[PATCH v5 0/9] Enhance the hv_vmbus driver to support hibernation

@@ -154,7 +154,7 @@ void hv_synic_free(void)
  * retrieve the initialized message and event pages.  Otherwise, we create and
  * initialize the message and event pages.
  */
-int hv_synic_init(unsigned int cpu)
+void hv_synic_enable_regs(unsigned int cpu)
 {
 	struct hv_per_cpu_context *hv_cpu
 		= per_cpu_ptr(hv_context.cpu_context, cpu);

@@ -196,6 +196,11 @@ int hv_synic_init(unsigned int cpu)
 	sctrl.enable = 1;
 
 	hv_set_synic_state(sctrl.as_uint64);
+}
+
+int hv_synic_init(unsigned int cpu)
+{
+	hv_synic_enable_regs(cpu);
 
 	hv_stimer_init(cpu);
 

@@ -205,20 +210,45 @@ int hv_synic_init(unsigned int cpu)
 /*
  * hv_synic_cleanup - Cleanup routine for hv_synic_init().
  */
-int hv_synic_cleanup(unsigned int cpu)
+void hv_synic_disable_regs(unsigned int cpu)
 {
 	union hv_synic_sint shared_sint;
 	union hv_synic_simp simp;
 	union hv_synic_siefp siefp;
 	union hv_synic_scontrol sctrl;
+
+	hv_get_synint_state(VMBUS_MESSAGE_SINT, shared_sint.as_uint64);
+
+	shared_sint.masked = 1;
+
+	/* Need to correctly cleanup in the case of SMP!!! */
+	/* Disable the interrupt */
+	hv_set_synint_state(VMBUS_MESSAGE_SINT, shared_sint.as_uint64);
+
+	hv_get_simp(simp.as_uint64);
+	simp.simp_enabled = 0;
+	simp.base_simp_gpa = 0;
+
+	hv_set_simp(simp.as_uint64);
+
+	hv_get_siefp(siefp.as_uint64);
+	siefp.siefp_enabled = 0;
+	siefp.base_siefp_gpa = 0;
+
+	hv_set_siefp(siefp.as_uint64);
+
+	/* Disable the global synic bit */
+	hv_get_synic_state(sctrl.as_uint64);
+	sctrl.enable = 0;
+	hv_set_synic_state(sctrl.as_uint64);
+}
+
+int hv_synic_cleanup(unsigned int cpu)
+{
 	struct vmbus_channel *channel, *sc;
 	bool channel_found = false;
 	unsigned long flags;
 
-	hv_get_synic_state(sctrl.as_uint64);
-	if (sctrl.enable != 1)
-		return -EFAULT;
-
 	/*
 	 * 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

@@ -249,29 +279,7 @@ int hv_synic_cleanup(unsigned int cpu)
 
 	hv_stimer_cleanup(cpu);
 
-	hv_get_synint_state(VMBUS_MESSAGE_SINT, shared_sint.as_uint64);
-
-	shared_sint.masked = 1;
-
-	/* Need to correctly cleanup in the case of SMP!!! */
-	/* Disable the interrupt */
-	hv_set_synint_state(VMBUS_MESSAGE_SINT, shared_sint.as_uint64);
-
-	hv_get_simp(simp.as_uint64);
-	simp.simp_enabled = 0;
-	simp.base_simp_gpa = 0;
-
-	hv_set_simp(simp.as_uint64);
-
-	hv_get_siefp(siefp.as_uint64);
-	siefp.siefp_enabled = 0;
-	siefp.base_siefp_gpa = 0;
-
-	hv_set_siefp(siefp.as_uint64);
-
-	/* Disable the global synic bit */
-	sctrl.enable = 0;
-	hv_set_synic_state(sctrl.as_uint64);
+	hv_synic_disable_regs(cpu);
 
 	return 0;
 }

@@ -171,8 +171,10 @@ extern int hv_post_message(union hv_connection_id connection_id,
 
 extern void hv_synic_free(void);
 
+extern void hv_synic_enable_regs(unsigned int cpu);
 extern int hv_synic_init(unsigned int cpu);
 
+extern void hv_synic_disable_regs(unsigned int cpu);
 extern int hv_synic_cleanup(unsigned int cpu);
 
 /* Interface */

@@ -30,6 +30,7 @@
 #include <linux/kdebug.h>
 #include <linux/efi.h>
 #include <linux/random.h>
+#include <linux/syscore_ops.h>
 #include <clocksource/hyperv_timer.h>
 #include "hyperv_vmbus.h"
 

