Merge tag 'irq-core-2025-01-21' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull interrupt subsystem updates from Thomas Gleixner:

- Consolidate the machine_kexec_mask_interrupts() by providing a
generic implementation and replacing the copy & pasta orgy in the
relevant architectures.

- Prevent unconditional operations on interrupt chips during kexec
shutdown, which can trigger warnings in certain cases when the
underlying interrupt has been shut down before.

- Make the enforcement of interrupt handling in interrupt context
unconditionally available, so that it actually works for non x86
related interrupt chips. The earlier enablement for ARM GIC chips set
the required chip flag, but did not notice that the check was hidden
behind a config switch which is not selected by ARM[64].

- Decrapify the handling of deferred interrupt affinity setting.

Some interrupt chips require that affinity changes are made from the
context of handling an interrupt to avoid certain race conditions.
For x86 this was the default, but with interrupt remapping this
requirement was lifted and a flag was introduced which tells the core
code that affinity changes can be done in any context. Unrestricted
affinity changes are the default for the majority of interrupt chips.

RISCV has the requirement to add the deferred mode to one of it's
interrupt controllers, but with the original implementation this
would require to add the any context flag to all other RISC-V
interrupt chips. That's backwards, so reverse the logic and require
that chips, which need the deferred mode have to be marked
accordingly. That avoids chasing the 'sane' chips and marking them.

- Add multi-node support to the Loongarch AVEC interrupt controller
driver.

- The usual tiny cleanups, fixes and improvements all over the place.

* tag 'irq-core-2025-01-21' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
genirq/generic_chip: Export irq_gc_mask_disable_and_ack_set()
genirq/timings: Add kernel-doc for a function parameter
genirq: Remove IRQ_MOVE_PCNTXT and related code
x86/apic: Convert to IRQCHIP_MOVE_DEFERRED
genirq: Provide IRQCHIP_MOVE_DEFERRED
hexagon: Remove GENERIC_PENDING_IRQ leftover
ARC: Remove GENERIC_PENDING_IRQ
genirq: Remove handle_enforce_irqctx() wrapper
genirq: Make handle_enforce_irqctx() unconditionally available
irqchip/loongarch-avec: Add multi-nodes topology support
irqchip/ts4800: Replace seq_printf() by seq_puts()
irqchip/ti-sci-inta : Add module build support
irqchip/ti-sci-intr: Add module build support
irqchip/irq-brcmstb-l2: Replace brcmstb_l2_mask_and_ack() by generic function
irqchip: keystone: Use syscon_regmap_lookup_by_phandle_args
genirq/kexec: Prevent redundant IRQ masking by checking state before shutdown
kexec: Consolidate machine_kexec_mask_interrupts() implementation
genirq: Reuse irq_thread_fn() for forced thread case
genirq: Move irq_thread_fn() further up in the code

arch/arc/Kconfig

···
 	# for now, we don't need GENERIC_IRQ_PROBE, CONFIG_GENERIC_IRQ_CHIP
 	select GENERIC_IRQ_SHOW
 	select GENERIC_PCI_IOMAP
-	select GENERIC_PENDING_IRQ if SMP
 	select GENERIC_SCHED_CLOCK
 	select GENERIC_SMP_IDLE_THREAD
 	select GENERIC_IOREMAP

arch/arc/kernel/mcip.c

···
 static int idu_irq_map(struct irq_domain *d, unsigned int virq, irq_hw_number_t hwirq)
 {
 	irq_set_chip_and_handler(virq, &idu_irq_chip, handle_level_irq);
-	irq_set_status_flags(virq, IRQ_MOVE_PCNTXT);
-
 	return 0;
 }
 

arch/arm/kernel/machine_kexec.c

···
 	cpus_stopped = 1;
 }
 
-static void machine_kexec_mask_interrupts(void)
-{
-	unsigned int i;
-	struct irq_desc *desc;
-
-	for_each_irq_desc(i, desc) {
-		struct irq_chip *chip;
-
-		chip = irq_desc_get_chip(desc);
-		if (!chip)
-			continue;
-
-		if (chip->irq_eoi && irqd_irq_inprogress(&desc->irq_data))
-			chip->irq_eoi(&desc->irq_data);
-
-		if (chip->irq_mask)
-			chip->irq_mask(&desc->irq_data);
-
-		if (chip->irq_disable && !irqd_irq_disabled(&desc->irq_data))
-			chip->irq_disable(&desc->irq_data);
-	}
-}
-
 void machine_crash_shutdown(struct pt_regs *regs)
 {
 	local_irq_disable();

