1 files changed, 93 insertions, 13 deletions

diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index 1192942aef91..d0788d0a72cc 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -1,9 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0-only
 /*
- * Kernel-based Virtual Machine driver for Linux
- *
- * This module enables machines with Intel VT-x extensions to run virtual
- * machines without emulation or binary translation.
+ * Kernel-based Virtual Machine (KVM) Hypervisor
  *
  * Copyright (C) 2006 Qumranet, Inc.
  * Copyright 2010 Red Hat, Inc. and/or its affiliates.
@@ -74,6 +71,7 @@
 #define ITOA_MAX_LEN 12
 
 MODULE_AUTHOR("Qumranet");
+MODULE_DESCRIPTION("Kernel-based Virtual Machine (KVM) Hypervisor");
 MODULE_LICENSE("GPL");
 
 /* Architectures should define their poll value according to the halt latency */
@@ -91,8 +89,8 @@ unsigned int halt_poll_ns_grow_start = 10000; /* 10us */
 module_param(halt_poll_ns_grow_start, uint, 0644);
 EXPORT_SYMBOL_GPL(halt_poll_ns_grow_start);
 
-/* Default resets per-vcpu halt_poll_ns . */
-unsigned int halt_poll_ns_shrink;
+/* Default halves per-vcpu halt_poll_ns. */
+unsigned int halt_poll_ns_shrink = 2;
 module_param(halt_poll_ns_shrink, uint, 0644);
 EXPORT_SYMBOL_GPL(halt_poll_ns_shrink);
 
@@ -110,8 +108,7 @@ static struct kmem_cache *kvm_vcpu_cache;
 static __read_mostly struct preempt_ops kvm_preempt_ops;
 static DEFINE_PER_CPU(struct kvm_vcpu *, kvm_running_vcpu);
 
-struct dentry *kvm_debugfs_dir;
-EXPORT_SYMBOL_GPL(kvm_debugfs_dir);
+static struct dentry *kvm_debugfs_dir;
 
 static const struct file_operations stat_fops_per_vm;
 
@@ -1145,8 +1142,7 @@ static struct kvm *kvm_create_vm(unsigned long type, const char *fdname)
 {
 	struct kvm *kvm = kvm_arch_alloc_vm();
 	struct kvm_memslots *slots;
-	int r = -ENOMEM;
-	int i, j;
+	int r, i, j;
 
 	if (!kvm)
 		return ERR_PTR(-ENOMEM);
@@ -1183,12 +1179,18 @@ static struct kvm *kvm_create_vm(unsigned long type, const char *fdname)
 	snprintf(kvm->stats_id, sizeof(kvm->stats_id), "kvm-%d",
 		 task_pid_nr(current));
 
+	r = -ENOMEM;
 	if (init_srcu_struct(&kvm->srcu))
 		goto out_err_no_srcu;
 	if (init_srcu_struct(&kvm->irq_srcu))
 		goto out_err_no_irq_srcu;
 
+	r = kvm_init_irq_routing(kvm);
+	if (r)
+		goto out_err_no_irq_routing;
+
 	refcount_set(&kvm->users_count, 1);
+
 	for (i = 0; i < kvm_arch_nr_memslot_as_ids(kvm); i++) {
 		for (j = 0; j < 2; j++) {
 			slots = &kvm->__memslots[i][j];
@@ -1206,6 +1208,7 @@ static struct kvm *kvm_create_vm(unsigned long type, const char *fdname)
 		rcu_assign_pointer(kvm->memslots[i], &kvm->__memslots[i][0]);
 	}
 
+	r = -ENOMEM;
 	for (i = 0; i < KVM_NR_BUSES; i++) {
 		rcu_assign_pointer(kvm->buses[i],
 			kzalloc(sizeof(struct kvm_io_bus), GFP_KERNEL_ACCOUNT));
@@ -1267,6 +1270,8 @@ out_err_no_arch_destroy_vm:
 	WARN_ON_ONCE(!refcount_dec_and_test(&kvm->users_count));
 	for (i = 0; i < KVM_NR_BUSES; i++)
 		kfree(kvm_get_bus(kvm, i));
+	kvm_free_irq_routing(kvm);
+out_err_no_irq_routing:
 	cleanup_srcu_struct(&kvm->irq_srcu);
 out_err_no_irq_srcu:
 	cleanup_srcu_struct(&kvm->srcu);
@@ -4202,12 +4207,21 @@ static void kvm_create_vcpu_debugfs(struct kvm_vcpu *vcpu)
 /*
  * Creates some virtual cpus.  Good luck creating more than one.
  */
-static int kvm_vm_ioctl_create_vcpu(struct kvm *kvm, u32 id)
+static int kvm_vm_ioctl_create_vcpu(struct kvm *kvm, unsigned long id)
 {
 	int r;
 	struct kvm_vcpu *vcpu;
 	struct page *page;
 
