[tip:timers/nohz] context_tracking: Inherit TIF_NOHZ through forks instead of context switches

[tip-bot for Frederic Weisbecker <tipbot@zytor.com>]

Commit-ID:  fafe870f31212a72f3c2d74e7b90e4ef39e83ee1
Gitweb:     http://git.kernel.org/tip/fafe870f31212a72f3c2d74e7b90e4ef39e83ee1
Author:     Frederic Weisbecker <fweisbec@gmail.com>
AuthorDate: Wed, 6 May 2015 18:04:24 +0200
Committer:  Ingo Molnar <mingo@kernel.org>
CommitDate: Thu, 7 May 2015 12:02:51 +0200

context_tracking: Inherit TIF_NOHZ through forks instead of context switches

TIF_NOHZ is used by context_tracking to force syscall slow-path
on every task in order to track userspace roundtrips. As such,
it must be set on all running tasks.

It's currently explicitly inherited through context switches.
There is no need to do it in this fast-path though. The flag
could simply be set once for all on all tasks, whether they are
running or not.

Lets do this by setting the flag for the init task on early boot,
and let it propagate through fork inheritance.

While at it, mark context_tracking_cpu_set() as init code, we
only need it at early boot time.

Suggested-by: Oleg Nesterov <oleg@redhat.com>
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Reviewed-by: Rik van Riel <riel@redhat.com>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Chris Metcalf <cmetcalf@ezchip.com>
Cc: Dave Jones <davej@redhat.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: Mike Galbraith <umgwanakikbuti@gmail.com>
Cc: Paul E . McKenney <paulmck@linux.vnet.ibm.com>
Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Rafael J . Wysocki <rafael.j.wysocki@intel.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/1430928266-24888-3-git-send-email-fweisbec@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
---
 include/linux/context_tracking.h | 10 ---------
 include/linux/sched.h            |  3 +++
 kernel/context_tracking.c        | 44 +++++++++++++++++-----------------------
 kernel/sched/core.c              |  1 -
 4 files changed, 22 insertions(+), 36 deletions(-)

diff --git a/include/linux/context_tracking.h b/include/linux/context_tracking.h
index 2821838..b96bd29 100644
--- a/include/linux/context_tracking.h
+++ b/include/linux/context_tracking.h
@@ -14,8 +14,6 @@ extern void context_tracking_enter(enum ctx_state state);
 extern void context_tracking_exit(enum ctx_state state);
 extern void context_tracking_user_enter(void);
 extern void context_tracking_user_exit(void);
-extern void __context_tracking_task_switch(struct task_struct *prev,
-					   struct task_struct *next);
 
 static inline void user_enter(void)
 {
@@ -51,19 +49,11 @@ static inline void exception_exit(enum ctx_state prev_ctx)
 	}
 }
 
-static inline void context_tracking_task_switch(struct task_struct *prev,
-						struct task_struct *next)
-{
-	if (context_tracking_is_enabled())
-		__context_tracking_task_switch(prev, next);
-}
 #else
 static inline void user_enter(void) { }
 static inline void user_exit(void) { }
 static inline enum ctx_state exception_enter(void) { return 0; }
 static inline void exception_exit(enum ctx_state prev_ctx) { }
-static inline void context_tracking_task_switch(struct task_struct *prev,
-						struct task_struct *next) { }
 #endif /* !CONFIG_CONTEXT_TRACKING */
 
 
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 26a2e61..185a750 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -2532,6 +2532,9 @@ static inline unsigned long wait_task_inactive(struct task_struct *p,
 }
 #endif
 
+#define tasklist_empty() \
+	list_empty(&init_task.tasks)
+
 #define next_task(p) \
 	list_entry_rcu((p)->tasks.next, struct task_struct, tasks)
 
diff --git a/kernel/context_tracking.c b/kernel/context_tracking.c
index 5b11a10..0a495ab 100644
--- a/kernel/context_tracking.c
+++ b/kernel/context_tracking.c
@@ -30,14 +30,6 @@ 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);
-	}
-}
-
 static bool context_tracking_recursion_enter(void)
 {
 	int recursion;
@@ -193,24 +185,26 @@ void context_tracking_user_exit(void)
 }
 NOKPROBE_SYMBOL(context_tracking_user_exit);
 
-/**
- * __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
- *
- * The context tracking uses the syscall slow path to implement its user-kernel
- * boundaries probes on syscalls. This way it doesn't impact the syscall fast
- * path on CPUs that don't do context tracking.
- *
- * But we need to clear the flag on the previous task because it may later
- * 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 __init context_tracking_cpu_set(int cpu)
 {
-	clear_tsk_thread_flag(prev, TIF_NOHZ);
-	set_tsk_thread_flag(next, TIF_NOHZ);
+	static __initdata bool initialized = false;
+
+	if (!per_cpu(context_tracking.active, cpu)) {
+		per_cpu(context_tracking.active, cpu) = true;
+		static_key_slow_inc(&context_tracking_enabled);
+	}
+
+	if (initialized)
+		return;
+
+	/*
+	 * Set TIF_NOHZ to init/0 and let it propagate to all tasks through fork
+	 * This assumes that init is the only task at this early boot stage.
+	 */
+	set_tsk_thread_flag(&init_task, TIF_NOHZ);
+	WARN_ON_ONCE(!tasklist_empty());
+
+	initialized = true;
 }
 
 #ifdef CONFIG_CONTEXT_TRACKING_FORCE
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index fe22f75..54f032c 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -2332,7 +2332,6 @@ context_switch(struct rq *rq, struct task_struct *prev,
 	 */
 	spin_release(&rq->lock.dep_map, 1, _THIS_IP_);
 
-	context_tracking_task_switch(prev, next);
 	/* Here we just switch the register state and the stack. */
 	switch_to(prev, next, prev);
 	barrier();