Merge tag 'hyperv-next-signed' of git://git.kernel.org/pub/scm/linux/kernel/git/hyperv/linux

Pull hyper-v updates from Wei Liu:

 - a series from Andrea to support channel reassignment

 - a series from Vitaly to clean up Vmbus message handling

 - a series from Michael to clean up and augment hyperv-tlfs.h

 - patches from Andy to clean up GUID usage in Hyper-V code

 - a few other misc patches

* tag 'hyperv-next-signed' of git://git.kernel.org/pub/scm/linux/kernel/git/hyperv/linux: (29 commits)
  Drivers: hv: vmbus: Resolve more races involving init_vp_index()
  Drivers: hv: vmbus: Resolve race between init_vp_index() and CPU hotplug
  vmbus: Replace zero-length array with flexible-array
  Driver: hv: vmbus: drop a no long applicable comment
  hyper-v: Switch to use UUID types directly
  hyper-v: Replace open-coded variant of %*phN specifier
  hyper-v: Supply GUID pointer to printf() like functions
  hyper-v: Use UUID API for exporting the GUID (part 2)
  asm-generic/hyperv: Add definitions for Get/SetVpRegister hypercalls
  x86/hyperv: Split hyperv-tlfs.h into arch dependent and independent files
  x86/hyperv: Remove HV_PROCESSOR_POWER_STATE #defines
  KVM: x86: hyperv: Remove duplicate definitions of Reference TSC Page
  drivers: hv: remove redundant assignment to pointer primary_channel
  scsi: storvsc: Re-init stor_chns when a channel interrupt is re-assigned
  Drivers: hv: vmbus: Introduce the CHANNELMSG_MODIFYCHANNEL message type
  Drivers: hv: vmbus: Synchronize init_vp_index() vs. CPU hotplug
  Drivers: hv: vmbus: Remove the unused HV_LOCALIZED channel affinity logic
  PCI: hv: Prepare hv_compose_msi_msg() for the VMBus-channel-interrupt-to-vCPU reassignment functionality
  Drivers: hv: vmbus: Use a spin lock for synchronizing channel scheduling vs. channel removal
  hv_utils: Always execute the fcopy and vss callbacks in a tasklet
  ...

MAINTAINERS

@@ -7924,6 +7924,7 @@ F:	drivers/pci/controller/pci-hyperv.c
 F:	drivers/scsi/storvsc_drv.c
 F:	drivers/uio/uio_hv_generic.c
 F:	drivers/video/fbdev/hyperv_fb.c
+F:	include/asm-generic/hyperv-tlfs.h
 F:	include/asm-generic/mshyperv.h
 F:	include/clocksource/hyperv_timer.h
 F:	include/linux/hyperv.h

arch/x86/include/asm/kvm_host.h

@@ -866,7 +866,7 @@ struct kvm_hv {
 	u64 hv_crash_param[HV_X64_MSR_CRASH_PARAMS];
 	u64 hv_crash_ctl;
 
-	HV_REFERENCE_TSC_PAGE tsc_ref;
+	struct ms_hyperv_tsc_page tsc_ref;
 
 	struct idr conn_to_evt;
 

arch/x86/kvm/hyperv.c

@@ -900,7 +900,7 @@ static int kvm_hv_msr_set_crash_data(struct kvm_vcpu *vcpu,
  * These two equivalencies are implemented in this function.
  */
 static bool compute_tsc_page_parameters(struct pvclock_vcpu_time_info *hv_clock,
-					HV_REFERENCE_TSC_PAGE *tsc_ref)
+					struct ms_hyperv_tsc_page *tsc_ref)
 {
 	u64 max_mul;
 
@@ -941,7 +941,7 @@ void kvm_hv_setup_tsc_page(struct kvm *kvm,
 	u64 gfn;
 
 	BUILD_BUG_ON(sizeof(tsc_seq) != sizeof(hv->tsc_ref.tsc_sequence));
-	BUILD_BUG_ON(offsetof(HV_REFERENCE_TSC_PAGE, tsc_sequence) != 0);
+	BUILD_BUG_ON(offsetof(struct ms_hyperv_tsc_page, tsc_sequence) != 0);
 
 	if (!(hv->hv_tsc_page & HV_X64_MSR_TSC_REFERENCE_ENABLE))
 		return;

drivers/hv/channel.c

@@ -289,6 +289,34 @@ int vmbus_send_tl_connect_request(const guid_t *shv_guest_servie_id,
 }
 EXPORT_SYMBOL_GPL(vmbus_send_tl_connect_request);
 
