12 files changed, 354 insertions, 756 deletions

diff --git a/drivers/hv/channel.c b/drivers/hv/channel.c
index 5fb4c6d9209b..be34547cdb68 100644
--- a/drivers/hv/channel.c
+++ b/drivers/hv/channel.c
@@ -157,6 +157,7 @@ int vmbus_open(struct vmbus_channel *newchannel, u32 send_ringbuffer_size,
 	}
 
 	init_completion(&open_info->waitevent);
+	open_info->waiting_channel = newchannel;
 
 	open_msg = (struct vmbus_channel_open_channel *)open_info->msg;
 	open_msg->header.msgtype = CHANNELMSG_OPENCHANNEL;
@@ -181,7 +182,7 @@ int vmbus_open(struct vmbus_channel *newchannel, u32 send_ringbuffer_size,
 	spin_unlock_irqrestore(&vmbus_connection.channelmsg_lock, flags);
 
 	ret = vmbus_post_msg(open_msg,
-			       sizeof(struct vmbus_channel_open_channel));
+			     sizeof(struct vmbus_channel_open_channel), true);
 
 	if (ret != 0) {
 		err = ret;
@@ -194,6 +195,11 @@ int vmbus_open(struct vmbus_channel *newchannel, u32 send_ringbuffer_size,
 	list_del(&open_info->msglistentry);
 	spin_unlock_irqrestore(&vmbus_connection.channelmsg_lock, flags);
 
+	if (newchannel->rescind) {
+		err = -ENODEV;
+		goto error_free_gpadl;
+	}
+
 	if (open_info->response.open_result.status) {
 		err = -EAGAIN;
 		goto error_free_gpadl;
@@ -233,7 +239,7 @@ int vmbus_send_tl_connect_request(const uuid_le *shv_guest_servie_id,
 	conn_msg.guest_endpoint_id = *shv_guest_servie_id;
 	conn_msg.host_service_id = *shv_host_servie_id;
 
-	return vmbus_post_msg(&conn_msg, sizeof(conn_msg));
+	return vmbus_post_msg(&conn_msg, sizeof(conn_msg), true);
 }
 EXPORT_SYMBOL_GPL(vmbus_send_tl_connect_request);
 
@@ -405,6 +411,7 @@ int vmbus_establish_gpadl(struct vmbus_channel *channel, void *kbuffer,
 		return ret;
 
 	init_completion(&msginfo->waitevent);
+	msginfo->waiting_channel = channel;
 
 	gpadlmsg = (struct vmbus_channel_gpadl_header *)msginfo->msg;
 	gpadlmsg->header.msgtype = CHANNELMSG_GPADL_HEADER;
@@ -419,7 +426,7 @@ int vmbus_establish_gpadl(struct vmbus_channel *channel, void *kbuffer,
 	spin_unlock_irqrestore(&vmbus_connection.channelmsg_lock, flags);
 
 	ret = vmbus_post_msg(gpadlmsg, msginfo->msgsize -
-			       sizeof(*msginfo));
+			     sizeof(*msginfo), true);
 	if (ret != 0)
 		goto cleanup;
 
@@ -433,14 +440,19 @@ int vmbus_establish_gpadl(struct vmbus_channel *channel, void *kbuffer,
 		gpadl_body->gpadl = next_gpadl_handle;
 
 		ret = vmbus_post_msg(gpadl_body,
-				     submsginfo->msgsize -
-				     sizeof(*submsginfo));
+				     submsginfo->msgsize - sizeof(*submsginfo),
+				     true);
 		if (ret != 0)
 			goto cleanup;
 
 	}
 	wait_for_completion(&msginfo->waitevent);
 
+	if (channel->rescind) {
+		ret = -ENODEV;
+		goto cleanup;
+	}
+
 	/* At this point, we received the gpadl created msg */
 	*gpadl_handle = gpadlmsg->gpadl;
 
@@ -474,6 +486,7 @@ int vmbus_teardown_gpadl(struct vmbus_channel *channel, u32 gpadl_handle)
 		return -ENOMEM;
 
 	init_completion(&info->waitevent);
+	info->waiting_channel = channel;
 
 	msg = (struct vmbus_channel_gpadl_teardown *)info->msg;
 
@@ -485,14 +498,19 @@ int vmbus_teardown_gpadl(struct vmbus_channel *channel, u32 gpadl_handle)
 	list_add_tail(&info->msglistentry,
 		      &vmbus_connection.chn_msg_list);
 	spin_unlock_irqrestore(&vmbus_connection.channelmsg_lock, flags);
-	ret = vmbus_post_msg(msg,
-			       sizeof(struct vmbus_channel_gpadl_teardown));
+	ret = vmbus_post_msg(msg, sizeof(struct vmbus_channel_gpadl_teardown),
+			     true);
 
 	if (ret)
 		goto post_msg_err;
 
 	wait_for_completion(&info->waitevent);
 
+	if (channel->rescind) {
+		ret = -ENODEV;
+		goto post_msg_err;
+	}
+
 post_msg_err:
 	spin_lock_irqsave(&vmbus_connection.channelmsg_lock, flags);
 	list_del(&info->msglistentry);
@@ -557,7 +575,8 @@ static int vmbus_close_internal(struct vmbus_channel *channel)
 	msg->header.msgtype = CHANNELMSG_CLOSECHANNEL;
 	msg->child_relid = channel->offermsg.child_relid;
 
