[RFC PATCH 08/12] entry: Classify ordinary hardirq return-tail work as hardirq context

[Karl Mehltretter <kmehltretter@gmail.com>]

An ordinary hardirq removes its original count and lockdep state before the
return path may preempt. Traceable return-tail callbacks then appear to run
in the interrupted task or softirq context and can collide with recursion
state owned by that context.

Use the saved ordinary-hardirq provenance to restore only preempt-count and
lockdep classification after the preemption decision. Keep it across
traceable return-tail work, deferred hrtimer rearming, IRQ-on preparation,
and context-tracking preparation.

Before removing the raw tail state, prepare the count and lockdep teardown
and close late regular or forced-thread softirq work. Complete any pending
RCU quiescent-state transition only after that raw teardown.

Do not repeat interrupt accounting, RCU or tick entry. Existing non-hardirq
return paths remain unchanged.

Assisted-by: LLM
---
 include/linux/hardirq.h          |  5 +++
 include/linux/irq-entry-common.h | 59 ++++++++++++++++++++++++++++++--
 kernel/softirq.c                 | 18 ++++++++++
 3 files changed, 79 insertions(+), 3 deletions(-)

diff --git a/include/linux/hardirq.h b/include/linux/hardirq.h
index ad27a06c859a0..a120e3756d076 100644
--- a/include/linux/hardirq.h
+++ b/include/linux/hardirq.h
@@ -27,6 +27,7 @@ static __always_inline void rcu_irq_enter_check_tick(void)
 
 void irq_enter_rcu_preempt_counted(void);
 bool irq_exit_rcu_preempt_counted_prepare(void);
+void noinstr irqentry_hardirq_tail_exit(void);
 
 /*
  * Prepare every potentially instrumentable part of hardirq teardown before
@@ -37,6 +38,10 @@ static __always_inline bool irqentry_hardirq_exit_prepare(void)
 {
 	bool do_sub;
 
+	/*
+	 * Preempt-on tracing can raise deferred work. The caller must perform
+	 * the final worker closure before removing the raw hardirq count.
+	 */
 	do_sub = preempt_count_sub_prepare(HARDIRQ_OFFSET);
 	lockdep_hardirq_exit_prepare();
 	return do_sub;
diff --git a/include/linux/irq-entry-common.h b/include/linux/irq-entry-common.h
index 2ed637cf66b0c..c6bdd5a2522e8 100644
--- a/include/linux/irq-entry-common.h
+++ b/include/linux/irq-entry-common.h
@@ -355,6 +355,28 @@ typedef struct irqentry_state {
 
 irqentry_state_t noinstr irqentry_hardirq_enter(struct pt_regs *regs);
 
