5 files changed, 759 insertions, 16 deletions

diff --git a/arch/x86/hyperv/Makefile b/arch/x86/hyperv/Makefile
index 89b1f74d3225..48e2c51464e8 100644
--- a/arch/x86/hyperv/Makefile
+++ b/arch/x86/hyperv/Makefile
@@ -1,6 +1,6 @@
 # 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
diff --git a/arch/x86/hyperv/hv_init.c b/arch/x86/hyperv/hv_init.c
index e04d90af4c27..b81047dec1da 100644
--- a/arch/x86/hyperv/hv_init.c
+++ b/arch/x86/hyperv/hv_init.c
@@ -10,12 +10,14 @@
 #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>
 #include <asm/hyperv-tlfs.h>
 #include <asm/mshyperv.h>
 #include <asm/idtentry.h>
+#include <linux/kexec.h>
 #include <linux/version.h>
 #include <linux/vmalloc.h>
 #include <linux/mm.h>
@@ -25,6 +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);
@@ -41,6 +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);
 
@@ -73,12 +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);
 
@@ -205,14 +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);
@@ -261,6 +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
@@ -312,6 +341,43 @@ static struct syscore_ops hv_syscore_ops = {
 	.resume		= hv_resume,
 };
 
+static void (* __initdata old_setup_percpu_clockev)(void);
+
+static void __init hv_stimer_setup_percpu_clockev(void)
+{
+	/*
+	 * Ignore any errors in setting up stimer clockevents
+	 * as we can run with the LAPIC timer as a fallback.
+	 */
+	(void)hv_stimer_alloc();
+
+	/*
+	 * Still register the LAPIC timer, because the direct-mode STIMER is
+	 * not supported by old versions of Hyper-V. This also allows users
+	 * to switch to LAPIC timer via /sys, if they want to.
+	 */
+	if (old_setup_percpu_clockev)
+		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.
@@ -346,6 +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);
@@ -386,14 +458,45 @@ 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);
+	}
 
 	/*
-	 * Ignore any errors in setting up stimer clockevents
-	 * as we can run with the LAPIC timer as a fallback.
+	 * hyperv_init() is called before LAPIC is initialized: see
+	 * apic_intr_mode_init() -> x86_platform.apic_post_init() and
+	 * apic_bsp_setup() -> setup_local_APIC(). The direct-mode STIMER
+	 * depends on LAPIC, so hv_stimer_alloc() should be called from
+	 * x86_init.timers.setup_percpu_clockev.
 	 */
-	(void)hv_stimer_alloc();
+	old_setup_percpu_clockev = x86_init.timers.setup_percpu_clockev;
+	x86_init.timers.setup_percpu_clockev = hv_stimer_setup_percpu_clockev;
 
 	hv_apic_init();
 
