20 files changed, 406 insertions, 163 deletions

diff --git a/arch/x86/kernel/acpi/cstate.c b/arch/x86/kernel/acpi/cstate.c
index e69182fd01cf..4b28159e0421 100644
--- a/arch/x86/kernel/acpi/cstate.c
+++ b/arch/x86/kernel/acpi/cstate.c
@@ -87,7 +87,9 @@ static long acpi_processor_ffh_cstate_probe_cpu(void *_cx)
 	num_cstate_subtype = edx_part & MWAIT_SUBSTATE_MASK;
 
 	retval = 0;
-	if (num_cstate_subtype < (cx->address & MWAIT_SUBSTATE_MASK)) {
+	/* If the HW does not support any sub-states in this C-state */
+	if (num_cstate_subtype == 0) {
+		pr_warn(FW_BUG "ACPI MWAIT C-state 0x%x not supported by HW (0x%x)\n", cx->address, edx_part);
 		retval = -1;
 		goto out;
 	}
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index 481ae38f6a44..ad28db7e6bde 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -1996,7 +1996,8 @@ static inline void __smp_error_interrupt(struct pt_regs *regs)
 	};
 
 	/* First tickle the hardware, only then report what went on. -- REW */
-	apic_write(APIC_ESR, 0);
+	if (lapic_get_maxlvt() > 3)	/* Due to the Pentium erratum 3AP. */
+		apic_write(APIC_ESR, 0);
 	v = apic_read(APIC_ESR);
 	ack_APIC_irq();
 	atomic_inc(&irq_err_count);
diff --git a/arch/x86/kernel/cpu/intel_cacheinfo.c b/arch/x86/kernel/cpu/intel_cacheinfo.c
index 0641113e2965..a952e9c85b6f 100644
--- a/arch/x86/kernel/cpu/intel_cacheinfo.c
+++ b/arch/x86/kernel/cpu/intel_cacheinfo.c
@@ -1225,21 +1225,24 @@ static struct notifier_block cacheinfo_cpu_notifier = {
 
 static int __init cache_sysfs_init(void)
 {
-	int i;
+	int i, err = 0;
 
 	if (num_cache_leaves == 0)
 		return 0;
 
+	cpu_notifier_register_begin();
 	for_each_online_cpu(i) {
-		int err;
 		struct device *dev = get_cpu_device(i);
 
 		err = cache_add_dev(dev);
 		if (err)
-			return err;
+			goto out;
 	}
-	register_hotcpu_notifier(&cacheinfo_cpu_notifier);
-	return 0;
+	__register_hotcpu_notifier(&cacheinfo_cpu_notifier);
+
+out:
+	cpu_notifier_register_done();
+	return err;
 }
 
 device_initcall(cache_sysfs_init);
diff --git a/arch/x86/kernel/cpu/mcheck/mce.c b/arch/x86/kernel/cpu/mcheck/mce.c
index 4d5419b249da..eeee23ff75ef 100644
--- a/arch/x86/kernel/cpu/mcheck/mce.c
+++ b/arch/x86/kernel/cpu/mcheck/mce.c
@@ -89,6 +89,9 @@ static DECLARE_WAIT_QUEUE_HEAD(mce_chrdev_wait);
 static DEFINE_PER_CPU(struct mce, mces_seen);
 static int			cpu_missing;
 
+/* CMCI storm detection filter */
+static DEFINE_PER_CPU(unsigned long, mce_polled_error);
+
 /*
  * MCA banks polled by the period polling timer for corrected events.
  * With Intel CMCI, this only has MCA banks which do not support CMCI (if any).
@@ -595,6 +598,7 @@ void machine_check_poll(enum mcp_flags flags, mce_banks_t *b)
 {
 	struct mce m;
 	int i;
+	unsigned long *v;
 
 	this_cpu_inc(mce_poll_count);
 
@@ -614,6 +618,8 @@ void machine_check_poll(enum mcp_flags flags, mce_banks_t *b)
 		if (!(m.status & MCI_STATUS_VAL))
 			continue;
 
+		v = &get_cpu_var(mce_polled_error);
+		set_bit(0, v);
 		/*
 		 * Uncorrected or signalled events are handled by the exception
 		 * handler when it is enabled, so don't process those here.
@@ -1278,10 +1284,18 @@ static unsigned long mce_adjust_timer_default(unsigned long interval)
 static unsigned long (*mce_adjust_timer)(unsigned long interval) =
 	mce_adjust_timer_default;
 
+static int cmc_error_seen(void)
+{
+	unsigned long *v = &__get_cpu_var(mce_polled_error);
+
+	return test_and_clear_bit(0, v);
+}
+
 static void mce_timer_fn(unsigned long data)
 {
 	struct timer_list *t = &__get_cpu_var(mce_timer);
 	unsigned long iv;
+	int notify;
 
 	WARN_ON(smp_processor_id() != data);
 
@@ -1296,7 +1310,9 @@ static void mce_timer_fn(unsigned long data)
 	 * polling interval, otherwise increase the polling interval.
 	 */
 	iv = __this_cpu_read(mce_next_interval);
-	if (mce_notify_irq()) {
+	notify = mce_notify_irq();
+	notify |= cmc_error_seen();
+	if (notify) {
 		iv = max(iv / 2, (unsigned long) HZ/100);
 	} else {
 		iv = min(iv * 2, round_jiffies_relative(check_interval * HZ));
@@ -2434,14 +2450,18 @@ static __init int mcheck_init_device(void)
 	if (err)
 		return err;
 
+	cpu_notifier_register_begin();
 	for_each_online_cpu(i) {
 		err = mce_device_create(i);
-		if (err)
+		if (err) {
+			cpu_notifier_register_done();
 			return err;
+		}
 	}
 
 	register_syscore_ops(&mce_syscore_ops);
-	register_hotcpu_notifier(&mce_cpu_notifier);
+	__register_hotcpu_notifier(&mce_cpu_notifier);
+	cpu_notifier_register_done();
 
