Merge feature/vpci/5.15 into v5.15

* commit '92c970cf37ef2b7d159905ca9df9e25f86618248':
  PCI: hv: Avoid the retarget interrupt hypercall in irq_unmask() on ARM64
  PCI: hv: Only reuse existing IRTE allocation for Multi-MSI
  Drivers: hv: vmbus: Propagate VMbus coherence to each VMbus device
  PCI: hv: Add arm64 Hyper-V vPCI support
  PCI: hv: Make the code arch neutral by adding arch specific interfaces

arch/arm64/include/asm/hyperv-tlfs.h

@@ -64,6 +64,15 @@
 #define HV_REGISTER_STIMER0_CONFIG	0x000B0000
 #define HV_REGISTER_STIMER0_COUNT	0x000B0001
 
+union hv_msi_entry {
+	u64 as_uint64[2];
+	struct {
+		u64 address;
+		u32 data;
+		u32 reserved;
+	} __packed;
+};
+
 #include <asm-generic/hyperv-tlfs.h>
 
 #endif

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

@@ -585,6 +585,39 @@ enum hv_interrupt_type {
 	HV_X64_INTERRUPT_TYPE_MAXIMUM           = 0x000A,
 };
 
+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 {
+		union hv_msi_address_register address;
+		union hv_msi_data_register data;
+	} __packed;
+};
+
 #include <asm-generic/hyperv-tlfs.h>
 
 #endif

drivers/hv/hv_common.c

@@ -20,6 +20,7 @@
 #include <linux/panic_notifier.h>
 #include <linux/ptrace.h>
 #include <linux/slab.h>
+#include <linux/dma-map-ops.h>
 #include <asm/hyperv-tlfs.h>
 #include <asm/mshyperv.h>
 
@@ -216,6 +217,16 @@ bool hv_query_ext_cap(u64 cap_query)
 }
 EXPORT_SYMBOL_GPL(hv_query_ext_cap);
 
+void hv_setup_dma_ops(struct device *dev, bool coherent)
+{
+	/*
+	 * Hyper-V does not offer a vIOMMU in the guest
+	 * VM, so pass 0/NULL for the IOMMU settings
+	 */
+	arch_setup_dma_ops(dev, 0, 0, NULL, coherent);
+}
+EXPORT_SYMBOL_GPL(hv_setup_dma_ops);
+
 bool hv_is_hibernation_supported(void)
 {
 	return !hv_root_partition && acpi_sleep_state_supported(ACPI_STATE_S4);

drivers/hv/vmbus_drv.c

@@ -904,6 +904,14 @@ static int vmbus_probe(struct device *child_device)
 	struct hv_device *dev = device_to_hv_device(child_device);
 	const struct hv_vmbus_device_id *dev_id;
 
+	/*
+	 * On ARM64, propagate the DMA coherence setting from the top level
+	 * VMbus ACPI device to the child VMbus device being added here.
+	 * On x86/x64 coherence is assumed and these calls have no effect.
+	 */
+	hv_setup_dma_ops(child_device,
+		device_get_dma_attr(&hv_acpi_dev->dev) == DEV_DMA_COHERENT);
+
 	dev_id = hv_vmbus_get_id(drv, dev);
 	if (drv->probe) {
 		ret = drv->probe(dev, dev_id);
@@ -2438,6 +2446,21 @@ static int vmbus_acpi_add(struct acpi_device *device)
 
 	hv_acpi_dev = device;
 
+	/*
+	 * Older versions of Hyper-V for ARM64 fail to include the _CCA
+	 * method on the top level VMbus device in the DSDT. But devices
+	 * are hardware coherent in all current Hyper-V use cases, so fix
+	 * up the ACPI device to behave as if _CCA is present and indicates
+	 * hardware coherence.
+	 */
+	ACPI_COMPANION_SET(&device->dev, device);
+	if (IS_ENABLED(CONFIG_ACPI_CCA_REQUIRED) &&
+	    device_get_dma_attr(&device->dev) == DEV_DMA_NOT_SUPPORTED) {
+		pr_info("No ACPI _CCA found; assuming coherent device I/O\n");
+		device->flags.cca_seen = true;
+		device->flags.coherent_dma = true;
+	}
+
 	result = acpi_walk_resources(device->handle, METHOD_NAME__CRS,
 					vmbus_walk_resources, NULL);
 

