Merge commit 'origin/next' into kvm-ppc-next

arch/s390/kvm/interrupt.c

@@ -55,6 +55,13 @@ static int psw_interrupts_disabled(struct kvm_vcpu *vcpu)
 	return 1;
 }
 
+static u64 int_word_to_isc_bits(u32 int_word)
+{
+	u8 isc = (int_word & 0x38000000) >> 27;
+
+	return (0x80 >> isc) << 24;
+}
+
 static int __interrupt_is_deliverable(struct kvm_vcpu *vcpu,
 				      struct kvm_s390_interrupt_info *inti)
 {
@@ -96,7 +103,8 @@ static int __interrupt_is_deliverable(struct kvm_vcpu *vcpu,
 	case KVM_S390_INT_IO_MIN...KVM_S390_INT_IO_MAX:
 		if (psw_ioint_disabled(vcpu))
 			return 0;
-		if (vcpu->arch.sie_block->gcr[6] & inti->io.io_int_word)
+		if (vcpu->arch.sie_block->gcr[6] &
+		    int_word_to_isc_bits(inti->io.io_int_word))
 			return 1;
 		return 0;
 	default:
@@ -724,7 +732,8 @@ struct kvm_s390_interrupt_info *kvm_s390_get_io_int(struct kvm *kvm,
 	list_for_each_entry(iter, &fi->list, list) {
 		if (!is_ioint(iter->type))
 			continue;
-		if (cr6 && ((cr6 & iter->io.io_int_word) == 0))
+		if (cr6 &&
+		    ((cr6 & int_word_to_isc_bits(iter->io.io_int_word)) == 0))
 			continue;
 		if (schid) {
 			if (((schid & 0x00000000ffff0000) >> 16) !=
@@ -811,11 +820,14 @@ int kvm_s390_inject_vm(struct kvm *kvm,
 	if (!is_ioint(inti->type))
 		list_add_tail(&inti->list, &fi->list);
 	else {
+		u64 isc_bits = int_word_to_isc_bits(inti->io.io_int_word);
+
 		/* Keep I/O interrupts sorted in isc order. */
 		list_for_each_entry(iter, &fi->list, list) {
 			if (!is_ioint(iter->type))
 				continue;
-			if (iter->io.io_int_word <= inti->io.io_int_word)
+			if (int_word_to_isc_bits(iter->io.io_int_word)
+			    <= isc_bits)
 				continue;
 			break;
 		}

arch/x86/kvm/emulate.c

@@ -2995,14 +2995,11 @@ static int em_aad(struct x86_emulate_ctxt *ctxt)
 
 	ctxt->dst.val = (ctxt->dst.val & 0xffff0000) | al;
 
-	ctxt->eflags &= ~(X86_EFLAGS_PF | X86_EFLAGS_SF | X86_EFLAGS_ZF);
-
-	if (!al)
-		ctxt->eflags |= X86_EFLAGS_ZF;
-	if (!(al & 1))
-		ctxt->eflags |= X86_EFLAGS_PF;
-	if (al & 0x80)
-		ctxt->eflags |= X86_EFLAGS_SF;
+	/* Set PF, ZF, SF */
+	ctxt->src.type = OP_IMM;
+	ctxt->src.val = 0;
+	ctxt->src.bytes = 1;
+	fastop(ctxt, em_or);
 
 	return X86EMUL_CONTINUE;
 }

arch/x86/kvm/mmu.c

@@ -832,8 +832,7 @@ static int mapping_level(struct kvm_vcpu *vcpu, gfn_t large_gfn)
 	if (host_level == PT_PAGE_TABLE_LEVEL)
 		return host_level;
 
-	max_level = kvm_x86_ops->get_lpage_level() < host_level ?
-		kvm_x86_ops->get_lpage_level() : host_level;
+	max_level = min(kvm_x86_ops->get_lpage_level(), host_level);
 
 	for (level = PT_DIRECTORY_LEVEL; level <= max_level; ++level)
 		if (has_wrprotected_page(vcpu->kvm, large_gfn, level))
@@ -1106,8 +1105,7 @@ static void drop_large_spte(struct kvm_vcpu *vcpu, u64 *sptep)
 
