Merge branch 'x86-apic-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull x96 apic updates from Thomas Gleixner:
 "Updates for the x86 APIC interrupt handling and APIC timer:

   - Fix a long standing issue with spurious interrupts which was caused
     by the big vector management rework a few years ago. Robert Hodaszi
     provided finally enough debug data and an excellent initial failure
     analysis which allowed to understand the underlying issues.

     This contains a change to the core interrupt management code which
     is required to handle this correctly for the APIC/IO_APIC. The core
     changes are NOOPs for most architectures except ARM64. ARM64 is not
     impacted by the change as confirmed by Marc Zyngier.

   - Newer systems allow to disable the PIT clock for power saving
     causing panic in the timer interrupt delivery check of the IO/APIC
     when the HPET timer is not enabled either. While the clock could be
     turned on this would cause an endless whack a mole game to chase
     the proper register in each affected chipset.

     These systems provide the relevant frequencies for TSC, CPU and the
     local APIC timer via CPUID and/or MSRs, which allows to avoid the
     PIT/HPET based calibration. As the calibration code is the only
     usage of the legacy timers on modern systems and is skipped anyway
     when the frequencies are known already, there is no point in
     setting up the PIT and actually checking for the interrupt delivery
     via IO/APIC.

     To achieve this on a wide variety of platforms, the CPUID/MSR based
     frequency readout has been made more robust, which also allowed to
     remove quite some workarounds which turned out to be not longer
     required. Thanks to Daniel Drake for analysis, patches and
     verification"

* 'x86-apic-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/irq: Seperate unused system vectors from spurious entry again
  x86/irq: Handle spurious interrupt after shutdown gracefully
  x86/ioapic: Implement irq_get_irqchip_state() callback
  genirq: Add optional hardware synchronization for shutdown
  genirq: Fix misleading synchronize_irq() documentation
  genirq: Delay deactivation in free_irq()
  x86/timer: Skip PIT initialization on modern chipsets
  x86/apic: Use non-atomic operations when possible
  x86/apic: Make apic_bsp_setup() static
  x86/tsc: Set LAPIC timer period to crystal clock frequency
  x86/apic: Rename 'lapic_timer_frequency' to 'lapic_timer_period'
  x86/tsc: Use CPUID.0x16 to calculate missing crystal frequency

20 files changed, 251 insertions, 69 deletions

diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S
index 7b23431be5cb..44c6e6f54bf7 100644
--- a/arch/x86/entry/entry_32.S
+++ b/arch/x86/entry/entry_32.S
@@ -1104,6 +1104,30 @@ ENTRY(irq_entries_start)
     .endr
 END(irq_entries_start)
 
+#ifdef CONFIG_X86_LOCAL_APIC
+	.align 8
+ENTRY(spurious_entries_start)
+    vector=FIRST_SYSTEM_VECTOR
+    .rept (NR_VECTORS - FIRST_SYSTEM_VECTOR)
+	pushl	$(~vector+0x80)			/* Note: always in signed byte range */
+    vector=vector+1
+	jmp	common_spurious
+	.align	8
+    .endr
+END(spurious_entries_start)
+
+common_spurious:
+	ASM_CLAC
+	addl	$-0x80, (%esp)			/* Adjust vector into the [-256, -1] range */
+	SAVE_ALL switch_stacks=1
+	ENCODE_FRAME_POINTER
+	TRACE_IRQS_OFF
+	movl	%esp, %eax
+	call	smp_spurious_interrupt
+	jmp	ret_from_intr
+ENDPROC(common_interrupt)
+#endif
+
 /*
  * the CPU automatically disables interrupts when executing an IRQ vector,
  * so IRQ-flags tracing has to follow that:
diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S
index 11aa3b2afa4d..8dbca86c249b 100644
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -375,6 +375,18 @@ ENTRY(irq_entries_start)
     .endr
 END(irq_entries_start)
 
+	.align 8
+ENTRY(spurious_entries_start)
+    vector=FIRST_SYSTEM_VECTOR
+    .rept (NR_VECTORS - FIRST_SYSTEM_VECTOR)
+	UNWIND_HINT_IRET_REGS
+	pushq	$(~vector+0x80)			/* Note: always in signed byte range */
+	jmp	common_spurious
+	.align	8
+	vector=vector+1
+    .endr
+END(spurious_entries_start)
+
 .macro DEBUG_ENTRY_ASSERT_IRQS_OFF
 #ifdef CONFIG_DEBUG_ENTRY
 	pushq %rax
@@ -571,10 +583,20 @@ _ASM_NOKPROBE(interrupt_entry)
 
 /* Interrupt entry/exit. */
 
-	/*
-	 * The interrupt stubs push (~vector+0x80) onto the stack and
-	 * then jump to common_interrupt.
-	 */
+/*
+ * The interrupt stubs push (~vector+0x80) onto the stack and
+ * then jump to common_spurious/interrupt.
+ */
+common_spurious:
+	addq	$-0x80, (%rsp)			/* Adjust vector to [-256, -1] range */
+	call	interrupt_entry
+	UNWIND_HINT_REGS indirect=1
+	call	smp_spurious_interrupt		/* rdi points to pt_regs */
+	jmp	ret_from_intr
+END(common_spurious)
+_ASM_NOKPROBE(common_spurious)
+
+/* common_interrupt is a hotpath. Align it */
 	.p2align CONFIG_X86_L1_CACHE_SHIFT
 common_interrupt:
 	addq	$-0x80, (%rsp)			/* Adjust vector to [-256, -1] range */
diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h
index 1340fa53b575..050e5f9ebf81 100644
--- a/arch/x86/include/asm/apic.h
+++ b/arch/x86/include/asm/apic.h
@@ -53,7 +53,7 @@ extern unsigned int apic_verbosity;
 extern int local_apic_timer_c2_ok;
 
 extern int disable_apic;
-extern unsigned int lapic_timer_frequency;
+extern unsigned int lapic_timer_period;
 
 extern enum apic_intr_mode_id apic_intr_mode;
 enum apic_intr_mode_id {
@@ -155,7 +155,6 @@ static inline int apic_force_enable(unsigned long addr)
 extern int apic_force_enable(unsigned long addr);
 #endif
 
-extern void apic_bsp_setup(bool upmode);
 extern void apic_ap_setup(void);
 
 /*
@@ -175,6 +174,7 @@ extern void lapic_assign_system_vectors(void);
 extern void lapic_assign_legacy_vector(unsigned int isairq, bool replace);
 extern void lapic_online(void);
 extern void lapic_offline(void);
+extern bool apic_needs_pit(void);
 
 #else /* !CONFIG_X86_LOCAL_APIC */
 static inline void lapic_shutdown(void) { }
@@ -188,6 +188,7 @@ static inline void init_bsp_APIC(void) { }
 static inline void apic_intr_mode_init(void) { }
 static inline void lapic_assign_system_vectors(void) { }
 static inline void lapic_assign_legacy_vector(unsigned int i, bool r) { }
+static inline bool apic_needs_pit(void) { return true; }
 #endif /* !CONFIG_X86_LOCAL_APIC */
 
 #ifdef CONFIG_X86_X2APIC
diff --git a/arch/x86/include/asm/hw_irq.h b/arch/x86/include/asm/hw_irq.h
index 32e666e1231e..cbd97e22d2f3 100644
--- a/arch/x86/include/asm/hw_irq.h
+++ b/arch/x86/include/asm/hw_irq.h
@@ -150,8 +150,11 @@ extern char irq_entries_start[];
 #define trace_irq_entries_start irq_entries_start
 #endif
 
+extern char spurious_entries_start[];
+
 #define VECTOR_UNUSED		NULL
-#define VECTOR_RETRIGGERED	((void *)~0UL)
+#define VECTOR_SHUTDOWN		((void *)~0UL)
+#define VECTOR_RETRIGGERED	((void *)~1UL)
 
 typedef struct irq_desc* vector_irq_t[NR_VECTORS];
 DECLARE_PER_CPU(vector_irq_t, vector_irq);
diff --git a/arch/x86/include/asm/time.h b/arch/x86/include/asm/time.h
index cef818b16045..8ac563abb567 100644
--- a/arch/x86/include/asm/time.h
+++ b/arch/x86/include/asm/time.h
@@ -7,6 +7,7 @@
 
 extern void hpet_time_init(void);
 extern void time_init(void);
+extern bool pit_timer_init(void);
 
 extern struct clock_event_device *global_clock_event;
 
diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
index 85be316665b4..1bd91cb7b320 100644
--- a/arch/x86/kernel/apic/apic.c
+++ b/arch/x86/kernel/apic/apic.c
@@ -195,7 +195,7 @@ static struct resource lapic_resource = {
 	.flags = IORESOURCE_MEM | IORESOURCE_BUSY,
 };
 
