2 files changed, 230 insertions, 56 deletions

diff --git a/virt/kvm/arm/pmu.c b/virt/kvm/arm/pmu.c
index 362a01886bab..8731dfeced8b 100644
--- a/virt/kvm/arm/pmu.c
+++ b/virt/kvm/arm/pmu.c
@@ -8,6 +8,7 @@
 #include <linux/kvm.h>
 #include <linux/kvm_host.h>
 #include <linux/perf_event.h>
+#include <linux/perf/arm_pmu.h>
 #include <linux/uaccess.h>
 #include <asm/kvm_emulate.h>
 #include <kvm/arm_pmu.h>
@@ -146,8 +147,7 @@ u64 kvm_pmu_get_counter_value(struct kvm_vcpu *vcpu, u64 select_idx)
 	if (kvm_pmu_pmc_is_chained(pmc) &&
 	    kvm_pmu_idx_is_high_counter(select_idx))
 		counter = upper_32_bits(counter);
-
-	else if (!kvm_pmu_idx_is_64bit(vcpu, select_idx))
+	else if (select_idx != ARMV8_PMU_CYCLE_IDX)
 		counter = lower_32_bits(counter);
 
 	return counter;
@@ -193,7 +193,7 @@ static void kvm_pmu_release_perf_event(struct kvm_pmc *pmc)
  */
 static void kvm_pmu_stop_counter(struct kvm_vcpu *vcpu, struct kvm_pmc *pmc)
 {
-	u64 counter, reg;
+	u64 counter, reg, val;
 
 	pmc = kvm_pmu_get_canonical_pmc(pmc);
 	if (!pmc->perf_event)
@@ -201,16 +201,19 @@ static void kvm_pmu_stop_counter(struct kvm_vcpu *vcpu, struct kvm_pmc *pmc)
 
 	counter = kvm_pmu_get_pair_counter_value(vcpu, pmc);
 
-	if (kvm_pmu_pmc_is_chained(pmc)) {
-		reg = PMEVCNTR0_EL0 + pmc->idx;
-		__vcpu_sys_reg(vcpu, reg) = lower_32_bits(counter);
-		__vcpu_sys_reg(vcpu, reg + 1) = upper_32_bits(counter);
+	if (pmc->idx == ARMV8_PMU_CYCLE_IDX) {
+		reg = PMCCNTR_EL0;
+		val = counter;
 	} else {
-		reg = (pmc->idx == ARMV8_PMU_CYCLE_IDX)
-		       ? PMCCNTR_EL0 : PMEVCNTR0_EL0 + pmc->idx;
-		__vcpu_sys_reg(vcpu, reg) = lower_32_bits(counter);
+		reg = PMEVCNTR0_EL0 + pmc->idx;
+		val = lower_32_bits(counter);
 	}
 
+	__vcpu_sys_reg(vcpu, reg) = val;
+
+	if (kvm_pmu_pmc_is_chained(pmc))
+		__vcpu_sys_reg(vcpu, reg + 1) = upper_32_bits(counter);
+
 	kvm_pmu_release_perf_event(pmc);
 }
 
@@ -440,8 +443,25 @@ static void kvm_pmu_perf_overflow(struct perf_event *perf_event,
 				  struct pt_regs *regs)
 {
 	struct kvm_pmc *pmc = perf_event->overflow_handler_context;
+	struct arm_pmu *cpu_pmu = to_arm_pmu(perf_event->pmu);
 	struct kvm_vcpu *vcpu = kvm_pmc_to_vcpu(pmc);
 	int idx = pmc->idx;
+	u64 period;
+
+	cpu_pmu->pmu.stop(perf_event, PERF_EF_UPDATE);
+
+	/*
+	 * Reset the sample period to the architectural limit,
+	 * i.e. the point where the counter overflows.
+	 */
+	period = -(local64_read(&perf_event->count));
+
+	if (!kvm_pmu_idx_is_64bit(vcpu, pmc->idx))
+		period &= GENMASK(31, 0);
+
+	local64_set(&perf_event->hw.period_left, 0);
+	perf_event->attr.sample_period = period;
+	perf_event->hw.sample_period = period;
 
 	__vcpu_sys_reg(vcpu, PMOVSSET_EL0) |= BIT(idx);
 
@@ -449,6 +469,8 @@ static void kvm_pmu_perf_overflow(struct perf_event *perf_event,
 		kvm_make_request(KVM_REQ_IRQ_PENDING, vcpu);
 		kvm_vcpu_kick(vcpu);
 	}
+
+	cpu_pmu->pmu.start(perf_event, PERF_EF_RELOAD);
 }
 
