Merge branch 'timers-nohz-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull timers/nohz changes from Ingo Molnar:
 "It mostly contains fixes and full dynticks off-case optimizations, by
  Frederic Weisbecker"

* 'timers-nohz-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (24 commits)
  nohz: Include local CPU in full dynticks global kick
  nohz: Optimize full dynticks's sched hooks with static keys
  nohz: Optimize full dynticks state checks with static keys
  nohz: Rename a few state variables
  vtime: Always debug check snapshot source _before_ updating it
  vtime: Always scale generic vtime accounting results
  vtime: Optimize full dynticks accounting off case with static keys
  vtime: Describe overriden functions in dedicated arch headers
  m68k: hardirq_count() only need preempt_mask.h
  hardirq: Split preempt count mask definitions
  context_tracking: Split low level state headers
  vtime: Fix racy cputime delta update
  vtime: Remove a few unneeded generic vtime state checks
  context_tracking: User/kernel broundary cross trace events
  context_tracking: Optimize context switch off case with static keys
  context_tracking: Optimize guest APIs off case with static key
  context_tracking: Optimize main APIs off case with static key
  context_tracking: Ground setup for static key use
  context_tracking: Remove full dynticks' hacky dependency on wide context tracking
  nohz: Only enable context tracking on full dynticks CPUs
  ...

1 files changed, 71 insertions, 54 deletions

diff --git a/kernel/context_tracking.c b/kernel/context_tracking.c
index 383f8231e436..247091bf0587 100644
--- a/kernel/context_tracking.c
+++ b/kernel/context_tracking.c
@@ -20,22 +20,33 @@
 #include <linux/hardirq.h>
 #include <linux/export.h>
 
-DEFINE_PER_CPU(struct context_tracking, context_tracking) = {
-#ifdef CONFIG_CONTEXT_TRACKING_FORCE
-	.active = true,
-#endif
-};
+#define CREATE_TRACE_POINTS
+#include <trace/events/context_tracking.h>
+
+struct static_key context_tracking_enabled = STATIC_KEY_INIT_FALSE;
+EXPORT_SYMBOL_GPL(context_tracking_enabled);
+
+DEFINE_PER_CPU(struct context_tracking, context_tracking);
+EXPORT_SYMBOL_GPL(context_tracking);
+
+void context_tracking_cpu_set(int cpu)
+{
+	if (!per_cpu(context_tracking.active, cpu)) {
+		per_cpu(context_tracking.active, cpu) = true;
+		static_key_slow_inc(&context_tracking_enabled);
+	}
+}
 
 /**
- * user_enter - Inform the context tracking that the CPU is going to
- *              enter userspace mode.
+ * context_tracking_user_enter - Inform the context tracking that the CPU is going to
+ *                               enter userspace mode.
  *
  * This function must be called right before we switch from the kernel
  * to userspace, when it's guaranteed the remaining kernel instructions
  * to execute won't use any RCU read side critical section because this
  * function sets RCU in extended quiescent state.
  */
-void user_enter(void)
+void context_tracking_user_enter(void)
 {
 	unsigned long flags;
 
@@ -54,17 +65,32 @@ void user_enter(void)
 	WARN_ON_ONCE(!current->mm);
 
 	local_irq_save(flags);
-	if (__this_cpu_read(context_tracking.active) &&
-	    __this_cpu_read(context_tracking.state) != IN_USER) {
+	if ( __this_cpu_read(context_tracking.state) != IN_USER) {
+		if (__this_cpu_read(context_tracking.active)) {
+			trace_user_enter(0);
+			/*
+			 * At this stage, only low level arch entry code remains and
+			 * then we'll run in userspace. We can assume there won't be
+			 * any RCU read-side critical section until the next call to
+			 * user_exit() or rcu_irq_enter(). Let's remove RCU's dependency
+			 * on the tick.
+			 */
+			vtime_user_enter(current);
+			rcu_user_enter();
+		}
 		/*
-		 * At this stage, only low level arch entry code remains and
-		 * then we'll run in userspace. We can assume there won't be
-		 * any RCU read-side critical section until the next call to
-		 * user_exit() or rcu_irq_enter(). Let's remove RCU's dependency
-		 * on the tick.
+		 * Even if context tracking is disabled on this CPU, because it's outside
+		 * the full dynticks mask for example, we still have to keep track of the
+		 * context transitions and states to prevent inconsistency on those of
+		 * other CPUs.
+		 * If a task triggers an exception in userspace, sleep on the exception
+		 * handler and then migrate to another CPU, that new CPU must know where
+		 * the exception returns by the time we call exception_exit().
+		 * This information can only be provided by the previous CPU when it called
+		 * exception_enter().
+		 * OTOH we can spare the calls to vtime and RCU when context_tracking.active
+		 * is false because we know that CPU is not tickless.
 		 */
-		vtime_user_enter(current);
-		rcu_user_enter();
 		__this_cpu_write(context_tracking.state, IN_USER);
 	}
 	local_irq_restore(flags);
@@ -87,10 +113,9 @@ void user_enter(void)
  */
 void __sched notrace preempt_schedule_context(void)
 {
-	struct thread_info *ti = current_thread_info();
 	enum ctx_state prev_ctx;
 
