1 files changed, 327 insertions, 214 deletions

diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index d617f69131d7..c353b4599cec 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -100,13 +100,7 @@ EXPORT_SYMBOL_GPL(kvm_rebooting);
 
 static bool largepages_enabled = true;
 
-static struct page *hwpoison_page;
-static pfn_t hwpoison_pfn;
-
-struct page *fault_page;
-pfn_t fault_pfn;
-
-inline int kvm_is_mmio_pfn(pfn_t pfn)
+bool kvm_is_mmio_pfn(pfn_t pfn)
 {
 	if (pfn_valid(pfn)) {
 		int reserved;
@@ -137,11 +131,12 @@ inline int kvm_is_mmio_pfn(pfn_t pfn)
 /*
  * Switches to specified vcpu, until a matching vcpu_put()
  */
-void vcpu_load(struct kvm_vcpu *vcpu)
+int vcpu_load(struct kvm_vcpu *vcpu)
 {
 	int cpu;
 
-	mutex_lock(&vcpu->mutex);
+	if (mutex_lock_killable(&vcpu->mutex))
+		return -EINTR;
 	if (unlikely(vcpu->pid != current->pids[PIDTYPE_PID].pid)) {
 		/* The thread running this VCPU changed. */
 		struct pid *oldpid = vcpu->pid;
@@ -154,6 +149,7 @@ void vcpu_load(struct kvm_vcpu *vcpu)
 	preempt_notifier_register(&vcpu->preempt_notifier);
 	kvm_arch_vcpu_load(vcpu, cpu);
 	put_cpu();
+	return 0;
 }
 
 void vcpu_put(struct kvm_vcpu *vcpu)
@@ -236,6 +232,9 @@ int kvm_vcpu_init(struct kvm_vcpu *vcpu, struct kvm *kvm, unsigned id)
 	}
 	vcpu->run = page_address(page);
 
+	kvm_vcpu_set_in_spin_loop(vcpu, false);
+	kvm_vcpu_set_dy_eligible(vcpu, false);
+
 	r = kvm_arch_vcpu_init(vcpu);
 	if (r < 0)
 		goto fail_free_run;
@@ -332,8 +331,7 @@ static void kvm_mmu_notifier_invalidate_range_start(struct mmu_notifier *mn,
 	 * count is also read inside the mmu_lock critical section.
 	 */
 	kvm->mmu_notifier_count++;
-	for (; start < end; start += PAGE_SIZE)
-		need_tlb_flush |= kvm_unmap_hva(kvm, start);
+	need_tlb_flush = kvm_unmap_hva_range(kvm, start, end);
 	need_tlb_flush |= kvm->tlbs_dirty;
 	/* we've to flush the tlb before the pages can be freed */
 	if (need_tlb_flush)
@@ -412,7 +410,7 @@ static void kvm_mmu_notifier_release(struct mmu_notifier *mn,
 	int idx;
 
 	idx = srcu_read_lock(&kvm->srcu);
-	kvm_arch_flush_shadow(kvm);
+	kvm_arch_flush_shadow_all(kvm);
 	srcu_read_unlock(&kvm->srcu, idx);
 }
 
@@ -551,16 +549,12 @@ static void kvm_destroy_dirty_bitmap(struct kvm_memory_slot *memslot)
 static void kvm_free_physmem_slot(struct kvm_memory_slot *free,
 				  struct kvm_memory_slot *dont)
 {
-	if (!dont || free->rmap != dont->rmap)
-		vfree(free->rmap);
-
 	if (!dont || free->dirty_bitmap != dont->dirty_bitmap)
 		kvm_destroy_dirty_bitmap(free);
 
 	kvm_arch_free_memslot(free, dont);
 
 	free->npages = 0;
-	free->rmap = NULL;
 }
 
 void kvm_free_physmem(struct kvm *kvm)
@@ -590,7 +584,7 @@ static void kvm_destroy_vm(struct kvm *kvm)
 #if defined(CONFIG_MMU_NOTIFIER) && defined(KVM_ARCH_WANT_MMU_NOTIFIER)
 	mmu_notifier_unregister(&kvm->mmu_notifier, kvm->mm);
 #else
-	kvm_arch_flush_shadow(kvm);
+	kvm_arch_flush_shadow_all(kvm);
 #endif
 	kvm_arch_destroy_vm(kvm);
 	kvm_free_physmem(kvm);
@@ -686,6 +680,20 @@ void update_memslots(struct kvm_memslots *slots, struct kvm_memory_slot *new)
 	slots->generation++;
 }
 
