[PATCH 00/13] x86/Hyper-V: Add Hyper-V Isolation VM support

@@ -20,6 +20,7 @@
 #include <linux/kexec.h>
 #include <linux/version.h>
 #include <linux/vmalloc.h>
+#include <linux/io.h>
 #include <linux/mm.h>
 #include <linux/hyperv.h>
 #include <linux/slab.h>

@@ -42,6 +43,26 @@ static void *hv_hypercall_pg_saved;
 struct hv_vp_assist_page **hv_vp_assist_page;
 EXPORT_SYMBOL_GPL(hv_vp_assist_page);
 
+static int hyperv_init_ghcb(void)
+{
+	u64 ghcb_gpa;
+	void *ghcb_va;
+	void **ghcb_base;
+
+	if (!ms_hyperv.ghcb_base)
+		return -EINVAL;
+
+	rdmsrl(MSR_AMD64_SEV_ES_GHCB, ghcb_gpa);
+	ghcb_va = memremap(ghcb_gpa, HV_HYP_PAGE_SIZE, MEMREMAP_WB);
+	if (!ghcb_va)
+		return -ENOMEM;
+
+	ghcb_base = (void **)this_cpu_ptr(ms_hyperv.ghcb_base);
+	*ghcb_base = ghcb_va;
+
+	return 0;
+}
+
 static int hv_cpu_init(unsigned int cpu)
 {
 	struct hv_vp_assist_page **hvp = &hv_vp_assist_page[smp_processor_id()];

@@ -75,6 +96,8 @@ static int hv_cpu_init(unsigned int cpu)
 		wrmsrl(HV_X64_MSR_VP_ASSIST_PAGE, val);
 	}
 
+	hyperv_init_ghcb();
+
 	return 0;
 }
 

@@ -167,6 +190,31 @@ static int hv_cpu_die(unsigned int cpu)
 {
 	struct hv_reenlightenment_control re_ctrl;
 	unsigned int new_cpu;
+	unsigned long flags;
+	void **input_arg;
+	void *pg;
+	void **ghcb_va = NULL;
+
+	local_irq_save(flags);
+	input_arg = (void **)this_cpu_ptr(hyperv_pcpu_input_arg);
+	pg = *input_arg;
+	*input_arg = NULL;
+
+	if (hv_root_partition) {
+		void **output_arg;
+
+		output_arg = (void **)this_cpu_ptr(hyperv_pcpu_output_arg);
+		*output_arg = NULL;
+	}
+
+	if (ms_hyperv.ghcb_base) {
+		ghcb_va = (void **)this_cpu_ptr(ms_hyperv.ghcb_base);
+		if (*ghcb_va)
+			memunmap(*ghcb_va);
+		*ghcb_va = NULL;
+	}
+
+	local_irq_restore(flags);
 
 	hv_common_cpu_die(cpu);
 

@@ -340,9 +388,22 @@ void __init hyperv_init(void)
 			VMALLOC_END, GFP_KERNEL, PAGE_KERNEL_ROX,
 			VM_FLUSH_RESET_PERMS, NUMA_NO_NODE,
 			__builtin_return_address(0));
-	if (hv_hypercall_pg == NULL) {
-		wrmsrl(HV_X64_MSR_GUEST_OS_ID, 0);
-		goto remove_cpuhp_state;
+	if (hv_hypercall_pg == NULL)
+		goto clean_guest_os_id;
+
+	if (hv_isolation_type_snp()) {
+		ms_hyperv.ghcb_base = alloc_percpu(void *);
+		if (!ms_hyperv.ghcb_base)
+			goto clean_guest_os_id;
+
+		if (hyperv_init_ghcb()) {
+			free_percpu(ms_hyperv.ghcb_base);
+			ms_hyperv.ghcb_base = NULL;
+			goto clean_guest_os_id;
+		}
+
+		/* Hyper-V requires to write guest os id via ghcb in SNP IVM. */
+		hv_ghcb_msr_write(HV_X64_MSR_GUEST_OS_ID, guest_id);
 	}
 
 	rdmsrl(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64);

@@ -403,7 +464,8 @@ void __init hyperv_init(void)
 	hv_query_ext_cap(0);
 	return;
 
-remove_cpuhp_state:
+clean_guest_os_id:
+	wrmsrl(HV_X64_MSR_GUEST_OS_ID, 0);
 	cpuhp_remove_state(cpuhp);
 free_vp_assist_page:
 	kfree(hv_vp_assist_page);

@@ -431,6 +493,9 @@ void hyperv_cleanup(void)
 	 */
 	hv_hypercall_pg = NULL;
 
+	if (ms_hyperv.ghcb_base)
+		free_percpu(ms_hyperv.ghcb_base);
+
 	/* Reset the hypercall page */
 	hypercall_msr.as_uint64 = 0;
 	wrmsrl(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64);

@@ -11,6 +11,8 @@
 #include <asm/paravirt.h>
 #include <asm/mshyperv.h>
 
+DECLARE_STATIC_KEY_FALSE(isolation_type_snp);
+
 typedef int (*hyperv_fill_flush_list_func)(
 		struct hv_guest_mapping_flush_list *flush,
 		void *data);

@@ -36,6 +36,7 @@ struct ms_hyperv_info {
 	u32 max_lp_index;
 	u32 isolation_config_a;
 	u32 isolation_config_b;
+	void  __percpu **ghcb_base;
 };
 extern struct ms_hyperv_info ms_hyperv;
 

@@ -237,6 +238,7 @@ bool hv_is_hyperv_initialized(void);
 bool hv_is_hibernation_supported(void);
 enum hv_isolation_type hv_get_isolation_type(void);
 bool hv_is_isolation_supported(void);
+bool hv_isolation_type_snp(void);
 void hyperv_cleanup(void);
 bool hv_query_ext_cap(u64 cap_query);
 #else /* CONFIG_HYPERV */

