12 files changed, 651 insertions, 158 deletions

diff --git a/drivers/clocksource/hyperv_timer.c b/drivers/clocksource/hyperv_timer.c
index a02b0a224807..977fd05ac35f 100644
--- a/drivers/clocksource/hyperv_timer.c
+++ b/drivers/clocksource/hyperv_timer.c
@@ -18,6 +18,9 @@
 #include <linux/sched_clock.h>
 #include <linux/mm.h>
 #include <linux/cpuhotplug.h>
+#include <linux/interrupt.h>
+#include <linux/irq.h>
+#include <linux/acpi.h>
 #include <clocksource/hyperv_timer.h>
 #include <asm/hyperv-tlfs.h>
 #include <asm/mshyperv.h>
@@ -43,14 +46,13 @@ static u64 hv_sched_clock_offset __ro_after_init;
  */
 static bool direct_mode_enabled;
 
-static int stimer0_irq;
-static int stimer0_vector;
+static int stimer0_irq = -1;
 static int stimer0_message_sint;
+static DEFINE_PER_CPU(long, stimer0_evt);
 
 /*
- * ISR for when stimer0 is operating in Direct Mode.  Direct Mode
- * does not use VMbus or any VMbus messages, so process here and not
- * in the VMbus driver code.
+ * Common code for stimer0 interrupts coming via Direct Mode or
+ * as a VMbus message.
  */
 void hv_stimer0_isr(void)
 {
@@ -61,6 +63,16 @@ void hv_stimer0_isr(void)
 }
 EXPORT_SYMBOL_GPL(hv_stimer0_isr);
 
+/*
+ * stimer0 interrupt handler for architectures that support
+ * per-cpu interrupts, which also implies Direct Mode.
+ */
+static irqreturn_t hv_stimer0_percpu_isr(int irq, void *dev_id)
+{
+	hv_stimer0_isr();
+	return IRQ_HANDLED;
+}
+
 static int hv_ce_set_next_event(unsigned long delta,
 				struct clock_event_device *evt)
 {
@@ -68,16 +80,16 @@ static int hv_ce_set_next_event(unsigned long delta,
 
 	current_tick = hv_read_reference_counter();
 	current_tick += delta;
-	hv_init_timer(0, current_tick);
+	hv_set_register(HV_REGISTER_STIMER0_COUNT, current_tick);
 	return 0;
 }
 
 static int hv_ce_shutdown(struct clock_event_device *evt)
 {
-	hv_init_timer(0, 0);
-	hv_init_timer_config(0, 0);
-	if (direct_mode_enabled)
-		hv_disable_stimer0_percpu_irq(stimer0_irq);
+	hv_set_register(HV_REGISTER_STIMER0_COUNT, 0);
+	hv_set_register(HV_REGISTER_STIMER0_CONFIG, 0);
+	if (direct_mode_enabled && stimer0_irq >= 0)
+		disable_percpu_irq(stimer0_irq);
 
 	return 0;
 }
@@ -95,8 +107,9 @@ static int hv_ce_set_oneshot(struct clock_event_device *evt)
 		 * on the specified hardware vector/IRQ.
 		 */
 		timer_cfg.direct_mode = 1;
-		timer_cfg.apic_vector = stimer0_vector;
-		hv_enable_stimer0_percpu_irq(stimer0_irq);
+		timer_cfg.apic_vector = HYPERV_STIMER0_VECTOR;
+		if (stimer0_irq >= 0)
+			enable_percpu_irq(stimer0_irq, IRQ_TYPE_NONE);
 	} else {
 		/*
 		 * When it expires, the timer will generate a VMbus message,
@@ -105,7 +118,7 @@ static int hv_ce_set_oneshot(struct clock_event_device *evt)
 		timer_cfg.direct_mode = 0;
 		timer_cfg.sintx = stimer0_message_sint;
 	}
-	hv_init_timer_config(0, timer_cfg.as_uint64);
+	hv_set_register(HV_REGISTER_STIMER0_CONFIG, timer_cfg.as_uint64);
 	return 0;
 }
 
@@ -169,10 +182,58 @@ int hv_stimer_cleanup(unsigned int cpu)
 }
 EXPORT_SYMBOL_GPL(hv_stimer_cleanup);
 
+/*
+ * These placeholders are overridden by arch specific code on
+ * architectures that need special setup of the stimer0 IRQ because
+ * they don't support per-cpu IRQs (such as x86/x64).
+ */
+void __weak hv_setup_stimer0_handler(void (*handler)(void))
+{
+};
+
+void __weak hv_remove_stimer0_handler(void)
+{
+};
+
+/* Called only on architectures with per-cpu IRQs (i.e., not x86/x64) */
+static int hv_setup_stimer0_irq(void)
+{
+	int ret;
+
+	ret = acpi_register_gsi(NULL, HYPERV_STIMER0_VECTOR,
+			ACPI_EDGE_SENSITIVE, ACPI_ACTIVE_HIGH);
+	if (ret < 0) {
+		pr_err("Can't register Hyper-V stimer0 GSI. Error %d", ret);
+		return ret;
+	}
+	stimer0_irq = ret;
+
+	ret = request_percpu_irq(stimer0_irq, hv_stimer0_percpu_isr,
+		"Hyper-V stimer0", &stimer0_evt);
+	if (ret) {
+		pr_err("Can't request Hyper-V stimer0 IRQ %d. Error %d",
+			stimer0_irq, ret);
+		acpi_unregister_gsi(stimer0_irq);
+		stimer0_irq = -1;
+	}
+	return ret;
+}
+
+static void hv_remove_stimer0_irq(void)
+{
+	if (stimer0_irq == -1) {
+		hv_remove_stimer0_handler();
+	} else {
+		free_percpu_irq(stimer0_irq, &stimer0_evt);
+		acpi_unregister_gsi(stimer0_irq);
+		stimer0_irq = -1;
+	}
+}
+
 /* hv_stimer_alloc - Global initialization of the clockevent and stimer0 */
-int hv_stimer_alloc(void)
+int hv_stimer_alloc(bool have_percpu_irqs)
 {
-	int ret = 0;
+	int ret;
 
