Merge tag 'hyperv-next-signed-20210216' of...

Merge tag 'hyperv-next-signed-20210216' of git://git.kernel.org/pub/scm/linux/kernel/git/hyperv/linux

Pull Hyper-V updates from Wei Liu:

 - VMBus hardening patches from Andrea Parri and Andres Beltran.

 - Patches to make Linux boot as the root partition on Microsoft
   Hypervisor from Wei Liu.

 - One patch to add a new sysfs interface to support hibernation on
   Hyper-V from Dexuan Cui.

 - Two miscellaneous clean-up patches from Colin and Gustavo.

* tag 'hyperv-next-signed-20210216' of git://git.kernel.org/pub/scm/linux/kernel/git/hyperv/linux: (31 commits)
  Revert "Drivers: hv: vmbus: Copy packets sent by Hyper-V out of the ring buffer"
  iommu/hyperv: setup an IO-APIC IRQ remapping domain for root partition
  x86/hyperv: implement an MSI domain for root partition
  asm-generic/hyperv: import data structures for mapping device interrupts
  asm-generic/hyperv: introduce hv_device_id and auxiliary structures
  asm-generic/hyperv: update hv_interrupt_entry
  asm-generic/hyperv: update hv_msi_entry
  x86/hyperv: implement and use hv_smp_prepare_cpus
  x86/hyperv: provide a bunch of helper functions
  ACPI / NUMA: add a stub function for node_to_pxm()
  x86/hyperv: handling hypercall page setup for root
  x86/hyperv: extract partition ID from Microsoft Hypervisor if necessary
  x86/hyperv: allocate output arg pages if required
  clocksource/hyperv: use MSR-based access if running as root
  Drivers: hv: vmbus: skip VMBus initialization if Linux is root
  x86/hyperv: detect if Linux is the root partition
  asm-generic/hyperv: change HV_CPU_POWER_MANAGEMENT to HV_CPU_MANAGEMENT
  hv: hyperv.h: Replace one-element array with flexible-array in struct icmsg_negotiate
  hv_netvsc: Restrict configurations on isolated guests
  Drivers: hv: vmbus: Enforce 'VMBus version >= 5.2' on isolated guests
  ...

Documentation/ABI/stable/sysfs-bus-vmbus

+What:		/sys/bus/vmbus/hibernation
+Date:		Jan 2021
+KernelVersion:	5.12
+Contact:	Dexuan Cui <decui@microsoft.com>
+Description:	Whether the host supports hibernation for the VM.
+Users:		Daemon that sets up swap partition/file for hibernation.
+
 What:		/sys/bus/vmbus/devices/<UUID>/id
 Date:		Jul 2009
 KernelVersion:	2.6.31

arch/x86/hyperv/Makefile

 # SPDX-License-Identifier: GPL-2.0-only
-obj-y			:= hv_init.o mmu.o nested.o
-obj-$(CONFIG_X86_64)	+= hv_apic.o
+obj-y			:= hv_init.o mmu.o nested.o irqdomain.o
+obj-$(CONFIG_X86_64)	+= hv_apic.o hv_proc.o
 
 ifdef CONFIG_X86_64
 obj-$(CONFIG_PARAVIRT_SPINLOCKS)	+= hv_spinlock.o

arch/x86/hyperv/hv_init.c

@@ -10,6 +10,7 @@
 #include <linux/acpi.h>
 #include <linux/efi.h>
 #include <linux/types.h>
+#include <linux/bitfield.h>
 #include <asm/apic.h>
 #include <asm/desc.h>
 #include <asm/hypervisor.h>
@@ -26,8 +27,11 @@
 #include <linux/cpuhotplug.h>
 #include <linux/syscore_ops.h>
 #include <clocksource/hyperv_timer.h>
+#include <linux/highmem.h>
 
 int hyperv_init_cpuhp;
+u64 hv_current_partition_id = ~0ull;
+EXPORT_SYMBOL_GPL(hv_current_partition_id);
 
 void *hv_hypercall_pg;
 EXPORT_SYMBOL_GPL(hv_hypercall_pg);
@@ -44,6 +48,9 @@ EXPORT_SYMBOL_GPL(hv_vp_assist_page);
 void  __percpu **hyperv_pcpu_input_arg;
 EXPORT_SYMBOL_GPL(hyperv_pcpu_input_arg);
 
+void  __percpu **hyperv_pcpu_output_arg;
+EXPORT_SYMBOL_GPL(hyperv_pcpu_output_arg);
+
 u32 hv_max_vp_index;
 EXPORT_SYMBOL_GPL(hv_max_vp_index);
 
@@ -76,12 +83,19 @@ static int hv_cpu_init(unsigned int cpu)
 	void **input_arg;
 	struct page *pg;
 
-	input_arg = (void **)this_cpu_ptr(hyperv_pcpu_input_arg);
 	/* hv_cpu_init() can be called with IRQs disabled from hv_resume() */
-	pg = alloc_page(irqs_disabled() ? GFP_ATOMIC : GFP_KERNEL);
+	pg = alloc_pages(irqs_disabled() ? GFP_ATOMIC : GFP_KERNEL, hv_root_partition ? 1 : 0);
 	if (unlikely(!pg))
 		return -ENOMEM;
+
+	input_arg = (void **)this_cpu_ptr(hyperv_pcpu_input_arg);
 	*input_arg = page_address(pg);
+	if (hv_root_partition) {
+		void **output_arg;
+
+		output_arg = (void **)this_cpu_ptr(hyperv_pcpu_output_arg);
+		*output_arg = page_address(pg + 1);
+	}
 
 	hv_get_vp_index(msr_vp_index);
 
@@ -208,14 +222,23 @@ static int hv_cpu_die(unsigned int cpu)
 	unsigned int new_cpu;
 	unsigned long flags;
 	void **input_arg;
-	void *input_pg = NULL;
+	void *pg;
 
 	local_irq_save(flags);
 	input_arg = (void **)this_cpu_ptr(hyperv_pcpu_input_arg);
-	input_pg = *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;
+	}
+
 	local_irq_restore(flags);
-	free_page((unsigned long)input_pg);
+
+	free_pages((unsigned long)pg, hv_root_partition ? 1 : 0);
 
 	if (hv_vp_assist_page && hv_vp_assist_page[cpu])
 		wrmsrl(HV_X64_MSR_VP_ASSIST_PAGE, 0);
@@ -264,6 +287,9 @@ static int hv_suspend(void)
 	union hv_x64_msr_hypercall_contents hypercall_msr;
 	int ret;
 
+	if (hv_root_partition)
+		return -EPERM;
+
 	/*
 	 * Reset the hypercall page as it is going to be invalidated
 	 * accross hibernation. Setting hv_hypercall_pg to NULL ensures
@@ -334,6 +360,24 @@ static void __init hv_stimer_setup_percpu_clockev(void)
 		old_setup_percpu_clockev();
 }
 
+static void __init hv_get_partition_id(void)
+{
+	struct hv_get_partition_id *output_page;
+	u64 status;
+	unsigned long flags;
+
+	local_irq_save(flags);
+	output_page = *this_cpu_ptr(hyperv_pcpu_output_arg);
+	status = hv_do_hypercall(HVCALL_GET_PARTITION_ID, NULL, output_page);
+	if ((status & HV_HYPERCALL_RESULT_MASK) != HV_STATUS_SUCCESS) {
+		/* No point in proceeding if this failed */
+		pr_err("Failed to get partition ID: %lld\n", status);
+		BUG();
+	}
+	hv_current_partition_id = output_page->partition_id;
+	local_irq_restore(flags);
+}
+
 /*
  * This function is to be invoked early in the boot sequence after the
  * hypervisor has been detected.
@@ -368,6 +412,12 @@ void __init hyperv_init(void)
 
 	BUG_ON(hyperv_pcpu_input_arg == NULL);
 
+	/* Allocate the per-CPU state for output arg for root */
+	if (hv_root_partition) {
+		hyperv_pcpu_output_arg = alloc_percpu(void *);
+		BUG_ON(hyperv_pcpu_output_arg == NULL);
+	}
+
 	/* Allocate percpu VP index */
 	hv_vp_index = kmalloc_array(num_possible_cpus(), sizeof(*hv_vp_index),
 				    GFP_KERNEL);
@@ -408,8 +458,35 @@ void __init hyperv_init(void)
 
 	rdmsrl(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64);
 	hypercall_msr.enable = 1;
-	hypercall_msr.guest_physical_address = vmalloc_to_pfn(hv_hypercall_pg);
-	wrmsrl(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64);
+
+	if (hv_root_partition) {
+		struct page *pg;
+		void *src, *dst;
+
+		/*
+		 * For the root partition, the hypervisor will set up its
+		 * hypercall page. The hypervisor guarantees it will not show
+		 * up in the root's address space. The root can't change the
+		 * location of the hypercall page.
+		 *
+		 * Order is important here. We must enable the hypercall page
+		 * so it is populated with code, then copy the code to an
+		 * executable page.
+		 */
+		wrmsrl(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64);
+
+		pg = vmalloc_to_page(hv_hypercall_pg);
+		dst = kmap(pg);
+		src = memremap(hypercall_msr.guest_physical_address << PAGE_SHIFT, PAGE_SIZE,
+				MEMREMAP_WB);
+		BUG_ON(!(src && dst));
+		memcpy(dst, src, HV_HYP_PAGE_SIZE);
+		memunmap(src);
+		kunmap(pg);
+	} else {
+		hypercall_msr.guest_physical_address = vmalloc_to_pfn(hv_hypercall_pg);
+		wrmsrl(HV_X64_MSR_HYPERCALL, hypercall_msr.as_uint64);
+	}
 
 	/*
 	 * hyperv_init() is called before LAPIC is initialized: see
@@ -428,6 +505,21 @@ void __init hyperv_init(void)
 	register_syscore_ops(&hv_syscore_ops);
 
 	hyperv_init_cpuhp = cpuhp;
+
+	if (cpuid_ebx(HYPERV_CPUID_FEATURES) & HV_ACCESS_PARTITION_ID)
+		hv_get_partition_id();
+
+	BUG_ON(hv_root_partition && hv_current_partition_id == ~0ull);
+
+#ifdef CONFIG_PCI_MSI
+	/*
+	 * If we're running as root, we want to create our own PCI MSI domain.
+	 * We can't set this in hv_pci_init because that would be too late.
+	 */
+	if (hv_root_partition)
+		x86_init.irqs.create_pci_msi_domain = hv_create_pci_msi_domain;
+#endif
+
 	return;
 
 remove_cpuhp_state:
@@ -552,6 +644,20 @@ EXPORT_SYMBOL_GPL(hv_is_hyperv_initialized);
 
 bool hv_is_hibernation_supported(void)
 {
-	return acpi_sleep_state_supported(ACPI_STATE_S4);
+	return !hv_root_partition && acpi_sleep_state_supported(ACPI_STATE_S4);
 }
 EXPORT_SYMBOL_GPL(hv_is_hibernation_supported);
+
+enum hv_isolation_type hv_get_isolation_type(void)
+{
+	if (!(ms_hyperv.features_b & 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;
+}
+EXPORT_SYMBOL_GPL(hv_is_isolation_supported);

