Merge branch 'hyperv-fixes' of https://git.kernel.org/pub/scm/linux/kernel/git/hyperv/linux.git

drivers/hv/connection.c

@@ -72,7 +72,8 @@ module_param(max_version, uint, S_IRUGO);
 MODULE_PARM_DESC(max_version,
 		 "Maximal VMBus protocol version which can be negotiated");
 
-int vmbus_negotiate_version(struct vmbus_channel_msginfo *msginfo, u32 version)
+static int vmbus_try_connection_id(struct vmbus_channel_msginfo *msginfo,
+				   u32 version, u32 connection_id)
 {
 	int ret = 0;
 	struct vmbus_channel_initiate_contact *msg;
@@ -87,20 +88,20 @@ int vmbus_negotiate_version(struct vmbus_channel_msginfo *msginfo, u32 version)
 	msg->vmbus_version_requested = version;
 
 	/*
-	 * VMBus protocol 5.0 (VERSION_WIN10_V5) and higher require that we must
-	 * use VMBUS_MESSAGE_CONNECTION_ID_4 for the Initiate Contact Message,
-	 * and for subsequent messages, we must use the Message Connection ID
-	 * field in the host-returned Version Response Message. And, with
-	 * VERSION_WIN10_V5 and higher, we don't use msg->interrupt_page, but we
-	 * tell the host explicitly that we still use VMBUS_MESSAGE_SINT(2) for
-	 * compatibility.
+	 * For VMBus protocol 5.0 (VERSION_WIN10_V5) and higher, use the
+	 * caller-supplied connection_id for the Initiate Contact message so
+	 * the caller can implement the required retry scheme. For subsequent
+	 * messages, use the Message Connection ID field in the host-returned
+	 * Version Response message. With VERSION_WIN10_V5 and higher, we don't
+	 * use msg->interrupt_page, but tell the host explicitly that we still
+	 * use VMBUS_MESSAGE_SINT(2) for compatibility.
 	 *
 	 * On old hosts, we should always use VMBUS_MESSAGE_CONNECTION_ID (1).
 	 */
 	if (version >= VERSION_WIN10_V5) {
 		msg->msg_sint = VMBUS_MESSAGE_SINT;
 		msg->msg_vtl = ms_hyperv.vtl;
-		vmbus_connection.msg_conn_id = VMBUS_MESSAGE_CONNECTION_ID_4;
+		vmbus_connection.msg_conn_id = connection_id;
 	} else {
 		msg->interrupt_page = virt_to_phys(vmbus_connection.int_page);
 		vmbus_connection.msg_conn_id = VMBUS_MESSAGE_CONNECTION_ID;
@@ -165,6 +166,22 @@ int vmbus_negotiate_version(struct vmbus_channel_msginfo *msginfo, u32 version)
 	return ret;
 }
 
+int vmbus_negotiate_version(struct vmbus_channel_msginfo *msginfo, u32 version)
+{
+	int ret;
+
+	/* Try the redirect ID first for VTL2 with VMBus protocol 5.0+. */
+	if (version >= VERSION_WIN10_V5 && ms_hyperv.vtl == 2) {
+		ret = vmbus_try_connection_id(msginfo, version,
+					      VMBUS_MESSAGE_CONNECTION_ID_REDIRECT);
+		if (ret != -ENXIO)
+			return ret;
+	}
+
+	return vmbus_try_connection_id(msginfo, version,
+				       VMBUS_MESSAGE_CONNECTION_ID_4);
+}
+
 /*
  * vmbus_connect - Sends a connect request on the partition service connection
  */
@@ -457,18 +474,10 @@ int vmbus_post_msg(void *buffer, size_t buflen, bool can_sleep)
 