@@ -2086,6 +2087,47 @@ static void hv_crash_handler(struct pt_regs *regs)
 	hyperv_cleanup();
 };
 
+static int hv_synic_suspend(void)
+{
+	/*
+	 * When we reach here, all the non-boot CPUs have been offlined, and
+	 * the stimers on them have been unbound in hv_synic_cleanup() ->
+	 * hv_stimer_cleanup() -> clockevents_unbind_device().
+	 *
+	 * hv_synic_suspend() only runs on CPU0 with interrupts disabled. Here
+	 * we do not unbind the stimer on CPU0 because: 1) it's unnecessary
+	 * because the interrupts remain disabled between syscore_suspend()
+	 * and syscore_resume(): see create_image() and resume_target_kernel();
+	 * 2) the stimer on CPU0 is automatically disabled later by
+	 * syscore_suspend() -> timekeeping_suspend() -> tick_suspend() -> ...
+	 * -> clockevents_shutdown() -> ... -> hv_ce_shutdown(); 3) a warning
+	 * would be triggered if we call clockevents_unbind_device(), which
+	 * may sleep, in an interrupts-disabled context. So, we intentionally
+	 * don't call hv_stimer_cleanup(0) here.
+	 */
+
+	hv_synic_disable_regs(0);
+
+	return 0;
+}
+
+static void hv_synic_resume(void)
+{
+	hv_synic_enable_regs(0);
+
+	/*
+	 * Note: we don't need to call hv_stimer_init(0), because the timer
+	 * on CPU0 is not unbound in hv_synic_suspend(), and the timer is
+	 * automatically re-enabled in timekeeping_resume().
+	 */
+}
+
+/* The callbacks run only on CPU0, with irqs_disabled. */
+static struct syscore_ops hv_synic_syscore_ops = {
+	.suspend = hv_synic_suspend,
+	.resume = hv_synic_resume,
+};
+
 static int __init hv_acpi_init(void)
 {
 	int ret, t;

@@ -2116,6 +2158,8 @@ static int __init hv_acpi_init(void)
 	hv_setup_kexec_handler(hv_kexec_handler);
 	hv_setup_crash_handler(hv_crash_handler);
 
+	register_syscore_ops(&hv_synic_syscore_ops);
+
 	return 0;
 
 cleanup:

@@ -2128,6 +2172,8 @@ static void __exit vmbus_exit(void)
 {
 	int cpu;
 
+	unregister_syscore_ops(&hv_synic_syscore_ops);
+
 	hv_remove_kexec_handler();
 	hv_remove_crash_handler();
 	vmbus_connection.conn_state = DISCONNECTED;

@@ -911,6 +911,43 @@ static void vmbus_shutdown(struct device *child_device)
 		drv->shutdown(dev);
 }
 
+/*
+ * vmbus_suspend - Suspend a vmbus device
+ */
+static int vmbus_suspend(struct device *child_device)
+{
+	struct hv_driver *drv;
+	struct hv_device *dev = device_to_hv_device(child_device);
+
+	/* The device may not be attached yet */
+	if (!child_device->driver)
+		return 0;
+
+	drv = drv_to_hv_drv(child_device->driver);
+	if (!drv->suspend)
+		return -EOPNOTSUPP;
+
+	return drv->suspend(dev);
+}
+
+/*
+ * vmbus_resume - Resume a vmbus device
+ */
+static int vmbus_resume(struct device *child_device)
+{
+	struct hv_driver *drv;
+	struct hv_device *dev = device_to_hv_device(child_device);
+
+	/* The device may not be attached yet */
+	if (!child_device->driver)
+		return 0;
+
+	drv = drv_to_hv_drv(child_device->driver);
+	if (!drv->resume)
+		return -EOPNOTSUPP;
+
+	return drv->resume(dev);
+}
 
 /*
  * vmbus_device_release - Final callback release of the vmbus child device

@@ -926,6 +963,14 @@ static void vmbus_device_release(struct device *device)
 	kfree(hv_dev);
 }
 
+/*
+ * Note: we must use SET_NOIRQ_SYSTEM_SLEEP_PM_OPS rather than
+ * SET_SYSTEM_SLEEP_PM_OPS: see the comment before vmbus_bus_pm.
+ */
+static const struct dev_pm_ops vmbus_pm = {
+	SET_NOIRQ_SYSTEM_SLEEP_PM_OPS(vmbus_suspend, vmbus_resume)
+};
+
 /* The one and only one */
 static struct bus_type  hv_bus = {
 	.name =		"vmbus",

