24 files changed, 174 insertions, 117 deletions

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/apic.c b/arch/x86/kernel/apic.c
index 115449f869ee..570f36e44e59 100644
--- a/arch/x86/kernel/apic.c
+++ b/arch/x86/kernel/apic.c
@@ -862,7 +862,7 @@ void clear_local_APIC(void)
 	}
 
 	/* lets not touch this if we didn't frob it */
-#if defined(CONFIG_X86_MCE_P4THERMAL) || defined(X86_MCE_INTEL)
+#if defined(CONFIG_X86_MCE_P4THERMAL) || defined(CONFIG_X86_MCE_INTEL)
 	if (maxlvt >= 5) {
 		v = apic_read(APIC_LVTTHMR);
 		apic_write(APIC_LVTTHMR, v | APIC_LVT_MASKED);
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/cpufreq/p4-clockmod.c b/arch/x86/kernel/cpu/cpufreq/p4-clockmod.c
index b585e04cbc9e..3178c3acd97e 100644
--- a/arch/x86/kernel/cpu/cpufreq/p4-clockmod.c
+++ b/arch/x86/kernel/cpu/cpufreq/p4-clockmod.c
@@ -277,7 +277,6 @@ static struct cpufreq_driver p4clockmod_driver = {
 	.name		= "p4-clockmod",
 	.owner		= THIS_MODULE,
 	.attr		= p4clockmod_attr,
-	.hide_interface	= 1,
 };
 
 
diff --git a/arch/x86/kernel/cpu/cpufreq/powernow-k8.c b/arch/x86/kernel/cpu/cpufreq/powernow-k8.c
index fb039cd345d8..6428aa17b40e 100644
--- a/arch/x86/kernel/cpu/cpufreq/powernow-k8.c
+++ b/arch/x86/kernel/cpu/cpufreq/powernow-k8.c
@@ -1157,8 +1157,7 @@ static int __cpuinit powernowk8_cpu_init(struct cpufreq_policy *pol)
 	data->cpu = pol->cpu;
 	data->currpstate = HW_PSTATE_INVALID;
 
-	rc = powernow_k8_cpu_init_acpi(data);
-	if (rc) {
+	if (powernow_k8_cpu_init_acpi(data)) {
 		/*
 		 * Use the PSB BIOS structure. This is only availabe on
 		 * an UP version, and is deprecated by AMD.
@@ -1176,17 +1175,20 @@ static int __cpuinit powernowk8_cpu_init(struct cpufreq_policy *pol)
 			       "ACPI maintainers and complain to your BIOS "
 			       "vendor.\n");
 #endif
-			goto err_out;
+			kfree(data);
+			return -ENODEV;
 		}
 		if (pol->cpu != 0) {
 			printk(KERN_ERR FW_BUG PFX "No ACPI _PSS objects for "
 			       "CPU other than CPU0. Complain to your BIOS "
 			       "vendor.\n");
-			goto err_out;
+			kfree(data);
+			return -ENODEV;
 		}
 		rc = find_psb_table(data);
 		if (rc) {
-			goto err_out;
+			kfree(data);
+			return -ENODEV;
 		}
 		/* Take a crude guess here.
 		 * That guess was in microseconds, so multiply with 1000 */
diff --git a/arch/x86/kernel/cpu/mcheck/mce_64.c b/arch/x86/kernel/cpu/mcheck/mce_64.c
index 1c838032fd37..fe79985ce0f2 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_64.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_64.c
@@ -295,11 +295,11 @@ void do_machine_check(struct pt_regs * regs, long error_code)
 		 * If we know that the error was in user space, send a
 		 * SIGBUS.  Otherwise, panic if tolerance is low.
 		 *
-		 * do_exit() takes an awful lot of locks and has a slight
+		 * force_sig() takes an awful lot of locks and has a slight
 		 * risk of deadlocking.
 		 */
 		if (user_space) {
-			do_exit(SIGBUS);
+			force_sig(SIGBUS, current);
 		} else if (panic_on_oops || tolerant < 2) {
 			mce_panic("Uncorrected machine check",
 				&panicm, mcestart);
@@ -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:
@@ -734,6 +734,7 @@ __setup("mce=", mcheck_enable);
 static int mce_resume(struct sys_device *dev)
 {
 	mce_init(NULL);
+	mce_cpu_features(&current_cpu_data);
 	return 0;
 }
 
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/ds.c b/arch/x86/kernel/ds.c
index 169a120587be..87b67e3a765a 100644
--- a/arch/x86/kernel/ds.c
+++ b/arch/x86/kernel/ds.c
@@ -729,7 +729,7 @@ struct pebs_tracer *ds_request_pebs(struct task_struct *task,
 
 	spin_unlock_irqrestore(&ds_lock, irq);
 
-	ds_write_config(tracer->ds.context, &tracer->trace.ds, ds_bts);
+	ds_write_config(tracer->ds.context, &tracer->trace.ds, ds_pebs);
 	ds_resume_pebs(tracer);
 
 	return tracer;
@@ -1029,5 +1029,4 @@ void ds_copy_thread(struct task_struct *tsk, struct task_struct *father)
 
 void ds_exit_thread(struct task_struct *tsk)
 {
-	WARN_ON(tsk->thread.ds_ctx);
 }
diff --git a/arch/x86/kernel/efi.c b/arch/x86/kernel/efi.c
index 1119d247fe11..eb1ef3b67dd5 100644
--- a/arch/x86/kernel/efi.c
+++ b/arch/x86/kernel/efi.c
@@ -467,7 +467,7 @@ void __init efi_enter_virtual_mode(void)
 	efi_memory_desc_t *md;
 	efi_status_t status;
 	unsigned long size;
-	u64 end, systab, addr, npages;
+	u64 end, systab, addr, npages, end_pfn;
 	void *p, *va;
 
 	efi.systab = NULL;
@@ -479,7 +479,10 @@ void __init efi_enter_virtual_mode(void)
 		size = md->num_pages << EFI_PAGE_SHIFT;
 		end = md->phys_addr + size;
 
-		if (PFN_UP(end) <= max_low_pfn_mapped)
+		end_pfn = PFN_UP(end);
+		if (end_pfn <= max_low_pfn_mapped
+		    || (end_pfn > (1UL << (32 - PAGE_SHIFT))
+			&& end_pfn <= max_pfn_mapped))
 			va = __va(md->phys_addr);
 		else
 			va = efi_ioremap(md->phys_addr, size);
diff --git a/arch/x86/kernel/efi_64.c b/arch/x86/kernel/efi_64.c
index 652c5287215f..cb783b92c50c 100644
--- a/arch/x86/kernel/efi_64.c
+++ b/arch/x86/kernel/efi_64.c
@@ -99,24 +99,11 @@ void __init efi_call_phys_epilog(void)
 
 void __iomem *__init efi_ioremap(unsigned long phys_addr, unsigned long size)
 {
-	static unsigned pages_mapped __initdata;
-	unsigned i, pages;
-	unsigned long offset;
+	unsigned long last_map_pfn;
 
-	pages = PFN_UP(phys_addr + size) - PFN_DOWN(phys_addr);
-	offset = phys_addr & ~PAGE_MASK;
-	phys_addr &= PAGE_MASK;
-
-	if (pages_mapped + pages > MAX_EFI_IO_PAGES)
+	last_map_pfn = init_memory_mapping(phys_addr, phys_addr + size);
+	if ((last_map_pfn << PAGE_SHIFT) < phys_addr + size)
 		return NULL;
 
