Merge tag 'hyperv-next-signed-20211102' of...

Merge tag 'hyperv-next-signed-20211102' of git://git.kernel.org/pub/scm/linux/kernel/git/hyperv/linux

Pull hyperv updates from Wei Liu:

 - Initial patch set for Hyper-V isolation VM support (Tianyu Lan)

 - Fix a warning on preemption (Vitaly Kuznetsov)

 - A bunch of misc cleanup patches

* tag 'hyperv-next-signed-20211102' of git://git.kernel.org/pub/scm/linux/kernel/git/hyperv/linux:
  x86/hyperv: Protect set_hv_tscchange_cb() against getting preempted
  Drivers: hv : vmbus: Adding NULL pointer check
  x86/hyperv: Remove duplicate include
  x86/hyperv: Remove duplicated include in hv_init
  Drivers: hv: vmbus: Remove unused code to check for subchannels
  Drivers: hv: vmbus: Initialize VMbus ring buffer for Isolation VM
  Drivers: hv: vmbus: Add SNP support for VMbus channel initiate message
  x86/hyperv: Add ghcb hvcall support for SNP VM
  x86/hyperv: Add Write/Read MSR registers via ghcb page
  Drivers: hv: vmbus: Mark vmbus ring buffer visible to host in Isolation VM
  x86/hyperv: Add new hvcall guest address host visibility support
  x86/hyperv: Initialize shared memory boundary in the Isolation VM.
  x86/hyperv: Initialize GHCB page in Isolation VM

arch/x86/hyperv/Makefile

 # 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

arch/x86/hyperv/hv_init.c

@@ -36,12 +36,42 @@ EXPORT_SYMBOL_GPL(hv_current_partition_id);
 void *hv_hypercall_pg;
 EXPORT_SYMBOL_GPL(hv_hypercall_pg);
 
+union hv_ghcb __percpu **hv_ghcb_pg;
+
 /* Storage to save the hypercall page temporarily for hibernation */
 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 (!hv_isolation_type_snp())
+		return 0;
+
+	if (!hv_ghcb_pg)
+		return -EINVAL;
+
+	/*
+	 * GHCB page is allocated by paravisor. The address
+	 * returned by MSR_AMD64_SEV_ES_GHCB is above shared
+	 * memory boundary and map it here.
+	 */
+	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(hv_ghcb_pg);
+	*ghcb_base = ghcb_va;
+
+	return 0;
+}
+
 static int hv_cpu_init(unsigned int cpu)
 {
 	union hv_vp_assist_msr_contents msr = { 0 };
@@ -85,7 +115,7 @@ static int hv_cpu_init(unsigned int cpu)
 		}
 	}
 
-	return 0;
+	return hyperv_init_ghcb();
 }
 
 static void (*hv_reenlightenment_cb)(void);
@@ -139,7 +169,6 @@ void set_hv_tscchange_cb(void (*cb)(void))
 	struct hv_reenlightenment_control re_ctrl = {
 		.vector = HYPERV_REENLIGHTENMENT_VECTOR,
 		.enabled = 1,
-		.target_vp = hv_vp_index[smp_processor_id()]
 	};
 	struct hv_tsc_emulation_control emu_ctrl = {.enabled = 1};
 
@@ -153,8 +182,12 @@ void set_hv_tscchange_cb(void (*cb)(void))
 	/* Make sure callback is registered before we write to MSRs */
 	wmb();
 
+	re_ctrl.target_vp = hv_vp_index[get_cpu()];
+
 	wrmsrl(HV_X64_MSR_REENLIGHTENMENT_CONTROL, *((u64 *)&re_ctrl));
 	wrmsrl(HV_X64_MSR_TSC_EMULATION_CONTROL, *((u64 *)&emu_ctrl));
+
+	put_cpu();
 }
 EXPORT_SYMBOL_GPL(set_hv_tscchange_cb);
 
@@ -177,6 +210,14 @@ static int hv_cpu_die(unsigned int cpu)
 {
 	struct hv_reenlightenment_control re_ctrl;
 	unsigned int new_cpu;
+	void **ghcb_va;
+
+	if (hv_ghcb_pg) {
+		ghcb_va = (void **)this_cpu_ptr(hv_ghcb_pg);
+		if (*ghcb_va)
+			memunmap(*ghcb_va);
+		*ghcb_va = NULL;
+	}
 
 	hv_common_cpu_die(cpu);
 
@@ -366,10 +407,16 @@ void __init hyperv_init(void)
 		goto common_free;
 	}
 
+	if (hv_isolation_type_snp()) {
+		hv_ghcb_pg = alloc_percpu(union hv_ghcb *);
+		if (!hv_ghcb_pg)
+			goto free_vp_assist_page;
+	}
+
 	cpuhp = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN, "x86/hyperv_init:online",
 				  hv_cpu_init, hv_cpu_die);
 	if (cpuhp < 0)
-		goto free_vp_assist_page;
+		goto free_ghcb_page;
 
 	/*
 	 * Setup the hypercall page and enable hypercalls.
@@ -379,14 +426,15 @@ void __init hyperv_init(void)
 	guest_id = generate_guest_id(0, LINUX_VERSION_CODE, 0);
 	wrmsrl(HV_X64_MSR_GUEST_OS_ID, guest_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);
+
 	hv_hypercall_pg = __vmalloc_node_range(PAGE_SIZE, 1, VMALLOC_START,
 			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;
 
 	rdmsrl(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64);
 	hypercall_msr.enable = 1;
@@ -456,8 +504,12 @@ 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);
+	hv_ghcb_msr_write(HV_X64_MSR_GUEST_OS_ID, 0);
 	cpuhp_remove_state(cpuhp);
+free_ghcb_page:
+	free_percpu(hv_ghcb_pg);
 free_vp_assist_page:
 	kfree(hv_vp_assist_page);
 	hv_vp_assist_page = NULL;
@@ -476,6 +528,7 @@ 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,
@@ -546,16 +599,3 @@ 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;
-}

