Re: [RFC PATCH 4/4] KVM: vmx: add support for emulating UMIP
From: Yang Zhang
Date: Wed Jul 13 2016 - 05:21:42 EST
On 2016/7/13 3:20, Paolo Bonzini wrote:
UMIP (User-Mode Instruction Prevention) is a feature of future
Intel processors (Cannonlake?) that blocks SLDT, SGDT, STR, SIDT
and SMSW from user-mode processes.
On Intel systems it's *almost* possible to emulate it; it slows
down the instructions when they're executed in ring 0, but they
are really never executed in practice. The catch is that SMSW
doesn't cause a vmexit, and hence SMSW will not fault.
When UMIP is enabled but not supported by the host, descriptor table
exits are enabled, and the emulator takes care of injecting a #GP when
any of SLDT, SGDT, STR, SIDT are encountered.
Signed-off-by: Paolo Bonzini <pbonzini@xxxxxxxxxx>
---
arch/x86/include/asm/vmx.h | 1 +
arch/x86/include/uapi/asm/vmx.h | 4 ++++
arch/x86/kvm/vmx.c | 36 ++++++++++++++++++++++++++++++++++--
3 files changed, 39 insertions(+), 2 deletions(-)
diff --git a/arch/x86/include/asm/vmx.h b/arch/x86/include/asm/vmx.h
index 14c63c7e8337..8b95f0ec0190 100644
--- a/arch/x86/include/asm/vmx.h
+++ b/arch/x86/include/asm/vmx.h
@@ -60,6 +60,7 @@
*/
#define SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES 0x00000001
#define SECONDARY_EXEC_ENABLE_EPT 0x00000002
+#define SECONDARY_EXEC_DESC 0x00000004
#define SECONDARY_EXEC_RDTSCP 0x00000008
#define SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE 0x00000010
#define SECONDARY_EXEC_ENABLE_VPID 0x00000020
diff --git a/arch/x86/include/uapi/asm/vmx.h b/arch/x86/include/uapi/asm/vmx.h
index 5b15d94a33f8..2f9a69b9559c 100644
--- a/arch/x86/include/uapi/asm/vmx.h
+++ b/arch/x86/include/uapi/asm/vmx.h
@@ -65,6 +65,8 @@
#define EXIT_REASON_TPR_BELOW_THRESHOLD 43
#define EXIT_REASON_APIC_ACCESS 44
#define EXIT_REASON_EOI_INDUCED 45
+#define EXIT_REASON_GDTR_IDTR 46
+#define EXIT_REASON_LDTR_TR 47
#define EXIT_REASON_EPT_VIOLATION 48
#define EXIT_REASON_EPT_MISCONFIG 49
#define EXIT_REASON_INVEPT 50
@@ -114,6 +116,8 @@
{ EXIT_REASON_MCE_DURING_VMENTRY, "MCE_DURING_VMENTRY" }, \
{ EXIT_REASON_TPR_BELOW_THRESHOLD, "TPR_BELOW_THRESHOLD" }, \
{ EXIT_REASON_APIC_ACCESS, "APIC_ACCESS" }, \
+ { EXIT_REASON_GDTR_IDTR, "GDTR_IDTR" }, \
+ { EXIT_REASON_LDTR_TR, "LDTR_TR" }, \
{ EXIT_REASON_EPT_VIOLATION, "EPT_VIOLATION" }, \
{ EXIT_REASON_EPT_MISCONFIG, "EPT_MISCONFIG" }, \
{ EXIT_REASON_INVEPT, "INVEPT" }, \
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index b133fc3d6a7d..0706e363c5e3 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -3342,6 +3342,7 @@ static __init int setup_vmcs_config(struct vmcs_config *vmcs_conf)
SECONDARY_EXEC_ENABLE_EPT |
SECONDARY_EXEC_UNRESTRICTED_GUEST |
SECONDARY_EXEC_PAUSE_LOOP_EXITING |
+ SECONDARY_EXEC_DESC |
SECONDARY_EXEC_RDTSCP |
SECONDARY_EXEC_ENABLE_INVPCID |
SECONDARY_EXEC_APIC_REGISTER_VIRT |
@@ -3967,6 +3968,14 @@ static int vmx_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
(to_vmx(vcpu)->rmode.vm86_active ?
