Merge tag 'sched-core-2022-03-22' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull scheduler updates from Ingo Molnar:

 - Cleanups for SCHED_DEADLINE

 - Tracing updates/fixes

 - CPU Accounting fixes

 - First wave of changes to optimize the overhead of the scheduler
   build, from the fast-headers tree - including placeholder *_api.h
   headers for later header split-ups.

 - Preempt-dynamic using static_branch() for ARM64

 - Isolation housekeeping mask rework; preperatory for further changes

 - NUMA-balancing: deal with CPU-less nodes

 - NUMA-balancing: tune systems that have multiple LLC cache domains per
   node (eg. AMD)

 - Updates to RSEQ UAPI in preparation for glibc usage

 - Lots of RSEQ/selftests, for same

 - Add Suren as PSI co-maintainer

* tag 'sched-core-2022-03-22' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (81 commits)
  sched/headers: ARM needs asm/paravirt_api_clock.h too
  sched/numa: Fix boot crash on arm64 systems
  headers/prep: Fix header to build standalone: <linux/psi.h>
  sched/headers: Only include <linux/entry-common.h> when CONFIG_GENERIC_ENTRY=y
  cgroup: Fix suspicious rcu_dereference_check() usage warning
  sched/preempt: Tell about PREEMPT_DYNAMIC on kernel headers
  sched/topology: Remove redundant variable and fix incorrect type in build_sched_domains
  sched/deadline,rt: Remove unused parameter from pick_next_[rt|dl]_entity()
  sched/deadline,rt: Remove unused functions for !CONFIG_SMP
  sched/deadline: Use __node_2_[pdl|dle]() and rb_first_cached() consistently
  sched/deadline: Merge dl_task_can_attach() and dl_cpu_busy()
  sched/deadline: Move bandwidth mgmt and reclaim functions into sched class source file
  sched/deadline: Remove unused def_dl_bandwidth
  sched/tracing: Report TASK_RTLOCK_WAIT tasks as TASK_UNINTERRUPTIBLE
  sched/tracing: Don't re-read p->state when emitting sched_switch event
  sched/rt: Plug rt_mutex_setprio() vs push_rt_task() race
  sched/cpuacct: Remove redundant RCU read lock
  sched/cpuacct: Optimize away RCU read lock
  sched/cpuacct: Fix charge percpu cpuusage
  sched/headers: Reorganize, clean up and optimize kernel/sched/sched.h dependencies
  ...

1 files changed, 30 insertions, 31 deletions

diff --git a/kernel/sched/psi.c b/kernel/sched/psi.c
index e14358178849..a4fa3aadfcba 100644
--- a/kernel/sched/psi.c
+++ b/kernel/sched/psi.c
@@ -137,21 +137,6 @@
  * sampling of the aggregate task states would be.
  */
 
-#include "../workqueue_internal.h"
-#include <linux/sched/loadavg.h>
-#include <linux/seq_file.h>
-#include <linux/proc_fs.h>
-#include <linux/seqlock.h>
-#include <linux/uaccess.h>
-#include <linux/cgroup.h>
-#include <linux/module.h>
-#include <linux/sched.h>
-#include <linux/ctype.h>
-#include <linux/file.h>
-#include <linux/poll.h>
-#include <linux/psi.h>
-#include "sched.h"
-
 static int psi_bug __read_mostly;
 
 DEFINE_STATIC_KEY_FALSE(psi_disabled);
@@ -523,7 +508,7 @@ static void init_triggers(struct psi_group *group, u64 now)
 static u64 update_triggers(struct psi_group *group, u64 now)
 {
 	struct psi_trigger *t;
-	bool new_stall = false;
+	bool update_total = false;
 	u64 *total = group->total[PSI_POLL];
 
 	/*
@@ -532,24 +517,35 @@ static u64 update_triggers(struct psi_group *group, u64 now)
 	 */
 	list_for_each_entry(t, &group->triggers, node) {
 		u64 growth;
+		bool new_stall;
 
-		/* Check for stall activity */
-		if (group->polling_total[t->state] == total[t->state])
-			continue;
+		new_stall = group->polling_total[t->state] != total[t->state];
 
+		/* Check for stall activity or a previous threshold breach */
+		if (!new_stall && !t->pending_event)
+			continue;
 		/*
-		 * Multiple triggers might be looking at the same state,
-		 * remember to update group->polling_total[] once we've
-		 * been through all of them. Also remember to extend the
-		 * polling time if we see new stall activity.
+		 * Check for new stall activity, as well as deferred
+		 * events that occurred in the last window after the
+		 * trigger had already fired (we want to ratelimit
+		 * events without dropping any).
 		 */
-		new_stall = true;
-
-		/* Calculate growth since last update */
-		growth = window_update(&t->win, now, total[t->state]);
-		if (growth < t->threshold)
-			continue;
-
+		if (new_stall) {
+			/*
+			 * Multiple triggers might be looking at the same state,
+			 * remember to update group->polling_total[] once we've
+			 * been through all of them. Also remember to extend the
+			 * polling time if we see new stall activity.
+			 */
+			update_total = true;
+
+			/* Calculate growth since last update */
+			growth = window_update(&t->win, now, total[t->state]);
+			if (growth < t->threshold)
+				continue;
+
+			t->pending_event = true;
+		}
 		/* Limit event signaling to once per window */
 		if (now < t->last_event_time + t->win.size)
 			continue;
@@ -558,9 +554,11 @@ static u64 update_triggers(struct psi_group *group, u64 now)
 		if (cmpxchg(&t->event, 0, 1) == 0)
 			wake_up_interruptible(&t->event_wait);
 		t->last_event_time = now;
+		/* Reset threshold breach flag once event got generated */
+		t->pending_event = false;
 	}
 
-	if (new_stall)
+	if (update_total)
 		memcpy(group->polling_total, total,
 				sizeof(group->polling_total));
 
@@ -1124,6 +1122,7 @@ struct psi_trigger *psi_trigger_create(struct psi_group *group,
 	t->event = 0;
 	t->last_event_time = 0;
 	init_waitqueue_head(&t->event_wait);
+	t->pending_event = false;
 
 	mutex_lock(&group->trigger_lock);