 	/* register character device /dev/mcelog */
 	misc_register(&mce_chrdev_device);
diff --git a/arch/x86/kernel/cpu/mcheck/mce_intel.c b/arch/x86/kernel/cpu/mcheck/mce_intel.c
index fb6156fee6f7..3bdb95ae8c43 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_intel.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_intel.c
@@ -9,6 +9,7 @@
 #include <linux/interrupt.h>
 #include <linux/percpu.h>
 #include <linux/sched.h>
+#include <linux/cpumask.h>
 #include <asm/apic.h>
 #include <asm/processor.h>
 #include <asm/msr.h>
@@ -137,6 +138,22 @@ unsigned long mce_intel_adjust_timer(unsigned long interval)
 	}
 }
 
+static void cmci_storm_disable_banks(void)
+{
+	unsigned long flags, *owned;
+	int bank;
+	u64 val;
+
+	raw_spin_lock_irqsave(&cmci_discover_lock, flags);
+	owned = __get_cpu_var(mce_banks_owned);
+	for_each_set_bit(bank, owned, MAX_NR_BANKS) {
+		rdmsrl(MSR_IA32_MCx_CTL2(bank), val);
+		val &= ~MCI_CTL2_CMCI_EN;
+		wrmsrl(MSR_IA32_MCx_CTL2(bank), val);
+	}
+	raw_spin_unlock_irqrestore(&cmci_discover_lock, flags);
+}
+
 static bool cmci_storm_detect(void)
 {
 	unsigned int cnt = __this_cpu_read(cmci_storm_cnt);
@@ -158,7 +175,7 @@ static bool cmci_storm_detect(void)
 	if (cnt <= CMCI_STORM_THRESHOLD)
 		return false;
 
-	cmci_clear();
+	cmci_storm_disable_banks();
 	__this_cpu_write(cmci_storm_state, CMCI_STORM_ACTIVE);
 	r = atomic_add_return(1, &cmci_storm_on_cpus);
 	mce_timer_kick(CMCI_POLL_INTERVAL);
diff --git a/arch/x86/kernel/cpu/mcheck/therm_throt.c b/arch/x86/kernel/cpu/mcheck/therm_throt.c
index 3eec7de76efb..d921b7ee6595 100644
--- a/arch/x86/kernel/cpu/mcheck/therm_throt.c
+++ b/arch/x86/kernel/cpu/mcheck/therm_throt.c
@@ -271,9 +271,6 @@ static void thermal_throttle_remove_dev(struct device *dev)
 	sysfs_remove_group(&dev->kobj, &thermal_attr_group);
 }
 
-/* Mutex protecting device creation against CPU hotplug: */
-static DEFINE_MUTEX(therm_cpu_lock);
-
 /* Get notified when a cpu comes on/off. Be hotplug friendly. */
 static int
 thermal_throttle_cpu_callback(struct notifier_block *nfb,
@@ -289,18 +286,14 @@ thermal_throttle_cpu_callback(struct notifier_block *nfb,
 	switch (action) {
 	case CPU_UP_PREPARE:
 	case CPU_UP_PREPARE_FROZEN:
-		mutex_lock(&therm_cpu_lock);
 		err = thermal_throttle_add_dev(dev, cpu);
-		mutex_unlock(&therm_cpu_lock);
 		WARN_ON(err);
 		break;
 	case CPU_UP_CANCELED:
 	case CPU_UP_CANCELED_FROZEN:
 	case CPU_DEAD:
 	case CPU_DEAD_FROZEN:
-		mutex_lock(&therm_cpu_lock);
 		thermal_throttle_remove_dev(dev);
-		mutex_unlock(&therm_cpu_lock);
 		break;
 	}
 	return notifier_from_errno(err);
@@ -319,19 +312,16 @@ static __init int thermal_throttle_init_device(void)
 	if (!atomic_read(&therm_throt_en))
 		return 0;
 
-	register_hotcpu_notifier(&thermal_throttle_cpu_notifier);
+	cpu_notifier_register_begin();
 
-#ifdef CONFIG_HOTPLUG_CPU
-	mutex_lock(&therm_cpu_lock);
-#endif
 	/* connect live CPUs to sysfs */
 	for_each_online_cpu(cpu) {
 		err = thermal_throttle_add_dev(get_cpu_device(cpu), cpu);
 		WARN_ON(err);
 	}
-#ifdef CONFIG_HOTPLUG_CPU
-	mutex_unlock(&therm_cpu_lock);
-#endif
+
+	__register_hotcpu_notifier(&thermal_throttle_cpu_notifier);
+	cpu_notifier_register_done();
 
 	return 0;
 }
diff --git a/arch/x86/kernel/cpu/perf_event_amd_ibs.c b/arch/x86/kernel/cpu/perf_event_amd_ibs.c
index 4b8e4d3cd6ea..4c36bbe3173a 100644
--- a/arch/x86/kernel/cpu/perf_event_amd_ibs.c
+++ b/arch/x86/kernel/cpu/perf_event_amd_ibs.c
@@ -926,13 +926,13 @@ static __init int amd_ibs_init(void)
 		goto out;
 
 	perf_ibs_pm_init();
-	get_online_cpus();
+	cpu_notifier_register_begin();
 	ibs_caps = caps;
 	/* make ibs_caps visible to other cpus: */
 	smp_mb();
-	perf_cpu_notifier(perf_ibs_cpu_notifier);
 	smp_call_function(setup_APIC_ibs, NULL, 1);
-	put_online_cpus();
+	__perf_cpu_notifier(perf_ibs_cpu_notifier);
+	cpu_notifier_register_done();
 
 	ret = perf_event_ibs_init();
 out:
diff --git a/arch/x86/kernel/cpu/perf_event_amd_uncore.c b/arch/x86/kernel/cpu/perf_event_amd_uncore.c
index 754291adec33..3bbdf4cd38b9 100644
--- a/arch/x86/kernel/cpu/perf_event_amd_uncore.c
+++ b/arch/x86/kernel/cpu/perf_event_amd_uncore.c
@@ -531,15 +531,16 @@ static int __init amd_uncore_init(void)
 	if (ret)
 		return -ENODEV;
 