arch/x86/hyperv/ivm.c

+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Hyper-V Isolation VM interface with paravisor and hypervisor
+ *
+ * Author:
+ *  Tianyu Lan <Tianyu.Lan@microsoft.com>
+ */
+
+#include <linux/bitfield.h>
+#include <linux/hyperv.h>
+#include <linux/types.h>
+#include <linux/slab.h>
+#include <asm/svm.h>
+#include <asm/sev.h>
+#include <asm/io.h>
+#include <asm/mshyperv.h>
+#include <asm/hypervisor.h>
+
+#ifdef CONFIG_AMD_MEM_ENCRYPT
+
+#define GHCB_USAGE_HYPERV_CALL	1
+
+union hv_ghcb {
+	struct ghcb ghcb;
+	struct {
+		u64 hypercalldata[509];
+		u64 outputgpa;
+		union {
+			union {
+				struct {
+					u32 callcode        : 16;
+					u32 isfast          : 1;
+					u32 reserved1       : 14;
+					u32 isnested        : 1;
+					u32 countofelements : 12;
+					u32 reserved2       : 4;
+					u32 repstartindex   : 12;
+					u32 reserved3       : 4;
+				};
+				u64 asuint64;
+			} hypercallinput;
+			union {
+				struct {
+					u16 callstatus;
+					u16 reserved1;
+					u32 elementsprocessed : 12;
+					u32 reserved2         : 20;
+				};
+				u64 asunit64;
+			} hypercalloutput;
+		};
+		u64 reserved2;
+	} hypercall;
+} __packed __aligned(HV_HYP_PAGE_SIZE);
+
+u64 hv_ghcb_hypercall(u64 control, void *input, void *output, u32 input_size)
+{
+	union hv_ghcb *hv_ghcb;
+	void **ghcb_base;
+	unsigned long flags;
+	u64 status;
+
+	if (!hv_ghcb_pg)
+		return -EFAULT;
+
+	WARN_ON(in_nmi());
+
+	local_irq_save(flags);
+	ghcb_base = (void **)this_cpu_ptr(hv_ghcb_pg);
+	hv_ghcb = (union hv_ghcb *)*ghcb_base;
+	if (!hv_ghcb) {
+		local_irq_restore(flags);
+		return -EFAULT;
+	}
+
+	hv_ghcb->ghcb.protocol_version = GHCB_PROTOCOL_MAX;
+	hv_ghcb->ghcb.ghcb_usage = GHCB_USAGE_HYPERV_CALL;
+
+	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));
+
+	status = hv_ghcb->hypercall.hypercalloutput.callstatus;
+
+	local_irq_restore(flags);
+
+	return status;
+}
+
+void hv_ghcb_msr_write(u64 msr, u64 value)
+{
+	union hv_ghcb *hv_ghcb;
+	void **ghcb_base;
+	unsigned long flags;
+	struct es_em_ctxt ctxt;
+
+	if (!hv_ghcb_pg)
+		return;
+
+	WARN_ON(in_nmi());
+
+	local_irq_save(flags);
+	ghcb_base = (void **)this_cpu_ptr(hv_ghcb_pg);
+	hv_ghcb = (union hv_ghcb *)*ghcb_base;
+	if (!hv_ghcb) {
+		local_irq_restore(flags);
+		return;
+	}
+
+	ghcb_set_rcx(&hv_ghcb->ghcb, msr);
+	ghcb_set_rax(&hv_ghcb->ghcb, lower_32_bits(value));
+	ghcb_set_rdx(&hv_ghcb->ghcb, upper_32_bits(value));
+
+	if (sev_es_ghcb_hv_call(&hv_ghcb->ghcb, false, &ctxt,
+				SVM_EXIT_MSR, 1, 0))
+		pr_warn("Fail to write msr via ghcb %llx.\n", msr);
+
+	local_irq_restore(flags);
+}
+EXPORT_SYMBOL_GPL(hv_ghcb_msr_write);
+
+void hv_ghcb_msr_read(u64 msr, u64 *value)
+{
+	union hv_ghcb *hv_ghcb;
+	void **ghcb_base;
+	unsigned long flags;
+	struct es_em_ctxt ctxt;
+
+	/* Check size of union hv_ghcb here. */
+	BUILD_BUG_ON(sizeof(union hv_ghcb) != HV_HYP_PAGE_SIZE);
+
+	if (!hv_ghcb_pg)
+		return;
+
+	WARN_ON(in_nmi());
+
+	local_irq_save(flags);
+	ghcb_base = (void **)this_cpu_ptr(hv_ghcb_pg);
+	hv_ghcb = (union hv_ghcb *)*ghcb_base;
+	if (!hv_ghcb) {
+		local_irq_restore(flags);
+		return;
+	}
+
+	ghcb_set_rcx(&hv_ghcb->ghcb, msr);
+	if (sev_es_ghcb_hv_call(&hv_ghcb->ghcb, false, &ctxt,
+				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);
+}
+EXPORT_SYMBOL_GPL(hv_ghcb_msr_read);
+#endif
+
+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)
+{
+	if (!cpu_feature_enabled(X86_FEATURE_HYPERVISOR))
+		return false;
+
+	if (!hypervisor_is_type(X86_HYPER_MS_HYPERV))
+		return false;
+
+	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);
+}
+
+/*
+ * hv_mark_gpa_visibility - Set pages visible to host via hvcall.
+ *
+ * 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.
+ */
+static int hv_mark_gpa_visibility(u16 count, const u64 pfn[],
+			   enum hv_mem_host_visibility 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_result_success(hv_status))
+		return 0;
+	else
+		return -EFAULT;
+}
+
+/*
+ * 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.
+ */
+int hv_set_mem_host_visibility(unsigned long kbuffer, int pagecount, bool visible)
+{
+	enum hv_mem_host_visibility visibility = visible ?
+			VMBUS_PAGE_VISIBLE_READ_WRITE : VMBUS_PAGE_NOT_VISIBLE;
+	u64 *pfn_array;
+	int ret = 0;
+	int i, pfn;
+
+	if (!hv_is_isolation_supported() || !hv_hypercall_pg)
+		return 0;
+
+	pfn_array = kmalloc(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((void *)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);
+			if (ret)
+				goto err_free_pfn_array;
+			pfn = 0;
+		}
+	}
+
+ err_free_pfn_array:
+	kfree(pfn_array);
+	return ret;
+}

arch/x86/include/asm/hyperv-tlfs.h

@@ -276,6 +276,23 @@ 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 memory host visibility */
+enum hv_mem_host_visibility {
+	VMBUS_PAGE_NOT_VISIBLE		= 0,
+	VMBUS_PAGE_VISIBLE_READ_ONLY	= 1,
+	VMBUS_PAGE_VISIBLE_READ_WRITE	= 3
+};
+
+/* HvCallModifySparseGpaPageHostVisibility hypercall */
+#define HV_MAX_MODIFY_GPA_REP_COUNT	((PAGE_SIZE / sizeof(u64)) - 2)
+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;
+
 /*
  * Declare the MSR used to setup pages used to communicate with the hypervisor.
  */

arch/x86/include/asm/mshyperv.h

@@ -11,23 +11,14 @@
 #include <asm/paravirt.h>
 #include <asm/mshyperv.h>
 
+union hv_ghcb;
+
+DECLARE_STATIC_KEY_FALSE(isolation_type_snp);
+
 typedef int (*hyperv_fill_flush_list_func)(
 		struct hv_guest_mapping_flush_list *flush,
 		void *data);
 
