Merge tag 'hyperv-next-signed-20251006' of git://git.kernel.org/pub/scm/linux/kernel/git/hyperv/linux

Pull hyperv updates from Wei Liu:

 - Unify guest entry code for KVM and MSHV (Sean Christopherson)

 - Switch Hyper-V MSI domain to use msi_create_parent_irq_domain()
   (Nam Cao)

 - Add CONFIG_HYPERV_VMBUS and limit the semantics of CONFIG_HYPERV
   (Mukesh Rathor)

 - Add kexec/kdump support on Azure CVMs (Vitaly Kuznetsov)

 - Deprecate hyperv_fb in favor of Hyper-V DRM driver (Prasanna
   Kumar T S M)

 - Miscellaneous enhancements, fixes and cleanups (Abhishek Tiwari,
   Alok Tiwari, Nuno Das Neves, Wei Liu, Roman Kisel, Michael Kelley)

* tag 'hyperv-next-signed-20251006' of git://git.kernel.org/pub/scm/linux/kernel/git/hyperv/linux:
  hyperv: Remove the spurious null directive line
  MAINTAINERS: Mark hyperv_fb driver Obsolete
  fbdev/hyperv_fb: deprecate this in favor of Hyper-V DRM driver
  Drivers: hv: Make CONFIG_HYPERV bool
  Drivers: hv: Add CONFIG_HYPERV_VMBUS option
  Drivers: hv: vmbus: Fix typos in vmbus_drv.c
  Drivers: hv: vmbus: Fix sysfs output format for ring buffer index
  Drivers: hv: vmbus: Clean up sscanf format specifier in target_cpu_store()
  x86/hyperv: Switch to msi_create_parent_irq_domain()
  mshv: Use common "entry virt" APIs to do work in root before running guest
  entry: Rename "kvm" entry code assets to "virt" to genericize APIs
  entry/kvm: KVM: Move KVM details related to signal/-EINTR into KVM proper
  mshv: Handle NEED_RESCHED_LAZY before transferring to guest
  x86/hyperv: Add kexec/kdump support on Azure CVMs
  Drivers: hv: Simplify data structures for VMBus channel close message
  Drivers: hv: util: Cosmetic changes for hv_utils_transport.c
  mshv: Add support for a new parent partition configuration
  clocksource: hyper-v: Skip unnecessary checks for the root partition
  hyperv: Add missing field to hv_output_map_device_interrupt

45 files changed, 449 insertions, 193 deletions

diff --git a/MAINTAINERS b/MAINTAINERS
index b45db73e55df..9b754d290f93 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -10390,7 +10390,7 @@ L:	linux-kernel@vger.kernel.org
 S:	Maintained
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git core/entry
 F:	include/linux/entry-common.h
-F:	include/linux/entry-kvm.h
+F:	include/linux/entry-virt.h
 F:	include/linux/irq-entry-common.h
 F:	kernel/entry/
 
@@ -11604,7 +11604,6 @@ F:	drivers/pci/controller/pci-hyperv-intf.c
 F:	drivers/pci/controller/pci-hyperv.c
 F:	drivers/scsi/storvsc_drv.c
 F:	drivers/uio/uio_hv_generic.c
-F:	drivers/video/fbdev/hyperv_fb.c
 F:	include/asm-generic/mshyperv.h
 F:	include/clocksource/hyperv_timer.h
 F:	include/hyperv/hvgdk.h
@@ -11618,6 +11617,16 @@ F:	include/uapi/linux/hyperv.h
 F:	net/vmw_vsock/hyperv_transport.c
 F:	tools/hv/
 
