- Most of the commits here are work to enable host-initiated hibernation

support by Dexuan Cui.
 - Fix for a warning shown when host sends non-aligned balloon requests
 by Tianyu Lan.
 -----BEGIN PGP SIGNATURE-----
 
 iQIzBAABCgAdFiEE4n5dijQDou9mhzu83qZv95d3LNwFAl43g98ACgkQ3qZv95d3
 LNzKrw/+LrlCrzsmFuH/0drGn+Y6UpaOUMY5SMFZVmkjWRg9CmEugO6vUn1KEEIX
 lx2JkamXmF6HMZ+xoy8b1QrZAO7ueBq7Nqe4UQuWPfA2MoAjQbFpCl/SP9r8cNYu
 3qBTP2zfay1qt0LyAC5LH/uXnm2e++LTFG/mnA0GYlt9e750LlgsjcsZrsNUBo0l
 yO56219/IBOIEI1LQLAN1q3rwFHnUWYbSY5HVSZBOwjDtTHwK64G45nKFNSnIC1h
 sFg6czDIPcYBGPzvSHcC4HJsRCddaqcBdt2O1mlXo0UJJXkhmdXx6o4W5DCP9BSD
 FzJIzU5NjGuPnUrQUBW04aH7IoIZLXOMhyZoX14BDswwNNPkAuWAmsDzwTP8irHH
 EvaH51c9RO34EkPF+2CgcT57+58KDL1NDOtak2gkOisBtw4SJgozz3vt2r5lZ/2b
 4vhho0i7tZcQvMsEwR0ltMsRabMJpO07dgc3OZv2m3s75AKvPI8wtqxUS9N0smu4
 dQ+wAYgjfiuvOJ1oLbOOiFWDGAuxNkttilN3h5ZYYJfZ1FamkwATa3xkmmV8MgEh
 lWj1MbOssEedUBG3asChJ+pjfdI19Pk9H5YNT0TIgSMUt5YFF6ZpP3RQURlDxhmG
 BxQyft0dua6Ra5MSl11gl4p90PJC5lbknwTToFD3hSPdzcYIr8U=
 =3tZ1
 -----END PGP SIGNATURE-----

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

Pull Hyper-V updates from Sasha Levin:

 - Most of the commits here are work to enable host-initiated
   hibernation support by Dexuan Cui.

 - Fix for a warning shown when host sends non-aligned balloon requests
   by Tianyu Lan.

* tag 'hyperv-next-signed' of git://git.kernel.org/pub/scm/linux/kernel/git/hyperv/linux:
  hv_utils: Add the support of hibernation
  hv_utils: Support host-initiated hibernation request
  hv_utils: Support host-initiated restart request
  Tools: hv: Reopen the devices if read() or write() returns errors
  video: hyperv: hyperv_fb: Use physical memory for fb on HyperV Gen 1 VMs.
  Drivers: hv: vmbus: Ignore CHANNELMSG_TL_CONNECT_RESULT(23)
  video: hyperv_fb: Fix hibernation for the deferred IO feature
  Input: hyperv-keyboard: Add the support of hibernation
  hv_balloon: Balloon up according to request page number

drivers/hv/channel_mgmt.c

@@ -1351,6 +1351,8 @@ channel_message_table[CHANNELMSG_COUNT] = {
 	{ CHANNELMSG_19,			0, NULL },
 	{ CHANNELMSG_20,			0, NULL },
 	{ CHANNELMSG_TL_CONNECT_REQUEST,	0, NULL },
+	{ CHANNELMSG_22,			0, NULL },
+	{ CHANNELMSG_TL_CONNECT_RESULT,		0, NULL },
 };
 
 /*
@@ -1362,25 +1364,16 @@ void vmbus_onmessage(void *context)
 {
 	struct hv_message *msg = context;
 	struct vmbus_channel_message_header *hdr;
-	int size;
 
 	hdr = (struct vmbus_channel_message_header *)msg->u.payload;
-	size = msg->header.payload_size;
 
 	trace_vmbus_on_message(hdr);
 
-	if (hdr->msgtype >= CHANNELMSG_COUNT) {
+	/*
-		pr_err("Received invalid channel message type %d size %d\n",
+	 * vmbus_on_msg_dpc() makes sure the hdr->msgtype here can not go
-			   hdr->msgtype, size);
+	 * out of bound and the message_handler pointer can not be NULL.
-		print_hex_dump_bytes("", DUMP_PREFIX_NONE,
+	 */
-				     (unsigned char *)msg->u.payload, size);
-		return;
-	}
-
-	if (channel_message_table[hdr->msgtype].message_handler)
 	channel_message_table[hdr->msgtype].message_handler(hdr);
-	else
-		pr_err("Unhandled channel message type %d\n", hdr->msgtype);
 }
 
 /*

drivers/hv/hv_balloon.c

@@ -1217,10 +1217,7 @@ static unsigned int alloc_balloon_pages(struct hv_dynmem_device *dm,
 	unsigned int i, j;
 	struct page *pg;
 
-	if (num_pages < alloc_unit)
+	for (i = 0; i < num_pages / alloc_unit; i++) {
-		return 0;
-
-	for (i = 0; (i * alloc_unit) < num_pages; i++) {
 		if (bl_resp->hdr.size + sizeof(union dm_mem_page_range) >
 			HV_HYP_PAGE_SIZE)
 			return i * alloc_unit;
@@ -1258,7 +1255,7 @@ static unsigned int alloc_balloon_pages(struct hv_dynmem_device *dm,
 
 	}
 
-	return num_pages;
+	return i * alloc_unit;
 }
 
 static void balloon_up(struct work_struct *dummy)
@@ -1273,9 +1270,6 @@ static void balloon_up(struct work_struct *dummy)
 	long avail_pages;
 	unsigned long floor;
 
-	/* The host balloons pages in 2M granularity. */
-	WARN_ON_ONCE(num_pages % PAGES_IN_2M != 0);
-
 	/*
 	 * We will attempt 2M allocations. However, if we fail to
 	 * allocate 2M chunks, we will go back to PAGE_SIZE allocations.
@@ -1285,14 +1279,13 @@ static void balloon_up(struct work_struct *dummy)
 	avail_pages = si_mem_available();
 	floor = compute_balloon_floor();
 
