Drivers: hv: vmbus: Suspend/resume the vmbus itself for hibernation

Before Linux enters hibernation, it sends the CHANNELMSG_UNLOAD message to
the host so all the offers are gone. After hibernation, Linux needs to
re-negotiate with the host using the same vmbus protocol version (which
was in use before hibernation), and ask the host to re-offer the vmbus
devices.

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

3 files changed, 62 insertions, 2 deletions

diff --git a/drivers/hv/connection.c b/drivers/hv/connection.c
index 09829e15d4a0..806319cd5ccf 100644
--- a/drivers/hv/connection.c
+++ b/drivers/hv/connection.c
@@ -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;
diff --git a/drivers/hv/hyperv_vmbus.h b/drivers/hv/hyperv_vmbus.h
index 26ea161a6876..e657197a027a 100644
--- a/drivers/hv/hyperv_vmbus.h
+++ b/drivers/hv/hyperv_vmbus.h
@@ -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);
diff --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c
index a30c70adf9a0..ce9974bf683f 100644
--- a/drivers/hv/vmbus_drv.c
+++ b/drivers/hv/vmbus_drv.c
@@ -2089,6 +2089,51 @@ acpi_walk_err:
 	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 const struct acpi_device_id vmbus_acpi_device_ids[] = {
 };
 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 struct acpi_driver vmbus_acpi_driver = {
 		.add = vmbus_acpi_add,
 		.remove = vmbus_acpi_remove,
 	},
+	.drv.pm = &vmbus_bus_pm,
 };
 
 static void hv_kexec_handler(void)