Merge tag 'char-misc-3.20-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/char-misc

Pull char / misc patches from Greg KH:
 "Here's the big char/misc driver update for 3.20-rc1.

  Lots of little things in here, all described in the changelog.
  Nothing major or unusual, except maybe the binder selinux stuff, which
  was all acked by the proper selinux people and they thought it best to
  come through this tree.

  All of this has been in linux-next with no reported issues for a while"

* tag 'char-misc-3.20-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/gregkh/char-misc: (90 commits)
  coresight: fix function etm_writel_cp14() parameter order
  coresight-etm: remove check for unknown Kconfig macro
  coresight: fixing CPU hwid lookup in device tree
  coresight: remove the unnecessary function coresight_is_bit_set()
  coresight: fix the debug AMBA bus name
  coresight: remove the extra spaces
  coresight: fix the link between orphan connection and newly added device
  coresight: remove the unnecessary replicator property
  coresight: fix the replicator subtype value
  pdfdocs: Fix 'make pdfdocs' failure for 'uio-howto.tmpl'
  mcb: Fix error path of mcb_pci_probe
  virtio/console: verify device has config space
  ti-st: clean up data types (fix harmless memory corruption)
  mei: me: release hw from reset only during the reset flow
  mei: mask interrupt set bit on clean reset bit
  extcon: max77693: Constify struct regmap_config
  extcon: adc-jack: Release IIO channel on driver remove
  extcon: Remove duplicated include from extcon-class.c
  Drivers: hv: vmbus: hv_process_timer_expiration() can be static
  Drivers: hv: vmbus: serialize Offer and Rescind offer
  ...

8 files changed, 323 insertions, 42 deletions

diff --git a/drivers/hv/channel.c b/drivers/hv/channel.c
index 433f72a1c006..2978f5ee8d2a 100644
--- a/drivers/hv/channel.c
+++ b/drivers/hv/channel.c
@@ -73,14 +73,14 @@ int vmbus_open(struct vmbus_channel *newchannel, u32 send_ringbuffer_size,
 	unsigned long flags;
 	int ret, t, err = 0;
 
-	spin_lock_irqsave(&newchannel->sc_lock, flags);
+	spin_lock_irqsave(&newchannel->lock, flags);
 	if (newchannel->state == CHANNEL_OPEN_STATE) {
 		newchannel->state = CHANNEL_OPENING_STATE;
 	} else {
-		spin_unlock_irqrestore(&newchannel->sc_lock, flags);
+		spin_unlock_irqrestore(&newchannel->lock, flags);
 		return -EINVAL;
 	}
-	spin_unlock_irqrestore(&newchannel->sc_lock, flags);
+	spin_unlock_irqrestore(&newchannel->lock, flags);
 
 	newchannel->onchannel_callback = onchannelcallback;
 	newchannel->channel_callback_context = context;
@@ -366,8 +366,8 @@ int vmbus_establish_gpadl(struct vmbus_channel *channel, void *kbuffer,
 	unsigned long flags;
 	int ret = 0;
 
-	next_gpadl_handle = atomic_read(&vmbus_connection.next_gpadl_handle);
-	atomic_inc(&vmbus_connection.next_gpadl_handle);
+	next_gpadl_handle =
+		(atomic_inc_return(&vmbus_connection.next_gpadl_handle) - 1);
 
