23 files changed, 231 insertions, 135 deletions

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 9c39095b33fc..bc2fbadff9f9 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -1803,7 +1803,7 @@ config DMAR
 	  remapping devices.
 
 config DMAR_DEFAULT_ON
-	def_bool n
+	def_bool y
 	prompt "Enable DMA Remapping Devices by default"
 	depends on DMAR
 	help
diff --git a/arch/x86/include/asm/iomap.h b/arch/x86/include/asm/iomap.h
index c1f06289b14b..86af26091d6c 100644
--- a/arch/x86/include/asm/iomap.h
+++ b/arch/x86/include/asm/iomap.h
@@ -23,6 +23,9 @@
 #include <asm/pgtable.h>
 #include <asm/tlbflush.h>
 
+int
+is_io_mapping_possible(resource_size_t base, unsigned long size);
+
 void *
 iomap_atomic_prot_pfn(unsigned long pfn, enum km_type type, pgprot_t prot);
 
diff --git a/arch/x86/include/asm/seccomp_32.h b/arch/x86/include/asm/seccomp_32.h
index a6ad87b352c4..b811d6f5780c 100644
--- a/arch/x86/include/asm/seccomp_32.h
+++ b/arch/x86/include/asm/seccomp_32.h
@@ -1,12 +1,6 @@
 #ifndef _ASM_X86_SECCOMP_32_H
 #define _ASM_X86_SECCOMP_32_H
 
-#include <linux/thread_info.h>
-
-#ifdef TIF_32BIT
-#error "unexpected TIF_32BIT on i386"
-#endif
-
 #include <linux/unistd.h>
 
 #define __NR_seccomp_read __NR_read
diff --git a/arch/x86/include/asm/seccomp_64.h b/arch/x86/include/asm/seccomp_64.h
index 4171bb794e9e..84ec1bd161a5 100644
--- a/arch/x86/include/asm/seccomp_64.h
+++ b/arch/x86/include/asm/seccomp_64.h
@@ -1,14 +1,6 @@
 #ifndef _ASM_X86_SECCOMP_64_H
 #define _ASM_X86_SECCOMP_64_H
 
-#include <linux/thread_info.h>
-
-#ifdef TIF_32BIT
-#error "unexpected TIF_32BIT on x86_64"
-#else
-#define TIF_32BIT TIF_IA32
-#endif
-
 #include <linux/unistd.h>
 #include <asm/ia32_unistd.h>
 
diff --git a/arch/x86/kernel/acpi/wakeup_64.S b/arch/x86/kernel/acpi/wakeup_64.S
index bcc293423a70..96258d9dc974 100644
--- a/arch/x86/kernel/acpi/wakeup_64.S
+++ b/arch/x86/kernel/acpi/wakeup_64.S
@@ -13,7 +13,6 @@
 	 * Hooray, we are in Long 64-bit mode (but still running in low memory)
 	 */
 ENTRY(wakeup_long64)
-wakeup_long64:
 	movq	saved_magic, %rax
 	movq	$0x123456789abcdef0, %rdx
 	cmpq	%rdx, %rax
@@ -34,16 +33,12 @@ wakeup_long64:
 
 	movq	saved_rip, %rax
 	jmp	*%rax
+ENDPROC(wakeup_long64)
 
 bogus_64_magic:
 	jmp	bogus_64_magic
 
-	.align 2
-	.p2align 4,,15
-.globl do_suspend_lowlevel
-	.type	do_suspend_lowlevel,@function
-do_suspend_lowlevel:
-.LFB5:
+ENTRY(do_suspend_lowlevel)
 	subq	$8, %rsp
 	xorl	%eax, %eax
 	call	save_processor_state
@@ -67,7 +62,7 @@ do_suspend_lowlevel:
 	pushfq
 	popq	pt_regs_flags(%rax)
 
-	movq	$.L97, saved_rip(%rip)
+	movq	$resume_point, saved_rip(%rip)
 
 	movq	%rsp, saved_rsp
 	movq	%rbp, saved_rbp
@@ -78,14 +73,12 @@ do_suspend_lowlevel:
 	addq	$8, %rsp
 	movl	$3, %edi
 	xorl	%eax, %eax
-	jmp	acpi_enter_sleep_state
-.L97:
-	.p2align 4,,7
-.L99:
-	.align 4
-	movl	$24, %eax
-	movw	%ax, %ds
+	call	acpi_enter_sleep_state
+	/* in case something went wrong, restore the machine status and go on */
+	jmp	resume_point
 