 	/*
 	 * Synthetic timers are always available except on old versions of
@@ -188,29 +249,37 @@ int hv_stimer_alloc(void)
 
 	direct_mode_enabled = ms_hyperv.misc_features &
 			HV_STIMER_DIRECT_MODE_AVAILABLE;
-	if (direct_mode_enabled) {
-		ret = hv_setup_stimer0_irq(&stimer0_irq, &stimer0_vector,
-				hv_stimer0_isr);
+
+	/*
+	 * If Direct Mode isn't enabled, the remainder of the initialization
+	 * is done later by hv_stimer_legacy_init()
+	 */
+	if (!direct_mode_enabled)
+		return 0;
+
+	if (have_percpu_irqs) {
+		ret = hv_setup_stimer0_irq();
 		if (ret)
-			goto free_percpu;
+			goto free_clock_event;
+	} else {
+		hv_setup_stimer0_handler(hv_stimer0_isr);
+	}
 
-		/*
-		 * Since we are in Direct Mode, stimer initialization
-		 * can be done now with a CPUHP value in the same range
-		 * as other clockevent devices.
-		 */
-		ret = cpuhp_setup_state(CPUHP_AP_HYPERV_TIMER_STARTING,
-				"clockevents/hyperv/stimer:starting",
-				hv_stimer_init, hv_stimer_cleanup);
-		if (ret < 0)
-			goto free_stimer0_irq;
+	/*
+	 * Since we are in Direct Mode, stimer initialization
+	 * can be done now with a CPUHP value in the same range
+	 * as other clockevent devices.
+	 */
+	ret = cpuhp_setup_state(CPUHP_AP_HYPERV_TIMER_STARTING,
+			"clockevents/hyperv/stimer:starting",
+			hv_stimer_init, hv_stimer_cleanup);
+	if (ret < 0) {
+		hv_remove_stimer0_irq();
+		goto free_clock_event;
 	}
 	return ret;
 
-free_stimer0_irq:
-	hv_remove_stimer0_irq(stimer0_irq);
-	stimer0_irq = 0;
-free_percpu:
+free_clock_event:
 	free_percpu(hv_clock_event);
 	hv_clock_event = NULL;
 	return ret;
@@ -254,23 +323,6 @@ void hv_stimer_legacy_cleanup(unsigned int cpu)
 }
 EXPORT_SYMBOL_GPL(hv_stimer_legacy_cleanup);
 
-
-/* hv_stimer_free - Free global resources allocated by hv_stimer_alloc() */
-void hv_stimer_free(void)
-{
-	if (!hv_clock_event)
-		return;
-
-	if (direct_mode_enabled) {
-		cpuhp_remove_state(CPUHP_AP_HYPERV_TIMER_STARTING);
-		hv_remove_stimer0_irq(stimer0_irq);
-		stimer0_irq = 0;
-	}
-	free_percpu(hv_clock_event);
-	hv_clock_event = NULL;
-}
-EXPORT_SYMBOL_GPL(hv_stimer_free);
-
 /*
  * Do a global cleanup of clockevents for the cases of kexec and
  * vmbus exit
@@ -287,12 +339,17 @@ void hv_stimer_global_cleanup(void)
 		hv_stimer_legacy_cleanup(cpu);
 	}
 
-	/*
-	 * If Direct Mode is enabled, the cpuhp teardown callback
-	 * (hv_stimer_cleanup) will be run on all CPUs to stop the
-	 * stimers.
-	 */
-	hv_stimer_free();
+	if (!hv_clock_event)
+		return;
+
+	if (direct_mode_enabled) {
+		cpuhp_remove_state(CPUHP_AP_HYPERV_TIMER_STARTING);
+		hv_remove_stimer0_irq();
+		stimer0_irq = -1;
+	}
+	free_percpu(hv_clock_event);
+	hv_clock_event = NULL;
+
 }
 EXPORT_SYMBOL_GPL(hv_stimer_global_cleanup);
 
@@ -302,14 +359,6 @@ EXPORT_SYMBOL_GPL(hv_stimer_global_cleanup);
  * the other that uses the TSC reference page feature as defined in the
  * TLFS.  The MSR version is for compatibility with old versions of
  * Hyper-V and 32-bit x86.  The TSC reference page version is preferred.
- *
- * The Hyper-V clocksource ratings of 250 are chosen to be below the
- * TSC clocksource rating of 300.  In configurations where Hyper-V offers
- * an InvariantTSC, the TSC is not marked "unstable", so the TSC clocksource
- * is available and preferred.  With the higher rating, it will be the
- * default.  On older hardware and Hyper-V versions, the TSC is marked
- * "unstable", so no TSC clocksource is created and the selected Hyper-V
- * clocksource will be the default.
  */
 
 u64 (*hv_read_reference_counter)(void);
@@ -331,7 +380,7 @@ static u64 notrace read_hv_clock_tsc(void)
 	u64 current_tick = hv_read_tsc_page(hv_get_tsc_page());
 
 	if (current_tick == U64_MAX)
-		hv_get_time_ref_count(current_tick);
+		current_tick = hv_get_register(HV_REGISTER_TIME_REF_COUNT);
 
 	return current_tick;
 }
@@ -352,9 +401,9 @@ static void suspend_hv_clock_tsc(struct clocksource *arg)
 	u64 tsc_msr;
 