arch/arm64/Kconfig

···
 	select GENERIC_IDLE_POLL_SETUP
 	select GENERIC_IOREMAP
 	select GENERIC_IRQ_IPI
+	select GENERIC_IRQ_KEXEC_CLEAR_VM_FORWARD
 	select GENERIC_IRQ_PROBE
 	select GENERIC_IRQ_SHOW
 	select GENERIC_IRQ_SHOW_LEVEL

arch/arm64/Kconfig.platforms

···
 	select SOC_TI
 	select TI_MESSAGE_MANAGER
 	select TI_SCI_PROTOCOL
-	select TI_SCI_INTR_IRQCHIP
-	select TI_SCI_INTA_IRQCHIP
 	select TI_K3_SOCINFO
 	help
 	  This enables support for Texas Instruments' K3 multicore SoC

arch/arm64/kernel/machine_kexec.c

···
 	BUG(); /* Should never get here. */
 }
 
-static void machine_kexec_mask_interrupts(void)
-{
-	unsigned int i;
-	struct irq_desc *desc;
-
-	for_each_irq_desc(i, desc) {
-		struct irq_chip *chip;
-		int ret;
-
-		chip = irq_desc_get_chip(desc);
-		if (!chip)
-			continue;
-
-		/*
-		 * First try to remove the active state. If this
-		 * fails, try to EOI the interrupt.
-		 */
-		ret = irq_set_irqchip_state(i, IRQCHIP_STATE_ACTIVE, false);
-
-		if (ret && irqd_irq_inprogress(&desc->irq_data) &&
-		    chip->irq_eoi)
-			chip->irq_eoi(&desc->irq_data);
-
-		if (chip->irq_mask)
-			chip->irq_mask(&desc->irq_data);
-
-		if (chip->irq_disable && !irqd_irq_disabled(&desc->irq_data))
-			chip->irq_disable(&desc->irq_data);
-	}
-}
-
 /**
  * machine_crash_shutdown - shutdown non-crashing cpus and save registers
  */

arch/hexagon/Kconfig

···
 	# select ARCH_HAS_CPU_IDLE_WAIT
 	# select GPIOLIB
 	# select HAVE_CLK
-	# select GENERIC_PENDING_IRQ if SMP
 	select GENERIC_ATOMIC64
 	select HAVE_PERF_EVENTS
 	# GENERIC_ALLOCATOR is used by dma_alloc_coherent()

arch/powerpc/include/asm/kexec.h

···
 extern void kexec_smp_wait(void);	/* get and clear naca physid, wait for
 					  master to copy new code to 0 */
 extern void default_machine_kexec(struct kimage *image);
-extern void machine_kexec_mask_interrupts(void);
 
 void relocate_new_kernel(unsigned long indirection_page, unsigned long reboot_code_buffer,
 			 unsigned long start_address) __noreturn;

arch/powerpc/kexec/core.c

···
 #include <asm/setup.h>
 #include <asm/firmware.h>
 
-void machine_kexec_mask_interrupts(void) {
-	unsigned int i;
-	struct irq_desc *desc;
-
-	for_each_irq_desc(i, desc) {
-		struct irq_chip *chip;
-
-		chip = irq_desc_get_chip(desc);
-		if (!chip)
-			continue;
-
-		if (chip->irq_eoi && irqd_irq_inprogress(&desc->irq_data))
-			chip->irq_eoi(&desc->irq_data);
-
-		if (chip->irq_mask)
-			chip->irq_mask(&desc->irq_data);
-
-		if (chip->irq_disable && !irqd_irq_disabled(&desc->irq_data))
-			chip->irq_disable(&desc->irq_data);
-	}
-}
-
 #ifdef CONFIG_CRASH_DUMP
 void machine_crash_shutdown(struct pt_regs *regs)
 {

arch/powerpc/kexec/core_32.c

···
  * Copyright (C) 2005 IBM Corporation.
  */
 
+#include <linux/irq.h>
 #include <linux/kexec.h>
 #include <linux/mm.h>
 #include <linux/string.h>