+	.align 4
+resume_point:
 	/* We don't restore %rax, it must be 0 anyway */
 	movq	$saved_context, %rax
 	movq	saved_context_cr4(%rax), %rbx
@@ -117,12 +110,9 @@ do_suspend_lowlevel:
 	xorl	%eax, %eax
 	addq	$8, %rsp
 	jmp	restore_processor_state
-.LFE5:
-.Lfe5:
-	.size	do_suspend_lowlevel, .Lfe5-do_suspend_lowlevel
-	
+ENDPROC(do_suspend_lowlevel)
+
 .data
-ALIGN
 ENTRY(saved_rbp)	.quad	0
 ENTRY(saved_rsi)	.quad	0
 ENTRY(saved_rdi)	.quad	0
diff --git a/arch/x86/kernel/apm_32.c b/arch/x86/kernel/apm_32.c
index 98807bb095ad..266ec6c18b6c 100644
--- a/arch/x86/kernel/apm_32.c
+++ b/arch/x86/kernel/apm_32.c
@@ -1192,6 +1192,7 @@ static int suspend(int vetoable)
 	device_suspend(PMSG_SUSPEND);
 	local_irq_disable();
 	device_power_down(PMSG_SUSPEND);
+	sysdev_suspend(PMSG_SUSPEND);
 
 	local_irq_enable();
 
@@ -1208,6 +1209,7 @@ static int suspend(int vetoable)
 	if (err != APM_SUCCESS)
 		apm_error("suspend", err);
 	err = (err == APM_SUCCESS) ? 0 : -EIO;
+	sysdev_resume();
 	device_power_up(PMSG_RESUME);
 	local_irq_enable();
 	device_resume(PMSG_RESUME);
@@ -1228,6 +1230,7 @@ static void standby(void)
 
 	local_irq_disable();
 	device_power_down(PMSG_SUSPEND);
+	sysdev_suspend(PMSG_SUSPEND);
 	local_irq_enable();
 
 	err = set_system_power_state(APM_STATE_STANDBY);
@@ -1235,6 +1238,7 @@ static void standby(void)
 		apm_error("standby", err);
 
 	local_irq_disable();
+	sysdev_resume();
 	device_power_up(PMSG_RESUME);
 	local_irq_enable();
 }
diff --git a/arch/x86/kernel/cpu/mcheck/mce_64.c b/arch/x86/kernel/cpu/mcheck/mce_64.c
index 25cf624eccb7..fe79985ce0f2 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_64.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_64.c
@@ -490,7 +490,7 @@ static void __cpuinit mce_cpu_quirks(struct cpuinfo_x86 *c)
 
 }
 
-static void __cpuinit mce_cpu_features(struct cpuinfo_x86 *c)
+static void mce_cpu_features(struct cpuinfo_x86 *c)
 {
 	switch (c->x86_vendor) {
 	case X86_VENDOR_INTEL:
diff --git a/arch/x86/kernel/cpu/mcheck/mce_amd_64.c b/arch/x86/kernel/cpu/mcheck/mce_amd_64.c
index 8ae8c4ff094d..f2ee0ae29bd6 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_amd_64.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_amd_64.c
@@ -121,7 +121,7 @@ static long threshold_restart_bank(void *_tr)
 }
 
 /* cpu init entry point, called from mce.c with preempt off */
-void __cpuinit mce_amd_feature_init(struct cpuinfo_x86 *c)
+void mce_amd_feature_init(struct cpuinfo_x86 *c)
 {
 	unsigned int bank, block;
 	unsigned int cpu = smp_processor_id();
diff --git a/arch/x86/kernel/cpu/mcheck/mce_intel_64.c b/arch/x86/kernel/cpu/mcheck/mce_intel_64.c
index 4b48f251fd39..f44c36624360 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_intel_64.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_intel_64.c
@@ -30,7 +30,7 @@ asmlinkage void smp_thermal_interrupt(void)
 	irq_exit();
 }
 
-static void __cpuinit intel_init_thermal(struct cpuinfo_x86 *c)
+static void intel_init_thermal(struct cpuinfo_x86 *c)
 {
 	u32 l, h;
 	int tm2 = 0;
@@ -84,7 +84,7 @@ static void __cpuinit intel_init_thermal(struct cpuinfo_x86 *c)
 	return;
 }
 
