1 files changed, 128 insertions, 45 deletions

diff --git a/arch/x86/kernel/apic/vector.c b/arch/x86/kernel/apic/vector.c
index 48293d15f1e1..3e6f6b448f6a 100644
--- a/arch/x86/kernel/apic/vector.c
+++ b/arch/x86/kernel/apic/vector.c
@@ -161,6 +161,7 @@ static void apic_update_vector(struct irq_data *irqd, unsigned int newvec,
 		apicd->move_in_progress = true;
 		apicd->prev_vector = apicd->vector;
 		apicd->prev_cpu = apicd->cpu;
+		WARN_ON_ONCE(apicd->cpu == newcpu);
 	} else {
 		irq_matrix_free(vector_matrix, apicd->cpu, apicd->vector,
 				managed);
@@ -272,20 +273,24 @@ static int assign_irq_vector_any_locked(struct irq_data *irqd)
 	const struct cpumask *affmsk = irq_data_get_affinity_mask(irqd);
 	int node = irq_data_get_node(irqd);
 
-	if (node == NUMA_NO_NODE)
-		goto all;
-	/* Try the intersection of @affmsk and node mask */
-	cpumask_and(vector_searchmask, cpumask_of_node(node), affmsk);
-	if (!assign_vector_locked(irqd, vector_searchmask))
-		return 0;
-	/* Try the node mask */
-	if (!assign_vector_locked(irqd, cpumask_of_node(node)))
-		return 0;
-all:
+	if (node != NUMA_NO_NODE) {
+		/* Try the intersection of @affmsk and node mask */
+		cpumask_and(vector_searchmask, cpumask_of_node(node), affmsk);
+		if (!assign_vector_locked(irqd, vector_searchmask))
+			return 0;
+	}
+
 	/* Try the full affinity mask */
 	cpumask_and(vector_searchmask, affmsk, cpu_online_mask);
 	if (!assign_vector_locked(irqd, vector_searchmask))
 		return 0;
+
+	if (node != NUMA_NO_NODE) {
+		/* Try the node mask */
+		if (!assign_vector_locked(irqd, cpumask_of_node(node)))
+			return 0;
+	}
+
 	/* Try the full online mask */
 	return assign_vector_locked(irqd, cpu_online_mask);
 }
@@ -446,12 +451,10 @@ static int x86_vector_activate(struct irq_domain *dom, struct irq_data *irqd,
 	trace_vector_activate(irqd->irq, apicd->is_managed,
 			      apicd->can_reserve, reserve);
 
-	/* Nothing to do for fixed assigned vectors */
-	if (!apicd->can_reserve && !apicd->is_managed)
-		return 0;
-
 	raw_spin_lock_irqsave(&vector_lock, flags);
-	if (reserve || irqd_is_managed_and_shutdown(irqd))
+	if (!apicd->can_reserve && !apicd->is_managed)
+		assign_irq_vector_any_locked(irqd);
+	else if (reserve || irqd_is_managed_and_shutdown(irqd))
 		vector_assign_managed_shutdown(irqd);
 	else if (apicd->is_managed)
 		ret = activate_managed(irqd);
@@ -540,6 +543,14 @@ static int x86_vector_alloc_irqs(struct irq_domain *domain, unsigned int virq,
 	if ((info->flags & X86_IRQ_ALLOC_CONTIGUOUS_VECTORS) && nr_irqs > 1)
 		return -ENOSYS;
 
+	/*
+	 * Catch any attempt to touch the cascade interrupt on a PIC
+	 * equipped system.
+	 */
+	if (WARN_ON_ONCE(info->flags & X86_IRQ_ALLOC_LEGACY &&
+			 virq == PIC_CASCADE_IR))
+		return -EINVAL;
+
 	for (i = 0; i < nr_irqs; i++) {
 		irqd = irq_domain_get_irq_data(domain, virq + i);
 		BUG_ON(!irqd);
@@ -557,6 +568,16 @@ static int x86_vector_alloc_irqs(struct irq_domain *domain, unsigned int virq,
 		irqd->hwirq = virq + i;
 		irqd_set_single_target(irqd);
 		/*
+		 * Prevent that any of these interrupts is invoked in
+		 * non interrupt context via e.g. generic_handle_irq()
+		 * as that can corrupt the affinity move state.
+		 */
+		irqd_set_handle_enforce_irqctx(irqd);
+
+		/* Don't invoke affinity setter on deactivated interrupts */
+		irqd_set_affinity_on_activate(irqd);
+
+		/*
 		 * Legacy vectors are already assigned when the IOAPIC
 		 * takes them over. They stay on the same vector. This is
 		 * required for check_timer() to work correctly as it might
@@ -627,7 +648,50 @@ static void x86_vector_debug_show(struct seq_file *m, struct irq_domain *d,
 }
 #endif
 