-	/* Refuse to balloon below the floor, keep the 2M granularity. */
+	/* Refuse to balloon below the floor. */
 	if (avail_pages < num_pages || avail_pages - num_pages < floor) {
 		pr_warn("Balloon request will be partially fulfilled. %s\n",
 			avail_pages < num_pages ? "Not enough memory." :
 			"Balloon floor reached.");
 
 		num_pages = avail_pages > floor ? (avail_pages - floor) : 0;
-		num_pages -= num_pages % PAGES_IN_2M;
 	}
 
 	while (!done) {

drivers/hv/hv_fcopy.c

@@ -346,9 +346,61 @@ int hv_fcopy_init(struct hv_util_service *srv)
 	return 0;
 }
 
+static void hv_fcopy_cancel_work(void)
+{
+	cancel_delayed_work_sync(&fcopy_timeout_work);
+	cancel_work_sync(&fcopy_send_work);
+}
+
+int hv_fcopy_pre_suspend(void)
+{
+	struct vmbus_channel *channel = fcopy_transaction.recv_channel;
+	struct hv_fcopy_hdr *fcopy_msg;
+
+	/*
+	 * Fake a CANCEL_FCOPY message for the user space daemon in case the
+	 * daemon is in the middle of copying some file. It doesn't matter if
+	 * there is already a message pending to be delivered to the user
+	 * space since we force fcopy_transaction.state to be HVUTIL_READY, so
+	 * the user space daemon's write() will fail with EINVAL (see
+	 * fcopy_on_msg()), and the daemon will reset the device by closing
+	 * and re-opening it.
+	 */
+	fcopy_msg = kzalloc(sizeof(*fcopy_msg), GFP_KERNEL);
+	if (!fcopy_msg)
+		return -ENOMEM;
+
+	tasklet_disable(&channel->callback_event);
+
+	fcopy_msg->operation = CANCEL_FCOPY;
+
+	hv_fcopy_cancel_work();
+
+	/* We don't care about the return value. */
+	hvutil_transport_send(hvt, fcopy_msg, sizeof(*fcopy_msg), NULL);
+
+	kfree(fcopy_msg);
+
+	fcopy_transaction.state = HVUTIL_READY;
+
+	/* tasklet_enable() will be called in hv_fcopy_pre_resume(). */
+	return 0;
+}
+
+int hv_fcopy_pre_resume(void)
+{
+	struct vmbus_channel *channel = fcopy_transaction.recv_channel;
+
+	tasklet_enable(&channel->callback_event);
+
+	return 0;
+}
+
 void hv_fcopy_deinit(void)
 {
 	fcopy_transaction.state = HVUTIL_DEVICE_DYING;
-	cancel_delayed_work_sync(&fcopy_timeout_work);
+
+	hv_fcopy_cancel_work();
+
 	hvutil_transport_destroy(hvt);
 }

drivers/hv/hv_kvp.c

@@ -758,11 +758,50 @@ hv_kvp_init(struct hv_util_service *srv)
 	return 0;
 }
 
-void hv_kvp_deinit(void)
+static void hv_kvp_cancel_work(void)
 {
-	kvp_transaction.state = HVUTIL_DEVICE_DYING;
 	cancel_delayed_work_sync(&kvp_host_handshake_work);
 	cancel_delayed_work_sync(&kvp_timeout_work);
 	cancel_work_sync(&kvp_sendkey_work);
+}
+
+int hv_kvp_pre_suspend(void)
+{
+	struct vmbus_channel *channel = kvp_transaction.recv_channel;
+
+	tasklet_disable(&channel->callback_event);
+
+	/*
+	 * If there is a pending transtion, it's unnecessary to tell the host
+	 * that the transaction will fail, because that is implied when
+	 * util_suspend() calls vmbus_close() later.
+	 */
+	hv_kvp_cancel_work();
+
+	/*
+	 * Forece the state to READY to handle the ICMSGTYPE_NEGOTIATE message
+	 * later. The user space daemon may go out of order and its write()
+	 * may fail with EINVAL: this doesn't matter since the daemon will
+	 * reset the device by closing and re-opening it.
+	 */
+	kvp_transaction.state = HVUTIL_READY;
+	return 0;
+}
+
+int hv_kvp_pre_resume(void)
+{
+	struct vmbus_channel *channel = kvp_transaction.recv_channel;
+
+	tasklet_enable(&channel->callback_event);
+
+	return 0;
+}
+
+void hv_kvp_deinit(void)
+{
+	kvp_transaction.state = HVUTIL_DEVICE_DYING;
+
+	hv_kvp_cancel_work();
+
 	hvutil_transport_destroy(hvt);
 }

drivers/hv/hv_snapshot.c

@@ -379,10 +379,61 @@ hv_vss_init(struct hv_util_service *srv)
 	return 0;
 }
 
+static void hv_vss_cancel_work(void)
+{
+	cancel_delayed_work_sync(&vss_timeout_work);
+	cancel_work_sync(&vss_handle_request_work);
+}
+
+int hv_vss_pre_suspend(void)
+{
+	struct vmbus_channel *channel = vss_transaction.recv_channel;
+	struct hv_vss_msg *vss_msg;
+
+	/*
+	 * Fake a THAW message for the user space daemon in case the daemon
+	 * has frozen the file systems. It doesn't matter if there is already
+	 * a message pending to be delivered to the user space since we force
+	 * vss_transaction.state to be HVUTIL_READY, so the user space daemon's
+	 * write() will fail with EINVAL (see vss_on_msg()), and the daemon
+	 * will reset the device by closing and re-opening it.
+	 */
+	vss_msg = kzalloc(sizeof(*vss_msg), GFP_KERNEL);
+	if (!vss_msg)
+		return -ENOMEM;
+
+	tasklet_disable(&channel->callback_event);
+
+	vss_msg->vss_hdr.operation = VSS_OP_THAW;
+
+	/* Cancel any possible pending work. */
+	hv_vss_cancel_work();
+
+	/* We don't care about the return value. */
+	hvutil_transport_send(hvt, vss_msg, sizeof(*vss_msg), NULL);
+
+	kfree(vss_msg);
+
+	vss_transaction.state = HVUTIL_READY;
+
+	/* tasklet_enable() will be called in hv_vss_pre_resume(). */
+	return 0;
+}
+
+int hv_vss_pre_resume(void)
+{
+	struct vmbus_channel *channel = vss_transaction.recv_channel;
+
+	tasklet_enable(&channel->callback_event);
+
+	return 0;
+}
+
 void hv_vss_deinit(void)
 {
 	vss_transaction.state = HVUTIL_DEVICE_DYING;
-	cancel_delayed_work_sync(&vss_timeout_work);
+
-	cancel_work_sync(&vss_handle_request_work);
+	hv_vss_cancel_work();
+
 	hvutil_transport_destroy(hvt);
 }

