[PATCH v2 00/19] Microsoft Hypervisor root partition ioctl interface

@@ -14,6 +14,30 @@
 
 #include <asm/trace/hyperv.h>
 
+int hv_status_to_errno(u64 hv_status)
+{
+	switch (hv_result(hv_status)) {
+	case HV_STATUS_SUCCESS:
+		return 0;
+	case HV_STATUS_INVALID_PARAMETER:
+	case HV_STATUS_UNKNOWN_PROPERTY:
+	case HV_STATUS_PROPERTY_VALUE_OUT_OF_RANGE:
+	case HV_STATUS_INVALID_VP_INDEX:
+	case HV_STATUS_INVALID_REGISTER_VALUE:
+	case HV_STATUS_INVALID_LP_INDEX:
+		return -EINVAL;
+	case HV_STATUS_ACCESS_DENIED:
+	case HV_STATUS_OPERATION_DENIED:
+		return -EACCES;
+	case HV_STATUS_NOT_ACKNOWLEDGED:
+	case HV_STATUS_INVALID_VP_STATE:
+	case HV_STATUS_INVALID_PARTITION_STATE:
+		return -EBADFD;
+	}
+	return -ENOTRECOVERABLE;
+}
+EXPORT_SYMBOL_GPL(hv_status_to_errno);
+
 /*
  * See struct hv_deposit_memory. The first u64 is partition ID, the rest
  * are GPAs.

@@ -94,7 +118,7 @@ int hv_call_deposit_pages(int node, u64 partition_id, u32 num_pages)
 	local_irq_restore(flags);
 	if (!hv_result_success(status)) {
 		pr_err("Failed to deposit pages: %lld\n", status);
-		ret = hv_result(status);
+		ret = hv_status_to_errno(status);
 		goto err_free_allocations;
 	}
 

@@ -150,7 +174,7 @@ int hv_call_add_logical_proc(int node, u32 lp_index, u32 apic_id)
 			if (!hv_result_success(status)) {
 				pr_err("%s: cpu %u apic ID %u, %lld\n", __func__,
 				       lp_index, apic_id, status);
-				ret = hv_result(status);
+				ret = hv_status_to_errno(status);
 			}
 			break;
 		}

@@ -200,7 +224,7 @@ int hv_call_create_vp(int node, u64 partition_id, u32 vp_index, u32 flags)
 			if (!hv_result_success(status)) {
 				pr_err("%s: vcpu %u, lp %u, %lld\n", __func__,
 				       vp_index, flags, status);
-				ret = hv_result(status);
+				ret = hv_status_to_errno(status);
 			}
 			break;
 		}

@@ -169,6 +169,7 @@ int hyperv_flush_guest_mapping_range(u64 as,
 int hyperv_fill_flush_guest_mapping_list(
 		struct hv_guest_mapping_flush_list *flush,
 		u64 start_gfn, u64 end_gfn);
+int hv_status_to_errno(u64 hv_status);
 
 extern bool hv_root_partition;
 

@@ -189,16 +189,28 @@ enum HV_GENERIC_SET_FORMAT {
 #define HV_HYPERCALL_REP_START_MASK	GENMASK_ULL(59, 48)
 
 /* hypercall status code */
-#define HV_STATUS_SUCCESS			0
-#define HV_STATUS_INVALID_HYPERCALL_CODE	2
-#define HV_STATUS_INVALID_HYPERCALL_INPUT	3
-#define HV_STATUS_INVALID_ALIGNMENT		4
-#define HV_STATUS_INVALID_PARAMETER		5
-#define HV_STATUS_OPERATION_DENIED		8
-#define HV_STATUS_INSUFFICIENT_MEMORY		11
-#define HV_STATUS_INVALID_PORT_ID		17
-#define HV_STATUS_INVALID_CONNECTION_ID		18
-#define HV_STATUS_INSUFFICIENT_BUFFERS		19
+#define HV_STATUS_SUCCESS			0x0
+#define HV_STATUS_INVALID_HYPERCALL_CODE	0x2
+#define HV_STATUS_INVALID_HYPERCALL_INPUT	0x3
+#define HV_STATUS_INVALID_ALIGNMENT		0x4
+#define HV_STATUS_INVALID_PARAMETER		0x5
+#define HV_STATUS_ACCESS_DENIED			0x6
+#define HV_STATUS_INVALID_PARTITION_STATE	0x7
+#define HV_STATUS_OPERATION_DENIED		0x8
+#define HV_STATUS_UNKNOWN_PROPERTY		0x9
+#define HV_STATUS_PROPERTY_VALUE_OUT_OF_RANGE	0xA
+#define HV_STATUS_INSUFFICIENT_MEMORY		0xB
+#define HV_STATUS_INVALID_PARTITION_ID		0xD
+#define HV_STATUS_INVALID_VP_INDEX		0xE
+#define HV_STATUS_NOT_FOUND			0x10
+#define HV_STATUS_INVALID_PORT_ID		0x11
+#define HV_STATUS_INVALID_CONNECTION_ID		0x12
+#define HV_STATUS_INSUFFICIENT_BUFFERS		0x13
+#define HV_STATUS_NOT_ACKNOWLEDGED		0x14
+#define HV_STATUS_INVALID_VP_STATE		0x15
+#define HV_STATUS_NO_RESOURCES			0x1D
+#define HV_STATUS_INVALID_LP_INDEX		0x41
+#define HV_STATUS_INVALID_REGISTER_VALUE	0x50
 