 /*
  * Write-protect on the specified @sptep, @pt_protect indicates whether
- * spte writ-protection is caused by protecting shadow page table.
- * @flush indicates whether tlb need be flushed.
+ * spte write-protection is caused by protecting shadow page table.
  *
  * Note: write protection is difference between drity logging and spte
  * protection:
@@ -1116,10 +1114,9 @@ static void drop_large_spte(struct kvm_vcpu *vcpu, u64 *sptep)
  * - for spte protection, the spte can be writable only after unsync-ing
  *   shadow page.
  *
- * Return true if the spte is dropped.
+ * Return true if tlb need be flushed.
  */
-static bool
-spte_write_protect(struct kvm *kvm, u64 *sptep, bool *flush, bool pt_protect)
+static bool spte_write_protect(struct kvm *kvm, u64 *sptep, bool pt_protect)
 {
 	u64 spte = *sptep;
 
@@ -1129,17 +1126,11 @@ spte_write_protect(struct kvm *kvm, u64 *sptep, bool *flush, bool pt_protect)
 
 	rmap_printk("rmap_write_protect: spte %p %llx\n", sptep, *sptep);
 
-	if (__drop_large_spte(kvm, sptep)) {
-		*flush |= true;
-		return true;
-	}
-
 	if (pt_protect)
 		spte &= ~SPTE_MMU_WRITEABLE;
 	spte = spte & ~PT_WRITABLE_MASK;
 
-	*flush |= mmu_spte_update(sptep, spte);
-	return false;
+	return mmu_spte_update(sptep, spte);
 }
 
 static bool __rmap_write_protect(struct kvm *kvm, unsigned long *rmapp,
@@ -1151,11 +1142,8 @@ static bool __rmap_write_protect(struct kvm *kvm, unsigned long *rmapp,
 
 	for (sptep = rmap_get_first(*rmapp, &iter); sptep;) {
 		BUG_ON(!(*sptep & PT_PRESENT_MASK));
-		if (spte_write_protect(kvm, sptep, &flush, pt_protect)) {
-			sptep = rmap_get_first(*rmapp, &iter);
-			continue;
-		}
 
+		flush |= spte_write_protect(kvm, sptep, pt_protect);
 		sptep = rmap_get_next(&iter);
 	}
 
@@ -1959,9 +1947,9 @@ static void link_shadow_page(u64 *sptep, struct kvm_mmu_page *sp)
 {
 	u64 spte;
 
-	spte = __pa(sp->spt)
-		| PT_PRESENT_MASK | PT_ACCESSED_MASK
-		| PT_WRITABLE_MASK | PT_USER_MASK;
+	spte = __pa(sp->spt) | PT_PRESENT_MASK | PT_WRITABLE_MASK |
+	       shadow_user_mask | shadow_x_mask | shadow_accessed_mask;
+
 	mmu_spte_set(sptep, spte);
 }
 
@@ -2400,16 +2388,15 @@ static int set_spte(struct kvm_vcpu *vcpu, u64 *sptep,
 }
 
 static void mmu_set_spte(struct kvm_vcpu *vcpu, u64 *sptep,
-			 unsigned pt_access, unsigned pte_access,
-			 int write_fault, int *emulate, int level, gfn_t gfn,
-			 pfn_t pfn, bool speculative, bool host_writable)
+			 unsigned pte_access, int write_fault, int *emulate,
+			 int level, gfn_t gfn, pfn_t pfn, bool speculative,
+			 bool host_writable)
 {
 	int was_rmapped = 0;
 	int rmap_count;
 
-	pgprintk("%s: spte %llx access %x write_fault %d gfn %llx\n",
-		 __func__, *sptep, pt_access,
-		 write_fault, gfn);
+	pgprintk("%s: spte %llx write_fault %d gfn %llx\n", __func__,
+		 *sptep, write_fault, gfn);
 
 	if (is_rmap_spte(*sptep)) {
 		/*
@@ -2525,7 +2512,7 @@ static int direct_pte_prefetch_many(struct kvm_vcpu *vcpu,
 		return -1;
 
 	for (i = 0; i < ret; i++, gfn++, start++)
-		mmu_set_spte(vcpu, start, ACC_ALL, access, 0, NULL,
+		mmu_set_spte(vcpu, start, access, 0, NULL,
 			     sp->role.level, gfn, page_to_pfn(pages[i]),
 			     true, true);
 