arch/x86/hyperv/hv_proc.c

+// SPDX-License-Identifier: GPL-2.0
+#include <linux/types.h>
+#include <linux/version.h>
+#include <linux/vmalloc.h>
+#include <linux/mm.h>
+#include <linux/clockchips.h>
+#include <linux/acpi.h>
+#include <linux/hyperv.h>
+#include <linux/slab.h>
+#include <linux/cpuhotplug.h>
+#include <linux/minmax.h>
+#include <asm/hypervisor.h>
+#include <asm/mshyperv.h>
+#include <asm/apic.h>
+
+#include <asm/trace/hyperv.h>
+
+/*
+ * See struct hv_deposit_memory. The first u64 is partition ID, the rest
+ * are GPAs.
+ */
+#define HV_DEPOSIT_MAX (HV_HYP_PAGE_SIZE / sizeof(u64) - 1)
+
+/* Deposits exact number of pages. Must be called with interrupts enabled.  */
+int hv_call_deposit_pages(int node, u64 partition_id, u32 num_pages)
+{
+	struct page **pages, *page;
+	int *counts;
+	int num_allocations;
+	int i, j, page_count;
+	int order;
+	u64 status;
+	int ret;
+	u64 base_pfn;
+	struct hv_deposit_memory *input_page;
+	unsigned long flags;
+
+	if (num_pages > HV_DEPOSIT_MAX)
+		return -E2BIG;
+	if (!num_pages)
+		return 0;
+
+	/* One buffer for page pointers and counts */
+	page = alloc_page(GFP_KERNEL);
+	if (!page)
+		return -ENOMEM;
+	pages = page_address(page);
+
+	counts = kcalloc(HV_DEPOSIT_MAX, sizeof(int), GFP_KERNEL);
+	if (!counts) {
+		free_page((unsigned long)pages);
+		return -ENOMEM;
+	}
+
+	/* Allocate all the pages before disabling interrupts */
+	i = 0;
+
+	while (num_pages) {
+		/* Find highest order we can actually allocate */
+		order = 31 - __builtin_clz(num_pages);
+
+		while (1) {
+			pages[i] = alloc_pages_node(node, GFP_KERNEL, order);
+			if (pages[i])
+				break;
+			if (!order) {
+				ret = -ENOMEM;
+				num_allocations = i;
+				goto err_free_allocations;
+			}
+			--order;
+		}
+
+		split_page(pages[i], order);
+		counts[i] = 1 << order;
+		num_pages -= counts[i];
+		i++;
+	}
+	num_allocations = i;
+
+	local_irq_save(flags);
+
+	input_page = *this_cpu_ptr(hyperv_pcpu_input_arg);
+
+	input_page->partition_id = partition_id;
+
+	/* Populate gpa_page_list - these will fit on the input page */
+	for (i = 0, page_count = 0; i < num_allocations; ++i) {
+		base_pfn = page_to_pfn(pages[i]);
+		for (j = 0; j < counts[i]; ++j, ++page_count)
+			input_page->gpa_page_list[page_count] = base_pfn + j;
+	}
+	status = hv_do_rep_hypercall(HVCALL_DEPOSIT_MEMORY,
+				     page_count, 0, input_page, NULL);
+	local_irq_restore(flags);
+
+	if ((status & HV_HYPERCALL_RESULT_MASK) != HV_STATUS_SUCCESS) {
+		pr_err("Failed to deposit pages: %lld\n", status);
+		ret = status;
+		goto err_free_allocations;
+	}
+
+	ret = 0;
+	goto free_buf;
+
+err_free_allocations:
+	for (i = 0; i < num_allocations; ++i) {
+		base_pfn = page_to_pfn(pages[i]);
+		for (j = 0; j < counts[i]; ++j)
+			__free_page(pfn_to_page(base_pfn + j));
+	}
+
+free_buf:
+	free_page((unsigned long)pages);
+	kfree(counts);
+	return ret;
+}
+
+int hv_call_add_logical_proc(int node, u32 lp_index, u32 apic_id)
+{
+	struct hv_add_logical_processor_in *input;
+	struct hv_add_logical_processor_out *output;
+	u64 status;
+	unsigned long flags;
+	int ret = 0;
+	int pxm = node_to_pxm(node);
+
+	/*
+	 * When adding a logical processor, the hypervisor may return
+	 * HV_STATUS_INSUFFICIENT_MEMORY. When that happens, we deposit more
+	 * pages and retry.
+	 */
+	do {
+		local_irq_save(flags);
+
+		input = *this_cpu_ptr(hyperv_pcpu_input_arg);
+		/* We don't do anything with the output right now */
+		output = *this_cpu_ptr(hyperv_pcpu_output_arg);
+
+		input->lp_index = lp_index;
+		input->apic_id = apic_id;
+		input->flags = 0;
+		input->proximity_domain_info.domain_id = pxm;
+		input->proximity_domain_info.flags.reserved = 0;
+		input->proximity_domain_info.flags.proximity_info_valid = 1;
+		input->proximity_domain_info.flags.proximity_preferred = 1;
+		status = hv_do_hypercall(HVCALL_ADD_LOGICAL_PROCESSOR,
+					 input, output);
+		local_irq_restore(flags);
+
+		status &= HV_HYPERCALL_RESULT_MASK;
+
+		if (status != HV_STATUS_INSUFFICIENT_MEMORY) {
+			if (status != HV_STATUS_SUCCESS) {
+				pr_err("%s: cpu %u apic ID %u, %lld\n", __func__,
+				       lp_index, apic_id, status);
+				ret = status;
+			}
+			break;
+		}
+		ret = hv_call_deposit_pages(node, hv_current_partition_id, 1);
+	} while (!ret);
+
+	return ret;
+}
+
+int hv_call_create_vp(int node, u64 partition_id, u32 vp_index, u32 flags)
+{
+	struct hv_create_vp *input;
+	u64 status;
+	unsigned long irq_flags;
+	int ret = 0;
+	int pxm = node_to_pxm(node);
+
+	/* Root VPs don't seem to need pages deposited */
+	if (partition_id != hv_current_partition_id) {
+		/* The value 90 is empirically determined. It may change. */
+		ret = hv_call_deposit_pages(node, partition_id, 90);
+		if (ret)
+			return ret;
+	}
+
+	do {
+		local_irq_save(irq_flags);
+
+		input = *this_cpu_ptr(hyperv_pcpu_input_arg);
+
+		input->partition_id = partition_id;
+		input->vp_index = vp_index;
+		input->flags = flags;
+		input->subnode_type = HvSubnodeAny;
+		if (node != NUMA_NO_NODE) {
+			input->proximity_domain_info.domain_id = pxm;
+			input->proximity_domain_info.flags.reserved = 0;
+			input->proximity_domain_info.flags.proximity_info_valid = 1;
+			input->proximity_domain_info.flags.proximity_preferred = 1;
+		} else {
+			input->proximity_domain_info.as_uint64 = 0;
+		}
+		status = hv_do_hypercall(HVCALL_CREATE_VP, input, NULL);
+		local_irq_restore(irq_flags);
+
+		status &= HV_HYPERCALL_RESULT_MASK;
+
+		if (status != HV_STATUS_INSUFFICIENT_MEMORY) {
+			if (status != HV_STATUS_SUCCESS) {
+				pr_err("%s: vcpu %u, lp %u, %lld\n", __func__,
+				       vp_index, flags, status);
+				ret = status;
+			}
+			break;
+		}
+		ret = hv_call_deposit_pages(node, partition_id, 1);
+
+	} while (!ret);
+
+	return ret;
+}
+

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

@@ -21,7 +21,9 @@
 #define HYPERV_CPUID_FEATURES			0x40000003
 #define HYPERV_CPUID_ENLIGHTMENT_INFO		0x40000004
 #define HYPERV_CPUID_IMPLEMENT_LIMITS		0x40000005
+#define HYPERV_CPUID_CPU_MANAGEMENT_FEATURES	0x40000007
 #define HYPERV_CPUID_NESTED_FEATURES		0x4000000A
+#define HYPERV_CPUID_ISOLATION_CONFIG		0x4000000C
 
 #define HYPERV_CPUID_VIRT_STACK_INTERFACE	0x40000081
 #define HYPERV_VS_INTERFACE_EAX_SIGNATURE	0x31235356  /* "VS#1" */
@@ -110,6 +112,15 @@
 /* Recommend using enlightened VMCS */
 #define HV_X64_ENLIGHTENED_VMCS_RECOMMENDED		BIT(14)
 
+/*
+ * CPU management features identification.
+ * These are HYPERV_CPUID_CPU_MANAGEMENT_FEATURES.EAX bits.
+ */
+#define HV_X64_START_LOGICAL_PROCESSOR			BIT(0)
+#define HV_X64_CREATE_ROOT_VIRTUAL_PROCESSOR		BIT(1)
+#define HV_X64_PERFORMANCE_COUNTER_SYNC			BIT(2)
+#define HV_X64_RESERVED_IDENTITY_BIT			BIT(31)
+
 /*
  * Virtual processor will never share a physical core with another virtual
  * processor, except for virtual processors that are reported as sibling SMT
@@ -122,6 +133,20 @@
 #define HV_X64_NESTED_GUEST_MAPPING_FLUSH		BIT(18)
 #define HV_X64_NESTED_MSR_BITMAP			BIT(19)
 
+/* HYPERV_CPUID_ISOLATION_CONFIG.EAX bits. */
+#define HV_PARAVISOR_PRESENT				BIT(0)
+
+/* HYPERV_CPUID_ISOLATION_CONFIG.EBX bits. */
+#define HV_ISOLATION_TYPE				GENMASK(3, 0)
+#define HV_SHARED_GPA_BOUNDARY_ACTIVE			BIT(5)
+#define HV_SHARED_GPA_BOUNDARY_BITS			GENMASK(11, 6)
+
+enum hv_isolation_type {
+	HV_ISOLATION_TYPE_NONE	= 0,
+	HV_ISOLATION_TYPE_VBS	= 1,
+	HV_ISOLATION_TYPE_SNP	= 2
+};
+
 /* Hyper-V specific model specific registers (MSRs) */
 
 /* MSR used to identify the guest OS. */
@@ -523,6 +548,19 @@ struct hv_partition_assist_pg {
 	u32 tlb_lock_count;
 };
 
+enum hv_interrupt_type {
+	HV_X64_INTERRUPT_TYPE_FIXED             = 0x0000,
+	HV_X64_INTERRUPT_TYPE_LOWESTPRIORITY    = 0x0001,
+	HV_X64_INTERRUPT_TYPE_SMI               = 0x0002,
+	HV_X64_INTERRUPT_TYPE_REMOTEREAD        = 0x0003,
+	HV_X64_INTERRUPT_TYPE_NMI               = 0x0004,
+	HV_X64_INTERRUPT_TYPE_INIT              = 0x0005,
+	HV_X64_INTERRUPT_TYPE_SIPI              = 0x0006,
+	HV_X64_INTERRUPT_TYPE_EXTINT            = 0x0007,
+	HV_X64_INTERRUPT_TYPE_LOCALINT0         = 0x0008,
+	HV_X64_INTERRUPT_TYPE_LOCALINT1         = 0x0009,
+	HV_X64_INTERRUPT_TYPE_MAXIMUM           = 0x000A,
+};
 
 #include <asm-generic/hyperv-tlfs.h>
 

arch/x86/include/asm/mshyperv.h

@@ -78,6 +78,13 @@ extern int hyperv_init_cpuhp;
 
 extern void *hv_hypercall_pg;
 extern void  __percpu  **hyperv_pcpu_input_arg;
+extern void  __percpu  **hyperv_pcpu_output_arg;
+
+extern u64 hv_current_partition_id;
+
+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);
 
 static inline u64 hv_do_hypercall(u64 control, void *input, void *output)
 {
@@ -239,6 +246,8 @@ int hyperv_fill_flush_guest_mapping_list(
 		struct hv_guest_mapping_flush_list *flush,
 		u64 start_gfn, u64 end_gfn);
 
+extern bool hv_root_partition;
+
 #ifdef CONFIG_X86_64
 void hv_apic_init(void);
 void __init hv_init_spinlocks(void);
@@ -250,10 +259,16 @@ static inline void hv_apic_init(void) {}
 static inline void hv_set_msi_entry_from_desc(union hv_msi_entry *msi_entry,
 					      struct msi_desc *msi_desc)
 {
-	msi_entry->address = msi_desc->msg.address_lo;
-	msi_entry->data = msi_desc->msg.data;
+	msi_entry->address.as_uint32 = msi_desc->msg.address_lo;
+	msi_entry->data.as_uint32 = msi_desc->msg.data;
 }
 