 		switch (ret) {
 		case HV_STATUS_INVALID_CONNECTION_ID:
-			/*
-			 * See vmbus_negotiate_version(): VMBus protocol 5.0
-			 * and higher require that we must use
-			 * VMBUS_MESSAGE_CONNECTION_ID_4 for the Initiate
-			 * Contact message, but on old hosts that only
-			 * support VMBus protocol 4.0 or lower, here we get
-			 * HV_STATUS_INVALID_CONNECTION_ID and we should
-			 * return an error immediately without retrying.
-			 */
+			/* Allow INITIATE_CONTACT to try another connection ID. */
 			hdr = buffer;
 			if (hdr->msgtype == CHANNELMSG_INITIATE_CONTACT)
-				return -EINVAL;
+				return -ENXIO;
 			/*
 			 * We could get this if we send messages too
 			 * frequently.

drivers/hv/hyperv_vmbus.h

@@ -110,6 +110,8 @@ struct hv_input_post_message {
 enum {
 	VMBUS_MESSAGE_CONNECTION_ID	= 1,
 	VMBUS_MESSAGE_CONNECTION_ID_4	= 4,
+	/* VTL2 redirect connection ID for INITIATE_CONTACT. */
+	VMBUS_MESSAGE_CONNECTION_ID_REDIRECT = 0x800074,
 	VMBUS_MESSAGE_PORT_ID		= 1,
 	VMBUS_EVENT_CONNECTION_ID	= 2,
 	VMBUS_EVENT_PORT_ID		= 2,

drivers/hv/mshv_eventfd.c

@@ -169,7 +169,14 @@ static int mshv_try_assert_irq_fast(struct mshv_irqfd *irqfd)
 		return -EOPNOTSUPP;
 #endif
 
-	vp = partition->pt_vp_array[irq->lapic_apic_id];
+	/*
+	 * Pairs with smp_store_release() in mshv_partition_ioctl_create_vp().
+	 * MSHV_IRQFD does not require the target lapic_apic_id to refer to an
+	 * existing VP, so this read can race a concurrent VP creation; the
+	 * acquire ensures that a non-NULL pointer implies the VP's
+	 * initialising stores are visible.
+	 */
+	vp = smp_load_acquire(&partition->pt_vp_array[irq->lapic_apic_id]);
 
 	if (!vp->vp_register_page)
 		return -EOPNOTSUPP;
@@ -284,7 +291,7 @@ static void mshv_irqfd_deactivate(struct mshv_irqfd *irqfd)
 	if (!mshv_irqfd_is_active(irqfd))
 		return;
 
-	hlist_del(&irqfd->irqfd_hnode);
+	hlist_del_init(&irqfd->irqfd_hnode);
 
 	queue_work(irqfd_cleanup_wq, &irqfd->irqfd_shutdown);
 }
@@ -473,18 +480,6 @@ static int mshv_irqfd_assign(struct mshv_partition *pt,
 	init_poll_funcptr(&irqfd->irqfd_polltbl, mshv_irqfd_queue_proc);
 
 	spin_lock_irq(&pt->pt_irqfds_lock);
-#if IS_ENABLED(CONFIG_X86)
-	if (args->flags & BIT(MSHV_IRQFD_BIT_RESAMPLE) &&
-	    !irqfd->irqfd_lapic_irq.lapic_control.level_triggered) {
-		/*
-		 * Resample Fd must be for level triggered interrupt
-		 * Otherwise return with failure
-		 */
-		spin_unlock_irq(&pt->pt_irqfds_lock);
-		ret = -EINVAL;
-		goto fail;
-	}
-#endif
 	ret = 0;
 	hlist_for_each_entry(tmp, &pt->pt_irqfds_list, irqfd_hnode) {
 		if (irqfd->irqfd_eventfd_ctx != tmp->irqfd_eventfd_ctx)
@@ -497,6 +492,21 @@ static int mshv_irqfd_assign(struct mshv_partition *pt,
 
