* [RFC][PATCH v2 1/2] sched: Avoid placing RT threads on cores handling long softirqs
2022-08-22 19:04 [RFC][PATCH v2 0/2] Softirq -rt Optimizations John Stultz
@ 2022-08-22 19:05 ` John Stultz
2022-08-22 19:05 ` [RFC][PATCH v2 2/2] softirq: defer softirq processing to ksoftirqd if CPU is busy with RT John Stultz
1 sibling, 0 replies; 3+ messages in thread
From: John Stultz @ 2022-08-22 19:05 UTC (permalink / raw)
To: LKML
Cc: Connor O'Brien, John Dias, Rick Yiu, John Kacur, Qais Yousef,
Chris Redpath, Abhijeet Dharmapurikar, Peter Zijlstra,
Ingo Molnar, Juri Lelli, Vincent Guittot, Dietmar Eggemann,
Steven Rostedt, Thomas Gleixner, kernel-team, J . Avila,
John Stultz
From: Connor O'Brien <connoro@google.com>
In certain audio use cases, scheduling RT threads on cores that
are handling softirqs can lead to glitches. Prevent this
behavior in cases where the softirq is likely to take a long
time. To avoid unnecessary migrations, the old behavior is
preserved for RCU, SCHED and TIMER irqs which are expected to be
relatively quick.
This patch reworks and combines two related changes originally
by John Dias <joaodias@google.com>
Cc: John Dias <joaodias@google.com>
Cc: Connor O'Brien <connoro@google.com>
Cc: Rick Yiu <rickyiu@google.com>
Cc: John Kacur <jkacur@redhat.com>
Cc: Qais Yousef <qais.yousef@arm.com>
Cc: Chris Redpath <chris.redpath@arm.com>
Cc: Abhijeet Dharmapurikar <adharmap@quicinc.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Juri Lelli <juri.lelli@redhat.com>
Cc: Vincent Guittot <vincent.guittot@linaro.org>
Cc: Dietmar Eggemann <dietmar.eggemann@arm.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: kernel-team@android.com
Signed-off-by: John Dias <joaodias@google.com>
[elavila: Port to mainline, amend commit text]
Signed-off-by: J. Avila <elavila@google.com>
[connoro: Reworked, simplified, and merged two patches together]
Signed-off-by: Connor O'Brien <connoro@google.com>
[jstultz: Further simplified and fixed issues, reworded commit
message, removed arm64-isms]
Signed-off-by: John Stultz <jstultz@google.com>
---
v2:
* Reformatted Kconfig entry to match coding style
(Reported-by: Randy Dunlap <rdunlap@infradead.org>)
* Made rt_task_fits_capacity_and_may_preempt static to
avoid warnings (Reported-by: kernel test robot <lkp@intel.com>)
* Rework to use preempt_count and drop kconfig dependency on ARM64
---
include/linux/interrupt.h | 7 +++++
init/Kconfig | 10 ++++++
kernel/sched/rt.c | 65 +++++++++++++++++++++++++++++++++------
kernel/softirq.c | 9 ++++++
4 files changed, 82 insertions(+), 9 deletions(-)
diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h
index a92bce40b04b..bac9da05b9c8 100644
--- a/include/linux/interrupt.h
+++ b/include/linux/interrupt.h
@@ -571,6 +571,12 @@ enum
* _ IRQ_POLL: irq_poll_cpu_dead() migrates the queue
*/
#define SOFTIRQ_HOTPLUG_SAFE_MASK (BIT(RCU_SOFTIRQ) | BIT(IRQ_POLL_SOFTIRQ))
+/* Softirq's where the handling might be long: */
+#define LONG_SOFTIRQ_MASK ((1 << NET_TX_SOFTIRQ) | \
+ (1 << NET_RX_SOFTIRQ) | \
+ (1 << BLOCK_SOFTIRQ) | \
+ (1 << IRQ_POLL_SOFTIRQ) | \
+ (1 << TASKLET_SOFTIRQ))
/* map softirq index to softirq name. update 'softirq_to_name' in
* kernel/softirq.c when adding a new softirq.
@@ -606,6 +612,7 @@ extern void raise_softirq_irqoff(unsigned int nr);
extern void raise_softirq(unsigned int nr);
DECLARE_PER_CPU(struct task_struct *, ksoftirqd);
+DECLARE_PER_CPU(u32, active_softirqs);
static inline struct task_struct *this_cpu_ksoftirqd(void)
{
diff --git a/init/Kconfig b/init/Kconfig
index 532362fcfe31..8b5add74b6cb 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -1284,6 +1284,16 @@ config SCHED_AUTOGROUP
desktop applications. Task group autogeneration is currently based
upon task session.