+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);
+
 #else /* CONFIG_HYPERV */
 static inline void hyperv_init(void) {}
 static inline void hyperv_setup_mmu_ops(void) {}

arch/x86/kernel/cpu/mshyperv.c

@@ -31,6 +31,11 @@
 #include <asm/reboot.h>
 #include <asm/nmi.h>
 #include <clocksource/hyperv_timer.h>
+#include <asm/numa.h>
+
+/* Is Linux running as the root partition? */
+bool hv_root_partition;
+EXPORT_SYMBOL_GPL(hv_root_partition);
 
 struct ms_hyperv_info ms_hyperv;
 EXPORT_SYMBOL_GPL(ms_hyperv);
@@ -226,6 +231,32 @@ static void __init hv_smp_prepare_boot_cpu(void)
 	hv_init_spinlocks();
 #endif
 }
+
+static void __init hv_smp_prepare_cpus(unsigned int max_cpus)
+{
+#ifdef CONFIG_X86_64
+	int i;
+	int ret;
+#endif
+
+	native_smp_prepare_cpus(max_cpus);
+
+#ifdef CONFIG_X86_64
+	for_each_present_cpu(i) {
+		if (i == 0)
+			continue;
+		ret = hv_call_add_logical_proc(numa_cpu_node(i), i, cpu_physical_id(i));
+		BUG_ON(ret);
+	}
+
+	for_each_present_cpu(i) {
+		if (i == 0)
+			continue;
+		ret = hv_call_create_vp(numa_cpu_node(i), hv_current_partition_id, i, i);
+		BUG_ON(ret);
+	}
+#endif
+}
 #endif
 
 static void __init ms_hyperv_init_platform(void)
@@ -243,6 +274,7 @@ static void __init ms_hyperv_init_platform(void)
 	 * Extract the features and hints
 	 */
 	ms_hyperv.features = cpuid_eax(HYPERV_CPUID_FEATURES);
+	ms_hyperv.features_b = cpuid_ebx(HYPERV_CPUID_FEATURES);
 	ms_hyperv.misc_features = cpuid_edx(HYPERV_CPUID_FEATURES);
 	ms_hyperv.hints    = cpuid_eax(HYPERV_CPUID_ENLIGHTMENT_INFO);
 
@@ -255,6 +287,22 @@ static void __init ms_hyperv_init_platform(void)
 	pr_debug("Hyper-V: max %u virtual processors, %u logical processors\n",
 		 ms_hyperv.max_vp_index, ms_hyperv.max_lp_index);
 
+	/*
+	 * Check CPU management privilege.
+	 *
+	 * To mirror what Windows does we should extract CPU management
+	 * features and use the ReservedIdentityBit to detect if Linux is the
+	 * root partition. But that requires negotiating CPU management
+	 * interface (a process to be finalized).
+	 *
+	 * For now, use the privilege flag as the indicator for running as
+	 * root.
+	 */
+	if (cpuid_ebx(HYPERV_CPUID_FEATURES) & HV_CPU_MANAGEMENT) {
+		hv_root_partition = true;
+		pr_info("Hyper-V: running as root partition\n");
+	}
+
 	/*
 	 * Extract host information.
 	 */
@@ -277,6 +325,14 @@ static void __init ms_hyperv_init_platform(void)
 		x86_platform.calibrate_cpu = hv_get_tsc_khz;
 	}
 
+	if (ms_hyperv.features_b & HV_ISOLATION) {
+		ms_hyperv.isolation_config_a = cpuid_eax(HYPERV_CPUID_ISOLATION_CONFIG);
+		ms_hyperv.isolation_config_b = cpuid_ebx(HYPERV_CPUID_ISOLATION_CONFIG);
+
+		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 (ms_hyperv.hints & HV_X64_ENLIGHTENED_VMCS_RECOMMENDED) {
 		ms_hyperv.nested_features =
 			cpuid_eax(HYPERV_CPUID_NESTED_FEATURES);
@@ -366,6 +422,8 @@ static void __init ms_hyperv_init_platform(void)
 
 # ifdef CONFIG_SMP
 	smp_ops.smp_prepare_boot_cpu = hv_smp_prepare_boot_cpu;
+	if (hv_root_partition)
+		smp_ops.smp_prepare_cpus = hv_smp_prepare_cpus;
 # endif
 
 	/*

drivers/clocksource/hyperv_timer.c

@@ -426,6 +426,9 @@ static bool __init hv_init_tsc_clocksource(void)
 	if (!(ms_hyperv.features & HV_MSR_REFERENCE_TSC_AVAILABLE))
 		return false;
 
+	if (hv_root_partition)
+		return false;
+
 	hv_read_reference_counter = read_hv_clock_tsc;
 	phys_addr = virt_to_phys(hv_get_tsc_page());
 

drivers/hv/channel.c

@@ -618,7 +618,7 @@ static int __vmbus_open(struct vmbus_channel *newchannel,
 		goto error_clean_ring;
 
 	/* Create and init the channel open message */
-	open_info = kmalloc(sizeof(*open_info) +
+	open_info = kzalloc(sizeof(*open_info) +
 			   sizeof(struct vmbus_channel_open_channel),
 			   GFP_KERNEL);
 	if (!open_info) {
@@ -745,7 +745,7 @@ int vmbus_teardown_gpadl(struct vmbus_channel *channel, u32 gpadl_handle)
 	unsigned long flags;
 	int ret;
 
-	info = kmalloc(sizeof(*info) +
+	info = kzalloc(sizeof(*info) +
 		       sizeof(struct vmbus_channel_gpadl_teardown), GFP_KERNEL);
 	if (!info)
 		return -ENOMEM;

drivers/hv/channel_mgmt.c

@@ -31,101 +31,118 @@ const struct vmbus_device vmbus_devs[] = {
 	{ .dev_type = HV_IDE,
 	  HV_IDE_GUID,
 	  .perf_device = true,
+	  .allowed_in_isolated = false,
 	},
 
 	/* SCSI */
 	{ .dev_type = HV_SCSI,
 	  HV_SCSI_GUID,
 	  .perf_device = true,
+	  .allowed_in_isolated = true,
 	},
 
 	/* Fibre Channel */
 	{ .dev_type = HV_FC,
 	  HV_SYNTHFC_GUID,
 	  .perf_device = true,
+	  .allowed_in_isolated = false,
 	},
 
 	/* Synthetic NIC */
 	{ .dev_type = HV_NIC,
 	  HV_NIC_GUID,
 	  .perf_device = true,
+	  .allowed_in_isolated = true,
 	},
 
 	/* Network Direct */
 	{ .dev_type = HV_ND,
 	  HV_ND_GUID,
 	  .perf_device = true,
+	  .allowed_in_isolated = false,
 	},
 
 	/* PCIE */
 	{ .dev_type = HV_PCIE,
 	  HV_PCIE_GUID,
 	  .perf_device = false,
+	  .allowed_in_isolated = false,
 	},
 
 	/* Synthetic Frame Buffer */
 	{ .dev_type = HV_FB,
 	  HV_SYNTHVID_GUID,
 	  .perf_device = false,
+	  .allowed_in_isolated = false,
 	},
 
 	/* Synthetic Keyboard */
 	{ .dev_type = HV_KBD,
 	  HV_KBD_GUID,
 	  .perf_device = false,
+	  .allowed_in_isolated = false,
 	},
 
 	/* Synthetic MOUSE */
 	{ .dev_type = HV_MOUSE,
 	  HV_MOUSE_GUID,
 	  .perf_device = false,
+	  .allowed_in_isolated = false,
 	},
 
 	/* KVP */
 	{ .dev_type = HV_KVP,
 	  HV_KVP_GUID,
 	  .perf_device = false,
+	  .allowed_in_isolated = false,
 	},
 
 	/* Time Synch */
 	{ .dev_type = HV_TS,
 	  HV_TS_GUID,
 	  .perf_device = false,
+	  .allowed_in_isolated = true,
 	},
 
 	/* Heartbeat */
 	{ .dev_type = HV_HB,
 	  HV_HEART_BEAT_GUID,
 	  .perf_device = false,
+	  .allowed_in_isolated = true,
 	},
 
 	/* Shutdown */
 	{ .dev_type = HV_SHUTDOWN,
 	  HV_SHUTDOWN_GUID,
 	  .perf_device = false,
+	  .allowed_in_isolated = true,
 	},
 
 	/* File copy */
 	{ .dev_type = HV_FCOPY,
 	  HV_FCOPY_GUID,
 	  .perf_device = false,
+	  .allowed_in_isolated = false,
 	},
 
 	/* Backup */
 	{ .dev_type = HV_BACKUP,
 	  HV_VSS_GUID,
 	  .perf_device = false,
+	  .allowed_in_isolated = false,
 	},
 
 	/* Dynamic Memory */
 	{ .dev_type = HV_DM,
 	  HV_DM_GUID,
 	  .perf_device = false,
+	  .allowed_in_isolated = false,
 	},
 
 	/* Unknown GUID */
 	{ .dev_type = HV_UNKNOWN,
 	  .perf_device = false,
+	  .allowed_in_isolated = false,
 	},
 };
 
@@ -190,6 +207,7 @@ static u16 hv_get_dev_type(const struct vmbus_channel *channel)
  * vmbus_prep_negotiate_resp() - Create default response for Negotiate message
  * @icmsghdrp: Pointer to msg header structure
  * @buf: Raw buffer channel data
+ * @buflen: Length of the raw buffer channel data.
  * @fw_version: The framework versions we can support.
  * @fw_vercnt: The size of @fw_version.
  * @srv_version: The service versions we can support.
@@ -202,8 +220,8 @@ static u16 hv_get_dev_type(const struct vmbus_channel *channel)
  * Set up and fill in default negotiate response message.
  * Mainly used by Hyper-V drivers.
  */
-bool vmbus_prep_negotiate_resp(struct icmsg_hdr *icmsghdrp,
-				u8 *buf, const int *fw_version, int fw_vercnt,
+bool vmbus_prep_negotiate_resp(struct icmsg_hdr *icmsghdrp, u8 *buf,
+				u32 buflen, const int *fw_version, int fw_vercnt,
 				const int *srv_version, int srv_vercnt,
 				int *nego_fw_version, int *nego_srv_version)
 {
@@ -215,10 +233,14 @@ bool vmbus_prep_negotiate_resp(struct icmsg_hdr *icmsghdrp,
 	bool found_match = false;
 	struct icmsg_negotiate *negop;
 
+	/* Check that there's enough space for icframe_vercnt, icmsg_vercnt */
+	if (buflen < ICMSG_HDR + offsetof(struct icmsg_negotiate, reserved)) {
+		pr_err_ratelimited("Invalid icmsg negotiate\n");
+		return false;
+	}
+
 	icmsghdrp->icmsgsize = 0x10;
-	negop = (struct icmsg_negotiate *)&buf[
-		sizeof(struct vmbuspipe_hdr) +
-		sizeof(struct icmsg_hdr)];
+	negop = (struct icmsg_negotiate *)&buf[ICMSG_HDR];
 
 	icframe_major = negop->icframe_vercnt;
 	icframe_minor = 0;
@@ -226,6 +248,15 @@ bool vmbus_prep_negotiate_resp(struct icmsg_hdr *icmsghdrp,
 	icmsg_major = negop->icmsg_vercnt;
 	icmsg_minor = 0;
 
+	/* Validate negop packet */
+	if (icframe_major > IC_VERSION_NEGOTIATION_MAX_VER_COUNT ||
+	    icmsg_major > IC_VERSION_NEGOTIATION_MAX_VER_COUNT ||
+	    ICMSG_NEGOTIATE_PKT_SIZE(icframe_major, icmsg_major) > buflen) {
+		pr_err_ratelimited("Invalid icmsg negotiate - icframe_major: %u, icmsg_major: %u\n",
+				   icframe_major, icmsg_major);
+		goto fw_error;
+	}
+
 	/*
 	 * Select the framework version number we will
 	 * support.
@@ -889,6 +920,20 @@ find_primary_channel_by_offer(const struct vmbus_channel_offer_channel *offer)
 	return channel;
 }
 
