Merge tag 'irq-core-2020-12-15' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull irq updates from Thomas Gleixner:
 "Generic interrupt and irqchips subsystem updates. Unusually, there is
  not a single completely new irq chip driver, just new DT bindings and
  extensions of existing drivers to accomodate new variants!

  Core:

   - Consolidation and robustness changes for irq time accounting

   - Cleanup and consolidation of irq stats

   - Remove the fasteoi IPI flow which has been proved useless

   - Provide an interface for converting legacy interrupt mechanism into
     irqdomains

  Drivers:

   - Preliminary support for managed interrupts on platform devices

   - Correctly identify allocation of MSIs proxyied by another device

   - Generalise the Ocelot support to new SoCs

   - Improve GICv4.1 vcpu entry, matching the corresponding KVM
     optimisation

   - Work around spurious interrupts on Qualcomm PDC

   - Random fixes and cleanups"

* tag 'irq-core-2020-12-15' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (54 commits)
  irqchip/qcom-pdc: Fix phantom irq when changing between rising/falling
  driver core: platform: Add devm_platform_get_irqs_affinity()
  ACPI: Drop acpi_dev_irqresource_disabled()
  resource: Add irqresource_disabled()
  genirq/affinity: Add irq_update_affinity_desc()
  irqchip/gic-v3-its: Flag device allocation as proxied if behind a PCI bridge
  irqchip/gic-v3-its: Tag ITS device as shared if allocating for a proxy device
  platform-msi: Track shared domain allocation
  irqchip/ti-sci-intr: Fix freeing of irqs
  irqchip/ti-sci-inta: Fix printing of inta id on probe success
  drivers/irqchip: Remove EZChip NPS interrupt controller
  Revert "genirq: Add fasteoi IPI flow"
  irqchip/hip04: Make IPIs use handle_percpu_devid_irq()
  irqchip/bcm2836: Make IPIs use handle_percpu_devid_irq()
  irqchip/armada-370-xp: Make IPIs use handle_percpu_devid_irq()
  irqchip/gic, gic-v3: Make SGIs use handle_percpu_devid_irq()
  irqchip/ocelot: Add support for Jaguar2 platforms
  irqchip/ocelot: Add support for Serval platforms
  irqchip/ocelot: Add support for Luton platforms
  irqchip/ocelot: prepare to support more SoC
  ...

kernel/irq/Kconfig

@@ -26,11 +26,6 @@ config GENERIC_IRQ_SHOW_LEVEL
 config GENERIC_IRQ_EFFECTIVE_AFF_MASK
        bool
 
-# Facility to allocate a hardware interrupt. This is legacy support
-# and should not be used in new code. Use irq domains instead.
-config GENERIC_IRQ_LEGACY_ALLOC_HWIRQ
-       bool
-
 # Support for delayed migration from interrupt context
 config GENERIC_PENDING_IRQ
 	bool

kernel/irq/chip.c

@@ -61,7 +61,7 @@ int irq_set_chip(unsigned int irq, struct irq_chip *chip)
 EXPORT_SYMBOL(irq_set_chip);
 
 /**
- *	irq_set_type - set the irq trigger type for an irq
+ *	irq_set_irq_type - set the irq trigger type for an irq
  *	@irq:	irq number
  *	@type:	IRQ_TYPE_{LEVEL,EDGE}_* value - see include/linux/irq.h
  */
@@ -944,33 +944,6 @@ void handle_percpu_devid_irq(struct irq_desc *desc)
 		chip->irq_eoi(&desc->irq_data);
 }
 
-/**
- * handle_percpu_devid_fasteoi_ipi - Per CPU local IPI handler with per cpu
- *				     dev ids
- * @desc:	the interrupt description structure for this irq
- *
- * The biggest difference with the IRQ version is that the interrupt is
- * EOIed early, as the IPI could result in a context switch, and we need to
- * make sure the IPI can fire again. We also assume that the arch code has
- * registered an action. If not, we are positively doomed.
- */
-void handle_percpu_devid_fasteoi_ipi(struct irq_desc *desc)
-{
-	struct irq_chip *chip = irq_desc_get_chip(desc);
-	struct irqaction *action = desc->action;
-	unsigned int irq = irq_desc_get_irq(desc);
-	irqreturn_t res;
-
-	__kstat_incr_irqs_this_cpu(desc);
-
-	if (chip->irq_eoi)
-		chip->irq_eoi(&desc->irq_data);
-
-	trace_irq_handler_entry(irq, action);
-	res = action->handler(irq, raw_cpu_ptr(action->percpu_dev_id));
-	trace_irq_handler_exit(irq, action, res);
-}
-
 /**
  * handle_percpu_devid_fasteoi_nmi - Per CPU local NMI handler with per cpu
  *				     dev ids

kernel/irq/generic-chip.c

@@ -269,7 +269,7 @@ irq_gc_init_mask_cache(struct irq_chip_generic *gc, enum irq_gc_flags flags)
 }
 
 /**
- * __irq_alloc_domain_generic_chip - Allocate generic chips for an irq domain
+ * __irq_alloc_domain_generic_chips - Allocate generic chips for an irq domain
  * @d:			irq domain for which to allocate chips
  * @irqs_per_chip:	Number of interrupts each chip handles (max 32)
  * @num_ct:		Number of irq_chip_type instances associated with this

kernel/irq/irqdesc.c

@@ -810,57 +810,6 @@ unlock:
 }
 EXPORT_SYMBOL_GPL(__irq_alloc_descs);
 
-#ifdef CONFIG_GENERIC_IRQ_LEGACY_ALLOC_HWIRQ
-/**
- * irq_alloc_hwirqs - Allocate an irq descriptor and initialize the hardware
- * @cnt:	number of interrupts to allocate
- * @node:	node on which to allocate
- *
- * Returns an interrupt number > 0 or 0, if the allocation fails.
- */
-unsigned int irq_alloc_hwirqs(int cnt, int node)
-{
-	int i, irq = __irq_alloc_descs(-1, 0, cnt, node, NULL, NULL);
-
-	if (irq < 0)
-		return 0;
-
-	for (i = irq; cnt > 0; i++, cnt--) {
-		if (arch_setup_hwirq(i, node))
-			goto err;
-		irq_clear_status_flags(i, _IRQ_NOREQUEST);
-	}
-	return irq;
-
-err:
-	for (i--; i >= irq; i--) {
-		irq_set_status_flags(i, _IRQ_NOREQUEST | _IRQ_NOPROBE);
-		arch_teardown_hwirq(i);
-	}
-	irq_free_descs(irq, cnt);
-	return 0;
-}
-EXPORT_SYMBOL_GPL(irq_alloc_hwirqs);
-
-/**
- * irq_free_hwirqs - Free irq descriptor and cleanup the hardware
- * @from:	Free from irq number
- * @cnt:	number of interrupts to free
- *
- */
-void irq_free_hwirqs(unsigned int from, int cnt)
-{
-	int i, j;
-
-	for (i = from, j = cnt; j > 0; i++, j--) {
-		irq_set_status_flags(i, _IRQ_NOREQUEST | _IRQ_NOPROBE);
-		arch_teardown_hwirq(i);
-	}
-	irq_free_descs(from, cnt);
-}
-EXPORT_SYMBOL_GPL(irq_free_hwirqs);
-#endif
-
 /**
  * irq_get_next_irq - get next allocated irq number
  * @offset:	where to start the search

kernel/irq/irqdomain.c

@@ -359,17 +359,28 @@ struct irq_domain *irq_domain_add_legacy(struct device_node *of_node,
 					 irq_hw_number_t first_hwirq,
 					 const struct irq_domain_ops *ops,
 					 void *host_data)
+{
+	return irq_domain_create_legacy(of_node_to_fwnode(of_node), size,
+					first_irq, first_hwirq, ops, host_data);
+}
+EXPORT_SYMBOL_GPL(irq_domain_add_legacy);
+
+struct irq_domain *irq_domain_create_legacy(struct fwnode_handle *fwnode,
+					 unsigned int size,
+					 unsigned int first_irq,
+					 irq_hw_number_t first_hwirq,
+					 const struct irq_domain_ops *ops,
+					 void *host_data)
 {
 	struct irq_domain *domain;
 