-	get_online_cpus();
+	cpu_notifier_register_begin();
+
 	/* init cpus already online before registering for hotplug notifier */
 	for_each_online_cpu(cpu) {
 		amd_uncore_cpu_up_prepare(cpu);
 		smp_call_function_single(cpu, init_cpu_already_online, NULL, 1);
 	}
 
-	register_cpu_notifier(&amd_uncore_cpu_notifier_block);
-	put_online_cpus();
+	__register_cpu_notifier(&amd_uncore_cpu_notifier_block);
+	cpu_notifier_register_done();
 
 	return 0;
 }
diff --git a/arch/x86/kernel/cpu/perf_event_intel_rapl.c b/arch/x86/kernel/cpu/perf_event_intel_rapl.c
index 5ad35ad94d0f..4b9a9e9466bd 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_rapl.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_rapl.c
@@ -59,7 +59,7 @@
 #define INTEL_RAPL_PKG		0x2	/* pseudo-encoding */
 #define RAPL_IDX_RAM_NRG_STAT	2	/* DRAM */
 #define INTEL_RAPL_RAM		0x3	/* pseudo-encoding */
-#define RAPL_IDX_PP1_NRG_STAT	3	/* DRAM */
+#define RAPL_IDX_PP1_NRG_STAT	3	/* gpu */
 #define INTEL_RAPL_PP1		0x4	/* pseudo-encoding */
 
 /* Clients have PP0, PKG */
@@ -72,6 +72,12 @@
 			 1<<RAPL_IDX_PKG_NRG_STAT|\
 			 1<<RAPL_IDX_RAM_NRG_STAT)
 
+/* Servers have PP0, PKG, RAM, PP1 */
+#define RAPL_IDX_HSW	(1<<RAPL_IDX_PP0_NRG_STAT|\
+			 1<<RAPL_IDX_PKG_NRG_STAT|\
+			 1<<RAPL_IDX_RAM_NRG_STAT|\
+			 1<<RAPL_IDX_PP1_NRG_STAT)
+
 /*
  * event code: LSB 8 bits, passed in attr->config
  * any other bit is reserved
@@ -425,6 +431,24 @@ static struct attribute *rapl_events_cln_attr[] = {
 	NULL,
 };
 
+static struct attribute *rapl_events_hsw_attr[] = {
+	EVENT_PTR(rapl_cores),
+	EVENT_PTR(rapl_pkg),
+	EVENT_PTR(rapl_gpu),
+	EVENT_PTR(rapl_ram),
+
+	EVENT_PTR(rapl_cores_unit),
+	EVENT_PTR(rapl_pkg_unit),
+	EVENT_PTR(rapl_gpu_unit),
+	EVENT_PTR(rapl_ram_unit),
+
+	EVENT_PTR(rapl_cores_scale),
+	EVENT_PTR(rapl_pkg_scale),
+	EVENT_PTR(rapl_gpu_scale),
+	EVENT_PTR(rapl_ram_scale),
+	NULL,
+};
+
 static struct attribute_group rapl_pmu_events_group = {
 	.name = "events",
 	.attrs = NULL, /* patched at runtime */
@@ -631,11 +655,14 @@ static int __init rapl_pmu_init(void)
 	switch (boot_cpu_data.x86_model) {
 	case 42: /* Sandy Bridge */
 	case 58: /* Ivy Bridge */
-	case 60: /* Haswell */
-	case 69: /* Haswell-Celeron */
 		rapl_cntr_mask = RAPL_IDX_CLN;
 		rapl_pmu_events_group.attrs = rapl_events_cln_attr;
 		break;
+	case 60: /* Haswell */
+	case 69: /* Haswell-Celeron */
+		rapl_cntr_mask = RAPL_IDX_HSW;
+		rapl_pmu_events_group.attrs = rapl_events_hsw_attr;
+		break;
 	case 45: /* Sandy Bridge-EP */
 	case 62: /* IvyTown */
 		rapl_cntr_mask = RAPL_IDX_SRV;
@@ -646,19 +673,20 @@ static int __init rapl_pmu_init(void)
 		/* unsupported */
 		return 0;
 	}
-	get_online_cpus();
+
+	cpu_notifier_register_begin();
 
 	for_each_online_cpu(cpu) {
 		rapl_cpu_prepare(cpu);
 		rapl_cpu_init(cpu);
 	}
 
-	perf_cpu_notifier(rapl_cpu_notifier);
+	__perf_cpu_notifier(rapl_cpu_notifier);
 
 	ret = perf_pmu_register(&rapl_pmu_class, "power", -1);
 	if (WARN_ON(ret)) {
 		pr_info("RAPL PMU detected, registration failed (%d), RAPL PMU disabled\n", ret);
-		put_online_cpus();
+		cpu_notifier_register_done();
 		return -1;
 	}
 
@@ -672,7 +700,7 @@ static int __init rapl_pmu_init(void)
 		hweight32(rapl_cntr_mask),
 		ktime_to_ms(pmu->timer_interval));
 
-	put_online_cpus();
+	cpu_notifier_register_done();
 
 	return 0;
 }
diff --git a/arch/x86/kernel/cpu/perf_event_intel_uncore.c b/arch/x86/kernel/cpu/perf_event_intel_uncore.c
index bd2253d40cff..65bbbea38b9c 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_uncore.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_uncore.c
@@ -4244,7 +4244,7 @@ static void __init uncore_cpumask_init(void)
 	if (!cpumask_empty(&uncore_cpu_mask))
 		return;
 
-	get_online_cpus();
+	cpu_notifier_register_begin();
 
 	for_each_online_cpu(cpu) {
 		int i, phys_id = topology_physical_package_id(cpu);
@@ -4263,9 +4263,9 @@ static void __init uncore_cpumask_init(void)
 	}
 	on_each_cpu(uncore_cpu_setup, NULL, 1);
 
-	register_cpu_notifier(&uncore_cpu_nb);
+	__register_cpu_notifier(&uncore_cpu_nb);
 