drivers/hv/hv_util.c

@@ -24,6 +24,10 @@
 
 #define SD_MAJOR	3
 #define SD_MINOR	0
+#define SD_MINOR_1	1
+#define SD_MINOR_2	2
+#define SD_VERSION_3_1	(SD_MAJOR << 16 | SD_MINOR_1)
+#define SD_VERSION_3_2	(SD_MAJOR << 16 | SD_MINOR_2)
 #define SD_VERSION	(SD_MAJOR << 16 | SD_MINOR)
 
 #define SD_MAJOR_1	1
@@ -50,8 +54,10 @@ static int sd_srv_version;
 static int ts_srv_version;
 static int hb_srv_version;
 
-#define SD_VER_COUNT 2
+#define SD_VER_COUNT 4
 static const int sd_versions[] = {
+	SD_VERSION_3_2,
+	SD_VERSION_3_1,
 	SD_VERSION,
 	SD_VERSION_1
 };
@@ -75,18 +81,56 @@ static const int fw_versions[] = {
 	UTIL_WS2K8_FW_VERSION
 };
 
+/*
+ * Send the "hibernate" udev event in a thread context.
+ */
+struct hibernate_work_context {
+	struct work_struct work;
+	struct hv_device *dev;
+};
+
+static struct hibernate_work_context hibernate_context;
+static bool hibernation_supported;
+
+static void send_hibernate_uevent(struct work_struct *work)
+{
+	char *uevent_env[2] = { "EVENT=hibernate", NULL };
+	struct hibernate_work_context *ctx;
+
+	ctx = container_of(work, struct hibernate_work_context, work);
+
+	kobject_uevent_env(&ctx->dev->device.kobj, KOBJ_CHANGE, uevent_env);
+
+	pr_info("Sent hibernation uevent\n");
+}
+
+static int hv_shutdown_init(struct hv_util_service *srv)
+{
+	struct vmbus_channel *channel = srv->channel;
+
+	INIT_WORK(&hibernate_context.work, send_hibernate_uevent);
+	hibernate_context.dev = channel->device_obj;
+
+	hibernation_supported = hv_is_hibernation_supported();
+
+	return 0;
+}
+
 static void shutdown_onchannelcallback(void *context);
 static struct hv_util_service util_shutdown = {
 	.util_cb = shutdown_onchannelcallback,
+	.util_init = hv_shutdown_init,
 };
 
 static int hv_timesync_init(struct hv_util_service *srv);
+static int hv_timesync_pre_suspend(void);
 static void hv_timesync_deinit(void);
 
 static void timesync_onchannelcallback(void *context);
 static struct hv_util_service util_timesynch = {
 	.util_cb = timesync_onchannelcallback,
 	.util_init = hv_timesync_init,
+	.util_pre_suspend = hv_timesync_pre_suspend,
 	.util_deinit = hv_timesync_deinit,
 };
 
@@ -98,18 +142,24 @@ static struct hv_util_service util_heartbeat = {
 static struct hv_util_service util_kvp = {
 	.util_cb = hv_kvp_onchannelcallback,
 	.util_init = hv_kvp_init,
+	.util_pre_suspend = hv_kvp_pre_suspend,
+	.util_pre_resume = hv_kvp_pre_resume,
 	.util_deinit = hv_kvp_deinit,
 };
 
 static struct hv_util_service util_vss = {
 	.util_cb = hv_vss_onchannelcallback,
 	.util_init = hv_vss_init,
+	.util_pre_suspend = hv_vss_pre_suspend,
+	.util_pre_resume = hv_vss_pre_resume,
 	.util_deinit = hv_vss_deinit,
 };
 
 static struct hv_util_service util_fcopy = {
 	.util_cb = hv_fcopy_onchannelcallback,
 	.util_init = hv_fcopy_init,
+	.util_pre_suspend = hv_fcopy_pre_suspend,
+	.util_pre_resume = hv_fcopy_pre_resume,
 	.util_deinit = hv_fcopy_deinit,
 };
 
@@ -118,17 +168,27 @@ static void perform_shutdown(struct work_struct *dummy)
 	orderly_poweroff(true);
 }
 
+static void perform_restart(struct work_struct *dummy)
+{
+	orderly_reboot();
+}
+
 /*
  * Perform the shutdown operation in a thread context.
  */
 static DECLARE_WORK(shutdown_work, perform_shutdown);
 
+/*
+ * Perform the restart operation in a thread context.
+ */
+static DECLARE_WORK(restart_work, perform_restart);
+
 static void shutdown_onchannelcallback(void *context)
 {
 	struct vmbus_channel *channel = context;
+	struct work_struct *work = NULL;
 	u32 recvlen;
 	u64 requestid;
-	bool execute_shutdown = false;
 	u8  *shut_txf_buf = util_shutdown.recv_buffer;
 
 	struct shutdown_msg_data *shutdown_msg;
@@ -157,19 +217,37 @@ static void shutdown_onchannelcallback(void *context)
 					sizeof(struct vmbuspipe_hdr) +
 					sizeof(struct icmsg_hdr)];
 