-	ret = vmbus_post_msg(msg, sizeof(struct vmbus_channel_close_channel));
+	ret = vmbus_post_msg(msg, sizeof(struct vmbus_channel_close_channel),
+			     true);
 
 	if (ret) {
 		pr_err("Close failed: close post msg return is %d\n", ret);
diff --git a/drivers/hv/channel_mgmt.c b/drivers/hv/channel_mgmt.c
index 26b419203f16..de90a9900fee 100644
--- a/drivers/hv/channel_mgmt.c
+++ b/drivers/hv/channel_mgmt.c
@@ -31,6 +31,7 @@
 #include <linux/completion.h>
 #include <linux/delay.h>
 #include <linux/hyperv.h>
+#include <asm/mshyperv.h>
 
 #include "hyperv_vmbus.h"
 
@@ -147,6 +148,29 @@ static const struct {
 	{ HV_RDV_GUID	},
 };
 
+/*
+ * The rescinded channel may be blocked waiting for a response from the host;
+ * take care of that.
+ */
+static void vmbus_rescind_cleanup(struct vmbus_channel *channel)
+{
+	struct vmbus_channel_msginfo *msginfo;
+	unsigned long flags;
+
+
+	spin_lock_irqsave(&vmbus_connection.channelmsg_lock, flags);
+
+	list_for_each_entry(msginfo, &vmbus_connection.chn_msg_list,
+				msglistentry) {
+
+		if (msginfo->waiting_channel == channel) {
+			complete(&msginfo->waitevent);
+			break;
+		}
+	}
+	spin_unlock_irqrestore(&vmbus_connection.channelmsg_lock, flags);
+}
+
 static bool is_unsupported_vmbus_devs(const uuid_le *guid)
 {
 	int i;
@@ -180,33 +204,34 @@ static u16 hv_get_dev_type(const struct vmbus_channel *channel)
  * @buf: Raw buffer channel data
  *
  * @icmsghdrp is of type &struct icmsg_hdr.
- * @negop is of type &struct icmsg_negotiate.
  * Set up and fill in default negotiate response message.
  *
- * The fw_version specifies the  framework version that
- * we can support and srv_version specifies the service
- * version we can support.
+ * The fw_version and fw_vercnt specifies the framework version that
+ * we can support.
+ *
+ * The srv_version and srv_vercnt specifies the service
+ * versions we can support.
+ *
+ * Versions are given in decreasing order.
+ *
+ * nego_fw_version and nego_srv_version store the selected protocol versions.
  *
  * Mainly used by Hyper-V drivers.
  */
 bool vmbus_prep_negotiate_resp(struct icmsg_hdr *icmsghdrp,
-				struct icmsg_negotiate *negop, u8 *buf,
-				int fw_version, int srv_version)
+				u8 *buf, const int *fw_version, int fw_vercnt,
+				const int *srv_version, int srv_vercnt,
+				int *nego_fw_version, int *nego_srv_version)
 {
 	int icframe_major, icframe_minor;
 	int icmsg_major, icmsg_minor;
 	int fw_major, fw_minor;
 	int srv_major, srv_minor;
-	int i;
+	int i, j;
 	bool found_match = false;
+	struct icmsg_negotiate *negop;
 
 	icmsghdrp->icmsgsize = 0x10;
-	fw_major = (fw_version >> 16);
-	fw_minor = (fw_version & 0xFFFF);
-
-	srv_major = (srv_version >> 16);
-	srv_minor = (srv_version & 0xFFFF);
-
 	negop = (struct icmsg_negotiate *)&buf[
 		sizeof(struct vmbuspipe_hdr) +
 		sizeof(struct icmsg_hdr)];
@@ -222,13 +247,22 @@ bool vmbus_prep_negotiate_resp(struct icmsg_hdr *icmsghdrp,
 	 * support.
 	 */
 
-	for (i = 0; i < negop->icframe_vercnt; i++) {
-		if ((negop->icversion_data[i].major == fw_major) &&
-		   (negop->icversion_data[i].minor == fw_minor)) {
-			icframe_major = negop->icversion_data[i].major;
-			icframe_minor = negop->icversion_data[i].minor;
-			found_match = true;
+	for (i = 0; i < fw_vercnt; i++) {
+		fw_major = (fw_version[i] >> 16);
+		fw_minor = (fw_version[i] & 0xFFFF);
+
+		for (j = 0; j < negop->icframe_vercnt; j++) {
+			if ((negop->icversion_data[j].major == fw_major) &&
+			    (negop->icversion_data[j].minor == fw_minor)) {
+				icframe_major = negop->icversion_data[j].major;
+				icframe_minor = negop->icversion_data[j].minor;
+				found_match = true;
+				break;
+			}
 		}
+
+		if (found_match)
+			break;
 	}
 
 	if (!found_match)
@@ -236,14 +270,26 @@ bool vmbus_prep_negotiate_resp(struct icmsg_hdr *icmsghdrp,
 
 	found_match = false;
 
