Drivers: hv: vmbus: Enable unloading of vmbus driver

index f518b8d7..3b18a66 100644
@@ -33,6 +33,7 @@
 #include <linux/hyperv.h>
 #include <linux/kernel_stat.h>
 #include <linux/clockchips.h>
+#include <linux/cpu.h>
 #include <asm/hyperv.h>
 #include <asm/hypervisor.h>
 #include <asm/mshyperv.h>

@@ -704,6 +705,39 @@ static void vmbus_isr(void)
 	}
 }
 
+#ifdef CONFIG_HOTPLUG_CPU
+static int hyperv_cpu_disable(void)
+{
+	return -ENOSYS;
+}
+
+static void hv_cpu_hotplug_quirk(bool vmbus_loaded)
+{
+	static void *previous_cpu_disable;
+
+	/*
+	 * Offlining a CPU when running on newer hypervisors (WS2012R2, Win8,
+	 * ...) is not supported at this moment as channel interrupts are
+	 * distributed across all of them.
+	 */
+
+	if ((vmbus_proto_version == VERSION_WS2008) ||
+	    (vmbus_proto_version == VERSION_WIN7))
+		return;
+
+	if (vmbus_loaded) {
+		previous_cpu_disable = smp_ops.cpu_disable;
+		smp_ops.cpu_disable = hyperv_cpu_disable;
+		pr_notice("CPU offlining is not supported by hypervisor\n");
+	} else if (previous_cpu_disable)
+		smp_ops.cpu_disable = previous_cpu_disable;
+}
+#else
+static void hv_cpu_hotplug_quirk(bool vmbus_loaded)
+{
+}
+#endif
+
 /*
  * vmbus_bus_init -Main vmbus driver initialization routine.
  *

@@ -744,6 +778,7 @@ static int vmbus_bus_init(int irq)
 	if (ret)
 		goto err_alloc;
 
+	hv_cpu_hotplug_quirk(true);
 	vmbus_request_offers();
 
 	return 0;

@@ -997,6 +1032,7 @@ static void __exit vmbus_exit(void)
 	bus_unregister(&hv_bus);
 	hv_cleanup();
 	acpi_bus_unregister_driver(&vmbus_acpi_driver);
+	hv_cpu_hotplug_quirk(false);
 }
 
 

index 3736f71..ba4b25f 100644
@@ -139,19 +139,22 @@ EXPORT_SYMBOL_GPL(vmbus_prep_negotiate_resp);
  */
 static struct vmbus_channel *alloc_channel(void)
 {
+	static atomic_t chan_num = ATOMIC_INIT(0);
 	struct vmbus_channel *channel;
 
 	channel = kzalloc(sizeof(*channel), GFP_ATOMIC);
 	if (!channel)
 		return NULL;
 
+	channel->id = atomic_inc_return(&chan_num);
 	spin_lock_init(&channel->inbound_lock);
 	spin_lock_init(&channel->lock);
 
 	INIT_LIST_HEAD(&channel->sc_list);
 	INIT_LIST_HEAD(&channel->percpu_list);
 
-	channel->controlwq = create_workqueue("hv_vmbus_ctl");
+	channel->controlwq = alloc_workqueue("hv_vmbus_ctl/%d", WQ_MEM_RECLAIM,
+					     1, channel->id);
 	if (!channel->controlwq) {
 		kfree(channel);
 		return NULL;

index 3b18a66..e334ccc 100644
@@ -875,10 +875,8 @@ int vmbus_device_register(struct hv_device *child_device_obj)
 {
 	int ret = 0;
 
-	static atomic_t device_num = ATOMIC_INIT(0);
-
-	dev_set_name(&child_device_obj->device, "vmbus_0_%d",
-		     atomic_inc_return(&device_num));
+	dev_set_name(&child_device_obj->device, "vmbus_%d",
+		     child_device_obj->channel->id);
 
 	child_device_obj->device.bus = &hv_bus;
 	child_device_obj->device.parent = &hv_acpi_dev->dev;

index 5a2ba67..26a32b7 100644
@@ -646,6 +646,9 @@ struct hv_input_signal_event_buffer {
 };
 
 struct vmbus_channel {
+	/* Unique channel id */
+	int id;
+
 	struct list_head listentry;
 
 	struct hv_device *device_obj;

index e334ccc..aebc8fe 100644
@@ -45,10 +45,7 @@ static struct tasklet_struct msg_dpc;
 static struct completion probe_event;
 static int irq;
 