@@ -936,6 +981,7 @@ static void vmbus_device_release(struct device *device)
 	.uevent =		vmbus_uevent,
 	.dev_groups =		vmbus_dev_groups,
 	.drv_groups =		vmbus_drv_groups,
+	.pm =			&vmbus_pm,
 };
 
 struct onmessage_work_context {

@@ -1157,6 +1157,9 @@ struct hv_driver {
 	int (*remove)(struct hv_device *);
 	void (*shutdown)(struct hv_device *);
 
+	int (*suspend)(struct hv_device *);
+	int (*resume)(struct hv_device *);
+
 };
 
 /* Base device object */

@@ -59,8 +59,7 @@ static __u32 vmbus_get_next_version(__u32 current_version)
 	}
 }
 
-static int vmbus_negotiate_version(struct vmbus_channel_msginfo *msginfo,
-					__u32 version)
+int vmbus_negotiate_version(struct vmbus_channel_msginfo *msginfo, u32 version)
 {
 	int ret = 0;
 	unsigned int cur_cpu;

@@ -274,6 +274,8 @@ struct vmbus_msginfo {
 
 extern struct vmbus_connection vmbus_connection;
 
+int vmbus_negotiate_version(struct vmbus_channel_msginfo *msginfo, u32 version);
+
 static inline void vmbus_send_interrupt(u32 relid)
 {
 	sync_set_bit(relid, vmbus_connection.send_int_page);

@@ -2089,6 +2089,51 @@ static int vmbus_acpi_add(struct acpi_device *device)
 	return ret_val;
 }
 
+static int vmbus_bus_suspend(struct device *dev)
+{
+	vmbus_initiate_unload(false);
+
+	vmbus_connection.conn_state = DISCONNECTED;
+
+	return 0;
+}
+
+static int vmbus_bus_resume(struct device *dev)
+{
+	struct vmbus_channel_msginfo *msginfo;
+	size_t msgsize;
+	int ret;
+
+	/*
+	 * We only use the 'vmbus_proto_version', which was in use before
+	 * hibernation, to re-negotiate with the host.
+	 */
+	if (vmbus_proto_version == VERSION_INVAL ||
+	    vmbus_proto_version == 0) {
+		pr_err("Invalid proto version = 0x%x\n", vmbus_proto_version);
+		return -EINVAL;
+	}
+
+	msgsize = sizeof(*msginfo) +
+		  sizeof(struct vmbus_channel_initiate_contact);
+
+	msginfo = kzalloc(msgsize, GFP_KERNEL);
+
+	if (msginfo == NULL)
+		return -ENOMEM;
+
+	ret = vmbus_negotiate_version(msginfo, vmbus_proto_version);
+
+	kfree(msginfo);
+
+	if (ret != 0)
+		return ret;
+
+	vmbus_request_offers();
+
+	return 0;
+}
+
 static const struct acpi_device_id vmbus_acpi_device_ids[] = {
 	{"VMBUS", 0},
 	{"VMBus", 0},

@@ -2096,6 +2141,19 @@ static int vmbus_acpi_add(struct acpi_device *device)
 };
 MODULE_DEVICE_TABLE(acpi, vmbus_acpi_device_ids);
 
+/*
+ * Note: we must use SET_NOIRQ_SYSTEM_SLEEP_PM_OPS rather than
+ * SET_SYSTEM_SLEEP_PM_OPS, otherwise NIC SR-IOV can not work, because the
+ * "pci_dev_pm_ops" uses the "noirq" callbacks: in the resume path, the
+ * pci "noirq" restore callback runs before "non-noirq" callbacks (see
+ * resume_target_kernel() -> dpm_resume_start(), and hibernation_restore() ->
+ * dpm_resume_end()). This means vmbus_bus_resume() and the pci-hyperv's
+ * resume callback must also run via the "noirq" callbacks.
+ */
+static const struct dev_pm_ops vmbus_bus_pm = {
+	SET_NOIRQ_SYSTEM_SLEEP_PM_OPS(vmbus_bus_suspend, vmbus_bus_resume)
+};
+
 static struct acpi_driver vmbus_acpi_driver = {
 	.name = "vmbus",
 	.ids = vmbus_acpi_device_ids,

