Merge tag 'hyperv-next-signed-20250324' of git://git.kernel.org/pub/scm/linux/kernel/git/hyperv/linux

Pull hyperv updates from Wei Liu:

 - Add support for running as the root partition in Hyper-V (Microsoft
   Hypervisor) by exposing /dev/mshv (Nuno and various people)

 - Add support for CPU offlining in Hyper-V (Hamza Mahfooz)

 - Misc fixes and cleanups (Roman Kisel, Tianyu Lan, Wei Liu, Michael
   Kelley, Thorsten Blum)

* tag 'hyperv-next-signed-20250324' of git://git.kernel.org/pub/scm/linux/kernel/git/hyperv/linux: (24 commits)
  x86/hyperv: fix an indentation issue in mshyperv.h
  x86/hyperv: Add comments about hv_vpset and var size hypercall input args
  Drivers: hv: Introduce mshv_root module to expose /dev/mshv to VMMs
  hyperv: Add definitions for root partition driver to hv headers
  x86: hyperv: Add mshv_handler() irq handler and setup function
  Drivers: hv: Introduce per-cpu event ring tail
  Drivers: hv: Export some functions for use by root partition module
  acpi: numa: Export node_to_pxm()
  hyperv: Introduce hv_recommend_using_aeoi()
  arm64/hyperv: Add some missing functions to arm64
  x86/mshyperv: Add support for extended Hyper-V features
  hyperv: Log hypercall status codes as strings
  x86/hyperv: Fix check of return value from snp_set_vmsa()
  x86/hyperv: Add VTL mode callback for restarting the system
  x86/hyperv: Add VTL mode emergency restart callback
  hyperv: Remove unused union and structs
  hyperv: Add CONFIG_MSHV_ROOT to gate root partition support
  hyperv: Change hv_root_partition into a function
  hyperv: Convert hypercall statuses to linux error codes
  drivers/hv: add CPU offlining support
  ...

16 files changed, 5927 insertions, 69 deletions

diff --git a/drivers/hv/Kconfig b/drivers/hv/Kconfig
index 862c47b191af..6c1416167bd2 100644
--- a/drivers/hv/Kconfig
+++ b/drivers/hv/Kconfig
@@ -55,4 +55,21 @@ config HYPERV_BALLOON
 	help
 	  Select this option to enable Hyper-V Balloon driver.
 
+config MSHV_ROOT
+	tristate "Microsoft Hyper-V root partition support"
+	depends on HYPERV && (X86_64 || ARM64)
+	depends on !HYPERV_VTL_MODE
+	# The hypervisor interface operates on 4k pages. Enforcing it here
+	# simplifies many assumptions in the root partition code.
+	# e.g. When withdrawing memory, the hypervisor gives back 4k pages in
+	# no particular order, making it impossible to reassemble larger pages
+	depends on PAGE_SIZE_4KB
+	select EVENTFD
+	default n
+	help
+	  Select this option to enable support for booting and running as root
+	  partition on Microsoft Hyper-V.
+
+	  If unsure, say N.
+
 endmenu
diff --git a/drivers/hv/Makefile b/drivers/hv/Makefile
index b992c0ed182b..976189c725dc 100644
--- a/drivers/hv/Makefile
+++ b/drivers/hv/Makefile
@@ -2,6 +2,7 @@
 obj-$(CONFIG_HYPERV)		+= hv_vmbus.o
 obj-$(CONFIG_HYPERV_UTILS)	+= hv_utils.o
 obj-$(CONFIG_HYPERV_BALLOON)	+= hv_balloon.o
+obj-$(CONFIG_MSHV_ROOT)		+= mshv_root.o
 
 CFLAGS_hv_trace.o = -I$(src)
 CFLAGS_hv_balloon.o = -I$(src)
@@ -11,6 +12,9 @@ hv_vmbus-y := vmbus_drv.o \
 		 channel_mgmt.o ring_buffer.o hv_trace.o
 hv_vmbus-$(CONFIG_HYPERV_TESTING)	+= hv_debugfs.o
 hv_utils-y := hv_util.o hv_kvp.o hv_snapshot.o hv_utils_transport.o
+mshv_root-y := mshv_root_main.o mshv_synic.o mshv_eventfd.o mshv_irq.o \
+	       mshv_root_hv_call.o mshv_portid_table.o
 
