Re: [BUG] infiniband: sw: rdmavt: possible ABBA deadlocks in rvt_ruc_loopback()

From: Dennis Dalessandro
Date: Thu Oct 20 2022 - 12:15:59 EST


On 10/20/22 9:37 AM, Jia-Ju Bai wrote:
> Hello,
>
> My static analysis tool reports several possible ABBA deadlock in the
> rdmavt driver in Linux 5.18:
>
> rvt_ruc_loopback()
>   spin_lock_irqsave(&sqp->s_lock, flags); --> Line 3190 (Lock A)
>   spin_lock(&sqp->r_lock); --> Line 3195 (Lock B)
>
> rvt_qp_mr_clean()
>   spin_lock_irq(&qp->r_lock); --> Line 698 (Lock B)
>   spin_lock(&qp->s_lock); --> Line 700 (Lock A)
>
> rvt_rc_timeout()
>   spin_lock_irqsave(&qp->r_lock, flags); --> Line 2595 (Lock B)
>   spin_lock(&qp->s_lock); --> Line 2596 (Lock A)
>
> rvt_modify_qp()
>   spin_lock_irq(&qp->r_lock); --> Line 1419 (Lock B)
>   spin_lock(&qp->s_lock); --> Line 1421(Lock A)
>
> _rvt_reset_qp()
>   spin_lock_irq(&qp->r_lock); --> Line 907 (Lock B)
>   spin_lock(&qp->s_lock); --> Line 909 (Lock A)
>
> rvt_reset_qp()
>   spin_lock_irq(&qp->r_lock); --> Line 936 (Lock B)
>   spin_lock(&qp->s_lock); --> Line 938 (Lock A)
>
> When rvt_ruc_loopback() is concurrently executed with rvt_qp_mr_clean(),
> rvt_rc_timeout(), rvt_modify_qp(), _rvt_reset_qp() or rvt_reset_qp(),
> the deadlocks can occur.
>
> I am not quite sure whether these possible deadlocks are real and how to
> fix them if real.
> Any feedback would be appreciated, thanks :)
>
> Reported-by: TOTE Robot <oslab@xxxxxxxxxxxxxxx>

Thanks, we'll look into them.

-Denny