 /*
  * The Hyper-V TimeRefCount register and the TSC

@@ -349,7 +349,7 @@ static void __init hv_get_partition_id(void)
 	status = hv_do_hypercall(HVCALL_GET_PARTITION_ID, NULL, output_page);
 	if (!hv_result_success(status)) {
 		/* No point in proceeding if this failed */
-		pr_err("Failed to get partition ID: %lld\n", status);
+		pr_err("Failed to get partition ID: %s\n", hv_status_to_string(status));
 		BUG();
 	}
 	hv_current_partition_id = output_page->partition_id;

@@ -38,6 +38,15 @@ int hv_status_to_errno(u64 hv_status)
 }
 EXPORT_SYMBOL_GPL(hv_status_to_errno);
 
+const char *hv_status_to_string(u64 hv_status)
+{
+	switch (hv_result(hv_status)) {
+	__HV_STATUS_DEF(__HV_MAKE_HV_STATUS_CASE)
+	default : return "Unknown";
+	}
+}
+EXPORT_SYMBOL_GPL(hv_status_to_string);
+
 /*
  * See struct hv_deposit_memory. The first u64 is partition ID, the rest
  * are GPAs.

@@ -117,7 +126,7 @@ int hv_call_deposit_pages(int node, u64 partition_id, u32 num_pages)
 				     page_count, 0, input_page, NULL);
 	local_irq_restore(flags);
 	if (!hv_result_success(status)) {
-		pr_err("Failed to deposit pages: %lld\n", status);
+		pr_err("Failed to deposit pages: %s\n", hv_status_to_string(status));
 		ret = hv_status_to_errno(status);
 		goto err_free_allocations;
 	}

@@ -172,8 +181,8 @@ int hv_call_add_logical_proc(int node, u32 lp_index, u32 apic_id)
 
 		if (hv_result(status) != HV_STATUS_INSUFFICIENT_MEMORY) {
 			if (!hv_result_success(status)) {
-				pr_err("%s: cpu %u apic ID %u, %lld\n", __func__,
-				       lp_index, apic_id, status);
+				pr_err("%s: cpu %u apic ID %u, %s\n", __func__,
+				       lp_index, apic_id, hv_status_to_string(status));
 				ret = hv_status_to_errno(status);
 			}
 			break;

@@ -222,8 +231,8 @@ int hv_call_create_vp(int node, u64 partition_id, u32 vp_index, u32 flags)
 
 		if (hv_result(status) != HV_STATUS_INSUFFICIENT_MEMORY) {
 			if (!hv_result_success(status)) {
-				pr_err("%s: vcpu %u, lp %u, %lld\n", __func__,
-				       vp_index, flags, status);
+				pr_err("%s: vcpu %u, lp %u, %s\n", __func__,
+				       vp_index, flags, hv_status_to_string(status));
 				ret = hv_status_to_errno(status);
 			}
 			break;

@@ -189,28 +189,36 @@ enum HV_GENERIC_SET_FORMAT {
 #define HV_HYPERCALL_REP_START_MASK	GENMASK_ULL(59, 48)
 
 /* hypercall status code */
-#define HV_STATUS_SUCCESS			0x0
-#define HV_STATUS_INVALID_HYPERCALL_CODE	0x2
-#define HV_STATUS_INVALID_HYPERCALL_INPUT	0x3
-#define HV_STATUS_INVALID_ALIGNMENT		0x4
-#define HV_STATUS_INVALID_PARAMETER		0x5
-#define HV_STATUS_ACCESS_DENIED			0x6
-#define HV_STATUS_INVALID_PARTITION_STATE	0x7
-#define HV_STATUS_OPERATION_DENIED		0x8
-#define HV_STATUS_UNKNOWN_PROPERTY		0x9
-#define HV_STATUS_PROPERTY_VALUE_OUT_OF_RANGE	0xA
-#define HV_STATUS_INSUFFICIENT_MEMORY		0xB
-#define HV_STATUS_INVALID_PARTITION_ID		0xD
-#define HV_STATUS_INVALID_VP_INDEX		0xE
-#define HV_STATUS_NOT_FOUND			0x10
-#define HV_STATUS_INVALID_PORT_ID		0x11
-#define HV_STATUS_INVALID_CONNECTION_ID		0x12
-#define HV_STATUS_INSUFFICIENT_BUFFERS		0x13
-#define HV_STATUS_NOT_ACKNOWLEDGED		0x14
-#define HV_STATUS_INVALID_VP_STATE		0x15
-#define HV_STATUS_NO_RESOURCES			0x1D
-#define HV_STATUS_INVALID_LP_INDEX		0x41
-#define HV_STATUS_INVALID_REGISTER_VALUE	0x50
+#define __HV_STATUS_DEF(OP) \
+	OP(HV_STATUS_SUCCESS,				0x0) \
+	OP(HV_STATUS_INVALID_HYPERCALL_CODE,		0x2) \
+	OP(HV_STATUS_INVALID_HYPERCALL_INPUT,		0x3) \
+	OP(HV_STATUS_INVALID_ALIGNMENT,			0x4) \
+	OP(HV_STATUS_INVALID_PARAMETER,			0x5) \
+	OP(HV_STATUS_ACCESS_DENIED,			0x6) \
+	OP(HV_STATUS_INVALID_PARTITION_STATE,		0x7) \
+	OP(HV_STATUS_OPERATION_DENIED,			0x8) \
+	OP(HV_STATUS_UNKNOWN_PROPERTY,			0x9) \
+	OP(HV_STATUS_PROPERTY_VALUE_OUT_OF_RANGE,	0xA) \
+	OP(HV_STATUS_INSUFFICIENT_MEMORY,		0xB) \
+	OP(HV_STATUS_INVALID_PARTITION_ID,		0xD) \
+	OP(HV_STATUS_INVALID_VP_INDEX,			0xE) \
+	OP(HV_STATUS_NOT_FOUND,				0x10) \
+	OP(HV_STATUS_INVALID_PORT_ID,			0x11) \
+	OP(HV_STATUS_INVALID_CONNECTION_ID,		0x12) \
+	OP(HV_STATUS_INSUFFICIENT_BUFFERS,		0x13) \
+	OP(HV_STATUS_NOT_ACKNOWLEDGED,			0x14) \
+	OP(HV_STATUS_INVALID_VP_STATE,			0x15) \
+	OP(HV_STATUS_NO_RESOURCES,			0x1D) \
+	OP(HV_STATUS_INVALID_LP_INDEX,			0x41) \
+	OP(HV_STATUS_INVALID_REGISTER_VALUE,		0x50)
+
+#define __HV_MAKE_HV_STATUS_ENUM(NAME, VAL) NAME = (VAL),
+#define __HV_MAKE_HV_STATUS_CASE(NAME, VAL) case (NAME): return (#NAME);
+
+enum hv_status {
+	__HV_STATUS_DEF(__HV_MAKE_HV_STATUS_ENUM)
+};
 