-unsigned int lapic_timer_frequency = 0;
+unsigned int lapic_timer_period = 0;
 
 static void apic_pm_activate(void);
 
@@ -501,7 +501,7 @@ lapic_timer_set_periodic_oneshot(struct clock_event_device *evt, bool oneshot)
 	if (evt->features & CLOCK_EVT_FEAT_DUMMY)
 		return 0;
 
-	__setup_APIC_LVTT(lapic_timer_frequency, oneshot, 1);
+	__setup_APIC_LVTT(lapic_timer_period, oneshot, 1);
 	return 0;
 }
 
@@ -805,11 +805,11 @@ calibrate_by_pmtimer(long deltapm, long *delta, long *deltatsc)
 
 static int __init lapic_init_clockevent(void)
 {
-	if (!lapic_timer_frequency)
+	if (!lapic_timer_period)
 		return -1;
 
 	/* Calculate the scaled math multiplication factor */
-	lapic_clockevent.mult = div_sc(lapic_timer_frequency/APIC_DIVISOR,
+	lapic_clockevent.mult = div_sc(lapic_timer_period/APIC_DIVISOR,
 					TICK_NSEC, lapic_clockevent.shift);
 	lapic_clockevent.max_delta_ns =
 		clockevent_delta2ns(0x7FFFFFFF, &lapic_clockevent);
@@ -821,6 +821,33 @@ static int __init lapic_init_clockevent(void)
 	return 0;
 }
 
+bool __init apic_needs_pit(void)
+{
+	/*
+	 * If the frequencies are not known, PIT is required for both TSC
+	 * and apic timer calibration.
+	 */
+	if (!tsc_khz || !cpu_khz)
+		return true;
+
+	/* Is there an APIC at all? */
+	if (!boot_cpu_has(X86_FEATURE_APIC))
+		return true;
+
+	/* Deadline timer is based on TSC so no further PIT action required */
+	if (boot_cpu_has(X86_FEATURE_TSC_DEADLINE_TIMER))
+		return false;
+
+	/* APIC timer disabled? */
+	if (disable_apic_timer)
+		return true;
+	/*
+	 * The APIC timer frequency is known already, no PIT calibration
+	 * required. If unknown, let the PIT be initialized.
+	 */
+	return lapic_timer_period == 0;
+}
+
 static int __init calibrate_APIC_clock(void)
 {
 	struct clock_event_device *levt = this_cpu_ptr(&lapic_events);
@@ -839,7 +866,7 @@ static int __init calibrate_APIC_clock(void)
 	 */
 	if (!lapic_init_clockevent()) {
 		apic_printk(APIC_VERBOSE, "lapic timer already calibrated %d\n",
-			    lapic_timer_frequency);
+			    lapic_timer_period);
 		/*
 		 * Direct calibration methods must have an always running
 		 * local APIC timer, no need for broadcast timer.
@@ -884,13 +911,13 @@ static int __init calibrate_APIC_clock(void)
 	pm_referenced = !calibrate_by_pmtimer(lapic_cal_pm2 - lapic_cal_pm1,
 					&delta, &deltatsc);
 
-	lapic_timer_frequency = (delta * APIC_DIVISOR) / LAPIC_CAL_LOOPS;
+	lapic_timer_period = (delta * APIC_DIVISOR) / LAPIC_CAL_LOOPS;
 	lapic_init_clockevent();
 
 	apic_printk(APIC_VERBOSE, "..... delta %ld\n", delta);
 	apic_printk(APIC_VERBOSE, "..... mult: %u\n", lapic_clockevent.mult);
 	apic_printk(APIC_VERBOSE, "..... calibration result: %u\n",
-		    lapic_timer_frequency);
+		    lapic_timer_period);
 
 	if (boot_cpu_has(X86_FEATURE_TSC)) {
 		apic_printk(APIC_VERBOSE, "..... CPU clock speed is "
@@ -901,13 +928,13 @@ static int __init calibrate_APIC_clock(void)
 
 	apic_printk(APIC_VERBOSE, "..... host bus clock speed is "
 		    "%u.%04u MHz.\n",
-		    lapic_timer_frequency / (1000000 / HZ),
-		    lapic_timer_frequency % (1000000 / HZ));
+		    lapic_timer_period / (1000000 / HZ),
+		    lapic_timer_period % (1000000 / HZ));
 