+HYPER-V FRAMEBUFFER DRIVER
+M:	"K. Y. Srinivasan" <kys@microsoft.com>
+M:	Haiyang Zhang <haiyangz@microsoft.com>
+M:	Wei Liu <wei.liu@kernel.org>
+M:	Dexuan Cui <decui@microsoft.com>
+L:	linux-hyperv@vger.kernel.org
+S:	Obsolete
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/hyperv/linux.git
+F:	drivers/video/fbdev/hyperv_fb.c
+
 HYPERBUS SUPPORT
 M:	Vignesh Raghavendra <vigneshr@ti.com>
 R:	Tudor Ambarus <tudor.ambarus@linaro.org>
diff --git a/arch/arm64/kvm/Kconfig b/arch/arm64/kvm/Kconfig
index bff62e75d681..4f803fd1c99a 100644
--- a/arch/arm64/kvm/Kconfig
+++ b/arch/arm64/kvm/Kconfig
@@ -25,7 +25,7 @@ menuconfig KVM
 	select HAVE_KVM_CPU_RELAX_INTERCEPT
 	select KVM_MMIO
 	select KVM_GENERIC_DIRTYLOG_READ_PROTECT
-	select KVM_XFER_TO_GUEST_WORK
+	select VIRT_XFER_TO_GUEST_WORK
 	select KVM_VFIO
 	select HAVE_KVM_DIRTY_RING_ACQ_REL
 	select NEED_KVM_DIRTY_RING_WITH_BITMAP
diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c
index fa79744290f3..f21d1b7f20f8 100644
--- a/arch/arm64/kvm/arm.c
+++ b/arch/arm64/kvm/arm.c
@@ -6,7 +6,6 @@
 
 #include <linux/bug.h>
 #include <linux/cpu_pm.h>
-#include <linux/entry-kvm.h>
 #include <linux/errno.h>
 #include <linux/err.h>
 #include <linux/kvm_host.h>
@@ -1183,7 +1182,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu)
 		/*
 		 * Check conditions before entering the guest
 		 */
-		ret = xfer_to_guest_mode_handle_work(vcpu);
+		ret = kvm_xfer_to_guest_mode_handle_work(vcpu);
 		if (!ret)
 			ret = 1;
 
diff --git a/arch/loongarch/kvm/Kconfig b/arch/loongarch/kvm/Kconfig
index 40eea6da7c25..ae64bbdf83a7 100644
--- a/arch/loongarch/kvm/Kconfig
+++ b/arch/loongarch/kvm/Kconfig
@@ -31,7 +31,7 @@ config KVM
 	select KVM_GENERIC_HARDWARE_ENABLING
 	select KVM_GENERIC_MMU_NOTIFIER
 	select KVM_MMIO
-	select KVM_XFER_TO_GUEST_WORK
+	select VIRT_XFER_TO_GUEST_WORK
 	select SCHED_INFO
 	select GUEST_PERF_EVENTS if PERF_EVENTS
 	help
diff --git a/arch/loongarch/kvm/vcpu.c b/arch/loongarch/kvm/vcpu.c
index 9c802f7103c6..30e3b089a596 100644
--- a/arch/loongarch/kvm/vcpu.c
+++ b/arch/loongarch/kvm/vcpu.c
@@ -4,7 +4,6 @@
  */
 
 #include <linux/kvm_host.h>
-#include <linux/entry-kvm.h>
 #include <asm/fpu.h>
 #include <asm/lbt.h>
 #include <asm/loongarch.h>
@@ -251,7 +250,7 @@ static int kvm_enter_guest_check(struct kvm_vcpu *vcpu)
 	/*
 	 * Check conditions before entering the guest
 	 */
-	ret = xfer_to_guest_mode_handle_work(vcpu);
+	ret = kvm_xfer_to_guest_mode_handle_work(vcpu);
 	if (ret < 0)
 		return ret;
 