arch/riscv/kernel/machine_kexec.c

···
 #endif
 }
 
-static void machine_kexec_mask_interrupts(void)
-{
-	unsigned int i;
-	struct irq_desc *desc;
-
-	for_each_irq_desc(i, desc) {
-		struct irq_chip *chip;
-
-		chip = irq_desc_get_chip(desc);
-		if (!chip)
-			continue;
-
-		if (chip->irq_eoi && irqd_irq_inprogress(&desc->irq_data))
-			chip->irq_eoi(&desc->irq_data);
-
-		if (chip->irq_mask)
-			chip->irq_mask(&desc->irq_data);
-
-		if (chip->irq_disable && !irqd_irq_disabled(&desc->irq_data))
-			chip->irq_disable(&desc->irq_data);
-	}
-}
-
 /*
  * machine_crash_shutdown - Prepare to kexec after a kernel crash
  *

arch/x86/hyperv/irqdomain.c

···
 	.irq_retrigger		= irq_chip_retrigger_hierarchy,
 	.irq_compose_msi_msg	= hv_irq_compose_msi_msg,
 	.irq_set_affinity	= msi_domain_set_affinity,
-	.flags			= IRQCHIP_SKIP_SET_WAKE,
+	.flags			= IRQCHIP_SKIP_SET_WAKE | IRQCHIP_MOVE_DEFERRED,
 };
 
 static struct msi_domain_ops pci_msi_domain_ops = {

arch/x86/kernel/apic/io_apic.c

···
 	.irq_set_affinity	= ioapic_set_affinity,
 	.irq_retrigger		= irq_chip_retrigger_hierarchy,
 	.irq_get_irqchip_state	= ioapic_irq_get_chip_state,
-	.flags			= IRQCHIP_SKIP_SET_WAKE |
+	.flags			= IRQCHIP_SKIP_SET_WAKE | IRQCHIP_MOVE_DEFERRED |
 				  IRQCHIP_AFFINITY_PRE_STARTUP,
 };
 

arch/x86/kernel/apic/msi.c

···
 		if (WARN_ON_ONCE(domain != real_parent))
 			return false;
 		info->chip->irq_set_affinity = msi_set_affinity;
+		info->chip->flags |= IRQCHIP_MOVE_DEFERRED;
 		break;
 	case DOMAIN_BUS_DMAR:
 	case DOMAIN_BUS_AMDVI:
···
 	.irq_retrigger		= irq_chip_retrigger_hierarchy,
 	.irq_compose_msi_msg	= dmar_msi_compose_msg,
 	.irq_write_msi_msg	= dmar_msi_write_msg,
-	.flags			= IRQCHIP_SKIP_SET_WAKE |
+	.flags			= IRQCHIP_SKIP_SET_WAKE | IRQCHIP_MOVE_DEFERRED |
 				  IRQCHIP_AFFINITY_PRE_STARTUP,
 };
 

arch/x86/kernel/hpet.c

···
 			 struct msi_domain_info *info, unsigned int virq,
 			 irq_hw_number_t hwirq, msi_alloc_info_t *arg)
 {
-	irq_set_status_flags(virq, IRQ_MOVE_PCNTXT);
 	irq_domain_set_info(domain, virq, arg->hwirq, info->chip, NULL,
 			    handle_edge_irq, arg->data, "edge");
 
 	return 0;
 }
 
-static void hpet_msi_free(struct irq_domain *domain,
-			  struct msi_domain_info *info, unsigned int virq)
-{
-	irq_clear_status_flags(virq, IRQ_MOVE_PCNTXT);
-}
-
 static struct msi_domain_ops hpet_msi_domain_ops = {
 	.msi_init	= hpet_msi_init,
-	.msi_free	= hpet_msi_free,
 };
 
 static struct msi_domain_info hpet_msi_domain_info = {

arch/x86/platform/uv/uv_irq.c

···
 	if (ret >= 0) {
 		if (info->uv.limit == UV_AFFINITY_CPU)
 			irq_set_status_flags(virq, IRQ_NO_BALANCING);
-		else
-			irq_set_status_flags(virq, IRQ_MOVE_PCNTXT);
 
 		chip_data->pnode = uv_blade_to_pnode(info->uv.blade);
 		chip_data->offset = info->uv.offset;
···
 