+config RT_SOFTIRQ_OPTIMIZATION
+ bool "Improve RT scheduling during long softirq execution"
+ depends on SMP
+ default n
+ help
+ Enable an optimization which tries to avoid placing RT tasks on CPUs
+ occupied by nonpreemptible tasks, such as a long softirq or CPUs
+ which may soon block preemptions, such as a CPU running a ksoftirq
+ thread which handles slow softirqs.
+
config SYSFS_DEPRECATED
bool "Enable deprecated sysfs features to support old userspace tools"
depends on SYSFS
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index 55f39c8f4203..5a5cf396d0d2 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -1599,12 +1599,50 @@ static void yield_task_rt(struct rq *rq)
#ifdef CONFIG_SMP
static int find_lowest_rq(struct task_struct *task);
+#ifdef CONFIG_RT_SOFTIRQ_OPTIMIZATION
+/*
+ * Return whether the task on the given cpu is currently non-preemptible
+ * while handling a potentially long softirq, or if the task is likely
+ * to block preemptions soon because it is a ksoftirq thread that is
+ * handling slow softirq.
+ */
+static bool task_may_preempt(struct task_struct *task, int cpu)
+{
+ u32 softirqs = per_cpu(active_softirqs, cpu) |
+ per_cpu(irq_stat, cpu).__softirq_pending;
+
+ struct task_struct *cpu_ksoftirqd = per_cpu(ksoftirqd, cpu);
+ struct task_struct *curr;
+ struct rq *rq = cpu_rq(cpu);
+ int ret;
+
+ rcu_read_lock();
+ curr = READ_ONCE(rq->curr); /* unlocked access */
+ ret = !((softirqs & LONG_SOFTIRQ_MASK) &&
+ (curr == cpu_ksoftirqd ||
+ preempt_count() & SOFTIRQ_MASK));
+ rcu_read_unlock();
+ return ret;
+}
+#else
+static bool task_may_preempt(struct task_struct *task, int cpu)
+{
+ return true;
+}
+#endif /* CONFIG_RT_SOFTIRQ_OPTIMIZATION */
+
+static bool rt_task_fits_capacity_and_may_preempt(struct task_struct *p, int cpu)
+{
+ return task_may_preempt(p, cpu) && rt_task_fits_capacity(p, cpu);
+}
+
static int
select_task_rq_rt(struct task_struct *p, int cpu, int flags)
{
struct task_struct *curr;
struct rq *rq;
bool test;
+ bool may_not_preempt;
/* For anything but wake ups, just return the task_cpu */
if (!(flags & (WF_TTWU | WF_FORK)))
@@ -1616,7 +1654,12 @@ select_task_rq_rt(struct task_struct *p, int cpu, int flags)
curr = READ_ONCE(rq->curr); /* unlocked access */
/*
- * If the current task on @p's runqueue is an RT task, then
+ * If the current task on @p's runqueue is a softirq task,
+ * it may run without preemption for a time that is
+ * ill-suited for a waiting RT task. Therefore, try to
+ * wake this RT task on another runqueue.
+ *
+ * Also, if the current task on @p's runqueue is an RT task, then
* try to see if we can wake this RT task up on another
* runqueue. Otherwise simply start this RT task
* on its current runqueue.
@@ -1641,9 +1684,10 @@ select_task_rq_rt(struct task_struct *p, int cpu, int flags)
* requirement of the task - which is only important on heterogeneous
* systems like big.LITTLE.
*/
- test = curr &&
- unlikely(rt_task(curr)) &&
- (curr->nr_cpus_allowed < 2 || curr->prio <= p->prio);
+ may_not_preempt = !task_may_preempt(curr, cpu);
+ test = (curr && (may_not_preempt ||
+ (unlikely(rt_task(curr)) &&
+ (curr->nr_cpus_allowed < 2 || curr->prio <= p->prio))));
if (test || !rt_task_fits_capacity(p, cpu)) {
int target = find_lowest_rq(p);
@@ -1656,11 +1700,14 @@ select_task_rq_rt(struct task_struct *p, int cpu, int flags)
goto out_unlock;
/*
- * Don't bother moving it if the destination CPU is
+ * If cpu is non-preemptible, prefer remote cpu
+ * even if it's running a higher-prio task.
+ * Otherwise: Don't bother moving it if the destination CPU is
* not running a lower priority task.
*/
if (target != -1 &&
- p->prio < cpu_rq(target)->rt.highest_prio.curr)
+ (may_not_preempt ||
+ p->prio < cpu_rq(target)->rt.highest_prio.curr))
cpu = target;
}
@@ -1901,11 +1948,11 @@ static int find_lowest_rq(struct task_struct *task)
ret = cpupri_find_fitness(&task_rq(task)->rd->cpupri,
task, lowest_mask,
- rt_task_fits_capacity);
+ rt_task_fits_capacity_and_may_preempt);
} else {
- ret = cpupri_find(&task_rq(task)->rd->cpupri,
- task, lowest_mask);
+ ret = cpupri_find_fitness(&task_rq(task)->rd->cpupri,
+ task, lowest_mask, task_may_preempt);
}
if (!ret)
diff --git a/kernel/softirq.c b/kernel/softirq.c
index c8a6913c067d..35ee79dd8786 100644
--- a/kernel/softirq.c
+++ b/kernel/softirq.c
@@ -60,6 +60,13 @@ static struct softirq_action softirq_vec[NR_SOFTIRQS] __cacheline_aligned_in_smp
DEFINE_PER_CPU(struct task_struct *, ksoftirqd);
+/*
+ * active_softirqs -- per cpu, a mask of softirqs that are being handled,
+ * with the expectation that approximate answers are acceptable and therefore
+ * no synchronization.
+ */
+DEFINE_PER_CPU(u32, active_softirqs);
+
const char * const softirq_to_name[NR_SOFTIRQS] = {
"HI", "TIMER", "NET_TX", "NET_RX", "BLOCK", "IRQ_POLL",
"TASKLET", "SCHED", "HRTIMER", "RCU"
@@ -551,6 +558,7 @@ asmlinkage __visible void __softirq_entry __do_softirq(void)
restart:
/* Reset the pending bitmask before enabling irqs */
set_softirq_pending(0);
+ __this_cpu_write(active_softirqs, pending);
local_irq_enable();
@@ -580,6 +588,7 @@ asmlinkage __visible void __softirq_entry __do_softirq(void)
pending >>= softirq_bit;
}
+ __this_cpu_write(active_softirqs, 0);
if (!IS_ENABLED(CONFIG_PREEMPT_RT) &&
__this_cpu_read(ksoftirqd) == current)
rcu_softirq_qs();
--
2.37.1.595.g718a3a8f04-goog
^ permalink raw reply related [flat|nested] 3+ messages in thread* [RFC][PATCH v2 2/2] softirq: defer softirq processing to ksoftirqd if CPU is busy with RT
2022-08-22 19:04 [RFC][PATCH v2 0/2] Softirq -rt Optimizations John Stultz
2022-08-22 19:05 ` [RFC][PATCH v2 1/2] sched: Avoid placing RT threads on cores handling long softirqs John Stultz
@ 2022-08-22 19:05 ` John Stultz
1 sibling, 0 replies; 3+ messages in thread
From: John Stultz @ 2022-08-22 19:05 UTC (permalink / raw)
To: LKML
Cc: Pavankumar Kondeti, John Dias, Connor O'Brien, Rick Yiu,
John Kacur, Qais Yousef, Chris Redpath, Abhijeet Dharmapurikar,
Peter Zijlstra, Ingo Molnar, Juri Lelli, Vincent Guittot,
Dietmar Eggemann, Steven Rostedt, Thomas Gleixner, kernel-team,
Satya Durga Srinivasu Prabhala, J . Avila, John Stultz
From: Pavankumar Kondeti <pkondeti@codeaurora.org>
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@codeaurora.org>
Satya Durga Srinivasu Prabhala <satyap@codeaurora.org>
J. Avila <elavila@google.com>
Cc: John Dias <joaodias@google.com>
Cc: Connor O'Brien <connoro@google.com>
Cc: Rick Yiu <rickyiu@google.com>
Cc: John Kacur <jkacur@redhat.com>
Cc: Qais Yousef <qais.yousef@arm.com>
Cc: Chris Redpath <chris.redpath@arm.com>
Cc: Abhijeet Dharmapurikar <adharmap@quicinc.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Juri Lelli <juri.lelli@redhat.com>
Cc: Vincent Guittot <vincent.guittot@linaro.org>
Cc: Dietmar Eggemann <dietmar.eggemann@arm.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: kernel-team@android.com
Signed-off-by: Pavankumar Kondeti <pkondeti@codeaurora.org>
[satyap@codeaurora.org: trivial merge conflict resolution.]
Signed-off-by: Satya Durga Srinivasu Prabhala <satyap@codeaurora.org>
[elavila: Port to mainline, squash with bugfix]
Signed-off-by: J. Avila <elavila@google.com>
[jstultz: Rebase to linus/HEAD, minor rearranging of code,
included bug fix Reported-by: Qais Yousef <qais.yousef@arm.com> ]
Signed-off-by: John Stultz <jstultz@google.com>
---
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 e7b2f8a5c711..7f76371cbbb0 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1826,6 +1826,16 @@ 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_effective_cpus);
+
+#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 35ee79dd8786..203a70dc9459 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);
--
2.37.1.595.g718a3a8f04-goog
^ permalink raw reply related [flat|nested] 3+ messages in thread