+static bool vmbus_is_valid_device(const guid_t *guid)
+{
+	u16 i;
+
+	if (!hv_is_isolation_supported())
+		return true;
+
+	for (i = 0; i < ARRAY_SIZE(vmbus_devs); i++) {
+		if (guid_equal(guid, &vmbus_devs[i].guid))
+			return vmbus_devs[i].allowed_in_isolated;
+	}
+	return false;
+}
+
 /*
  * vmbus_onoffer - Handler for channel offers from vmbus in parent partition.
  *
@@ -903,6 +948,13 @@ static void vmbus_onoffer(struct vmbus_channel_message_header *hdr)
 
 	trace_vmbus_onoffer(offer);
 
+	if (!vmbus_is_valid_device(&offer->offer.if_type)) {
+		pr_err_ratelimited("Invalid offer %d from the host supporting isolation\n",
+				   offer->child_relid);
+		atomic_dec(&vmbus_connection.offer_in_progress);
+		return;
+	}
+
 	oldchannel = find_primary_channel_by_offer(offer);
 
 	if (oldchannel != NULL) {
@@ -1049,6 +1101,18 @@ static void vmbus_onoffer_rescind(struct vmbus_channel_message_header *hdr)
 
 	mutex_lock(&vmbus_connection.channel_mutex);
 	channel = relid2channel(rescind->child_relid);
+	if (channel != NULL) {
+		/*
+		 * Guarantee that no other instance of vmbus_onoffer_rescind()
+		 * has got a reference to the channel object.  Synchronize on
+		 * &vmbus_connection.channel_mutex.
+		 */
+		if (channel->rescind_ref) {
+			mutex_unlock(&vmbus_connection.channel_mutex);
+			return;
+		}
+		channel->rescind_ref = true;
+	}
 	mutex_unlock(&vmbus_connection.channel_mutex);
 
 	if (channel == NULL) {
@@ -1102,8 +1166,7 @@ static void vmbus_onoffer_rescind(struct vmbus_channel_message_header *hdr)
 			vmbus_device_unregister(channel->device_obj);
 			put_device(dev);
 		}
-	}
-	if (channel->primary_channel != NULL) {
+	} else if (channel->primary_channel != NULL) {
 		/*
 		 * Sub-channel is being rescinded. Following is the channel
 		 * close sequence when initiated from the driveri (refer to

drivers/hv/connection.c

@@ -244,6 +244,13 @@ int vmbus_connect(void)
 			break;
 	}
 
+	if (hv_is_isolation_supported() && version < VERSION_WIN10_V5_2) {
+		pr_err("Invalid VMBus version %d.%d (expected >= %d.%d) from the host supporting isolation\n",
+		       version >> 16, version & 0xFFFF, VERSION_WIN10_V5_2 >> 16, VERSION_WIN10_V5_2 & 0xFFFF);
+		ret = -EINVAL;
+		goto cleanup;
+	}
+
 	vmbus_proto_version = version;
 	pr_info("Vmbus version:%d.%d\n",
 		version >> 16, version & 0xFFFF);

drivers/hv/hv_fcopy.c

@@ -235,15 +235,27 @@ void hv_fcopy_onchannelcallback(void *context)
 	if (fcopy_transaction.state > HVUTIL_READY)
 		return;
 
-	vmbus_recvpacket(channel, recv_buffer, HV_HYP_PAGE_SIZE * 2, &recvlen,
-			 &requestid);
-	if (recvlen <= 0)
+	if (vmbus_recvpacket(channel, recv_buffer, HV_HYP_PAGE_SIZE * 2, &recvlen, &requestid)) {
+		pr_err_ratelimited("Fcopy request received. Could not read into recv buf\n");
 		return;
+	}
+
+	if (!recvlen)
+		return;
+
+	/* Ensure recvlen is big enough to read header data */
+	if (recvlen < ICMSG_HDR) {
+		pr_err_ratelimited("Fcopy request received. Packet length too small: %d\n",
+				   recvlen);
+		return;
+	}
 
 	icmsghdr = (struct icmsg_hdr *)&recv_buffer[
 			sizeof(struct vmbuspipe_hdr)];
+
 	if (icmsghdr->icmsgtype == ICMSGTYPE_NEGOTIATE) {
-		if (vmbus_prep_negotiate_resp(icmsghdr, recv_buffer,
+		if (vmbus_prep_negotiate_resp(icmsghdr,
+				recv_buffer, recvlen,
 				fw_versions, FW_VER_COUNT,
 				fcopy_versions, FCOPY_VER_COUNT,
 				NULL, &fcopy_srv_version)) {
@@ -252,10 +264,14 @@ void hv_fcopy_onchannelcallback(void *context)
 				fcopy_srv_version >> 16,
 				fcopy_srv_version & 0xFFFF);
 		}
-	} else {
-		fcopy_msg = (struct hv_fcopy_hdr *)&recv_buffer[
-				sizeof(struct vmbuspipe_hdr) +
-				sizeof(struct icmsg_hdr)];
+	} else if (icmsghdr->icmsgtype == ICMSGTYPE_FCOPY) {
+		/* Ensure recvlen is big enough to contain hv_fcopy_hdr */
+		if (recvlen < ICMSG_HDR + sizeof(struct hv_fcopy_hdr)) {
+			pr_err_ratelimited("Invalid Fcopy hdr. Packet length too small: %u\n",
+					   recvlen);
+			return;
+		}
+		fcopy_msg = (struct hv_fcopy_hdr *)&recv_buffer[ICMSG_HDR];
 
 		/*
 		 * Stash away this global state for completing the
@@ -280,6 +296,10 @@ void hv_fcopy_onchannelcallback(void *context)
 		schedule_delayed_work(&fcopy_timeout_work,
 				      HV_UTIL_TIMEOUT * HZ);
 		return;
+	} else {
+		pr_err_ratelimited("Fcopy request received. Invalid msg type: %d\n",
+				   icmsghdr->icmsgtype);
+		return;
 	}
 	icmsghdr->icflags = ICMSGHDRFLAG_TRANSACTION | ICMSGHDRFLAG_RESPONSE;
 	vmbus_sendpacket(channel, recv_buffer, recvlen, requestid,

drivers/hv/hv_kvp.c

@@ -662,71 +662,87 @@ void hv_kvp_onchannelcallback(void *context)
 	if (kvp_transaction.state > HVUTIL_READY)
 		return;
 
-	vmbus_recvpacket(channel, recv_buffer, HV_HYP_PAGE_SIZE * 4, &recvlen,
-			 &requestid);
-
-	if (recvlen > 0) {
-		icmsghdrp = (struct icmsg_hdr *)&recv_buffer[
-			sizeof(struct vmbuspipe_hdr)];
-
-		if (icmsghdrp->icmsgtype == ICMSGTYPE_NEGOTIATE) {
-			if (vmbus_prep_negotiate_resp(icmsghdrp,
-				 recv_buffer, fw_versions, FW_VER_COUNT,
-				 kvp_versions, KVP_VER_COUNT,
-				 NULL, &kvp_srv_version)) {
-				pr_info("KVP IC version %d.%d\n",
-					kvp_srv_version >> 16,
-					kvp_srv_version & 0xFFFF);
-			}
-		} else {
-			kvp_msg = (struct hv_kvp_msg *)&recv_buffer[
-				sizeof(struct vmbuspipe_hdr) +
-				sizeof(struct icmsg_hdr)];
+	if (vmbus_recvpacket(channel, recv_buffer, HV_HYP_PAGE_SIZE * 4, &recvlen, &requestid)) {
+		pr_err_ratelimited("KVP request received. Could not read into recv buf\n");
+		return;
+	}
 
-			/*
-			 * Stash away this global state for completing the
-			 * transaction; note transactions are serialized.
-			 */
+	if (!recvlen)
+		return;
 
-			kvp_transaction.recv_len = recvlen;
-			kvp_transaction.recv_req_id = requestid;
-			kvp_transaction.kvp_msg = kvp_msg;
+	/* Ensure recvlen is big enough to read header data */
+	if (recvlen < ICMSG_HDR) {
+		pr_err_ratelimited("KVP request received. Packet length too small: %d\n",
+				   recvlen);
+		return;
+	}
 
-			if (kvp_transaction.state < HVUTIL_READY) {
-				/* Userspace is not registered yet */
-				kvp_respond_to_host(NULL, HV_E_FAIL);
-				return;
-			}
-			kvp_transaction.state = HVUTIL_HOSTMSG_RECEIVED;
+	icmsghdrp = (struct icmsg_hdr *)&recv_buffer[sizeof(struct vmbuspipe_hdr)];
+
+	if (icmsghdrp->icmsgtype == ICMSGTYPE_NEGOTIATE) {
+		if (vmbus_prep_negotiate_resp(icmsghdrp,
+				recv_buffer, recvlen,
+				fw_versions, FW_VER_COUNT,
+				kvp_versions, KVP_VER_COUNT,
+				NULL, &kvp_srv_version)) {
+			pr_info("KVP IC version %d.%d\n",
+				kvp_srv_version >> 16,
+				kvp_srv_version & 0xFFFF);
+		}
+	} else if (icmsghdrp->icmsgtype == ICMSGTYPE_KVPEXCHANGE) {
+		/*
+		 * recvlen is not checked against sizeof(struct kvp_msg) because kvp_msg contains
+		 * a union of structs and the msg type received is not known. Code using this
+		 * struct should provide validation when accessing its fields.
+		 */
+		kvp_msg = (struct hv_kvp_msg *)&recv_buffer[ICMSG_HDR];
 
-			/*
-			 * Get the information from the
-			 * user-mode component.
-			 * component. This transaction will be
-			 * completed when we get the value from
-			 * the user-mode component.
-			 * Set a timeout to deal with
-			 * user-mode not responding.
-			 */
-			schedule_work(&kvp_sendkey_work);
-			schedule_delayed_work(&kvp_timeout_work,
-					      HV_UTIL_TIMEOUT * HZ);
+		/*
+		 * Stash away this global state for completing the
+		 * transaction; note transactions are serialized.
+		 */
 
-			return;
+		kvp_transaction.recv_len = recvlen;
+		kvp_transaction.recv_req_id = requestid;
+		kvp_transaction.kvp_msg = kvp_msg;
 
+		if (kvp_transaction.state < HVUTIL_READY) {
+			/* Userspace is not registered yet */
+			kvp_respond_to_host(NULL, HV_E_FAIL);
+			return;
 		}
+		kvp_transaction.state = HVUTIL_HOSTMSG_RECEIVED;
 
-		icmsghdrp->icflags = ICMSGHDRFLAG_TRANSACTION
-			| ICMSGHDRFLAG_RESPONSE;
+		/*
+		 * Get the information from the
+		 * user-mode component.
+		 * component. This transaction will be
+		 * completed when we get the value from
+		 * the user-mode component.
+		 * Set a timeout to deal with
+		 * user-mode not responding.
+		 */
+		schedule_work(&kvp_sendkey_work);
+		schedule_delayed_work(&kvp_timeout_work,
+					HV_UTIL_TIMEOUT * HZ);
 
-		vmbus_sendpacket(channel, recv_buffer,
-				       recvlen, requestid,
-				       VM_PKT_DATA_INBAND, 0);
+		return;
 
-		host_negotiatied = NEGO_FINISHED;
-		hv_poll_channel(kvp_transaction.recv_channel, kvp_poll_wrapper);
+	} else {
+		pr_err_ratelimited("KVP request received. Invalid msg type: %d\n",
+				   icmsghdrp->icmsgtype);
+		return;
 	}
 
