diff mbox series

[v2,17/25] KVM: nVMX: Add support for the secondary VM exit controls

Message ID 20240207172646.3981-18-xin3.li@intel.com
State New
Headers show
Series Enable FRED with KVM VMX | expand

Commit Message

Li, Xin3 Feb. 7, 2024, 5:26 p.m. UTC 
Enable the secondary VM exit controls to prepare for nested FRED.

Signed-off-by: Xin Li <xin3.li@intel.com>
Tested-by: Shan Kang <shan.kang@intel.com>
---
 Documentation/virt/kvm/x86/nested-vmx.rst |  1 +
 arch/x86/kvm/vmx/capabilities.h           |  1 +
 arch/x86/kvm/vmx/nested.c                 | 15 ++++++++++++++-
 arch/x86/kvm/vmx/vmcs12.c                 |  1 +
 arch/x86/kvm/vmx/vmcs12.h                 |  2 ++
 arch/x86/kvm/x86.h                        |  2 +-
 6 files changed, 20 insertions(+), 2 deletions(-)

Comments

Sean Christopherson June 13, 2024, 6:11 p.m. UTC | #1 
On Wed, Feb 07, 2024, Xin Li wrote:
> @@ -6856,13 +6865,17 @@ static void nested_vmx_setup_exit_ctls(struct vmcs_config *vmcs_conf,
>  		VM_EXIT_HOST_ADDR_SPACE_SIZE |
>  #endif
>  		VM_EXIT_LOAD_IA32_PAT | VM_EXIT_SAVE_IA32_PAT |
> -		VM_EXIT_CLEAR_BNDCFGS;
> +		VM_EXIT_CLEAR_BNDCFGS | VM_EXIT_ACTIVATE_SECONDARY_CONTROLS;
>  	msrs->exit_ctls_high |=
>  		VM_EXIT_ALWAYSON_WITHOUT_TRUE_MSR |
>  		VM_EXIT_LOAD_IA32_EFER | VM_EXIT_SAVE_IA32_EFER |
>  		VM_EXIT_SAVE_VMX_PREEMPTION_TIMER | VM_EXIT_ACK_INTR_ON_EXIT |
>  		VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL;
>  
> +	/* secondary exit controls */

Drop the comment, it's pretty obvious what field is being setup.

> +	if (msrs->exit_ctls_high & VM_EXIT_ACTIVATE_SECONDARY_CONTROLS)
> +		rdmsrl(MSR_IA32_VMX_EXIT_CTLS2, msrs->secondary_exit_ctls);

This is wrong, the resulting msrs->secondary_exit_ctls needs to be sanitized
based on what KVM supports for nVMX.

On a very related topic, this should not do a raw RDMSR.  One of the reasons why
KVM uses vmcs_config as the base is to avoid advertising features to L1 that KVM
itself doesn't support, e.g. because the expected entry+exit pairs aren't
supported.

And by pulling state from vmcs_conf->secondary_exit_ctls there's no need to check
the activation bit.

I.e. literaly just this:

	msrs->secondary_exit_ctls = vmcs_conf->secondary_exit_ctls;
	msrs->secondary_exit_ctls &= 0;

and then when nVMX FRED support is ready, it becomes:

	msrs->secondary_exit_ctls = vmcs_conf->secondary_exit_ctls;
	msrs->secondary_exit_ctls &= SECONDARY_VM_EXIT_SAVE_IA32_FRED |
				     SECONDARY_VM_EXIT_LOAD_IA32_FRED;
diff mbox series

Patch

diff --git a/Documentation/virt/kvm/x86/nested-vmx.rst b/Documentation/virt/kvm/x86/nested-vmx.rst
index ac2095d41f02..e64ef231f310 100644
--- a/Documentation/virt/kvm/x86/nested-vmx.rst
+++ b/Documentation/virt/kvm/x86/nested-vmx.rst
@@ -217,6 +217,7 @@  struct shadow_vmcs is ever changed.
 		u16 host_fs_selector;
 		u16 host_gs_selector;
 		u16 host_tr_selector;
+		u64 secondary_vm_exit_controls;
 	};
 
 
diff --git a/arch/x86/kvm/vmx/capabilities.h b/arch/x86/kvm/vmx/capabilities.h
index 73bf6618c425..b41c2cde811d 100644
--- a/arch/x86/kvm/vmx/capabilities.h
+++ b/arch/x86/kvm/vmx/capabilities.h
@@ -38,6 +38,7 @@  struct nested_vmx_msrs {
 	u32 pinbased_ctls_high;
 	u32 exit_ctls_low;
 	u32 exit_ctls_high;
+	u64 secondary_exit_ctls;
 	u32 entry_ctls_low;
 	u32 entry_ctls_high;
 	u32 misc_low;
diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c
index 8a5fda04e2de..1132e360ff13 100644
--- a/arch/x86/kvm/vmx/nested.c
+++ b/arch/x86/kvm/vmx/nested.c
@@ -1431,6 +1431,7 @@  int vmx_set_vmx_msr(struct kvm_vcpu *vcpu, u32 msr_index, u64 data)
 	case MSR_IA32_VMX_PINBASED_CTLS:
 	case MSR_IA32_VMX_PROCBASED_CTLS:
 	case MSR_IA32_VMX_EXIT_CTLS:
+	case MSR_IA32_VMX_EXIT_CTLS2:
 	case MSR_IA32_VMX_ENTRY_CTLS:
 		/*
 		 * The "non-true" VMX capability MSRs are generated from the
@@ -1509,6 +1510,9 @@  int vmx_get_vmx_msr(struct nested_vmx_msrs *msrs, u32 msr_index, u64 *pdata)
 		if (msr_index == MSR_IA32_VMX_EXIT_CTLS)
 			*pdata |= VM_EXIT_ALWAYSON_WITHOUT_TRUE_MSR;
 		break;
+	case MSR_IA32_VMX_EXIT_CTLS2:
+		*pdata = msrs->secondary_exit_ctls;
+		break;
 	case MSR_IA32_VMX_TRUE_ENTRY_CTLS:
 	case MSR_IA32_VMX_ENTRY_CTLS:
 		*pdata = vmx_control_msr(
@@ -2443,6 +2447,11 @@  static void prepare_vmcs02_early(struct vcpu_vmx *vmx, struct loaded_vmcs *vmcs0
 		exec_control &= ~VM_EXIT_LOAD_IA32_EFER;
 	vm_exit_controls_set(vmx, exec_control);
 
