From: Rik van Riel <r...@redhat.com>

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

On CPUs that are nohz_full, people typically do not assign IRQs.
On the housekeeping CPU (when a system is booted up with nohz_full),
sampling should work ok to determine irq and softirq time use, but
that only covers the housekeeping CPU itself, not the other
non-nohz_full CPUs.

On CPUs that are nohz_idle (the typical way a distro kernel is
booted), irq time is not accounted at all while the CPU is idle,
due to the lack of timer ticks.

Remove the VTIME_GEN vtime irq time code. The next patch will
allow NO_HZ_FULL kernels to use the IRQ_TIME_ACCOUNTING code.

Signed-off-by: Rik van Riel <r...@redhat.com>
---
 include/linux/vtime.h  | 32 ++++++++++++++------------------
 kernel/sched/cputime.c | 26 +++++++++++++-------------
 2 files changed, 27 insertions(+), 31 deletions(-)

diff --git a/include/linux/vtime.h b/include/linux/vtime.h
index fa2196990f84..d1977d84ebdf 100644
--- a/include/linux/vtime.h
+++ b/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);
 
diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c
index 9bd2d4f42037..261c9002348a 100644
--- a/kernel/sched/cputime.c
+++ b/kernel/sched/cputime.c
@@ -115,6 +115,16 @@ static unsigned long irqtime_account_si_update(unsigned 
long max_jiffies)
 
 #define sched_clock_irqtime    (0)
 
+static unsigned long irqtime_account_hi_update(unsigned long dummy)
+{
+       return 0;
+}
+
+static unsigned long irqtime_account_si_update(unsigned long dummy)
+{
+       return 0;
+}
+
 #endif /* !CONFIG_IRQ_TIME_ACCOUNTING */
 
 static inline void task_group_account_field(struct task_struct *p, int index,
@@ -708,14 +718,14 @@ 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);
-       unsigned long delta_jiffies, steal_jiffies;
+       unsigned long delta_jiffies, other_jiffies;
 
        delta_jiffies = now - tsk->vtime_snap;
-       steal_jiffies = steal_account_process_tick(delta_jiffies);
+       other_jiffies = account_other_ticks(delta_jiffies);
        WARN_ON_ONCE(tsk->vtime_snap_whence == VTIME_INACTIVE);
        tsk->vtime_snap = now;
 
-       return jiffies_to_cputime(delta_jiffies - steal_jiffies);
+       return jiffies_to_cputime(delta_jiffies - other_jiffies);
 }
 
 static void __vtime_account_system(struct task_struct *tsk)
@@ -735,16 +745,6 @@ 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;
-- 
2.5.5

Reply via email to