+static int check_memory_region_flags(struct kvm_userspace_memory_region *mem)
+{
+	u32 valid_flags = KVM_MEM_LOG_DIRTY_PAGES;
+
+#ifdef KVM_CAP_READONLY_MEM
+	valid_flags |= KVM_MEM_READONLY;
+#endif
+
+	if (mem->flags & ~valid_flags)
+		return -EINVAL;
+
+	return 0;
+}
+
 /*
  * Allocate some memory and give it an address in the guest physical address
  * space.
@@ -706,6 +714,10 @@ int __kvm_set_memory_region(struct kvm *kvm,
 	struct kvm_memory_slot old, new;
 	struct kvm_memslots *slots, *old_memslots;
 
+	r = check_memory_region_flags(mem);
+	if (r)
+		goto out;
+
 	r = -EINVAL;
 	/* General sanity checks */
 	if (mem->memory_size & (PAGE_SIZE - 1))
@@ -769,11 +781,7 @@ int __kvm_set_memory_region(struct kvm *kvm,
 	if (npages && !old.npages) {
 		new.user_alloc = user_alloc;
 		new.userspace_addr = mem->userspace_addr;
-#ifndef CONFIG_S390
-		new.rmap = vzalloc(npages * sizeof(*new.rmap));
-		if (!new.rmap)
-			goto out_free;
-#endif /* not defined CONFIG_S390 */
+
 		if (kvm_arch_create_memslot(&new, npages))
 			goto out_free;
 	}
@@ -785,7 +793,7 @@ int __kvm_set_memory_region(struct kvm *kvm,
 		/* destroy any largepage mappings for dirty tracking */
 	}
 
-	if (!npages) {
+	if (!npages || base_gfn != old.base_gfn) {
 		struct kvm_memory_slot *slot;
 
 		r = -ENOMEM;
@@ -801,14 +809,14 @@ int __kvm_set_memory_region(struct kvm *kvm,
 		old_memslots = kvm->memslots;
 		rcu_assign_pointer(kvm->memslots, slots);
 		synchronize_srcu_expedited(&kvm->srcu);
-		/* From this point no new shadow pages pointing to a deleted
-		 * memslot will be created.
+		/* From this point no new shadow pages pointing to a deleted,
+		 * or moved, memslot will be created.
 		 *
 		 * validation of sp->gfn happens in:
 		 * 	- gfn_to_hva (kvm_read_guest, gfn_to_pfn)
 		 * 	- kvm_is_visible_gfn (mmu_check_roots)
 		 */
-		kvm_arch_flush_shadow(kvm);
+		kvm_arch_flush_shadow_memslot(kvm, slot);
 		kfree(old_memslots);
 	}
 
@@ -832,7 +840,6 @@ int __kvm_set_memory_region(struct kvm *kvm,
 
 	/* actual memory is freed via old in kvm_free_physmem_slot below */
 	if (!npages) {
-		new.rmap = NULL;
 		new.dirty_bitmap = NULL;
 		memset(&new.arch, 0, sizeof(new.arch));
 	}
@@ -844,13 +851,6 @@ int __kvm_set_memory_region(struct kvm *kvm,
 
 	kvm_arch_commit_memory_region(kvm, mem, old, user_alloc);
 
-	/*
-	 * If the new memory slot is created, we need to clear all
-	 * mmio sptes.
-	 */
-	if (npages && old.base_gfn != mem->guest_phys_addr >> PAGE_SHIFT)
-		kvm_arch_flush_shadow(kvm);
-
 	kvm_free_physmem_slot(&old, &new);
 	kfree(old_memslots);
 
@@ -932,53 +932,6 @@ void kvm_disable_largepages(void)
 }
 EXPORT_SYMBOL_GPL(kvm_disable_largepages);
 