+/*
+ * Set/change the vCPU (@target_vp) the channel (@child_relid) will interrupt.
+ *
+ * CHANNELMSG_MODIFYCHANNEL messages are aynchronous.  Also, Hyper-V does not
+ * ACK such messages.  IOW we can't know when the host will stop interrupting
+ * the "old" vCPU and start interrupting the "new" vCPU for the given channel.
+ *
+ * The CHANNELMSG_MODIFYCHANNEL message type is supported since VMBus version
+ * VERSION_WIN10_V4_1.
+ */
+int vmbus_send_modifychannel(u32 child_relid, u32 target_vp)
+{
+	struct vmbus_channel_modifychannel conn_msg;
+	int ret;
+
+	memset(&conn_msg, 0, sizeof(conn_msg));
+	conn_msg.header.msgtype = CHANNELMSG_MODIFYCHANNEL;
+	conn_msg.child_relid = child_relid;
+	conn_msg.target_vp = target_vp;
+
+	ret = vmbus_post_msg(&conn_msg, sizeof(conn_msg), true);
+
+	trace_vmbus_send_modifychannel(&conn_msg, ret);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(vmbus_send_modifychannel);
+
 /*
  * create_gpadl_header - Creates a gpadl for the specified buffer
  */
@@ -594,35 +622,31 @@ int vmbus_teardown_gpadl(struct vmbus_channel *channel, u32 gpadl_handle)
 }
 EXPORT_SYMBOL_GPL(vmbus_teardown_gpadl);
 
-static void reset_channel_cb(void *arg)
-{
-	struct vmbus_channel *channel = arg;
-
-	channel->onchannel_callback = NULL;
-}
-
 void vmbus_reset_channel_cb(struct vmbus_channel *channel)
 {
+	unsigned long flags;
+
 	/*
 	 * vmbus_on_event(), running in the per-channel tasklet, can race
 	 * with vmbus_close_internal() in the case of SMP guest, e.g., when
 	 * the former is accessing channel->inbound.ring_buffer, the latter
 	 * could be freeing the ring_buffer pages, so here we must stop it
 	 * first.
+	 *
+	 * vmbus_chan_sched() might call the netvsc driver callback function
+	 * that ends up scheduling NAPI work that accesses the ring buffer.
+	 * At this point, we have to ensure that any such work is completed
+	 * and that the channel ring buffer is no longer being accessed, cf.
+	 * the calls to napi_disable() in netvsc_device_remove().
 	 */
 	tasklet_disable(&channel->callback_event);
 
-	channel->sc_creation_callback = NULL;
+	/* See the inline comments in vmbus_chan_sched(). */
+	spin_lock_irqsave(&channel->sched_lock, flags);
+	channel->onchannel_callback = NULL;
+	spin_unlock_irqrestore(&channel->sched_lock, flags);
 
-	/* Stop the callback asap */
-	if (channel->target_cpu != get_cpu()) {
-		put_cpu();
-		smp_call_function_single(channel->target_cpu, reset_channel_cb,
-					 channel, true);
-	} else {
-		reset_channel_cb(channel);
-		put_cpu();
-	}
+	channel->sc_creation_callback = NULL;
 
 	/* Re-enable tasklet for use on re-open */
 	tasklet_enable(&channel->callback_event);

drivers/hv/connection.c

@@ -69,7 +69,6 @@ MODULE_PARM_DESC(max_version,
 int vmbus_negotiate_version(struct vmbus_channel_msginfo *msginfo, u32 version)
 {
 	int ret = 0;
-	unsigned int cur_cpu;
 	struct vmbus_channel_initiate_contact *msg;
 	unsigned long flags;
 
@@ -102,24 +101,7 @@ int vmbus_negotiate_version(struct vmbus_channel_msginfo *msginfo, u32 version)
 
 	msg->monitor_page1 = virt_to_phys(vmbus_connection.monitor_pages[0]);
 	msg->monitor_page2 = virt_to_phys(vmbus_connection.monitor_pages[1]);
-	/*
-	 * We want all channel messages to be delivered on CPU 0.
-	 * This has been the behavior pre-win8. This is not
-	 * perf issue and having all channel messages delivered on CPU 0
-	 * would be ok.
-	 * For post win8 hosts, we support receiving channel messagges on
-	 * all the CPUs. This is needed for kexec to work correctly where
-	 * the CPU attempting to connect may not be CPU 0.
-	 */
-	if (version >= VERSION_WIN8_1) {
-		cur_cpu = get_cpu();
-		msg->target_vcpu = hv_cpu_number_to_vp_number(cur_cpu);
-		vmbus_connection.connect_cpu = cur_cpu;
-		put_cpu();
-	} else {
-		msg->target_vcpu = 0;
-		vmbus_connection.connect_cpu = 0;
-	}
+	msg->target_vcpu = hv_cpu_number_to_vp_number(VMBUS_CONNECT_CPU);
 
 	/*
 	 * Add to list before we send the request since we may
@@ -266,6 +248,14 @@ int vmbus_connect(void)
 	pr_info("Vmbus version:%d.%d\n",
 		version >> 16, version & 0xFFFF);
 
+	vmbus_connection.channels = kcalloc(MAX_CHANNEL_RELIDS,
+					    sizeof(struct vmbus_channel *),
+					    GFP_KERNEL);
+	if (vmbus_connection.channels == NULL) {
+		ret = -ENOMEM;
+		goto cleanup;
+	}
+
 	kfree(msginfo);
 	return 0;
 
