Drivers: hv: vmbus: Some miscellaneous fixes

index 6117891..5f8e47b 100644
@@ -23,6 +23,7 @@
 #include <linux/kernel.h>
 #include <linux/sched.h>
 #include <linux/wait.h>
+#include <linux/delay.h>
 #include <linux/mm.h>
 #include <linux/slab.h>
 #include <linux/list.h>

@@ -37,6 +38,10 @@ struct vmbus_channel_message_table_entry {
 	void (*message_handler)(struct vmbus_channel_message_header *msg);
 };
 
+struct vmbus_rescind_work {
+	struct work_struct work;
+	struct vmbus_channel *channel;
+};
 
 /**
  * vmbus_prep_negotiate_resp() - Create default response for Hyper-V Negotiate message

@@ -134,20 +139,6 @@ fw_error:
 
 EXPORT_SYMBOL_GPL(vmbus_prep_negotiate_resp);
 
-static void vmbus_process_device_unregister(struct work_struct *work)
-{
-	struct device *dev;
-	struct vmbus_channel *channel = container_of(work,
-							struct vmbus_channel,
-							work);
-
-	dev = get_device(&channel->device_obj->device);
-	if (dev) {
-		vmbus_device_unregister(channel->device_obj);
-		put_device(dev);
-	}
-}
-
 static void vmbus_sc_creation_cb(struct work_struct *work)
 {
 	struct vmbus_channel *newchannel = container_of(work,

@@ -220,6 +211,40 @@ static void free_channel(struct vmbus_channel *channel)
 	queue_work(vmbus_connection.work_queue, &channel->work);
 }
 
+static void process_rescind_fn(struct work_struct *work)
+{
+	struct vmbus_rescind_work *rc_work;
+	struct vmbus_channel *channel;
+	struct device *dev;
+
+	rc_work = container_of(work, struct vmbus_rescind_work, work);
+	channel = rc_work->channel;
+
+	/*
+	 * We have already acquired a reference on the channel
+	 * and so it cannot vanish underneath us.
+	 * It is possible (while very unlikely) that we may
+	 * get here while the processing of the initial offer
+	 * is still not complete. Deal with this situation by
+	 * just waiting until the channel is in the correct state.
+	 */
+
+	while (channel->work.func != release_channel)
+		msleep(1000);
+
+	if (channel->device_obj) {
+		dev = get_device(&channel->device_obj->device);
+		if (dev) {
+			vmbus_device_unregister(channel->device_obj);
+			put_device(dev);
+		}
+	} else {
+		hv_process_channel_removal(channel,
+					   channel->offermsg.child_relid);
+	}
+	kfree(work);
+}
+
 static void percpu_channel_enq(void *arg)
 {
 	struct vmbus_channel *channel = arg;

@@ -282,6 +307,46 @@ void vmbus_free_channels(void)
 	}
 }
 
+static void vmbus_do_device_register(struct work_struct *work)
+{
+	struct hv_device *device_obj;
+	int ret;
+	unsigned long flags;
+	struct vmbus_channel *newchannel = container_of(work,
+						     struct vmbus_channel,
+						     work);
+
+	ret = vmbus_device_register(newchannel->device_obj);
+	if (ret != 0) {
+		pr_err("unable to add child device object (relid %d)\n",
+			newchannel->offermsg.child_relid);
+		spin_lock_irqsave(&vmbus_connection.channel_lock, flags);
+		list_del(&newchannel->listentry);
+		device_obj = newchannel->device_obj;
+		newchannel->device_obj = NULL;
+		spin_unlock_irqrestore(&vmbus_connection.channel_lock, flags);
+
+		if (newchannel->target_cpu != get_cpu()) {
+			put_cpu();
+			smp_call_function_single(newchannel->target_cpu,
+					 percpu_channel_deq, newchannel, true);
+		} else {
+			percpu_channel_deq(newchannel);
+			put_cpu();
+		}
+
+		kfree(device_obj);
+		if (!newchannel->rescind) {
+			free_channel(newchannel);
+			return;
+		}
+	}
+	/*
+	 * The next state for this channel is to be freed.
+	 */
+	INIT_WORK(&newchannel->work, release_channel);
+}
+
 /*
  * vmbus_process_offer - Process the offer by creating a channel/device
  * associated with this offer

