linux-kernel - [PATCH V4 5/6] Sched: Add tracepoint for sched time slice extension

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: <20250513214554.4160454-6-prakash.sangappa@oracle.com>
Date: Tue, 13 May 2025 21:45:53 +0000
From: Prakash Sangappa <prakash.sangappa@...cle.com>
To: linux-kernel@...r.kernel.org
Cc: peterz@...radead.org, rostedt@...dmis.org, mathieu.desnoyers@...icios.com,
        tglx@...utronix.de, bigeasy@...utronix.de, kprateek.nayak@....com
Subject: [PATCH V4 5/6] Sched: Add tracepoint for sched time slice extension

Trace thread's preemption getting delayed. Which can occur if
the running thread requested extra time on cpu.  Also, indicate
the NEED_RESCHED flag, that is set on the thread, getting cleared.

Suggested-by: Sebastian Andrzej Siewior <bigeasy@...utronix.de>
Signed-off-by: Prakash Sangappa <prakash.sangappa@...cle.com>
---
 include/trace/events/sched.h | 28 ++++++++++++++++++++++++++++
 kernel/entry/common.c        | 12 ++++++++++--
 2 files changed, 38 insertions(+), 2 deletions(-)

diff --git a/include/trace/events/sched.h b/include/trace/events/sched.h
index 8994e97d86c1..4aa04044b14a 100644
--- a/include/trace/events/sched.h
+++ b/include/trace/events/sched.h
@@ -296,6 +296,34 @@ TRACE_EVENT(sched_migrate_task,
 		  __entry->orig_cpu, __entry->dest_cpu)
 );
 
+/*
+ * Tracepoint for delayed resched requested by task:
+ */
+TRACE_EVENT(sched_delay_resched,
+
+	TP_PROTO(struct task_struct *p, unsigned int resched_flg),
+
+	TP_ARGS(p, resched_flg),
+
+	TP_STRUCT__entry(
+		__array( char, comm, TASK_COMM_LEN	)
+		__field( pid_t, pid			)
+		__field( int, cpu			)
+		__field( int, flg			)
+	),
+
+	TP_fast_assign(
+		memcpy(__entry->comm, p->comm, TASK_COMM_LEN);
+		__entry->pid		= p->pid;
+		__entry->cpu 		= task_cpu(p);
+		__entry->flg		= resched_flg;
+	),
+
+	TP_printk("comm=%s pid=%d cpu=%d resched_flg_cleared=0x%x",
+		__entry->comm, __entry->pid, __entry->cpu, __entry->flg)
+
+);
+
 DECLARE_EVENT_CLASS(sched_process_template,
 
 	TP_PROTO(struct task_struct *p),
diff --git a/kernel/entry/common.c b/kernel/entry/common.c
index b26adccb32df..cd0f076920fd 100644
--- a/kernel/entry/common.c
+++ b/kernel/entry/common.c
@@ -12,6 +12,7 @@
 
 #include "common.h"
 
+#include <trace/events/sched.h>
 #define CREATE_TRACE_POINTS
 #include <trace/events/syscalls.h>
 
@@ -91,6 +92,7 @@ __always_inline unsigned long exit_to_user_mode_loop(struct pt_regs *regs,
 						     unsigned long ti_work,
 						     bool irq)
 {
+	unsigned long ti_work_cleared = 0;
 	/*
 	 * Before returning to user space ensure that all pending work
 	 * items have been completed.
@@ -100,10 +102,12 @@ __always_inline unsigned long exit_to_user_mode_loop(struct pt_regs *regs,
 		local_irq_enable_exit_to_user(ti_work);
 
 		if (ti_work & (_TIF_NEED_RESCHED | _TIF_NEED_RESCHED_LAZY)) {
-		       if (irq && rseq_delay_resched())
+		       if (irq && rseq_delay_resched()) {
 			       clear_tsk_need_resched(current);
-		       else
+			       ti_work_cleared = ti_work;
+		       } else {
 			       schedule();
+		       }
 		}
 
 		if (ti_work & _TIF_UPROBE)
@@ -134,6 +138,10 @@ __always_inline unsigned long exit_to_user_mode_loop(struct pt_regs *regs,
 		ti_work = read_thread_flags();
 	}
 
+	if (ti_work_cleared)
+		trace_sched_delay_resched(current, ti_work_cleared &
+			(_TIF_NEED_RESCHED | _TIF_NEED_RESCHED_LAZY));
+
 	/* Return the latest work state for arch_exit_to_user_mode() */
 	return ti_work;
 }
-- 
2.43.5