 /*
  * The Hyper-V TimeRefCount register and the TSC

@@ -219,6 +219,7 @@ static inline int cpumask_to_vpset(struct hv_vpset *vpset,
 	return nr_bank;
 }
 
+const char *hv_status_to_string(u64 hv_status);
 void hyperv_report_panic(struct pt_regs *regs, long err, bool in_die);
 bool hv_is_hyperv_initialized(void);
 bool hv_is_hibernation_supported(void);

@@ -5,3 +5,4 @@ obj-$(CONFIG_X86_64)	+= hv_apic.o hv_proc.o
 ifdef CONFIG_X86_64
 obj-$(CONFIG_PARAVIRT_SPINLOCKS)	+= hv_spinlock.o
 endif
+

@@ -27,4 +27,22 @@ config HYPERV_BALLOON
 	help
 	  Select this option to enable Hyper-V Balloon driver.
 
+config HYPERV_VMM_API
+	tristate "Microsoft Hypervisor root partition interfaces: /dev/mshv"
+	depends on HYPERV
+	help
+	  Provides access to interfaces for managing guest virtual machines
+	  running under the Microsoft Hypervisor.
+
+	  These interfaces will only work when Linux is running as root
+	  partition on the Microsoft Hypervisor.
+
+	  The interfaces are provided via a device named /dev/mshv.
+
+	  To compile this as a module, choose M here.
+	  The module is named mshv.
+
+	  If unsure, say N.
+
+
 endmenu

@@ -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_HYPERV_ROOT_API)   += mshv.o
 
 CFLAGS_hv_trace.o = -I$(src)
 CFLAGS_hv_balloon.o = -I$(src)

@@ -11,3 +12,5 @@ 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_fcopy.o hv_utils_transport.o
+
+mshv-y                          += mshv_main.o

@@ -0,0 +1,77 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (c) 2020, Microsoft Corporation.
+ *
+ * Authors:
+ *   Nuno Das Neves <nudasnev@microsoft.com>
+ *   Lillian Grassin-Drake <ligrassi@microsoft.com>
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/fs.h>
+#include <linux/miscdevice.h>
+
+MODULE_AUTHOR("Microsoft");
+MODULE_LICENSE("GPL");
+
+static int mshv_dev_open(struct inode *inode, struct file *filp);
+static int mshv_dev_release(struct inode *inode, struct file *filp);
+static long mshv_dev_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg);
+
+static const struct file_operations mshv_dev_fops = {
+	.owner = THIS_MODULE,
+	.open = mshv_dev_open,
+	.release = mshv_dev_release,
+	.unlocked_ioctl = mshv_dev_ioctl,
+	.llseek = noop_llseek,
+};
+
+static struct miscdevice mshv_dev = {
+	.minor = MISC_DYNAMIC_MINOR,
+	.name = "mshv",
+	.fops = &mshv_dev_fops,
+	.mode = 0600,
+};
+
+static long
+mshv_dev_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg)
+{
+	return -ENOTTY;
+}
+
+static int
+mshv_dev_open(struct inode *inode, struct file *filp)
+{
+	return 0;
+}
+
+static int
+mshv_dev_release(struct inode *inode, struct file *filp)
+{
+	return 0;
+}
+
+static int
+__init mshv_init(void)
+{
+	int ret;
+
+	if (!hv_is_hyperv_initialized())
+		return -ENODEV;
+
+	ret = misc_register(&mshv_dev);
+	if (ret)
+		pr_err("%s: misc device register failed\n", __func__);
+
+	return ret;
+}
+
+static void
+__exit mshv_exit(void)
+{
+	misc_deregister(&mshv_dev);
+}
+
+module_init(mshv_init);
+module_exit(mshv_exit);

@@ -350,6 +350,8 @@ Code  Seq#    Include File                                           Comments
 0xB6  all    linux/fpga-dfl.h
 0xB7  all    uapi/linux/remoteproc_cdev.h                            <mailto:linux-remoteproc@vger.kernel.org>
 0xB7  all    uapi/linux/nsfs.h                                       <mailto:Andrei Vagin <avagin@openvz.org>>
+0xB8  all    uapi/linux/mshv.h                                       Microsoft Hypervisor root partition APIs
+                                                                     <mailto:linux-hyperv@vger.kernel.org>
 0xC0  00-0F  linux/usb/iowarrior.h
 0xCA  00-0F  uapi/misc/cxl.h
 0xCA  10-2F  uapi/misc/ocxl.h