 	BUG_ON(nr_irqs != 1);
 	kfree(irq_data->chip_data);
-	irq_clear_status_flags(virq, IRQ_MOVE_PCNTXT);
 	irq_clear_status_flags(virq, IRQ_NO_BALANCING);
 	irq_domain_free_irqs_top(domain, virq, nr_irqs);
 }

drivers/iommu/amd/init.c

···
 	.irq_retrigger		= irq_chip_retrigger_hierarchy,
 	.irq_set_affinity       = intcapxt_set_affinity,
 	.irq_set_wake		= intcapxt_set_wake,
-	.flags			= IRQCHIP_MASK_ON_SUSPEND,
+	.flags			= IRQCHIP_MASK_ON_SUSPEND | IRQCHIP_MOVE_DEFERRED,
 };
 
 static const struct irq_domain_ops intcapxt_domain_ops = {

drivers/iommu/amd/iommu.c

···
 		irq_data->chip_data = data;
 		irq_data->chip = &amd_ir_chip;
 		irq_remapping_prepare_irte(data, cfg, info, devid, index, i);
-		irq_set_status_flags(virq + i, IRQ_MOVE_PCNTXT);
 	}
 
 	return 0;

drivers/iommu/intel/irq_remapping.c

···
 		else
 			irq_data->chip = &intel_ir_chip;
 		intel_irq_remapping_prepare_irte(ird, irq_cfg, info, index, i);
-		irq_set_status_flags(virq + i, IRQ_MOVE_PCNTXT);
 	}
 	return 0;
 

drivers/irqchip/Kconfig

···
 	  Support for the Loongson-1 platform Interrupt Controller.
 
 config TI_SCI_INTR_IRQCHIP
-	bool
+	tristate "TI SCI INTR Interrupt Controller"
 	depends on TI_SCI_PROTOCOL
+	depends on ARCH_K3 || COMPILE_TEST
 	select IRQ_DOMAIN_HIERARCHY
 	help
 	  This enables the irqchip driver support for K3 Interrupt router
···
 	  TI System Controller, say Y here. Otherwise, say N.
 
 config TI_SCI_INTA_IRQCHIP
-	bool
+	tristate "TI SCI INTA Interrupt Controller"
 	depends on TI_SCI_PROTOCOL
+	depends on ARCH_K3 || (COMPILE_TEST && ARM64)
 	select IRQ_DOMAIN_HIERARCHY
 	select TI_SCI_INTA_MSI_DOMAIN
 	help

drivers/irqchip/irq-brcmstb-l2.c

···
 	u32 saved_mask; /* for suspend/resume */
 };
 
-/**
- * brcmstb_l2_mask_and_ack - Mask and ack pending interrupt
- * @d: irq_data
- *
- * Chip has separate enable/disable registers instead of a single mask
- * register and pending interrupt is acknowledged by setting a bit.
- *
- * Note: This function is generic and could easily be added to the
- * generic irqchip implementation if there ever becomes a will to do so.
- * Perhaps with a name like irq_gc_mask_disable_and_ack_set().
- *
- * e.g.: https://patchwork.kernel.org/patch/9831047/
- */
-static void brcmstb_l2_mask_and_ack(struct irq_data *d)
-{
-	struct irq_chip_generic *gc = irq_data_get_irq_chip_data(d);
-	struct irq_chip_type *ct = irq_data_get_chip_type(d);
-	u32 mask = d->mask;
-
-	irq_gc_lock(gc);
-	irq_reg_writel(gc, mask, ct->regs.disable);
-	*ct->mask_cache &= ~mask;
-	irq_reg_writel(gc, mask, ct->regs.ack);
-	irq_gc_unlock(gc);
-}
-
 static void brcmstb_l2_intc_irq_handle(struct irq_desc *desc)
 {
 	struct brcmstb_l2_intc_data *b = irq_desc_get_handler_data(desc);
···
 	if (init_params->cpu_clear >= 0) {
 		ct->regs.ack = init_params->cpu_clear;
 		ct->chip.irq_ack = irq_gc_ack_set_bit;
-		ct->chip.irq_mask_ack = brcmstb_l2_mask_and_ack;
+		ct->chip.irq_mask_ack = irq_gc_mask_disable_and_ack_set;
 	} else {
 		/* No Ack - but still slightly more efficient to define this */
 		ct->chip.irq_mask_ack = irq_gc_mask_disable_reg;

drivers/irqchip/irq-keystone.c

···
 	if (!kirq)
 		return -ENOMEM;
 
-	kirq->devctrl_regs =
-		syscon_regmap_lookup_by_phandle(np, "ti,syscon-dev");
+	kirq->devctrl_regs = syscon_regmap_lookup_by_phandle_args(np, "ti,syscon-dev",
+								  1, &kirq->devctrl_offset);
 	if (IS_ERR(kirq->devctrl_regs))
 		return PTR_ERR(kirq->devctrl_regs);
-
-	ret = of_property_read_u32_index(np, "ti,syscon-dev", 1,
-					 &kirq->devctrl_offset);
-	if (ret) {
-		dev_err(dev, "couldn't read the devctrl_offset offset!\n");
-		return ret;
-	}
 
 	kirq->irq = platform_get_irq(pdev, 0);
 	if (kirq->irq < 0)

drivers/irqchip/irq-loongarch-avec.c

···
 	unsigned int		moving;
 };
 