@@ -1,5 +1,5 @@
 # SPDX-License-Identifier: GPL-2.0-only
-obj-y			:= hv_init.o mmu.o nested.o irqdomain.o
+obj-y			:= hv_init.o mmu.o nested.o irqdomain.o ivm.o
 obj-$(CONFIG_X86_64)	+= hv_apic.o hv_proc.o
 
 ifdef CONFIG_X86_64

@@ -0,0 +1,112 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Hyper-V Isolation VM interface with paravisor and hypervisor
+ *
+ * Author:
+ *  Tianyu Lan <Tianyu.Lan@microsoft.com>
+ */
+
+#include <linux/hyperv.h>
+#include <linux/types.h>
+#include <linux/bitfield.h>
+#include <linux/slab.h>
+#include <asm/io.h>
+#include <asm/mshyperv.h>
+
+/*
+ * hv_mark_gpa_visibility - Set pages visible to host via hvcall.
+ *
+ * In Isolation VM, all guest memory is encripted from host and guest
+ * needs to set memory visible to host via hvcall before sharing memory
+ * with host.
+ */
+int hv_mark_gpa_visibility(u16 count, const u64 pfn[], u32 visibility)
+{
+	struct hv_gpa_range_for_visibility **input_pcpu, *input;
+	u16 pages_processed;
+	u64 hv_status;
+	unsigned long flags;
+
+	/* no-op if partition isolation is not enabled */
+	if (!hv_is_isolation_supported())
+		return 0;
+
+	if (count > HV_MAX_MODIFY_GPA_REP_COUNT) {
+		pr_err("Hyper-V: GPA count:%d exceeds supported:%lu\n", count,
+			HV_MAX_MODIFY_GPA_REP_COUNT);
+		return -EINVAL;
+	}
+
+	local_irq_save(flags);
+	input_pcpu = (struct hv_gpa_range_for_visibility **)
+			this_cpu_ptr(hyperv_pcpu_input_arg);
+	input = *input_pcpu;
+	if (unlikely(!input)) {
+		local_irq_restore(flags);
+		return -EINVAL;
+	}
+
+	input->partition_id = HV_PARTITION_ID_SELF;
+	input->host_visibility = visibility;
+	input->reserved0 = 0;
+	input->reserved1 = 0;
+	memcpy((void *)input->gpa_page_list, pfn, count * sizeof(*pfn));
+	hv_status = hv_do_rep_hypercall(
+			HVCALL_MODIFY_SPARSE_GPA_PAGE_HOST_VISIBILITY, count,
+			0, input, &pages_processed);
+	local_irq_restore(flags);
+
+	if (!(hv_status & HV_HYPERCALL_RESULT_MASK))
+		return 0;
+
+	return hv_status & HV_HYPERCALL_RESULT_MASK;
+}
+EXPORT_SYMBOL(hv_mark_gpa_visibility);
+
+/*
+ * hv_set_mem_host_visibility - Set specified memory visible to host.
+ *
+ * In Isolation VM, all guest memory is encrypted from host and guest
+ * needs to set memory visible to host via hvcall before sharing memory
+ * with host. This function works as wrap of hv_mark_gpa_visibility()
+ * with memory base and size.
+ */
+static int hv_set_mem_host_visibility(void *kbuffer, size_t size, u32 visibility)
+{
+	int pagecount = size >> HV_HYP_PAGE_SHIFT;
+	u64 *pfn_array;
+	int ret = 0;
+	int i, pfn;
+
+	if (!hv_is_isolation_supported() || !ms_hyperv.ghcb_base)
+		return 0;
+
+	pfn_array = kzalloc(HV_HYP_PAGE_SIZE, GFP_KERNEL);
+	if (!pfn_array)
+		return -ENOMEM;
+
+	for (i = 0, pfn = 0; i < pagecount; i++) {
+		pfn_array[pfn] = virt_to_hvpfn(kbuffer + i * HV_HYP_PAGE_SIZE);
+		pfn++;
+
+		if (pfn == HV_MAX_MODIFY_GPA_REP_COUNT || i == pagecount - 1) {
+			ret |= hv_mark_gpa_visibility(pfn, pfn_array, visibility);
+			pfn = 0;
+
+			if (ret)
+				goto err_free_pfn_array;
+		}
+	}
+
+ err_free_pfn_array:
+	kfree(pfn_array);
+	return ret;
+}
+
+int hv_set_mem_enc(unsigned long addr, int numpages, bool enc)
+{
+	return hv_set_mem_host_visibility((void *)addr,
+			numpages * HV_HYP_PAGE_SIZE,
+			enc ? VMBUS_PAGE_NOT_VISIBLE
+			: VMBUS_PAGE_VISIBLE_READ_WRITE);
+}

@@ -276,6 +276,11 @@ enum hv_isolation_type {
 #define HV_X64_MSR_TIME_REF_COUNT	HV_REGISTER_TIME_REF_COUNT
 #define HV_X64_MSR_REFERENCE_TSC	HV_REGISTER_REFERENCE_TSC
 
+/* Hyper-V GPA map flags */
+#define	VMBUS_PAGE_NOT_VISIBLE		0
+#define	VMBUS_PAGE_VISIBLE_READ_ONLY	1
+#define	VMBUS_PAGE_VISIBLE_READ_WRITE	3
+
 /*
  * Declare the MSR used to setup pages used to communicate with the hypervisor.
  */

@@ -578,4 +583,17 @@ enum hv_interrupt_type {
 
 #include <asm-generic/hyperv-tlfs.h>
 
+/* All input parameters should be in single page. */
+#define HV_MAX_MODIFY_GPA_REP_COUNT		\
+	((PAGE_SIZE / sizeof(u64)) - 2)
+
+/* HvCallModifySparseGpaPageHostVisibility hypercall */
+struct hv_gpa_range_for_visibility {
+	u64 partition_id;
+	u32 host_visibility:2;
+	u32 reserved0:30;
+	u32 reserved1;
+	u64 gpa_page_list[HV_MAX_MODIFY_GPA_REP_COUNT];
+} __packed;
+
 #endif