drivers/pci/Kconfig

@@ -184,7 +184,7 @@ config PCI_LABEL
 
 config PCI_HYPERV
 	tristate "Hyper-V PCI Frontend"
-	depends on X86_64 && HYPERV && PCI_MSI && PCI_MSI_IRQ_DOMAIN && SYSFS
+	depends on ((X86 && X86_64) || ARM64) && HYPERV && PCI_MSI && PCI_MSI_IRQ_DOMAIN && SYSFS
 	select PCI_HYPERV_INTERFACE
 	help
 	  The PCI device frontend driver allows the kernel to import arbitrary

drivers/pci/controller/Kconfig

@@ -280,7 +280,7 @@ config PCIE_BRCMSTB
 
 config PCI_HYPERV_INTERFACE
 	tristate "Hyper-V PCI Interface"
-	depends on X86 && HYPERV && PCI_MSI && PCI_MSI_IRQ_DOMAIN && X86_64
+	depends on ((X86 && X86_64) || ARM64) && HYPERV && PCI_MSI && PCI_MSI_IRQ_DOMAIN
 	help
 	  The Hyper-V PCI Interface is a helper driver allows other drivers to
 	  have a common interface with the Hyper-V PCI frontend driver.

drivers/pci/controller/pci-hyperv.c

@@ -43,13 +43,12 @@
 #include <linux/pci-ecam.h>
 #include <linux/delay.h>
 #include <linux/semaphore.h>
-#include <linux/irqdomain.h>
-#include <asm/irqdomain.h>
-#include <asm/apic.h>
 #include <linux/irq.h>
 #include <linux/msi.h>
 #include <linux/hyperv.h>
 #include <linux/refcount.h>
+#include <linux/irqdomain.h>
+#include <linux/acpi.h>
 #include <asm/mshyperv.h>
 
 /*
@@ -577,6 +576,388 @@ struct hv_pci_compl {
 
 static void hv_pci_onchannelcallback(void *context);
 