-static inline void hv_set_register(unsigned int reg, u64 value)
-{
-	wrmsrl(reg, value);
-}
-
-static inline u64 hv_get_register(unsigned int reg)
-{
-	u64 value;
-
-	rdmsrl(reg, value);
-	return value;
-}
-
 #define hv_get_raw_timer() rdtsc_ordered()
 
 void hyperv_vector_handler(struct pt_regs *regs);
@@ -39,6 +30,8 @@ extern void *hv_hypercall_pg;
 
 extern u64 hv_current_partition_id;
 
+extern union hv_ghcb  __percpu **hv_ghcb_pg;
+
 int hv_call_deposit_pages(int node, u64 partition_id, u32 num_pages);
 int hv_call_add_logical_proc(int node, u32 lp_index, u32 acpi_id);
 int hv_call_create_vp(int node, u64 partition_id, u32 vp_index, u32 flags);
@@ -188,6 +181,50 @@ 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_set_mem_host_visibility(unsigned long addr, int numpages, bool visible);
+
+#ifdef CONFIG_AMD_MEM_ENCRYPT
+void hv_ghcb_msr_write(u64 msr, u64 value);
+void hv_ghcb_msr_read(u64 msr, u64 *value);
+#else
+static inline void hv_ghcb_msr_write(u64 msr, u64 value) {}
+static inline void hv_ghcb_msr_read(u64 msr, u64 *value) {}
+#endif
+
+extern bool hv_isolation_type_snp(void);
+
+static inline bool hv_is_synic_reg(unsigned int reg)
+{
+	if ((reg >= HV_REGISTER_SCONTROL) &&
+	    (reg <= HV_REGISTER_SINT15))
+		return true;
+	return false;
+}
+
+static inline u64 hv_get_register(unsigned int reg)
+{
+	u64 value;
+
+	if (hv_is_synic_reg(reg) && hv_isolation_type_snp())
+		hv_ghcb_msr_read(reg, &value);
+	else
+		rdmsrl(reg, value);
+	return value;
+}
+
+static inline void hv_set_register(unsigned int reg, u64 value)
+{
+	if (hv_is_synic_reg(reg) && hv_isolation_type_snp()) {
+		hv_ghcb_msr_write(reg, value);
+
+		/* Write proxy bit via wrmsl instruction */
+		if (reg >= HV_REGISTER_SINT0 &&
+		    reg <= HV_REGISTER_SINT15)
+			wrmsrl(reg, value | 1 << 20);
+	} else {
+		wrmsrl(reg, value);
+	}
+}
 
 #else /* CONFIG_HYPERV */
 static inline void hyperv_init(void) {}
@@ -205,6 +242,13 @@ static inline int hyperv_flush_guest_mapping_range(u64 as,
 {
 	return -1;
 }
+static inline void hv_set_register(unsigned int reg, u64 value) { }
+static inline u64 hv_get_register(unsigned int reg) { return 0; }
+static inline int hv_set_mem_host_visibility(unsigned long addr, int numpages,
+					     bool visible)
+{
+	return -1;
+}
 #endif /* CONFIG_HYPERV */
 
 

arch/x86/kernel/cpu/mshyperv.c

@@ -313,9 +313,14 @@ 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 =
+			BIT_ULL(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);
+
+		if (hv_get_isolation_type() == HV_ISOLATION_TYPE_SNP)
+			static_branch_enable(&isolation_type_snp);
 	}
 
 	if (hv_max_functions_eax >= HYPERV_CPUID_NESTED_FEATURES) {

arch/x86/mm/pat/set_memory.c

@@ -30,6 +30,8 @@
 #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"
 
@@ -1981,15 +1983,15 @@ int set_memory_global(unsigned long addr, int numpages)
 				    __pgprot(_PAGE_GLOBAL), 0);
 }
 
-static int __set_memory_enc_dec(unsigned long addr, int numpages, bool enc)
+/*
+ * __set_memory_enc_pgtable() is used for the hypervisors that get
+ * informed about "encryption" status via page tables.
+ */
+static int __set_memory_enc_pgtable(unsigned long addr, int numpages, bool enc)
 {
 	struct cpa_data cpa;
 	int ret;
 
-	/* Nothing to do if memory encryption is not active */
-	if (!cc_platform_has(CC_ATTR_MEM_ENCRYPT))
-		return 0;
-
 	/* Should not be working on unaligned addresses */
 	if (WARN_ONCE(addr & ~PAGE_MASK, "misaligned address: %#lx\n", addr))
 		addr &= PAGE_MASK;
@@ -2024,6 +2026,17 @@ static int __set_memory_enc_dec(unsigned long addr, int numpages, bool enc)
 	return ret;
 }
 
+static int __set_memory_enc_dec(unsigned long addr, int numpages, bool enc)
+{
+	if (hv_is_isolation_supported())
+		return hv_set_mem_host_visibility(addr, numpages, !enc);
+
+	if (cc_platform_has(CC_ATTR_MEM_ENCRYPT))
+		return __set_memory_enc_pgtable(addr, numpages, enc);
+
+	return 0;
+}
+
 int set_memory_encrypted(unsigned long addr, int numpages)
 {
 	return __set_memory_enc_dec(addr, numpages, true);

drivers/hv/Kconfig

@@ -8,6 +8,7 @@ config HYPERV
 		|| (ARM64 && !CPU_BIG_ENDIAN))
 	select PARAVIRT
 	select X86_HV_CALLBACK_VECTOR if X86
+	select VMAP_PFN
 	help
 	  Select this option to run Linux as a Hyper-V client operating
 	  system.

drivers/hv/channel.c

@@ -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>
 
@@ -456,7 +457,7 @@ static int create_gpadl_header(enum hv_gpadl_type type, void *kbuffer,
 static int __vmbus_establish_gpadl(struct vmbus_channel *channel,
 				   enum hv_gpadl_type type, void *kbuffer,
 				   u32 size, u32 send_offset,
-				   u32 *gpadl_handle)
+				   struct vmbus_gpadl *gpadl)
 {
 	struct vmbus_channel_gpadl_header *gpadlmsg;
 	struct vmbus_channel_gpadl_body *gpadl_body;
@@ -474,6 +475,15 @@ static int __vmbus_establish_gpadl(struct vmbus_channel *channel,
 	if (ret)
 		return ret;
 