 	ret = create_gpadl_header(kbuffer, size, &msginfo, &msgcount);
 	if (ret)
@@ -686,6 +686,50 @@ EXPORT_SYMBOL_GPL(vmbus_sendpacket_pagebuffer);
 /*
  * vmbus_sendpacket_multipagebuffer - Send a multi-page buffer packet
  * using a GPADL Direct packet type.
+ * The buffer includes the vmbus descriptor.
+ */
+int vmbus_sendpacket_mpb_desc(struct vmbus_channel *channel,
+			      struct vmbus_packet_mpb_array *desc,
+			      u32 desc_size,
+			      void *buffer, u32 bufferlen, u64 requestid)
+{
+	int ret;
+	u32 packetlen;
+	u32 packetlen_aligned;
+	struct kvec bufferlist[3];
+	u64 aligned_data = 0;
+	bool signal = false;
+
+	packetlen = desc_size + bufferlen;
+	packetlen_aligned = ALIGN(packetlen, sizeof(u64));
+
+	/* Setup the descriptor */
+	desc->type = VM_PKT_DATA_USING_GPA_DIRECT;
+	desc->flags = VMBUS_DATA_PACKET_FLAG_COMPLETION_REQUESTED;
+	desc->dataoffset8 = desc_size >> 3; /* in 8-bytes grandularity */
+	desc->length8 = (u16)(packetlen_aligned >> 3);
+	desc->transactionid = requestid;
+	desc->rangecount = 1;
+
+	bufferlist[0].iov_base = desc;
+	bufferlist[0].iov_len = desc_size;
+	bufferlist[1].iov_base = buffer;
+	bufferlist[1].iov_len = bufferlen;
+	bufferlist[2].iov_base = &aligned_data;
+	bufferlist[2].iov_len = (packetlen_aligned - packetlen);
+
+	ret = hv_ringbuffer_write(&channel->outbound, bufferlist, 3, &signal);
+
+	if (ret == 0 && signal)
+		vmbus_setevent(channel);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(vmbus_sendpacket_mpb_desc);
+
+/*
+ * vmbus_sendpacket_multipagebuffer - Send a multi-page buffer packet
+ * using a GPADL Direct packet type.
  */
 int vmbus_sendpacket_multipagebuffer(struct vmbus_channel *channel,
 				struct hv_multipage_buffer *multi_pagebuffer,
diff --git a/drivers/hv/channel_mgmt.c b/drivers/hv/channel_mgmt.c
index 2c59f030546b..3736f71bdec5 100644
--- a/drivers/hv/channel_mgmt.c
+++ b/drivers/hv/channel_mgmt.c
@@ -146,7 +146,7 @@ static struct vmbus_channel *alloc_channel(void)
 		return NULL;
 
 	spin_lock_init(&channel->inbound_lock);
-	spin_lock_init(&channel->sc_lock);
+	spin_lock_init(&channel->lock);
 
 	INIT_LIST_HEAD(&channel->sc_list);
 	INIT_LIST_HEAD(&channel->percpu_list);
@@ -246,9 +246,9 @@ static void vmbus_process_rescind_offer(struct work_struct *work)
 		spin_unlock_irqrestore(&vmbus_connection.channel_lock, flags);
 	} else {
 		primary_channel = channel->primary_channel;
-		spin_lock_irqsave(&primary_channel->sc_lock, flags);
+		spin_lock_irqsave(&primary_channel->lock, flags);
 		list_del(&channel->sc_list);
-		spin_unlock_irqrestore(&primary_channel->sc_lock, flags);
+		spin_unlock_irqrestore(&primary_channel->lock, flags);
 	}
 	free_channel(channel);
 }
@@ -279,9 +279,6 @@ static void vmbus_process_offer(struct work_struct *work)
 	int ret;
 	unsigned long flags;
 
-	/* The next possible work is rescind handling */
-	INIT_WORK(&newchannel->work, vmbus_process_rescind_offer);
-
 	/* Make sure this is a new offer */
 	spin_lock_irqsave(&vmbus_connection.channel_lock, flags);
 
@@ -323,9 +320,9 @@ static void vmbus_process_offer(struct work_struct *work)
 			 * Process the sub-channel.
 			 */
 			newchannel->primary_channel = channel;
-			spin_lock_irqsave(&channel->sc_lock, flags);
+			spin_lock_irqsave(&channel->lock, flags);
 			list_add_tail(&newchannel->sc_list, &channel->sc_list);
-			spin_unlock_irqrestore(&channel->sc_lock, flags);
+			spin_unlock_irqrestore(&channel->lock, flags);
 
 			if (newchannel->target_cpu != get_cpu()) {
 				put_cpu();
@@ -341,11 +338,10 @@ static void vmbus_process_offer(struct work_struct *work)
 			if (channel->sc_creation_callback != NULL)
 				channel->sc_creation_callback(newchannel);
 