-	for (i = negop->icframe_vercnt;
-		 (i < negop->icframe_vercnt + negop->icmsg_vercnt); i++) {
-		if ((negop->icversion_data[i].major == srv_major) &&
-		   (negop->icversion_data[i].minor == srv_minor)) {
-			icmsg_major = negop->icversion_data[i].major;
-			icmsg_minor = negop->icversion_data[i].minor;
-			found_match = true;
+	for (i = 0; i < srv_vercnt; i++) {
+		srv_major = (srv_version[i] >> 16);
+		srv_minor = (srv_version[i] & 0xFFFF);
+
+		for (j = negop->icframe_vercnt;
+			(j < negop->icframe_vercnt + negop->icmsg_vercnt);
+			j++) {
+
+			if ((negop->icversion_data[j].major == srv_major) &&
+				(negop->icversion_data[j].minor == srv_minor)) {
+
+				icmsg_major = negop->icversion_data[j].major;
+				icmsg_minor = negop->icversion_data[j].minor;
+				found_match = true;
+				break;
+			}
 		}
+
+		if (found_match)
+			break;
 	}
 
 	/*
@@ -260,6 +306,12 @@ fw_error:
 		negop->icmsg_vercnt = 1;
 	}
 
+	if (nego_fw_version)
+		*nego_fw_version = (icframe_major << 16) | icframe_minor;
+
+	if (nego_srv_version)
+		*nego_srv_version = (icmsg_major << 16) | icmsg_minor;
+
 	negop->icversion_data[0].major = icframe_major;
 	negop->icversion_data[0].minor = icframe_minor;
 	negop->icversion_data[1].major = icmsg_major;
@@ -321,7 +373,8 @@ static void vmbus_release_relid(u32 relid)
 	memset(&msg, 0, sizeof(struct vmbus_channel_relid_released));
 	msg.child_relid = relid;
 	msg.header.msgtype = CHANNELMSG_RELID_RELEASED;
-	vmbus_post_msg(&msg, sizeof(struct vmbus_channel_relid_released));
+	vmbus_post_msg(&msg, sizeof(struct vmbus_channel_relid_released),
+		       true);
 }
 
 void hv_event_tasklet_disable(struct vmbus_channel *channel)
@@ -728,7 +781,8 @@ void vmbus_initiate_unload(bool crash)
 	init_completion(&vmbus_connection.unload_event);
 	memset(&hdr, 0, sizeof(struct vmbus_channel_message_header));
 	hdr.msgtype = CHANNELMSG_UNLOAD;
-	vmbus_post_msg(&hdr, sizeof(struct vmbus_channel_message_header));
+	vmbus_post_msg(&hdr, sizeof(struct vmbus_channel_message_header),
+		       !crash);
 
 	/*
 	 * vmbus_initiate_unload() is also called on crash and the crash can be
@@ -823,6 +877,8 @@ static void vmbus_onoffer_rescind(struct vmbus_channel_message_header *hdr)
 	channel->rescind = true;
 	spin_unlock_irqrestore(&channel->lock, flags);
 
+	vmbus_rescind_cleanup(channel);
+
 	if (channel->device_obj) {
 		if (channel->chn_rescind_callback) {
 			channel->chn_rescind_callback(channel);
@@ -1116,8 +1172,8 @@ int vmbus_request_offers(void)
 	msg->msgtype = CHANNELMSG_REQUESTOFFERS;
 
 
-	ret = vmbus_post_msg(msg,
-			       sizeof(struct vmbus_channel_message_header));
+	ret = vmbus_post_msg(msg, sizeof(struct vmbus_channel_message_header),
+			     true);
 	if (ret != 0) {
 		pr_err("Unable to request offers - %d\n", ret);
 
diff --git a/drivers/hv/connection.c b/drivers/hv/connection.c
index 6ce8b874e833..307a5a8937f6 100644
--- a/drivers/hv/connection.c
+++ b/drivers/hv/connection.c
@@ -111,7 +111,8 @@ static int vmbus_negotiate_version(struct vmbus_channel_msginfo *msginfo,
 	spin_unlock_irqrestore(&vmbus_connection.channelmsg_lock, flags);
 
 	ret = vmbus_post_msg(msg,
-			       sizeof(struct vmbus_channel_initiate_contact));
+			     sizeof(struct vmbus_channel_initiate_contact),
+			     true);
 	if (ret != 0) {
 		spin_lock_irqsave(&vmbus_connection.channelmsg_lock, flags);
 		list_del(&msginfo->msglistentry);
@@ -220,11 +221,8 @@ int vmbus_connect(void)
 		goto cleanup;
 
 	vmbus_proto_version = version;
-	pr_info("Hyper-V Host Build:%d-%d.%d-%d-%d.%d; Vmbus version:%d.%d\n",
-		    host_info_eax, host_info_ebx >> 16,
-		    host_info_ebx & 0xFFFF, host_info_ecx,
-		    host_info_edx >> 24, host_info_edx & 0xFFFFFF,
-		    version >> 16, version & 0xFFFF);
+	pr_info("Vmbus version:%d.%d\n",
+		version >> 16, version & 0xFFFF);
 
