From c0422b83fc69f41298b94d21093638bceec6af43 Mon Sep 17 00:00:00 2001 From: meganz009 Date: Thu, 1 Jun 2023 16:31:43 +0800 Subject: [PATCH 1/9] sched: Fix hotplug vs CPU bandwidth control commit 8d84c740bec416a7645fc0d61caa793a657dbb72 upstream. Since we now migrate tasks away before DYING, we should also move bandwidth unthrottle, otherwise we can gain tasks from unthrottle after we expect all tasks to be gone already. Also; it looks like the RT balancers don't respect cpu_active() and instead rely on rq->online in part, complete this. This too requires we do set_rq_offline() earlier to match the cpu_active() semantics. (The bigger patch is to convert RT to cpu_active() entirely) Since set_rq_online() is called from sched_cpu_activate(), place set_rq_offline() in sched_cpu_deactivate(). Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Sebastian Andrzej Siewior --- kernel/sched/core.c | 14 ++++++++++---- kernel/sched/deadline.c | 2 +- kernel/sched/rt.c | 2 +- 3 files changed, 12 insertions(+), 6 deletions(-) diff --git a/kernel/sched/core.c b/kernel/sched/core.c index f3efa710397d..bb4a23b2ac9b 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -7036,6 +7036,8 @@ int sched_cpu_activate(unsigned int cpu) int sched_cpu_deactivate(unsigned int cpu) { + struct rq *rq = cpu_rq(cpu); + struct rq_flags rf; int ret; set_cpu_active(cpu, false); @@ -7050,6 +7052,14 @@ int sched_cpu_deactivate(unsigned int cpu) balance_push_set(cpu, true); + rq_lock_irqsave(rq, &rf); + if (rq->rd) { + update_rq_clock(rq); + BUG_ON(!cpumask_test_cpu(cpu, rq->rd->span)); + set_rq_offline(rq); + } + rq_unlock_irqrestore(rq, &rf); + #ifdef CONFIG_SCHED_SMT /* * When going down, decrement the number of cores with SMT present. @@ -7135,10 +7145,6 @@ int sched_cpu_dying(unsigned int cpu) sched_tick_stop(cpu); rq_lock_irqsave(rq, &rf); - if (rq->rd) { - BUG_ON(!cpumask_test_cpu(cpu, rq->rd->span)); - set_rq_offline(rq); - } BUG_ON(rq->nr_running != 1); rq_unlock_irqrestore(rq, &rf); diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c index af1b97d2456e..d72c2fdb4b37 100644 --- a/kernel/sched/deadline.c +++ b/kernel/sched/deadline.c @@ -551,7 +551,7 @@ static int push_dl_task(struct rq *rq); static inline bool need_pull_dl_task(struct rq *rq, struct task_struct *prev) { - return dl_task(prev); + return rq->online && dl_task(prev); } static DEFINE_PER_CPU(struct callback_head, dl_push_head); diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c index 79a870d4f963..c8bcccae731e 100644 --- a/kernel/sched/rt.c +++ b/kernel/sched/rt.c @@ -270,7 +270,7 @@ static void pull_rt_task(struct rq *this_rq); static inline bool need_pull_rt_task(struct rq *rq, struct task_struct *prev) { /* Try to pull RT tasks here if we lower this rq's prio */ - return rq->rt.highest_prio.curr > prev->prio; + return rq->online && rq->rt.highest_prio.curr > prev->prio; } static inline int rt_overloaded(struct rq *rq) -- Gitee From 97a1dc264975944399a13f365d37842827969677 Mon Sep 17 00:00:00 2001 From: meganz009 Date: Thu, 1 Jun 2023 16:42:11 +0800 Subject: [PATCH 2/9] sched: Massage set_cpus_allowed() commit 687d196c9c3d44ec18d2cad10d5a500be9c771eb upstream. Thread a u32 flags word through the *set_cpus_allowed*() callchain. This will allow adding behavioural tweaks for future users. Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Sebastian Andrzej Siewior --- kernel/sched/core.c | 28 ++++++++++++++++++---------- kernel/sched/deadline.c | 5 +++-- kernel/sched/sched.h | 7 +++++-- 3 files changed, 26 insertions(+), 14 deletions(-) diff --git a/kernel/sched/core.c b/kernel/sched/core.c index bb4a23b2ac9b..6fe6a9d772f1 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -1850,13 +1850,14 @@ static int migration_cpu_stop(void *data) * sched_class::set_cpus_allowed must do the below, but is not required to * actually call this function. */ -void set_cpus_allowed_common(struct task_struct *p, const struct cpumask *new_mask) +void set_cpus_allowed_common(struct task_struct *p, const struct cpumask *new_mask, u32 flags) { cpumask_copy(&p->cpus_mask, new_mask); p->nr_cpus_allowed = cpumask_weight(new_mask); } -void do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask) +static void +__do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask, u32 flags) { struct rq *rq = task_rq(p); bool queued, running; @@ -1877,7 +1878,7 @@ void do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask) if (running) put_prev_task(rq, p); - p->sched_class->set_cpus_allowed(p, new_mask); + p->sched_class->set_cpus_allowed(p, new_mask, flags); if (queued) enqueue_task(rq, p, ENQUEUE_RESTORE | ENQUEUE_NOCLOCK); @@ -1885,6 +1886,11 @@ void do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask) set_next_task(rq, p); } +void do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask) +{ + __do_set_cpus_allowed(p, new_mask, 0); +} + /* * Change a given task's CPU affinity. Migrate the thread to a * proper CPU and schedule it away if the CPU it's executing on @@ -1895,7 +1901,8 @@ void do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask) * call is not atomic; no spinlocks may be held. */ static int __set_cpus_allowed_ptr(struct task_struct *p, - const struct cpumask *new_mask, bool check) + const struct cpumask *new_mask, + u32 flags) { const struct cpumask *cpu_valid_mask = cpu_active_mask; unsigned int dest_cpu; @@ -1917,7 +1924,7 @@ static int __set_cpus_allowed_ptr(struct task_struct *p, * Must re-check here, to close a race against __kthread_bind(), * sched_setaffinity() is not guaranteed to observe the flag. */ - if (check && (p->flags & PF_NO_SETAFFINITY)) { + if ((flags & SCA_CHECK) && (p->flags & PF_NO_SETAFFINITY)) { ret = -EINVAL; goto out; } @@ -1936,7 +1943,7 @@ static int __set_cpus_allowed_ptr(struct task_struct *p, goto out; } - do_set_cpus_allowed(p, new_mask); + __do_set_cpus_allowed(p, new_mask, flags); if (p->flags & PF_KTHREAD) { /* @@ -1973,7 +1980,7 @@ static int __set_cpus_allowed_ptr(struct task_struct *p, int set_cpus_allowed_ptr(struct task_struct *p, const struct cpumask *new_mask) { - return __set_cpus_allowed_ptr(p, new_mask, false); + return __set_cpus_allowed_ptr(p, new_mask, 0); } EXPORT_SYMBOL_GPL(set_cpus_allowed_ptr); @@ -2433,7 +2440,8 @@ void sched_set_stop_task(int cpu, struct task_struct *stop) #else static inline int __set_cpus_allowed_ptr(struct task_struct *p, - const struct cpumask *new_mask, bool check) + const struct cpumask *new_mask, + u32 flags) { return set_cpus_allowed_ptr(p, new_mask); } @@ -6073,7 +6081,7 @@ long sched_setaffinity(pid_t pid, const struct cpumask *in_mask) } #endif again: - retval = __set_cpus_allowed_ptr(p, new_mask, true); + retval = __set_cpus_allowed_ptr(p, new_mask, SCA_CHECK); if (!retval) { cpuset_cpus_allowed(p, cpus_allowed); @@ -6649,7 +6657,7 @@ void __init init_idle(struct task_struct *idle, int cpu) * * And since this is boot we can forgo the serialization. */ - set_cpus_allowed_common(idle, cpumask_of(cpu)); + set_cpus_allowed_common(idle, cpumask_of(cpu), 0); #endif /* * We're having a chicken and egg problem, even though