-int is_error_page(struct page *page)
-{
-	return page == bad_page || page == hwpoison_page || page == fault_page;
-}
-EXPORT_SYMBOL_GPL(is_error_page);
-
-int is_error_pfn(pfn_t pfn)
-{
-	return pfn == bad_pfn || pfn == hwpoison_pfn || pfn == fault_pfn;
-}
-EXPORT_SYMBOL_GPL(is_error_pfn);
-
-int is_hwpoison_pfn(pfn_t pfn)
-{
-	return pfn == hwpoison_pfn;
-}
-EXPORT_SYMBOL_GPL(is_hwpoison_pfn);
-
-int is_fault_pfn(pfn_t pfn)
-{
-	return pfn == fault_pfn;
-}
-EXPORT_SYMBOL_GPL(is_fault_pfn);
-
-int is_noslot_pfn(pfn_t pfn)
-{
-	return pfn == bad_pfn;
-}
-EXPORT_SYMBOL_GPL(is_noslot_pfn);
-
-int is_invalid_pfn(pfn_t pfn)
-{
-	return pfn == hwpoison_pfn || pfn == fault_pfn;
-}
-EXPORT_SYMBOL_GPL(is_invalid_pfn);
-
-static inline unsigned long bad_hva(void)
-{
-	return PAGE_OFFSET;
-}
-
-int kvm_is_error_hva(unsigned long addr)
-{
-	return addr == bad_hva();
-}
-EXPORT_SYMBOL_GPL(kvm_is_error_hva);
-
 struct kvm_memory_slot *gfn_to_memslot(struct kvm *kvm, gfn_t gfn)
 {
 	return __gfn_to_memslot(kvm_memslots(kvm), gfn);
@@ -1021,28 +974,62 @@ out:
 	return size;
 }
 
-static unsigned long gfn_to_hva_many(struct kvm_memory_slot *slot, gfn_t gfn,
-				     gfn_t *nr_pages)
+static bool memslot_is_readonly(struct kvm_memory_slot *slot)
+{
+	return slot->flags & KVM_MEM_READONLY;
+}
+
+static unsigned long __gfn_to_hva_many(struct kvm_memory_slot *slot, gfn_t gfn,
+				       gfn_t *nr_pages, bool write)
 {
 	if (!slot || slot->flags & KVM_MEMSLOT_INVALID)
-		return bad_hva();
+		return KVM_HVA_ERR_BAD;
+
+	if (memslot_is_readonly(slot) && write)
+		return KVM_HVA_ERR_RO_BAD;
 
 	if (nr_pages)
 		*nr_pages = slot->npages - (gfn - slot->base_gfn);
 
-	return gfn_to_hva_memslot(slot, gfn);
+	return __gfn_to_hva_memslot(slot, gfn);
 }
 
+static unsigned long gfn_to_hva_many(struct kvm_memory_slot *slot, gfn_t gfn,
+				     gfn_t *nr_pages)
+{
+	return __gfn_to_hva_many(slot, gfn, nr_pages, true);
+}
+
+unsigned long gfn_to_hva_memslot(struct kvm_memory_slot *slot,
+				 gfn_t gfn)
+{
+	return gfn_to_hva_many(slot, gfn, NULL);
+}
+EXPORT_SYMBOL_GPL(gfn_to_hva_memslot);
+
 unsigned long gfn_to_hva(struct kvm *kvm, gfn_t gfn)
 {
 	return gfn_to_hva_many(gfn_to_memslot(kvm, gfn), gfn, NULL);
 }
 EXPORT_SYMBOL_GPL(gfn_to_hva);
 
-static pfn_t get_fault_pfn(void)
+/*
+ * The hva returned by this function is only allowed to be read.
+ * It should pair with kvm_read_hva() or kvm_read_hva_atomic().
+ */
+static unsigned long gfn_to_hva_read(struct kvm *kvm, gfn_t gfn)
+{
+	return __gfn_to_hva_many(gfn_to_memslot(kvm, gfn), gfn, NULL, false);
+}
+
+static int kvm_read_hva(void *data, void __user *hva, int len)
 {
-	get_page(fault_page);
-	return fault_pfn;
+	return __copy_from_user(data, hva, len);
+}
+
+static int kvm_read_hva_atomic(void *data, void __user *hva, int len)
+{
+	return __copy_from_user_inatomic(data, hva, len);
 }
 
 int get_user_page_nowait(struct task_struct *tsk, struct mm_struct *mm,
@@ -1065,108 +1052,186 @@ static inline int check_user_page_hwpoison(unsigned long addr)
 	return rc == -EHWPOISON;
 }
 