@@ -0,0 +1,60 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+=====================================================
+Microsoft Hypervisor Root Partition API Documentation
+=====================================================
+
+1. Overview
+===========
+
+This document describes APIs for creating and managing guest virtual machines
+when running Linux as the root partition on the Microsoft Hypervisor.
+
+Note that this API is not yet stable!
+
+2. Glossary/Terms
+=================
+
+hv
+--
+Short for Hyper-V. This name is used in the kernel to describe interfaces to
+the Microsoft Hypervisor.
+
+mshv
+----
+Short for Microsoft Hypervisor. This is the name of the userland API module
+described in this document.
+
+Partition
+---------
+A virtual machine running on the Microsoft Hypervisor.
+
+Root Partition
+--------------
+The partition that is created and assumes control when the machine boots. The
+root partition can use mshv APIs to create guest partitions.
+
+3. API description
+==================
+
+The module is named mshv and can be configured with CONFIG_HYPERV_ROOT_API.
+
+Mshv is file descriptor-based, following a similar pattern to KVM.
+
+To get a handle to the mshv driver, use open("/dev/mshv").
+
+3.1 MSHV_CHECK_EXTENSION
+------------------------
+:Type: /dev/mshv ioctl
+:Parameters: pointer to a u32
+:Returns: 0 if extension unsupported, positive number if supported
+
+This ioctl takes a single argument corresponding to an API extension to check
+support for.
+
+If the extension is supported, MSHV_CHECK_EXTENSION will return a positive
+number. If not, it will return 0.
+
+The first extension that can be checked is MSHV_CAP_CORE_API_STABLE. This
+will be supported when the core API is stable.
+

@@ -11,6 +11,8 @@
 #include <linux/module.h>
 #include <linux/fs.h>
 #include <linux/miscdevice.h>
+#include <linux/slab.h>
+#include <linux/mshv.h>
 
 MODULE_AUTHOR("Microsoft");
 MODULE_LICENSE("GPL");

@@ -34,9 +36,30 @@ static struct miscdevice mshv_dev = {
 	.mode = 0600,
 };
 
+static long
+mshv_ioctl_check_extension(void __user *user_arg)
+{
+	u32 arg;
+
+	if (copy_from_user(&arg, user_arg, sizeof(arg)))
+		return -EFAULT;
+
+	switch (arg) {
+	case MSHV_CAP_CORE_API_STABLE:
+		return 0;
+	}
+
+	return -ENOTSUP;
+}
+
 static long
 mshv_dev_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg)
 {
+	switch (ioctl) {
+	case MSHV_CHECK_EXTENSION:
+		return mshv_ioctl_check_extension((void __user *)arg);
+	}
+
 	return -ENOTTY;
 }
 

@@ -0,0 +1,11 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+#ifndef _LINUX_MSHV_H
+#define _LINUX_MSHV_H
+
+/*
+ * Microsoft Hypervisor root partition driver for /dev/mshv
+ */
+
+#include <uapi/linux/mshv.h>
+
+#endif

@@ -0,0 +1,20 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef _UAPI_LINUX_MSHV_H
+#define _UAPI_LINUX_MSHV_H
+
+/*
+ * Userspace interface for /dev/mshv
+ * Microsoft Hypervisor root partition APIs
+ * NOTE: This API is not yet stable!
+ */
+
+#include <linux/types.h>
+
+#define MSHV_CAP_CORE_API_STABLE    0x0
+
+#define MSHV_IOCTL 0xB8
+
+/* mshv device */
+#define MSHV_CHECK_EXTENSION    _IOW(MSHV_IOCTL, 0x00, __u32)
+
+#endif

@@ -70,3 +70,20 @@ will be supported when the core API is stable.
 This ioctl creates a guest partition, returning a file descriptor to use as a
 handle for partition ioctls.
 
+3.3 MSHV_MAP_GUEST_MEMORY and MSHV_UNMAP_GUEST_MEMORY
+-----------------------------------------------------
+:Type: partition ioctl
+:Parameters: struct mshv_user_mem_region
+:Returns: 0 on success
+
+Create a mapping from memory in the user space of the calling process (running
+in the root partition) to a region of guest physical memory in a guest partition.
+
+Mappings must be disjoint from each other in both userspace and guest physical
+address space.
+
+Note: In the current implementation, this memory is pinned to real physical
+memory to stop the pages being moved by Linux in the root partition,
+and subsequently being clobbered by the hypervisor. So the region is backed
+by real physical memory.
+

@@ -180,3 +180,117 @@ int hv_call_delete_partition(u64 partition_id)
 	return hv_status_to_errno(status);
 }
 