+#ifdef CONFIG_X86
+#define DELIVERY_MODE	APIC_DELIVERY_MODE_FIXED
+#define FLOW_HANDLER	handle_edge_irq
+#define FLOW_NAME	"edge"
+
+static int hv_pci_irqchip_init(void)
+{
+	return 0;
+}
+
+static struct irq_domain *hv_pci_get_root_domain(void)
+{
+	return x86_vector_domain;
+}
+
+static unsigned int hv_msi_get_int_vector(struct irq_data *data)
+{
+	struct irq_cfg *cfg = irqd_cfg(data);
+
+	return cfg->vector;
+}
+
+static int hv_msi_prepare(struct irq_domain *domain, struct device *dev,
+			  int nvec, msi_alloc_info_t *info)
+{
+	int ret = pci_msi_prepare(domain, dev, nvec, info);
+
+	/*
+	 * By using the interrupt remapper in the hypervisor IOMMU, contiguous
+	 * CPU vectors is not needed for multi-MSI
+	 */
+	if (info->type == X86_IRQ_ALLOC_TYPE_PCI_MSI)
+		info->flags &= ~X86_IRQ_ALLOC_CONTIGUOUS_VECTORS;
+
+	return ret;
+}
+
+/**
+ * hv_arch_irq_unmask() - "Unmask" the IRQ by setting its current
+ * affinity.
+ * @data:	Describes the IRQ
+ *
+ * Build new a destination for the MSI and make a hypercall to
+ * update the Interrupt Redirection Table. "Device Logical ID"
+ * is built out of this PCI bus's instance GUID and the function
+ * number of the device.
+ */
+static void hv_arch_irq_unmask(struct irq_data *data)
+{
+	struct msi_desc *msi_desc = irq_data_get_msi_desc(data);
+	struct hv_retarget_device_interrupt *params;
+	struct tran_int_desc *int_desc;
+	struct hv_pcibus_device *hbus;
+	struct cpumask *dest;
+	cpumask_var_t tmp;
+	struct pci_bus *pbus;
+	struct pci_dev *pdev;
+	unsigned long flags;
+	u32 var_size = 0;
+	int cpu, nr_bank;
+	u64 res;
+
+	dest = irq_data_get_effective_affinity_mask(data);
+	pdev = msi_desc_to_pci_dev(msi_desc);
+	pbus = pdev->bus;
+	hbus = container_of(pbus->sysdata, struct hv_pcibus_device, sysdata);
+	int_desc = data->chip_data;
+	if (!int_desc) {
+		dev_warn(&hbus->hdev->device, "%s() can not unmask irq %u\n",
+			 __func__, data->irq);
+		return;
+	}
+
+	spin_lock_irqsave(&hbus->retarget_msi_interrupt_lock, flags);
+
+	params = &hbus->retarget_msi_interrupt_params;
+	memset(params, 0, sizeof(*params));
+	params->partition_id = HV_PARTITION_ID_SELF;
+	params->int_entry.source = HV_INTERRUPT_SOURCE_MSI;
+	params->int_entry.msi_entry.address.as_uint32 = int_desc->address & 0xffffffff;
+	params->int_entry.msi_entry.data.as_uint32 = int_desc->data;
+	params->device_id = (hbus->hdev->dev_instance.b[5] << 24) |
+			   (hbus->hdev->dev_instance.b[4] << 16) |
+			   (hbus->hdev->dev_instance.b[7] << 8) |
+			   (hbus->hdev->dev_instance.b[6] & 0xf8) |
+			   PCI_FUNC(pdev->devfn);
+	params->int_target.vector = hv_msi_get_int_vector(data);
+
+	/*
+	 * Honoring apic->delivery_mode set to APIC_DELIVERY_MODE_FIXED by
+	 * setting the HV_DEVICE_INTERRUPT_TARGET_MULTICAST flag results in a
+	 * spurious interrupt storm. Not doing so does not seem to have a
+	 * negative effect (yet?).
+	 */
+
+	if (hbus->protocol_version >= PCI_PROTOCOL_VERSION_1_2) {
+		/*
+		 * PCI_PROTOCOL_VERSION_1_2 supports the VP_SET version of the
+		 * HVCALL_RETARGET_INTERRUPT hypercall, which also coincides
+		 * with >64 VP support.
+		 * ms_hyperv.hints & HV_X64_EX_PROCESSOR_MASKS_RECOMMENDED
+		 * is not sufficient for this hypercall.
+		 */
+		params->int_target.flags |=
+			HV_DEVICE_INTERRUPT_TARGET_PROCESSOR_SET;
+
+		if (!alloc_cpumask_var(&tmp, GFP_ATOMIC)) {
+			res = 1;
+			goto exit_unlock;
+		}
+
+		cpumask_and(tmp, dest, cpu_online_mask);
+		nr_bank = cpumask_to_vpset(&params->int_target.vp_set, tmp);
+		free_cpumask_var(tmp);
+
+		if (nr_bank <= 0) {
+			res = 1;
+			goto exit_unlock;
+		}
+
+		/*
+		 * 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 = 1 + nr_bank;
+	} else {
+		for_each_cpu_and(cpu, dest, cpu_online_mask) {
+			params->int_target.vp_mask |=
+				(1ULL << hv_cpu_number_to_vp_number(cpu));
+		}
+	}
+
+	res = hv_do_hypercall(HVCALL_RETARGET_INTERRUPT | (var_size << 17),
+			      params, NULL);
+
+exit_unlock:
+	spin_unlock_irqrestore(&hbus->retarget_msi_interrupt_lock, flags);
+
+	/*
+	 * During hibernation, when a CPU is offlined, the kernel tries
+	 * to move the interrupt to the remaining CPUs that haven't
+	 * been offlined yet. In this case, the below hv_do_hypercall()
+	 * always fails since the vmbus channel has been closed:
+	 * refer to cpu_disable_common() -> fixup_irqs() ->
+	 * irq_migrate_all_off_this_cpu() -> migrate_one_irq().
+	 *
+	 * Suppress the error message for hibernation because the failure
+	 * during hibernation does not matter (at this time all the devices
+	 * have been frozen). Note: the correct affinity info is still updated
+	 * into the irqdata data structure in migrate_one_irq() ->
+	 * irq_do_set_affinity() -> hv_set_affinity(), so later when the VM
+	 * resumes, hv_pci_restore_msi_state() is able to correctly restore
+	 * the interrupt with the correct affinity.
+	 */
+	if (!hv_result_success(res) && hbus->state != hv_pcibus_removing)
+		dev_err(&hbus->hdev->device,
+			"%s() failed: %#llx", __func__, res);
+}
+#elif defined(CONFIG_ARM64)
+/*
+ * SPI vectors to use for vPCI; arch SPIs range is [32, 1019], but leaving a bit
+ * of room at the start to allow for SPIs to be specified through ACPI and
+ * starting with a power of two to satisfy power of 2 multi-MSI requirement.
+ */
+#define HV_PCI_MSI_SPI_START	64
+#define HV_PCI_MSI_SPI_NR	(1020 - HV_PCI_MSI_SPI_START)
+#define DELIVERY_MODE		0
+#define FLOW_HANDLER		NULL
+#define FLOW_NAME		NULL
+#define hv_msi_prepare		NULL
+
+struct hv_pci_chip_data {
+	DECLARE_BITMAP(spi_map, HV_PCI_MSI_SPI_NR);
+	struct mutex	map_lock;
+};
+
+/* Hyper-V vPCI MSI GIC IRQ domain */
+static struct irq_domain *hv_msi_gic_irq_domain;
+
+/* Hyper-V PCI MSI IRQ chip */
+static struct irq_chip hv_arm64_msi_irq_chip = {
+	.name = "MSI",
+	.irq_set_affinity = irq_chip_set_affinity_parent,
+	.irq_eoi = irq_chip_eoi_parent,
+	.irq_mask = irq_chip_mask_parent,
+	.irq_unmask = irq_chip_unmask_parent
+};
+
+static unsigned int hv_msi_get_int_vector(struct irq_data *irqd)
+{
+	return irqd->parent_data->hwirq;
+}
+
+/*
+ * @nr_bm_irqs:		Indicates the number of IRQs that were allocated from
+ *			the bitmap.
+ * @nr_dom_irqs:	Indicates the number of IRQs that were allocated from
+ *			the parent domain.
+ */
+static void hv_pci_vec_irq_free(struct irq_domain *domain,
+				unsigned int virq,
+				unsigned int nr_bm_irqs,
+				unsigned int nr_dom_irqs)
+{
+	struct hv_pci_chip_data *chip_data = domain->host_data;
+	struct irq_data *d = irq_domain_get_irq_data(domain, virq);
+	int first = d->hwirq - HV_PCI_MSI_SPI_START;
+	int i;
+
+	mutex_lock(&chip_data->map_lock);
+	bitmap_release_region(chip_data->spi_map,
+			      first,
+			      get_count_order(nr_bm_irqs));
+	mutex_unlock(&chip_data->map_lock);
+	for (i = 0; i < nr_dom_irqs; i++) {
+		if (i)
+			d = irq_domain_get_irq_data(domain, virq + i);
+		irq_domain_reset_irq_data(d);
+	}
+
+	irq_domain_free_irqs_parent(domain, virq, nr_dom_irqs);
+}
+
+static void hv_pci_vec_irq_domain_free(struct irq_domain *domain,
+				       unsigned int virq,
+				       unsigned int nr_irqs)
+{
+	hv_pci_vec_irq_free(domain, virq, nr_irqs, nr_irqs);
+}
+
+static int hv_pci_vec_alloc_device_irq(struct irq_domain *domain,
+				       unsigned int nr_irqs,
+				       irq_hw_number_t *hwirq)
+{
+	struct hv_pci_chip_data *chip_data = domain->host_data;
+	int index;
+
+	/* Find and allocate region from the SPI bitmap */
+	mutex_lock(&chip_data->map_lock);
+	index = bitmap_find_free_region(chip_data->spi_map,
+					HV_PCI_MSI_SPI_NR,
+					get_count_order(nr_irqs));
