lists.openwall.net   lists  /  announce  owl-users  owl-dev  john-users  john-dev  passwdqc-users  yescrypt  popa3d-users  /  oss-security  kernel-hardening  musl  sabotage  tlsify  passwords  /  crypt-dev  xvendor  /  Bugtraq  Full-Disclosure  linux-kernel  linux-netdev  linux-ext4  linux-hardening  linux-cve-announce  PHC 
Open Source and information security mailing list archives
 
Hash Suite for Android: free password hash cracker in your pocket
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20251113231420.1695919-3-seanjc@google.com>
Date: Thu, 13 Nov 2025 15:14:17 -0800
From: Sean Christopherson <seanjc@...gle.com>
To: Sean Christopherson <seanjc@...gle.com>, Paolo Bonzini <pbonzini@...hat.com>
Cc: kvm@...r.kernel.org, linux-kernel@...r.kernel.org
Subject: [PATCH 2/5] KVM: SVM: Skip OSVW MSR reads if KVM is treating all
 errata as present

Don't bother reading the OSVW MSRs if osvw_len is already zero, i.e. if
KVM is already treating all errata as present, in which case the positive
path of the if-statement is one giant nop.

Opportunistically update the comment to more thoroughly explain how the
MSRs work and why the code does what it does.

Signed-off-by: Sean Christopherson <seanjc@...gle.com>
---
 arch/x86/kvm/svm/svm.c | 14 ++++++++++++--
 1 file changed, 12 insertions(+), 2 deletions(-)

diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
index 5612e46e481c..0101da1a3c26 100644
--- a/arch/x86/kvm/svm/svm.c
+++ b/arch/x86/kvm/svm/svm.c
@@ -539,15 +539,25 @@ static int svm_enable_virtualization_cpu(void)
 
 
 	/*
-	 * Get OSVW bits.
+	 * Get OS-Visible Workarounds (OSVW) bits.
 	 *
 	 * Note that it is possible to have a system with mixed processor
 	 * revisions and therefore different OSVW bits. If bits are not the same
 	 * on different processors then choose the worst case (i.e. if erratum
 	 * is present on one processor and not on another then assume that the
 	 * erratum is present everywhere).
+	 *
+	 * Note #2!  The OSVW MSRs are used to communciate that an erratum is
+	 * NOT present!  Software must assume erratum as present if its bit is
+	 * set in OSVW_STATUS *or* the bit number exceeds OSVW_ID_LENGTH.  If
+	 * either RDMSR fails, simply zero out the length to treat all errata
+	 * as being present.  Similarly, use the *minimum* length across all
+	 * CPUs, not the maximum length.
+	 *
+	 * If the length is zero, then is KVM already treating all errata as
+	 * being present and there's nothing left to do.
 	 */
-	if (cpu_has(&boot_cpu_data, X86_FEATURE_OSVW)) {
+	if (osvw_len && cpu_has(&boot_cpu_data, X86_FEATURE_OSVW)) {
 		u64 len, status = 0;
 		int err;
 
-- 
2.52.0.rc1.455.g30608eb744-goog


Powered by blists - more mailing lists

Powered by Openwall GNU/*/Linux Powered by OpenVZ