-	for (i = 0; i < pages; i++) {
-		__set_fixmap(FIX_EFI_IO_MAP_FIRST_PAGE - pages_mapped,
-			     phys_addr, PAGE_KERNEL);
-		phys_addr += PAGE_SIZE;
-		pages_mapped++;
-	}
-
-	return (void __iomem *)__fix_to_virt(FIX_EFI_IO_MAP_FIRST_PAGE - \
-					     (pages_mapped - pages)) + offset;
+	return (void __iomem *)__va(phys_addr);
 }
diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c
index 388254f69a2a..a00545fe5cdd 100644
--- a/arch/x86/kernel/hpet.c
+++ b/arch/x86/kernel/hpet.c
@@ -269,6 +269,8 @@ static void hpet_set_mode(enum clock_event_mode mode,
 		now = hpet_readl(HPET_COUNTER);
 		cmp = now + (unsigned long) delta;
 		cfg = hpet_readl(HPET_Tn_CFG(timer));
+		/* Make sure we use edge triggered interrupts */
+		cfg &= ~HPET_TN_LEVEL;
 		cfg |= HPET_TN_ENABLE | HPET_TN_PERIODIC |
 		       HPET_TN_SETVAL | HPET_TN_32BIT;
 		hpet_writel(cfg, HPET_Tn_CFG(timer));
diff --git a/arch/x86/kernel/i387.c b/arch/x86/kernel/i387.c
index b0f61f0dcd0a..f2f8540a7f3d 100644
--- a/arch/x86/kernel/i387.c
+++ b/arch/x86/kernel/i387.c
@@ -136,7 +136,7 @@ int init_fpu(struct task_struct *tsk)
 #ifdef CONFIG_X86_32
 	if (!HAVE_HWFP) {
 		memset(tsk->thread.xstate, 0, xstate_size);
-		finit();
+		finit_task(tsk);
 		set_stopped_child_used_math(tsk);
 		return 0;
 	}
diff --git a/arch/x86/kernel/kprobes.c b/arch/x86/kernel/kprobes.c
index e948b28a5a9a..4558dd3918cf 100644
--- a/arch/x86/kernel/kprobes.c
+++ b/arch/x86/kernel/kprobes.c
@@ -193,6 +193,9 @@ static int __kprobes can_boost(kprobe_opcode_t *opcodes)
 	kprobe_opcode_t opcode;
 	kprobe_opcode_t *orig_opcodes = opcodes;
 
+	if (search_exception_tables(opcodes))
+		return 0;	/* Page fault may occur on this address. */
+
 retry:
 	if (opcodes - orig_opcodes > MAX_INSN_SIZE - 1)
 		return 0;
diff --git a/arch/x86/kernel/olpc.c b/arch/x86/kernel/olpc.c
index 7a13fac63a1f..4006c522adc7 100644
--- a/arch/x86/kernel/olpc.c
+++ b/arch/x86/kernel/olpc.c
@@ -203,7 +203,7 @@ static void __init platform_detect(void)
 static void __init platform_detect(void)
 {
 	/* stopgap until OFW support is added to the kernel */
-	olpc_platform_info.boardrev = 0xc2;
+	olpc_platform_info.boardrev = olpc_board(0xc2);
 }
 #endif
 
diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c
index e4c8fb608873..c6520a4e85d4 100644
--- a/arch/x86/kernel/paravirt.c
+++ b/arch/x86/kernel/paravirt.c
@@ -268,6 +268,32 @@ enum paravirt_lazy_mode paravirt_get_lazy_mode(void)
 	return __get_cpu_var(paravirt_lazy_mode);
 }
 
+void arch_flush_lazy_mmu_mode(void)
+{
+	preempt_disable();
+
+	if (paravirt_get_lazy_mode() == PARAVIRT_LAZY_MMU) {
+		WARN_ON(preempt_count() == 1);
+		arch_leave_lazy_mmu_mode();
+		arch_enter_lazy_mmu_mode();
+	}
+
+	preempt_enable();
+}
+
+void arch_flush_lazy_cpu_mode(void)
+{
+	preempt_disable();
+
+	if (paravirt_get_lazy_mode() == PARAVIRT_LAZY_CPU) {
+		WARN_ON(preempt_count() == 1);
+		arch_leave_lazy_cpu_mode();
+		arch_enter_lazy_cpu_mode();
+	}
+
+	preempt_enable();
+}
+
 struct pv_info pv_info = {
 	.name = "bare hardware",
 	.paravirt_enabled = 0,
diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c
index a546f55c77b4..bd4da2af08ae 100644
--- a/arch/x86/kernel/process_32.c
+++ b/arch/x86/kernel/process_32.c
@@ -104,9 +104,6 @@ void cpu_idle(void)
 			check_pgt_cache();
 			rmb();
 