-void __cpuinit mce_intel_feature_init(struct cpuinfo_x86 *c)
+void mce_intel_feature_init(struct cpuinfo_x86 *c)
 {
 	intel_init_thermal(c);
 }
diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c
index 5a4c23d89892..06ca07f6ad86 100644
--- a/arch/x86/kernel/ptrace.c
+++ b/arch/x86/kernel/ptrace.c
@@ -1388,7 +1388,7 @@ void send_sigtrap(struct task_struct *tsk, struct pt_regs *regs,
 #ifdef CONFIG_X86_32
 # define IS_IA32	1
 #elif defined CONFIG_IA32_EMULATION
-# define IS_IA32	test_thread_flag(TIF_IA32)
+# define IS_IA32	is_compat_task()
 #else
 # define IS_IA32	0
 #endif
diff --git a/arch/x86/kernel/time_64.c b/arch/x86/kernel/time_64.c
index e6e695acd725..241ec3923f61 100644
--- a/arch/x86/kernel/time_64.c
+++ b/arch/x86/kernel/time_64.c
@@ -115,7 +115,7 @@ unsigned long __init calibrate_cpu(void)
 
 static struct irqaction irq0 = {
 	.handler	= timer_interrupt,
-	.flags		= IRQF_DISABLED | IRQF_IRQPOLL | IRQF_NOBALANCING,
+	.flags		= IRQF_DISABLED | IRQF_IRQPOLL | IRQF_NOBALANCING | IRQF_TIMER,
 	.mask		= CPU_MASK_NONE,
 	.name		= "timer"
 };
diff --git a/arch/x86/kernel/vmiclock_32.c b/arch/x86/kernel/vmiclock_32.c
index c4c1f9e09402..e5b088fffa40 100644
--- a/arch/x86/kernel/vmiclock_32.c
+++ b/arch/x86/kernel/vmiclock_32.c
@@ -202,7 +202,7 @@ static irqreturn_t vmi_timer_interrupt(int irq, void *dev_id)
 static struct irqaction vmi_clock_action  = {
 	.name 		= "vmi-timer",
 	.handler 	= vmi_timer_interrupt,
-	.flags 		= IRQF_DISABLED | IRQF_NOBALANCING,
+	.flags 		= IRQF_DISABLED | IRQF_NOBALANCING | IRQF_TIMER,
 	.mask 		= CPU_MASK_ALL,
 };
 
@@ -283,10 +283,13 @@ void __devinit vmi_time_ap_init(void)
 #endif
 
 /** vmi clocksource */
+static struct clocksource clocksource_vmi;
 
 static cycle_t read_real_cycles(void)
 {
-	return vmi_timer_ops.get_cycle_counter(VMI_CYCLES_REAL);
+	cycle_t ret = (cycle_t)vmi_timer_ops.get_cycle_counter(VMI_CYCLES_REAL);
+	return ret >= clocksource_vmi.cycle_last ?
+		ret : clocksource_vmi.cycle_last;
 }
 
 static struct clocksource clocksource_vmi = {
diff --git a/arch/x86/mach-default/setup.c b/arch/x86/mach-default/setup.c
index a265a7c63190..50b591871128 100644
--- a/arch/x86/mach-default/setup.c
+++ b/arch/x86/mach-default/setup.c
@@ -96,7 +96,7 @@ void __init trap_init_hook(void)
 
 static struct irqaction irq0  = {
 	.handler = timer_interrupt,
-	.flags = IRQF_DISABLED | IRQF_NOBALANCING | IRQF_IRQPOLL,
+	.flags = IRQF_DISABLED | IRQF_NOBALANCING | IRQF_IRQPOLL | IRQF_TIMER,
 	.mask = CPU_MASK_NONE,
 	.name = "timer"
 };
diff --git a/arch/x86/mach-voyager/setup.c b/arch/x86/mach-voyager/setup.c
index d914a7996a66..8e5118371f0f 100644
--- a/arch/x86/mach-voyager/setup.c
+++ b/arch/x86/mach-voyager/setup.c
@@ -56,7 +56,7 @@ void __init trap_init_hook(void)
 
 static struct irqaction irq0 = {
 	.handler = timer_interrupt,
-	.flags = IRQF_DISABLED | IRQF_NOBALANCING | IRQF_IRQPOLL,
+	.flags = IRQF_DISABLED | IRQF_NOBALANCING | IRQF_IRQPOLL | IRQF_TIMER,
 	.mask = CPU_MASK_NONE,
 	.name = "timer"
 };
diff --git a/arch/x86/mach-voyager/voyager_smp.c b/arch/x86/mach-voyager/voyager_smp.c
index 7ffcdeec4631..b9cc84a2a4fc 100644
--- a/arch/x86/mach-voyager/voyager_smp.c
+++ b/arch/x86/mach-voyager/voyager_smp.c
@@ -65,7 +65,7 @@ static volatile unsigned long smp_invalidate_needed;
 
 /* Bitmask of CPUs present in the system - exported by i386_syms.c, used
  * by scheduler but indexed physically */
-cpumask_t phys_cpu_present_map = CPU_MASK_NONE;
+static cpumask_t voyager_phys_cpu_present_map = CPU_MASK_NONE;
 
