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

8 files changed, 306 insertions, 38 deletions

diff --git a/drivers/hv/channel_mgmt.c b/drivers/hv/channel_mgmt.c
index 8eb167540b4f..0370364169c4 100644
--- a/drivers/hv/channel_mgmt.c
+++ b/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",
-			   hdr->msgtype, size);
-		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);
+	/*
+	 * vmbus_on_msg_dpc() makes sure the hdr->msgtype here can not go
+	 * out of bound and the message_handler pointer can not be NULL.
+	 */
+	channel_message_table[hdr->msgtype].message_handler(hdr);
 }
 
 /*
diff --git a/drivers/hv/hv_balloon.c b/drivers/hv/hv_balloon.c
index b155d0052981..a02ce43d778d 100644
--- a/drivers/hv/hv_balloon.c
+++ b/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)
-		return 0;
-
-	for (i = 0; (i * alloc_unit) < num_pages; i++) {
+	for (i = 0; i < num_pages / alloc_unit; 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) {
diff --git a/drivers/hv/hv_fcopy.c b/drivers/hv/hv_fcopy.c
index 08fa4a5de644..bb9ba3f7c794 100644
--- a/drivers/hv/hv_fcopy.c
+++ b/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);
 }
diff --git a/drivers/hv/hv_kvp.c b/drivers/hv/hv_kvp.c
index ae7c028dc5a8..e74b144b8f3d 100644
--- a/drivers/hv/hv_kvp.c
+++ b/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);
 }
diff --git a/drivers/hv/hv_snapshot.c b/drivers/hv/hv_snapshot.c
index 03b6454268b3..1c75b38f0d6d 100644
--- a/drivers/hv/hv_snapshot.c
+++ b/drivers/hv/hv_snapshot.c
@@ -379,10 +379,61 @@ hv_vss_init(struct hv_util_service *srv)
 	return 0;
 }
 
-void hv_vss_deinit(void)
+static void hv_vss_cancel_work(void)
 {
-	vss_transaction.state = HVUTIL_DEVICE_DYING;
 	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;
+
+	hv_vss_cancel_work();
+
 	hvutil_transport_destroy(hvt);
 }
diff --git a/drivers/hv/hv_util.c b/drivers/hv/hv_util.c
index 296f9098c9e4..92ee0fe4c919 100644
--- a/drivers/hv/hv_util.c
+++ b/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)
-		schedule_work(&shutdown_work);
+	if (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)
diff --git a/drivers/hv/hyperv_vmbus.h b/drivers/hv/hyperv_vmbus.h
index 20edcfd3b96c..f5fa3b3c9baf 100644
--- a/drivers/hv/hyperv_vmbus.h
+++ b/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);
 
diff --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c
index 4ef5a66df680..029378c27421 100644
--- a/drivers/hv/vmbus_drv.c
+++ b/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)