linux-kernel - [patch V5 35/72] locking/rtmutex: Squash !RT tasks to DEFAULT

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: <20210815211303.938676930@linutronix.de>
Date:   Sun, 15 Aug 2021 23:28:30 +0200 (CEST)
From:   Thomas Gleixner <tglx@...utronix.de>
To:     LKML <linux-kernel@...r.kernel.org>
Cc:     Peter Zijlstra <peterz@...radead.org>,
        Ingo Molnar <mingo@...nel.org>,
        Juri Lelli <juri.lelli@...hat.com>,
        Steven Rostedt <rostedt@...dmis.org>,
        Daniel Bristot de Oliveira <bristot@...hat.com>,
        Will Deacon <will@...nel.org>,
        Waiman Long <longman@...hat.com>,
        Boqun Feng <boqun.feng@...il.com>,
        Sebastian Andrzej Siewior <bigeasy@...utronix.de>,
        Davidlohr Bueso <dave@...olabs.net>,
        Mike Galbraith <efault@....de>
Subject: [patch V5 35/72] locking/rtmutex: Squash !RT tasks to DEFAULT_PRIO

Ensure all !RT tasks have the same prio such that they end up in FIFO
order and aren't split up according to nice level.

The reason why nice levels were taken into account so far is historical. In
the early days of the rtmutex code it was done to give the PI boosting and
deboosting a larger coverage.

Signed-off-by: Peter Zijlstra (Intel) <peterz@...radead.org>
Signed-off-by: Thomas Gleixner <tglx@...utronix.de>
---
V4: Picked up as a new patch
---
---
 kernel/locking/rtmutex.c |   25 ++++++++++++++++++++-----
 1 file changed, 20 insertions(+), 5 deletions(-)

--- a/kernel/locking/rtmutex.c
+++ b/kernel/locking/rtmutex.c
@@ -244,11 +244,28 @@ static __always_inline bool unlock_rt_mu
 }
 #endif
 
+static __always_inline int __waiter_prio(struct task_struct *task)
+{
+	int prio = task->prio;
+
+	if (!rt_prio(prio))
+		return DEFAULT_PRIO;
+
+	return prio;
+}
+
+static __always_inline void
+waiter_update_prio(struct rt_mutex_waiter *waiter, struct task_struct *task)
+{
+	waiter->prio = __waiter_prio(task);
+	waiter->deadline = task->dl.deadline;
+}
+
 /*
  * Only use with rt_mutex_waiter_{less,equal}()
  */
 #define task_to_waiter(p)	\
-	&(struct rt_mutex_waiter){ .prio = (p)->prio, .deadline = (p)->dl.deadline }
+	&(struct rt_mutex_waiter){ .prio = __waiter_prio(p), .deadline = (p)->dl.deadline }
 
 static __always_inline int rt_mutex_waiter_less(struct rt_mutex_waiter *left,
 						struct rt_mutex_waiter *right)
@@ -698,8 +715,7 @@ static int __sched rt_mutex_adjust_prio_
 	 * serializes all pi_waiters access and rb_erase() does not care about
 	 * the values of the node being removed.
 	 */
-	waiter->prio = task->prio;
-	waiter->deadline = task->dl.deadline;
+	waiter_update_prio(waiter, task);
 
 	rt_mutex_enqueue(lock, waiter);
 
@@ -969,8 +985,7 @@ static int __sched task_blocks_on_rt_mut
 	raw_spin_lock(&task->pi_lock);
 	waiter->task = task;
 	waiter->lock = lock;
-	waiter->prio = task->prio;
-	waiter->deadline = task->dl.deadline;
+	waiter_update_prio(waiter, task);
 
 	/* Get the top priority waiter on the lock */
 	if (rt_mutex_has_waiters(lock))