 	idx = srcu_read_lock(&pt->pt_irq_srcu);
 	mshv_irqfd_update(pt, irqfd);
+
+#if IS_ENABLED(CONFIG_X86)
+	if (args->flags & BIT(MSHV_IRQFD_BIT_RESAMPLE) &&
+	    !irqfd->irqfd_lapic_irq.lapic_control.level_triggered) {
+		/*
+		 * Resample Fd must be for level triggered interrupt
+		 * Otherwise return with failure
+		 */
+		spin_unlock_irq(&pt->pt_irqfds_lock);
+		srcu_read_unlock(&pt->pt_irq_srcu, idx);
+		ret = -EINVAL;
+		goto fail;
+	}
+#endif
+
 	hlist_add_head(&irqfd->irqfd_hnode, &pt->pt_irqfds_list);
 	spin_unlock_irq(&pt->pt_irqfds_lock);
 
@@ -541,13 +551,14 @@ static int mshv_irqfd_deassign(struct mshv_partition *pt,
 	if (IS_ERR(eventfd))
 		return PTR_ERR(eventfd);
 
+	spin_lock_irq(&pt->pt_irqfds_lock);
 	hlist_for_each_entry_safe(irqfd, n, &pt->pt_irqfds_list,
 				  irqfd_hnode) {
 		if (irqfd->irqfd_eventfd_ctx == eventfd &&
 		    irqfd->irqfd_irqnum == args->gsi)
-
 			mshv_irqfd_deactivate(irqfd);
 	}
+	spin_unlock_irq(&pt->pt_irqfds_lock);
 
 	eventfd_ctx_put(eventfd);
 

drivers/hv/mshv_irq.c

@@ -51,7 +51,7 @@ int mshv_update_routing_table(struct mshv_partition *partition,
 		/*
 		 * Allow only one to one mapping between GSI and MSI routing.
 		 */
-		if (girq->guest_irq_num != 0) {
+		if (girq->girq_entry_valid) {
 			r = -EINVAL;
 			goto out;
 		}

drivers/hv/mshv_portid_table.c

@@ -40,12 +40,14 @@ mshv_port_table_fini(void)
 int
 mshv_portid_alloc(struct port_table_info *info)
 {
-	int ret = 0;
+	int ret;
 
+	idr_preload(GFP_KERNEL);
 	idr_lock(&port_table_idr);
 	ret = idr_alloc(&port_table_idr, info, PORTID_MIN,
-			PORTID_MAX, GFP_KERNEL);
+			PORTID_MAX, GFP_NOWAIT);
 	idr_unlock(&port_table_idr);
+	idr_preload_end();
 
 	return ret;
 }
@@ -60,8 +62,7 @@ mshv_portid_free(int port_id)
 	WARN_ON(!info);
 	idr_unlock(&port_table_idr);
 
-	synchronize_rcu();
-	kfree(info);
+	kfree_rcu(info, portbl_rcu);
 }
 
 int

drivers/hv/mshv_root_main.c

@@ -1072,6 +1072,8 @@ mshv_partition_ioctl_create_vp(struct mshv_partition *partition,
 	struct mshv_vp *vp;
 	struct page *intercept_msg_page, *register_page, *ghcb_page;
 	struct hv_stats_page *stats_pages[2];
+	struct file *file;
+	int fd;
 	long ret;
 
 	if (copy_from_user(&args, arg, sizeof(args)))
@@ -1117,8 +1119,10 @@ mshv_partition_ioctl_create_vp(struct mshv_partition *partition,
 		goto unmap_ghcb_page;
 
 	vp = kzalloc_obj(*vp);
-	if (!vp)
+	if (!vp) {
+		ret = -ENOMEM;
 		goto unmap_stats_pages;
+	}
 
 	vp->vp_partition = mshv_partition_get(partition);
 	if (!vp->vp_partition) {
@@ -1144,21 +1148,40 @@ mshv_partition_ioctl_create_vp(struct mshv_partition *partition,
 	if (ret)
 		goto put_partition;
 