-	put_online_cpus();
+	cpu_notifier_register_done();
 }
 
 
diff --git a/arch/x86/kernel/cpuid.c b/arch/x86/kernel/cpuid.c
index 7d9481c743f8..3225ae6c5180 100644
--- a/arch/x86/kernel/cpuid.c
+++ b/arch/x86/kernel/cpuid.c
@@ -198,14 +198,15 @@ static int __init cpuid_init(void)
 		goto out_chrdev;
 	}
 	cpuid_class->devnode = cpuid_devnode;
-	get_online_cpus();
+
+	cpu_notifier_register_begin();
 	for_each_online_cpu(i) {
 		err = cpuid_device_create(i);
 		if (err != 0)
 			goto out_class;
 	}
-	register_hotcpu_notifier(&cpuid_class_cpu_notifier);
-	put_online_cpus();
+	__register_hotcpu_notifier(&cpuid_class_cpu_notifier);
+	cpu_notifier_register_done();
 
 	err = 0;
 	goto out;
@@ -215,7 +216,7 @@ out_class:
 	for_each_online_cpu(i) {
 		cpuid_device_destroy(i);
 	}
-	put_online_cpus();
+	cpu_notifier_register_done();
 	class_destroy(cpuid_class);
 out_chrdev:
 	__unregister_chrdev(CPUID_MAJOR, 0, NR_CPUS, "cpu/cpuid");
@@ -227,13 +228,13 @@ static void __exit cpuid_exit(void)
 {
 	int cpu = 0;
 
-	get_online_cpus();
+	cpu_notifier_register_begin();
 	for_each_online_cpu(cpu)
 		cpuid_device_destroy(cpu);
 	class_destroy(cpuid_class);
 	__unregister_chrdev(CPUID_MAJOR, 0, NR_CPUS, "cpu/cpuid");
-	unregister_hotcpu_notifier(&cpuid_class_cpu_notifier);
-	put_online_cpus();
+	__unregister_hotcpu_notifier(&cpuid_class_cpu_notifier);
+	cpu_notifier_register_done();
 }
 
 module_init(cpuid_init);
diff --git a/arch/x86/kernel/early-quirks.c b/arch/x86/kernel/early-quirks.c
index 6d7d5a1260a6..6e2537c32190 100644
--- a/arch/x86/kernel/early-quirks.c
+++ b/arch/x86/kernel/early-quirks.c
@@ -225,7 +225,7 @@ static void __init intel_remapping_check(int num, int slot, int func)
  *
  * And yes, so far on current devices the base addr is always under 4G.
  */
-static u32 __init intel_stolen_base(int num, int slot, int func)
+static u32 __init intel_stolen_base(int num, int slot, int func, size_t stolen_size)
 {
 	u32 base;
 
@@ -240,10 +240,118 @@ static u32 __init intel_stolen_base(int num, int slot, int func)
 	return base;
 }
 
-#define KB(x)	((x) * 1024)
+#define KB(x)	((x) * 1024UL)
 #define MB(x)	(KB (KB (x)))
 #define GB(x)	(MB (KB (x)))
 
+static size_t __init i830_tseg_size(void)
+{
+	u8 tmp = read_pci_config_byte(0, 0, 0, I830_ESMRAMC);
+
+	if (!(tmp & TSEG_ENABLE))
+		return 0;
+
+	if (tmp & I830_TSEG_SIZE_1M)
+		return MB(1);
+	else
+		return KB(512);
+}
+
+static size_t __init i845_tseg_size(void)
+{
+	u8 tmp = read_pci_config_byte(0, 0, 0, I845_ESMRAMC);
+
+	if (!(tmp & TSEG_ENABLE))
+		return 0;
+
+	switch (tmp & I845_TSEG_SIZE_MASK) {
+	case I845_TSEG_SIZE_512K:
+		return KB(512);
+	case I845_TSEG_SIZE_1M:
+		return MB(1);
+	default:
+		WARN_ON(1);
+		return 0;
+	}
+}
+
+static size_t __init i85x_tseg_size(void)
+{
+	u8 tmp = read_pci_config_byte(0, 0, 0, I85X_ESMRAMC);
+
+	if (!(tmp & TSEG_ENABLE))
+		return 0;
+
+	return MB(1);
+}
+
+static size_t __init i830_mem_size(void)
+{
+	return read_pci_config_byte(0, 0, 0, I830_DRB3) * MB(32);
+}
+
+static size_t __init i85x_mem_size(void)
+{
+	return read_pci_config_byte(0, 0, 1, I85X_DRB3) * MB(32);
+}
+
+/*
+ * On 830/845/85x the stolen memory base isn't available in any
+ * register. We need to calculate it as TOM-TSEG_SIZE-stolen_size.
+ */
+static u32 __init i830_stolen_base(int num, int slot, int func, size_t stolen_size)
+{
+	return i830_mem_size() - i830_tseg_size() - stolen_size;
+}
+
+static u32 __init i845_stolen_base(int num, int slot, int func, size_t stolen_size)
+{
+	return i830_mem_size() - i845_tseg_size() - stolen_size;
+}
+
+static u32 __init i85x_stolen_base(int num, int slot, int func, size_t stolen_size)
+{
+	return i85x_mem_size() - i85x_tseg_size() - stolen_size;
+}
+
+static u32 __init i865_stolen_base(int num, int slot, int func, size_t stolen_size)
+{
+	/*
+	 * FIXME is the graphics stolen memory region
+	 * always at TOUD? Ie. is it always the last
+	 * one to be allocated by the BIOS?
+	 */
+	return read_pci_config_16(0, 0, 0, I865_TOUD) << 16;
+}
+
+static size_t __init i830_stolen_size(int num, int slot, int func)
+{
+	size_t stolen_size;
+	u16 gmch_ctrl;
+
+	gmch_ctrl = read_pci_config_16(0, 0, 0, I830_GMCH_CTRL);
+
+	switch (gmch_ctrl & I830_GMCH_GMS_MASK) {
+	case I830_GMCH_GMS_STOLEN_512:
+		stolen_size = KB(512);
+		break;
+	case I830_GMCH_GMS_STOLEN_1024:
+		stolen_size = MB(1);
+		break;
+	case I830_GMCH_GMS_STOLEN_8192:
+		stolen_size = MB(8);
+		break;
+	case I830_GMCH_GMS_LOCAL:
+		/* local memory isn't part of the normal address space */
+		stolen_size = 0;
+		break;
+	default:
+		return 0;
+	}
+
+	return stolen_size;
+}
+
 static size_t __init gen3_stolen_size(int num, int slot, int func)
 {
 	size_t stolen_size;
@@ -310,7 +418,7 @@ static size_t __init gen6_stolen_size(int num, int slot, int func)
 	return gmch_ctrl << 25; /* 32 MB units */
 }
 
