delayacct: track delays from IRQ/SOFTIRQ

Delay accounting does not track the delay of IRQ/SOFTIRQ. While
IRQ/SOFTIRQ could have obvious impact on some workloads productivity, such
as when workloads are running on system which is busy handling network
IRQ/SOFTIRQ.

Get the delay of IRQ/SOFTIRQ could help users to reduce such delay. Such
as setting interrupt affinity or task affinity, using kernel thread for
NAPI etc. This is inspired by "sched/psi: Add PSI_IRQ to track
IRQ/SOFTIRQ pressure"[1]. Also fix some code indent problems of older
code.

And update tools/accounting/getdelays.c:
/ # ./getdelays -p 156 -di
print delayacct stats ON
printing IO accounting
PID 156

CPU count real total virtual total delay total delay average
15 15836008 16218149 275700790 18.380ms
IO count delay total delay average
0 0 0.000ms
SWAP count delay total delay average
0 0 0.000ms
RECLAIM count delay total delay average
0 0 0.000ms
THRASHING count delay total delay average
0 0 0.000ms
COMPACT count delay total delay average
0 0 0.000ms
WPCOPY count delay total delay average
36 7586118 0.211ms
IRQ count delay total delay average
42 929161 0.022ms

[1] commit 52b1364ba0b1("sched/psi: Add PSI_IRQ to track IRQ/SOFTIRQ pressure")

Link: https://lkml.kernel.org/r/[e-mail]
Signed-off-by: Yang Yang <[e-mail]>
Cc: Jiang Xuexin <[e-mail]>
Cc: wangyong <[e-mail]>
Cc: junhua huang <[e-mail]>
Cc: Balbir Singh <[e-mail]>
Cc: Ingo Molnar <[e-mail]>
Cc: Jonathan Corbet <[e-mail]>
Cc: Juri Lelli <[e-mail]>
Cc: Peter Zijlstra <[e-mail]>
Signed-off-by: Andrew Morton <[e-mail]>

Documentation/accounting/delay-accounting.rst

···
 e) thrashing
 f) direct compact
 g) write-protect copy
+h) IRQ/SOFTIRQ
 
 and makes these statistics available to userspace through
 the taskstats interface.
···
 for a description of the fields pertaining to delay accounting.
 It will generally be in the form of counters returning the cumulative
 delay seen for cpu, sync block I/O, swapin, memory reclaim, thrash page
-cache, direct compact, write-protect copy etc.
+cache, direct compact, write-protect copy, IRQ/SOFTIRQ etc.
 
 Taking the difference of two successive readings of a given
 counter (say cpu_delay_total) for a task will give the delay
···
                        0              0          0.000ms
 	COMPACT         count    delay total  delay average
                        0              0          0.000ms
-   WPCOPY          count    delay total  delay average
+	WPCOPY          count    delay total  delay average
+                       0              0          0.000ms
+	IRQ             count    delay total  delay average
                        0              0          0.000ms
 
 Get IO accounting for pid 1, it works only with -p::

include/linux/delayacct.h

···
 	u64 wpcopy_start;
 	u64 wpcopy_delay;	/* wait for write-protect copy */
 
+	u64 irq_delay;	/* wait for IRQ/SOFTIRQ */
+
 	u32 freepages_count;	/* total count of memory reclaim */
 	u32 thrashing_count;	/* total count of thrash waits */
 	u32 compact_count;	/* total count of memory compact */
 	u32 wpcopy_count;	/* total count of write-protect copy */
+	u32 irq_count;	/* total count of IRQ/SOFTIRQ */
 };
 #endif
 
···
 extern void __delayacct_compact_end(void);
 extern void __delayacct_wpcopy_start(void);
 extern void __delayacct_wpcopy_end(void);
+extern void __delayacct_irq(struct task_struct *task, u32 delta);
 
 static inline void delayacct_tsk_init(struct task_struct *tsk)
 {
···
 		__delayacct_wpcopy_end();
 }
 
+static inline void delayacct_irq(struct task_struct *task, u32 delta)
+{
+	if (!static_branch_unlikely(&delayacct_key))
+		return;
+
+	if (task->delays)
+		__delayacct_irq(task, delta);
+}
+
 #else
 static inline void delayacct_init(void)
 {}
···
 static inline void delayacct_wpcopy_start(void)
 {}
 static inline void delayacct_wpcopy_end(void)
+{}
+static inline void delayacct_irq(struct task_struct *task, u32 delta)
 {}
 
 #endif /* CONFIG_TASK_DELAY_ACCT */

include/uapi/linux/taskstats.h

···
  */
 
 
-#define TASKSTATS_VERSION	13
+#define TASKSTATS_VERSION	14
 #define TS_COMM_LEN		32	/* should be >= TASK_COMM_LEN
 					 * in linux/sched.h */
 
···
 	/* v13: Delay waiting for write-protect copy */
 	__u64    wpcopy_count;
 	__u64    wpcopy_delay_total;
+
+	/* v14: Delay waiting for IRQ/SOFTIRQ */
+	__u64    irq_count;
+	__u64    irq_delay_total;
 };
 