@@ -2103,6 +2161,7 @@ static int vmbus_acpi_add(struct acpi_device *device)
 		.add = vmbus_acpi_add,
 		.remove = vmbus_acpi_remove,
 	},
+	.drv.pm = &vmbus_bus_pm,
 };
 
 static void hv_kexec_handler(void)

@@ -545,6 +545,10 @@ static void vmbus_process_offer(struct vmbus_channel *newchannel)
 
 	mutex_lock(&vmbus_connection.channel_mutex);
 
+	/* Remember the channels that should be cleaned up upon suspend. */
+	if (is_hvsock_channel(newchannel) || is_sub_channel(newchannel))
+		atomic_inc(&vmbus_connection.nr_chan_close_on_suspend);
+
 	/*
 	 * Now that we have acquired the channel_mutex,
 	 * we can release the potentially racing rescind thread.

@@ -944,6 +948,16 @@ static void vmbus_onoffer(struct vmbus_channel_message_header *hdr)
 	vmbus_process_offer(newchannel);
 }
 
+static void check_ready_for_suspend_event(void)
+{
+	/*
+	 * If all the sub-channels or hv_sock channels have been cleaned up,
+	 * then it's safe to suspend.
+	 */
+	if (atomic_dec_and_test(&vmbus_connection.nr_chan_close_on_suspend))
+		complete(&vmbus_connection.ready_for_suspend_event);
+}
+
 /*
  * vmbus_onoffer_rescind - Rescind offer handler.
  *

@@ -954,6 +968,7 @@ static void vmbus_onoffer_rescind(struct vmbus_channel_message_header *hdr)
 	struct vmbus_channel_rescind_offer *rescind;
 	struct vmbus_channel *channel;
 	struct device *dev;
+	bool clean_up_chan_for_suspend;
 
 	rescind = (struct vmbus_channel_rescind_offer *)hdr;
 

@@ -993,6 +1008,8 @@ static void vmbus_onoffer_rescind(struct vmbus_channel_message_header *hdr)
 		return;
 	}
 
+	clean_up_chan_for_suspend = is_hvsock_channel(channel) ||
+				    is_sub_channel(channel);
 	/*
 	 * Before setting channel->rescind in vmbus_rescind_cleanup(), we
 	 * should make sure the channel callback is not running any more.

@@ -1018,6 +1035,10 @@ static void vmbus_onoffer_rescind(struct vmbus_channel_message_header *hdr)
 	if (channel->device_obj) {
 		if (channel->chn_rescind_callback) {
 			channel->chn_rescind_callback(channel);
+
+			if (clean_up_chan_for_suspend)
+				check_ready_for_suspend_event();
+
 			return;
 		}
 		/*

@@ -1050,6 +1071,11 @@ static void vmbus_onoffer_rescind(struct vmbus_channel_message_header *hdr)
 		}
 		mutex_unlock(&vmbus_connection.channel_mutex);
 	}
+
+	/* The "channel" may have been freed. Do not access it any longer. */
+
+	if (clean_up_chan_for_suspend)
+		check_ready_for_suspend_event();
 }
 
 void vmbus_hvsock_device_unregister(struct vmbus_channel *channel)

@@ -26,6 +26,9 @@
 struct vmbus_connection vmbus_connection = {
 	.conn_state		= DISCONNECTED,
 	.next_gpadl_handle	= ATOMIC_INIT(0xE1E10),
+
+	.ready_for_suspend_event= COMPLETION_INITIALIZER(
+				  vmbus_connection.ready_for_suspend_event),
 };
 EXPORT_SYMBOL_GPL(vmbus_connection);
 

@@ -260,6 +260,18 @@ struct vmbus_connection {
 	struct workqueue_struct *work_queue;
 	struct workqueue_struct *handle_primary_chan_wq;
 	struct workqueue_struct *handle_sub_chan_wq;
+
+	/*
+	 * The number of sub-channels and hv_sock channels that should be
+	 * cleaned up upon suspend: sub-channels will be re-created upon
+	 * resume, and hv_sock channels should not survive suspend.
+	 */
+	atomic_t nr_chan_close_on_suspend;
+	/*
+	 * vmbus_bus_suspend() waits for "nr_chan_close_on_suspend" to
+	 * drop to zero.
+	 */
+	struct completion ready_for_suspend_event;
 };
 
 