 # Code that must be built-in
 obj-$(subst m,y,$(CONFIG_HYPERV)) += hv_common.o
+obj-$(subst m,y,$(CONFIG_MSHV_ROOT)) += hv_proc.o mshv_common.o
diff --git a/drivers/hv/hv.c b/drivers/hv/hv.c
index 36d9ba097ff5..308c8f279df8 100644
--- a/drivers/hv/hv.c
+++ b/drivers/hv/hv.c
@@ -144,7 +144,7 @@ int hv_synic_alloc(void)
 		 * Synic message and event pages are allocated by paravisor.
 		 * Skip these pages allocation here.
 		 */
-		if (!ms_hyperv.paravisor_present && !hv_root_partition) {
+		if (!ms_hyperv.paravisor_present && !hv_root_partition()) {
 			hv_cpu->synic_message_page =
 				(void *)get_zeroed_page(GFP_ATOMIC);
 			if (!hv_cpu->synic_message_page) {
@@ -272,7 +272,7 @@ void hv_synic_enable_regs(unsigned int cpu)
 	simp.as_uint64 = hv_get_msr(HV_MSR_SIMP);
 	simp.simp_enabled = 1;
 
-	if (ms_hyperv.paravisor_present || hv_root_partition) {
+	if (ms_hyperv.paravisor_present || hv_root_partition()) {
 		/* Mask out vTOM bit. ioremap_cache() maps decrypted */
 		u64 base = (simp.base_simp_gpa << HV_HYP_PAGE_SHIFT) &
 				~ms_hyperv.shared_gpa_boundary;
@@ -291,7 +291,7 @@ void hv_synic_enable_regs(unsigned int cpu)
 	siefp.as_uint64 = hv_get_msr(HV_MSR_SIEFP);
 	siefp.siefp_enabled = 1;
 
-	if (ms_hyperv.paravisor_present || hv_root_partition) {
+	if (ms_hyperv.paravisor_present || hv_root_partition()) {
 		/* Mask out vTOM bit. ioremap_cache() maps decrypted */
 		u64 base = (siefp.base_siefp_gpa << HV_HYP_PAGE_SHIFT) &
 				~ms_hyperv.shared_gpa_boundary;
@@ -313,17 +313,7 @@ void hv_synic_enable_regs(unsigned int cpu)
 
 	shared_sint.vector = vmbus_interrupt;
 	shared_sint.masked = false;
-
-	/*
-	 * 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
+	shared_sint.auto_eoi = hv_recommend_using_aeoi();
 	hv_set_msr(HV_MSR_SINT0 + VMBUS_MESSAGE_SINT, shared_sint.as_uint64);
 
 	/* Enable the global synic bit */
@@ -367,7 +357,7 @@ void hv_synic_disable_regs(unsigned int cpu)
 	 * addresses.
 	 */
 	simp.simp_enabled = 0;
-	if (ms_hyperv.paravisor_present || hv_root_partition) {
+	if (ms_hyperv.paravisor_present || hv_root_partition()) {
 		iounmap(hv_cpu->synic_message_page);
 		hv_cpu->synic_message_page = NULL;
 	} else {
@@ -379,7 +369,7 @@ void hv_synic_disable_regs(unsigned int cpu)
 	siefp.as_uint64 = hv_get_msr(HV_MSR_SIEFP);
 	siefp.siefp_enabled = 0;
 
-	if (ms_hyperv.paravisor_present || hv_root_partition) {
+	if (ms_hyperv.paravisor_present || hv_root_partition()) {
 		iounmap(hv_cpu->synic_event_page);
 		hv_cpu->synic_event_page = NULL;
 	} else {
@@ -433,13 +423,47 @@ retry:
 	return pending;
 }
 
+static int hv_pick_new_cpu(struct vmbus_channel *channel)
+{
+	int ret = -EBUSY;
+	int start;
+	int cpu;
+
+	lockdep_assert_cpus_held();
+	lockdep_assert_held(&vmbus_connection.channel_mutex);
+
+	/*
+	 * We can't assume that the relevant interrupts will be sent before
+	 * the cpu is offlined on older versions of hyperv.
+	 */
+	if (vmbus_proto_version < VERSION_WIN10_V5_3)
+		return -EBUSY;
+
+	start = get_random_u32_below(nr_cpu_ids);
+
+	for_each_cpu_wrap(cpu, cpu_online_mask, start) {
+		if (channel->target_cpu == cpu ||
+		    channel->target_cpu == VMBUS_CONNECT_CPU)
+			continue;
+
+		ret = vmbus_channel_set_cpu(channel, cpu);
+		if (!ret)
+			break;
+	}
+
+	if (ret)
+		ret = vmbus_channel_set_cpu(channel, VMBUS_CONNECT_CPU);
+
+	return ret;
+}
+
 /*
  * hv_synic_cleanup - Cleanup routine for hv_synic_init().
  */
 int hv_synic_cleanup(unsigned int cpu)
 {
 	struct vmbus_channel *channel, *sc;
-	bool channel_found = false;
+	int ret = 0;
 
 	if (vmbus_connection.conn_state != CONNECTED)
 		goto always_cleanup;
@@ -456,38 +480,34 @@ int hv_synic_cleanup(unsigned int cpu)
 
