diff options
Diffstat (limited to 'include/linux/sched')
| -rw-r--r-- | include/linux/sched/deadline.h | 27 | ||||
| -rw-r--r-- | include/linux/sched/ext.h | 109 | ||||
| -rw-r--r-- | include/linux/sched/signal.h | 3 | ||||
| -rw-r--r-- | include/linux/sched/topology.h | 26 |
4 files changed, 112 insertions, 53 deletions
diff --git a/include/linux/sched/deadline.h b/include/linux/sched/deadline.h index c40115d4e34d..1198138cb839 100644 --- a/include/linux/sched/deadline.h +++ b/include/linux/sched/deadline.h @@ -37,4 +37,31 @@ extern void dl_clear_root_domain_cpu(int cpu); extern u64 dl_cookie; extern bool dl_bw_visited(int cpu, u64 cookie); +static inline bool dl_server(struct sched_dl_entity *dl_se) +{ + return dl_se->dl_server; +} + +static inline struct task_struct *dl_task_of(struct sched_dl_entity *dl_se) +{ + BUG_ON(dl_server(dl_se)); + return container_of(dl_se, struct task_struct, dl); +} + +/* + * Regarding the deadline, a task with implicit deadline has a relative + * deadline == relative period. A task with constrained deadline has a + * relative deadline <= relative period. + * + * We support constrained deadline tasks. However, there are some restrictions + * applied only for tasks which do not have an implicit deadline. See + * update_dl_entity() to know more about such restrictions. + * + * The dl_is_implicit() returns true if the task has an implicit deadline. + */ +static inline bool dl_is_implicit(struct sched_dl_entity *dl_se) +{ + return dl_se->dl_deadline == dl_se->dl_period; +} + #endif /* _LINUX_SCHED_DEADLINE_H */ diff --git a/include/linux/sched/ext.h b/include/linux/sched/ext.h index bcb962d5ee7d..1a3af2ea2a79 100644 --- a/include/linux/sched/ext.h +++ b/include/linux/sched/ext.h @@ -62,6 +62,16 @@ enum scx_dsq_id_flags { SCX_DSQ_LOCAL_CPU_MASK = 0xffffffffLLU, }; +struct scx_deferred_reenq_user { + struct list_head node; + u64 flags; +}; + +struct scx_dsq_pcpu { + struct scx_dispatch_q *dsq; + struct scx_deferred_reenq_user deferred_reenq_user; +}; + /* * A dispatch queue (DSQ) can be either a FIFO or p->scx.dsq_vtime ordered * queue. A built-in DSQ is always a FIFO. The built-in local DSQs are used to @@ -78,30 +88,58 @@ struct scx_dispatch_q { u64 id; struct rhash_head hash_node; struct llist_node free_node; + struct scx_sched *sched; + struct scx_dsq_pcpu __percpu *pcpu; struct rcu_head rcu; }; -/* scx_entity.flags */ +/* sched_ext_entity.flags */ enum scx_ent_flags { SCX_TASK_QUEUED = 1 << 0, /* on ext runqueue */ + SCX_TASK_IN_CUSTODY = 1 << 1, /* in custody, needs ops.dequeue() when leaving */ SCX_TASK_RESET_RUNNABLE_AT = 1 << 2, /* runnable_at should be reset */ SCX_TASK_DEQD_FOR_SLEEP = 1 << 3, /* last dequeue was for SLEEP */ + SCX_TASK_SUB_INIT = 1 << 4, /* task being initialized for a sub sched */ + SCX_TASK_IMMED = 1 << 5, /* task is on local DSQ with %SCX_ENQ_IMMED */ - SCX_TASK_STATE_SHIFT = 8, /* bit 8 and 9 are used to carry scx_task_state */ + /* + * Bits 8 and 9 are used to carry task state: + * + * NONE ops.init_task() not called yet + * INIT ops.init_task() succeeded, but task can be cancelled + * READY fully initialized, but not in sched_ext + * ENABLED fully initialized and in sched_ext + */ + SCX_TASK_STATE_SHIFT = 8, /* bits 8 and 9 are used to carry task state */ SCX_TASK_STATE_BITS = 2, SCX_TASK_STATE_MASK = ((1 << SCX_TASK_STATE_BITS) - 1) << SCX_TASK_STATE_SHIFT, - SCX_TASK_CURSOR = 1 << 31, /* iteration cursor, not a task */ -}; + SCX_TASK_NONE = 0 << SCX_TASK_STATE_SHIFT, + SCX_TASK_INIT = 1 << SCX_TASK_STATE_SHIFT, + SCX_TASK_READY = 2 << SCX_TASK_STATE_SHIFT, + SCX_TASK_ENABLED = 3 << SCX_TASK_STATE_SHIFT, -/* scx_entity.flags & SCX_TASK_STATE_MASK */ -enum scx_task_state { - SCX_TASK_NONE, /* ops.init_task() not called yet */ - SCX_TASK_INIT, /* ops.init_task() succeeded, but task can be cancelled */ - SCX_TASK_READY, /* fully initialized, but not in sched_ext */ - SCX_TASK_ENABLED, /* fully initialized and in sched_ext */ + /* + * Bits 12 and 13 are used to carry reenqueue reason. In addition to + * %SCX_ENQ_REENQ flag, ops.enqueue() can also test for + * %SCX_TASK_REENQ_REASON_NONE to distinguish reenqueues. + * + * NONE not being reenqueued + * KFUNC reenqueued by scx_bpf_dsq_reenq() and friends + * IMMED reenqueued due to failed ENQ_IMMED + * PREEMPTED preempted while running + */ + SCX_TASK_REENQ_REASON_SHIFT = 12, + SCX_TASK_REENQ_REASON_BITS = 2, + SCX_TASK_REENQ_REASON_MASK = ((1 << SCX_TASK_REENQ_REASON_BITS) - 1) << SCX_TASK_REENQ_REASON_SHIFT, + + SCX_TASK_REENQ_NONE = 0 << SCX_TASK_REENQ_REASON_SHIFT, + SCX_TASK_REENQ_KFUNC = 1 << SCX_TASK_REENQ_REASON_SHIFT, + SCX_TASK_REENQ_IMMED = 2 << SCX_TASK_REENQ_REASON_SHIFT, + SCX_TASK_REENQ_PREEMPTED = 3 << SCX_TASK_REENQ_REASON_SHIFT, - SCX_TASK_NR_STATES, + /* iteration cursor, not a task */ + SCX_TASK_CURSOR = 1 << 31, }; /* scx_entity.dsq_flags */ @@ -109,33 +147,6 @@ enum scx_ent_dsq_flags { SCX_TASK_DSQ_ON_PRIQ = 1 << 0, /* task is queued on the priority queue of a dsq */ }; -/* - * Mask bits for scx_entity.kf_mask. Not all kfuncs can be called from - * everywhere and the following bits track which kfunc sets are currently - * allowed for %current. This simple per-task tracking works because SCX ops - * nest in a limited way. BPF will likely implement a way to allow and disallow - * kfuncs depending on the calling context which will replace this manual - * mechanism. See scx_kf_allow(). - */ -enum scx_kf_mask { - SCX_KF_UNLOCKED = 0, /* sleepable and not rq locked */ - /* ENQUEUE and DISPATCH may be nested inside CPU_RELEASE */ - SCX_KF_CPU_RELEASE = 1 << 0, /* ops.cpu_release() */ - /* - * ops.dispatch() may release rq lock temporarily and thus ENQUEUE and - * SELECT_CPU may be nested inside. ops.dequeue (in REST) may also be - * nested inside DISPATCH. - */ - SCX_KF_DISPATCH = 1 << 1, /* ops.dispatch() */ - SCX_KF_ENQUEUE = 1 << 2, /* ops.enqueue() and ops.select_cpu() */ - SCX_KF_SELECT_CPU = 1 << 3, /* ops.select_cpu() */ - SCX_KF_REST = 1 << 4, /* other rq-locked operations */ - - __SCX_KF_RQ_LOCKED = SCX_KF_CPU_RELEASE | SCX_KF_DISPATCH | - SCX_KF_ENQUEUE | SCX_KF_SELECT_CPU | SCX_KF_REST, - __SCX_KF_TERMINAL = SCX_KF_ENQUEUE | SCX_KF_SELECT_CPU | SCX_KF_REST, -}; - enum scx_dsq_lnode_flags { SCX_DSQ_LNODE_ITER_CURSOR = 1 << 0, @@ -149,19 +160,31 @@ struct scx_dsq_list_node { u32 priv; /* can be used by iter cursor */ }; -#define INIT_DSQ_LIST_CURSOR(__node, __flags, __priv) \ +#define INIT_DSQ_LIST_CURSOR(__cursor, __dsq, __flags) \ (struct scx_dsq_list_node) { \ - .node = LIST_HEAD_INIT((__node).node), \ + .node = LIST_HEAD_INIT((__cursor).node), \ .flags = SCX_DSQ_LNODE_ITER_CURSOR | (__flags), \ - .priv = (__priv), \ + .priv = READ_ONCE((__dsq)->seq), \ } +struct scx_sched; + /* * The following is embedded in task_struct and contains all fields necessary * for a task to be scheduled by SCX. */ struct sched_ext_entity { +#ifdef