summaryrefslogtreecommitdiff
path: root/kernel
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2025-01-21 13:51:07 -0800
committerLinus Torvalds <torvalds@linux-foundation.org>2025-01-21 13:51:07 -0800
commit4c551165e771ff565bf6c3b13e06a587e70acdef (patch)
tree4ffc4792fb79f2de66f3c1bd4bb38ae8ce2b0ce9 /kernel
parentf200c315da80584ad4d7d752f9eda1cea05fe183 (diff)
parenta4b3990e01df169334ff2695d2fe494eda63a297 (diff)
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
Diffstat (limited to 'kernel')
-rw-r--r--kernel/irq/Kconfig10
-rw-r--r--kernel/irq/Makefile2
-rw-r--r--kernel/irq/chip.c4
-rw-r--r--kernel/irq/debugfs.c2
-rw-r--r--kernel/irq/generic-chip.c1
-rw-r--r--kernel/irq/internals.h10
-rw-r--r--kernel/irq/irqdesc.c2
-rw-r--r--kernel/irq/kexec.c36
-rw-r--r--kernel/irq/manage.c41
-rw-r--r--kernel/irq/resend.c2
-rw-r--r--kernel/irq/settings.h6
-rw-r--r--kernel/irq/timings.c1
12 files changed, 71 insertions, 46 deletions
diff --git a/kernel/irq/Kconfig b/kernel/irq/Kconfig
index 529adb1f5859..5432418c0fea 100644
--- a/kernel/irq/Kconfig
+++ b/kernel/irq/Kconfig
@@ -31,6 +31,10 @@ config GENERIC_IRQ_EFFECTIVE_AFF_MASK
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
@@ -141,6 +145,12 @@ config GENERIC_IRQ_DEBUGFS
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
config GENERIC_IRQ_MULTI_HANDLER
diff --git a/kernel/irq/Makefile b/kernel/irq/Makefile
index f19d3080bf11..c0f44c06d69d 100644
--- a/kernel/irq/Makefile
+++ b/kernel/irq/Makefile
@@ -1,6 +1,6 @@
# 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
diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c
index 271e9139de77..c901436ebd9f 100644
--- a/kernel/irq/chip.c
+++ b/kernel/irq/chip.c
@@ -1114,13 +1114,11 @@ void irq_modify_status(unsigned int irq, unsigned long clr, unsigned long set)
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);
diff --git a/kernel/irq/debugfs.c b/kernel/irq/debugfs.c
index c6ffb97966be..ca142b9a4db3 100644
--- a/kernel/irq/debugfs.c
+++ b/kernel/irq/debugfs.c
@@ -53,6 +53,7 @@ static const struct irq_bit_descr irqchip_flags[] = {
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
@@ -108,7 +109,6 @@ static const struct irq_bit_descr irqdata_states[] = {
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),
diff --git a/kernel/irq/generic-chip.c b/kernel/irq/generic-chip.c
index 32ffcbb87fa1..c4a8bca5f2b0 100644
--- a/kernel/irq/generic-chip.c
+++ b/kernel/irq/generic-chip.c
@@ -162,6 +162,7 @@ void irq_gc_mask_disable_and_ack_set(struct irq_data *d)
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
diff --git a/kernel/irq/internals.h b/kernel/irq/internals.h
index fe0272cd84a5..a979523640d0 100644
--- a/kernel/irq/internals.h
+++ b/kernel/irq/internals.h
@@ -421,7 +421,7 @@ irq_init_generic_chip(struct irq_chip_generic *gc, const char *name,
#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)
{
@@ -441,10 +441,6 @@ 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 */
static inline bool irq_can_move_pcntxt(struct irq_data *data)
@@ -471,10 +467,6 @@ 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;
-}
#endif /* !CONFIG_GENERIC_PENDING_IRQ */
#if !defined(CONFIG_IRQ_DOMAIN) || !defined(CONFIG_IRQ_DOMAIN_HIERARCHY)
diff --git a/kernel/irq/irqdesc.c b/kernel/irq/irqdesc.c
index 0253e77fcd9a..287830739783 100644
--- a/kernel/irq/irqdesc.c
+++ b/kernel/irq/irqdesc.c
@@ -708,7 +708,7 @@ int handle_irq_desc(struct irq_desc *desc)
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);
diff --git a/kernel/irq/kexec.c b/kernel/irq/kexec.c
new file mode 100644
index 000000000000..1a3deffe6b5b
--- /dev/null
+++ b/kernel/irq/kexec.c
@@ -0,0 +1,36 @@
+// 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);
+ }
+}
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index f0803d6bd296..f300bb6be3bd 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -1182,45 +1182,38 @@ out_unlock:
}
/*
- * 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.
+ * 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_forced_thread_fn(struct irq_desc *desc, struct irqaction *action)
+static irqreturn_t irq_thread_fn(struct irq_desc *desc, struct irqaction *action)
{
- irqreturn_t ret;
+ irqreturn_t ret = action->thread_fn(action->irq, action->dev_id);
- 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);
- 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.
+ * 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_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;
- ret = action->thread_fn(action->irq, action->dev_id);
- if (ret == IRQ_HANDLED)
- atomic_inc(&desc->threads_handled);
-
- irq_finalize_oneshot(desc, action);
+ local_bh_disable();
+ if (!IS_ENABLED(CONFIG_PREEMPT_RT))
+ local_irq_disable();
+ ret = irq_thread_fn(desc, action);
+ if (!IS_ENABLED(CONFIG_PREEMPT_RT))
+ local_irq_enable();
+ local_bh_enable();
return ret;
}
diff --git a/kernel/irq/resend.c b/kernel/irq/resend.c
index b07a2d732ffb..1b7fa72968bd 100644
--- a/kernel/irq/resend.c
+++ b/kernel/irq/resend.c
@@ -53,7 +53,7 @@ static int irq_sw_resend(struct irq_desc *desc)
* 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;
/*
diff --git a/kernel/irq/settings.h b/kernel/irq/settings.h
index 7b7efb1a114b..00b3bd127692 100644
--- a/kernel/irq/settings.h
+++ b/kernel/irq/settings.h
@@ -11,7 +11,6 @@ enum {
_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,
@@ -142,11 +141,6 @@ 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)
{
return !(desc->status_use_accessors & _IRQ_NOAUTOEN);
diff --git a/kernel/irq/timings.c b/kernel/irq/timings.c
index c43e2ac2f8de..4b7315e99bd6 100644
--- a/kernel/irq/timings.c
+++ b/kernel/irq/timings.c
@@ -509,6 +509,7 @@ static inline void irq_timings_store(int irq, struct irqt_stat *irqs, u64 ts)
/**
* 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