 	/* Disable the TSC page */
-	hv_get_reference_tsc(tsc_msr);
+	tsc_msr = hv_get_register(HV_REGISTER_REFERENCE_TSC);
 	tsc_msr &= ~BIT_ULL(0);
-	hv_set_reference_tsc(tsc_msr);
+	hv_set_register(HV_REGISTER_REFERENCE_TSC, tsc_msr);
 }
 
 
@@ -364,39 +413,44 @@ static void resume_hv_clock_tsc(struct clocksource *arg)
 	u64 tsc_msr;
 
 	/* Re-enable the TSC page */
-	hv_get_reference_tsc(tsc_msr);
+	tsc_msr = hv_get_register(HV_REGISTER_REFERENCE_TSC);
 	tsc_msr &= GENMASK_ULL(11, 0);
 	tsc_msr |= BIT_ULL(0) | (u64)phys_addr;
-	hv_set_reference_tsc(tsc_msr);
+	hv_set_register(HV_REGISTER_REFERENCE_TSC, tsc_msr);
 }
 
+#ifdef VDSO_CLOCKMODE_HVCLOCK
 static int hv_cs_enable(struct clocksource *cs)
 {
-	hv_enable_vdso_clocksource();
+	vclocks_set_used(VDSO_CLOCKMODE_HVCLOCK);
 	return 0;
 }
+#endif
 
 static struct clocksource hyperv_cs_tsc = {
 	.name	= "hyperv_clocksource_tsc_page",
-	.rating	= 250,
+	.rating	= 500,
 	.read	= read_hv_clock_tsc_cs,
 	.mask	= CLOCKSOURCE_MASK(64),
 	.flags	= CLOCK_SOURCE_IS_CONTINUOUS,
 	.suspend= suspend_hv_clock_tsc,
 	.resume	= resume_hv_clock_tsc,
+#ifdef VDSO_CLOCKMODE_HVCLOCK
 	.enable = hv_cs_enable,
+	.vdso_clock_mode = VDSO_CLOCKMODE_HVCLOCK,
+#else
+	.vdso_clock_mode = VDSO_CLOCKMODE_NONE,
+#endif
 };
 
 static u64 notrace read_hv_clock_msr(void)
 {
-	u64 current_tick;
 	/*
 	 * Read the partition counter to get the current tick count. This count
 	 * is set to 0 when the partition is created and is incremented in
 	 * 100 nanosecond units.
 	 */
-	hv_get_time_ref_count(current_tick);
-	return current_tick;
+	return hv_get_register(HV_REGISTER_TIME_REF_COUNT);
 }
 
 static u64 notrace read_hv_clock_msr_cs(struct clocksource *arg)
@@ -412,12 +466,36 @@ static u64 notrace read_hv_sched_clock_msr(void)
 
 static struct clocksource hyperv_cs_msr = {
 	.name	= "hyperv_clocksource_msr",
-	.rating	= 250,
+	.rating	= 500,
 	.read	= read_hv_clock_msr_cs,
 	.mask	= CLOCKSOURCE_MASK(64),
 	.flags	= CLOCK_SOURCE_IS_CONTINUOUS,
 };
 
+/*
+ * Reference to pv_ops must be inline so objtool
+ * detection of noinstr violations can work correctly.
+ */
+#ifdef CONFIG_GENERIC_SCHED_CLOCK
+static __always_inline void hv_setup_sched_clock(void *sched_clock)
+{
+	/*
+	 * We're on an architecture with generic sched clock (not x86/x64).
+	 * The Hyper-V sched clock read function returns nanoseconds, not
+	 * the normal 100ns units of the Hyper-V synthetic clock.
+	 */
+	sched_clock_register(sched_clock, 64, NSEC_PER_SEC);
+}
+#elif defined CONFIG_PARAVIRT
+static __always_inline void hv_setup_sched_clock(void *sched_clock)
+{
+	/* We're on x86/x64 *and* using PV ops */
+	paravirt_set_sched_clock(sched_clock);
+}
+#else /* !CONFIG_GENERIC_SCHED_CLOCK && !CONFIG_PARAVIRT */
+static __always_inline void hv_setup_sched_clock(void *sched_clock) {}
+#endif /* CONFIG_GENERIC_SCHED_CLOCK */
+
 static bool __init hv_init_tsc_clocksource(void)
 {
 	u64		tsc_msr;
@@ -429,6 +507,22 @@ static bool __init hv_init_tsc_clocksource(void)
 	if (hv_root_partition)
 		return false;
 
