1 files changed, 193 insertions, 93 deletions

diff --git a/arch/x86/kernel/irq.c b/arch/x86/kernel/irq.c
index 83ec0175f98..922d2858102 100644
--- a/arch/x86/kernel/irq.c
+++ b/arch/x86/kernel/irq.c
@@ -4,9 +4,12 @@
 #include <linux/cpu.h>
 #include <linux/interrupt.h>
 #include <linux/kernel_stat.h>
+#include <linux/of.h>
 #include <linux/seq_file.h>
 #include <linux/smp.h>
 #include <linux/ftrace.h>
+#include <linux/delay.h>
+#include <linux/export.h>
 
 #include <asm/apic.h>
 #include <asm/io_apic.h>
@@ -14,6 +17,10 @@
 #include <asm/idle.h>
 #include <asm/mce.h>
 #include <asm/hw_irq.h>
+#include <asm/desc.h>
+
+#define CREATE_TRACE_POINTS
+#include <asm/trace/irq_vectors.h>
 
 atomic_t irq_err_count;
 
@@ -43,9 +50,9 @@ void ack_bad_irq(unsigned int irq)
 
 #define irq_stats(x)		(&per_cpu(irq_stat, x))
 /*
- * /proc/interrupts printing:
+ * /proc/interrupts printing for arch specific interrupts
  */
-static int show_other_interrupts(struct seq_file *p, int prec)
+int arch_show_interrupts(struct seq_file *p, int prec)
 {
 	int j;
 
@@ -71,6 +78,10 @@ static int show_other_interrupts(struct seq_file *p, int prec)
 	for_each_online_cpu(j)
 		seq_printf(p, "%10u ", irq_stats(j)->apic_irq_work_irqs);
 	seq_printf(p, "  IRQ work interrupts\n");
+	seq_printf(p, "%*s: ", prec, "RTR");
+	for_each_online_cpu(j)
+		seq_printf(p, "%10u ", irq_stats(j)->icr_read_retry_count);
+	seq_printf(p, "  APIC ICR read retries\n");
 #endif
 	if (x86_platform_ipi_callback) {
 		seq_printf(p, "%*s: ", prec, "PLT");
@@ -85,7 +96,8 @@ static int show_other_interrupts(struct seq_file *p, int prec)
 	seq_printf(p, "  Rescheduling interrupts\n");
 	seq_printf(p, "%*s: ", prec, "CAL");
 	for_each_online_cpu(j)
-		seq_printf(p, "%10u ", irq_stats(j)->irq_call_count);
+		seq_printf(p, "%10u ", irq_stats(j)->irq_call_count -
+					irq_stats(j)->irq_tlb_count);
 	seq_printf(p, "  Function call interrupts\n");
 	seq_printf(p, "%*s: ", prec, "TLB");
 	for_each_online_cpu(j)
@@ -114,6 +126,12 @@ static int show_other_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 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);
+	seq_printf(p, "  Hypervisor callback interrupts\n");
+#endif
 	seq_printf(p, "%*s: %10u\n", prec, "ERR", atomic_read(&irq_err_count));
 #if defined(CONFIG_X86_IO_APIC)
 	seq_printf(p, "%*s: %10u\n", prec, "MIS", atomic_read(&irq_mis_count));
@@ -121,59 +139,6 @@ static int show_other_interrupts(struct seq_file *p, int prec)
 	return 0;
 }
 