-	if (likely(ti->preempt_count || irqs_disabled()))
+	if (likely(!preemptible()))
 		return;
 
 	/*
@@ -112,8 +137,8 @@ EXPORT_SYMBOL_GPL(preempt_schedule_context);
 #endif /* CONFIG_PREEMPT */
 
 /**
- * user_exit - Inform the context tracking that the CPU is
- *             exiting userspace mode and entering the kernel.
+ * context_tracking_user_exit - Inform the context tracking that the CPU is
+ *                              exiting userspace mode and entering the kernel.
  *
  * This function must be called after we entered the kernel from userspace
  * before any use of RCU read side critical section. This potentially include
@@ -122,7 +147,7 @@ EXPORT_SYMBOL_GPL(preempt_schedule_context);
  * This call supports re-entrancy. This way it can be called from any exception
  * handler without needing to know if we came from userspace or not.
  */
-void user_exit(void)
+void context_tracking_user_exit(void)
 {
 	unsigned long flags;
 
@@ -131,38 +156,22 @@ void user_exit(void)
 
 	local_irq_save(flags);
 	if (__this_cpu_read(context_tracking.state) == IN_USER) {
-		/*
-		 * We are going to run code that may use RCU. Inform
-		 * RCU core about that (ie: we may need the tick again).
-		 */
-		rcu_user_exit();
-		vtime_user_exit(current);
+		if (__this_cpu_read(context_tracking.active)) {
+			/*
+			 * We are going to run code that may use RCU. Inform
+			 * RCU core about that (ie: we may need the tick again).
+			 */
+			rcu_user_exit();
+			vtime_user_exit(current);
+			trace_user_exit(0);
+		}
 		__this_cpu_write(context_tracking.state, IN_KERNEL);
 	}
 	local_irq_restore(flags);
 }
 
-void guest_enter(void)
-{
-	if (vtime_accounting_enabled())
-		vtime_guest_enter(current);
-	else
-		__guest_enter();
-}
-EXPORT_SYMBOL_GPL(guest_enter);
-
-void guest_exit(void)
-{
-	if (vtime_accounting_enabled())
-		vtime_guest_exit(current);
-	else
-		__guest_exit();
-}
-EXPORT_SYMBOL_GPL(guest_exit);
-
-
 /**
- * context_tracking_task_switch - context switch the syscall callbacks
+ * __context_tracking_task_switch - context switch the syscall callbacks
  * @prev: the task that is being switched out
  * @next: the task that is being switched in
  *
@@ -174,11 +183,19 @@ EXPORT_SYMBOL_GPL(guest_exit);
  * migrate to some CPU that doesn't do the context tracking. As such the TIF
  * flag may not be desired there.
  */
-void context_tracking_task_switch(struct task_struct *prev,
-			     struct task_struct *next)
+void __context_tracking_task_switch(struct task_struct *prev,
+				    struct task_struct *next)
 {
-	if (__this_cpu_read(context_tracking.active)) {
-		clear_tsk_thread_flag(prev, TIF_NOHZ);
-		set_tsk_thread_flag(next, TIF_NOHZ);
-	}
+	clear_tsk_thread_flag(prev, TIF_NOHZ);
+	set_tsk_thread_flag(next, TIF_NOHZ);
 }
+
+#ifdef CONFIG_CONTEXT_TRACKING_FORCE
+void __init context_tracking_init(void)
+{
+	int cpu;
+
+	for_each_possible_cpu(cpu)
+		context_tracking_cpu_set(cpu);
+}
+#endif