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

5 files changed, 84 insertions, 25 deletions

diff --git a/kernel/irq/autoprobe.c b/kernel/irq/autoprobe.c
index 16cbf6beb276..ae60cae24e9a 100644
--- a/kernel/irq/autoprobe.c
+++ b/kernel/irq/autoprobe.c
@@ -90,7 +90,7 @@ unsigned long probe_irq_on(void)
 			/* It triggered already - consider it spurious. */
 			if (!(desc->istate & IRQS_WAITING)) {
 				desc->istate &= ~IRQS_AUTODETECT;
-				irq_shutdown(desc);
+				irq_shutdown_and_deactivate(desc);
 			} else
 				if (i < 32)
 					mask |= 1 << i;
@@ -127,7 +127,7 @@ unsigned int probe_irq_mask(unsigned long val)
 				mask |= 1 << i;
 
 			desc->istate &= ~IRQS_AUTODETECT;
-			irq_shutdown(desc);
+			irq_shutdown_and_deactivate(desc);
 		}
 		raw_spin_unlock_irq(&desc->lock);
 	}
@@ -169,7 +169,7 @@ int probe_irq_off(unsigned long val)
 				nr_of_irqs++;
 			}
 			desc->istate &= ~IRQS_AUTODETECT;
-			irq_shutdown(desc);
+			irq_shutdown_and_deactivate(desc);
 		}
 		raw_spin_unlock_irq(&desc->lock);
 	}
diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c
index 04c850fb70cb..b76703b2c0af 100644
--- a/kernel/irq/chip.c
+++ b/kernel/irq/chip.c
@@ -314,6 +314,12 @@ void irq_shutdown(struct irq_desc *desc)
 		}
 		irq_state_clr_started(desc);
 	}
+}
+
+
+void irq_shutdown_and_deactivate(struct irq_desc *desc)
+{
+	irq_shutdown(desc);
 	/*
 	 * This must be called even if the interrupt was never started up,
 	 * because the activation can happen before the interrupt is
diff --git a/kernel/irq/cpuhotplug.c b/kernel/irq/cpuhotplug.c
index 5b1072e394b2..6c7ca2e983a5 100644
--- a/kernel/irq/cpuhotplug.c
+++ b/kernel/irq/cpuhotplug.c
@@ -116,7 +116,7 @@ static bool migrate_one_irq(struct irq_desc *desc)
 		 */
 		if (irqd_affinity_is_managed(d)) {
 			irqd_set_managed_shutdown(d);
-			irq_shutdown(desc);
+			irq_shutdown_and_deactivate(desc);
 			return false;
 		}
 		affinity = cpu_online_mask;
diff --git a/kernel/irq/internals.h b/kernel/irq/internals.h
index 21f9927ff5ad..3924fbe829d4 100644
--- a/kernel/irq/internals.h
+++ b/kernel/irq/internals.h
@@ -82,6 +82,7 @@ extern int irq_activate_and_startup(struct irq_desc *desc, bool resend);
 extern int irq_startup(struct irq_desc *desc, bool resend, bool force);
 
 extern void irq_shutdown(struct irq_desc *desc);
+extern void irq_shutdown_and_deactivate(struct irq_desc *desc);
 extern void irq_enable(struct irq_desc *desc);
 extern void irq_disable(struct irq_desc *desc);
 extern void irq_percpu_enable(struct irq_desc *desc, unsigned int cpu);
@@ -96,6 +97,10 @@ static inline void irq_mark_irq(unsigned int irq) { }
 extern void irq_mark_irq(unsigned int irq);
 #endif
 
+extern int __irq_get_irqchip_state(struct irq_data *data,
+				   enum irqchip_irq_state which,
+				   bool *state);
+
 extern void init_kstat_irqs(struct irq_desc *desc, int node, int nr);
 
 irqreturn_t __handle_irq_event_percpu(struct irq_desc *desc, unsigned int *flags);
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index 78f3ddeb7fe4..e8f7f179bf77 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -13,6 +13,7 @@
 #include <linux/module.h>
 #include <linux/random.h>
 #include <linux/interrupt.h>
+#include <linux/irqdomain.h>
 #include <linux/slab.h>
 #include <linux/sched.h>
 #include <linux/sched/rt.h>
@@ -34,8 +35,9 @@ static int __init setup_forced_irqthreads(char *arg)
 early_param("threadirqs", setup_forced_irqthreads);
 #endif
 
-static void __synchronize_hardirq(struct irq_desc *desc)
+static void __synchronize_hardirq(struct irq_desc *desc, bool sync_chip)
 {
+	struct irq_data *irqd = irq_desc_get_irq_data(desc);
 	bool inprogress;
 
 	do {
@@ -51,6 +53,20 @@ static void __synchronize_hardirq(struct irq_desc *desc)
 		/* Ok, that indicated we're done: double-check carefully. */
 		raw_spin_lock_irqsave(&desc->lock, flags);
 		inprogress = irqd_irq_inprogress(&desc->irq_data);
+
+		/*
+		 * If requested and supported, check at the chip whether it
+		 * is in flight at the hardware level, i.e. already pending
+		 * in a CPU and waiting for service and acknowledge.
+		 */
+		if (!inprogress && sync_chip) {
+			/*
+			 * Ignore the return code. inprogress is only updated
+			 * when the chip supports it.
+			 */
+			__irq_get_irqchip_state(irqd, IRQCHIP_STATE_ACTIVE,
+						&inprogress);
+		}
 		raw_spin_unlock_irqrestore(&desc->lock, flags);
 
 		/* Oops, that failed? */
@@ -73,13 +89,18 @@ static void __synchronize_hardirq(struct irq_desc *desc)
  *	Returns: false if a threaded handler is active.
  *
  *	This function may be called - with care - from IRQ context.
+ *
+ *	It does not check whether there is an interrupt in flight at the
+ *	hardware level, but not serviced yet, as this might deadlock when
+ *	called with interrupts disabled and the target CPU of the interrupt
+ *	is the current CPU.
  */
 bool synchronize_hardirq(unsigned int irq)
 {
 	struct irq_desc *desc = irq_to_desc(irq);
 
 	if (desc) {
-		__synchronize_hardirq(desc);
+		__synchronize_hardirq(desc, false);
 		return !atomic_read(&desc->threads_active);
 	}
 
@@ -95,14 +116,19 @@ EXPORT_SYMBOL(synchronize_hardirq);
  *	to complete before returning. If you use this function while
  *	holding a resource the IRQ handler may need you will deadlock.
  *
- *	This function may be called - with care - from IRQ context.
+ *	Can only be called from preemptible code as it might sleep when
+ *	an interrupt thread is associated to @irq.
+ *
+ *	It optionally makes sure (when the irq chip supports that method)
+ *	that the interrupt is not pending in any CPU and waiting for
+ *	service.
  */
 void synchronize_irq(unsigned int irq)
 {
 	struct irq_desc *desc = irq_to_desc(irq);
 
 	if (desc) {
-		__synchronize_hardirq(desc);
+		__synchronize_hardirq(desc, true);
 		/*
 		 * We made sure that no hardirq handler is
 		 * running. Now verify that no threaded handlers are
@@ -1699,6 +1725,7 @@ static struct irqaction *__free_irq(struct irq_desc *desc, void *dev_id)
 	/* If this was the last handler, shut down the IRQ line: */
 	if (!desc->action) {
 		irq_settings_clr_disable_unlazy(desc);
+		/* Only shutdown. Deactivate after synchronize_hardirq() */
 		irq_shutdown(desc);
 	}
 
@@ -1727,8 +1754,12 @@ static struct irqaction *__free_irq(struct irq_desc *desc, void *dev_id)
 
 	unregister_handler_proc(irq, action);
 
-	/* Make sure it's not being used on another CPU: */
-	synchronize_hardirq(irq);
+	/*
+	 * Make sure it's not being used on another CPU and if the chip
+	 * supports it also make sure that there is no (not yet serviced)
+	 * interrupt in flight at the hardware level.
+	 */
+	__synchronize_hardirq(desc, true);
 
 #ifdef CONFIG_DEBUG_SHIRQ
 	/*
@@ -1768,6 +1799,14 @@ static struct irqaction *__free_irq(struct irq_desc *desc, void *dev_id)
 		 * require it to deallocate resources over the slow bus.
 		 */
 		chip_bus_lock(desc);
+		/*
+		 * There is no interrupt on the fly anymore. Deactivate it
+		 * completely.
+		 */
+		raw_spin_lock_irqsave(&desc->lock, flags);
+		irq_domain_deactivate_irq(&desc->irq_data);
+		raw_spin_unlock_irqrestore(&desc->lock, flags);
+
 		irq_release_resources(desc);
 		chip_bus_sync_unlock(desc);
 		irq_remove_timings(desc);
@@ -1855,7 +1894,7 @@ static const void *__cleanup_nmi(unsigned int irq, struct irq_desc *desc)
 	}
 
 	irq_settings_clr_disable_unlazy(desc);
-	irq_shutdown(desc);
+	irq_shutdown_and_deactivate(desc);
 
 	irq_release_resources(desc);
 
@@ -2578,6 +2617,28 @@ out:
 	irq_put_desc_unlock(desc, flags);
 }
 
+int __irq_get_irqchip_state(struct irq_data *data, enum irqchip_irq_state which,
+			    bool *state)
+{
+	struct irq_chip *chip;
+	int err = -EINVAL;
+
+	do {
+		chip = irq_data_get_irq_chip(data);
+		if (chip->irq_get_irqchip_state)
+			break;
+#ifdef CONFIG_IRQ_DOMAIN_HIERARCHY
+		data = data->parent_data;
+#else
+		data = NULL;
+#endif
+	} while (data);
+
+	if (data)
+		err = chip->irq_get_irqchip_state(data, which, state);
+	return err;
+}
+
 /**
  *	irq_get_irqchip_state - returns the irqchip state of a interrupt.
  *	@irq: Interrupt line that is forwarded to a VM
@@ -2596,7 +2657,6 @@ int irq_get_irqchip_state(unsigned int irq, enum irqchip_irq_state which,
 {
 	struct irq_desc *desc;
 	struct irq_data *data;
-	struct irq_chip *chip;
 	unsigned long flags;
 	int err = -EINVAL;
 
@@ -2606,19 +2666,7 @@ int irq_get_irqchip_state(unsigned int irq, enum irqchip_irq_state which,
 
 	data = irq_desc_get_irq_data(desc);
 
-	do {
-		chip = irq_data_get_irq_chip(data);
-		if (chip->irq_get_irqchip_state)
-			break;
-#ifdef CONFIG_IRQ_DOMAIN_HIERARCHY
-		data = data->parent_data;
-#else
-		data = NULL;
-#endif
-	} while (data);
-
-	if (data)
-		err = chip->irq_get_irqchip_state(data, which, state);
+	err = __irq_get_irqchip_state(data, which, state);
 
 	irq_put_desc_busunlock(desc, flags);
 	return err;