 	kfree(msginfo);
 	return 0;
@@ -435,7 +433,7 @@ void vmbus_on_event(unsigned long data)
 /*
  * vmbus_post_msg - Send a msg on the vmbus's message connection
  */
-int vmbus_post_msg(void *buffer, size_t buflen)
+int vmbus_post_msg(void *buffer, size_t buflen, bool can_sleep)
 {
 	union hv_connection_id conn_id;
 	int ret = 0;
@@ -450,7 +448,7 @@ int vmbus_post_msg(void *buffer, size_t buflen)
 	 * insufficient resources. Retry the operation a couple of
 	 * times before giving up.
 	 */
-	while (retries < 20) {
+	while (retries < 100) {
 		ret = hv_post_message(conn_id, 1, buffer, buflen);
 
 		switch (ret) {
@@ -473,8 +471,14 @@ int vmbus_post_msg(void *buffer, size_t buflen)
 		}
 
 		retries++;
-		udelay(usec);
-		if (usec < 2048)
+		if (can_sleep && usec > 1000)
+			msleep(usec / 1000);
+		else if (usec < MAX_UDELAY_MS * 1000)
+			udelay(usec);
+		else
+			mdelay(usec / 1000);
+
+		if (usec < 256000)
 			usec *= 2;
 	}
 	return ret;
diff --git a/drivers/hv/hv.c b/drivers/hv/hv.c
index b44b32f21e61..0f73237bed0a 100644
--- a/drivers/hv/hv.c
+++ b/drivers/hv/hv.c
@@ -36,7 +36,6 @@
 /* The one and only */
 struct hv_context hv_context = {
 	.synic_initialized	= false,
-	.hypercall_page		= NULL,
 };
 
 #define HV_TIMER_FREQUENCY (10 * 1000 * 1000) /* 100ns period */
@@ -44,156 +43,12 @@ struct hv_context hv_context = {
 #define HV_MIN_DELTA_TICKS 1
 
 /*
- * query_hypervisor_info - Get version info of the windows hypervisor
- */
-unsigned int host_info_eax;
-unsigned int host_info_ebx;
-unsigned int host_info_ecx;
-unsigned int host_info_edx;
-
-static int query_hypervisor_info(void)
-{
-	unsigned int eax;
-	unsigned int ebx;
-	unsigned int ecx;
-	unsigned int edx;
-	unsigned int max_leaf;
-	unsigned int op;
-
-	/*
-	* Its assumed that this is called after confirming that Viridian
-	* is present. Query id and revision.
-	*/
-	eax = 0;
-	ebx = 0;
-	ecx = 0;
-	edx = 0;
-	op = HVCPUID_VENDOR_MAXFUNCTION;
-	cpuid(op, &eax, &ebx, &ecx, &edx);
-
-	max_leaf = eax;
-
-	if (max_leaf >= HVCPUID_VERSION) {
-		eax = 0;
-		ebx = 0;
-		ecx = 0;
-		edx = 0;
-		op = HVCPUID_VERSION;
-		cpuid(op, &eax, &ebx, &ecx, &edx);
-		host_info_eax = eax;
-		host_info_ebx = ebx;
-		host_info_ecx = ecx;
-		host_info_edx = edx;
-	}
-	return max_leaf;
-}
-
-/*
- * hv_do_hypercall- Invoke the specified hypercall
- */
-u64 hv_do_hypercall(u64 control, void *input, void *output)
-{
-	u64 input_address = (input) ? virt_to_phys(input) : 0;
-	u64 output_address = (output) ? virt_to_phys(output) : 0;
-	void *hypercall_page = hv_context.hypercall_page;
-#ifdef CONFIG_X86_64
-	u64 hv_status = 0;
-
-	if (!hypercall_page)
-		return (u64)ULLONG_MAX;
-
-	__asm__ __volatile__("mov %0, %%r8" : : "r" (output_address) : "r8");
-	__asm__ __volatile__("call *%3" : "=a" (hv_status) :
-			     "c" (control), "d" (input_address),
-			     "m" (hypercall_page));
-
-	return hv_status;
-
-#else
-
-	u32 control_hi = control >> 32;
-	u32 control_lo = control & 0xFFFFFFFF;
-	u32 hv_status_hi = 1;
-	u32 hv_status_lo = 1;
-	u32 input_address_hi = input_address >> 32;
-	u32 input_address_lo = input_address & 0xFFFFFFFF;
-	u32 output_address_hi = output_address >> 32;
-	u32 output_address_lo = output_address & 0xFFFFFFFF;
-
-	if (!hypercall_page)
-		return (u64)ULLONG_MAX;
-
-	__asm__ __volatile__ ("call *%8" : "=d"(hv_status_hi),
-			      "=a"(hv_status_lo) : "d" (control_hi),
-			      "a" (control_lo), "b" (input_address_hi),
-			      "c" (input_address_lo), "D"(output_address_hi),
-			      "S"(output_address_lo), "m" (hypercall_page));
-
-	return hv_status_lo | ((u64)hv_status_hi << 32);
-#endif /* !x86_64 */
-}
-EXPORT_SYMBOL_GPL(hv_do_hypercall);
-
-#ifdef CONFIG_X86_64
-static u64 read_hv_clock_tsc(struct clocksource *arg)
-{
-	u64 current_tick;
-	struct ms_hyperv_tsc_page *tsc_pg = hv_context.tsc_page;
-
-	if (tsc_pg->tsc_sequence != 0) {
-		/*
-		 * Use the tsc page to compute the value.
-		 */
-
-		while (1) {
-			u64 tmp;
-			u32 sequence = tsc_pg->tsc_sequence;
-			u64 cur_tsc;
-			u64 scale = tsc_pg->tsc_scale;
-			s64 offset = tsc_pg->tsc_offset;
-
-			rdtscll(cur_tsc);
-			/* current_tick = ((cur_tsc *scale) >> 64) + offset */
-			asm("mulq %3"
-				: "=d" (current_tick), "=a" (tmp)
-				: "a" (cur_tsc), "r" (scale));
-
-			current_tick += offset;
-			if (tsc_pg->tsc_sequence == sequence)
-				return current_tick;
-
-			if (tsc_pg->tsc_sequence != 0)
-				continue;
-			/*
-			 * Fallback using MSR method.
-			 */
-			break;
-		}
-	}
-	rdmsrl(HV_X64_MSR_TIME_REF_COUNT, current_tick);
-	return current_tick;
-}
-
-static struct clocksource hyperv_cs_tsc = {
-		.name           = "hyperv_clocksource_tsc_page",
-		.rating         = 425,
-		.read           = read_hv_clock_tsc,
-		.mask           = CLOCKSOURCE_MASK(64),
-		.flags          = CLOCK_SOURCE_IS_CONTINUOUS,
-};
-#endif
-
-
-/*
  * hv_init - Main initialization routine.
  *
  * This routine must be called before any other routines in here are called
  */
 int hv_init(void)
 {
-	int max_leaf;
-	union hv_x64_msr_hypercall_contents hypercall_msr;
-	void *virtaddr = NULL;
 