+int x86_fwspec_is_ioapic(struct irq_fwspec *fwspec)
+{
+	if (fwspec->param_count != 1)
+		return 0;
+
+	if (is_fwnode_irqchip(fwspec->fwnode)) {
+		const char *fwname = fwnode_get_name(fwspec->fwnode);
+		return fwname && !strncmp(fwname, "IO-APIC-", 8) &&
+			simple_strtol(fwname+8, NULL, 10) == fwspec->param[0];
+	}
+	return to_of_node(fwspec->fwnode) &&
+		of_device_is_compatible(to_of_node(fwspec->fwnode),
+					"intel,ce4100-ioapic");
+}
+
+int x86_fwspec_is_hpet(struct irq_fwspec *fwspec)
+{
+	if (fwspec->param_count != 1)
+		return 0;
+
+	if (is_fwnode_irqchip(fwspec->fwnode)) {
+		const char *fwname = fwnode_get_name(fwspec->fwnode);
+		return fwname && !strncmp(fwname, "HPET-MSI-", 9) &&
+			simple_strtol(fwname+9, NULL, 10) == fwspec->param[0];
+	}
+	return 0;
+}
+
+static int x86_vector_select(struct irq_domain *d, struct irq_fwspec *fwspec,
+			     enum irq_domain_bus_token bus_token)
+{
+	/*
+	 * HPET and I/OAPIC cannot be parented in the vector domain
+	 * if IRQ remapping is enabled. APIC IDs above 15 bits are
+	 * only permitted if IRQ remapping is enabled, so check that.
+	 */
+	if (apic->apic_id_valid(32768))
+		return 0;
+
+	return x86_fwspec_is_ioapic(fwspec) || x86_fwspec_is_hpet(fwspec);
+}
+
 static const struct irq_domain_ops x86_vector_domain_ops = {
+	.select		= x86_vector_select,
 	.alloc		= x86_vector_alloc_irqs,
 	.free		= x86_vector_free_irqs,
 	.activate	= x86_vector_activate,
@@ -674,11 +738,31 @@ void lapic_assign_legacy_vector(unsigned int irq, bool replace)
 	irq_matrix_assign_system(vector_matrix, ISA_IRQ_VECTOR(irq), replace);
 }
 
+void __init lapic_update_legacy_vectors(void)
+{
+	unsigned int i;
+
+	if (IS_ENABLED(CONFIG_X86_IO_APIC) && nr_ioapics > 0)
+		return;
+
+	/*
+	 * If the IO/APIC is disabled via config, kernel command line or
+	 * lack of enumeration then all legacy interrupts are routed
+	 * through the PIC. Make sure that they are marked as legacy
+	 * vectors. PIC_CASCADE_IRQ has already been marked in
+	 * lapic_assign_system_vectors().
+	 */
+	for (i = 0; i < nr_legacy_irqs(); i++) {
+		if (i != PIC_CASCADE_IR)
+			lapic_assign_legacy_vector(i, true);
+	}
+}
+
 void __init lapic_assign_system_vectors(void)
 {
-	unsigned int i, vector = 0;
+	unsigned int i, vector;
 
-	for_each_set_bit_from(vector, system_vectors, NR_VECTORS)
+	for_each_set_bit(vector, system_vectors, NR_VECTORS)
 		irq_matrix_assign_system(vector_matrix, vector, false);
 
 	if (nr_legacy_irqs() > 1)
@@ -689,6 +773,11 @@ void __init lapic_assign_system_vectors(void)
 
 	/* Mark the preallocated legacy interrupts */
 	for (i = 0; i < nr_legacy_irqs(); i++) {
+		/*
+		 * Don't touch the cascade interrupt. It's unusable
+		 * on PIC equipped machines. See the large comment
+		 * in the IO/APIC code.
+		 */
 		if (i != PIC_CASCADE_IR)
 			irq_matrix_assign(vector_matrix, ISA_IRQ_VECTOR(i));
 	}
@@ -703,11 +792,8 @@ int __init arch_early_irq_init(void)
 	x86_vector_domain = irq_domain_create_tree(fn, &x86_vector_domain_ops,
 						   NULL);
 	BUG_ON(x86_vector_domain == NULL);
-	irq_domain_free_fwnode(fn);
 	irq_set_default_host(x86_vector_domain);
 
-	arch_init_msi_domain(x86_vector_domain);
-
 	BUG_ON(!alloc_cpumask_var(&vector_searchmask, GFP_KERNEL));
 
 	/*
@@ -769,20 +855,10 @@ void lapic_offline(void)
 static int apic_set_affinity(struct irq_data *irqd,
 			     const struct cpumask *dest, bool force)
 {
-	struct apic_chip_data *apicd = apic_chip_data(irqd);
 	int err;
 