-static pfn_t hva_to_pfn(struct kvm *kvm, unsigned long addr, bool atomic,
-			bool *async, bool write_fault, bool *writable)
+/*
+ * The atomic path to get the writable pfn which will be stored in @pfn,
+ * true indicates success, otherwise false is returned.
+ */
+static bool hva_to_pfn_fast(unsigned long addr, bool atomic, bool *async,
+			    bool write_fault, bool *writable, pfn_t *pfn)
 {
 	struct page *page[1];
-	int npages = 0;
-	pfn_t pfn;
+	int npages;
 
-	/* we can do it either atomically or asynchronously, not both */
-	BUG_ON(atomic && async);
+	if (!(async || atomic))
+		return false;
 
-	BUG_ON(!write_fault && !writable);
+	/*
+	 * Fast pin a writable pfn only if it is a write fault request
+	 * or the caller allows to map a writable pfn for a read fault
+	 * request.
+	 */
+	if (!(write_fault || writable))
+		return false;
 
-	if (writable)
-		*writable = true;
+	npages = __get_user_pages_fast(addr, 1, 1, page);
+	if (npages == 1) {
+		*pfn = page_to_pfn(page[0]);
 
-	if (atomic || async)
-		npages = __get_user_pages_fast(addr, 1, 1, page);
+		if (writable)
+			*writable = true;
+		return true;
+	}
 
-	if (unlikely(npages != 1) && !atomic) {
-		might_sleep();
+	return false;
+}
 
-		if (writable)
-			*writable = write_fault;
+/*
+ * The slow path to get the pfn of the specified host virtual address,
+ * 1 indicates success, -errno is returned if error is detected.
+ */
+static int hva_to_pfn_slow(unsigned long addr, bool *async, bool write_fault,
+			   bool *writable, pfn_t *pfn)
+{
+	struct page *page[1];
+	int npages = 0;
 
-		if (async) {
-			down_read(&current->mm->mmap_sem);
-			npages = get_user_page_nowait(current, current->mm,
-						     addr, write_fault, page);
-			up_read(&current->mm->mmap_sem);
-		} else
-			npages = get_user_pages_fast(addr, 1, write_fault,
-						     page);
-
-		/* map read fault as writable if possible */
-		if (unlikely(!write_fault) && npages == 1) {
-			struct page *wpage[1];
-
-			npages = __get_user_pages_fast(addr, 1, 1, wpage);
-			if (npages == 1) {
-				*writable = true;
-				put_page(page[0]);
-				page[0] = wpage[0];
-			}
-			npages = 1;
+	might_sleep();
+
+	if (writable)
+		*writable = write_fault;
+
+	if (async) {
+		down_read(&current->mm->mmap_sem);
+		npages = get_user_page_nowait(current, current->mm,
+					      addr, write_fault, page);
+		up_read(&current->mm->mmap_sem);
+	} else
+		npages = get_user_pages_fast(addr, 1, write_fault,
+					     page);
+	if (npages != 1)
+		return npages;
+
+	/* map read fault as writable if possible */
+	if (unlikely(!write_fault) && writable) {
+		struct page *wpage[1];
+
+		npages = __get_user_pages_fast(addr, 1, 1, wpage);
+		if (npages == 1) {
+			*writable = true;
+			put_page(page[0]);
+			page[0] = wpage[0];
 		}
+
+		npages = 1;
 	}
+	*pfn = page_to_pfn(page[0]);
+	return npages;
+}
 
-	if (unlikely(npages != 1)) {
-		struct vm_area_struct *vma;
+static bool vma_is_valid(struct vm_area_struct *vma, bool write_fault)
+{
+	if (unlikely(!(vma->vm_flags & VM_READ)))
+		return false;
 
-		if (atomic)
-			return get_fault_pfn();
+	if (write_fault && (unlikely(!(vma->vm_flags & VM_WRITE))))
+		return false;
 