+	icmsghdrp->icflags = ICMSGHDRFLAG_TRANSACTION
+		| ICMSGHDRFLAG_RESPONSE;
+
+	vmbus_sendpacket(channel, recv_buffer,
+			 recvlen, requestid,
+			 VM_PKT_DATA_INBAND, 0);
+
+	host_negotiatied = NEGO_FINISHED;
+	hv_poll_channel(kvp_transaction.recv_channel, kvp_poll_wrapper);
 }
 
 static void kvp_on_reset(void)

drivers/hv/hv_snapshot.c

@@ -298,49 +298,64 @@ void hv_vss_onchannelcallback(void *context)
 	if (vss_transaction.state > HVUTIL_READY)
 		return;
 
-	vmbus_recvpacket(channel, recv_buffer, HV_HYP_PAGE_SIZE * 2, &recvlen,
-			 &requestid);
-
-	if (recvlen > 0) {
-		icmsghdrp = (struct icmsg_hdr *)&recv_buffer[
-			sizeof(struct vmbuspipe_hdr)];
-
-		if (icmsghdrp->icmsgtype == ICMSGTYPE_NEGOTIATE) {
-			if (vmbus_prep_negotiate_resp(icmsghdrp,
-				 recv_buffer, fw_versions, FW_VER_COUNT,
-				 vss_versions, VSS_VER_COUNT,
-				 NULL, &vss_srv_version)) {
-
-				pr_info("VSS IC version %d.%d\n",
-					vss_srv_version >> 16,
-					vss_srv_version & 0xFFFF);
-			}
-		} else {
-			vss_msg = (struct hv_vss_msg *)&recv_buffer[
-				sizeof(struct vmbuspipe_hdr) +
-				sizeof(struct icmsg_hdr)];
-
-			/*
-			 * Stash away this global state for completing the
-			 * transaction; note transactions are serialized.
-			 */
-
-			vss_transaction.recv_len = recvlen;
-			vss_transaction.recv_req_id = requestid;
-			vss_transaction.msg = (struct hv_vss_msg *)vss_msg;
-
-			schedule_work(&vss_handle_request_work);
+	if (vmbus_recvpacket(channel, recv_buffer, HV_HYP_PAGE_SIZE * 2, &recvlen, &requestid)) {
+		pr_err_ratelimited("VSS request received. Could not read into recv buf\n");
+		return;
+	}
+
+	if (!recvlen)
+		return;
+
+	/* Ensure recvlen is big enough to read header data */
+	if (recvlen < ICMSG_HDR) {
+		pr_err_ratelimited("VSS request received. Packet length too small: %d\n",
+				   recvlen);
+		return;
+	}
+
+	icmsghdrp = (struct icmsg_hdr *)&recv_buffer[sizeof(struct vmbuspipe_hdr)];
+
+	if (icmsghdrp->icmsgtype == ICMSGTYPE_NEGOTIATE) {
+		if (vmbus_prep_negotiate_resp(icmsghdrp,
+				recv_buffer, recvlen,
+				fw_versions, FW_VER_COUNT,
+				vss_versions, VSS_VER_COUNT,
+				NULL, &vss_srv_version)) {
+
+			pr_info("VSS IC version %d.%d\n",
+				vss_srv_version >> 16,
+				vss_srv_version & 0xFFFF);
+		}
+	} else if (icmsghdrp->icmsgtype == ICMSGTYPE_VSS) {
+		/* Ensure recvlen is big enough to contain hv_vss_msg */
+		if (recvlen < ICMSG_HDR + sizeof(struct hv_vss_msg)) {
+			pr_err_ratelimited("Invalid VSS msg. Packet length too small: %u\n",
+					   recvlen);
 			return;
 		}
+		vss_msg = (struct hv_vss_msg *)&recv_buffer[ICMSG_HDR];
+
+		/*
+		 * Stash away this global state for completing the
+		 * transaction; note transactions are serialized.
+		 */
 
-		icmsghdrp->icflags = ICMSGHDRFLAG_TRANSACTION
-			| ICMSGHDRFLAG_RESPONSE;
+		vss_transaction.recv_len = recvlen;
+		vss_transaction.recv_req_id = requestid;
+		vss_transaction.msg = (struct hv_vss_msg *)vss_msg;
 
-		vmbus_sendpacket(channel, recv_buffer,
-				       recvlen, requestid,
-				       VM_PKT_DATA_INBAND, 0);
+		schedule_work(&vss_handle_request_work);
+		return;
+	} else {
+		pr_err_ratelimited("VSS request received. Invalid msg type: %d\n",
+				   icmsghdrp->icmsgtype);
+		return;
 	}
 
+	icmsghdrp->icflags = ICMSGHDRFLAG_TRANSACTION |
+		ICMSGHDRFLAG_RESPONSE;
+	vmbus_sendpacket(channel, recv_buffer, recvlen, requestid,
+			 VM_PKT_DATA_INBAND, 0);
 }
 
 static void vss_on_reset(void)

drivers/hv/hv_util.c

@@ -195,73 +195,88 @@ static void shutdown_onchannelcallback(void *context)
 
 	struct icmsg_hdr *icmsghdrp;
 
-	vmbus_recvpacket(channel, shut_txf_buf,
-			 HV_HYP_PAGE_SIZE, &recvlen, &requestid);
+	if (vmbus_recvpacket(channel, shut_txf_buf, HV_HYP_PAGE_SIZE, &recvlen, &requestid)) {
+		pr_err_ratelimited("Shutdown request received. Could not read into shut txf buf\n");
+		return;
+	}
 
-	if (recvlen > 0) {
-		icmsghdrp = (struct icmsg_hdr *)&shut_txf_buf[
-			sizeof(struct vmbuspipe_hdr)];
+	if (!recvlen)
+		return;
 
-		if (icmsghdrp->icmsgtype == ICMSGTYPE_NEGOTIATE) {
-			if (vmbus_prep_negotiate_resp(icmsghdrp, shut_txf_buf,
-					fw_versions, FW_VER_COUNT,
-					sd_versions, SD_VER_COUNT,
-					NULL, &sd_srv_version)) {
-				pr_info("Shutdown IC version %d.%d\n",
-					sd_srv_version >> 16,
-					sd_srv_version & 0xFFFF);
-			}
-		} else {
-			shutdown_msg =
-				(struct shutdown_msg_data *)&shut_txf_buf[
-					sizeof(struct vmbuspipe_hdr) +
-					sizeof(struct icmsg_hdr)];
+	/* Ensure recvlen is big enough to read header data */
+	if (recvlen < ICMSG_HDR) {
+		pr_err_ratelimited("Shutdown request received. Packet length too small: %d\n",
+				   recvlen);
+		return;
+	}
 
-			/*
-			 * shutdown_msg->flags can be 0(shut down), 2(reboot),
-			 * or 4(hibernate). It may bitwise-OR 1, which means
-			 * performing the request by force. Linux always tries
-			 * to perform the request by force.
-			 */
-			switch (shutdown_msg->flags) {
-			case 0:
-			case 1:
-				icmsghdrp->status = HV_S_OK;
-				work = &shutdown_work;
-				pr_info("Shutdown request received -"
-					    " graceful shutdown initiated\n");
-				break;
-			case 2:
-			case 3:
-				icmsghdrp->status = HV_S_OK;
-				work = &restart_work;
-				pr_info("Restart request received -"
-					    " graceful restart initiated\n");
-				break;
-			case 4:
-			case 5:
-				pr_info("Hibernation request received\n");
-				icmsghdrp->status = hibernation_supported ?
-					HV_S_OK : HV_E_FAIL;
-				if (hibernation_supported)
-					work = &hibernate_context.work;
-				break;
-			default:
-				icmsghdrp->status = HV_E_FAIL;
-				pr_info("Shutdown request received -"
-					    " Invalid request\n");
-				break;
-			}
+	icmsghdrp = (struct icmsg_hdr *)&shut_txf_buf[sizeof(struct vmbuspipe_hdr)];
+
+	if (icmsghdrp->icmsgtype == ICMSGTYPE_NEGOTIATE) {
+		if (vmbus_prep_negotiate_resp(icmsghdrp,
+				shut_txf_buf, recvlen,
+				fw_versions, FW_VER_COUNT,
+				sd_versions, SD_VER_COUNT,
+				NULL, &sd_srv_version)) {
+			pr_info("Shutdown IC version %d.%d\n",
+				sd_srv_version >> 16,
+				sd_srv_version & 0xFFFF);
+		}
+	} else if (icmsghdrp->icmsgtype == ICMSGTYPE_SHUTDOWN) {
+		/* Ensure recvlen is big enough to contain shutdown_msg_data struct */
+		if (recvlen < ICMSG_HDR + sizeof(struct shutdown_msg_data)) {
+			pr_err_ratelimited("Invalid shutdown msg data. Packet length too small: %u\n",
+					   recvlen);
+			return;
 		}
 
-		icmsghdrp->icflags = ICMSGHDRFLAG_TRANSACTION
-			| ICMSGHDRFLAG_RESPONSE;
-
-		vmbus_sendpacket(channel, shut_txf_buf,
-				       recvlen, requestid,
-				       VM_PKT_DATA_INBAND, 0);
+		shutdown_msg = (struct shutdown_msg_data *)&shut_txf_buf[ICMSG_HDR];
+
+		/*
+		 * shutdown_msg->flags can be 0(shut down), 2(reboot),
+		 * or 4(hibernate). It may bitwise-OR 1, which means
+		 * performing the request by force. Linux always tries
+		 * to perform the request by force.
+		 */
+		switch (shutdown_msg->flags) {
+		case 0:
+		case 1:
+			icmsghdrp->status = HV_S_OK;
+			work = &shutdown_work;
+			pr_info("Shutdown request received - graceful shutdown initiated\n");
+			break;
+		case 2:
+		case 3:
+			icmsghdrp->status = HV_S_OK;
+			work = &restart_work;
+			pr_info("Restart request received - graceful restart initiated\n");
+			break;
+		case 4:
+		case 5:
+			pr_info("Hibernation request received\n");
+			icmsghdrp->status = hibernation_supported ?
+				HV_S_OK : HV_E_FAIL;
+			if (hibernation_supported)
+				work = &hibernate_context.work;
+			break;
+		default:
+			icmsghdrp->status = HV_E_FAIL;
+			pr_info("Shutdown request received - Invalid request\n");
+			break;
+		}
+	} else {
+		icmsghdrp->status = HV_E_FAIL;
+		pr_err_ratelimited("Shutdown request received. Invalid msg type: %d\n",
+				   icmsghdrp->icmsgtype);
 	}
 
+	icmsghdrp->icflags = ICMSGHDRFLAG_TRANSACTION
+		| ICMSGHDRFLAG_RESPONSE;
+
+	vmbus_sendpacket(channel, shut_txf_buf,
+			 recvlen, requestid,
+			 VM_PKT_DATA_INBAND, 0);
+
 	if (work)
 		schedule_work(work);
 }
@@ -396,19 +411,27 @@ static void timesync_onchannelcallback(void *context)
 					   HV_HYP_PAGE_SIZE, &recvlen,
 					   &requestid);
 		if (ret) {
-			pr_warn_once("TimeSync IC pkt recv failed (Err: %d)\n",
-				     ret);
+			pr_err_ratelimited("TimeSync IC pkt recv failed (Err: %d)\n",
+					   ret);
 			break;
 		}
 
 		if (!recvlen)
 			break;
 