+			/*
+			 * shutdown_msg->flags can be 0(shut down), 2(reboot),
+			 * or 4(hibernate). It may bitwise-OR 1, which means
+			 * performing the request by force. Linux always tries
+			 * to perform the request by force.
+			 */
 			switch (shutdown_msg->flags) {
 			case 0:
 			case 1:
 				icmsghdrp->status = HV_S_OK;
-				execute_shutdown = true;
+				work = &shutdown_work;
-
 				pr_info("Shutdown request received -"
 					    " graceful shutdown initiated\n");
 				break;
+			case 2:
+			case 3:
+				icmsghdrp->status = HV_S_OK;
+				work = &restart_work;
+				pr_info("Restart request received -"
+					    " graceful restart initiated\n");
+				break;
+			case 4:
+			case 5:
+				pr_info("Hibernation request received\n");
+				icmsghdrp->status = hibernation_supported ?
+					HV_S_OK : HV_E_FAIL;
+				if (hibernation_supported)
+					work = &hibernate_context.work;
+				break;
 			default:
 				icmsghdrp->status = HV_E_FAIL;
-				execute_shutdown = false;
-
 				pr_info("Shutdown request received -"
 					    " Invalid request\n");
 				break;
@@ -184,8 +262,8 @@ static void shutdown_onchannelcallback(void *context)
 				       VM_PKT_DATA_INBAND, 0);
 	}
 
-	if (execute_shutdown == true)
+	if (work)
-		schedule_work(&shutdown_work);
+		schedule_work(work);
 }
 
 /*
@@ -441,6 +519,44 @@ static int util_remove(struct hv_device *dev)
 	return 0;
 }
 
+/*
+ * When we're in util_suspend(), all the userspace processes have been frozen
+ * (refer to hibernate() -> freeze_processes()). The userspace is thawed only
+ * after the whole resume procedure, including util_resume(), finishes.
+ */
+static int util_suspend(struct hv_device *dev)
+{
+	struct hv_util_service *srv = hv_get_drvdata(dev);
+	int ret = 0;
+
+	if (srv->util_pre_suspend) {
+		ret = srv->util_pre_suspend();
+		if (ret)
+			return ret;
+	}
+
+	vmbus_close(dev->channel);
+
+	return 0;
+}
+
+static int util_resume(struct hv_device *dev)
+{
+	struct hv_util_service *srv = hv_get_drvdata(dev);
+	int ret = 0;
+
+	if (srv->util_pre_resume) {
+		ret = srv->util_pre_resume();
+		if (ret)
+			return ret;
+	}
+
+	ret = vmbus_open(dev->channel, 4 * HV_HYP_PAGE_SIZE,
+			 4 * HV_HYP_PAGE_SIZE, NULL, 0, srv->util_cb,
+			 dev->channel);
+	return ret;
+}
+
 static const struct hv_vmbus_device_id id_table[] = {
 	/* Shutdown guid */
 	{ HV_SHUTDOWN_GUID,
@@ -477,6 +593,8 @@ static  struct hv_driver util_drv = {
 	.id_table = id_table,
 	.probe =  util_probe,
 	.remove =  util_remove,
+	.suspend = util_suspend,
+	.resume =  util_resume,
 	.driver = {
 		.probe_type = PROBE_PREFER_ASYNCHRONOUS,
 	},
@@ -546,11 +664,23 @@ static int hv_timesync_init(struct hv_util_service *srv)
 	return 0;
 }
 
+static void hv_timesync_cancel_work(void)
+{
+	cancel_work_sync(&adj_time_work);
+}
+
+static int hv_timesync_pre_suspend(void)
+{
+	hv_timesync_cancel_work();
+	return 0;
+}
+
 static void hv_timesync_deinit(void)
 {
 	if (hv_ptp_clock)
 		ptp_clock_unregister(hv_ptp_clock);
-	cancel_work_sync(&adj_time_work);
+
+	hv_timesync_cancel_work();
 }
 
 static int __init init_hyperv_utils(void)

drivers/hv/hyperv_vmbus.h

@@ -352,14 +352,20 @@ void vmbus_on_msg_dpc(unsigned long data);
 
 int hv_kvp_init(struct hv_util_service *srv);
 void hv_kvp_deinit(void);
+int hv_kvp_pre_suspend(void);
+int hv_kvp_pre_resume(void);
 void hv_kvp_onchannelcallback(void *context);
 
 int hv_vss_init(struct hv_util_service *srv);
 void hv_vss_deinit(void);
+int hv_vss_pre_suspend(void);
+int hv_vss_pre_resume(void);
 void hv_vss_onchannelcallback(void *context);
 
 int hv_fcopy_init(struct hv_util_service *srv);
 void hv_fcopy_deinit(void);
+int hv_fcopy_pre_suspend(void);
+int hv_fcopy_pre_resume(void);
 void hv_fcopy_onchannelcallback(void *context);
 void vmbus_initiate_unload(bool crash);
 

drivers/hv/vmbus_drv.c

@@ -1033,6 +1033,10 @@ void vmbus_on_msg_dpc(unsigned long data)
 	}
 
 	entry = &channel_message_table[hdr->msgtype];
+
+	if (!entry->message_handler)
+		goto msg_handled;
+
 	if (entry->handler_type	== VMHT_BLOCKING) {
 		ctx = kmalloc(sizeof(*ctx), GFP_ATOMIC);
 		if (ctx == NULL)

drivers/input/serio/hyperv-keyboard.c

@@ -259,6 +259,8 @@ static int hv_kbd_connect_to_vsp(struct hv_device *hv_dev)
 	u32 proto_status;
 	int error;
 
+	reinit_completion(&kbd_dev->wait_event);
+
 	request = &kbd_dev->protocol_req;
 	memset(request, 0, sizeof(struct synth_kbd_protocol_request));
 	request->header.type = __cpu_to_le32(SYNTH_KBD_PROTOCOL_REQUEST);
@@ -380,6 +382,29 @@ static int hv_kbd_remove(struct hv_device *hv_dev)
 	return 0;
 }
 
