KVM: nVMX: Sync all PGDs on nested transition with shadow paging

stable inclusion
from stable-5.10.50
commit b2c5af71ce4b6e21f6af9fa292e72fd4662a2490
bugzilla: 174522 https://gitee.com/openeuler/kernel/issues/I4DNFY

Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id=b2c5af71ce4b6e21f6af9fa292e72fd4662a2490

--------------------------------

[ Upstream commit 07ffaf34 ]

Trigger a full TLB flush on behalf of the guest on nested VM-Enter and
VM-Exit when VPID is disabled for L2.  kvm_mmu_new_pgd() syncs only the
current PGD, which can theoretically leave stale, unsync'd entries in a
previous guest PGD, which could be consumed if L2 is allowed to load CR3
with PCID_NOFLUSH=1.

Rename KVM_REQ_HV_TLB_FLUSH to KVM_REQ_TLB_FLUSH_GUEST so that it can
be utilized for its obvious purpose of emulating a guest TLB flush.

Note, there is no change the actual TLB flush executed by KVM, even
though the fast PGD switch uses KVM_REQ_TLB_FLUSH_CURRENT.  When VPID is
disabled for L2, vpid02 is guaranteed to be '0', and thus
nested_get_vpid02() will return the VPID that is shared by L1 and L2.

Generate the request outside of kvm_mmu_new_pgd(), as getting the common
helper to correctly identify which requested is needed is quite painful.
E.g. using KVM_REQ_TLB_FLUSH_GUEST when nested EPT is in play is wrong as
a TLB flush from the L1 kernel's perspective does not invalidate EPT
mappings.  And, by using KVM_REQ_TLB_FLUSH_GUEST, nVMX can do future
simplification by moving the logic into nested_vmx_transition_tlb_flush().

Fixes: 41fab65e ("KVM: nVMX: Skip MMU sync on nested VMX transition when possible")
Signed-off-by: NSean Christopherson <seanjc@google.com>
Message-Id: <20210609234235.1244004-2-seanjc@google.com>
Signed-off-by: NPaolo Bonzini <pbonzini@redhat.com>
Signed-off-by: NSasha Levin <sashal@kernel.org>
Signed-off-by: NChen Jun <chenjun102@huawei.com>
Acked-by: NWeilong Chen <chenweilong@huawei.com>
Signed-off-by: NChen Jun <chenjun102@huawei.com>
Signed-off-by: NZheng Zengkai <zhengzengkai@huawei.com>

arch/x86/include/asm/kvm_host.h

@@ -84,7 +84,7 @@
 #define KVM_REQ_APICV_UPDATE \
 	KVM_ARCH_REQ_FLAGS(25, KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP)
 #define KVM_REQ_TLB_FLUSH_CURRENT	KVM_ARCH_REQ(26)
-#define KVM_REQ_HV_TLB_FLUSH \
+#define KVM_REQ_TLB_FLUSH_GUEST \
 	KVM_ARCH_REQ_FLAGS(27, KVM_REQUEST_NO_WAKEUP)
 #define KVM_REQ_APF_READY		KVM_ARCH_REQ(28)
 #define KVM_REQ_MSR_FILTER_CHANGED	KVM_ARCH_REQ(29)

arch/x86/kvm/hyperv.c

@@ -1564,7 +1564,7 @@ static u64 kvm_hv_flush_tlb(struct kvm_vcpu *current_vcpu, u64 ingpa,
 	 * vcpu->arch.cr3 may not be up-to-date for running vCPUs so we can't
 	 * analyze it here, flush TLB regardless of the specified address space.
 	 */
-	kvm_make_vcpus_request_mask(kvm, KVM_REQ_HV_TLB_FLUSH,
+	kvm_make_vcpus_request_mask(kvm, KVM_REQ_TLB_FLUSH_GUEST,
 				    NULL, vcpu_mask, &hv_vcpu->tlb_flush);
 
 ret_success:

arch/x86/kvm/vmx/nested.c

@@ -1142,12 +1142,19 @@ static int nested_vmx_load_cr3(struct kvm_vcpu *vcpu, unsigned long cr3, bool ne
 
 	/*
 	 * Unconditionally skip the TLB flush on fast CR3 switch, all TLB
-	 * flushes are handled by nested_vmx_transition_tlb_flush().  See
-	 * nested_vmx_transition_mmu_sync for details on skipping the MMU sync.
+	 * flushes are handled by nested_vmx_transition_tlb_flush().
 	 */
-	if (!nested_ept)
-		kvm_mmu_new_pgd(vcpu, cr3, true,
-				!nested_vmx_transition_mmu_sync(vcpu));
+	if (!nested_ept) {
+		kvm_mmu_new_pgd(vcpu, cr3, true, true);
+
+		/*
+		 * A TLB flush on VM-Enter/VM-Exit flushes all linear mappings
+		 * across all PCIDs, i.e. all PGDs need to be synchronized.
+		 * See nested_vmx_transition_mmu_sync() for more details.
+		 */
+		if (nested_vmx_transition_mmu_sync(vcpu))
+			kvm_make_request(KVM_REQ_TLB_FLUSH_GUEST, vcpu);
+	}
 
 	vcpu->arch.cr3 = cr3;
 	kvm_register_mark_available(vcpu, VCPU_EXREG_CR3);

arch/x86/kvm/x86.c

@@ -8919,7 +8919,7 @@ static int vcpu_enter_guest(struct kvm_vcpu *vcpu)
 		}
 		if (kvm_check_request(KVM_REQ_TLB_FLUSH_CURRENT, vcpu))
 			kvm_vcpu_flush_tlb_current(vcpu);
-		if (kvm_check_request(KVM_REQ_HV_TLB_FLUSH, vcpu))
+		if (kvm_check_request(KVM_REQ_TLB_FLUSH_GUEST, vcpu))
 			kvm_vcpu_flush_tlb_guest(vcpu);
 
 		if (kvm_check_request(KVM_REQ_REPORT_TPR_ACCESS, vcpu)) {