 	/*
 	 * 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
-	 * fail; this will effectively prevent CPU offlining.
-	 *
-	 * TODO: Re-bind the channels to different CPUs.
+	 * cleanup.
 	 */
 	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;
+			ret = hv_pick_new_cpu(channel);
+			if (ret) {
+				mutex_unlock(&vmbus_connection.channel_mutex);
+				return ret;
+			}
 		}
 		list_for_each_entry(sc, &channel->sc_list, sc_list) {
 			if (sc->target_cpu == cpu) {
-				channel_found = true;
-				break;
+				ret = hv_pick_new_cpu(sc);
+				if (ret) {
+					mutex_unlock(&vmbus_connection.channel_mutex);
+					return ret;
+				}
 			}
 		}
-		if (channel_found)
-			break;
 	}
 	mutex_unlock(&vmbus_connection.channel_mutex);
 
-	if (channel_found)
-		return -EBUSY;
-
 	/*
-	 * channel_found == false means that any channels that were previously
-	 * assigned to the CPU have been reassigned elsewhere with a call of
-	 * vmbus_send_modifychannel().  Scan the event flags page looking for
-	 * bits that are set and waiting with a timeout for vmbus_chan_sched()
-	 * to process such bits.  If bits are still set after this operation
-	 * and VMBus is connected, fail the CPU offlining operation.
+	 * Scan the event flags page looking for bits that are set and waiting
+	 * with a timeout for vmbus_chan_sched() to process such bits. If bits
+	 * are still set after this operation and VMBus is connected, fail the
+	 * CPU offlining operation.
 	 */
 	if (vmbus_proto_version >= VERSION_WIN10_V4_1 && hv_synic_event_pending())
 		return -EBUSY;
@@ -497,5 +517,5 @@ always_cleanup:
 
 	hv_synic_disable_regs(cpu);
 
-	return 0;
+	return ret;
 }
diff --git a/drivers/hv/hv_common.c b/drivers/hv/hv_common.c
index f2e6f55d6ca6..b3b11be11650 100644
--- a/drivers/hv/hv_common.c
+++ b/drivers/hv/hv_common.c
@@ -31,8 +31,14 @@
 #include <hyperv/hvhdk.h>
 #include <asm/mshyperv.h>
 
+u64 hv_current_partition_id = HV_PARTITION_ID_SELF;
+EXPORT_SYMBOL_GPL(hv_current_partition_id);
+
+enum hv_partition_type hv_curr_partition_type;
+EXPORT_SYMBOL_GPL(hv_curr_partition_type);
+
 /*
- * hv_root_partition, ms_hyperv and hv_nested are defined here with other
+ * ms_hyperv and hv_nested are defined here with other
  * Hyper-V specific globals so they are shared across all architectures and are
  * built only when CONFIG_HYPERV is defined.  But on x86,
  * ms_hyperv_init_platform() is built even when CONFIG_HYPERV is not
@@ -40,9 +46,6 @@
  * here, allowing for an overriding definition in the module containing
  * ms_hyperv_init_platform().
  */
-bool __weak hv_root_partition;
-EXPORT_SYMBOL_GPL(hv_root_partition);
-
 bool __weak hv_nested;
 EXPORT_SYMBOL_GPL(hv_nested);
 
@@ -66,6 +69,16 @@ static void hv_kmsg_dump_unregister(void);
 static struct ctl_table_header *hv_ctl_table_hdr;
 
 /*
+ * Per-cpu array holding the tail pointer for the SynIC event ring buffer
+ * for each SINT.
+ *
+ * We cannot maintain this in mshv driver because the tail pointer should
+ * persist even if the mshv driver is unloaded.
+ */
+u8 * __percpu *hv_synic_eventring_tail;
+EXPORT_SYMBOL_GPL(hv_synic_eventring_tail);
+
+/*
  * Hyper-V specific initialization and shutdown code that is
  * common across all architectures.  Called from architecture
  * specific initialization functions.
@@ -87,6 +100,9 @@ void __init hv_common_free(void)
 
 	free_percpu(hyperv_pcpu_input_arg);
 	hyperv_pcpu_input_arg = NULL;
+
+	free_percpu(hv_synic_eventring_tail);
+	hv_synic_eventring_tail = NULL;
 }
 
 /*
@@ -280,7 +296,26 @@ static void hv_kmsg_dump_register(void)
 
 static inline bool hv_output_page_exists(void)
 {
-	return hv_root_partition || IS_ENABLED(CONFIG_HYPERV_VTL_MODE);
+	return hv_root_partition() || IS_ENABLED(CONFIG_HYPERV_VTL_MODE);
+}
+
+void __init hv_get_partition_id(void)
+{
+	struct hv_output_get_partition_id *output;
+	unsigned long flags;
+	u64 status, pt_id;
+
+	local_irq_save(flags);
+	output = *this_cpu_ptr(hyperv_pcpu_input_arg);
+	status = hv_do_hypercall(HVCALL_GET_PARTITION_ID, NULL, &output);
+	pt_id = output->partition_id;
+	local_irq_restore(flags);
+
+	if (hv_result_success(status))
+		hv_current_partition_id = pt_id;
+	else
+		pr_err("Hyper-V: failed to get partition ID: %#x\n",
+		       hv_result(status));
 }
 
 int __init hv_common_init(void)
@@ -350,6 +385,11 @@ int __init hv_common_init(void)
 		BUG_ON(!hyperv_pcpu_output_arg);
 	}
 