-			return;
+			goto done_init_rescind;
 		}
 
-		free_channel(newchannel);
-		return;
+		goto err_free_chan;
 	}
 
 	/*
@@ -364,6 +360,8 @@ static void vmbus_process_offer(struct work_struct *work)
 		&newchannel->offermsg.offer.if_type,
 		&newchannel->offermsg.offer.if_instance,
 		newchannel);
+	if (!newchannel->device_obj)
+		goto err_free_chan;
 
 	/*
 	 * Add the new device to the bus. This will kick off device-driver
@@ -379,9 +377,19 @@ static void vmbus_process_offer(struct work_struct *work)
 		list_del(&newchannel->listentry);
 		spin_unlock_irqrestore(&vmbus_connection.channel_lock, flags);
 		kfree(newchannel->device_obj);
-
-		free_channel(newchannel);
+		goto err_free_chan;
 	}
+done_init_rescind:
+	spin_lock_irqsave(&newchannel->lock, flags);
+	/* The next possible work is rescind handling */
+	INIT_WORK(&newchannel->work, vmbus_process_rescind_offer);
+	/* Check if rescind offer was already received */
+	if (newchannel->rescind)
+		queue_work(newchannel->controlwq, &newchannel->work);
+	spin_unlock_irqrestore(&newchannel->lock, flags);
+	return;
+err_free_chan:
+	free_channel(newchannel);
 }
 
 enum {
@@ -516,6 +524,7 @@ static void vmbus_onoffer_rescind(struct vmbus_channel_message_header *hdr)
 {
 	struct vmbus_channel_rescind_offer *rescind;
 	struct vmbus_channel *channel;
+	unsigned long flags;
 
 	rescind = (struct vmbus_channel_rescind_offer *)hdr;
 	channel = relid2channel(rescind->child_relid);
@@ -524,11 +533,20 @@ static void vmbus_onoffer_rescind(struct vmbus_channel_message_header *hdr)
 		/* Just return here, no channel found */
 		return;
 
+	spin_lock_irqsave(&channel->lock, flags);
 	channel->rescind = true;
+	/*
+	 * channel->work.func != vmbus_process_rescind_offer means we are still
+	 * processing offer request and the rescind offer processing should be
+	 * postponed. It will be done at the very end of vmbus_process_offer()
+	 * as rescind flag is being checked there.
+	 */
+	if (channel->work.func == vmbus_process_rescind_offer)
+		/* work is initialized for vmbus_process_rescind_offer() from
+		 * vmbus_process_offer() where the channel got created */
+		queue_work(channel->controlwq, &channel->work);
 
-	/* work is initialized for vmbus_process_rescind_offer() from
-	 * vmbus_process_offer() where the channel got created */
-	queue_work(channel->controlwq, &channel->work);
+	spin_unlock_irqrestore(&channel->lock, flags);
 }
 
 /*
@@ -815,7 +833,7 @@ cleanup:
 struct vmbus_channel *vmbus_get_outgoing_channel(struct vmbus_channel *primary)
 {
 	struct list_head *cur, *tmp;
-	int cur_cpu = hv_context.vp_index[smp_processor_id()];
+	int cur_cpu;
 	struct vmbus_channel *cur_channel;
 	struct vmbus_channel *outgoing_channel = primary;
 	int cpu_distance, new_cpu_distance;
@@ -823,6 +841,8 @@ struct vmbus_channel *vmbus_get_outgoing_channel(struct vmbus_channel *primary)
 	if (list_empty(&primary->sc_list))
 		return outgoing_channel;
 
