On Wed, Aug 11, 2021, Chenyi Qiang wrote:
> + u32 pkrs;
...
> @@ -1115,6 +1117,7 @@ void vmx_prepare_switch_to_guest(struct kvm_vcpu *vcpu)
> #endif
> unsigned long fs_base, gs_base;
> u16 fs_sel, gs_sel;
> + u32 host_pkrs;
As mentioned in the previosu patch, I think it makes sense to track this as a u64
so that the only place in KVM that deas with the u64<=>u32 conversion is the below
host_pkrs = get_current_pkrs();
> int i;
>
> vmx->req_immediate_exit = false;
> @@ -1150,6 +1153,20 @@ void vmx_prepare_switch_to_guest(struct kvm_vcpu *vcpu)
> */
> host_state->ldt_sel = kvm_read_ldt();
>
> + /*
> + * Update the host pkrs vmcs field before vcpu runs.
> + * The setting of VM_EXIT_LOAD_IA32_PKRS can ensure
> + * kvm_cpu_cap_has(X86_FEATURE_PKS) &&
> + * guest_cpuid_has(vcpu, X86_FEATURE_PKS)
> + */
> + if (vm_exit_controls_get(vmx) & VM_EXIT_LOAD_IA32_PKRS) {
> + host_pkrs = get_current_pkrs();
> + if (unlikely(host_pkrs != host_state->pkrs)) {
> + vmcs_write64(HOST_IA32_PKRS, host_pkrs);
> + host_state->pkrs = host_pkrs;
> + }
> + }
> +
> #ifdef CONFIG_X86_64
> savesegment(ds, host_state->ds_sel);
> savesegment(es, host_state->es_sel);
> @@ -1371,6 +1388,15 @@ void vmx_set_rflags(struct kvm_vcpu *vcpu, unsigned long rflags)
> vmx->emulation_required = emulation_required(vcpu);
> }
>
> +static void vmx_set_pkrs(struct kvm_vcpu *vcpu, u64 pkrs)
> +{
Hrm. Ideally this would be open coded in vmx_set_msr(). Long term, the RESET/INIT
paths should really treat MSR updates as "normal" host_initiated writes instead of
having to manually handle every MSR.
That would be a bit gross to handle in vmx_vcpu_reset() since it would have to
create a struct msr_data (because __kvm_set_msr() isn't exposed to vendor code),
but since vcpu->arch.pkrs is relevant to the MMU I think it makes sense to
initiate the write from common x86.
E.g. this way there's not out-of-band special code, vmx_vcpu_reset() is kept clean,
and if/when SVM gains support for PKRS this particular path Just Works. And it would
be an easy conversion for my pipe dream plan of handling MSRs at RESET/INIT via a
list of MSRs+values.
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index ac83d873d65b..55881d13620f 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -11147,6 +11147,9 @@ void kvm_vcpu_reset(struct kvm_vcpu *vcpu, bool init_event)
kvm_set_rflags(vcpu, X86_EFLAGS_FIXED);
kvm_rip_write(vcpu, 0xfff0);
+ if (kvm_cpu_cap_has(X86_FEATURE_PKS))
+ __kvm_set_msr(vcpu, MSR_IA32_PKRS, 0, true);
+
vcpu->arch.cr3 = 0;
kvm_register_mark_dirty(vcpu, VCPU_EXREG_CR3);
> + if (kvm_cpu_cap_has(X86_FEATURE_PKS)) {
> + vcpu->arch.pkrs = pkrs;
> + kvm_register_mark_available(vcpu, VCPU_EXREG_PKRS);
> + vmcs_write64(GUEST_IA32_PKRS, pkrs);
> + }
> +}