@@ -190,7 +190,8 @@ struct irq_domain *hv_create_pci_msi_domain(void);
 int hv_map_ioapic_interrupt(int ioapic_id, bool level, int vcpu, int vector,
 		struct hv_interrupt_entry *entry);
 int hv_unmap_ioapic_interrupt(int ioapic_id, struct hv_interrupt_entry *entry);
-
+int hv_mark_gpa_visibility(u16 count, const u64 pfn[], u32 visibility);
+int hv_set_mem_enc(unsigned long addr, int numpages, bool enc);
 #else /* CONFIG_HYPERV */
 static inline void hyperv_init(void) {}
 static inline void hyperv_setup_mmu_ops(void) {}

@@ -29,6 +29,8 @@
 #include <asm/proto.h>
 #include <asm/memtype.h>
 #include <asm/set_memory.h>
+#include <asm/hyperv-tlfs.h>
+#include <asm/mshyperv.h>
 
 #include "../mm_internal.h"
 

@@ -1986,7 +1988,9 @@ static int __set_memory_enc_dec(unsigned long addr, int numpages, bool enc)
 	int ret;
 
 	/* Nothing to do if memory encryption is not active */
-	if (!mem_encrypt_active())
+	if (hv_is_isolation_supported())
+		return hv_set_mem_enc(addr, numpages, enc);
+	else if (!mem_encrypt_active())
 		return 0;
 
 	/* Should not be working on unaligned addresses */

@@ -158,6 +158,7 @@ struct ms_hyperv_tsc_page {
 #define HVCALL_RETARGET_INTERRUPT		0x007e
 #define HVCALL_FLUSH_GUEST_PHYSICAL_ADDRESS_SPACE 0x00af
 #define HVCALL_FLUSH_GUEST_PHYSICAL_ADDRESS_LIST 0x00b0
+#define HVCALL_MODIFY_SPARSE_GPA_PAGE_HOST_VISIBILITY 0x00db
 
 /* Extended hypercalls */
 #define HV_EXT_CALL_QUERY_CAPABILITIES		0x8001

@@ -327,6 +327,8 @@ static void __init ms_hyperv_init_platform(void)
 	if (ms_hyperv.priv_high & HV_ISOLATION) {
 		ms_hyperv.isolation_config_a = cpuid_eax(HYPERV_CPUID_ISOLATION_CONFIG);
 		ms_hyperv.isolation_config_b = cpuid_ebx(HYPERV_CPUID_ISOLATION_CONFIG);
+		ms_hyperv.shared_gpa_boundary =
+			(u64)1 << ms_hyperv.shared_gpa_boundary_bits;
 
 		pr_info("Hyper-V: Isolation Config: Group A 0x%x, Group B 0x%x\n",
 			ms_hyperv.isolation_config_a, ms_hyperv.isolation_config_b);

@@ -35,8 +35,18 @@ struct ms_hyperv_info {
 	u32 max_vp_index;
 	u32 max_lp_index;
 	u32 isolation_config_a;
-	u32 isolation_config_b;
+	union {
+		u32 isolation_config_b;
+		struct {
+			u32 cvm_type : 4;
+			u32 Reserved11 : 1;
+			u32 shared_gpa_boundary_active : 1;
+			u32 shared_gpa_boundary_bits : 6;
+			u32 Reserved12 : 20;
+		};
+	};
 	void  __percpu **ghcb_base;
+	u64 shared_gpa_boundary;
 };
 extern struct ms_hyperv_info ms_hyperv;
 

@@ -17,6 +17,7 @@
 #include <linux/hyperv.h>
 #include <linux/uio.h>
 #include <linux/interrupt.h>
+#include <linux/set_memory.h>
 #include <asm/page.h>
 #include <asm/mshyperv.h>
 

@@ -465,7 +466,7 @@ static int __vmbus_establish_gpadl(struct vmbus_channel *channel,
 	struct list_head *curr;
 	u32 next_gpadl_handle;
 	unsigned long flags;
-	int ret = 0;
+	int ret = 0, index;
 
 	next_gpadl_handle =
 		(atomic_inc_return(&vmbus_connection.next_gpadl_handle) - 1);

@@ -474,6 +475,13 @@ static int __vmbus_establish_gpadl(struct vmbus_channel *channel,
 	if (ret)
 		return ret;
 
+	ret = set_memory_decrypted((unsigned long)kbuffer,
+				   HVPFN_UP(size));
+	if (ret) {
+		pr_warn("Failed to set host visibility.\n");
+		return ret;
+	}
+
 	init_completion(&msginfo->waitevent);
 	msginfo->waiting_channel = channel;
 

@@ -539,6 +547,15 @@ static int __vmbus_establish_gpadl(struct vmbus_channel *channel,
 	/* At this point, we received the gpadl created msg */
 	*gpadl_handle = gpadlmsg->gpadl;
 
+	if (type == HV_GPADL_BUFFER)
+		index = 0;
+	else
+		index = channel->gpadl_range[1].gpadlhandle ? 2 : 1;
+
+	channel->gpadl_range[index].size = size;
+	channel->gpadl_range[index].buffer = kbuffer;
+	channel->gpadl_range[index].gpadlhandle = *gpadl_handle;
+
 cleanup:
 	spin_lock_irqsave(&vmbus_connection.channelmsg_lock, flags);
 	list_del(&msginfo->msglistentry);

@@ -549,6 +566,11 @@ static int __vmbus_establish_gpadl(struct vmbus_channel *channel,
 	}
 
 	kfree(msginfo);
+
+	if (ret)
+		set_memory_encrypted((unsigned long)kbuffer,
+				     HVPFN_UP(size));
+
 	return ret;
 }
 