 /* The internal functions */
 static void send_CPI(__u32 cpuset, __u8 cpi);
@@ -366,19 +366,19 @@ void __init find_smp_config(void)
 	/* set up everything for just this CPU, we can alter
 	 * this as we start the other CPUs later */
 	/* now get the CPU disposition from the extended CMOS */
-	cpus_addr(phys_cpu_present_map)[0] =
+	cpus_addr(voyager_phys_cpu_present_map)[0] =
 	    voyager_extended_cmos_read(VOYAGER_PROCESSOR_PRESENT_MASK);
-	cpus_addr(phys_cpu_present_map)[0] |=
+	cpus_addr(voyager_phys_cpu_present_map)[0] |=
 	    voyager_extended_cmos_read(VOYAGER_PROCESSOR_PRESENT_MASK + 1) << 8;
-	cpus_addr(phys_cpu_present_map)[0] |=
+	cpus_addr(voyager_phys_cpu_present_map)[0] |=
 	    voyager_extended_cmos_read(VOYAGER_PROCESSOR_PRESENT_MASK +
 				       2) << 16;
-	cpus_addr(phys_cpu_present_map)[0] |=
+	cpus_addr(voyager_phys_cpu_present_map)[0] |=
 	    voyager_extended_cmos_read(VOYAGER_PROCESSOR_PRESENT_MASK +
 				       3) << 24;
-	init_cpu_possible(&phys_cpu_present_map);
-	printk("VOYAGER SMP: phys_cpu_present_map = 0x%lx\n",
-	       cpus_addr(phys_cpu_present_map)[0]);
+	init_cpu_possible(&voyager_phys_cpu_present_map);
+	printk("VOYAGER SMP: voyager_phys_cpu_present_map = 0x%lx\n",
+	       cpus_addr(voyager_phys_cpu_present_map)[0]);
 	/* Here we set up the VIC to enable SMP */
 	/* enable the CPIs by writing the base vector to their register */
 	outb(VIC_DEFAULT_CPI_BASE, VIC_CPI_BASE_REGISTER);
@@ -628,15 +628,15 @@ void __init smp_boot_cpus(void)
 		/* now that the cat has probed the Voyager System Bus, sanity
 		 * check the cpu map */
 		if (((voyager_quad_processors | voyager_extended_vic_processors)
-		     & cpus_addr(phys_cpu_present_map)[0]) !=
-		    cpus_addr(phys_cpu_present_map)[0]) {
+		     & cpus_addr(voyager_phys_cpu_present_map)[0]) !=
+		    cpus_addr(voyager_phys_cpu_present_map)[0]) {
 			/* should panic */
 			printk("\n\n***WARNING*** "
 			       "Sanity check of CPU present map FAILED\n");
 		}
 	} else if (voyager_level == 4)
 		voyager_extended_vic_processors =
-		    cpus_addr(phys_cpu_present_map)[0];
+		    cpus_addr(voyager_phys_cpu_present_map)[0];
 
 	/* this sets up the idle task to run on the current cpu */
 	voyager_extended_cpus = 1;
@@ -670,7 +670,7 @@ void __init smp_boot_cpus(void)
 	/* loop over all the extended VIC CPUs and boot them.  The
 	 * Quad CPUs must be bootstrapped by their extended VIC cpu */
 	for (i = 0; i < nr_cpu_ids; i++) {
-		if (i == boot_cpu_id || !cpu_isset(i, phys_cpu_present_map))
+		if (i == boot_cpu_id || !cpu_isset(i, voyager_phys_cpu_present_map))
 			continue;
 		do_boot_cpu(i);
 		/* This udelay seems to be needed for the Quad boots
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index e6d36b490250..b1352250096e 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -714,6 +714,8 @@ unsigned long __init_refok init_memory_mapping(unsigned long start,
 	pos = start_pfn << PAGE_SHIFT;
 	end_pfn = ((pos + (PMD_SIZE - 1)) >> PMD_SHIFT)
 			<< (PMD_SHIFT - PAGE_SHIFT);
+	if (end_pfn > (end >> PAGE_SHIFT))
+		end_pfn = end >> PAGE_SHIFT;
 	if (start_pfn < end_pfn) {
 		nr_range = save_mr(mr, nr_range, start_pfn, end_pfn, 0);
 		pos = end_pfn << PAGE_SHIFT;
diff --git a/arch/x86/mm/iomap_32.c b/arch/x86/mm/iomap_32.c
index ca53224fc56c..04102d42ff42 100644
--- a/arch/x86/mm/iomap_32.c
+++ b/arch/x86/mm/iomap_32.c
@@ -20,6 +20,17 @@
 #include <asm/pat.h>
 #include <linux/module.h>
 