@@ -291,7 +356,6 @@ static void vmbus_process_offer(struct vmbus_channel *newchannel)
 	struct vmbus_channel *channel;
 	bool fnew = true;
 	bool enq = false;
-	int ret;
 	unsigned long flags;
 
 	/* Make sure this is a new offer */

@@ -393,16 +457,13 @@ static void vmbus_process_offer(struct vmbus_channel *newchannel)
 	 * Add the new device to the bus. This will kick off device-driver
 	 * binding which eventually invokes the device driver's AddDevice()
 	 * method.
+	 * Invoke this call on the per-channel work context.
+	 * Until we return from this function, rescind offer message
+	 * cannot be processed as we are running on the global message
+	 * handling work.
 	 */
-	ret = vmbus_device_register(newchannel->device_obj);
-	if (ret != 0) {
-		pr_err("unable to add child device object (relid %d)\n",
-			   newchannel->offermsg.child_relid);
-
-		kfree(newchannel->device_obj);
-		goto err_deq_chan;
-	}
-
+	INIT_WORK(&newchannel->work, vmbus_do_device_register);
+	queue_work(newchannel->controlwq, &newchannel->work);
 	return;
 
 err_deq_chan:

@@ -556,33 +617,31 @@ static void vmbus_onoffer_rescind(struct vmbus_channel_message_header *hdr)
 {
 	struct vmbus_channel_rescind_offer *rescind;
 	struct vmbus_channel *channel;
-	unsigned long flags;
+	struct vmbus_rescind_work *rc_work;
 
 	rescind = (struct vmbus_channel_rescind_offer *)hdr;
-	channel = relid2channel(rescind->child_relid);
+	channel = relid2channel(rescind->child_relid, true);
 
 	if (channel == NULL) {
 		hv_process_channel_removal(NULL, rescind->child_relid);
 		return;
 	}
 
-	spin_lock_irqsave(&channel->lock, flags);
-	channel->rescind = true;
-	spin_unlock_irqrestore(&channel->lock, flags);
-
-	if (channel->device_obj) {
-		/*
-		 * We will have to unregister this device from the
-		 * driver core. Do this in the per-channel work context.
-		 * Note that we are currently executing on the global
-		 * workq for handling messages from the host.
-		 */
-		INIT_WORK(&channel->work, vmbus_process_device_unregister);
-		queue_work(channel->controlwq, &channel->work);
-	} else {
-		hv_process_channel_removal(channel,
-					   channel->offermsg.child_relid);
+	/*
+	 * We have acquired a reference on the channel and have posted
+	 * the rescind state. Perform further cleanup in a work context
+	 * that is different from the global work context in which
+	 * we process messages from the host (we are currently executing
+	 * on that global context.
+	 */
+	rc_work = kzalloc(sizeof(struct vmbus_rescind_work), GFP_KERNEL);
+	if (!rc_work) {
+		pr_err("Unable to allocate memory for rescind processing ");
+		return;
 	}
+	rc_work->channel = channel;
+	INIT_WORK(&rc_work->work, process_rescind_fn);
+	schedule_work(&rc_work->work);
 }
 
 /*

index 583d7d4..8bcd307 100644
@@ -270,7 +270,7 @@ static struct vmbus_channel *pcpu_relid2channel(u32 relid)
  * relid2channel - Get the channel object given its
  * child relative id (ie channel id)
  */
-struct vmbus_channel *relid2channel(u32 relid)
+struct vmbus_channel *relid2channel(u32 relid, bool rescind)
 {
 	struct vmbus_channel *channel;
 	struct vmbus_channel *found_channel  = NULL;

@@ -282,6 +282,8 @@ struct vmbus_channel *relid2channel(u32 relid)
 	list_for_each_entry(channel, &vmbus_connection.chn_list, listentry) {
 		if (channel->offermsg.child_relid == relid) {
 			found_channel = channel;
+			if (rescind)
+				found_channel->rescind = true;
 			break;
 		} else if (!list_empty(&channel->sc_list)) {
 			/*