-static inline size_t gen8_stolen_size(int num, int slot, int func)
+static size_t gen8_stolen_size(int num, int slot, int func)
 {
 	u16 gmch_ctrl;
 
@@ -320,31 +428,74 @@ static inline size_t gen8_stolen_size(int num, int slot, int func)
 	return gmch_ctrl << 25; /* 32 MB units */
 }
 
-typedef size_t (*stolen_size_fn)(int num, int slot, int func);
+
+struct intel_stolen_funcs {
+	size_t (*size)(int num, int slot, int func);
+	u32 (*base)(int num, int slot, int func, size_t size);
+};
+
+static const struct intel_stolen_funcs i830_stolen_funcs = {
+	.base = i830_stolen_base,
+	.size = i830_stolen_size,
+};
+
+static const struct intel_stolen_funcs i845_stolen_funcs = {
+	.base = i845_stolen_base,
+	.size = i830_stolen_size,
+};
+
+static const struct intel_stolen_funcs i85x_stolen_funcs = {
+	.base = i85x_stolen_base,
+	.size = gen3_stolen_size,
+};
+
+static const struct intel_stolen_funcs i865_stolen_funcs = {
+	.base = i865_stolen_base,
+	.size = gen3_stolen_size,
+};
+
+static const struct intel_stolen_funcs gen3_stolen_funcs = {
+	.base = intel_stolen_base,
+	.size = gen3_stolen_size,
+};
+
+static const struct intel_stolen_funcs gen6_stolen_funcs = {
+	.base = intel_stolen_base,
+	.size = gen6_stolen_size,
+};
+
+static const struct intel_stolen_funcs gen8_stolen_funcs = {
+	.base = intel_stolen_base,
+	.size = gen8_stolen_size,
+};
 
 static struct pci_device_id intel_stolen_ids[] __initdata = {
-	INTEL_I915G_IDS(gen3_stolen_size),
-	INTEL_I915GM_IDS(gen3_stolen_size),
-	INTEL_I945G_IDS(gen3_stolen_size),
-	INTEL_I945GM_IDS(gen3_stolen_size),
-	INTEL_VLV_M_IDS(gen6_stolen_size),
-	INTEL_VLV_D_IDS(gen6_stolen_size),
-	INTEL_PINEVIEW_IDS(gen3_stolen_size),
-	INTEL_I965G_IDS(gen3_stolen_size),
-	INTEL_G33_IDS(gen3_stolen_size),
-	INTEL_I965GM_IDS(gen3_stolen_size),
-	INTEL_GM45_IDS(gen3_stolen_size),
-	INTEL_G45_IDS(gen3_stolen_size),
-	INTEL_IRONLAKE_D_IDS(gen3_stolen_size),
-	INTEL_IRONLAKE_M_IDS(gen3_stolen_size),
-	INTEL_SNB_D_IDS(gen6_stolen_size),
-	INTEL_SNB_M_IDS(gen6_stolen_size),
-	INTEL_IVB_M_IDS(gen6_stolen_size),
-	INTEL_IVB_D_IDS(gen6_stolen_size),
-	INTEL_HSW_D_IDS(gen6_stolen_size),
-	INTEL_HSW_M_IDS(gen6_stolen_size),
-	INTEL_BDW_M_IDS(gen8_stolen_size),
-	INTEL_BDW_D_IDS(gen8_stolen_size)
+	INTEL_I830_IDS(&i830_stolen_funcs),
+	INTEL_I845G_IDS(&i845_stolen_funcs),
+	INTEL_I85X_IDS(&i85x_stolen_funcs),
+	INTEL_I865G_IDS(&i865_stolen_funcs),
+	INTEL_I915G_IDS(&gen3_stolen_funcs),
+	INTEL_I915GM_IDS(&gen3_stolen_funcs),
+	INTEL_I945G_IDS(&gen3_stolen_funcs),
+	INTEL_I945GM_IDS(&gen3_stolen_funcs),
+	INTEL_VLV_M_IDS(&gen6_stolen_funcs),
+	INTEL_VLV_D_IDS(&gen6_stolen_funcs),
+	INTEL_PINEVIEW_IDS(&gen3_stolen_funcs),
+	INTEL_I965G_IDS(&gen3_stolen_funcs),
+	INTEL_G33_IDS(&gen3_stolen_funcs),
+	INTEL_I965GM_IDS(&gen3_stolen_funcs),
+	INTEL_GM45_IDS(&gen3_stolen_funcs),
+	INTEL_G45_IDS(&gen3_stolen_funcs),
+	INTEL_IRONLAKE_D_IDS(&gen3_stolen_funcs),
+	INTEL_IRONLAKE_M_IDS(&gen3_stolen_funcs),
+	INTEL_SNB_D_IDS(&gen6_stolen_funcs),
+	INTEL_SNB_M_IDS(&gen6_stolen_funcs),
+	INTEL_IVB_M_IDS(&gen6_stolen_funcs),
+	INTEL_IVB_D_IDS(&gen6_stolen_funcs),
+	INTEL_HSW_D_IDS(&gen6_stolen_funcs),
+	INTEL_HSW_M_IDS(&gen6_stolen_funcs),
+	INTEL_BDW_M_IDS(&gen8_stolen_funcs),
+	INTEL_BDW_D_IDS(&gen8_stolen_funcs)
 };
 
 static void __init intel_graphics_stolen(int num, int slot, int func)
@@ -361,11 +512,13 @@ static void __init intel_graphics_stolen(int num, int slot, int func)
 
 	for (i = 0; i < ARRAY_SIZE(intel_stolen_ids); i++) {
 		if (intel_stolen_ids[i].device == device) {
-			stolen_size_fn stolen_size =
-				(stolen_size_fn)intel_stolen_ids[i].driver_data;
-			size = stolen_size(num, slot, func);
-			start = intel_stolen_base(num, slot, func);
+			const struct intel_stolen_funcs *stolen_funcs =
+				(const struct intel_stolen_funcs *)intel_stolen_ids[i].driver_data;
+			size = stolen_funcs->size(num, slot, func);
+			start = stolen_funcs->base(num, slot, func, size);
 			if (size && start) {
+				printk(KERN_INFO "Reserving Intel graphics stolen memory at 0x%x-0x%x\n",
+				       start, start + (u32)size - 1);
 				/* Mark this space as reserved */
 				e820_add_region(start, size, E820_RESERVED);
 				sanitize_e820_map(e820.map,
diff --git a/arch/x86/kernel/ftrace.c b/arch/x86/kernel/ftrace.c
index e6253195a301..52819e816f87 100644
--- a/arch/x86/kernel/ftrace.c
+++ b/arch/x86/kernel/ftrace.c
@@ -308,7 +308,10 @@ static int ftrace_write(unsigned long ip, const char *val, int size)
 	if (within(ip, (unsigned long)_text, (unsigned long)_etext))
 		ip = (unsigned long)__va(__pa_symbol(ip));
 
-	return probe_kernel_write((void *)ip, val, size);
+	if (probe_kernel_write((void *)ip, val, size))
+		return -EPERM;
+
+	return 0;
 }
 
 static int add_break(unsigned long ip, const char *old)
@@ -323,10 +326,7 @@ static int add_break(unsigned long ip, const char *old)
 	if (memcmp(replaced, old, MCOUNT_INSN_SIZE) != 0)
 		return -EINVAL;
 
-	if (ftrace_write(ip, &brk, 1))
-		return -EPERM;
-
-	return 0;
+	return ftrace_write(ip, &brk, 1);
 }
 
 static int add_brk_on_call(struct dyn_ftrace *rec, unsigned long addr)
@@ -425,7 +425,7 @@ static int remove_breakpoint(struct dyn_ftrace *rec)
 
 	/* If this does not have a breakpoint, we are done */
 	if (ins[0] != brk)
-		return -1;
+		return 0;
 
 	nop = ftrace_nop_replace();
 
@@ -455,7 +455,7 @@ static int remove_breakpoint(struct dyn_ftrace *rec)
 	}
 
  update:
-	return probe_kernel_write((void *)ip, &nop[0], 1);
+	return ftrace_write(ip, nop, 1);
 }
 
 static int add_update_code(unsigned long ip, unsigned const char *new)
@@ -463,9 +463,7 @@ static int add_update_code(unsigned long ip, unsigned const char *new)
 	/* skip breakpoint */
 	ip++;
 	new++;
-	if (ftrace_write(ip, new, MCOUNT_INSN_SIZE - 1))
-		return -EPERM;
-	return 0;
+	return ftrace_write(ip, new, MCOUNT_INSN_SIZE - 1);
 }
 
 static int add_update_call(struct dyn_ftrace *rec, unsigned long addr)
@@ -520,10 +518,7 @@ static int finish_update_call(struct dyn_ftrace *rec, unsigned long addr)
 
 	new = ftrace_call_replace(ip, addr);
 
-	if (ftrace_write(ip, new, 1))
-		return -EPERM;
-
-	return 0;
+	return ftrace_write(ip, new, 1);
 }
 
 static int finish_update_nop(struct dyn_ftrace *rec)
@@ -533,9 +528,7 @@ static int finish_update_nop(struct dyn_ftrace *rec)
 
 	new = ftrace_nop_replace();
 
-	if (ftrace_write(ip, new, 1))
-		return -EPERM;
-	return 0;
+	return ftrace_write(ip, new, 1);
 }
 
 static int finish_update(struct dyn_ftrace *rec, int enable)
@@ -632,8 +625,14 @@ void ftrace_replace_code(int enable)
 	printk(KERN_WARNING "Failed on %s (%d):\n", report, count);
 	for_ftrace_rec_iter(iter) {
 		rec = ftrace_rec_iter_record(iter);
-		remove_breakpoint(rec);
+		/*
+		 * Breakpoints are handled only when this function is in
+		 * progress. The system could not work with them.
+		 */
+		if (remove_breakpoint(rec))
+			BUG();
 	}
+	run_sync();
 }
 
 static int
@@ -655,16 +654,19 @@ ftrace_modify_code(unsigned long ip, unsigned const char *old_code,
 	run_sync();
 
 	ret = ftrace_write(ip, new_code, 1);
-	if (ret) {
-		ret = -EPERM;
-		goto out;
-	}
-	run_sync();
+	/*
+	 * The breakpoint is handled only when this function is in progress.
+	 * The system could not work if we could not remove it.
+	 */
+	BUG_ON(ret);
  out:
+	run_sync();
 	return ret;
 
  fail_update:
-	probe_kernel_write((void *)ip, &old_code[0], 1);
+	/* Also here the system could not work with the breakpoint */
+	if (ftrace_write(ip, old_code, 1))
+		BUG();
 	goto out;
 }
 
@@ -678,11 +680,8 @@ void arch_ftrace_update_code(int command)
 	atomic_dec(&modifying_ftrace_code);
 }
 
-int __init ftrace_dyn_arch_init(void *data)
+int __init ftrace_dyn_arch_init(void)
 {
-	/* The return code is retured via data */
-	*(unsigned long *)data = 0;
-
 	return 0;
 }
 #endif
diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c
index 93eed15a8fd4..8d80ae011603 100644
--- a/arch/x86/kernel/hpet.c
+++ b/arch/x86/kernel/hpet.c
@@ -941,12 +941,14 @@ static __init int hpet_late_init(void)
 	if (boot_cpu_has(X86_FEATURE_ARAT))
 		return 0;
 
+	cpu_notifier_register_begin();
 	for_each_online_cpu(cpu) {
 		hpet_cpuhp_notify(NULL, CPU_ONLINE, (void *)(long)cpu);
 	}
 