+	ret = set_memory_decrypted((unsigned long)kbuffer,
+				   PFN_UP(size));
+	if (ret) {
+		dev_warn(&channel->device_obj->device,
+			 "Failed to set host visibility for new GPADL %d.\n",
+			 ret);
+		return ret;
+	}
+
 	init_completion(&msginfo->waitevent);
 	msginfo->waiting_channel = channel;
 
@@ -537,7 +547,10 @@ static int __vmbus_establish_gpadl(struct vmbus_channel *channel,
 	}
 
 	/* At this point, we received the gpadl created msg */
-	*gpadl_handle = gpadlmsg->gpadl;
+	gpadl->gpadl_handle = gpadlmsg->gpadl;
+	gpadl->buffer = kbuffer;
+	gpadl->size = size;
+
 
 cleanup:
 	spin_lock_irqsave(&vmbus_connection.channelmsg_lock, flags);
@@ -549,6 +562,11 @@ static int __vmbus_establish_gpadl(struct vmbus_channel *channel,
 	}
 
 	kfree(msginfo);
+
+	if (ret)
+		set_memory_encrypted((unsigned long)kbuffer,
+				     PFN_UP(size));
+
 	return ret;
 }
 
@@ -561,10 +579,10 @@ static int __vmbus_establish_gpadl(struct vmbus_channel *channel,
  * @gpadl_handle: some funky thing
  */
 int vmbus_establish_gpadl(struct vmbus_channel *channel, void *kbuffer,
-			  u32 size, u32 *gpadl_handle)
+			  u32 size, struct vmbus_gpadl *gpadl)
 {
 	return __vmbus_establish_gpadl(channel, HV_GPADL_BUFFER, kbuffer, size,
-				       0U, gpadl_handle);
+				       0U, gpadl);
 }
 EXPORT_SYMBOL_GPL(vmbus_establish_gpadl);
 
@@ -665,17 +683,8 @@ static int __vmbus_open(struct vmbus_channel *newchannel,
 	if (!newchannel->max_pkt_size)
 		newchannel->max_pkt_size = VMBUS_DEFAULT_MAX_PKT_SIZE;
 
-	err = hv_ringbuffer_init(&newchannel->outbound, page, send_pages, 0);
-	if (err)
-		goto error_clean_ring;
-
-	err = hv_ringbuffer_init(&newchannel->inbound, &page[send_pages],
-				 recv_pages, newchannel->max_pkt_size);
-	if (err)
-		goto error_clean_ring;
-
 	/* Establish the gpadl for the ring buffer */
-	newchannel->ringbuffer_gpadlhandle = 0;
+	newchannel->ringbuffer_gpadlhandle.gpadl_handle = 0;
 
 	err = __vmbus_establish_gpadl(newchannel, HV_GPADL_RING,
 				      page_address(newchannel->ringbuffer_page),
@@ -685,6 +694,16 @@ static int __vmbus_open(struct vmbus_channel *newchannel,
 	if (err)
 		goto error_clean_ring;
 
+	err = hv_ringbuffer_init(&newchannel->outbound,
+				 page, send_pages, 0);
+	if (err)
+		goto error_free_gpadl;
+
+	err = hv_ringbuffer_init(&newchannel->inbound, &page[send_pages],
+				 recv_pages, newchannel->max_pkt_size);
+	if (err)
+		goto error_free_gpadl;
+
 	/* Create and init the channel open message */
 	open_info = kzalloc(sizeof(*open_info) +
 			   sizeof(struct vmbus_channel_open_channel),
@@ -701,7 +720,8 @@ static int __vmbus_open(struct vmbus_channel *newchannel,
 	open_msg->header.msgtype = CHANNELMSG_OPENCHANNEL;
 	open_msg->openid = newchannel->offermsg.child_relid;
 	open_msg->child_relid = newchannel->offermsg.child_relid;
-	open_msg->ringbuffer_gpadlhandle = newchannel->ringbuffer_gpadlhandle;
+	open_msg->ringbuffer_gpadlhandle
+		= newchannel->ringbuffer_gpadlhandle.gpadl_handle;
 	/*
 	 * The unit of ->downstream_ringbuffer_pageoffset is HV_HYP_PAGE and
 	 * the unit of ->ringbuffer_send_offset (i.e. send_pages) is PAGE, so
@@ -759,8 +779,7 @@ static int __vmbus_open(struct vmbus_channel *newchannel,
 error_free_info:
 	kfree(open_info);
 error_free_gpadl:
-	vmbus_teardown_gpadl(newchannel, newchannel->ringbuffer_gpadlhandle);
-	newchannel->ringbuffer_gpadlhandle = 0;
+	vmbus_teardown_gpadl(newchannel, &newchannel->ringbuffer_gpadlhandle);
 error_clean_ring:
 	hv_ringbuffer_cleanup(&newchannel->outbound);
 	hv_ringbuffer_cleanup(&newchannel->inbound);
@@ -806,7 +825,7 @@ EXPORT_SYMBOL_GPL(vmbus_open);
 /*
  * vmbus_teardown_gpadl -Teardown the specified GPADL handle
  */
-int vmbus_teardown_gpadl(struct vmbus_channel *channel, u32 gpadl_handle)
+int vmbus_teardown_gpadl(struct vmbus_channel *channel, struct vmbus_gpadl *gpadl)
 {
 	struct vmbus_channel_gpadl_teardown *msg;
 	struct vmbus_channel_msginfo *info;
@@ -825,7 +844,7 @@ int vmbus_teardown_gpadl(struct vmbus_channel *channel, u32 gpadl_handle)
 
 	msg->header.msgtype = CHANNELMSG_GPADL_TEARDOWN;
 	msg->child_relid = channel->offermsg.child_relid;
-	msg->gpadl = gpadl_handle;
+	msg->gpadl = gpadl->gpadl_handle;
 
 	spin_lock_irqsave(&vmbus_connection.channelmsg_lock, flags);
 	list_add_tail(&info->msglistentry,
@@ -845,6 +864,8 @@ int vmbus_teardown_gpadl(struct vmbus_channel *channel, u32 gpadl_handle)
 
 	wait_for_completion(&info->waitevent);
 
+	gpadl->gpadl_handle = 0;
+
 post_msg_err:
 	/*
 	 * If the channel has been rescinded;
@@ -859,6 +880,12 @@ int vmbus_teardown_gpadl(struct vmbus_channel *channel, u32 gpadl_handle)
 	spin_unlock_irqrestore(&vmbus_connection.channelmsg_lock, flags);
 
 	kfree(info);
+
+	ret = set_memory_encrypted((unsigned long)gpadl->buffer,
+				   PFN_UP(gpadl->size));
+	if (ret)
+		pr_warn("Fail to set mem host visibility in GPADL teardown %d.\n", ret);
+
 	return ret;
 }
 EXPORT_SYMBOL_GPL(vmbus_teardown_gpadl);
@@ -933,9 +960,8 @@ static int vmbus_close_internal(struct vmbus_channel *channel)
 	}
 
