[PATCH 0/2] KVM: nVMX: Don't let L2's LMSW modify CR0 bits owned by L1

[PATCH 0/2] KVM: nVMX: Don't let L2's LMSW modify CR0 bits owned by L1

[ma.mandourr]

From: Mahmoud Abumandour <ma.mandourr@gmail.com>

When L2's LMSW exits to L0 but not to L1, KVM emulates it with
kvm_lmsw(), which ignores vmcs12's CR0 guest/host mask, so L2 can change
CR0 bits that L1 owns.

Mahmoud Abumandour (2):
  KVM: nVMX: Don't let L2's LMSW modify CR0 bits owned by L1
  KVM: selftests: Verify that L2's LMSW leaves L1-owned CR0 bits alone

 arch/x86/kvm/vmx/vmx.c                        | 15 ++++++++
 .../kvm/x86/nested_exceptions_test.c          | 36 +++++++++++++++++++
 2 files changed, 51 insertions(+)


base-commit: dea4f6380f4ec96e8f3b0aaf2343764bd0d25ef4
-- 
2.25.1

[PATCH 1/2] KVM: nVMX: Don't let L2's LMSW modify CR0 bits owned by L1

[ma.mandourr]

From: Mahmoud Abumandour <ma.mandourr@gmail.com>

When L2's LMSW exits to L0 but not to L1, emulate it through
handle_set_cr0(), as is done for MOV to CR0.  kvm_lmsw() ignores
vmcs12's CR0 guest/host mask, so L2 could change CR0 bits that L1 owns,
e.g. clear TS, and read their effective values instead of the read shadow.

Fixes: eeadf9e7558c ("KVM: nVMX: Handling of CR0 and CR4 modifying instructions")
Signed-off-by: Mahmoud Abumandour <ma.mandourr@gmail.com>
---
 arch/x86/kvm/vmx/vmx.c | 15 +++++++++++++++
 1 file changed, 15 insertions(+)

diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index b341af4c60..3633496299 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -5748,6 +5748,21 @@ static int handle_cr(struct kvm_vcpu *vcpu)
 	case 3: /* lmsw */
 		val = (exit_qualification >> LMSW_SOURCE_DATA_SHIFT) & 0x0f;
 		trace_kvm_cr_write(0, (kvm_read_cr0_bits(vcpu, ~0xful) | val));
+		if (is_guest_mode(vcpu)) {
+			struct vmcs12 *vmcs12 = get_vmcs12(vcpu);
+			unsigned long mask = vmcs12->cr0_guest_host_mask;
+			unsigned long cr0;
+
+			/*
+			 * LMSW leaves the bits L1 owns unmodified, as does a MOV
+			 * to CR0 that writes their read shadow values.  Emulate
+			 * it as that MOV: L2's view of CR0 with LMSW's bits.
+			 */
+			cr0 = (kvm_read_cr0(vcpu) & ~mask) |
+			      (vmcs12->cr0_read_shadow & mask);
+			err = handle_set_cr0(vcpu, (cr0 & ~0x0eul) | val);
+			return kvm_complete_insn_gp(vcpu, err);
+		}
 		kvm_lmsw(vcpu, val);
 
 		return kvm_skip_emulated_instruction(vcpu);
-- 
2.25.1

[PATCH 2/2] KVM: selftests: Verify that L2's LMSW leaves L1-owned CR0 bits alone

[ma.mandourr]

From: Mahmoud Abumandour <ma.mandourr@gmail.com>

Verify that an LMSW in L2 that exits to L0 only leaves an L1-owned CR0.TS
set, and that L2 reads an L1-owned CR0.NE from the read shadow.

Assisted-by: LLM
Signed-off-by: Mahmoud Abumandour <ma.mandourr@gmail.com>
---
 .../kvm/x86/nested_exceptions_test.c          | 36 +++++++++++++++++++
 1 file changed, 36 insertions(+)

diff --git a/tools/testing/selftests/kvm/x86/nested_exceptions_test.c b/tools/testing/selftests/kvm/x86/nested_exceptions_test.c
index f47432526e..7113018ee6 100644
--- a/tools/testing/selftests/kvm/x86/nested_exceptions_test.c
+++ b/tools/testing/selftests/kvm/x86/nested_exceptions_test.c
@@ -109,6 +109,40 @@ static void l1_svm_code(struct svm_test_data *svm)
 	GUEST_DONE();
 }
 
+static u64 l2_cr0;
+
+static void l2_lmsw_test(void)
+{
+	/* Toggle CR0.MP, which KVM intercepts and L1 doesn't. */
+	asm volatile("lmsw %w0" : : "r" (get_cr0() ^ X86_CR0_MP));
+	l2_cr0 = get_cr0();
+	asm volatile("fnop");
+	GUEST_FAIL("L2's FNOP didn't take #NM");
+}
+
+/*
+ * L1 owns CR0.TS (set) and CR0.NE, both with a read shadow of 0.  L2's LMSW
+ * must leave both alone: FNOP takes #NM and L2 reads NE as 0.
+ */
+static void vmx_run_l2_lmsw(void)
+{
+	u64 cr0 = vmread(GUEST_CR0);
+
+	vmwrite(CR0_GUEST_HOST_MASK, X86_CR0_TS | X86_CR0_NE);
+	vmwrite(CR0_READ_SHADOW, cr0 & ~(X86_CR0_TS | X86_CR0_NE));
+	vmwrite(GUEST_CR0, cr0 | X86_CR0_TS);
+	vmwrite(EXCEPTION_BITMAP, BIT(NM_VECTOR));
+	vmwrite(GUEST_RIP, (u64)l2_lmsw_test);
+	vmresume();
+
+	GUEST_ASSERT_EQ(vmread(VM_EXIT_REASON), EXIT_REASON_EXCEPTION_NMI);
+	GUEST_ASSERT_EQ(vmread(VM_EXIT_INTR_INFO) & 0xff, NM_VECTOR);
+	GUEST_ASSERT(!(l2_cr0 & X86_CR0_NE));
+
+	vmwrite(CR0_GUEST_HOST_MASK, 0);
+	vmwrite(GUEST_CR0, cr0);
+}
+
 static void vmx_run_l2(void *l2_code, int vector, u32 error_code)
 {
 	vmwrite(GUEST_RIP, (u64)l2_code);
@@ -149,6 +183,8 @@ static void l1_vmx_code(struct vmx_pages *vmx)
 	vmwrite(EXCEPTION_BITMAP, INTERCEPT_SS_DF);
 	vmx_run_l2(l2_ss_injected_df_test, DF_VECTOR, DF_ERROR_CODE);
 
+	vmx_run_l2_lmsw();
+
 	vmwrite(EXCEPTION_BITMAP, INTERCEPT_SS);
 	vmx_run_l2(l2_ss_injected_tf_test, FAKE_TRIPLE_FAULT_VECTOR, 0);
 	GUEST_ASSERT_EQ(vmread(VM_EXIT_REASON), EXIT_REASON_TRIPLE_FAULT);
-- 
2.25.1