Drivers: hv: Some miscellaneous fixes

index 9b9b370..cb1a916 100644
@@ -78,9 +78,11 @@ static void kvp_send_key(struct work_struct *dummy);
 
 static void kvp_respond_to_host(struct hv_kvp_msg *msg, int error);
 static void kvp_timeout_func(struct work_struct *dummy);
+static void kvp_host_handshake_func(struct work_struct *dummy);
 static void kvp_register(int);
 
 static DECLARE_DELAYED_WORK(kvp_timeout_work, kvp_timeout_func);
+static DECLARE_DELAYED_WORK(kvp_host_handshake_work, kvp_host_handshake_func);
 static DECLARE_WORK(kvp_sendkey_work, kvp_send_key);
 
 static const char kvp_devname[] = "vmbus/hv_kvp";

@@ -130,6 +132,11 @@ static void kvp_timeout_func(struct work_struct *dummy)
 	hv_poll_channel(kvp_transaction.recv_channel, kvp_poll_wrapper);
 }
 
+static void kvp_host_handshake_func(struct work_struct *dummy)
+{
+	hv_poll_channel(kvp_transaction.recv_channel, hv_kvp_onchannelcallback);
+}
+
 static int kvp_handle_handshake(struct hv_kvp_msg *msg)
 {
 	switch (msg->kvp_hdr.operation) {

@@ -154,6 +161,12 @@ static int kvp_handle_handshake(struct hv_kvp_msg *msg)
 	pr_debug("KVP: userspace daemon ver. %d registered\n",
 		 KVP_OP_REGISTER);
 	kvp_register(dm_reg_value);
+
+	/*
+	 * If we're still negotiating with the host cancel the timeout
+	 * work to not poll the channel twice.
+	 */
+	cancel_delayed_work_sync(&kvp_host_handshake_work);
 	hv_poll_channel(kvp_transaction.recv_channel, kvp_poll_wrapper);
 
 	return 0;

@@ -594,7 +607,22 @@ void hv_kvp_onchannelcallback(void *context)
 	struct icmsg_negotiate *negop = NULL;
 	int util_fw_version;
 	int kvp_srv_version;
+	static enum {NEGO_NOT_STARTED,
+		     NEGO_IN_PROGRESS,
+		     NEGO_FINISHED} host_negotiatied = NEGO_NOT_STARTED;
 
+	if (host_negotiatied == NEGO_NOT_STARTED &&
+	    kvp_transaction.state < HVUTIL_READY) {
+		/*
+		 * If userspace daemon is not connected and host is asking
+		 * us to negotiate we need to delay to not lose messages.
+		 * This is important for Failover IP setting.
+		 */
+		host_negotiatied = NEGO_IN_PROGRESS;
+		schedule_delayed_work(&kvp_host_handshake_work,
+				      HV_UTIL_NEGO_TIMEOUT * HZ);
+		return;
+	}
 	if (kvp_transaction.state > HVUTIL_READY)
 		return;
 

@@ -672,6 +700,8 @@ void hv_kvp_onchannelcallback(void *context)
 		vmbus_sendpacket(channel, recv_buffer,
 				       recvlen, requestid,
 				       VM_PKT_DATA_INBAND, 0);
+
+		host_negotiatied = NEGO_FINISHED;
 	}
 
 }

@@ -708,6 +738,7 @@ hv_kvp_init(struct hv_util_service *srv)
 void hv_kvp_deinit(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);
 	hvutil_transport_destroy(hvt);

index e5c586f..e5203e4 100644
@@ -36,6 +36,11 @@
 #define HV_UTIL_TIMEOUT 30
 
 /*
+ * Timeout for guest-host handshake for services.
+ */
+#define HV_UTIL_NEGO_TIMEOUT 60
+
+/*
  * The below CPUID leaves are present if VersionAndFeatures.HypervisorPresent
  * is set by CPUID(HVCPUID_VERSION_FEATURES).
  */

index 38b682ba..b6c1211 100644
@@ -597,27 +597,55 @@ static void init_vp_index(struct vmbus_channel *channel, u16 dev_type)
 
 static void vmbus_wait_for_unload(void)
 {
-	int cpu = smp_processor_id();
-	void *page_addr = hv_context.synic_message_page[cpu];
-	struct hv_message *msg = (struct hv_message *)page_addr +
-				  VMBUS_MESSAGE_SINT;
+	int cpu;
+	void *page_addr;
+	struct hv_message *msg;
 	struct vmbus_channel_message_header *hdr;
-	bool unloaded = false;
+	u32 message_type;
 
+	/*
+	 * CHANNELMSG_UNLOAD_RESPONSE is always delivered to the CPU which was
+	 * used for initial contact or to CPU0 depending on host version. When
+	 * we're crashing on a different CPU let's hope that IRQ handler on
+	 * the cpu which receives CHANNELMSG_UNLOAD_RESPONSE is still
+	 * functional and vmbus_unload_response() will complete
+	 * vmbus_connection.unload_event. If not, the last thing we can do is
+	 * read message pages for all CPUs directly.
+	 */
 	while (1) {
-		if (READ_ONCE(msg->header.message_type) == HVMSG_NONE) {
-			mdelay(10);
-			continue;
-		}
+		if (completion_done(&vmbus_connection.unload_event))
+			break;
 
