linux-kernel - [PATCH v5 2/2] sched/numa: Add tracepoint that tracks the skipping of numa balancing due to cpuset memory pinning

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <20250424024523.2298272-3-libo.chen@oracle.com>
Date: Wed, 23 Apr 2025 19:45:23 -0700
From: Libo Chen <libo.chen@...cle.com>
To: akpm@...ux-foundation.org, rostedt@...dmis.org, peterz@...radead.org,
        mgorman@...e.de, mingo@...hat.com, juri.lelli@...hat.com,
        vincent.guittot@...aro.org, tj@...nel.org, llong@...hat.com
Cc: sraithal@....com, venkat88@...ux.ibm.com, kprateek.nayak@....com,
        raghavendra.kt@....com, yu.c.chen@...el.com, tim.c.chen@...el.com,
        vineethr@...ux.ibm.com, chris.hyser@...cle.com,
        daniel.m.jordan@...cle.com, lorenzo.stoakes@...cle.com,
        mkoutny@...e.com, linux-mm@...ck.org, cgroups@...r.kernel.org,
        linux-kernel@...r.kernel.org
Subject: [PATCH v5 2/2] 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.

Signed-off-by: Libo Chen <libo.chen@...cle.com>
---
 include/trace/events/sched.h | 33 +++++++++++++++++++++++++++++++++
 kernel/sched/fair.c          |  4 +++-
 2 files changed, 36 insertions(+), 1 deletion(-)

diff --git a/include/trace/events/sched.h b/include/trace/events/sched.h
index 8994e97d86c1..ff3990318aec 100644
--- a/include/trace/events/sched.h
+++ b/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 */
 
 /*
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index c9903b1b3948..cc892961ce15 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -3333,8 +3333,10 @@ 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 +
-- 
2.43.5