@@ -313,33 +303,9 @@ void vmbus_disconnect(void)
  */
 struct vmbus_channel *relid2channel(u32 relid)
 {
-	struct vmbus_channel *channel;
-	struct vmbus_channel *found_channel  = NULL;
-	struct list_head *cur, *tmp;
-	struct vmbus_channel *cur_sc;
-
-	BUG_ON(!mutex_is_locked(&vmbus_connection.channel_mutex));
-
-	list_for_each_entry(channel, &vmbus_connection.chn_list, listentry) {
-		if (channel->offermsg.child_relid == relid) {
-			found_channel = channel;
-			break;
-		} else if (!list_empty(&channel->sc_list)) {
-			/*
-			 * Deal with sub-channels.
-			 */
-			list_for_each_safe(cur, tmp, &channel->sc_list) {
-				cur_sc = list_entry(cur, struct vmbus_channel,
-							sc_list);
-				if (cur_sc->offermsg.child_relid == relid) {
-					found_channel = cur_sc;
-					break;
-				}
-			}
-		}
-	}
-
-	return found_channel;
+	if (WARN_ON(relid >= MAX_CHANNEL_RELIDS))
+		return NULL;
+	return READ_ONCE(vmbus_connection.channels[relid]);
 }
 
 /*

drivers/hv/hv.c

@@ -117,8 +117,6 @@ int hv_synic_alloc(void)
 			pr_err("Unable to allocate post msg page\n");
 			goto err;
 		}
-
-		INIT_LIST_HEAD(&hv_cpu->chan_list);
 	}
 
 	return 0;
@@ -245,11 +243,19 @@ int hv_synic_cleanup(unsigned int cpu)
 	bool channel_found = false;
 	unsigned long flags;
 
+	/*
+	 * Hyper-V does not provide a way to change the connect CPU once
+	 * it is set; we must prevent the connect CPU from going offline.
+	 */
+	if (cpu == VMBUS_CONNECT_CPU)
+		return -EBUSY;
+
 	/*
 	 * Search for channels which are bound to the CPU we're about to
-	 * cleanup. In case we find one and vmbus is still connected we need to
-	 * fail, this will effectively prevent CPU offlining. There is no way
-	 * we can re-bind channels to different CPUs for now.
+	 * cleanup.  In case we find one and vmbus is still connected, we
+	 * fail; this will effectively prevent CPU offlining.
+	 *
+	 * TODO: Re-bind the channels to different CPUs.
 	 */
 	mutex_lock(&vmbus_connection.channel_mutex);
 	list_for_each_entry(channel, &vmbus_connection.chn_list, listentry) {

drivers/hv/hv_fcopy.c

@@ -71,7 +71,7 @@ static void fcopy_poll_wrapper(void *channel)
 {
 	/* Transaction is finished, reset the state here to avoid races. */
 	fcopy_transaction.state = HVUTIL_READY;
-	hv_fcopy_onchannelcallback(channel);
+	tasklet_schedule(&((struct vmbus_channel *)channel)->callback_event);
 }
 
 static void fcopy_timeout_func(struct work_struct *dummy)

drivers/hv/hv_snapshot.c

@@ -80,7 +80,7 @@ static void vss_poll_wrapper(void *channel)
 {
 	/* Transaction is finished, reset the state here to avoid races. */
 	vss_transaction.state = HVUTIL_READY;
-	hv_vss_onchannelcallback(channel);
+	tasklet_schedule(&((struct vmbus_channel *)channel)->callback_event);
 }
 
 /*

drivers/hv/hv_trace.h

@@ -44,10 +44,8 @@ TRACE_EVENT(vmbus_onoffer,
 			   __entry->monitorid = offer->monitorid;
 			   __entry->is_ddc_int = offer->is_dedicated_interrupt;
 			   __entry->connection_id = offer->connection_id;
-			   memcpy(__entry->if_type,
-				  &offer->offer.if_type.b, 16);
-			   memcpy(__entry->if_instance,
-				  &offer->offer.if_instance.b, 16);
+			   export_guid(__entry->if_type, &offer->offer.if_type);
+			   export_guid(__entry->if_instance, &offer->offer.if_instance);
 			   __entry->chn_flags = offer->offer.chn_flags;
 			   __entry->mmio_mb = offer->offer.mmio_megabytes;
 			   __entry->sub_idx = offer->offer.sub_channel_index;
@@ -296,6 +294,25 @@ TRACE_EVENT(vmbus_send_tl_connect_request,
 		    )
 	);
 
