linux-kernel - [PATCH 4.13 082/110] KVM: nVMX: fix HOST_CR3/HOST

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: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Date:   Tue,  3 Oct 2017 14:29:44 +0200
From:   Greg Kroah-Hartman <gregkh@...uxfoundation.org>
To:     linux-kernel@...r.kernel.org
Cc:     Greg Kroah-Hartman <gregkh@...uxfoundation.org>,
        stable@...r.kernel.org, Ladi Prosek <lprosek@...hat.com>,
        Paolo Bonzini <pbonzini@...hat.com>
Subject: [PATCH 4.13 082/110] KVM: nVMX: fix HOST_CR3/HOST_CR4 cache

4.13-stable review patch.  If anyone has any objections, please let me know.

------------------

From: Ladi Prosek <lprosek@...hat.com>

commit 44889942b6eb356eab27ce25fe10701adfec7776 upstream.

For nested virt we maintain multiple VMCS that can run on a vCPU. So it is
incorrect to keep vmcs_host_cr3 and vmcs_host_cr4, whose purpose is caching
the value of the rarely changing HOST_CR3 and HOST_CR4 VMCS fields, in
vCPU-wide data structures.

Hyper-V nested on KVM runs into this consistently for me with PCID enabled.
CR3 is updated with a new value, unlikely(cr3 != vmx->host_state.vmcs_host_cr3)
fires, and the currently loaded VMCS is updated. Then we switch from L2 to
L1 and the next exit reverts CR3 to its old value.

Fixes: d6e41f1151fe ("x86/mm, KVM: Teach KVM's VMX code that CR3 isn't a constant")
Signed-off-by: Ladi Prosek <lprosek@...hat.com>
Signed-off-by: Paolo Bonzini <pbonzini@...hat.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@...uxfoundation.org>

---
 arch/x86/kvm/vmx.c |   16 ++++++++--------
 1 file changed, 8 insertions(+), 8 deletions(-)

--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -200,6 +200,8 @@ struct loaded_vmcs {
 	int cpu;
 	bool launched;
 	bool nmi_known_unmasked;
+	unsigned long vmcs_host_cr3;	/* May not match real cr3 */
+	unsigned long vmcs_host_cr4;	/* May not match real cr4 */
 	struct list_head loaded_vmcss_on_cpu_link;
 };
 
@@ -595,8 +597,6 @@ struct vcpu_vmx {
 		int           gs_ldt_reload_needed;
 		int           fs_reload_needed;
 		u64           msr_host_bndcfgs;
-		unsigned long vmcs_host_cr3;	/* May not match real cr3 */
-		unsigned long vmcs_host_cr4;	/* May not match real cr4 */
 	} host_state;
 	struct {
 		int vm86_active;
@@ -5138,12 +5138,12 @@ static void vmx_set_constant_host_state(
 	 */
 	cr3 = __read_cr3();
 	vmcs_writel(HOST_CR3, cr3);		/* 22.2.3  FIXME: shadow tables */
-	vmx->host_state.vmcs_host_cr3 = cr3;
+	vmx->loaded_vmcs->vmcs_host_cr3 = cr3;
 
 	/* Save the most likely value for this task's CR4 in the VMCS. */
 	cr4 = cr4_read_shadow();
 	vmcs_writel(HOST_CR4, cr4);			/* 22.2.3, 22.2.5 */
-	vmx->host_state.vmcs_host_cr4 = cr4;
+	vmx->loaded_vmcs->vmcs_host_cr4 = cr4;
 
 	vmcs_write16(HOST_CS_SELECTOR, __KERNEL_CS);  /* 22.2.4 */
 #ifdef CONFIG_X86_64
@@ -8992,15 +8992,15 @@ static void __noclone vmx_vcpu_run(struc
 		vmcs_writel(GUEST_RIP, vcpu->arch.regs[VCPU_REGS_RIP]);
 
 	cr3 = __get_current_cr3_fast();
-	if (unlikely(cr3 != vmx->host_state.vmcs_host_cr3)) {
+	if (unlikely(cr3 != vmx->loaded_vmcs->vmcs_host_cr3)) {
 		vmcs_writel(HOST_CR3, cr3);
-		vmx->host_state.vmcs_host_cr3 = cr3;
+		vmx->loaded_vmcs->vmcs_host_cr3 = cr3;
 	}
 
 	cr4 = cr4_read_shadow();
-	if (unlikely(cr4 != vmx->host_state.vmcs_host_cr4)) {
+	if (unlikely(cr4 != vmx->loaded_vmcs->vmcs_host_cr4)) {
 		vmcs_writel(HOST_CR4, cr4);
-		vmx->host_state.vmcs_host_cr4 = cr4;
+		vmx->loaded_vmcs->vmcs_host_cr4 = cr4;
 	}
 
 	/* When single-stepping over STI and MOV SS, we must clear the