@@ -401,6 +504,22 @@ 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:
@@ -525,6 +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);
diff --git a/arch/x86/hyperv/hv_proc.c b/arch/x86/hyperv/hv_proc.c
new file mode 100644
index 000000000000..60461e598239
--- /dev/null
+++ b/arch/x86/hyperv/hv_proc.c
@@ -0,0 +1,219 @@
+// 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;
+}
+
diff --git a/arch/x86/hyperv/irqdomain.c b/arch/x86/hyperv/irqdomain.c
new file mode 100644
index 000000000000..4421a8d92e23
--- /dev/null
+++ b/arch/x86/hyperv/irqdomain.c
@@ -0,0 +1,385 @@
+// SPDX-License-Identifier: GPL-2.0
+
+/*
+ * Irqdomain for Linux to run as the root partition on Microsoft Hypervisor.
+ *
+ * Authors:
+ *  Sunil Muthuswamy <[email protected]>
+ *  Wei Liu <[email protected]>
+ */
+
+#include <linux/pci.h>
+#include <linux/irq.h>
+#include <asm/mshyperv.h>
+
+static int hv_map_interrupt(union hv_device_id device_id, bool level,
+		int cpu, int vector, struct hv_interrupt_entry *entry)
+{
+	struct hv_input_map_device_interrupt *input;
+	struct hv_output_map_device_interrupt *output;
+	struct hv_device_interrupt_descriptor *intr_desc;
+	unsigned long flags;
+	u64 status;
+	int nr_bank, var_size;
+
+	local_irq_save(flags);
+
+	input = *this_cpu_ptr(hyperv_pcpu_input_arg);
+	output = *this_cpu_ptr(hyperv_pcpu_output_arg);
+
+	intr_desc = &input->interrupt_descriptor;
+	memset(input, 0, sizeof(*input));
+	input->partition_id = hv_current_partition_id;
+	input->device_id = device_id.as_uint64;
+	intr_desc->interrupt_type = HV_X64_INTERRUPT_TYPE_FIXED;
+	intr_desc->vector_count = 1;
+	intr_desc->target.vector = vector;
+
+	if (level)
+		intr_desc->trigger_mode = HV_INTERRUPT_TRIGGER_MODE_LEVEL;
+	else
+		intr_desc->trigger_mode = HV_INTERRUPT_TRIGGER_MODE_EDGE;
+
+	intr_desc->target.vp_set.valid_bank_mask = 0;
+	intr_desc->target.vp_set.format = HV_GENERIC_SET_SPARSE_4K;
+	nr_bank = cpumask_to_vpset(&(intr_desc->target.vp_set), cpumask_of(cpu));
+	if (nr_bank < 0) {
+		local_irq_restore(flags);
+		pr_err("%s: unable to generate VP set\n", __func__);
+		return EINVAL;
+	}
+	intr_desc->target.flags = HV_DEVICE_INTERRUPT_TARGET_PROCESSOR_SET;
+
+	/*
+	 * var-sized hypercall, var-size starts after vp_mask (thus
+	 * vp_set.format does not count, but vp_set.valid_bank_mask
+	 * does).
+	 */
+	var_size = nr_bank + 1;
+
+	status = hv_do_rep_hypercall(HVCALL_MAP_DEVICE_INTERRUPT, 0, var_size,
+			input, output);
+	*entry = output->interrupt_entry;
+
+	local_irq_restore(flags);
+
+	if ((status & HV_HYPERCALL_RESULT_MASK) != HV_STATUS_SUCCESS)
+		pr_err("%s: hypercall failed, status %lld\n", __func__, status);
+
+	return status & HV_HYPERCALL_RESULT_MASK;
+}
+
+static int hv_unmap_interrupt(u64 id, struct hv_interrupt_entry *old_entry)
+{
+	unsigned long flags;
+	struct hv_input_unmap_device_interrupt *input;
+	struct hv_interrupt_entry *intr_entry;
+	u64 status;
+
