lkml.org 
[lkml]   [2022]   [Jul]   [4]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
    /
    From
    SubjectRe: [PATCH] sched: fix rq lock recursion issue
    Date

    On 6/30/22 2:53 PM, Qais Yousef wrote:
    > Hi Satya
    >
    > On 06/24/22 00:42, Satya Durga Srinivasu Prabhala wrote:
    >> Below recursion is observed in a rare scenario where __schedule()
    >> takes rq lock, at around same time task's affinity is being changed,
    >> bpf function for tracing sched_switch calls migrate_enabled(),
    >> checks for affinity change (cpus_ptr != cpus_mask) lands into
    >> __set_cpus_allowed_ptr which tries acquire rq lock and causing the
    >> recursion bug.
    >>
    >> Fix the issue by switching to preempt_enable/disable() for non-RT
    >> Kernels.
    > Interesting bug. Thanks for the report. Unfortunately I can't see this being
    > a fix as it just limits the bug visibility to PREEMPT_RT kernels, but won't fix
    > anything, no? ie: Kernels compiled with PREEMPT_RT will still hit this failure.
    Thanks for taking a look. That's right.
    > I'm curious how the race with set affinity is happening. I would have thought
    > user space would get blocked as __schedule() will hold the rq lock.
    >
    > Do you have more details on that?
    I'm still trying to figure out how we even end with up such a race. No
    easy way repro
    the issue, I'm checking internally with some debug logs.
    >
    > Thanks
    >
    > --
    > Qais Yousef
    >
    >> -010 |spin_bug(lock = ???, msg = ???)
    >> -011 |debug_spin_lock_before(inline)
    >> -011 |do_raw_spin_lock(lock = 0xFFFFFF89323BB600)
    >> -012 |_raw_spin_lock(inline)
    >> -012 |raw_spin_rq_lock_nested(inline)
    >> -012 |raw_spin_rq_lock(inline)
    >> -012 |task_rq_lock(p = 0xFFFFFF88CFF1DA00, rf = 0xFFFFFFC03707BBE8)
    >> -013 |__set_cpus_allowed_ptr(inline)
    >> -013 |migrate_enable()
    >> -014 |trace_call_bpf(call = ?, ctx = 0xFFFFFFFDEF954600)
    >> -015 |perf_trace_run_bpf_submit(inline)
    >> -015 |perf_trace_sched_switch(__data = 0xFFFFFFE82CF0BCB8, preempt = FALSE, prev = ?, next = ?)
    >> -016 |__traceiter_sched_switch(inline)
    >> -016 |trace_sched_switch(inline)
    >> -016 |__schedule(sched_mode = ?)
    >> -017 |schedule()
    >> -018 |arch_local_save_flags(inline)
    >> -018 |arch_irqs_disabled(inline)
    >> -018 |__raw_spin_lock_irq(inline)
    >> -018 |_raw_spin_lock_irq(inline)
    >> -018 |worker_thread(__worker = 0xFFFFFF88CE251300)
    >> -019 |kthread(_create = 0xFFFFFF88730A5A80)
    >> -020 |ret_from_fork(asm)
    >>
    >> Signed-off-by: Satya Durga Srinivasu Prabhala <quic_satyap@quicinc.com>
    >> ---
    >> kernel/sched/core.c | 8 ++++++++
    >> 1 file changed, 8 insertions(+)
    >>
    >> diff --git a/kernel/sched/core.c b/kernel/sched/core.c
    >> index bfa7452ca92e..e254e9227341 100644
    >> --- a/kernel/sched/core.c
    >> +++ b/kernel/sched/core.c
    >> @@ -2223,6 +2223,7 @@ static void migrate_disable_switch(struct rq *rq, struct task_struct *p)
    >>
    >> void migrate_disable(void)
    >> {
    >> +#ifdef CONFIG_PREEMPT_RT
    >> struct task_struct *p = current;
    >>
    >> if (p->migration_disabled) {
    >> @@ -2234,11 +2235,15 @@ void migrate_disable(void)
    >> this_rq()->nr_pinned++;
    >> p->migration_disabled = 1;
    >> preempt_enable();
    >> +#else
    >> + preempt_disable();
    >> +#endif
    >> }
    >> EXPORT_SYMBOL_GPL(migrate_disable);
    >>
    >> void migrate_enable(void)
    >> {
    >> +#ifdef CONFIG_PREEMPT_RT
    >> struct task_struct *p = current;
    >>
    >> if (p->migration_disabled > 1) {
    >> @@ -2265,6 +2270,9 @@ void migrate_enable(void)
    >> p->migration_disabled = 0;
    >> this_rq()->nr_pinned--;
    >> preempt_enable();
    >> +#else
    >> + preempt_enable();
    >> +#endif
    >> }
    >> EXPORT_SYMBOL_GPL(migrate_enable);
    >>
    >> --
    >> 2.36.1
    >>

    \
     
     \ /
      Last update: 2022-07-05 04:07    [W:3.601 / U:0.736 seconds]
    ©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site