+	if (hv_root_partition()) {
+		hv_synic_eventring_tail = alloc_percpu(u8 *);
+		BUG_ON(!hv_synic_eventring_tail);
+	}
+
 	hv_vp_index = kmalloc_array(nr_cpu_ids, sizeof(*hv_vp_index),
 				    GFP_KERNEL);
 	if (!hv_vp_index) {
@@ -438,11 +478,12 @@ error:
 int hv_common_cpu_init(unsigned int cpu)
 {
 	void **inputarg, **outputarg;
+	u8 **synic_eventring_tail;
 	u64 msr_vp_index;
 	gfp_t flags;
 	const int pgcount = hv_output_page_exists() ? 2 : 1;
 	void *mem;
-	int ret;
+	int ret = 0;
 
 	/* hv_cpu_init() can be called with IRQs disabled from hv_resume() */
 	flags = irqs_disabled() ? GFP_ATOMIC : GFP_KERNEL;
@@ -450,8 +491,8 @@ int hv_common_cpu_init(unsigned int cpu)
 	inputarg = (void **)this_cpu_ptr(hyperv_pcpu_input_arg);
 
 	/*
-	 * hyperv_pcpu_input_arg and hyperv_pcpu_output_arg memory is already
-	 * allocated if this CPU was previously online and then taken offline
+	 * The per-cpu memory is already allocated if this CPU was previously
+	 * online and then taken offline
 	 */
 	if (!*inputarg) {
 		mem = kmalloc(pgcount * HV_HYP_PAGE_SIZE, flags);
@@ -498,11 +539,21 @@ int hv_common_cpu_init(unsigned int cpu)
 	if (msr_vp_index > hv_max_vp_index)
 		hv_max_vp_index = msr_vp_index;
 
-	return 0;
+	if (hv_root_partition()) {
+		synic_eventring_tail = (u8 **)this_cpu_ptr(hv_synic_eventring_tail);
+		*synic_eventring_tail = kcalloc(HV_SYNIC_SINT_COUNT,
+						sizeof(u8), flags);
+		/* No need to unwind any of the above on failure here */
+		if (unlikely(!*synic_eventring_tail))
+			ret = -ENOMEM;
+	}
+
+	return ret;
 }
 
 int hv_common_cpu_die(unsigned int cpu)
 {
+	u8 **synic_eventring_tail;
 	/*
 	 * The hyperv_pcpu_input_arg and hyperv_pcpu_output_arg memory
 	 * is not freed when the CPU goes offline as the hyperv_pcpu_input_arg
@@ -515,6 +566,10 @@ int hv_common_cpu_die(unsigned int cpu)
 	 * originally allocated memory is reused in hv_common_cpu_init().
 	 */
 
+	synic_eventring_tail = this_cpu_ptr(hv_synic_eventring_tail);
+	kfree(*synic_eventring_tail);
+	*synic_eventring_tail = NULL;
+
 	return 0;
 }
 
@@ -572,7 +627,7 @@ EXPORT_SYMBOL_GPL(hv_setup_dma_ops);
 
 bool hv_is_hibernation_supported(void)
 {
-	return !hv_root_partition && acpi_sleep_state_supported(ACPI_STATE_S4);
+	return !hv_root_partition() && acpi_sleep_state_supported(ACPI_STATE_S4);
 }
 EXPORT_SYMBOL_GPL(hv_is_hibernation_supported);
 
@@ -625,6 +680,11 @@ void __weak hv_remove_vmbus_handler(void)
 }
 EXPORT_SYMBOL_GPL(hv_remove_vmbus_handler);
 