+static int hv_kbd_suspend(struct hv_device *hv_dev)
+{
+	vmbus_close(hv_dev->channel);
+
+	return 0;
+}
+
+static int hv_kbd_resume(struct hv_device *hv_dev)
+{
+	int ret;
+
+	ret = vmbus_open(hv_dev->channel,
+			 KBD_VSC_SEND_RING_BUFFER_SIZE,
+			 KBD_VSC_RECV_RING_BUFFER_SIZE,
+			 NULL, 0,
+			 hv_kbd_on_channel_callback,
+			 hv_dev);
+	if (ret == 0)
+		ret = hv_kbd_connect_to_vsp(hv_dev);
+
+	return ret;
+}
+
 static const struct hv_vmbus_device_id id_table[] = {
 	/* Keyboard guid */
 	{ HV_KBD_GUID, },
@@ -393,6 +418,8 @@ static struct  hv_driver hv_kbd_drv = {
 	.id_table = id_table,
 	.probe = hv_kbd_probe,
 	.remove = hv_kbd_remove,
+	.suspend = hv_kbd_suspend,
+	.resume = hv_kbd_resume,
 	.driver = {
 		.probe_type = PROBE_PREFER_ASYNCHRONOUS,
 	},

drivers/video/fbdev/Kconfig

@@ -2215,6 +2215,7 @@ config FB_HYPERV
 	select FB_CFB_COPYAREA
 	select FB_CFB_IMAGEBLIT
 	select FB_DEFERRED_IO
+	select DMA_CMA if HAVE_DMA_CONTIGUOUS && CMA
 	help
 	  This framebuffer driver supports Microsoft Hyper-V Synthetic Video.
 

drivers/video/fbdev/hyperv_fb.c

@@ -31,6 +31,16 @@
  * "set-vmvideo" command. For example
  *     set-vmvideo -vmname name -horizontalresolution:1920 \
  * -verticalresolution:1200 -resolutiontype single
+ *
+ * Gen 1 VMs also support direct using VM's physical memory for framebuffer.
+ * It could improve the efficiency and performance for framebuffer and VM.
+ * This requires to allocate contiguous physical memory from Linux kernel's
+ * CMA memory allocator. To enable this, supply a kernel parameter to give
+ * enough memory space to CMA allocator for framebuffer. For example:
+ *    cma=130m
+ * This gives 130MB memory to CMA allocator that can be allocated to
+ * framebuffer. For reference, 8K resolution (7680x4320) takes about
+ * 127MB memory.
  */
 
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
@@ -228,7 +238,6 @@ struct synthvid_msg {
 } __packed;
 
 
-
 /* FB driver definitions and structures */
 #define HVFB_WIDTH 1152 /* default screen width */
 #define HVFB_HEIGHT 864 /* default screen height */
@@ -258,12 +267,15 @@ struct hvfb_par {
 	/* If true, the VSC notifies the VSP on every framebuffer change */
 	bool synchronous_fb;
 
+	/* If true, need to copy from deferred IO mem to framebuffer mem */
+	bool need_docopy;
+
 	struct notifier_block hvfb_panic_nb;
 
 	/* Memory for deferred IO and frame buffer itself */
 	unsigned char *dio_vp;
 	unsigned char *mmio_vp;
-	unsigned long mmio_pp;
+	phys_addr_t mmio_pp;
 
 	/* Dirty rectangle, protected by delayed_refresh_lock */
 	int x1, y1, x2, y2;
@@ -434,7 +446,7 @@ static void synthvid_deferred_io(struct fb_info *p,
 		maxy = max_t(int, maxy, y2);
 
 		/* Copy from dio space to mmio address */
-		if (par->fb_ready)
+		if (par->fb_ready && par->need_docopy)
 			hvfb_docopy(par, start, PAGE_SIZE);
 	}
 
@@ -751,12 +763,12 @@ static void hvfb_update_work(struct work_struct *w)
 		return;
 
 	/* Copy the dirty rectangle to frame buffer memory */
-	for (j = y1; j < y2; j++) {
+	if (par->need_docopy)
+		for (j = y1; j < y2; j++)
 			hvfb_docopy(par,
 				    j * info->fix.line_length +
 				    (x1 * screen_depth / 8),
 				    (x2 - x1) * screen_depth / 8);
-	}
 
 	/* Refresh */
 	if (par->fb_ready && par->update)
@@ -801,6 +813,7 @@ static int hvfb_on_panic(struct notifier_block *nb,
 	par = container_of(nb, struct hvfb_par, hvfb_panic_nb);
 	par->synchronous_fb = true;
 	info = par->info;
+	if (par->need_docopy)
 		hvfb_docopy(par, 0, dio_fb_size);
 	synthvid_update(info, 0, 0, INT_MAX, INT_MAX);
 
@@ -940,6 +953,62 @@ static void hvfb_get_option(struct fb_info *info)
 	return;
 }
 
+/*
+ * Allocate enough contiguous physical memory.
+ * Return physical address if succeeded or -1 if failed.
+ */
+static phys_addr_t hvfb_get_phymem(struct hv_device *hdev,
+				   unsigned int request_size)
+{
+	struct page *page = NULL;
+	dma_addr_t dma_handle;
+	void *vmem;
+	phys_addr_t paddr = 0;
+	unsigned int order = get_order(request_size);
+
+	if (request_size == 0)
+		return -1;
+
+	if (order < MAX_ORDER) {
+		/* Call alloc_pages if the size is less than 2^MAX_ORDER */
+		page = alloc_pages(GFP_KERNEL | __GFP_ZERO, order);
+		if (!page)
+			return -1;
+
+		paddr = (page_to_pfn(page) << PAGE_SHIFT);
+	} else {
+		/* Allocate from CMA */
+		hdev->device.coherent_dma_mask = DMA_BIT_MASK(64);
+
+		vmem = dma_alloc_coherent(&hdev->device,
+					  round_up(request_size, PAGE_SIZE),
+					  &dma_handle,
+					  GFP_KERNEL | __GFP_NOWARN);
+
+		if (!vmem)
+			return -1;
+
+		paddr = virt_to_phys(vmem);
+	}
+
+	return paddr;
+}
+
+/* Release contiguous physical memory */
+static void hvfb_release_phymem(struct hv_device *hdev,
+				phys_addr_t paddr, unsigned int size)
+{
+	unsigned int order = get_order(size);
+
+	if (order < MAX_ORDER)
+		__free_pages(pfn_to_page(paddr >> PAGE_SHIFT), order);
+	else
+		dma_free_coherent(&hdev->device,
+				  round_up(size, PAGE_SIZE),
+				  phys_to_virt(paddr),
+				  paddr);
+}
+
 