-		down_read(&current->mm->mmap_sem);
-		if (npages == -EHWPOISON ||
-			(!async && check_user_page_hwpoison(addr))) {
-			up_read(&current->mm->mmap_sem);
-			get_page(hwpoison_page);
-			return page_to_pfn(hwpoison_page);
-		}
+	return true;
+}
 
-		vma = find_vma_intersection(current->mm, addr, addr+1);
-
-		if (vma == NULL)
-			pfn = get_fault_pfn();
-		else if ((vma->vm_flags & VM_PFNMAP)) {
-			pfn = ((addr - vma->vm_start) >> PAGE_SHIFT) +
-				vma->vm_pgoff;
-			BUG_ON(!kvm_is_mmio_pfn(pfn));
-		} else {
-			if (async && (vma->vm_flags & VM_WRITE))
-				*async = true;
-			pfn = get_fault_pfn();
-		}
-		up_read(&current->mm->mmap_sem);
-	} else
-		pfn = page_to_pfn(page[0]);
+/*
+ * Pin guest page in memory and return its pfn.
+ * @addr: host virtual address which maps memory to the guest
+ * @atomic: whether this function can sleep
+ * @async: whether this function need to wait IO complete if the
+ *         host page is not in the memory
+ * @write_fault: whether we should get a writable host page
+ * @writable: whether it allows to map a writable host page for !@write_fault
+ *
+ * The function will map a writable host page for these two cases:
+ * 1): @write_fault = true
+ * 2): @write_fault = false && @writable, @writable will tell the caller
+ *     whether the mapping is writable.
+ */
+static pfn_t hva_to_pfn(unsigned long addr, bool atomic, bool *async,
+			bool write_fault, bool *writable)
+{
+	struct vm_area_struct *vma;
+	pfn_t pfn = 0;
+	int npages;
+
+	/* we can do it either atomically or asynchronously, not both */
+	BUG_ON(atomic && async);
 
+	if (hva_to_pfn_fast(addr, atomic, async, write_fault, writable, &pfn))
+		return pfn;
+
+	if (atomic)
+		return KVM_PFN_ERR_FAULT;
+
+	npages = hva_to_pfn_slow(addr, async, write_fault, writable, &pfn);
+	if (npages == 1)
+		return pfn;
+
+	down_read(&current->mm->mmap_sem);
+	if (npages == -EHWPOISON ||
+	      (!async && check_user_page_hwpoison(addr))) {
+		pfn = KVM_PFN_ERR_HWPOISON;
+		goto exit;
+	}
+
+	vma = find_vma_intersection(current->mm, addr, addr + 1);
+
+	if (vma == NULL)
+		pfn = KVM_PFN_ERR_FAULT;
+	else if ((vma->vm_flags & VM_PFNMAP)) {
+		pfn = ((addr - vma->vm_start) >> PAGE_SHIFT) +
+			vma->vm_pgoff;
+		BUG_ON(!kvm_is_mmio_pfn(pfn));
+	} else {
+		if (async && vma_is_valid(vma, write_fault))
+			*async = true;
+		pfn = KVM_PFN_ERR_FAULT;
+	}
+exit:
+	up_read(&current->mm->mmap_sem);
 	return pfn;
 }
 
-pfn_t hva_to_pfn_atomic(struct kvm *kvm, unsigned long addr)
+static pfn_t
+__gfn_to_pfn_memslot(struct kvm_memory_slot *slot, gfn_t gfn, bool atomic,
+		     bool *async, bool write_fault, bool *writable)
 {
-	return hva_to_pfn(kvm, addr, true, NULL, true, NULL);
+	unsigned long addr = __gfn_to_hva_many(slot, gfn, NULL, write_fault);
+
+	if (addr == KVM_HVA_ERR_RO_BAD)
+		return KVM_PFN_ERR_RO_FAULT;
+
+	if (kvm_is_error_hva(addr))
+		return KVM_PFN_ERR_BAD;
+
+	/* Do not map writable pfn in the readonly memslot. */
+	if (writable && memslot_is_readonly(slot)) {
+		*writable = false;
+		writable = NULL;
+	}
+
+	return hva_to_pfn(addr, atomic, async, write_fault,
+			  writable);
 }
-EXPORT_SYMBOL_GPL(hva_to_pfn_atomic);
 
 static pfn_t __gfn_to_pfn(struct kvm *kvm, gfn_t gfn, bool atomic, bool *async,
 			  bool write_fault, bool *writable)
 {
-	unsigned long addr;
+	struct kvm_memory_slot *slot;
 
 	if (async)
 		*async = false;
 
