Merge tag 'kvm-x86-generic-6.11' of https://github.com/kvm-x86/linux into HEAD

KVM generic changes for 6.11

 - Enable halt poll shrinking by default, as Intel found it to be a clear win.

 - Setup empty IRQ routing when creating a VM to avoid having to synchronize
   SRCU when creating a split IRQCHIP on x86.

 - Rework the sched_in/out() paths to replace kvm_arch_sched_in() with a flag
   that arch code can use for hooking both sched_in() and sched_out().

 - Take the vCPU @id as an "unsigned long" instead of "u32" to avoid
   truncating a bogus value from userspace, e.g. to help userspace detect bugs.

 - Mark a vCPU as preempted if and only if it's scheduled out while in the
   KVM_RUN loop, e.g. to avoid marking it preempted and thus writing guest
   memory when retrieving guest state during live migration blackout.

 - A few minor cleanups

virt/kvm/async_pf.c

@@ -80,7 +80,6 @@ static void async_pf_execute(struct work_struct *work)
 	spin_lock(&vcpu->async_pf.lock);
 	first = list_empty(&vcpu->async_pf.done);
 	list_add_tail(&apf->link, &vcpu->async_pf.done);
-	apf->vcpu = NULL;
 	spin_unlock(&vcpu->async_pf.lock);
 
 	/*
@@ -120,8 +119,6 @@ static void kvm_flush_and_free_async_pf_work(struct kvm_async_pf *work)
 
 void kvm_clear_async_pf_completion_queue(struct kvm_vcpu *vcpu)
 {
-	spin_lock(&vcpu->async_pf.lock);
-
 	/* cancel outstanding work queue item */
 	while (!list_empty(&vcpu->async_pf.queue)) {
 		struct kvm_async_pf *work =
@@ -129,23 +126,15 @@ void kvm_clear_async_pf_completion_queue(struct kvm_vcpu *vcpu)
 					 typeof(*work), queue);
 		list_del(&work->queue);
 
-		/*
-		 * We know it's present in vcpu->async_pf.done, do
-		 * nothing here.
-		 */
-		if (!work->vcpu)
-			continue;
-
-		spin_unlock(&vcpu->async_pf.lock);
 #ifdef CONFIG_KVM_ASYNC_PF_SYNC
 		flush_work(&work->work);
 #else
 		if (cancel_work_sync(&work->work))
 			kmem_cache_free(async_pf_cache, work);
 #endif
-		spin_lock(&vcpu->async_pf.lock);
 	}
 
+	spin_lock(&vcpu->async_pf.lock);
 	while (!list_empty(&vcpu->async_pf.done)) {
 		struct kvm_async_pf *work =
 			list_first_entry(&vcpu->async_pf.done,

virt/kvm/irqchip.c

@@ -237,3 +237,27 @@ out:
 
 	return r;
 }
+
+/*
+ * Allocate empty IRQ routing by default so that additional setup isn't needed
+ * when userspace-driven IRQ routing is activated, and so that kvm->irq_routing
+ * is guaranteed to be non-NULL.
+ */
+int kvm_init_irq_routing(struct kvm *kvm)
+{
+	struct kvm_irq_routing_table *new;
+	int chip_size;
+
+	new = kzalloc(struct_size(new, map, 1), GFP_KERNEL_ACCOUNT);
+	if (!new)
+		return -ENOMEM;
+
+	new->nr_rt_entries = 1;
+
+	chip_size = sizeof(int) * KVM_NR_IRQCHIPS * KVM_IRQCHIP_NUM_PINS;
+	memset(new->chip, -1, chip_size);
+
+	RCU_INIT_POINTER(kvm->irq_routing, new);
+
+	return 0;
+}

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;
 
@@ -4467,7 +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;
 	}
@@ -6347,8 +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,
@@ -6356,7 +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);
 	}