+	/*
+	 * If Hyper-V offers TSC_INVARIANT, then the virtualized TSC correctly
+	 * handles frequency and offset changes due to live migration,
+	 * pause/resume, and other VM management operations.  So lower the
+	 * Hyper-V Reference TSC rating, causing the generic TSC to be used.
+	 * TSC_INVARIANT is not offered on ARM64, so the Hyper-V Reference
+	 * TSC will be preferred over the virtualized ARM64 arch counter.
+	 * While the Hyper-V MSR clocksource won't be used since the
+	 * Reference TSC clocksource is present, change its rating as
+	 * well for consistency.
+	 */
+	if (ms_hyperv.features & HV_ACCESS_TSC_INVARIANT) {
+		hyperv_cs_tsc.rating = 250;
+		hyperv_cs_msr.rating = 250;
+	}
+
 	hv_read_reference_counter = read_hv_clock_tsc;
 	phys_addr = virt_to_phys(hv_get_tsc_page());
 
@@ -439,12 +533,11 @@ static bool __init hv_init_tsc_clocksource(void)
 	 * (which already has at least the low 12 bits set to zero since
 	 * it is page aligned). Also set the "enable" bit, which is bit 0.
 	 */
-	hv_get_reference_tsc(tsc_msr);
+	tsc_msr = hv_get_register(HV_REGISTER_REFERENCE_TSC);
 	tsc_msr &= GENMASK_ULL(11, 0);
 	tsc_msr = tsc_msr | 0x1 | (u64)phys_addr;
-	hv_set_reference_tsc(tsc_msr);
+	hv_set_register(HV_REGISTER_REFERENCE_TSC, tsc_msr);
 
-	hv_set_clocksource_vdso(hyperv_cs_tsc);
 	clocksource_register_hz(&hyperv_cs_tsc, NSEC_PER_SEC/100);
 
 	hv_sched_clock_offset = hv_read_reference_counter();
diff --git a/drivers/hv/Kconfig b/drivers/hv/Kconfig
index 79e5356a737a..66c794d92391 100644
--- a/drivers/hv/Kconfig
+++ b/drivers/hv/Kconfig
@@ -23,6 +23,7 @@ config HYPERV_UTILS
 config HYPERV_BALLOON
 	tristate "Microsoft Hyper-V Balloon driver"
 	depends on HYPERV
+	select PAGE_REPORTING
 	help
 	  Select this option to enable Hyper-V Balloon driver.
 
diff --git a/drivers/hv/channel.c b/drivers/hv/channel.c
index 0bd202de7960..c2635e913a92 100644
--- a/drivers/hv/channel.c
+++ b/drivers/hv/channel.c
@@ -209,31 +209,96 @@ int vmbus_send_tl_connect_request(const guid_t *shv_guest_servie_id,
 }
 EXPORT_SYMBOL_GPL(vmbus_send_tl_connect_request);
 
+static int send_modifychannel_without_ack(struct vmbus_channel *channel, u32 target_vp)
+{
+	struct vmbus_channel_modifychannel msg;
+	int ret;
+
+	memset(&msg, 0, sizeof(msg));
+	msg.header.msgtype = CHANNELMSG_MODIFYCHANNEL;
+	msg.child_relid = channel->offermsg.child_relid;
+	msg.target_vp = target_vp;
+
+	ret = vmbus_post_msg(&msg, sizeof(msg), true);
+	trace_vmbus_send_modifychannel(&msg, ret);
+
+	return ret;
+}
+
+static int send_modifychannel_with_ack(struct vmbus_channel *channel, u32 target_vp)
+{
+	struct vmbus_channel_modifychannel *msg;
+	struct vmbus_channel_msginfo *info;
+	unsigned long flags;
+	int ret;
+
+	info = kzalloc(sizeof(struct vmbus_channel_msginfo) +
+				sizeof(struct vmbus_channel_modifychannel),
+		       GFP_KERNEL);
+	if (!info)
+		return -ENOMEM;
+
+	init_completion(&info->waitevent);
+	info->waiting_channel = channel;
+
+	msg = (struct vmbus_channel_modifychannel *)info->msg;
+	msg->header.msgtype = CHANNELMSG_MODIFYCHANNEL;
+	msg->child_relid = channel->offermsg.child_relid;
+	msg->target_vp = target_vp;
+
+	spin_lock_irqsave(&vmbus_connection.channelmsg_lock, flags);
+	list_add_tail(&info->msglistentry, &vmbus_connection.chn_msg_list);
+	spin_unlock_irqrestore(&vmbus_connection.channelmsg_lock, flags);
+
+	ret = vmbus_post_msg(msg, sizeof(*msg), true);
+	trace_vmbus_send_modifychannel(msg, ret);
+	if (ret != 0) {
+		spin_lock_irqsave(&vmbus_connection.channelmsg_lock, flags);
+		list_del(&info->msglistentry);
+		spin_unlock_irqrestore(&vmbus_connection.channelmsg_lock, flags);
+		goto free_info;
+	}
+
+	/*
+	 * Release channel_mutex; otherwise, vmbus_onoffer_rescind() could block on
+	 * the mutex and be unable to signal the completion.
+	 *
+	 * See the caller target_cpu_store() for information about the usage of the
+	 * mutex.
+	 */
+	mutex_unlock(&vmbus_connection.channel_mutex);
+	wait_for_completion(&info->waitevent);
+	mutex_lock(&vmbus_connection.channel_mutex);
+
+	spin_lock_irqsave(&vmbus_connection.channelmsg_lock, flags);
+	list_del(&info->msglistentry);
+	spin_unlock_irqrestore(&vmbus_connection.channelmsg_lock, flags);
+
+	if (info->response.modify_response.status)
+		ret = -EAGAIN;
+
+free_info:
+	kfree(info);
+	return ret;
+}
+
 /*
  * Set/change the vCPU (@target_vp) the channel (@child_relid) will interrupt.
  *
- * CHANNELMSG_MODIFYCHANNEL messages are aynchronous.  Also, Hyper-V does not
- * ACK such messages.  IOW we can't know when the host will stop interrupting
- * the "old" vCPU and start interrupting the "new" vCPU for the given channel.
+ * CHANNELMSG_MODIFYCHANNEL messages are aynchronous.  When VMbus version 5.3
+ * or later is negotiated, Hyper-V always sends an ACK in response to such a
+ * message.  For VMbus version 5.2 and earlier, it never sends an ACK.  With-
+ * out an ACK, we can not know when the host will stop interrupting the "old"
+ * vCPU and start interrupting the "new" vCPU for the given channel.
  *
  * The CHANNELMSG_MODIFYCHANNEL message type is supported since VMBus version
  * VERSION_WIN10_V4_1.
  */
-int vmbus_send_modifychannel(u32 child_relid, u32 target_vp)
+int vmbus_send_modifychannel(struct vmbus_channel *channel, u32 target_vp)
 {
-	struct vmbus_channel_modifychannel conn_msg;
-	int ret;
-
-	memset(&conn_msg, 0, sizeof(conn_msg));
-	conn_msg.header.msgtype = CHANNELMSG_MODIFYCHANNEL;
-	conn_msg.child_relid = child_relid;
-	conn_msg.target_vp = target_vp;
-
-	ret = vmbus_post_msg(&conn_msg, sizeof(conn_msg), true);
-
-	trace_vmbus_send_modifychannel(&conn_msg, ret);
-
-	return ret;
+	if (vmbus_proto_version >= VERSION_WIN10_V5_3)
+		return send_modifychannel_with_ack(channel, target_vp);
+	return send_modifychannel_without_ack(channel, target_vp);
 }
 EXPORT_SYMBOL_GPL(vmbus_send_modifychannel);
 