+		/* Ensure recvlen is big enough to read header data */
+		if (recvlen < ICMSG_HDR) {
+			pr_err_ratelimited("Timesync request received. Packet length too small: %d\n",
+					   recvlen);
+			break;
+		}
+
 		icmsghdrp = (struct icmsg_hdr *)&time_txf_buf[
 				sizeof(struct vmbuspipe_hdr)];
 
 		if (icmsghdrp->icmsgtype == ICMSGTYPE_NEGOTIATE) {
-			if (vmbus_prep_negotiate_resp(icmsghdrp, time_txf_buf,
+			if (vmbus_prep_negotiate_resp(icmsghdrp,
+						time_txf_buf, recvlen,
 						fw_versions, FW_VER_COUNT,
 						ts_versions, TS_VER_COUNT,
 						NULL, &ts_srv_version)) {
@@ -416,33 +439,44 @@ static void timesync_onchannelcallback(void *context)
 					ts_srv_version >> 16,
 					ts_srv_version & 0xFFFF);
 			}
-		} else {
+		} else if (icmsghdrp->icmsgtype == ICMSGTYPE_TIMESYNC) {
 			if (ts_srv_version > TS_VERSION_3) {
-				refdata = (struct ictimesync_ref_data *)
-					&time_txf_buf[
-					sizeof(struct vmbuspipe_hdr) +
-					sizeof(struct icmsg_hdr)];
+				/* Ensure recvlen is big enough to read ictimesync_ref_data */
+				if (recvlen < ICMSG_HDR + sizeof(struct ictimesync_ref_data)) {
+					pr_err_ratelimited("Invalid ictimesync ref data. Length too small: %u\n",
+							   recvlen);
+					break;
+				}
+				refdata = (struct ictimesync_ref_data *)&time_txf_buf[ICMSG_HDR];
 
 				adj_guesttime(refdata->parenttime,
 						refdata->vmreferencetime,
 						refdata->flags);
 			} else {
-				timedatap = (struct ictimesync_data *)
-					&time_txf_buf[
-					sizeof(struct vmbuspipe_hdr) +
-					sizeof(struct icmsg_hdr)];
+				/* Ensure recvlen is big enough to read ictimesync_data */
+				if (recvlen < ICMSG_HDR + sizeof(struct ictimesync_data)) {
+					pr_err_ratelimited("Invalid ictimesync data. Length too small: %u\n",
+							   recvlen);
+					break;
+				}
+				timedatap = (struct ictimesync_data *)&time_txf_buf[ICMSG_HDR];
+
 				adj_guesttime(timedatap->parenttime,
 					      hv_read_reference_counter(),
 					      timedatap->flags);
 			}
+		} else {
+			icmsghdrp->status = HV_E_FAIL;
+			pr_err_ratelimited("Timesync request received. Invalid msg type: %d\n",
+					   icmsghdrp->icmsgtype);
 		}
 
 		icmsghdrp->icflags = ICMSGHDRFLAG_TRANSACTION
 			| ICMSGHDRFLAG_RESPONSE;
 
 		vmbus_sendpacket(channel, time_txf_buf,
-				recvlen, requestid,
-				VM_PKT_DATA_INBAND, 0);
+				 recvlen, requestid,
+				 VM_PKT_DATA_INBAND, 0);
 	}
 }
 
@@ -462,18 +496,28 @@ static void heartbeat_onchannelcallback(void *context)
 
 	while (1) {
 
-		vmbus_recvpacket(channel, hbeat_txf_buf,
-				 HV_HYP_PAGE_SIZE, &recvlen, &requestid);
+		if (vmbus_recvpacket(channel, hbeat_txf_buf, HV_HYP_PAGE_SIZE,
+				     &recvlen, &requestid)) {
+			pr_err_ratelimited("Heartbeat request received. Could not read into hbeat txf buf\n");
+			return;
+		}
 
 		if (!recvlen)
 			break;
 
+		/* Ensure recvlen is big enough to read header data */
+		if (recvlen < ICMSG_HDR) {
+			pr_err_ratelimited("Heartbeat request received. Packet length too small: %d\n",
+					   recvlen);
+			break;
+		}
+
 		icmsghdrp = (struct icmsg_hdr *)&hbeat_txf_buf[
 				sizeof(struct vmbuspipe_hdr)];
 
 		if (icmsghdrp->icmsgtype == ICMSGTYPE_NEGOTIATE) {
 			if (vmbus_prep_negotiate_resp(icmsghdrp,
-					hbeat_txf_buf,
+					hbeat_txf_buf, recvlen,
 					fw_versions, FW_VER_COUNT,
 					hb_versions, HB_VER_COUNT,
 					NULL, &hb_srv_version)) {
@@ -482,21 +526,31 @@ static void heartbeat_onchannelcallback(void *context)
 					hb_srv_version >> 16,
 					hb_srv_version & 0xFFFF);
 			}
-		} else {
-			heartbeat_msg =
-				(struct heartbeat_msg_data *)&hbeat_txf_buf[
-					sizeof(struct vmbuspipe_hdr) +
-					sizeof(struct icmsg_hdr)];
+		} else if (icmsghdrp->icmsgtype == ICMSGTYPE_HEARTBEAT) {
+			/*
+			 * Ensure recvlen is big enough to read seq_num. Reserved area is not
+			 * included in the check as the host may not fill it up entirely
+			 */
+			if (recvlen < ICMSG_HDR + sizeof(u64)) {
+				pr_err_ratelimited("Invalid heartbeat msg data. Length too small: %u\n",
+						   recvlen);
+				break;
+			}
+			heartbeat_msg = (struct heartbeat_msg_data *)&hbeat_txf_buf[ICMSG_HDR];
 
 			heartbeat_msg->seq_num += 1;
+		} else {
+			icmsghdrp->status = HV_E_FAIL;
+			pr_err_ratelimited("Heartbeat request received. Invalid msg type: %d\n",
+					   icmsghdrp->icmsgtype);
 		}
 
 		icmsghdrp->icflags = ICMSGHDRFLAG_TRANSACTION
 			| ICMSGHDRFLAG_RESPONSE;
 
 		vmbus_sendpacket(channel, hbeat_txf_buf,
-				       recvlen, requestid,
-				       VM_PKT_DATA_INBAND, 0);
+				 recvlen, requestid,
+				 VM_PKT_DATA_INBAND, 0);
 	}
 }
 

drivers/hv/vmbus_drv.c

@@ -678,6 +678,23 @@ static const struct attribute_group vmbus_dev_group = {
 };
 __ATTRIBUTE_GROUPS(vmbus_dev);
 
+/* Set up the attribute for /sys/bus/vmbus/hibernation */
+static ssize_t hibernation_show(struct bus_type *bus, char *buf)
+{
+	return sprintf(buf, "%d\n", !!hv_is_hibernation_supported());
+}
+
+static BUS_ATTR_RO(hibernation);
+
+static struct attribute *vmbus_bus_attrs[] = {
+	&bus_attr_hibernation.attr,
+	NULL,
+};
+static const struct attribute_group vmbus_bus_group = {
+	.attrs = vmbus_bus_attrs,
+};
+__ATTRIBUTE_GROUPS(vmbus_bus);
+
 /*
  * vmbus_uevent - add uevent for our device
  *
@@ -1024,6 +1041,7 @@ static struct bus_type  hv_bus = {
 	.uevent =		vmbus_uevent,
 	.dev_groups =		vmbus_dev_groups,
 	.drv_groups =		vmbus_drv_groups,
+	.bus_groups =		vmbus_bus_groups,
 	.pm =			&vmbus_pm,
 };
 
@@ -1054,12 +1072,14 @@ void vmbus_on_msg_dpc(unsigned long data)
 {
 	struct hv_per_cpu_context *hv_cpu = (void *)data;
 	void *page_addr = hv_cpu->synic_message_page;
-	struct hv_message *msg = (struct hv_message *)page_addr +
+	struct hv_message msg_copy, *msg = (struct hv_message *)page_addr +
 				  VMBUS_MESSAGE_SINT;
 	struct vmbus_channel_message_header *hdr;
+	enum vmbus_channel_message_type msgtype;
 	const struct vmbus_channel_message_table_entry *entry;
 	struct onmessage_work_context *ctx;
-	u32 message_type = msg->header.message_type;
+	__u8 payload_size;
+	u32 message_type;
 
 	/*
 	 * 'enum vmbus_channel_message_type' is supposed to always be 'u32' as
@@ -1068,45 +1088,52 @@ void vmbus_on_msg_dpc(unsigned long data)
 	 */
 	BUILD_BUG_ON(sizeof(enum vmbus_channel_message_type) != sizeof(u32));
 
+	/*
+	 * Since the message is in memory shared with the host, an erroneous or
+	 * malicious Hyper-V could modify the message while vmbus_on_msg_dpc()
+	 * or individual message handlers are executing; to prevent this, copy
+	 * the message into private memory.
+	 */
+	memcpy(&msg_copy, msg, sizeof(struct hv_message));
+
+	message_type = msg_copy.header.message_type;
 	if (message_type == HVMSG_NONE)
 		/* no msg */
 		return;
 
-	hdr = (struct vmbus_channel_message_header *)msg->u.payload;
+	hdr = (struct vmbus_channel_message_header *)msg_copy.u.payload;
+	msgtype = hdr->msgtype;
 
 	trace_vmbus_on_msg_dpc(hdr);
 
-	if (hdr->msgtype >= CHANNELMSG_COUNT) {
-		WARN_ONCE(1, "unknown msgtype=%d\n", hdr->msgtype);
+	if (msgtype >= CHANNELMSG_COUNT) {
+		WARN_ONCE(1, "unknown msgtype=%d\n", msgtype);
 		goto msg_handled;
 	}
 
-	if (msg->header.payload_size > HV_MESSAGE_PAYLOAD_BYTE_COUNT) {
-		WARN_ONCE(1, "payload size is too large (%d)\n",
-			  msg->header.payload_size);
+	payload_size = msg_copy.header.payload_size;
+	if (payload_size > HV_MESSAGE_PAYLOAD_BYTE_COUNT) {
+		WARN_ONCE(1, "payload size is too large (%d)\n", payload_size);
 		goto msg_handled;
 	}
 
-	entry = &channel_message_table[hdr->msgtype];
+	entry = &channel_message_table[msgtype];
 
 	if (!entry->message_handler)
 		goto msg_handled;
 
-	if (msg->header.payload_size < entry->min_payload_len) {
-		WARN_ONCE(1, "message too short: msgtype=%d len=%d\n",
-			  hdr->msgtype, msg->header.payload_size);
+	if (payload_size < entry->min_payload_len) {
+		WARN_ONCE(1, "message too short: msgtype=%d len=%d\n", msgtype, payload_size);
 		goto msg_handled;
 	}
 
 	if (entry->handler_type	== VMHT_BLOCKING) {
-		ctx = kmalloc(sizeof(*ctx) + msg->header.payload_size,
-			      GFP_ATOMIC);
+		ctx = kmalloc(sizeof(*ctx) + payload_size, GFP_ATOMIC);
 		if (ctx == NULL)
 			return;
 
 		INIT_WORK(&ctx->work, vmbus_onmessage_work);
-		memcpy(&ctx->msg, msg, sizeof(msg->header) +
-		       msg->header.payload_size);
+		memcpy(&ctx->msg, &msg_copy, sizeof(msg->header) + payload_size);
 
 		/*
 		 * The host can generate a rescind message while we
@@ -1115,7 +1142,7 @@ void vmbus_on_msg_dpc(unsigned long data)
 		 * by offer_in_progress and by channel_mutex.  See also the
 		 * inline comments in vmbus_onoffer_rescind().
 		 */
-		switch (hdr->msgtype) {
+		switch (msgtype) {
 		case CHANNELMSG_RESCIND_CHANNELOFFER:
 			/*
 			 * If we are handling the rescind message;
@@ -2618,6 +2645,9 @@ static int __init hv_acpi_init(void)
 	if (!hv_is_hyperv_initialized())
 		return -ENODEV;
 
+	if (hv_root_partition)
+		return 0;
+
 	init_completion(&probe_event);
 
 	/*

drivers/iommu/hyperv-iommu.c

@@ -20,6 +20,7 @@
 #include <asm/io_apic.h>
 #include <asm/irq_remapping.h>
 #include <asm/hypervisor.h>
+#include <asm/mshyperv.h>
 
 #include "irq_remapping.h"
 