 /* Get framebuffer memory from Hyper-V video pci space */
 static int hvfb_getmem(struct hv_device *hdev, struct fb_info *info)
@@ -949,8 +1018,54 @@ static int hvfb_getmem(struct hv_device *hdev, struct fb_info *info)
 	void __iomem *fb_virt;
 	int gen2vm = efi_enabled(EFI_BOOT);
 	resource_size_t pot_start, pot_end;
+	phys_addr_t paddr;
 	int ret;
 
+	info->apertures = alloc_apertures(1);
+	if (!info->apertures)
+		return -ENOMEM;
+
+	if (!gen2vm) {
+		pdev = pci_get_device(PCI_VENDOR_ID_MICROSOFT,
+			PCI_DEVICE_ID_HYPERV_VIDEO, NULL);
+		if (!pdev) {
+			pr_err("Unable to find PCI Hyper-V video\n");
+			kfree(info->apertures);
+			return -ENODEV;
+		}
+
+		info->apertures->ranges[0].base = pci_resource_start(pdev, 0);
+		info->apertures->ranges[0].size = pci_resource_len(pdev, 0);
+
+		/*
+		 * For Gen 1 VM, we can directly use the contiguous memory
+		 * from VM. If we succeed, deferred IO happens directly
+		 * on this allocated framebuffer memory, avoiding extra
+		 * memory copy.
+		 */
+		paddr = hvfb_get_phymem(hdev, screen_fb_size);
+		if (paddr != (phys_addr_t) -1) {
+			par->mmio_pp = paddr;
+			par->mmio_vp = par->dio_vp = __va(paddr);
+
+			info->fix.smem_start = paddr;
+			info->fix.smem_len = screen_fb_size;
+			info->screen_base = par->mmio_vp;
+			info->screen_size = screen_fb_size;
+
+			par->need_docopy = false;
+			goto getmem_done;
+		}
+		pr_info("Unable to allocate enough contiguous physical memory on Gen 1 VM. Using MMIO instead.\n");
+	} else {
+		info->apertures->ranges[0].base = screen_info.lfb_base;
+		info->apertures->ranges[0].size = screen_info.lfb_size;
+	}
+
+	/*
+	 * Cannot use the contiguous physical memory.
+	 * Allocate mmio space for framebuffer.
+	 */
 	dio_fb_size =
 		screen_width * screen_height * screen_depth / 8;
 
@@ -958,13 +1073,6 @@ static int hvfb_getmem(struct hv_device *hdev, struct fb_info *info)
 		pot_start = 0;
 		pot_end = -1;
 	} else {
-		pdev = pci_get_device(PCI_VENDOR_ID_MICROSOFT,
-			      PCI_DEVICE_ID_HYPERV_VIDEO, NULL);
-		if (!pdev) {
-			pr_err("Unable to find PCI Hyper-V video\n");
-			return -ENODEV;
-		}
-
 		if (!(pci_resource_flags(pdev, 0) & IORESOURCE_MEM) ||
 		    pci_resource_len(pdev, 0) < screen_fb_size) {
 			pr_err("Resource not available or (0x%lx < 0x%lx)\n",
@@ -993,20 +1101,6 @@ static int hvfb_getmem(struct hv_device *hdev, struct fb_info *info)
 	if (par->dio_vp == NULL)
 		goto err3;
 
-	info->apertures = alloc_apertures(1);
-	if (!info->apertures)
-		goto err4;
-
-	if (gen2vm) {
-		info->apertures->ranges[0].base = screen_info.lfb_base;
-		info->apertures->ranges[0].size = screen_info.lfb_size;
-		remove_conflicting_framebuffers(info->apertures,
-						KBUILD_MODNAME, false);
-	} else {
-		info->apertures->ranges[0].base = pci_resource_start(pdev, 0);
-		info->apertures->ranges[0].size = pci_resource_len(pdev, 0);
-	}
-
 	/* Physical address of FB device */
 	par->mmio_pp = par->mem->start;
 	/* Virtual address of FB device */
@@ -1017,13 +1111,15 @@ static int hvfb_getmem(struct hv_device *hdev, struct fb_info *info)
 	info->screen_base = par->dio_vp;
 	info->screen_size = dio_fb_size;
 
+getmem_done:
+	remove_conflicting_framebuffers(info->apertures,
+					KBUILD_MODNAME, false);
 	if (!gen2vm)
 		pci_dev_put(pdev);
+	kfree(info->apertures);
 
 	return 0;
 
-err4:
-	vfree(par->dio_vp);
 err3:
 	iounmap(fb_virt);
 err2:
@@ -1032,18 +1128,25 @@ err2:
 err1:
 	if (!gen2vm)
 		pci_dev_put(pdev);
+	kfree(info->apertures);
 
 	return -ENOMEM;
 }
 
 /* Release the framebuffer */
-static void hvfb_putmem(struct fb_info *info)
+static void hvfb_putmem(struct hv_device *hdev, struct fb_info *info)
 {
 	struct hvfb_par *par = info->par;
 
+	if (par->need_docopy) {
 		vfree(par->dio_vp);
 		iounmap(info->screen_base);
 		vmbus_free_mmio(par->mem->start, screen_fb_size);
+	} else {
+		hvfb_release_phymem(hdev, info->fix.smem_start,
+				    screen_fb_size);
+	}
+
 	par->mem = NULL;
 }
 
@@ -1062,6 +1165,7 @@ static int hvfb_probe(struct hv_device *hdev,
 	par = info->par;
 	par->info = info;
 	par->fb_ready = false;
+	par->need_docopy = true;
 	init_completion(&par->wait);
 	INIT_DELAYED_WORK(&par->dwork, hvfb_update_work);
 
@@ -1147,7 +1251,7 @@ static int hvfb_probe(struct hv_device *hdev,
 
 error:
 	fb_deferred_io_cleanup(info);
-	hvfb_putmem(info);
+	hvfb_putmem(hdev, info);
 error2:
 	vmbus_close(hdev->channel);
 error1:
@@ -1177,7 +1281,7 @@ static int hvfb_remove(struct hv_device *hdev)
 	vmbus_close(hdev->channel);
 	hv_set_drvdata(hdev, NULL);
 