@@ -385,7 +450,7 @@ nomem:
  * @kbuffer: from kmalloc or vmalloc
  * @size: page-size multiple
  * @send_offset: the offset (in bytes) where the send ring buffer starts,
- * 		 should be 0 for BUFFER type gpadl
+ *              should be 0 for BUFFER type gpadl
  * @gpadl_handle: some funky thing
  */
 static int __vmbus_establish_gpadl(struct vmbus_channel *channel,
@@ -653,7 +718,7 @@ static int __vmbus_open(struct vmbus_channel *newchannel,
 
 	if (newchannel->rescind) {
 		err = -ENODEV;
-		goto error_free_info;
+		goto error_clean_msglist;
 	}
 
 	err = vmbus_post_msg(open_msg,
diff --git a/drivers/hv/channel_mgmt.c b/drivers/hv/channel_mgmt.c
index f0ed730e2e4e..caf6d0c4bc1b 100644
--- a/drivers/hv/channel_mgmt.c
+++ b/drivers/hv/channel_mgmt.c
@@ -333,7 +333,6 @@ fw_error:
 	negop->icversion_data[1].minor = icmsg_minor;
 	return found_match;
 }
-
 EXPORT_SYMBOL_GPL(vmbus_prep_negotiate_resp);
 
 /*
@@ -593,10 +592,10 @@ static void vmbus_process_offer(struct vmbus_channel *newchannel)
 	 * CPUS_READ_UNLOCK		CPUS_WRITE_UNLOCK
 	 *
 	 * Forbids: CPU1's LOAD from *not* seing CPU2's STORE &&
-	 * 		CPU2's SEARCH from *not* seeing CPU1's INSERT
+	 *              CPU2's SEARCH from *not* seeing CPU1's INSERT
 	 *
 	 * Forbids: CPU2's SEARCH from seeing CPU1's INSERT &&
-	 * 		CPU2's LOAD from *not* seing CPU1's STORE
+	 *              CPU2's LOAD from *not* seing CPU1's STORE
 	 */
 	cpus_read_lock();
 
@@ -756,6 +755,12 @@ static void init_vp_index(struct vmbus_channel *channel)
 	free_cpumask_var(available_mask);
 }
 
+#define UNLOAD_DELAY_UNIT_MS	10		/* 10 milliseconds */
+#define UNLOAD_WAIT_MS		(100*1000)	/* 100 seconds */
+#define UNLOAD_WAIT_LOOPS	(UNLOAD_WAIT_MS/UNLOAD_DELAY_UNIT_MS)
+#define UNLOAD_MSG_MS		(5*1000)	/* Every 5 seconds */
+#define UNLOAD_MSG_LOOPS	(UNLOAD_MSG_MS/UNLOAD_DELAY_UNIT_MS)
+
 static void vmbus_wait_for_unload(void)
 {
 	int cpu;
@@ -773,12 +778,17 @@ static void vmbus_wait_for_unload(void)
 	 * vmbus_connection.unload_event. If not, the last thing we can do is
 	 * read message pages for all CPUs directly.
 	 *
-	 * Wait no more than 10 seconds so that the panic path can't get
-	 * hung forever in case the response message isn't seen.
+	 * Wait up to 100 seconds since an Azure host must writeback any dirty
+	 * data in its disk cache before the VMbus UNLOAD request will
+	 * complete. This flushing has been empirically observed to take up
+	 * to 50 seconds in cases with a lot of dirty data, so allow additional
+	 * leeway and for inaccuracies in mdelay(). But eventually time out so
+	 * that the panic path can't get hung forever in case the response
+	 * message isn't seen.
 	 */
-	for (i = 0; i < 1000; i++) {
+	for (i = 1; i <= UNLOAD_WAIT_LOOPS; i++) {
 		if (completion_done(&vmbus_connection.unload_event))
-			break;
+			goto completed;
 
 		for_each_online_cpu(cpu) {
 			struct hv_per_cpu_context *hv_cpu
@@ -801,9 +811,18 @@ static void vmbus_wait_for_unload(void)
 			vmbus_signal_eom(msg, message_type);
 		}
 
