genirq: Add interrupt redirection infrastructure

Add infrastructure to redirect interrupt handler execution to a
different CPU when the current CPU is not part of the interrupt's CPU
affinity mask.

This is primarily aimed at (de)multiplexed interrupts, where the child
interrupt handler runs in the context of the parent interrupt handler,
and therefore CPU affinity control for the child interrupt is typically
not available.

With the new infrastructure, the child interrupt is allowed to freely
change its affinity setting, independently of the parent. If the
interrupt handler happens to be triggered on an "incompatible" CPU (a
CPU that's not part of the child interrupt's affinity mask), the handler
is redirected and runs in IRQ work context on a "compatible" CPU.

No functional change is being made to any existing irqchip driver, and
irqchip drivers must be explicitly modified to use the newly added
infrastructure to support interrupt redirection.

Originally-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Radu Rendec <rrendec@redhat.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/linux-pci/878qpg4o4t.ffs@tglx/
Link: https://patch.msgid.link/20251128212055.1409093-2-rrendec@redhat.com

2 files changed, 26 insertions, 1 deletions

diff --git a/include/linux/irq.h b/include/linux/irq.h
index 4a9f1d7b08c3..41d5bc53eefc 100644
--- a/include/linux/irq.h
+++ b/include/linux/irq.h
@@ -459,6 +459,8 @@ static inline irq_hw_number_t irqd_to_hwirq(struct irq_data *d)
  *			checks against the supplied affinity mask are not
  *			required. This is used for CPU hotplug where the
  *			target CPU is not yet set in the cpu_online_mask.
+ * @irq_pre_redirect:	Optional function to be invoked before redirecting
+ *			an interrupt via irq_work. Called only on CONFIG_SMP.
  * @irq_retrigger:	resend an IRQ to the CPU
  * @irq_set_type:	set the flow type (IRQ_TYPE_LEVEL/etc.) of an IRQ
  * @irq_set_wake:	enable/disable power-management wake-on of an IRQ
@@ -503,6 +505,7 @@ struct irq_chip {
 	void		(*irq_eoi)(struct irq_data *data);
 
 	int		(*irq_set_affinity)(struct irq_data *data, const struct cpumask *dest, bool force);
+	void		(*irq_pre_redirect)(struct irq_data *data);
 	int		(*irq_retrigger)(struct irq_data *data);
 	int		(*irq_set_type)(struct irq_data *data, unsigned int flow_type);
 	int		(*irq_set_wake)(struct irq_data *data, unsigned int on);
@@ -687,6 +690,13 @@ extern int irq_chip_set_vcpu_affinity_parent(struct irq_data *data,
 extern int irq_chip_set_type_parent(struct irq_data *data, unsigned int type);
 extern int irq_chip_request_resources_parent(struct irq_data *data);
 extern void irq_chip_release_resources_parent(struct irq_data *data);
+#ifdef CONFIG_SMP
+void irq_chip_pre_redirect_parent(struct irq_data *data);
+#endif
+#endif
+
+#ifdef CONFIG_SMP
+int irq_chip_redirect_set_affinity(struct irq_data *data, const struct cpumask *dest, bool force);
 #endif
 
 /* Disable or mask interrupts during a kernel kexec */
diff --git a/include/linux/irqdesc.h b/include/linux/irqdesc.h
index 17902861de76..dae9a9b93665 100644
--- a/include/linux/irqdesc.h
+++ b/include/linux/irqdesc.h
@@ -2,9 +2,10 @@
 #ifndef _LINUX_IRQDESC_H
 #define _LINUX_IRQDESC_H
 
-#include <linux/rcupdate.h>
+#include <linux/irq_work.h>
 #include <linux/kobject.h>
 #include <linux/mutex.h>
+#include <linux/rcupdate.h>
 
 /*
  * Core internal functions to deal with irq descriptors
@@ -30,6 +31,17 @@ struct irqstat {
 };
 
 /**
+ * struct irq_redirect - interrupt redirection metadata
+ * @work:	Harg irq_work item for handler execution on a different CPU
+ * @target_cpu:	CPU to run irq handler on in case the current CPU is not part
+ *		of the irq affinity mask
+ */
+struct irq_redirect {
+	struct irq_work	work;
+	unsigned int	target_cpu;
+};
+
+/**
  * struct irq_desc - interrupt descriptor
  * @irq_common_data:	per irq and chip data passed down to chip functions
  * @kstat_irqs:		irq stats per cpu
@@ -46,6 +58,7 @@ struct irqstat {
  * @threads_handled:	stats field for deferred spurious detection of threaded handlers
  * @threads_handled_last: comparator field for deferred spurious detection of threaded handlers
  * @lock:		locking for SMP
+ * @redirect:		Facility for redirecting interrupts via irq_work
  * @affinity_hint:	hint to user space for preferred irq affinity
  * @affinity_notify:	context for notification of affinity changes
  * @pending_mask:	pending rebalanced interrupts
@@ -83,6 +96,7 @@ struct irq_desc {
 	raw_spinlock_t		lock;
 	struct cpumask		*percpu_enabled;
 #ifdef CONFIG_SMP
+	struct irq_redirect	redirect;
 	const struct cpumask	*affinity_hint;
 	struct irq_affinity_notify *affinity_notify;
 #ifdef CONFIG_GENERIC_PENDING_IRQ
@@ -185,6 +199,7 @@ int generic_handle_irq_safe(unsigned int irq);
 int generic_handle_domain_irq(struct irq_domain *domain, irq_hw_number_t hwirq);
 int generic_handle_domain_irq_safe(struct irq_domain *domain, irq_hw_number_t hwirq);
 int generic_handle_domain_nmi(struct irq_domain *domain, irq_hw_number_t hwirq);
+bool generic_handle_demux_domain_irq(struct irq_domain *domain, irq_hw_number_t hwirq);
 #endif
 
 /* Test to see if a driver has successfully requested an irq */