From: Liran Alon <liran.alon@oracle.com>
To: "Singh, Brijesh" <brijesh.singh@amd.com>
Cc: "pbonzini@redhat.com" <pbonzini@redhat.com>,
"rkrcmar@redhat.com" <rkrcmar@redhat.com>,
"kvm@vger.kernel.org" <kvm@vger.kernel.org>,
Boris Ostrovsky <boris.ostrovsky@oracle.com>
Subject: Re: [PATCH 1/2] KVM: SVM: Fix workaround for AMD Errata 1096
Date: Tue, 16 Jul 2019 18:56:19 +0300 [thread overview]
Message-ID: <CF48BCA4-4BC8-4AC8-8B48-85FA29E16719@oracle.com> (raw)
In-Reply-To: <1ef0f594-2039-1aeb-4fe0-edbc21fa1f60@amd.com>
> On 16 Jul 2019, at 18:48, Singh, Brijesh <brijesh.singh@amd.com> wrote:
>
> On 7/15/19 3:30 PM, Liran Alon wrote:
>> According to AMD Errata 1096:
>> "On a nested data page fault when CR4.SMAP = 1 and the guest data read generates a SMAP violation, the
>> GuestInstrBytes field of the VMCB on a VMEXIT will incorrectly return 0h instead the correct guest instruction
>> bytes."
>>
>> As stated above, errata is encountered when guest read generates a SMAP violation. i.e. vCPU runs
>> with CPL<3 and CR4.SMAP=1. However, code have mistakenly checked if CPL==3 and CR4.SMAP==0.
>>
>
> The SMAP violation will occur from CPL3 so CPL==3 is a valid check.
>
> See [1] for complete discussion
>
> https://urldefense.proofpoint.com/v2/url?u=https-3A__patchwork.kernel.org_patch_10808075_-2322479271&d=DwIGaQ&c=RoP1YumCXCgaWHvlZYR8PZh8Bv7qIrMUB65eapI_JnE&r=Jk6Q8nNzkQ6LJ6g42qARkg6ryIDGQr-yKXPNGZbpTx0&m=RAt8t8nBaCxUPy5OTDkO0n8BMQ5l9oSfLMiL0TLTu6c&s=Nkwe8rTJhygBCIPz27LXrylptjnWyMwB-nJaiowWpWc&e=
I still don’t understand. SMAP is a mechanism which is meant to protect a CPU running in CPL<3 from mistakenly referencing data controllable by CPL==3.
Therefore, SMAP violation should be raised when CPL<3 and data referenced is mapped in page-tables with PTE with U/S bit set to 1. (i.e. User accessible).
Thus, we should check if CPL<3 and CR4.SMAP==1.
-Liran
>
> However, code mistakenly checked CR4.SMAP==0, it should be CR4.SMAP==1
>
>> To avoid future confusion and improve code readbility, comment errata details in code and not
>> just in commit message.
>>
>> Fixes: 05d5a4863525 ("KVM: SVM: Workaround errata#1096 (insn_len maybe zero on SMAP violation)")
>> Reviewed-by: Boris Ostrovsky <boris.ostrovsky@oracle.com>
>> Signed-off-by: Liran Alon <liran.alon@oracle.com>
>> ---
>> arch/x86/kvm/svm.c | 17 +++++++++++++----
>> 1 file changed, 13 insertions(+), 4 deletions(-)
>>
>> diff --git a/arch/x86/kvm/svm.c b/arch/x86/kvm/svm.c
>> index 735b8c01895e..79023a41f7a7 100644
>> --- a/arch/x86/kvm/svm.c
>> +++ b/arch/x86/kvm/svm.c
>> @@ -7123,10 +7123,19 @@ static bool svm_need_emulation_on_page_fault(struct kvm_vcpu *vcpu)
>> bool is_user, smap;
>>
>> is_user = svm_get_cpl(vcpu) == 3;
>> - smap = !kvm_read_cr4_bits(vcpu, X86_CR4_SMAP);
>> + smap = kvm_read_cr4_bits(vcpu, X86_CR4_SMAP);
>>
>
> Ah good catch. thank
>
>
>> /*
>> - * Detect and workaround Errata 1096 Fam_17h_00_0Fh
>> + * Detect and workaround Errata 1096 Fam_17h_00_0Fh.
>> + *
>> + * Errata:
>> + * On a nested page fault when CR4.SMAP=1 and the guest data read generates
>> + * a SMAP violation, GuestIntrBytes field of the VMCB on a VMEXIT will
>> + * incorrectly return 0 instead the correct guest instruction bytes.
>> + *
>> + * Workaround:
>> + * To determine what instruction the guest was executing, the hypervisor
>> + * will have to decode the instruction at the instruction pointer.
>> *
>> * In non SEV guest, hypervisor will be able to read the guest
>> * memory to decode the instruction pointer when insn_len is zero
>> @@ -7137,11 +7146,11 @@ static bool svm_need_emulation_on_page_fault(struct kvm_vcpu *vcpu)
>> * instruction pointer so we will not able to workaround it. Lets
>> * print the error and request to kill the guest.
>> */
>> - if (is_user && smap) {
>> + if (!is_user && smap) {
>> if (!sev_guest(vcpu->kvm))
>> return true;
>>
>> - pr_err_ratelimited("KVM: Guest triggered AMD Erratum 1096\n");
>> + pr_err_ratelimited("KVM: SEV Guest triggered AMD Erratum 1096\n");
>> kvm_make_request(KVM_REQ_TRIPLE_FAULT, vcpu);
>> }
>>
>>
next prev parent reply other threads:[~2019-07-16 15:56 UTC|newest]
Thread overview: 34+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-07-15 20:30 KVM: SVM: Fix workaround for AMD Errata 1096 Liran Alon
2019-07-15 20:30 ` [PATCH 1/2] " Liran Alon
2019-07-16 15:48 ` Singh, Brijesh
2019-07-16 15:56 ` Liran Alon [this message]
2019-07-16 16:07 ` Liran Alon
2019-07-16 16:10 ` Singh, Brijesh
2019-07-16 16:20 ` Liran Alon
2019-07-16 16:41 ` Sean Christopherson
2019-07-16 16:56 ` Liran Alon
2019-07-16 17:27 ` Sean Christopherson
2019-07-16 17:27 ` Paolo Bonzini
2019-07-16 17:35 ` Liran Alon
2019-07-16 19:28 ` Singh, Brijesh
2019-07-16 19:34 ` Liran Alon
2019-07-16 19:39 ` Paolo Bonzini
2019-07-16 19:45 ` Sean Christopherson
2019-07-16 19:50 ` Liran Alon
2019-07-16 19:47 ` Liran Alon
2019-07-16 19:41 ` Sean Christopherson
2019-07-16 19:52 ` Liran Alon
2019-07-16 20:02 ` Singh, Brijesh
2019-07-16 20:07 ` Sean Christopherson
2019-07-16 20:13 ` Paolo Bonzini
2019-07-16 20:09 ` Liran Alon
2019-07-16 20:27 ` Singh, Brijesh
2019-07-16 20:54 ` Sean Christopherson
2019-07-16 21:53 ` Liran Alon
2019-07-16 18:05 ` Singh, Brijesh
2019-07-16 18:06 ` Singh, Brijesh
2019-07-15 20:30 ` [PATCH 2/2] KVM: x86: Rename need_emulation_on_page_fault() to handle_no_insn_on_page_fault() Liran Alon
2019-07-16 15:48 ` Sean Christopherson
2019-07-16 16:01 ` Liran Alon
2019-07-16 16:10 ` Sean Christopherson
2019-07-16 19:33 ` Singh, Brijesh
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=CF48BCA4-4BC8-4AC8-8B48-85FA29E16719@oracle.com \
--to=liran.alon@oracle.com \
--cc=boris.ostrovsky@oracle.com \
--cc=brijesh.singh@amd.com \
--cc=kvm@vger.kernel.org \
--cc=pbonzini@redhat.com \
--cc=rkrcmar@redhat.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).