+static inline void avecintc_enable(void)
+{
+	u64 value;
+
+	value = iocsr_read64(LOONGARCH_IOCSR_MISC_FUNC);
+	value |= IOCSR_MISC_FUNC_AVEC_EN;
+	iocsr_write64(value, LOONGARCH_IOCSR_MISC_FUNC);
+}
+
 static inline void avecintc_ack_irq(struct irq_data *d)
 {
 }
···
 		return 0;
 
 	guard(raw_spinlock)(&loongarch_avec.lock);
+
+	avecintc_enable();
 
 	irq_matrix_online(loongarch_avec.vector_matrix);
 
···
 static int __init avecintc_init(struct irq_domain *parent)
 {
 	int ret, parent_irq;
-	unsigned long value;
 
 	raw_spin_lock_init(&loongarch_avec.lock);
 
···
 				  "irqchip/loongarch/avecintc:starting",
 				  avecintc_cpu_online, avecintc_cpu_offline);
 #endif
-	value = iocsr_read64(LOONGARCH_IOCSR_MISC_FUNC);
-	value |= IOCSR_MISC_FUNC_AVEC_EN;
-	iocsr_write64(value, LOONGARCH_IOCSR_MISC_FUNC);
+	avecintc_enable();
 
 	return ret;
 

drivers/irqchip/irq-ti-sci-inta.c

···
 
 MODULE_AUTHOR("Lokesh Vutla <[e-mail]>");
 MODULE_DESCRIPTION("K3 Interrupt Aggregator driver over TI SCI protocol");
+MODULE_LICENSE("GPL");

drivers/irqchip/irq-ti-sci-intr.c

···
 
 MODULE_AUTHOR("Lokesh Vutla <lokeshvutla@ticom>");
 MODULE_DESCRIPTION("K3 Interrupt Router driver over TI SCI protocol");
+MODULE_LICENSE("GPL");

drivers/irqchip/irq-ts4800.c

···
 {
 	struct ts4800_irq_data *data = irq_data_get_irq_chip_data(d);
 
-	seq_printf(p, "%s", dev_name(&data->pdev->dev));
+	seq_puts(p, dev_name(&data->pdev->dev));
 }
 
 static const struct irq_chip ts4800_chip = {

drivers/pci/controller/pci-hyperv.c

···
 	.irq_set_affinity	= irq_chip_set_affinity_parent,
 #ifdef CONFIG_X86
 	.irq_ack		= irq_chip_ack_parent,
+	.flags			= IRQCHIP_MOVE_DEFERRED,
 #elif defined(CONFIG_ARM64)
 	.irq_eoi		= irq_chip_eoi_parent,
 #endif

drivers/xen/events/events_base.c

···
 		INIT_RCU_WORK(&info->rwork, delayed_free_irq);
 
 		set_info_for_irq(irq, info);
-		/*
-		 * Interrupt affinity setting can be immediate. No point
-		 * in delaying it until an interrupt is handled.
-		 */
-		irq_set_status_flags(irq, IRQ_MOVE_PCNTXT);
-
 		INIT_LIST_HEAD(&info->eoi_list);
 		list_add_tail(&info->list, &xen_irq_list_head);
 	}

include/linux/irq.h

···
  * IRQ_NOAUTOEN			- Interrupt is not automatically enabled in
  *				  request/setup_irq()
  * IRQ_NO_BALANCING		- Interrupt cannot be balanced (affinity set)
- * IRQ_MOVE_PCNTXT		- Interrupt can be migrated from process context
  * IRQ_NESTED_THREAD		- Interrupt nests into another thread
  * IRQ_PER_CPU_DEVID		- Dev_id is a per-cpu variable
  * IRQ_IS_POLLED		- Always polled by another interrupt. Exclude
···
 	IRQ_NOREQUEST		= (1 << 11),
 	IRQ_NOAUTOEN		= (1 << 12),
 	IRQ_NO_BALANCING	= (1 << 13),
-	IRQ_MOVE_PCNTXT		= (1 << 14),
 	IRQ_NESTED_THREAD	= (1 << 15),
 	IRQ_NOTHREAD		= (1 << 16),
 	IRQ_PER_CPU_DEVID	= (1 << 17),
···
 