+	cur_cpu = hv_context.vp_index[get_cpu()];
+	put_cpu();
 	list_for_each_safe(cur, tmp, &primary->sc_list) {
 		cur_channel = list_entry(cur, struct vmbus_channel, sc_list);
 		if (cur_channel->state != CHANNEL_OPENED_STATE)
diff --git a/drivers/hv/connection.c b/drivers/hv/connection.c
index e206619b946e..a63a795300b9 100644
--- a/drivers/hv/connection.c
+++ b/drivers/hv/connection.c
@@ -80,8 +80,10 @@ static int vmbus_negotiate_version(struct vmbus_channel_msginfo *msginfo,
 	msg->interrupt_page = virt_to_phys(vmbus_connection.int_page);
 	msg->monitor_page1 = virt_to_phys(vmbus_connection.monitor_pages[0]);
 	msg->monitor_page2 = virt_to_phys(vmbus_connection.monitor_pages[1]);
-	if (version == VERSION_WIN8_1)
-		msg->target_vcpu = hv_context.vp_index[smp_processor_id()];
+	if (version == VERSION_WIN8_1) {
+		msg->target_vcpu = hv_context.vp_index[get_cpu()];
+		put_cpu();
+	}
 
 	/*
 	 * Add to list before we send the request since we may
diff --git a/drivers/hv/hv.c b/drivers/hv/hv.c
index 3e4235c7a47f..50e51a51ff8b 100644
--- a/drivers/hv/hv.c
+++ b/drivers/hv/hv.c
@@ -28,7 +28,9 @@
 #include <linux/hyperv.h>
 #include <linux/version.h>
 #include <linux/interrupt.h>
+#include <linux/clockchips.h>
 #include <asm/hyperv.h>
+#include <asm/mshyperv.h>
 #include "hyperv_vmbus.h"
 
 /* The one and only */
@@ -37,6 +39,10 @@ struct hv_context hv_context = {
 	.hypercall_page		= NULL,
 };
 
+#define HV_TIMER_FREQUENCY (10 * 1000 * 1000) /* 100ns period */
+#define HV_MAX_MAX_DELTA_TICKS 0xffffffff
+#define HV_MIN_DELTA_TICKS 1
+
 /*
  * query_hypervisor_info - Get version info of the windows hypervisor
  */
@@ -144,6 +150,8 @@ int hv_init(void)
 	       sizeof(int) * NR_CPUS);
 	memset(hv_context.event_dpc, 0,
 	       sizeof(void *) * NR_CPUS);
+	memset(hv_context.clk_evt, 0,
+	       sizeof(void *) * NR_CPUS);
 
 	max_leaf = query_hypervisor_info();
 
@@ -258,10 +266,63 @@ u16 hv_signal_event(void *con_id)
 	return status;
 }
 
+static int hv_ce_set_next_event(unsigned long delta,
+				struct clock_event_device *evt)
+{
+	cycle_t current_tick;
+
+	WARN_ON(evt->mode != CLOCK_EVT_MODE_ONESHOT);
+
+	rdmsrl(HV_X64_MSR_TIME_REF_COUNT, current_tick);
+	current_tick += delta;
+	wrmsrl(HV_X64_MSR_STIMER0_COUNT, current_tick);
+	return 0;
+}
+
+static void hv_ce_setmode(enum clock_event_mode mode,
+			  struct clock_event_device *evt)
+{
+	union hv_timer_config timer_cfg;
+
+	switch (mode) {
+	case CLOCK_EVT_MODE_PERIODIC:
+		/* unsupported */
+		break;
+
+	case CLOCK_EVT_MODE_ONESHOT:
+		timer_cfg.enable = 1;
+		timer_cfg.auto_enable = 1;
+		timer_cfg.sintx = VMBUS_MESSAGE_SINT;
+		wrmsrl(HV_X64_MSR_STIMER0_CONFIG, timer_cfg.as_uint64);
+		break;
+
+	case CLOCK_EVT_MODE_UNUSED:
+	case CLOCK_EVT_MODE_SHUTDOWN:
+		wrmsrl(HV_X64_MSR_STIMER0_COUNT, 0);
+		wrmsrl(HV_X64_MSR_STIMER0_CONFIG, 0);
+		break;
+	case CLOCK_EVT_MODE_RESUME:
+		break;
+	}
+}
+
+static void hv_init_clockevent_device(struct clock_event_device *dev, int cpu)
+{
+	dev->name = "Hyper-V clockevent";
+	dev->features = CLOCK_EVT_FEAT_ONESHOT;
+	dev->cpumask = cpumask_of(cpu);
+	dev->rating = 1000;
+	dev->owner = THIS_MODULE;
+
+	dev->set_mode = hv_ce_setmode;
+	dev->set_next_event = hv_ce_set_next_event;
+}
+
 