-		mdelay(10);
+		/*
+		 * Give a notice periodically so someone watching the
+		 * serial output won't think it is completely hung.
+		 */
+		if (!(i % UNLOAD_MSG_LOOPS))
+			pr_notice("Waiting for VMBus UNLOAD to complete\n");
+
+		mdelay(UNLOAD_DELAY_UNIT_MS);
 	}
+	pr_err("Continuing even though VMBus UNLOAD did not complete\n");
 
+completed:
 	/*
 	 * We're crashing and already got the UNLOAD_RESPONSE, cleanup all
 	 * maybe-pending messages on all CPUs to be able to receive new
@@ -827,6 +846,11 @@ static void vmbus_unload_response(struct vmbus_channel_message_header *hdr)
 	/*
 	 * This is a global event; just wakeup the waiting thread.
 	 * Once we successfully unload, we can cleanup the monitor state.
+	 *
+	 * NB.  A malicious or compromised Hyper-V could send a spurious
+	 * message of type CHANNELMSG_UNLOAD_RESPONSE, and trigger a call
+	 * of the complete() below.  Make sure that unload_event has been
+	 * initialized by the time this complete() is executed.
 	 */
 	complete(&vmbus_connection.unload_event);
 }
@@ -842,7 +866,7 @@ void vmbus_initiate_unload(bool crash)
 	if (vmbus_proto_version < VERSION_WIN8_1)
 		return;
 
-	init_completion(&vmbus_connection.unload_event);
+	reinit_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),
@@ -980,7 +1004,7 @@ static void vmbus_onoffer(struct vmbus_channel_message_header *hdr)
 		 *					UNLOCK channel_mutex
 		 *
 		 * Forbids: r1 == valid_relid &&
-		 * 		channels[valid_relid] == channel
+		 *              channels[valid_relid] == channel
 		 *
 		 * Note.  r1 can be INVALID_RELID only for an hv_sock channel.
 		 * None of the hv_sock channels which were present before the
@@ -1313,6 +1337,46 @@ static void vmbus_ongpadl_created(struct vmbus_channel_message_header *hdr)
 }
 
 /*
+ * vmbus_onmodifychannel_response - Modify Channel response handler.
+ *
+ * This is invoked when we received a response to our channel modify request.
+ * Find the matching request, copy the response and signal the requesting thread.
+ */
+static void vmbus_onmodifychannel_response(struct vmbus_channel_message_header *hdr)
+{
+	struct vmbus_channel_modifychannel_response *response;
+	struct vmbus_channel_msginfo *msginfo;
+	unsigned long flags;
+
+	response = (struct vmbus_channel_modifychannel_response *)hdr;
+
+	trace_vmbus_onmodifychannel_response(response);
+
+	/*
+	 * Find the modify msg, copy the response and signal/unblock the wait event.
+	 */
+	spin_lock_irqsave(&vmbus_connection.channelmsg_lock, flags);
+
+	list_for_each_entry(msginfo, &vmbus_connection.chn_msg_list, msglistentry) {
+		struct vmbus_channel_message_header *responseheader =
+				(struct vmbus_channel_message_header *)msginfo->msg;
+
+		if (responseheader->msgtype == CHANNELMSG_MODIFYCHANNEL) {
+			struct vmbus_channel_modifychannel *modifymsg;
+
+			modifymsg = (struct vmbus_channel_modifychannel *)msginfo->msg;
+			if (modifymsg->child_relid == response->child_relid) {
+				memcpy(&msginfo->response.modify_response, response,
+				       sizeof(*response));
+				complete(&msginfo->waitevent);
+				break;
+			}
+		}
+	}
+	spin_unlock_irqrestore(&vmbus_connection.channelmsg_lock, flags);
+}
+
+/*
  * vmbus_ongpadl_torndown - GPADL torndown handler.
  *
  * This is invoked when we received a response to our gpadl teardown request.
@@ -1429,6 +1493,8 @@ channel_message_table[CHANNELMSG_COUNT] = {
 	{ CHANNELMSG_TL_CONNECT_REQUEST,	0, NULL, 0},
 	{ CHANNELMSG_MODIFYCHANNEL,		0, NULL, 0},
 	{ CHANNELMSG_TL_CONNECT_RESULT,		0, NULL, 0},
+	{ CHANNELMSG_MODIFYCHANNEL_RESPONSE,	1, vmbus_onmodifychannel_response,
+		sizeof(struct vmbus_channel_modifychannel_response)},
 };
 
 /*
diff --git a/drivers/hv/connection.c b/drivers/hv/connection.c
index c83612cddb99..311cd005b3be 100644
--- a/drivers/hv/connection.c
+++ b/drivers/hv/connection.c
@@ -26,9 +26,11 @@
 
 struct vmbus_connection vmbus_connection = {
 	.conn_state		= DISCONNECTED,
+	.unload_event		= COMPLETION_INITIALIZER(
+				  vmbus_connection.unload_event),
 	.next_gpadl_handle	= ATOMIC_INIT(0xE1E10),
 
