From: Peter Zijlstra peterz@infradead.org

stable inclusion from stable-5.10.58 commit a3e6bd0c71bb5e4821aff9ab8f221bfc08039d73 bugzilla: 176984 https://gitee.com/openeuler/kernel/issues/I4E2P4

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id=...

--------------------------------

commit f558c2b834ec27e75d37b1c860c139e7b7c3a8e4 upstream.

Double enqueues in rt runqueues (list) have been reported while running a simple test that spawns a number of threads doing a short sleep/run pattern while being concurrently setscheduled between rt and fair class.

WARNING: CPU: 3 PID: 2825 at kernel/sched/rt.c:1294 enqueue_task_rt+0x355/0x360 CPU: 3 PID: 2825 Comm: setsched__13 RIP: 0010:enqueue_task_rt+0x355/0x360 Call Trace: __sched_setscheduler+0x581/0x9d0 _sched_setscheduler+0x63/0xa0 do_sched_setscheduler+0xa0/0x150 __x64_sys_sched_setscheduler+0x1a/0x30 do_syscall_64+0x33/0x40 entry_SYSCALL_64_after_hwframe+0x44/0xae

list_add double add: new=ffff9867cb629b40, prev=ffff9867cb629b40, next=ffff98679fc67ca0. kernel BUG at lib/list_debug.c:31! invalid opcode: 0000 [#1] PREEMPT_RT SMP PTI CPU: 3 PID: 2825 Comm: setsched__13 RIP: 0010:__list_add_valid+0x41/0x50 Call Trace: enqueue_task_rt+0x291/0x360 __sched_setscheduler+0x581/0x9d0 _sched_setscheduler+0x63/0xa0 do_sched_setscheduler+0xa0/0x150 __x64_sys_sched_setscheduler+0x1a/0x30 do_syscall_64+0x33/0x40 entry_SYSCALL_64_after_hwframe+0x44/0xae

__sched_setscheduler() uses rt_effective_prio() to handle proper queuing of priority boosted tasks that are setscheduled while being boosted. rt_effective_prio() is however called twice per each __sched_setscheduler() call: first directly by __sched_setscheduler() before dequeuing the task and then by __setscheduler() to actually do the priority change. If the priority of the pi_top_task is concurrently being changed however, it might happen that the two calls return different results. If, for example, the first call returned the same rt priority the task was running at and the second one a fair priority, the task won't be removed by the rt list (on_list still set) and then enqueued in the fair runqueue. When eventually setscheduled back to rt it will be seen as enqueued already and the WARNING/BUG be issued.

Fix this by calling rt_effective_prio() only once and then reusing the return value. While at it refactor code as well for clarity. Concurrent priority inheritance handling is still safe and will eventually converge to a new state by following the inheritance chain(s).

Fixes: 0782e63bc6fe ("sched: Handle priority boosted tasks proper in setscheduler()") [squashed Peterz changes; added changelog] Reported-by: Mark Simmons msimmons@redhat.com Signed-off-by: Juri Lelli juri.lelli@redhat.com Signed-off-by: Peter Zijlstra (Intel) peterz@infradead.org Link: https://lkml.kernel.org/r/20210803104501.38333-1-juri.lelli@redhat.com Signed-off-by: Greg Kroah-Hartman gregkh@linuxfoundation.org

Signed-off-by: Chen Jun chenjun102@huawei.com Acked-by: Weilong Chen chenweilong@huawei.com Signed-off-by: Chen Jun chenjun102@huawei.com Signed-off-by: Zheng Zucheng zhengzucheng@huawei.com --- kernel/sched/core.c | 95 ++++++++++++++++++--------------------------- 1 file changed, 37 insertions(+), 58 deletions(-)

diff --git a/kernel/sched/core.c b/kernel/sched/core.c index cb5c2f9be849..d5434cc99934 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -1590,12 +1590,18 @@ void deactivate_task(struct rq *rq, struct task_struct *p, int flags) dequeue_task(rq, p, flags); }

-/* - * __normal_prio - return the priority that is based on the static prio - */ -static inline int __normal_prio(struct task_struct *p) +static inline int __normal_prio(int policy, int rt_prio, int nice) { - return p->static_prio; + int prio; + + if (dl_policy(policy)) + prio = MAX_DL_PRIO - 1; + else if (rt_policy(policy)) + prio = MAX_RT_PRIO - 1 - rt_prio; + else + prio = NICE_TO_PRIO(nice); + + return prio; }

/* @@ -1607,15 +1613,7 @@ static inline int __normal_prio(struct task_struct *p) */ static inline int normal_prio(struct task_struct *p) { - int prio; - - if (task_has_dl_policy(p)) - prio = MAX_DL_PRIO-1; - else if (task_has_rt_policy(p)) - prio = MAX_RT_PRIO-1 - p->rt_priority; - else - prio = __normal_prio(p); - return prio; + return __normal_prio(p->policy, p->rt_priority, PRIO_TO_NICE(p->static_prio)); }

/* @@ -3240,7 +3238,7 @@ int sched_fork(unsigned long clone_flags, struct task_struct *p) } else if (PRIO_TO_NICE(p->static_prio) < 0) p->static_prio = NICE_TO_PRIO(0);

