Messages in this thread | | | Date | Mon, 7 Nov 2022 18:12:53 +0100 | From | Sebastian Andrzej Siewior <> | Subject | Re: Crash with PREEMPT_RT on aarch64 machine |
| |
On 2022-11-07 17:30:16 [+0100], Jan Kara wrote: > On Mon 07-11-22 16:10:34, Sebastian Andrzej Siewior wrote: > > + locking, arm64 > > > > On 2022-11-07 14:56:36 [+0100], Jan Kara wrote: > > > > spinlock_t and raw_spinlock_t differ slightly in terms of locking. > > > > rt_spin_lock() has the fast path via try_cmpxchg_acquire(). If you > > > > enable CONFIG_DEBUG_RT_MUTEXES then you would force the slow path which > > > > always acquires the rt_mutex_base::wait_lock (which is a raw_spinlock_t) > > > > while the actual lock is modified via cmpxchg. > > > > > > So I've tried enabling CONFIG_DEBUG_RT_MUTEXES and indeed the corruption > > > stops happening as well. So do you suspect some bug in the CPU itself? > > > > If it is only enabling CONFIG_DEBUG_RT_MUTEXES (and not whole lockdep) > > then it looks very suspicious. > > Just to confirm, CONFIG_DEBUG_RT_MUTEXES is the only thing I've enabled and > the list corruption disappeared.
I don't know if this works but: if you tell task_struct_cachep to be created with SLAB_CACHE_DMA32 then the pointer should only have the lower 32bit set. With this could make rt_mutex_base::owner an atomic_t type. You could then replace try_cmpxchg_acquire() with atomic_try_cmpxchg_acquire() and do the 32bit cmpxchg. You would then need set the const upper 32bit of the pointer while returning the pointer. I have no idea how much sense it makes but you would avoid the 64bit cmpxchg making those two a little more alike :)
> Honza >
Sebastian
| |