-		hdr = (struct vmbus_channel_message_header *)msg->u.payload;
-		if (hdr->msgtype == CHANNELMSG_UNLOAD_RESPONSE)
-			unloaded = true;
+		for_each_online_cpu(cpu) {
+			page_addr = hv_context.synic_message_page[cpu];
+			msg = (struct hv_message *)page_addr +
+				VMBUS_MESSAGE_SINT;
 
-		vmbus_signal_eom(msg);
+			message_type = READ_ONCE(msg->header.message_type);
+			if (message_type == HVMSG_NONE)
+				continue;
 
-		if (unloaded)
-			break;
+			hdr = (struct vmbus_channel_message_header *)
+				msg->u.payload;
+
+			if (hdr->msgtype == CHANNELMSG_UNLOAD_RESPONSE)
+				complete(&vmbus_connection.unload_event);
+
+			vmbus_signal_eom(msg, message_type);
+		}
+
+		mdelay(10);
+	}
+
+	/*
+	 * We're crashing and already got the UNLOAD_RESPONSE, cleanup all
+	 * maybe-pending messages on all CPUs to be able to receive new
+	 * messages after we reconnect.
+	 */
+	for_each_online_cpu(cpu) {
+		page_addr = hv_context.synic_message_page[cpu];
+		msg = (struct hv_message *)page_addr + VMBUS_MESSAGE_SINT;
+		msg->header.message_type = HVMSG_NONE;
 	}
 }
 

index e5203e4..718b5c7 100644
@@ -625,9 +625,21 @@ extern struct vmbus_channel_message_table_entry
 	channel_message_table[CHANNELMSG_COUNT];
 
 /* Free the message slot and signal end-of-message if required */
-static inline void vmbus_signal_eom(struct hv_message *msg)
+static inline void vmbus_signal_eom(struct hv_message *msg, u32 old_msg_type)
 {
-	msg->header.message_type = HVMSG_NONE;
+	/*
+	 * On crash we're reading some other CPU's message page and we need
+	 * to be careful: this other CPU may already had cleared the header
+	 * and the host may already had delivered some other message there.
+	 * In case we blindly write msg->header.message_type we're going
+	 * to lose it. We can still lose a message of the same type but
+	 * we count on the fact that there can only be one
+	 * CHANNELMSG_UNLOAD_RESPONSE and we don't care about other messages
+	 * on crash.
+	 */
+	if (cmpxchg(&msg->header.message_type, old_msg_type,
+		    HVMSG_NONE) != old_msg_type)
+		return;
 
 	/*
 	 * Make sure the write to MessageType (ie set to

index a29a6c0..952f20f 100644
@@ -712,7 +712,7 @@ static void hv_process_timer_expiration(struct hv_message *msg, int cpu)
 	if (dev->event_handler)
 		dev->event_handler(dev);
 
-	vmbus_signal_eom(msg);
+	vmbus_signal_eom(msg, HVMSG_TIMER_EXPIRED);
 }
 
 void vmbus_on_msg_dpc(unsigned long data)

@@ -724,8 +724,9 @@ void vmbus_on_msg_dpc(unsigned long data)
 	struct vmbus_channel_message_header *hdr;
 	struct vmbus_channel_message_table_entry *entry;
 	struct onmessage_work_context *ctx;
+	u32 message_type = msg->header.message_type;
 
-	if (msg->header.message_type == HVMSG_NONE)
+	if (message_type == HVMSG_NONE)
 		/* no msg */
 		return;
 

@@ -750,7 +751,7 @@ void vmbus_on_msg_dpc(unsigned long data)
 		entry->message_handler(hdr);
 
 msg_handled:
-	vmbus_signal_eom(msg);
+	vmbus_signal_eom(msg, message_type);
 }
 
 static void vmbus_isr(void)

index b853b4b..43af913 100644
@@ -714,7 +714,7 @@ static bool pfn_covered(unsigned long start_pfn, unsigned long pfn_cnt)
 		 * If the pfn range we are dealing with is not in the current
 		 * "hot add block", move on.
 		 */
-		if ((start_pfn >= has->end_pfn))
+		if (start_pfn < has->start_pfn || start_pfn >= has->end_pfn)
 			continue;
 		/*
 		 * If the current hot add-request extends beyond

@@ -768,7 +768,7 @@ static unsigned long handle_pg_range(unsigned long pg_start,
 		 * If the pfn range we are dealing with is not in the current
 		 * "hot add block", move on.
 		 */
-		if ((start_pfn >= has->end_pfn))
+		if (start_pfn < has->start_pfn || start_pfn >= has->end_pfn)
 			continue;
 
 		old_covered_state = has->covered_end_pfn;

index 43af913..df35fb7 100644
@@ -1400,6 +1400,7 @@ static void balloon_onchannelcallback(void *context)
 				 * This is a normal hot-add request specifying
 				 * hot-add memory.
 				 */
+				dm->host_specified_ha_region = false;
 				ha_pg_range = &ha_msg->range;
 				dm->ha_wrk.ha_page_range = *ha_pg_range;
 				dm->ha_wrk.ha_region_range.page_range = 0;