diff --git a/Documentation/scheduler/sched-ext.rst b/Documentation/scheduler/sched-ext.rst index 794ae80b3ba3..13ba2cb7831c 100644 --- a/Documentation/scheduler/sched-ext.rst +++ b/Documentation/scheduler/sched-ext.rst @@ -503,6 +503,19 @@ and edge cases, to name a few examples: class, in which case it will exit the tick-dispatch loop even though it is runnable and has a non-zero slice. +* Under proxy execution, sched_ext continues to observe the donor as the + current scheduling context. Accordingly, ``ops.running()`` and + ``ops.stopping()`` report when the donor's scheduling context becomes active + and inactive, even when the donor is blocked and a lock owner executes on its + behalf. The physical execution context is intentionally not reported through + these callbacks. + + A blocked donor enters a running session only after proxy resolution finds + an execution context. The session remains active if only the physical + execution context changes while the donor remains the same. Running sessions + are tracked so that ``ops.running()`` and ``ops.stopping()`` remain paired + and are not emitted recursively. + See the "Scheduling Cycle" section for a more detailed description of how a freshly woken up task gets on a CPU. diff --git a/kernel/sched/ext/ext.c b/kernel/sched/ext/ext.c index 7ae4e6d0e2e4..9d41ec82f3bf 100644 --- a/kernel/sched/ext/ext.c +++ b/kernel/sched/ext/ext.c @@ -425,28 +425,28 @@ static bool rq_is_open(struct rq *rq, u64 enq_flags) */ /* - * If we're in the dispatch path holding rq lock, $curr may or may not + * If we're in the dispatch path holding rq lock, $donor may or may not * be ready depending on whether the on-going dispatch decides to extend - * $curr's slice. We say yes here and resolve it at the end of dispatch. + * $donor's slice. We say yes here and resolve it at the end of dispatch. * See dispatch_one(). */ if (rq->scx.flags & SCX_RQ_IN_DISPATCH) return true; /* - * The preemption flags clear $curr's slice if on SCX and kick dispatch, - * so allow them to avoid spuriously triggering reenq on a combined + * The preemption flags clear $donor's slice if on SCX and kick dispatch, + * so allow it to avoid spuriously triggering reenq on a combined * PREEMPT|IMMED insertion. */ if (enq_flags & (SCX_ENQ_PREEMPT | SCX_ENQ_PREEMPT_LAZY)) { - struct task_struct *curr = rq->curr; + struct task_struct *donor = rq->donor; /* * A protected slice refuses the preemption and the cpu stays * occupied. See rq_owned_post_enq(). */ - return curr->sched_class != &ext_sched_class || - likely(!(curr->scx.flags & SCX_TASK_PROTECTED)); + return donor->sched_class != &ext_sched_class || + likely(!(donor->scx.flags & SCX_TASK_PROTECTED)); } /* @@ -1462,20 +1462,27 @@ static void apply_slice_vtime(struct task_struct *p, u64 slice, u64 vtime, u64 e static void update_curr_scx(struct rq *rq) { - struct task_struct *curr = rq->curr; + struct task_struct *donor; s64 delta_exec; + /* + * update_curr_scx() is selected through rq->donor->sched_class, not + * rq->curr->sched_class, so @donor is always an EXT task here. If an EXT + * owner executes for a FAIR donor, FAIR's update_curr() runs instead. + */ + donor = rq->donor; + /* apply even on 0 delta_exec, callers may still act on the slice */ - apply_task_slice_oob(rq, curr); + apply_task_slice_oob(rq, donor); delta_exec = update_curr_common(rq); if (unlikely(delta_exec <= 0)) return; - if (curr->scx.slice != SCX_SLICE_INF) - curr->scx.slice -= min_t(u64, curr->scx.slice, delta_exec); + if (donor->scx.slice != SCX_SLICE_INF) + donor->scx.slice -= min_t(u64, donor->scx.slice, delta_exec); - if (unlikely(curr == scx_rescuee(rq))) + if (unlikely(donor == scx_rescuee(rq))) scx_rescue_charge(rq, delta_exec); dl_server_update(&rq->ext_server, delta_exec); @@ -1666,9 +1673,9 @@ static void rq_owned_post_enq(struct scx_sched *sch, struct rq *rq, if (rq->scx.flags & SCX_RQ_IN_DISPATCH) return; - if ((enq_flags & (SCX_ENQ_PREEMPT | SCX_ENQ_PREEMPT_LAZY)) && p != rq->curr && - rq->curr->sched_class == &ext_sched_class) { - if (likely(scx_set_task_slice(rq->curr, 0))) { + if ((enq_flags & (SCX_ENQ_PREEMPT | SCX_ENQ_PREEMPT_LAZY)) && + p != rq->donor && rq->donor->sched_class == &ext_sched_class) { + if (likely(scx_set_task_slice(rq->donor, 0))) { if (enq_flags & SCX_ENQ_PREEMPT) resched_curr(rq); else @@ -2273,13 +2280,14 @@ static void enqueue_task_scx(struct rq *rq, struct task_struct *p, int core_enq_ rq->scx.flags |= SCX_RQ_IN_WAKEUP; /* - * Restoring a running task will be immediately followed by - * set_next_task_scx() which expects the task to not be on the BPF + * Restoring the current scheduling context will be immediately followed + * by set_next_task_scx() which expects the task to not be on the BPF * scheduler as tasks can only start running through local DSQs. Force * direct-dispatch into the local DSQ by setting the sticky_cpu. Mark * IGNORE_CAPS to force entry into the local DSQ. */ - if (unlikely(enq_flags & ENQUEUE_RESTORE) && task_current(rq, p)) { + if (unlikely(enq_flags & ENQUEUE_RESTORE) && + task_current_donor(rq, p)) { sticky_cpu = cpu_of(rq); enq_flags |= SCX_ENQ_IGNORE_CAPS; } @@ -2446,7 +2454,7 @@ static bool dequeue_task_scx(struct rq *rq, struct task_struct *p, int core_deq_ p->scx.flags &= ~SCX_TASK_REENQ_REASON_MASK; /* see scx_task_slice_ended() for the save/restore exception */ - if (!((deq_flags & DEQUEUE_SAVE) && task_current(rq, p))) + if (!((deq_flags & DEQUEUE_SAVE) && task_current_donor(rq, p))) scx_task_slice_ended(rq, p); clear_direct_dispatch(p); @@ -3014,7 +3022,8 @@ static void dispatch_to_local_dsq(struct scx_sched *sch, struct rq *rq, } /* if the destination CPU is idle, wake it up */ - if (!fallback && sched_class_above(p->sched_class, dst_rq->curr->sched_class)) + if (!fallback && sched_class_above(p->sched_class, + dst_rq->donor->sched_class)) resched_curr(dst_rq); } @@ -3248,6 +3257,7 @@ static void scx_start_task_running(struct rq *rq, struct task_struct *p) static void set_next_task_scx(struct rq *rq, struct task_struct *p, enum snt_e type) { bool first = type == SNT_PICK; + bool can_stop_tick; if (type == SNT_REPICK) return; @@ -3283,6 +3293,7 @@ static void set_next_task_scx(struct rq *rq, struct task_struct *p, enum snt_e t /* apply any pending out-of-band slice request before the tick decision */ apply_task_slice_oob(rq, p); + can_stop_tick = p->scx.slice == SCX_SLICE_INF && !p->is_blocked; /* * @p is getting newly scheduled or got kicked after someone updated its @@ -3293,7 +3304,7 @@ static void set_next_task_scx(struct rq *rq, struct task_struct *p, enum snt_e t * nohz. In the future, we might want to add a mechanism to update * load_avgs periodically on tick-stopped CPUs. */ - if (p->scx.slice == SCX_SLICE_INF) { + if (can_stop_tick) { if (!