[RFC PATCH 05/12] context_tracking: Split IRQ-exit preparation from the EQS transition

[Karl Mehltretter <kmehltretter@gmail.com>]

ct_irq_exit() combines traceable nesting and tracepoint work with the final
transition to an RCU extended quiescent state. A pre-counted ordinary
hardirq return needs to run that preparation before its synthetic hardirq
classification is removed, but it must enter the quiescent state only after
the raw count and lockdep teardown.

Split IRQ exit into prepare and finish phases. The prepare phase validates
and updates interrupt nesting, then emits the tracepoint while RCU is
watching. The finish phase performs the raw quiescent-state transition and
RCU Tasks bookkeeping.

Keep ct_irq_exit() and ct_nmi_exit() as adjacent prepare and finish
wrappers. Existing IRQ and NMI callers retain their ordering and behavior.

Assisted-by: LLM
---
 include/linux/context_tracking_irq.h | 32 +++++++++++-
 kernel/context_tracking.c            | 78 ++++++++++++++++++++++------
 2 files changed, 93 insertions(+), 17 deletions(-)

diff --git a/include/linux/context_tracking_irq.h b/include/linux/context_tracking_irq.h
index 197916ee91a4b..b038cd1249148 100644
--- a/include/linux/context_tracking_irq.h
+++ b/include/linux/context_tracking_irq.h
@@ -2,8 +2,23 @@
 #ifndef _LINUX_CONTEXT_TRACKING_IRQ_H
 #define _LINUX_CONTEXT_TRACKING_IRQ_H
 
+#include <linux/types.h>
+
+/**
+ * struct ct_irq_exit_state - Opaque context-tracking IRQ-exit state
+ * @exit_rcu: The interrupted context was in an RCU extended quiescent state
+ *
+ * This object is filled in by ct_irq_exit_prepare() and must be passed to the
+ * matching ct_irq_exit_finish(). Callers must consider its members private.
+ */
+struct ct_irq_exit_state {
+	bool exit_rcu;
+};
+
 #ifdef CONFIG_CONTEXT_TRACKING_IDLE
 void ct_irq_enter(void);
+struct ct_irq_exit_state ct_irq_exit_prepare(void);
+void ct_irq_exit_finish(struct ct_irq_exit_state state);
 void ct_irq_exit(void);
 void ct_irq_enter_irqson(void);
 void ct_irq_exit_irqson(void);
@@ -11,7 +26,22 @@ void ct_nmi_enter(void);
 void ct_nmi_exit(void);
 #else
 static __always_inline void ct_irq_enter(void) { }
-static __always_inline void ct_irq_exit(void) { }
+static __always_inline struct ct_irq_exit_state ct_irq_exit_prepare(void)
+{
+	return (struct ct_irq_exit_state) { };
+}
+
+static __always_inline void ct_irq_exit_finish(struct ct_irq_exit_state state)
+{
+	(void)state;
+}
+
+static __always_inline void ct_irq_exit(void)
+{
+	struct ct_irq_exit_state state = ct_irq_exit_prepare();
+
+	ct_irq_exit_finish(state);
+}
 static inline void ct_irq_enter_irqson(void) { }
 static inline void ct_irq_exit_irqson(void) { }
 static __always_inline void ct_nmi_enter(void) { }
diff --git a/kernel/context_tracking.c b/kernel/context_tracking.c
index a743e7ffa6c00..80ed8ec606c6a 100644
--- a/kernel/context_tracking.c
+++ b/kernel/context_tracking.c
@@ -169,20 +169,10 @@ static void noinstr ct_kernel_enter(bool user, int offset)
 	instrumentation_end();
 }
 