@@ -292,6 +294,8 @@ struct vmbus_channel *relid2channel(u32 relid)
 							sc_list);
 				if (cur_sc->offermsg.child_relid == relid) {
 					found_channel = cur_sc;
+					if (rescind)
+						found_channel->rescind = true;
 					break;
 				}
 			}

index 88af4ec..6339589 100644
@@ -698,7 +698,7 @@ void vmbus_device_unregister(struct hv_device *device_obj);
 /* VmbusChildDeviceDestroy( */
 /* struct hv_device *); */
 
-struct vmbus_channel *relid2channel(u32 relid);
+struct vmbus_channel *relid2channel(u32 relid, bool rescind);
 
 void vmbus_free_channels(void);
 

index c5bb872..f1f17c5 100644
@@ -652,6 +652,7 @@ static void hv_mem_hot_add(unsigned long start, unsigned long size,
 			}
 			has->ha_end_pfn -= HA_CHUNK;
 			has->covered_end_pfn -=  processed_pfn;
+			mutex_lock(&dm_device.ha_region_mutex);
 			break;
 		}
 

index f1f17c5..014256a 100644
@@ -428,14 +428,13 @@ struct dm_info_msg {
  * currently hot added. We hot add in multiples of 128M
  * chunks; it is possible that we may not be able to bring
  * online all the pages in the region. The range
- * covered_start_pfn : covered_end_pfn defines the pages that can
+ * covered_end_pfn defines the pages that can
  * be brough online.
  */
 
 struct hv_hotadd_state {
 	struct list_head list;
 	unsigned long start_pfn;
-	unsigned long covered_start_pfn;
 	unsigned long covered_end_pfn;
 	unsigned long ha_end_pfn;
 	unsigned long end_pfn;

@@ -679,8 +678,7 @@ static void hv_online_page(struct page *pg)
 
 	list_for_each(cur, &dm_device.ha_region_list) {
 		has = list_entry(cur, struct hv_hotadd_state, list);
-		cur_start_pgp = (unsigned long)
-				pfn_to_page(has->covered_start_pfn);
+		cur_start_pgp = (unsigned long)pfn_to_page(has->start_pfn);
 		cur_end_pgp = (unsigned long)pfn_to_page(has->covered_end_pfn);
 
 		if (((unsigned long)pg >= cur_start_pgp) &&

@@ -692,7 +690,6 @@ static void hv_online_page(struct page *pg)
 			__online_page_set_limits(pg);
 			__online_page_increment_counters(pg);
 			__online_page_free(pg);
-			has->covered_start_pfn++;
 		}
 	}
 }

@@ -736,10 +733,9 @@ static bool pfn_covered(unsigned long start_pfn, unsigned long pfn_cnt)
 		 * is, update it.
 		 */
 
-		if (has->covered_end_pfn != start_pfn) {
+		if (has->covered_end_pfn != start_pfn)
 			has->covered_end_pfn = start_pfn;
-			has->covered_start_pfn = start_pfn;
-		}
+
 		return true;
 
 	}

@@ -784,7 +780,6 @@ static unsigned long handle_pg_range(unsigned long pg_start,
 				pgs_ol = pfn_cnt;
 			hv_bring_pgs_online(start_pfn, pgs_ol);
 			has->covered_end_pfn +=  pgs_ol;
-			has->covered_start_pfn +=  pgs_ol;
 			pfn_cnt -= pgs_ol;
 		}
 

@@ -845,7 +840,6 @@ static unsigned long process_hot_add(unsigned long pg_start,
 		list_add_tail(&ha_region->list, &dm_device.ha_region_list);
 		ha_region->start_pfn = rg_start;
 		ha_region->ha_end_pfn = rg_start;
-		ha_region->covered_start_pfn = pg_start;
 		ha_region->covered_end_pfn = pg_start;
 		ha_region->end_pfn = rg_start + rg_size;
 	}

index 6339589..c8e27e0 100644
@@ -58,7 +58,7 @@ enum hv_cpuid_function {
 #define HV_X64_MSR_CRASH_P4   0x40000104
 #define HV_X64_MSR_CRASH_CTL  0x40000105
 
