Merge tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm

Pull KVM updates from Paolo Bonzini:

 - ARM: GICv3 ITS emulation and various fixes.  Removal of the
   old VGIC implementation.

 - s390: support for trapping software breakpoints, nested
   virtualization (vSIE), the STHYI opcode, initial extensions
   for CPU model support.

 - MIPS: support for MIPS64 hosts (32-bit guests only) and lots
   of cleanups, preliminary to this and the upcoming support for
   hardware virtualization extensions.

 - x86: support for execute-only mappings in nested EPT; reduced
   vmexit latency for TSC deadline timer (by about 30%) on Intel
   hosts; support for more than 255 vCPUs.

 - PPC: bugfixes.

* tag 'for-linus' of git://git.kernel.org/pub/scm/virt/kvm/kvm: (302 commits)
  KVM: PPC: Introduce KVM_CAP_PPC_HTM
  MIPS: Select HAVE_KVM for MIPS64_R{2,6}
  MIPS: KVM: Reset CP0_PageMask during host TLB flush
  MIPS: KVM: Fix ptr->int cast via KVM_GUEST_KSEGX()
  MIPS: KVM: Sign extend MFC0/RDHWR results
  MIPS: KVM: Fix 64-bit big endian dynamic translation
  MIPS: KVM: Fail if ebase doesn't fit in CP0_EBase
  MIPS: KVM: Use 64-bit CP0_EBase when appropriate
  MIPS: KVM: Set CP0_Status.KX on MIPS64
  MIPS: KVM: Make entry code MIPS64 friendly
  MIPS: KVM: Use kmap instead of CKSEG0ADDR()
  MIPS: KVM: Use virt_to_phys() to get commpage PFN
  MIPS: Fix definition of KSEGX() for 64-bit
  KVM: VMX: Add VMCS to CPU's loaded VMCSs before VMPTRLD
  kvm: x86: nVMX: maintain internal copy of current VMCS
  KVM: PPC: Book3S HV: Save/restore TM state in H_CEDE
  KVM: PPC: Book3S HV: Pull out TM state save/restore into separate procedures
  KVM: arm64: vgic-its: Simplify MAPI error handling
  KVM: arm64: vgic-its: Make vgic_its_cmd_handle_mapi similar to other handlers
  KVM: arm64: vgic-its: Turn device_id validation into generic ID validation
  ...

arch/x86/kvm/mmu.c

@@ -176,6 +176,7 @@ static u64 __read_mostly shadow_user_mask;
 static u64 __read_mostly shadow_accessed_mask;
 static u64 __read_mostly shadow_dirty_mask;
 static u64 __read_mostly shadow_mmio_mask;
+static u64 __read_mostly shadow_present_mask;
 
 static void mmu_spte_set(u64 *sptep, u64 spte);
 static void mmu_free_roots(struct kvm_vcpu *vcpu);
@@ -283,13 +284,14 @@ static bool check_mmio_spte(struct kvm_vcpu *vcpu, u64 spte)
 }
 
 void kvm_mmu_set_mask_ptes(u64 user_mask, u64 accessed_mask,
-		u64 dirty_mask, u64 nx_mask, u64 x_mask)
+		u64 dirty_mask, u64 nx_mask, u64 x_mask, u64 p_mask)
 {
 	shadow_user_mask = user_mask;
 	shadow_accessed_mask = accessed_mask;
 	shadow_dirty_mask = dirty_mask;
 	shadow_nx_mask = nx_mask;
 	shadow_x_mask = x_mask;
+	shadow_present_mask = p_mask;
 }
 EXPORT_SYMBOL_GPL(kvm_mmu_set_mask_ptes);
 
@@ -305,7 +307,7 @@ static int is_nx(struct kvm_vcpu *vcpu)
 
 static int is_shadow_present_pte(u64 pte)
 {
-	return pte & PT_PRESENT_MASK && !is_mmio_spte(pte);
+	return (pte & 0xFFFFFFFFull) && !is_mmio_spte(pte);
 }
 
 static int is_large_pte(u64 pte)
@@ -524,7 +526,7 @@ static void mmu_spte_set(u64 *sptep, u64 new_spte)
 }
 
 /* Rules for using mmu_spte_update:
- * Update the state bits, it means the mapped pfn is not changged.
+ * Update the state bits, it means the mapped pfn is not changed.
  *
  * Whenever we overwrite a writable spte with a read-only one we
  * should flush remote TLBs. Otherwise rmap_write_protect
@@ -2246,10 +2248,9 @@ static void link_shadow_page(struct kvm_vcpu *vcpu, u64 *sptep,
 {
 	u64 spte;
 
-	BUILD_BUG_ON(VMX_EPT_READABLE_MASK != PT_PRESENT_MASK ||
-			VMX_EPT_WRITABLE_MASK != PT_WRITABLE_MASK);
+	BUILD_BUG_ON(VMX_EPT_WRITABLE_MASK != PT_WRITABLE_MASK);
 
-	spte = __pa(sp->spt) | PT_PRESENT_MASK | PT_WRITABLE_MASK |
+	spte = __pa(sp->spt) | shadow_present_mask | PT_WRITABLE_MASK |
 	       shadow_user_mask | shadow_x_mask | shadow_accessed_mask;
 
 	mmu_spte_set(sptep, spte);
@@ -2516,13 +2517,19 @@ static int set_spte(struct kvm_vcpu *vcpu, u64 *sptep,
 		    gfn_t gfn, kvm_pfn_t pfn, bool speculative,
 		    bool can_unsync, bool host_writable)
 {
-	u64 spte;
+	u64 spte = 0;
 	int ret = 0;
 
 	if (set_mmio_spte(vcpu, sptep, gfn, pfn, pte_access))
 		return 0;
 
-	spte = PT_PRESENT_MASK;
+	/*
+	 * For the EPT case, shadow_present_mask is 0 if hardware
+	 * supports exec-only page table entries.  In that case,
+	 * ACC_USER_MASK and shadow_user_mask are used to represent
+	 * read access.  See FNAME(gpte_access) in paging_tmpl.h.
+	 */
+	spte |= shadow_present_mask;
 	if (!speculative)
 		spte |= shadow_accessed_mask;
 
@@ -3190,7 +3197,7 @@ static int mmu_alloc_shadow_roots(struct kvm_vcpu *vcpu)
 		MMU_WARN_ON(VALID_PAGE(root));
 		if (vcpu->arch.mmu.root_level == PT32E_ROOT_LEVEL) {
 			pdptr = vcpu->arch.mmu.get_pdptr(vcpu, i);
-			if (!is_present_gpte(pdptr)) {
+			if (!(pdptr & PT_PRESENT_MASK)) {
 				vcpu->arch.mmu.pae_root[i] = 0;
 				continue;
 			}
@@ -3915,9 +3922,7 @@ static void update_permission_bitmask(struct kvm_vcpu *vcpu,
 				 *   clearer.
 				 */
 				smap = cr4_smap && u && !uf && !ff;
-			} else
-				/* Not really needed: no U/S accesses on ept  */
-				u = 1;
+			}
 
 			fault = (ff && !x) || (uf && !u) || (wf && !w) ||
 				(smapf && smap);