-int show_interrupts(struct seq_file *p, void *v)
-{
-	unsigned long flags, any_count = 0;
-	int i = *(loff_t *) v, j, prec;
-	struct irqaction *action;
-	struct irq_desc *desc;
-
-	if (i > nr_irqs)
-		return 0;
-
-	for (prec = 3, j = 1000; prec < 10 && j <= nr_irqs; ++prec)
-		j *= 10;
-
-	if (i == nr_irqs)
-		return show_other_interrupts(p, prec);
-
-	/* print header */
-	if (i == 0) {
-		seq_printf(p, "%*s", prec + 8, "");
-		for_each_online_cpu(j)
-			seq_printf(p, "CPU%-8d", j);
-		seq_putc(p, '\n');
-	}
-
-	desc = irq_to_desc(i);
-	if (!desc)
-		return 0;
-
-	raw_spin_lock_irqsave(&desc->lock, flags);
-	for_each_online_cpu(j)
-		any_count |= kstat_irqs_cpu(i, j);
-	action = desc->action;
-	if (!action && !any_count)
-		goto out;
-
-	seq_printf(p, "%*d: ", prec, i);
-	for_each_online_cpu(j)
-		seq_printf(p, "%10u ", kstat_irqs_cpu(i, j));
-	seq_printf(p, " %8s", desc->irq_data.chip->name);
-	seq_printf(p, "-%-8s", desc->name);
-
-	if (action) {
-		seq_printf(p, "  %s", action->name);
-		while ((action = action->next) != NULL)
-			seq_printf(p, ", %s", action->name);
-	}
-
-	seq_putc(p, '\n');
-out:
-	raw_spin_unlock_irqrestore(&desc->lock, flags);
-	return 0;
-}
-
 /*
  * /proc/stat helpers
  */
@@ -186,13 +151,13 @@ u64 arch_irq_stat_cpu(unsigned int cpu)
 	sum += irq_stats(cpu)->irq_spurious_count;
 	sum += irq_stats(cpu)->apic_perf_irqs;
 	sum += irq_stats(cpu)->apic_irq_work_irqs;
+	sum += irq_stats(cpu)->icr_read_retry_count;
 #endif
 	if (x86_platform_ipi_callback)
 		sum += irq_stats(cpu)->x86_platform_ipis;
 #ifdef CONFIG_SMP
 	sum += irq_stats(cpu)->irq_resched_count;
 	sum += irq_stats(cpu)->irq_call_count;
-	sum += irq_stats(cpu)->irq_tlb_count;
 #endif
 #ifdef CONFIG_X86_THERMAL_VECTOR
 	sum += irq_stats(cpu)->irq_thermal_count;
@@ -210,10 +175,6 @@ u64 arch_irq_stat_cpu(unsigned int cpu)
 u64 arch_irq_stat(void)
 {
 	u64 sum = atomic_read(&irq_err_count);
-
-#ifdef CONFIG_X86_IO_APIC
-	sum += atomic_read(&irq_mis_count);
-#endif
 	return sum;
 }
 
@@ -223,7 +184,7 @@ u64 arch_irq_stat(void)
  * SMP cross-CPU interrupts have their own specific
  * handlers).
  */
-unsigned int __irq_entry do_IRQ(struct pt_regs *regs)
+__visible unsigned int __irq_entry do_IRQ(struct pt_regs *regs)
 {
 	struct pt_regs *old_regs = set_irq_regs(regs);
 
@@ -231,17 +192,21 @@ unsigned int __irq_entry do_IRQ(struct pt_regs *regs)
 	unsigned vector = ~regs->orig_ax;
 	unsigned irq;
 
-	exit_idle();
 	irq_enter();
+	exit_idle();
 
-	irq = __get_cpu_var(vector_irq)[vector];
+	irq = __this_cpu_read(vector_irq[vector]);
 
 	if (!handle_irq(irq, regs)) {
 		ack_APIC_irq();
 
-		if (printk_ratelimit())
-			pr_emerg("%s: %d.%d No irq handler for vector (irq %d)\n",
-				__func__, smp_processor_id(), vector, irq);
+		if (irq != VECTOR_RETRIGGERED) {
+			pr_emerg_ratelimited("%s: %d.%d No irq handler for vector (irq %d)\n",
+					     __func__, smp_processor_id(),
+					     vector, irq);
+		} else {
+			__this_cpu_write(vector_irq[vector], VECTOR_UNDEFINED);
+		}
 	}
 
 	irq_exit();
@@ -253,29 +218,145 @@ unsigned int __irq_entry do_IRQ(struct pt_regs *regs)
 /*
  * Handler for X86_PLATFORM_IPI_VECTOR.
  */
-void smp_x86_platform_ipi(struct pt_regs *regs)
+void __smp_x86_platform_ipi(void)
+{
+	inc_irq_stat(x86_platform_ipis);
+
+	if (x86_platform_ipi_callback)
+		x86_platform_ipi_callback();
+}
+
+__visible void smp_x86_platform_ipi(struct pt_regs *regs)
 {
 	struct pt_regs *old_regs = set_irq_regs(regs);
 
-	ack_APIC_irq();
+	entering_ack_irq();
+	__smp_x86_platform_ipi();
+	exiting_irq();
+	set_irq_regs(old_regs);
+}
 
-	exit_idle();
+#ifdef CONFIG_HAVE_KVM
+/*
+ * Handler for POSTED_INTERRUPT_VECTOR.
+ */
+__visible void smp_kvm_posted_intr_ipi(struct pt_regs *regs)
+{
+	struct pt_regs *old_regs = set_irq_regs(regs);
+
+	ack_APIC_irq();
 
 	irq_enter();
 