-struct resource hyperv_mmio = {
-	.name  = "hyperv mmio",
-	.flags = IORESOURCE_MEM,
-};
+struct resource *hyperv_mmio;
 EXPORT_SYMBOL_GPL(hyperv_mmio);
 
 static int vmbus_exists(void)

@@ -915,30 +912,98 @@ void vmbus_device_unregister(struct hv_device *device_obj)
 
 
 /*
- * VMBUS is an acpi enumerated device. Get the the information we
+ * VMBUS is an acpi enumerated device. Get the information we
  * need from DSDT.
  */
 
 static acpi_status vmbus_walk_resources(struct acpi_resource *res, void *ctx)
 {
+	resource_size_t start = 0;
+	resource_size_t end = 0;
+	struct resource *new_res;
+	struct resource **old_res = &hyperv_mmio;
+
 	switch (res->type) {
 	case ACPI_RESOURCE_TYPE_IRQ:
 		irq = res->data.irq.interrupts[0];
+		return AE_OK;
+
+	/*
+	 * "Address" descriptors are for bus windows. Ignore
+	 * "memory" descriptors, which are for registers on
+	 * devices.
+	 */
+	case ACPI_RESOURCE_TYPE_ADDRESS32:
+		start = res->data.address32.address.minimum;
+		end = res->data.address32.address.maximum;
 		break;
 
 	case ACPI_RESOURCE_TYPE_ADDRESS64:
-		hyperv_mmio.start = res->data.address64.address.minimum;
-		hyperv_mmio.end = res->data.address64.address.maximum;
+		start = res->data.address64.address.minimum;
+		end = res->data.address64.address.maximum;
 		break;
+
+	default:
+		/* Unused resource type */
+		return AE_OK;
+
 	}
+	/*
+	 * Ignore ranges that are below 1MB, as they're not
+	 * necessary or useful here.
+	*/
+	if (end < 0x100000)
+		return AE_OK;
+
+	new_res = kzalloc(sizeof(*new_res), GFP_ATOMIC);
+	if (!new_res)
+		return AE_NO_MEMORY;
+
+	new_res->name = "hyperv mmio";
+	new_res->flags = IORESOURCE_MEM;
+	new_res->start = start;
+	new_res->end = end;
+
+	do {
+		if (!*old_res) {
+			*old_res = new_res;
+			break;
+		}
+
+		if ((*old_res)->start > new_res->end) {
+			new_res->sibling = *old_res;
+			*old_res = new_res;
+			break;
+		}
+
+		old_res = &(*old_res)->sibling;
+
+	} while (1);
 
 	return AE_OK;
 }
 
+static int vmbus_acpi_remove(struct acpi_device *device)
+{
+	struct resource *cur_res;
+	struct resource *next_res;
+
+	if (hyperv_mmio) {
+		release_resource(hyperv_mmio);
+		for (cur_res = hyperv_mmio; cur_res; cur_res = next_res) {
+			next_res = cur_res->sibling;
+			kfree(cur_res);
+		}
+	}
+
+	return 0;
+}
+
 static int vmbus_acpi_add(struct acpi_device *device)
 {
 	acpi_status result;
 	int ret_val = -ENODEV;
+	struct acpi_device *ancestor;
 
 	hv_acpi_dev = device;
 

@@ -948,23 +1013,26 @@ static int vmbus_acpi_add(struct acpi_device *device)
 	if (ACPI_FAILURE(result))
 		goto acpi_walk_err;
 	/*
-	 * The parent of the vmbus acpi device (Gen2 firmware) is the VMOD that
-	 * has the mmio ranges. Get that.
+	 * Some ancestor of the vmbus acpi device (Gen1 or Gen2
+	 * firmware) is the VMOD that has the mmio ranges. Get that.
 	 */
-	if (device->parent) {
-		result = acpi_walk_resources(device->parent->handle,
+	for (ancestor = device->parent; ancestor; ancestor = ancestor->parent) {
+		result = acpi_walk_resources(ancestor->handle,
 					METHOD_NAME__CRS,
 					vmbus_walk_resources, NULL);
 
 		if (ACPI_FAILURE(result))
-			goto acpi_walk_err;
-		if (hyperv_mmio.start && hyperv_mmio.end)
-			request_resource(&iomem_resource, &hyperv_mmio);
+			continue;
+		if (hyperv_mmio) {
+			request_resource(&iomem_resource, hyperv_mmio);
+			break;
+		}
 	}
 	ret_val = 0;
 
 acpi_walk_err:
 	complete(&probe_event);
+	vmbus_acpi_remove(device);
 	return ret_val;
 }
 

