From f23c042ce34ba265cf3129d530702b5d218e3f4b Mon Sep 17 00:00:00 2001 From: Daniel Bristot de Oliveira Date: Mon, 27 May 2024 14:06:47 +0200 Subject: sched/deadline: Comment sched_dl_entity::dl_server variable Add an explanation for the newly added variable. Fixes: 63ba8422f876 ("sched/deadline: Introduce deadline servers") Signed-off-by: Daniel Bristot de Oliveira Signed-off-by: Peter Zijlstra (Intel) Tested-by: Juri Lelli Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/147f7aa8cb8fd925f36aa8059af6a35aad08b45a.1716811044.git.bristot@kernel.org --- include/linux/sched.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/sched.h b/include/linux/sched.h index f8d150343d42..1c771ea4481d 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -639,6 +639,8 @@ struct sched_dl_entity { * * @dl_overrun tells if the task asked to be informed about runtime * overruns. + * + * @dl_server tells if this is a server entity. */ unsigned int dl_throttled : 1; unsigned int dl_yielded : 1; -- cgit v1.2.3 From a110a81c52a9de73e2e57e826dd3bf0fd4c22226 Mon Sep 17 00:00:00 2001 From: Daniel Bristot de Oliveira Date: Mon, 27 May 2024 14:06:51 +0200 Subject: sched/deadline: Deferrable dl server Among the motivations for the DL servers is the real-time throttling mechanism. This mechanism works by throttling the rt_rq after running for a long period without leaving space for fair tasks. The base dl server avoids this problem by boosting fair tasks instead of throttling the rt_rq. The point is that it boosts without waiting for potential starvation, causing some non-intuitive cases. For example, an IRQ dispatches two tasks on an idle system, a fair and an RT. The DL server will be activated, running the fair task before the RT one. This problem can be avoided by deferring the dl server activation. By setting the defer option, the dl_server will dispatch an SCHED_DEADLINE reservation with replenished runtime, but throttled. The dl_timer will be set for the defer time at (period - runtime) ns from start time. Thus boosting the fair rq at defer time. If the fair scheduler has the opportunity to run while waiting for defer time, the dl server runtime will be consumed. If the runtime is completely consumed before the defer time, the server will be replenished while still in a throttled state. Then, the dl_timer will be reset to the new defer time If the fair server reaches the defer time without consuming its runtime, the server will start running, following CBS rules (thus without breaking SCHED_DEADLINE). Then the server will continue the running state (without deferring) until it fair tasks are able to execute as regular fair scheduler (end of the starvation). Signed-off-by: Daniel Bristot de Oliveira Signed-off-by: Peter Zijlstra (Intel) Tested-by: Juri Lelli Link: https://lore.kernel.org/r/dd175943c72533cd9f0b87767c6499204879cc38.1716811044.git.bristot@kernel.org --- include/linux/sched.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'include') diff --git a/include/linux/sched.h b/include/linux/sched.h index 1c771ea4481d..4edd7e2096fb 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -641,12 +641,24 @@ struct sched_dl_entity { * overruns. * * @dl_server tells if this is a server entity. + * + * @dl_defer tells if this is a deferred or regular server. For + * now only defer server exists. + * + * @dl_defer_armed tells if the deferrable server is waiting + * for the replenishment timer to activate it. + * + * @dl_defer_running tells if the deferrable server is actually + * running, skipping the defer phase. */ unsigned int dl_throttled : 1; unsigned int dl_yielded : 1; unsigned int dl_non_contending : 1; unsigned int dl_overrun : 1; unsigned int dl_server : 1; + unsigned int dl_defer : 1; + unsigned int dl_defer_armed : 1; + unsigned int dl_defer_running : 1; /* * Bandwidth enforcement timer. Each -deadline task has its -- cgit v1.2.3 From c8a85394cfdb4696b4e2f8a0f3066a1c921af426 Mon Sep 17 00:00:00 2001 From: "Joel Fernandes (Google)" Date: Mon, 27 May 2024 14:06:54 +0200 Subject: sched/core: Fix picking of tasks for core scheduling with DL server * Use simple CFS pick_task for DL pick_task DL server's pick_task calls CFS's pick_next_task_fair(), this is wrong because core scheduling's pick_task only calls CFS's pick_task() for evaluation / checking of the CFS task (comparing across CPUs), not for actually affirmatively picking the next task. This causes RB tree corruption issues in CFS that were found by syzbot. * Make pick_task_fair clear DL server A DL task pick might set ->dl_server, but it is possible the task will never run (say the other HT has a stop task). If the CFS task is picked in the future directly (say without DL server), ->dl_server will be set. So clear it in pick_task_fair(). This fixes the KASAN issue reported by syzbot in set_next_entity(). (DL refactoring suggestions by Vineeth Pillai). Reported-by: Suleiman Souhlal Signed-off-by: "Joel Fernandes (Google)" Signed-off-by: Daniel Bristot de Oliveira Signed-off-by: Peter Zijlstra (Intel) Reviewed-by: Vineeth Pillai Tested-by: Juri Lelli Link: https://lore.kernel.org/r/b10489ab1f03d23e08e6097acea47442e7d6466f.1716811044.git.bristot@kernel.org --- include/linux/sched.h | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/include/linux/sched.h b/include/linux/sched.h index 4edd7e2096fb..2c1b4ee3234f 100644 --- a/include/linux/sched.h +++ b/include/linux/sched.h @@ -686,7 +686,8 @@ struct sched_dl_entity { */ struct rq *rq; dl_server_has_tasks_f server_has_tasks; - dl_server_pick_f server_pick; + dl_server_pick_f server_pick_next; + dl_server_pick_f server_pick_task; #ifdef CONFIG_RT_MUTEXES /* -- cgit v1.2.3