we are diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c index d72c2fdb4b37..4bc48eafa392 100644 --- a/kernel/sched/deadline.c +++ b/kernel/sched/deadline.c @@ -2290,7 +2290,8 @@ static void task_woken_dl(struct rq *rq, struct task_struct *p) } static void set_cpus_allowed_dl(struct task_struct *p, - const struct cpumask *new_mask) + const struct cpumask *new_mask, + u32 flags) { struct root_domain *src_rd; struct rq *rq; @@ -2319,7 +2320,7 @@ static void set_cpus_allowed_dl(struct task_struct *p, raw_spin_unlock(&src_dl_b->lock); } - set_cpus_allowed_common(p, new_mask); + set_cpus_allowed_common(p, new_mask, flags); } /* Assumes rq->lock is held */ diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index 8abcef232448..4269e38d46b0 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -2032,7 +2032,8 @@ struct sched_class { void (*task_woken)(struct rq *this_rq, struct task_struct *task); void (*set_cpus_allowed)(struct task_struct *p, - const struct cpumask *newmask); + const struct cpumask *newmask, + u32 flags); void (*rq_online)(struct rq *rq); void (*rq_offline)(struct rq *rq); @@ -2143,7 +2144,9 @@ extern void update_group_capacity(struct sched_domain *sd, int cpu); extern void trigger_load_balance(struct rq *rq); -extern void set_cpus_allowed_common(struct task_struct *p, const struct cpumask *new_mask); +#define SCA_CHECK 0x01 + +extern void set_cpus_allowed_common(struct task_struct *p, const struct cpumask *new_mask, u32 flags); #endif -- Gitee From dcc252c0aaa8a4e2f94b9eb2519ab1d7e106624f Mon Sep 17 00:00:00 2001 From: meganz009 Date: Thu, 1 Jun 2023 22:26:00 +0800 Subject: [PATCH 3/9] sched: Add migrate_disable() commit 8c22c6ba30bf5f5d0eb1c54e2b0e8ba52320ea9a upstream. Add the base migrate_disable() support (under protest). While migrate_disable() is (currently) required for PREEMPT_RT, it is also one of the biggest flaws in the system. Notably this is just the base implementation, it is broken vs sched_setaffinity() and hotplug, both solved in additional patches for ease of review. Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Sebastian Andrzej Siewior --- include/linux/preempt.h | 65 +++++++++++++++++++++++ include/linux/sched.h | 3 ++ kernel/sched/core.c | 112 +++++++++++++++++++++++++++++++++++++--- kernel/sched/sched.h | 6 ++- lib/smp_processor_id.c | 5 ++ 5 files changed, 183 insertions(+), 8 deletions(-) diff --git a/include/linux/preempt.h b/include/linux/preempt.h index 7d9c1c0e149c..97ba7c920653 100644 --- a/include/linux/preempt.h +++ b/include/linux/preempt.h @@ -322,6 +322,69 @@ static inline void preempt_notifier_init(struct preempt_notifier *notifier, #endif +#if defined(CONFIG_SMP) && defined(CONFIG_PREEMPT_RT) + +/* + * Migrate-Disable and why it is (strongly) undesired. + * + * The premise of the Real-Time schedulers we have on Linux + * (SCHED_FIFO/SCHED_DEADLINE) is that M CPUs can/will run M tasks + * concurrently, provided there are sufficient runnable tasks, also known as + * work-conserving. For instance SCHED_DEADLINE tries to schedule the M + * earliest deadline threads, and SCHED_FIFO the M highest priority threads. + * + * The correctness of various scheduling models depends on this, but is it + * broken by migrate_disable() that doesn't imply preempt_disable(). Where + * preempt_disable() implies an immediate priority ceiling, preemptible + * migrate_disable() allows nesting. + * + * The worst case is that all tasks preempt one another in a migrate_disable() + * region and stack on a single CPU. This then reduces the available bandwidth + * to a single CPU. And since Real-Time schedulability theory considers the + * Worst-Case only, all Real-Time analysis shall revert to single-CPU + * (instantly solving the SMP analysis problem). + * + * + * The reason we have it anyway. + * + * PREEMPT_RT breaks a number of assumptions traditionally held. By forcing a + * number of primitives into becoming preemptible, they would also allow + * migration. This turns out to break a bunch of per-cpu usage. To this end, + * all these primitives employ migirate_disable() to restore this implicit + * assumption. + * + * This is a 'temporary' work-around at best. The correct solution is getting + * rid of the above assumptions and reworking the code to employ explicit + * per-cpu locking or short preempt-disable regions. + * + * The end goal must be to get rid of migrate_disable(), alternatively we need + * a schedulability theory that does not depend on abritrary migration. + * + * + * Notes on the implementation. + * + * The implementation is particularly tricky since existing code patterns + * dictate neither migrate_disable() nor migrate_enable() is allowed to block. + * This means that it cannot use cpus_read_lock() to serialize against hotplug, + * nor can it easily migrate itself into a pending affinity mask change on + * migrate_enable(). + * + * + * Note: even non-work-conserving schedulers like semi-partitioned depends on + * migration, so migrate_disable() is not only a problem for + * work-conserving schedulers. + * + */ +extern void migrate_disable(void); +extern void migrate_enable(void); + +#elif defined(CONFIG_PREEMPT_RT) + +static inline void migrate_disable(void) { } +static inline void migrate_enable(void) { } + +#else /* !CONFIG_PREEMPT_RT */ + /** * migrate_disable - Prevent migration of the current task * @@ -352,4 +415,6 @@ static __always_inline void migrate_enable(void) preempt_enable(); } +#endif /* CONFIG_SMP && CONFIG_PREEMPT_RT */ + #endif /* __LINUX_PREEMPT_H */ diff --git a/include/linux/sched.h b/include/linux/sched.h index 23e47e38b3ba..def172a64b33 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -829,6 +829,9 @@ struct task_struct { int nr_cpus_allowed; const cpumask_t *cpus_ptr; cpumask_t cpus_mask; +#if defined(CONFIG_SMP) && defined(CONFIG_PREEMPT_RT) + int migration_disabled; +#endif #ifdef CONFIG_PREEMPT_RCU int rcu_read_lock_nesting; diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 6fe6a9d772f1..05d3be03a5f2 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -1722,6 +1722,61 @@ void check_preempt_curr(struct rq *rq, struct task_struct *p, int flags) #ifdef CONFIG_SMP +#ifdef CONFIG_PREEMPT_RT + +static void +__do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask, u32 flags); + +static int __set_cpus_allowed_ptr(struct task_struct *p, + const struct cpumask *new_mask, + u32 flags); + +static void migrate_disable_switch(struct rq *rq, struct task_struct *p) +{ + if (likely(!p->migration_disabled)) + return; + + if (p->cpus_ptr != &p->cpus_mask) + return; + + /* + * Violates locking rules! see comment in __do_set_cpus_allowed(). + */ + __do_set_cpus_allowed(p, cpumask_of(rq->cpu), SCA_MIGRATE_DISABLE); +} + +void migrate_disable(void) +{ + if (current->migration_disabled++) + return; + + barrier(); +} +EXPORT_SYMBOL_GPL(migrate_disable); + +void migrate_enable(void) +{ + struct task_struct *p = current; + + if (--p->migration_disabled) + return; + + barrier(); + + if (p->cpus_ptr == &p->cpus_mask) + return; + + __set_cpus_allowed_ptr(p, &p->cpus_mask, SCA_MIGRATE_ENABLE); +} +EXPORT_SYMBOL_GPL(migrate_enable); + +static inline bool is_migration_disabled(struct task_struct *p) +{ + return p->migration_disabled; +} + +#endif + /* * Per-CPU kthreads are allowed to run on !active && online CPUs, see * __set_cpus_allowed_ptr() and select_fallback_rq(). @@ -1731,7 +1786,7 @@ static inline bool is_cpu_allowed(struct task_struct *p, int cpu) if (!cpumask_test_cpu(cpu, p->cpus_ptr)) return false; - if (is_per_cpu_kthread(p)) + if (is_per_cpu_kthread(p) || is_migration_disabled(p)) return cpu_online(cpu); return cpu_active(cpu); @@ -1852,6 +1907,11 @@ static int migration_cpu_stop(void *data) */ void set_cpus_allowed_common(struct task_struct *p, const struct cpumask *new_mask, u32 flags) { + if (flags & (SCA_MIGRATE_ENABLE | SCA_MIGRATE_DISABLE)) { + p->cpus_ptr = new_mask; + return; + } + cpumask_copy(&p->cpus_mask, new_mask); p->nr_cpus_allowed = cpumask_weight(new_mask); } @@ -1862,7 +1922,22 @@ __do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask, u32 struct rq *rq = task_rq(p); bool queued, running; - lockdep_assert_held(&p->pi_lock); + /* + * This here violates the locking rules for affinity, since we're only + * supposed to change these variables while holding both rq->lock and + * p->pi_lock. + * + * HOWEVER, it magically works, because ttwu() is the only code that + * accesses these variables under p->pi_lock and only does so after + * smp_cond_load_acquire(&p->on_cpu, !VAL), and we're in __schedule() + * before finish_task(). + * + * XXX do further audits, this smells like something putrid. + */ + if (flags & SCA_MIGRATE_DISABLE) + SCHED_WARN_ON(!p->on_cpu); + else + lockdep_assert_held(&p->pi_lock); queued = task_on_rq_queued(p); running = task_current(rq, p); @@ -1913,9 +1988,14 @@ static int __set_cpus_allowed_ptr(struct task_struct *p, rq = task_rq_lock(p, &rf); update_rq_clock(rq); - if (p->flags & PF_KTHREAD) { + if (p->flags & PF_KTHREAD || is_migration_disabled(p)) { /* - * Kernel threads are allowed on online && !active CPUs + * Kernel threads are allowed on online && !active CPUs. + * + * Specifically, migration_disabled() tasks must not fail the + * cpumask_any_and_distribute() pick below, esp. so on + * SCA_MIGRATE_ENABLE, otherwise we'll not call + * set_cpus_allowed_common() and actually reset p->cpus_ptr. */ cpu_valid_mask = cpu_online_mask; } @@ -1929,7 +2009,7 @@ static int __set_cpus_allowed_ptr(struct task_struct *p, goto out; } - if (cpumask_equal(&p->cpus_mask, new_mask)) + if (!(flags & SCA_MIGRATE_ENABLE) && cpumask_equal(&p->cpus_mask, new_mask)) goto out; /* @@ -2021,6 +2101,8 @@ void set_task_cpu(struct task_struct *p, unsigned int new_cpu) * Clearly, migrating tasks to offline CPUs is a fairly daft thing. */ WARN_ON_ONCE(!cpu_online(new_cpu)); + + WARN_ON_ONCE(is_migration_disabled(p)); #endif trace_sched_migrate_task(p, new_cpu); @@ -2352,6 +2434,12 @@ static int select_fallback_rq(int cpu, struct task_struct *p) } fallthrough; case possible: + /* + * XXX When called from select_task_rq() we only + * hold p->pi_lock and again violate locking order. + * + * More yuck to audit. + */ do_set_cpus_allowed(p, cpu_possible_mask); state = fail; break; @@ -2386,7 +2474,7 @@ int select_task_rq(struct task_struct *p, int cpu, int sd_flags, int wake_flags) { lockdep_assert_held(&p->pi_lock); - if (p->nr_cpus_allowed > 1) + if (p->nr_cpus_allowed > 1 && !is_migration_disabled(p)) cpu = p->sched_class->select_task_rq(p, cpu, sd_flags, wake_flags); else cpu = cpumask_any(p->cpus_ptr); @@ -2448,6 +2536,17 @@ static inline int __set_cpus_allowed_ptr(struct task_struct *p, #endif /* CONFIG_SMP */ +#if !defined(CONFIG_SMP) || !defined(CONFIG_PREEMPT_RT) + +static inline void migrate_disable_switch(struct rq *rq, struct task_struct *p) { } + +static inline bool is_migration_disabled(struct task_struct *p) +{ + return false; +} + +#endif + static void ttwu_stat(struct task_struct *p, int cpu, int wake_flags) { @@ -4651,6 +4750,7 @@ static void __sched notrace __schedule(bool preempt) */ ++*switch_count; + migrate_disable_switch(rq, prev); psi_sched_switch(prev, next, !task_on_rq_queued(prev)); trace_sched_switch(preempt, prev, next); diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index 4269e38d46b0..b40b2c6d640e 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -2138,14 +2138,16 @@ static inline bool sched_fair_runnable(struct rq *rq) extern struct task_struct *pick_next_task_fair(struct rq *rq, struct task_struct *prev, struct rq_flags *rf); extern struct task_struct *pick_next_task_idle(struct rq *rq); +#define SCA_CHECK 0x01 +#define SCA_MIGRATE_DISABLE 0x02 +#define SCA_MIGRATE_ENABLE 0x04 + #ifdef CONFIG_SMP extern void update_group_capacity(struct sched_domain *sd, int cpu); extern void trigger_load_balance(struct rq *rq); -#define SCA_CHECK 0x01 - extern void set_cpus_allowed_common(struct task_struct *p, const struct cpumask *new_mask, u32 flags); #endif diff --git a/lib/smp_processor_id.c b/lib/smp_processor_id.c index 525222e4f409..faaa927ac2c8 100644 --- a/lib/smp_processor_id.c +++ b/lib/smp_processor_id.c @@ -26,6 +26,11 @@ unsigned int check_preemption_disabled(const char *what1, const char *what2) if (current->nr_cpus_allowed == 1) goto out; +#if defined(CONFIG_SMP) && defined(CONFIG_PREEMPT_RT) + if (current->migration_disabled) + goto out; +#endif + /* * It is valid to assume CPU-locality during early bootup: */ -- Gitee From 8da17d88109f9b1a20c4fcdc02e4411d4c798ff2 Mon Sep 17 00:00:00 2001 From: meganz009 Date: Thu, 1 Jun 2023 22:27:45 +0800 Subject: [PATCH 4/9] sched: Fix migrate_disable() vs set_cpus_allowed_ptr() commit 77654a617091779773a06f8450c387c2bbe6c247 upstream. Concurrent migrate_disable() and set_cpus_allowed_ptr() has interesting features. We rely on set_cpus_allowed_ptr() to not return until the task runs inside the provided mask. This expectation is exported to userspace. This means that any set_cpus_allowed_ptr() caller must wait until migrate_enable() allows migrations. At the same time, we don't want migrate_enable() to schedule, due to patterns like: preempt_disable(); migrate_disable(); ... migrate_enable(); preempt_enable(); And: raw_spin_lock(&B); spin_unlock(&A); this means that when migrate_enable() must restore the affinity mask, it cannot wait for completion thereof. Luck will have it that that is exactly the case where there is a pending set_cpus_allowed_ptr(), so let that provide storage for the async stop machine. Much thanks to Valentin who used TLA+ most effective and found lots of 'interesting' cases. Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Sebastian Andrzej Siewior --- include/linux/sched.h | 1 + kernel/sched/core.c | 234 ++++++++++++++++++++++++++++++++++++------ 2 files changed, 205 insertions(+), 30 deletions(-) diff --git a/include/linux/sched.h b/include/linux/sched.h index def172a64b33..848b36badbed 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -829,6 +829,7 @@ struct task_struct { int nr_cpus_allowed; const cpumask_t *cpus_ptr; cpumask_t cpus_mask; + void *migration_pending; #if defined(CONFIG_SMP) && defined(CONFIG_PREEMPT_RT) int migration_disabled; #endif diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 05d3be03a5f2..3f368f2f86fd 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -1758,15 +1758,26 @@ void migrate_enable(void) { struct task_struct *p = current; - if (--p->migration_disabled) + if (p->migration_disabled > 1) { + p->migration_disabled--; return; + } + /* + * Ensure stop_task runs either before or after this, and that + * __set_cpus_allowed_ptr(SCA_MIGRATE_ENABLE) doesn't schedule(). + */ + preempt_disable(); + if (p->cpus_ptr != &p->cpus_mask) + __set_cpus_allowed_ptr(p, &p->cpus_mask, SCA_MIGRATE_ENABLE); + /* + * Mustn't clear migration_disabled() until cpus_ptr points back at the + * regular cpus_mask, otherwise things that race (eg. + * select_fallback_rq) get confused. + */ barrier(); - - if (p->cpus_ptr == &p->cpus_mask) - return; - - __set_cpus_allowed_ptr(p, &p->cpus_mask, SCA_MIGRATE_ENABLE); + p->migration_disabled = 0; + preempt_enable(); } EXPORT_SYMBOL_GPL(migrate_enable); @@ -1831,8 +1842,16 @@ static struct rq *move_queued_task(struct rq *rq, struct rq_flags *rf, } struct migration_arg { - struct task_struct *task; - int dest_cpu; + struct task_struct *task; + int dest_cpu; + struct set_affinity_pending *pending; +}; + +struct set_affinity_pending { + refcount_t refs; + struct completion done; + struct cpu_stop_work stop_work; + struct migration_arg arg; }; /* @@ -1864,16 +1883,19 @@ static struct rq *__migrate_task(struct rq *rq, struct rq_flags *rf, */ static int migration_cpu_stop(void *data) { + struct set_affinity_pending *pending; struct migration_arg *arg = data; struct task_struct *p = arg->task; + int dest_cpu = arg->dest_cpu; struct rq *rq = this_rq(); + bool complete = false; struct rq_flags rf; /* * The original target CPU might have gone down and we might * be on another CPU but it doesn't matter. */ - local_irq_disable(); + local_irq_save(rf.flags); /* * We need to explicitly wake pending tasks before running * __migrate_task() such that we will not miss enforcing cpus_ptr @@ -1883,21 +1905,83 @@ static int migration_cpu_stop(void *data) raw_spin_lock(&p->pi_lock); rq_lock(rq, &rf); + + pending = p->migration_pending; /* * If task_rq(p) != rq, it cannot be migrated here, because we're * holding rq->lock, if p->on_rq == 0 it cannot get enqueued because * we're holding p->pi_lock. */ if (task_rq(p) == rq) { + if (is_migration_disabled(p)) + goto out; + + if (pending) { + p->migration_pending = NULL; + complete = true; + } + + /* migrate_enable() -- we must not race against SCA */ + if (dest_cpu < 0) { + /* + * When this was migrate_enable() but we no longer + * have a @pending, a concurrent SCA 'fixed' things + * and we should be valid again. Nothing to do. + */ + if (!pending) { + WARN_ON_ONCE(!is_cpu_allowed(p, cpu_of(rq))); + goto out; + } + + dest_cpu = cpumask_any_distribute(&p->cpus_mask); + } + if (task_on_rq_queued(p)) - rq = __migrate_task(rq, &rf, p, arg->dest_cpu); + rq = __migrate_task(rq, &rf, p, dest_cpu); else - p->wake_cpu = arg->dest_cpu; + p->wake_cpu = dest_cpu; + + } else if (dest_cpu < 0) { + /* + * This happens when we get migrated between migrate_enable()'s + * preempt_enable() and scheduling the stopper task. At that + * point we're a regular task again and not current anymore. + * + * A !PREEMPT kernel has a giant hole here, which makes it far + * more likely. + */ + + /* + * When this was migrate_enable() but we no longer have an + * @pending, a concurrent SCA 'fixed' things and we should be + * valid again. Nothing to do. + */ + if (!pending) { + WARN_ON_ONCE(!is_cpu_allowed(p, cpu_of(rq))); + goto out; + } + + /* + * When migrate_enable() hits a rq mis-match we can't reliably + * determine is_migration_disabled() and so have to chase after + * it. + */ + task_rq_unlock(rq, p, &rf); + stop_one_cpu_nowait(task_cpu(p), migration_cpu_stop, + &pending->arg, &pending->stop_work); + return 0; } - rq_unlock(rq, &rf); - raw_spin_unlock(&p->pi_lock); +out: + task_rq_unlock(rq, p, &rf); + + if (complete) + complete_all(&pending->done); + + /* For pending->{arg,stop_work} */ + pending = arg->pending; + if (pending && refcount_dec_and_test(&pending->refs)) + wake_up_var(&pending->refs); - local_irq_enable(); return 0; } @@ -1966,6 +2050,110 @@ void do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask) __do_set_cpus_allowed(p, new_mask, 0); } +/* + * This function is wildly self concurrent, consider at least 3 times. + */ +static int affine_move_task(struct rq *rq, struct task_struct *p, struct rq_flags *rf, + int dest_cpu, unsigned int flags) +{ + struct set_affinity_pending my_pending = { }, *pending = NULL; + struct migration_arg arg = { + .task = p, + .dest_cpu = dest_cpu, + }; + bool complete = false; + + /* Can the task run on the task's current CPU? If so, we're done */ + if (cpumask_test_cpu(task_cpu(p), &p->cpus_mask)) { + pending = p->migration_pending; + if (pending) { + refcount_inc(&pending->refs); + p->migration_pending = NULL; + complete = true; + } + task_rq_unlock(rq, p, rf); + + if (complete) + goto do_complete; + + return 0; + } + + if (!(flags & SCA_MIGRATE_ENABLE)) { + /* serialized by p->pi_lock */ + if (!p->migration_pending) { + refcount_set(&my_pending.refs, 1); + init_completion(&my_pending.done); + p->migration_pending = &my_pending; + } else { + pending = p->migration_pending; + refcount_inc(&pending->refs); + } + } + pending = p->migration_pending; + /* + * - !MIGRATE_ENABLE: + * we'll have installed a pending if there wasn't one already. + * + * - MIGRATE_ENABLE: + * we're here because the current CPU isn't matching anymore, + * the only way that can happen is because of a concurrent + * set_cpus_allowed_ptr() call, which should then still be + * pending completion. + * + * Either way, we really should have a @pending here. + */ + if (WARN_ON_ONCE(!pending)) + return -EINVAL; + + if (flags & SCA_MIGRATE_ENABLE) { + + refcount_inc(&pending->refs); /* pending->{arg,stop_work} */ + task_rq_unlock(rq, p, rf); + + pending->arg = (struct migration_arg) { + .task = p, + .dest_cpu = -1, + .pending = pending, + }; + + stop_one_cpu_nowait(cpu_of(rq), migration_cpu_stop, + &pending->arg, &pending->stop_work); + + return 0; + } + + if (task_running(rq, p) || p->state == TASK_WAKING) { + + task_rq_unlock(rq, p, rf); + stop_one_cpu(cpu_of(rq), migration_cpu_stop, &arg); + + } else { + + if (!is_migration_disabled(p)) { + if (task_on_rq_queued(p)) + rq = move_queued_task(rq, rf, p, dest_cpu); + + p->migration_pending = NULL; + complete = true; + } + task_rq_unlock(rq, p, rf); + +do_complete: + if (complete) + complete_all(&pending->done); + } + + wait_for_completion(&pending->done); + + if (refcount_dec_and_test(&pending->refs)) + wake_up_var(&pending->refs); + + wait_var_event(&my_pending.refs, !refcount_read(&my_pending.refs)); + + return 0; +} + /* * Change a given task's CPU affinity. Migrate the thread to a * proper CPU and schedule it away if the CPU it's executing on @@ -2035,23 +2223,8 @@ static int __set_cpus_allowed_ptr(struct