+TRACE_EVENT(vmbus_send_modifychannel,
+	    TP_PROTO(const struct vmbus_channel_modifychannel *msg,
+		     int ret),
+	    TP_ARGS(msg, ret),
+	    TP_STRUCT__entry(
+		    __field(u32, child_relid)
+		    __field(u32, target_vp)
+		    __field(int, ret)
+		    ),
+	    TP_fast_assign(
+		    __entry->child_relid = msg->child_relid;
+		    __entry->target_vp = msg->target_vp;
+		    __entry->ret = ret;
+		    ),
+	    TP_printk("binding child_relid 0x%x to target_vp 0x%x, ret %d",
+		      __entry->child_relid, __entry->target_vp, __entry->ret
+		    )
+	);
+
 DECLARE_EVENT_CLASS(vmbus_channel,
 	TP_PROTO(const struct vmbus_channel *channel),
 	TP_ARGS(channel),

drivers/hv/hyperv_vmbus.h

@@ -132,12 +132,6 @@ struct hv_per_cpu_context {
 	 * basis.
 	 */
 	struct tasklet_struct msg_dpc;
-
-	/*
-	 * To optimize the mapping of relid to channel, maintain
-	 * per-cpu list of the channels based on their CPU affinity.
-	 */
-	struct list_head chan_list;
 };
 
 struct hv_context {
@@ -202,6 +196,8 @@ int hv_ringbuffer_read(struct vmbus_channel *channel,
 /* TODO: Need to make this configurable */
 #define MAX_NUM_CHANNELS_SUPPORTED	256
 
+#define MAX_CHANNEL_RELIDS					\
+	max(MAX_NUM_CHANNELS_SUPPORTED, HV_EVENT_FLAGS_COUNT)
 
 enum vmbus_connect_state {
 	DISCONNECTED,
@@ -212,12 +208,13 @@ enum vmbus_connect_state {
 
 #define MAX_SIZE_CHANNEL_MESSAGE	HV_MESSAGE_PAYLOAD_BYTE_COUNT
 
-struct vmbus_connection {
-	/*
-	 * CPU on which the initial host contact was made.
-	 */
-	int connect_cpu;
+/*
+ * The CPU that Hyper-V will interrupt for VMBUS messages, such as
+ * CHANNELMSG_OFFERCHANNEL and CHANNELMSG_RESCIND_CHANNELOFFER.
+ */
+#define VMBUS_CONNECT_CPU	0
 
+struct vmbus_connection {
 	u32 msg_conn_id;
 
 	atomic_t offer_in_progress;
@@ -250,6 +247,9 @@ struct vmbus_connection {
 	struct list_head chn_list;
 	struct mutex channel_mutex;
 
+	/* Array of channels */
+	struct vmbus_channel **channels;
+
 	/*
 	 * An offer message is handled first on the work_queue, and then
 	 * is further handled on handle_primary_chan_wq or
@@ -317,6 +317,7 @@ struct vmbus_channel_message_table_entry {
 	enum vmbus_channel_message_type message_type;
 	enum vmbus_message_handler_type handler_type;
 	void (*message_handler)(struct vmbus_channel_message_header *msg);
+	u32 min_payload_len;
 };
 
 extern const struct vmbus_channel_message_table_entry
@@ -336,6 +337,9 @@ int vmbus_add_channel_kobj(struct hv_device *device_obj,
 
 void vmbus_remove_channel_attr_group(struct vmbus_channel *channel);
 
+void vmbus_channel_map_relid(struct vmbus_channel *channel);
+void vmbus_channel_unmap_relid(struct vmbus_channel *channel);
+
 struct vmbus_channel *relid2channel(u32 relid);
 
 void vmbus_free_channels(void);
@@ -374,12 +378,7 @@ static inline void hv_poll_channel(struct vmbus_channel *channel,
 {
 	if (!channel)
 		return;
-
-	if (in_interrupt() && (channel->target_cpu == smp_processor_id())) {
-		cb(channel);
-		return;
-	}
-	smp_call_function_single(channel->target_cpu, cb, channel, true);
+	cb(channel);
 }
 
 enum hvutil_device_state {
@@ -396,6 +395,54 @@ enum delay {
 	MESSAGE_DELAY   = 1,
 };
 
+extern const struct vmbus_device vmbus_devs[];
+
+static inline bool hv_is_perf_channel(struct vmbus_channel *channel)
+{
+	return vmbus_devs[channel->device_id].perf_device;
+}
+
+static inline bool hv_is_alloced_cpu(unsigned int cpu)
+{
+	struct vmbus_channel *channel, *sc;
+
+	lockdep_assert_held(&vmbus_connection.channel_mutex);
+	/*
+	 * List additions/deletions as well as updates of the target CPUs are
+	 * protected by channel_mutex.
+	 */
+	list_for_each_entry(channel, &vmbus_connection.chn_list, listentry) {
+		if (!hv_is_perf_channel(channel))
+			continue;
+		if (channel->target_cpu == cpu)
+			return true;
+		list_for_each_entry(sc, &channel->sc_list, sc_list) {
+			if (sc->target_cpu == cpu)
+				return true;
+		}
+	}
+	return false;
+}
+
+static inline void hv_set_alloced_cpu(unsigned int cpu)
+{
+	cpumask_set_cpu(cpu, &hv_context.hv_numa_map[cpu_to_node(cpu)]);
+}
+
+static inline void hv_clear_alloced_cpu(unsigned int cpu)
+{
+	if (hv_is_alloced_cpu(cpu))
+		return;
+	cpumask_clear_cpu(cpu, &hv_context.hv_numa_map[cpu_to_node(cpu)]);
+}
+
+static inline void hv_update_alloced_cpus(unsigned int old_cpu,
+					  unsigned int new_cpu)
+{
+	hv_set_alloced_cpu(new_cpu);
+	hv_clear_alloced_cpu(old_cpu);
+}
+
 #ifdef CONFIG_HYPERV_TESTING
 