 int hv_synic_alloc(void)
 {
 	size_t size = sizeof(struct tasklet_struct);
+	size_t ced_size = sizeof(struct clock_event_device);
 	int cpu;
 
 	for_each_online_cpu(cpu) {
@@ -272,6 +333,13 @@ int hv_synic_alloc(void)
 		}
 		tasklet_init(hv_context.event_dpc[cpu], vmbus_on_event, cpu);
 
+		hv_context.clk_evt[cpu] = kzalloc(ced_size, GFP_ATOMIC);
+		if (hv_context.clk_evt[cpu] == NULL) {
+			pr_err("Unable to allocate clock event device\n");
+			goto err;
+		}
+		hv_init_clockevent_device(hv_context.clk_evt[cpu], cpu);
+
 		hv_context.synic_message_page[cpu] =
 			(void *)get_zeroed_page(GFP_ATOMIC);
 
@@ -305,6 +373,7 @@ err:
 static void hv_synic_free_cpu(int cpu)
 {
 	kfree(hv_context.event_dpc[cpu]);
+	kfree(hv_context.clk_evt[cpu]);
 	if (hv_context.synic_event_page[cpu])
 		free_page((unsigned long)hv_context.synic_event_page[cpu]);
 	if (hv_context.synic_message_page[cpu])
@@ -388,6 +457,15 @@ void hv_synic_init(void *arg)
 	hv_context.vp_index[cpu] = (u32)vp_index;
 
 	INIT_LIST_HEAD(&hv_context.percpu_list[cpu]);
+
+	/*
+	 * Register the per-cpu clockevent source.
+	 */
+	if (ms_hyperv.features & HV_X64_MSR_SYNTIMER_AVAILABLE)
+		clockevents_config_and_register(hv_context.clk_evt[cpu],
+						HV_TIMER_FREQUENCY,
+						HV_MIN_DELTA_TICKS,
+						HV_MAX_MAX_DELTA_TICKS);
 	return;
 }
 
diff --git a/drivers/hv/hv_balloon.c b/drivers/hv/hv_balloon.c
index b958ded8ac7e..ff169386b2c7 100644
--- a/drivers/hv/hv_balloon.c
+++ b/drivers/hv/hv_balloon.c
@@ -533,6 +533,9 @@ struct hv_dynmem_device {
 	 */
 	struct task_struct *thread;
 
+	struct mutex ha_region_mutex;
+	struct completion waiter_event;
+
 	/*
 	 * A list of hot-add regions.
 	 */
@@ -549,7 +552,59 @@ struct hv_dynmem_device {
 static struct hv_dynmem_device dm_device;
 
 static void post_status(struct hv_dynmem_device *dm);
+
 #ifdef CONFIG_MEMORY_HOTPLUG
+static void acquire_region_mutex(bool trylock)
+{
+	if (trylock) {
+		reinit_completion(&dm_device.waiter_event);
+		while (!mutex_trylock(&dm_device.ha_region_mutex))
+			wait_for_completion(&dm_device.waiter_event);
+	} else {
+		mutex_lock(&dm_device.ha_region_mutex);
+	}
+}
+
+static void release_region_mutex(bool trylock)
+{
+	if (trylock) {
+		mutex_unlock(&dm_device.ha_region_mutex);
+	} else {
+		mutex_unlock(&dm_device.ha_region_mutex);
+		complete(&dm_device.waiter_event);
+	}
+}
+
+static int hv_memory_notifier(struct notifier_block *nb, unsigned long val,
+			      void *v)
+{
+	switch (val) {
+	case MEM_GOING_ONLINE:
+		acquire_region_mutex(true);
+		break;
+
+	case MEM_ONLINE:
+	case MEM_CANCEL_ONLINE:
+		release_region_mutex(true);
+		if (dm_device.ha_waiting) {
+			dm_device.ha_waiting = false;
+			complete(&dm_device.ol_waitevent);
+		}
+		break;
+
+	case MEM_GOING_OFFLINE:
+	case MEM_OFFLINE:
+	case MEM_CANCEL_OFFLINE:
+		break;
+	}
+	return NOTIFY_OK;
+}
+
+static struct notifier_block hv_memory_nb = {
+	.notifier_call = hv_memory_notifier,
+	.priority = 0
+};
+
 
