KVM: VMX: Move RESET emulation to vmx_vcpu_reset()

Move vCPU RESET emulation, including initializating of select VMCS state,
to vmx_vcpu_reset().  Drop the open coded "vCPU load" sequence, as
->vcpu_reset() is invoked while the vCPU is properly loaded (which is
kind of the point of ->vcpu_reset()...).  Hopefully KVM will someday
expose a dedicated RESET ioctl(), and in the meantime separating "create"
from "RESET" is a nice cleanup.

Deferring VMCS initialization is effectively a nop as it's impossible to
safely access the VMCS between the current call site and its new home, as
both the vCPU and the pCPU are put immediately after init_vmcs(), i.e.
the VMCS isn't guaranteed to be loaded.

Note, task preemption is not a problem as vmx_sched_in() _can't_ touch
the VMCS as ->sched_in() is invoked before the vCPU, and thus VMCS, is
reloaded.  I.e. the preemption path also can't consume VMCS state.

Cc: Reiji Watanabe <reijiw@google.com>
Signed-off-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Message-Id: <20210921000303.400537-9-seanjc@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index 65be361..b8bfb46 100644 (file)
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -4328,10 +4328,6 @@ static u32 vmx_secondary_exec_control(struct vcpu_vmx *vmx)
 
 #define VMX_XSS_EXIT_BITMAP 0
 
-/*
- * Noting that the initialization of Guest-state Area of VMCS is in
- * vmx_vcpu_reset().
- */
 static void init_vmcs(struct vcpu_vmx *vmx)
 {
        if (nested)
@@ -4436,10 +4432,40 @@ static void init_vmcs(struct vcpu_vmx *vmx)
        vmx_setup_uret_msrs(vmx);
 }
 
+static void __vmx_vcpu_reset(struct kvm_vcpu *vcpu)
+{
+       struct vcpu_vmx *vmx = to_vmx(vcpu);
+
+       init_vmcs(vmx);
+
+       if (nested)
+               memcpy(&vmx->nested.msrs, &vmcs_config.nested, sizeof(vmx->nested.msrs));
+
+       vcpu_setup_sgx_lepubkeyhash(vcpu);
+
+       vmx->nested.posted_intr_nv = -1;
+       vmx->nested.vmxon_ptr = INVALID_GPA;
+       vmx->nested.current_vmptr = INVALID_GPA;
+       vmx->nested.hv_evmcs_vmptr = EVMPTR_INVALID;
+
+       vcpu->arch.microcode_version = 0x100000000ULL;
+       vmx->msr_ia32_feature_control_valid_bits = FEAT_CTL_LOCKED;
+
+       /*
+        * Enforce invariant: pi_desc.nv is always either POSTED_INTR_VECTOR
+        * or POSTED_INTR_WAKEUP_VECTOR.
+        */
+       vmx->pi_desc.nv = POSTED_INTR_VECTOR;
+       vmx->pi_desc.sn = 1;
+}
+
 static void vmx_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event)
 {
        struct vcpu_vmx *vmx = to_vmx(vcpu);
 
+       if (!init_event)
+               __vmx_vcpu_reset(vcpu);
+
        vmx->rmode.vm86_active = 0;
        vmx->spec_ctrl = 0;
 
@@ -6816,7 +6842,7 @@ static int vmx_create_vcpu(struct kvm_vcpu *vcpu)
 {
        struct vmx_uret_msr *tsx_ctrl;
        struct vcpu_vmx *vmx;
-       int i, cpu, err;
+       int i, err;
 
        BUILD_BUG_ON(offsetof(struct vcpu_vmx, vcpu) != 0);
        vmx = to_vmx(vcpu);
@@ -6875,12 +6901,7 @@ static int vmx_create_vcpu(struct kvm_vcpu *vcpu)
        }
 
        vmx->loaded_vmcs = &vmx->vmcs01;
-       cpu = get_cpu();
-       vmx_vcpu_load(vcpu, cpu);
-       vcpu->cpu = cpu;
-       init_vmcs(vmx);
-       vmx_vcpu_put(vcpu);
-       put_cpu();
+
        if (cpu_need_virtualize_apic_accesses(vcpu)) {
                err = alloc_apic_access_page(vcpu->kvm);
                if (err)
@@ -6893,26 +6914,6 @@ static int vmx_create_vcpu(struct kvm_vcpu *vcpu)
                        goto free_vmcs;
        }
 
-       if (nested)
-               memcpy(&vmx->nested.msrs, &vmcs_config.nested, sizeof(vmx->nested.msrs));
-
-       vcpu_setup_sgx_lepubkeyhash(vcpu);
-
-       vmx->nested.posted_intr_nv = -1;
-       vmx->nested.vmxon_ptr = INVALID_GPA;
-       vmx->nested.current_vmptr = INVALID_GPA;
-       vmx->nested.hv_evmcs_vmptr = EVMPTR_INVALID;
-
-       vcpu->arch.microcode_version = 0x100000000ULL;
-       vmx->msr_ia32_feature_control_valid_bits = FEAT_CTL_LOCKED;
-
-       /*
-        * Enforce invariant: pi_desc.nv is always either POSTED_INTR_VECTOR
-        * or POSTED_INTR_WAKEUP_VECTOR.
-        */
-       vmx->pi_desc.nv = POSTED_INTR_VECTOR;
-       vmx->pi_desc.sn = 1;
-
        return 0;
 
 free_vmcs: