1 files changed, 228 insertions, 75 deletions

diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 383df23514b9..2799c6660cce 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -451,35 +451,170 @@ static void kvm_mmu_notifier_invalidate_range(struct mmu_notifier *mn,
 	srcu_read_unlock(&kvm->srcu, idx);
 }
 
-static void kvm_mmu_notifier_change_pte(struct mmu_notifier *mn,
-					struct mm_struct *mm,
-					unsigned long address,
-					pte_t pte)
+typedef bool (*hva_handler_t)(struct kvm *kvm, struct kvm_gfn_range *range);
+
+typedef void (*on_lock_fn_t)(struct kvm *kvm, unsigned long start,
+			     unsigned long end);
+
+struct kvm_hva_range {
+	unsigned long start;
+	unsigned long end;
+	pte_t pte;
+	hva_handler_t handler;
+	on_lock_fn_t on_lock;
+	bool flush_on_ret;
+	bool may_block;
+};
+
+/*
+ * Use a dedicated stub instead of NULL to indicate that there is no callback
+ * function/handler.  The compiler technically can't guarantee that a real
+ * function will have a non-zero address, and so it will generate code to
+ * check for !NULL, whereas comparing against a stub will be elided at compile
+ * time (unless the compiler is getting long in the tooth, e.g. gcc 4.9).
+ */
+static void kvm_null_fn(void)
 {
-	struct kvm *kvm = mmu_notifier_to_kvm(mn);
-	int idx;
+
+}
+#define IS_KVM_NULL_FN(fn) ((fn) == (void *)kvm_null_fn)
+
+static __always_inline int __kvm_handle_hva_range(struct kvm *kvm,
+						  const struct kvm_hva_range *range)
+{
+	bool ret = false, locked = false;
+	struct kvm_gfn_range gfn_range;
+	struct kvm_memory_slot *slot;
+	struct kvm_memslots *slots;
+	int i, idx;
+
+	/* A null handler is allowed if and only if on_lock() is provided. */
+	if (WARN_ON_ONCE(IS_KVM_NULL_FN(range->on_lock) &&
+			 IS_KVM_NULL_FN(range->handler)))
+		return 0;
 
 	idx = srcu_read_lock(&kvm->srcu);
 
-	KVM_MMU_LOCK(kvm);
+	/* The on_lock() path does not yet support lock elision. */
+	if (!IS_KVM_NULL_FN(range->on_lock)) {
+		locked = true;
+		KVM_MMU_LOCK(kvm);
 
-	kvm->mmu_notifier_seq++;
+		range->on_lock(kvm, range->start, range->end);
+
+		if (IS_KVM_NULL_FN(range->handler))
+			goto out_unlock;
+	}
 
-	if (kvm_set_spte_hva(kvm, address, pte))
+	for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) {
+		slots = __kvm_memslots(kvm, i);
+		kvm_for_each_memslot(slot, slots) {
+			unsigned long hva_start, hva_end;
+
+			hva_start = max(range->start, slot->userspace_addr);
+			hva_end = min(range->end, slot->userspace_addr +
+						  (slot->npages << PAGE_SHIFT));
+			if (hva_start >= hva_end)
+				continue;
+
+			/*
+			 * To optimize for the likely case where the address
+			 * range is covered by zero or one memslots, don't
+			 * bother making these conditional (to avoid writes on
+			 * the second or later invocation of the handler).
+			 */
+			gfn_range.pte = range->pte;
+			gfn_range.may_block = range->may_block;
+
+			/*
+			 * {gfn(page) | page intersects with [hva_start, hva_end)} =
+			 * {gfn_start, gfn_start+1, ..., gfn_end-1}.
+			 */
+			gfn_range.start = hva_to_gfn_memslot(hva_start, slot);
+			gfn_range.end = hva_to_gfn_memslot(hva_end + PAGE_SIZE - 1, slot);
+			gfn_range.slot = slot;
+
+			if (!locked) {
+				locked = true;
+				KVM_MMU_LOCK(kvm);
+			}
+			ret |= range->handler(kvm, &gfn_range);
+		}
+	}
+
+	if (range->flush_on_ret && (ret || kvm->tlbs_dirty))
 		kvm_flush_remote_tlbs(kvm);
 
-	KVM_MMU_UNLOCK(kvm);
+out_unlock:
+	if (locked)
+		KVM_MMU_UNLOCK(kvm);
+
 	srcu_read_unlock(&kvm->srcu, idx);
+
+	/* The notifiers are averse to booleans. :-( */
+	return (int)ret;
 }
 
-static int kvm_mmu_notifier_invalidate_range_start(struct mmu_notifier *mn,
-					const struct mmu_notifier_range *range)
+static __always_inline int kvm_handle_hva_range(struct mmu_notifier *mn,
+						unsigned long start,
+						unsigned long end,
+						pte_t pte,
+						hva_handler_t handler)
 {
 	struct kvm *kvm = mmu_notifier_to_kvm(mn);
-	int need_tlb_flush = 0, idx;
+	const struct kvm_hva_range range = {
+		.start		= start,
+		.end		= end,
+		.pte		= pte,
+		.handler	= handler,
+		.on_lock	= (void *)kvm_null_fn,
+		.flush_on_ret	= true,
+		.may_block	= false,
+	};
+
+	return __kvm_handle_hva_range(kvm, &range);
+}
+
+static __always_inline int kvm_handle_hva_range_no_flush(struct mmu_notifier *mn,
+							 unsigned long start,
+							 unsigned long end,
+							 hva_handler_t handler)
+{
+	struct kvm *kvm = mmu_notifier_to_kvm(mn);
+	const struct kvm_hva_range range = {
+		.start		= start,
+		.end		= end,
+		.pte		= __pte(0),
+		.handler	= handler,
+		.on_lock	= (void *)kvm_null_fn,
+		.flush_on_ret	= false,
+		.may_block	= false,
+	};
+
+	return __kvm_handle_hva_range(kvm, &range);
+}
+static void kvm_mmu_notifier_change_pte(struct mmu_notifier *mn,
+					struct mm_struct *mm,
+					unsigned long address,
+					pte_t pte)
+{
+	struct kvm *kvm = mmu_notifier_to_kvm(mn);
+
+	trace_kvm_set_spte_hva(address);
 
-	idx = srcu_read_lock(&kvm->srcu);
-	KVM_MMU_LOCK(kvm);
+	/*
+	 * .change_pte() must be surrounded by .invalidate_range_{start,end}(),
+	 * and so always runs with an elevated notifier count.  This obviates
+	 * the need to bump the sequence count.
+	 */
+	WARN_ON_ONCE(!kvm->mmu_notifier_count);
+
+	kvm_handle_hva_range(mn, address, address + 1, pte, kvm_set_spte_gfn);
+}
+
+static void kvm_inc_notifier_count(struct kvm *kvm, unsigned long start,
+				   unsigned long end)
+{
 	/*
 	 * The count increase must become visible at unlock time as no
 	 * spte can be established without taking the mmu_lock and
@@ -487,8 +622,8 @@ static int kvm_mmu_notifier_invalidate_range_start(struct mmu_notifier *mn,
 	 */
 	kvm->mmu_notifier_count++;
 	if (likely(kvm->mmu_notifier_count == 1)) {
-		kvm->mmu_notifier_range_start = range->start;
-		kvm->mmu_notifier_range_end = range->end;
+		kvm->mmu_notifier_range_start = start;
+		kvm->mmu_notifier_range_end = end;
 	} else {
 		/*
 		 * Fully tracking multiple concurrent ranges has dimishing
@@ -500,28 +635,36 @@ static int kvm_mmu_notifier_invalidate_range_start(struct mmu_notifier *mn,
 		 * complete.
 		 */
 		kvm->mmu_notifier_range_start =
-			min(kvm->mmu_notifier_range_start, range->start);
+			min(kvm->mmu_notifier_range_start, start);
 		kvm->mmu_notifier_range_end =
-			max(kvm->mmu_notifier_range_end, range->end);
+			max(kvm->mmu_notifier_range_end, end);
 	}
-	need_tlb_flush = kvm_unmap_hva_range(kvm, range->start, range->end,
-					     range->flags);
-	/* we've to flush the tlb before the pages can be freed */
-	if (need_tlb_flush || kvm->tlbs_dirty)
-		kvm_flush_remote_tlbs(kvm);
-
-	KVM_MMU_UNLOCK(kvm);
-	srcu_read_unlock(&kvm->srcu, idx);
-
-	return 0;
 }
 
-static void kvm_mmu_notifier_invalidate_range_end(struct mmu_notifier *mn,
+static int kvm_mmu_notifier_invalidate_range_start(struct mmu_notifier *mn,
 					const struct mmu_notifier_range *range)
 {
 	struct kvm *kvm = mmu_notifier_to_kvm(mn);
+	const struct kvm_hva_range hva_range = {
+		.start		= range->start,
+		.end		= range->end,
+		.pte		= __pte(0),
+		.handler	= kvm_unmap_gfn_range,
+		.on_lock	= kvm_inc_notifier_count,
+		.flush_on_ret	= true,
+		.may_block	= mmu_notifier_range_blockable(range),
+	};
 
-	KVM_MMU_LOCK(kvm);
+	trace_kvm_unmap_hva_range(range->start, range->end);
+
+	__kvm_handle_hva_range(kvm, &hva_range);
+
+	return 0;
+}
+
+static void kvm_dec_notifier_count(struct kvm *kvm, unsigned long start,
+				   unsigned long end)
+{
 	/*
 	 * This sequence increase will notify the kvm page fault that
 	 * the page that is going to be mapped in the spte could have
@@ -535,7 +678,23 @@ static void kvm_mmu_notifier_invalidate_range_end(struct mmu_notifier *mn,
 	 * in conjunction with the smp_rmb in mmu_notifier_retry().
 	 */
 	kvm->mmu_notifier_count--;
-	KVM_MMU_UNLOCK(kvm);
+}
+
+static void kvm_mmu_notifier_invalidate_range_end(struct mmu_notifier *mn,
+					const struct mmu_notifier_range *range)
+{
+	struct kvm *kvm = mmu_notifier_to_kvm(mn);
+	const struct kvm_hva_range hva_range = {
+		.start		= range->start,
+		.end		= range->end,
+		.pte		= __pte(0),
+		.handler	= (void *)kvm_null_fn,
+		.on_lock	= kvm_dec_notifier_count,
+		.flush_on_ret	= false,
+		.may_block	= mmu_notifier_range_blockable(range),
+	};
+
+	__kvm_handle_hva_range(kvm, &hva_range);
 
 	BUG_ON(kvm->mmu_notifier_count < 0);
 }
@@ -545,20 +704,9 @@ static int kvm_mmu_notifier_clear_flush_young(struct mmu_notifier *mn,
 					      unsigned long start,
 					      unsigned long end)
 {
-	struct kvm *kvm = mmu_notifier_to_kvm(mn);
-	int young, idx;
+	trace_kvm_age_hva(start, end);
 
-	idx = srcu_read_lock(&kvm->srcu);
-	KVM_MMU_LOCK(kvm);
-
-	young = kvm_age_hva(kvm, start, end);
-	if (young)
-		kvm_flush_remote_tlbs(kvm);
-
-	KVM_MMU_UNLOCK(kvm);
-	srcu_read_unlock(&kvm->srcu, idx);
-
-	return young;
+	return kvm_handle_hva_range(mn, start, end, __pte(0), kvm_age_gfn);
 }
 
 static int kvm_mmu_notifier_clear_young(struct mmu_notifier *mn,
@@ -566,11 +714,8 @@ static int kvm_mmu_notifier_clear_young(struct mmu_notifier *mn,
 					unsigned long start,
 					unsigned long end)
 {
-	struct kvm *kvm = mmu_notifier_to_kvm(mn);
-	int young, idx;
+	trace_kvm_age_hva(start, end);
 
-	idx = srcu_read_lock(&kvm->srcu);
-	KVM_MMU_LOCK(kvm);
 	/*
 	 * Even though we do not flush TLB, this will still adversely
 	 * affect performance on pre-Haswell Intel EPT, where there is
@@ -584,27 +729,17 @@ static int kvm_mmu_notifier_clear_young(struct mmu_notifier *mn,
 	 * cadence. If we find this inaccurate, we might come up with a
 	 * more sophisticated heuristic later.
 	 */
-	young = kvm_age_hva(kvm, start, end);
-	KVM_MMU_UNLOCK(kvm);
-	srcu_read_unlock(&kvm->srcu, idx);
-
-	return young;
+	return kvm_handle_hva_range_no_flush(mn, start, end, kvm_age_gfn);
 }
 
 static int kvm_mmu_notifier_test_young(struct mmu_notifier *mn,
 				       struct mm_struct *mm,
 				       unsigned long address)
 {
-	struct kvm *kvm = mmu_notifier_to_kvm(mn);
-	int young, idx;
+	trace_kvm_test_age_hva(address);
 
-	idx = srcu_read_lock(&kvm->srcu);
-	KVM_MMU_LOCK(kvm);
-	young = kvm_test_age_hva(kvm, address);
-	KVM_MMU_UNLOCK(kvm);
-	srcu_read_unlock(&kvm->srcu, idx);
-
-	return young;
+	return kvm_handle_hva_range_no_flush(mn, address, address + 1,
+					     kvm_test_age_gfn);
 }
 
 static void kvm_mmu_notifier_release(struct mmu_notifier *mn,
@@ -3002,6 +3137,11 @@ static bool vcpu_dy_runnable(struct kvm_vcpu *vcpu)
 	return false;
 }
 