+int hv_call_map_gpa_pages(
+		u64 partition_id,
+		u64 gpa_target,
+		u64 page_count, u32 flags,
+		struct page **pages)
+{
+	struct hv_map_gpa_pages *input_page;
+	u64 status;
+	int i;
+	struct page **p;
+	u32 completed = 0;
+	unsigned long remaining = page_count;
+	int rep_count;
+	unsigned long irq_flags;
+	int ret = 0;
+
+	while (remaining) {
+
+		rep_count = min(remaining, HV_MAP_GPA_BATCH_SIZE);
+
+		local_irq_save(irq_flags);
+		input_page = (struct hv_map_gpa_pages *)(*this_cpu_ptr(
+			hyperv_pcpu_input_arg));
+
+		input_page->target_partition_id = partition_id;
+		input_page->target_gpa_base = gpa_target;
+		input_page->map_flags = flags;
+
+		for (i = 0, p = pages; i < rep_count; i++, p++)
+			input_page->source_gpa_page_list[i] = page_to_pfn(*p);
+		status = hv_do_rep_hypercall(
+			HVCALL_MAP_GPA_PAGES, rep_count, 0, input_page, NULL);
+		local_irq_restore(irq_flags);
+
+		completed = hv_repcomp(status);
+
+		if (hv_result(status) == HV_STATUS_INSUFFICIENT_MEMORY) {
+			ret = hv_call_deposit_pages(NUMA_NO_NODE,
+						    partition_id,
+						    HV_MAP_GPA_DEPOSIT_PAGES);
+			if (ret)
+				break;
+		} else if (!hv_result_success(status)) {
+			pr_err("%s: completed %llu out of %llu, %s\n",
+			       __func__,
+			       page_count - remaining, page_count,
+			       hv_status_to_string(status));
+			ret = hv_status_to_errno(status);
+			break;
+		}
+
+		pages += completed;
+		remaining -= completed;
+		gpa_target += completed;
+	}
+
+	if (ret && remaining < page_count) {
+		pr_err("%s: Partially succeeded; mapped regions may be in invalid state",
+		       __func__);
+		ret = -EBADFD;
+	}
+
+	return ret;
+}
+
+int hv_call_unmap_gpa_pages(
+		u64 partition_id,
+		u64 gpa_target,
+		u64 page_count, u32 flags)
+{
+	struct hv_unmap_gpa_pages *input_page;
+	u64 status;
+	int ret = 0;
+	u32 completed = 0;
+	unsigned long remaining = page_count;
+	int rep_count;
+	unsigned long irq_flags;
+
+	while (remaining) {
+		local_irq_save(irq_flags);
+		input_page = (struct hv_unmap_gpa_pages *)(*this_cpu_ptr(
+			hyperv_pcpu_input_arg));
+
+		input_page->target_partition_id = partition_id;
+		input_page->target_gpa_base = gpa_target;
+		input_page->unmap_flags = flags;
+		rep_count = min(remaining, HV_MAP_GPA_BATCH_SIZE);
+		status = hv_do_rep_hypercall(
+			HVCALL_UNMAP_GPA_PAGES, rep_count, 0, input_page, NULL);
+		local_irq_restore(irq_flags);
+
+		completed = hv_repcomp(status);
+		if (!hv_result_success(status)) {
+			pr_err("%s: completed %llu out of %llu, %s\n",
+			       __func__,
+			       page_count - remaining, page_count,
+			       hv_status_to_string(status));
+			ret = hv_status_to_errno(status);
+			break;
+		}
+
+		remaining -= completed;
+		gpa_target += completed;
+	}
+
+	if (ret && remaining < page_count) {
+		pr_err("%s: Partially succeeded; mapped regions may be in invalid state",
+		       __func__);
+		ret = -EBADFD;
+	}
+
+	return ret;
+}
+

@@ -15,8 +15,12 @@
 
 /* Determined empirically */
 #define HV_INIT_PARTITION_DEPOSIT_PAGES 208
+#define HV_MAP_GPA_DEPOSIT_PAGES	256
 
 #define HV_WITHDRAW_BATCH_SIZE	(HV_HYP_PAGE_SIZE / sizeof(u64))
+#define HV_MAP_GPA_BATCH_SIZE	\
+		((HV_HYP_PAGE_SIZE - sizeof(struct hv_map_gpa_pages)) / sizeof(u64))
+#define PIN_PAGES_BATCH_SIZE	(0x10000000 / HV_HYP_PAGE_SIZE)
 
 /*
  * Hyper-V hypercalls

@@ -30,5 +34,14 @@ int hv_call_create_partition(
 int hv_call_initialize_partition(u64 partition_id);
 int hv_call_finalize_partition(u64 partition_id);
 int hv_call_delete_partition(u64 partition_id);
+int hv_call_map_gpa_pages(
+		u64 partition_id,
+		u64 gpa_target,
+		u64 page_count, u32 flags,
+		struct page **pages);
+int hv_call_unmap_gpa_pages(
+		u64 partition_id,
+		u64 gpa_target,
+		u64 page_count, u32 flags);
 
 #endif /* _MSHV_H */

@@ -53,16 +53,194 @@ static struct miscdevice mshv_dev = {
 	.mode = 0600,
 };
 