-	domain = __irq_domain_add(of_node_to_fwnode(of_node), first_hwirq + size,
-				  first_hwirq + size, 0, ops, host_data);
+	domain = __irq_domain_add(fwnode, first_hwirq + size, first_hwirq + size, 0, ops, host_data);
 	if (domain)
 		irq_domain_associate_many(domain, first_irq, first_hwirq, size);
 
 	return domain;
 }
-EXPORT_SYMBOL_GPL(irq_domain_add_legacy);
+EXPORT_SYMBOL_GPL(irq_domain_create_legacy);
 
 /**
  * irq_find_matching_fwspec() - Locates a domain for a given fwspec
@@ -494,7 +505,7 @@ static void irq_domain_set_mapping(struct irq_domain *domain,
 	}
 }
 
-void irq_domain_disassociate(struct irq_domain *domain, unsigned int irq)
+static void irq_domain_disassociate(struct irq_domain *domain, unsigned int irq)
 {
 	struct irq_data *irq_data = irq_get_irq_data(irq);
 	irq_hw_number_t hwirq;
@@ -749,7 +760,7 @@ static void of_phandle_args_to_fwspec(struct device_node *np, const u32 *args,
 {
 	int i;
 
-	fwspec->fwnode = np ? &np->fwnode : NULL;
+	fwspec->fwnode = of_node_to_fwnode(np);
 	fwspec->param_count = count;
 
 	for (i = 0; i < count; i++)
@@ -1382,8 +1393,15 @@ static void irq_domain_free_irqs_hierarchy(struct irq_domain *domain,
 					   unsigned int irq_base,
 					   unsigned int nr_irqs)
 {
-	if (domain->ops->free)
-		domain->ops->free(domain, irq_base, nr_irqs);
+	unsigned int i;
+
+	if (!domain->ops->free)
+		return;
+
+	for (i = 0; i < nr_irqs; i++) {
+		if (irq_domain_get_irq_data(domain, irq_base + i))
+			domain->ops->free(domain, irq_base + i, 1);
+	}
 }
 
 int irq_domain_alloc_irqs_hierarchy(struct irq_domain *domain,

kernel/irq/manage.c

@@ -371,6 +371,76 @@ int irq_set_affinity_locked(struct irq_data *data, const struct cpumask *mask,
 	return ret;
 }
 
