Merge tag 'locking-urgent-2020-08-30' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull locking fixes from Thomas Gleixner:
 "A set of fixes for lockdep, tracing and RCU:

   - Prevent recursion by using raw_cpu_* operations

   - Fixup the interrupt state in the cpu idle code to be consistent

   - Push rcu_idle_enter/exit() invocations deeper into the idle path so
     that the lock operations are inside the RCU watching sections

   - Move trace_cpu_idle() into generic code so it's called before RCU
     goes idle.

   - Handle raw_local_irq* vs. local_irq* operations correctly

   - Move the tracepoints out from under the lockdep recursion handling
     which turned out to be fragile and inconsistent"

* tag 'locking-urgent-2020-08-30' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  lockdep,trace: Expose tracepoints
  lockdep: Only trace IRQ edges
  mips: Implement arch_irqs_disabled()
  arm64: Implement arch_irqs_disabled()
  nds32: Implement arch_irqs_disabled()
  locking/lockdep: Cleanup
  x86/entry: Remove unused THUNKs
  cpuidle: Move trace_cpu_idle() into generic code
  cpuidle: Make CPUIDLE_FLAG_TLB_FLUSHED generic
  sched,idle,rcu: Push rcu_idle deeper into the idle path
  cpuidle: Fixup IRQ state
  lockdep: Use raw_cpu_*() for per-cpu variables

2 files changed, 22 insertions, 21 deletions

diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c
index 2fad21d345b0..54b74fabf40c 100644
--- a/kernel/locking/lockdep.c
+++ b/kernel/locking/lockdep.c
@@ -3756,7 +3756,7 @@ void noinstr lockdep_hardirqs_on(unsigned long ip)
 
 skip_checks:
 	/* we'll do an OFF -> ON transition: */
-	this_cpu_write(hardirqs_enabled, 1);
+	__this_cpu_write(hardirqs_enabled, 1);
 	trace->hardirq_enable_ip = ip;
 	trace->hardirq_enable_event = ++trace->irq_events;
 	debug_atomic_inc(hardirqs_on_events);
@@ -3795,7 +3795,7 @@ void noinstr lockdep_hardirqs_off(unsigned long ip)
 		/*
 		 * We have done an ON -> OFF transition:
 		 */
-		this_cpu_write(hardirqs_enabled, 0);
+		__this_cpu_write(hardirqs_enabled, 0);
 		trace->hardirq_disable_ip = ip;
 		trace->hardirq_disable_event = ++trace->irq_events;
 		debug_atomic_inc(hardirqs_off_events);
@@ -4977,6 +4977,8 @@ void lock_acquire(struct lockdep_map *lock, unsigned int subclass,
 {
 	unsigned long flags;
 
+	trace_lock_acquire(lock, subclass, trylock, read, check, nest_lock, ip);
+
 	if (unlikely(current->lockdep_recursion)) {
 		/* XXX allow trylock from NMI ?!? */
 		if (lockdep_nmi() && !trylock) {
@@ -5001,7 +5003,6 @@ void lock_acquire(struct lockdep_map *lock, unsigned int subclass,
 	check_flags(flags);
 
 	current->lockdep_recursion++;
-	trace_lock_acquire(lock, subclass, trylock, read, check, nest_lock, ip);
 	__lock_acquire(lock, subclass, trylock, read, check,
 		       irqs_disabled_flags(flags), nest_lock, ip, 0, 0);
 	lockdep_recursion_finish();
@@ -5013,13 +5014,15 @@ void lock_release(struct lockdep_map *lock, unsigned long ip)
 {
 	unsigned long flags;
 
+	trace_lock_release(lock, ip);
+
 	if (unlikely(current->lockdep_recursion))
 		return;
 
 	raw_local_irq_save(flags);
 	check_flags(flags);
+
 	current->lockdep_recursion++;
-	trace_lock_release(lock, ip);
 	if (__lock_release(lock, ip))
 		check_chain_key(current);
 	lockdep_recursion_finish();
@@ -5205,8 +5208,6 @@ __lock_acquired(struct lockdep_map *lock, unsigned long ip)
 		hlock->holdtime_stamp = now;
 	}
 