 /**
@@ -567,12 +589,12 @@ static void kvm_pmu_create_perf_event(struct kvm_vcpu *vcpu, u64 select_idx)
 		 * high counter.
 		 */
 		attr.sample_period = (-counter) & GENMASK(63, 0);
+		if (kvm_pmu_counter_is_enabled(vcpu, pmc->idx + 1))
+			attr.config1 |= PERF_ATTR_CFG1_KVM_PMU_CHAINED;
+
 		event = perf_event_create_kernel_counter(&attr, -1, current,
 							 kvm_pmu_perf_overflow,
 							 pmc + 1);
-
-		if (kvm_pmu_counter_is_enabled(vcpu, pmc->idx + 1))
-			attr.config1 |= PERF_ATTR_CFG1_KVM_PMU_CHAINED;
 	} else {
 		/* The initial sample period (overflow count) of an event. */
 		if (kvm_pmu_idx_is_64bit(vcpu, pmc->idx))
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index fd68fbe0a75d..13efc291b1c7 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -50,6 +50,7 @@
 #include <linux/bsearch.h>
 #include <linux/io.h>
 #include <linux/lockdep.h>
+#include <linux/kthread.h>
 
 #include <asm/processor.h>
 #include <asm/ioctl.h>
@@ -121,9 +122,22 @@ static long kvm_vcpu_compat_ioctl(struct file *file, unsigned int ioctl,
 				  unsigned long arg);
 #define KVM_COMPAT(c)	.compat_ioctl	= (c)
 #else
+/*
+ * For architectures that don't implement a compat infrastructure,
+ * adopt a double line of defense:
+ * - Prevent a compat task from opening /dev/kvm
+ * - If the open has been done by a 64bit task, and the KVM fd
+ *   passed to a compat task, let the ioctls fail.
+ */
 static long kvm_no_compat_ioctl(struct file *file, unsigned int ioctl,
 				unsigned long arg) { return -EINVAL; }
-#define KVM_COMPAT(c)	.compat_ioctl	= kvm_no_compat_ioctl
+
+static int kvm_no_compat_open(struct inode *inode, struct file *file)
+{
+	return is_compat_task() ? -ENODEV : 0;
+}
+#define KVM_COMPAT(c)	.compat_ioctl	= kvm_no_compat_ioctl,	\
+			.open		= kvm_no_compat_open
 #endif
 static int hardware_enable_all(void);
 static void hardware_disable_all(void);
@@ -149,10 +163,30 @@ __weak int kvm_arch_mmu_notifier_invalidate_range(struct kvm *kvm,
 	return 0;
 }
 
+bool kvm_is_zone_device_pfn(kvm_pfn_t pfn)
+{
+	/*
+	 * The metadata used by is_zone_device_page() to determine whether or
+	 * not a page is ZONE_DEVICE is guaranteed to be valid if and only if
+	 * the device has been pinned, e.g. by get_user_pages().  WARN if the
+	 * page_count() is zero to help detect bad usage of this helper.
+	 */
+	if (!pfn_valid(pfn) || WARN_ON_ONCE(!page_count(pfn_to_page(pfn))))
+		return false;
+
+	return is_zone_device_page(pfn_to_page(pfn));
+}
+
 bool kvm_is_reserved_pfn(kvm_pfn_t pfn)
 {
+	/*
+	 * ZONE_DEVICE pages currently set PG_reserved, but from a refcounting
+	 * perspective they are "normal" pages, albeit with slightly different
+	 * usage rules.
+	 */
 	if (pfn_valid(pfn))
-		return PageReserved(pfn_to_page(pfn));
+		return PageReserved(pfn_to_page(pfn)) &&
+		       !kvm_is_zone_device_pfn(pfn);
 
 	return true;
 }
@@ -625,10 +659,28 @@ static int kvm_create_vm_debugfs(struct kvm *kvm, int fd)
 	return 0;
 }
 
+/*
+ * Called after the VM is otherwise initialized, but just before adding it to
+ * the vm_list.
+ */
+int __weak kvm_arch_post_init_vm(struct kvm *kvm)
+{
+	return 0;
+}
+
+/*
+ * Called just after removing the VM from the vm_list, but before doing any
+ * other destruction.
+ */
+void __weak kvm_arch_pre_destroy_vm(struct kvm *kvm)
+{
+}
+
 static struct kvm *kvm_create_vm(unsigned long type)
 {
-	int r, i;
 	struct kvm *kvm = kvm_arch_alloc_vm();
+	int r = -ENOMEM;
+	int i;
 
 	if (!kvm)
 		return ERR_PTR(-ENOMEM);
@@ -640,46 +692,51 @@ static struct kvm *kvm_create_vm(unsigned long type)
 	mutex_init(&kvm->lock);
 	mutex_init(&kvm->irq_lock);
 	mutex_init(&kvm->slots_lock);
-	refcount_set(&kvm->users_count, 1);
 	INIT_LIST_HEAD(&kvm->devices);
 