diff --git a/arch/riscv/kvm/Kconfig b/arch/riscv/kvm/Kconfig
index 5a62091b0809..c50328212917 100644
--- a/arch/riscv/kvm/Kconfig
+++ b/arch/riscv/kvm/Kconfig
@@ -30,7 +30,7 @@ config KVM
 	select KVM_GENERIC_DIRTYLOG_READ_PROTECT
 	select KVM_GENERIC_HARDWARE_ENABLING
 	select KVM_MMIO
-	select KVM_XFER_TO_GUEST_WORK
+	select VIRT_XFER_TO_GUEST_WORK
 	select KVM_GENERIC_MMU_NOTIFIER
 	select SCHED_INFO
 	select GUEST_PERF_EVENTS if PERF_EVENTS
diff --git a/arch/riscv/kvm/vcpu.c b/arch/riscv/kvm/vcpu.c
index 47bcf190ccc5..bccb919ca615 100644
--- a/arch/riscv/kvm/vcpu.c
+++ b/arch/riscv/kvm/vcpu.c
@@ -7,7 +7,6 @@
  */
 
 #include <linux/bitops.h>
-#include <linux/entry-kvm.h>
 #include <linux/errno.h>
 #include <linux/err.h>
 #include <linux/kdebug.h>
@@ -911,7 +910,7 @@ int kvm_arch_vcpu_ioctl_run(struct kvm_vcpu *vcpu)
 	run->exit_reason = KVM_EXIT_UNKNOWN;
 	while (ret > 0) {
 		/* Check conditions before entering the guest */
-		ret = xfer_to_guest_mode_handle_work(vcpu);
+		ret = kvm_xfer_to_guest_mode_handle_work(vcpu);
 		if (ret)
 			continue;
 		ret = 1;
diff --git a/arch/x86/hyperv/irqdomain.c b/arch/x86/hyperv/irqdomain.c
index 090f5ac9f492..c3ba12b1bc07 100644
--- a/arch/x86/hyperv/irqdomain.c
+++ b/arch/x86/hyperv/irqdomain.c
@@ -11,6 +11,7 @@
 #include <linux/pci.h>
 #include <linux/irq.h>
 #include <linux/export.h>
+#include <linux/irqchip/irq-msi-lib.h>
 #include <asm/mshyperv.h>
 
 static int hv_map_interrupt(union hv_device_id device_id, bool level,
@@ -289,59 +290,99 @@ static void hv_teardown_msi_irq(struct pci_dev *dev, struct irq_data *irqd)
 	(void)hv_unmap_msi_interrupt(dev, &old_entry);
 }
 
-static void hv_msi_free_irq(struct irq_domain *domain,
-			    struct msi_domain_info *info, unsigned int virq)
-{
-	struct irq_data *irqd = irq_get_irq_data(virq);
-	struct msi_desc *desc;
-
-	if (!irqd)
-		return;
-
-	desc = irq_data_get_msi_desc(irqd);
-	if (!desc || !desc->irq || WARN_ON_ONCE(!dev_is_pci(desc->dev)))
-		return;
-
-	hv_teardown_msi_irq(to_pci_dev(desc->dev), irqd);
-}
-
 /*
  * IRQ Chip for MSI PCI/PCI-X/PCI-Express Devices,
  * which implement the MSI or MSI-X Capability Structure.
  */
 static struct irq_chip hv_pci_msi_controller = {
 	.name			= "HV-PCI-MSI",
-	.irq_unmask		= pci_msi_unmask_irq,
-	.irq_mask		= pci_msi_mask_irq,
 	.irq_ack		= irq_chip_ack_parent,
-	.irq_retrigger		= irq_chip_retrigger_hierarchy,
 	.irq_compose_msi_msg	= hv_irq_compose_msi_msg,
-	.irq_set_affinity	= msi_domain_set_affinity,
-	.flags			= IRQCHIP_SKIP_SET_WAKE | IRQCHIP_MOVE_DEFERRED,
+	.irq_set_affinity	= irq_chip_set_affinity_parent,
 };
 