+	mutex_unlock(&chip_data->map_lock);
+	if (index < 0)
+		return -ENOSPC;
+
+	*hwirq = index + HV_PCI_MSI_SPI_START;
+
+	return 0;
+}
+
+static int hv_pci_vec_irq_gic_domain_alloc(struct irq_domain *domain,
+					   unsigned int virq,
+					   irq_hw_number_t hwirq)
+{
+	struct irq_fwspec fwspec;
+	struct irq_data *d;
+	int ret;
+
+	fwspec.fwnode = domain->parent->fwnode;
+	fwspec.param_count = 2;
+	fwspec.param[0] = hwirq;
+	fwspec.param[1] = IRQ_TYPE_EDGE_RISING;
+
+	ret = irq_domain_alloc_irqs_parent(domain, virq, 1, &fwspec);
+	if (ret)
+		return ret;
+
+	/*
+	 * Since the interrupt specifier is not coming from ACPI or DT, the
+	 * trigger type will need to be set explicitly. Otherwise, it will be
+	 * set to whatever is in the GIC configuration.
+	 */
+	d = irq_domain_get_irq_data(domain->parent, virq);
+
+	return d->chip->irq_set_type(d, IRQ_TYPE_EDGE_RISING);
+}
+
+static int hv_pci_vec_irq_domain_alloc(struct irq_domain *domain,
+				       unsigned int virq, unsigned int nr_irqs,
+				       void *args)
+{
+	irq_hw_number_t hwirq;
+	unsigned int i;
+	int ret;
+
+	ret = hv_pci_vec_alloc_device_irq(domain, nr_irqs, &hwirq);
+	if (ret)
+		return ret;
+
+	for (i = 0; i < nr_irqs; i++) {
+		ret = hv_pci_vec_irq_gic_domain_alloc(domain, virq + i,
+						      hwirq + i);
+		if (ret) {
+			hv_pci_vec_irq_free(domain, virq, nr_irqs, i);
+			return ret;
+		}
+
+		irq_domain_set_hwirq_and_chip(domain, virq + i,
+					      hwirq + i,
+					      &hv_arm64_msi_irq_chip,
+					      domain->host_data);
+		pr_debug("pID:%d vID:%u\n", (int)(hwirq + i), virq + i);
+	}
+
+	return 0;
+}
+
+/*
+ * Pick the first cpu as the irq affinity that can be temporarily used for
+ * composing MSI from the hypervisor. GIC will eventually set the right
+ * affinity for the irq and the 'unmask' will retarget the interrupt to that
+ * cpu.
+ */
+static int hv_pci_vec_irq_domain_activate(struct irq_domain *domain,
+					  struct irq_data *irqd, bool reserve)
+{
+	int cpu = cpumask_first(cpu_present_mask);
+
+	irq_data_update_effective_affinity(irqd, cpumask_of(cpu));
+
+	return 0;
+}
+
+static const struct irq_domain_ops hv_pci_domain_ops = {
+	.alloc	= hv_pci_vec_irq_domain_alloc,
+	.free	= hv_pci_vec_irq_domain_free,
+	.activate = hv_pci_vec_irq_domain_activate,
+};
+
+static int hv_pci_irqchip_init(void)
+{
+	static struct hv_pci_chip_data *chip_data;
+	struct fwnode_handle *fn = NULL;
+	int ret = -ENOMEM;
+
+	chip_data = kzalloc(sizeof(*chip_data), GFP_KERNEL);
+	if (!chip_data)
+		return ret;
+
+	mutex_init(&chip_data->map_lock);
+	fn = irq_domain_alloc_named_fwnode("hv_vpci_arm64");
+	if (!fn)
+		goto free_chip;
+
+	/*
+	 * IRQ domain once enabled, should not be removed since there is no
+	 * way to ensure that all the corresponding devices are also gone and
+	 * no interrupts will be generated.
+	 */
+	hv_msi_gic_irq_domain = acpi_irq_create_hierarchy(0, HV_PCI_MSI_SPI_NR,
+							  fn, &hv_pci_domain_ops,
+							  chip_data);
+
+	if (!hv_msi_gic_irq_domain) {
+		pr_err("Failed to create Hyper-V arm64 vPCI MSI IRQ domain\n");
+		goto free_chip;
+	}
+
+	return 0;
+
+free_chip:
+	kfree(chip_data);
+	if (fn)
+		irq_domain_free_fwnode(fn);
+
+	return ret;
+}
+
+static struct irq_domain *hv_pci_get_root_domain(void)
+{
+	return hv_msi_gic_irq_domain;
+}
+
+/*
+ * SPIs are used for interrupts of PCI devices and SPIs is managed via GICD
+ * registers which Hyper-V already supports, so no hypercall needed.
+ */
+static void hv_arch_irq_unmask(struct irq_data *data) { }
+#endif /* CONFIG_ARM64 */
+
 /**
  * hv_pci_generic_compl() - Invoked for a completion packet
  * @context:		Set up by the sender of the packet.
@@ -1189,164 +1570,19 @@ static void hv_msi_free(struct irq_domain *domain, struct msi_domain_info *info,
 	put_pcichild(hpdev);
 }
 