@@ -811,7 +833,7 @@ int vmbus_teardown_gpadl(struct vmbus_channel *channel, u32 gpadl_handle)
 	struct vmbus_channel_gpadl_teardown *msg;
 	struct vmbus_channel_msginfo *info;
 	unsigned long flags;
-	int ret;
+	int ret, i;
 
 	info = kzalloc(sizeof(*info) +
 		       sizeof(struct vmbus_channel_gpadl_teardown), GFP_KERNEL);

@@ -859,6 +881,18 @@ int vmbus_teardown_gpadl(struct vmbus_channel *channel, u32 gpadl_handle)
 	spin_unlock_irqrestore(&vmbus_connection.channelmsg_lock, flags);
 
 	kfree(info);
+
+	/* Find gpadl buffer virtual address and size. */
+	for (i = 0; i < VMBUS_GPADL_RANGE_COUNT; i++)
+		if (channel->gpadl_range[i].gpadlhandle == gpadl_handle)
+			break;
+
+	if (set_memory_encrypted((unsigned long)channel->gpadl_range[i].buffer,
+			HVPFN_UP(channel->gpadl_range[i].size)))
+		pr_warn("Fail to set mem host visibility.\n");
+
+	channel->gpadl_range[i].gpadlhandle = 0;
+
 	return ret;
 }
 EXPORT_SYMBOL_GPL(vmbus_teardown_gpadl);

@@ -809,6 +809,14 @@ struct vmbus_device {
 
 #define VMBUS_DEFAULT_MAX_PKT_SIZE 4096
 
+struct vmbus_gpadl_range {
+	u32 gpadlhandle;
+	u32 size;
+	void *buffer;
+};
+
+#define VMBUS_GPADL_RANGE_COUNT		3
+
 struct vmbus_channel {
 	struct list_head listentry;
 

@@ -829,6 +837,8 @@ struct vmbus_channel {
 	struct completion rescind_event;
 
 	u32 ringbuffer_gpadlhandle;
+	/* GPADL_RING and Send/Receive GPADL_BUFFER. */
+	struct vmbus_gpadl_range gpadl_range[VMBUS_GPADL_RANGE_COUNT];
 
 	/* Allocated memory for ring buffer */
 	struct page *ringbuffer_page;

@@ -392,7 +392,7 @@ void __init hyperv_init(void)
 		goto clean_guest_os_id;
 
 	if (hv_isolation_type_snp()) {
-		ms_hyperv.ghcb_base = alloc_percpu(void *);
+		ms_hyperv.ghcb_base = alloc_percpu(union hv_ghcb __percpu *);
 		if (!ms_hyperv.ghcb_base)
 			goto clean_guest_os_id;
 

@@ -485,6 +485,7 @@ void hyperv_cleanup(void)
 
 	/* Reset our OS id */
 	wrmsrl(HV_X64_MSR_GUEST_OS_ID, 0);
+	hv_ghcb_msr_write(HV_X64_MSR_GUEST_OS_ID, 0);
 
 	/*
 	 * Reset hypercall page reference before reset the page,

@@ -558,16 +559,3 @@ bool hv_is_hyperv_initialized(void)
 	return hypercall_msr.enable;
 }
 EXPORT_SYMBOL_GPL(hv_is_hyperv_initialized);
-
-enum hv_isolation_type hv_get_isolation_type(void)
-{
-	if (!(ms_hyperv.priv_high & HV_ISOLATION))
-		return HV_ISOLATION_TYPE_NONE;
-	return FIELD_GET(HV_ISOLATION_TYPE, ms_hyperv.isolation_config_b);
-}
-EXPORT_SYMBOL_GPL(hv_get_isolation_type);
-
-bool hv_is_isolation_supported(void)
-{
-	return hv_get_isolation_type() != HV_ISOLATION_TYPE_NONE;
-}

@@ -6,6 +6,8 @@
  *  Tianyu Lan <Tianyu.Lan@microsoft.com>
  */
 
+#include <linux/types.h>
+#include <linux/bitfield.h>
 #include <linux/hyperv.h>
 #include <linux/types.h>
 #include <linux/bitfield.h>