-static struct msi_domain_ops pci_msi_domain_ops = {
-	.msi_free		= hv_msi_free_irq,
-	.msi_prepare		= pci_msi_prepare,
+static bool hv_init_dev_msi_info(struct device *dev, struct irq_domain *domain,
+				 struct irq_domain *real_parent, struct msi_domain_info *info)
+{
+	struct irq_chip *chip = info->chip;
+
+	if (!msi_lib_init_dev_msi_info(dev, domain, real_parent, info))
+		return false;
+
+	chip->flags |= IRQCHIP_SKIP_SET_WAKE | IRQCHIP_MOVE_DEFERRED;
+
+	info->ops->msi_prepare = pci_msi_prepare;
+
+	return true;
+}
+
+#define HV_MSI_FLAGS_SUPPORTED	(MSI_GENERIC_FLAGS_MASK | MSI_FLAG_PCI_MSIX)
+#define HV_MSI_FLAGS_REQUIRED	(MSI_FLAG_USE_DEF_DOM_OPS | MSI_FLAG_USE_DEF_CHIP_OPS)
+
+static struct msi_parent_ops hv_msi_parent_ops = {
+	.supported_flags	= HV_MSI_FLAGS_SUPPORTED,
+	.required_flags		= HV_MSI_FLAGS_REQUIRED,
+	.bus_select_token	= DOMAIN_BUS_NEXUS,
+	.bus_select_mask	= MATCH_PCI_MSI,
+	.chip_flags		= MSI_CHIP_FLAG_SET_ACK,
+	.prefix			= "HV-",
+	.init_dev_msi_info	= hv_init_dev_msi_info,
 };
 
-static struct msi_domain_info hv_pci_msi_domain_info = {
-	.flags		= MSI_FLAG_USE_DEF_DOM_OPS | MSI_FLAG_USE_DEF_CHIP_OPS |
-			  MSI_FLAG_PCI_MSIX,
-	.ops		= &pci_msi_domain_ops,
-	.chip		= &hv_pci_msi_controller,
-	.handler	= handle_edge_irq,
-	.handler_name	= "edge",
+static int hv_msi_domain_alloc(struct irq_domain *d, unsigned int virq, unsigned int nr_irqs,
+			       void *arg)
+{
+	/*
+	 * TODO: The allocation bits of hv_irq_compose_msi_msg(), i.e. everything except
+	 * entry_to_msi_msg() should be in here.
+	 */
+
+	int ret;
+
+	ret = irq_domain_alloc_irqs_parent(d, virq, nr_irqs, arg);
+	if (ret)
+		return ret;
+
+	for (int i = 0; i < nr_irqs; ++i) {
+		irq_domain_set_info(d, virq + i, 0, &hv_pci_msi_controller, NULL,
+				    handle_edge_irq, NULL, "edge");
+	}
+	return 0;
+}
+
+static void hv_msi_domain_free(struct irq_domain *d, unsigned int virq, unsigned int nr_irqs)
+{
+	for (int i = 0; i < nr_irqs; ++i) {
+		struct irq_data *irqd = irq_domain_get_irq_data(d, virq);
+		struct msi_desc *desc;
+
+		desc = irq_data_get_msi_desc(irqd);
+		if (!desc || !desc->irq || WARN_ON_ONCE(!dev_is_pci(desc->dev)))
+			continue;
+
+		hv_teardown_msi_irq(to_pci_dev(desc->dev), irqd);
+	}
+	irq_domain_free_irqs_top(d, virq, nr_irqs);
+}
+
+static const struct irq_domain_ops hv_msi_domain_ops = {
+	.select	= msi_lib_irq_domain_select,
+	.alloc	= hv_msi_domain_alloc,
+	.free	= hv_msi_domain_free,
 };
 
 struct irq_domain * __init hv_create_pci_msi_domain(void)
 {
 	struct irq_domain *d = NULL;
-	struct fwnode_handle *fn;
 
-	fn = irq_domain_alloc_named_fwnode("HV-PCI-MSI");
-	if (fn)
-		d = pci_msi_create_irq_domain(fn, &hv_pci_msi_domain_info, x86_vector_domain);
+	struct irq_domain_info info = {
+		.fwnode		= irq_domain_alloc_named_fwnode("HV-PCI-MSI"),
+		.ops		= &hv_msi_domain_ops,
+		.parent		= x86_vector_domain,
+	};
+
+	if (info.fwnode)
+		d = msi_create_parent_irq_domain(&info, &hv_msi_parent_ops);
 