+bool __weak kvm_arch_dy_has_pending_interrupt(struct kvm_vcpu *vcpu)
+{
+	return false;
+}
+
 void kvm_vcpu_on_spin(struct kvm_vcpu *me, bool yield_to_kernel_mode)
 {
 	struct kvm *kvm = me->kvm;
@@ -3035,7 +3175,8 @@ void kvm_vcpu_on_spin(struct kvm_vcpu *me, bool yield_to_kernel_mode)
 			    !vcpu_dy_runnable(vcpu))
 				continue;
 			if (READ_ONCE(vcpu->preempted) && yield_to_kernel_mode &&
-				!kvm_arch_vcpu_in_kernel(vcpu))
+			    !kvm_arch_dy_has_pending_interrupt(vcpu) &&
+			    !kvm_arch_vcpu_in_kernel(vcpu))
 				continue;
 			if (!kvm_vcpu_eligible_for_directed_yield(vcpu))
 				continue;
@@ -3182,7 +3323,7 @@ static int kvm_vm_ioctl_create_vcpu(struct kvm *kvm, u32 id)
 	if (r)
 		goto vcpu_decrement;
 
-	vcpu = kmem_cache_zalloc(kvm_vcpu_cache, GFP_KERNEL);
+	vcpu = kmem_cache_zalloc(kvm_vcpu_cache, GFP_KERNEL_ACCOUNT);
 	if (!vcpu) {
 		r = -ENOMEM;
 		goto vcpu_decrement;
@@ -4062,6 +4203,12 @@ static struct file_operations kvm_vm_fops = {
 	KVM_COMPAT(kvm_vm_compat_ioctl),
 };
 
+bool file_is_kvm(struct file *file)
+{
+	return file && file->f_op == &kvm_vm_fops;
+}
+EXPORT_SYMBOL_GPL(file_is_kvm);
+
 static int kvm_dev_ioctl_create_vm(unsigned long type)
 {
 	int r;
@@ -4485,24 +4632,26 @@ int kvm_io_bus_register_dev(struct kvm *kvm, enum kvm_bus bus_idx, gpa_t addr,
 	return 0;
 }
 
-/* Caller must hold slots_lock. */
-void kvm_io_bus_unregister_dev(struct kvm *kvm, enum kvm_bus bus_idx,
-			       struct kvm_io_device *dev)
+int kvm_io_bus_unregister_dev(struct kvm *kvm, enum kvm_bus bus_idx,
+			      struct kvm_io_device *dev)
 {
 	int i, j;
 	struct kvm_io_bus *new_bus, *bus;
 
+	lockdep_assert_held(&kvm->slots_lock);
+
 	bus = kvm_get_bus(kvm, bus_idx);
 	if (!bus)
-		return;
+		return 0;
 
-	for (i = 0; i < bus->dev_count; i++)
+	for (i = 0; i < bus->dev_count; i++) {
 		if (bus->range[i].dev == dev) {
 			break;
 		}
+	}
 
 	if (i == bus->dev_count)
-		return;
+		return 0;
 
 	new_bus = kmalloc(struct_size(bus, range, bus->dev_count - 1),
 			  GFP_KERNEL_ACCOUNT);
@@ -4511,7 +4660,13 @@ void kvm_io_bus_unregister_dev(struct kvm *kvm, enum kvm_bus bus_idx,
 		new_bus->dev_count--;
 		memcpy(new_bus->range + i, bus->range + i + 1,
 				flex_array_size(new_bus, range, new_bus->dev_count - i));
-	} else {
+	}
+
+	rcu_assign_pointer(kvm->buses[bus_idx], new_bus);
+	synchronize_srcu_expedited(&kvm->srcu);
+
+	/* Destroy the old bus _after_ installing the (null) bus. */
+	if (!new_bus) {
 		pr_err("kvm: failed to shrink bus, removing it completely\n");
 		for (j = 0; j < bus->dev_count; j++) {
 			if (j == i)
@@ -4520,10 +4675,8 @@ void kvm_io_bus_unregister_dev(struct kvm *kvm, enum kvm_bus bus_idx,
 		}
 	}
 
-	rcu_assign_pointer(kvm->buses[bus_idx], new_bus);
-	synchronize_srcu_expedited(&kvm->srcu);
 	kfree(bus);
-	return;
+	return new_bus ? 0 : -ENOMEM;
 }
 
 struct kvm_io_device *kvm_io_bus_get_dev(struct kvm *kvm, enum kvm_bus bus_idx,