@@ -13,6 +15,118 @@
 #include <asm/io.h>
 #include <asm/mshyperv.h>
 
+void hv_ghcb_msr_write(u64 msr, u64 value)
+{
+	union hv_ghcb *hv_ghcb;
+	void **ghcb_base;
+	unsigned long flags;
+
+	if (!ms_hyperv.ghcb_base)
+		return;
+
+	WARN_ON(in_nmi());
+
+	local_irq_save(flags);
+	ghcb_base = (void **)this_cpu_ptr(ms_hyperv.ghcb_base);
+	hv_ghcb = (union hv_ghcb *)*ghcb_base;
+	if (!hv_ghcb) {
+		local_irq_restore(flags);
+		return;
+	}
+
+	memset(hv_ghcb, 0x00, HV_HYP_PAGE_SIZE);
+
+	ghcb_set_rcx(&hv_ghcb->ghcb, msr);
+	ghcb_set_rax(&hv_ghcb->ghcb, lower_32_bits(value));
+	ghcb_set_rdx(&hv_ghcb->ghcb, value >> 32);
+
+	if (sev_es_ghcb_hv_call(&hv_ghcb->ghcb, NULL, SVM_EXIT_MSR, 1, 0))
+		pr_warn("Fail to write msr via ghcb %llx.\n", msr);
+
+	local_irq_restore(flags);
+}
+
+void hv_ghcb_msr_read(u64 msr, u64 *value)
+{
+	union hv_ghcb *hv_ghcb;
+	void **ghcb_base;
+	unsigned long flags;
+
+	if (!ms_hyperv.ghcb_base)
+		return;
+
+	WARN_ON(in_nmi());
+
+	local_irq_save(flags);
+	ghcb_base = (void **)this_cpu_ptr(ms_hyperv.ghcb_base);
+	hv_ghcb = (union hv_ghcb *)*ghcb_base;
+	if (!hv_ghcb) {
+		local_irq_restore(flags);
+		return;
+	}
+
+	memset(hv_ghcb, 0x00, HV_HYP_PAGE_SIZE);
+
+	ghcb_set_rcx(&hv_ghcb->ghcb, msr);
+	if (sev_es_ghcb_hv_call(&hv_ghcb->ghcb, NULL, SVM_EXIT_MSR, 0, 0))
+		pr_warn("Fail to read msr via ghcb %llx.\n", msr);
+	else
+		*value = (u64)lower_32_bits(hv_ghcb->ghcb.save.rax)
+			| ((u64)lower_32_bits(hv_ghcb->ghcb.save.rdx) << 32);
+	local_irq_restore(flags);
+}
+
+void hv_sint_rdmsrl_ghcb(u64 msr, u64 *value)
+{
+	hv_ghcb_msr_read(msr, value);
+}
+EXPORT_SYMBOL_GPL(hv_sint_rdmsrl_ghcb);
+
+void hv_sint_wrmsrl_ghcb(u64 msr, u64 value)
+{
+	hv_ghcb_msr_write(msr, value);
+
+	/* Write proxy bit vua wrmsrl instruction. */
+	if (msr >= HV_X64_MSR_SINT0 && msr <= HV_X64_MSR_SINT15)
+		wrmsrl(msr, value | 1 << 20);
+}
+EXPORT_SYMBOL_GPL(hv_sint_wrmsrl_ghcb);
+
+void hv_signal_eom_ghcb(void)
+{
+	hv_sint_wrmsrl_ghcb(HV_X64_MSR_EOM, 0);
+}
+EXPORT_SYMBOL_GPL(hv_signal_eom_ghcb);
+
+enum hv_isolation_type hv_get_isolation_type(void)
+{
+	if (!(ms_hyperv.priv_high & HV_ISOLATION))
+		return HV_ISOLATION_TYPE_NONE;
+	return FIELD_GET(HV_ISOLATION_TYPE, ms_hyperv.isolation_config_b);
+}
+EXPORT_SYMBOL_GPL(hv_get_isolation_type);
+
+/*
+ * hv_is_isolation_supported - Check system runs in the Hyper-V
+ * isolation VM.
+ */
+bool hv_is_isolation_supported(void)
+{
+	return hv_get_isolation_type() != HV_ISOLATION_TYPE_NONE;
+}
+
+DEFINE_STATIC_KEY_FALSE(isolation_type_snp);
+
+/*
+ * hv_isolation_type_snp - Check system runs in the AMD SEV-SNP based
+ * isolation VM.
+ */
+bool hv_isolation_type_snp(void)
+{
+	return static_branch_unlikely(&isolation_type_snp);
+}
+EXPORT_SYMBOL_GPL(hv_isolation_type_snp);
+
 /*
  * hv_mark_gpa_visibility - Set pages visible to host via hvcall.
  *

@@ -30,6 +30,63 @@ static inline u64 hv_get_register(unsigned int reg)
 	return value;
 }
 
+#define hv_get_sint_reg(val, reg) {		\
+	if (hv_isolation_type_snp())		\
+		hv_get_##reg##_ghcb(&val);	\
+	else					\
+		rdmsrl(HV_X64_MSR_##reg, val);	\
+	}
+
+#define hv_set_sint_reg(val, reg) {		\
+	if (hv_isolation_type_snp())		\
+		hv_set_##reg##_ghcb(val);	\
+	else					\
+		wrmsrl(HV_X64_MSR_##reg, val);	\
+	}
+
+
+#define hv_get_simp(val) hv_get_sint_reg(val, SIMP)
+#define hv_get_siefp(val) hv_get_sint_reg(val, SIEFP)
+
+#define hv_set_simp(val) hv_set_sint_reg(val, SIMP)
+#define hv_set_siefp(val) hv_set_sint_reg(val, SIEFP)
+
+#define hv_get_synic_state(val) {			\
+	if (hv_isolation_type_snp())			\
+		hv_get_synic_state_ghcb(&val);		\
+	else						\
+		rdmsrl(HV_X64_MSR_SCONTROL, val);	\
+	}
+#define hv_set_synic_state(val) {			\
+	if (hv_isolation_type_snp())			\
+		hv_set_synic_state_ghcb(val);		\
+	else						\
+		wrmsrl(HV_X64_MSR_SCONTROL, val);	\
+	}
+
+#define hv_get_vp_index(index) rdmsrl(HV_X64_MSR_VP_INDEX, index)
+
+#define hv_signal_eom() {			 \
+	if (hv_isolation_type_snp() &&		 \
+	    old_msg_type != HVMSG_TIMER_EXPIRED) \
+		hv_signal_eom_ghcb();		 \
+	else					 \
+		wrmsrl(HV_X64_MSR_EOM, 0);	 \
+	}
+
+#define hv_get_synint_state(int_num, val) {		\
+	if (hv_isolation_type_snp())			\
+		hv_get_synint_state_ghcb(int_num, &val);\
+	else						\
+		rdmsrl(HV_X64_MSR_SINT0 + int_num, val);\
+	}
+#define hv_set_synint_state(int_num, val) {		\
+	if (hv_isolation_type_snp())			\
+		hv_set_synint_state_ghcb(int_num, val);	\
+	else						\
+		wrmsrl(HV_X64_MSR_SINT0 + int_num, val);\
+	}
+
 #define hv_get_raw_timer() rdtsc_ordered()
 
 void hyperv_vector_handler(struct pt_regs *regs);