 	/*
 	 * Do a sanity check on the APIC calibration result
 	 */
-	if (lapic_timer_frequency < (1000000 / HZ)) {
+	if (lapic_timer_period < (1000000 / HZ)) {
 		local_irq_enable();
 		pr_warning("APIC frequency too slow, disabling apic timer\n");
 		return -1;
@@ -1351,6 +1378,8 @@ void __init init_bsp_APIC(void)
 	apic_write(APIC_LVT1, value);
 }
 
+static void __init apic_bsp_setup(bool upmode);
+
 /* Init the interrupt delivery mode for the BSP */
 void __init apic_intr_mode_init(void)
 {
@@ -2041,21 +2070,32 @@ __visible void __irq_entry smp_spurious_interrupt(struct pt_regs *regs)
 	entering_irq();
 	trace_spurious_apic_entry(vector);
 
+	inc_irq_stat(irq_spurious_count);
+
+	/*
+	 * If this is a spurious interrupt then do not acknowledge
+	 */
+	if (vector == SPURIOUS_APIC_VECTOR) {
+		/* See SDM vol 3 */
+		pr_info("Spurious APIC interrupt (vector 0xFF) on CPU#%d, should never happen.\n",
+			smp_processor_id());
+		goto out;
+	}
+
 	/*
-	 * Check if this really is a spurious interrupt and ACK it
-	 * if it is a vectored one.  Just in case...
-	 * Spurious interrupts should not be ACKed.
+	 * If it is a vectored one, verify it's set in the ISR. If set,
+	 * acknowledge it.
 	 */
 	v = apic_read(APIC_ISR + ((vector & ~0x1f) >> 1));
-	if (v & (1 << (vector & 0x1f)))
+	if (v & (1 << (vector & 0x1f))) {
+		pr_info("Spurious interrupt (vector 0x%02x) on CPU#%d. Acked\n",
+			vector, smp_processor_id());
 		ack_APIC_irq();
-
-	inc_irq_stat(irq_spurious_count);
-
-	/* see sw-dev-man vol 3, chapter 7.4.13.5 */
-	pr_info("spurious APIC interrupt through vector %02x on CPU#%d, "
-		"should never happen.\n", vector, smp_processor_id());
-
+	} else {
+		pr_info("Spurious interrupt (vector 0x%02x) on CPU#%d. Not pending!\n",
+			vector, smp_processor_id());
+	}
+out:
 	trace_spurious_apic_exit(vector);
 	exiting_irq();
 }
@@ -2416,11 +2456,8 @@ static void __init apic_bsp_up_setup(void)
 /**
  * apic_bsp_setup - Setup function for local apic and io-apic
  * @upmode:		Force UP mode (for APIC_init_uniprocessor)
- *
- * Returns:
- * apic_id of BSP APIC
  */
-void __init apic_bsp_setup(bool upmode)
+static void __init apic_bsp_setup(bool upmode)
 {
 	connect_bsp_APIC();
 	if (upmode)
diff --git a/arch/x86/kernel/apic/apic_flat_64.c b/arch/x86/kernel/apic/apic_flat_64.c
index bf083c3f1d73..bbdca603f94a 100644
--- a/arch/x86/kernel/apic/apic_flat_64.c
+++ b/arch/x86/kernel/apic/apic_flat_64.c
@@ -78,7 +78,7 @@ flat_send_IPI_mask_allbutself(const struct cpumask *cpumask, int vector)
 	int cpu = smp_processor_id();
 
 	if (cpu < BITS_PER_LONG)
-		clear_bit(cpu, &mask);
+		__clear_bit(cpu, &mask);
 
 	_flat_send_IPI_mask(mask, vector);
 }
@@ -92,7 +92,7 @@ static void flat_send_IPI_allbutself(int vector)
 			unsigned long mask = cpumask_bits(cpu_online_mask)[0];
 
 			if (cpu < BITS_PER_LONG)
-				clear_bit(cpu, &mask);
+				__clear_bit(cpu, &mask);
 