+/**
+ * irq_update_affinity_desc - Update affinity management for an interrupt
+ * @irq:	The interrupt number to update
+ * @affinity:	Pointer to the affinity descriptor
+ *
+ * This interface can be used to configure the affinity management of
+ * interrupts which have been allocated already.
+ *
+ * There are certain limitations on when it may be used - attempts to use it
+ * for when the kernel is configured for generic IRQ reservation mode (in
+ * config GENERIC_IRQ_RESERVATION_MODE) will fail, as it may conflict with
+ * managed/non-managed interrupt accounting. In addition, attempts to use it on
+ * an interrupt which is already started or which has already been configured
+ * as managed will also fail, as these mean invalid init state or double init.
+ */
+int irq_update_affinity_desc(unsigned int irq,
+			     struct irq_affinity_desc *affinity)
+{
+	struct irq_desc *desc;
+	unsigned long flags;
+	bool activated;
+	int ret = 0;
+
+	/*
+	 * Supporting this with the reservation scheme used by x86 needs
+	 * some more thought. Fail it for now.
+	 */
+	if (IS_ENABLED(CONFIG_GENERIC_IRQ_RESERVATION_MODE))
+		return -EOPNOTSUPP;
+
+	desc = irq_get_desc_buslock(irq, &flags, 0);
+	if (!desc)
+		return -EINVAL;
+
+	/* Requires the interrupt to be shut down */
+	if (irqd_is_started(&desc->irq_data)) {
+		ret = -EBUSY;
+		goto out_unlock;
+	}
+
+	/* Interrupts which are already managed cannot be modified */
+	if (irqd_affinity_is_managed(&desc->irq_data)) {
+		ret = -EBUSY;
+		goto out_unlock;
+	}
+
+	/*
+	 * Deactivate the interrupt. That's required to undo
+	 * anything an earlier activation has established.
+	 */
+	activated = irqd_is_activated(&desc->irq_data);
+	if (activated)
+		irq_domain_deactivate_irq(&desc->irq_data);
+
+	if (affinity->is_managed) {
+		irqd_set(&desc->irq_data, IRQD_AFFINITY_MANAGED);
+		irqd_set(&desc->irq_data, IRQD_MANAGED_SHUTDOWN);
+	}
+
+	cpumask_copy(desc->irq_common_data.affinity, &affinity->mask);
+
+	/* Restore the activation state */
+	if (activated)
+		irq_domain_activate_irq(&desc->irq_data, false);
+
+out_unlock:
+	irq_put_desc_busunlock(desc, flags);
+	return ret;
+}
+
 int __irq_set_affinity(unsigned int irq, const struct cpumask *mask, bool force)
 {
 	struct irq_desc *desc = irq_to_desc(irq);

kernel/sched/cputime.c

@@ -44,12 +44,13 @@ static void irqtime_account_delta(struct irqtime *irqtime, u64 delta,
 }
 
 /*
- * Called before incrementing preempt_count on {soft,}irq_enter
+ * Called after incrementing preempt_count on {soft,}irq_enter
  * and before decrementing preempt_count on {soft,}irq_exit.
  */
-void irqtime_account_irq(struct task_struct *curr)
+void irqtime_account_irq(struct task_struct *curr, unsigned int offset)
 {
 	struct irqtime *irqtime = this_cpu_ptr(&cpu_irqtime);
+	unsigned int pc;
 	s64 delta;
 	int cpu;
 
@@ -59,6 +60,7 @@ void irqtime_account_irq(struct task_struct *curr)
 	cpu = smp_processor_id();
 	delta = sched_clock_cpu(cpu) - irqtime->irq_start_time;
 	irqtime->irq_start_time += delta;
+	pc = preempt_count() - offset;
 
 	/*
 	 * We do not account for softirq time from ksoftirqd here.
@@ -66,12 +68,11 @@ void irqtime_account_irq(struct task_struct *curr)
 	 * in that case, so as not to confuse scheduler with a special task
 	 * that do not consume any time, but still wants to run.
 	 */
-	if (hardirq_count())
+	if (pc & HARDIRQ_MASK)
 		irqtime_account_delta(irqtime, delta, CPUTIME_IRQ);
-	else if (in_serving_softirq() && curr != this_cpu_ksoftirqd())
+	else if ((pc & SOFTIRQ_OFFSET) && curr != this_cpu_ksoftirqd())
 		irqtime_account_delta(irqtime, delta, CPUTIME_SOFTIRQ);
 }
-EXPORT_SYMBOL_GPL(irqtime_account_irq);
 
 static u64 irqtime_tick_accounted(u64 maxtime)
 {
@@ -418,24 +419,21 @@ void vtime_task_switch(struct task_struct *prev)
 }
 # endif
 