 	/* This notifier should be called after workqueue is ready */
-	hotcpu_notifier(hpet_cpuhp_notify, -20);
+	__hotcpu_notifier(hpet_cpuhp_notify, -20);
+	cpu_notifier_register_done();
 
 	return 0;
 }
diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c
index 42805fac0092..283a76a9cc40 100644
--- a/arch/x86/kernel/irq.c
+++ b/arch/x86/kernel/irq.c
@@ -125,7 +125,7 @@ int arch_show_interrupts(struct seq_file *p, int prec)
 		seq_printf(p, "%10u ", per_cpu(mce_poll_count, j));
 	seq_printf(p, "  Machine check polls\n");
 #endif
-#if defined(CONFIG_HYPERV) || defined(CONFIG_XEN)
+#if IS_ENABLED(CONFIG_HYPERV) || defined(CONFIG_XEN)
 	seq_printf(p, "%*s: ", prec, "THR");
 	for_each_online_cpu(j)
 		seq_printf(p, "%10u ", irq_stats(j)->irq_hv_callback_count);
diff --git a/arch/x86/kernel/ldt.c b/arch/x86/kernel/ldt.c
index ebc987398923..af1d14a9ebda 100644
--- a/arch/x86/kernel/ldt.c
+++ b/arch/x86/kernel/ldt.c
@@ -229,6 +229,17 @@ static int write_ldt(void __user *ptr, unsigned long bytecount, int oldmode)
 		}
 	}
 
+	/*
+	 * On x86-64 we do not support 16-bit segments due to
+	 * IRET leaking the high bits of the kernel stack address.
+	 */
+#ifdef CONFIG_X86_64
+	if (!ldt_info.seg_32bit) {
+		error = -EINVAL;
+		goto out_unlock;
+	}
+#endif
+
 	fill_ldt(&ldt, &ldt_info);
 	if (oldmode)
 		ldt.avl = 0;
diff --git a/arch/x86/kernel/msr.c b/arch/x86/kernel/msr.c
index 05266b5aae22..c9603ac80de5 100644
--- a/arch/x86/kernel/msr.c
+++ b/arch/x86/kernel/msr.c
@@ -259,14 +259,15 @@ static int __init msr_init(void)
 		goto out_chrdev;
 	}
 	msr_class->devnode = msr_devnode;
-	get_online_cpus();
+
+	cpu_notifier_register_begin();
 	for_each_online_cpu(i) {
 		err = msr_device_create(i);
 		if (err != 0)
 			goto out_class;
 	}
-	register_hotcpu_notifier(&msr_class_cpu_notifier);
-	put_online_cpus();
+	__register_hotcpu_notifier(&msr_class_cpu_notifier);
+	cpu_notifier_register_done();
 
 	err = 0;
 	goto out;
@@ -275,7 +276,7 @@ out_class:
 	i = 0;
 	for_each_online_cpu(i)
 		msr_device_destroy(i);
-	put_online_cpus();
+	cpu_notifier_register_done();
 	class_destroy(msr_class);
 out_chrdev:
 	__unregister_chrdev(MSR_MAJOR, 0, NR_CPUS, "cpu/msr");
@@ -286,13 +287,14 @@ out:
 static void __exit msr_exit(void)
 {
 	int cpu = 0;
-	get_online_cpus();
+
+	cpu_notifier_register_begin();
 	for_each_online_cpu(cpu)
 		msr_device_destroy(cpu);
 	class_destroy(msr_class);
 	__unregister_chrdev(MSR_MAJOR, 0, NR_CPUS, "cpu/msr");
-	unregister_hotcpu_notifier(&msr_class_cpu_notifier);
-	put_online_cpus();
+	__unregister_hotcpu_notifier(&msr_class_cpu_notifier);
+	cpu_notifier_register_done();
 }
 
 module_init(msr_init);
diff --git a/arch/x86/kernel/pci-calgary_64.c b/arch/x86/kernel/pci-calgary_64.c
index 299d49302e7d..0497f719977d 100644
--- a/arch/x86/kernel/pci-calgary_64.c
+++ b/arch/x86/kernel/pci-calgary_64.c
@@ -1207,23 +1207,31 @@ error:
 	return ret;
 }
 
-static inline int __init determine_tce_table_size(u64 ram)
+static inline int __init determine_tce_table_size(void)
 {
 	int ret;
 
 	if (specified_table_size != TCE_TABLE_SIZE_UNSPECIFIED)
 		return specified_table_size;
 
-	/*
-	 * Table sizes are from 0 to 7 (TCE_TABLE_SIZE_64K to
-	 * TCE_TABLE_SIZE_8M). Table size 0 has 8K entries and each
-	 * larger table size has twice as many entries, so shift the
-	 * max ram address by 13 to divide by 8K and then look at the
-	 * order of the result to choose between 0-7.
-	 */
-	ret = get_order(ram >> 13);
-	if (ret > TCE_TABLE_SIZE_8M)
+	if (is_kdump_kernel() && saved_max_pfn) {
+		/*
+		 * Table sizes are from 0 to 7 (TCE_TABLE_SIZE_64K to
+		 * TCE_TABLE_SIZE_8M). Table size 0 has 8K entries and each
+		 * larger table size has twice as many entries, so shift the
+		 * max ram address by 13 to divide by 8K and then look at the
+		 * order of the result to choose between 0-7.
+		 */
+		ret = get_order((saved_max_pfn * PAGE_SIZE) >> 13);
+		if (ret > TCE_TABLE_SIZE_8M)
+			ret = TCE_TABLE_SIZE_8M;
+	} else {
+		/*
+		 * Use 8M by default (suggested by Muli) if it's not
+		 * kdump kernel and saved_max_pfn isn't set.
+		 */
 		ret = TCE_TABLE_SIZE_8M;
+	}
 
 	return ret;
 }
@@ -1418,8 +1426,7 @@ int __init detect_calgary(void)
 		return -ENOMEM;
 	}
 
