Merge: sched: fixes from sched/urgent for v6.10

MR: https://gitlab.com/redhat/centos-stream/src/kernel/centos-stream-9/-/merge_requests/4745

JIRA: https://issues.redhat.com/browse/RHEL-48226  
  
A small set of fixes came into v6.10 via sched/urgent.  Some are trivial doc changes   
but they apply cleanly and won't effect code. And a couple are really needed, including   
the last which is for VROOM-20591.  A couple were added to make things apply cleanly.  
  
Signed-off-by: Phil Auld <pauld@redhat.com>

Approved-by: Waiman Long <longman@redhat.com>
Approved-by: Eder Zulian <ezulian@redhat.com>
Approved-by: CKI KWF Bot <cki-ci-bot+kwf-gitlab-com@redhat.com>

Merged-by: Lucas Zampieri <lzampier@redhat.com>

Author: zampierilucas

Documentation/accounting/delay-accounting.rst

@@ -16,6 +16,7 @@ d) memory reclaim
 e) thrashing
 f) direct compact
 g) write-protect copy
+h) IRQ/SOFTIRQ
 
 and makes these statistics available to userspace through
 the taskstats interface.
@@ -49,7 +50,7 @@ this structure. See
 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
@@ -109,17 +110,19 @@ Get sum of delays, since system boot, for all pids with tgid 5::
 	CPU             count     real total  virtual total    delay total  delay average
 	                    8        7000000        6872122        3382277          0.423ms
 	IO              count    delay total  delay average
-		            0              0              0ms
+                   0              0          0.000ms
 	SWAP            count    delay total  delay average
-	                    0              0              0ms
+                       0              0          0.000ms
 	RECLAIM         count    delay total  delay average
-		            0              0              0ms
+                   0              0          0.000ms
 	THRASHING       count    delay total  delay average
-	                    0              0              0ms
+                       0              0          0.000ms
 	COMPACT         count    delay total  delay average
-	                    0              0              0ms
-        WPCOPY          count    delay total  delay average
-                            0              0              0ms
+                       0              0          0.000ms
+	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::
 

Documentation/admin-guide/cgroup-v1/cpusets.rst

@@ -568,7 +568,7 @@ on the next tick.  For some applications in special situation, waiting
 
 The 'cpuset.sched_relax_domain_level' file allows you to request changing
 this searching range as you like.  This file takes int value which
-indicates size of searching range in levels ideally as follows,
+indicates size of searching range in levels approximately as follows,
 otherwise initial value -1 that indicates the cpuset has no request.
 
 ====== ===========================================================
@@ -581,6 +581,11 @@ otherwise initial value -1 that indicates the cpuset has no request.
    5   search system wide [on NUMA system]
 ====== ===========================================================
 
+Not all levels can be present and values can change depending on the
+system architecture and kernel configuration. Check
+/sys/kernel/debug/sched/domains/cpu*/domain*/ for system-specific
+details.
+
 The system default is architecture dependent.  The system default
 can be changed using the relax_domain_level= boot parameter.
 

include/linux/delayacct.h

@@ -49,10 +49,13 @@ struct task_delay_info {
 	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
 
@@ -85,6 +88,7 @@ extern void __delayacct_compact_start(void);
 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_set_flag(struct task_struct *p, int flag)
 {
@@ -213,6 +217,15 @@ static inline void delayacct_wpcopy_end(void)
 		__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_set_flag(struct task_struct *p, int flag)
 {}
@@ -255,6 +268,8 @@ 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

@@ -34,7 +34,7 @@
  */
 
 
-#define TASKSTATS_VERSION	13
+#define TASKSTATS_VERSION	14
 #define TS_COMM_LEN		32	/* should be >= TASK_COMM_LEN
 					 * in linux/sched.h */
 
@@ -198,6 +198,10 @@ struct taskstats {
 	/* 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/cgroup/cpuset.c