 	memset(hv_context.synic_event_page, 0, sizeof(void *) * NR_CPUS);
 	memset(hv_context.synic_message_page, 0,
@@ -209,111 +64,10 @@ int hv_init(void)
 	memset(hv_context.clk_evt, 0,
 	       sizeof(void *) * NR_CPUS);
 
-	max_leaf = query_hypervisor_info();
-
-	/*
-	 * Write our OS ID.
-	 */
-	hv_context.guestid = generate_guest_id(0, LINUX_VERSION_CODE, 0);
-	wrmsrl(HV_X64_MSR_GUEST_OS_ID, hv_context.guestid);
-
-	/* See if the hypercall page is already set */
-	rdmsrl(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64);
-
-	virtaddr = __vmalloc(PAGE_SIZE, GFP_KERNEL, PAGE_KERNEL_EXEC);
-
-	if (!virtaddr)
-		goto cleanup;
+	if (!hv_is_hypercall_page_setup())
+		return -ENOTSUPP;
 
-	hypercall_msr.enable = 1;
-
-	hypercall_msr.guest_physical_address = vmalloc_to_pfn(virtaddr);
-	wrmsrl(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64);
-
-	/* Confirm that hypercall page did get setup. */
-	hypercall_msr.as_uint64 = 0;
-	rdmsrl(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64);
-
-	if (!hypercall_msr.enable)
-		goto cleanup;
-
-	hv_context.hypercall_page = virtaddr;
-
-#ifdef CONFIG_X86_64
-	if (ms_hyperv.features & HV_X64_MSR_REFERENCE_TSC_AVAILABLE) {
-		union hv_x64_msr_hypercall_contents tsc_msr;
-		void *va_tsc;
-
-		va_tsc = __vmalloc(PAGE_SIZE, GFP_KERNEL, PAGE_KERNEL);
-		if (!va_tsc)
-			goto cleanup;
-		hv_context.tsc_page = va_tsc;
-
-		rdmsrl(HV_X64_MSR_REFERENCE_TSC, tsc_msr.as_uint64);
-
-		tsc_msr.enable = 1;
-		tsc_msr.guest_physical_address = vmalloc_to_pfn(va_tsc);
-
-		wrmsrl(HV_X64_MSR_REFERENCE_TSC, tsc_msr.as_uint64);
-		clocksource_register_hz(&hyperv_cs_tsc, NSEC_PER_SEC/100);
-	}
-#endif
 	return 0;
-
-cleanup:
-	if (virtaddr) {
-		if (hypercall_msr.enable) {
-			hypercall_msr.as_uint64 = 0;
-			wrmsrl(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64);
-		}
-
-		vfree(virtaddr);
-	}
-
-	return -ENOTSUPP;
-}
-
-/*
- * hv_cleanup - Cleanup routine.
- *
- * This routine is called normally during driver unloading or exiting.
- */
-void hv_cleanup(bool crash)
-{
-	union hv_x64_msr_hypercall_contents hypercall_msr;
-
-	/* Reset our OS id */
-	wrmsrl(HV_X64_MSR_GUEST_OS_ID, 0);
-
-	if (hv_context.hypercall_page) {
-		hypercall_msr.as_uint64 = 0;
-		wrmsrl(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64);
-		if (!crash)
-			vfree(hv_context.hypercall_page);
-		hv_context.hypercall_page = NULL;
-	}
-
-#ifdef CONFIG_X86_64
-	/*
-	 * Cleanup the TSC page based CS.
-	 */
-	if (ms_hyperv.features & HV_X64_MSR_REFERENCE_TSC_AVAILABLE) {
-		/*
-		 * Crash can happen in an interrupt context and unregistering
-		 * a clocksource is impossible and redundant in this case.
-		 */
-		if (!oops_in_progress) {
-			clocksource_change_rating(&hyperv_cs_tsc, 10);
-			clocksource_unregister(&hyperv_cs_tsc);
-		}
-
-		hypercall_msr.as_uint64 = 0;
-		wrmsrl(HV_X64_MSR_REFERENCE_TSC, hypercall_msr.as_uint64);
-		if (!crash)
-			vfree(hv_context.tsc_page);
-		hv_context.tsc_page = NULL;
-	}
-#endif
 }
 