@@ -115,30 +116,43 @@ static const struct irq_domain_ops hyperv_ir_domain_ops = {
 	.free = hyperv_irq_remapping_free,
 };
 
+static const struct irq_domain_ops hyperv_root_ir_domain_ops;
 static int __init hyperv_prepare_irq_remapping(void)
 {
 	struct fwnode_handle *fn;
 	int i;
+	const char *name;
+	const struct irq_domain_ops *ops;
 
 	if (!hypervisor_is_type(X86_HYPER_MS_HYPERV) ||
 	    x86_init.hyper.msi_ext_dest_id() ||
 	    !x2apic_supported())
 		return -ENODEV;
 
-	fn = irq_domain_alloc_named_id_fwnode("HYPERV-IR", 0);
+	if (hv_root_partition) {
+		name = "HYPERV-ROOT-IR";
+		ops = &hyperv_root_ir_domain_ops;
+	} else {
+		name = "HYPERV-IR";
+		ops = &hyperv_ir_domain_ops;
+	}
+
+	fn = irq_domain_alloc_named_id_fwnode(name, 0);
 	if (!fn)
 		return -ENOMEM;
 
 	ioapic_ir_domain =
 		irq_domain_create_hierarchy(arch_get_ir_parent_domain(),
-				0, IOAPIC_REMAPPING_ENTRY, fn,
-				&hyperv_ir_domain_ops, NULL);
+				0, IOAPIC_REMAPPING_ENTRY, fn, ops, NULL);
 
 	if (!ioapic_ir_domain) {
 		irq_domain_free_fwnode(fn);
 		return -ENOMEM;
 	}
 
+	if (hv_root_partition)
+		return 0; /* The rest is only relevant to guests */
+
 	/*
 	 * Hyper-V doesn't provide irq remapping function for
 	 * IO-APIC and so IO-APIC only accepts 8-bit APIC ID.
@@ -166,4 +180,161 @@ struct irq_remap_ops hyperv_irq_remap_ops = {
 	.enable			= hyperv_enable_irq_remapping,
 };
 
+/* IRQ remapping domain when Linux runs as the root partition */
+struct hyperv_root_ir_data {
+	u8 ioapic_id;
+	bool is_level;
+	struct hv_interrupt_entry entry;
+};
+
+static void
+hyperv_root_ir_compose_msi_msg(struct irq_data *irq_data, struct msi_msg *msg)
+{
+	u64 status;
+	u32 vector;
+	struct irq_cfg *cfg;
+	int ioapic_id;
+	struct cpumask *affinity;
+	int cpu;
+	struct hv_interrupt_entry entry;
+	struct hyperv_root_ir_data *data = irq_data->chip_data;
+	struct IO_APIC_route_entry e;
+
+	cfg = irqd_cfg(irq_data);
+	affinity = irq_data_get_effective_affinity_mask(irq_data);
+	cpu = cpumask_first_and(affinity, cpu_online_mask);
+
+	vector = cfg->vector;
+	ioapic_id = data->ioapic_id;
+
+	if (data->entry.source == HV_DEVICE_TYPE_IOAPIC
+	    && data->entry.ioapic_rte.as_uint64) {
+		entry = data->entry;
+
+		status = hv_unmap_ioapic_interrupt(ioapic_id, &entry);
+
+		if (status != HV_STATUS_SUCCESS)
+			pr_debug("%s: unexpected unmap status %lld\n", __func__, status);
+
+		data->entry.ioapic_rte.as_uint64 = 0;
+		data->entry.source = 0; /* Invalid source */
+	}
+
+
+	status = hv_map_ioapic_interrupt(ioapic_id, data->is_level, cpu,
+					vector, &entry);
+
+	if (status != HV_STATUS_SUCCESS) {
+		pr_err("%s: map hypercall failed, status %lld\n", __func__, status);
+		return;
+	}
+
+	data->entry = entry;
+
+	/* Turn it into an IO_APIC_route_entry, and generate MSI MSG. */
+	e.w1 = entry.ioapic_rte.low_uint32;
+	e.w2 = entry.ioapic_rte.high_uint32;
+
+	memset(msg, 0, sizeof(*msg));
+	msg->arch_data.vector = e.vector;
+	msg->arch_data.delivery_mode = e.delivery_mode;
+	msg->arch_addr_lo.dest_mode_logical = e.dest_mode_logical;
+	msg->arch_addr_lo.dmar_format = e.ir_format;
+	msg->arch_addr_lo.dmar_index_0_14 = e.ir_index_0_14;
+}
+
+static int hyperv_root_ir_set_affinity(struct irq_data *data,
+		const struct cpumask *mask, bool force)
+{
+	struct irq_data *parent = data->parent_data;
+	struct irq_cfg *cfg = irqd_cfg(data);
+	int ret;
+
+	ret = parent->chip->irq_set_affinity(parent, mask, force);
+	if (ret < 0 || ret == IRQ_SET_MASK_OK_DONE)
+		return ret;
+
+	send_cleanup_vector(cfg);
+
+	return 0;
+}
+
+static struct irq_chip hyperv_root_ir_chip = {
+	.name			= "HYPERV-ROOT-IR",
+	.irq_ack		= apic_ack_irq,
+	.irq_set_affinity	= hyperv_root_ir_set_affinity,
+	.irq_compose_msi_msg	= hyperv_root_ir_compose_msi_msg,
+};
+
+static int hyperv_root_irq_remapping_alloc(struct irq_domain *domain,
+				     unsigned int virq, unsigned int nr_irqs,
+				     void *arg)
+{
+	struct irq_alloc_info *info = arg;
+	struct irq_data *irq_data;
+	struct hyperv_root_ir_data *data;
+	int ret = 0;
+
+	if (!info || info->type != X86_IRQ_ALLOC_TYPE_IOAPIC || nr_irqs > 1)
+		return -EINVAL;
+
+	ret = irq_domain_alloc_irqs_parent(domain, virq, nr_irqs, arg);
+	if (ret < 0)
+		return ret;
+
+	data = kzalloc(sizeof(*data), GFP_KERNEL);
+	if (!data) {
+		irq_domain_free_irqs_common(domain, virq, nr_irqs);
+		return -ENOMEM;
+	}
+
+	irq_data = irq_domain_get_irq_data(domain, virq);
+	if (!irq_data) {
+		kfree(data);
+		irq_domain_free_irqs_common(domain, virq, nr_irqs);
+		return -EINVAL;
+	}
+
+	data->ioapic_id = info->devid;
+	data->is_level = info->ioapic.is_level;
+
+	irq_data->chip = &hyperv_root_ir_chip;
+	irq_data->chip_data = data;
+
+	return 0;
+}
+
+static void hyperv_root_irq_remapping_free(struct irq_domain *domain,
+				 unsigned int virq, unsigned int nr_irqs)
+{
+	struct irq_data *irq_data;
+	struct hyperv_root_ir_data *data;
+	struct hv_interrupt_entry *e;
+	int i;
+
+	for (i = 0; i < nr_irqs; i++) {
+		irq_data = irq_domain_get_irq_data(domain, virq + i);
+
+		if (irq_data && irq_data->chip_data) {
+			data = irq_data->chip_data;
+			e = &data->entry;
+
+			if (e->source == HV_DEVICE_TYPE_IOAPIC
+			      && e->ioapic_rte.as_uint64)
+				hv_unmap_ioapic_interrupt(data->ioapic_id,
+							&data->entry);
+
+			kfree(data);
+		}
+	}
+
+	irq_domain_free_irqs_common(domain, virq, nr_irqs);
+}
+
+static const struct irq_domain_ops hyperv_root_ir_domain_ops = {
+	.select = hyperv_irq_remapping_select,
+	.alloc = hyperv_root_irq_remapping_alloc,
+	.free = hyperv_root_irq_remapping_free,
+};
+
 #endif

drivers/net/hyperv/netvsc.c

@@ -22,6 +22,7 @@
 #include <linux/prefetch.h>
 
 #include <asm/sync_bitops.h>
+#include <asm/mshyperv.h>
 
 #include "hyperv_net.h"
 #include "netvsc_trace.h"
@@ -562,7 +563,10 @@ static int negotiate_nvsp_ver(struct hv_device *device,
 	init_packet->msg.v2_msg.send_ndis_config.capability.ieee8021q = 1;
 
 	if (nvsp_ver >= NVSP_PROTOCOL_VERSION_5) {
-		init_packet->msg.v2_msg.send_ndis_config.capability.sriov = 1;
+		if (hv_is_isolation_supported())
+			netdev_info(ndev, "SR-IOV not advertised by guests on the host supporting isolation\n");
+		else
+			init_packet->msg.v2_msg.send_ndis_config.capability.sriov = 1;
 
 		/* Teaming bit is needed to receive link speed updates */
 		init_packet->msg.v2_msg.send_ndis_config.capability.teaming = 1;
@@ -609,6 +613,13 @@ static int netvsc_connect_vsp(struct hv_device *device,
 		goto cleanup;
 	}
 
+	if (hv_is_isolation_supported() && net_device->nvsp_version < NVSP_PROTOCOL_VERSION_61) {
+		netdev_err(ndev, "Invalid NVSP version 0x%x (expected >= 0x%x) from the host supporting isolation\n",
+			   net_device->nvsp_version, NVSP_PROTOCOL_VERSION_61);
+		ret = -EPROTO;
+		goto cleanup;
+	}
+
 	pr_debug("Negotiated NVSP version:%x\n", net_device->nvsp_version);
 
 	/* Send the ndis version */
@@ -1416,7 +1427,10 @@ static void netvsc_receive_inband(struct net_device *ndev,
 		break;
 
 	case NVSP_MSG4_TYPE_SEND_VF_ASSOCIATION:
-		netvsc_send_vf(ndev, nvmsg, msglen);
+		if (hv_is_isolation_supported())
+			netdev_err(ndev, "Ignore VF_ASSOCIATION msg from the host supporting isolation\n");
+		else
+			netvsc_send_vf(ndev, nvmsg, msglen);
 		break;
 	}
 }

drivers/pci/controller/pci-hyperv.c

@@ -1216,7 +1216,7 @@ static void hv_irq_unmask(struct irq_data *data)
 	params = &hbus->retarget_msi_interrupt_params;
 	memset(params, 0, sizeof(*params));
 	params->partition_id = HV_PARTITION_ID_SELF;
-	params->int_entry.source = 1; /* MSI(-X) */
+	params->int_entry.source = HV_INTERRUPT_SOURCE_MSI;
 	hv_set_msi_entry_from_desc(&params->int_entry.msi_entry, msi_desc);
 	params->device_id = (hbus->hdev->dev_instance.b[5] << 24) |
 			   (hbus->hdev->dev_instance.b[4] << 16) |

include/acpi/acpi_numa.h

@@ -30,6 +30,10 @@ static inline int pxm_to_node(int pxm)
 {
 	return 0;
 }
+static inline int node_to_pxm(int node)
+{
+	return 0;
+}
 #endif				/* CONFIG_ACPI_NUMA */
 
 #ifdef CONFIG_ACPI_HMAT

include/asm-generic/hyperv-tlfs.h

@@ -88,7 +88,8 @@
 #define HV_CONNECT_PORT				BIT(7)
 #define HV_ACCESS_STATS				BIT(8)
 #define HV_DEBUGGING				BIT(11)
-#define HV_CPU_POWER_MANAGEMENT			BIT(12)
+#define HV_CPU_MANAGEMENT			BIT(12)
+#define HV_ISOLATION				BIT(22)
 
