[RFC PATCH v2 11/13] arm64: Use the pre-counted hardirq lifecycle

[Karl Mehltretter <kmehltretter@gmail.com>]

Ordinary EL0 and EL1 interrupt paths establish generic entry state before
irq_enter_rcu() adds HARDIRQ_OFFSET and lockdep nesting. Callbacks in that
early window are therefore not classified as hardirq work. Their exit paths
also drop the classification before function-graph return callbacks and the
kernel return tail have completed.

After the EL1 pseudo-NMI decision, enter ordinary interrupts through
irqentry_hardirq_enter(). Finish the staged count update and delayed timer
and accounting work with irq_enter_rcu_preempt_counted(). Use the retained
exit preparation followed immediately by conditional raw count and lockdep
teardown.

For kernel returns, preserve the existing per-CPU register adjustment, then
stage hardirq return-tail classification before MTE exit tracing. Keep the
pseudo-NMI lifecycle unchanged.

The noinstr path also depends on the raw preempt-count and
__kern_my_cpu_offset() inlining prerequisites earlier in this series.

Link: https://lore.kernel.org/all/c3a90368dd6c096af9d918e036a27728696fb8a4.1786603168.git.hongyan.xia@transsion.com/
Link: https://lore.kernel.org/r/20260918161407.2300-12-will@kernel.org
Assisted-by: LLM
---
 arch/arm64/kernel/entry-common.c | 28 ++++++++++++++++++++++------
 1 file changed, 22 insertions(+), 6 deletions(-)

diff --git a/arch/arm64/kernel/entry-common.c b/arch/arm64/kernel/entry-common.c
index 003f84109a913..d70cffffe71c6 100644
--- a/arch/arm64/kernel/entry-common.c
+++ b/arch/arm64/kernel/entry-common.c
@@ -94,6 +94,8 @@ static void noinstr __arm64_exit_to_kernel_mode(struct pt_regs *regs,
 {
 	local_daif_mask();
 	irqentry_exit_pcpu_adjust(regs);
+	/* arm64 uses the split exit API, so enter the tail before MTE tracing. */
+	irqentry_hardirq_tail_enter(&state);
 	mte_check_tfsr_exit();
 	irqentry_exit_to_kernel_mode_after_preempt(regs, state);
 }
@@ -560,13 +562,19 @@ static __always_inline void __el1_pnmi(struct pt_regs *regs,
 static __always_inline void __el1_irq(struct pt_regs *regs,
 				      void (*handler)(struct pt_regs *))
 {
+	struct irqentry_hardirq_cookie cookie;
 	irqentry_state_t state;
+	bool do_sub;
 
-	state = arm64_enter_from_kernel_mode(regs);
+	state = irqentry_hardirq_enter(regs);
+	cookie = irqentry_hardirq_count_state(state);
+	mte_check_tfsr_entry();
+	mte_disable_tco_entry(current);
 
-	irq_enter_rcu();
+	irq_enter_rcu_preempt_counted(cookie);
 	do_interrupt_handler(regs, handler);
-	irq_exit_rcu();
+	do_sub = irq_exit_rcu_preempt_counted_prepare(cookie);
+	irqentry_hardirq_exit_finish(do_sub);
 
 	arm64_exit_to_kernel_mode_preempt(regs, state);
 }
@@ -877,16 +885,24 @@ asmlinkage void noinstr el0t_64_sync_handler(struct pt_regs *regs)
 static void noinstr el0_interrupt(struct pt_regs *regs,
 				  void (*handler)(struct pt_regs *))
 {
-	arm64_enter_from_user_mode(regs);
+	struct irqentry_hardirq_cookie cookie;
+	irqentry_state_t state;
+	bool do_sub;
+
+	state = irqentry_hardirq_enter(regs);
+	cookie = irqentry_hardirq_count_state(state);
+	mte_disable_tco_entry(current);
+	sme_enter_from_user_mode();
 
 	write_sysreg(DAIF_PROCCTX_NOIRQ, daif);
 
 	if (regs->pc & BIT(55))
 		arm64_apply_bp_hardening();
 
-	irq_enter_rcu();
+	irq_enter_rcu_preempt_counted(cookie);
 	do_interrupt_handler(regs, handler);
-	irq_exit_rcu();
+	do_sub = irq_exit_rcu_preempt_counted_prepare(cookie);
+	irqentry_hardirq_exit_finish(do_sub);
 
 	arm64_exit_to_user_mode(regs);
 }
-- 
2.39.5 (Apple Git-154)