 

kernel/delayacct.c

···
 	d->compact_delay_total = (tmp < d->compact_delay_total) ? 0 : tmp;
 	tmp = d->wpcopy_delay_total + tsk->delays->wpcopy_delay;
 	d->wpcopy_delay_total = (tmp < d->wpcopy_delay_total) ? 0 : tmp;
+	tmp = d->irq_delay_total + tsk->delays->irq_delay;
+	d->irq_delay_total = (tmp < d->irq_delay_total) ? 0 : tmp;
 	d->blkio_count += tsk->delays->blkio_count;
 	d->swapin_count += tsk->delays->swapin_count;
 	d->freepages_count += tsk->delays->freepages_count;
 	d->thrashing_count += tsk->delays->thrashing_count;
 	d->compact_count += tsk->delays->compact_count;
 	d->wpcopy_count += tsk->delays->wpcopy_count;
+	d->irq_count += tsk->delays->irq_count;
 	raw_spin_unlock_irqrestore(&tsk->delays->lock, flags);
 
 	return 0;
···
 		      &current->delays->wpcopy_delay,
 		      &current->delays->wpcopy_count);
 }
+
+void __delayacct_irq(struct task_struct *task, u32 delta)
+{
+	unsigned long flags;
+
+	raw_spin_lock_irqsave(&task->delays->lock, flags);
+	task->delays->irq_delay += delta;
+	task->delays->irq_count++;
+	raw_spin_unlock_irqrestore(&task->delays->lock, flags);
+}
+

kernel/sched/core.c

···
 	rq->prev_irq_time += irq_delta;
 	delta -= irq_delta;
 	psi_account_irqtime(rq->curr, irq_delta);
+	delayacct_irq(rq->curr, irq_delta);
 #endif
 #ifdef CONFIG_PARAVIRT_TIME_ACCOUNTING
 	if (static_key_false((&paravirt_steal_rq_enabled))) {

tools/accounting/getdelays.c

···
 	printf("\n\nCPU   %15s%15s%15s%15s%15s\n"
 	       "      %15llu%15llu%15llu%15llu%15.3fms\n"
 	       "IO    %15s%15s%15s\n"
-          "      %15llu%15llu%15.3fms\n"
+	       "      %15llu%15llu%15.3fms\n"
 	       "SWAP  %15s%15s%15s\n"
-          "      %15llu%15llu%15.3fms\n"
+	       "      %15llu%15llu%15.3fms\n"
 	       "RECLAIM  %12s%15s%15s\n"
-          "      %15llu%15llu%15.3fms\n"
+	       "      %15llu%15llu%15.3fms\n"
 	       "THRASHING%12s%15s%15s\n"
-          "      %15llu%15llu%15.3fms\n"
+	       "      %15llu%15llu%15.3fms\n"
 	       "COMPACT  %12s%15s%15s\n"
-          "      %15llu%15llu%15.3fms\n"
+	       "      %15llu%15llu%15.3fms\n"
 	       "WPCOPY   %12s%15s%15s\n"
-          "      %15llu%15llu%15.3fms\n",
+	       "      %15llu%15llu%15.3fms\n"
+	       "IRQ   %15s%15s%15s\n"
+	       "      %15llu%15llu%15.3fms\n",
 	       "count", "real total", "virtual total",
 	       "delay total", "delay average",
 	       (unsigned long long)t->cpu_count,
···
 	       "count", "delay total", "delay average",
 	       (unsigned long long)t->blkio_count,
 	       (unsigned long long)t->blkio_delay_total,
-          average_ms((double)t->blkio_delay_total, t->blkio_count),
+	       average_ms((double)t->blkio_delay_total, t->blkio_count),
 	       "count", "delay total", "delay average",
 	       (unsigned long long)t->swapin_count,
 	       (unsigned long long)t->swapin_delay_total,
-          average_ms((double)t->swapin_delay_total, t->swapin_count),
+	       average_ms((double)t->swapin_delay_total, t->swapin_count),
 	       "count", "delay total", "delay average",
 	       (unsigned long long)t->freepages_count,
 	       (unsigned long long)t->freepages_delay_total,
-          average_ms((double)t->freepages_delay_total, t->freepages_count),
+	       average_ms((double)t->freepages_delay_total, t->freepages_count),
 	       "count", "delay total", "delay average",
 	       (unsigned long long)t->thrashing_count,
 	       (unsigned long long)t->thrashing_delay_total,
-          average_ms((double)t->thrashing_delay_total, t->thrashing_count),
+	       average_ms((double)t->thrashing_delay_total, t->thrashing_count),
 	       "count", "delay total", "delay average",
 	       (unsigned long long)t->compact_count,
 	       (unsigned long long)t->compact_delay_total,
-          average_ms((double)t->compact_delay_total, t->compact_count),
+	       average_ms((double)t->compact_delay_total, t->compact_count),
 	       "count", "delay total", "delay average",
 	       (unsigned long long)t->wpcopy_count,
 	       (unsigned long long)t->wpcopy_delay_total,
-          average_ms((double)t->wpcopy_delay_total, t->wpcopy_count));
+	       average_ms((double)t->wpcopy_delay_total, t->wpcopy_count),
+	       "count", "delay total", "delay average",
+	       (unsigned long long)t->irq_count,
+	       (unsigned long long)t->irq_delay_total,
+	       average_ms((double)t->irq_delay_total, t->irq_count));
 }
 
 static void task_context_switch_counts(struct taskstats *t)