task_struct *p, p->nr_cpus_allowed != 1); } - /* Can the task run on the task's current CPU? If so, we're done */ - if (cpumask_test_cpu(task_cpu(p), new_mask)) - goto out; + return affine_move_task(rq, p, &rf, dest_cpu, flags); - if (task_running(rq, p) || p->state == TASK_WAKING) { - struct migration_arg arg = { p, dest_cpu }; - /* Need help from migration thread: drop lock and wait. */ - task_rq_unlock(rq, p, &rf); - stop_one_cpu(cpu_of(rq), migration_cpu_stop, &arg); - return 0; - } else if (task_on_rq_queued(p)) { - /* - * OK, since we're going to drop the lock immediately - * afterwards anyway. - */ - rq = move_queued_task(rq, &rf, p, dest_cpu); - } out: task_rq_unlock(rq, p, &rf); @@ -3262,6 +3435,7 @@ static void __sched_fork(unsigned long clone_flags, struct task_struct *p) init_numa_balancing(clone_flags, p); #ifdef CONFIG_SMP p->wake_entry.u_flags = CSD_TYPE_TTWU; + p->migration_pending = NULL; #endif } -- Gitee From 5d03b2134ebf1ecccb8afbb1b7c1cc2b463ab2c5 Mon Sep 17 00:00:00 2001 From: meganz009 Date: Thu, 1 Jun 2023 22:56:25 +0800 Subject: [PATCH 5/9] sched/core: Make migrate disable and CPU hotplug cooperative commit e99aa4929f78a8d457b444ad8facfa82f699e21b upstream. On CPU unplug tasks which are in a migrate disabled region cannot be pushed to a different CPU until they returned to migrateable state. Account the number of tasks on a runqueue which are in a migrate disabled section and make the hotplug wait mechanism respect that. Signed-off-by: Thomas Gleixner Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Sebastian Andrzej Siewior --- kernel/sched/core.c | 36 ++++++++++++++++++++++++++++++------ kernel/sched/sched.h | 4 ++++ 2 files changed, 34 insertions(+), 6 deletions(-) diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 3f368f2f86fd..90e4cc32098e 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -1747,10 +1747,17 @@ static void migrate_disable_switch(struct rq *rq, struct task_struct *p) void migrate_disable(void) { - if (current->migration_disabled++) + struct task_struct *p = current; + + if (p->migration_disabled) { + p->migration_disabled++; return; + } - barrier(); + preempt_disable(); + this_rq()->nr_pinned++; + p->migration_disabled = 1; + preempt_enable(); } EXPORT_SYMBOL_GPL(migrate_disable); @@ -1777,6 +1784,7 @@ void migrate_enable(void) */ barrier(); p->migration_disabled = 0; + this_rq()->nr_pinned--; preempt_enable(); } EXPORT_SYMBOL_GPL(migrate_enable); @@ -1786,6 +1794,11 @@ static inline bool is_migration_disabled(struct task_struct *p) return p->migration_disabled; } +static inline bool rq_has_pinned_tasks(struct rq *rq) +{ + return rq->nr_pinned; +} + #endif /* @@ -2718,6 +2731,11 @@ static inline bool is_migration_disabled(struct task_struct *p) return false; } +static inline bool rq_has_pinned_tasks(struct rq *rq) +{ + return false; +} + #endif static void @@ -7123,15 +7141,20 @@ static void balance_push(struct rq *rq) * Both the cpu-hotplug and stop task are in this case and are * required to complete the hotplug process. */ - if (is_per_cpu_kthread(push_task)) { + if (is_per_cpu_kthread(push_task) || is_migration_disabled(push_task)) { /* * If this is the idle task on the outgoing CPU try to wake * up the hotplug control thread which might wait for the * last task to vanish. The rcuwait_active() check is * accurate here because the waiter is pinned on this CPU * and can't obviously be running in parallel. + * + * On RT kernels this also has to check whether there are + * pinned and scheduled out tasks on the runqueue. They + * need to leave the migrate disabled section first. */ - if (!rq->nr_running && rcuwait_active(&rq->hotplug_wait)) { + if (!rq->nr_running && !rq_has_pinned_tasks(rq) && + rcuwait_active(&rq->hotplug_wait)) { raw_spin_unlock(&rq->lock); rcuwait_wake_up(&rq->hotplug_wait); raw_spin_lock(&rq->lock); @@ -7178,7 +7201,8 @@ static void balance_hotplug_wait(void) { struct rq *rq = this_rq(); - rcuwait_wait_event(&rq->hotplug_wait, rq->nr_running == 1, + rcuwait_wait_event(&rq->hotplug_wait, + rq->nr_running == 1 && !rq_has_pinned_tasks(rq), TASK_UNINTERRUPTIBLE); } @@ -7427,7 +7451,7 @@ int sched_cpu_dying(unsigned int cpu) sched_tick_stop(cpu); rq_lock_irqsave(rq, &rf); - BUG_ON(rq->nr_running != 1); + BUG_ON(rq->nr_running != 1 || rq_has_pinned_tasks(rq)); rq_unlock_irqrestore(rq, &rf); calc_load_migrate(rq); diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index b40b2c6d640e..4848331964c5 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -1220,6 +1220,10 @@ struct rq { struct cpuidle_state *idle_state; #endif +#if defined(CONFIG_PREEMPT_RT) && defined(CONFIG_SMP) + unsigned int nr_pinned; +#endif + #ifdef CONFIG_HT_STABLE bool need_ht_stable; bool in_ht_stable; -- Gitee From f23bd15175984fb53d440d4317854105f4aea204 Mon Sep 17 00:00:00 2001 From: meganz009 Date: Thu, 1 Jun 2023 22:57:29 +0800 Subject: [PATCH 6/9] sched,rt: Use cpumask_any*_distribute() commit 4c19475100b3f0664e3f5a66f4067ce28412537f upstream. Replace a bunch of cpumask_any*() instances with cpumask_any*_distribute(), by injecting this little bit of random in cpu selection, we reduce the chance two competing balance operations working off the same lowest_mask pick the same CPU. Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Sebastian Andrzej Siewior --- include/linux/cpumask.h | 6 ++++++ kernel/sched/deadline.c | 6 +++--- kernel/sched/rt.c | 6 +++--- lib/cpumask.c | 18 ++++++++++++++++++ 4 files changed, 30 insertions(+), 6 deletions(-) diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h index f0d895d6ac39..383684e30f12 100644 --- a/include/linux/cpumask.h +++ b/include/linux/cpumask.h @@ -199,6 +199,11 @@ static inline int cpumask_any_and_distribute(const struct cpumask *src1p, return cpumask_next_and(-1, src1p, src2p); } +static inline int cpumask_any_distribute(const struct cpumask *srcp) +{ + return cpumask_first(srcp); +} + #define for_each_cpu(cpu, mask) \ for ((cpu) = 0; (cpu) < 1; (cpu)++, (void)mask) #define for_each_cpu_not(cpu, mask) \ @@ -252,6 +257,7 @@ int cpumask_any_but(const struct cpumask *mask, unsigned int cpu); unsigned int cpumask_local_spread(unsigned int i, int node); int cpumask_any_and_distribute(const struct cpumask *src1p, const struct cpumask *src2p); +int cpumask_any_distribute(const struct cpumask *srcp); /** * for_each_cpu - iterate over every cpu in a mask diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c index 4bc48eafa392..87d0b18abdda 100644 --- a/kernel/sched/deadline.c +++ b/kernel/sched/deadline.c @@ -1991,8 +1991,8 @@ static int find_later_rq(struct task_struct *task) return this_cpu; } - best_cpu = cpumask_first_and(later_mask, - sched_domain_span(sd)); + best_cpu = cpumask_any_and_distribute(later_mask, + sched_domain_span(sd)); /* * Last chance: if a CPU being in both later_mask * and current sd span is valid, that becomes our @@ -2014,7 +2014,7 @@ static int find_later_rq(struct task_struct *task) if (this_cpu != -1) return this_cpu; - cpu = cpumask_any(later_mask); + cpu = cpumask_any_distribute(later_mask); if (cpu < nr_cpu_ids) return cpu; diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c index c8bcccae731e..b79d78f150d7 100644 --- a/kernel/sched/rt.c +++ b/kernel/sched/rt.c @@ -1764,8 +1764,8 @@ static int find_lowest_rq(struct task_struct *task) return this_cpu; } - best_cpu = cpumask_first_and(lowest_mask, - sched_domain_span(sd)); + best_cpu = cpumask_any_and_distribute(lowest_mask, + sched_domain_span(sd)); if (best_cpu < nr_cpu_ids) { rcu_read_unlock(); return best_cpu; @@ -1782,7 +1782,7 @@ static int find_lowest_rq(struct task_struct *task) if (this_cpu != -1) return this_cpu; - cpu = cpumask_any(lowest_mask); + cpu = cpumask_any_distribute(lowest_mask); if (cpu < nr_cpu_ids) return cpu; diff --git a/lib/cpumask.c b/lib/cpumask.c index fb22fb266f93..c3c76b833384 100644 --- a/lib/cpumask.c +++ b/lib/cpumask.c @@ -261,3 +261,21 @@ int cpumask_any_and_distribute(const struct cpumask *src1p, return next; } EXPORT_SYMBOL(cpumask_any_and_distribute); + +int cpumask_any_distribute(const struct cpumask *srcp) +{ + int next, prev; + + /* NOTE: our first selection will skip 0. */ + prev = __this_cpu_read(distribute_cpu_mask_prev); + + next = cpumask_next(prev, srcp); + if (next >= nr_cpu_ids) + next = cpumask_first(srcp); + + if (next < nr_cpu_ids) + __this_cpu_write(distribute_cpu_mask_prev, next); + + return next; +} +EXPORT_SYMBOL(cpumask_any_distribute); -- Gitee From a29a8c1d02035f2a865802ee302427ea97ad5c2b Mon Sep 17 00:00:00 2001 From: meganz009 Date: Thu, 1 Jun 2023 22:58:34 +0800 Subject: [PATCH 7/9] sched,rt: Use the full cpumask for balancing commit 80b59abd910a7088a230294269973ad83da9ea0c upstream. We want migrate_disable() tasks to get PULLs in order for them to PUSH away the higher priority task. Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Sebastian Andrzej Siewior --- kernel/sched/cpudeadline.c | 4 ++-- kernel/sched/cpupri.c | 4 ++-- kernel/sched/deadline.c | 4 ++-- kernel/sched/rt.c | 4 ++-- 4 files changed, 8 insertions(+), 8 deletions(-) diff --git a/kernel/sched/cpudeadline.c b/kernel/sched/cpudeadline.c index 8cb06c8c7eb1..ceb03d76c0cc 100644 --- a/kernel/sched/cpudeadline.c +++ b/kernel/sched/cpudeadline.c @@ -120,7 +120,7 @@ int cpudl_find(struct cpudl *cp, struct task_struct *p, const struct sched_dl_entity *dl_se = &p->dl; if (later_mask && - cpumask_and(later_mask, cp->free_cpus, p->cpus_ptr)) { + cpumask_and(later_mask, cp->free_cpus, &p->cpus_mask)) { unsigned long cap, max_cap = 0; int cpu, max_cpu = -1; @@ -151,7 +151,7 @@ int cpudl_find(struct cpudl *cp, struct task_struct *p, WARN_ON(best_cpu != -1 && !cpu_present(best_cpu)); - if (cpumask_test_cpu(best_cpu, p->cpus_ptr) && + if (cpumask_test_cpu(best_cpu, &p->cpus_mask) && dl_time_before(dl_se->deadline, cp->elements[0].dl)) { if (later_mask) cpumask_set_cpu(best_cpu, later_mask); diff --git a/kernel/sched/cpupri.c b/kernel/sched/cpupri.c index 0033731a0797..11c4df2010de 100644 --- a/kernel/sched/cpupri.c +++ b/kernel/sched/cpupri.c @@ -73,11 +73,11 @@ static inline int __cpupri_find(struct cpupri *cp, struct task_struct *p, if (skip) return 0; - if (cpumask_any_and(p->cpus_ptr, vec->mask) >= nr_cpu_ids) + if (cpumask_any_and(&p->cpus_mask, vec->mask) >= nr_cpu_ids) return 0; if (lowest_mask) { - cpumask_and(lowest_mask, p->cpus_ptr, vec->mask); + cpumask_and(lowest_mask, &p->cpus_mask, vec->mask); /* * We have to ensure that we have at least one bit diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c index 87d0b18abdda..793b4e807fd5 100644 --- a/kernel/sched/deadline.c +++ b/kernel/sched/deadline.c @@ -1901,7 +1901,7 @@ static void task_fork_dl(struct task_struct *p) static int pick_dl_task(struct rq *rq, struct task_struct *p, int cpu) { if (!task_running(rq, p) && - cpumask_test_cpu(cpu, p->cpus_ptr)) + cpumask_test_cpu(cpu, &p->cpus_mask)) return 1; return 0; } @@ -2051,7 +2051,7 @@ static struct rq *find_lock_later_rq(struct task_struct *task, struct rq *rq) /* Retry if something changed. */ if (double_lock_balance(rq, later_rq)) { if (unlikely(task_rq(task) != rq || - !cpumask_test_cpu(later_rq->cpu, task->cpus_ptr) || + !cpumask_test_cpu(later_rq->cpu, &task->cpus_mask) || task_running(rq, task) || !dl_task(task) || !task_on_rq_queued(task))) { diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c index b79d78f150d7..441bee60fa4b 100644 --- a/kernel/sched/rt.c +++ b/kernel/sched/rt.c @@ -1670,7 +1670,7 @@ static void put_prev_task_rt(struct rq *rq, struct task_struct *p) static int pick_rt_task(struct rq *rq, struct task_struct *p, int cpu) { if (!task_running(rq, p) && - cpumask_test_cpu(cpu, p->cpus_ptr)) + cpumask_test_cpu(cpu, &p->cpus_mask)) return 1; return 0; @@ -1823,7 +1823,7 @@ static struct rq *find_lock_lowest_rq(struct task_struct *task, struct rq *rq) * Also make sure that it wasn't scheduled on its rq. */ if (unlikely(task_rq(task) != rq || - !cpumask_test_cpu(lowest_rq->cpu, task->cpus_ptr) || + !cpumask_test_cpu(lowest_rq->cpu, &task->cpus_mask) || task_running(rq, task) || !rt_task(task) || !task_on_rq_queued(task))) { -- Gitee From eebe0e6a9dc1b48a7d497189b07a5a96073eded7 Mon Sep 17 00:00:00 2001 From: meganz009 Date: Thu, 1 Jun 2023 22:58:45 +0800 Subject: [PATCH 8/9] sched, lockdep: Annotate ->pi_lock recursion commit eed2ee87d2f7eacbc639cb6b471a27a330ed81eb upstream. There's a valid ->pi_lock recursion issue where the actual PI code tries to wake up the stop task. Make lockdep aware so it doesn't complain about this. Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Sebastian Andrzej Siewior --- kernel/sched/core.c | 15 +++++++++++++++ 1 file changed, 15 insertions(+) diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 90e4cc32098e..32027dabef1a 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -2683,6 +2683,7 @@ int select_task_rq(struct task_struct *p, int cpu, int sd_flags, int wake_flags) void sched_set_stop_task(int cpu, struct task_struct *stop) { + static struct lock_class_key stop_pi_lock; struct sched_param param = { .sched_priority = MAX_RT_PRIO - 1 }; struct task_struct *old_stop = cpu_rq(cpu)->stop; @@ -2698,6 +2699,20 @@ void sched_set_stop_task(int cpu, struct task_struct *stop) sched_setscheduler_nocheck(stop, SCHED_FIFO, ¶m); stop->sched_class = &stop_sched_class; + + /* + * The PI code calls rt_mutex_setprio() with ->pi_lock held to + * adjust the effective priority of a task. As a result, + * rt_mutex_setprio() can trigger (RT) balancing operations, + * which can then trigger wakeups of the stop thread to push + * around the current task. + * + * The stop task itself will never be part of the PI-chain, it + * never blocks, therefore that ->pi_lock recursion is safe. + * Tell lockdep about this by placing the stop->pi_lock in its + * own class. + */ + lockdep_set_class(&stop->pi_lock, &stop_pi_lock); } cpu_rq(cpu)->stop = stop; -- Gitee From fb5b1652ef4d538981ef40081316802f6407d8a3 Mon Sep 17 00:00:00 2001 From: meganz009 Date: Thu, 1 Jun 2023 23:07:04 +0800 Subject: [PATCH 9/9] sched: Fix migrate_disable() vs rt/dl balancing commit 4daccf68f6910e0ac30df2eb80ae25fc04afaa55 upstream. In order to minimize the interference of migrate_disable() on lower priority tasks, which can be deprived of runtime due to being stuck below a higher priority task. Teach the RT/DL balancers to push away these higher priority tasks when a lower priority task gets selected to run on a freshly demoted CPU (pull). This adds migration interference to the higher priority task, but restores bandwidth to system that would otherwise be irrevocably lost. Without this it would be possible to have all tasks on the system stuck on a single CPU, each task preempted in a migrate_disable() section with a single high priority task running. This way we can still approximate running the M highest priority tasks on the system. Migrating the top task away is (ofcourse) still subject to migrate_disable() too, which means the lower task is subject to an interference equivalent to the worst case migrate_disable() section. Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Sebastian Andrzej Siewior --- include/linux/preempt.h | 40 +++++++++++++----------- include/linux/sched.h | 3 +- kernel/sched/core.c | 67 +++++++++++++++++++++++++++++++++++------ kernel/sched/deadline.c | 29 +++++++++++++----- kernel/sched/rt.c | 63 ++++++++++++++++++++++++++++++-------- kernel/sched/sched.h | 34 ++++++++++++++++++++- 6 files changed, 187 insertions(+), 49 deletions(-) diff --git a/include/linux/preempt.h b/include/linux/preempt.h index 97ba7c920653..8b43922e65df 100644 --- a/include/linux/preempt.h +++ b/include/linux/preempt.h @@ -325,24 +325,28 @@ static inline void preempt_notifier_init(struct preempt_notifier *notifier, #if defined(CONFIG_SMP) && defined(CONFIG_PREEMPT_RT) /* - * Migrate-Disable and why it is (strongly) undesired. - * - * The premise of the Real-Time schedulers we have on Linux - * (SCHED_FIFO/SCHED_DEADLINE) is that M CPUs can/will run M tasks - * concurrently, provided there are sufficient runnable tasks, also known as - * work-conserving. For instance SCHED_DEADLINE tries to schedule the M - * earliest deadline threads, and SCHED_FIFO the M highest priority threads. - * - * The correctness of various scheduling models depends on this, but is it - * broken by migrate_disable() that doesn't imply preempt_disable(). Where - * preempt_disable() implies an immediate priority ceiling, preemptible - * migrate_disable() allows nesting. - * - * The worst case is that all tasks preempt one another in a migrate_disable() - * region and stack on a single CPU. This then reduces the available bandwidth - * to a single CPU. And since Real-Time schedulability theory considers the - * Worst-Case only, all Real-Time analysis shall revert to single-CPU - * (instantly solving the SMP analysis problem). + * Migrate-Disable and why it is undesired. + * + * When a preempted task becomes elegible to run under the ideal model (IOW it + * becomes one of the M highest priority tasks), it might still have to wait + * for the preemptee's migrate_disable() section to complete. Thereby suffering + * a reduction in bandwidth in the exact duration of the migrate_disable() + * section. + * + * Per this argument, the change from preempt_disable() to migrate_disable() + * gets us: + * + * - a higher priority tasks gains reduced wake-up latency; with preempt_disable() + * it would have had to wait for the lower priority task. + * + * - a lower priority tasks; which under preempt_disable() could've instantly + * migrated away when another CPU becomes available, is now constrained + * by the ability to push the higher priority task away, which might itself be + * in a migrate_disable() section, reducing it's available bandwidth. + * + * IOW it trades latency / moves the interference term, but it stays in the + * system, and as long as it remains unbounded, the system is not fully + * deterministic. * * * The reason we have it anyway. diff --git a/include/linux/sched.h b/include/linux/sched.h index 848b36badbed..9a9a471af547 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -831,8 +831,9 @@ struct task_struct { cpumask_t cpus_mask; void *migration_pending; #if defined(CONFIG_SMP) && defined(CONFIG_PREEMPT_RT) - int migration_disabled; + unsigned short migration_disabled; #endif + unsigned short migration_flags; #ifdef CONFIG_PREEMPT_RCU int rcu_read_lock_nesting; diff --git a/kernel/sched/core.c b/kernel/sched/core.c index 32027dabef1a..0fe97a9a547b 100644 --- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -1789,11 +1789,6 @@ void migrate_enable(void) } EXPORT_SYMBOL_GPL(migrate_enable); -static inline bool is_migration_disabled(struct task_struct *p) -{ - return p->migration_disabled; -} - static inline bool rq_has_pinned_tasks(struct rq *rq) { return rq->nr_pinned; @@ -1998,6 +1993,49 @@ static int migration_cpu_stop(void *data) return 0; } +int push_cpu_stop(void *arg) +{ + struct rq *lowest_rq = NULL, *rq = this_rq(); + struct task_struct *p = arg; + + raw_spin_lock_irq(&p->pi_lock); + raw_spin_lock(&rq->lock); + + if (task_rq(p) != rq) + goto out_unlock; + + if (is_migration_disabled(p)) { + p->migration_flags |= MDF_PUSH; + goto out_unlock; + } + + p->migration_flags &= ~MDF_PUSH; + + if (p->sched_class->find_lock_rq) + lowest_rq = p->sched_class->find_lock_rq(p, rq); + + if (!lowest_rq) + goto out_unlock; + + // XXX validate p is still the highest prio task + if (task_rq(p) == rq) { + deactivate_task(rq, p, 0); + set_task_cpu(p, lowest_rq->cpu); + activate_task(lowest_rq, p, 0); + resched_curr(lowest_rq); + } + + double_unlock_balance(rq, lowest_rq); + +out_unlock: + rq->push_busy = false; + raw_spin_unlock(&rq->lock); + raw_spin_unlock_irq(&p->pi_lock); + + put_task_struct(p); + return 0; +} + /* * sched_class::set_cpus_allowed must do the below, but is not required to * actually call this function. @@ -2078,6 +2116,14 @@ static int affine_move_task(struct rq *rq, struct task_struct *p, struct rq_flag /* Can the task run on the task's current CPU? If so, we're done */ if (cpumask_test_cpu(task_cpu(p), &p->cpus_mask)) { + struct task_struct *push_task = NULL; + + if ((flags & SCA_MIGRATE_ENABLE) && + (p->migration_flags & MDF_PUSH) && !rq->push_busy) { + rq->push_busy = true; + push_task = get_task_struct(p); + } + pending = p->migration_pending; if (pending) { refcount_inc(&pending->refs); @@ -2086,6 +2132,11 @@ static int affine_move_task(struct rq *rq, struct task_struct *p, struct rq_flag } task_rq_unlock(rq, p, rf); + if (push_task) { + stop_one_cpu_nowait(rq->cpu, push_cpu_stop, + p, &rq->push_work); + } + if (complete) goto do_complete; @@ -2122,6 +2173,7 @@ static int affine_move_task(struct rq *rq, struct task_struct *p, struct rq_flag if (flags & SCA_MIGRATE_ENABLE) { refcount_inc(&pending->refs); /* pending->{arg,stop_work} */ + p->migration_flags &= ~MDF_PUSH; task_rq_unlock(rq, p, rf); pending->arg = (struct migration_arg) { @@ -2741,11 +2793,6 @@ static inline int __set_cpus_allowed_ptr(struct task_struct *p, static inline void migrate_disable_switch(struct rq *rq, struct task_struct *p) { } -static inline bool is_migration_disabled(struct task_struct *p) -{ - return