+static long
+mshv_partition_ioctl_map_memory(struct mshv_partition *partition,
+				struct mshv_user_mem_region __user *user_mem)
+{
+	struct mshv_user_mem_region mem;
+	struct mshv_mem_region *region;
+	int completed;
+	unsigned long remaining, batch_size;
+	int i;
+	struct page **pages;
+	u64 page_count, user_start, user_end, gpfn_start, gpfn_end;
+	u64 region_page_count, region_user_start, region_user_end;
+	u64 region_gpfn_start, region_gpfn_end;
+	long ret = 0;
+
+	/* Check we have enough slots*/
+	if (partition->regions.count == MSHV_MAX_MEM_REGIONS) {
+		pr_err("%s: not enough memory region slots\n", __func__);
+		return -ENOSPC;
+	}
+
+	if (copy_from_user(&mem, user_mem, sizeof(mem)))
+		return -EFAULT;
+
+	if (!mem.size ||
+	    !PAGE_ALIGNED(mem.size) ||
+	    !PAGE_ALIGNED(mem.userspace_addr) ||
+	    !access_ok(mem.userspace_addr, mem.size))
+		return -EINVAL;
+
+	/* Reject overlapping regions */
+	page_count = mem.size >> HV_HYP_PAGE_SHIFT;
+	user_start = mem.userspace_addr;
+	user_end = mem.userspace_addr + mem.size;
+	gpfn_start = mem.guest_pfn;
+	gpfn_end = mem.guest_pfn + page_count;
+	for (i = 0; i < MSHV_MAX_MEM_REGIONS; ++i) {
+		region = &partition->regions.slots[i];
+		if (!region->size)
+			continue;
+		region_page_count = region->size >> HV_HYP_PAGE_SHIFT;
+		region_user_start = region->userspace_addr;
+		region_user_end = region->userspace_addr + region->size;
+		region_gpfn_start = region->guest_pfn;
+		region_gpfn_end = region->guest_pfn + region_page_count;
+
+		if (!(user_end <= region_user_start) &&
+		    !(region_user_end <= user_start)) {
+			return -EEXIST;
+		}
+		if (!(gpfn_end <= region_gpfn_start) &&
+		    !(region_gpfn_end <= gpfn_start)) {
+			return -EEXIST;
+		}
+	}
+
+	/* Pin the userspace pages */
+	pages = vzalloc(sizeof(struct page *) * page_count);
+	if (!pages)
+		return -ENOMEM;
+
+	remaining = page_count;
+	while (remaining) {
+		/*
+		 * We need to batch this, as pin_user_pages_fast with the
+		 * FOLL_LONGTERM flag does a big temporary allocation
+		 * of contiguous memory
+		 */
+		batch_size = min(remaining, PIN_PAGES_BATCH_SIZE);
+		completed = pin_user_pages_fast(
+				mem.userspace_addr + (page_count - remaining) * HV_HYP_PAGE_SIZE,
+				batch_size,
+				FOLL_WRITE | FOLL_LONGTERM,
+				&pages[page_count - remaining]);
+		if (completed < 0) {
+			pr_err("%s: failed to pin user pages error %i\n",
+			       __func__,
+			       completed);
+			ret = completed;
+			goto err_unpin_pages;
+		}
+		remaining -= completed;
+	}
+
+	/* Map the pages to GPA pages */
+	ret = hv_call_map_gpa_pages(partition->id, mem.guest_pfn,
+				    page_count, mem.flags, pages);
+	if (ret)
+		goto err_unpin_pages;
+
+	/* Install the new region */
+	for (i = 0; i < MSHV_MAX_MEM_REGIONS; ++i) {
+		if (!partition->regions.slots[i].size) {
+			region = &partition->regions.slots[i];
+			break;
+		}
+	}
+	region->pages = pages;
+	region->size = mem.size;
+	region->guest_pfn = mem.guest_pfn;
+	region->userspace_addr = mem.userspace_addr;
+
+	partition->regions.count++;
+
+	return 0;
+
+err_unpin_pages:
+	unpin_user_pages(pages, page_count - remaining);
+	vfree(pages);
+
+	return ret;
+}
+
+static long
+mshv_partition_ioctl_unmap_memory(struct mshv_partition *partition,
+				  struct mshv_user_mem_region __user *user_mem)
+{
+	struct mshv_user_mem_region mem;
+	struct mshv_mem_region *region_ptr;
+	int i;
+	u64 page_count;
+	long ret;
+
+	if (!partition->regions.count)
+		return -EINVAL;
+
+	if (copy_from_user(&mem, user_mem, sizeof(mem)))
+		return -EFAULT;
+
+	/* Find matching region */
+	for (i = 0; i < MSHV_MAX_MEM_REGIONS; ++i) {
+		if (!partition->regions.slots[i].size)
+			continue;
+		region_ptr = &partition->regions.slots[i];
+		if (region_ptr->userspace_addr == mem.userspace_addr &&
+		    region_ptr->size == mem.size &&
+		    region_ptr->guest_pfn == mem.guest_pfn)
+			break;
+	}
+
+	if (i == MSHV_MAX_MEM_REGIONS)
+		return -EINVAL;
+
+	page_count = region_ptr->size >> HV_HYP_PAGE_SHIFT;
+	ret = hv_call_unmap_gpa_pages(partition->id, region_ptr->guest_pfn,
+				      page_count, 0);
+	if (ret)
+		return ret;
+
+	unpin_user_pages(region_ptr->pages, page_count);
+	vfree(region_ptr->pages);
+	memset(region_ptr, 0, sizeof(*region_ptr));
+	partition->regions.count--;
+
+	return 0;
+}
+
 static long
 mshv_partition_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg)
 {
-	return -ENOTTY;
+	struct mshv_partition *partition = filp->private_data;
+	long ret;
+
+	if (mutex_lock_killable(&partition->mutex))
+		return -EINTR;
+
+	switch (ioctl) {
+	case MSHV_MAP_GUEST_MEMORY:
+		ret = mshv_partition_ioctl_map_memory(partition,
+							(void __user *)arg);
+		break;
+	case MSHV_UNMAP_GUEST_MEMORY:
+		ret = mshv_partition_ioctl_unmap_memory(partition,
+							(void __user *)arg);
+		break;
+	default:
+		ret = -ENOTTY;
+	}
+
+	mutex_unlock(&partition->mutex);
+	return ret;
 }
 
 static void
 destroy_partition(struct mshv_partition *partition)
 {
-	unsigned long flags;
+	unsigned long flags, page_count;
+	struct mshv_mem_region *region;
 	int i;
 
 	/* Remove from list of partitions */

@@ -94,6 +272,16 @@ destroy_partition(struct mshv_partition *partition)
 
 	hv_call_delete_partition(partition->id);
 
+	/* Remove regions and unpin the pages */
+	for (i = 0; i < MSHV_MAX_MEM_REGIONS; ++i) {
+		region = &partition->regions.slots[i];
+		if (!region->size)
+			continue;
+		page_count = region->size >> HV_HYP_PAGE_SHIFT;
+		unpin_user_pages(region->pages, page_count);
+		vfree(region->pages);
+	}
+
 	kfree(partition);
 }
 

@@ -161,6 +349,8 @@ mshv_ioctl_create_partition(void __user *user_arg)
 	if (!partition)
 		return -ENOMEM;
 