+void __weak hv_setup_mshv_handler(void (*handler)(void))
+{
+}
+EXPORT_SYMBOL_GPL(hv_setup_mshv_handler);
+
 void __weak hv_setup_kexec_handler(void (*handler)(void))
 {
 }
@@ -661,3 +721,121 @@ u64 __weak hv_tdx_hypercall(u64 control, u64 param1, u64 param2)
 	return HV_STATUS_INVALID_PARAMETER;
 }
 EXPORT_SYMBOL_GPL(hv_tdx_hypercall);
+
+void hv_identify_partition_type(void)
+{
+	/* Assume guest role */
+	hv_curr_partition_type = HV_PARTITION_TYPE_GUEST;
+	/*
+	 * Check partition creation and cpu management privileges
+	 *
+	 * Hyper-V should never specify running as root and as a Confidential
+	 * VM. But to protect against a compromised/malicious Hyper-V trying
+	 * to exploit root behavior to expose Confidential VM memory, ignore
+	 * the root partition setting if also a Confidential VM.
+	 */
+	if ((ms_hyperv.priv_high & HV_CREATE_PARTITIONS) &&
+	    (ms_hyperv.priv_high & HV_CPU_MANAGEMENT) &&
+	    !(ms_hyperv.priv_high & HV_ISOLATION)) {
+		pr_info("Hyper-V: running as root partition\n");
+		if (IS_ENABLED(CONFIG_MSHV_ROOT))
+			hv_curr_partition_type = HV_PARTITION_TYPE_ROOT;
+		else
+			pr_crit("Hyper-V: CONFIG_MSHV_ROOT not enabled!\n");
+	}
+}
+
+struct hv_status_info {
+	char *string;
+	int errno;
+	u16 code;
+};
+
+/*
+ * Note on the errno mappings:
+ * A failed hypercall is usually only recoverable (or loggable) near
+ * the call site where the HV_STATUS_* code is known. So the errno
+ * it gets converted to is not too useful further up the stack.
+ * Provide a few mappings that could be useful, and revert to -EIO
+ * as a fallback.
+ */
+static const struct hv_status_info hv_status_infos[] = {
+#define _STATUS_INFO(status, errno) { #status, (errno), (status) }
+	_STATUS_INFO(HV_STATUS_SUCCESS,				0),
+	_STATUS_INFO(HV_STATUS_INVALID_HYPERCALL_CODE,		-EINVAL),
+	_STATUS_INFO(HV_STATUS_INVALID_HYPERCALL_INPUT,		-EINVAL),
+	_STATUS_INFO(HV_STATUS_INVALID_ALIGNMENT,		-EIO),
+	_STATUS_INFO(HV_STATUS_INVALID_PARAMETER,		-EINVAL),
+	_STATUS_INFO(HV_STATUS_ACCESS_DENIED,			-EIO),
+	_STATUS_INFO(HV_STATUS_INVALID_PARTITION_STATE,		-EIO),
+	_STATUS_INFO(HV_STATUS_OPERATION_DENIED,		-EIO),
+	_STATUS_INFO(HV_STATUS_UNKNOWN_PROPERTY,		-EIO),
+	_STATUS_INFO(HV_STATUS_PROPERTY_VALUE_OUT_OF_RANGE,	-EIO),
+	_STATUS_INFO(HV_STATUS_INSUFFICIENT_MEMORY,		-ENOMEM),
+	_STATUS_INFO(HV_STATUS_INVALID_PARTITION_ID,		-EINVAL),
+	_STATUS_INFO(HV_STATUS_INVALID_VP_INDEX,		-EINVAL),
+	_STATUS_INFO(HV_STATUS_NOT_FOUND,			-EIO),
+	_STATUS_INFO(HV_STATUS_INVALID_PORT_ID,			-EINVAL),
+	_STATUS_INFO(HV_STATUS_INVALID_CONNECTION_ID,		-EINVAL),
+	_STATUS_INFO(HV_STATUS_INSUFFICIENT_BUFFERS,		-EIO),
+	_STATUS_INFO(HV_STATUS_NOT_ACKNOWLEDGED,		-EIO),
+	_STATUS_INFO(HV_STATUS_INVALID_VP_STATE,		-EIO),
+	_STATUS_INFO(HV_STATUS_NO_RESOURCES,			-EIO),
+	_STATUS_INFO(HV_STATUS_PROCESSOR_FEATURE_NOT_SUPPORTED,	-EIO),
+	_STATUS_INFO(HV_STATUS_INVALID_LP_INDEX,		-EINVAL),
+	_STATUS_INFO(HV_STATUS_INVALID_REGISTER_VALUE,		-EINVAL),
+	_STATUS_INFO(HV_STATUS_INVALID_LP_INDEX,		-EIO),
+	_STATUS_INFO(HV_STATUS_INVALID_REGISTER_VALUE,		-EIO),
+	_STATUS_INFO(HV_STATUS_OPERATION_FAILED,		-EIO),
+	_STATUS_INFO(HV_STATUS_TIME_OUT,			-EIO),
+	_STATUS_INFO(HV_STATUS_CALL_PENDING,			-EIO),
+	_STATUS_INFO(HV_STATUS_VTL_ALREADY_ENABLED,		-EIO),
+#undef _STATUS_INFO
+};
+
+static inline const struct hv_status_info *find_hv_status_info(u64 hv_status)
+{
+	int i;
+	u16 code = hv_result(hv_status);
+
+	for (i = 0; i < ARRAY_SIZE(hv_status_infos); ++i) {
+		const struct hv_status_info *info = &hv_status_infos[i];
+
+		if (info->code == code)
+			return info;
+	}
+
+	return NULL;
+}
+
+/* Convert a hypercall result into a linux-friendly error code. */