false; -} - static inline bool rq_has_pinned_tasks(struct rq *rq) { return false; diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c index 793b4e807fd5..69e9ac84237e 100644 --- a/kernel/sched/deadline.c +++ b/kernel/sched/deadline.c @@ -2118,6 +2118,9 @@ static int push_dl_task(struct rq *rq) return 0; retry: + if (is_migration_disabled(next_task)) + return 0; + if (WARN_ON(next_task == rq->curr)) return 0; @@ -2195,7 +2198,7 @@ static void push_dl_tasks(struct rq *rq) static void pull_dl_task(struct rq *this_rq) { int this_cpu = this_rq->cpu, cpu; - struct task_struct *p; + struct task_struct *p, *push_task; bool resched = false; struct rq *src_rq; u64 dmin = LONG_MAX; @@ -2225,6 +2228,7 @@ static void pull_dl_task(struct rq *this_rq) continue; /* Might drop this_rq->lock */ + push_task = NULL; double_lock_balance(this_rq, src_rq); /* @@ -2256,17 +2260,27 @@ static void pull_dl_task(struct rq *this_rq) src_rq->curr->dl.deadline)) goto skip; - resched = true; - - deactivate_task(src_rq, p, 0); - set_task_cpu(p, this_cpu); - activate_task(this_rq, p, 0); - dmin = p->dl.deadline; + if (is_migration_disabled(p)) { + push_task = get_push_task(src_rq); + } else { + deactivate_task(src_rq, p, 0); + set_task_cpu(p, this_cpu); + activate_task(this_rq, p, 0); + dmin = p->dl.deadline; + resched = true; + } /* Is there any other task even earlier? */ } skip: double_unlock_balance(this_rq, src_rq); + + if (push_task) { + raw_spin_unlock(&this_rq->lock); + stop_one_cpu_nowait(src_rq->cpu, push_cpu_stop, + push_task, &src_rq->push_work); + raw_spin_lock(&this_rq->lock); + } } if (resched) @@ -2515,6 +2529,7 @@ const struct sched_class dl_sched_class .rq_online = rq_online_dl, .rq_offline = rq_offline_dl, .task_woken = task_woken_dl, + .find_lock_rq = find_lock_later_rq, #endif .task_tick = task_tick_dl, diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c index 441bee60fa4b..480d6cf3001d 100644 --- a/kernel/sched/rt.c +++ b/kernel/sched/rt.c @@ -1871,7 +1871,7 @@ static struct task_struct *pick_next_pushable_task(struct rq *rq) * running task can migrate over to a CPU that is running a task * of lesser priority. */ -static int push_rt_task(struct rq *rq) +static int push_rt_task(struct rq *rq, bool pull) { struct task_struct *next_task; struct rq *lowest_rq; @@ -1885,6 +1885,34 @@ static int push_rt_task(struct rq *rq) return 0; retry: + if (is_migration_disabled(next_task)) { + struct task_struct *push_task = NULL; + int cpu; + + if (!pull || rq->push_busy) + return 0; + + cpu = find_lowest_rq(rq->curr); + if (cpu == -1 || cpu == rq->cpu) + return 0; + + /* + * Given we found a CPU with lower priority than @next_task, + * therefore it should be running. However we cannot migrate it + * to this other CPU, instead attempt to push the current + * running task on this CPU away. + */ + push_task = get_push_task(rq); + if (push_task) { + raw_spin_unlock(&rq->lock); + stop_one_cpu_nowait(rq->cpu, push_cpu_stop, + push_task, &rq->push_work); + raw_spin_lock(&rq->lock); + } + + return 0; + } + if (WARN_ON(next_task == rq->curr)) return 0; @@ -1939,12 +1967,10 @@ static int push_rt_task(struct rq *rq) deactivate_task(rq, next_task, 0); set_task_cpu(next_task, lowest_rq->cpu); activate_task(lowest_rq, next_task, 0); - ret = 1; - resched_curr(lowest_rq); + ret = 1; double_unlock_balance(rq, lowest_rq); - out: put_task_struct(next_task); @@ -1954,7 +1980,7 @@ static int push_rt_task(struct rq *rq) static void push_rt_tasks(struct rq *rq) { /* push_rt_task will return true if it moved an RT */ - while (push_rt_task(rq)) + while (push_rt_task(rq, false)) ; } @@ -2107,7 +2133,8 @@ void rto_push_irq_work_func(struct irq_work *work) */ if (has_pushable_tasks(rq)) { raw_spin_lock(&rq->lock); - push_rt_tasks(rq); + while (push_rt_task(rq, true)) + ; raw_spin_unlock(&rq->lock); } @@ -2132,7 +2159,7 @@ static void pull_rt_task(struct rq *this_rq) { int this_cpu = this_rq->cpu, cpu; bool resched = false; - struct task_struct *p; + struct task_struct *p, *push_task; struct rq *src_rq; int rt_overload_count = rt_overloaded(this_rq); @@ -2179,6 +2206,7 @@ static void pull_rt_task(struct rq *this_rq) * double_lock_balance, and another CPU could * alter this_rq */ + push_task = NULL; double_lock_balance(this_rq, src_rq); /* @@ -2206,11 +2234,14 @@ static void pull_rt_task(struct rq *this_rq) if (p->prio < src_rq->curr->prio) goto skip; - resched = true; - - deactivate_task(src_rq, p, 0); - set_task_cpu(p, this_cpu); - activate_task(this_rq, p, 0); + if (is_migration_disabled(p)) { + push_task = get_push_task(src_rq); + } else { + deactivate_task(src_rq, p, 0); + set_task_cpu(p, this_cpu); + activate_task(this_rq, p, 0); + resched = true; + } /* * We continue with the search, just in * case there's an even higher prio task @@ -2220,6 +2251,13 @@ static void pull_rt_task(struct rq *this_rq) } skip: double_unlock_balance(this_rq, src_rq); + + if (push_task) { + raw_spin_unlock(&this_rq->lock); + stop_one_cpu_nowait(src_rq->cpu, push_cpu_stop, + push_task, &src_rq->push_work); + raw_spin_lock(&this_rq->lock); + } } if (resched) @@ -2478,6 +2516,7 @@ const struct sched_class rt_sched_class .rq_offline = rq_offline_rt, .task_woken = task_woken_rt, .switched_from = switched_from_rt, + .find_lock_rq = find_lock_lowest_rq, #endif .task_tick = task_tick_rt, diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h index 4848331964c5..2fe8183e9c44 100644 --- a/kernel/sched/sched.h +++ b/kernel/sched/sched.h @@ -1223,6 +1223,8 @@ struct rq { #if defined(CONFIG_PREEMPT_RT) && defined(CONFIG_SMP) unsigned int nr_pinned; #endif + unsigned int push_busy; + struct cpu_stop_work push_work; #ifdef CONFIG_HT_STABLE bool need_ht_stable; @@ -1264,6 +1266,17 @@ static inline int cpu_of(struct rq *rq) #endif } +#define MDF_PUSH 0x01 + +static inline bool is_migration_disabled(struct task_struct *p) +{ +#if defined(CONFIG_SMP) && defined(CONFIG_PREEMPT_RT) + return p->migration_disabled; +#else + return false; +#endif +} + #ifdef CONFIG_GROUP_IDENTITY DECLARE_STATIC_KEY_FALSE(__group_identity_enabled); @@ -2041,6 +2054,8 @@ struct sched_class { void (*rq_online)(struct rq *rq); void (*rq_offline)(struct rq *rq); + + struct rq *(*find_lock_rq)(struct task_struct *p, struct rq *rq); #endif void (*task_tick)(struct rq *rq, struct task_struct *p, int queued); @@ -2154,6 +2169,24 @@ extern void trigger_load_balance(struct rq *rq); extern void set_cpus_allowed_common(struct task_struct *p, const struct cpumask *new_mask, u32 flags); +static inline struct task_struct *get_push_task(struct rq *rq) +{ + struct task_struct *p = rq->curr; + + lockdep_assert_held(&rq->lock); + + if (rq->push_busy) + return NULL; + + if (p->nr_cpus_allowed == 1) + return NULL; + + rq->push_busy = true; + return get_task_struct(p); +} + +extern int push_cpu_stop(void *arg); + #endif #ifdef CONFIG_CPU_IDLE @@ -2558,7 +2591,6 @@ extern void nohz_balance_exit_idle(struct rq *rq); static inline void nohz_balance_exit_idle(struct rq *rq) { } #endif - #ifdef CONFIG_SMP static inline void __dl_update(struct dl_bw *dl_b, s64 bw) -- Gitee