-	specified_table_size = determine_tce_table_size((is_kdump_kernel() ?
-					saved_max_pfn : max_pfn) * PAGE_SIZE);
+	specified_table_size = determine_tce_table_size();
 
 	for (bus = 0; bus < MAX_PHB_BUS_NUM; bus++) {
 		struct calgary_bus_info *info = &bus_info[bus];
diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c
index 654b46574b91..3399d3a99730 100644
--- a/arch/x86/kernel/reboot.c
+++ b/arch/x86/kernel/reboot.c
@@ -114,8 +114,8 @@ EXPORT_SYMBOL(machine_real_restart);
  */
 static int __init set_pci_reboot(const struct dmi_system_id *d)
 {
-	if (reboot_type != BOOT_CF9) {
-		reboot_type = BOOT_CF9;
+	if (reboot_type != BOOT_CF9_FORCE) {
+		reboot_type = BOOT_CF9_FORCE;
 		pr_info("%s series board detected. Selecting %s-method for reboots.\n",
 			d->ident, "PCI");
 	}
@@ -458,20 +458,23 @@ void __attribute__((weak)) mach_reboot_fixups(void)
 }
 
 /*
- * Windows compatible x86 hardware expects the following on reboot:
+ * To the best of our knowledge Windows compatible x86 hardware expects
+ * the following on reboot:
  *
  * 1) If the FADT has the ACPI reboot register flag set, try it
  * 2) If still alive, write to the keyboard controller
  * 3) If still alive, write to the ACPI reboot register again
  * 4) If still alive, write to the keyboard controller again
  * 5) If still alive, call the EFI runtime service to reboot
- * 6) If still alive, write to the PCI IO port 0xCF9 to reboot
- * 7) If still alive, inform BIOS to do a proper reboot
+ * 6) If no EFI runtime service, call the BIOS to do a reboot
  *
- * If the machine is still alive at this stage, it gives up. We default to
- * following the same pattern, except that if we're still alive after (7) we'll
- * try to force a triple fault and then cycle between hitting the keyboard
- * controller and doing that
+ * We default to following the same pattern. We also have
+ * two other reboot methods: 'triple fault' and 'PCI', which
+ * can be triggered via the reboot= kernel boot option or
+ * via quirks.
+ *
+ * This means that this function can never return, it can misbehave
+ * by not rebooting properly and hanging.
  */
 static void native_machine_emergency_restart(void)
 {
@@ -492,6 +495,11 @@ static void native_machine_emergency_restart(void)
 	for (;;) {
 		/* Could also try the reset bit in the Hammer NB */
 		switch (reboot_type) {
+		case BOOT_ACPI:
+			acpi_reboot();
+			reboot_type = BOOT_KBD;
+			break;
+
 		case BOOT_KBD:
 			mach_reboot_fixups(); /* For board specific fixups */
 
@@ -509,43 +517,29 @@ static void native_machine_emergency_restart(void)
 			}
 			break;
 
-		case BOOT_TRIPLE:
-			load_idt(&no_idt);
-			__asm__ __volatile__("int3");
-
-			/* We're probably dead after this, but... */
-			reboot_type = BOOT_KBD;
-			break;
-
-		case BOOT_BIOS:
-			machine_real_restart(MRR_BIOS);
-
-			/* We're probably dead after this, but... */
-			reboot_type = BOOT_TRIPLE;
-			break;
-
-		case BOOT_ACPI:
-			acpi_reboot();
-			reboot_type = BOOT_KBD;
-			break;
-
 		case BOOT_EFI:
 			if (efi_enabled(EFI_RUNTIME_SERVICES))
 				efi.reset_system(reboot_mode == REBOOT_WARM ?
 						 EFI_RESET_WARM :
 						 EFI_RESET_COLD,
 						 EFI_SUCCESS, 0, NULL);
-			reboot_type = BOOT_CF9_COND;
+			reboot_type = BOOT_BIOS;
+			break;
+
+		case BOOT_BIOS:
+			machine_real_restart(MRR_BIOS);
+
+			/* We're probably dead after this, but... */
+			reboot_type = BOOT_CF9_SAFE;
 			break;
 
-		case BOOT_CF9:
+		case BOOT_CF9_FORCE:
 			port_cf9_safe = true;
 			/* Fall through */
 
-		case BOOT_CF9_COND:
+		case BOOT_CF9_SAFE:
 			if (port_cf9_safe) {
-				u8 reboot_code = reboot_mode == REBOOT_WARM ?
-					0x06 : 0x0E;
+				u8 reboot_code = reboot_mode == REBOOT_WARM ?  0x06 : 0x0E;
 				u8 cf9 = inb(0xcf9) & ~reboot_code;
 				outb(cf9|2, 0xcf9); /* Request hard reset */
 				udelay(50);
@@ -553,7 +547,15 @@ static void native_machine_emergency_restart(void)
 				outb(cf9|reboot_code, 0xcf9);
 				udelay(50);
 			}
-			reboot_type = BOOT_BIOS;
+			reboot_type = BOOT_TRIPLE;
+			break;
+
+		case BOOT_TRIPLE:
+			load_idt(&no_idt);
+			__asm__ __volatile__("int3");
+
+			/* We're probably dead after this, but... */
+			reboot_type = BOOT_KBD;
 			break;
 		}
 	}
diff --git a/arch/x86/kernel/vsyscall_64.c b/arch/x86/kernel/vsyscall_64.c
index 9ea287666c65..8b3b3eb3cead 100644
--- a/arch/x86/kernel/vsyscall_64.c
+++ b/arch/x86/kernel/vsyscall_64.c
@@ -348,9 +348,13 @@ static int __init vsyscall_init(void)
 {
 	BUG_ON(VSYSCALL_ADDR(0) != __fix_to_virt(VSYSCALL_FIRST_PAGE));
 
+	cpu_notifier_register_begin();
+
 	on_each_cpu(cpu_vsyscall_init, NULL, 1);
 	/* notifier priority > KVM */
-	hotcpu_notifier(cpu_vsyscall_notifier, 30);
+	__hotcpu_notifier(cpu_vsyscall_notifier, 30);
+
+	cpu_notifier_register_done();
 
 	return 0;
 }