linux-kernel - [PATCH 2/2] sched/deadline: Correctly account for allocated bandwidth during hotplug

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: <20241113125724.450249-3-juri.lelli@redhat.com>
Date: Wed, 13 Nov 2024 12:57:23 +0000
From: Juri Lelli <juri.lelli@...hat.com>
To: Waiman Long <longman@...hat.com>,
	Tejun Heo <tj@...nel.org>,
	Johannes Weiner <hannes@...xchg.org>,
	Michal Koutny <mkoutny@...e.com>,
	Ingo Molnar <mingo@...hat.com>,
	Peter Zijlstra <peterz@...radead.org>,
	Vincent Guittot <vincent.guittot@...aro.org>,
	Dietmar Eggemann <dietmar.eggemann@....com>,
	Steven Rostedt <rostedt@...dmis.org>,
	Ben Segall <bsegall@...gle.com>,
	Mel Gorman <mgorman@...e.de>,
	Valentin Schneider <vschneid@...hat.com>
Cc: Qais Yousef <qyousef@...alina.io>,
	Sebastian Andrzej Siewior <bigeasy@...utronix.de>,
	"Joel Fernandes (Google)" <joel@...lfernandes.org>,
	Suleiman Souhlal <suleiman@...gle.com>,
	Aashish Sharma <shraash@...gle.com>,
	Shin Kawamura <kawasin@...gle.com>,
	Vineeth Remanan Pillai <vineeth@...byteword.org>,
	linux-kernel@...r.kernel.org,
	cgroups@...r.kernel.org,
	Juri Lelli <juri.lelli@...hat.com>
Subject: [PATCH 2/2] sched/deadline: Correctly account for allocated bandwidth during hotplug

For hotplug operations, DEADLINE needs to check that there is still enough
bandwidth left after removing the CPU that is going offline. We however
fail to do so currently.

Restore the correct behavior by restructuring dl_bw_manage() a bit, so
that overflow conditions (not enough bandwidth left) are properly
checked. Also account for dl_server bandwidth, i.e. discount such
bandwidht in the calculation since NORMAL tasks will be anyway moved
away from the CPU as a result of the hotplug operation.

Signed-off-by: Juri Lelli <juri.lelli@...hat.com>
---
 kernel/sched/core.c     |  2 +-
 kernel/sched/deadline.c | 33 ++++++++++++++++++++++++---------
 kernel/sched/sched.h    |  2 +-
 3 files changed, 26 insertions(+), 11 deletions(-)

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 43e453ab7e20..d1049e784510 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -8057,7 +8057,7 @@ static void cpuset_cpu_active(void)
 static int cpuset_cpu_inactive(unsigned int cpu)
 {
 	if (!cpuhp_tasks_frozen) {
-		int ret = dl_bw_check_overflow(cpu);
+		int ret = dl_bw_deactivate(cpu);
 
 		if (ret)
 			return ret;
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index e53208a50279..609685c5df05 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -3467,29 +3467,31 @@ int dl_cpuset_cpumask_can_shrink(const struct cpumask *cur,
 }
 
 enum dl_bw_request {
-	dl_bw_req_check_overflow = 0,
+	dl_bw_req_deactivate = 0,
 	dl_bw_req_alloc,
 	dl_bw_req_free
 };
 
 static int dl_bw_manage(enum dl_bw_request req, int cpu, u64 dl_bw)
 {
-	unsigned long flags;
+	unsigned long flags, cap;
 	struct dl_bw *dl_b;
 	bool overflow = 0;
+	u64 fair_server_bw = 0;
 
 	rcu_read_lock_sched();
 	dl_b = dl_bw_of(cpu);
 	raw_spin_lock_irqsave(&dl_b->lock, flags);
 
-	if (req == dl_bw_req_free) {
+	cap = dl_bw_capacity(cpu);
+	switch (req) {
+	case dl_bw_req_free:
 		__dl_sub(dl_b, dl_bw, dl_bw_cpus(cpu));
-	} else {
-		unsigned long cap = dl_bw_capacity(cpu);
-
+		break;
+	case dl_bw_req_alloc:
 		overflow = __dl_overflow(dl_b, cap, 0, dl_bw);
 
-		if (req == dl_bw_req_alloc && !overflow) {
+		if (!overflow) {
 			/*
 			 * We reserve space in the destination
 			 * root_domain, as we can't fail after this point.
@@ -3498,6 +3500,19 @@ static int dl_bw_manage(enum dl_bw_request req, int cpu, u64 dl_bw)
 			 */
 			__dl_add(dl_b, dl_bw, dl_bw_cpus(cpu));
 		}
+		break;
+	case dl_bw_req_deactivate:
+		/*
+		 * cpu is going offline and NORMAL tasks will be moved away
+		 * from it. We can thus discount dl_server bandwidth
+		 * contribution as it won't need to be servicing tasks after
+		 * the cpu is off.
+		 */
+		if (cpu_rq(cpu)->fair_server.dl_server)
+			fair_server_bw = cpu_rq(cpu)->fair_server.dl_bw;
+
+		overflow = __dl_overflow(dl_b, cap, fair_server_bw, 0);
+		break;
 	}
 
 	raw_spin_unlock_irqrestore(&dl_b->lock, flags);
@@ -3506,9 +3521,9 @@ static int dl_bw_manage(enum dl_bw_request req, int cpu, u64 dl_bw)
 	return overflow ? -EBUSY : 0;
 }
 
-int dl_bw_check_overflow(int cpu)
+int dl_bw_deactivate(int cpu)
 {
-	return dl_bw_manage(dl_bw_req_check_overflow, cpu, 0);
+	return dl_bw_manage(dl_bw_req_deactivate, cpu, 0);
 }
 
 int dl_bw_alloc(int cpu, u64 dl_bw)
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index b1c3588a8f00..1fee840f1bab 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -362,7 +362,7 @@ extern void __getparam_dl(struct task_struct *p, struct sched_attr *attr);
 extern bool __checkparam_dl(const struct sched_attr *attr);
 extern bool dl_param_changed(struct task_struct *p, const struct sched_attr *attr);
 extern int  dl_cpuset_cpumask_can_shrink(const struct cpumask *cur, const struct cpumask *trial);
-extern int  dl_bw_check_overflow(int cpu);
+extern int  dl_bw_deactivate(int cpu);
 extern s64 dl_scaled_delta_exec(struct rq *rq, struct sched_dl_entity *dl_se, s64 delta_exec);
 /*
  * SCHED_DEADLINE supports servers (nested scheduling) with the following
-- 
2.47.0