 /*
@@ -354,16 +108,16 @@ static int hv_ce_set_next_event(unsigned long delta,
 
 	WARN_ON(!clockevent_state_oneshot(evt));
 
-	rdmsrl(HV_X64_MSR_TIME_REF_COUNT, current_tick);
+	hv_get_current_tick(current_tick);
 	current_tick += delta;
-	wrmsrl(HV_X64_MSR_STIMER0_COUNT, current_tick);
+	hv_init_timer(HV_X64_MSR_STIMER0_COUNT, current_tick);
 	return 0;
 }
 
 static int hv_ce_shutdown(struct clock_event_device *evt)
 {
-	wrmsrl(HV_X64_MSR_STIMER0_COUNT, 0);
-	wrmsrl(HV_X64_MSR_STIMER0_CONFIG, 0);
+	hv_init_timer(HV_X64_MSR_STIMER0_COUNT, 0);
+	hv_init_timer_config(HV_X64_MSR_STIMER0_CONFIG, 0);
 
 	return 0;
 }
@@ -375,7 +129,7 @@ static int hv_ce_set_oneshot(struct clock_event_device *evt)
 	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);
+	hv_init_timer_config(HV_X64_MSR_STIMER0_CONFIG, timer_cfg.as_uint64);
 
 	return 0;
 }
@@ -411,7 +165,7 @@ int hv_synic_alloc(void)
 		goto err;
 	}
 
-	for_each_online_cpu(cpu) {
+	for_each_present_cpu(cpu) {
 		hv_context.event_dpc[cpu] = kmalloc(size, GFP_ATOMIC);
 		if (hv_context.event_dpc[cpu] == NULL) {
 			pr_err("Unable to allocate event dpc\n");
@@ -457,6 +211,8 @@ int hv_synic_alloc(void)
 			pr_err("Unable to allocate post msg page\n");
 			goto err;
 		}
+
+		INIT_LIST_HEAD(&hv_context.percpu_list[cpu]);
 	}
 
 	return 0;
@@ -482,7 +238,7 @@ void hv_synic_free(void)
 	int cpu;
 
 	kfree(hv_context.hv_numa_map);
-	for_each_online_cpu(cpu)
+	for_each_present_cpu(cpu)
 		hv_synic_free_cpu(cpu);
 }
 
@@ -493,54 +249,47 @@ void hv_synic_free(void)
  * retrieve the initialized message and event pages.  Otherwise, we create and
  * initialize the message and event pages.
  */
-void hv_synic_init(void *arg)
+int hv_synic_init(unsigned int cpu)
 {
-	u64 version;
 	union hv_synic_simp simp;
 	union hv_synic_siefp siefp;
 	union hv_synic_sint shared_sint;
 	union hv_synic_scontrol sctrl;
 	u64 vp_index;
 
-	int cpu = smp_processor_id();
-
-	if (!hv_context.hypercall_page)
-		return;
-
-	/* Check the version */
-	rdmsrl(HV_X64_MSR_SVERSION, version);
-
 	/* Setup the Synic's message page */
-	rdmsrl(HV_X64_MSR_SIMP, simp.as_uint64);
+	hv_get_simp(simp.as_uint64);
 	simp.simp_enabled = 1;
 	simp.base_simp_gpa = virt_to_phys(hv_context.synic_message_page[cpu])
 		>> PAGE_SHIFT;
 
-	wrmsrl(HV_X64_MSR_SIMP, simp.as_uint64);
+	hv_set_simp(simp.as_uint64);
 
 	/* Setup the Synic's event page */
-	rdmsrl(HV_X64_MSR_SIEFP, siefp.as_uint64);
+	hv_get_siefp(siefp.as_uint64);
 	siefp.siefp_enabled = 1;
 	siefp.base_siefp_gpa = virt_to_phys(hv_context.synic_event_page[cpu])
 		>> PAGE_SHIFT;
 
-	wrmsrl(HV_X64_MSR_SIEFP, siefp.as_uint64);
+	hv_set_siefp(siefp.as_uint64);
 
 	/* Setup the shared SINT. */
-	rdmsrl(HV_X64_MSR_SINT0 + VMBUS_MESSAGE_SINT, shared_sint.as_uint64);
+	hv_get_synint_state(HV_X64_MSR_SINT0 + VMBUS_MESSAGE_SINT,
+			    shared_sint.as_uint64);
 
 	shared_sint.as_uint64 = 0;
 	shared_sint.vector = HYPERVISOR_CALLBACK_VECTOR;
 	shared_sint.masked = false;
 	shared_sint.auto_eoi = true;
 