 	/* Tear down the gpadl for the channel's ring buffer */
-	else if (channel->ringbuffer_gpadlhandle) {
-		ret = vmbus_teardown_gpadl(channel,
-					   channel->ringbuffer_gpadlhandle);
+	else if (channel->ringbuffer_gpadlhandle.gpadl_handle) {
+		ret = vmbus_teardown_gpadl(channel, &channel->ringbuffer_gpadlhandle);
 		if (ret) {
 			pr_err("Close failed: teardown gpadl return %d\n", ret);
 			/*
@@ -943,8 +969,6 @@ static int vmbus_close_internal(struct vmbus_channel *channel)
 			 * it is perhaps better to leak memory.
 			 */
 		}
-
-		channel->ringbuffer_gpadlhandle = 0;
 	}
 
 	if (!ret)

drivers/hv/channel_mgmt.c

@@ -1581,21 +1581,6 @@ int vmbus_request_offers(void)
 	return ret;
 }
 
-static void invoke_sc_cb(struct vmbus_channel *primary_channel)
-{
-	struct list_head *cur, *tmp;
-	struct vmbus_channel *cur_channel;
-
-	if (primary_channel->sc_creation_callback == NULL)
-		return;
-
-	list_for_each_safe(cur, tmp, &primary_channel->sc_list) {
-		cur_channel = list_entry(cur, struct vmbus_channel, sc_list);
-
-		primary_channel->sc_creation_callback(cur_channel);
-	}
-}
-
 void vmbus_set_sc_create_callback(struct vmbus_channel *primary_channel,
 				void (*sc_cr_cb)(struct vmbus_channel *new_sc))
 {
@@ -1603,25 +1588,6 @@ void vmbus_set_sc_create_callback(struct vmbus_channel *primary_channel,
 }
 EXPORT_SYMBOL_GPL(vmbus_set_sc_create_callback);
 
-bool vmbus_are_subchannels_present(struct vmbus_channel *primary)
-{
-	bool ret;
-
-	ret = !list_empty(&primary->sc_list);
-
-	if (ret) {
-		/*
-		 * Invoke the callback on sub-channel creation.
-		 * This will present a uniform interface to the
-		 * clients.
-		 */
-		invoke_sc_cb(primary);
-	}
-
-	return ret;
-}
-EXPORT_SYMBOL_GPL(vmbus_are_subchannels_present);
-
 void vmbus_set_chn_rescind_callback(struct vmbus_channel *channel,
 		void (*chn_rescind_cb)(struct vmbus_channel *))
 {

drivers/hv/connection.c

@@ -19,6 +19,8 @@
 #include <linux/vmalloc.h>
 #include <linux/hyperv.h>
 #include <linux/export.h>
+#include <linux/io.h>
+#include <linux/set_memory.h>
 #include <asm/mshyperv.h>
 
 #include "hyperv_vmbus.h"
@@ -102,8 +104,9 @@ int vmbus_negotiate_version(struct vmbus_channel_msginfo *msginfo, u32 version)
 		vmbus_connection.msg_conn_id = VMBUS_MESSAGE_CONNECTION_ID;
 	}
 
-	msg->monitor_page1 = virt_to_phys(vmbus_connection.monitor_pages[0]);
-	msg->monitor_page2 = virt_to_phys(vmbus_connection.monitor_pages[1]);
+	msg->monitor_page1 = vmbus_connection.monitor_pages_pa[0];
+	msg->monitor_page2 = vmbus_connection.monitor_pages_pa[1];
+
 	msg->target_vcpu = hv_cpu_number_to_vp_number(VMBUS_CONNECT_CPU);
 
 	/*
@@ -216,6 +219,65 @@ int vmbus_connect(void)
 		goto cleanup;
 	}
 
+	vmbus_connection.monitor_pages_original[0]
+		= vmbus_connection.monitor_pages[0];
+	vmbus_connection.monitor_pages_original[1]
+		= vmbus_connection.monitor_pages[1];
+	vmbus_connection.monitor_pages_pa[0]
+		= virt_to_phys(vmbus_connection.monitor_pages[0]);
+	vmbus_connection.monitor_pages_pa[1]
+		= virt_to_phys(vmbus_connection.monitor_pages[1]);
+
+	if (hv_is_isolation_supported()) {
+		ret = set_memory_decrypted((unsigned long)
+					   vmbus_connection.monitor_pages[0],
+					   1);
+		ret |= set_memory_decrypted((unsigned long)
+					    vmbus_connection.monitor_pages[1],
+					    1);
+		if (ret)
+			goto cleanup;
+
+		/*
+		 * Isolation VM with AMD SNP needs to access monitor page via
+		 * address space above shared gpa boundary.
+		 */
+		if (hv_isolation_type_snp()) {
+			vmbus_connection.monitor_pages_pa[0] +=
+				ms_hyperv.shared_gpa_boundary;
+			vmbus_connection.monitor_pages_pa[1] +=
+				ms_hyperv.shared_gpa_boundary;
+
+			vmbus_connection.monitor_pages[0]
+				= memremap(vmbus_connection.monitor_pages_pa[0],
+					   HV_HYP_PAGE_SIZE,
+					   MEMREMAP_WB);
+			if (!vmbus_connection.monitor_pages[0]) {
+				ret = -ENOMEM;
+				goto cleanup;
+			}
+
+			vmbus_connection.monitor_pages[1]
+				= memremap(vmbus_connection.monitor_pages_pa[1],
+					   HV_HYP_PAGE_SIZE,
+					   MEMREMAP_WB);
+			if (!vmbus_connection.monitor_pages[1]) {
+				ret = -ENOMEM;
+				goto cleanup;
+			}
+		}
+
+		/*
+		 * Set memory host visibility hvcall smears memory
+		 * and so zero monitor pages here.
+		 */
+		memset(vmbus_connection.monitor_pages[0], 0x00,
+		       HV_HYP_PAGE_SIZE);
+		memset(vmbus_connection.monitor_pages[1], 0x00,
+		       HV_HYP_PAGE_SIZE);
+
+	}
+
 	msginfo = kzalloc(sizeof(*msginfo) +
 			  sizeof(struct vmbus_channel_initiate_contact),
 			  GFP_KERNEL);
@@ -303,10 +365,31 @@ void vmbus_disconnect(void)
 		vmbus_connection.int_page = NULL;
 	}
 