-	addr = gfn_to_hva(kvm, gfn);
-	if (kvm_is_error_hva(addr)) {
-		get_page(bad_page);
-		return page_to_pfn(bad_page);
-	}
+	slot = gfn_to_memslot(kvm, gfn);
 
-	return hva_to_pfn(kvm, addr, atomic, async, write_fault, writable);
+	return __gfn_to_pfn_memslot(slot, gfn, atomic, async, write_fault,
+				    writable);
 }
 
 pfn_t gfn_to_pfn_atomic(struct kvm *kvm, gfn_t gfn)
@@ -1195,12 +1260,16 @@ pfn_t gfn_to_pfn_prot(struct kvm *kvm, gfn_t gfn, bool write_fault,
 }
 EXPORT_SYMBOL_GPL(gfn_to_pfn_prot);
 
-pfn_t gfn_to_pfn_memslot(struct kvm *kvm,
-			 struct kvm_memory_slot *slot, gfn_t gfn)
+pfn_t gfn_to_pfn_memslot(struct kvm_memory_slot *slot, gfn_t gfn)
+{
+	return __gfn_to_pfn_memslot(slot, gfn, false, NULL, true, NULL);
+}
+
+pfn_t gfn_to_pfn_memslot_atomic(struct kvm_memory_slot *slot, gfn_t gfn)
 {
-	unsigned long addr = gfn_to_hva_memslot(slot, gfn);
-	return hva_to_pfn(kvm, addr, false, NULL, true, NULL);
+	return __gfn_to_pfn_memslot(slot, gfn, true, NULL, true, NULL);
 }
+EXPORT_SYMBOL_GPL(gfn_to_pfn_memslot_atomic);
 
 int gfn_to_page_many_atomic(struct kvm *kvm, gfn_t gfn, struct page **pages,
 								  int nr_pages)
@@ -1219,30 +1288,42 @@ int gfn_to_page_many_atomic(struct kvm *kvm, gfn_t gfn, struct page **pages,
 }
 EXPORT_SYMBOL_GPL(gfn_to_page_many_atomic);
 
+static struct page *kvm_pfn_to_page(pfn_t pfn)
+{
+	if (is_error_pfn(pfn))
+		return KVM_ERR_PTR_BAD_PAGE;
+
+	if (kvm_is_mmio_pfn(pfn)) {
+		WARN_ON(1);
+		return KVM_ERR_PTR_BAD_PAGE;
+	}
+
+	return pfn_to_page(pfn);
+}
+
 struct page *gfn_to_page(struct kvm *kvm, gfn_t gfn)
 {
 	pfn_t pfn;
 
 	pfn = gfn_to_pfn(kvm, gfn);
-	if (!kvm_is_mmio_pfn(pfn))
-		return pfn_to_page(pfn);
-
-	WARN_ON(kvm_is_mmio_pfn(pfn));
 
-	get_page(bad_page);
-	return bad_page;
+	return kvm_pfn_to_page(pfn);
 }
 
 EXPORT_SYMBOL_GPL(gfn_to_page);
 
 void kvm_release_page_clean(struct page *page)
 {
+	WARN_ON(is_error_page(page));
+
 	kvm_release_pfn_clean(page_to_pfn(page));
 }
 EXPORT_SYMBOL_GPL(kvm_release_page_clean);
 
 void kvm_release_pfn_clean(pfn_t pfn)
 {
+	WARN_ON(is_error_pfn(pfn));
+
 	if (!kvm_is_mmio_pfn(pfn))
 		put_page(pfn_to_page(pfn));
 }
@@ -1250,6 +1331,8 @@ EXPORT_SYMBOL_GPL(kvm_release_pfn_clean);
 
 void kvm_release_page_dirty(struct page *page)
 {
+	WARN_ON(is_error_page(page));
+
 	kvm_release_pfn_dirty(page_to_pfn(page));
 }
 EXPORT_SYMBOL_GPL(kvm_release_page_dirty);
@@ -1305,10 +1388,10 @@ int kvm_read_guest_page(struct kvm *kvm, gfn_t gfn, void *data, int offset,
 	int r;
 	unsigned long addr;
 