@@ -2127,7 +2127,8 @@ static int vmbus_acpi_add(struct acpi_device *device)
 
 static int vmbus_bus_suspend(struct device *dev)
 {
-	struct vmbus_channel *channel;
+	struct vmbus_channel *channel, *sc;
+	unsigned long flags;
 
 	while (atomic_read(&vmbus_connection.offer_in_progress) != 0) {
 		/*

@@ -2146,6 +2147,44 @@ static int vmbus_bus_suspend(struct device *dev)
 	}
 	mutex_unlock(&vmbus_connection.channel_mutex);
 
+	/*
+	 * Wait until all the sub-channels and hv_sock channels have been
+	 * cleaned up. Sub-channels should be destroyed upon suspend, otherwise
+	 * they would conflict with the new sub-channels that will be created
+	 * in the resume path. hv_sock channels should also be destroyed, but
+	 * a hv_sock channel of an established hv_sock connection can not be
+	 * really destroyed since it may still be referenced by the userspace
+	 * application, so we just force the hv_sock channel to be rescinded
+	 * by vmbus_force_channel_rescinded(), and the userspace application
+	 * will thoroughly destroy the channel after hibernation.
+	 *
+	 * Note: the counter nr_chan_close_on_suspend may never go above 0 if
+	 * the VM has no sub-channel and hv_sock channel, e.g. a 1-vCPU VM.
+	 */
+	if (atomic_read(&vmbus_connection.nr_chan_close_on_suspend) > 0)
+		wait_for_completion(&vmbus_connection.ready_for_suspend_event);
+
+	mutex_lock(&vmbus_connection.channel_mutex);
+
+	list_for_each_entry(channel, &vmbus_connection.chn_list, listentry) {
+		if (is_hvsock_channel(channel)) {
+			if (!channel->rescind) {
+				pr_err("hv_sock channel not rescinded!\n");
+				WARN_ON_ONCE(1);
+			}
+			continue;
+		}
+
+		spin_lock_irqsave(&channel->lock, flags);
+		list_for_each_entry(sc, &channel->sc_list, sc_list) {
+			pr_err("Sub-channel not deleted!\n");
+			WARN_ON_ONCE(1);
+		}
+		spin_unlock_irqrestore(&channel->lock, flags);
+	}
+
+	mutex_unlock(&vmbus_connection.channel_mutex);
+
 	vmbus_initiate_unload(false);
 
 	vmbus_connection.conn_state = DISCONNECTED;

@@ -2186,6 +2225,9 @@ static int vmbus_bus_resume(struct device *dev)
 
 	vmbus_request_offers();
 
+	/* Reset the event for the next suspend. */
+	reinit_completion(&vmbus_connection.ready_for_suspend_event);
+
 	return 0;
 }
 

@@ -407,7 +407,15 @@ void hv_process_channel_removal(struct vmbus_channel *channel)
 		cpumask_clear_cpu(channel->target_cpu,
 				  &primary_channel->alloced_cpus_in_node);
 
-	vmbus_release_relid(channel->offermsg.child_relid);
+	/*
+	 * Upon suspend, an in-use hv_sock channel is marked as "rescinded" and
+	 * the relid is invalidated; after hibernation, when the user-space app
+	 * destroys the channel, the relid is INVALID_RELID, and in this case
+	 * it's unnecessary and unsafe to release the old relid, since the same
+	 * relid can refer to a completely different channel now.
+	 */
+	if (channel->offermsg.child_relid != INVALID_RELID)
+		vmbus_release_relid(channel->offermsg.child_relid);
 
 	free_channel(channel);
 }

@@ -851,6 +859,36 @@ void vmbus_initiate_unload(bool crash)
 		vmbus_wait_for_unload();
 }
 
+static void check_ready_for_resume_event(void)
+{
+	/*
+	 * If all the old primary channels have been fixed up, then it's safe
+	 * to resume.
+	 */
+	if (atomic_dec_and_test(&vmbus_connection.nr_chan_fixup_on_resume))
+		complete(&vmbus_connection.ready_for_resume_event);
+}
+
+static void vmbus_setup_channel_state(struct vmbus_channel *channel,
+				      struct vmbus_channel_offer_channel *offer)
+{
+	/*
+	 * Setup state for signalling the host.
+	 */
+	channel->sig_event = VMBUS_EVENT_CONNECTION_ID;
+
+	if (vmbus_proto_version != VERSION_WS2008) {
+		channel->is_dedicated_interrupt =
+				(offer->is_dedicated_interrupt != 0);
+		channel->sig_event = offer->connection_id;
+	}
+
+	memcpy(&channel->offermsg, offer,
+	       sizeof(struct vmbus_channel_offer_channel));
+	channel->monitor_grp = (u8)offer->monitorid / 32;
+	channel->monitor_bit = (u8)offer->monitorid % 32;
+}
+
 /*
  * find_primary_channel_by_offer - Get the channel object given the new offer.
  * This is only used in the resume path of hibernation.

@@ -902,14 +940,29 @@ static void vmbus_onoffer(struct vmbus_channel_message_header *hdr)
 		atomic_dec(&vmbus_connection.offer_in_progress);
 
 		/*
-		 * We're resuming from hibernation: we expect the host to send
-		 * exactly the same offers that we had before the hibernation.
+		 * We're resuming from hibernation: all the sub-channel and
+		 * hv_sock channels we had before the hibernation should have
+		 * been cleaned up, and now we must be seeing a re-offered
+		 * primary channel that we had before the hibernation.
 		 */
+
+		WARN_ON(oldchannel->offermsg.child_relid != INVALID_RELID);
+		/* Fix up the relid. */
+		oldchannel->offermsg.child_relid = offer->child_relid;
+
 		offer_sz = sizeof(*offer);
-		if (memcmp(offer, &oldchannel->offermsg, offer_sz) == 0)
+		if (memcmp(offer, &oldchannel->offermsg, offer_sz) == 0) {
+			check_ready_for_resume_event();
 			return;
+		}
 
-		pr_debug("Mismatched offer from the host (relid=%d)\n",
+		/*
+		 * This is not an error, since the host can also change the
+		 * other field(s) of the offer, e.g. on WS RS5 (Build 17763),
+		 * the offer->connection_id of the Mellanox VF vmbus device
+		 * can change when the host reoffers the device upon resume.
+		 */
+		pr_debug("vmbus offer changed: relid=%d\n",
 			 offer->child_relid);
 
 		print_hex_dump_debug("Old vmbus offer: ", DUMP_PREFIX_OFFSET,

@@ -917,6 +970,12 @@ static void vmbus_onoffer(struct vmbus_channel_message_header *hdr)
 				     false);
 		print_hex_dump_debug("New vmbus offer: ", DUMP_PREFIX_OFFSET,
 				     16, 4, offer, offer_sz, false);
+
+		/* Fix up the old channel. */
+		vmbus_setup_channel_state(oldchannel, offer);
+
+		check_ready_for_resume_event();
+
 		return;
 	}
 

@@ -929,21 +988,7 @@ static void vmbus_onoffer(struct vmbus_channel_message_header *hdr)
 		return;
 	}
 
-	/*
-	 * Setup state for signalling the host.
-	 */
-	newchannel->sig_event = VMBUS_EVENT_CONNECTION_ID;
-
-	if (vmbus_proto_version != VERSION_WS2008) {
-		newchannel->is_dedicated_interrupt =
-				(offer->is_dedicated_interrupt != 0);
-		newchannel->sig_event = offer->connection_id;
-	}
-
-	memcpy(&newchannel->offermsg, offer,
-	       sizeof(struct vmbus_channel_offer_channel));
-	newchannel->monitor_grp = (u8)offer->monitorid / 32;
-	newchannel->monitor_bit = (u8)offer->monitorid % 32;
+	vmbus_setup_channel_state(newchannel, offer);
 
 	vmbus_process_offer(newchannel);
 }

@@ -29,6 +29,8 @@ struct vmbus_connection vmbus_connection = {
 
 	.ready_for_suspend_event= COMPLETION_INITIALIZER(
 				  vmbus_connection.ready_for_suspend_event),
+	.ready_for_resume_event	= COMPLETION_INITIALIZER(
+				  vmbus_connection.ready_for_resume_event),
 };
 EXPORT_SYMBOL_GPL(vmbus_connection);
 

@@ -272,6 +272,20 @@ struct vmbus_connection {
 	 * drop to zero.
 	 */
 	struct completion ready_for_suspend_event;
+
+	/*
+	 * The number of primary channels that should be "fixed up"
+	 * upon resume: these channels are re-offered upon resume, and some
+	 * fields of the channel offers (i.e. child_relid and connection_id)
+	 * can change, so the old offermsg must be fixed up, before the resume
+	 * callbacks of the VSC drivers start to further touch the channels.
+	 */
+	atomic_t nr_chan_fixup_on_resume;
+	/*
+	 * vmbus_bus_resume() waits for "nr_chan_fixup_on_resume" to
+	 * drop to zero.
+	 */
+	struct completion ready_for_resume_event;
 };
 