 static void hv_bring_pgs_online(unsigned long start_pfn, unsigned long size)
 {
@@ -591,6 +646,7 @@ static void hv_mem_hot_add(unsigned long start, unsigned long size,
 		init_completion(&dm_device.ol_waitevent);
 		dm_device.ha_waiting = true;
 
+		release_region_mutex(false);
 		nid = memory_add_physaddr_to_nid(PFN_PHYS(start_pfn));
 		ret = add_memory(nid, PFN_PHYS((start_pfn)),
 				(HA_CHUNK << PAGE_SHIFT));
@@ -619,6 +675,7 @@ static void hv_mem_hot_add(unsigned long start, unsigned long size,
 		 * have not been "onlined" within the allowed time.
 		 */
 		wait_for_completion_timeout(&dm_device.ol_waitevent, 5*HZ);
+		acquire_region_mutex(false);
 		post_status(&dm_device);
 	}
 
@@ -632,11 +689,6 @@ static void hv_online_page(struct page *pg)
 	unsigned long cur_start_pgp;
 	unsigned long cur_end_pgp;
 
-	if (dm_device.ha_waiting) {
-		dm_device.ha_waiting = false;
-		complete(&dm_device.ol_waitevent);
-	}
-
 	list_for_each(cur, &dm_device.ha_region_list) {
 		has = list_entry(cur, struct hv_hotadd_state, list);
 		cur_start_pgp = (unsigned long)
@@ -834,6 +886,7 @@ static void hot_add_req(struct work_struct *dummy)
 	resp.hdr.size = sizeof(struct dm_hot_add_response);
 
 #ifdef CONFIG_MEMORY_HOTPLUG
+	acquire_region_mutex(false);
 	pg_start = dm->ha_wrk.ha_page_range.finfo.start_page;
 	pfn_cnt = dm->ha_wrk.ha_page_range.finfo.page_cnt;
 
@@ -865,6 +918,7 @@ static void hot_add_req(struct work_struct *dummy)
 	if (do_hot_add)
 		resp.page_count = process_hot_add(pg_start, pfn_cnt,
 						rg_start, rg_sz);
+	release_region_mutex(false);
 #endif
 	/*
 	 * The result field of the response structure has the
@@ -928,9 +982,8 @@ static unsigned long compute_balloon_floor(void)
 	 *     128        72    (1/2)
 	 *     512       168    (1/4)
 	 *    2048       360    (1/8)
-	 *    8192       552    (1/32)
-	 *   32768      1320
-	 *  131072      4392
+	 *    8192       768    (1/16)
+	 *   32768      1536	(1/32)
 	 */
 	if (totalram_pages < MB2PAGES(128))
 		min_pages = MB2PAGES(8) + (totalram_pages >> 1);
@@ -938,8 +991,10 @@ static unsigned long compute_balloon_floor(void)
 		min_pages = MB2PAGES(40) + (totalram_pages >> 2);
 	else if (totalram_pages < MB2PAGES(2048))
 		min_pages = MB2PAGES(104) + (totalram_pages >> 3);
+	else if (totalram_pages < MB2PAGES(8192))
+		min_pages = MB2PAGES(256) + (totalram_pages >> 4);
 	else
-		min_pages = MB2PAGES(296) + (totalram_pages >> 5);
+		min_pages = MB2PAGES(512) + (totalram_pages >> 5);
 #undef MB2PAGES
 	return min_pages;
 }
@@ -1171,7 +1226,7 @@ static void balloon_down(struct hv_dynmem_device *dm,
 