-			if (rcu_pending(cpu))
-				rcu_check_callbacks(cpu, 0);
-
 			if (cpu_is_offline(cpu))
 				play_dead();
 
diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c
index 0a5df5f82fb9..06ca07f6ad86 100644
--- a/arch/x86/kernel/ptrace.c
+++ b/arch/x86/kernel/ptrace.c
@@ -810,12 +810,16 @@ static void ptrace_bts_untrace(struct task_struct *child)
 
 static void ptrace_bts_detach(struct task_struct *child)
 {
-	if (unlikely(child->bts)) {
-		ds_release_bts(child->bts);
-		child->bts = NULL;
-
-		ptrace_bts_free_buffer(child);
-	}
+	/*
+	 * Ptrace_detach() races with ptrace_untrace() in case
+	 * the child dies and is reaped by another thread.
+	 *
+	 * We only do the memory accounting at this point and
+	 * leave the buffer deallocation and the bts tracer
+	 * release to ptrace_bts_untrace() which will be called
+	 * later on with tasklist_lock held.
+	 */
+	release_locked_buffer(child->bts_buffer, child->bts_size);
 }
 #else
 static inline void ptrace_bts_fork(struct task_struct *tsk) {}
@@ -1384,7 +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/reboot.c b/arch/x86/kernel/reboot.c
index 2b46eb41643b..4526b3a75ed2 100644
--- a/arch/x86/kernel/reboot.c
+++ b/arch/x86/kernel/reboot.c
@@ -217,6 +217,14 @@ static struct dmi_system_id __initdata reboot_dmi_table[] = {
 			DMI_MATCH(DMI_PRODUCT_NAME, "HP Compaq"),
 		},
 	},
+	{	/* Handle problems with rebooting on Dell XPS710 */
+		.callback = set_bios_reboot,
+		.ident = "Dell XPS710",
+		.matches = {
+			DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
+			DMI_MATCH(DMI_PRODUCT_NAME, "Dell XPS710"),
+		},
+	},
 	{ }
 };
 
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index c461f6d69074..6a8811a69324 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -770,6 +770,9 @@ void __init setup_arch(char **cmdline_p)
 
 	finish_e820_parsing();
 
+	if (efi_enabled)
+		efi_init();
+
 	dmi_scan_machine();
 
 	dmi_check_system(bad_bios_dmi_table);
@@ -789,8 +792,6 @@ void __init setup_arch(char **cmdline_p)
 	insert_resource(&iomem_resource, &data_resource);
 	insert_resource(&iomem_resource, &bss_resource);
 
-	if (efi_enabled)
-		efi_init();
 
 #ifdef CONFIG_X86_32
 	if (ppro_with_ram_bug()) {
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/traps.c b/arch/x86/kernel/traps.c
index 7932338d7cb3..a9e7548e1790 100644
--- a/arch/x86/kernel/traps.c
+++ b/arch/x86/kernel/traps.c
@@ -99,6 +99,12 @@ static inline void preempt_conditional_sti(struct pt_regs *regs)
 		local_irq_enable();
 }
 
+static inline void conditional_cli(struct pt_regs *regs)
+{
+	if (regs->flags & X86_EFLAGS_IF)
+		local_irq_disable();
+}
+
 static inline void preempt_conditional_cli(struct pt_regs *regs)
 {
 	if (regs->flags & X86_EFLAGS_IF)
@@ -626,8 +632,10 @@ clear_dr7:
 
 #ifdef CONFIG_X86_32
 debug_vm86:
+	/* reenable preemption: handle_vm86_trap() might sleep */
+	dec_preempt_count();
 	handle_vm86_trap((struct kernel_vm86_regs *) regs, error_code, 1);
-	preempt_conditional_cli(regs);
+	conditional_cli(regs);
 	return;
 #endif
 
diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index 599e58168631..d5cebb52d45b 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -273,30 +273,43 @@ static unsigned long pit_calibrate_tsc(u32 latch, unsigned long ms, int loopmin)
  * use the TSC value at the transitions to calculate a pretty
  * good value for the TSC frequencty.
  */
-static inline int pit_expect_msb(unsigned char val)
+static inline int pit_expect_msb(unsigned char val, u64 *tscp, unsigned long *deltap)
 {
-	int count = 0;
+	int count;
+	u64 tsc = 0;
 
 	for (count = 0; count < 50000; count++) {
 		/* Ignore LSB */
 		inb(0x42);
 		if (inb(0x42) != val)
 			break;
+		tsc = get_cycles();
 	}
-	return count > 50;
+	*deltap = get_cycles() - tsc;
+	*tscp = tsc;
+
+	/*
+	 * We require _some_ success, but the quality control
+	 * will be based on the error terms on the TSC values.
+	 */
+	return count > 5;
 }
 