@@ -980,6 +1048,7 @@ static struct acpi_driver vmbus_acpi_driver = {
 	.ids = vmbus_acpi_device_ids,
 	.ops = {
 		.add = vmbus_acpi_add,
+		.remove = vmbus_acpi_remove,
 	},
 };
 

index 4254336..003c8f0 100644
@@ -686,7 +686,7 @@ static int hvfb_getmem(struct fb_info *info)
 	par->mem.name = KBUILD_MODNAME;
 	par->mem.flags = IORESOURCE_MEM | IORESOURCE_BUSY;
 	if (gen2vm) {
-		ret = allocate_resource(&hyperv_mmio, &par->mem,
+		ret = allocate_resource(hyperv_mmio, &par->mem,
 					screen_fb_size,
 					0, -1,
 					screen_fb_size,

index 26a32b7..e73cfeb 100644
@@ -1217,7 +1217,7 @@ int hv_vss_init(struct hv_util_service *);
 void hv_vss_deinit(void);
 void hv_vss_onchannelcallback(void *);
 
-extern struct resource hyperv_mmio;
+extern struct resource *hyperv_mmio;
 
 /*
  * Negotiated version with the Host.

index ba4b25f..36bacc7 100644
@@ -262,7 +262,6 @@ void vmbus_free_channels(void)
 
 	list_for_each_entry(channel, &vmbus_connection.chn_list, listentry) {
 		vmbus_device_unregister(channel->device_obj);
-		kfree(channel->device_obj);
 		free_channel(channel);
 	}
 }

index a63a795..c4acd1c 100644
@@ -216,10 +216,21 @@ int vmbus_connect(void)
 
 cleanup:
 	pr_err("Unable to connect to host\n");
+
 	vmbus_connection.conn_state = DISCONNECTED;
+	vmbus_disconnect();
+
+	kfree(msginfo);
+
+	return ret;
+}
 
-	if (vmbus_connection.work_queue)
+void vmbus_disconnect(void)
+{
+	if (vmbus_connection.work_queue) {
+		drain_workqueue(vmbus_connection.work_queue);
 		destroy_workqueue(vmbus_connection.work_queue);
+	}
 
 	if (vmbus_connection.int_page) {
 		free_pages((unsigned long)vmbus_connection.int_page, 0);

@@ -230,10 +241,6 @@ cleanup:
 	free_pages((unsigned long)vmbus_connection.monitor_pages[1], 0);
 	vmbus_connection.monitor_pages[0] = NULL;
 	vmbus_connection.monitor_pages[1] = NULL;
-
-	kfree(msginfo);
-
-	return ret;
 }
 
 /*

index 44b1c94..6cf2de9 100644
@@ -692,6 +692,7 @@ void vmbus_free_channels(void);
 /* Connection interface */
 
 int vmbus_connect(void);
+void vmbus_disconnect(void);
 
 int vmbus_post_msg(void *buffer, size_t buflen);
 

index aebc8fe..3b304b9 100644
@@ -571,6 +571,10 @@ static void vmbus_onmessage_work(struct work_struct *work)
 {
 	struct onmessage_work_context *ctx;
 
+	/* Do not process messages if we're in DISCONNECTED state */
+	if (vmbus_connection.conn_state == DISCONNECTED)
+		return;
+
 	ctx = container_of(work, struct onmessage_work_context,
 			   work);
 	vmbus_onmessage(&ctx->msg);

@@ -1094,12 +1098,14 @@ cleanup:
 
 static void __exit vmbus_exit(void)
 {
+	vmbus_connection.conn_state = DISCONNECTED;
 	hv_remove_vmbus_irq();
 	vmbus_free_channels();
 	bus_unregister(&hv_bus);
 	hv_cleanup();
 	acpi_bus_unregister_driver(&vmbus_acpi_driver);
 	hv_cpu_hotplug_quirk(false);
+	vmbus_disconnect();
 }
 
 

index 50e51a5..39531dc 100644
@@ -477,6 +477,7 @@ void hv_synic_cleanup(void *arg)
 	union hv_synic_sint shared_sint;
 	union hv_synic_simp simp;
 	union hv_synic_siefp siefp;
+	union hv_synic_scontrol sctrl;
 	int cpu = smp_processor_id();
 
 	if (!hv_context.synic_initialized)

