[PATCH 4/4] KVM: nVMX: initialize more non-shadowed fields in prepare_vmcs02_full

From: Paolo Bonzini
Date: Thu Dec 21 2017 - 07:44:17 EST


These fields are also simple copies of the data in the vmcs12 struct.
For some of them, prepare_vmcs02 was skipping the copy when the field
was unused. In prepare_vmcs02_full, we copy them always as long as the
field exists on the host, because the corresponding execution control
might be one of the shadowed fields.

Optimization opportunities remain for MSRs that, depending on the
entry/exit controls, have to be copied from either the vmcs01 or
the vmcs12: EFER (whose value is partly stored in the entry controls
too), PAT, DEBUGCTL (and also DR7). Before moving these three and
the entry/exit controls to prepare_vmcs02_full, KVM would have to set
dirty_vmcs12 on writes to the L1 MSRs.

Signed-off-by: Paolo Bonzini <pbonzini@xxxxxxxxxx>
---
arch/x86/kvm/vmx.c | 158 +++++++++++++++++++++++++++--------------------------
1 file changed, 80 insertions(+), 78 deletions(-)

diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index cc42994f4ba2..e2ac5bf64ad5 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -10623,6 +10623,85 @@ static void prepare_vmcs02_full(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12,
vmcs_writel(GUEST_TR_BASE, vmcs12->guest_tr_base);
vmcs_writel(GUEST_GDTR_BASE, vmcs12->guest_gdtr_base);
vmcs_writel(GUEST_IDTR_BASE, vmcs12->guest_idtr_base);
+
+ vmcs_write32(GUEST_SYSENTER_CS, vmcs12->guest_sysenter_cs);
+ vmcs_writel(GUEST_PENDING_DBG_EXCEPTIONS,
+ vmcs12->guest_pending_dbg_exceptions);
+ vmcs_writel(GUEST_SYSENTER_ESP, vmcs12->guest_sysenter_esp);
+ vmcs_writel(GUEST_SYSENTER_EIP, vmcs12->guest_sysenter_eip);
+
+ if (nested_cpu_has_xsaves(vmcs12))
+ vmcs_write64(XSS_EXIT_BITMAP, vmcs12->xss_exit_bitmap);
+ vmcs_write64(VMCS_LINK_POINTER, -1ull);
+
+ /*
+ * Whether page-faults are trapped is determined by a combination of
+ * 3 settings: PFEC_MASK, PFEC_MATCH and EXCEPTION_BITMAP.PF.
+ * If enable_ept, L0 doesn't care about page faults and we should
+ * set all of these to L1's desires. However, if !enable_ept, L0 does
+ * care about (at least some) page faults, and because it is not easy
+ * (if at all possible?) to merge L0 and L1's desires, we simply ask
+ * to exit on each and every L2 page fault. This is done by setting
+ * MASK=MATCH=0 and (see below) EB.PF=1.
+ * Note that below we don't need special code to set EB.PF beyond the
+ * "or"ing of the EB of vmcs01 and vmcs12, because when enable_ept,
+ * vmcs01's EB.PF is 0 so the "or" will take vmcs12's value, and when
+ * !enable_ept, EB.PF is 1, so the "or" will always be 1.
+ */
+ vmcs_write32(PAGE_FAULT_ERROR_CODE_MASK,
+ enable_ept ? vmcs12->page_fault_error_code_mask : 0);
+ vmcs_write32(PAGE_FAULT_ERROR_CODE_MATCH,
+ enable_ept ? vmcs12->page_fault_error_code_match : 0);
+
+ /* All VMFUNCs are currently emulated through L0 vmexits. */
+ if (cpu_has_vmx_vmfunc())
+ vmcs_write64(VM_FUNCTION_CONTROL, 0);
+
+ if (cpu_has_vmx_apicv()) {
+ vmcs_write64(EOI_EXIT_BITMAP0, vmcs12->eoi_exit_bitmap0);
+ vmcs_write64(EOI_EXIT_BITMAP1, vmcs12->eoi_exit_bitmap1);
+ vmcs_write64(EOI_EXIT_BITMAP2, vmcs12->eoi_exit_bitmap2);
+ vmcs_write64(EOI_EXIT_BITMAP3, vmcs12->eoi_exit_bitmap3);
+ }
+
+ /*
+ * Set host-state according to L0's settings (vmcs12 is irrelevant here)
+ * Some constant fields are set here by vmx_set_constant_host_state().
+ * Other fields are different per CPU, and will be set later when
+ * vmx_vcpu_load() is called, and when vmx_save_host_state() is called.
+ */
+ vmx_set_constant_host_state(vmx);
+
+ /*
+ * Set the MSR load/store lists to match L0's settings.
+ */
+ vmcs_write32(VM_EXIT_MSR_STORE_COUNT, 0);
+ vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, vmx->msr_autoload.nr);
+ vmcs_write64(VM_EXIT_MSR_LOAD_ADDR, __pa(vmx->msr_autoload.host));
+ vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, vmx->msr_autoload.nr);
+ vmcs_write64(VM_ENTRY_MSR_LOAD_ADDR, __pa(vmx->msr_autoload.guest));
+
+ set_cr4_guest_host_mask(vmx);
+
+ if (vmx_mpx_supported())
+ vmcs_write64(GUEST_BNDCFGS, vmcs12->guest_bndcfgs);
+
+ if (enable_vpid) {
+ if (nested_cpu_has_vpid(vmcs12) && vmx->nested.vpid02)
+ vmcs_write16(VIRTUAL_PROCESSOR_ID, vmx->nested.vpid02);
+ else
+ vmcs_write16(VIRTUAL_PROCESSOR_ID, vmx->vpid);
+ }
+
+ /*
+ * L1 may access the L2's PDPTR, so save them to construct vmcs12
+ */
+ if (enable_ept) {
+ vmcs_write64(GUEST_PDPTR0, vmcs12->guest_pdptr0);
+ vmcs_write64(GUEST_PDPTR1, vmcs12->guest_pdptr1);
+ vmcs_write64(GUEST_PDPTR2, vmcs12->guest_pdptr2);
+ vmcs_write64(GUEST_PDPTR3, vmcs12->guest_pdptr3);
+ }
}

