linux-kernel - [PATCH MANUALSEL 5.10 1/4] sched/cputime: Fix getrusage(RUSAGE_THREAD) with nohz

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-next>] [day] [month] [year] [list]

Message-Id: <20211213142020.352376-1-sashal@kernel.org>
Date:   Mon, 13 Dec 2021 09:20:15 -0500
From:   Sasha Levin <sashal@...nel.org>
To:     linux-kernel@...r.kernel.org, stable@...r.kernel.org
Cc:     Frederic Weisbecker <frederic@...nel.org>,
        Hasegawa Hitomi <hasegawa-hitomi@...itsu.com>,
        Thomas Gleixner <tglx@...utronix.de>,
        Masayoshi Mizuma <m.mizuma@...fujitsu.com>,
        Phil Auld <pauld@...hat.com>, Sasha Levin <sashal@...nel.org>,
        mingo@...hat.com, peterz@...radead.org, juri.lelli@...hat.com,
        vincent.guittot@...aro.org
Subject: [PATCH MANUALSEL 5.10 1/4] sched/cputime: Fix getrusage(RUSAGE_THREAD) with nohz_full

From: Frederic Weisbecker <frederic@...nel.org>

[ Upstream commit e7f2be115f0746b969c0df14c0d182f65f005ca5 ]

getrusage(RUSAGE_THREAD) with nohz_full may return shorter utime/stime
than the actual time.

task_cputime_adjusted() snapshots utime and stime and then adjust their
sum to match the scheduler maintained cputime.sum_exec_runtime.
Unfortunately in nohz_full, sum_exec_runtime is only updated once per
second in the worst case, causing a discrepancy against utime and stime
that can be updated anytime by the reader using vtime.

To fix this situation, perform an update of cputime.sum_exec_runtime
when the cputime snapshot reports the task as actually running while
the tick is disabled. The related overhead is then contained within the
relevant situations.

Reported-by: Hasegawa Hitomi <hasegawa-hitomi@...itsu.com>
Signed-off-by: Frederic Weisbecker <frederic@...nel.org>
Signed-off-by: Hasegawa Hitomi <hasegawa-hitomi@...itsu.com>
Signed-off-by: Thomas Gleixner <tglx@...utronix.de>
Tested-by: Masayoshi Mizuma <m.mizuma@...fujitsu.com>
Acked-by: Phil Auld <pauld@...hat.com>
Link: https://lore.kernel.org/r/20211026141055.57358-3-frederic@kernel.org
Signed-off-by: Sasha Levin <sashal@...nel.org>
---
 include/linux/sched/cputime.h |  5 +++--
 kernel/sched/cputime.c        | 12 +++++++++---
 2 files changed, 12 insertions(+), 5 deletions(-)

diff --git a/include/linux/sched/cputime.h b/include/linux/sched/cputime.h
index 6c9f19a33865a..ce3c58286062c 100644
--- a/include/linux/sched/cputime.h
+++ b/include/linux/sched/cputime.h
@@ -18,15 +18,16 @@
 #endif /* CONFIG_VIRT_CPU_ACCOUNTING_NATIVE */
 
 #ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN
-extern void task_cputime(struct task_struct *t,
+extern bool task_cputime(struct task_struct *t,
 			 u64 *utime, u64 *stime);
 extern u64 task_gtime(struct task_struct *t);
 #else
-static inline void task_cputime(struct task_struct *t,
+static inline bool task_cputime(struct task_struct *t,
 				u64 *utime, u64 *stime)
 {
 	*utime = t->utime;
 	*stime = t->stime;
+	return false;
 }
 
 static inline u64 task_gtime(struct task_struct *t)
diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c
index 5a55d23004524..9cd34730cf623 100644
--- a/kernel/sched/cputime.c
+++ b/kernel/sched/cputime.c
@@ -617,7 +617,8 @@ void task_cputime_adjusted(struct task_struct *p, u64 *ut, u64 *st)
 		.sum_exec_runtime = p->se.sum_exec_runtime,
 	};
 
-	task_cputime(p, &cputime.utime, &cputime.stime);
+	if (task_cputime(p, &cputime.utime, &cputime.stime))
+		cputime.sum_exec_runtime = task_sched_runtime(p);
 	cputime_adjust(&cputime, &p->prev_cputime, ut, st);
 }
 EXPORT_SYMBOL_GPL(task_cputime_adjusted);
@@ -830,19 +831,21 @@ u64 task_gtime(struct task_struct *t)
  * add up the pending nohz execution time since the last
  * cputime snapshot.
  */
-void task_cputime(struct task_struct *t, u64 *utime, u64 *stime)
+bool task_cputime(struct task_struct *t, u64 *utime, u64 *stime)
 {
 	struct vtime *vtime = &t->vtime;
 	unsigned int seq;
 	u64 delta;
+	int ret;
 
 	if (!vtime_accounting_enabled()) {
 		*utime = t->utime;
 		*stime = t->stime;
-		return;
+		return false;
 	}
 
 	do {
+		ret = false;
 		seq = read_seqcount_begin(&vtime->seqcount);
 
 		*utime = t->utime;
@@ -852,6 +855,7 @@ void task_cputime(struct task_struct *t, u64 *utime, u64 *stime)
 		if (vtime->state < VTIME_SYS)
 			continue;
 
+		ret = true;
 		delta = vtime_delta(vtime);
 
 		/*
@@ -863,6 +867,8 @@ void task_cputime(struct task_struct *t, u64 *utime, u64 *stime)
 		else
 			*utime += vtime->utime + delta;
 	} while (read_seqcount_retry(&vtime->seqcount, seq));
+
+	return ret;
 }
 
 static int vtime_state_fetch(struct vtime *vtime, int cpu)
-- 
2.33.0