-	hvfb_putmem(info);
+	hvfb_putmem(hdev, info);
 	framebuffer_release(info);
 
 	return 0;
@@ -1194,6 +1298,7 @@ static int hvfb_suspend(struct hv_device *hdev)
 	fb_set_suspend(info, 1);
 
 	cancel_delayed_work_sync(&par->dwork);
+	cancel_delayed_work_sync(&info->deferred_work);
 
 	par->update_saved = par->update;
 	par->update = false;
@@ -1227,6 +1332,7 @@ static int hvfb_resume(struct hv_device *hdev)
 	par->fb_ready = true;
 	par->update = par->update_saved;
 
+	schedule_delayed_work(&info->deferred_work, info->fbdefio->delay);
 	schedule_delayed_work(&par->dwork, HVFB_UPDATE_DELAY);
 
 	/* 0 means do resume */

include/linux/hyperv.h

@@ -425,6 +425,8 @@ enum vmbus_channel_message_type {
 	CHANNELMSG_19				= 19,
 	CHANNELMSG_20				= 20,
 	CHANNELMSG_TL_CONNECT_REQUEST		= 21,
+	CHANNELMSG_22				= 22,
+	CHANNELMSG_TL_CONNECT_RESULT		= 23,
 	CHANNELMSG_COUNT
 };
 
@@ -1433,6 +1435,8 @@ struct hv_util_service {
 	void (*util_cb)(void *);
 	int (*util_init)(struct hv_util_service *);
 	void (*util_deinit)(void);
+	int (*util_pre_suspend)(void);
+	int (*util_pre_resume)(void);
 };
 
 struct vmbuspipe_hdr {

tools/hv/hv_fcopy_daemon.c

@@ -80,6 +80,8 @@ static int hv_start_fcopy(struct hv_start_fcopy *smsg)
 
 	error = 0;
 done:
+	if (error)
+		target_fname[0] = '\0';
 	return error;
 }
 
@@ -108,15 +110,29 @@ static int hv_copy_data(struct hv_do_fcopy *cpmsg)
 	return ret;
 }
 
+/*
+ * Reset target_fname to "" in the two below functions for hibernation: if
+ * the fcopy operation is aborted by hibernation, the daemon should remove the
+ * partially-copied file; to achieve this, the hv_utils driver always fakes a
+ * CANCEL_FCOPY message upon suspend, and later when the VM resumes back,
+ * the daemon calls hv_copy_cancel() to remove the file; if a file is copied
+ * successfully before suspend, hv_copy_finished() must reset target_fname to
+ * avoid that the file can be incorrectly removed upon resume, since the faked
+ * CANCEL_FCOPY message is spurious in this case.
+ */
 static int hv_copy_finished(void)
 {
 	close(target_fd);
+	target_fname[0] = '\0';
 	return 0;
 }
 static int hv_copy_cancel(void)
 {
 	close(target_fd);
+	if (strlen(target_fname) > 0) {
 		unlink(target_fname);
+		target_fname[0] = '\0';
+	}
 	return 0;
 
 }
@@ -131,7 +147,7 @@ void print_usage(char *argv[])
 
 int main(int argc, char *argv[])
 {
-	int fcopy_fd;
+	int fcopy_fd = -1;
 	int error;
 	int daemonize = 1, long_index = 0, opt;
 	int version = FCOPY_CURRENT_VERSION;
@@ -141,7 +157,7 @@ int main(int argc, char *argv[])
 		struct hv_do_fcopy copy;
 		__u32 kernel_modver;
 	} buffer = { };
-	int in_handshake = 1;
+	int in_handshake;
 
 	static struct option long_options[] = {
 		{"help",	no_argument,	   0,  'h' },
@@ -170,6 +186,12 @@ int main(int argc, char *argv[])
 	openlog("HV_FCOPY", 0, LOG_USER);
 	syslog(LOG_INFO, "starting; pid is:%d", getpid());
 
+reopen_fcopy_fd:
+	if (fcopy_fd != -1)
+		close(fcopy_fd);
+	/* Remove any possible partially-copied file on error */
+	hv_copy_cancel();
+	in_handshake = 1;
 	fcopy_fd = open("/dev/vmbus/hv_fcopy", O_RDWR);
 
 	if (fcopy_fd < 0) {
@@ -196,7 +218,7 @@ int main(int argc, char *argv[])
 		len = pread(fcopy_fd, &buffer, sizeof(buffer), 0);
 		if (len < 0) {
 			syslog(LOG_ERR, "pread failed: %s", strerror(errno));
-			exit(EXIT_FAILURE);
+			goto reopen_fcopy_fd;
 		}
 
 		if (in_handshake) {
@@ -231,9 +253,14 @@ int main(int argc, char *argv[])
 
 		}
 
+		/*
+		 * pwrite() may return an error due to the faked CANCEL_FCOPY
+		 * message upon hibernation. Ignore the error by resetting the
+		 * dev file, i.e. closing and re-opening it.
+		 */
 		if (pwrite(fcopy_fd, &error, sizeof(int), 0) != sizeof(int)) {
 			syslog(LOG_ERR, "pwrite failed: %s", strerror(errno));
-			exit(EXIT_FAILURE);
+			goto reopen_fcopy_fd;
 		}
 	}
 }

tools/hv/hv_kvp_daemon.c

@@ -76,7 +76,7 @@ enum {
 	DNS
 };
 
-static int in_hand_shake = 1;
+static int in_hand_shake;
 
 static char *os_name = "";
 static char *os_major = "";
@@ -1360,7 +1360,7 @@ void print_usage(char *argv[])
 
 int main(int argc, char *argv[])
 {
-	int kvp_fd, len;
+	int kvp_fd = -1, len;
 	int error;
 	struct pollfd pfd;
 	char    *p;
@@ -1400,14 +1400,6 @@ int main(int argc, char *argv[])
 	openlog("KVP", 0, LOG_USER);
 	syslog(LOG_INFO, "KVP starting; pid is:%d", getpid());
 