-	inc_irq_stat(x86_platform_ipis);
+	exit_idle();
 
-	if (x86_platform_ipi_callback)
-		x86_platform_ipi_callback();
+	inc_irq_stat(kvm_posted_intr_ipis);
 
 	irq_exit();
 
 	set_irq_regs(old_regs);
 }
+#endif
+
+__visible void smp_trace_x86_platform_ipi(struct pt_regs *regs)
+{
+	struct pt_regs *old_regs = set_irq_regs(regs);
+
+	entering_ack_irq();
+	trace_x86_platform_ipi_entry(X86_PLATFORM_IPI_VECTOR);
+	__smp_x86_platform_ipi();
+	trace_x86_platform_ipi_exit(X86_PLATFORM_IPI_VECTOR);
+	exiting_irq();
+	set_irq_regs(old_regs);
+}
 
 EXPORT_SYMBOL_GPL(vector_used_by_percpu_irq);
 
 #ifdef CONFIG_HOTPLUG_CPU
+
+/* These two declarations are only used in check_irq_vectors_for_cpu_disable()
+ * below, which is protected by stop_machine().  Putting them on the stack
+ * results in a stack frame overflow.  Dynamically allocating could result in a
+ * failure so declare these two cpumasks as global.
+ */
+static struct cpumask affinity_new, online_new;
+
+/*
+ * This cpu is going to be removed and its vectors migrated to the remaining
+ * online cpus.  Check to see if there are enough vectors in the remaining cpus.
+ * This function is protected by stop_machine().
+ */
+int check_irq_vectors_for_cpu_disable(void)
+{
+	int irq, cpu;
+	unsigned int this_cpu, vector, this_count, count;
+	struct irq_desc *desc;
+	struct irq_data *data;
+
+	this_cpu = smp_processor_id();
+	cpumask_copy(&online_new, cpu_online_mask);
+	cpu_clear(this_cpu, online_new);
+
+	this_count = 0;
+	for (vector = FIRST_EXTERNAL_VECTOR; vector < NR_VECTORS; vector++) {
+		irq = __this_cpu_read(vector_irq[vector]);
+		if (irq >= 0) {
+			desc = irq_to_desc(irq);
+			data = irq_desc_get_irq_data(desc);
+			cpumask_copy(&affinity_new, data->affinity);
+			cpu_clear(this_cpu, affinity_new);
+
+			/* Do not count inactive or per-cpu irqs. */
+			if (!irq_has_action(irq) || irqd_is_per_cpu(data))
+				continue;
+
+			/*
+			 * A single irq may be mapped to multiple
+			 * cpu's vector_irq[] (for example IOAPIC cluster
+			 * mode).  In this case we have two
+			 * possibilities:
+			 *
+			 * 1) the resulting affinity mask is empty; that is
+			 * this the down'd cpu is the last cpu in the irq's
+			 * affinity mask, or
+			 *
+			 * 2) the resulting affinity mask is no longer
+			 * a subset of the online cpus but the affinity
+			 * mask is not zero; that is the down'd cpu is the
+			 * last online cpu in a user set affinity mask.
+			 */
+			if (cpumask_empty(&affinity_new) ||
+			    !cpumask_subset(&affinity_new, &online_new))
+				this_count++;
+		}
+	}
+
+	count = 0;
+	for_each_online_cpu(cpu) {
+		if (cpu == this_cpu)
+			continue;
+		/*
+		 * We scan from FIRST_EXTERNAL_VECTOR to first system
+		 * vector. If the vector is marked in the used vectors
+		 * bitmap or an irq is assigned to it, we don't count
+		 * it as available.
+		 */
+		for (vector = FIRST_EXTERNAL_VECTOR;
+		     vector < first_system_vector; vector++) {
+			if (!test_bit(vector, used_vectors) &&
+			    per_cpu(vector_irq, cpu)[vector] < 0)
+					count++;
+		}
+	}
+
+	if (count < this_count) {
+		pr_warn("CPU %d disable failed: CPU has %u vectors assigned and there are only %u available.\n",
+			this_cpu, this_count, count);
+		return -ERANGE;
+	}
+	return 0;
+}
+
 /* A cpu has been removed from cpu_online_mask.  Reset irq affinities. */
 void fixup_irqs(void)
 {
@@ -283,6 +364,8 @@ void fixup_irqs(void)
 	static int warned;
 	struct irq_desc *desc;
 	struct irq_data *data;
+	struct irq_chip *chip;
+	int ret;
 
 	for_each_irq_desc(irq, desc) {
 		int break_affinity = 0;
@@ -297,10 +380,10 @@ void fixup_irqs(void)
 		/* interrupt's are disabled at this point */
 		raw_spin_lock(&desc->lock);
 
