Messages in this thread | | | Subject | Re: [PATCH] KVM: SVM: Issue WBINVD after deactivating an SEV guest | From | Tom Lendacky <> | Date | Sat, 21 Mar 2020 07:16:35 -0500 |
| |
On 3/21/20 4:00 AM, Greg KH wrote: > On Fri, Mar 20, 2020 at 03:37:23PM -0500, Tom Lendacky wrote: >> On 3/20/20 3:34 PM, David Rientjes wrote: >>> On Fri, 20 Mar 2020, Tom Lendacky wrote: >>> >>>> Currently, CLFLUSH is used to flush SEV guest memory before the guest is >>>> terminated (or a memory hotplug region is removed). However, CLFLUSH is >>>> not enough to ensure that SEV guest tagged data is flushed from the cache. >>>> >>>> With 33af3a7ef9e6 ("KVM: SVM: Reduce WBINVD/DF_FLUSH invocations"), the >>>> original WBINVD was removed. This then exposed crashes at random times >>>> because of a cache flush race with a page that had both a hypervisor and >>>> a guest tag in the cache. >>>> >>>> Restore the WBINVD when destroying an SEV guest and add a WBINVD to the >>>> svm_unregister_enc_region() function to ensure hotplug memory is flushed >>>> when removed. The DF_FLUSH can still be avoided at this point. >>>> >>>> Fixes: 33af3a7ef9e6 ("KVM: SVM: Reduce WBINVD/DF_FLUSH invocations") >>>> Signed-off-by: Tom Lendacky <thomas.lendacky@amd.com> >>> >>> Acked-by: David Rientjes <rientjes@google.com> >>> >>> Should this be marked for stable? >> >> The Fixes tag should take care of that. > > No it does not. > Please read: > https://nam11.safelinks.protection.outlook.com/?url=https%3A%2F%2Fwww.kernel.org%2Fdoc%2Fhtml%2Flatest%2Fprocess%2Fstable-kernel-rules.html&data=02%7C01%7Cthomas.lendacky%40amd.com%7C197f666080144732040108d7cd765107%7C3dd8961fe4884e608e11a82d994e183d%7C0%7C0%7C637203780365719535&sdata=NKgNt6Hd7y6BGBdpI52ckCxZvIsCRuEf9FJ7GW2PqPw%3D&reserved=0 > for how to do this properly. > > Yes, I have had to go around and clean up after maintainers who don't > seem to realize this, but for KVM patches I have been explicitly told to > NOT take any patch unless it has a cc: stable on it, due to issues that > have happened in the past. > > So for this subsystem, what you suggested guaranteed it would NOT get > picked up, please do not do that.
Thanks for clarifying that, Greg.
Then, yes, it should have the Cc: to stable that David mentioned. If it gets applied without that, I'll follow the process to send an email to stable to get it included in 5.5-stable.
Thanks, Tom
> > greg k-h >
| |