+	mutex_init(&partition->mutex);
+
 	fd = get_unused_fd_flags(O_CLOEXEC);
 	if (fd < 0) {
 		ret = fd;

@@ -20,9 +20,9 @@
  * guest physical pages and guest physical page addresses, since the guest page
  * size may not be 4096 on all architectures.
  */
-#define HV_HYP_PAGE_SHIFT      12
-#define HV_HYP_PAGE_SIZE       BIT(HV_HYP_PAGE_SHIFT)
-#define HV_HYP_PAGE_MASK       (~(HV_HYP_PAGE_SIZE - 1))
+#define HV_HYP_PAGE_SHIFT		12
+#define HV_HYP_PAGE_SIZE		BIT(HV_HYP_PAGE_SHIFT)
+#define HV_HYP_PAGE_MASK		(~(HV_HYP_PAGE_SIZE - 1))
 
 /*
  * Hyper-V provides two categories of flags relevant to guest VMs.  The

@@ -150,6 +150,8 @@ struct ms_hyperv_tsc_page {
 #define HVCALL_GET_PARTITION_ID			0x0046
 #define HVCALL_DEPOSIT_MEMORY			0x0048
 #define HVCALL_WITHDRAW_MEMORY			0x0049
+#define HVCALL_MAP_GPA_PAGES			0x004b
+#define HVCALL_UNMAP_GPA_PAGES			0x004c
 #define HVCALL_CREATE_VP			0x004e
 #define HVCALL_GET_VP_REGISTERS			0x0050
 #define HVCALL_SET_VP_REGISTERS			0x0051

@@ -886,4 +888,19 @@ struct hv_delete_partition {
 	u64 partition_id;
 } __packed;
 
+struct hv_map_gpa_pages {
+	u64 target_partition_id;
+	u64 target_gpa_base;
+	u32 map_flags;
+	u32 padding;
+	u64 source_gpa_page_list[];
+} __packed;
+
+struct hv_unmap_gpa_pages {
+	u64 target_partition_id;
+	u64 target_gpa_base;
+	u32 unmap_flags;
+	u32 padding;
+} __packed;
+
 #endif

@@ -7,13 +7,27 @@
  */
 
 #include <linux/spinlock.h>
+#include <linux/mutex.h>
 #include <uapi/linux/mshv.h>
 
 #define MSHV_MAX_PARTITIONS		128
+#define MSHV_MAX_MEM_REGIONS		64
+
+struct mshv_mem_region {
+	u64 size; /* bytes */
+	u64 guest_pfn;
+	u64 userspace_addr; /* start of the userspace allocated memory */
+	struct page **pages;
+};
 
 struct mshv_partition {
 	u64 id;
 	refcount_t ref_count;
+	struct mutex mutex;
+	struct {
+		u32 count;
+		struct mshv_mem_region slots[MSHV_MAX_MEM_REGIONS];
+	} regions;
 };
 
 struct mshv {

@@ -12,4 +12,13 @@
 #define HV_PARTITION_CREATION_FLAG_GPA_SUPER_PAGES_ENABLED          BIT(4)
 #define HV_PARTITION_CREATION_FLAG_LAPIC_ENABLED                    BIT(13)
 
+/* HV Map GPA (Guest Physical Address) Flags */
+#define HV_MAP_GPA_PERMISSIONS_NONE     0x0
+#define HV_MAP_GPA_READABLE             0x1
+#define HV_MAP_GPA_WRITABLE             0x2
+#define HV_MAP_GPA_KERNEL_EXECUTABLE    0x4
+#define HV_MAP_GPA_USER_EXECUTABLE      0x8
+#define HV_MAP_GPA_EXECUTABLE           0xC
+#define HV_MAP_GPA_PERMISSIONS_MASK     0xF
+
 #endif

@@ -19,10 +19,25 @@ struct mshv_create_partition {
 	struct hv_partition_creation_properties partition_creation_properties;
 };
 
+/*
+ * Mappings can't overlap in GPA space or userspace
+ * To unmap, these fields must match an existing mapping
+ */
+struct mshv_user_mem_region {
+	__u64 size;		/* bytes */
+	__u64 guest_pfn;
+	__u64 userspace_addr;	/* start of the userspace allocated memory */
+	__u32 flags;		/* ignored on unmap */
+};
+
 #define MSHV_IOCTL 0xB8
 
 /* mshv device */
 #define MSHV_CHECK_EXTENSION    _IOW(MSHV_IOCTL, 0x00, __u32)
 #define MSHV_CREATE_PARTITION	_IOW(MSHV_IOCTL, 0x01, struct mshv_create_partition)
 
+/* partition device */
+#define MSHV_MAP_GUEST_MEMORY	_IOW(MSHV_IOCTL, 0x02, struct mshv_user_mem_region)
+#define MSHV_UNMAP_GUEST_MEMORY	_IOW(MSHV_IOCTL, 0x03, struct mshv_user_mem_region)
+
 #endif

@@ -146,6 +146,7 @@ int hv_call_deposit_pages(int node, u64 partition_id, u32 num_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)
 {

@@ -243,4 +244,5 @@ int hv_call_create_vp(int node, u64 partition_id, u32 vp_index, u32 flags)
 
 	return ret;
 }
+EXPORT_SYMBOL_GPL(hv_call_create_vp);
 

@@ -13,4 +13,4 @@ hv_vmbus-y := vmbus_drv.o \
 hv_vmbus-$(CONFIG_HYPERV_TESTING)	+= hv_debugfs.o
 hv_utils-y := hv_util.o hv_kvp.o hv_snapshot.o hv_fcopy.o hv_utils_transport.o
 
-mshv-y                          += mshv_main.o
+mshv-y                          += mshv_main.o hv_call.o

