From 0e4097c3354e2f5a5ad8affd9dc7f7f7d00bb6b9 Mon Sep 17 00:00:00 2001 From: Wanpeng Li Date: Sun, 9 Jul 2017 00:40:28 -0700 Subject: sched/cputime: Don't use smp_processor_id() in preemptible context Recent kernels trigger this warning: BUG: using smp_processor_id() in preemptible [00000000] code: 99-trinity/181 caller is debug_smp_processor_id+0x17/0x19 CPU: 0 PID: 181 Comm: 99-trinity Not tainted 4.12.0-01059-g2a42eb9 #1 Call Trace: dump_stack+0x82/0xb8 check_preemption_disabled() debug_smp_processor_id() vtime_delta() task_cputime() thread_group_cputime() thread_group_cputime_adjusted() wait_consider_task() do_wait() SYSC_wait4() do_syscall_64() entry_SYSCALL64_slow_path() As Frederic pointed out: | Although those sched_clock_cpu() things seem to only matter when the | sched_clock() is unstable. And that stability is a condition for nohz_full | to work anyway. So probably sched_clock() alone would be enough. This patch fixes it by replacing sched_clock_cpu() with sched_clock() to avoid calling smp_processor_id() in a preemptible context. Reported-by: Xiaolong Ye Signed-off-by: Wanpeng Li Cc: Frederic Weisbecker Cc: Linus Torvalds Cc: Luiz Capitulino Cc: Peter Zijlstra Cc: Rik van Riel Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/1499586028-7402-1-git-send-email-wanpeng.li@hotmail.com [ Prettified the changelog. ] Signed-off-by: Ingo Molnar --- kernel/sched/cputime.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) (limited to 'kernel') diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c index 6e3ea4ac1bda..14d2dbf97c53 100644 --- a/kernel/sched/cputime.c +++ b/kernel/sched/cputime.c @@ -683,7 +683,7 @@ static u64 vtime_delta(struct vtime *vtime) { unsigned long long clock; - clock = sched_clock_cpu(smp_processor_id()); + clock = sched_clock(); if (clock < vtime->starttime) return 0; @@ -814,7 +814,7 @@ void arch_vtime_task_switch(struct task_struct *prev) write_seqcount_begin(&vtime->seqcount); vtime->state = VTIME_SYS; - vtime->starttime = sched_clock_cpu(smp_processor_id()); + vtime->starttime = sched_clock(); write_seqcount_end(&vtime->seqcount); } @@ -826,7 +826,7 @@ void vtime_init_idle(struct task_struct *t, int cpu) local_irq_save(flags); write_seqcount_begin(&vtime->seqcount); vtime->state = VTIME_SYS; - vtime->starttime = sched_clock_cpu(cpu); + vtime->starttime = sched_clock(); write_seqcount_end(&vtime->seqcount); local_irq_restore(flags); } -- cgit v1.2.3 From 193be41e33168a3a06eb9d356d9e39c69de161d2 Mon Sep 17 00:00:00 2001 From: Joel Fernandes Date: Wed, 12 Jul 2017 19:24:29 -0700 Subject: sched/deadline: Fix confusing comments about selection of top pi-waiter This comment in the code is incomplete, and I believe it begs a definition of dl_boosted to make sense of the condition that follows. Rewrite the comment and also rearrange the condition that follows to reflect the first condition "we have a top pi-waiter which is a SCHED_DEADLINE task" in that order. Also fix a typo that follows. Signed-off-by: Joel Fernandes Reviewed-by: Daniel Bristot de Oliveira Acked-by: Juri Lelli Cc: Linus Torvalds Cc: Peter Zijlstra Cc: Thomas Gleixner Link: http://lkml.kernel.org/r/20170713022429.10307-1-joelaf@google.com Signed-off-by: Ingo Molnar --- kernel/sched/deadline.c | 14 ++++++++------ 1 file changed, 8 insertions(+), 6 deletions(-) (limited to 'kernel') diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c index a84299f44b5d..755bd3f1a1a9 100644 --- a/kernel/sched/deadline.c +++ b/kernel/sched/deadline.c @@ -1392,17 +1392,19 @@ static void enqueue_task_dl(struct rq *rq, struct task_struct *p, int flags) struct sched_dl_entity *pi_se = &p->dl; /* - * Use the scheduling parameters of the top pi-waiter - * task if we have one and its (absolute) deadline is - * smaller than our one... OTW we keep our runtime and - * deadline. + * Use the scheduling parameters of the top pi-waiter task if: + * - we have a top pi-waiter which is a SCHED_DEADLINE task AND + * - our dl_boosted is set (i.e. the pi-waiter's (absolute) deadline is + * smaller than our deadline OR we are a !SCHED_DEADLINE task getting + * boosted due to a SCHED_DEADLINE pi-waiter). + * Otherwise we keep our runtime and deadline. */ - if (pi_task && p->dl.dl_boosted && dl_prio(pi_task->normal_prio)) { + if (pi_task && dl_prio(pi_task->normal_prio) && p->dl.dl_boosted) { pi_se = &pi_task->dl; } else if (!dl_prio(p->normal_prio)) { /* * Special case in which we have a !SCHED_DEADLINE task - * that is going to be deboosted, but exceedes its + * that is going to be deboosted, but exceeds its * runtime while doing so. No point in replenishing * it, as it's going to return back to its original * scheduling class after this. -- cgit v1.2.3