@@ -192,6 +249,25 @@ int hv_map_ioapic_interrupt(int ioapic_id, bool level, int vcpu, int vector,
 int hv_unmap_ioapic_interrupt(int ioapic_id, struct hv_interrupt_entry *entry);
 int hv_mark_gpa_visibility(u16 count, const u64 pfn[], u32 visibility);
 int hv_set_mem_enc(unsigned long addr, int numpages, bool enc);
+void hv_sint_wrmsrl_ghcb(u64 msr, u64 value);
+void hv_sint_rdmsrl_ghcb(u64 msr, u64 *value);
+void hv_signal_eom_ghcb(void);
+void hv_ghcb_msr_write(u64 msr, u64 value);
+void hv_ghcb_msr_read(u64 msr, u64 *value);
+
+#define hv_get_synint_state_ghcb(int_num, val)			\
+	hv_sint_rdmsrl_ghcb(HV_X64_MSR_SINT0 + int_num, val)
+#define hv_set_synint_state_ghcb(int_num, val) \
+	hv_sint_wrmsrl_ghcb(HV_X64_MSR_SINT0 + int_num, val)
+
+#define hv_get_SIMP_ghcb(val) hv_sint_rdmsrl_ghcb(HV_X64_MSR_SIMP, val)
+#define hv_set_SIMP_ghcb(val) hv_sint_wrmsrl_ghcb(HV_X64_MSR_SIMP, val)
+
+#define hv_get_SIEFP_ghcb(val) hv_sint_rdmsrl_ghcb(HV_X64_MSR_SIEFP, val)
+#define hv_set_SIEFP_ghcb(val) hv_sint_wrmsrl_ghcb(HV_X64_MSR_SIEFP, val)
+
+#define hv_get_synic_state_ghcb(val) hv_sint_rdmsrl_ghcb(HV_X64_MSR_SCONTROL, val)
+#define hv_set_synic_state_ghcb(val) hv_sint_wrmsrl_ghcb(HV_X64_MSR_SCONTROL, val)
 #else /* CONFIG_HYPERV */
 static inline void hyperv_init(void) {}
 static inline void hyperv_setup_mmu_ops(void) {}

@@ -208,9 +284,9 @@ static inline int hyperv_flush_guest_mapping_range(u64 as,
 {
 	return -1;
 }
+static inline void hv_signal_eom_ghcb(void) { };
 #endif /* CONFIG_HYPERV */
 
-
 #include <asm-generic/mshyperv.h>
 
 #endif

@@ -81,6 +81,10 @@ static __always_inline void sev_es_nmi_complete(void)
 		__sev_es_nmi_complete();
 }
 extern int __init sev_es_efi_map_ghcbs(pgd_t *pgd);
+extern enum es_result sev_es_ghcb_hv_call(struct ghcb *ghcb,
+				   struct es_em_ctxt *ctxt,
+				   u64 exit_code, u64 exit_info_1,
+				   u64 exit_info_2);
 #else
 static inline void sev_es_ist_enter(struct pt_regs *regs) { }
 static inline void sev_es_ist_exit(void) { }

@@ -332,6 +332,9 @@ static void __init ms_hyperv_init_platform(void)
 
 		pr_info("Hyper-V: Isolation Config: Group A 0x%x, Group B 0x%x\n",
 			ms_hyperv.isolation_config_a, ms_hyperv.isolation_config_b);
+
+		if (hv_get_isolation_type() == HV_ISOLATION_TYPE_SNP)
+			static_branch_enable(&isolation_type_snp);
 	}
 
 	if (hv_max_functions_eax >= HYPERV_CPUID_NESTED_FEATURES) {

@@ -94,10 +94,10 @@ static void vc_finish_insn(struct es_em_ctxt *ctxt)
 	ctxt->regs->ip += ctxt->insn.length;
 }
 
-static enum es_result sev_es_ghcb_hv_call(struct ghcb *ghcb,
-					  struct es_em_ctxt *ctxt,
-					  u64 exit_code, u64 exit_info_1,
-					  u64 exit_info_2)
+enum es_result sev_es_ghcb_hv_call(struct ghcb *ghcb,
+				   struct es_em_ctxt *ctxt,
+				   u64 exit_code, u64 exit_info_1,
+				   u64 exit_info_2)
 {
 	enum es_result ret;
 

@@ -109,7 +109,16 @@ static enum es_result sev_es_ghcb_hv_call(struct ghcb *ghcb,
 	ghcb_set_sw_exit_info_1(ghcb, exit_info_1);
 	ghcb_set_sw_exit_info_2(ghcb, exit_info_2);
 
-	sev_es_wr_ghcb_msr(__pa(ghcb));
+	/*
+	 * Hyper-V runs paravisor with SEV. Ghcb page is allocated by
+	 * paravisor and not needs to be updated in the Linux guest.
+	 * Otherwise, the ghcb page's PA reported by paravisor is above
+	 * VTOM. Hyper-V use this function with NULL for ctxt point and
+	 * skip setting ghcb page in such case.
+	 */
+	if (ctxt)
+		sev_es_wr_ghcb_msr(__pa(ghcb));
+
 	VMGEXIT();
 
 	if ((ghcb->save.sw_exit_info_1 & 0xffffffff) == 1) {

@@ -120,7 +129,7 @@ static enum es_result sev_es_ghcb_hv_call(struct ghcb *ghcb,
 		v = info & SVM_EVTINJ_VEC_MASK;
 
 		/* Check if exception information from hypervisor is sane. */
-		if ((info & SVM_EVTINJ_VALID) &&
+		if (ctxt && (info & SVM_EVTINJ_VALID) &&
 		    ((v == X86_TRAP_GP) || (v == X86_TRAP_UD)) &&
 		    ((info & SVM_EVTINJ_TYPE_MASK) == SVM_EVTINJ_TYPE_EXEPT)) {
 			ctxt->fi.vector = v;

@@ -8,6 +8,7 @@
  */
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 
+#include <linux/io.h>
 #include <linux/kernel.h>
 #include <linux/mm.h>
 #include <linux/slab.h>

@@ -136,17 +137,24 @@ int hv_synic_alloc(void)
 		tasklet_init(&hv_cpu->msg_dpc,
 			     vmbus_on_msg_dpc, (unsigned long) hv_cpu);
 
