1 files changed, 116 insertions, 56 deletions

diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index 400856abf672..0bb29316b436 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -547,7 +547,7 @@ int irq_set_affinity_notifier(unsigned int irq, struct irq_affinity_notify *noti
 		INIT_WORK(&notify->work, irq_affinity_notify);
 	}
 
-	scoped_guard(raw_spinlock_irqsave, &desc->lock) {
+	scoped_guard(raw_spinlock_irq, &desc->lock) {
 		old_notify = desc->affinity_notify;
 		desc->affinity_notify = notify;
 	}
@@ -1001,7 +1001,6 @@ static irqreturn_t irq_forced_secondary_handler(int irq, void *dev_id)
 static void irq_thread_check_affinity(struct irq_desc *desc, struct irqaction *action)
 {
 	cpumask_var_t mask;
-	bool valid = false;
 
 	if (!test_and_clear_bit(IRQTF_AFFINITY, &action->thread_flags))
 		return;
@@ -1018,21 +1017,13 @@ static void irq_thread_check_affinity(struct irq_desc *desc, struct irqaction *a
 	}
 
 	scoped_guard(raw_spinlock_irq, &desc->lock) {
-		/*
-		 * This code is triggered unconditionally. Check the affinity
-		 * mask pointer. For CPU_MASK_OFFSTACK=n this is optimized out.
-		 */
-		if (cpumask_available(desc->irq_common_data.affinity)) {
-			const struct cpumask *m;
+		const struct cpumask *m;
 
-			m = irq_data_get_effective_affinity_mask(&desc->irq_data);
-			cpumask_copy(mask, m);
-			valid = true;
-		}
+		m = irq_data_get_effective_affinity_mask(&desc->irq_data);
+		cpumask_copy(mask, m);
 	}
 
-	if (valid)
-		set_cpus_allowed_ptr(current, mask);
+	set_cpus_allowed_ptr(current, mask);
 	free_cpumask_var(mask);
 }
 #else
@@ -1239,7 +1230,10 @@ static int irq_thread(void *data)
 
 	irq_thread_set_ready(desc, action);
 
-	sched_set_fifo(current);
+	if (action->handler == irq_forced_secondary_handler)
+		sched_set_fifo_secondary(current);
+	else
+		sched_set_fifo(current);
 
 	if (force_irqthreads() && test_bit(IRQTF_FORCED_THREAD,
 					   &action->thread_flags))
@@ -1405,19 +1399,39 @@ setup_irq_thread(struct irqaction *new, unsigned int irq, bool secondary)
 	 * references an already freed task_struct.
 	 */
 	new->thread = get_task_struct(t);
+
 	/*
-	 * Tell the thread to set its affinity. This is
-	 * important for shared interrupt handlers as we do
-	 * not invoke setup_affinity() for the secondary
-	 * handlers as everything is already set up. Even for
-	 * interrupts marked with IRQF_NO_BALANCE this is
-	 * correct as we want the thread to move to the cpu(s)
-	 * on which the requesting code placed the interrupt.
+	 * The affinity can not be established yet, but it will be once the
+	 * interrupt is enabled. Delay and defer the actual setting to the
+	 * thread itself once it is ready to run. In the meantime, prevent
+	 * it from ever being re-affined directly by cpuset or
+	 * housekeeping. The proper way to do it is to re-affine the whole
+	 * vector.
 	 */
-	set_bit(IRQTF_AFFINITY, &new->thread_flags);
+	kthread_bind_mask(t, cpu_possible_mask);
+
+	/*
+	 * Ensure the thread adjusts the affinity once it reaches the
+	 * thread function.
+	 */
+	new->thread_flags = BIT(IRQTF_AFFINITY);
+
 	return 0;
 }
 
+static bool valid_percpu_irqaction(struct irqaction *old, struct irqaction *new)
+{
+	do {
+		if (cpumask_intersects(old->affinity, new->affinity) ||
+		    old->percpu_dev_id == new->percpu_dev_id)
+			return false;
+
+		old = old->next;
+	} while (old);
+
+	return true;
+}
+
 /*
  * Internal function to register an irqaction - typically used to
  * allocate special interrupts that are part of the architecture.
@@ -1438,6 +1452,7 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new)
 	struct irqaction *old, **old_ptr;
 	unsigned long flags, thread_mask = 0;
 	int ret, nested, shared = 0;
+	bool per_cpu_devid;
 
 	if (!desc)
 		return -EINVAL;
@@ -1447,6 +1462,8 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new)
 	if (!try_module_get(desc->owner))
 		return -ENODEV;
 