 
 /*
@@ -141,6 +142,9 @@ struct ms_hyperv_tsc_page {
 #define HVCALL_FLUSH_VIRTUAL_ADDRESS_SPACE_EX	0x0013
 #define HVCALL_FLUSH_VIRTUAL_ADDRESS_LIST_EX	0x0014
 #define HVCALL_SEND_IPI_EX			0x0015
+#define HVCALL_GET_PARTITION_ID			0x0046
+#define HVCALL_DEPOSIT_MEMORY			0x0048
+#define HVCALL_CREATE_VP			0x004e
 #define HVCALL_GET_VP_REGISTERS			0x0050
 #define HVCALL_SET_VP_REGISTERS			0x0051
 #define HVCALL_POST_MESSAGE			0x005c
@@ -148,6 +152,9 @@ struct ms_hyperv_tsc_page {
 #define HVCALL_POST_DEBUG_DATA			0x0069
 #define HVCALL_RETRIEVE_DEBUG_DATA		0x006a
 #define HVCALL_RESET_DEBUG_SESSION		0x006b
+#define HVCALL_ADD_LOGICAL_PROCESSOR		0x0076
+#define HVCALL_MAP_DEVICE_INTERRUPT		0x007c
+#define HVCALL_UNMAP_DEVICE_INTERRUPT		0x007d
 #define HVCALL_RETARGET_INTERRUPT		0x007e
 #define HVCALL_FLUSH_GUEST_PHYSICAL_ADDRESS_SPACE 0x00af
 #define HVCALL_FLUSH_GUEST_PHYSICAL_ADDRESS_LIST 0x00b0
@@ -407,19 +414,144 @@ struct hv_tlb_flush_ex {
 	u64 gva_list[];
 } __packed;
 
+/* HvGetPartitionId hypercall (output only) */
+struct hv_get_partition_id {
+	u64 partition_id;
+} __packed;
+
+/* HvDepositMemory hypercall */
+struct hv_deposit_memory {
+	u64 partition_id;
+	u64 gpa_page_list[];
+} __packed;
+
+struct hv_proximity_domain_flags {
+	u32 proximity_preferred : 1;
+	u32 reserved : 30;
+	u32 proximity_info_valid : 1;
+} __packed;
+
+/* Not a union in windows but useful for zeroing */
+union hv_proximity_domain_info {
+	struct {
+		u32 domain_id;
+		struct hv_proximity_domain_flags flags;
+	};
+	u64 as_uint64;
+} __packed;
+
+struct hv_lp_startup_status {
+	u64 hv_status;
+	u64 substatus1;
+	u64 substatus2;
+	u64 substatus3;
+	u64 substatus4;
+	u64 substatus5;
+	u64 substatus6;
+} __packed;
+
+/* HvAddLogicalProcessor hypercall */
+struct hv_add_logical_processor_in {
+	u32 lp_index;
+	u32 apic_id;
+	union hv_proximity_domain_info proximity_domain_info;
+	u64 flags;
+} __packed;
+
+struct hv_add_logical_processor_out {
+	struct hv_lp_startup_status startup_status;
+} __packed;
+
+enum HV_SUBNODE_TYPE
+{
+    HvSubnodeAny = 0,
+    HvSubnodeSocket = 1,
+    HvSubnodeAmdNode = 2,
+    HvSubnodeL3 = 3,
+    HvSubnodeCount = 4,
+    HvSubnodeInvalid = -1
+};
+
+/* HvCreateVp hypercall */
+struct hv_create_vp {
+	u64 partition_id;
+	u32 vp_index;
+	u8 padding[3];
+	u8 subnode_type;
+	u64 subnode_id;
+	union hv_proximity_domain_info proximity_domain_info;
+	u64 flags;
+} __packed;
+
+enum hv_interrupt_source {
+	HV_INTERRUPT_SOURCE_MSI = 1, /* MSI and MSI-X */
+	HV_INTERRUPT_SOURCE_IOAPIC,
+};
+
+union hv_msi_address_register {
+	u32 as_uint32;
+	struct {
+		u32 reserved1:2;
+		u32 destination_mode:1;
+		u32 redirection_hint:1;
+		u32 reserved2:8;
+		u32 destination_id:8;
+		u32 msi_base:12;
+	};
+} __packed;
+
+union hv_msi_data_register {
+	u32 as_uint32;
+	struct {
+		u32 vector:8;
+		u32 delivery_mode:3;
+		u32 reserved1:3;
+		u32 level_assert:1;
+		u32 trigger_mode:1;
+		u32 reserved2:16;
+	};
+} __packed;
+
 /* HvRetargetDeviceInterrupt hypercall */
 union hv_msi_entry {
 	u64 as_uint64;
 	struct {
-		u32 address;
-		u32 data;
+		union hv_msi_address_register address;
+		union hv_msi_data_register data;
 	} __packed;
 };
 
+union hv_ioapic_rte {
+	u64 as_uint64;
+
+	struct {
+		u32 vector:8;
+		u32 delivery_mode:3;
+		u32 destination_mode:1;
+		u32 delivery_status:1;
+		u32 interrupt_polarity:1;
+		u32 remote_irr:1;
+		u32 trigger_mode:1;
+		u32 interrupt_mask:1;
+		u32 reserved1:15;
+
+		u32 reserved2:24;
+		u32 destination_id:8;
+	};
+
+	struct {
+		u32 low_uint32;
+		u32 high_uint32;
+	};
+} __packed;
+
 struct hv_interrupt_entry {
-	u32 source;			/* 1 for MSI(-X) */
+	u32 source;
 	u32 reserved1;
-	union hv_msi_entry msi_entry;
+	union {
+		union hv_msi_entry msi_entry;
+		union hv_ioapic_rte ioapic_rte;
+	};
 } __packed;
 
 /*
@@ -494,4 +626,117 @@ struct hv_set_vp_registers_input {
 	} element[];
 } __packed;
 
+enum hv_device_type {
+	HV_DEVICE_TYPE_LOGICAL = 0,
+	HV_DEVICE_TYPE_PCI = 1,
+	HV_DEVICE_TYPE_IOAPIC = 2,
+	HV_DEVICE_TYPE_ACPI = 3,
+};
+
+typedef u16 hv_pci_rid;
+typedef u16 hv_pci_segment;
+typedef u64 hv_logical_device_id;
+union hv_pci_bdf {
+	u16 as_uint16;
+
+	struct {
+		u8 function:3;
+		u8 device:5;
+		u8 bus;
+	};
+} __packed;
+
+union hv_pci_bus_range {
+	u16 as_uint16;
+
+	struct {
+		u8 subordinate_bus;
+		u8 secondary_bus;
+	};
+} __packed;
+
+union hv_device_id {
+	u64 as_uint64;
+
+	struct {
+		u64 reserved0:62;
+		u64 device_type:2;
+	};
+
+	/* HV_DEVICE_TYPE_LOGICAL */
+	struct {
+		u64 id:62;
+		u64 device_type:2;
+	} logical;
+
+	/* HV_DEVICE_TYPE_PCI */
+	struct {
+		union {
+			hv_pci_rid rid;
+			union hv_pci_bdf bdf;
+		};
+
+		hv_pci_segment segment;
+		union hv_pci_bus_range shadow_bus_range;
+
+		u16 phantom_function_bits:2;
+		u16 source_shadow:1;
+
+		u16 rsvdz0:11;
+		u16 device_type:2;
+	} pci;
+
+	/* HV_DEVICE_TYPE_IOAPIC */
+	struct {
+		u8 ioapic_id;
+		u8 rsvdz0;
+		u16 rsvdz1;
+		u16 rsvdz2;
+
+		u16 rsvdz3:14;
+		u16 device_type:2;
+	} ioapic;
+
+	/* HV_DEVICE_TYPE_ACPI */
+	struct {
+		u32 input_mapping_base;
+		u32 input_mapping_count:30;
+		u32 device_type:2;
+	} acpi;
+} __packed;
+
+enum hv_interrupt_trigger_mode {
+	HV_INTERRUPT_TRIGGER_MODE_EDGE = 0,
+	HV_INTERRUPT_TRIGGER_MODE_LEVEL = 1,
+};
+
+struct hv_device_interrupt_descriptor {
+	u32 interrupt_type;
+	u32 trigger_mode;
+	u32 vector_count;
+	u32 reserved;
+	struct hv_device_interrupt_target target;
+} __packed;
+
+struct hv_input_map_device_interrupt {
+	u64 partition_id;
+	u64 device_id;
+	u64 flags;
+	struct hv_interrupt_entry logical_interrupt_entry;
+	struct hv_device_interrupt_descriptor interrupt_descriptor;
+} __packed;
+
+struct hv_output_map_device_interrupt {
+	struct hv_interrupt_entry interrupt_entry;
+} __packed;
+
+struct hv_input_unmap_device_interrupt {
+	u64 partition_id;
+	u64 device_id;
+	struct hv_interrupt_entry interrupt_entry;
+} __packed;
+
+#define HV_SOURCE_SHADOW_NONE               0x0
+#define HV_SOURCE_SHADOW_BRIDGE_BUS_RANGE   0x1
+
 #endif

include/asm-generic/mshyperv.h

@@ -27,11 +27,14 @@
 
 struct ms_hyperv_info {
 	u32 features;
+	u32 features_b;
 	u32 misc_features;
 	u32 hints;
 	u32 nested_features;
 	u32 max_vp_index;
 	u32 max_lp_index;
+	u32 isolation_config_a;
+	u32 isolation_config_b;
 };
 extern struct ms_hyperv_info ms_hyperv;
 
@@ -169,6 +172,8 @@ void hyperv_report_panic(struct pt_regs *regs, long err, bool in_die);
 void hyperv_report_panic_msg(phys_addr_t pa, size_t size);
 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);
 void hyperv_cleanup(void);
 #else /* CONFIG_HYPERV */
 static inline bool hv_is_hyperv_initialized(void) { return false; }

include/linux/hyperv.h

@@ -785,6 +785,7 @@ struct vmbus_device {
 	u16  dev_type;
 	guid_t guid;
 	bool perf_device;
+	bool allowed_in_isolated;
 };
 
 struct vmbus_channel {
@@ -803,6 +804,7 @@ struct vmbus_channel {
 	u8 monitor_bit;
 
 	bool rescind; /* got rescind msg */
+	bool rescind_ref; /* got rescind msg, got channel reference */
 	struct completion rescind_event;
 
 	u32 ringbuffer_gpadlhandle;
@@ -1471,6 +1473,7 @@ void vmbus_free_mmio(resource_size_t start, resource_size_t size);
 #define ICMSGTYPE_SHUTDOWN		3
 #define ICMSGTYPE_TIMESYNC		4
 #define ICMSGTYPE_VSS			5
+#define ICMSGTYPE_FCOPY			7
 
 #define ICMSGHDRFLAG_TRANSACTION	1
 #define ICMSGHDRFLAG_REQUEST		2
@@ -1514,11 +1517,17 @@ struct icmsg_hdr {
 	u8 reserved[2];
 } __packed;
 
+#define IC_VERSION_NEGOTIATION_MAX_VER_COUNT 100
+#define ICMSG_HDR (sizeof(struct vmbuspipe_hdr) + sizeof(struct icmsg_hdr))
+#define ICMSG_NEGOTIATE_PKT_SIZE(icframe_vercnt, icmsg_vercnt) \
+	(ICMSG_HDR + sizeof(struct icmsg_negotiate) + \
+	 (((icframe_vercnt) + (icmsg_vercnt)) * sizeof(struct ic_version)))
+
 struct icmsg_negotiate {
 	u16 icframe_vercnt;
 	u16 icmsg_vercnt;
 	u32 reserved;
-	struct ic_version icversion_data[1]; /* any size array */
+	struct ic_version icversion_data[]; /* any size array */
 } __packed;
 
 struct shutdown_msg_data {
@@ -1569,7 +1578,7 @@ struct hyperv_service_callback {
 };
 
 #define MAX_SRV_VER	0x7ffffff
-extern bool vmbus_prep_negotiate_resp(struct icmsg_hdr *icmsghdrp, u8 *buf,
+extern bool vmbus_prep_negotiate_resp(struct icmsg_hdr *icmsghdrp, u8 *buf, u32 buflen,
 				const int *fw_version, int fw_vercnt,
 				const int *srv_version, int srv_vercnt,
 				int *nego_fw_version, int *nego_srv_version);