Messages in this thread | | | Subject | Re: [PATCH] x86, MCE, AMD: save IA32_MCi_STATUS before machine_check_poll() resets it | From | Chen Yucong <> | Date | Tue, 30 Sep 2014 17:56:31 +0800 |
| |
On Tue, 2014-09-30 at 09:25 +0200, Borislav Petkov wrote: > > if (high & MASK_OVERFLOW_HI) { > > rdmsrl(address, m.misc); > > rdmsrl(MSR_IA32_MCx_STATUS(bank), > m.status); > > + if (m.status & MCI_STATUS_ADDRV) > > > + rdmsrl(MSR_IA32_MCx_ADDR(bank), > m.addr); > > m.bank = K8_MCE_THRESHOLD_BASE > > + bank * NR_BLOCKS > > + block; > > mce_log(&m); > > - return; > > + > > + wrmsrl(MSR_IA32_MCx_STATUS(bank), 0); > > No, machine_check_poll will clear it anyway and now you're adding a > purely useless MSR write here which costs. I just clear it to avoid that the mce_log() call logs the above threshold event again in machine_check_poll(). > > > + goto log_mcheck; > > Why goto? It will hit that machine_check_poll below even without > it... It is just used for scanning other banks for recording other valid error information.
thx! cyc
| |