-	addr = gfn_to_hva(kvm, gfn);
+	addr = gfn_to_hva_read(kvm, gfn);
 	if (kvm_is_error_hva(addr))
 		return -EFAULT;
-	r = __copy_from_user(data, (void __user *)addr + offset, len);
+	r = kvm_read_hva(data, (void __user *)addr + offset, len);
 	if (r)
 		return -EFAULT;
 	return 0;
@@ -1343,11 +1426,11 @@ int kvm_read_guest_atomic(struct kvm *kvm, gpa_t gpa, void *data,
 	gfn_t gfn = gpa >> PAGE_SHIFT;
 	int offset = offset_in_page(gpa);
 
-	addr = gfn_to_hva(kvm, gfn);
+	addr = gfn_to_hva_read(kvm, gfn);
 	if (kvm_is_error_hva(addr))
 		return -EFAULT;
 	pagefault_disable();
-	r = __copy_from_user_inatomic(data, (void __user *)addr + offset, len);
+	r = kvm_read_hva_atomic(data, (void __user *)addr + offset, len);
 	pagefault_enable();
 	if (r)
 		return -EFAULT;
@@ -1580,6 +1663,43 @@ bool kvm_vcpu_yield_to(struct kvm_vcpu *target)
 }
 EXPORT_SYMBOL_GPL(kvm_vcpu_yield_to);
 
+#ifdef CONFIG_HAVE_KVM_CPU_RELAX_INTERCEPT
+/*
+ * Helper that checks whether a VCPU is eligible for directed yield.
+ * Most eligible candidate to yield is decided by following heuristics:
+ *
+ *  (a) VCPU which has not done pl-exit or cpu relax intercepted recently
+ *  (preempted lock holder), indicated by @in_spin_loop.
+ *  Set at the beiginning and cleared at the end of interception/PLE handler.
+ *
+ *  (b) VCPU which has done pl-exit/ cpu relax intercepted but did not get
+ *  chance last time (mostly it has become eligible now since we have probably
+ *  yielded to lockholder in last iteration. This is done by toggling
+ *  @dy_eligible each time a VCPU checked for eligibility.)
+ *
+ *  Yielding to a recently pl-exited/cpu relax intercepted VCPU before yielding
+ *  to preempted lock-holder could result in wrong VCPU selection and CPU
+ *  burning. Giving priority for a potential lock-holder increases lock
+ *  progress.
+ *
+ *  Since algorithm is based on heuristics, accessing another VCPU data without
+ *  locking does not harm. It may result in trying to yield to  same VCPU, fail
+ *  and continue with next VCPU and so on.
+ */
+bool kvm_vcpu_eligible_for_directed_yield(struct kvm_vcpu *vcpu)
+{
+	bool eligible;
+
+	eligible = !vcpu->spin_loop.in_spin_loop ||
+			(vcpu->spin_loop.in_spin_loop &&
+			 vcpu->spin_loop.dy_eligible);
+
+	if (vcpu->spin_loop.in_spin_loop)
+		kvm_vcpu_set_dy_eligible(vcpu, !vcpu->spin_loop.dy_eligible);
+
+	return eligible;
+}
+#endif
 void kvm_vcpu_on_spin(struct kvm_vcpu *me)
 {
 	struct kvm *kvm = me->kvm;
@@ -1589,6 +1709,7 @@ void kvm_vcpu_on_spin(struct kvm_vcpu *me)
 	int pass;
 	int i;
 
