From: Sean Christopherson Date: Wed, 9 Jun 2021 23:42:30 +0000 (-0700) Subject: KVM: x86: Use KVM_REQ_TLB_FLUSH_GUEST to handle INVPCID(ALL) emulation X-Git-Url: http://git.maquefel.me/?a=commitdiff_plain;h=28f28d453ffcca4a45c1fd93666d9e77a48cb45b;p=linux.git KVM: x86: Use KVM_REQ_TLB_FLUSH_GUEST to handle INVPCID(ALL) emulation Use KVM_REQ_TLB_FLUSH_GUEST instead of KVM_REQ_MMU_RELOAD when emulating INVPCID of all contexts. In the current code, this is a glorified nop as TLB_FLUSH_GUEST becomes kvm_mmu_unload(), same as MMU_RELOAD, when TDP is disabled, which is the only time INVPCID is only intercepted+emulated. In the future, reusing TLB_FLUSH_GUEST will simplify optimizing paths that emulate a guest TLB flush, e.g. by synchronizing as needed instead of completely unloading all MMUs. Signed-off-by: Sean Christopherson Message-Id: <20210609234235.1244004-11-seanjc@google.com> Signed-off-by: Paolo Bonzini --- diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 1a0fb0f1c1cb7..41b936187b2c8 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -12031,7 +12031,7 @@ int kvm_handle_invpcid(struct kvm_vcpu *vcpu, unsigned long type, gva_t gva) fallthrough; case INVPCID_TYPE_ALL_INCL_GLOBAL: - kvm_make_request(KVM_REQ_MMU_RELOAD, vcpu); + kvm_make_request(KVM_REQ_TLB_FLUSH_GUEST, vcpu); return kvm_skip_emulated_instruction(vcpu); default: