On 2014-07-02 11:13, Hu, Robert wrote: > >> -----Original Message----- >> From: Jan Kiszka [mailto:jan.kiszka@xxxxxxxxxxx] >> Sent: Wednesday, July 2, 2014 5:03 PM >> To: Hu, Robert; Wanpeng Li; Paolo Bonzini; Gleb Natapov >> Cc: kvm@xxxxxxxxxxxxxxx; linux-kernel@xxxxxxxxxxxxxxx >> Subject: Re: [PATCH] KVM: nVMX: Fix IRQs inject to L2 which belong to L1 since >> race >> >> On 2014-07-02 09:20, Hu, Robert wrote: >>>> -----Original Message----- >>>> From: Wanpeng Li [mailto:wanpeng.li@xxxxxxxxxxxxxxx] >>>> Sent: Wednesday, July 2, 2014 2:54 PM >>>> To: Paolo Bonzini; Jan Kiszka; Gleb Natapov >>>> Cc: Hu, Robert; kvm@xxxxxxxxxxxxxxx; linux-kernel@xxxxxxxxxxxxxxx; Wanpeng >> Li >>>> Subject: [PATCH] KVM: nVMX: Fix IRQs inject to L2 which belong to L1 since >> race >>>> >>>> This patch fix bug https://bugzilla.kernel.org/show_bug.cgi?id=72381 >>>> >>>> If we didn't inject a still-pending event to L1 since nested_run_pending, >>>> KVM_REQ_EVENT should be requested after the vmexit in order to inject the >>>> event to L1. However, current log blindly request a KVM_REQ_EVENT even if >>>> there is no still-pending event to L1 which blocked by nested_run_pending. >>>> There is a race which lead to an interrupt will be injected to L2 which >>>> belong to L1 if L0 send an interrupt to L1 during this window. >>>> >>>> VCPU0 another thread >>>> >>>> L1 intr not blocked on L2 first entry >>>> vmx_vcpu_run req event >>>> kvm check request req event >>>> check_nested_events don't have any intr >>>> not nested exit >>>> intr occur (8254, lapic timer >>>> etc) >>>> inject_pending_event now have intr >>>> inject interrupt >>>> >>>> This patch fix this race by introduced a l1_events_blocked field in nested_vmx >>>> which indicates there is still-pending event which blocked by >>>> nested_run_pending, >>>> and smart request a KVM_REQ_EVENT if there is a still-pending event which >>>> blocked >>>> by nested_run_pending. >>>> >>>> Signed-off-by: Wanpeng Li <wanpeng.li@xxxxxxxxxxxxxxx> >>> Tested-by: Robert Hu<robert.hu@xxxxxxxxx> >> >> Do you happen to have a kvm-unit-test for this race? Or how did you >> test? Just curious, and if there is a test, it would be good to >> integrate it. > I just apply the patch and test the reported scenario. Ah, sorry, missed the referenced bug report. Jan -- Siemens AG, Corporate Technology, CT RTC ITP SES-DE Corporate Competence Center Embedded Linux -- To unsubscribe from this list: send the line "unsubscribe kvm" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html