@@ -2586,9 +2573,7 @@ static int __direct_map(struct kvm_vcpu *vcpu, gpa_t v, int write,
 
 	for_each_shadow_entry(vcpu, (u64)gfn << PAGE_SHIFT, iterator) {
 		if (iterator.level == level) {
-			unsigned pte_access = ACC_ALL;
-
-			mmu_set_spte(vcpu, iterator.sptep, ACC_ALL, pte_access,
+			mmu_set_spte(vcpu, iterator.sptep, ACC_ALL,
 				     write, &emulate, level, gfn, pfn,
 				     prefault, map_writable);
 			direct_pte_prefetch(vcpu, iterator.sptep);
@@ -2596,6 +2581,8 @@ static int __direct_map(struct kvm_vcpu *vcpu, gpa_t v, int write,
 			break;
 		}
 
+		drop_large_spte(vcpu, iterator.sptep);
+
 		if (!is_shadow_present_pte(*iterator.sptep)) {
 			u64 base_addr = iterator.addr;
 
@@ -2605,11 +2592,7 @@ static int __direct_map(struct kvm_vcpu *vcpu, gpa_t v, int write,
 					      iterator.level - 1,
 					      1, ACC_ALL, iterator.sptep);
 
-			mmu_spte_set(iterator.sptep,
-				     __pa(sp->spt)
-				     | PT_PRESENT_MASK | PT_WRITABLE_MASK
-				     | shadow_user_mask | shadow_x_mask
-				     | shadow_accessed_mask);
+			link_shadow_page(iterator.sptep, sp);
 		}
 	}
 	return emulate;

arch/x86/kvm/paging_tmpl.h

@@ -326,8 +326,8 @@ FNAME(prefetch_gpte)(struct kvm_vcpu *vcpu, struct kvm_mmu_page *sp,
 	 * we call mmu_set_spte() with host_writable = true because
 	 * pte_prefetch_gfn_to_pfn always gets a writable pfn.
 	 */
-	mmu_set_spte(vcpu, spte, sp->role.access, pte_access, 0,
-		     NULL, PT_PAGE_TABLE_LEVEL, gfn, pfn, true, true);
+	mmu_set_spte(vcpu, spte, pte_access, 0, NULL, PT_PAGE_TABLE_LEVEL,
+		     gfn, pfn, true, true);
 
 	return true;
 }
@@ -470,9 +470,8 @@ static int FNAME(fetch)(struct kvm_vcpu *vcpu, gva_t addr,
 	}
 
 	clear_sp_write_flooding_count(it.sptep);
-	mmu_set_spte(vcpu, it.sptep, access, gw->pte_access,
-		     write_fault, &emulate, it.level,
-		     gw->gfn, pfn, prefault, map_writable);
+	mmu_set_spte(vcpu, it.sptep, gw->pte_access, write_fault, &emulate,
+		     it.level, gw->gfn, pfn, prefault, map_writable);
 	FNAME(pte_prefetch)(vcpu, gw, it.sptep);
 
 	return emulate;

arch/x86/kvm/vmx.c

@@ -84,8 +84,7 @@ module_param(vmm_exclusive, bool, S_IRUGO);
 static bool __read_mostly fasteoi = 1;
 module_param(fasteoi, bool, S_IRUGO);
 
-static bool __read_mostly enable_apicv_reg_vid = 1;
-module_param(enable_apicv_reg_vid, bool, S_IRUGO);
+static bool __read_mostly enable_apicv_reg_vid;
 
 /*
  * If nested=1, nested virtualization is supported, i.e., guests may use
@@ -95,12 +94,8 @@ module_param(enable_apicv_reg_vid, bool, S_IRUGO);
 static bool __read_mostly nested = 0;
 module_param(nested, bool, S_IRUGO);
 
-#define KVM_GUEST_CR0_MASK_UNRESTRICTED_GUEST				\
-	(X86_CR0_WP | X86_CR0_NE | X86_CR0_NW | X86_CR0_CD)
-#define KVM_GUEST_CR0_MASK						\
-	(KVM_GUEST_CR0_MASK_UNRESTRICTED_GUEST | X86_CR0_PG | X86_CR0_PE)
-#define KVM_VM_CR0_ALWAYS_ON_UNRESTRICTED_GUEST				\
-	(X86_CR0_WP | X86_CR0_NE)
+#define KVM_GUEST_CR0_MASK (X86_CR0_NW | X86_CR0_CD)
+#define KVM_VM_CR0_ALWAYS_ON_UNRESTRICTED_GUEST (X86_CR0_WP | X86_CR0_NE)
 #define KVM_VM_CR0_ALWAYS_ON						\
 	(KVM_VM_CR0_ALWAYS_ON_UNRESTRICTED_GUEST | X86_CR0_PG | X86_CR0_PE)
 #define KVM_CR4_GUEST_OWNED_BITS				      \
@@ -3137,11 +3132,11 @@ static void vmx_set_cr0(struct kvm_vcpu *vcpu, unsigned long cr0)
 	struct vcpu_vmx *vmx = to_vmx(vcpu);
 	unsigned long hw_cr0;
 