KVM_RMODE_VM_CR4_ALWAYS_ON : KVM_PMODE_VM_CR4_ALWAYS_ON);
+ if ((cr4 & X86_CR4_UMIP) && !boot_cpu_has(X86_FEATURE_UMIP)) {
+ vmcs_set_bits(SECONDARY_VM_EXEC_CONTROL,
+ SECONDARY_EXEC_DESC);
+ hw_cr4 &= ~X86_CR4_UMIP;
+ } else
+ vmcs_clear_bits(SECONDARY_VM_EXEC_CONTROL,
+ SECONDARY_EXEC_DESC);
+
Since the faults based on privilege level have priority over VM exits.
So we don't need to enable/disable SECONDARY_EXEC_DESC dynamically.
Instead, we can set it unconditionally.
if (cr4 & X86_CR4_VMXE) {
/*
* To use VMXON (and later other VMX instructions), a guest
@@ -4913,6 +4922,11 @@ static u32 vmx_exec_control(struct vcpu_vmx *vmx)
static u32 vmx_secondary_exec_control(struct vcpu_vmx *vmx)
{
u32 exec_control = vmcs_config.cpu_based_2nd_exec_ctrl;
+
+ /* SECONDARY_EXEC_DESC is enabled/disabled on writes to CR4.UMIP,
+ * in vmx_set_cr4. */
+ exec_control &= ~SECONDARY_EXEC_DESC;
+
if (!cpu_need_virtualize_apic_accesses(&vmx->vcpu))
exec_control &= ~SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES;
if (vmx->vpid == 0)
@@ -5649,6 +5663,12 @@ static void handle_clts(struct kvm_vcpu *vcpu)
vmx_set_cr0(vcpu, kvm_read_cr0_bits(vcpu, ~X86_CR0_TS));
}
+static int handle_desc(struct kvm_vcpu *vcpu)
+{
+ WARN_ON(!(vcpu->arch.cr4 & X86_CR4_UMIP));
I think WARN_ON is too heavy since a malicious guest may trigger it always.
+ return emulate_instruction(vcpu, 0) == EMULATE_DONE;
+}
+
static int handle_cr(struct kvm_vcpu *vcpu)
{
unsigned long exit_qualification, val;
@@ -7705,6 +7731,8 @@ static int (*const kvm_vmx_exit_handlers[])(struct kvm_vcpu *vcpu) = {
[EXIT_REASON_XSETBV] = handle_xsetbv,
[EXIT_REASON_TASK_SWITCH] = handle_task_switch,
[EXIT_REASON_MCE_DURING_VMENTRY] = handle_machine_check,
+ [EXIT_REASON_GDTR_IDTR] = handle_desc,
+ [EXIT_REASON_LDTR_TR] = handle_desc,
[EXIT_REASON_EPT_VIOLATION] = handle_ept_violation,
[EXIT_REASON_EPT_MISCONFIG] = handle_ept_misconfig,
[EXIT_REASON_PAUSE_INSTRUCTION] = handle_pause,
@@ -7972,6 +8000,8 @@ static bool nested_vmx_exit_handled(struct kvm_vcpu *vcpu)
return nested_cpu_has(vmcs12, CPU_BASED_MOV_DR_EXITING);
case EXIT_REASON_IO_INSTRUCTION:
return nested_vmx_exit_handled_io(vcpu, vmcs12);
+ case EXIT_REASON_GDTR_IDTR: case EXIT_REASON_LDTR_TR:
+ return nested_cpu_has2(vmcs12, SECONDARY_EXEC_DESC);
case EXIT_REASON_MSR_READ:
case EXIT_REASON_MSR_WRITE:
return nested_vmx_exit_handled_msr(vcpu, vmcs12, exit_reason);
@@ -8597,7 +8627,8 @@ static bool vmx_xsaves_supported(void)
static bool vmx_umip_emulated(void)
{
- return false;
+ return vmcs_config.cpu_based_2nd_exec_ctrl &
+ SECONDARY_EXEC_DESC;
}
static void vmx_recover_nmi_blocking(struct vcpu_vmx *vmx)
@@ -9173,7 +9204,8 @@ static void vmcs_set_secondary_exec_control(u32 new_ctl)
u32 mask =
SECONDARY_EXEC_SHADOW_VMCS |
SECONDARY_EXEC_VIRTUALIZE_X2APIC_MODE |
- SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES;
+ SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES |
+ SECONDARY_EXEC_DESC;
u32 cur_ctl = vmcs_read32(SECONDARY_VM_EXEC_CONTROL);
--
Yang
Alibaba Cloud Computing