-	.ready_for_suspend_event= COMPLETION_INITIALIZER(
+	.ready_for_suspend_event = COMPLETION_INITIALIZER(
 				  vmbus_connection.ready_for_suspend_event),
 	.ready_for_resume_event	= COMPLETION_INITIALIZER(
 				  vmbus_connection.ready_for_resume_event),
@@ -45,6 +47,7 @@ EXPORT_SYMBOL_GPL(vmbus_proto_version);
  * Table of VMBus versions listed from newest to oldest.
  */
 static __u32 vmbus_versions[] = {
+	VERSION_WIN10_V5_3,
 	VERSION_WIN10_V5_2,
 	VERSION_WIN10_V5_1,
 	VERSION_WIN10_V5,
@@ -60,7 +63,7 @@ static __u32 vmbus_versions[] = {
  * Maximal VMBus protocol version guests can negotiate.  Useful to cap the
  * VMBus version for testing and debugging purpose.
  */
-static uint max_version = VERSION_WIN10_V5_2;
+static uint max_version = VERSION_WIN10_V5_3;
 
 module_param(max_version, uint, S_IRUGO);
 MODULE_PARM_DESC(max_version,
diff --git a/drivers/hv/hv.c b/drivers/hv/hv.c
index f202ac7f4b3d..e83507f49676 100644
--- a/drivers/hv/hv.c
+++ b/drivers/hv/hv.c
@@ -13,9 +13,10 @@
 #include <linux/slab.h>
 #include <linux/vmalloc.h>
 #include <linux/hyperv.h>
-#include <linux/version.h>
 #include <linux/random.h>
 #include <linux/clockchips.h>
+#include <linux/delay.h>
+#include <linux/interrupt.h>
 #include <clocksource/hyperv_timer.h>
 #include <asm/mshyperv.h>
 #include "hyperv_vmbus.h"
@@ -37,6 +38,42 @@ int hv_init(void)
 }
 
 /*
+ * Functions for allocating and freeing memory with size and
+ * alignment HV_HYP_PAGE_SIZE. These functions are needed because
+ * the guest page size may not be the same as the Hyper-V page
+ * size. We depend upon kmalloc() aligning power-of-two size
+ * allocations to the allocation size boundary, so that the
+ * allocated memory appears to Hyper-V as a page of the size
+ * it expects.
+ */
+
+void *hv_alloc_hyperv_page(void)
+{
+	BUILD_BUG_ON(PAGE_SIZE <  HV_HYP_PAGE_SIZE);
+
+	if (PAGE_SIZE == HV_HYP_PAGE_SIZE)
+		return (void *)__get_free_page(GFP_KERNEL);
+	else
+		return kmalloc(HV_HYP_PAGE_SIZE, GFP_KERNEL);
+}
+
+void *hv_alloc_hyperv_zeroed_page(void)
+{
+	if (PAGE_SIZE == HV_HYP_PAGE_SIZE)
+		return (void *)__get_free_page(GFP_KERNEL | __GFP_ZERO);
+	else
+		return kzalloc(HV_HYP_PAGE_SIZE, GFP_KERNEL);
+}
+
+void hv_free_hyperv_page(unsigned long addr)
+{
+	if (PAGE_SIZE == HV_HYP_PAGE_SIZE)
+		free_page(addr);
+	else
+		kfree((void *)addr);
+}
+
+/*
  * hv_post_message - Post a message using the hypervisor message IPC.
  *
  * This involves a hypercall.
@@ -68,7 +105,7 @@ int hv_post_message(union hv_connection_id connection_id,
 	 */
 	put_cpu_ptr(hv_cpu);
 
-	return status & 0xFFFF;
+	return hv_result(status);
 }
 
 int hv_synic_alloc(void)
@@ -162,34 +199,48 @@ void hv_synic_enable_regs(unsigned int cpu)
 	union hv_synic_scontrol sctrl;
 
 	/* Setup the Synic's message page */
-	hv_get_simp(simp.as_uint64);
+	simp.as_uint64 = hv_get_register(HV_REGISTER_SIMP);
 	simp.simp_enabled = 1;
 	simp.base_simp_gpa = virt_to_phys(hv_cpu->synic_message_page)
 		>> HV_HYP_PAGE_SHIFT;
 
-	hv_set_simp(simp.as_uint64);
+	hv_set_register(HV_REGISTER_SIMP, simp.as_uint64);
 
 	/* Setup the Synic's event page */
-	hv_get_siefp(siefp.as_uint64);
+	siefp.as_uint64 = hv_get_register(HV_REGISTER_SIEFP);
 	siefp.siefp_enabled = 1;
 	siefp.base_siefp_gpa = virt_to_phys(hv_cpu->synic_event_page)
 		>> HV_HYP_PAGE_SHIFT;
 
-	hv_set_siefp(siefp.as_uint64);
+	hv_set_register(HV_REGISTER_SIEFP, siefp.as_uint64);
 
 	/* Setup the shared SINT. */
-	hv_get_synint_state(VMBUS_MESSAGE_SINT, shared_sint.as_uint64);
+	if (vmbus_irq != -1)
+		enable_percpu_irq(vmbus_irq, 0);
+	shared_sint.as_uint64 = hv_get_register(HV_REGISTER_SINT0 +
+					VMBUS_MESSAGE_SINT);
 