+	local_irq_save(flags);
+	input = *this_cpu_ptr(hyperv_pcpu_input_arg);
+
+	memset(input, 0, sizeof(*input));
+	intr_entry = &input->interrupt_entry;
+	input->partition_id = hv_current_partition_id;
+	input->device_id = id;
+	*intr_entry = *old_entry;
+
+	status = hv_do_hypercall(HVCALL_UNMAP_DEVICE_INTERRUPT, input, NULL);
+	local_irq_restore(flags);
+
+	return status & HV_HYPERCALL_RESULT_MASK;
+}
+
+#ifdef CONFIG_PCI_MSI
+struct rid_data {
+	struct pci_dev *bridge;
+	u32 rid;
+};
+
+static int get_rid_cb(struct pci_dev *pdev, u16 alias, void *data)
+{
+	struct rid_data *rd = data;
+	u8 bus = PCI_BUS_NUM(rd->rid);
+
+	if (pdev->bus->number != bus || PCI_BUS_NUM(alias) != bus) {
+		rd->bridge = pdev;
+		rd->rid = alias;
+	}
+
+	return 0;
+}
+
+static union hv_device_id hv_build_pci_dev_id(struct pci_dev *dev)
+{
+	union hv_device_id dev_id;
+	struct rid_data data = {
+		.bridge = NULL,
+		.rid = PCI_DEVID(dev->bus->number, dev->devfn)
+	};
+
+	pci_for_each_dma_alias(dev, get_rid_cb, &data);
+
+	dev_id.as_uint64 = 0;
+	dev_id.device_type = HV_DEVICE_TYPE_PCI;
+	dev_id.pci.segment = pci_domain_nr(dev->bus);
+
+	dev_id.pci.bdf.bus = PCI_BUS_NUM(data.rid);
+	dev_id.pci.bdf.device = PCI_SLOT(data.rid);
+	dev_id.pci.bdf.function = PCI_FUNC(data.rid);
+	dev_id.pci.source_shadow = HV_SOURCE_SHADOW_NONE;
+
+	if (data.bridge) {
+		int pos;
+
+		/*
+		 * Microsoft Hypervisor requires a bus range when the bridge is
+		 * running in PCI-X mode.
+		 *
+		 * To distinguish conventional vs PCI-X bridge, we can check
+		 * the bridge's PCI-X Secondary Status Register, Secondary Bus
+		 * Mode and Frequency bits. See PCI Express to PCI/PCI-X Bridge
+		 * Specification Revision 1.0 5.2.2.1.3.
+		 *
+		 * Value zero means it is in conventional mode, otherwise it is
+		 * in PCI-X mode.
+		 */
+
+		pos = pci_find_capability(data.bridge, PCI_CAP_ID_PCIX);
+		if (pos) {
+			u16 status;
+
+			pci_read_config_word(data.bridge, pos +
+					PCI_X_BRIDGE_SSTATUS, &status);
+
+			if (status & PCI_X_SSTATUS_FREQ) {
+				/* Non-zero, PCI-X mode */
+				u8 sec_bus, sub_bus;
+
+				dev_id.pci.source_shadow = HV_SOURCE_SHADOW_BRIDGE_BUS_RANGE;
+
+				pci_read_config_byte(data.bridge, PCI_SECONDARY_BUS, &sec_bus);
+				dev_id.pci.shadow_bus_range.secondary_bus = sec_bus;
+				pci_read_config_byte(data.bridge, PCI_SUBORDINATE_BUS, &sub_bus);
+				dev_id.pci.shadow_bus_range.subordinate_bus = sub_bus;
+			}
+		}
+	}
+
+	return dev_id;
+}
+
+static int hv_map_msi_interrupt(struct pci_dev *dev, int cpu, int vector,
+				struct hv_interrupt_entry *entry)
+{
+	union hv_device_id device_id = hv_build_pci_dev_id(dev);
+
+	return hv_map_interrupt(device_id, false, cpu, vector, entry);
+}
+
+static inline void entry_to_msi_msg(struct hv_interrupt_entry *entry, struct msi_msg *msg)
+{
+	/* High address is always 0 */
+	msg->address_hi = 0;
+	msg->address_lo = entry->msi_entry.address.as_uint32;
+	msg->data = entry->msi_entry.data.as_uint32;