 #define IRQF_MODIFY_MASK	\
 	(IRQ_TYPE_SENSE_MASK | IRQ_NOPROBE | IRQ_NOREQUEST | \
-	 IRQ_NOAUTOEN | IRQ_MOVE_PCNTXT | IRQ_LEVEL | IRQ_NO_BALANCING | \
+	 IRQ_NOAUTOEN | IRQ_LEVEL | IRQ_NO_BALANCING | \
 	 IRQ_PER_CPU | IRQ_NESTED_THREAD | IRQ_NOTHREAD | IRQ_PER_CPU_DEVID | \
 	 IRQ_IS_POLLED | IRQ_DISABLE_UNLAZY | IRQ_HIDDEN)
 
···
  * IRQD_LEVEL			- Interrupt is level triggered
  * IRQD_WAKEUP_STATE		- Interrupt is configured for wakeup
  *				  from suspend
- * IRQD_MOVE_PCNTXT		- Interrupt can be moved in process
- *				  context
  * IRQD_IRQ_DISABLED		- Disabled state of the interrupt
  * IRQD_IRQ_MASKED		- Masked state of the interrupt
  * IRQD_IRQ_INPROGRESS		- In progress state of the interrupt
···
 	IRQD_AFFINITY_SET		= BIT(12),
 	IRQD_LEVEL			= BIT(13),
 	IRQD_WAKEUP_STATE		= BIT(14),
-	IRQD_MOVE_PCNTXT		= BIT(15),
 	IRQD_IRQ_DISABLED		= BIT(16),
 	IRQD_IRQ_MASKED			= BIT(17),
 	IRQD_IRQ_INPROGRESS		= BIT(18),
···
 static inline bool irqd_is_wakeup_set(struct irq_data *d)
 {
 	return __irqd_to_state(d) & IRQD_WAKEUP_STATE;
-}
-
-static inline bool irqd_can_move_in_process_context(struct irq_data *d)
-{
-	return __irqd_to_state(d) & IRQD_MOVE_PCNTXT;
 }
 
 static inline bool irqd_irq_disabled(struct irq_data *d)
···
  *                                    in the suspend path if they are in disabled state
  * IRQCHIP_AFFINITY_PRE_STARTUP:      Default affinity update before startup
  * IRQCHIP_IMMUTABLE:		      Don't ever change anything in this chip
+ * IRQCHIP_MOVE_DEFERRED:	      Move the interrupt in actual interrupt context
  */
 enum {
 	IRQCHIP_SET_TYPE_MASKED			= (1 <<  0),
···
 	IRQCHIP_ENABLE_WAKEUP_ON_SUSPEND	= (1 <<  9),
 	IRQCHIP_AFFINITY_PRE_STARTUP		= (1 << 10),
 	IRQCHIP_IMMUTABLE			= (1 << 11),
+	IRQCHIP_MOVE_DEFERRED			= (1 << 12),
 };
 
 #include <linux/irqdesc.h>
···
 extern int irq_chip_request_resources_parent(struct irq_data *data);
 extern void irq_chip_release_resources_parent(struct irq_data *data);
 #endif
+
+/* Disable or mask interrupts during a kernel kexec */
+extern void machine_kexec_mask_interrupts(void);
 
 /* Handling of unhandled and spurious interrupts: */
 extern void note_interrupt(struct irq_desc *desc, irqreturn_t action_ret);

kernel/irq/Kconfig

···
 config GENERIC_PENDING_IRQ
 	bool
 
+# Deduce delayed migration from top-level interrupt chip flags
+config GENERIC_PENDING_IRQ_CHIPFLAGS
+	bool
+
 # Support for generic irq migrating off cpu before the cpu is offline.
 config GENERIC_IRQ_MIGRATION
 	bool
···
 	  developers and debugging of hard to diagnose interrupt problems.
 
 	  If you don't know what to do here, say N.
+
+# Clear forwarded VM interrupts during kexec.
+# This option ensures the kernel clears active states for interrupts
+# forwarded to virtual machines (VMs) during a machine kexec.
+config GENERIC_IRQ_KEXEC_CLEAR_VM_FORWARD
+	bool
 
 endmenu
 

kernel/irq/Makefile

···
 # SPDX-License-Identifier: GPL-2.0
 
-obj-y := irqdesc.o handle.o manage.o spurious.o resend.o chip.o dummychip.o devres.o
+obj-y := irqdesc.o handle.o manage.o spurious.o resend.o chip.o dummychip.o devres.o kexec.o
 obj-$(CONFIG_IRQ_TIMINGS) += timings.o
 ifeq ($(CONFIG_TEST_IRQ_TIMINGS),y)
 	CFLAGS_timings.o += -DDEBUG