-	r = kvm_arch_init_vm(kvm, type);
-	if (r)
-		goto out_err_no_disable;
-
-	r = hardware_enable_all();
-	if (r)
-		goto out_err_no_disable;
-
-#ifdef CONFIG_HAVE_KVM_IRQFD
-	INIT_HLIST_HEAD(&kvm->irq_ack_notifier_list);
-#endif
-
 	BUILD_BUG_ON(KVM_MEM_SLOTS_NUM > SHRT_MAX);
 
-	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;
+
+	refcount_set(&kvm->users_count, 1);
 	for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++) {
 		struct kvm_memslots *slots = kvm_alloc_memslots();
+
 		if (!slots)
-			goto out_err_no_srcu;
+			goto out_err_no_arch_destroy_vm;
 		/* Generations must be different for each address space. */
 		slots->generation = i;
 		rcu_assign_pointer(kvm->memslots[i], slots);
 	}
 
-	if (init_srcu_struct(&kvm->srcu))
-		goto out_err_no_srcu;
-	if (init_srcu_struct(&kvm->irq_srcu))
-		goto out_err_no_irq_srcu;
 	for (i = 0; i < KVM_NR_BUSES; i++) {
 		rcu_assign_pointer(kvm->buses[i],
 			kzalloc(sizeof(struct kvm_io_bus), GFP_KERNEL_ACCOUNT));
 		if (!kvm->buses[i])
-			goto out_err;
+			goto out_err_no_arch_destroy_vm;
 	}
 
+	r = kvm_arch_init_vm(kvm, type);
+	if (r)
+		goto out_err_no_arch_destroy_vm;
+
+	r = hardware_enable_all();
+	if (r)
+		goto out_err_no_disable;
+
+#ifdef CONFIG_HAVE_KVM_IRQFD
+	INIT_HLIST_HEAD(&kvm->irq_ack_notifier_list);
+#endif
+
 	r = kvm_init_mmu_notifier(kvm);
 	if (r)
+		goto out_err_no_mmu_notifier;
+
+	r = kvm_arch_post_init_vm(kvm);
+	if (r)
 		goto out_err;
 
 	mutex_lock(&kvm_lock);
@@ -691,17 +748,24 @@ static struct kvm *kvm_create_vm(unsigned long type)
 	return kvm;
 
 out_err:
-	cleanup_srcu_struct(&kvm->irq_srcu);
-out_err_no_irq_srcu:
-	cleanup_srcu_struct(&kvm->srcu);
-out_err_no_srcu:
+#if defined(CONFIG_MMU_NOTIFIER) && defined(KVM_ARCH_WANT_MMU_NOTIFIER)
+	if (kvm->mmu_notifier.ops)
+		mmu_notifier_unregister(&kvm->mmu_notifier, current->mm);
+#endif
+out_err_no_mmu_notifier:
 	hardware_disable_all();
 out_err_no_disable:
-	refcount_set(&kvm->users_count, 0);
+	kvm_arch_destroy_vm(kvm);
+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));
 	for (i = 0; i < KVM_ADDRESS_SPACE_NUM; i++)
 		kvm_free_memslots(kvm, __kvm_memslots(kvm, i));
+	cleanup_srcu_struct(&kvm->irq_srcu);
+out_err_no_irq_srcu:
+	cleanup_srcu_struct(&kvm->srcu);
+out_err_no_srcu:
 	kvm_arch_free_vm(kvm);
 	mmdrop(current->mm);
 	return ERR_PTR(r);
@@ -733,6 +797,8 @@ static void kvm_destroy_vm(struct kvm *kvm)
 	mutex_lock(&kvm_lock);
 	list_del(&kvm->vm_list);
 	mutex_unlock(&kvm_lock);
+	kvm_arch_pre_destroy_vm(kvm);
+
 	kvm_free_irq_routing(kvm);
 	for (i = 0; i < KVM_NR_BUSES; i++) {
 		struct kvm_io_bus *bus = kvm_get_bus(kvm, i);
@@ -1853,7 +1919,7 @@ EXPORT_SYMBOL_GPL(kvm_release_pfn_dirty);
 
 void kvm_set_pfn_dirty(kvm_pfn_t pfn)
 {
-	if (!kvm_is_reserved_pfn(pfn)) {
+	if (!kvm_is_reserved_pfn(pfn) && !kvm_is_zone_device_pfn(pfn)) {
 		struct page *page = pfn_to_page(pfn);
 
