lockdep: Add lockdep_cleanup_dead_cpu()

Add a function to check that an offline CPU has left the tracing
infrastructure in a sane state.

Commit 9bb69ba4c177 ("ACPI: processor_idle: use raw_safe_halt() in
acpi_idle_play_dead()") fixed an issue where the acpi_idle_play_dead()
function called safe_halt() instead of raw_safe_halt(), which had the
side-effect of setting the hardirqs_enabled flag for the offline CPU.

On x86 this triggered warnings from lockdep_assert_irqs_disabled() when
the CPU was brought back online again later. These warnings were too
early for the exception to be handled correctly, leading to a
triple-fault.

Add lockdep_cleanup_dead_cpu() to check for this kind of failure mode,
print the events leading up to it, and correct it so that the CPU can
come online again correctly. Re-introducing the original bug now merely
results in this warning instead:

[ 61.556652] smpboot: CPU 1 is now offline
[ 61.556769] CPU 1 left hardirqs enabled!
[ 61.556915] irq event stamp: 128149
[ 61.556965] hardirqs last enabled at (128149): [<ffffffff81720a36>] acpi_idle_play_dead+0x46/0x70
[ 61.557055] hardirqs last disabled at (128148): [<ffffffff81124d50>] do_idle+0x90/0xe0
[ 61.557117] softirqs last enabled at (128078): [<ffffffff81cec74c>] __do_softirq+0x31c/0x423
[ 61.557199] softirqs last disabled at (128065): [<ffffffff810baae1>] __irq_exit_rcu+0x91/0x100

[boqun: Capitalize the title and reword the message a bit]

Signed-off-by: David Woodhouse <[e-mail]>
Reviewed-by: Thomas Gleixner <[e-mail]>
Signed-off-by: Boqun Feng <[e-mail]>
Link: https://lore.kernel.org/r/[e-mail]

include/linux/irqflags.h

···
 #include <asm/irqflags.h>
 #include <asm/percpu.h>
 
+struct task_struct;
+
 /* Currently lockdep_softirqs_on/off is used only by lockdep */
 #ifdef CONFIG_PROVE_LOCKING
   extern void lockdep_softirqs_on(unsigned long ip);
···
   extern void lockdep_hardirqs_on_prepare(void);
   extern void lockdep_hardirqs_on(unsigned long ip);
   extern void lockdep_hardirqs_off(unsigned long ip);
+  extern void lockdep_cleanup_dead_cpu(unsigned int cpu,
+				       struct task_struct *idle);
 #else
   static inline void lockdep_softirqs_on(unsigned long ip) { }
   static inline void lockdep_softirqs_off(unsigned long ip) { }
   static inline void lockdep_hardirqs_on_prepare(void) { }
   static inline void lockdep_hardirqs_on(unsigned long ip) { }
   static inline void lockdep_hardirqs_off(unsigned long ip) { }
+  static inline void lockdep_cleanup_dead_cpu(unsigned int cpu,
+					      struct task_struct *idle) {}
 #endif
 
 #ifdef CONFIG_TRACE_IRQFLAGS

kernel/cpu.c

···
 
 	cpuhp_bp_sync_dead(cpu);
 
+	lockdep_cleanup_dead_cpu(cpu, idle_thread_get(cpu));
 	tick_cleanup_dead_cpu(cpu);
 
 	/*

kernel/locking/lockdep.c

···
 		debug_atomic_inc(redundant_softirqs_off);
 }
 
+/**
+ * lockdep_cleanup_dead_cpu - Ensure CPU lockdep state is cleanly stopped
+ *
+ * @cpu: index of offlined CPU
+ * @idle: task pointer for offlined CPU's idle thread
+ *
+ * Invoked after the CPU is dead. Ensures that the tracing infrastructure
+ * is left in a suitable state for the CPU to be subsequently brought
+ * online again.
+ */
+void lockdep_cleanup_dead_cpu(unsigned int cpu, struct task_struct *idle)
+{
+	if (unlikely(!debug_locks))
+		return;
+
+	if (unlikely(per_cpu(hardirqs_enabled, cpu))) {
+		pr_warn("CPU %u left hardirqs enabled!", cpu);
+		if (idle)
+			print_irqtrace_events(idle);
+		/* Clean it up for when the CPU comes online again. */
+		per_cpu(hardirqs_enabled, cpu) = 0;
+	}
+}
+
 static int
 mark_usage(struct task_struct *curr, struct held_lock *hlock, int check)
 {