- p->prio = p->normal_prio = __normal_prio(p); + p->prio = p->normal_prio = p->static_prio; set_load_weight(p, false);

/* @@ -4986,6 +4984,18 @@ int default_wake_function(wait_queue_entry_t *curr, unsigned mode, int wake_flag } EXPORT_SYMBOL(default_wake_function);

+static void __setscheduler_prio(struct task_struct *p, int prio) +{ + if (dl_prio(prio)) + p->sched_class = &dl_sched_class; + else if (rt_prio(prio)) + p->sched_class = &rt_sched_class; + else + p->sched_class = &fair_sched_class; + + p->prio = prio; +} + #ifdef CONFIG_RT_MUTEXES

static inline int __rt_effective_prio(struct task_struct *pi_task, int prio) @@ -5101,22 +5111,19 @@ void rt_mutex_setprio(struct task_struct *p, struct task_struct *pi_task) } else { p->dl.pi_se = &p->dl; } - p->sched_class = &dl_sched_class; } else if (rt_prio(prio)) { if (dl_prio(oldprio)) p->dl.pi_se = &p->dl; if (oldprio < prio) queue_flag |= ENQUEUE_HEAD; - p->sched_class = &rt_sched_class; } else { if (dl_prio(oldprio)) p->dl.pi_se = &p->dl; if (rt_prio(oldprio)) p->rt.timeout = 0; - p->sched_class = &fair_sched_class; }

- p->prio = prio; + __setscheduler_prio(p, prio);

if (queued) enqueue_task(rq, p, queue_flag); @@ -5349,35 +5356,6 @@ static void __setscheduler_params(struct task_struct *p, set_load_weight(p, true); }

-/* Actually do priority change: must hold pi & rq lock. */ -static void __setscheduler(struct rq *rq, struct task_struct *p, - const struct sched_attr *attr, bool keep_boost) -{ - /* - * If params can't change scheduling class changes aren't allowed - * either. - */ - if (attr->sched_flags & SCHED_FLAG_KEEP_PARAMS) - return; - - __setscheduler_params(p, attr); - - /* - * Keep a potential priority boosting if called from - * sched_setscheduler(). - */ - p->prio = normal_prio(p); - if (keep_boost) - p->prio = rt_effective_prio(p, p->prio); - - if (dl_prio(p->prio)) - p->sched_class = &dl_sched_class; - else if (rt_prio(p->prio)) - p->sched_class = &rt_sched_class; - else - p->sched_class = &fair_sched_class; -} - /* * Check the target process has a UID that matches the current process's: */ @@ -5398,10 +5376,8 @@ static int __sched_setscheduler(struct task_struct *p, const struct sched_attr *attr, bool user, bool pi) { - int newprio = dl_policy(attr->sched_policy) ? MAX_DL_PRIO - 1 : - MAX_RT_PRIO - 1 - attr->sched_priority; - int retval, oldprio, oldpolicy = -1, queued, running; - int new_effective_prio, policy = attr->sched_policy; + int oldpolicy = -1, policy = attr->sched_policy; + int retval, oldprio, newprio, queued, running; const struct sched_class *prev_class; struct rq_flags rf; int reset_on_fork; @@ -5611,6 +5587,7 @@ static int __sched_setscheduler(struct task_struct *p, p->sched_reset_on_fork = reset_on_fork; oldprio = p->prio;

+ newprio = __normal_prio(policy, attr->sched_priority, attr->sched_nice); if (pi) { /* * Take priority boosted tasks into account. If the new @@ -5619,8 +5596,8 @@ static int __sched_setscheduler(struct task_struct *p, * the runqueue. This will be done when the task deboost * itself. */ - new_effective_prio = rt_effective_prio(p, newprio); - if (new_effective_prio == oldprio) + newprio = rt_effective_prio(p, newprio); + if (newprio == oldprio) queue_flags &= ~DEQUEUE_MOVE; }

@@ -5633,7 +5610,10 @@ static int __sched_setscheduler(struct task_struct *p,

prev_class = p->sched_class;

- __setscheduler(rq, p, attr, pi); + if (!(attr->sched_flags & SCHED_FLAG_KEEP_PARAMS)) { + __setscheduler_params(p, attr); + __setscheduler_prio(p, newprio); + } __setscheduler_uclamp(p, attr);

if (queued) { @@ -7640,7 +7620,6 @@ static inline int alloc_qos_sched_group(struct task_group *tg, static void sched_change_qos_group(struct task_struct *tsk, struct task_group *tg) { struct sched_attr attr; - struct rq *rq = task_rq(tsk);

/* * No need to re-setcheduler when a task is exiting or the task @@ -7651,8 +7630,8 @@ static void sched_change_qos_group(struct task_struct *tsk, struct task_group *t (tg->qos_level == -1)) { attr.sched_priority = 0; attr.sched_policy = SCHED_IDLE; - attr.sched_nice = PRIO_TO_NICE(tsk->static_prio); - __setscheduler(rq, tsk, &attr, 0); + __setscheduler_params(tsk, &attr); + __setscheduler_prio(tsk, tsk->static_prio); } }