 			_flat_send_IPI_mask(mask, vector);
 		}
diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
index 53aa234a6803..c7bb6c69f21c 100644
--- a/arch/x86/kernel/apic/io_apic.c
+++ b/arch/x86/kernel/apic/io_apic.c
@@ -58,6 +58,7 @@
 #include <asm/acpi.h>
 #include <asm/dma.h>
 #include <asm/timer.h>
+#include <asm/time.h>
 #include <asm/i8259.h>
 #include <asm/setup.h>
 #include <asm/irq_remapping.h>
@@ -1893,6 +1894,50 @@ static int ioapic_set_affinity(struct irq_data *irq_data,
 	return ret;
 }
 
+/*
+ * Interrupt shutdown masks the ioapic pin, but the interrupt might already
+ * be in flight, but not yet serviced by the target CPU. That means
+ * __synchronize_hardirq() would return and claim that everything is calmed
+ * down. So free_irq() would proceed and deactivate the interrupt and free
+ * resources.
+ *
+ * Once the target CPU comes around to service it it will find a cleared
+ * vector and complain. While the spurious interrupt is harmless, the full
+ * release of resources might prevent the interrupt from being acknowledged
+ * which keeps the hardware in a weird state.
+ *
+ * Verify that the corresponding Remote-IRR bits are clear.
+ */
+static int ioapic_irq_get_chip_state(struct irq_data *irqd,
+				   enum irqchip_irq_state which,
+				   bool *state)
+{
+	struct mp_chip_data *mcd = irqd->chip_data;
+	struct IO_APIC_route_entry rentry;
+	struct irq_pin_list *p;
+
+	if (which != IRQCHIP_STATE_ACTIVE)
+		return -EINVAL;
+
+	*state = false;
+	raw_spin_lock(&ioapic_lock);
+	for_each_irq_pin(p, mcd->irq_2_pin) {
+		rentry = __ioapic_read_entry(p->apic, p->pin);
+		/*
+		 * The remote IRR is only valid in level trigger mode. It's
+		 * meaning is undefined for edge triggered interrupts and
+		 * irrelevant because the IO-APIC treats them as fire and
+		 * forget.
+		 */
+		if (rentry.irr && rentry.trigger) {
+			*state = true;
+			break;
+		}
+	}
+	raw_spin_unlock(&ioapic_lock);
+	return 0;
+}
+
 static struct irq_chip ioapic_chip __read_mostly = {
 	.name			= "IO-APIC",
 	.irq_startup		= startup_ioapic_irq,
@@ -1902,6 +1947,7 @@ static struct irq_chip ioapic_chip __read_mostly = {
 	.irq_eoi		= ioapic_ack_level,
 	.irq_set_affinity	= ioapic_set_affinity,
 	.irq_retrigger		= irq_chip_retrigger_hierarchy,
+	.irq_get_irqchip_state	= ioapic_irq_get_chip_state,
 	.flags			= IRQCHIP_SKIP_SET_WAKE,
 };
 
@@ -1914,6 +1960,7 @@ static struct irq_chip ioapic_ir_chip __read_mostly = {
 	.irq_eoi		= ioapic_ir_ack_level,
 	.irq_set_affinity	= ioapic_set_affinity,
 	.irq_retrigger		= irq_chip_retrigger_hierarchy,
+	.irq_get_irqchip_state	= ioapic_irq_get_chip_state,
 	.flags			= IRQCHIP_SKIP_SET_WAKE,
 };
 
@@ -2083,6 +2130,9 @@ static inline void __init check_timer(void)
 	unsigned long flags;
 	int no_pin1 = 0;
 
+	if (!global_clock_event)
+		return;
+
 	local_irq_save(flags);
 
 	/*
diff --git a/arch/x86/kernel/apic/vector.c b/arch/x86/kernel/apic/vector.c
index e7cb78aed644..fdacb864c3dd 100644
--- a/arch/x86/kernel/apic/vector.c
+++ b/arch/x86/kernel/apic/vector.c
@@ -340,7 +340,7 @@ static void clear_irq_vector(struct irq_data *irqd)
 	trace_vector_clear(irqd->irq, vector, apicd->cpu, apicd->prev_vector,
 			   apicd->prev_cpu);
 
-	per_cpu(vector_irq, apicd->cpu)[vector] = VECTOR_UNUSED;
+	per_cpu(vector_irq, apicd->cpu)[vector] = VECTOR_SHUTDOWN;
 	irq_matrix_free(vector_matrix, apicd->cpu, vector, managed);
 	apicd->vector = 0;
 
