[RFC PATCH 1/3] cputime: fix a account error of softirq

[RFC PATCH 1/3] cputime: fix a account error of softirq

[Alex Shi]

According the comments before this line:
 * ksoftirqd time do not get accounted in cpu_softirq_time.
And process in irqtime_account_irq()
I guess the original attempt is to account ksoftirqd into
system time instead of softirq time.

Signed-off-by: Alex Shi <alex.shi@linux.alibaba.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Wanpeng Li <wanpeng.li@hotmail.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
---
 kernel/sched/cputime.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c
index 2305ce89a26c..d78aee140957 100644
--- a/kernel/sched/cputime.c
+++ b/kernel/sched/cputime.c
@@ -378,7 +378,7 @@ static void irqtime_account_process_tick(struct task_struct *p, int user_tick,
 		 * So, we have to handle it separately here.
 		 * Also, p->stime needs to be updated for ksoftirqd.
 		 */
-		account_system_index_time(p, cputime, CPUTIME_SOFTIRQ);
+		account_system_index_time(p, cputime, CPUTIME_SYSTEM);
 	} else if (user_tick) {
 		account_user_time(p, cputime);
 	} else if (p == rq->idle) {
-- 
2.19.1.856.g8858448bb

[RFC PATCH 2/3] cputime: unify account_idle_ticks

[Alex Shi]

Check the 'current' task in account_idle_ticks is meaningless. So we
could remove irqtime_account_idle_ticks and unify this function.

Signed-off-by: Alex Shi <alex.shi@linux.alibaba.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Wanpeng Li <wanpeng.li@hotmail.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
---
 kernel/sched/cputime.c | 21 ++++-----------------
 1 file changed, 4 insertions(+), 17 deletions(-)

diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c
index d78aee140957..3bf94eb7b7c6 100644
--- a/kernel/sched/cputime.c
+++ b/kernel/sched/cputime.c
@@ -389,15 +389,7 @@ static void irqtime_account_process_tick(struct task_struct *p, int user_tick,
 		account_system_index_time(p, cputime, CPUTIME_SYSTEM);
 	}
 }
-
-static void irqtime_account_idle_ticks(int ticks)
-{
-	struct rq *rq = this_rq();
-
-	irqtime_account_process_tick(current, 0, rq, ticks);
-}
 #else /* CONFIG_IRQ_TIME_ACCOUNTING */
-static inline void irqtime_account_idle_ticks(int ticks) { }
 static inline void irqtime_account_process_tick(struct task_struct *p, int user_tick,
 						struct rq *rq, int nr_ticks) { }
 #endif /* CONFIG_IRQ_TIME_ACCOUNTING */
@@ -507,20 +499,15 @@ void account_process_tick(struct task_struct *p, int user_tick)
  */
 void account_idle_ticks(unsigned long ticks)
 {
-	u64 cputime, steal;
-
-	if (sched_clock_irqtime) {
-		irqtime_account_idle_ticks(ticks);
-		return;
-	}
+	u64 cputime, other;
 
 	cputime = ticks * TICK_NSEC;
-	steal = steal_account_process_time(ULONG_MAX);
+	other = account_other_time(ULONG_MAX);
 
-	if (steal >= cputime)
+	if (other >= cputime)
 		return;
 
-	cputime -= steal;
+	cputime -= other;
 	account_idle_time(cputime);
 }
 
-- 
2.19.1.856.g8858448bb

[RFC PATCH 3/3] cputime: unify account_process_tick func

[Alex Shi]

The irqtime_account_process_tick path was introduced for precise ns irq
time account from commit abb74cefa9c6 ("sched: Export ns irqtimes
through /proc/stat") while account_process_tick still use jiffes. This
divide isn't necessary especially now both paths are ns precison.

Move out the irqtime_account_process_tick func from IRQ_TIME_ACCOUNTING.
and combine the code for both *account_process_tick funcs for 2 paths.
Then remove the useless irqtime_account_process_tick().

