Drivers: hv: vmbus: Suspend after cleaning up hv_sock and sub channels

Before suspend, Linux must make sure all the hv_sock channels have been
properly cleaned up, because a hv_sock connection can not persist across
hibernation, and the user-space app must be properly notified of the
state change of the connection.

Before suspend, Linux also must make sure all the sub-channels have been
destroyed, i.e. the related channel structs of the sub-channels must be
properly removed, otherwise they would cause a conflict when the
sub-channels are recreated upon resume.

Add a counter to track such channels, and vmbus_bus_suspend() should wait
for the counter to drop to zero.

Signed-off-by: Dexuan Cui <decui@microsoft.com>
Reviewed-by: Michael Kelley <mikelley@microsoft.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>

drivers/hv/channel_mgmt.c

@@ -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)

drivers/hv/connection.c

@@ -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);
 

drivers/hv/hyperv_vmbus.h

@@ -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;
 };
 
 

drivers/hv/vmbus_drv.c

@@ -2127,7 +2127,8 @@ acpi_walk_err:
 
 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;
 }