 

@@ -2164,9 +2164,17 @@ static int vmbus_bus_suspend(struct device *dev)
 	if (atomic_read(&vmbus_connection.nr_chan_close_on_suspend) > 0)
 		wait_for_completion(&vmbus_connection.ready_for_suspend_event);
 
+	WARN_ON(atomic_read(&vmbus_connection.nr_chan_fixup_on_resume) != 0);
+
 	mutex_lock(&vmbus_connection.channel_mutex);
 
 	list_for_each_entry(channel, &vmbus_connection.chn_list, listentry) {
+		/*
+		 * Invalidate the field. Upon resume, vmbus_onoffer() will fix
+		 * up the field, and the other fields (if necessary).
+		 */
+		channel->offermsg.child_relid = INVALID_RELID;
+
 		if (is_hvsock_channel(channel)) {
 			if (!channel->rescind) {
 				pr_err("hv_sock channel not rescinded!\n");

@@ -2181,6 +2189,8 @@ static int vmbus_bus_suspend(struct device *dev)
 			WARN_ON_ONCE(1);
 		}
 		spin_unlock_irqrestore(&channel->lock, flags);
+
+		atomic_inc(&vmbus_connection.nr_chan_fixup_on_resume);
 	}
 
 	mutex_unlock(&vmbus_connection.channel_mutex);

@@ -2189,6 +2199,9 @@ static int vmbus_bus_suspend(struct device *dev)
 
 	vmbus_connection.conn_state = DISCONNECTED;
 
+	/* Reset the event for the next resume. */
+	reinit_completion(&vmbus_connection.ready_for_resume_event);
+
 	return 0;
 }
 

@@ -2223,8 +2236,12 @@ static int vmbus_bus_resume(struct device *dev)
 	if (ret != 0)
 		return ret;
 
+	WARN_ON(atomic_read(&vmbus_connection.nr_chan_fixup_on_resume) == 0);
+
 	vmbus_request_offers();
 
+	wait_for_completion(&vmbus_connection.ready_for_resume_event);
+
 	/* Reset the event for the next suspend. */
 	reinit_completion(&vmbus_connection.ready_for_suspend_event);
 

@@ -426,6 +426,9 @@ enum vmbus_channel_message_type {
 	CHANNELMSG_COUNT
 };
 
+/* Hyper-V supports about 2048 channels, and the RELIDs start with 1. */
+#define INVALID_RELID	U32_MAX
+
 struct vmbus_channel_message_header {
 	enum vmbus_channel_message_type msgtype;
 	u32 padding;

@@ -848,18 +848,74 @@ void vmbus_initiate_unload(bool crash)
 }
 
 /*
+ * find_primary_channel_by_offer - Get the channel object given the new offer.
+ * This is only used in the resume path of hibernation.
+ */
+static struct vmbus_channel *
+find_primary_channel_by_offer(const struct vmbus_channel_offer_channel *offer)
+{
+	struct vmbus_channel *channel = NULL, *iter;
+	const guid_t *inst1, *inst2;
+
+	/* Ignore sub-channel offers. */
+	if (offer->offer.sub_channel_index != 0)
+		return NULL;
+
+	mutex_lock(&vmbus_connection.channel_mutex);
+
+	list_for_each_entry(iter, &vmbus_connection.chn_list, listentry) {
+		inst1 = &iter->offermsg.offer.if_instance;
+		inst2 = &offer->offer.if_instance;
+
+		if (guid_equal(inst1, inst2)) {
+			channel = iter;
+			break;
+		}
+	}
+
+	mutex_unlock(&vmbus_connection.channel_mutex);
+
+	return channel;
+}
+
+/*
  * vmbus_onoffer - Handler for channel offers from vmbus in parent partition.
  *
  */
 static void vmbus_onoffer(struct vmbus_channel_message_header *hdr)
 {
 	struct vmbus_channel_offer_channel *offer;
-	struct vmbus_channel *newchannel;
+	struct vmbus_channel *oldchannel, *newchannel;
+	size_t offer_sz;
 
 	offer = (struct vmbus_channel_offer_channel *)hdr;
 
 	trace_vmbus_onoffer(offer);
 