@@ -0,0 +1,129 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (c) 2021, Microsoft Corporation.
+ *
+ * Authors:
+ *   Nuno Das Neves <nudasnev@microsoft.com>
+ *   Lillian Grassin-Drake <ligrassi@microsoft.com>
+ *   Vineeth Pillai <viremana@linux.microsoft.com>
+ */
+
+#include <linux/kernel.h>
+#include <linux/mm.h>
+#include <asm/mshyperv.h>
+
+#include "mshv.h"
+
+int hv_call_create_partition(
+		u64 flags,
+		struct hv_partition_creation_properties creation_properties,
+		u64 *partition_id)
+{
+	struct hv_create_partition_in *input;
+	struct hv_create_partition_out *output;
+	u64 status;
+	int ret;
+	unsigned long irq_flags;
+	int i;
+
+	do {
+		local_irq_save(irq_flags);
+		input = (struct hv_create_partition_in *)(*this_cpu_ptr(
+			hyperv_pcpu_input_arg));
+		output = (struct hv_create_partition_out *)(*this_cpu_ptr(
+			hyperv_pcpu_output_arg));
+
+		input->flags = flags;
+		input->proximity_domain_info.as_uint64 = 0;
+		input->compatibility_version = HV_COMPATIBILITY_20_H1;
+		for (i = 0; i < HV_PARTITION_PROCESSOR_FEATURE_BANKS; ++i)
+			input->partition_creation_properties
+				.disabled_processor_features.as_uint64[i] = 0;
+		input->partition_creation_properties
+			.disabled_processor_xsave_features.as_uint64 = 0;
+		input->isolation_properties.as_uint64 = 0;
+
+		status = hv_do_hypercall(HVCALL_CREATE_PARTITION,
+					 input, output);
+
+		if (hv_result(status) != HV_STATUS_INSUFFICIENT_MEMORY) {
+			if (hv_result_success(status))
+				*partition_id = output->partition_id;
+			else
+				pr_err("%s: %s\n",
+				       __func__, hv_status_to_string(status));
+			local_irq_restore(irq_flags);
+			ret = hv_status_to_errno(status);
+			break;
+		}
+		local_irq_restore(irq_flags);
+		ret = hv_call_deposit_pages(NUMA_NO_NODE,
+					    hv_current_partition_id, 1);
+	} while (!ret);
+
+	return ret;
+}
+
+int hv_call_initialize_partition(u64 partition_id)
+{
+	struct hv_initialize_partition input;
+	u64 status;
+	int ret;
+
+	input.partition_id = partition_id;
+
+	ret = hv_call_deposit_pages(
+				NUMA_NO_NODE,
+				partition_id,
+				HV_INIT_PARTITION_DEPOSIT_PAGES);
+	if (ret)
+		return ret;
+
+	do {
+		status = hv_do_fast_hypercall8(
+				HVCALL_INITIALIZE_PARTITION,
+				*(u64 *)&input);
+
+		if (hv_result(status) != HV_STATUS_INSUFFICIENT_MEMORY) {
+			if (!hv_result_success(status))
+				pr_err("%s: %s\n",
+				       __func__, hv_status_to_string(status));
+			ret = hv_status_to_errno(status);
+			break;
+		}
+		ret = hv_call_deposit_pages(NUMA_NO_NODE, partition_id, 1);
+	} while (!ret);
+
+	return ret;
+}
+
+int hv_call_finalize_partition(u64 partition_id)
+{
+	struct hv_finalize_partition input;
+	u64 status;
+
+	input.partition_id = partition_id;
+	status = hv_do_fast_hypercall8(
+			HVCALL_FINALIZE_PARTITION,
+			*(u64 *)&input);
+
+	if (!hv_result_success(status))
+		pr_err("%s: %s\n", __func__, hv_status_to_string(status));
+
+	return hv_status_to_errno(status);
+}
+
+int hv_call_delete_partition(u64 partition_id)
+{
+	struct hv_delete_partition input;
+	u64 status;
+
+	input.partition_id = partition_id;
+	status = hv_do_fast_hypercall8(HVCALL_DELETE_PARTITION, *(u64 *)&input);
+
+	if (!hv_result_success(status))
+		pr_err("%s: %s\n", __func__, hv_status_to_string(status));
+
+	return hv_status_to_errno(status);
+}
+

@@ -0,0 +1,28 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (c) 2021, Microsoft Corporation.
+ *
+ * Authors:
+ *   Nuno Das Neves <nudasnev@microsoft.com>
+ *   Lillian Grassin-Drake <ligrassi@microsoft.com>
+ *   Vineeth Pillai <viremana@linux.microsoft.com>
+ */
+
+#ifndef _MSHV_H_
+#define _MSHV_H_
+
+/* Determined empirically */
+#define HV_INIT_PARTITION_DEPOSIT_PAGES 208
+
+/*
+ * Hyper-V hypercalls
+ */
+int hv_call_create_partition(
+		u64 flags,
+		struct hv_partition_creation_properties creation_properties,
+		u64 *partition_id);
+int hv_call_initialize_partition(u64 partition_id);
+int hv_call_finalize_partition(u64 partition_id);
+int hv_call_delete_partition(u64 partition_id);
+
+#endif /* _MSHV_H */

@@ -15,6 +15,9 @@
 #include <linux/file.h>
 #include <linux/anon_inodes.h>
 #include <linux/mshv.h>
+#include <asm/mshyperv.h>
+
+#include "mshv.h"
 
 MODULE_AUTHOR("Microsoft");
 MODULE_LICENSE("GPL");

@@ -49,6 +52,7 @@ static struct miscdevice mshv_dev = {
 	.mode = 0600,
 };
 
+
 static long
 mshv_partition_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg)
 {