 	/* No point in going further if we can't get an irq domain */
 	BUG_ON(!d);
diff --git a/arch/x86/hyperv/ivm.c b/arch/x86/hyperv/ivm.c
index ade6c665c97e..a4615b889f3e 100644
--- a/arch/x86/hyperv/ivm.c
+++ b/arch/x86/hyperv/ivm.c
@@ -463,6 +463,195 @@ void hv_ivm_msr_read(u64 msr, u64 *value)
 }
 
 /*
+ * Keep track of the PFN regions which were shared with the host. The access
+ * must be revoked upon kexec/kdump (see hv_ivm_clear_host_access()).
+ */
+struct hv_enc_pfn_region {
+	struct list_head list;
+	u64 pfn;
+	int count;
+};
+
+static LIST_HEAD(hv_list_enc);
+static DEFINE_RAW_SPINLOCK(hv_list_enc_lock);
+
+static int hv_list_enc_add(const u64 *pfn_list, int count)
+{
+	struct hv_enc_pfn_region *ent;
+	unsigned long flags;
+	u64 pfn;
+	int i;
+
+	for (i = 0; i < count; i++) {
+		pfn = pfn_list[i];
+
+		raw_spin_lock_irqsave(&hv_list_enc_lock, flags);
+		/* Check if the PFN already exists in some region first */
+		list_for_each_entry(ent, &hv_list_enc, list) {
+			if ((ent->pfn <= pfn) && (ent->pfn + ent->count - 1 >= pfn))
+				/* Nothing to do - pfn is already in the list */
+				goto unlock_done;
+		}
+
+		/*
+		 * Check if the PFN is adjacent to an existing region. Growing
+		 * a region can make it adjacent to another one but merging is
+		 * not (yet) implemented for simplicity. A PFN cannot be added
+		 * to two regions to keep the logic in hv_list_enc_remove()
+		 * correct.
+		 */
+		list_for_each_entry(ent, &hv_list_enc, list) {
+			if (ent->pfn + ent->count == pfn) {
+				/* Grow existing region up */
+				ent->count++;
+				goto unlock_done;
+			} else if (pfn + 1 == ent->pfn) {
+				/* Grow existing region down */
+				ent->pfn--;
+				ent->count++;
+				goto unlock_done;
+			}
+		}
+		raw_spin_unlock_irqrestore(&hv_list_enc_lock, flags);
+
+		/* No adjacent region found -- create a new one */
+		ent = kzalloc(sizeof(struct hv_enc_pfn_region), GFP_KERNEL);
+		if (!ent)
+			return -ENOMEM;
+
+		ent->pfn = pfn;
+		ent->count = 1;
+
+		raw_spin_lock_irqsave(&hv_list_enc_lock, flags);
+		list_add(&ent->list, &hv_list_enc);
+
+unlock_done:
+		raw_spin_unlock_irqrestore(&hv_list_enc_lock, flags);
+	}
+
+	return 0;
+}
+
+static int hv_list_enc_remove(const u64 *pfn_list, int count)
+{
+	struct hv_enc_pfn_region *ent, *t;
+	struct hv_enc_pfn_region new_region;
+	unsigned long flags;
+	u64 pfn;
+	int i;
+
+	for (i = 0; i < count; i++) {
+		pfn = pfn_list[i];
+
+		raw_spin_lock_irqsave(&hv_list_enc_lock, flags);
+		list_for_each_entry_safe(ent, t, &hv_list_enc, list) {
+			if (pfn == ent->pfn + ent->count - 1) {
+				/* Removing tail pfn */
+				ent->count--;
+				if (!ent->count) {
+					list_del(&ent->list);
+					kfree(ent);
+				}
+				goto unlock_done;
+			} else if (pfn == ent->pfn) {
+				/* Removing head pfn */
+				ent->count--;
+				ent->pfn++;
