Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1423672AbbFEO1R (ORCPT ); Fri, 5 Jun 2015 10:27:17 -0400 Received: from youngberry.canonical.com ([91.189.89.112]:59753 "EHLO youngberry.canonical.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1161018AbbFEN7a (ORCPT ); Fri, 5 Jun 2015 09:59:30 -0400 From: Luis Henriques To: linux-kernel@vger.kernel.org, stable@vger.kernel.org, kernel-team@lists.ubuntu.com Cc: Thomas Gleixner , "Peter Zijlstra (Intel)" , Borislav Petkov , "H. Peter Anvin" , Mike Galbraith , Ingo Molnar , Luis Henriques Subject: [PATCH 3.16.y-ckt 024/110] sched: Handle priority boosted tasks proper in setscheduler() Date: Fri, 5 Jun 2015 14:57:07 +0100 Message-Id: <1433512713-22984-25-git-send-email-luis.henriques@canonical.com> X-Mailer: git-send-email 2.1.4 In-Reply-To: <1433512713-22984-1-git-send-email-luis.henriques@canonical.com> References: <1433512713-22984-1-git-send-email-luis.henriques@canonical.com> X-Extended-Stable: 3.16 Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 6496 Lines: 184 3.16.7-ckt13 -stable review patch. If anyone has any objections, please let me know. ------------------ From: Thomas Gleixner commit 0782e63bc6fe7e2d3408d250df11d388b7799c6b upstream. Ronny reported that the following scenario is not handled correctly: T1 (prio = 10) lock(rtmutex); T2 (prio = 20) lock(rtmutex) boost T1 T1 (prio = 20) sys_set_scheduler(prio = 30) T1 prio = 30 .... sys_set_scheduler(prio = 10) T1 prio = 30 The last step is wrong as T1 should now be back at prio 20. Commit c365c292d059 ("sched: Consider pi boosting in setscheduler()") only handles the case where a boosted tasks tries to lower its priority. Fix it by taking the new effective priority into account for the decision whether a change of the priority is required. Reported-by: Ronny Meeus Tested-by: Steven Rostedt Signed-off-by: Thomas Gleixner Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Steven Rostedt Cc: Borislav Petkov Cc: H. Peter Anvin Cc: Mike Galbraith Fixes: c365c292d059 ("sched: Consider pi boosting in setscheduler()") Link: http://lkml.kernel.org/r/alpine.DEB.2.11.1505051806060.4225@nanos Signed-off-by: Ingo Molnar [ luis: backported to 3.16: adjusted context ] Signed-off-by: Luis Henriques --- include/linux/sched/rt.h | 7 ++++--- kernel/locking/rtmutex.c | 12 +++++++----- kernel/sched/core.c | 26 ++++++++++++++------------ 3 files changed, 25 insertions(+), 20 deletions(-) diff --git a/include/linux/sched/rt.h b/include/linux/sched/rt.h index 6341f5be6e24..a30b172df6e1 100644 --- a/include/linux/sched/rt.h +++ b/include/linux/sched/rt.h @@ -18,7 +18,7 @@ static inline int rt_task(struct task_struct *p) #ifdef CONFIG_RT_MUTEXES extern int rt_mutex_getprio(struct task_struct *p); extern void rt_mutex_setprio(struct task_struct *p, int prio); -extern int rt_mutex_check_prio(struct task_struct *task, int newprio); +extern int rt_mutex_get_effective_prio(struct task_struct *task, int newprio); extern struct task_struct *rt_mutex_get_top_task(struct task_struct *task); extern void rt_mutex_adjust_pi(struct task_struct *p); static inline bool tsk_is_pi_blocked(struct task_struct *tsk) @@ -31,9 +31,10 @@ static inline int rt_mutex_getprio(struct task_struct *p) return p->normal_prio; } -static inline int rt_mutex_check_prio(struct task_struct *task, int newprio) +static inline int rt_mutex_get_effective_prio(struct task_struct *task, + int newprio) { - return 0; + return newprio; } static inline struct task_struct *rt_mutex_get_top_task(struct task_struct *task) diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c index f9878d16b80b..3c9082036365 100644 --- a/kernel/locking/rtmutex.c +++ b/kernel/locking/rtmutex.c @@ -265,15 +265,17 @@ struct task_struct *rt_mutex_get_top_task(struct task_struct *task) } /* - * Called by sched_setscheduler() to check whether the priority change - * is overruled by a possible priority boosting. + * Called by sched_setscheduler() to get the priority which will be + * effective after the change. */ -int rt_mutex_check_prio(struct task_struct *task, int newprio) +int rt_mutex_get_effective_prio(struct task_struct *task, int newprio) { if (!task_has_pi_waiters(task)) - return 0; + return newprio; - return task_top_pi_waiter(task)->task->prio <= newprio; + if (task_top_pi_waiter(task)->task->prio <= newprio) + return task_top_pi_waiter(task)->task->prio; + return newprio; } /* diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 6356f644a47b..5c89af9ea192 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -3251,15 +3251,18 @@ static void __setscheduler_params(struct task_struct *p, /* Actually do priority change: must hold pi & rq lock. */ static void __setscheduler(struct rq *rq, struct task_struct *p, - const struct sched_attr *attr) + const struct sched_attr *attr, bool keep_boost) { __setscheduler_params(p, attr); /* - * If we get here, there was no pi waiters boosting the - * task. It is safe to use the normal prio. + * Keep a potential priority boosting if called from + * sched_setscheduler(). */ - p->prio = normal_prio(p); + if (keep_boost) + p->prio = rt_mutex_get_effective_prio(p, normal_prio(p)); + else + p->prio = normal_prio(p); if (dl_prio(p->prio)) p->sched_class = &dl_sched_class; @@ -3345,7 +3348,7 @@ static int __sched_setscheduler(struct task_struct *p, int newprio = dl_policy(attr->sched_policy) ? MAX_DL_PRIO - 1 : MAX_RT_PRIO - 1 - attr->sched_priority; int retval, oldprio, oldpolicy = -1, on_rq, running; - int policy = attr->sched_policy; + int new_effective_prio, policy = attr->sched_policy; unsigned long flags; const struct sched_class *prev_class; struct rq *rq; @@ -3527,15 +3530,14 @@ change: oldprio = p->prio; /* - * Special case for priority boosted tasks. - * - * If the new priority is lower or equal (user space view) - * than the current (boosted) priority, we just store the new + * Take priority boosted tasks into account. If the new + * effective priority is unchanged, we just store the new * normal parameters and do not touch the scheduler class and * the runqueue. This will be done when the task deboost * itself. */ - if (rt_mutex_check_prio(p, newprio)) { + new_effective_prio = rt_mutex_get_effective_prio(p, newprio); + if (new_effective_prio == oldprio) { __setscheduler_params(p, attr); task_rq_unlock(rq, p, &flags); return 0; @@ -3549,7 +3551,7 @@ change: p->sched_class->put_prev_task(rq, p); prev_class = p->sched_class; - __setscheduler(rq, p, attr); + __setscheduler(rq, p, attr, true); if (running) p->sched_class->set_curr_task(rq); @@ -7112,7 +7114,7 @@ static void normalize_task(struct rq *rq, struct task_struct *p) on_rq = p->on_rq; if (on_rq) dequeue_task(rq, p, 0); - __setscheduler(rq, p, &attr); + __setscheduler(rq, p, &attr, false); if (on_rq) { enqueue_task(rq, p, 0); resched_task(rq->curr); -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/