sched/numa: add tracepoint that tracks the skipping of numa balancing due to cpuset memory pinning

JIRA: https://issues.redhat.com/browse/RHEL-110301

commit 3fc567e
Author: Libo Chen <[email protected]>
Date:   Wed Apr 23 19:45:23 2025 -0700

    sched/numa: add tracepoint that tracks the skipping of numa balancing due to cpuset memory pinning

    Unlike sched_skip_vma_numa tracepoint which tracks skipped VMAs, this
    tracks the task subjected to cpuset.mems pinning and prints out its
    allowed memory node mask.

    Link: https://lkml.kernel.org/r/[email protected]
    Signed-off-by: Libo Chen <[email protected]>
    Cc: "Chen, Tim C" <[email protected]>
    Cc: Chen Yu <[email protected]>
    Cc: Chris Hyser <[email protected]>
    Cc: Daniel Jordan <[email protected]>
    Cc: Ingo Molnar <[email protected]>
    Cc: Juri Lelli <[email protected]>
    Cc: K Prateek Nayak <[email protected]>
    Cc: Lorenzo Stoakes <[email protected]>
    Cc: Madadi Vineeth Reddy <[email protected]>
    Cc: Mel Gorman <mgorman <[email protected]>
    Cc: Michal Koutný <[email protected]>
    Cc: Peter Zijlstra <[email protected]>
    Cc: Raghavendra K T <[email protected]>
    Cc: Srikanth Aithal <[email protected]>
    Cc: Steven Rostedt <[email protected]>
    Cc: Tejun Heo <[email protected]>
    Cc: Venkat Rao Bagalkote <[email protected]>
    Cc: Vincent Guittot <[email protected]>
    Signed-off-by: Andrew Morton <[email protected]>

Signed-off-by: Phil Auld <[email protected]>

Author: auldp

include/trace/events/sched.h

@@ -745,6 +745,39 @@ TRACE_EVENT(sched_skip_vma_numa,
 		  __entry->vm_end,
 		  __print_symbolic(__entry->reason, NUMAB_SKIP_REASON))
 );
+
+TRACE_EVENT(sched_skip_cpuset_numa,
+
+	TP_PROTO(struct task_struct *tsk, nodemask_t *mem_allowed_ptr),
+
+	TP_ARGS(tsk, mem_allowed_ptr),
+
+	TP_STRUCT__entry(
+		__array( char,		comm,		TASK_COMM_LEN		)
+		__field( pid_t,		pid					)
+		__field( pid_t,		tgid					)
+		__field( pid_t,		ngid					)
+		__array( unsigned long, mem_allowed, BITS_TO_LONGS(MAX_NUMNODES))
+	),
+
+	TP_fast_assign(
+		memcpy(__entry->comm, tsk->comm, TASK_COMM_LEN);
+		__entry->pid		 = task_pid_nr(tsk);
+		__entry->tgid		 = task_tgid_nr(tsk);
+		__entry->ngid		 = task_numa_group_id(tsk);
+		BUILD_BUG_ON(sizeof(nodemask_t) != \
+			     BITS_TO_LONGS(MAX_NUMNODES) * sizeof(long));
+		memcpy(__entry->mem_allowed, mem_allowed_ptr->bits,
+		       sizeof(__entry->mem_allowed));
+	),
+
+	TP_printk("comm=%s pid=%d tgid=%d ngid=%d mem_nodes_allowed=%*pbl",
+		  __entry->comm,
+		  __entry->pid,
+		  __entry->tgid,
+		  __entry->ngid,
+		  MAX_NUMNODES, __entry->mem_allowed)
+);
 #endif /* CONFIG_NUMA_BALANCING */
 
 /*

kernel/sched/fair.c

@@ -3310,8 +3310,10 @@ static void task_numa_work(struct callback_head *work)
 	 * Memory is pinned to only one NUMA node via cpuset.mems, naturally
 	 * no page can be migrated.
 	 */
-	if (cpusets_enabled() && nodes_weight(cpuset_current_mems_allowed) == 1)
+	if (cpusets_enabled() && nodes_weight(cpuset_current_mems_allowed) == 1) {
+		trace_sched_skip_cpuset_numa(current, &cpuset_current_mems_allowed);
 		return;
+	}
 
 	if (!mm->numa_next_scan) {
 		mm->numa_next_scan = now +