@@ -502,6 +503,10 @@ void hv_synic_cleanup(void *arg)
 
 	wrmsrl(HV_X64_MSR_SIEFP, siefp.as_uint64);
 
-	free_page((unsigned long)hv_context.synic_message_page[cpu]);
-	free_page((unsigned long)hv_context.synic_event_page[cpu]);
+	/* Disable the global synic bit */
+	rdmsrl(HV_X64_MSR_SCONTROL, sctrl.as_uint64);
+	sctrl.enable = 0;
+	wrmsrl(HV_X64_MSR_SCONTROL, sctrl.as_uint64);
+
+	hv_synic_free_cpu(cpu);
 }

index 3b304b9..8ff6f69 100644
@@ -1098,11 +1098,15 @@ cleanup:
 
 static void __exit vmbus_exit(void)
 {
+	int cpu;
+
 	vmbus_connection.conn_state = DISCONNECTED;
 	hv_remove_vmbus_irq();
 	vmbus_free_channels();
 	bus_unregister(&hv_bus);
 	hv_cleanup();
+	for_each_online_cpu(cpu)
+		smp_call_function_single(cpu, hv_synic_cleanup, NULL, 1);
 	acpi_bus_unregister_driver(&vmbus_acpi_driver);
 	hv_cpu_hotplug_quirk(false);
 	vmbus_disconnect();

index 5544990..888ecc1 100644
@@ -371,7 +371,7 @@ int clockevents_unbind_device(struct clock_event_device *ced, int cpu)
 	mutex_unlock(&clockevents_mutex);
 	return ret;
 }
-EXPORT_SYMBOL_GPL(clockevents_unbind);
+EXPORT_SYMBOL_GPL(clockevents_unbind_device);
 
 /**
  * clockevents_register_device - register a clock event device

index 39531dc..d3943bc 100644
@@ -312,7 +312,11 @@ static void hv_init_clockevent_device(struct clock_event_device *dev, int cpu)
 	dev->features = CLOCK_EVT_FEAT_ONESHOT;
 	dev->cpumask = cpumask_of(cpu);
 	dev->rating = 1000;
-	dev->owner = THIS_MODULE;
+	/*
+	 * Avoid settint dev->owner = THIS_MODULE deliberately as doing so will
+	 * result in clockevents_config_and_register() taking additional
+	 * references to the hv_vmbus module making it impossible to unload.
+	 */
 
 	dev->set_mode = hv_ce_setmode;
 	dev->set_next_event = hv_ce_set_next_event;

@@ -470,6 +474,20 @@ void hv_synic_init(void *arg)
 }
 
 /*
+ * hv_synic_clockevents_cleanup - Cleanup clockevent devices
+ */
+void hv_synic_clockevents_cleanup(void)
+{
+	int cpu;
+
+	if (!(ms_hyperv.features & HV_X64_MSR_SYNTIMER_AVAILABLE))
+		return;
+
+	for_each_online_cpu(cpu)
+		clockevents_unbind_device(hv_context.clk_evt[cpu], cpu);
+}
+
+/*
  * hv_synic_cleanup - Cleanup routine for hv_synic_init().
  */
 void hv_synic_cleanup(void *arg)

@@ -483,6 +501,11 @@ void hv_synic_cleanup(void *arg)
 	if (!hv_context.synic_initialized)
 		return;
 
+	/* Turn off clockevent device */
+	if (ms_hyperv.features & HV_X64_MSR_SYNTIMER_AVAILABLE)
+		hv_ce_setmode(CLOCK_EVT_MODE_SHUTDOWN,
+			      hv_context.clk_evt[cpu]);
+
 	rdmsrl(HV_X64_MSR_SINT0 + VMBUS_MESSAGE_SINT, shared_sint.as_uint64);
 
 	shared_sint.masked = 1;

index 6cf2de9..b055e53 100644
@@ -572,6 +572,8 @@ extern void hv_synic_init(void *irqarg);
 
 extern void hv_synic_cleanup(void *arg);
 
+extern void hv_synic_clockevents_cleanup(void);
+
 /*
  * Host version information.
  */

index 8ff6f69..2de170a 100644
@@ -1101,6 +1101,7 @@ static void __exit vmbus_exit(void)
 	int cpu;
 
 	vmbus_connection.conn_state = DISCONNECTED;
+	hv_synic_clockevents_cleanup();
 	hv_remove_vmbus_irq();
 	vmbus_free_channels();
 	bus_unregister(&hv_bus);