From 8dafa9d0eb1a1550a0f4d462db9354161bc51e0c Mon Sep 17 00:00:00 2001 From: Peter Zijlstra Date: Fri, 6 Oct 2023 21:24:45 +0200 Subject: [PATCH 1/2] sched/eevdf: Fix min_deadline heap integrity Marek and Biju reported instances of: "EEVDF scheduling fail, picking leftmost" which Mike correlated with cgroup scheduling and the min_deadline heap getting corrupted; some trace output confirms: > And yeah, min_deadline is hosed somehow: > > validate_cfs_rq: --- / > __print_se: ffff88845cf48080 w: 1024 ve: -58857638 lag: 870381 vd: -55861854 vmd: -66302085 E (11372/tr) > __print_se: ffff88810d165800 w: 25 ve: -80323686 lag: 22336429 vd: -41496434 vmd: -66302085 E (-1//autogroup-31) > __print_se: ffff888108379000 w: 25 ve: 0 lag: -57987257 vd: 114632828 vmd: 114632828 N (-1//autogroup-33) > validate_cfs_rq: min_deadline: -55861854 avg_vruntime: -62278313462 / 1074 = -57987256 Turns out that reweight_entity(), which tries really hard to be fast, does not do the normal dequeue+update+enqueue pattern but *does* scale the deadline. However, it then fails to propagate the updated deadline value up the heap. Fixes: 147f3efaa241 ("sched/fair: Implement an EEVDF-like scheduling policy") Reported-by: Marek Szyprowski Reported-by: Biju Das Reported-by: Mike Galbraith Signed-off-by: Peter Zijlstra (Intel) Tested-by: Marek Szyprowski Tested-by: Biju Das Tested-by: Mike Galbraith Link: https://lkml.kernel.org/r/20231006192445.GE743@noisy.programming.kicks-ass.net --- kernel/sched/fair.c | 1 + 1 file changed, 1 insertion(+) diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index ef7490c4b8b4..a4b904a010c6 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -3613,6 +3613,7 @@ static void reweight_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, */ deadline = div_s64(deadline * old_weight, weight); se->deadline = se->vruntime + deadline; + min_deadline_cb_propagate(&se->run_node, NULL); } #ifdef CONFIG_SMP From b01db23d5923a35023540edc4f0c5f019e11ac7d Mon Sep 17 00:00:00 2001 From: Benjamin Segall Date: Fri, 29 Sep 2023 17:09:30 -0700 Subject: [PATCH 2/2] sched/eevdf: Fix pick_eevdf() The old pick_eevdf() could fail to find the actual earliest eligible deadline when it descended to the right looking for min_deadline, but it turned out that that min_deadline wasn't actually eligible. In that case we need to go back and search through any left branches we skipped looking for the actual best _eligible_ min_deadline. This is more expensive, but still O(log n), and at worst should only involve descending two branches of the rbtree. I've run this through a userspace stress test (thank you tools/lib/rbtree.c), so hopefully this implementation doesn't miss any corner cases. Fixes: 147f3efaa241 ("sched/fair: Implement an EEVDF-like scheduling policy") Signed-off-by: Ben Segall Signed-off-by: Peter Zijlstra (Intel) Link: https://lkml.kernel.org/r/xm261qego72d.fsf_-_@google.com --- kernel/sched/fair.c | 72 ++++++++++++++++++++++++++++++++++++--------- 1 file changed, 58 insertions(+), 14 deletions(-) diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c index a4b904a010c6..061a30a8925a 100644 --- a/kernel/sched/fair.c +++ b/kernel/sched/fair.c @@ -872,14 +872,16 @@ struct sched_entity *__pick_first_entity(struct cfs_rq *cfs_rq) * * Which allows an EDF like search on (sub)trees. */ -static struct sched_entity *pick_eevdf(struct cfs_rq *cfs_rq) +static struct sched_entity *__pick_eevdf(struct cfs_rq *cfs_rq) { struct rb_node *node = cfs_rq->tasks_timeline.rb_root.rb_node; struct sched_entity *curr = cfs_rq->curr; struct sched_entity *best = NULL; + struct sched_entity *best_left = NULL; if (curr && (!curr->on_rq || !entity_eligible(cfs_rq, curr))) curr = NULL; + best = curr; /* * Once selected, run a task until it either becomes non-eligible or @@ -900,33 +902,75 @@ static struct sched_entity *pick_eevdf(struct cfs_rq *cfs_rq) } /* - * If this entity has an earlier deadline than the previous - * best, take this one. If it also has the earliest deadline - * of its subtree, we're done. + * Now we heap search eligible trees for the best (min_)deadline */ - if (!best || deadline_gt(deadline, best, se)) { + if (!best || deadline_gt(deadline, best, se)) best = se; - if (best->deadline == best->min_deadline) + + /* + * Every se in a left branch is eligible, keep track of the + * branch with the best min_deadline + */ + if (node->rb_left) { + struct sched_entity *left = __node_2_se(node->rb_left); + + if (!best_left || deadline_gt(min_deadline, best_left, left)) + best_left = left; + + /* + * min_deadline is in the left branch. rb_left and all + * descendants are eligible, so immediately switch to the second + * loop. + */ + if (left->min_deadline == se->min_deadline) break; } - /* - * If the earlest deadline in this subtree is in the fully - * eligible left half of our space, go there. - */ + /* min_deadline is at this node, no need to look right */ + if (se->deadline == se->min_deadline) + break; + + /* else min_deadline is in the right branch. */ + node = node->rb_right; + } + + /* + * We ran into an eligible node which is itself the best. + * (Or nr_running == 0 and both are NULL) + */ + if (!best_left || (s64)(best_left->min_deadline - best->deadline) > 0) + return best; + + /* + * Now best_left and all of its children are eligible, and we are just + * looking for deadline == min_deadline + */ + node = &best_left->run_node; + while (node) { + struct sched_entity *se = __node_2_se(node); + + /* min_deadline is the current node */ + if (se->deadline == se->min_deadline) + return se; + + /* min_deadline is in the left branch */ if (node->rb_left && __node_2_se(node->rb_left)->min_deadline == se->min_deadline) { node = node->rb_left; continue; } + /* else min_deadline is in the right branch */ node = node->rb_right; } + return NULL; +} - if (!best || (curr && deadline_gt(deadline, best, curr))) - best = curr; +static struct sched_entity *pick_eevdf(struct cfs_rq *cfs_rq) +{ + struct sched_entity *se = __pick_eevdf(cfs_rq); - if (unlikely(!best)) { + if (!se) { struct sched_entity *left = __pick_first_entity(cfs_rq); if (left) { pr_err("EEVDF scheduling fail, picking leftmost\n"); @@ -934,7 +978,7 @@ static struct sched_entity *pick_eevdf(struct cfs_rq *cfs_rq) } } - return best; + return se; } #ifdef CONFIG_SCHED_DEBUG