-	/*
-	 * Keep anon_inode_getfd last: it installs fd in the file struct and
-	 * thus makes the state accessible in user space.
-	 */
-	ret = anon_inode_getfd("mshv_vp", &mshv_vp_fops, vp,
-			       O_RDWR | O_CLOEXEC);
-	if (ret < 0)
+	fd = get_unused_fd_flags(O_RDWR | O_CLOEXEC);
+	if (fd < 0) {
+		ret = fd;
 		goto remove_debugfs_vp;
+	}
+
+	file = anon_inode_getfile("mshv_vp", &mshv_vp_fops, vp,
+				  O_RDWR | O_CLOEXEC);
+	if (IS_ERR(file)) {
+		ret = PTR_ERR(file);
+		goto put_unused_vp_fd;
+	}
 
 	/* already exclusive with the partition mutex for all ioctls */
 	partition->pt_vp_count++;
-	partition->pt_vp_array[args.vp_index] = vp;
+	/*
+	 * Pairs with smp_load_acquire() in mshv_try_assert_irq_fast(), which
+	 * can run concurrently from an irqfd waker without holding pt_mutex.
+	 * The release ensures the VP's initialising stores are visible to any
+	 * reader that observes a non-NULL pointer in pt_vp_array.
+	 */
+	smp_store_release(&partition->pt_vp_array[args.vp_index], vp);
+
+	/*
+	 * fd_install() is the userspace-visibility commit point.  Must be the
+	 * last operation that can fail or be observed.
+	 */
+	fd_install(fd, file);
+	ret = fd;
 
 	goto out;
 
+put_unused_vp_fd:
+	put_unused_fd(fd);
 remove_debugfs_vp:
 	mshv_debugfs_vp_remove(vp);
 put_partition:

drivers/hv/mshv_vtl_main.c

@@ -129,6 +129,7 @@ mshv_ioctl_create_vtl(void __user *user_arg, struct device *module_dev)
 	file = anon_inode_getfile("mshv_vtl", &mshv_vtl_fops,
 				  vtl, O_RDWR);
 	if (IS_ERR(file)) {
+		put_unused_fd(fd);
 		kfree(vtl);
 		return PTR_ERR(file);
 	}
@@ -801,7 +802,7 @@ static vm_fault_t mshv_vtl_fault(struct vm_fault *vmf)
 	int cpu = vmf->pgoff & MSHV_PG_OFF_CPU_MASK;
 	int real_off = vmf->pgoff >> MSHV_REAL_OFF_SHIFT;
 
-	if (!cpu_online(cpu))
+	if (cpu >= nr_cpu_ids || !cpu_online(cpu))
 		return VM_FAULT_SIGBUS;
 	/*
 	 * CPU Hotplug is not supported in VTL2 in OpenHCL, where this kernel driver exists.
@@ -1148,12 +1149,22 @@ static int mshv_vtl_hvcall_call(struct mshv_vtl_hvcall_fd *fd,
 	 */
 	in = (void *)__get_free_page(GFP_KERNEL);
 	out = (void *)__get_free_page(GFP_KERNEL);
+	if (!in || !out) {
+		ret = -ENOMEM;
+		goto free_pages;
+	}
 
 	if (copy_from_user(in, (void __user *)hvcall.input_ptr, hvcall.input_size)) {
 		ret = -EFAULT;
 		goto free_pages;
 	}
 
+	/*
+	 * The caller supplies output_size, so clear the range copied back to
+	 * userspace in case the hypercall writes fewer bytes than requested.
+	 */
+	memset(out, 0, hvcall.output_size);
+
 	hvcall.status = hv_do_hypercall(hvcall.control, in, out);
 
 	if (copy_to_user((void __user *)hvcall.output_ptr, out, hvcall.output_size)) {

drivers/hv/vmbus_drv.c

@@ -1369,8 +1369,6 @@ static void run_vmbus_irqd(unsigned int cpu)
 	__vmbus_isr();
 }
 