CONFIG_CGROUPS + /* + * Associated scx_sched. Updated either during fork or while holding + * both p->pi_lock and rq lock. + */ + struct scx_sched __rcu *sched; +#endif struct scx_dispatch_q *dsq; + atomic_long_t ops_state; + u64 ddsp_dsq_id; + u64 ddsp_enq_flags; struct scx_dsq_list_node dsq_list; /* dispatch order */ struct rb_node dsq_priq; /* p->scx.dsq_vtime order */ u32 dsq_seq; @@ -171,9 +194,7 @@ struct sched_ext_entity { s32 sticky_cpu; s32 holding_cpu; s32 selected_cpu; - u32 kf_mask; /* see scx_kf_mask above */ struct task_struct *kf_tasks[2]; /* see SCX_CALL_OP_TASK() */ - atomic_long_t ops_state; struct list_head runnable_node; /* rq->scx.runnable_list */ unsigned long runnable_at; @@ -181,8 +202,6 @@ struct sched_ext_entity { #ifdef CONFIG_SCHED_CORE u64 core_sched_at; /* see scx_prio_less() */ #endif - u64 ddsp_dsq_id; - u64 ddsp_enq_flags; /* BPF scheduler modifiable fields */ diff --git a/include/linux/sched/signal.h b/include/linux/sched/signal.h index a22248aebcf9..584ae88b435e 100644 --- a/include/linux/sched/signal.h +++ b/include/linux/sched/signal.h @@ -132,6 +132,7 @@ struct signal_struct { */ unsigned int is_child_subreaper:1; unsigned int has_child_subreaper:1; + unsigned int autoreap:1; #ifdef CONFIG_POSIX_TIMERS @@ -739,7 +740,7 @@ static inline int thread_group_empty(struct task_struct *p) extern struct sighand_struct *lock_task_sighand(struct task_struct *task, unsigned long *flags) - __acquires(&task->sighand->siglock); + __cond_acquires(nonnull, &task->sighand->siglock); static inline void unlock_task_sighand(struct task_struct *task, unsigned long *flags) diff --git a/include/linux/sched/topology.h b/include/linux/sched/topology.h index 45c0022b91ce..36553e14866d 100644 --- a/include/linux/sched/topology.h +++ b/include/linux/sched/topology.h @@ -95,6 +95,7 @@ struct sched_domain { unsigned int newidle_call; unsigned int newidle_success; unsigned int newidle_ratio; + u64 newidle_stamp; u64 max_newidle_lb_cost; unsigned long last_decay_max_lb_cost; @@ -141,18 +142,30 @@ struct sched_domain { unsigned int span_weight; /* - * Span of all CPUs in this domain. + * See sched_domain_span(), on why flex arrays are broken. * - * NOTE: this field is variable length. (Allocated dynamically - * by attaching extra space to the end of the structure, - * depending on how many CPUs the kernel has booted up with) - */ unsigned long span[]; + */ }; static inline struct cpumask *sched_domain_span(struct sched_domain *sd) { - return to_cpumask(sd->span); + /* + * Turns out that C flexible arrays are fundamentally broken since it + * is allowed for offsetof(*sd, span) < sizeof(*sd), this means that + * structure initialzation *sd = { ... }; which writes every byte + * inside sizeof(*type), will over-write the start of the flexible + * array. + * + * Luckily, the way we allocate sched_domain is by: + * + * sizeof(*sd) + cpumask_size() + * + * this means that we have sufficient space for the whole flex array + * *outside* of sizeof(*sd). So use that, and avoid using sd->span. + */ + unsigned long *bitmap = (void *)sd + sizeof(*sd); + return to_cpumask(bitmap); } extern void partition_sched_domains(int ndoms_new, cpumask_var_t doms_new[], @@ -171,7 +184,6 @@ typedef int (*sched_domain_flags_f)(void); struct sd_data { struct sched_domain *__percpu *sd; - struct sched_domain_shared *__percpu *sds; struct sched_group *__percpu *sg; struct sched_group_capacity *__percpu *sgc; }; |