+int hv_result_to_errno(u64 status)
+{
+	const struct hv_status_info *info;
+
+	/* hv_do_hypercall() may return U64_MAX, hypercalls aren't possible */
+	if (unlikely(status == U64_MAX))
+		return -EOPNOTSUPP;
+
+	info = find_hv_status_info(status);
+	if (info)
+		return info->errno;
+
+	return -EIO;
+}
+EXPORT_SYMBOL_GPL(hv_result_to_errno);
+
+const char *hv_result_to_string(u64 status)
+{
+	const struct hv_status_info *info;
+
+	if (unlikely(status == U64_MAX))
+		return "Hypercall page missing!";
+
+	info = find_hv_status_info(status);
+	if (info)
+		return info->string;
+
+	return "Unknown";
+}
+EXPORT_SYMBOL_GPL(hv_result_to_string);
diff --git a/drivers/hv/hv_proc.c b/drivers/hv/hv_proc.c
new file mode 100644
index 000000000000..7d7ecb6f6137
--- /dev/null
+++ b/drivers/hv/hv_proc.c
@@ -0,0 +1,195 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/types.h>
+#include <linux/vmalloc.h>
+#include <linux/mm.h>
+#include <linux/clockchips.h>
+#include <linux/slab.h>
+#include <linux/cpuhotplug.h>
+#include <linux/minmax.h>
+#include <asm/mshyperv.h>
+
+/*
+ * See struct hv_deposit_memory. The first u64 is partition ID, the rest
+ * are GPAs.
+ */
+#define HV_DEPOSIT_MAX (HV_HYP_PAGE_SIZE / sizeof(u64) - 1)
+
+/* Deposits exact number of pages. Must be called with interrupts enabled.  */
+int hv_call_deposit_pages(int node, u64 partition_id, u32 num_pages)
+{
+	struct page **pages, *page;
+	int *counts;
+	int num_allocations;
+	int i, j, page_count;
+	int order;
+	u64 status;
+	int ret;
+	u64 base_pfn;
+	struct hv_deposit_memory *input_page;
+	unsigned long flags;
+
+	if (num_pages > HV_DEPOSIT_MAX)
+		return -E2BIG;
+	if (!num_pages)
+		return 0;
+
+	/* One buffer for page pointers and counts */
+	page = alloc_page(GFP_KERNEL);
+	if (!page)
+		return -ENOMEM;
+	pages = page_address(page);
+
+	counts = kcalloc(HV_DEPOSIT_MAX, sizeof(int), GFP_KERNEL);
+	if (!counts) {
+		free_page((unsigned long)pages);
+		return -ENOMEM;
+	}
+
+	/* Allocate all the pages before disabling interrupts */
+	i = 0;
+
+	while (num_pages) {
+		/* Find highest order we can actually allocate */
+		order = 31 - __builtin_clz(num_pages);
+
+		while (1) {
+			pages[i] = alloc_pages_node(node, GFP_KERNEL, order);
+			if (pages[i])
+				break;
+			if (!order) {
+				ret = -ENOMEM;
+				num_allocations = i;
+				goto err_free_allocations;
+			}
+			--order;
+		}
+
+		split_page(pages[i], order);
+		counts[i] = 1 << order;
+		num_pages -= counts[i];
+		i++;
+	}
+	num_allocations = i;
+
+	local_irq_save(flags);
+
+	input_page = *this_cpu_ptr(hyperv_pcpu_input_arg);
+
+	input_page->partition_id = partition_id;
+
+	/* Populate gpa_page_list - these will fit on the input page */
+	for (i = 0, page_count = 0; i < num_allocations; ++i) {
+		base_pfn = page_to_pfn(pages[i]);
+		for (j = 0; j < counts[i]; ++j, ++page_count)
+			input_page->gpa_page_list[page_count] = base_pfn + j;
+	}
+	status = hv_do_rep_hypercall(HVCALL_DEPOSIT_MEMORY,
+				     page_count, 0, input_page, NULL);
+	local_irq_restore(flags);
+	if (!hv_result_success(status)) {
+		hv_status_err(status, "\n");
+		ret = hv_result_to_errno(status);
+		goto err_free_allocations;
+	}
+
+	ret = 0;
+	goto free_buf;
+
+err_free_allocations:
+	for (i = 0; i < num_allocations; ++i) {
+		base_pfn = page_to_pfn(pages[i]);
+		for (j = 0; j < counts[i]; ++j)
+			__free_page(pfn_to_page(base_pfn + j));
+	}
+
+free_buf:
+	free_page((unsigned long)pages);
+	kfree(counts);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(hv_call_deposit_pages);
+
+int hv_call_add_logical_proc(int node, u32 lp_index, u32 apic_id)
+{
+	struct hv_input_add_logical_processor *input;
+	struct hv_output_add_logical_processor *output;