+	/*
+	 * KVM tracks vCPU IDs as 'int', be kind to userspace and reject
+	 * too-large values instead of silently truncating.
+	 *
+	 * Ensure KVM_MAX_VCPU_IDS isn't pushed above INT_MAX without first
+	 * changing the storage type (at the very least, IDs should be tracked
+	 * as unsigned ints).
+	 */
+	BUILD_BUG_ON(KVM_MAX_VCPU_IDS > INT_MAX);
 	if (id >= KVM_MAX_VCPU_IDS)
 		return -EINVAL;
 
@@ -4375,6 +4389,52 @@ static int kvm_vcpu_ioctl_get_stats_fd(struct kvm_vcpu *vcpu)
 	return fd;
 }
 
+#ifdef CONFIG_KVM_GENERIC_PRE_FAULT_MEMORY
+static int kvm_vcpu_pre_fault_memory(struct kvm_vcpu *vcpu,
+				     struct kvm_pre_fault_memory *range)
+{
+	int idx;
+	long r;
+	u64 full_size;
+
+	if (range->flags)
+		return -EINVAL;
+
+	if (!PAGE_ALIGNED(range->gpa) ||
+	    !PAGE_ALIGNED(range->size) ||
+	    range->gpa + range->size <= range->gpa)
+		return -EINVAL;
+
+	vcpu_load(vcpu);
+	idx = srcu_read_lock(&vcpu->kvm->srcu);
+
+	full_size = range->size;
+	do {
+		if (signal_pending(current)) {
+			r = -EINTR;
+			break;
+		}
+
+		r = kvm_arch_vcpu_pre_fault_memory(vcpu, range);
+		if (WARN_ON_ONCE(r == 0 || r == -EIO))
+			break;
+
+		if (r < 0)
+			break;
+
+		range->size -= r;
+		range->gpa += r;
+		cond_resched();
+	} while (range->size);
+
+	srcu_read_unlock(&vcpu->kvm->srcu, idx);
+	vcpu_put(vcpu);
+
+	/* Return success if at least one page was mapped successfully.  */
+	return full_size == range->size ? r : 0;
+}
+#endif
+
 static long kvm_vcpu_ioctl(struct file *filp,
 			   unsigned int ioctl, unsigned long arg)
 {
@@ -4421,7 +4481,10 @@ static long kvm_vcpu_ioctl(struct file *filp,
 				synchronize_rcu();
 			put_pid(oldpid);
 		}
+		vcpu->wants_to_run = !READ_ONCE(vcpu->run->immediate_exit__unsafe);
 		r = kvm_arch_vcpu_ioctl_run(vcpu);
+		vcpu->wants_to_run = false;
+
 		trace_kvm_userspace_exit(vcpu->run->exit_reason, r);
 		break;
 	}
@@ -4575,6 +4638,20 @@ out_free1:
 		r = kvm_vcpu_ioctl_get_stats_fd(vcpu);
 		break;
 	}
+#ifdef CONFIG_KVM_GENERIC_PRE_FAULT_MEMORY
+	case KVM_PRE_FAULT_MEMORY: {
+		struct kvm_pre_fault_memory range;
+
+		r = -EFAULT;
+		if (copy_from_user(&range, argp, sizeof(range)))
+			break;
+		r = kvm_vcpu_pre_fault_memory(vcpu, &range);
+		/* Pass back leftover range. */
+		if (copy_to_user(argp, &range, sizeof(range)))
+			r = -EFAULT;
+		break;
+	}
+#endif
 	default:
 		r = kvm_arch_vcpu_ioctl(filp, ioctl, arg);
 	}
@@ -6287,8 +6364,9 @@ static void kvm_sched_in(struct preempt_notifier *pn, int cpu)
 	WRITE_ONCE(vcpu->ready, false);
 
 	__this_cpu_write(kvm_running_vcpu, vcpu);
-	kvm_arch_sched_in(vcpu, cpu);
 	kvm_arch_vcpu_load(vcpu, cpu);
+
+	WRITE_ONCE(vcpu->scheduled_out, false);
 }
 
 static void kvm_sched_out(struct preempt_notifier *pn,
@@ -6296,7 +6374,9 @@ static void kvm_sched_out(struct preempt_notifier *pn,
 {
 	struct kvm_vcpu *vcpu = preempt_notifier_to_vcpu(pn);
 
-	if (current->on_rq) {
+	WRITE_ONCE(vcpu->scheduled_out, true);
+
+	if (current->on_rq && vcpu->wants_to_run) {
 		WRITE_ONCE(vcpu->preempted, true);
 		WRITE_ONCE(vcpu->ready, true);
 	}