-static bool vmbus_irq_initialized;
-
 static struct smp_hotplug_thread vmbus_irq_threads = {
 	.store                  = &vmbus_irqd,
 	.setup			= vmbus_irqd_setup,
@@ -1384,8 +1382,19 @@ void vmbus_isr(void)
 	if (IS_ENABLED(CONFIG_PREEMPT_RT)) {
 		vmbus_irqd_wake();
 	} else {
-		lockdep_hardirq_threaded();
+		static DEFINE_WAIT_OVERRIDE_MAP(vmbus_map, LD_WAIT_CONFIG);
+
+		/*
+		 * vmbus_isr is never force-threaded and always invoked at hard
+		 * IRQ level. __vmbus_isr() below can acquire a spinlock_t
+		 * which becomes a sleeping lock and must not be acquired in
+		 * this context. Therefore on PREEMPT_RT this will be threaded
+		 * via vmbus_irqd_wake(). On non-PREEMPT the annotation lets
+		 * lockdep know that acquiring a spinlock_t is not an issue.
+		 */
+		lock_map_acquire_try(&vmbus_map);
 		__vmbus_isr();
+		lock_map_release(&vmbus_map);
 	}
 }
 EXPORT_SYMBOL_FOR_MODULES(vmbus_isr, "mshv_vtl");
@@ -1486,11 +1495,10 @@ static int vmbus_bus_init(void)
 	 * the VMbus interrupt handler.
 	 */
 
-	if (IS_ENABLED(CONFIG_PREEMPT_RT) && !vmbus_irq_initialized) {
+	if (IS_ENABLED(CONFIG_PREEMPT_RT)) {
 		ret = smpboot_register_percpu_thread(&vmbus_irq_threads);
 		if (ret)
 			goto err_kthread;
-		vmbus_irq_initialized = true;
 	}
 
 	if (vmbus_irq == -1) {
@@ -1534,10 +1542,8 @@ err_connect:
 	else
 		free_percpu_irq(vmbus_irq, &vmbus_evt);
 err_setup:
-	if (IS_ENABLED(CONFIG_PREEMPT_RT) && vmbus_irq_initialized) {
+	if (IS_ENABLED(CONFIG_PREEMPT_RT))
 		smpboot_unregister_percpu_thread(&vmbus_irq_threads);
-		vmbus_irq_initialized = false;
-	}
 err_kthread:
 	bus_unregister(&hv_bus);
 	return ret;
@@ -2169,6 +2175,7 @@ int vmbus_device_register(struct hv_device *child_device_obj)
 	child_device_obj->device.dma_parms = &child_device_obj->dma_parms;
 	child_device_obj->device.dma_mask = &child_device_obj->dma_mask;
 	dma_set_mask(&child_device_obj->device, DMA_BIT_MASK(64));
+	dma_set_coherent_mask(&child_device_obj->device, DMA_BIT_MASK(64));
 
 	/*
 	 * Register with the LDM. This will kick off the driver/device
@@ -3034,10 +3041,9 @@ static void __exit vmbus_exit(void)
 		hv_remove_vmbus_handler();
 	else
 		free_percpu_irq(vmbus_irq, &vmbus_evt);
-	if (IS_ENABLED(CONFIG_PREEMPT_RT) && vmbus_irq_initialized) {
+	if (IS_ENABLED(CONFIG_PREEMPT_RT))
 		smpboot_unregister_percpu_thread(&vmbus_irq_threads);
-		vmbus_irq_initialized = false;
-	}
+
 	for_each_online_cpu(cpu) {
 		struct hv_per_cpu_context *hv_cpu
 			= per_cpu_ptr(hv_context.cpu_context, cpu);

include/hyperv/hvhdk_mini.h

@@ -184,8 +184,9 @@ enum hv_dynamic_processor_feature_property {
 
 struct hv_input_get_system_property {
 	u32 property_id; /* enum hv_system_property */
+	u32 reserved;
 	union {
-		u32 as_uint32;
+		u64 as_uint64;
 #if IS_ENABLED(CONFIG_X86)
 		/* enum hv_dynamic_processor_feature_property */
 		u32 hv_processor_feature;