+/**
+ * irqentry_hardirq_tail_enter - Restore ordinary-hardirq return-tail state
+ * @state: Return value from the matching irqentry_hardirq_enter()
+ *
+ * Restore only the hardirq classification which traceable return-tail work
+ * needs. Accounting, RCU and tick handling belong to the completed interrupt
+ * and must not be repeated here.
+ */
+static __always_inline void
+irqentry_hardirq_tail_enter(irqentry_state_t state)
+{
+	if (!state.hardirq)
+		return;
+
+	__preempt_count_add(HARDIRQ_OFFSET);
+	lockdep_hardirq_enter();
+
+	instrumentation_begin();
+	preempt_count_add_finish(HARDIRQ_OFFSET);
+	instrumentation_end();
+}
+
 /**
  * irqentry_exit_cond_resched - Conditionally reschedule on return from interrupt
  *
@@ -505,7 +527,9 @@ static inline void irqentry_exit_to_kernel_mode_preempt(struct pt_regs *regs,
  *
  * The rearm on return to user mode needs no such annotation: no locks are
  * held there, so it uses the same lock chains as the rearm in hardirq
- * context.
+ * context. Ordinary-hardirq return paths do not use this wrapper: their saved
+ * provenance restores both the hardirq count and lockdep nesting across the
+ * whole traceable tail and they call hrtimer_rearm_deferred() directly.
  */
 static __always_inline void irqentry_hrtimer_rearm_deferred(void)
 {
@@ -520,7 +544,9 @@ static __always_inline void irqentry_hrtimer_rearm_deferred(void)
  * @state:	Return value from matching call to irqentry_enter_from_kernel_mode()
  *
  * This is to be invoked after irqentry_exit_to_kernel_mode_preempt() and before
- * actually returning to the interrupted context.
+ * actually returning to the interrupted context. If @state records ordinary
+ * hardirq provenance, the caller must first invoke
+ * irqentry_hardirq_tail_enter() exactly once.
  *
  * There are no requirements for the CPU state other than being able to complete
  * the tracing, lockdep and RCU state transitions. After this function returns
@@ -529,6 +555,31 @@ static __always_inline void irqentry_hrtimer_rearm_deferred(void)
 static __always_inline void
 irqentry_exit_to_kernel_mode_after_preempt(struct pt_regs *regs, irqentry_state_t state)
 {
+	struct ct_irq_exit_state ct_state = { };
+
+	if (state.hardirq) {
+		if (!regs_irqs_disabled(regs)) {
+			instrumentation_begin();
+			hrtimer_rearm_deferred();
+			/* Tell the tracer that the return will enable IRQs. */
+			trace_hardirqs_on_prepare();
+			lockdep_hardirqs_on_prepare_irqtail();
+			instrumentation_end();
+		}
+
+		if (state.exit_rcu)
+			ct_state = ct_irq_exit_prepare();
+
+		irqentry_hardirq_tail_exit();
+
+		if (state.exit_rcu)
+			ct_irq_exit_finish(ct_state);
+
+		if (!regs_irqs_disabled(regs))
+			lockdep_hardirqs_on(CALLER_ADDR0);
+		return;
+	}
+
 	if (!regs_irqs_disabled(regs)) {
 		/*
 		 * If RCU was not watching on entry this needs to be done
@@ -570,7 +621,8 @@ irqentry_exit_to_kernel_mode_after_preempt(struct pt_regs *regs, irqentry_state_
  *
  * This is the counterpart of irqentry_enter_from_kernel_mode() and combines
  * the calls to irqentry_exit_to_kernel_mode_preempt() and
- * irqentry_exit_to_kernel_mode_after_preempt().
+ * irqentry_exit_to_kernel_mode_after_preempt(). It also establishes the
+ * conditional hardirq return tail between those calls.
  *
  * The requirement for the CPU state is that it can schedule. After the function
  * returns the tracing, lockdep and RCU state transitions are completed and the
@@ -585,6 +637,7 @@ static __always_inline void irqentry_exit_to_kernel_mode(struct pt_regs *regs,
 	irqentry_exit_to_kernel_mode_preempt(regs, state);
 	instrumentation_end();
 
+	irqentry_hardirq_tail_enter(state);
 	irqentry_exit_to_kernel_mode_after_preempt(regs, state);
 }
 
diff --git a/kernel/softirq.c b/kernel/softirq.c
index 63427d29cb6d1..80d12deeb694a 100644
--- a/kernel/softirq.c
+++ b/kernel/softirq.c
@@ -833,6 +833,24 @@ irq_exit_wake_late_softirqs(unsigned int wake_flags)
 		irq_exit_wake_ksoftirqd();
 }
 
+/**
+ * irqentry_hardirq_tail_exit - Close work and remove return-tail state
+ *
+ * Run every instrumentable teardown operation, including the final worker
+ * closure, before removing the raw hardirq count and lockdep nesting.
+ */
+void noinstr irqentry_hardirq_tail_exit(void)
+{
+	bool do_sub;
+
+	instrumentation_begin();
+	do_sub = irqentry_hardirq_exit_prepare();
+	irq_exit_wake_late_softirqs(0);
+	instrumentation_end();
+
+	irqentry_hardirq_exit_finish(do_sub);
+}
+
 static __always_inline unsigned int __irq_exit_rcu(bool keep_hardirq_count)
 {
 	unsigned int wake_flags = 0;
-- 
2.39.5 (Apple Git-154)