-	hv_free_hyperv_page((unsigned long)vmbus_connection.monitor_pages[0]);
-	hv_free_hyperv_page((unsigned long)vmbus_connection.monitor_pages[1]);
-	vmbus_connection.monitor_pages[0] = NULL;
-	vmbus_connection.monitor_pages[1] = NULL;
+	if (hv_is_isolation_supported()) {
+		/*
+		 * memunmap() checks input address is ioremap address or not
+		 * inside. It doesn't unmap any thing in the non-SNP CVM and
+		 * so not check CVM type here.
+		 */
+		memunmap(vmbus_connection.monitor_pages[0]);
+		memunmap(vmbus_connection.monitor_pages[1]);
+
+		set_memory_encrypted((unsigned long)
+			vmbus_connection.monitor_pages_original[0],
+			1);
+		set_memory_encrypted((unsigned long)
+			vmbus_connection.monitor_pages_original[1],
+			1);
+	}
+
+	hv_free_hyperv_page((unsigned long)
+		vmbus_connection.monitor_pages_original[0]);
+	hv_free_hyperv_page((unsigned long)
+		vmbus_connection.monitor_pages_original[1]);
+	vmbus_connection.monitor_pages_original[0] =
+		vmbus_connection.monitor_pages[0] = NULL;
+	vmbus_connection.monitor_pages_original[1] =
+		vmbus_connection.monitor_pages[1] = NULL;
 }
 
 /*
@@ -447,6 +530,10 @@ void vmbus_set_event(struct vmbus_channel *channel)
 
 	++channel->sig_events;
 
-	hv_do_fast_hypercall8(HVCALL_SIGNAL_EVENT, channel->sig_event);
+	if (hv_isolation_type_snp())
+		hv_ghcb_hypercall(HVCALL_SIGNAL_EVENT, &channel->sig_event,
+				NULL, sizeof(channel->sig_event));
+	else
+		hv_do_fast_hypercall8(HVCALL_SIGNAL_EVENT, channel->sig_event);
 }
 EXPORT_SYMBOL_GPL(vmbus_set_event);

drivers/hv/hv.c

@@ -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>
@@ -97,7 +98,13 @@ int hv_post_message(union hv_connection_id connection_id,
 	aligned_msg->payload_size = payload_size;
 	memcpy((void *)aligned_msg->payload, payload, payload_size);
 
-	status = hv_do_hypercall(HVCALL_POST_MESSAGE, aligned_msg, NULL);
+	if (hv_isolation_type_snp())
+		status = hv_ghcb_hypercall(HVCALL_POST_MESSAGE,
+				(void *)aligned_msg, NULL,
+				sizeof(*aligned_msg));
+	else
+		status = hv_do_hypercall(HVCALL_POST_MESSAGE,
+				aligned_msg, NULL);
 
 	/* Preemption must remain disabled until after the hypercall
 	 * so some other thread can't get scheduled onto this cpu and
@@ -136,17 +143,24 @@ 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);
@@ -201,16 +215,35 @@ void hv_synic_enable_regs(unsigned int cpu)
 	/* Setup the Synic's message page */
 	simp.as_uint64 = hv_get_register(HV_REGISTER_SIMP);
 	simp.simp_enabled = 1;
-	simp.base_simp_gpa = virt_to_phys(hv_cpu->synic_message_page)
-		>> HV_HYP_PAGE_SHIFT;
+
+	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_register(HV_REGISTER_SIMP, simp.as_uint64);
 
 	/* Setup the Synic's event page */
 	siefp.as_uint64 = hv_get_register(HV_REGISTER_SIEFP);
 	siefp.siefp_enabled = 1;
-	siefp.base_siefp_gpa = virt_to_phys(hv_cpu->synic_event_page)
-		>> HV_HYP_PAGE_SHIFT;
+
+	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_register(HV_REGISTER_SIEFP, siefp.as_uint64);
 
@@ -257,6 +290,8 @@ 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;
@@ -273,14 +308,27 @@ void hv_synic_disable_regs(unsigned int cpu)
 				shared_sint.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);
 
 	siefp.as_uint64 = hv_get_register(HV_REGISTER_SIEFP);
 	siefp.siefp_enabled = 0;
-	siefp.base_siefp_gpa = 0;
+
+	if (hv_isolation_type_snp())
+		memunmap(hv_cpu->synic_event_page);
+	else
+		siefp.base_siefp_gpa = 0;
 
 	hv_set_register(HV_REGISTER_SIEFP, siefp.as_uint64);
 

drivers/hv/hv_common.c

@@ -249,6 +249,12 @@ bool __weak hv_is_isolation_supported(void)
 }
 EXPORT_SYMBOL_GPL(hv_is_isolation_supported);
 
+bool __weak hv_isolation_type_snp(void)
+{
+	return false;
+}
+EXPORT_SYMBOL_GPL(hv_isolation_type_snp);
+
 void __weak hv_setup_vmbus_handler(void (*handler)(void))
 {
 }
@@ -283,3 +289,9 @@ void __weak hyperv_cleanup(void)
 {
 }
 EXPORT_SYMBOL_GPL(hyperv_cleanup);
+
+u64 __weak hv_ghcb_hypercall(u64 control, void *input, void *output, u32 input_size)
+{
+	return HV_STATUS_INVALID_PARAMETER;
+}
+EXPORT_SYMBOL_GPL(hv_ghcb_hypercall);

drivers/hv/hyperv_vmbus.h

@@ -241,6 +241,8 @@ struct vmbus_connection {
 	 * is child->parent notification
 	 */
 	struct hv_monitor_page *monitor_pages[2];
+	void *monitor_pages_original[2];
+	phys_addr_t monitor_pages_pa[2];
 	struct list_head chn_msg_list;
 	spinlock_t channelmsg_lock;
 

drivers/hv/ring_buffer.c

@@ -17,6 +17,8 @@
 #include <linux/vmalloc.h>
 #include <linux/slab.h>
 #include <linux/prefetch.h>
+#include <linux/io.h>
+#include <asm/mshyperv.h>
 
 #include "hyperv_vmbus.h"
 
@@ -183,8 +185,10 @@ void hv_ringbuffer_pre_init(struct vmbus_channel *channel)
 int hv_ringbuffer_init(struct hv_ring_buffer_info *ring_info,
 		       struct page *pages, u32 page_cnt, u32 max_pkt_size)
 {
-	int i;
 	struct page **pages_wraparound;
+	unsigned long *pfns_wraparound;
+	u64 pfn;
+	int i;
 