 int hv_debug_add_dev_dir(struct hv_device *dev);

drivers/net/hyperv/netvsc.c

@@ -636,9 +636,12 @@ void netvsc_device_remove(struct hv_device *device)
 
 	RCU_INIT_POINTER(net_device_ctx->nvdev, NULL);
 
-	/* And disassociate NAPI context from device */
-	for (i = 0; i < net_device->num_chn; i++)
+	/* Disable NAPI and disassociate its context from the device. */
+	for (i = 0; i < net_device->num_chn; i++) {
+		/* See also vmbus_reset_channel_cb(). */
+		napi_disable(&net_device->chan_table[i].napi);
 		netif_napi_del(&net_device->chan_table[i].napi);
+	}
 
 	/*
 	 * At this point, no one should be accessing net_device

drivers/pci/controller/pci-hyperv.c

@@ -1356,11 +1356,11 @@ static void hv_compose_msi_msg(struct irq_data *data, struct msi_msg *msg)
 {
 	struct irq_cfg *cfg = irqd_cfg(data);
 	struct hv_pcibus_device *hbus;
+	struct vmbus_channel *channel;
 	struct hv_pci_dev *hpdev;
 	struct pci_bus *pbus;
 	struct pci_dev *pdev;
 	struct cpumask *dest;
-	unsigned long flags;
 	struct compose_comp_ctxt comp;
 	struct tran_int_desc *int_desc;
 	struct {
@@ -1378,6 +1378,7 @@ static void hv_compose_msi_msg(struct irq_data *data, struct msi_msg *msg)
 	dest = irq_data_get_effective_affinity_mask(data);
 	pbus = pdev->bus;
 	hbus = container_of(pbus->sysdata, struct hv_pcibus_device, sysdata);
+	channel = hbus->hdev->channel;
 	hpdev = get_pcichild_wslot(hbus, devfn_to_wslot(pdev->devfn));
 	if (!hpdev)
 		goto return_null_message;
@@ -1435,43 +1436,52 @@ static void hv_compose_msi_msg(struct irq_data *data, struct msi_msg *msg)
 		goto free_int_desc;
 	}
 
+	/*
+	 * Prevents hv_pci_onchannelcallback() from running concurrently
+	 * in the tasklet.
+	 */
+	tasklet_disable(&channel->callback_event);
+
 	/*
 	 * Since this function is called with IRQ locks held, can't
 	 * do normal wait for completion; instead poll.
 	 */
 	while (!try_wait_for_completion(&comp.comp_pkt.host_event)) {
+		unsigned long flags;
+
 		/* 0xFFFF means an invalid PCI VENDOR ID. */
 		if (hv_pcifront_get_vendor_id(hpdev) == 0xFFFF) {
 			dev_err_once(&hbus->hdev->device,
 				     "the device has gone\n");
-			goto free_int_desc;
+			goto enable_tasklet;
 		}
 
 		/*
-		 * When the higher level interrupt code calls us with
-		 * interrupt disabled, we must poll the channel by calling
-		 * the channel callback directly when channel->target_cpu is
-		 * the current CPU. When the higher level interrupt code
-		 * calls us with interrupt enabled, let's add the
-		 * local_irq_save()/restore() to avoid race:
-		 * hv_pci_onchannelcallback() can also run in tasklet.
+		 * Make sure that the ring buffer data structure doesn't get
+		 * freed while we dereference the ring buffer pointer.  Test
+		 * for the channel's onchannel_callback being NULL within a
+		 * sched_lock critical section.  See also the inline comments
+		 * in vmbus_reset_channel_cb().
 		 */
-		local_irq_save(flags);
-
-		if (hbus->hdev->channel->target_cpu == smp_processor_id())
-			hv_pci_onchannelcallback(hbus);
-
-		local_irq_restore(flags);
+		spin_lock_irqsave(&channel->sched_lock, flags);
+		if (unlikely(channel->onchannel_callback == NULL)) {
+			spin_unlock_irqrestore(&channel->sched_lock, flags);
+			goto enable_tasklet;
+		}
+		hv_pci_onchannelcallback(hbus);
+		spin_unlock_irqrestore(&channel->sched_lock, flags);
 
 		if (hpdev->state == hv_pcichild_ejecting) {
 			dev_err_once(&hbus->hdev->device,
 				     "the device is being ejected\n");
-			goto free_int_desc;
+			goto enable_tasklet;
 		}
 
 		udelay(100);
 	}
 
+	tasklet_enable(&channel->callback_event);
+
 	if (comp.comp_pkt.completion_status < 0) {
 		dev_err(&hbus->hdev->device,
 			"Request for interrupt failed: 0x%x",
@@ -1495,6 +1505,8 @@ static void hv_compose_msi_msg(struct irq_data *data, struct msi_msg *msg)
 	put_pcichild(hpdev);
 	return;
 