 	for (i = 0; i < range_count; i++) {
 		free_balloon_pages(dm, &range_array[i]);
-		post_status(&dm_device);
+		complete(&dm_device.config_event);
 	}
 
 	if (req->more_pages == 1)
@@ -1195,19 +1250,16 @@ static void balloon_onchannelcallback(void *context);
 static int dm_thread_func(void *dm_dev)
 {
 	struct hv_dynmem_device *dm = dm_dev;
-	int t;
 
 	while (!kthread_should_stop()) {
-		t = wait_for_completion_interruptible_timeout(
+		wait_for_completion_interruptible_timeout(
 						&dm_device.config_event, 1*HZ);
 		/*
 		 * The host expects us to post information on the memory
 		 * pressure every second.
 		 */
-
-		if (t == 0)
-			post_status(dm);
-
+		reinit_completion(&dm_device.config_event);
+		post_status(dm);
 	}
 
 	return 0;
@@ -1387,7 +1439,9 @@ static int balloon_probe(struct hv_device *dev,
 	dm_device.next_version = DYNMEM_PROTOCOL_VERSION_WIN7;
 	init_completion(&dm_device.host_event);
 	init_completion(&dm_device.config_event);
+	init_completion(&dm_device.waiter_event);
 	INIT_LIST_HEAD(&dm_device.ha_region_list);
+	mutex_init(&dm_device.ha_region_mutex);
 	INIT_WORK(&dm_device.balloon_wrk.wrk, balloon_up);
 	INIT_WORK(&dm_device.ha_wrk.wrk, hot_add_req);
 	dm_device.host_specified_ha_region = false;
@@ -1401,6 +1455,7 @@ static int balloon_probe(struct hv_device *dev,
 
 #ifdef CONFIG_MEMORY_HOTPLUG
 	set_online_page_callback(&hv_online_page);
+	register_memory_notifier(&hv_memory_nb);
 #endif
 
 	hv_set_drvdata(dev, &dm_device);
@@ -1519,6 +1574,7 @@ static int balloon_remove(struct hv_device *dev)
 	kfree(send_buffer);
 #ifdef CONFIG_MEMORY_HOTPLUG
 	restore_online_page_callback(&hv_online_page);
+	unregister_memory_notifier(&hv_memory_nb);
 #endif
 	list_for_each_safe(cur, tmp, &dm->ha_region_list) {
 		has = list_entry(cur, struct hv_hotadd_state, list);
diff --git a/drivers/hv/hv_fcopy.c b/drivers/hv/hv_fcopy.c
index 23b2ce294c4c..cd453e4b2a07 100644
--- a/drivers/hv/hv_fcopy.c
+++ b/drivers/hv/hv_fcopy.c
@@ -86,6 +86,18 @@ static void fcopy_work_func(struct work_struct *dummy)
 	 * process the pending transaction.
 	 */
 	fcopy_respond_to_host(HV_E_FAIL);
+
+	/* In the case the user-space daemon crashes, hangs or is killed, we
+	 * need to down the semaphore, otherwise, after the daemon starts next
+	 * time, the obsolete data in fcopy_transaction.message or
+	 * fcopy_transaction.fcopy_msg will be used immediately.
+	 *
+	 * NOTE: fcopy_read() happens to get the semaphore (very rare)? We're
+	 * still OK, because we've reported the failure to the host.
+	 */
+	if (down_trylock(&fcopy_transaction.read_sema))
+		;
+
 }
 
 static int fcopy_handle_handshake(u32 version)
@@ -344,6 +356,14 @@ static int fcopy_open(struct inode *inode, struct file *f)
 	return 0;
 }
 
