linux-kernel - [PATCH v2 2/6] KVM: nVMX: delay loading of PDPTRs to KVM_REQ_GET_NESTED_STATE

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-Id: <20210426111333.967729-3-mlevitsk@redhat.com>
Date:   Mon, 26 Apr 2021 14:13:29 +0300
From:   Maxim Levitsky <mlevitsk@...hat.com>
To:     kvm@...r.kernel.org
Cc:     linux-doc@...r.kernel.org (open list:DOCUMENTATION),
        Thomas Gleixner <tglx@...utronix.de>,
        Jonathan Corbet <corbet@....net>,
        Paolo Bonzini <pbonzini@...hat.com>,
        x86@...nel.org (maintainer:X86 ARCHITECTURE (32-BIT AND 64-BIT)),
        linux-kernel@...r.kernel.org (open list:X86 ARCHITECTURE (32-BIT AND
        64-BIT)), "H. Peter Anvin" <hpa@...or.com>,
        Ingo Molnar <mingo@...hat.com>, Borislav Petkov <bp@...en8.de>,
        Wanpeng Li <wanpengli@...cent.com>,
        Vitaly Kuznetsov <vkuznets@...hat.com>,
        Jim Mattson <jmattson@...gle.com>,
        Sean Christopherson <seanjc@...gle.com>,
        Joerg Roedel <joro@...tes.org>,
        Maxim Levitsky <mlevitsk@...hat.com>
Subject: [PATCH v2 2/6] KVM: nVMX: delay loading of PDPTRs to KVM_REQ_GET_NESTED_STATE_PAGES

Similar to the rest of guest page accesses after a migration,
this access should be delayed to KVM_REQ_GET_NESTED_STATE_PAGES.

Signed-off-by: Maxim Levitsky <mlevitsk@...hat.com>
---
 arch/x86/kvm/vmx/nested.c | 23 ++++++++++++++++++-----
 1 file changed, 18 insertions(+), 5 deletions(-)

diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c
index 00339d624c92..764781ab805b 100644
--- a/arch/x86/kvm/vmx/nested.c
+++ b/arch/x86/kvm/vmx/nested.c
@@ -1105,7 +1105,8 @@ static bool nested_vmx_transition_mmu_sync(struct kvm_vcpu *vcpu)
  * Exit Qualification (for a VM-Entry consistency check VM-Exit) is assigned to
  * @entry_failure_code.
  */
-static int nested_vmx_load_cr3(struct kvm_vcpu *vcpu, unsigned long cr3, bool nested_ept,
+static int nested_vmx_load_cr3(struct kvm_vcpu *vcpu, unsigned long cr3,
+			       bool nested_ept, bool reload_pdptrs,
 			       enum vm_entry_failure_code *entry_failure_code)
 {
 	if (CC(kvm_vcpu_is_illegal_gpa(vcpu, cr3))) {
@@ -1117,7 +1118,7 @@ static int nested_vmx_load_cr3(struct kvm_vcpu *vcpu, unsigned long cr3, bool ne
 	 * If PAE paging and EPT are both on, CR3 is not used by the CPU and
 	 * must not be dereferenced.
 	 */
-	if (!nested_ept && is_pae_paging(vcpu) &&
+	if (reload_pdptrs && !nested_ept && is_pae_paging(vcpu) &&
 	    (cr3 != kvm_read_cr3(vcpu) || pdptrs_changed(vcpu))) {
 		if (CC(!load_pdptrs(vcpu, vcpu->arch.walk_mmu, cr3))) {
 			*entry_failure_code = ENTRY_FAIL_PDPTE;
@@ -2488,6 +2489,7 @@ static void prepare_vmcs02_rare(struct vcpu_vmx *vmx, struct vmcs12 *vmcs12)
  * is assigned to entry_failure_code on failure.
  */
 static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12,
+			  bool from_vmentry,
 			  enum vm_entry_failure_code *entry_failure_code)
 {
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
@@ -2572,7 +2574,7 @@ static int prepare_vmcs02(struct kvm_vcpu *vcpu, struct vmcs12 *vmcs12,
 
 	/* Shadow page tables on either EPT or shadow page tables. */
 	if (nested_vmx_load_cr3(vcpu, vmcs12->guest_cr3, nested_cpu_has_ept(vmcs12),
-				entry_failure_code))
+			from_vmentry, entry_failure_code))
 		return -EINVAL;
 
 	/*
@@ -3120,6 +3122,17 @@ static bool nested_get_vmcs12_pages(struct kvm_vcpu *vcpu)
 	struct page *page;
 	u64 hpa;
 
+	if (!nested_cpu_has_ept(vmcs12) && is_pae_paging(vcpu)) {
+		/*
+		 * Reload the guest's PDPTRs since after a migration
+		 * the guest CR3 might be restored prior to setting the nested
+		 * state which can lead to a load of wrong PDPTRs.
+		 */
+		if (CC(!load_pdptrs(vcpu, vcpu->arch.walk_mmu, vcpu->arch.cr3)))
+			return false;
+	}
+
+
 	if (nested_cpu_has2(vmcs12, SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES)) {
 		/*
 		 * Translate L1 physical address to host physical
@@ -3356,7 +3369,7 @@ enum nvmx_vmentry_status nested_vmx_enter_non_root_mode(struct kvm_vcpu *vcpu,
 	if (vmcs12->cpu_based_vm_exec_control & CPU_BASED_USE_TSC_OFFSETTING)
 		vcpu->arch.tsc_offset += vmcs12->tsc_offset;
 
-	if (prepare_vmcs02(vcpu, vmcs12, &entry_failure_code)) {
+	if (prepare_vmcs02(vcpu, vmcs12, from_vmentry, &entry_failure_code)) {
 		exit_reason.basic = EXIT_REASON_INVALID_STATE;
 		vmcs12->exit_qualification = entry_failure_code;
 		goto vmentry_fail_vmexit_guest_mode;
@@ -4205,7 +4218,7 @@ static void load_vmcs12_host_state(struct kvm_vcpu *vcpu,
 	 * Only PDPTE load can fail as the value of cr3 was checked on entry and
 	 * couldn't have changed.
 	 */
-	if (nested_vmx_load_cr3(vcpu, vmcs12->host_cr3, false, &ignored))
+	if (nested_vmx_load_cr3(vcpu, vmcs12->host_cr3, false, true, &ignored))
 		nested_vmx_abort(vcpu, VMX_ABORT_LOAD_HOST_PDPTE_FAIL);
 
 	nested_vmx_transition_tlb_flush(vcpu, vmcs12, false);
-- 
2.26.2