@@ -349,7 +349,7 @@ static void clear_irq_vector(struct irq_data *irqd)
 	if (!vector)
 		return;
 
-	per_cpu(vector_irq, apicd->prev_cpu)[vector] = VECTOR_UNUSED;
+	per_cpu(vector_irq, apicd->prev_cpu)[vector] = VECTOR_SHUTDOWN;
 	irq_matrix_free(vector_matrix, apicd->prev_cpu, vector, managed);
 	apicd->prev_vector = 0;
 	apicd->move_in_progress = 0;
diff --git a/arch/x86/kernel/apic/x2apic_cluster.c b/arch/x86/kernel/apic/x2apic_cluster.c
index 7685444a106b..609e499387a1 100644
--- a/arch/x86/kernel/apic/x2apic_cluster.c
+++ b/arch/x86/kernel/apic/x2apic_cluster.c
@@ -50,7 +50,7 @@ __x2apic_send_IPI_mask(const struct cpumask *mask, int vector, int apic_dest)
 	cpumask_copy(tmpmsk, mask);
 	/* If IPI should not be sent to self, clear current CPU */
 	if (apic_dest != APIC_DEST_ALLINC)
-		cpumask_clear_cpu(smp_processor_id(), tmpmsk);
+		__cpumask_clear_cpu(smp_processor_id(), tmpmsk);
 
 	/* Collapse cpus in a cluster so a single IPI per cluster is sent */
 	for_each_cpu(cpu, tmpmsk) {
diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c
index 1e5f7a03ddf5..062f77279ce3 100644
--- a/arch/x86/kernel/cpu/mshyperv.c
+++ b/arch/x86/kernel/cpu/mshyperv.c
@@ -268,9 +268,9 @@ static void __init ms_hyperv_init_platform(void)
 
 		rdmsrl(HV_X64_MSR_APIC_FREQUENCY, hv_lapic_frequency);
 		hv_lapic_frequency = div_u64(hv_lapic_frequency, HZ);
-		lapic_timer_frequency = hv_lapic_frequency;
+		lapic_timer_period = hv_lapic_frequency;
 		pr_info("Hyper-V: LAPIC Timer Frequency: %#x\n",
-			lapic_timer_frequency);
+			lapic_timer_period);
 	}
 
 	register_nmi_handler(NMI_UNKNOWN, hv_nmi_unknown, NMI_FLAG_FIRST,
diff --git a/arch/x86/kernel/cpu/vmware.c b/arch/x86/kernel/cpu/vmware.c
index 0eda91f8eeac..3c648476d4fb 100644
--- a/arch/x86/kernel/cpu/vmware.c
+++ b/arch/x86/kernel/cpu/vmware.c
@@ -157,7 +157,7 @@ static void __init vmware_platform_setup(void)
 
 #ifdef CONFIG_X86_LOCAL_APIC
 		/* Skip lapic calibration since we know the bus frequency. */
-		lapic_timer_frequency = ecx / HZ;
+		lapic_timer_period = ecx / HZ;
 		pr_info("Host bus clock speed read from hypervisor : %u Hz\n",
 			ecx);
 #endif
diff --git a/arch/x86/kernel/i8253.c b/arch/x86/kernel/i8253.c
index 0d307a657abb..2b7999a1a50a 100644
--- a/arch/x86/kernel/i8253.c
+++ b/arch/x86/kernel/i8253.c
@@ -8,6 +8,7 @@
 #include <linux/timex.h>
 #include <linux/i8253.h>
 
+#include <asm/apic.h>
 #include <asm/hpet.h>
 #include <asm/time.h>
 #include <asm/smp.h>
@@ -18,10 +19,32 @@
  */
 struct clock_event_device *global_clock_event;
 
-void __init setup_pit_timer(void)
+/*
+ * Modern chipsets can disable the PIT clock which makes it unusable. It
+ * would be possible to enable the clock but the registers are chipset
+ * specific and not discoverable. Avoid the whack a mole game.
+ *
+ * These platforms have discoverable TSC/CPU frequencies but this also
+ * requires to know the local APIC timer frequency as it normally is
+ * calibrated against the PIT interrupt.
+ */
+static bool __init use_pit(void)
+{
+	if (!IS_ENABLED(CONFIG_X86_TSC) || !boot_cpu_has(X86_FEATURE_TSC))
+		return true;
+
+	/* This also returns true when APIC is disabled */
+	return apic_needs_pit();
+}
+
+bool __init pit_timer_init(void)
 {
+	if (!use_pit())
+		return false;
+
 	clockevent_i8253_init(true);
 	global_clock_event = &i8253_clockevent;
+	return true;
 }
 
 #ifndef CONFIG_X86_64
diff --git a/arch/x86/kernel/idt.c b/arch/x86/kernel/idt.c
index d2482bbbe3d0..87ef69a72c52 100644
--- a/arch/x86/kernel/idt.c
+++ b/arch/x86/kernel/idt.c
@@ -319,7 +319,8 @@ void __init idt_setup_apic_and_irq_gates(void)
 #ifdef CONFIG_X86_LOCAL_APIC
 	for_each_clear_bit_from(i, system_vectors, NR_VECTORS) {
 		set_bit(i, system_vectors);
-		set_intr_gate(i, spurious_interrupt);
+		entry = spurious_entries_start + 8 * (i - FIRST_SYSTEM_VECTOR);
+		set_intr_gate(i, entry);
 	}
 #endif
 }
diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c
index 9b68b5b00ac9..cc496eb7a8d2 100644
--- a/arch/x86/kernel/irq.c
+++ b/arch/x86/kernel/irq.c
@@ -247,7 +247,7 @@ __visible unsigned int __irq_entry do_IRQ(struct pt_regs *regs)
 	if (!handle_irq(desc, regs)) {
 		ack_APIC_irq();
 
-		if (desc != VECTOR_RETRIGGERED) {
+		if (desc != VECTOR_RETRIGGERED && desc != VECTOR_SHUTDOWN) {
 			pr_emerg_ratelimited("%s: %d.%d No irq handler for vector\n",
 					     __func__, smp_processor_id(),
 					     vector);
diff --git a/arch/x86/kernel/jailhouse.c b/arch/x86/kernel/jailhouse.c
index 1b2ee55a2dfb..ba95bc70460d 100644
--- a/arch/x86/kernel/jailhouse.c
+++ b/arch/x86/kernel/jailhouse.c
@@ -45,7 +45,7 @@ static void jailhouse_get_wallclock(struct timespec64 *now)
 
 static void __init jailhouse_timer_init(void)
 {
-	lapic_timer_frequency = setup_data.apic_khz * (1000 / HZ);
+	lapic_timer_period = setup_data.apic_khz * (1000 / HZ);
 }
 
 static unsigned long jailhouse_get_tsc(void)
diff --git a/arch/x86/kernel/smp.c b/arch/x86/kernel/smp.c
index 4693e2f3a03e..96421f97e75c 100644
--- a/arch/x86/kernel/smp.c
+++ b/arch/x86/kernel/smp.c
@@ -144,7 +144,7 @@ void native_send_call_func_ipi(const struct cpumask *mask)
 	}
 
 	cpumask_copy(allbutself, cpu_online_mask);
-	cpumask_clear_cpu(smp_processor_id(), allbutself);
+	__cpumask_clear_cpu(smp_processor_id(), allbutself);
 
 	if (cpumask_equal(mask, allbutself) &&
 	    cpumask_equal(cpu_online_mask, cpu_callout_mask))
diff --git a/arch/x86/kernel/time.c b/arch/x86/kernel/time.c
index 0e14f6c0d35e..07c0e960b3f3 100644
--- a/arch/x86/kernel/time.c
+++ b/arch/x86/kernel/time.c
@@ -82,8 +82,11 @@ static void __init setup_default_timer_irq(void)
 /* Default timer init function */
 void __init hpet_time_init(void)
 {
-	if (!hpet_enable())
-		setup_pit_timer();
+	if (!hpet_enable()) {
+		if (!pit_timer_init())
+			return;
+	}
+
 	setup_default_timer_irq();
 }
 
diff --git a/arch/x86/kernel/tsc.c b/arch/x86/kernel/tsc.c
index 0b29e58f288e..59b57605e66c 100644
--- a/arch/x86/kernel/tsc.c
+++ b/arch/x86/kernel/tsc.c
@@ -632,31 +632,38 @@ unsigned long native_calibrate_tsc(void)
 
 	crystal_khz = ecx_hz / 1000;
 
-	if (crystal_khz == 0) {
-		switch (boot_cpu_data.x86_model) {
-		case INTEL_FAM6_SKYLAKE_MOBILE:
-		case INTEL_FAM6_SKYLAKE_DESKTOP:
-		case INTEL_FAM6_KABYLAKE_MOBILE:
-		case INTEL_FAM6_KABYLAKE_DESKTOP:
-			crystal_khz = 24000;	/* 24.0 MHz */
-			break;
-		case INTEL_FAM6_ATOM_GOLDMONT_X:
-			crystal_khz = 25000;	/* 25.0 MHz */
-			break;
-		case INTEL_FAM6_ATOM_GOLDMONT:
-			crystal_khz = 19200;	/* 19.2 MHz */
-			break;
-		}
-	}
+	/*
+	 * Denverton SoCs don't report crystal clock, and also don't support
+	 * CPUID.0x16 for the calculation below, so hardcode the 25MHz crystal
+	 * clock.
+	 */
+	if (crystal_khz == 0 &&
+			boot_cpu_data.x86_model == INTEL_FAM6_ATOM_GOLDMONT_X)
+		crystal_khz = 25000;
 
-	if (crystal_khz == 0)
-		return 0;
 	/*
-	 * TSC frequency determined by CPUID is a "hardware reported"
+	 * TSC frequency reported directly by CPUID is a "hardware reported"
 	 * frequency and is the most accurate one so far we have. This
 	 * is considered a known frequency.
 	 */
-	setup_force_cpu_cap(X86_FEATURE_TSC_KNOWN_FREQ);
+	if (crystal_khz != 0)
+		setup_force_cpu_cap(X86_FEATURE_TSC_KNOWN_FREQ);
+
+	/*
+	 * Some Intel SoCs like Skylake and Kabylake don't report the crystal
+	 * clock, but we can easily calculate it to a high degree of accuracy
+	 * by considering the crystal ratio and the CPU speed.
+	 */
+	if (crystal_khz == 0 && boot_cpu_data.cpuid_level >= 0x16) {
+		unsigned int eax_base_mhz, ebx, ecx, edx;
+
+		cpuid(0x16, &eax_base_mhz, &ebx, &ecx, &edx);
+		crystal_khz = eax_base_mhz * 1000 *
+			eax_denominator / ebx_numerator;
+	}
+
+	if (crystal_khz == 0)
+		return 0;
 
 	/*
 	 * For Atom SoCs TSC is the only reliable clocksource.
@@ -665,6 +672,16 @@ unsigned long native_calibrate_tsc(void)
 	if (boot_cpu_data.x86_model == INTEL_FAM6_ATOM_GOLDMONT)
 		setup_force_cpu_cap(X86_FEATURE_TSC_RELIABLE);
 
+#ifdef CONFIG_X86_LOCAL_APIC
+	/*
+	 * The local APIC appears to be fed by the core crystal clock
+	 * (which sounds entirely sensible). We can set the global
+	 * lapic_timer_period here to avoid having to calibrate the APIC
+	 * timer later.
+	 */
+	lapic_timer_period = crystal_khz * 1000 / HZ;
+#endif
+
 	return crystal_khz * ebx_numerator / eax_denominator;
 }
 
diff --git a/arch/x86/kernel/tsc_msr.c b/arch/x86/kernel/tsc_msr.c
index 3d0e9aeea7c8..067858fe4db8 100644
--- a/arch/x86/kernel/tsc_msr.c
+++ b/arch/x86/kernel/tsc_msr.c
@@ -71,7 +71,7 @@ static const struct x86_cpu_id tsc_msr_cpu_ids[] = {
 /*
  * MSR-based CPU/TSC frequency discovery for certain CPUs.
  *
- * Set global "lapic_timer_frequency" to bus_clock_cycles/jiffy
+ * Set global "lapic_timer_period" to bus_clock_cycles/jiffy
  * Return processor base frequency in KHz, or 0 on failure.
  */
 unsigned long cpu_khz_from_msr(void)
@@ -104,7 +104,7 @@ unsigned long cpu_khz_from_msr(void)
 	res = freq * ratio;
 
 #ifdef CONFIG_X86_LOCAL_APIC
-	lapic_timer_frequency = (freq * 1000) / HZ;
+	lapic_timer_period = (freq * 1000) / HZ;
 #endif
 
 	/*