-		data = &desc->irq_data;
+		data = irq_desc_get_irq_data(desc);
 		affinity = data->affinity;
-		if (!irq_has_action(irq) ||
-		    cpumask_equal(affinity, cpu_online_mask)) {
+		if (!irq_has_action(irq) || irqd_is_per_cpu(data) ||
+		    cpumask_subset(affinity, cpu_online_mask)) {
 			raw_spin_unlock(&desc->lock);
 			continue;
 		}
@@ -314,26 +397,37 @@ void fixup_irqs(void)
 
 		if (cpumask_any_and(affinity, cpu_online_mask) >= nr_cpu_ids) {
 			break_affinity = 1;
-			affinity = cpu_all_mask;
+			affinity = cpu_online_mask;
 		}
 
-		if (!(desc->status & IRQ_MOVE_PCNTXT) && data->chip->irq_mask)
-			data->chip->irq_mask(data);
-
-		if (data->chip->irq_set_affinity)
-			data->chip->irq_set_affinity(data, affinity, true);
-		else if (!(warned++))
-			set_affinity = 0;
+		chip = irq_data_get_irq_chip(data);
+		if (!irqd_can_move_in_process_context(data) && chip->irq_mask)
+			chip->irq_mask(data);
+
+		if (chip->irq_set_affinity) {
+			ret = chip->irq_set_affinity(data, affinity, true);
+			if (ret == -ENOSPC)
+				pr_crit("IRQ %d set affinity failed because there are no available vectors.  The device assigned to this IRQ is unstable.\n", irq);
+		} else {
+			if (!(warned++))
+				set_affinity = 0;
+		}
 
-		if (!(desc->status & IRQ_MOVE_PCNTXT) && data->chip->irq_unmask)
-			data->chip->irq_unmask(data);
+		/*
+		 * We unmask if the irq was not marked masked by the
+		 * core code. That respects the lazy irq disable
+		 * behaviour.
+		 */
+		if (!irqd_can_move_in_process_context(data) &&
+		    !irqd_irq_masked(data) && chip->irq_unmask)
+			chip->irq_unmask(data);
 
 		raw_spin_unlock(&desc->lock);
 
 		if (break_affinity && set_affinity)
-			printk("Broke affinity for irq %i\n", irq);
+			pr_notice("Broke affinity for irq %i\n", irq);
 		else if (!set_affinity)
-			printk("Cannot set affinity for irq %i\n", irq);
+			pr_notice("Cannot set affinity for irq %i\n", irq);
 	}
 
 	/*
@@ -350,19 +444,25 @@ void fixup_irqs(void)
 	for (vector = FIRST_EXTERNAL_VECTOR; vector < NR_VECTORS; vector++) {
 		unsigned int irr;
 
-		if (__get_cpu_var(vector_irq)[vector] < 0)
+		if (__this_cpu_read(vector_irq[vector]) <= VECTOR_UNDEFINED)
 			continue;
 
 		irr = apic_read(APIC_IRR + (vector / 32 * 0x10));
 		if (irr  & (1 << (vector % 32))) {
-			irq = __get_cpu_var(vector_irq)[vector];
+			irq = __this_cpu_read(vector_irq[vector]);
 
-			data = irq_get_irq_data(irq);
+			desc = irq_to_desc(irq);
+			data = irq_desc_get_irq_data(desc);
+			chip = irq_data_get_irq_chip(data);
 			raw_spin_lock(&desc->lock);
-			if (data->chip->irq_retrigger)
-				data->chip->irq_retrigger(data);
+			if (chip->irq_retrigger) {
+				chip->irq_retrigger(data);
+				__this_cpu_write(vector_irq[vector], VECTOR_RETRIGGERED);
+			}
 			raw_spin_unlock(&desc->lock);
 		}
+		if (__this_cpu_read(vector_irq[vector]) != VECTOR_RETRIGGERED)
+			__this_cpu_write(vector_irq[vector], VECTOR_UNDEFINED);
 	}
 }
 #endif