-	shared_sint.vector = hv_get_vector();
+	shared_sint.vector = vmbus_interrupt;
 	shared_sint.masked = false;
-	shared_sint.auto_eoi = hv_recommend_using_aeoi();
-	hv_set_synint_state(VMBUS_MESSAGE_SINT, shared_sint.as_uint64);
+
+	/*
+	 * On architectures where Hyper-V doesn't support AEOI (e.g., ARM64),
+	 * it doesn't provide a recommendation flag and AEOI must be disabled.
+	 */
+#ifdef HV_DEPRECATING_AEOI_RECOMMENDED
+	shared_sint.auto_eoi =
+			!(ms_hyperv.hints & HV_DEPRECATING_AEOI_RECOMMENDED);
+#else
+	shared_sint.auto_eoi = 0;
+#endif
+	hv_set_register(HV_REGISTER_SINT0 + VMBUS_MESSAGE_SINT,
+				shared_sint.as_uint64);
 
 	/* Enable the global synic bit */
-	hv_get_synic_state(sctrl.as_uint64);
+	sctrl.as_uint64 = hv_get_register(HV_REGISTER_SCONTROL);
 	sctrl.enable = 1;
 
-	hv_set_synic_state(sctrl.as_uint64);
+	hv_set_register(HV_REGISTER_SCONTROL, sctrl.as_uint64);
 }
 
 int hv_synic_init(unsigned int cpu)
@@ -211,30 +262,71 @@ void hv_synic_disable_regs(unsigned int cpu)
 	union hv_synic_siefp siefp;
 	union hv_synic_scontrol sctrl;
 
-	hv_get_synint_state(VMBUS_MESSAGE_SINT, shared_sint.as_uint64);
+	shared_sint.as_uint64 = hv_get_register(HV_REGISTER_SINT0 +
+					VMBUS_MESSAGE_SINT);
 
 	shared_sint.masked = 1;
 
 	/* Need to correctly cleanup in the case of SMP!!! */
 	/* Disable the interrupt */
-	hv_set_synint_state(VMBUS_MESSAGE_SINT, shared_sint.as_uint64);
+	hv_set_register(HV_REGISTER_SINT0 + VMBUS_MESSAGE_SINT,
+				shared_sint.as_uint64);
 
-	hv_get_simp(simp.as_uint64);
+	simp.as_uint64 = hv_get_register(HV_REGISTER_SIMP);
 	simp.simp_enabled = 0;
 	simp.base_simp_gpa = 0;
 
-	hv_set_simp(simp.as_uint64);
+	hv_set_register(HV_REGISTER_SIMP, simp.as_uint64);
 
-	hv_get_siefp(siefp.as_uint64);
+	siefp.as_uint64 = hv_get_register(HV_REGISTER_SIEFP);
 	siefp.siefp_enabled = 0;
 	siefp.base_siefp_gpa = 0;
 
-	hv_set_siefp(siefp.as_uint64);
+	hv_set_register(HV_REGISTER_SIEFP, siefp.as_uint64);
 
 	/* Disable the global synic bit */
-	hv_get_synic_state(sctrl.as_uint64);
+	sctrl.as_uint64 = hv_get_register(HV_REGISTER_SCONTROL);
 	sctrl.enable = 0;
-	hv_set_synic_state(sctrl.as_uint64);
+	hv_set_register(HV_REGISTER_SCONTROL, sctrl.as_uint64);
+
+	if (vmbus_irq != -1)
+		disable_percpu_irq(vmbus_irq);
+}
+
+#define HV_MAX_TRIES 3
+/*
+ * Scan the event flags page of 'this' CPU looking for any bit that is set.  If we find one
+ * bit set, then wait for a few milliseconds.  Repeat these steps for a maximum of 3 times.
+ * Return 'true', if there is still any set bit after this operation; 'false', otherwise.
+ *
+ * If a bit is set, that means there is a pending channel interrupt.  The expectation is
+ * that the normal interrupt handling mechanism will find and process the channel interrupt
+ * "very soon", and in the process clear the bit.
+ */
+static bool hv_synic_event_pending(void)
+{
+	struct hv_per_cpu_context *hv_cpu = this_cpu_ptr(hv_context.cpu_context);
+	union hv_synic_event_flags *event =
+		(union hv_synic_event_flags *)hv_cpu->synic_event_page + VMBUS_MESSAGE_SINT;
+	unsigned long *recv_int_page = event->flags; /* assumes VMBus version >= VERSION_WIN8 */
+	bool pending;
+	u32 relid;
+	int tries = 0;
+
+retry:
+	pending = false;
+	for_each_set_bit(relid, recv_int_page, HV_EVENT_FLAGS_COUNT) {
+		/* Special case - VMBus channel protocol messages */
+		if (relid == 0)
+			continue;
+		pending = true;
+		break;
+	}
+	if (pending && tries++ < HV_MAX_TRIES) {
+		usleep_range(10000, 20000);
+		goto retry;
+	}
+	return pending;
 }
 
 int hv_synic_cleanup(unsigned int cpu)
@@ -242,6 +334,9 @@ int hv_synic_cleanup(unsigned int cpu)
 	struct vmbus_channel *channel, *sc;
 	bool channel_found = false;
 
+	if (vmbus_connection.conn_state != CONNECTED)
+		goto always_cleanup;
+
 	/*
 	 * Hyper-V does not provide a way to change the connect CPU once
 	 * it is set; we must preven