-/*
- * Archs that account the whole time spent in the idle task
- * (outside irq) as idle time can rely on this and just implement
- * vtime_account_kernel() and vtime_account_idle(). Archs that
- * have other meaning of the idle time (s390 only includes the
- * time spent by the CPU when it's in low power mode) must override
- * vtime_account().
- */
-#ifndef __ARCH_HAS_VTIME_ACCOUNT
-void vtime_account_irq_enter(struct task_struct *tsk)
+void vtime_account_irq(struct task_struct *tsk, unsigned int offset)
 {
-	if (!in_interrupt() && is_idle_task(tsk))
+	unsigned int pc = preempt_count() - offset;
+
+	if (pc & HARDIRQ_OFFSET) {
+		vtime_account_hardirq(tsk);
+	} else if (pc & SOFTIRQ_OFFSET) {
+		vtime_account_softirq(tsk);
+	} else if (!IS_ENABLED(CONFIG_HAVE_VIRT_CPU_ACCOUNTING_IDLE) &&
+		   is_idle_task(tsk)) {
 		vtime_account_idle(tsk);
-	else
+	} else {
 		vtime_account_kernel(tsk);
+	}
 }
-EXPORT_SYMBOL_GPL(vtime_account_irq_enter);
-#endif /* __ARCH_HAS_VTIME_ACCOUNT */
 
 void cputime_adjust(struct task_cputime *curr, struct prev_cputime *prev,
 		    u64 *ut, u64 *st)

kernel/softirq.c

@@ -92,6 +92,13 @@ static bool ksoftirqd_running(unsigned long pending)
 		!__kthread_should_park(tsk);
 }
 
+#ifdef CONFIG_TRACE_IRQFLAGS
+DEFINE_PER_CPU(int, hardirqs_enabled);
+DEFINE_PER_CPU(int, hardirq_context);
+EXPORT_PER_CPU_SYMBOL_GPL(hardirqs_enabled);
+EXPORT_PER_CPU_SYMBOL_GPL(hardirq_context);
+#endif
+
 /*
  * preempt_count and SOFTIRQ_OFFSET usage:
  * - preempt_count is changed by SOFTIRQ_OFFSET on entering or leaving
@@ -102,17 +109,11 @@ static bool ksoftirqd_running(unsigned long pending)
  * softirq and whether we just have bh disabled.
  */
 
-/*
- * This one is for softirq.c-internal use,
- * where hardirqs are disabled legitimately:
- */
 #ifdef CONFIG_TRACE_IRQFLAGS
-
-DEFINE_PER_CPU(int, hardirqs_enabled);
-DEFINE_PER_CPU(int, hardirq_context);
-EXPORT_PER_CPU_SYMBOL_GPL(hardirqs_enabled);
-EXPORT_PER_CPU_SYMBOL_GPL(hardirq_context);
-
+/*
+ * This is for softirq.c-internal use, where hardirqs are disabled
+ * legitimately:
+ */
 void __local_bh_disable_ip(unsigned long ip, unsigned int cnt)
 {
 	unsigned long flags;
@@ -203,6 +204,50 @@ void __local_bh_enable_ip(unsigned long ip, unsigned int cnt)
 }
 EXPORT_SYMBOL(__local_bh_enable_ip);
 
+static inline void invoke_softirq(void)
+{
+	if (ksoftirqd_running(local_softirq_pending()))
+		return;
+
+	if (!force_irqthreads) {
+#ifdef CONFIG_HAVE_IRQ_EXIT_ON_IRQ_STACK
+		/*
+		 * We can safely execute softirq on the current stack if
+		 * it is the irq stack, because it should be near empty
+		 * at this stage.
+		 */
+		__do_softirq();
+#else
+		/*
+		 * Otherwise, irq_exit() is called on the task stack that can
+		 * be potentially deep already. So call softirq in its own stack
+		 * to prevent from any overrun.
+		 */
+		do_softirq_own_stack();
+#endif
+	} else {
+		wakeup_softirqd();
+	}
+}
+
+asmlinkage __visible void do_softirq(void)
+{
+	__u32 pending;
+	unsigned long flags;
+
+	if (in_interrupt())
+		return;
+
+	local_irq_save(flags);
+
+	pending = local_softirq_pending();
+
+	if (pending && !ksoftirqd_running(pending))
+		do_softirq_own_stack();
+
+	local_irq_restore(flags);
+}
+
 /*
  * We restart softirq processing for at most MAX_SOFTIRQ_RESTART times,
  * but break the loop if need_resched() is set or after 2 ms.
@@ -270,10 +315,10 @@ asmlinkage __visible void __softirq_entry __do_softirq(void)
 	current->flags &= ~PF_MEMALLOC;
 