-		hv_cpu->synic_message_page =
-			(void *)get_zeroed_page(GFP_ATOMIC);
-		if (hv_cpu->synic_message_page == NULL) {
-			pr_err("Unable to allocate SYNIC message page\n");
-			goto err;
-		}
+		/*
+		 * Synic message and event pages are allocated by paravisor.
+		 * Skip these pages allocation here.
+		 */
+		if (!hv_isolation_type_snp()) {
+			hv_cpu->synic_message_page =
+				(void *)get_zeroed_page(GFP_ATOMIC);
+			if (hv_cpu->synic_message_page == NULL) {
+				pr_err("Unable to allocate SYNIC message page\n");
+				goto err;
+			}
 
-		hv_cpu->synic_event_page = (void *)get_zeroed_page(GFP_ATOMIC);
-		if (hv_cpu->synic_event_page == NULL) {
-			pr_err("Unable to allocate SYNIC event page\n");
-			goto err;
+			hv_cpu->synic_event_page =
+				(void *)get_zeroed_page(GFP_ATOMIC);
+			if (hv_cpu->synic_event_page == NULL) {
+				pr_err("Unable to allocate SYNIC event page\n");
+				goto err;
+			}
 		}
 
 		hv_cpu->post_msg_page = (void *)get_zeroed_page(GFP_ATOMIC);

@@ -173,10 +181,17 @@ void hv_synic_free(void)
 	for_each_present_cpu(cpu) {
 		struct hv_per_cpu_context *hv_cpu
 			= per_cpu_ptr(hv_context.cpu_context, cpu);
+		free_page((unsigned long)hv_cpu->post_msg_page);
+
+		/*
+		 * Synic message and event pages are allocated by paravisor.
+		 * Skip free these pages here.
+		 */
+		if (hv_isolation_type_snp())
+			continue;
 
 		free_page((unsigned long)hv_cpu->synic_event_page);
 		free_page((unsigned long)hv_cpu->synic_message_page);
-		free_page((unsigned long)hv_cpu->post_msg_page);
 	}
 
 	kfree(hv_context.hv_numa_map);

@@ -199,26 +214,43 @@ void hv_synic_enable_regs(unsigned int cpu)
 	union hv_synic_scontrol sctrl;
 
 	/* Setup the Synic's message page */
-	simp.as_uint64 = hv_get_register(HV_REGISTER_SIMP);
+	hv_get_simp(simp.as_uint64);
 	simp.simp_enabled = 1;
-	simp.base_simp_gpa = virt_to_phys(hv_cpu->synic_message_page)
-		>> HV_HYP_PAGE_SHIFT;
 
-	hv_set_register(HV_REGISTER_SIMP, simp.as_uint64);
+	if (hv_isolation_type_snp()) {
+		hv_cpu->synic_message_page
+			= memremap(simp.base_simp_gpa << HV_HYP_PAGE_SHIFT,
+				   HV_HYP_PAGE_SIZE, MEMREMAP_WB);
+		if (!hv_cpu->synic_message_page)
+			pr_err("Fail to map syinc message page.\n");
+	} else {
+		simp.base_simp_gpa = virt_to_phys(hv_cpu->synic_message_page)
+			>> HV_HYP_PAGE_SHIFT;
+	}
+
+	hv_set_simp(simp.as_uint64);
 
 	/* Setup the Synic's event page */
-	siefp.as_uint64 = hv_get_register(HV_REGISTER_SIEFP);
+	hv_get_siefp(siefp.as_uint64);
 	siefp.siefp_enabled = 1;
-	siefp.base_siefp_gpa = virt_to_phys(hv_cpu->synic_event_page)
-		>> HV_HYP_PAGE_SHIFT;
 
-	hv_set_register(HV_REGISTER_SIEFP, siefp.as_uint64);
+	if (hv_isolation_type_snp()) {
+		hv_cpu->synic_event_page =
+			memremap(siefp.base_siefp_gpa << HV_HYP_PAGE_SHIFT,
+				 HV_HYP_PAGE_SIZE, MEMREMAP_WB);
+
+		if (!hv_cpu->synic_event_page)
+			pr_err("Fail to map syinc event page.\n");
+	} else {
+		siefp.base_siefp_gpa = virt_to_phys(hv_cpu->synic_event_page)
+			>> HV_HYP_PAGE_SHIFT;
+	}
+	hv_set_siefp(siefp.as_uint64);
 
 	/* Setup the shared SINT. */
 	if (vmbus_irq != -1)
 		enable_percpu_irq(vmbus_irq, 0);
-	shared_sint.as_uint64 = hv_get_register(HV_REGISTER_SINT0 +
-					VMBUS_MESSAGE_SINT);
+	hv_get_synint_state(VMBUS_MESSAGE_SINT, shared_sint.as_uint64);
 
 	shared_sint.vector = vmbus_interrupt;
 	shared_sint.masked = false;

@@ -233,14 +265,12 @@ void hv_synic_enable_regs(unsigned int cpu)
 #else
 	shared_sint.auto_eoi = 0;
 #endif
-	hv_set_register(HV_REGISTER_SINT0 + VMBUS_MESSAGE_SINT,
-				shared_sint.as_uint64);
+	hv_set_synint_state(VMBUS_MESSAGE_SINT, shared_sint.as_uint64);
 
 	/* Enable the global synic bit */
-	sctrl.as_uint64 = hv_get_register(HV_REGISTER_SCONTROL);
+	hv_get_synic_state(sctrl.as_uint64);
 	sctrl.enable = 1;
-
-	hv_set_register(HV_REGISTER_SCONTROL, sctrl.as_uint64);
+	hv_set_synic_state(sctrl.as_uint64);
 }
 
 int hv_synic_init(unsigned int cpu)

@@ -257,37 +287,50 @@ int hv_synic_init(unsigned int cpu)
  */
 void hv_synic_disable_regs(unsigned int cpu)
 {
+	struct hv_per_cpu_context *hv_cpu
+		= per_cpu_ptr(hv_context.cpu_context, cpu);
 	union hv_synic_sint shared_sint;
 	union hv_synic_simp simp;
 	union hv_synic_siefp siefp;
 	union hv_synic_scontrol sctrl;
 