+}
+
+static int hv_unmap_msi_interrupt(struct pci_dev *dev, struct hv_interrupt_entry *old_entry);
+static void hv_irq_compose_msi_msg(struct irq_data *data, struct msi_msg *msg)
+{
+	struct msi_desc *msidesc;
+	struct pci_dev *dev;
+	struct hv_interrupt_entry out_entry, *stored_entry;
+	struct irq_cfg *cfg = irqd_cfg(data);
+	cpumask_t *affinity;
+	int cpu;
+	u64 status;
+
+	msidesc = irq_data_get_msi_desc(data);
+	dev = msi_desc_to_pci_dev(msidesc);
+
+	if (!cfg) {
+		pr_debug("%s: cfg is NULL", __func__);
+		return;
+	}
+
+	affinity = irq_data_get_effective_affinity_mask(data);
+	cpu = cpumask_first_and(affinity, cpu_online_mask);
+
+	if (data->chip_data) {
+		/*
+		 * This interrupt is already mapped. Let's unmap first.
+		 *
+		 * We don't use retarget interrupt hypercalls here because
+		 * Microsoft Hypervisor doens't allow root to change the vector
+		 * or specify VPs outside of the set that is initially used
+		 * during mapping.
+		 */
+		stored_entry = data->chip_data;
+		data->chip_data = NULL;
+
+		status = hv_unmap_msi_interrupt(dev, stored_entry);
+
+		kfree(stored_entry);
+
+		if (status != HV_STATUS_SUCCESS) {
+			pr_debug("%s: failed to unmap, status %lld", __func__, status);
+			return;
+		}
+	}
+
+	stored_entry = kzalloc(sizeof(*stored_entry), GFP_ATOMIC);
+	if (!stored_entry) {
+		pr_debug("%s: failed to allocate chip data\n", __func__);
+		return;
+	}
+
+	status = hv_map_msi_interrupt(dev, cpu, cfg->vector, &out_entry);
+	if (status != HV_STATUS_SUCCESS) {
+		kfree(stored_entry);
+		return;
+	}
+
+	*stored_entry = out_entry;
+	data->chip_data = stored_entry;
+	entry_to_msi_msg(&out_entry, msg);
+
+	return;
+}
+
+static int hv_unmap_msi_interrupt(struct pci_dev *dev, struct hv_interrupt_entry *old_entry)
+{
+	return hv_unmap_interrupt(hv_build_pci_dev_id(dev).as_uint64, old_entry);
+}
+
+static void hv_teardown_msi_irq_common(struct pci_dev *dev, struct msi_desc *msidesc, int irq)
+{
+	u64 status;
+	struct hv_interrupt_entry old_entry;
+	struct irq_desc *desc;
+	struct irq_data *data;
+	struct msi_msg msg;
+
+	desc = irq_to_desc(irq);
+	if (!desc) {
+		pr_debug("%s: no irq desc\n", __func__);
+		return;
+	}
+
+	data = &desc->irq_data;
+	if (!data) {
+		pr_debug("%s: no irq data\n", __func__);
+		return;
+	}
+
+	if (!data->chip_data) {
+		pr_debug("%s: no chip data\n!", __func__);
+		return;
+	}
+
+	old_entry = *(struct hv_interrupt_entry *)data->chip_data;
+	entry_to_msi_msg(&old_entry, &msg);
+
+	kfree(data->chip_data);
+	data->chip_data = NULL;
+
+	status = hv_unmap_msi_interrupt(dev, &old_entry);
+
+	if (status != HV_STATUS_SUCCESS) {
+		pr_err("%s: hypercall failed, status %lld\n", __func__, status);
+		return;
+	}
+}
+
+static void hv_msi_domain_free_irqs(struct irq_domain *domain, struct device *dev)
+{
+	int i;
+	struct msi_desc *entry;
+	struct pci_dev *pdev;
+
+	if (WARN_ON_ONCE(!dev_is_pci(dev)))
+		return;
+