+	oldchannel = find_primary_channel_by_offer(offer);
+
+	if (oldchannel != NULL) {
+		atomic_dec(&vmbus_connection.offer_in_progress);
+
+		/*
+		 * We're resuming from hibernation: we expect the host to send
+		 * exactly the same offers that we had before the hibernation.
+		 */
+		offer_sz = sizeof(*offer);
+		if (memcmp(offer, &oldchannel->offermsg, offer_sz) == 0)
+			return;
+
+		pr_debug("Mismatched offer from the host (relid=%d)\n",
+			 offer->child_relid);
+
+		print_hex_dump_debug("Old vmbus offer: ", DUMP_PREFIX_OFFSET,
+				     16, 4, &oldchannel->offermsg, offer_sz,
+				     false);
+		print_hex_dump_debug("New vmbus offer: ", DUMP_PREFIX_OFFSET,
+				     16, 4, offer, offer_sz, false);
+		return;
+	}
+
 	/* Allocate the channel object and save this offer. */
 	newchannel = alloc_channel();
 	if (!newchannel) {

@@ -24,6 +24,7 @@
 #include <linux/sched/task_stack.h>
 
 #include <asm/mshyperv.h>
+#include <linux/delay.h>
 #include <linux/notifier.h>
 #include <linux/ptrace.h>
 #include <linux/screen_info.h>

@@ -1069,6 +1070,41 @@ void vmbus_on_msg_dpc(unsigned long data)
 	vmbus_signal_eom(msg, message_type);
 }
 
+/*
+ * Fake RESCIND_CHANNEL messages to clean up hv_sock channels by force for
+ * hibernation, because hv_sock connections can not persist across hibernation.
+ */
+static void vmbus_force_channel_rescinded(struct vmbus_channel *channel)
+{
+	struct onmessage_work_context *ctx;
+	struct vmbus_channel_rescind_offer *rescind;
+
+	WARN_ON(!is_hvsock_channel(channel));
+
+	/*
+	 * sizeof(*ctx) is small and the allocation should really not fail,
+	 * otherwise the state of the hv_sock connections ends up in limbo.
+	 */
+	ctx = kzalloc(sizeof(*ctx), GFP_KERNEL | __GFP_NOFAIL);
+
+	/*
+	 * So far, these are not really used by Linux. Just set them to the
+	 * reasonable values conforming to the definitions of the fields.
+	 */
+	ctx->msg.header.message_type = 1;
+	ctx->msg.header.payload_size = sizeof(*rescind);
+
+	/* These values are actually used by Linux. */
+	rescind = (struct vmbus_channel_rescind_offer *)ctx->msg.u.payload;
+	rescind->header.msgtype = CHANNELMSG_RESCIND_CHANNELOFFER;
+	rescind->child_relid = channel->offermsg.child_relid;
+
+	INIT_WORK(&ctx->work, vmbus_onmessage_work);
+
+	queue_work_on(vmbus_connection.connect_cpu,
+		      vmbus_connection.work_queue,
+		      &ctx->work);
+}
 
 /*
  * Direct callback for channels using other deferred processing

@@ -2091,6 +2127,25 @@ static int vmbus_acpi_add(struct acpi_device *device)
 
 static int vmbus_bus_suspend(struct device *dev)
 {
+	struct vmbus_channel *channel;
+
+	while (atomic_read(&vmbus_connection.offer_in_progress) != 0) {
+		/*
+		 * We wait here until the completion of any channel
+		 * offers that are currently in progress.
+		 */
+		msleep(1);
+	}
+
+	mutex_lock(&vmbus_connection.channel_mutex);
+	list_for_each_entry(channel, &vmbus_connection.chn_list, listentry) {
+		if (!is_hvsock_channel(channel))
+			continue;
+
+		vmbus_force_channel_rescinded(channel);
+	}
+	mutex_unlock(&vmbus_connection.channel_mutex);
+
 	vmbus_initiate_unload(false);
 
 	vmbus_connection.conn_state = DISCONNECTED;

@@ -245,7 +245,10 @@ struct vmbus_channel_offer {
 		} pipe;
 	} u;
 	/*
-	 * The sub_channel_index is defined in win8.
+	 * The sub_channel_index is defined in Win8: a value of zero means a
+	 * primary channel and a value of non-zero means a sub-channel.
+	 *
+	 * Before Win8, the field is reserved, meaning it's always zero.
 	 */
 	u16 sub_channel_index;
 	u16 reserved3;

@@ -934,6 +937,11 @@ static inline bool is_hvsock_channel(const struct vmbus_channel *c)
 		  VMBUS_CHANNEL_TLNPI_PROVIDER_OFFER);
 }
 
+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)
 {