Messages in this thread | | | Date | Mon, 10 Sep 2012 18:57:17 +0200 | From | Sebastian Andrzej Siewior <> | Subject | Re: [PATCH 4/7] ptrace: Partly fix set_task_blockstep()->update_debugctlmsr() logic |
| |
* Oleg Nesterov | 2012-09-03 17:26:09 [+0200]:
>Afaics the usage of update_debugctlmsr() and TIF_BLOCKSTEP in >step.c was always very wrong. > >1. update_debugctlmsr() was simply unneeded. The child sleeps > TASK_TRACED, __switch_to_xtra(next_p => child) should notice > TIF_BLOCKSTEP and set/clear DEBUGCTLMSR_BTF after resume if > needed. > >2. It is wrong. The state of DEBUGCTLMSR_BTF bit in CPU register > should always match the state of current's TIF_BLOCKSTEP bit. > >3. Even get_debugctlmsr() + update_debugctlmsr() itself does not > look right. Irq can change other bits in MSR_IA32_DEBUGCTLMSR > register or the caller can be preempted in between.
ptrace and uprobe are calling this function from process context. As long as you have here get_cpu() instead of local_irq_disable() you should be safe here. The only user that is touching this bits in irq context is perf. perf uses raw_local_irqsave() (raw_* most likely due to -RT). I have no idea what you can against NMI unless not touching the register in NMI context.
Sebastian
| |