-	wrmsrl(HV_X64_MSR_SINT0 + VMBUS_MESSAGE_SINT, shared_sint.as_uint64);
+	hv_set_synint_state(HV_X64_MSR_SINT0 + VMBUS_MESSAGE_SINT,
+			    shared_sint.as_uint64);
 
 	/* Enable the global synic bit */
-	rdmsrl(HV_X64_MSR_SCONTROL, sctrl.as_uint64);
+	hv_get_synic_state(sctrl.as_uint64);
 	sctrl.enable = 1;
 
-	wrmsrl(HV_X64_MSR_SCONTROL, sctrl.as_uint64);
+	hv_set_synic_state(sctrl.as_uint64);
 
 	hv_context.synic_initialized = true;
 
@@ -549,11 +298,9 @@ void hv_synic_init(void *arg)
 	 * of cpuid and Linux' notion of cpuid.
 	 * This array will be indexed using Linux cpuid.
 	 */
-	rdmsrl(HV_X64_MSR_VP_INDEX, vp_index);
+	hv_get_vp_index(vp_index);
 	hv_context.vp_index[cpu] = (u32)vp_index;
 
-	INIT_LIST_HEAD(&hv_context.percpu_list[cpu]);
-
 	/*
 	 * Register the per-cpu clockevent source.
 	 */
@@ -562,7 +309,7 @@ void hv_synic_init(void *arg)
 						HV_TIMER_FREQUENCY,
 						HV_MIN_DELTA_TICKS,
 						HV_MAX_MAX_DELTA_TICKS);
-	return;
+	return 0;
 }
 
 /*
@@ -582,16 +329,46 @@ void hv_synic_clockevents_cleanup(void)
 /*
  * hv_synic_cleanup - Cleanup routine for hv_synic_init().
  */
-void hv_synic_cleanup(void *arg)
+int hv_synic_cleanup(unsigned int cpu)
 {
 	union hv_synic_sint shared_sint;
 	union hv_synic_simp simp;
 	union hv_synic_siefp siefp;
 	union hv_synic_scontrol sctrl;
-	int cpu = smp_processor_id();
+	struct vmbus_channel *channel, *sc;
+	bool channel_found = false;
+	unsigned long flags;
 
 	if (!hv_context.synic_initialized)
-		return;
+		return -EFAULT;
+
+	/*
+	 * Search for channels which are bound to the CPU we're about to
+	 * cleanup. In case we find one and vmbus is still connected we need to
+	 * fail, this will effectively prevent CPU offlining. There is no way
+	 * we can re-bind channels to different CPUs for now.
+	 */
+	mutex_lock(&vmbus_connection.channel_mutex);
+	list_for_each_entry(channel, &vmbus_connection.chn_list, listentry) {
+		if (channel->target_cpu == cpu) {
+			channel_found = true;
+			break;
+		}
+		spin_lock_irqsave(&channel->lock, flags);
+		list_for_each_entry(sc, &channel->sc_list, sc_list) {
+			if (sc->target_cpu == cpu) {
+				channel_found = true;
+				break;
+			}
+		}
+		spin_unlock_irqrestore(&channel->lock, flags);
+		if (channel_found)
+			break;
+	}
+	mutex_unlock(&vmbus_connection.channel_mutex);
+
+	if (channel_found && vmbus_connection.conn_state == CONNECTED)
+		return -EBUSY;
 
 	/* Turn off clockevent device */
 	if (ms_hyperv.features & HV_X64_MSR_SYNTIMER_AVAILABLE) {
@@ -599,28 +376,32 @@ void hv_synic_cleanup(void *arg)
 		hv_ce_shutdown(hv_context.clk_evt[cpu]);
 	}
 
-	rdmsrl(HV_X64_MSR_SINT0 + VMBUS_MESSAGE_SINT, shared_sint.as_uint64);
+	hv_get_synint_state(HV_X64_MSR_SINT0 + VMBUS_MESSAGE_SINT,
+			    shared_sint.as_uint64);
 
 	shared_sint.masked = 1;
 
 	/* Need to correctly cleanup in the case of SMP!!! */
 	/* Disable the interrupt */
-	wrmsrl(HV_X64_MSR_SINT0 + VMBUS_MESSAGE_SINT, shared_sint.as_uint64);
+	hv_set_synint_state(HV_X64_MSR_SINT0 + VMBUS_MESSAGE_SINT,
+			    shared_sint.as_uint64);
 
-	rdmsrl(HV_X64_MSR_SIMP, simp.as_uint64);
+	hv_get_simp(simp.as_uint64);
 	simp.simp_enabled = 0;
 	simp.base_simp_gpa = 0;
 
-	wrmsrl(HV_X64_MSR_SIMP, simp.as_uint64);
+	hv_set_simp(simp.as_uint64);
 
-	rdmsrl(HV_X64_MSR_SIEFP, siefp.as_uint64);
+	hv_get_siefp(siefp.as_uint64);
 	siefp.siefp_enabled = 0;
 	siefp.base_siefp_gpa = 0;
 