-	kvp_fd = open("/dev/vmbus/hv_kvp", O_RDWR | O_CLOEXEC);
-
-	if (kvp_fd < 0) {
-		syslog(LOG_ERR, "open /dev/vmbus/hv_kvp failed; error: %d %s",
-			errno, strerror(errno));
-		exit(EXIT_FAILURE);
-	}
-
 	/*
 	 * Retrieve OS release information.
 	 */
@@ -1423,6 +1415,18 @@ int main(int argc, char *argv[])
 		exit(EXIT_FAILURE);
 	}
 
+reopen_kvp_fd:
+	if (kvp_fd != -1)
+		close(kvp_fd);
+	in_hand_shake = 1;
+	kvp_fd = open("/dev/vmbus/hv_kvp", O_RDWR | O_CLOEXEC);
+
+	if (kvp_fd < 0) {
+		syslog(LOG_ERR, "open /dev/vmbus/hv_kvp failed; error: %d %s",
+		       errno, strerror(errno));
+		exit(EXIT_FAILURE);
+	}
+
 	/*
 	 * Register ourselves with the kernel.
 	 */
@@ -1456,9 +1460,7 @@ int main(int argc, char *argv[])
 		if (len != sizeof(struct hv_kvp_msg)) {
 			syslog(LOG_ERR, "read failed; error:%d %s",
 			       errno, strerror(errno));
-
+			goto reopen_kvp_fd;
-			close(kvp_fd);
-			return EXIT_FAILURE;
 		}
 
 		/*
@@ -1617,13 +1619,17 @@ int main(int argc, char *argv[])
 			break;
 		}
 
-		/* Send the value back to the kernel. */
+		/*
+		 * Send the value back to the kernel. Note: the write() may
+		 * return an error due to hibernation; we can ignore the error
+		 * by resetting the dev file, i.e. closing and re-opening it.
+		 */
 kvp_done:
 		len = write(kvp_fd, hv_msg, sizeof(struct hv_kvp_msg));
 		if (len != sizeof(struct hv_kvp_msg)) {
 			syslog(LOG_ERR, "write failed; error: %d %s", errno,
 			       strerror(errno));
-			exit(EXIT_FAILURE);
+			goto reopen_kvp_fd;
 		}
 	}
 

tools/hv/hv_vss_daemon.c

@@ -28,6 +28,8 @@
 #include <stdbool.h>
 #include <dirent.h>
 
+static bool fs_frozen;
+
 /* Don't use syslog() in the function since that can cause write to disk */
 static int vss_do_freeze(char *dir, unsigned int cmd)
 {
@@ -155,17 +157,26 @@ static int vss_operate(int operation)
 			continue;
 		}
 		error |= vss_do_freeze(ent->mnt_dir, cmd);
-		if (error && operation == VSS_OP_FREEZE)
+		if (operation == VSS_OP_FREEZE) {
+			if (error)
 				goto err;
+			fs_frozen = true;
+		}
 	}
 
 	endmntent(mounts);
 
 	if (root_seen) {
 		error |= vss_do_freeze("/", cmd);
-		if (error && operation == VSS_OP_FREEZE)
+		if (operation == VSS_OP_FREEZE) {
+			if (error)
 				goto err;
+			fs_frozen = true;
 		}
+	}
+
+	if (operation == VSS_OP_THAW && !error)
+		fs_frozen = false;
 
 	goto out;
 err:
@@ -175,6 +186,7 @@ err:
 		endmntent(mounts);
 	}
 	vss_operate(VSS_OP_THAW);
+	fs_frozen = false;
 	/* Call syslog after we thaw all filesystems */
 	if (ent)
 		syslog(LOG_ERR, "FREEZE of %s failed; error:%d %s",
@@ -196,13 +208,13 @@ void print_usage(char *argv[])
 
 int main(int argc, char *argv[])
 {
-	int vss_fd, len;
+	int vss_fd = -1, len;
 	int error;
 	struct pollfd pfd;
 	int	op;
 	struct hv_vss_msg vss_msg[1];
 	int daemonize = 1, long_index = 0, opt;
-	int in_handshake = 1;
+	int in_handshake;
 	__u32 kernel_modver;
 
 	static struct option long_options[] = {
@@ -232,6 +244,18 @@ int main(int argc, char *argv[])
 	openlog("Hyper-V VSS", 0, LOG_USER);
 	syslog(LOG_INFO, "VSS starting; pid is:%d", getpid());
 
+reopen_vss_fd:
+	if (vss_fd != -1)
+		close(vss_fd);
+	if (fs_frozen) {
+		if (vss_operate(VSS_OP_THAW) || fs_frozen) {
+			syslog(LOG_ERR, "failed to thaw file system: err=%d",
+			       errno);
+			exit(EXIT_FAILURE);
+		}
+	}
+
+	in_handshake = 1;
 	vss_fd = open("/dev/vmbus/hv_vss", O_RDWR);
 	if (vss_fd < 0) {
 		syslog(LOG_ERR, "open /dev/vmbus/hv_vss failed; error: %d %s",
@@ -284,8 +308,7 @@ int main(int argc, char *argv[])
 		if (len != sizeof(struct hv_vss_msg)) {
 			syslog(LOG_ERR, "read failed; error:%d %s",
 			       errno, strerror(errno));
-			close(vss_fd);
+			goto reopen_vss_fd;
-			return EXIT_FAILURE;
 		}
 
 		op = vss_msg->vss_hdr.operation;
@@ -312,14 +335,18 @@ int main(int argc, char *argv[])
 		default:
 			syslog(LOG_ERR, "Illegal op:%d\n", op);
 		}
+
+		/*
+		 * The write() may return an error due to the faked VSS_OP_THAW
+		 * message upon hibernation. Ignore the error by resetting the
+		 * dev file, i.e. closing and re-opening it.
+		 */
 		vss_msg->error = error;
 		len = write(vss_fd, vss_msg, sizeof(struct hv_vss_msg));
 		if (len != sizeof(struct hv_vss_msg)) {
 			syslog(LOG_ERR, "write failed; error: %d %s", errno,
 			       strerror(errno));
-
+			goto reopen_vss_fd;
-			if (op == VSS_OP_FREEZE)
-				vss_operate(VSS_OP_THAW);
 		}
 	}