/*
@@ -10680,16 +10759,7 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12,
} else {
vmcs_write32(VM_ENTRY_INTR_INFO_FIELD, 0);
}
- vmcs_write32(GUEST_SYSENTER_CS, vmcs12->guest_sysenter_cs);
vmx_set_rflags(vcpu, vmcs12->guest_rflags);
- vmcs_writel(GUEST_PENDING_DBG_EXCEPTIONS,
- vmcs12->guest_pending_dbg_exceptions);
- vmcs_writel(GUEST_SYSENTER_ESP, vmcs12->guest_sysenter_esp);
- vmcs_writel(GUEST_SYSENTER_EIP, vmcs12->guest_sysenter_eip);
-
- if (nested_cpu_has_xsaves(vmcs12))
- vmcs_write64(XSS_EXIT_BITMAP, vmcs12->xss_exit_bitmap);
- vmcs_write64(VMCS_LINK_POINTER, -1ull);

exec_control = vmcs12->pin_based_vm_exec_control;

@@ -10714,25 +10784,6 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12,
if (nested_cpu_has_preemption_timer(vmcs12))
vmx_start_preemption_timer(vcpu);

- /*
- * Whether page-faults are trapped is determined by a combination of
- * 3 settings: PFEC_MASK, PFEC_MATCH and EXCEPTION_BITMAP.PF.
- * If enable_ept, L0 doesn't care about page faults and we should
- * set all of these to L1's desires. However, if !enable_ept, L0 does
- * care about (at least some) page faults, and because it is not easy
- * (if at all possible?) to merge L0 and L1's desires, we simply ask
- * to exit on each and every L2 page fault. This is done by setting
- * MASK=MATCH=0 and (see below) EB.PF=1.
- * Note that below we don't need special code to set EB.PF beyond the
- * "or"ing of the EB of vmcs01 and vmcs12, because when enable_ept,
- * vmcs01's EB.PF is 0 so the "or" will take vmcs12's value, and when
- * !enable_ept, EB.PF is 1, so the "or" will always be 1.
- */
- vmcs_write32(PAGE_FAULT_ERROR_CODE_MASK,
- enable_ept ? vmcs12->page_fault_error_code_mask : 0);
- vmcs_write32(PAGE_FAULT_ERROR_CODE_MATCH,
- enable_ept ? vmcs12->page_fault_error_code_match : 0);
-
if (cpu_has_secondary_exec_ctrls()) {
exec_control = vmx->secondary_exec_control;

@@ -10751,22 +10802,9 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12,
exec_control |= vmcs12_exec_ctrl;
}