-static int hv_set_affinity(struct irq_data *data, const struct cpumask *dest,
-			   bool force)
-{
-	struct irq_data *parent = data->parent_data;
-
-	return parent->chip->irq_set_affinity(parent, dest, force);
-}
-
 static void hv_irq_mask(struct irq_data *data)
 {
 	pci_msi_mask_irq(data);
+	if (data->parent_data->chip->irq_mask)
+		irq_chip_mask_parent(data);
 }
 
-static unsigned int hv_msi_get_int_vector(struct irq_data *data)
-{
-	struct irq_cfg *cfg = irqd_cfg(data);
-
-	return cfg->vector;
-}
-
-static int hv_msi_prepare(struct irq_domain *domain, struct device *dev,
-			  int nvec, msi_alloc_info_t *info)
-{
-	int ret = pci_msi_prepare(domain, dev, nvec, info);
-
-	/*
-	 * By using the interrupt remapper in the hypervisor IOMMU, contiguous
-	 * CPU vectors is not needed for multi-MSI
-	 */
-	if (info->type == X86_IRQ_ALLOC_TYPE_PCI_MSI)
-		info->flags &= ~X86_IRQ_ALLOC_CONTIGUOUS_VECTORS;
-
-	return ret;
-}
-
-/**
- * hv_irq_unmask() - "Unmask" the IRQ by setting its current
- * affinity.
- * @data:	Describes the IRQ
- *
- * Build new a destination for the MSI and make a hypercall to
- * update the Interrupt Redirection Table. "Device Logical ID"
- * is built out of this PCI bus's instance GUID and the function
- * number of the device.
- */
 static void hv_irq_unmask(struct irq_data *data)
 {
-	struct msi_desc *msi_desc = irq_data_get_msi_desc(data);
-	struct irq_cfg *cfg = irqd_cfg(data);
-	struct hv_retarget_device_interrupt *params;
-	struct tran_int_desc *int_desc;
-	struct hv_pcibus_device *hbus;
-	struct cpumask *dest;
-	cpumask_var_t tmp;
-	struct pci_bus *pbus;
-	struct pci_dev *pdev;
-	unsigned long flags;
-	u32 var_size = 0;
-	int cpu, nr_bank;
-	u64 res;
-
-	dest = irq_data_get_effective_affinity_mask(data);
-	pdev = msi_desc_to_pci_dev(msi_desc);
-	pbus = pdev->bus;
-	hbus = container_of(pbus->sysdata, struct hv_pcibus_device, sysdata);
-	int_desc = data->chip_data;
-	if (!int_desc) {
-		dev_warn(&hbus->hdev->device, "%s() can not unmask irq %u\n",
-			 __func__, data->irq);
-		return;
-	}
-
-	spin_lock_irqsave(&hbus->retarget_msi_interrupt_lock, flags);
-
-	params = &hbus->retarget_msi_interrupt_params;
-	memset(params, 0, sizeof(*params));
-	params->partition_id = HV_PARTITION_ID_SELF;
-	params->int_entry.source = HV_INTERRUPT_SOURCE_MSI;
-	params->int_entry.msi_entry.address.as_uint32 = int_desc->address & 0xffffffff;
-	params->int_entry.msi_entry.data.as_uint32 = int_desc->data;
-	params->device_id = (hbus->hdev->dev_instance.b[5] << 24) |
-			   (hbus->hdev->dev_instance.b[4] << 16) |
-			   (hbus->hdev->dev_instance.b[7] << 8) |
-			   (hbus->hdev->dev_instance.b[6] & 0xf8) |
-			   PCI_FUNC(pdev->devfn);
-	params->int_target.vector = cfg->vector;
-
-	/*
-	 * Honoring apic->delivery_mode set to APIC_DELIVERY_MODE_FIXED by
-	 * setting the HV_DEVICE_INTERRUPT_TARGET_MULTICAST flag results in a
-	 * spurious interrupt storm. Not doing so does not seem to have a
-	 * negative effect (yet?).
-	 */
-
-	if (hbus->protocol_version >= PCI_PROTOCOL_VERSION_1_2) {
-		/*
-		 * PCI_PROTOCOL_VERSION_1_2 supports the VP_SET version of the
-		 * HVCALL_RETARGET_INTERRUPT hypercall, which also coincides
-		 * with >64 VP support.
-		 * ms_hyperv.hints & HV_X64_EX_PROCESSOR_MASKS_RECOMMENDED
-		 * is not sufficient for this hypercall.
-		 */
-		params->int_target.flags |=
-			HV_DEVICE_INTERRUPT_TARGET_PROCESSOR_SET;
-
-		if (!alloc_cpumask_var(&tmp, GFP_ATOMIC)) {
-			res = 1;
-			goto exit_unlock;
-		}
-
-		cpumask_and(tmp, dest, cpu_online_mask);
-		nr_bank = cpumask_to_vpset(&params->int_target.vp_set, tmp);
-		free_cpumask_var(tmp);
-
-		if (nr_bank <= 0) {
-			res = 1;
-			goto exit_unlock;
-		}
-
-		/*
-		 * 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 = 1 + nr_bank;
-	} else {
-		for_each_cpu_and(cpu, dest, cpu_online_mask) {
-			params->int_target.vp_mask |=
-				(1ULL << hv_cpu_number_to_vp_number(cpu));
-		}
-	}
-
-	res = hv_do_hypercall(HVCALL_RETARGET_INTERRUPT | (var_size << 17),
-			      params, NULL);
-
-exit_unlock:
-	spin_unlock_irqrestore(&hbus->retarget_msi_interrupt_lock, flags);
-
-	/*
-	 * During hibernation, when a CPU is offlined, the kernel tries
-	 * to move the interrupt to the remaining CPUs that haven't
-	 * been offlined yet. In this case, the below hv_do_hypercall()
-	 * always fails since the vmbus channel has been closed:
-	 * refer to cpu_disable_common() -> fixup_irqs() ->
-	 * irq_migrate_all_off_this_cpu() -> migrate_one_irq().
-	 *
-	 * Suppress the error message for hibernation because the failure
-	 * during hibernation does not matter (at this time all the devices
-	 * have been frozen). Note: the correct affinity info is still updated
-	 * into the irqdata data structure in migrate_one_irq() ->
-	 * irq_do_set_affinity() -> hv_set_affinity(), so later when the VM
-	 * resumes, hv_pci_restore_msi_state() is able to correctly restore
-	 * the interrupt with the correct affinity.
-	 */
-	if (!hv_result_success(res) && hbus->state != hv_pcibus_removing)
-		dev_err(&hbus->hdev->device,
-			"%s() failed: %#llx", __func__, res);
+	hv_arch_irq_unmask(data);
 