+enable_tasklet:
+	tasklet_enable(&channel->callback_event);
 free_int_desc:
 	kfree(int_desc);
 drop_reference:

drivers/scsi/storvsc_drv.c

@@ -621,6 +621,64 @@ static inline struct storvsc_device *get_in_stor_device(
 
 }
 
+static void storvsc_change_target_cpu(struct vmbus_channel *channel, u32 old,
+				      u32 new)
+{
+	struct storvsc_device *stor_device;
+	struct vmbus_channel *cur_chn;
+	bool old_is_alloced = false;
+	struct hv_device *device;
+	unsigned long flags;
+	int cpu;
+
+	device = channel->primary_channel ?
+			channel->primary_channel->device_obj
+				: channel->device_obj;
+	stor_device = get_out_stor_device(device);
+	if (!stor_device)
+		return;
+
+	/* See storvsc_do_io() -> get_og_chn(). */
+	spin_lock_irqsave(&device->channel->lock, flags);
+
+	/*
+	 * Determines if the storvsc device has other channels assigned to
+	 * the "old" CPU to update the alloced_cpus mask and the stor_chns
+	 * array.
+	 */
+	if (device->channel != channel && device->channel->target_cpu == old) {
+		cur_chn = device->channel;
+		old_is_alloced = true;
+		goto old_is_alloced;
+	}
+	list_for_each_entry(cur_chn, &device->channel->sc_list, sc_list) {
+		if (cur_chn == channel)
+			continue;
+		if (cur_chn->target_cpu == old) {
+			old_is_alloced = true;
+			goto old_is_alloced;
+		}
+	}
+
+old_is_alloced:
+	if (old_is_alloced)
+		WRITE_ONCE(stor_device->stor_chns[old], cur_chn);
+	else
+		cpumask_clear_cpu(old, &stor_device->alloced_cpus);
+
+	/* "Flush" the stor_chns array. */
+	for_each_possible_cpu(cpu) {
+		if (stor_device->stor_chns[cpu] && !cpumask_test_cpu(
+					cpu, &stor_device->alloced_cpus))
+			WRITE_ONCE(stor_device->stor_chns[cpu], NULL);
+	}
+
+	WRITE_ONCE(stor_device->stor_chns[new], channel);
+	cpumask_set_cpu(new, &stor_device->alloced_cpus);
+
+	spin_unlock_irqrestore(&device->channel->lock, flags);
+}
+
 static void handle_sc_creation(struct vmbus_channel *new_sc)
 {
 	struct hv_device *device = new_sc->primary_channel->device_obj;
@@ -648,6 +706,8 @@ static void handle_sc_creation(struct vmbus_channel *new_sc)
 		return;
 	}
 
+	new_sc->change_target_cpu_callback = storvsc_change_target_cpu;
+
 	/* Add the sub-channel to the array of available channels. */
 	stor_device->stor_chns[new_sc->target_cpu] = new_sc;
 	cpumask_set_cpu(new_sc->target_cpu, &stor_device->alloced_cpus);
@@ -876,6 +936,8 @@ static int storvsc_channel_init(struct hv_device *device, bool is_fc)
 	if (stor_device->stor_chns == NULL)
 		return -ENOMEM;
 
+	device->channel->change_target_cpu_callback = storvsc_change_target_cpu;
+
 	stor_device->stor_chns[device->channel->target_cpu] = device->channel;
 	cpumask_set_cpu(device->channel->target_cpu,
 			&stor_device->alloced_cpus);
@@ -1248,8 +1310,10 @@ static struct vmbus_channel *get_og_chn(struct storvsc_device *stor_device,
 	const struct cpumask *node_mask;
 	int num_channels, tgt_cpu;
 
-	if (stor_device->num_sc == 0)
+	if (stor_device->num_sc == 0) {
+		stor_device->stor_chns[q_num] = stor_device->device->channel;
 		return stor_device->device->channel;
+	}
 