 	BUILD_BUG_ON((sizeof(struct hv_ring_buffer) != PAGE_SIZE));
 
@@ -192,23 +196,50 @@ int hv_ringbuffer_init(struct hv_ring_buffer_info *ring_info,
 	 * First page holds struct hv_ring_buffer, do wraparound mapping for
 	 * the rest.
 	 */
-	pages_wraparound = kcalloc(page_cnt * 2 - 1, sizeof(struct page *),
-				   GFP_KERNEL);
-	if (!pages_wraparound)
-		return -ENOMEM;
+	if (hv_isolation_type_snp()) {
+		pfn = page_to_pfn(pages) +
+			PFN_DOWN(ms_hyperv.shared_gpa_boundary);
+
+		pfns_wraparound = kcalloc(page_cnt * 2 - 1,
+			sizeof(unsigned long), GFP_KERNEL);
+		if (!pfns_wraparound)
+			return -ENOMEM;
 
-	pages_wraparound[0] = pages;
-	for (i = 0; i < 2 * (page_cnt - 1); i++)
-		pages_wraparound[i + 1] = &pages[i % (page_cnt - 1) + 1];
+		pfns_wraparound[0] = pfn;
+		for (i = 0; i < 2 * (page_cnt - 1); i++)
+			pfns_wraparound[i + 1] = pfn + i % (page_cnt - 1) + 1;
 
-	ring_info->ring_buffer = (struct hv_ring_buffer *)
-		vmap(pages_wraparound, page_cnt * 2 - 1, VM_MAP, PAGE_KERNEL);
+		ring_info->ring_buffer = (struct hv_ring_buffer *)
+			vmap_pfn(pfns_wraparound, page_cnt * 2 - 1,
+				 PAGE_KERNEL);
+		kfree(pfns_wraparound);
 
-	kfree(pages_wraparound);
+		if (!ring_info->ring_buffer)
+			return -ENOMEM;
 
+		/* Zero ring buffer after setting memory host visibility. */
+		memset(ring_info->ring_buffer, 0x00, PAGE_SIZE * page_cnt);
+	} else {
+		pages_wraparound = kcalloc(page_cnt * 2 - 1,
+					   sizeof(struct page *),
+					   GFP_KERNEL);
+		if (!pages_wraparound)
+			return -ENOMEM;
+
+		pages_wraparound[0] = pages;
+		for (i = 0; i < 2 * (page_cnt - 1); i++)
+			pages_wraparound[i + 1] =
+				&pages[i % (page_cnt - 1) + 1];
+
+		ring_info->ring_buffer = (struct hv_ring_buffer *)
+			vmap(pages_wraparound, page_cnt * 2 - 1, VM_MAP,
+				PAGE_KERNEL);
+
+		kfree(pages_wraparound);
+		if (!ring_info->ring_buffer)
+			return -ENOMEM;
+	}
 
-	if (!ring_info->ring_buffer)
-		return -ENOMEM;
 
 	ring_info->ring_buffer->read_index =
 		ring_info->ring_buffer->write_index = 0;

drivers/net/hyperv/hyperv_net.h

@@ -1075,14 +1075,15 @@ struct netvsc_device {
 	/* Receive buffer allocated by us but manages by NetVSP */
 	void *recv_buf;
 	u32 recv_buf_size; /* allocated bytes */
-	u32 recv_buf_gpadl_handle;
+	struct vmbus_gpadl recv_buf_gpadl_handle;
 	u32 recv_section_cnt;
 	u32 recv_section_size;
 	u32 recv_completion_cnt;
 
 	/* Send buffer allocated by us */
 	void *send_buf;
-	u32 send_buf_gpadl_handle;
+	u32 send_buf_size;
+	struct vmbus_gpadl send_buf_gpadl_handle;
 	u32 send_section_cnt;
 	u32 send_section_size;
 	unsigned long *send_section_map;

drivers/net/hyperv/netvsc.c

@@ -278,9 +278,9 @@ static void netvsc_teardown_recv_gpadl(struct hv_device *device,
 {
 	int ret;
 
-	if (net_device->recv_buf_gpadl_handle) {
+	if (net_device->recv_buf_gpadl_handle.gpadl_handle) {
 		ret = vmbus_teardown_gpadl(device->channel,
-					   net_device->recv_buf_gpadl_handle);
+					   &net_device->recv_buf_gpadl_handle);
 
 		/* If we failed here, we might as well return and have a leak
 		 * rather than continue and a bugchk
@@ -290,7 +290,6 @@ static void netvsc_teardown_recv_gpadl(struct hv_device *device,
 				   "unable to teardown receive buffer's gpadl\n");
 			return;
 		}
-		net_device->recv_buf_gpadl_handle = 0;
 	}
 }
 
@@ -300,9 +299,9 @@ static void netvsc_teardown_send_gpadl(struct hv_device *device,
 {
 	int ret;
 
-	if (net_device->send_buf_gpadl_handle) {
+	if (net_device->send_buf_gpadl_handle.gpadl_handle) {
 		ret = vmbus_teardown_gpadl(device->channel,
-					   net_device->send_buf_gpadl_handle);
+					   &net_device->send_buf_gpadl_handle);
 
 		/* If we failed here, we might as well return and have a leak
 		 * rather than continue and a bugchk
@@ -312,7 +311,6 @@ static void netvsc_teardown_send_gpadl(struct hv_device *device,
 				   "unable to teardown send buffer's gpadl\n");
 			return;
 		}
-		net_device->send_buf_gpadl_handle = 0;
 	}
 }
 
@@ -380,7 +378,7 @@ static int netvsc_init_buf(struct hv_device *device,
 	memset(init_packet, 0, sizeof(struct nvsp_message));
 	init_packet->hdr.msg_type = NVSP_MSG1_TYPE_SEND_RECV_BUF;
 	init_packet->msg.v1_msg.send_recv_buf.
-		gpadl_handle = net_device->recv_buf_gpadl_handle;
+		gpadl_handle = net_device->recv_buf_gpadl_handle.gpadl_handle;
 	init_packet->msg.v1_msg.
 		send_recv_buf.id = NETVSC_RECEIVE_BUFFER_ID;
 
@@ -463,6 +461,7 @@ static int netvsc_init_buf(struct hv_device *device,
 		ret = -ENOMEM;
 		goto cleanup;
 	}
+	net_device->send_buf_size = buf_size;
 