+	u64 status;
+	unsigned long flags;
+	int ret = 0;
+
+	/*
+	 * When adding a logical processor, the hypervisor may return
+	 * HV_STATUS_INSUFFICIENT_MEMORY. When that happens, we deposit more
+	 * pages and retry.
+	 */
+	do {
+		local_irq_save(flags);
+
+		input = *this_cpu_ptr(hyperv_pcpu_input_arg);
+		/* We don't do anything with the output right now */
+		output = *this_cpu_ptr(hyperv_pcpu_output_arg);
+
+		input->lp_index = lp_index;
+		input->apic_id = apic_id;
+		input->proximity_domain_info = hv_numa_node_to_pxm_info(node);
+		status = hv_do_hypercall(HVCALL_ADD_LOGICAL_PROCESSOR,
+					 input, output);
+		local_irq_restore(flags);
+
+		if (hv_result(status) != HV_STATUS_INSUFFICIENT_MEMORY) {
+			if (!hv_result_success(status)) {
+				hv_status_err(status, "cpu %u apic ID: %u\n",
+					      lp_index, apic_id);
+				ret = hv_result_to_errno(status);
+			}
+			break;
+		}
+		ret = hv_call_deposit_pages(node, hv_current_partition_id, 1);
+	} while (!ret);
+
+	return ret;
+}
+
+int hv_call_create_vp(int node, u64 partition_id, u32 vp_index, u32 flags)
+{
+	struct hv_create_vp *input;
+	u64 status;
+	unsigned long irq_flags;
+	int ret = 0;
+
+	/* Root VPs don't seem to need pages deposited */
+	if (partition_id != hv_current_partition_id) {
+		/* The value 90 is empirically determined. It may change. */
+		ret = hv_call_deposit_pages(node, partition_id, 90);
+		if (ret)
+			return ret;
+	}
+
+	do {
+		local_irq_save(irq_flags);
+
+		input = *this_cpu_ptr(hyperv_pcpu_input_arg);
+
+		input->partition_id = partition_id;
+		input->vp_index = vp_index;
+		input->flags = flags;
+		input->subnode_type = HV_SUBNODE_ANY;
+		input->proximity_domain_info = hv_numa_node_to_pxm_info(node);
+		status = hv_do_hypercall(HVCALL_CREATE_VP, input, NULL);
+		local_irq_restore(irq_flags);
+
+		if (hv_result(status) != HV_STATUS_INSUFFICIENT_MEMORY) {
+			if (!hv_result_success(status)) {
+				hv_status_err(status, "vcpu: %u, lp: %u\n",
+					      vp_index, flags);
+				ret = hv_result_to_errno(status);
+			}
+			break;
+		}
+		ret = hv_call_deposit_pages(node, partition_id, 1);
+
+	} while (!ret);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(hv_call_create_vp);
diff --git a/drivers/hv/mshv.h b/drivers/hv/mshv.h
new file mode 100644
index 000000000000..0340a67acd0a
--- /dev/null
+++ b/drivers/hv/mshv.h
@@ -0,0 +1,30 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (c) 2023, Microsoft Corporation.
+ */
+
+#ifndef _MSHV_H_
+#define _MSHV_H_
+
+#include <linux/stddef.h>
+#include <linux/string.h>
+#include <hyperv/hvhdk.h>
+
+#define mshv_field_nonzero(STRUCT, MEMBER) \
+	memchr_inv(&((STRUCT).MEMBER), \
+		   0, sizeof_field(typeof(STRUCT), MEMBER))
+
+int hv_call_get_vp_registers(u32 vp_index, u64 partition_id, u16 count,
+			     union hv_input_vtl input_vtl,
+			     struct hv_register_assoc *registers);
+
+int hv_call_set_vp_registers(u32 vp_index, u64 partition_id, u16 count,
+			     union hv_input_vtl input_vtl,
+			     struct hv_register_assoc *registers);
+
+int hv_call_get_partition_property(u64 partition_id, u64 property_code,
+				   u64 *property_value);
+
+int mshv_do_pre_guest_mode_work(ulong th_flags);
+
+#endif /* _MSHV_H */
diff --git a/drivers/hv/mshv_common.c b/drivers/hv/mshv_common.c
new file mode 100644
index 000000000000..2575e6d7a71f
--- /dev/null
+++ b/drivers/hv/mshv_common.c
@@ -0,0 +1,161 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (c) 2024, Microsoft Corporation.
+ *
+ * This file contains functions that will be called from one or more modules.
+ * If any of these modules are configured to build, this file is built and just
+ * statically linked in.