+int is_io_mapping_possible(resource_size_t base, unsigned long size)
+{
+#ifndef CONFIG_X86_PAE
+	/* There is no way to map greater than 1 << 32 address without PAE */
+	if (base + size > 0x100000000ULL)
+		return 0;
+#endif
+	return 1;
+}
+EXPORT_SYMBOL_GPL(is_io_mapping_possible);
+
 /* Map 'pfn' using fixed map 'type' and protections 'prot'
  */
 void *
diff --git a/arch/x86/mm/kmmio.c b/arch/x86/mm/kmmio.c
index 93d82038af4b..9f205030d9aa 100644
--- a/arch/x86/mm/kmmio.c
+++ b/arch/x86/mm/kmmio.c
@@ -32,11 +32,14 @@ struct kmmio_fault_page {
 	struct list_head list;
 	struct kmmio_fault_page *release_next;
 	unsigned long page; /* location of the fault page */
+	bool old_presence; /* page presence prior to arming */
+	bool armed;
 
 	/*
 	 * Number of times this page has been registered as a part
 	 * of a probe. If zero, page is disarmed and this may be freed.
-	 * Used only by writers (RCU).
+	 * Used only by writers (RCU) and post_kmmio_handler().
+	 * Protected by kmmio_lock, when linked into kmmio_page_table.
 	 */
 	int count;
 };
@@ -105,57 +108,85 @@ static struct kmmio_fault_page *get_kmmio_fault_page(unsigned long page)
 	return NULL;
 }
 
-static void set_page_present(unsigned long addr, bool present,
-							unsigned int *pglevel)
+static void set_pmd_presence(pmd_t *pmd, bool present, bool *old)
+{
+	pmdval_t v = pmd_val(*pmd);
+	*old = !!(v & _PAGE_PRESENT);
+	v &= ~_PAGE_PRESENT;
+	if (present)
+		v |= _PAGE_PRESENT;
+	set_pmd(pmd, __pmd(v));
+}
+
+static void set_pte_presence(pte_t *pte, bool present, bool *old)
+{
+	pteval_t v = pte_val(*pte);
+	*old = !!(v & _PAGE_PRESENT);
+	v &= ~_PAGE_PRESENT;
+	if (present)
+		v |= _PAGE_PRESENT;
+	set_pte_atomic(pte, __pte(v));
+}
+
+static int set_page_presence(unsigned long addr, bool present, bool *old)
 {
-	pteval_t pteval;
-	pmdval_t pmdval;
 	unsigned int level;
-	pmd_t *pmd;
 	pte_t *pte = lookup_address(addr, &level);
 
 	if (!pte) {
 		pr_err("kmmio: no pte for page 0x%08lx\n", addr);
-		return;
+		return -1;
 	}
 
-	if (pglevel)
-		*pglevel = level;
-
 	switch (level) {
 	case PG_LEVEL_2M:
-		pmd = (pmd_t *)pte;
-		pmdval = pmd_val(*pmd) & ~_PAGE_PRESENT;
-		if (present)
-			pmdval |= _PAGE_PRESENT;
-		set_pmd(pmd, __pmd(pmdval));
+		set_pmd_presence((pmd_t *)pte, present, old);
 		break;
-
 	case PG_LEVEL_4K:
-		pteval = pte_val(*pte) & ~_PAGE_PRESENT;
-		if (present)
-			pteval |= _PAGE_PRESENT;
-		set_pte_atomic(pte, __pte(pteval));
+		set_pte_presence(pte, present, old);
 		break;
-
 	default:
 		pr_err("kmmio: unexpected page level 0x%x.\n", level);
-		return;
+		return -1;
 	}
 
 	__flush_tlb_one(addr);
+	return 0;
 }
 
-/** Mark the given page as not present. Access to it will trigger a fault. */
-static void arm_kmmio_fault_page(unsigned long page, unsigned int *pglevel)
+/*
+ * Mark the given page as not present. Access to it will trigger a fault.
+ *
+ * Struct kmmio_fault_page is protected by RCU and kmmio_lock, but the
+ * protection is ignored here. RCU read lock is assumed held, so the struct
+ * will not disappear unexpectedly. Furthermore, the caller must guarantee,
+ * that double arming the same virtual address (page) cannot occur.
+ *
+ * Double disarming on the other hand is allowed, and may occur when a fault
+ * and mmiotrace shutdown happen simultaneously.
+ */
+static int arm_kmmio_fault_page(struct kmmio_fault_page *f)
 {
-	set_page_present(page & PAGE_MASK, false, pglevel);
+	int ret;
+	WARN_ONCE(f->armed, KERN_ERR "kmmio page already armed.\n");
+	if (f->armed) {
+		pr_warning("kmmio double-arm: page 0x%08lx, ref %d, old %d\n",
+					f->page, f->count, f->old_presence);
+	}
+	ret = set_page_presence(f->page, false, &f->old_presence);
+	WARN_ONCE(ret < 0, KERN_ERR "kmmio arming 0x%08lx failed.\n", f->page);
+	f->armed = true;
+	return ret;
 }
 