+	if (exec_control & VM_EXIT_ACTIVATE_SECONDARY_CONTROLS) {
+		exec_control = __secondary_vm_exit_controls_get(vmcs01);
+		secondary_vm_exit_controls_set(vmx, exec_control);
+	}
+
 	/*
 	 * Interrupt/Exception Fields
 	 */
@@ -6856,13 +6865,17 @@  static void nested_vmx_setup_exit_ctls(struct vmcs_config *vmcs_conf,
 		VM_EXIT_HOST_ADDR_SPACE_SIZE |
 #endif
 		VM_EXIT_LOAD_IA32_PAT | VM_EXIT_SAVE_IA32_PAT |
-		VM_EXIT_CLEAR_BNDCFGS;
+		VM_EXIT_CLEAR_BNDCFGS | VM_EXIT_ACTIVATE_SECONDARY_CONTROLS;
 	msrs->exit_ctls_high |=
 		VM_EXIT_ALWAYSON_WITHOUT_TRUE_MSR |
 		VM_EXIT_LOAD_IA32_EFER | VM_EXIT_SAVE_IA32_EFER |
 		VM_EXIT_SAVE_VMX_PREEMPTION_TIMER | VM_EXIT_ACK_INTR_ON_EXIT |
 		VM_EXIT_LOAD_IA32_PERF_GLOBAL_CTRL;
 
+	/* secondary exit controls */
+	if (msrs->exit_ctls_high & VM_EXIT_ACTIVATE_SECONDARY_CONTROLS)
+		rdmsrl(MSR_IA32_VMX_EXIT_CTLS2, msrs->secondary_exit_ctls);
+
 	/* We support free control of debug control saving. */
 	msrs->exit_ctls_low &= ~VM_EXIT_SAVE_DEBUG_CONTROLS;
 }
diff --git a/arch/x86/kvm/vmx/vmcs12.c b/arch/x86/kvm/vmx/vmcs12.c
index 106a72c923ca..98457d7b2b23 100644
--- a/arch/x86/kvm/vmx/vmcs12.c
+++ b/arch/x86/kvm/vmx/vmcs12.c
@@ -73,6 +73,7 @@  const unsigned short vmcs12_field_offsets[] = {
 	FIELD(PAGE_FAULT_ERROR_CODE_MATCH, page_fault_error_code_match),
 	FIELD(CR3_TARGET_COUNT, cr3_target_count),
 	FIELD(VM_EXIT_CONTROLS, vm_exit_controls),
+	FIELD(SECONDARY_VM_EXIT_CONTROLS, secondary_vm_exit_controls),
 	FIELD(VM_EXIT_MSR_STORE_COUNT, vm_exit_msr_store_count),
 	FIELD(VM_EXIT_MSR_LOAD_COUNT, vm_exit_msr_load_count),
 	FIELD(VM_ENTRY_CONTROLS, vm_entry_controls),
diff --git a/arch/x86/kvm/vmx/vmcs12.h b/arch/x86/kvm/vmx/vmcs12.h
index 01936013428b..f50f897b9b5f 100644
--- a/arch/x86/kvm/vmx/vmcs12.h
+++ b/arch/x86/kvm/vmx/vmcs12.h
@@ -185,6 +185,7 @@  struct __packed vmcs12 {
 	u16 host_gs_selector;
 	u16 host_tr_selector;
 	u16 guest_pml_index;
+	u64 secondary_vm_exit_controls;
 };
 
 /*
@@ -358,6 +359,7 @@  static inline void vmx_check_vmcs12_offsets(void)
 	CHECK_OFFSET(host_gs_selector, 992);
 	CHECK_OFFSET(host_tr_selector, 994);
 	CHECK_OFFSET(guest_pml_index, 996);
+	CHECK_OFFSET(secondary_vm_exit_controls, 998);
 }
 
 extern const unsigned short vmcs12_field_offsets[];
diff --git a/arch/x86/kvm/x86.h b/arch/x86/kvm/x86.h
index c1f1d5696080..498bb6090b1e 100644
--- a/arch/x86/kvm/x86.h
+++ b/arch/x86/kvm/x86.h
@@ -47,7 +47,7 @@  void kvm_spurious_fault(void);
  * associated feature that KVM supports for nested virtualization.
  */
 #define KVM_FIRST_EMULATED_VMX_MSR	MSR_IA32_VMX_BASIC
-#define KVM_LAST_EMULATED_VMX_MSR	MSR_IA32_VMX_VMFUNC
+#define KVM_LAST_EMULATED_VMX_MSR	MSR_IA32_VMX_EXIT_CTLS2
 
 #define KVM_DEFAULT_PLE_GAP		128
 #define KVM_VMX_DEFAULT_PLE_WINDOW	4096