+				if (!ent->count) {
+					list_del(&ent->list);
+					kfree(ent);
+				}
+				goto unlock_done;
+			} else if (pfn > ent->pfn && pfn < ent->pfn + ent->count - 1) {
+				/*
+				 * Removing a pfn in the middle. Cut off the tail
+				 * of the existing region and create a template for
+				 * the new one.
+				 */
+				new_region.pfn = pfn + 1;
+				new_region.count = ent->count - (pfn - ent->pfn + 1);
+				ent->count = pfn - ent->pfn;
+				goto unlock_split;
+			}
+
+		}
+unlock_done:
+		raw_spin_unlock_irqrestore(&hv_list_enc_lock, flags);
+		continue;
+
+unlock_split:
+		raw_spin_unlock_irqrestore(&hv_list_enc_lock, flags);
+
+		ent = kzalloc(sizeof(struct hv_enc_pfn_region), GFP_KERNEL);
+		if (!ent)
+			return -ENOMEM;
+
+		ent->pfn = new_region.pfn;
+		ent->count = new_region.count;
+
+		raw_spin_lock_irqsave(&hv_list_enc_lock, flags);
+		list_add(&ent->list, &hv_list_enc);
+		raw_spin_unlock_irqrestore(&hv_list_enc_lock, flags);
+	}
+
+	return 0;
+}
+
+/* Stop new private<->shared conversions */
+static void hv_vtom_kexec_begin(void)
+{
+	if (!IS_ENABLED(CONFIG_KEXEC_CORE))
+		return;
+
+	/*
+	 * Crash kernel reaches here with interrupts disabled: can't wait for
+	 * conversions to finish.
+	 *
+	 * If race happened, just report and proceed.
+	 */
+	if (!set_memory_enc_stop_conversion())
+		pr_warn("Failed to stop shared<->private conversions\n");
+}
+
+static void hv_vtom_kexec_finish(void)
+{
+	struct hv_gpa_range_for_visibility *input;
+	struct hv_enc_pfn_region *ent;
+	unsigned long flags;
+	u64 hv_status;
+	int cur, i;
+
+	local_irq_save(flags);
+	input = *this_cpu_ptr(hyperv_pcpu_input_arg);
+
+	if (unlikely(!input))
+		goto out;
+
+	list_for_each_entry(ent, &hv_list_enc, list) {
+		for (i = 0, cur = 0; i < ent->count; i++) {
+			input->gpa_page_list[cur] = ent->pfn + i;
+			cur++;
+
+			if (cur == HV_MAX_MODIFY_GPA_REP_COUNT || i == ent->count - 1) {
+				input->partition_id = HV_PARTITION_ID_SELF;
+				input->host_visibility = VMBUS_PAGE_NOT_VISIBLE;
+				input->reserved0 = 0;
+				input->reserved1 = 0;
+				hv_status = hv_do_rep_hypercall(
+					HVCALL_MODIFY_SPARSE_GPA_PAGE_HOST_VISIBILITY,
+					cur, 0, input, NULL);
+				WARN_ON_ONCE(!hv_result_success(hv_status));
+				cur = 0;
+			}
+		}
+
+	}
+
+out:
+	local_irq_restore(flags);
+}
+
+/*
  * hv_mark_gpa_visibility - Set pages visible to host via hvcall.
  *
  * In Isolation VM, all guest memory is encrypted from host and guest
@@ -475,6 +664,7 @@ static int hv_mark_gpa_visibility(u16 count, const u64 pfn[],
 	struct hv_gpa_range_for_visibility *input;
 	u64 hv_status;
 	unsigned long flags;
+	int ret;
 
 	/* no-op if partition isolation is not enabled */
 	if (!hv_is_isolation_supported())
@@ -486,6 +676,13 @@ static int hv_mark_gpa_visibility(u16 count, const u64 pfn[],
 		return -EINVAL;
 	}
 