kernel/irq/chip.c

···
 	trigger = irqd_get_trigger_type(&desc->irq_data);
 
 	irqd_clear(&desc->irq_data, IRQD_NO_BALANCING | IRQD_PER_CPU |
-		   IRQD_TRIGGER_MASK | IRQD_LEVEL | IRQD_MOVE_PCNTXT);
+		   IRQD_TRIGGER_MASK | IRQD_LEVEL);
 	if (irq_settings_has_no_balance_set(desc))
 		irqd_set(&desc->irq_data, IRQD_NO_BALANCING);
 	if (irq_settings_is_per_cpu(desc))
 		irqd_set(&desc->irq_data, IRQD_PER_CPU);
-	if (irq_settings_can_move_pcntxt(desc))
-		irqd_set(&desc->irq_data, IRQD_MOVE_PCNTXT);
 	if (irq_settings_is_level(desc))
 		irqd_set(&desc->irq_data, IRQD_LEVEL);
 

kernel/irq/debugfs.c

···
 	BIT_MASK_DESCR(IRQCHIP_SUPPORTS_NMI),
 	BIT_MASK_DESCR(IRQCHIP_ENABLE_WAKEUP_ON_SUSPEND),
 	BIT_MASK_DESCR(IRQCHIP_IMMUTABLE),
+	BIT_MASK_DESCR(IRQCHIP_MOVE_DEFERRED),
 };
 
 static void
···
 	BIT_MASK_DESCR(IRQD_NO_BALANCING),
 
 	BIT_MASK_DESCR(IRQD_SINGLE_TARGET),
-	BIT_MASK_DESCR(IRQD_MOVE_PCNTXT),
 	BIT_MASK_DESCR(IRQD_AFFINITY_SET),
 	BIT_MASK_DESCR(IRQD_SETAFFINITY_PENDING),
 	BIT_MASK_DESCR(IRQD_AFFINITY_MANAGED),

kernel/irq/generic-chip.c

···
 	irq_reg_writel(gc, mask, ct->regs.ack);
 	irq_gc_unlock(gc);
 }
+EXPORT_SYMBOL_GPL(irq_gc_mask_disable_and_ack_set);
 
 /**
  * irq_gc_eoi - EOI interrupt

kernel/irq/internals.h

···
 #ifdef CONFIG_GENERIC_PENDING_IRQ
 static inline bool irq_can_move_pcntxt(struct irq_data *data)
 {
-	return irqd_can_move_in_process_context(data);
+	return !(data->chip->flags & IRQCHIP_MOVE_DEFERRED);
 }
 static inline bool irq_move_pending(struct irq_data *data)
 {
···
 static inline struct cpumask *irq_desc_get_pending_mask(struct irq_desc *desc)
 {
 	return desc->pending_mask;
-}
-static inline bool handle_enforce_irqctx(struct irq_data *data)
-{
-	return irqd_is_handle_enforce_irqctx(data);
 }
 bool irq_fixup_move_pending(struct irq_desc *desc, bool force_clear);
 #else /* CONFIG_GENERIC_PENDING_IRQ */
···
 	return NULL;
 }
 static inline bool irq_fixup_move_pending(struct irq_desc *desc, bool fclear)
-{
-	return false;
-}
-static inline bool handle_enforce_irqctx(struct irq_data *data)
 {
 	return false;
 }

kernel/irq/irqdesc.c

···
 		return -EINVAL;
 
 	data = irq_desc_get_irq_data(desc);
-	if (WARN_ON_ONCE(!in_hardirq() && handle_enforce_irqctx(data)))
+	if (WARN_ON_ONCE(!in_hardirq() && irqd_is_handle_enforce_irqctx(data)))
 		return -EPERM;
 
 	generic_handle_irq_desc(desc);