+/* XXX: there are still some tricky corner cases, e.g.,
+ * 1) In a SMP guest, when fcopy_release() runs between
+ * schedule_delayed_work() and fcopy_send_data(), there is
+ * still a chance an obsolete message will be queued.
+ *
+ * 2) When the fcopy daemon is running, if we unload the driver,
+ * we'll notice a kernel oops when we kill the daemon later.
+ */
 static int fcopy_release(struct inode *inode, struct file *f)
 {
 	/*
@@ -351,6 +371,13 @@ static int fcopy_release(struct inode *inode, struct file *f)
 	 */
 	in_hand_shake = true;
 	opened = false;
+
+	if (cancel_delayed_work_sync(&fcopy_work)) {
+		/* We haven't up()-ed the semaphore(very rare)? */
+		if (down_trylock(&fcopy_transaction.read_sema))
+			;
+		fcopy_respond_to_host(HV_E_FAIL);
+	}
 	return 0;
 }
 
diff --git a/drivers/hv/hyperv_vmbus.h b/drivers/hv/hyperv_vmbus.h
index c386d8dc7223..44b1c9424712 100644
--- a/drivers/hv/hyperv_vmbus.h
+++ b/drivers/hv/hyperv_vmbus.h
@@ -178,6 +178,23 @@ struct hv_message_header {
 	};
 };
 
+/*
+ * Timer configuration register.
+ */
+union hv_timer_config {
+	u64 as_uint64;
+	struct {
+		u64 enable:1;
+		u64 periodic:1;
+		u64 lazy:1;
+		u64 auto_enable:1;
+		u64 reserved_z0:12;
+		u64 sintx:4;
+		u64 reserved_z1:44;
+	};
+};
+
+
 /* Define timer message payload structure. */
 struct hv_timer_message_payload {
 	u32 timer_index;
@@ -519,6 +536,10 @@ struct hv_context {
 	 * buffer to post messages to the host.
 	 */
 	void *post_msg_page[NR_CPUS];
+	/*
+	 * Support PV clockevent device.
+	 */
+	struct clock_event_device *clk_evt[NR_CPUS];
 };
 
 extern struct hv_context hv_context;
diff --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c
index bb3725b672cf..f518b8d7a5b5 100644
--- a/drivers/hv/vmbus_drv.c
+++ b/drivers/hv/vmbus_drv.c
@@ -32,6 +32,7 @@
 #include <linux/completion.h>
 #include <linux/hyperv.h>
 #include <linux/kernel_stat.h>
+#include <linux/clockchips.h>
 #include <asm/hyperv.h>
 #include <asm/hypervisor.h>
 #include <asm/mshyperv.h>
@@ -578,6 +579,34 @@ static void vmbus_onmessage_work(struct work_struct *work)
 	kfree(ctx);
 }
 
+static void hv_process_timer_expiration(struct hv_message *msg, int cpu)
+{
+	struct clock_event_device *dev = hv_context.clk_evt[cpu];
+
+	if (dev->event_handler)
+		dev->event_handler(dev);
+
+	msg->header.message_type = HVMSG_NONE;
+
+	/*
+	 * Make sure the write to MessageType (ie set to
+	 * HVMSG_NONE) happens before we read the
+	 * MessagePending and EOMing. Otherwise, the EOMing
+	 * will not deliver any more messages since there is
+	 * no empty slot
+	 */
+	mb();
+
+	if (msg->header.message_flags.msg_pending) {
+		/*
+		 * This will cause message queue rescan to
+		 * possibly deliver another msg from the
+		 * hypervisor
+		 */
+		wrmsrl(HV_X64_MSR_EOM, 0);
+	}
+}
+
 static void vmbus_on_msg_dpc(unsigned long data)
 {
 	int cpu = smp_processor_id();
@@ -667,8 +696,12 @@ static void vmbus_isr(void)
 	msg = (struct hv_message *)page_addr + VMBUS_MESSAGE_SINT;
 
 	/* Check if there are actual msgs to be processed */
-	if (msg->header.message_type != HVMSG_NONE)
-		tasklet_schedule(&msg_dpc);
+	if (msg->header.message_type != HVMSG_NONE) {
+		if (msg->header.message_type == HVMSG_TIMER_EXPIRED)
+			hv_process_timer_expiration(msg, cpu);
+		else
+			tasklet_schedule(&msg_dpc);
+	}
 }
 
 /*