Merge tag 'kvm-x86-vmx-6.5' of https://github.com/kvm-x86/linux into HEAD

KVM VMX changes for 6.5:

 - Fix missing/incorrect #GP checks on ENCLS

 - Use standard mmu_notifier hooks for handling APIC access page

 - Misc cleanups

1 files changed, 56 insertions, 10 deletions

diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index 2d9d155691a7..0ecf4be2c6af 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -3384,15 +3384,15 @@ static bool vmx_is_valid_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
 
 void vmx_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
 {
-	unsigned long old_cr4 = vcpu->arch.cr4;
+	unsigned long old_cr4 = kvm_read_cr4(vcpu);
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
+	unsigned long hw_cr4;
+
 	/*
 	 * Pass through host's Machine Check Enable value to hw_cr4, which
 	 * is in force while we are in guest mode.  Do not let guests control
 	 * this bit, even if host CR4.MCE == 0.
 	 */
-	unsigned long hw_cr4;
-
 	hw_cr4 = (cr4_read_shadow() & X86_CR4_MCE) | (cr4 & ~X86_CR4_MCE);
 	if (is_unrestricted_guest(vcpu))
 		hw_cr4 |= KVM_VM_CR4_ALWAYS_ON_UNRESTRICTED_GUEST;
@@ -3401,7 +3401,7 @@ void vmx_set_cr4(struct kvm_vcpu *vcpu, unsigned long cr4)
 	else
 		hw_cr4 |= KVM_PMODE_VM_CR4_ALWAYS_ON;
 
-	if (!boot_cpu_has(X86_FEATURE_UMIP) && vmx_umip_emulated()) {
+	if (vmx_umip_emulated()) {
 		if (cr4 & X86_CR4_UMIP) {
 			secondary_exec_controls_setbit(vmx, SECONDARY_EXEC_DESC);
 			hw_cr4 &= ~X86_CR4_UMIP;
@@ -5399,7 +5399,13 @@ static int handle_set_cr4(struct kvm_vcpu *vcpu, unsigned long val)
 
 static int handle_desc(struct kvm_vcpu *vcpu)
 {
-	WARN_ON(!(vcpu->arch.cr4 & X86_CR4_UMIP));
+	/*
+	 * UMIP emulation relies on intercepting writes to CR4.UMIP, i.e. this
+	 * and other code needs to be updated if UMIP can be guest owned.
+	 */
+	BUILD_BUG_ON(KVM_POSSIBLE_CR4_GUEST_BITS & X86_CR4_UMIP);
+
+	WARN_ON_ONCE(!kvm_is_cr4_bit_set(vcpu, X86_CR4_UMIP));
 	return kvm_emulate_instruction(vcpu, 0);
 }
 
@@ -6705,7 +6711,12 @@ void vmx_set_virtual_apic_mode(struct kvm_vcpu *vcpu)
 
 static void vmx_set_apic_access_page_addr(struct kvm_vcpu *vcpu)
 {
-	struct page *page;
+	const gfn_t gfn = APIC_DEFAULT_PHYS_BASE >> PAGE_SHIFT;
+	struct kvm *kvm = vcpu->kvm;
+	struct kvm_memslots *slots = kvm_memslots(kvm);
+	struct kvm_memory_slot *slot;
+	unsigned long mmu_seq;
+	kvm_pfn_t pfn;
 
 	/* Defer reload until vmcs01 is the current VMCS. */
 	if (is_guest_mode(vcpu)) {
@@ -6717,18 +6728,53 @@ static void vmx_set_apic_access_page_addr(struct kvm_vcpu *vcpu)
 	    SECONDARY_EXEC_VIRTUALIZE_APIC_ACCESSES))
 		return;
 
-	page = gfn_to_page(vcpu->kvm, APIC_DEFAULT_PHYS_BASE >> PAGE_SHIFT);
-	if (is_error_page(page))
+	/*
+	 * Grab the memslot so that the hva lookup for the mmu_notifier retry
+	 * is guaranteed to use the same memslot as the pfn lookup, i.e. rely
+	 * on the pfn lookup's validation of the memslot to ensure a valid hva
+	 * is used for the retry check.
+	 */
+	slot = id_to_memslot(slots, APIC_ACCESS_PAGE_PRIVATE_MEMSLOT);
+	if (!slot || slot->flags & KVM_MEMSLOT_INVALID)
 		return;
 
-	vmcs_write64(APIC_ACCESS_ADDR, page_to_phys(page));
+	/*
+	 * Ensure that the mmu_notifier sequence count is read before KVM
+	 * retrieves the pfn from the primary MMU.  Note, the memslot is
+	 * protected by SRCU, not the mmu_notifier.  Pairs with the smp_wmb()
+	 * in kvm_mmu_invalidate_end().
+	 */
+	mmu_seq = kvm->mmu_invalidate_seq;
+	smp_rmb();
+
+	/*
+	 * No need to retry if the memslot does not exist or is invalid.  KVM
+	 * controls the APIC-access page memslot, and only deletes the memslot
+	 * if APICv is permanently inhibited, i.e. the memslot won't reappear.
+	 */
+	pfn = gfn_to_pfn_memslot(slot, gfn);
+	if (is_error_noslot_pfn(pfn))
+		return;
+
+	read_lock(&vcpu->kvm->mmu_lock);
+	if (mmu_invalidate_retry_hva(kvm, mmu_seq,
+				     gfn_to_hva_memslot(slot, gfn))) {
+		kvm_make_request(KVM_REQ_APIC_PAGE_RELOAD, vcpu);
+		read_unlock(&vcpu->kvm->mmu_lock);
+		goto out;
+	}
+
+	vmcs_write64(APIC_ACCESS_ADDR, pfn_to_hpa(pfn));
+	read_unlock(&vcpu->kvm->mmu_lock);
+
 	vmx_flush_tlb_current(vcpu);
 
+out:
 	/*
 	 * Do not pin apic access page in memory, the MMU notifier
 	 * will call us again if it is migrated or swapped out.
 	 */
-	put_page(page);
+	kvm_release_pfn_clean(pfn);
 }
 
 static void vmx_hwapic_isr_update(int max_isr)