-/** Mark the given page as present. */
-static void disarm_kmmio_fault_page(unsigned long page, unsigned int *pglevel)
+/** Restore the given page to saved presence state. */
+static void disarm_kmmio_fault_page(struct kmmio_fault_page *f)
 {
-	set_page_present(page & PAGE_MASK, true, pglevel);
+	bool tmp;
+	int ret = set_page_presence(f->page, f->old_presence, &tmp);
+	WARN_ONCE(ret < 0,
+			KERN_ERR "kmmio disarming 0x%08lx failed.\n", f->page);
+	f->armed = false;
 }
 
 /*
@@ -202,28 +233,32 @@ int kmmio_handler(struct pt_regs *regs, unsigned long addr)
 
 	ctx = &get_cpu_var(kmmio_ctx);
 	if (ctx->active) {
-		disarm_kmmio_fault_page(faultpage->page, NULL);
 		if (addr == ctx->addr) {
 			/*
-			 * On SMP we sometimes get recursive probe hits on the
-			 * same address. Context is already saved, fall out.
+			 * A second fault on the same page means some other
+			 * condition needs handling by do_page_fault(), the
+			 * page really not being present is the most common.
 			 */
-			pr_debug("kmmio: duplicate probe hit on CPU %d, for "
-						"address 0x%08lx.\n",
-						smp_processor_id(), addr);
-			ret = 1;
-			goto no_kmmio_ctx;
-		}
-		/*
-		 * Prevent overwriting already in-flight context.
-		 * This should not happen, let's hope disarming at least
-		 * prevents a panic.
-		 */
-		pr_emerg("kmmio: recursive probe hit on CPU %d, "
+			pr_debug("kmmio: secondary hit for 0x%08lx CPU %d.\n",
+					addr, smp_processor_id());
+
+			if (!faultpage->old_presence)
+				pr_info("kmmio: unexpected secondary hit for "
+					"address 0x%08lx on CPU %d.\n", addr,
+					smp_processor_id());
+		} else {
+			/*
+			 * Prevent overwriting already in-flight context.
+			 * This should not happen, let's hope disarming at
+			 * least prevents a panic.
+			 */
+			pr_emerg("kmmio: recursive probe hit on CPU %d, "
 					"for address 0x%08lx. Ignoring.\n",
 					smp_processor_id(), addr);
-		pr_emerg("kmmio: previous hit was at 0x%08lx.\n",
-					ctx->addr);
+			pr_emerg("kmmio: previous hit was at 0x%08lx.\n",
+						ctx->addr);
+			disarm_kmmio_fault_page(faultpage);
+		}
 		goto no_kmmio_ctx;
 	}
 	ctx->active++;
@@ -244,7 +279,7 @@ int kmmio_handler(struct pt_regs *regs, unsigned long addr)
 	regs->flags &= ~X86_EFLAGS_IF;
 
 	/* Now we set present bit in PTE and single step. */
-	disarm_kmmio_fault_page(ctx->fpage->page, NULL);
+	disarm_kmmio_fault_page(ctx->fpage);
 
 	/*
 	 * If another cpu accesses the same page while we are stepping,
@@ -275,7 +310,7 @@ static int post_kmmio_handler(unsigned long condition, struct pt_regs *regs)
 	struct kmmio_context *ctx = &get_cpu_var(kmmio_ctx);
 
 	if (!ctx->active) {
-		pr_debug("kmmio: spurious debug trap on CPU %d.\n",
+		pr_warning("kmmio: spurious debug trap on CPU %d.\n",
 							smp_processor_id());
 		goto out;
 	}
@@ -283,7 +318,11 @@ static int post_kmmio_handler(unsigned long condition, struct pt_regs *regs)
 	if (ctx->probe && ctx->probe->post_handler)
 		ctx->probe->post_handler(ctx->probe, condition, regs);
 
-	arm_kmmio_fault_page(ctx->fpage->page, NULL);
+	/* Prevent racing against release_kmmio_fault_page(). */
+	spin_lock(&kmmio_lock);
+	if (ctx->fpage->count)
+		arm_kmmio_fault_page(ctx->fpage);
+	spin_unlock(&kmmio_lock);
 
 	regs->flags &= ~X86_EFLAGS_TF;
 	regs->flags |= ctx->saved_flags;
@@ -315,20 +354,24 @@ static int add_kmmio_fault_page(unsigned long page)
 	f = get_kmmio_fault_page(page);
 	if (f) {
 		if (!f->count)
-			arm_kmmio_fault_page(f->page, NULL);
+			arm_kmmio_fault_page(f);
 		f->count++;
 		return 0;
 	}
 
-	f = kmalloc(sizeof(*f), GFP_ATOMIC);
+	f = kzalloc(sizeof(*f), GFP_ATOMIC);
 	if (!f)
 		return -1;
 
 	f->count = 1;
 	f->page = page;
-	list_add_rcu(&f->list, kmmio_page_list(f->page));
 
-	arm_kmmio_fault_page(f->page, NULL);
+	if (arm_kmmio_fault_page(f)) {
+		kfree(f);
+		return -1;
+	}
+
+	list_add_rcu(&f->list, kmmio_page_list(f->page));
 
 	return 0;
 }
@@ -347,7 +390,7 @@ static void release_kmmio_fault_page(unsigned long page,
 	f->count--;
 	BUG_ON(f->count < 0);
 	if (!f->count) {
-		disarm_kmmio_fault_page(f->page, NULL);
+		disarm_kmmio_fault_page(f);
 		f->release_next = *release_list;
 		*release_list = f;
 	}
diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c
index 8ca0d8566fc8..7be47d1a97e4 100644
--- a/arch/x86/mm/pageattr.c
+++ b/arch/x86/mm/pageattr.c
@@ -508,18 +508,13 @@ static int split_large_page(pte_t *kpte, unsigned long address)
 #endif
 
 	/*
-	 * Install the new, split up pagetable. Important details here:
+	 * Install the new, split up pagetable.
 	 *
-	 * On Intel the NX bit of all levels must be cleared to make a
-	 * page executable. See section 4.13.2 of Intel 64 and IA-32
-	 * Architectures Software Developer's Manual).
-	 *
-	 * Mark the entry present. The current mapping might be
-	 * set to not present, which we preserved above.
+	 * We use the standard kernel pagetable protections for the new
+	 * pagetable protections, the actual ptes set above control the
+	 * primary protection behavior:
 	 */
-	ref_prot = pte_pgprot(pte_mkexec(pte_clrhuge(*kpte)));
-	pgprot_val(ref_prot) |= _PAGE_PRESENT;
-	__set_pmd_pte(kpte, address, mk_pte(base, ref_prot));
+	__set_pmd_pte(kpte, address, mk_pte(base, __pgprot(_KERNPG_TABLE)));
 	base = NULL;
 
 out_unlock:
diff --git a/arch/x86/mm/pat.c b/arch/x86/mm/pat.c
index aebbf67a79d0..e0ab173b6974 100644
--- a/arch/x86/mm/pat.c
+++ b/arch/x86/mm/pat.c
@@ -11,6 +11,7 @@
 #include <linux/bootmem.h>
 #include <linux/debugfs.h>
 #include <linux/kernel.h>
+#include <linux/module.h>
 #include <linux/gfp.h>
 #include <linux/mm.h>
 #include <linux/fs.h>
@@ -868,6 +869,7 @@ pgprot_t pgprot_writecombine(pgprot_t prot)
 	else
 		return pgprot_noncached(prot);
 }
+EXPORT_SYMBOL_GPL(pgprot_writecombine);
 
 #if defined(CONFIG_DEBUG_FS) && defined(CONFIG_X86_PAT)
 
diff --git a/arch/x86/mm/testmmiotrace.c b/arch/x86/mm/testmmiotrace.c
index ab50a8d7402c..427fd1b56df5 100644
--- a/arch/x86/mm/testmmiotrace.c
+++ b/arch/x86/mm/testmmiotrace.c
@@ -1,5 +1,5 @@
 /*
- * Written by Pekka Paalanen, 2008 <pq@iki.fi>
+ * Written by Pekka Paalanen, 2008-2009 <pq@iki.fi>
  */
 #include <linux/module.h>
 #include <linux/io.h>
@@ -9,35 +9,74 @@
 
 static unsigned long mmio_address;
 module_param(mmio_address, ulong, 0);
-MODULE_PARM_DESC(mmio_address, "Start address of the mapping of 16 kB.");
+MODULE_PARM_DESC(mmio_address, " Start address of the mapping of 16 kB "
+				"(or 8 MB if read_far is non-zero).");
+
+static unsigned long read_far = 0x400100;
+module_param(read_far, ulong, 0);
+MODULE_PARM_DESC(read_far, " Offset of a 32-bit read within 8 MB "
+				"(default: 0x400100).");
+
+static unsigned v16(unsigned i)
+{
+	return i * 12 + 7;
+}
+
+static unsigned v32(unsigned i)
+{
+	return i * 212371 + 13;
+}
 
 static void do_write_test(void __iomem *p)
 {
 	unsigned int i;
+	pr_info(MODULE_NAME ": write test.\n");
 	mmiotrace_printk("Write test.\n");
+
 	for (i = 0; i < 256; i++)
 		iowrite8(i, p + i);
+
 	for (i = 1024; i < (5 * 1024); i += 2)
-		iowrite16(i * 12 + 7, p + i);
+		iowrite16(v16(i), p + i);
+
 	for (i = (5 * 1024); i < (16 * 1024); i += 4)
-		iowrite32(i * 212371 + 13, p + i);
+		iowrite32(v32(i), p + i);
 }
 