+	hw_cr0 = (cr0 & ~KVM_GUEST_CR0_MASK);
 	if (enable_unrestricted_guest)
-		hw_cr0 = (cr0 & ~KVM_GUEST_CR0_MASK_UNRESTRICTED_GUEST)
-			| KVM_VM_CR0_ALWAYS_ON_UNRESTRICTED_GUEST;
+		hw_cr0 |= KVM_VM_CR0_ALWAYS_ON_UNRESTRICTED_GUEST;
 	else {
-		hw_cr0 = (cr0 & ~KVM_GUEST_CR0_MASK) | KVM_VM_CR0_ALWAYS_ON;
+		hw_cr0 |= KVM_VM_CR0_ALWAYS_ON;
 
 		if (vmx->rmode.vm86_active && (cr0 & X86_CR0_PE))
 			enter_pmode(vcpu);
@@ -5925,7 +5920,7 @@ static bool nested_vmx_exit_handled_msr(struct kvm_vcpu *vcpu,
 	u32 msr_index = vcpu->arch.regs[VCPU_REGS_RCX];
 	gpa_t bitmap;
 
-	if (!nested_cpu_has(get_vmcs12(vcpu), CPU_BASED_USE_MSR_BITMAPS))
+	if (!nested_cpu_has(vmcs12, CPU_BASED_USE_MSR_BITMAPS))
 		return 1;
 
 	/*

arch/x86/kvm/x86.c

@@ -6897,32 +6897,27 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm,
 				bool user_alloc)
 {
 	int npages = memslot->npages;
-	int map_flags = MAP_PRIVATE | MAP_ANONYMOUS;
 
-	/* Prevent internal slot pages from being moved by fork()/COW. */
-	if (memslot->id >= KVM_USER_MEM_SLOTS)
-		map_flags = MAP_SHARED | MAP_ANONYMOUS;
-
-	/*To keep backward compatibility with older userspace,
-	 *x86 needs to handle !user_alloc case.
+	/*
+	 * Only private memory slots need to be mapped here since
+	 * KVM_SET_MEMORY_REGION ioctl is no longer supported.
 	 */
-	if (!user_alloc) {
-		if (npages && !old.npages) {
+	if ((memslot->id >= KVM_USER_MEM_SLOTS) && npages && !old.npages) {
 		unsigned long userspace_addr;
 
-			userspace_addr = vm_mmap(NULL, 0,
-						 npages * PAGE_SIZE,
+		/*
+		 * MAP_SHARED to prevent internal slot pages from being moved
+		 * by fork()/COW.
+		 */
+		userspace_addr = vm_mmap(NULL, 0, npages * PAGE_SIZE,
 					 PROT_READ | PROT_WRITE,
-						 map_flags,
-						 0);
+					 MAP_SHARED | MAP_ANONYMOUS, 0);
 
 		if (IS_ERR((void *)userspace_addr))
 			return PTR_ERR((void *)userspace_addr);
 
 		memslot->userspace_addr = userspace_addr;
 	}
-	}
-
 
 	return 0;
 }
@@ -6935,7 +6930,7 @@ void kvm_arch_commit_memory_region(struct kvm *kvm,
 
 	int nr_mmu_pages = 0, npages = mem->memory_size >> PAGE_SHIFT;
 
-	if (!user_alloc && !old.user_alloc && old.npages && !npages) {
+	if ((mem->slot >= KVM_USER_MEM_SLOTS) && old.npages && !npages) {
 		int ret;
 
 		ret = vm_munmap(old.userspace_addr,

include/linux/kvm_host.h

@@ -273,7 +273,6 @@ struct kvm_memory_slot {
 	unsigned long userspace_addr;
 	u32 flags;
 	short id;
-	bool user_alloc;
 };
 
 static inline unsigned long kvm_dirty_bitmap_bytes(struct kvm_memory_slot *memslot)

virt/kvm/kvm_main.c

@@ -839,7 +839,6 @@ int __kvm_set_memory_region(struct kvm *kvm,
 
 	r = -ENOMEM;
 	if (change == KVM_MR_CREATE) {
-		new.user_alloc = user_alloc;
 		new.userspace_addr = mem->userspace_addr;
 
 		if (kvm_arch_create_memslot(&new, npages))