Merge tag 'sched-core-2023-10-28' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull scheduler updates from Ingo Molnar:
 "Fair scheduler (SCHED_OTHER) improvements:
   - Remove the old and now unused SIS_PROP code & option
   - Scan cluster before LLC in the wake-up path
   - Use candidate prev/recent_used CPU if scanning failed for cluster
     wakeup

  NUMA scheduling improvements:
   - Improve the VMA access-PID code to better skip/scan VMAs
   - Extend tracing to cover VMA-skipping decisions
   - Improve/fix the recently introduced sched_numa_find_nth_cpu() code
   - Generalize numa_map_to_online_node()

  Energy scheduling improvements:
   - Remove the EM_MAX_COMPLEXITY limit
   - Add tracepoints to track energy computation
   - Make the behavior of the 'sched_energy_aware' sysctl more
     consistent
   - Consolidate and clean up access to a CPU's max compute capacity
   - Fix uclamp code corner cases

  RT scheduling improvements:
   - Drive dl_rq->overloaded with dl_rq->pushable_dl_tasks updates
   - Drive the ->rto_mask with rt_rq->pushable_tasks updates

  Scheduler scalability improvements:
   - Rate-limit updates to tg->load_avg
   - On x86 disable IBRS when CPU is offline to improve single-threaded
     performance
   - Micro-optimize in_task() and in_interrupt()
   - Micro-optimize the PSI code
   - Avoid updating PSI triggers and ->rtpoll_total when there are no
     state changes

  Core scheduler infrastructure improvements:
   - Use saved_state to reduce some spurious freezer wakeups
   - Bring in a handful of fast-headers improvements to scheduler
     headers
   - Make the scheduler UAPI headers more widely usable by user-space
   - Simplify the control flow of scheduler syscalls by using lock
     guards
   - Fix sched_setaffinity() vs. CPU hotplug race

  Scheduler debuggability improvements:
   - Disallow writing invalid values to sched_rt_period_us
   - Fix a race in the rq-clock debugging code triggering warnings
   - Fix a warning in the bandwidth distribution code
   - Micro-optimize in_atomic_preempt_off() checks
   - Enforce that the tasklist_lock is held in for_each_thread()
   - Print the TGID in sched_show_task()
   - Remove the /proc/sys/kernel/sched_child_runs_first sysctl

  ... and misc cleanups & fixes"

* tag 'sched-core-2023-10-28' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (82 commits)
  sched/fair: Remove SIS_PROP
  sched/fair: Use candidate prev/recent_used CPU if scanning failed for cluster wakeup
  sched/fair: Scan cluster before scanning LLC in wake-up path
  sched: Add cpus_share_resources API
  sched/core: Fix RQCF_ACT_SKIP leak
  sched/fair: Remove unused 'curr' argument from pick_next_entity()
  sched/nohz: Update comments about NEWILB_KICK
  sched/fair: Remove duplicate #include
  sched/psi: Update poll => rtpoll in relevant comments
  sched: Make PELT acronym definition searchable
  sched: Fix stop_one_cpu_nowait() vs hotplug
  sched/psi: Bail out early from irq time accounting
  sched/topology: Rename 'DIE' domain to 'PKG'
  sched/psi: Delete the 'update_total' function parameter from update_triggers()
  sched/psi: Avoid updating PSI triggers and ->rtpoll_total when there are no state changes
  sched/headers: Remove comment referring to rq::cpu_load, since this has been removed
  sched/numa: Complete scanning of inactive VMAs when there is no alternative
  sched/numa: Complete scanning of partial VMAs regardless of PID activity
  sched/numa: Move up the access pid reset logic
  sched/numa: Trace decisions related to skipping VMAs
  ...

1 files changed, 57 insertions, 0 deletions

diff --git a/include/trace/events/sched.h b/include/trace/events/sched.h
index fbb99a61f714..6188ad0d9e0d 100644
--- a/include/trace/events/sched.h
+++ b/include/trace/events/sched.h
@@ -664,6 +664,58 @@ DEFINE_EVENT(sched_numa_pair_template, sched_swap_numa,
 	TP_ARGS(src_tsk, src_cpu, dst_tsk, dst_cpu)
 );
 
+#ifdef CONFIG_NUMA_BALANCING
+#define NUMAB_SKIP_REASON					\
+	EM( NUMAB_SKIP_UNSUITABLE,		"unsuitable" )	\
+	EM( NUMAB_SKIP_SHARED_RO,		"shared_ro" )	\
+	EM( NUMAB_SKIP_INACCESSIBLE,		"inaccessible" )	\
+	EM( NUMAB_SKIP_SCAN_DELAY,		"scan_delay" )	\
+	EM( NUMAB_SKIP_PID_INACTIVE,		"pid_inactive" )	\
+	EM( NUMAB_SKIP_IGNORE_PID,		"ignore_pid_inactive" )		\
+	EMe(NUMAB_SKIP_SEQ_COMPLETED,		"seq_completed" )
+
+/* Redefine for export. */
+#undef EM
+#undef EMe
+#define EM(a, b)	TRACE_DEFINE_ENUM(a);
+#define EMe(a, b)	TRACE_DEFINE_ENUM(a);
+
+NUMAB_SKIP_REASON
+
+/* Redefine for symbolic printing. */
+#undef EM
+#undef EMe
+#define EM(a, b)	{ a, b },
+#define EMe(a, b)	{ a, b }
+
+TRACE_EVENT(sched_skip_vma_numa,
+
+	TP_PROTO(struct mm_struct *mm, struct vm_area_struct *vma,
+		 enum numa_vmaskip_reason reason),
+
+	TP_ARGS(mm, vma, reason),
+
+	TP_STRUCT__entry(
+		__field(unsigned long, numa_scan_offset)
+		__field(unsigned long, vm_start)
+		__field(unsigned long, vm_end)
+		__field(enum numa_vmaskip_reason, reason)
+	),
+
+	TP_fast_assign(
+		__entry->numa_scan_offset	= mm->numa_scan_offset;
+		__entry->vm_start		= vma->vm_start;
+		__entry->vm_end			= vma->vm_end;
+		__entry->reason			= reason;
+	),
+
+	TP_printk("numa_scan_offset=%lX vm_start=%lX vm_end=%lX reason=%s",
+		  __entry->numa_scan_offset,
+		  __entry->vm_start,
+		  __entry->vm_end,
+		  __print_symbolic(__entry->reason, NUMAB_SKIP_REASON))
+);
+#endif /* CONFIG_NUMA_BALANCING */
 
 /*
  * Tracepoint for waking a polling cpu without an IPI.
@@ -735,6 +787,11 @@ DECLARE_TRACE(sched_update_nr_running_tp,
 	TP_PROTO(struct rq *rq, int change),
 	TP_ARGS(rq, change));
 
+DECLARE_TRACE(sched_compute_energy_tp,
+	TP_PROTO(struct task_struct *p, int dst_cpu, unsigned long energy,
+		 unsigned long max_util, unsigned long busy_time),
+	TP_ARGS(p, dst_cpu, energy, max_util, busy_time));
+
 #endif /* _TRACE_SCHED_H */
 
 /* This part must be outside protection */