From: Josh Poimboeuf <jpoimboe@kernel.org>
Date: Thu, 27 Oct 2022 20:55:31 +0000 (-0700)
Subject: KVM: VMX: Fix IBRS handling after vmexit
X-Git-Tag: v4.14.297~9
X-Git-Url: http://git.ipfire.org/cgi-bin/gitweb.cgi?a=commitdiff_plain;h=647457858c548364f482676d8b4abddd1c9255b2;p=thirdparty%2Fkernel%2Fstable.git

KVM: VMX: Fix IBRS handling after vmexit

commit bea7e31a5caccb6fe8ed989c065072354f0ecb52 upstream.

For legacy IBRS to work, the IBRS bit needs to be always re-written
after vmexit, even if it's already on.

Signed-off-by: Josh Poimboeuf <jpoimboe@kernel.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Borislav Petkov <bp@suse.de>
Signed-off-by: Thadeu Lima de Souza Cascardo <cascardo@canonical.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---

diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 539720a8e0941..e35cb9560eeb7 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -9781,8 +9781,13 @@ u64 __always_inline vmx_spec_ctrl_restore_host(struct vcpu_vmx *vmx)
 
 	/*
 	 * If the guest/host SPEC_CTRL values differ, restore the host value.
+	 *
+	 * For legacy IBRS, the IBRS bit always needs to be written after
+	 * transitioning from a less privileged predictor mode, regardless of
+	 * whether the guest/host values differ.
 	 */
-	if (guestval != hostval)
+	if (cpu_feature_enabled(X86_FEATURE_KERNEL_IBRS) ||
+	    guestval != hostval)
 		native_wrmsrl(MSR_IA32_SPEC_CTRL, hostval);
 
 	barrier_nospec();