 	/*
 	 * Our channel array is sparsley populated and we
@@ -1258,7 +1322,6 @@ static struct vmbus_channel *get_og_chn(struct storvsc_device *stor_device,
 	 * The strategy is simple:
 	 * I. Ensure NUMA locality
 	 * II. Distribute evenly (best effort)
-	 * III. Mapping is persistent.
 	 */
 
 	node_mask = cpumask_of_node(cpu_to_node(q_num));
@@ -1268,8 +1331,10 @@ static struct vmbus_channel *get_og_chn(struct storvsc_device *stor_device,
 		if (cpumask_test_cpu(tgt_cpu, node_mask))
 			num_channels++;
 	}
-	if (num_channels == 0)
+	if (num_channels == 0) {
+		stor_device->stor_chns[q_num] = stor_device->device->channel;
 		return stor_device->device->channel;
+	}
 
 	hash_qnum = q_num;
 	while (hash_qnum >= num_channels)
@@ -1295,6 +1360,7 @@ static int storvsc_do_io(struct hv_device *device,
 	struct storvsc_device *stor_device;
 	struct vstor_packet *vstor_packet;
 	struct vmbus_channel *outgoing_channel, *channel;
+	unsigned long flags;
 	int ret = 0;
 	const struct cpumask *node_mask;
 	int tgt_cpu;
@@ -1308,10 +1374,11 @@ static int storvsc_do_io(struct hv_device *device,
 
 	request->device  = device;
 	/*
-	 * Select an an appropriate channel to send the request out.
+	 * Select an appropriate channel to send the request out.
 	 */
-	if (stor_device->stor_chns[q_num] != NULL) {
-		outgoing_channel = stor_device->stor_chns[q_num];
+	/* See storvsc_change_target_cpu(). */
+	outgoing_channel = READ_ONCE(stor_device->stor_chns[q_num]);
+	if (outgoing_channel != NULL) {
 		if (outgoing_channel->target_cpu == q_num) {
 			/*
 			 * Ideally, we want to pick a different channel if
@@ -1324,7 +1391,10 @@ static int storvsc_do_io(struct hv_device *device,
 					continue;
 				if (tgt_cpu == q_num)
 					continue;
-				channel = stor_device->stor_chns[tgt_cpu];
+				channel = READ_ONCE(
+					stor_device->stor_chns[tgt_cpu]);
+				if (channel == NULL)
+					continue;
 				if (hv_get_avail_to_write_percent(
 							&channel->outbound)
 						> ring_avail_percent_lowater) {
@@ -1350,7 +1420,10 @@ static int storvsc_do_io(struct hv_device *device,
 			for_each_cpu(tgt_cpu, &stor_device->alloced_cpus) {
 				if (cpumask_test_cpu(tgt_cpu, node_mask))
 					continue;
-				channel = stor_device->stor_chns[tgt_cpu];
+				channel = READ_ONCE(
+					stor_device->stor_chns[tgt_cpu]);
+				if (channel == NULL)
+					continue;
 				if (hv_get_avail_to_write_percent(
 							&channel->outbound)
 						> ring_avail_percent_lowater) {
@@ -1360,7 +1433,14 @@ static int storvsc_do_io(struct hv_device *device,
 			}
 		}
 	} else {
+		spin_lock_irqsave(&device->channel->lock, flags);
+		outgoing_channel = stor_device->stor_chns[q_num];
+		if (outgoing_channel != NULL) {
+			spin_unlock_irqrestore(&device->channel->lock, flags);
+			goto found_channel;
+		}
 		outgoing_channel = get_og_chn(stor_device, q_num);
+		spin_unlock_irqrestore(&device->channel->lock, flags);
 	}
 
 found_channel:

include/linux/hyperv.h

@@ -117,7 +117,7 @@ struct hv_ring_buffer {
 	 * Ring data starts here + RingDataStartOffset
 	 * !!! DO NOT place any fields below this !!!
 	 */
-	u8 buffer[0];
+	u8 buffer[];
 } __packed;
 
 struct hv_ring_buffer_info {
@@ -313,7 +313,7 @@ struct vmadd_remove_transfer_page_set {
 struct gpa_range {
 	u32 byte_count;
 	u32 byte_offset;
-	u64 pfn_array[0];
+	u64 pfn_array[];
 };
 
 /*
@@ -425,7 +425,7 @@ enum vmbus_channel_message_type {
 	CHANNELMSG_19				= 19,
 	CHANNELMSG_20				= 20,
 	CHANNELMSG_TL_CONNECT_REQUEST		= 21,
-	CHANNELMSG_22				= 22,
+	CHANNELMSG_MODIFYCHANNEL		= 22,
 	CHANNELMSG_TL_CONNECT_RESULT		= 23,
 	CHANNELMSG_COUNT
 };
@@ -563,7 +563,7 @@ struct vmbus_channel_gpadl_header {
 	u32 gpadl;
 	u16 range_buflen;
 	u16 rangecount;
-	struct gpa_range range[0];
+	struct gpa_range range[];
 } __packed;
 
 /* This is the followup packet that contains more PFNs. */
@@ -571,7 +571,7 @@ struct vmbus_channel_gpadl_body {
 	struct vmbus_channel_message_header header;
 	u32 msgnumber;
 	u32 gpadl;
-	u64 pfn[0];
+	u64 pfn[];
 } __packed;
 
 struct vmbus_channel_gpadl_created {
@@ -620,6 +620,13 @@ struct vmbus_channel_tl_connect_request {
 	guid_t host_service_id;
 } __packed;
 
