FLUSH_ALL);
+
+	preempt_enable();
+}
+
+void flush_tlb_page(struct vm_area_struct *vma, unsigned long va)
+{
+	struct mm_struct *mm = vma->vm_mm;
+
+	preempt_disable();
+
+	if (current->active_mm == mm) {
+		if (current->mm)
+			__flush_tlb_one(va);
+		else
+			leave_mm(smp_processor_id());
+	}
+
+	if (cpumask_any_but(&mm->cpu_vm_mask, smp_processor_id()) < nr_cpu_ids)
+		flush_tlb_others(&mm->cpu_vm_mask, mm, va);
+
+	preempt_enable();
+}
+
+static void do_flush_tlb_all(void *info)
+{
+	unsigned long cpu = smp_processor_id();
+
+	__flush_tlb_all();
+	if (percpu_read(cpu_tlbstate.state) == TLBSTATE_LAZY)
+		leave_mm(cpu);
+}
+
+void flush_tlb_all(void)
+{
+	on_each_cpu(do_flush_tlb_all, NULL, 1);
+}