linux-kernel - [RFC PATCH 42/86] sched: force preemption on tick expiration

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: <20231107215742.363031-43-ankur.a.arora@oracle.com>
Date:   Tue,  7 Nov 2023 13:57:28 -0800
From:   Ankur Arora <ankur.a.arora@...cle.com>
To:     linux-kernel@...r.kernel.org
Cc:     tglx@...utronix.de, peterz@...radead.org,
        torvalds@...ux-foundation.org, paulmck@...nel.org,
        linux-mm@...ck.org, x86@...nel.org, akpm@...ux-foundation.org,
        luto@...nel.org, bp@...en8.de, dave.hansen@...ux.intel.com,
        hpa@...or.com, mingo@...hat.com, juri.lelli@...hat.com,
        vincent.guittot@...aro.org, willy@...radead.org, mgorman@...e.de,
        jon.grimm@....com, bharata@....com, raghavendra.kt@....com,
        boris.ostrovsky@...cle.com, konrad.wilk@...cle.com,
        jgross@...e.com, andrew.cooper3@...rix.com, mingo@...nel.org,
        bristot@...nel.org, mathieu.desnoyers@...icios.com,
        geert@...ux-m68k.org, glaubitz@...sik.fu-berlin.de,
        anton.ivanov@...bridgegreys.com, mattst88@...il.com,
        krypton@...ich-teichert.org, rostedt@...dmis.org,
        David.Laight@...LAB.COM, richard@....at, mjguzik@...il.com,
        Ankur Arora <ankur.a.arora@...cle.com>
Subject: [RFC PATCH 42/86] sched: force preemption on tick expiration

The kernel can have long running tasks which don't pass through
preemption points for prolonged periods and so will never see
a scheduler's polite TIF_NEED_RESCHED_LAZY.

Force a reschedule at the next tick by upgrading to TIF_NEED_RESCHED,
which will get folded into the preempt_count and a reschedule at the
next safe preemption point.

TODO: deadline scheduler.

Originally-by: Thomas Gleixner <tglx@...utronix.de>
Signed-off-by: Ankur Arora <ankur.a.arora@...cle.com>
---
 kernel/sched/fair.c  | 32 +++++++++++++++++++++++---------
 kernel/sched/rt.c    |  7 ++++++-
 kernel/sched/sched.h |  1 +
 3 files changed, 30 insertions(+), 10 deletions(-)

diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 4d86c618ffa2..fe7e5e9b2207 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -1016,8 +1016,11 @@ static void clear_buddies(struct cfs_rq *cfs_rq, struct sched_entity *se);
  * XXX: strictly: vd_i += N*r_i/w_i such that: vd_i > ve_i
  * this is probably good enough.
  */
-static void update_deadline(struct cfs_rq *cfs_rq, struct sched_entity *se)
+static void update_deadline(struct cfs_rq *cfs_rq,
+			    struct sched_entity *se, bool tick)
 {
+	struct rq *rq = rq_of(cfs_rq);
+
 	if ((s64)(se->vruntime - se->deadline) < 0)
 		return;
 
@@ -1033,13 +1036,19 @@ static void update_deadline(struct cfs_rq *cfs_rq, struct sched_entity *se)
 	 */
 	se->deadline = se->vruntime + calc_delta_fair(se->slice, se);
 
+	if (cfs_rq->nr_running < 2)
+		return;
+
 	/*
-	 * The task has consumed its request, reschedule.
+	 * The task has consumed its request, reschedule; eagerly
+	 * if it ignored our last lazy reschedule.
 	 */
-	if (cfs_rq->nr_running > 1) {
-		resched_curr(rq_of(cfs_rq));
-		clear_buddies(cfs_rq, se);
-	}
+	if (tick && test_tsk_thread_flag(rq->curr, TIF_NEED_RESCHED_LAZY))
+		__resched_curr(rq, RESCHED_eager);
+	else
+		resched_curr(rq);
+
+	clear_buddies(cfs_rq, se);
 }
 
 #include "pelt.h"
@@ -1147,7 +1156,7 @@ static void update_tg_load_avg(struct cfs_rq *cfs_rq)
 /*
  * Update the current task's runtime statistics.
  */
-static void update_curr(struct cfs_rq *cfs_rq)
+static void __update_curr(struct cfs_rq *cfs_rq, bool tick)
 {
 	struct sched_entity *curr = cfs_rq->curr;
 	u64 now = rq_clock_task(rq_of(cfs_rq));
@@ -1174,7 +1183,7 @@ static void update_curr(struct cfs_rq *cfs_rq)
 	schedstat_add(cfs_rq->exec_clock, delta_exec);
 
 	curr->vruntime += calc_delta_fair(delta_exec, curr);
-	update_deadline(cfs_rq, curr);
+	update_deadline(cfs_rq, curr, tick);
 	update_min_vruntime(cfs_rq);
 
 	if (entity_is_task(curr)) {
@@ -1188,6 +1197,11 @@ static void update_curr(struct cfs_rq *cfs_rq)
 	account_cfs_rq_runtime(cfs_rq, delta_exec);
 }
 
+static void update_curr(struct cfs_rq *cfs_rq)
+{
+	__update_curr(cfs_rq, false);
+}
+
 static void update_curr_fair(struct rq *rq)
 {
 	update_curr(cfs_rq_of(&rq->curr->se));
@@ -5309,7 +5323,7 @@ entity_tick(struct cfs_rq *cfs_rq, struct sched_entity *curr, int queued)
 	/*
 	 * Update run-time statistics of the 'current'.
 	 */
-	update_curr(cfs_rq);
+	__update_curr(cfs_rq, true);
 
 	/*
 	 * Ensure that runnable average is periodically updated.
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index a79ce6746dd0..5fdb93f1b87e 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -2664,7 +2664,12 @@ static void task_tick_rt(struct rq *rq, struct task_struct *p, int queued)
 	for_each_sched_rt_entity(rt_se) {
 		if (rt_se->run_list.prev != rt_se->run_list.next) {
 			requeue_task_rt(rq, p, 0);
-			resched_curr(rq);
+
+			if (test_tsk_thread_flag(rq->curr, TIF_NEED_RESCHED_LAZY))
+				__resched_curr(rq, RESCHED_eager);
+			else
+				resched_curr(rq);
+
 			return;
 		}
 	}
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 9e1329a4e890..e29a8897f573 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -2434,6 +2434,7 @@ extern void init_sched_fair_class(void);
 
 extern void reweight_task(struct task_struct *p, int prio);
 
+extern void __resched_curr(struct rq *rq, resched_t rs);
 extern void resched_curr(struct rq *rq);
 extern void resched_cpu(int cpu);
 
-- 
2.31.1