 	pending = local_softirq_pending();
-	account_irq_enter_time(current);
 
 	__local_bh_disable_ip(_RET_IP_, SOFTIRQ_OFFSET);
 	in_hardirq = lockdep_softirq_start();
+	account_softirq_enter(current);
 
 restart:
 	/* Reset the pending bitmask before enabling irqs */
@@ -320,46 +365,24 @@ restart:
 		wakeup_softirqd();
 	}
 
+	account_softirq_exit(current);
 	lockdep_softirq_end(in_hardirq);
-	account_irq_exit_time(current);
 	__local_bh_enable(SOFTIRQ_OFFSET);
 	WARN_ON_ONCE(in_interrupt());
 	current_restore_flags(old_flags, PF_MEMALLOC);
 }
 
-asmlinkage __visible void do_softirq(void)
-{
-	__u32 pending;
-	unsigned long flags;
-
-	if (in_interrupt())
-		return;
-
-	local_irq_save(flags);
-
-	pending = local_softirq_pending();
-
-	if (pending && !ksoftirqd_running(pending))
-		do_softirq_own_stack();
-
-	local_irq_restore(flags);
-}
-
 /**
  * irq_enter_rcu - Enter an interrupt context with RCU watching
  */
 void irq_enter_rcu(void)
 {
-	if (is_idle_task(current) && !in_interrupt()) {
-		/*
-		 * Prevent raise_softirq from needlessly waking up ksoftirqd
-		 * here, as softirq will be serviced on return from interrupt.
-		 */
-		local_bh_disable();
+	__irq_enter_raw();
+
+	if (is_idle_task(current) && (irq_count() == HARDIRQ_OFFSET))
 		tick_irq_enter();
-		_local_bh_enable();
-	}
-	__irq_enter();
+
+	account_hardirq_enter(current);
 }
 
 /**
@@ -371,32 +394,6 @@ void irq_enter(void)
 	irq_enter_rcu();
 }
 
-static inline void invoke_softirq(void)
-{
-	if (ksoftirqd_running(local_softirq_pending()))
-		return;
-
-	if (!force_irqthreads) {
-#ifdef CONFIG_HAVE_IRQ_EXIT_ON_IRQ_STACK
-		/*
-		 * We can safely execute softirq on the current stack if
-		 * it is the irq stack, because it should be near empty
-		 * at this stage.
-		 */
-		__do_softirq();
-#else
-		/*
-		 * Otherwise, irq_exit() is called on the task stack that can
-		 * be potentially deep already. So call softirq in its own stack
-		 * to prevent from any overrun.
-		 */
-		do_softirq_own_stack();
-#endif
-	} else {
-		wakeup_softirqd();
-	}
-}
-
 static inline void tick_irq_exit(void)
 {
 #ifdef CONFIG_NO_HZ_COMMON
@@ -417,7 +414,7 @@ static inline void __irq_exit_rcu(void)
 #else
 	lockdep_assert_irqs_disabled();
 #endif
-	account_irq_exit_time(current);
+	account_hardirq_exit(current);
 	preempt_count_sub(HARDIRQ_OFFSET);
 	if (!in_interrupt() && local_softirq_pending())
 		invoke_softirq();