kernel/irq/kexec.c

···
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/interrupt.h>
+#include <linux/irq.h>
+#include <linux/irqdesc.h>
+#include <linux/irqnr.h>
+
+#include "internals.h"
+
+void machine_kexec_mask_interrupts(void)
+{
+	struct irq_desc *desc;
+	unsigned int i;
+
+	for_each_irq_desc(i, desc) {
+		struct irq_chip *chip;
+		int check_eoi = 1;
+
+		chip = irq_desc_get_chip(desc);
+		if (!chip || !irqd_is_started(&desc->irq_data))
+			continue;
+
+		if (IS_ENABLED(CONFIG_GENERIC_IRQ_KEXEC_CLEAR_VM_FORWARD)) {
+			/*
+			 * First try to remove the active state from an interrupt which is forwarded
+			 * to a VM. If the interrupt is not forwarded, try to EOI the interrupt.
+			 */
+			check_eoi = irq_set_irqchip_state(i, IRQCHIP_STATE_ACTIVE, false);
+		}
+
+		if (check_eoi && chip->irq_eoi && irqd_irq_inprogress(&desc->irq_data))
+			chip->irq_eoi(&desc->irq_data);
+
+		irq_shutdown(desc);
+	}
+}

kernel/irq/manage.c

···
 }
 
 /*
+ * Interrupts explicitly requested as threaded interrupts want to be
+ * preemptible - many of them need to sleep and wait for slow busses to
+ * complete.
+ */
+static irqreturn_t irq_thread_fn(struct irq_desc *desc,	struct irqaction *action)
+{
+	irqreturn_t ret = action->thread_fn(action->irq, action->dev_id);
+
+	if (ret == IRQ_HANDLED)
+		atomic_inc(&desc->threads_handled);
+
+	irq_finalize_oneshot(desc, action);
+	return ret;
+}
+
+/*
  * Interrupts which are not explicitly requested as threaded
  * interrupts rely on the implicit bh/preempt disable of the hard irq
  * context. So we need to disable bh here to avoid deadlocks and other
  * side effects.
  */
-static irqreturn_t
-irq_forced_thread_fn(struct irq_desc *desc, struct irqaction *action)
+static irqreturn_t irq_forced_thread_fn(struct irq_desc *desc, struct irqaction *action)
 {
 	irqreturn_t ret;
 
 	local_bh_disable();
 	if (!IS_ENABLED(CONFIG_PREEMPT_RT))
 		local_irq_disable();
-	ret = action->thread_fn(action->irq, action->dev_id);
-	if (ret == IRQ_HANDLED)
-		atomic_inc(&desc->threads_handled);
-
-	irq_finalize_oneshot(desc, action);
+	ret = irq_thread_fn(desc, action);
 	if (!IS_ENABLED(CONFIG_PREEMPT_RT))
 		local_irq_enable();
 	local_bh_enable();
-	return ret;
-}
-
-/*
- * Interrupts explicitly requested as threaded interrupts want to be
- * preemptible - many of them need to sleep and wait for slow busses to
- * complete.
- */
-static irqreturn_t irq_thread_fn(struct irq_desc *desc,
-		struct irqaction *action)
-{
-	irqreturn_t ret;
-
-	ret = action->thread_fn(action->irq, action->dev_id);
-	if (ret == IRQ_HANDLED)
-		atomic_inc(&desc->threads_handled);
-
-	irq_finalize_oneshot(desc, action);
 	return ret;
 }
 

kernel/irq/resend.c

···
 	 * Validate whether this interrupt can be safely injected from
 	 * non interrupt context
 	 */
-	if (handle_enforce_irqctx(&desc->irq_data))
+	if (irqd_is_handle_enforce_irqctx(&desc->irq_data))
 		return -EINVAL;
 
 	/*

kernel/irq/settings.h

···
 	_IRQ_NOREQUEST		= IRQ_NOREQUEST,
 	_IRQ_NOTHREAD		= IRQ_NOTHREAD,
 	_IRQ_NOAUTOEN		= IRQ_NOAUTOEN,
-	_IRQ_MOVE_PCNTXT	= IRQ_MOVE_PCNTXT,
 	_IRQ_NO_BALANCING	= IRQ_NO_BALANCING,
 	_IRQ_NESTED_THREAD	= IRQ_NESTED_THREAD,
 	_IRQ_PER_CPU_DEVID	= IRQ_PER_CPU_DEVID,
···
 static inline void irq_settings_set_noprobe(struct irq_desc *desc)
 {
 	desc->status_use_accessors |= _IRQ_NOPROBE;
-}
-
-static inline bool irq_settings_can_move_pcntxt(struct irq_desc *desc)
-{
-	return desc->status_use_accessors & _IRQ_MOVE_PCNTXT;
 }
 
 static inline bool irq_settings_can_autoenable(struct irq_desc *desc)

kernel/irq/timings.c

···
 
 /**
  * irq_timings_next_event - Return when the next event is supposed to arrive
+ * @now: current time
  *
  * During the last busy cycle, the number of interrupts is incremented
  * and stored in the irq_timings structure. This information is