+	kvm_vcpu_set_in_spin_loop(me, true);
 	/*
 	 * We boost the priority of a VCPU that is runnable but not
 	 * currently running, because it got preempted by something
@@ -1607,6 +1728,8 @@ void kvm_vcpu_on_spin(struct kvm_vcpu *me)
 				continue;
 			if (waitqueue_active(&vcpu->wq))
 				continue;
+			if (!kvm_vcpu_eligible_for_directed_yield(vcpu))
+				continue;
 			if (kvm_vcpu_yield_to(vcpu)) {
 				kvm->last_boosted_vcpu = i;
 				yielded = 1;
@@ -1614,6 +1737,10 @@ void kvm_vcpu_on_spin(struct kvm_vcpu *me)
 			}
 		}
 	}
+	kvm_vcpu_set_in_spin_loop(me, false);
+
+	/* Ensure vcpu is not eligible during next spinloop */
+	kvm_vcpu_set_dy_eligible(me, false);
 }
 EXPORT_SYMBOL_GPL(kvm_vcpu_on_spin);
 
@@ -1766,7 +1893,9 @@ static long kvm_vcpu_ioctl(struct file *filp,
 #endif
 
 
-	vcpu_load(vcpu);
+	r = vcpu_load(vcpu);
+	if (r)
+		return r;
 	switch (ioctl) {
 	case KVM_RUN:
 		r = -EINVAL;
@@ -2094,6 +2223,29 @@ static long kvm_vm_ioctl(struct file *filp,
 		break;
 	}
 #endif
+#ifdef __KVM_HAVE_IRQ_LINE
+	case KVM_IRQ_LINE_STATUS:
+	case KVM_IRQ_LINE: {
+		struct kvm_irq_level irq_event;
+
+		r = -EFAULT;
+		if (copy_from_user(&irq_event, argp, sizeof irq_event))
+			goto out;
+
+		r = kvm_vm_ioctl_irq_line(kvm, &irq_event);
+		if (r)
+			goto out;
+
+		r = -EFAULT;
+		if (ioctl == KVM_IRQ_LINE_STATUS) {
+			if (copy_to_user(argp, &irq_event, sizeof irq_event))
+				goto out;
+		}
+
+		r = 0;
+		break;
+	}
+#endif
 	default:
 		r = kvm_arch_vm_ioctl(filp, ioctl, arg);
 		if (r == -ENOTTY)
@@ -2698,9 +2850,6 @@ static struct syscore_ops kvm_syscore_ops = {
 	.resume = kvm_resume,
 };
 
-struct page *bad_page;
-pfn_t bad_pfn;
-
 static inline
 struct kvm_vcpu *preempt_notifier_to_vcpu(struct preempt_notifier *pn)
 {
@@ -2732,33 +2881,6 @@ int kvm_init(void *opaque, unsigned vcpu_size, unsigned vcpu_align,
 	if (r)
 		goto out_fail;
 
-	bad_page = alloc_page(GFP_KERNEL | __GFP_ZERO);
-
-	if (bad_page == NULL) {
-		r = -ENOMEM;
-		goto out;
-	}
-
-	bad_pfn = page_to_pfn(bad_page);
-
-	hwpoison_page = alloc_page(GFP_KERNEL | __GFP_ZERO);
-
-	if (hwpoison_page == NULL) {
-		r = -ENOMEM;
-		goto out_free_0;
-	}
-
-	hwpoison_pfn = page_to_pfn(hwpoison_page);
-
-	fault_page = alloc_page(GFP_KERNEL | __GFP_ZERO);
-
-	if (fault_page == NULL) {
-		r = -ENOMEM;
-		goto out_free_0;
-	}
-
-	fault_pfn = page_to_pfn(fault_page);
-
 	if (!zalloc_cpumask_var(&cpus_hardware_enabled, GFP_KERNEL)) {
 		r = -ENOMEM;
 		goto out_free_0;
@@ -2833,12 +2955,6 @@ out_free_1:
 out_free_0a:
 	free_cpumask_var(cpus_hardware_enabled);
 out_free_0:
-	if (fault_page)
-		__free_page(fault_page);
-	if (hwpoison_page)
-		__free_page(hwpoison_page);
-	__free_page(bad_page);
-out:
 	kvm_arch_exit();
 out_fail:
 	return r;
@@ -2858,8 +2974,5 @@ void kvm_exit(void)
 	kvm_arch_hardware_unsetup();
 	kvm_arch_exit();
 	free_cpumask_var(cpus_hardware_enabled);
-	__free_page(fault_page);
-	__free_page(hwpoison_page);
-	__free_page(bad_page);
 }
 EXPORT_SYMBOL_GPL(kvm_exit);