(rq->scx.flags & SCX_RQ_CAN_STOP_TICK)) { /* * Bypass mode always assigns finite slices, so @p @@ -3314,7 +3325,8 @@ static void set_next_task_scx(struct rq *rq, struct task_struct *p, enum snt_e t /* * @rq still references the outgoing scheduling context. A finite - * slice is sufficient by itself to require the tick. + * slice or a blocked proxy donor is sufficient by itself to require + * the tick. */ if (tick_nohz_full_cpu(cpu_of(rq))) tick_nohz_dep_set_cpu(cpu_of(rq), TICK_DEP_BIT_SCHED); @@ -3633,7 +3645,7 @@ static enum scx_dsp_verdict dispatch_core_pick(struct rq *rq, struct rq_flags *r static struct task_struct * do_pick_task_scx(struct rq *rq, struct rq_flags *rf, bool force_scx) { - struct task_struct *prev = rq->curr; + struct task_struct *prev = rq->donor; enum scx_dsp_verdict verdict; struct task_struct *p; @@ -4079,9 +4091,9 @@ void scx_tick(struct rq *rq) update_other_load_avgs(rq); } -static void task_tick_scx(struct rq *rq, struct task_struct *curr, int queued) +static void task_tick_scx(struct rq *rq, struct task_struct *donor, int queued) { - struct scx_sched *sch = scx_task_sched(curr); + struct scx_sched *sch = scx_task_sched(donor); update_curr_scx(rq); @@ -4090,13 +4102,14 @@ static void task_tick_scx(struct rq *rq, struct task_struct *curr, int queued) * management. */ if (scx_bypassing(sch, cpu_of(rq))) - scx_set_task_slice(curr, 0); + scx_set_task_slice(donor, 0); else if (SCX_HAS_OP(sch, tick)) - SCX_CALL_OP_TASK(sch, tick, rq, curr); + SCX_CALL_OP_TASK(sch, tick, rq, donor); - if (!curr->scx.slice) { + if (!donor->scx.slice) { /* the slice can't be trusted while bypassing */ - if (READ_ONCE(curr->scx.lazy_resched) && !scx_bypassing(sch, cpu_of(rq))) + if (READ_ONCE(donor->scx.lazy_resched) && + !scx_bypassing(sch, cpu_of(rq))) scx_resched_curr_lazy(rq); else resched_curr(rq); @@ -4789,16 +4802,16 @@ static u32 reenq_local(struct scx_sched *sch, struct rq *rq, u64 reenq_flags) } /* - * The revoke that scheduled this scan may have raced the pick: curr + * The revoke that scheduled this scan may have raced the pick: donor * may be a now-capless task, either one that kept running or one * promoted off the local DSQ between the ecaps sync and this scan. * Zero the slice to evict it. The enqueue gate blocks new capless * inserts, so no later pick can slip through after the scan. */ if ((reenq_flags & SCX_REENQ_CAP_REVOKE) && - rq->curr->sched_class == &ext_sched_class && - scx_task_reenq_on_cap_revoke(rq, rq->curr)) { - scx_set_task_slice(rq->curr, 0); + rq->donor->sched_class == &ext_sched_class && + scx_task_reenq_on_cap_revoke(rq, rq->donor)) { + scx_set_task_slice(rq->donor, 0); resched_curr(rq); } @@ -5033,14 +5046,18 @@ static void run_deferred(struct rq *rq) #ifdef CONFIG_NO_HZ_FULL bool scx_can_stop_tick(struct rq *rq) { - struct task_struct *p = rq->curr; + struct task_struct *p = rq->donor; struct scx_sched *sch = scx_task_sched(p); + /* Keep the tick running while a blocked proxy donor is selected. */ + if (p->is_blocked) + return false; + if (p->sched_class != &ext_sched_class) return true; /* - * @rq->curr may still reference an outgoing EXT task after it has been + * @rq->donor may still reference an outgoing EXT task after it has been * dequeued. If no EXT tasks are accounted on @rq, ignore its stale * slice state. If another task is dispatched from a DSQ, * set_next_task_scx() will update the dependency for the incoming task. @@ -5061,7 +5078,8 @@ bool scx_can_stop_tick(struct rq *rq) /* * @rq can dispatch from different DSQs, so we can't tell whether it * needs the tick or not by looking at nr_running. Allow stopping ticks - * iff the BPF scheduler indicated so. See set_next_task_scx(). + * iff set_next_task_scx() determined that the selected scheduling context + * can run tickless. */ return rq->scx.flags & SCX_RQ_CAN_STOP_TICK; } @@ -6576,9 +6594,9 @@ void scx_bypass(struct scx_sched *sch, bool