+	if (data->parent_data->chip->irq_unmask)
+		irq_chip_unmask_parent(data);
 	pci_msi_unmask_irq(data);
 }
 
@@ -1375,7 +1611,7 @@ static u32 hv_compose_msi_req_v1(
 	int_pkt->wslot.slot = slot;
 	int_pkt->int_desc.vector = vector;
 	int_pkt->int_desc.vector_count = vector_count;
-	int_pkt->int_desc.delivery_mode = APIC_DELIVERY_MODE_FIXED;
+	int_pkt->int_desc.delivery_mode = DELIVERY_MODE;
 
 	/*
 	 * Create MSI w/ dummy vCPU set, overwritten by subsequent retarget in
@@ -1405,7 +1641,7 @@ static u32 hv_compose_msi_req_v2(
 	int_pkt->wslot.slot = slot;
 	int_pkt->int_desc.vector = vector;
 	int_pkt->int_desc.vector_count = vector_count;
-	int_pkt->int_desc.delivery_mode = APIC_DELIVERY_MODE_FIXED;
+	int_pkt->int_desc.delivery_mode = DELIVERY_MODE;
 	cpu = hv_compose_msi_req_get_cpu(affinity);
 	int_pkt->int_desc.processor_array[0] =
 		hv_cpu_number_to_vp_number(cpu);
@@ -1425,7 +1661,7 @@ static u32 hv_compose_msi_req_v3(
 	int_pkt->int_desc.vector = vector;
 	int_pkt->int_desc.reserved = 0;
 	int_pkt->int_desc.vector_count = vector_count;
-	int_pkt->int_desc.delivery_mode = APIC_DELIVERY_MODE_FIXED;
+	int_pkt->int_desc.delivery_mode = DELIVERY_MODE;
 	cpu = hv_compose_msi_req_get_cpu(affinity);
 	int_pkt->int_desc.processor_array[0] =
 		hv_cpu_number_to_vp_number(cpu);
@@ -1456,6 +1692,7 @@ static void hv_compose_msi_msg(struct irq_data *data, struct msi_msg *msg)
 	struct compose_comp_ctxt comp;
 	struct tran_int_desc *int_desc;
 	struct msi_desc *msi_desc;
+	bool multi_msi;
 	u8 vector, vector_count;
 	struct {
 		struct pci_packet pci_pkt;
@@ -1469,8 +1706,16 @@ static void hv_compose_msi_msg(struct irq_data *data, struct msi_msg *msg)
 	u32 size;
 	int ret;
 
