sched/cputime: Replace VTIME_GEN irq time code with IRQ_TIME_ACCOUNTING code

The CONFIG_VIRT_CPU_ACCOUNTING_GEN irq time tracking code does not
appear to currently work right.

On CPUs without nohz_full=, only tick based irq time sampling is
done, which breaks down when dealing with a nohz_idle CPU.

On firewalls and similar systems, no ticks may happen on a CPU for a
while, and the irq time spent may never get accounted properly. This
can cause issues with capacity planning and power saving, which use
the CPU statistics as inputs in decision making.

Remove the VTIME_GEN vtime irq time code, and replace it with the
IRQ_TIME_ACCOUNTING code, when selected as a config option by the user.
Signed-off-by: NRik van Riel <riel@redhat.com>
Signed-off-by: NFrederic Weisbecker <fweisbec@gmail.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Radim Krcmar <rkrcmar@redhat.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Wanpeng Li <wanpeng.li@hotmail.com>
Link: http://lkml.kernel.org/r/1468421405-20056-3-git-send-email-fweisbec@gmail.comSigned-off-by: NIngo Molnar <mingo@kernel.org>

include/linux/vtime.h

@@ -14,6 +14,18 @@ struct task_struct;
  */
 #ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE
 static inline bool vtime_accounting_cpu_enabled(void) { return true; }
+
+#ifdef __ARCH_HAS_VTIME_ACCOUNT
+extern void vtime_account_irq_enter(struct task_struct *tsk);
+#else
+extern void vtime_common_account_irq_enter(struct task_struct *tsk);
+static inline void vtime_account_irq_enter(struct task_struct *tsk)
+{
+	if (vtime_accounting_cpu_enabled())
+		vtime_common_account_irq_enter(tsk);
+}
+#endif /* __ARCH_HAS_VTIME_ACCOUNT */
+
 #endif /* CONFIG_VIRT_CPU_ACCOUNTING_NATIVE */
 
 #ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN
@@ -64,17 +76,6 @@ extern void vtime_account_system(struct task_struct *tsk);
 extern void vtime_account_idle(struct task_struct *tsk);
 extern void vtime_account_user(struct task_struct *tsk);
 
-#ifdef __ARCH_HAS_VTIME_ACCOUNT
-extern void vtime_account_irq_enter(struct task_struct *tsk);
-#else
-extern void vtime_common_account_irq_enter(struct task_struct *tsk);
-static inline void vtime_account_irq_enter(struct task_struct *tsk)
-{
-	if (vtime_accounting_cpu_enabled())
-		vtime_common_account_irq_enter(tsk);
-}
-#endif /* __ARCH_HAS_VTIME_ACCOUNT */
-
 #else /* !CONFIG_VIRT_CPU_ACCOUNTING */
 
 static inline void vtime_task_switch(struct task_struct *prev) { }
@@ -85,13 +86,8 @@ static inline void vtime_account_irq_enter(struct task_struct *tsk) { }
 
 #ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN
 extern void arch_vtime_task_switch(struct task_struct *tsk);
-extern void vtime_gen_account_irq_exit(struct task_struct *tsk);
-
-static inline void vtime_account_irq_exit(struct task_struct *tsk)
-{
-	if (vtime_accounting_cpu_enabled())
-		vtime_gen_account_irq_exit(tsk);
-}
+static inline void vtime_account_irq_enter(struct task_struct *tsk) { }
+static inline void vtime_account_irq_exit(struct task_struct *tsk) { }
 
 extern void vtime_user_enter(struct task_struct *tsk);
 

init/Kconfig

@@ -375,9 +375,11 @@ config VIRT_CPU_ACCOUNTING_GEN
 
 	  If unsure, say N.
 
+endchoice
+
 config IRQ_TIME_ACCOUNTING
 	bool "Fine granularity task level IRQ time accounting"
-	depends on HAVE_IRQ_TIME_ACCOUNTING && !NO_HZ_FULL
+	depends on HAVE_IRQ_TIME_ACCOUNTING && !VIRT_CPU_ACCOUNTING_NATIVE
 	help
 	  Select this option to enable fine granularity task irq time
 	  accounting. This is done by reading a timestamp on each
@@ -386,8 +388,6 @@ config IRQ_TIME_ACCOUNTING
 
 	  If in doubt, say N here.
 
-endchoice
-
 config BSD_PROCESS_ACCT
 	bool "BSD Process Accounting"
 	depends on MULTIUSER

kernel/sched/cputime.c

@@ -711,14 +711,14 @@ static cputime_t vtime_delta(struct task_struct *tsk)
 static cputime_t get_vtime_delta(struct task_struct *tsk)
 {
 	unsigned long now = READ_ONCE(jiffies);
-	cputime_t delta, steal;
+	cputime_t delta, other;
 
 	delta = jiffies_to_cputime(now - tsk->vtime_snap);
-	steal = steal_account_process_time(delta);
+	other = account_other_time(delta);
 	WARN_ON_ONCE(tsk->vtime_snap_whence == VTIME_INACTIVE);
 	tsk->vtime_snap = now;
 
-	return delta - steal;
+	return delta - other;
 }
 
 static void __vtime_account_system(struct task_struct *tsk)
@@ -738,16 +738,6 @@ void vtime_account_system(struct task_struct *tsk)
 	write_seqcount_end(&tsk->vtime_seqcount);
 }
 
-void vtime_gen_account_irq_exit(struct task_struct *tsk)
-{
-	write_seqcount_begin(&tsk->vtime_seqcount);
-	if (vtime_delta(tsk))
-		__vtime_account_system(tsk);
-	if (context_tracking_in_user())
-		tsk->vtime_snap_whence = VTIME_USER;
-	write_seqcount_end(&tsk->vtime_seqcount);
-}
-
 void vtime_account_user(struct task_struct *tsk)
 {
 	cputime_t delta_cpu;