bypass) /* * Bypass trumps protection. Cycling clears for queued - * tasks but current task needs explicit stripping. + * tasks but the current donor needs explicit stripping. */ - if (bypass && task_current(rq, p)) + if (bypass && task_current_donor(rq, p)) scx_task_slice_ended(rq, p); /* cycling deq/enq is enough, see the function comment */ @@ -7286,6 +7304,8 @@ static void scx_dump_cpu(struct scx_sched *sch, struct seq_buf *s, scx_rescue_dump(&ns, rq); scx_dump_line(&ns, " curr=%s[%d] class=%ps", rq->curr->comm, rq->curr->pid, rq->curr->sched_class); + scx_dump_line(&ns, " donor=%s[%d] class=%ps", + rq->donor->comm, rq->donor->pid, rq->donor->sched_class); if (!cpumask_empty(pcpu->cpus_to_kick)) scx_dump_line(&ns, " cpus_to_kick : %*pb", cpumask_pr_args(pcpu->cpus_to_kick)); @@ -7332,6 +7352,10 @@ static void scx_dump_cpu(struct scx_sched *sch, struct seq_buf *s, if (rq->curr->sched_class == &ext_sched_class && (dump_all_tasks || scx_task_on_sched(sch, rq->curr))) scx_dump_task(sch, s, dctx, rq, rq->curr, '*'); + if (rq->donor != rq->curr && + rq->donor->sched_class == &ext_sched_class && + (dump_all_tasks || scx_task_on_sched(sch, rq->donor))) + scx_dump_task(sch, s, dctx, rq, rq->donor, ' '); list_for_each_entry(p, &rq->scx.runnable_list, scx.runnable_node) if (dump_all_tasks || scx_task_on_sched(sch, p)) @@ -8890,7 +8914,7 @@ static bool kick_one_cpu(s32 cpu, struct scx_sched_pcpu *pcpu, struct rq *this_r bool preempt, preempt_lazy, wait, immediate; rq_lock_irqsave(rq, &rf); - cur_class = rq->curr->sched_class; + cur_class = rq->donor->sched_class; preempt = cpumask_test_cpu(cpu, pcpu->cpus_to_preempt); preempt_lazy = cpumask_test_cpu(cpu, pcpu->cpus_to_preempt_lazy); wait = cpumask_test_cpu(cpu, pcpu->cpus_to_wait); @@ -8921,7 +8945,7 @@ static bool kick_one_cpu(s32 cpu, struct scx_sched_pcpu *pcpu, struct rq *this_r __scx_add_event(pcpu->sch, SCX_EV_SUB_PREEMPT_DENIED, 1); /* degrade to a plain, immediate kick */ immediate = true; - } else if (unlikely(!scx_set_task_slice(rq->curr, 0))) { + } else if (unlikely(!scx_set_task_slice(rq->donor, 0))) { __scx_add_event(pcpu->sch, SCX_EV_SLICE_DENIED, 1); } } @@ -9924,8 +9948,10 @@ __bpf_kfunc bool scx_bpf_task_set_slice(struct task_struct *p, u64 slice, return false; /* - * Directly write only when we hold the lock of the rq @p is queued or - * running on. See the write rules above. + * Directly write only when we hold the lock of the rq @p is queued on or + * provides the current scheduling context for. Under proxy execution, + * rq->donor owns and consumes the slice while rq->curr executes on its + * behalf. See the slice write rules above. * * While @p is queued on a user DSQ or in the BPF scheduler, * synchronization is the scheduler's responsibility. This write can @@ -9939,7 +9965,7 @@ __bpf_kfunc bool scx_bpf_task_set_slice(struct task_struct *p, u64 slice, locked_rq = scx_locked_rq(); if (!locked_rq || (READ_ONCE(p->scx.runnable_cpu) != cpu_of(locked_rq) && - !task_current(locked_rq, p))) { + !task_current_donor(locked_rq, p))) { set_task_slice_oob(sch, p, slice); return true; } @@ -10927,12 +10953,17 @@ __bpf_kfunc void scx_bpf_put_cpumask(const struct cpumask *cpumask) } /** - * scx_bpf_task_running - Is task currently running? + * scx_bpf_task_running - Is task the current scheduling context? * @p: task of interest + * + * Under proxy execution, this reports the donor rather than the task whose + * code is physically executing. The physical execution context is intentionally + * not exposed to the BPF scheduler, which continues