 		SetPageDirty(page);
@@ -1863,7 +1929,7 @@ EXPORT_SYMBOL_GPL(kvm_set_pfn_dirty);
 
 void kvm_set_pfn_accessed(kvm_pfn_t pfn)
 {
-	if (!kvm_is_reserved_pfn(pfn))
+	if (!kvm_is_reserved_pfn(pfn) && !kvm_is_zone_device_pfn(pfn))
 		mark_page_accessed(pfn_to_page(pfn));
 }
 EXPORT_SYMBOL_GPL(kvm_set_pfn_accessed);
@@ -2360,20 +2426,23 @@ out:
 	kvm_arch_vcpu_unblocking(vcpu);
 	block_ns = ktime_to_ns(cur) - ktime_to_ns(start);
 
-	if (!vcpu_valid_wakeup(vcpu))
-		shrink_halt_poll_ns(vcpu);
-	else if (halt_poll_ns) {
-		if (block_ns <= vcpu->halt_poll_ns)
-			;
-		/* we had a long block, shrink polling */
-		else if (vcpu->halt_poll_ns && block_ns > halt_poll_ns)
+	if (!kvm_arch_no_poll(vcpu)) {
+		if (!vcpu_valid_wakeup(vcpu)) {
 			shrink_halt_poll_ns(vcpu);
-		/* we had a short halt and our poll time is too small */
-		else if (vcpu->halt_poll_ns < halt_poll_ns &&
-			block_ns < halt_poll_ns)
-			grow_halt_poll_ns(vcpu);
-	} else
-		vcpu->halt_poll_ns = 0;
+		} else if (halt_poll_ns) {
+			if (block_ns <= vcpu->halt_poll_ns)
+				;
+			/* we had a long block, shrink polling */
+			else if (vcpu->halt_poll_ns && block_ns > halt_poll_ns)
+				shrink_halt_poll_ns(vcpu);
+			/* we had a short halt and our poll time is too small */
+			else if (vcpu->halt_poll_ns < halt_poll_ns &&
+				block_ns < halt_poll_ns)
+				grow_halt_poll_ns(vcpu);
+		} else {
+			vcpu->halt_poll_ns = 0;
+		}
+	}
 
 	trace_kvm_vcpu_wakeup(block_ns, waited, vcpu_valid_wakeup(vcpu));
 	kvm_arch_vcpu_block_finish(vcpu);
@@ -4364,3 +4433,86 @@ void kvm_exit(void)
 	kvm_vfio_ops_exit();
 }
 EXPORT_SYMBOL_GPL(kvm_exit);
+
+struct kvm_vm_worker_thread_context {
+	struct kvm *kvm;
+	struct task_struct *parent;
+	struct completion init_done;
+	kvm_vm_thread_fn_t thread_fn;
+	uintptr_t data;
+	int err;
+};
+
+static int kvm_vm_worker_thread(void *context)
+{
+	/*
+	 * The init_context is allocated on the stack of the parent thread, so
+	 * we have to locally copy anything that is needed beyond initialization
+	 */
+	struct kvm_vm_worker_thread_context *init_context = context;
+	struct kvm *kvm = init_context->kvm;
+	kvm_vm_thread_fn_t thread_fn = init_context->thread_fn;
+	uintptr_t data = init_context->data;
+	int err;
+
+	err = kthread_park(current);
+	/* kthread_park(current) is never supposed to return an error */
+	WARN_ON(err != 0);
+	if (err)
+		goto init_complete;
+
+	err = cgroup_attach_task_all(init_context->parent, current);
+	if (err) {
+		kvm_err("%s: cgroup_attach_task_all failed with err %d\n",
+			__func__, err);
+		goto init_complete;
+	}
+
+	set_user_nice(current, task_nice(init_context->parent));
+
+init_complete:
+	init_context->err = err;
+	complete(&init_context->init_done);
+	init_context = NULL;
+
+	if (err)
+		return err;
+
+	/* Wait to be woken up by the spawner before proceeding. */
+	kthread_parkme();
+
+	if (!kthread_should_stop())
+		err = thread_fn(kvm, data);
+
+	return err;
+}
+
+int kvm_vm_create_worker_thread(struct kvm *kvm, kvm_vm_thread_fn_t thread_fn,
+				uintptr_t data, const char *name,
+				struct task_struct **thread_ptr)
+{
+	struct kvm_vm_worker_thread_context init_context = {};
+	struct task_struct *thread;
+
+	*thread_ptr = NULL;
+	init_context.kvm = kvm;
+	init_context.parent = current;
+	init_context.thread_fn = thread_fn;
+	init_context.data = data;
+	init_completion(&init_context.init_done);
+
+	thread = kthread_run(kvm_vm_worker_thread, &init_context,
+			     "%s-%d", name, task_pid_nr(current));
+	if (IS_ERR(thread))
+		return PTR_ERR(thread);
+
+	/* kthread_run is never supposed to return NULL */
+	WARN_ON(thread == NULL);
+
+	wait_for_completion(&init_context.init_done);
+
+	if (!init_context.err)
+		*thread_ptr = thread;
+
+	return init_context.err;
+}