From: Sean Christopherson <seanjc@google.com>
To: Sean Christopherson <seanjc@google.com>,
Paolo Bonzini <pbonzini@redhat.com>,
Vitaly Kuznetsov <vkuznets@redhat.com>,
"K. Y. Srinivasan" <kys@microsoft.com>,
Haiyang Zhang <haiyangz@microsoft.com>,
Wei Liu <wei.liu@kernel.org>, Dexuan Cui <decui@microsoft.com>
Cc: kvm@vger.kernel.org, linux-hyperv@vger.kernel.org,
linux-kernel@vger.kernel.org, Jim Mattson <jmattson@google.com>,
Yosry Ahmed <yosry.ahmed@linux.dev>
Subject: [PATCH 9/9] KVM: SVM: Harden exit_code against being used in Spectre-like attacks
Date: Thu, 13 Nov 2025 14:56:21 -0800 [thread overview]
Message-ID: <20251113225621.1688428-10-seanjc@google.com> (raw)
In-Reply-To: <20251113225621.1688428-1-seanjc@google.com>
Explicitly clamp the exit code used to index KVM's exit handlers to guard
against Spectre-like attacks, mainly to provide consistency between VMX
and SVM (VMX was given the same treatment by commit c926f2f7230b ("KVM:
x86: Protect exit_reason from being used in Spectre-v1/L1TF attacks").
For normal VMs, it's _extremely_ unlikely the exit code could be used to
exploit a speculation vulnerability, as the exit code is set by hardware
and unexpected/unknown exit codes should be quite well bounded (as is/was
the case with VMX). But with SEV-ES+, the exit code is guest-controlled
as it comes from the GHCB, not from hardware, i.e. an attack from the
guest is at least somewhat plausible.
Irrespective of SEV-ES+, hardening KVM is easy and inexpensive, and such
an attack is theoretically possible.
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
arch/x86/kvm/svm/svm.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index 85bc99f93275..308c70b6924e 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -3467,6 +3467,7 @@ int svm_invoke_exit_handler(struct kvm_vcpu *vcpu, u64 __exit_code)
if (exit_code >= ARRAY_SIZE(svm_exit_handlers))
goto unexpected_vmexit;
+ exit_code = array_index_nospec(exit_code, ARRAY_SIZE(svm_exit_handlers));
if (!svm_exit_handlers[exit_code])
goto unexpected_vmexit;
--
2.52.0.rc1.455.g30608eb744-goog
next prev parent reply other threads:[~2025-11-13 22:56 UTC|newest]
Thread overview: 31+ messages / expand[flat|nested] mbox.gz Atom feed top
2025-11-13 22:56 [PATCH 0/9] KVM: SVM: Fix (hilarious) exit_code bugs Sean Christopherson
2025-11-13 22:56 ` [PATCH 1/9] KVM: nSVM: Clear exit_code_hi in VMCB when synthesizing nested VM-Exits Sean Christopherson
2025-11-13 23:03 ` Yosry Ahmed
2025-11-13 22:56 ` [PATCH 2/9] KVM: nSVM: Set exit_code_hi to -1 when synthesizing SVM_EXIT_ERR (failed VMRUN) Sean Christopherson
2025-11-13 23:17 ` Yosry Ahmed
2025-11-13 23:28 ` Yosry Ahmed
2025-11-13 22:56 ` [PATCH 3/9] KVM: SVM: Add a helper to detect VMRUN failures Sean Christopherson
2025-11-13 23:30 ` Yosry Ahmed
2025-11-13 23:35 ` Sean Christopherson
2025-11-13 22:56 ` [PATCH 4/9] KVM: SVM: Open code handling of unexpected exits in svm_invoke_exit_handler() Sean Christopherson
2025-11-13 23:33 ` Yosry Ahmed
2025-11-13 22:56 ` [PATCH 5/9] KVM: SVM: Check for an unexpected VM-Exit after RETPOLINE "fast" handling Sean Christopherson
2025-11-14 0:04 ` Yosry Ahmed
2025-11-13 22:56 ` [PATCH 6/9] KVM: SVM: Filter out 64-bit exit codes when invoking exit handlers on bare metal Sean Christopherson
2025-11-14 0:06 ` Yosry Ahmed
2025-11-14 23:32 ` Paolo Bonzini
2025-11-19 22:05 ` Sean Christopherson
2025-11-13 22:56 ` [PATCH 7/9] KVM: SVM: Treat exit_code as an unsigned 64-bit value through all of KVM Sean Christopherson
2025-11-14 0:08 ` Yosry Ahmed
2025-11-14 5:26 ` Michael Kelley
2025-11-14 15:22 ` Sean Christopherson
2025-11-14 18:29 ` Wei Liu
2025-11-14 18:35 ` Sean Christopherson
2025-11-14 18:40 ` Wei Liu
2025-11-14 15:27 ` Sean Christopherson
2025-11-14 15:47 ` Sean Christopherson
2025-11-14 23:33 ` Paolo Bonzini
2025-11-13 22:56 ` [PATCH 8/9] KVM: SVM: Limit incorrect check on SVM_EXIT_ERR to running as a VM Sean Christopherson
2025-11-14 0:11 ` Yosry Ahmed
2025-11-13 22:56 ` Sean Christopherson [this message]
2025-12-05 16:59 ` [PATCH 0/9] KVM: SVM: Fix (hilarious) exit_code bugs Sean Christopherson
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=20251113225621.1688428-10-seanjc@google.com \
--to=seanjc@google.com \
--cc=decui@microsoft.com \
--cc=haiyangz@microsoft.com \
--cc=jmattson@google.com \
--cc=kvm@vger.kernel.org \
--cc=kys@microsoft.com \
--cc=linux-hyperv@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=pbonzini@redhat.com \
--cc=vkuznets@redhat.com \
--cc=wei.liu@kernel.org \
--cc=yosry.ahmed@linux.dev \
/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
all inboxes | Powered by JetHome®