-#define HV_CRASH_CTL_CRASH_NOTIFY 0x8000000000000000
+#define HV_CRASH_CTL_CRASH_NOTIFY (1ULL << 63)
 
 /* Define version of the synthetic interrupt controller. */
 #define HV_SYNIC_VERSION		(1)

index 5f8e47b..25dbbaf 100644
@@ -415,7 +415,7 @@ static void vmbus_process_offer(struct vmbus_channel *newchannel)
 
 			newchannel->state = CHANNEL_OPEN_STATE;
 			channel->num_sc++;
-			if (channel->sc_creation_callback != NULL)
+			if (channel->sc_creation_callback != NULL) {
 				/*
 				 * We need to invoke the sub-channel creation
 				 * callback; invoke this in a seperate work

@@ -427,6 +427,7 @@ static void vmbus_process_offer(struct vmbus_channel *newchannel)
 					  vmbus_sc_creation_cb);
 				queue_work(newchannel->controlwq,
 					   &newchannel->work);
+			}
 
 			return;
 		}

index da53180..2c8206d 100644
@@ -501,15 +501,6 @@ static int vmbus_close_internal(struct vmbus_channel *channel)
 		put_cpu();
 	}
 
-	/*
-	 * If the channel has been rescinded; process device removal.
-	 */
-	if (channel->rescind) {
-		hv_process_channel_removal(channel,
-					   channel->offermsg.child_relid);
-		return 0;
-	}
-
 	/* Send a closing message */
 
 	msg = &channel->close_msg.msg;

@@ -549,6 +540,12 @@ static int vmbus_close_internal(struct vmbus_channel *channel)
 	free_pages((unsigned long)channel->ringbuffer_pages,
 		get_order(channel->ringbuffer_pagecount * PAGE_SIZE));
 
+	/*
+	 * If the channel has been rescinded; process device removal.
+	 */
+	if (channel->rescind)
+		hv_process_channel_removal(channel,
+					   channel->offermsg.child_relid);
 	return ret;
 }
 

index 5e63f70..506dd01 100644
@@ -81,6 +81,7 @@ static int vss_operate(int operation)
 	char match[] = "/dev/";
 	FILE *mounts;
 	struct mntent *ent;
+	char errdir[1024] = {0};
 	unsigned int cmd;
 	int error = 0, root_seen = 0, save_errno = 0;
 

@@ -115,6 +116,8 @@ static int vss_operate(int operation)
 			goto err;
 	}
 
+	endmntent(mounts);
+
 	if (root_seen) {
 		error |= vss_do_freeze("/", cmd);
 		if (error && operation == VSS_OP_FREEZE)

@@ -124,16 +127,19 @@ static int vss_operate(int operation)
 	goto out;
 err:
 	save_errno = errno;
+	if (ent) {
+		strncpy(errdir, ent->mnt_dir, sizeof(errdir)-1);
+		endmntent(mounts);
+	}
 	vss_operate(VSS_OP_THAW);
 	/* Call syslog after we thaw all filesystems */
 	if (ent)
 		syslog(LOG_ERR, "FREEZE of %s failed; error:%d %s",
-		       ent->mnt_dir, save_errno, strerror(save_errno));
+		       errdir, save_errno, strerror(save_errno));
 	else
 		syslog(LOG_ERR, "FREEZE of / failed; error:%d %s", save_errno,
 		       strerror(save_errno));
 out:
-	endmntent(mounts);
 	return error;
 }
 

index 2c8206d..fddd3b5 100644
@@ -707,6 +707,7 @@ int vmbus_sendpacket_pagebuffer_ctl(struct vmbus_channel *channel,
 
 	return ret;
 }
+EXPORT_SYMBOL_GPL(vmbus_sendpacket_pagebuffer_ctl);
 
 /*
  * vmbus_sendpacket_pagebuffer - Send a range of single-page buffer