Signed-off-by: Alex Shi <alex.shi@linux.alibaba.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Wanpeng Li <wanpeng.li@hotmail.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
---
 kernel/sched/cputime.c | 84 ++++++------------------------------------
 1 file changed, 12 insertions(+), 72 deletions(-)

diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c
index 3bf94eb7b7c6..3cc581409252 100644
--- a/kernel/sched/cputime.c
+++ b/kernel/sched/cputime.c
@@ -332,68 +332,6 @@ void thread_group_cputime(struct task_struct *tsk, struct task_cputime *times)
 	rcu_read_unlock();
 }
 
-#ifdef CONFIG_IRQ_TIME_ACCOUNTING
-/*
- * Account a tick to a process and cpustat
- * @p: the process that the CPU time gets accounted to
- * @user_tick: is the tick from userspace
- * @rq: the pointer to rq
- *
- * Tick demultiplexing follows the order
- * - pending hardirq update
- * - pending softirq update
- * - user_time
- * - idle_time
- * - system time
- *   - check for guest_time
- *   - else account as system_time
- *
- * Check for hardirq is done both for system and user time as there is
- * no timer going off while we are on hardirq and hence we may never get an
- * opportunity to update it solely in system time.
- * p->stime and friends are only updated on system time and not on irq
- * softirq as those do not count in task exec_runtime any more.
- */
-static void irqtime_account_process_tick(struct task_struct *p, int user_tick,
-					 struct rq *rq, int ticks)
-{
-	u64 other, cputime = TICK_NSEC * ticks;
-
-	/*
-	 * When returning from idle, many ticks can get accounted at
-	 * once, including some ticks of steal, irq, and softirq time.
-	 * Subtract those ticks from the amount of time accounted to
-	 * idle, or potentially user or system time. Due to rounding,
-	 * other time can exceed ticks occasionally.
-	 */
-	other = account_other_time(ULONG_MAX);
-	if (other >= cputime)
-		return;
-
-	cputime -= other;
-
-	if (this_cpu_ksoftirqd() == p) {
-		/*
-		 * ksoftirqd time do not get accounted in cpu_softirq_time.
-		 * So, we have to handle it separately here.
-		 * Also, p->stime needs to be updated for ksoftirqd.
-		 */
-		account_system_index_time(p, cputime, CPUTIME_SYSTEM);
-	} else if (user_tick) {
-		account_user_time(p, cputime);
-	} else if (p == rq->idle) {
-		account_idle_time(cputime);
-	} else if (p->flags & PF_VCPU) { /* System time or guest time */
-		account_guest_time(p, cputime);
-	} else {
-		account_system_index_time(p, cputime, CPUTIME_SYSTEM);
-	}
-}
-#else /* CONFIG_IRQ_TIME_ACCOUNTING */
-static inline void irqtime_account_process_tick(struct task_struct *p, int user_tick,
-						struct rq *rq, int nr_ticks) { }
-#endif /* CONFIG_IRQ_TIME_ACCOUNTING */
-
 /*
  * Use precise platform statistics if available:
  */
@@ -466,26 +404,28 @@ void thread_group_cputime_adjusted(struct task_struct *p, u64 *ut, u64 *st)
  */
 void account_process_tick(struct task_struct *p, int user_tick)
 {
-	u64 cputime, steal;
+	u64 cputime, other;
 	struct rq *rq = this_rq();
 
 	if (vtime_accounting_cpu_enabled())
 		return;
 
-	if (sched_clock_irqtime) {
-		irqtime_account_process_tick(p, user_tick, rq, 1);
-		return;
-	}
-
 	cputime = TICK_NSEC;
-	steal = steal_account_process_time(ULONG_MAX);
+	other = account_other_time(ULONG_MAX);
 
-	if (steal >= cputime)
+	if (other >= cputime)
 		return;
 
-	cputime -= steal;
+	cputime -= other;
 
-	if (user_tick)
+	if (this_cpu_ksoftirqd() == p)
+		/*
+		 * ksoftirqd time do not get accounted in cpu_softirq_time.
+		 * So, we have to handle it separately here.
+		 * Also, p->stime needs to be updated for ksoftirqd.
+		 */
+		account_system_index_time(p, cputime, CPUTIME_SYSTEM);
+	else if (user_tick)
 		account_user_time(p, cputime);
 	else if ((p != rq->idle) || (irq_count() != HARDIRQ_OFFSET))
 		account_system_time(p, HARDIRQ_OFFSET, cputime);
-- 
2.19.1.856.g8858448bb