-	trace_lock_acquired(lock, ip);
-
 	stats = get_lock_stats(hlock_class(hlock));
 	if (waittime) {
 		if (hlock->read)
@@ -5225,6 +5226,8 @@ void lock_contended(struct lockdep_map *lock, unsigned long ip)
 {
 	unsigned long flags;
 
+	trace_lock_acquired(lock, ip);
+
 	if (unlikely(!lock_stat || !debug_locks))
 		return;
 
@@ -5234,7 +5237,6 @@ void lock_contended(struct lockdep_map *lock, unsigned long ip)
 	raw_local_irq_save(flags);
 	check_flags(flags);
 	current->lockdep_recursion++;
-	trace_lock_contended(lock, ip);
 	__lock_contended(lock, ip);
 	lockdep_recursion_finish();
 	raw_local_irq_restore(flags);
@@ -5245,6 +5247,8 @@ void lock_acquired(struct lockdep_map *lock, unsigned long ip)
 {
 	unsigned long flags;
 
+	trace_lock_contended(lock, ip);
+
 	if (unlikely(!lock_stat || !debug_locks))
 		return;
 
diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c
index 6bf34986f45c..f324dc36fc43 100644
--- a/kernel/sched/idle.c
+++ b/kernel/sched/idle.c
@@ -54,17 +54,18 @@ __setup("hlt", cpu_idle_nopoll_setup);
 
 static noinline int __cpuidle cpu_idle_poll(void)
 {
+	trace_cpu_idle(0, smp_processor_id());
+	stop_critical_timings();
 	rcu_idle_enter();
-	trace_cpu_idle_rcuidle(0, smp_processor_id());
 	local_irq_enable();
-	stop_critical_timings();
 
 	while (!tif_need_resched() &&
-		(cpu_idle_force_poll || tick_check_broadcast_expired()))
+	       (cpu_idle_force_poll || tick_check_broadcast_expired()))
 		cpu_relax();
-	start_critical_timings();
-	trace_cpu_idle_rcuidle(PWR_EVENT_EXIT, smp_processor_id());
+
 	rcu_idle_exit();
+	start_critical_timings();
+	trace_cpu_idle(PWR_EVENT_EXIT, smp_processor_id());
 
 	return 1;
 }
@@ -90,9 +91,14 @@ void __cpuidle default_idle_call(void)
 	if (current_clr_polling_and_test()) {
 		local_irq_enable();
 	} else {
+
+		trace_cpu_idle(1, smp_processor_id());
 		stop_critical_timings();
+		rcu_idle_enter();
 		arch_cpu_idle();
+		rcu_idle_exit();
 		start_critical_timings();
+		trace_cpu_idle(PWR_EVENT_EXIT, smp_processor_id());
 	}
 }
 
@@ -158,7 +164,6 @@ static void cpuidle_idle_call(void)
 
 	if (cpuidle_not_available(drv, dev)) {
 		tick_nohz_idle_stop_tick();
-		rcu_idle_enter();
 
 		default_idle_call();
 		goto exit_idle;
@@ -178,21 +183,17 @@ static void cpuidle_idle_call(void)
 		u64 max_latency_ns;
 
 		if (idle_should_enter_s2idle()) {
-			rcu_idle_enter();
 
 			entered_state = call_cpuidle_s2idle(drv, dev);
 			if (entered_state > 0)
 				goto exit_idle;
 
-			rcu_idle_exit();
-
 			max_latency_ns = U64_MAX;
 		} else {
 			max_latency_ns = dev->forced_idle_latency_limit_ns;
 		}
 
 		tick_nohz_idle_stop_tick();
-		rcu_idle_enter();
 
 		next_state = cpuidle_find_deepest_state(drv, dev, max_latency_ns);
 		call_cpuidle(drv, dev, next_state);
@@ -209,8 +210,6 @@ static void cpuidle_idle_call(void)
 		else
 			tick_nohz_idle_retain_tick();
 
-		rcu_idle_enter();
-
 		entered_state = call_cpuidle(drv, dev, next_state);
 		/*
 		 * Give the governor an opportunity to reflect on the outcome
@@ -226,8 +225,6 @@ exit_idle:
 	 */
 	if (WARN_ON_ONCE(irqs_disabled()))
 		local_irq_enable();
-
-	rcu_idle_exit();
 }
 
 /*