+	pdev = to_pci_dev(dev);
+
+	for_each_pci_msi_entry(entry, pdev) {
+		if (entry->irq) {
+			for (i = 0; i < entry->nvec_used; i++) {
+				hv_teardown_msi_irq_common(pdev, entry, entry->irq + i);
+				irq_domain_free_irqs(entry->irq + i, 1);
+			}
+		}
+	}
+}
+
+/*
+ * IRQ Chip for MSI PCI/PCI-X/PCI-Express Devices,
+ * which implement the MSI or MSI-X Capability Structure.
+ */
+static struct irq_chip hv_pci_msi_controller = {
+	.name			= "HV-PCI-MSI",
+	.irq_unmask		= pci_msi_unmask_irq,
+	.irq_mask		= pci_msi_mask_irq,
+	.irq_ack		= irq_chip_ack_parent,
+	.irq_retrigger		= irq_chip_retrigger_hierarchy,
+	.irq_compose_msi_msg	= hv_irq_compose_msi_msg,
+	.irq_set_affinity	= msi_domain_set_affinity,
+	.flags			= IRQCHIP_SKIP_SET_WAKE,
+};
+
+static struct msi_domain_ops pci_msi_domain_ops = {
+	.domain_free_irqs	= hv_msi_domain_free_irqs,
+	.msi_prepare		= pci_msi_prepare,
+};
+
+static struct msi_domain_info hv_pci_msi_domain_info = {
+	.flags		= MSI_FLAG_USE_DEF_DOM_OPS | MSI_FLAG_USE_DEF_CHIP_OPS |
+			  MSI_FLAG_PCI_MSIX,
+	.ops		= &pci_msi_domain_ops,
+	.chip		= &hv_pci_msi_controller,
+	.handler	= handle_edge_irq,
+	.handler_name	= "edge",
+};
+
+struct irq_domain * __init hv_create_pci_msi_domain(void)
+{
+	struct irq_domain *d = NULL;
+	struct fwnode_handle *fn;
+
+	fn = irq_domain_alloc_named_fwnode("HV-PCI-MSI");
+	if (fn)
+		d = pci_msi_create_irq_domain(fn, &hv_pci_msi_domain_info, x86_vector_domain);
+
+	/* No point in going further if we can't get an irq domain */
+	BUG_ON(!d);
+
+	return d;
+}
+
+#endif /* CONFIG_PCI_MSI */
+
+int hv_unmap_ioapic_interrupt(int ioapic_id, struct hv_interrupt_entry *entry)
+{
+	union hv_device_id device_id;
+
+	device_id.as_uint64 = 0;
+	device_id.device_type = HV_DEVICE_TYPE_IOAPIC;
+	device_id.ioapic.ioapic_id = (u8)ioapic_id;
+
+	return hv_unmap_interrupt(device_id.as_uint64, entry);
+}
+EXPORT_SYMBOL_GPL(hv_unmap_ioapic_interrupt);
+
+int hv_map_ioapic_interrupt(int ioapic_id, bool level, int cpu, int vector,
+		struct hv_interrupt_entry *entry)
+{
+	union hv_device_id device_id;
+
+	device_id.as_uint64 = 0;
+	device_id.device_type = HV_DEVICE_TYPE_IOAPIC;
+	device_id.ioapic.ioapic_id = (u8)ioapic_id;
+
+	return hv_map_interrupt(device_id, level, cpu, vector, entry);
+}
+EXPORT_SYMBOL_GPL(hv_map_ioapic_interrupt);
diff --git a/arch/x86/hyperv/mmu.c b/arch/x86/hyperv/mmu.c
index 5208ba49c89a..2c87350c1fb0 100644
--- a/arch/x86/hyperv/mmu.c
+++ b/arch/x86/hyperv/mmu.c
@@ -66,11 +66,17 @@ static void hyperv_flush_tlb_others(const struct cpumask *cpus,
 	if (!hv_hypercall_pg)
 		goto do_native;
 
-	if (cpumask_empty(cpus))
-		return;
-
 	local_irq_save(flags);
 
+	/*
+	 * Only check the mask _after_ interrupt has been disabled to avoid the
+	 * mask changing under our feet.
+	 */
+	if (cpumask_empty(cpus)) {
+		local_irq_restore(flags);
+		return;
+	}
+
 	flush_pcpu = (struct hv_tlb_flush **)
 		     this_cpu_ptr(hyperv_pcpu_input_arg);