 	/* Establish the gpadl handle for this buffer on this
 	 * channel.  Note: This call uses the vmbus connection rather
@@ -482,7 +481,7 @@ static int netvsc_init_buf(struct hv_device *device,
 	memset(init_packet, 0, sizeof(struct nvsp_message));
 	init_packet->hdr.msg_type = NVSP_MSG1_TYPE_SEND_SEND_BUF;
 	init_packet->msg.v1_msg.send_send_buf.gpadl_handle =
-		net_device->send_buf_gpadl_handle;
+		net_device->send_buf_gpadl_handle.gpadl_handle;
 	init_packet->msg.v1_msg.send_send_buf.id = NETVSC_SEND_BUFFER_ID;
 
 	trace_nvsp_send(ndev, init_packet);

drivers/uio/uio_hv_generic.c

@@ -58,11 +58,11 @@ struct hv_uio_private_data {
 	atomic_t refcnt;
 
 	void	*recv_buf;
-	u32	recv_gpadl;
+	struct vmbus_gpadl recv_gpadl;
 	char	recv_name[32];	/* "recv_4294967295" */
 
 	void	*send_buf;
-	u32	send_gpadl;
+	struct vmbus_gpadl send_gpadl;
 	char	send_name[32];
 };
 
@@ -179,15 +179,13 @@ hv_uio_new_channel(struct vmbus_channel *new_sc)
 static void
 hv_uio_cleanup(struct hv_device *dev, struct hv_uio_private_data *pdata)
 {
-	if (pdata->send_gpadl) {
-		vmbus_teardown_gpadl(dev->channel, pdata->send_gpadl);
-		pdata->send_gpadl = 0;
+	if (pdata->send_gpadl.gpadl_handle) {
+		vmbus_teardown_gpadl(dev->channel, &pdata->send_gpadl);
 		vfree(pdata->send_buf);
 	}
 
-	if (pdata->recv_gpadl) {
-		vmbus_teardown_gpadl(dev->channel, pdata->recv_gpadl);
-		pdata->recv_gpadl = 0;
+	if (pdata->recv_gpadl.gpadl_handle) {
+		vmbus_teardown_gpadl(dev->channel, &pdata->recv_gpadl);
 		vfree(pdata->recv_buf);
 	}
 }
@@ -303,7 +301,7 @@ hv_uio_probe(struct hv_device *dev,
 
 	/* put Global Physical Address Label in name */
 	snprintf(pdata->recv_name, sizeof(pdata->recv_name),
-		 "recv:%u", pdata->recv_gpadl);
+		 "recv:%u", pdata->recv_gpadl.gpadl_handle);
 	pdata->info.mem[RECV_BUF_MAP].name = pdata->recv_name;
 	pdata->info.mem[RECV_BUF_MAP].addr
 		= (uintptr_t)pdata->recv_buf;
@@ -324,7 +322,7 @@ hv_uio_probe(struct hv_device *dev,
 	}
 
 	snprintf(pdata->send_name, sizeof(pdata->send_name),
-		 "send:%u", pdata->send_gpadl);
+		 "send:%u", pdata->send_gpadl.gpadl_handle);
 	pdata->info.mem[SEND_BUF_MAP].name = pdata->send_name;
 	pdata->info.mem[SEND_BUF_MAP].addr
 		= (uintptr_t)pdata->send_buf;

include/asm-generic/hyperv-tlfs.h

@@ -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

include/asm-generic/mshyperv.h

@@ -35,7 +35,17 @@ 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 reserved1 : 1;
+			u32 shared_gpa_boundary_active : 1;
+			u32 shared_gpa_boundary_bits : 6;
+			u32 reserved2 : 20;
+		};
+	};
+	u64 shared_gpa_boundary;
 };
 extern struct ms_hyperv_info ms_hyperv;
 
@@ -44,6 +54,7 @@ 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)
@@ -254,12 +265,19 @@ 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);
+u64 hv_ghcb_hypercall(u64 control, void *input, void *output, u32 input_size);
 void hyperv_cleanup(void);
 bool hv_query_ext_cap(u64 cap_query);
 #else /* CONFIG_HYPERV */
 static inline bool hv_is_hyperv_initialized(void) { return false; }
 static inline bool hv_is_hibernation_supported(void) { return false; }
 static inline void hyperv_cleanup(void) {}
+static inline bool hv_is_isolation_supported(void) { return false; }
+static inline enum hv_isolation_type hv_get_isolation_type(void)
+{
+	return HV_ISOLATION_TYPE_NONE;
+}
 #endif /* CONFIG_HYPERV */
 
 #endif

include/linux/hyperv.h

@@ -803,6 +803,12 @@ struct vmbus_device {
 
 #define VMBUS_DEFAULT_MAX_PKT_SIZE 4096
 
+struct vmbus_gpadl {
+	u32 gpadl_handle;
+	u32 size;
+	void *buffer;
+};
+
 struct vmbus_channel {
 	struct list_head listentry;
 
@@ -822,7 +828,7 @@ struct vmbus_channel {
 	bool rescind_ref; /* got rescind msg, got channel reference */
 	struct completion rescind_event;
 
-	u32 ringbuffer_gpadlhandle;
+	struct vmbus_gpadl ringbuffer_gpadlhandle;
 
 	/* Allocated memory for ring buffer */
 	struct page *ringbuffer_page;
@@ -1100,19 +1106,6 @@ void vmbus_set_sc_create_callback(struct vmbus_channel *primary_channel,
 void vmbus_set_chn_rescind_callback(struct vmbus_channel *channel,
 		void (*chn_rescind_cb)(struct vmbus_channel *));
 
-/*
- * Check if sub-channels have already been offerred. This API will be useful
- * when the driver is unloaded after establishing sub-channels. In this case,
- * when the driver is re-loaded, the driver would have to check if the
- * subchannels have already been established before attempting to request
- * the creation of sub-channels.
- * This function returns TRUE to indicate that subchannels have already been
- * created.
- * This function should be invoked after setting the callback function for
- * sub-channel creation.
- */
-bool vmbus_are_subchannels_present(struct vmbus_channel *primary);
-
 /* The format must be the same as struct vmdata_gpa_direct */
 struct vmbus_channel_packet_page_buffer {
 	u16 type;
@@ -1192,10 +1185,10 @@ extern int vmbus_sendpacket_mpb_desc(struct vmbus_channel *channel,
 extern int vmbus_establish_gpadl(struct vmbus_channel *channel,
 				      void *kbuffer,
 				      u32 size,
-				      u32 *gpadl_handle);
+				      struct vmbus_gpadl *gpadl);
 
 extern int vmbus_teardown_gpadl(struct vmbus_channel *channel,
-				     u32 gpadl_handle);
+				     struct vmbus_gpadl *gpadl);
 
 void vmbus_reset_channel_cb(struct vmbus_channel *channel);