 static void do_read_test(void __iomem *p)
 {
 	unsigned int i;
+	unsigned errs[3] = { 0 };
+	pr_info(MODULE_NAME ": read test.\n");
 	mmiotrace_printk("Read test.\n");
+
 	for (i = 0; i < 256; i++)
-		ioread8(p + i);
+		if (ioread8(p + i) != i)
+			++errs[0];
+
 	for (i = 1024; i < (5 * 1024); i += 2)
-		ioread16(p + i);
+		if (ioread16(p + i) != v16(i))
+			++errs[1];
+
 	for (i = (5 * 1024); i < (16 * 1024); i += 4)
-		ioread32(p + i);
+		if (ioread32(p + i) != v32(i))
+			++errs[2];
+
+	mmiotrace_printk("Read errors: 8-bit %d, 16-bit %d, 32-bit %d.\n",
+						errs[0], errs[1], errs[2]);
 }
 
-static void do_test(void)
+static void do_read_far_test(void __iomem *p)
 {
-	void __iomem *p = ioremap_nocache(mmio_address, 0x4000);
+	pr_info(MODULE_NAME ": read far test.\n");
+	mmiotrace_printk("Read far test.\n");
+
+	ioread32(p + read_far);
+}
+
+static void do_test(unsigned long size)
+{
+	void __iomem *p = ioremap_nocache(mmio_address, size);
 	if (!p) {
 		pr_err(MODULE_NAME ": could not ioremap, aborting.\n");
 		return;
@@ -45,11 +84,15 @@ static void do_test(void)
 	mmiotrace_printk("ioremap returned %p.\n", p);
 	do_write_test(p);
 	do_read_test(p);
+	if (read_far && read_far < size - 4)
+		do_read_far_test(p);
 	iounmap(p);
 }
 
 static int __init init(void)
 {
+	unsigned long size = (read_far) ? (8 << 20) : (16 << 10);
+
 	if (mmio_address == 0) {
 		pr_err(MODULE_NAME ": you have to use the module argument "
 							"mmio_address.\n");
@@ -58,10 +101,11 @@ static int __init init(void)
 		return -ENXIO;
 	}
 
-	pr_warning(MODULE_NAME ": WARNING: mapping 16 kB @ 0x%08lx "
-					"in PCI address space, and writing "
-					"rubbish in there.\n", mmio_address);
-	do_test();
+	pr_warning(MODULE_NAME ": WARNING: mapping %lu kB @ 0x%08lx in PCI "
+		"address space, and writing 16 kB of rubbish in there.\n",
+		 size >> 10, mmio_address);
+	do_test(size);
+	pr_info(MODULE_NAME ": All done.\n");
 	return 0;
 }
 
diff --git a/arch/x86/oprofile/op_model_ppro.c b/arch/x86/oprofile/op_model_ppro.c
index e9f80c744cf3..10131fbdaada 100644
--- a/arch/x86/oprofile/op_model_ppro.c
+++ b/arch/x86/oprofile/op_model_ppro.c
@@ -78,8 +78,18 @@ static void ppro_setup_ctrs(struct op_msrs const * const msrs)
 	if (cpu_has_arch_perfmon) {
 		union cpuid10_eax eax;
 		eax.full = cpuid_eax(0xa);
-		if (counter_width < eax.split.bit_width)
-			counter_width = eax.split.bit_width;
+
+		/*
+		 * For Core2 (family 6, model 15), don't reset the
+		 * counter width:
+		 */
+		if (!(eax.split.version_id == 0 &&
+			current_cpu_data.x86 == 6 &&
+				current_cpu_data.x86_model == 15)) {
+
+			if (counter_width < eax.split.bit_width)
+				counter_width = eax.split.bit_width;
+		}
 	}
 
 	/* clear all counters */
diff --git a/arch/x86/xen/enlighten.c b/arch/x86/xen/enlighten.c
index bea215230b20..b58e96338149 100644
--- a/arch/x86/xen/enlighten.c
+++ b/arch/x86/xen/enlighten.c
@@ -1672,6 +1672,9 @@ asmlinkage void __init xen_start_kernel(void)
 	   possible map and a non-dummy shared_info. */
 	per_cpu(xen_vcpu, 0) = &HYPERVISOR_shared_info->vcpu_info[0];
 
+	local_irq_disable();
+	early_boot_irqs_off();
+
 	xen_raw_console_write("mapping kernel into physical memory\n");
 	pgd = xen_setup_kernel_pagetable(pgd, xen_start_info->nr_pages);