-/**
- * ct_nmi_exit - inform RCU of exit from NMI context
- *
- * If we are returning from the outermost NMI handler that interrupted an
- * RCU-idle period, update ct->state and ct->nmi_nesting
- * to let the RCU grace-period handling know that the CPU is back to
- * being RCU-idle.
- *
- * If you add or remove a call to ct_nmi_exit(), be sure to test
- * with CONFIG_RCU_EQS_DEBUG=y.
- */
-void noinstr ct_nmi_exit(void)
+static struct ct_irq_exit_state noinstr __ct_nmi_exit_prepare(void)
 {
 	struct context_tracking *ct = this_cpu_ptr(&context_tracking);
+	struct ct_irq_exit_state state = { };
 
 	instrumentation_begin();
 	/*
@@ -203,7 +193,7 @@ void noinstr ct_nmi_exit(void)
 		WRITE_ONCE(ct->nmi_nesting, /* No store tearing. */
 			   ct_nmi_nesting() - 2);
 		instrumentation_end();
-		return;
+		return state;
 	}
 
 	/* This NMI interrupted an RCU-idle CPU, restore RCU-idleness. */
@@ -213,6 +203,15 @@ void noinstr ct_nmi_exit(void)
 	// instrumentation for the noinstr ct_kernel_exit_state()
 	instrument_atomic_write(&ct->state, sizeof(ct->state));
 	instrumentation_end();
+	state.exit_rcu = true;
+
+	return state;
+}
+
+static void noinstr __ct_nmi_exit_finish(struct ct_irq_exit_state state)
+{
+	if (!state.exit_rcu)
+		return;
 
 	// RCU is watching here ...
 	ct_kernel_exit_state(CT_RCU_WATCHING);
@@ -222,6 +221,24 @@ void noinstr ct_nmi_exit(void)
 		rcu_task_exit();
 }
 
+/**
+ * ct_nmi_exit - inform RCU of exit from NMI context
+ *
+ * If we are returning from the outermost NMI handler that interrupted an
+ * RCU-idle period, update ct->state and ct->nmi_nesting
+ * to let the RCU grace-period handling know that the CPU is back to
+ * being RCU-idle.
+ *
+ * If you add or remove a call to ct_nmi_exit(), be sure to test
+ * with CONFIG_RCU_EQS_DEBUG=y.
+ */
+void noinstr ct_nmi_exit(void)
+{
+	struct ct_irq_exit_state state = __ct_nmi_exit_prepare();
+
+	__ct_nmi_exit_finish(state);
+}
+
 /**
  * ct_nmi_enter - inform RCU of entry to NMI context
  *
@@ -348,7 +365,35 @@ noinstr void ct_irq_enter(void)
 }
 
 /**
- * ct_irq_exit - inform RCU that current CPU is exiting irq towards idle
+ * ct_irq_exit_prepare - prepare to exit an IRQ towards idle
+ *
+ * Perform the traceable part of an IRQ exit and return an opaque object for
+ * ct_irq_exit_finish(). RCU remains watching until the matching finish call.
+ * The caller must keep interrupts disabled, must not schedule or migrate, and
+ * must invoke ct_irq_exit_finish() exactly once.
+ *
+ * Return: An opaque object to pass to ct_irq_exit_finish().
+ */
+struct ct_irq_exit_state noinstr ct_irq_exit_prepare(void)
+{
+	lockdep_assert_irqs_disabled();
+	return __ct_nmi_exit_prepare();
+}
+
+/**
+ * ct_irq_exit_finish - finish exiting an IRQ towards idle
+ * @state: Return value from the matching ct_irq_exit_prepare()
+ *
+ * Complete a pending transition to an RCU extended quiescent state. Nothing
+ * traceable may run between this function and the low-level return path.
+ */
+void noinstr ct_irq_exit_finish(struct ct_irq_exit_state state)
+{
+	__ct_nmi_exit_finish(state);
+}
+
+/**
+ * ct_irq_exit - inform RCU that current CPU is exiting IRQ towards idle
  *
  * Exit from an interrupt handler, which might possibly result in entering
  * idle mode, in other words, leaving the mode in which read-side critical
@@ -368,8 +413,9 @@ noinstr void ct_irq_enter(void)
  */
 noinstr void ct_irq_exit(void)
 {
-	lockdep_assert_irqs_disabled();
-	ct_nmi_exit();
+	struct ct_irq_exit_state state = ct_irq_exit_prepare();
+
+	ct_irq_exit_finish(state);
 }
 
 /*
-- 
2.39.5 (Apple Git-154)