+	if (visibility == VMBUS_PAGE_NOT_VISIBLE)
+		ret = hv_list_enc_remove(pfn, count);
+	else
+		ret = hv_list_enc_add(pfn, count);
+	if (ret)
+		return ret;
+
 	local_irq_save(flags);
 	input = *this_cpu_ptr(hyperv_pcpu_input_arg);
 
@@ -506,8 +703,18 @@ static int hv_mark_gpa_visibility(u16 count, const u64 pfn[],
 
 	if (hv_result_success(hv_status))
 		return 0;
+
+	if (visibility == VMBUS_PAGE_NOT_VISIBLE)
+		ret = hv_list_enc_add(pfn, count);
 	else
-		return -EFAULT;
+		ret = hv_list_enc_remove(pfn, count);
+	/*
+	 * There's no good way to recover from -ENOMEM here, the accounting is
+	 * wrong either way.
+	 */
+	WARN_ON_ONCE(ret);
+
+	return -EFAULT;
 }
 
 /*
@@ -669,6 +876,8 @@ void __init hv_vtom_init(void)
 	x86_platform.guest.enc_tlb_flush_required = hv_vtom_tlb_flush_required;
 	x86_platform.guest.enc_status_change_prepare = hv_vtom_clear_present;
 	x86_platform.guest.enc_status_change_finish = hv_vtom_set_host_visibility;
+	x86_platform.guest.enc_kexec_begin = hv_vtom_kexec_begin;
+	x86_platform.guest.enc_kexec_finish = hv_vtom_kexec_finish;
 
 	/* Set WB as the default cache mode. */
 	guest_force_mtrr_state(NULL, 0, MTRR_TYPE_WRBACK);
diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c
index c78f860419d6..25773af116bc 100644
--- a/arch/x86/kernel/cpu/mshyperv.c
+++ b/arch/x86/kernel/cpu/mshyperv.c
@@ -565,6 +565,11 @@ static void __init ms_hyperv_init_platform(void)
 	machine_ops.crash_shutdown = hv_machine_crash_shutdown;
 #endif
 #endif
+	/*
+	 * HV_ACCESS_TSC_INVARIANT is always zero for the root partition. Root
+	 * partition doesn't need to write to synthetic MSR to enable invariant
+	 * TSC feature. It sees what the hardware provides.
+	 */
 	if (ms_hyperv.features & HV_ACCESS_TSC_INVARIANT) {
 		/*
 		 * Writing to synthetic MSR 0x40000118 updates/changes the
@@ -636,8 +641,12 @@ static void __init ms_hyperv_init_platform(void)
 	 * TSC should be marked as unstable only after Hyper-V
 	 * clocksource has been initialized. This ensures that the
 	 * stability of the sched_clock is not altered.
+	 *
+	 * HV_ACCESS_TSC_INVARIANT is always zero for the root partition. No
+	 * need to check for it.
 	 */
-	if (!(ms_hyperv.features & HV_ACCESS_TSC_INVARIANT))
+	if (!hv_root_partition() &&
+	    !(ms_hyperv.features & HV_ACCESS_TSC_INVARIANT))
 		mark_tsc_unstable("running on Hyper-V");
 
 	hardlockup_detector_disable();
diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig
index 4e43923656d0..67d4f23bab66 100644
--- a/arch/x86/kvm/Kconfig
+++ b/arch/x86/kvm/Kconfig
@@ -40,7 +40,7 @@ config KVM_X86
 	select HAVE_KVM_MSI
 	select HAVE_KVM_CPU_RELAX_INTERCEPT
 	select HAVE_KVM_NO_POLL
-	select KVM_XFER_TO_GUEST_WORK
+	select VIRT_XFER_TO_GUEST_WORK
 	select KVM_GENERIC_DIRTYLOG_READ_PROTECT
 	select KVM_VFIO
 	select HAVE_KVM_PM_NOTIFIER if PM
diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
index 546272a5d34d..d7b258af63ea 100644
--- a/arch/x86/kvm/vmx/vmx.c
+++ b/arch/x86/kvm/vmx/vmx.c
@@ -28,7 +28,6 @@
 #include <linux/slab.h>
 #include <linux/tboot.h>
 #include <linux/trace_events.h>
-#include <linux/entry-kvm.h>
 