+	per_cpu_devid = irq_settings_is_per_cpu_devid(desc);
+
 	new->irq = irq;
 
 	/*
@@ -1554,13 +1571,20 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new)
 		 */
 		unsigned int oldtype;
 
-		if (irq_is_nmi(desc)) {
+		if (irq_is_nmi(desc) && !per_cpu_devid) {
 			pr_err("Invalid attempt to share NMI for %s (irq %d) on irqchip %s.\n",
 				new->name, irq, desc->irq_data.chip->name);
 			ret = -EINVAL;
 			goto out_unlock;
 		}
 
+		if (per_cpu_devid && !valid_percpu_irqaction(old, new)) {
+			pr_err("Overlapping affinities for %s (irq %d) on irqchip %s.\n",
+				new->name, irq, desc->irq_data.chip->name);
+			ret = -EINVAL;
+			goto out_unlock;
+		}
+
 		/*
 		 * If nobody did set the configuration before, inherit
 		 * the one provided by the requester.
@@ -1711,7 +1735,7 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new)
 		if (!(new->flags & IRQF_NO_AUTOEN) &&
 		    irq_settings_can_autoenable(desc)) {
 			irq_startup(desc, IRQ_RESEND, IRQ_START_COND);
-		} else {
+		} else if (!per_cpu_devid) {
 			/*
 			 * Shared interrupts do not go well with disabling
 			 * auto enable. The sharing interrupt might request
@@ -2346,7 +2370,7 @@ void disable_percpu_nmi(unsigned int irq)
 static struct irqaction *__free_percpu_irq(unsigned int irq, void __percpu *dev_id)
 {
 	struct irq_desc *desc = irq_to_desc(irq);
-	struct irqaction *action;
+	struct irqaction *action, **action_ptr;
 
 	WARN(in_interrupt(), "Trying to free IRQ %d from IRQ context!\n", irq);
 
@@ -2354,21 +2378,33 @@ static struct irqaction *__free_percpu_irq(unsigned int irq, void __percpu *dev_
 		return NULL;
 
 	scoped_guard(raw_spinlock_irqsave, &desc->lock) {
-		action = desc->action;
-		if (!action || action->percpu_dev_id != dev_id) {
-			WARN(1, "Trying to free already-free IRQ %d\n", irq);
-			return NULL;
+		action_ptr = &desc->action;
+		for (;;) {
+			action = *action_ptr;
+
+			if (!action) {
+				WARN(1, "Trying to free already-free IRQ %d\n", irq);
+				return NULL;
+			}
+
+			if (action->percpu_dev_id == dev_id)
+				break;
+
+			action_ptr = &action->next;
 		}
 
-		if (!cpumask_empty(desc->percpu_enabled)) {
-			WARN(1, "percpu IRQ %d still enabled on CPU%d!\n",
-			     irq, cpumask_first(desc->percpu_enabled));
+		if (cpumask_intersects(desc->percpu_enabled, action->affinity)) {
+			WARN(1, "percpu IRQ %d still enabled on CPU%d!\n", irq,
+			     cpumask_first_and(desc->percpu_enabled, action->affinity));
 			return NULL;
 		}
 
 		/* Found it - now remove it from the list of entries: */
-		desc->action = NULL;
-		desc->istate &= ~IRQS_NMI;
+		*action_ptr = action->next;
+
+		/* Demote from NMI if we killed the last action */
+		if (!desc->action)
+			desc->istate &= ~IRQS_NMI;
 	}
 
 	unregister_handler_proc(irq, action);
@@ -2442,17 +2478,49 @@ int setup_percpu_irq(unsigned int irq, struct irqaction *act)
 	return retval;
 }
 