@@ -3026,7 +3026,7 @@ bool current_cpuset_is_being_rebound(void)
 static int update_relax_domain_level(struct cpuset *cs, s64 val)
 {
 #ifdef CONFIG_SMP
-	if (val < -1 || val >= sched_domain_level_max)
+	if (val < -1 || val > sched_domain_level_max + 1)
 		return -EINVAL;
 #endif
 

kernel/delayacct.c

@@ -159,12 +159,15 @@ int delayacct_add_tsk(struct taskstats *d, struct task_struct *tsk)
 	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;
@@ -254,3 +257,14 @@ void __delayacct_wpcopy_end(void)
 		      &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

@@ -722,7 +722,7 @@ static void update_rq_clock_task(struct rq *rq, s64 delta)
 
 	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))) {
@@ -5671,7 +5671,7 @@ void scheduler_tick(void)
 {
 	int cpu = smp_processor_id();
 	struct rq *rq = cpu_rq(cpu);
-	struct task_struct *curr = rq->curr;
+	struct task_struct *curr;
 	struct rq_flags rf;
 	unsigned long thermal_pressure;
 	u64 resched_latency;
@@ -5683,6 +5683,9 @@ void scheduler_tick(void)
 
 	rq_lock(rq, &rf);
 
+	curr = rq->curr;
+	psi_account_irqtime(rq, curr, NULL);
+
 	update_rq_clock(rq);
 	thermal_pressure = arch_scale_thermal_pressure(cpu_of(rq));
 	update_thermal_load_avg(rq_clock_thermal(rq), rq, thermal_pressure);
@@ -6733,6 +6736,7 @@ static void __sched notrace __schedule(unsigned int sched_mode)
 		++*switch_count;
 
 		migrate_disable_switch(rq, prev);
+		psi_account_irqtime(rq, prev, next);
 		psi_sched_switch(prev, next, !task_on_rq_queued(prev));
 
 		trace_sched_switch(sched_mode & SM_MASK_PREEMPT, prev, next, prev_state);
@@ -11505,7 +11509,7 @@ static ssize_t cpu_max_write(struct kernfs_open_file *of,
 {
 	struct task_group *tg = css_tg(of_css(of));
 	u64 period = tg_get_cfs_period(tg);
-	u64 burst = tg_get_cfs_burst(tg);
+	u64 burst = tg->cfs_bandwidth.burst;
 	u64 quota;
 	int ret;
 

kernel/sched/deadline.c

@@ -1805,8 +1805,13 @@ static void enqueue_task_dl(struct rq *rq, struct task_struct *p, int flags)
 			 * The replenish timer needs to be canceled. No
 			 * problem if it fires concurrently: boosted threads
 			 * are ignored in dl_task_timer().
+			 *
+			 * If the timer callback was running (hrtimer_try_to_cancel == -1),
+			 * it will eventually call put_task_struct().
 			 */
-			hrtimer_try_to_cancel(&p->dl.dl_timer);
+			if (hrtimer_try_to_cancel(&p->dl.dl_timer) == 1 &&
+			    !dl_server(&p->dl))
+				put_task_struct(p);
 			p->dl.dl_throttled = 0;
 		}
 	} else if (!dl_prio(p->normal_prio)) {

kernel/sched/debug.c

@@ -428,6 +428,7 @@ static void register_sd(struct sched_domain *sd, struct dentry *parent)
 
 	debugfs_create_file("flags", 0444, parent, &sd->flags, &sd_flags_fops);
 	debugfs_create_file("groups_flags", 0444, parent, &sd->groups->flags, &sd_flags_fops);
+	debugfs_create_u32("level", 0444, parent, (u32 *)&sd->level);
 }
 
 void update_sched_domain_debugfs(void)

kernel/sched/fair.c

@@ -7659,8 +7659,8 @@ eenv_pd_max_util(struct energy_env *eenv, struct cpumask *pd_cpus,
 		 * Performance domain frequency: utilization clamping
 		 * must be considered since it affects the selection
 		 * of the performance domain frequency.
-		 * NOTE: in case RT tasks are running, by default the
-		 * FREQUENCY_UTIL's utilization can be max OPP.
+		 * NOTE: in case RT tasks are running, by default the min
+		 * utilization can be max OPP.
 		 */
 		eff_util = effective_cpu_util(cpu, util, &min, &max);