to observe the donor as the + * running scheduling context. */ __bpf_kfunc bool scx_bpf_task_running(const struct task_struct *p) { - return task_rq(p)->curr == p; + return rcu_access_pointer(task_rq(p)->donor) == p; } /** @@ -10993,10 +11024,15 @@ __bpf_kfunc struct rq *scx_bpf_locked_rq(const struct bpf_prog_aux *aux) } /** - * scx_bpf_cpu_curr - Return remote CPU's curr task + * scx_bpf_cpu_curr - Return remote CPU's current scheduling context * @cpu: CPU of interest * @aux: implicit BPF argument to access bpf_prog_aux hidden from BPF progs * + * Under proxy execution, this returns the donor, which supplies the scheduling + * policy and runtime budget, rather than the task whose code is physically + * executing. The physical execution context is intentionally not exposed to + * the BPF scheduler. + * * Callers must hold RCU read lock (KF_RCU). */ __bpf_kfunc struct task_struct *scx_bpf_cpu_curr(s32 cpu, const struct bpf_prog_aux *aux) @@ -11012,7 +11048,7 @@ __bpf_kfunc struct task_struct *scx_bpf_cpu_curr(s32 cpu, const struct bpf_prog_ if (!scx_cpu_valid(sch, cpu, NULL)) return NULL; - return rcu_dereference(cpu_rq(cpu)->curr); + return rcu_dereference(cpu_rq(cpu)->donor); } /** @@ -11036,7 +11072,7 @@ __bpf_kfunc struct task_struct *scx_bpf_cid_curr(s32 cid, const struct bpf_prog_ cpu = scx_cid_to_cpu(sch, cid); if (cpu < 0) return NULL; - return rcu_dereference(cpu_rq(cpu)->curr); + return rcu_dereference(cpu_rq(cpu)->donor); } /** diff --git a/kernel/sched/ext/sub.c b/kernel/sched/ext/sub.c index 08599bc57801..4541ef8eec95 100644 --- a/kernel/sched/ext/sub.c +++ b/kernel/sched/ext/sub.c @@ -285,7 +285,8 @@ void scx_rescue_charge(struct rq *rq, s64 delta_exec) rq->scx.rescue.budget -= delta_exec; /* per-cpu usage average feeds the overload victim pick */ - pcpu = per_cpu_ptr(scx_task_sched(rq->curr)->pcpu, cpu_of(rq)); + pcpu = per_cpu_ptr(scx_task_sched(rq->scx.rescue.curr)->pcpu, + cpu_of(rq)); pcpu->rescue_avg = scx_rescue_decay_avg(pcpu) + delta_exec; if (!scx_rescue_slice_remaining(rq)) @@ -557,7 +558,7 @@ static void scx_rescue_timerfn(struct timer_list *timer) scx_rescue_admit(rq, p, slice); scx_move_local_task_to_local_dsq(scx_task_sched(p), p, SCX_ENQ_IGNORE_CAPS, rq); - if (sched_class_above(&ext_sched_class, rq->curr->sched_class)) + if (sched_class_above(&ext_sched_class, rq->donor->sched_class)) resched_curr(rq); } else if (p->scx.dsq && rq->scx.rescue.budget > 2 * scx_rescue_quantum_ns) { /* diff --git a/kernel/sched/ext/sub.h b/kernel/sched/ext/sub.h index 7621c28c7e8c..c0174e523f2a 100644 --- a/kernel/sched/ext/sub.h +++ b/kernel/sched/ext/sub.h @@ -186,17 +186,18 @@ static inline u64 scx_caps_for_task(struct task_struct *p) return SCX_CAP_ENQ; } -/* the cap @sch needs to preempt @rq's current task, 0 if none */ -static inline u64 scx_caps_for_preempt(struct scx_sched *sch, struct rq *rq, u64 enq_flags) +/* the cap @sch needs to preempt @rq's current scheduling context, 0 if none */ +static inline u64 scx_caps_for_preempt(struct scx_sched *sch, struct rq *rq, + u64 enq_flags) { - struct task_struct *curr = rq->curr; + struct task_struct *donor = rq->donor; /* a kernel-forced placement preempts regardless of caps */ if (unlikely(enq_flags & SCX_ENQ_IGNORE_CAPS)) return 0; /* a non-ext task can't be preempted by ext, own-subtree needs no cap */ - if (curr->sched_class != &ext_sched_class || - scx_is_descendant(scx_task_sched(curr), sch)) + if (donor->sched_class != &ext_sched_class || + scx_is_descendant(scx_task_sched(donor), sch)) return 0; return SCX_CAP_PREEMPT; }