-	wrmsrl(HV_X64_MSR_SIEFP, siefp.as_uint64);
+	hv_set_siefp(siefp.as_uint64);
 
 	/* Disable the global synic bit */
-	rdmsrl(HV_X64_MSR_SCONTROL, sctrl.as_uint64);
+	hv_get_synic_state(sctrl.as_uint64);
 	sctrl.enable = 0;
-	wrmsrl(HV_X64_MSR_SCONTROL, sctrl.as_uint64);
+	hv_set_synic_state(sctrl.as_uint64);
+
+	return 0;
 }
diff --git a/drivers/hv/hv_balloon.c b/drivers/hv/hv_balloon.c
index 14c3dc4bd23c..5fd03e59cee5 100644
--- a/drivers/hv/hv_balloon.c
+++ b/drivers/hv/hv_balloon.c
@@ -587,6 +587,7 @@ static int hv_memory_notifier(struct notifier_block *nb, unsigned long val,
 		spin_lock_irqsave(&dm_device.ha_lock, flags);
 		dm_device.num_pages_onlined += mem->nr_pages;
 		spin_unlock_irqrestore(&dm_device.ha_lock, flags);
+		/* Fall through */
 	case MEM_CANCEL_ONLINE:
 		if (dm_device.ha_waiting) {
 			dm_device.ha_waiting = false;
diff --git a/drivers/hv/hv_fcopy.c b/drivers/hv/hv_fcopy.c
index 8b2ba98831ec..9aee6014339d 100644
--- a/drivers/hv/hv_fcopy.c
+++ b/drivers/hv/hv_fcopy.c
@@ -31,6 +31,16 @@
 #define WIN8_SRV_MINOR		1
 #define WIN8_SRV_VERSION	(WIN8_SRV_MAJOR << 16 | WIN8_SRV_MINOR)
 
+#define FCOPY_VER_COUNT 1
+static const int fcopy_versions[] = {
+	WIN8_SRV_VERSION
+};
+
+#define FW_VER_COUNT 1
+static const int fw_versions[] = {
+	UTIL_FW_VERSION
+};
+
 /*
  * Global state maintained for transaction that is being processed.
  * For a class of integration services, including the "file copy service",
@@ -61,6 +71,7 @@ static DECLARE_WORK(fcopy_send_work, fcopy_send_data);
 static const char fcopy_devname[] = "vmbus/hv_fcopy";
 static u8 *recv_buffer;
 static struct hvutil_transport *hvt;
+static struct completion release_event;
 /*
  * This state maintains the version number registered by the daemon.
  */
@@ -227,8 +238,6 @@ void hv_fcopy_onchannelcallback(void *context)
 	u64 requestid;
 	struct hv_fcopy_hdr *fcopy_msg;
 	struct icmsg_hdr *icmsghdr;
-	struct icmsg_negotiate *negop = NULL;
-	int util_fw_version;
 	int fcopy_srv_version;
 
 	if (fcopy_transaction.state > HVUTIL_READY)
@@ -242,10 +251,15 @@ void hv_fcopy_onchannelcallback(void *context)
 	icmsghdr = (struct icmsg_hdr *)&recv_buffer[
 			sizeof(struct vmbuspipe_hdr)];
 	if (icmsghdr->icmsgtype == ICMSGTYPE_NEGOTIATE) {
-		util_fw_version = UTIL_FW_VERSION;
-		fcopy_srv_version = WIN8_SRV_VERSION;
-		vmbus_prep_negotiate_resp(icmsghdr, negop, recv_buffer,
-				util_fw_version, fcopy_srv_version);
+		if (vmbus_prep_negotiate_resp(icmsghdr, recv_buffer,
+				fw_versions, FW_VER_COUNT,
+				fcopy_versions, FCOPY_VER_COUNT,
+				NULL, &fcopy_srv_version)) {
+
+			pr_info("FCopy IC version %d.%d\n",
+				fcopy_srv_version >> 16,
+				fcopy_srv_version & 0xFFFF);
+		}
 	} else {
 		fcopy_msg = (struct hv_fcopy_hdr *)&recv_buffer[
 				sizeof(struct vmbuspipe_hdr) +
@@ -317,6 +331,7 @@ static void fcopy_on_reset(void)
 
 	if (cancel_delayed_work_sync(&fcopy_timeout_work))
 		fcopy_respond_to_host(HV_E_FAIL);
+	complete(&release_event);
 }
 
 int hv_fcopy_init(struct hv_util_service *srv)
@@ -324,6 +339,7 @@ int hv_fcopy_init(struct hv_util_service *srv)
 	recv_buffer = srv->recv_buffer;
 	fcopy_transaction.recv_channel = srv->channel;
 
+	init_completion(&release_event);
 	/*
 	 * When this driver loads, the user level daemon that
 	 * processes the host requests may not yet be running.
@@ -345,4 +361,5 @@ void hv_fcopy_deinit(void)
 	fcopy_transaction.state = HVUTIL_DEVICE_DYING;
 	cancel_delayed_work_sync(&fcopy_timeout_work);
 	hvutil_transport_destroy(hvt);
+	wait_for_completion(&release_event);
 }