[RFC][PATCH 2/2] softirq: defer softirq processing to ksoftirqd if CPU is busy with RT

[John Stultz]

From: Pavankumar Kondeti <pkondeti@xxxxxxxxxxxxxx>

Defer the softirq processing to ksoftirqd if a RT task is
running or queued on the current CPU. This complements the RT
task placement algorithm which tries to find a CPU that is not
currently busy with softirqs.

Currently NET_TX, NET_RX, BLOCK and TASKLET softirqs are only
deferred as they can potentially run for long time.

Additionally, this patch stubs out ksoftirqd_running() logic,
in the CONFIG_RT_SOFTIRQ_OPTIMIZATION case, as deferring
potentially long-running softirqs will cause the logic to not
process shorter-running softirqs immediately. By stubbing it out
the potentially long running softirqs are deferred, but the
shorter running ones can still run immediately.

This patch includes folded-in fixes by:
  Lingutla Chandrasekhar <clingutla@xxxxxxxxxxxxxx>
  Satya Durga Srinivasu Prabhala <satyap@xxxxxxxxxxxxxx>
  J. Avila <elavila@xxxxxxxxxx>

Cc: John Dias <joaodias@xxxxxxxxxx>
Cc: Connor O'Brien <connoro@xxxxxxxxxx>
Cc: Rick Yiu <rickyiu@xxxxxxxxxx>
Cc: John Kacur <jkacur@xxxxxxxxxx>
Cc: Qais Yousef <qais.yousef@xxxxxxx>
Cc: Chris Redpath <chris.redpath@xxxxxxx>,
Cc: Abhijeet Dharmapurikar <adharmap@xxxxxxxxxxx>
Cc: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
Cc: Ingo Molnar <mingo@xxxxxxxxxx>
Cc: Juri Lelli <juri.lelli@xxxxxxxxxx>
Cc: Vincent Guittot <vincent.guittot@xxxxxxxxxx>
Cc: Dietmar Eggemann <dietmar.eggemann@xxxxxxx>
Cc: Steven Rostedt <rostedt@xxxxxxxxxxx>
Cc: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
Cc: kernel-team@xxxxxxxxxxx
Signed-off-by: Pavankumar Kondeti <pkondeti@xxxxxxxxxxxxxx>
[satyap@xxxxxxxxxxxxxx: trivial merge conflict resolution.]
Signed-off-by: Satya Durga Srinivasu Prabhala <satyap@xxxxxxxxxxxxxx>
[elavila: Port to mainline, squash with bugfix]
Signed-off-by: J. Avila <elavila@xxxxxxxxxx>
[jstultz: Rebase to linus/HEAD, minor rearranging of code,
 included bug fix Reported-by: Qais Yousef <qais.yousef@xxxxxxx> ]
Signed-off-by: John Stultz <jstultz@xxxxxxxxxx>
---
 include/linux/sched.h | 10 ++++++++++
 kernel/sched/cpupri.c | 13 +++++++++++++
 kernel/softirq.c      | 25 +++++++++++++++++++++++--
 3 files changed, 46 insertions(+), 2 deletions(-)

diff --git a/include/linux/sched.h b/include/linux/sched.h
index c46f3a63b758..4a12e638b694 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1814,6 +1814,16 @@ current_restore_flags(unsigned long orig_flags, unsigned long flags)
 
 extern int cpuset_cpumask_can_shrink(const struct cpumask *cur, const struct cpumask *trial);
 extern int task_can_attach(struct task_struct *p, const struct cpumask *cs_cpus_allowed);
+
+#ifdef CONFIG_RT_SOFTIRQ_OPTIMIZATION
+extern bool cpupri_check_rt(void);
+#else
+static inline bool cpupri_check_rt(void)
+{
+	return false;
+}
+#endif
+
 #ifdef CONFIG_SMP
 extern void do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask);
 extern int set_cpus_allowed_ptr(struct task_struct *p, const struct cpumask *new_mask);
diff --git a/kernel/sched/cpupri.c b/kernel/sched/cpupri.c
index fa9ce9d83683..18dc75d16951 100644
--- a/kernel/sched/cpupri.c
+++ b/kernel/sched/cpupri.c
@@ -64,6 +64,19 @@ static int convert_prio(int prio)
 	return cpupri;
 }
 
+#ifdef CONFIG_RT_SOFTIRQ_OPTIMIZATION
+/*
+ * cpupri_check_rt - check if CPU has a RT task
+ * should be called from rcu-sched read section.
+ */
+bool cpupri_check_rt(void)
+{
+	int cpu = raw_smp_processor_id();
+
+	return cpu_rq(cpu)->rd->cpupri.cpu_to_pri[cpu] > CPUPRI_NORMAL;
+}
+#endif
+
 static inline int __cpupri_find(struct cpupri *cp, struct task_struct *p,
 				struct cpumask *lowest_mask, int idx)
 {
diff --git a/kernel/softirq.c b/kernel/softirq.c
index 92fa82400a80..b4f879cd421d 100644
--- a/kernel/softirq.c
+++ b/kernel/softirq.c
@@ -87,6 +87,7 @@ static void wakeup_softirqd(void)
 		wake_up_process(tsk);
 }
 
+#ifndef CONFIG_RT_SOFTIRQ_OPTIMIZATION
 /*
  * If ksoftirqd is scheduled, we do not want to process pending softirqs
  * right now. Let ksoftirqd handle this at its own rate, to get fairness,
@@ -101,6 +102,9 @@ static bool ksoftirqd_running(unsigned long pending)
 		return false;
 	return tsk && task_is_running(tsk) && !__kthread_should_park(tsk);
 }
+#else
+#define ksoftirqd_running(pending) (false)
+#endif /* CONFIG_RT_SOFTIRQ_OPTIMIZATION */
 
 #ifdef CONFIG_TRACE_IRQFLAGS
 DEFINE_PER_CPU(int, hardirqs_enabled);
@@ -532,6 +536,17 @@ static inline bool lockdep_softirq_start(void) { return false; }
 static inline void lockdep_softirq_end(bool in_hardirq) { }
 #endif
 
+static __u32 softirq_deferred_for_rt(__u32 *pending)
+{
+	__u32 deferred = 0;
+
+	if (cpupri_check_rt()) {
+		deferred = *pending & LONG_SOFTIRQ_MASK;
+		*pending &= ~LONG_SOFTIRQ_MASK;
+	}
+	return deferred;
+}
+
 asmlinkage __visible void __softirq_entry __do_softirq(void)
 {
 	unsigned long end = jiffies + MAX_SOFTIRQ_TIME;
@@ -539,6 +554,7 @@ asmlinkage __visible void __softirq_entry __do_softirq(void)
 	int max_restart = MAX_SOFTIRQ_RESTART;
 	struct softirq_action *h;
 	bool in_hardirq;
+	__u32 deferred;
 	__u32 pending;
 	int softirq_bit;
 
@@ -551,13 +567,15 @@ asmlinkage __visible void __softirq_entry __do_softirq(void)
 
 	pending = local_softirq_pending();
 
+	deferred = softirq_deferred_for_rt(&pending);
 	softirq_handle_begin();
+
 	in_hardirq = lockdep_softirq_start();
 	account_softirq_enter(current);
 
 restart:
 	/* Reset the pending bitmask before enabling irqs */
-	set_softirq_pending(0);
+	set_softirq_pending(deferred);
 	__this_cpu_write(active_softirqs, pending);
 
 	local_irq_enable();
@@ -596,13 +614,16 @@ asmlinkage __visible void __softirq_entry __do_softirq(void)
 	local_irq_disable();
 
 	pending = local_softirq_pending();
+	deferred = softirq_deferred_for_rt(&pending);
+
 	if (pending) {
 		if (time_before(jiffies, end) && !need_resched() &&
 		    --max_restart)
 			goto restart;
+	}
 
+	if (pending | deferred)
 		wakeup_softirqd();
-	}
 
 	account_softirq_exit(current);
 	lockdep_softirq_end(in_hardirq);
-- 
2.37.1.559.g78731f0fdb-goog