- /* All VMFUNCs are currently emulated through L0 vmexits. */
- if (exec_control & SECONDARY_EXEC_ENABLE_VMFUNC)
- vmcs_write64(VM_FUNCTION_CONTROL, 0);
-
- if (exec_control & SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY) {
- vmcs_write64(EOI_EXIT_BITMAP0,
- vmcs12->eoi_exit_bitmap0);
- vmcs_write64(EOI_EXIT_BITMAP1,
- vmcs12->eoi_exit_bitmap1);
- vmcs_write64(EOI_EXIT_BITMAP2,
- vmcs12->eoi_exit_bitmap2);
- vmcs_write64(EOI_EXIT_BITMAP3,
- vmcs12->eoi_exit_bitmap3);
+ if (exec_control & SECONDARY_EXEC_VIRTUAL_INTR_DELIVERY)
vmcs_write16(GUEST_INTR_STATUS,
vmcs12->guest_intr_status);
- }

/*
* Write an illegal value to APIC_ACCESS_ADDR. Later,
@@ -10779,24 +10817,6 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12,
vmcs_write32(SECONDARY_VM_EXEC_CONTROL, exec_control);
}

-
- /*
- * Set host-state according to L0's settings (vmcs12 is irrelevant here)
- * Some constant fields are set here by vmx_set_constant_host_state().
- * Other fields are different per CPU, and will be set later when
- * vmx_vcpu_load() is called, and when vmx_save_host_state() is called.
- */
- vmx_set_constant_host_state(vmx);
-
- /*
- * Set the MSR load/store lists to match L0's settings.
- */
- vmcs_write32(VM_EXIT_MSR_STORE_COUNT, 0);
- vmcs_write32(VM_EXIT_MSR_LOAD_COUNT, vmx->msr_autoload.nr);
- vmcs_write64(VM_EXIT_MSR_LOAD_ADDR, __pa(vmx->msr_autoload.host));
- vmcs_write32(VM_ENTRY_MSR_LOAD_COUNT, vmx->msr_autoload.nr);
- vmcs_write64(VM_ENTRY_MSR_LOAD_ADDR, __pa(vmx->msr_autoload.guest));
-
/*
* HOST_RSP is normally set correctly in vmx_vcpu_run() just before
* entry, but only if the current (host) sp changed from the value
@@ -10866,12 +10886,6 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12,
vmcs_write64(GUEST_IA32_PAT, vmx->vcpu.arch.pat);
}

- set_cr4_guest_host_mask(vmx);
-
- if (from_vmentry &&
- vmcs12->vm_entry_controls & VM_ENTRY_LOAD_BNDCFGS)
- vmcs_write64(GUEST_BNDCFGS, vmcs12->guest_bndcfgs);
-
if (vmcs12->cpu_based_vm_exec_control & CPU_BASED_USE_TSC_OFFSETING)
vmcs_write64(TSC_OFFSET,
vcpu->arch.tsc_offset + vmcs12->tsc_offset);
@@ -10890,13 +10904,11 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12,
* even if spawn a lot of nested vCPUs.
*/
if (nested_cpu_has_vpid(vmcs12) && vmx->nested.vpid02) {
- vmcs_write16(VIRTUAL_PROCESSOR_ID, vmx->nested.vpid02);
if (vmcs12->virtual_processor_id != vmx->nested.last_vpid) {
vmx->nested.last_vpid = vmcs12->virtual_processor_id;
__vmx_flush_tlb(vcpu, to_vmx(vcpu)->nested.vpid02, true);
}
} else {
- vmcs_write16(VIRTUAL_PROCESSOR_ID, vmx->vpid);
vmx_flush_tlb(vcpu, true);
}
}
@@ -10960,16 +10972,6 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12,
if (!enable_ept)
vcpu->arch.walk_mmu->inject_page_fault = vmx_inject_page_fault_nested;

- /*
- * L1 may access the L2's PDPTR, so save them to construct vmcs12
- */
- if (enable_ept) {
- vmcs_write64(GUEST_PDPTR0, vmcs12->guest_pdptr0);
- vmcs_write64(GUEST_PDPTR1, vmcs12->guest_pdptr1);
- vmcs_write64(GUEST_PDPTR2, vmcs12->guest_pdptr2);
- vmcs_write64(GUEST_PDPTR3, vmcs12->guest_pdptr3);
- }
-
kvm_register_write(vcpu, VCPU_REGS_RSP, vmcs12->guest_rsp);
kvm_register_write(vcpu, VCPU_REGS_RIP, vmcs12->guest_rip);
return 0;
--
1.8.3.1