 #include <asm/apic.h>
 #include <asm/asm.h>
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 4b8138bd4857..42ecd093bb4c 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -59,7 +59,6 @@
 #include <linux/sched/stat.h>
 #include <linux/sched/isolation.h>
 #include <linux/mem_encrypt.h>
-#include <linux/entry-kvm.h>
 #include <linux/suspend.h>
 #include <linux/smp.h>
 
@@ -11635,7 +11634,7 @@ static int vcpu_run(struct kvm_vcpu *vcpu)
 
 		if (__xfer_to_guest_mode_work_pending()) {
 			kvm_vcpu_srcu_read_unlock(vcpu);
-			r = xfer_to_guest_mode_handle_work(vcpu);
+			r = kvm_xfer_to_guest_mode_handle_work(vcpu);
 			kvm_vcpu_srcu_read_lock(vcpu);
 			if (r)
 				return r;
diff --git a/drivers/Makefile b/drivers/Makefile
index a104163b1353..8e1ffa4358d5 100644
--- a/drivers/Makefile
+++ b/drivers/Makefile
@@ -161,7 +161,7 @@ obj-$(CONFIG_SOUNDWIRE)		+= soundwire/
 
 # Virtualization drivers
 obj-$(CONFIG_VIRT_DRIVERS)	+= virt/
-obj-$(subst m,y,$(CONFIG_HYPERV))	+= hv/
+obj-$(CONFIG_HYPERV)		+= hv/
 
 obj-$(CONFIG_PM_DEVFREQ)	+= devfreq/
 obj-$(CONFIG_EXTCON)		+= extcon/
diff --git a/drivers/clocksource/hyperv_timer.c b/drivers/clocksource/hyperv_timer.c
index 2edc13ca184e..10356d4ec55c 100644
--- a/drivers/clocksource/hyperv_timer.c
+++ b/drivers/clocksource/hyperv_timer.c
@@ -549,14 +549,22 @@ static void __init hv_init_tsc_clocksource(void)
 	union hv_reference_tsc_msr tsc_msr;
 
 	/*
+	 * When running as a guest partition:
+	 *
 	 * 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.
+	 *
+	 * When running as the root partition:
+	 *
+	 * There is no HV_ACCESS_TSC_INVARIANT feature. Always lower the rating
+	 * of the Hyper-V Reference TSC.
 	 */
-	if (ms_hyperv.features & HV_ACCESS_TSC_INVARIANT) {
+	if ((ms_hyperv.features & HV_ACCESS_TSC_INVARIANT) ||
+	    hv_root_partition()) {
 		hyperv_cs_tsc.rating = 250;
 		hyperv_cs_msr.rating = 245;
 	}
diff --git a/drivers/gpu/drm/Kconfig b/drivers/gpu/drm/Kconfig
index fda170730468..7e6bc0b3a589 100644
--- a/drivers/gpu/drm/Kconfig
+++ b/drivers/gpu/drm/Kconfig
@@ -400,7 +400,7 @@ source "drivers/gpu/drm/tyr/Kconfig"
 
 config DRM_HYPERV
 	tristate "DRM Support for Hyper-V synthetic video device"
-	depends on DRM && PCI && HYPERV
+	depends on DRM && PCI && HYPERV_VMBUS
 	select DRM_CLIENT_SELECTION
 	select DRM_KMS_HELPER
 	select DRM_GEM_SHMEM_HELPER
diff --git a/drivers/hid/Kconfig b/drivers/hid/Kconfig
index 7ff85c7200e5..5341aa79f387 100644
--- a/drivers/hid/Kconfig
+++ b/drivers/h