 /*
- * How many MSB values do we want to see? We aim for a
- * 15ms calibration, which assuming a 2us counter read
- * error should give us roughly 150 ppm precision for
- * the calibration.
+ * How many MSB values do we want to see? We aim for
+ * a maximum error rate of 500ppm (in practice the
+ * real error is much smaller), but refuse to spend
+ * more than 25ms on it.
  */
-#define QUICK_PIT_MS 15
-#define QUICK_PIT_ITERATIONS (QUICK_PIT_MS * PIT_TICK_RATE / 1000 / 256)
+#define MAX_QUICK_PIT_MS 25
+#define MAX_QUICK_PIT_ITERATIONS (MAX_QUICK_PIT_MS * PIT_TICK_RATE / 1000 / 256)
 
 static unsigned long quick_pit_calibrate(void)
 {
+	int i;
+	u64 tsc, delta;
+	unsigned long d1, d2;
+
 	/* Set the Gate high, disable speaker */
 	outb((inb(0x61) & ~0x02) | 0x01, 0x61);
 
@@ -315,45 +328,52 @@ static unsigned long quick_pit_calibrate(void)
 	outb(0xff, 0x42);
 	outb(0xff, 0x42);
 
-	if (pit_expect_msb(0xff)) {
-		int i;
-		u64 t1, t2, delta;
-		unsigned char expect = 0xfe;
-
-		t1 = get_cycles();
-		for (i = 0; i < QUICK_PIT_ITERATIONS; i++, expect--) {
-			if (!pit_expect_msb(expect))
-				goto failed;
+	/*
+	 * The PIT starts counting at the next edge, so we
+	 * need to delay for a microsecond. The easiest way
+	 * to do that is to just read back the 16-bit counter
+	 * once from the PIT.
+	 */
+	inb(0x42);
+	inb(0x42);
+
+	if (pit_expect_msb(0xff, &tsc, &d1)) {
+		for (i = 1; i <= MAX_QUICK_PIT_ITERATIONS; i++) {
+			if (!pit_expect_msb(0xff-i, &delta, &d2))
+				break;
+
+			/*
+			 * Iterate until the error is less than 500 ppm
+			 */
+			delta -= tsc;
+			if (d1+d2 < delta >> 11)
+				goto success;
 		}
-		t2 = get_cycles();
-
-		/*
-		 * Make sure we can rely on the second TSC timestamp:
-		 */
-		if (!pit_expect_msb(expect))
-			goto failed;
-
-		/*
-		 * Ok, if we get here, then we've seen the
-		 * MSB of the PIT decrement QUICK_PIT_ITERATIONS
-		 * times, and each MSB had many hits, so we never
-		 * had any sudden jumps.
-		 *
-		 * As a result, we can depend on there not being
-		 * any odd delays anywhere, and the TSC reads are
-		 * reliable.
-		 *
-		 * kHz = ticks / time-in-seconds / 1000;
-		 * kHz = (t2 - t1) / (QPI * 256 / PIT_TICK_RATE) / 1000
-		 * kHz = ((t2 - t1) * PIT_TICK_RATE) / (QPI * 256 * 1000)
-		 */
-		delta = (t2 - t1)*PIT_TICK_RATE;
-		do_div(delta, QUICK_PIT_ITERATIONS*256*1000);
-		printk("Fast TSC calibration using PIT\n");
-		return delta;
 	}
-failed:
+	printk("Fast TSC calibration failed\n");
 	return 0;
+
+success:
+	/*
+	 * Ok, if we get here, then we've seen the
+	 * MSB of the PIT decrement 'i' times, and the
+	 * error has shrunk to less than 500 ppm.
+	 *
+	 * As a result, we can depend on there not being
+	 * any odd delays anywhere, and the TSC reads are
+	 * reliable (within the error). We also adjust the
+	 * delta to the middle of the error bars, just
+	 * because it looks nicer.
+	 *
+	 * kHz = ticks / time-in-seconds / 1000;
+	 * kHz = (t2 - t1) / (I * 256 / PIT_TICK_RATE) / 1000
+	 * kHz = ((t2 - t1) * PIT_TICK_RATE) / (I * 256 * 1000)
+	 */
+	delta += (long)(d2 - d1)/2;
+	delta *= PIT_TICK_RATE;
+	do_div(delta, i*256*1000);
+	printk("Fast TSC calibration using PIT\n");
+	return delta;
 }
 
 /**
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 = {