+ *
+ * Authors: Microsoft Linux virtualization team
+ */
+
+#include <linux/kernel.h>
+#include <linux/mm.h>
+#include <asm/mshyperv.h>
+#include <linux/resume_user_mode.h>
+
+#include "mshv.h"
+
+#define HV_GET_REGISTER_BATCH_SIZE	\
+	(HV_HYP_PAGE_SIZE / sizeof(union hv_register_value))
+#define HV_SET_REGISTER_BATCH_SIZE	\
+	((HV_HYP_PAGE_SIZE - sizeof(struct hv_input_set_vp_registers)) \
+		/ sizeof(struct hv_register_assoc))
+
+int hv_call_get_vp_registers(u32 vp_index, u64 partition_id, u16 count,
+			     union hv_input_vtl input_vtl,
+			     struct hv_register_assoc *registers)
+{
+	struct hv_input_get_vp_registers *input_page;
+	union hv_register_value *output_page;
+	u16 completed = 0;
+	unsigned long remaining = count;
+	int rep_count, i;
+	u64 status = HV_STATUS_SUCCESS;
+	unsigned long flags;
+
+	local_irq_save(flags);
+
+	input_page = *this_cpu_ptr(hyperv_pcpu_input_arg);
+	output_page = *this_cpu_ptr(hyperv_pcpu_output_arg);
+
+	input_page->partition_id = partition_id;
+	input_page->vp_index = vp_index;
+	input_page->input_vtl.as_uint8 = input_vtl.as_uint8;
+	input_page->rsvd_z8 = 0;
+	input_page->rsvd_z16 = 0;
+
+	while (remaining) {
+		rep_count = min(remaining, HV_GET_REGISTER_BATCH_SIZE);
+		for (i = 0; i < rep_count; ++i)
+			input_page->names[i] = registers[i].name;
+
+		status = hv_do_rep_hypercall(HVCALL_GET_VP_REGISTERS, rep_count,
+					     0, input_page, output_page);
+		if (!hv_result_success(status))
+			break;
+
+		completed = hv_repcomp(status);
+		for (i = 0; i < completed; ++i)
+			registers[i].value = output_page[i];
+
+		registers += completed;
+		remaining -= completed;
+	}
+	local_irq_restore(flags);
+
+	return hv_result_to_errno(status);
+}
+EXPORT_SYMBOL_GPL(hv_call_get_vp_registers);
+
+int hv_call_set_vp_registers(u32 vp_index, u64 partition_id, u16 count,
+			     union hv_input_vtl input_vtl,
+			     struct hv_register_assoc *registers)
+{
+	struct hv_input_set_vp_registers *input_page;
+	u16 completed = 0;
+	unsigned long remaining = count;
+	int rep_count;
+	u64 status = HV_STATUS_SUCCESS;
+	unsigned long flags;
+
+	local_irq_save(flags);
+	input_page = *this_cpu_ptr(hyperv_pcpu_input_arg);
+
+	input_page->partition_id = partition_id;
+	input_page->vp_index = vp_index;
+	input_page->input_vtl.as_uint8 = input_vtl.as_uint8;
+	input_page->rsvd_z8 = 0;
+	input_page->rsvd_z16 = 0;
+
+	while (remaining) {
+		rep_count = min(remaining, HV_SET_REGISTER_BATCH_SIZE);
+		memcpy(input_page->elements, registers,
+		       sizeof(struct hv_register_assoc) * rep_count);
+
+		status = hv_do_rep_hypercall(HVCALL_SET_VP_REGISTERS, rep_count,
+					     0, input_page, NULL);
+		if (!hv_result_success(status))
+			break;
+
+		completed = hv_repcomp(status);
+		registers += completed;
+		remaining -= completed;
+	}
+
+	local_irq_restore(flags);
+
+	return hv_result_to_errno(status);
+}
+EXPORT_SYMBOL_GPL(hv_call_set_vp_registers);
+
+int hv_call_get_partition_property(u64 partition_id,
+				   u64 property_code,
+				   u64 *property_value)
+{
+	u64 status;
+	unsigned long flags;
+	struct hv_input_get_partition_property *input;
+	struct hv_output_get_partition_property *output;
+
+	local_irq_save(flags);
+	input = *this_cpu_ptr(hyperv_pcpu_input_arg);
+	output = *this_cpu_ptr(hyperv_pcpu_output_arg);
+	memset(input, 0, sizeof(*input));
+	input->partition_id = partition_id;
+	input->property_code = property_code;
+	status = hv_do_hypercall(HVCALL_GET_PARTITION_PROPERTY, input, output);
+
+	if (!hv_result_success(status)) {
+		local_irq_restore(flags);
+		return hv_result_to_errno(status);
+	}
+	*property_value = output->property_value;
+
+	local_irq_restore(flags);
+
+	return 0;