+static
+struct irqaction *create_percpu_irqaction(irq_handler_t handler, unsigned long flags,
+					  const char *devname, const cpumask_t *affinity,
+					  void __percpu *dev_id)
+{
+	struct irqaction *action;
+
+	if (!affinity)
+		affinity = cpu_possible_mask;
+
+	action = kzalloc(sizeof(struct irqaction), GFP_KERNEL);
+	if (!action)
+		return NULL;
+
+	action->handler = handler;
+	action->flags = flags | IRQF_PERCPU | IRQF_NO_SUSPEND;
+	action->name = devname;
+	action->percpu_dev_id = dev_id;
+	action->affinity = affinity;
+
+	/*
+	 * We allow some form of sharing for non-overlapping affinity
+	 * masks. Obviously, covering all CPUs prevents any sharing in
+	 * the first place.
+	 */
+	if (!cpumask_equal(affinity, cpu_possible_mask))
+		action->flags |= IRQF_SHARED;
+
+	return action;
+}
+
 /**
  * __request_percpu_irq - allocate a percpu interrupt line
  * @irq:	Interrupt line to allocate
  * @handler:	Function to be called when the IRQ occurs.
  * @flags:	Interrupt type flags (IRQF_TIMER only)
  * @devname:	An ascii name for the claiming device
+ * @affinity:	A cpumask describing the target CPUs for this interrupt
  * @dev_id:	A percpu cookie passed back to the handler function
  *
- * This call allocates interrupt resources and enables the interrupt on the
- * local CPU. If the interrupt is supposed to be enabled on other CPUs, it
- * has to be done on each CPU using enable_percpu_irq().
+ * This call allocates interrupt resources, but doesn't enable the interrupt
+ * on any CPU, as all percpu-devid interrupts are flagged with IRQ_NOAUTOEN.
+ * It has to be done on each CPU using enable_percpu_irq().
  *
  * @dev_id must be globally unique. It is a per-cpu variable, and
  * the handler gets called with the interrupted CPU's instance of
@@ -2460,7 +2528,7 @@ int setup_percpu_irq(unsigned int irq, struct irqaction *act)
  */
 int __request_percpu_irq(unsigned int irq, irq_handler_t handler,
 			 unsigned long flags, const char *devname,
-			 void __percpu *dev_id)
+			 const cpumask_t *affinity, void __percpu *dev_id)
 {
 	struct irqaction *action;
 	struct irq_desc *desc;
@@ -2477,15 +2545,10 @@ int __request_percpu_irq(unsigned int irq, irq_handler_t handler,
 	if (flags && flags != IRQF_TIMER)
 		return -EINVAL;
 
-	action = kzalloc(sizeof(struct irqaction), GFP_KERNEL);
+	action = create_percpu_irqaction(handler, flags, devname, affinity, dev_id);
 	if (!action)
 		return -ENOMEM;
 
-	action->handler = handler;
-	action->flags = flags | IRQF_PERCPU | IRQF_NO_SUSPEND;
-	action->name = devname;
-	action->percpu_dev_id = dev_id;
-
 	retval = irq_chip_pm_get(&desc->irq_data);
 	if (retval < 0) {
 		kfree(action);
@@ -2508,6 +2571,7 @@ EXPORT_SYMBOL_GPL(__request_percpu_irq);
  * @irq:	Interrupt line to allocate
  * @handler:	Function to be called when the IRQ occurs.
  * @name:	An ascii name for the claiming device
+ * @affinity:	A cpumask describing the target CPUs for this interrupt
  * @dev_id:	A percpu cookie passed back to the handler function
  *
  * This call allocates interrupt resources for a per CPU NMI. Per CPU NMIs
@@ -2524,8 +2588,8 @@ EXPORT_SYMBOL_GPL(__request_percpu_irq);
  * If the interrupt line cannot be used to deliver NMIs, function
  * will fail returning a negative value.
  */
-int request_percpu_nmi(unsigned int irq, irq_handler_t handler,
-		       const char *name, void __percpu *dev_id)
+int request_percpu_nmi(unsigned int irq, irq_handler_t handler, const char *name,
+		       const struct cpumask *affinity, void __percpu *dev_id)
 {
 	struct irqaction *action;
 	struct irq_desc *desc;
@@ -2542,20 +2606,16 @@ int request_percpu_nmi(unsigned int irq, irq_handler_t handler,
 	    !irq_supports_nmi(desc))
 		return -EINVAL;
 
-	/* The line cannot already be NMI */
-	if (irq_is_nmi(desc))
+	/* The line cannot be NMI already if the new request covers all CPUs */
+	if (irq_is_nmi(desc) &&
+	    (!affinity || cpumask_equal(affinity, cpu_possible_mask)))
 		return -EINVAL;
 
-	action = kzalloc(sizeof(struct irqaction), GFP_KERNEL);
+	action = create_percpu_irqaction(handler, IRQF_NO_THREAD | IRQF_NOBALANCING,
+					 name, affinity, dev_id);
 	if (!action)
 		return -ENOMEM;
 
-	action->handler = handler;
-	action->flags = IRQF_PERCPU | IRQF_NO_SUSPEND | IRQF_NO_THREAD
-		| IRQF_NOBALANCING;
-	action->name = name;
-	action->percpu_dev_id = dev_id;
-
 	retval = irq_chip_pm_get(&desc->irq_data);
 	if (retval < 0)
 		goto err_out;