-	shared_sint.as_uint64 = hv_get_register(HV_REGISTER_SINT0 +
-					VMBUS_MESSAGE_SINT);
-
+	hv_get_synint_state(VMBUS_MESSAGE_SINT, shared_sint.as_uint64);
 	shared_sint.masked = 1;
+	hv_set_synint_state(VMBUS_MESSAGE_SINT, shared_sint.as_uint64);
+
 
 	/* Need to correctly cleanup in the case of SMP!!! */
 	/* Disable the interrupt */
-	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);
+	/*
+	 * In Isolation VM, sim and sief pages are allocated by
+	 * paravisor. These pages also will be used by kdump
+	 * kernel. So just reset enable bit here and keep page
+	 * addresses.
+	 */
 	simp.simp_enabled = 0;
-	simp.base_simp_gpa = 0;
+	if (hv_isolation_type_snp())
+		memunmap(hv_cpu->synic_message_page);
+	else
+		simp.base_simp_gpa = 0;
 
-	hv_set_register(HV_REGISTER_SIMP, simp.as_uint64);
+	hv_set_simp(simp.as_uint64);
 
-	siefp.as_uint64 = hv_get_register(HV_REGISTER_SIEFP);
+	hv_get_siefp(siefp.as_uint64);
 	siefp.siefp_enabled = 0;
-	siefp.base_siefp_gpa = 0;
 
-	hv_set_register(HV_REGISTER_SIEFP, siefp.as_uint64);
+	if (hv_isolation_type_snp())
+		memunmap(hv_cpu->synic_event_page);
+	else
+		siefp.base_siefp_gpa = 0;
+
+	hv_set_siefp(siefp.as_uint64);
 
 	/* Disable the global synic bit */
-	sctrl.as_uint64 = hv_get_register(HV_REGISTER_SCONTROL);
+	hv_get_synic_state(sctrl.as_uint64);
 	sctrl.enable = 0;
-	hv_set_register(HV_REGISTER_SCONTROL, sctrl.as_uint64);
+	hv_set_synic_state(sctrl.as_uint64);
 
 	if (vmbus_irq != -1)
 		disable_percpu_irq(vmbus_irq);

@@ -23,9 +23,16 @@
 #include <linux/bitops.h>
 #include <linux/cpumask.h>
 #include <linux/nmi.h>
+#include <asm/svm.h>
+#include <asm/sev.h>
 #include <asm/ptrace.h>
+#include <asm/mshyperv.h>
 #include <asm/hyperv-tlfs.h>
 
+union hv_ghcb {
+	struct ghcb ghcb;
+} __packed __aligned(PAGE_SIZE);
+
 struct ms_hyperv_info {
 	u32 features;
 	u32 priv_high;

@@ -45,7 +52,7 @@ struct ms_hyperv_info {
 			u32 Reserved12 : 20;
 		};
 	};
-	void  __percpu **ghcb_base;
+	union hv_ghcb __percpu **ghcb_base;
 	u64 shared_gpa_boundary;
 };
 extern struct ms_hyperv_info ms_hyperv;

@@ -55,6 +62,7 @@ extern void  __percpu  **hyperv_pcpu_output_arg;
 
 extern u64 hv_do_hypercall(u64 control, void *inputaddr, void *outputaddr);
 extern u64 hv_do_fast_hypercall8(u16 control, u64 input8);
+extern bool hv_isolation_type_snp(void);
 
 /* Helper functions that provide a consistent pattern for checking Hyper-V hypercall status. */
 static inline int hv_result(u64 status)

@@ -149,7 +157,7 @@ static inline void vmbus_signal_eom(struct hv_message *msg, u32 old_msg_type)
 		 * possibly deliver another msg from the
 		 * hypervisor
 		 */
-		hv_set_register(HV_REGISTER_EOM, 0);
+		hv_signal_eom();
 	}
 }
 

@@ -15,6 +15,48 @@
 #include <asm/io.h>
 #include <asm/mshyperv.h>
 
+u64 hv_ghcb_hypercall(u64 control, void *input, void *output, u32 input_size)
+{
+	union hv_ghcb *hv_ghcb;
+	void **ghcb_base;
+	unsigned long flags;
+
+	if (!ms_hyperv.ghcb_base)
+		return -EFAULT;
+
+	WARN_ON(in_nmi());
+
+	local_irq_save(flags);
+	ghcb_base = (void **)this_cpu_ptr(ms_hyperv.ghcb_base);
+	hv_ghcb = (union hv_ghcb *)*ghcb_base;
+	if (!hv_ghcb) {
+		local_irq_restore(flags);
+		return -EFAULT;
+	}
+
+	memset(hv_ghcb, 0x00, HV_HYP_PAGE_SIZE);
+	hv_ghcb->ghcb.protocol_version = 1;
+	hv_ghcb->ghcb.ghcb_usage = 1;
+
+	hv_ghcb->hypercall.outputgpa = (u64)output;
+	hv_ghcb->hypercall.hypercallinput.asuint64 = 0;
+	hv_ghcb->hypercall.hypercallinput.callcode = control;
+
+	if (input_size)
+		memcpy(hv_ghcb->hypercall.hypercalldata, input, input_size);
+
+	VMGEXIT();
+
+	hv_ghcb->ghcb.ghcb_usage = 0xffffffff;
+	memset(hv_ghcb->ghcb.save.valid_bitmap, 0,
+	       sizeof(hv_ghcb->ghcb.save.valid_bitmap));
+
+	local_irq_restore(flags);
+
+	return hv_ghcb->hypercall.hypercalloutput.callstatus;
+}
+EXPORT_SYMBOL_GPL(hv_ghcb_hypercall);
+
 void hv_ghcb_msr_write(u64 msr, u64 value)
 {
 	union hv_ghcb *hv_ghcb;