Question about qspinlock nest
Quoted 54 lines · ----- [email protected] wrote:
Quoted 12 lines · Zhenzhong Duan
Quoted 9 lines · Waiman Long
Quoted 8 lines · Zhenzhong Duan
Hi Maintainer,
There is a question confused me for days. Appreciate an answer.
In below code, the comment says we never have more than 4 nested contexts.
Quoted 6 lines
Quoted 6 lines
Quoted 6 lines
What happen if debug and mce exceptions nest with the four, or we ensure it never happen?
/*
* Per-CPU queue node structures; we can never have more than 4nested
Quoted 5 lines
Quoted 5 lines
Quoted 5 lines
* contexts: task, softirq, hardirq, nmi.
*
* Exactly fits one 64-byte cacheline on a 64-bit architecture. *
* PV doubles the storage and uses the second cacheline for PVstate.
Quoted 5 lines
Quoted 5 lines
Quoted 3 lines
*/
staticDEFINE_PER_CPU_ALIGNED(struct qnode, qnodes[MAX_NODES]);Yes, both debug and mce exceptions are some kind of NMIs. So theoretically, it is possible to have more than four. Are you aware
of
Quoted 1 line
Quoted 1 line
any debug and MCE exception handlers that need to take a spinlock
for
Quoted 2 lines
Quoted 1 line
synchronization?
Not for debug exception, for MCE exception handler I found below
two:
Quoted 8 lines
do_machine_check->mce_report_event->schedule_workdo_machine_check->force_sig->force_sig_info
schedule_work()andforce_sig_info()take spinlocks.Signature · 2 lines
Thanks ZhenzhongThe comment for
do_machine_scheck()has already state that:* This is executed in NMI context not subject to normal locking rules. This
* implies that most kernel services cannot be safely used. Don't even
* think about putting a printk in there!
Quoted 4 lines
So even if it doesn't exceed the
MAX_NODESlimit, it could hit deadlock
and other kind of locking hazards. So supporting MCE is not a reason strong enough to extendMAX_NODES.
Agree.
Quoted 4 lines
In hindsight, we should have added a "
BUG_ON(idx >= MAX_NODES);" check
to avoid silent corruption because of that issue.
Looks a good idea if it's hard to avoid using spinlock in MCE handler.
Thanks
Zhenzhong