-	/*
-	 * Core code can call here for inactive interrupts. For inactive
-	 * interrupts which use managed or reservation mode there is no
-	 * point in going through the vector assignment right now as the
-	 * activation will assign a vector which fits the destination
-	 * cpumask. Let the core code store the destination mask and be
-	 * done with it.
-	 */
-	if (!irqd_is_activated(irqd) &&
-	    (apicd->is_managed || apicd->can_reserve))
-		return IRQ_SET_MASK_OK;
+	if (WARN_ON_ONCE(!irqd_is_activated(irqd)))
+		return -EIO;
 
 	raw_spin_lock(&vector_lock);
 	cpumask_and(vector_searchmask, dest, cpu_online_mask);
@@ -822,10 +898,17 @@ void apic_ack_edge(struct irq_data *irqd)
 	apic_ack_irq(irqd);
 }
 
+static void x86_vector_msi_compose_msg(struct irq_data *data,
+				       struct msi_msg *msg)
+{
+       __irq_msi_compose_msg(irqd_cfg(data), msg, false);
+}
+
 static struct irq_chip lapic_controller = {
 	.name			= "APIC",
 	.irq_ack		= apic_ack_edge,
 	.irq_set_affinity	= apic_set_affinity,
+	.irq_compose_msi_msg	= x86_vector_msi_compose_msg,
 	.irq_retrigger		= apic_retrigger_irq,
 };
 
@@ -855,13 +938,13 @@ static void free_moved_vector(struct apic_chip_data *apicd)
 	apicd->move_in_progress = 0;
 }
 
-asmlinkage __visible void __irq_entry smp_irq_move_cleanup_interrupt(void)
+DEFINE_IDTENTRY_SYSVEC(sysvec_irq_move_cleanup)
 {
 	struct hlist_head *clhead = this_cpu_ptr(&cleanup_list);
 	struct apic_chip_data *apicd;
 	struct hlist_node *tmp;
 
-	entering_ack_irq();
+	ack_APIC_irq();
 	/* Prevent vectors vanishing under us */
 	raw_spin_lock(&vector_lock);
 
@@ -886,7 +969,6 @@ asmlinkage __visible void __irq_entry smp_irq_move_cleanup_interrupt(void)
 	}
 
 	raw_spin_unlock(&vector_lock);
-	exiting_irq();
 }
 
 static void __send_cleanup_vector(struct apic_chip_data *apicd)
@@ -914,7 +996,7 @@ void send_cleanup_vector(struct irq_cfg *cfg)
 		__send_cleanup_vector(apicd);
 }
 
-static void __irq_complete_move(struct irq_cfg *cfg, unsigned vector)
+void irq_complete_move(struct irq_cfg *cfg)
 {
 	struct apic_chip_data *apicd;
 
@@ -922,15 +1004,16 @@ static void __irq_complete_move(struct irq_cfg *cfg, unsigned vector)
 	if (likely(!apicd->move_in_progress))
 		return;
 
-	if (vector == apicd->vector && apicd->cpu == smp_processor_id())
+	/*
+	 * If the interrupt arrived on the new target CPU, cleanup the
+	 * vector on the old target CPU. A vector check is not required
+	 * because an interrupt can never move from one vector to another
+	 * on the same CPU.
+	 */
+	if (apicd->cpu == smp_processor_id())
 		__send_cleanup_vector(apicd);
 }
 
-void irq_complete_move(struct irq_cfg *cfg)
-{
-	__irq_complete_move(cfg, ~get_irq_regs()->orig_ax);
-}
-
 /*
  * Called from fixup_irqs() with @desc->lock held and interrupts disabled.
  */
@@ -995,7 +1078,7 @@ void irq_force_complete_move(struct irq_desc *desc)
 		 *
 		 * But in case of cpu hotplug this should be a non issue
 		 * because if the affinity update happens right before all
-		 * cpus rendevouz in stop machine, there is no way that the
+		 * cpus rendezvous in stop machine, there is no way that the
 		 * interrupt can be blocked on the target cpu because all cpus
 		 * loops first with interrupts enabled in stop machine, so the
 		 * old vector is not yet cleaned up when the interrupt fires.
@@ -1004,7 +1087,7 @@ void irq_force_complete_move(struct irq_desc *desc)
 		 * of the interrupt on the apic/system bus would be delayed
 		 * beyond the point where the target cpu disables interrupts
 		 * in stop machine. I doubt that it can happen, but at least
-		 * there is a theroretical chance. Virtualization might be
+		 * there is a theoretical chance. Virtualization might be
 		 * able to expose this, but AFAICT the IOAPIC emulation is not
 		 * as stupid as the real hardware.
 		 *
@@ -1216,7 +1299,7 @@ static void __init print_PIC(void)
 
 	pr_debug("... PIC  ISR: %04x\n", v);
 
-	v = inb(0x4d1) << 8 | inb(0x4d0);
+	v = inb(PIC_ELCR2) << 8 | inb(PIC_ELCR1);
 	pr_debug("... PIC ELCR: %04x\n", v);
 }