+/* Modify Channel parameters, cf. vmbus_send_modifychannel() */
+struct vmbus_channel_modifychannel {
+	struct vmbus_channel_message_header header;
+	u32 child_relid;
+	u32 target_vp;
+} __packed;
+
 struct vmbus_channel_version_response {
 	struct vmbus_channel_message_header header;
 	u8 version_supported;
@@ -672,7 +679,7 @@ struct vmbus_channel_msginfo {
 	 * The channel message that goes out on the "wire".
 	 * It will contain at minimum the VMBUS_CHANNEL_MESSAGE_HEADER header
 	 */
-	unsigned char msg[0];
+	unsigned char msg[];
 };
 
 struct vmbus_close_msg {
@@ -689,11 +696,6 @@ union hv_connection_id {
 	} u;
 };
 
-enum hv_numa_policy {
-	HV_BALANCED = 0,
-	HV_LOCALIZED,
-};
-
 enum vmbus_device_type {
 	HV_IDE = 0,
 	HV_SCSI,
@@ -771,6 +773,15 @@ struct vmbus_channel {
 	void (*onchannel_callback)(void *context);
 	void *channel_callback_context;
 
+	void (*change_target_cpu_callback)(struct vmbus_channel *channel,
+			u32 old, u32 new);
+
+	/*
+	 * Synchronize channel scheduling and channel removal; see the inline
+	 * comments in vmbus_chan_sched() and vmbus_reset_channel_cb().
+	 */
+	spinlock_t sched_lock;
+
 	/*
 	 * A channel can be marked for one of three modes of reading:
 	 *   BATCHED - callback called from taslket and should read
@@ -802,10 +813,6 @@ struct vmbus_channel {
 	u32 target_vp;
 	/* The corresponding CPUID in the guest */
 	u32 target_cpu;
-	/*
-	 * State to manage the CPU affiliation of channels.
-	 */
-	struct cpumask alloced_cpus_in_node;
 	int numa_node;
 	/*
 	 * Support for sub-channels. For high performance devices,
@@ -854,11 +861,6 @@ struct vmbus_channel {
 	 * Support per-channel state for use by vmbus drivers.
 	 */
 	void *per_channel_state;
-	/*
-	 * To support per-cpu lookup mapping of relid to channel,
-	 * link up channels based on their CPU affinity.
-	 */
-	struct list_head percpu_list;
 
 	/*
 	 * Defer freeing channel until after all cpu's have
@@ -897,19 +899,14 @@ struct vmbus_channel {
 	 */
 	bool low_latency;
 
+	bool probe_done;
+
 	/*
-	 * NUMA distribution policy:
-	 * We support two policies:
-	 * 1) Balanced: Here all performance critical channels are
-	 *    distributed evenly amongst all the NUMA nodes.
-	 *    This policy will be the default policy.
-	 * 2) Localized: All channels of a given instance of a
-	 *    performance critical service will be assigned CPUs
-	 *    within a selected NUMA node.
+	 * Cache the device ID here for easy access; this is useful, in
+	 * particular, in situations where the channel's device_obj has
+	 * not been allocated/initialized yet.
 	 */
-	enum hv_numa_policy affinity_policy;
-
-	bool probe_done;
+	u16 device_id;
 
 	/*
 	 * We must offload the handling of the primary/sub channels
@@ -964,12 +961,6 @@ static inline bool is_sub_channel(const struct vmbus_channel *c)
 	return c->offermsg.offer.sub_channel_index != 0;
 }
 
-static inline void set_channel_affinity_state(struct vmbus_channel *c,
-					      enum hv_numa_policy policy)
-{
-	c->affinity_policy = policy;
-}
-
 static inline void set_channel_read_mode(struct vmbus_channel *c,
 					enum hv_callback_mode mode)
 {
@@ -1017,7 +1008,7 @@ static inline void clear_low_latency_mode(struct vmbus_channel *c)
 	c->low_latency = false;
 }
 
-void vmbus_onmessage(void *context);
+void vmbus_onmessage(struct vmbus_channel_message_header *hdr);
 
 int vmbus_request_offers(void);
 
@@ -1531,6 +1522,7 @@ extern __u32 vmbus_proto_version;
 
 int vmbus_send_tl_connect_request(const guid_t *shv_guest_servie_id,
 				  const guid_t *shv_host_servie_id);
+int vmbus_send_modifychannel(u32 child_relid, u32 target_vp);
 void vmbus_set_event(struct vmbus_channel *channel);
 
 /* Get the start of the ring buffer. */

include/linux/mod_devicetable.h

@@ -434,7 +434,7 @@ struct virtio_device_id {
  * For Hyper-V devices we use the device guid as the id.
  */
 struct hv_vmbus_device_id {
-	uuid_le guid;
+	guid_t guid;
 	kernel_ulong_t driver_data;	/* Data private to the driver */
 };