-	/* Reuse the previous allocation */
-	if (data->chip_data) {
+	msi_desc = irq_data_get_msi_desc(data);
+	multi_msi = !msi_desc->msi_attrib.is_msix &&
+		    msi_desc->nvec_used > 1;
+	/*
+	 * Reuse the previous allocation for Multi-MSI. This is required for
+	 * Multi-MSI and is optional for single-MSI and MSI-X. Note: for now,
+	 * don't reuse the previous allocation for MSI-X because this causes
+	 * unreliable interrupt delivery for some NVMe devices.
+	 */
+	if (data->chip_data && multi_msi) {
 		int_desc = data->chip_data;
 		msg->address_hi = int_desc->address >> 32;
 		msg->address_lo = int_desc->address & 0xffffffff;
@@ -1478,7 +1723,6 @@ static void hv_compose_msi_msg(struct irq_data *data, struct msi_msg *msg)
 		return;
 	}
 
-	msi_desc  = irq_data_get_msi_desc(data);
 	pdev = msi_desc_to_pci_dev(msi_desc);
 	dest = irq_data_get_effective_affinity_mask(data);
 	pbus = pdev->bus;
@@ -1488,11 +1732,18 @@ static void hv_compose_msi_msg(struct irq_data *data, struct msi_msg *msg)
 	if (!hpdev)
 		goto return_null_message;
 
+	/* Free any previous message that might have already been composed. */
+	if (data->chip_data && !multi_msi) {
+		int_desc = data->chip_data;
+		data->chip_data = NULL;
+		hv_int_desc_free(hpdev, int_desc);
+	}
+
 	int_desc = kzalloc(sizeof(*int_desc), GFP_ATOMIC);
 	if (!int_desc)
 		goto drop_reference;
 
-	if (!msi_desc->msi_attrib.is_msix && msi_desc->nvec_used > 1) {
+	if (multi_msi) {
 		/*
 		 * If this is not the first MSI of Multi MSI, we already have
 		 * a mapping.  Can exit early.
@@ -1653,8 +1904,12 @@ return_null_message:
 static struct irq_chip hv_msi_irq_chip = {
 	.name			= "Hyper-V PCIe MSI",
 	.irq_compose_msi_msg	= hv_compose_msi_msg,
-	.irq_set_affinity	= hv_set_affinity,
+	.irq_set_affinity	= irq_chip_set_affinity_parent,
+#ifdef CONFIG_X86
 	.irq_ack		= irq_chip_ack_parent,
+#elif defined(CONFIG_ARM64)
+	.irq_eoi		= irq_chip_eoi_parent,
+#endif
 	.irq_mask		= hv_irq_mask,
 	.irq_unmask		= hv_irq_unmask,
 };
@@ -1684,12 +1939,12 @@ static int hv_pcie_init_irq_domain(struct hv_pcibus_device *hbus)
 	hbus->msi_info.flags = (MSI_FLAG_USE_DEF_DOM_OPS |
 		MSI_FLAG_USE_DEF_CHIP_OPS | MSI_FLAG_MULTI_PCI_MSI |
 		MSI_FLAG_PCI_MSIX);
-	hbus->msi_info.handler = handle_edge_irq;
-	hbus->msi_info.handler_name = "edge";
+	hbus->msi_info.handler = FLOW_HANDLER;
+	hbus->msi_info.handler_name = FLOW_NAME;
 	hbus->msi_info.data = hbus;
 	hbus->irq_domain = pci_msi_create_irq_domain(hbus->fwnode,
 						     &hbus->msi_info,
-						     x86_vector_domain);
+						     hv_pci_get_root_domain());
 	if (!hbus->irq_domain) {
 		dev_err(&hbus->hdev->device,
 			"Failed to build an MSI IRQ domain\n");
@@ -3651,9 +3906,15 @@ static void __exit exit_hv_pci_drv(void)
 
 static int __init init_hv_pci_drv(void)
 {
+	int ret;
+
 	if (!hv_is_hyperv_initialized())
 		return -ENODEV;
 
+	ret = hv_pci_irqchip_init();
+	if (ret)
+		return ret;
+
 	/* Set the invalid domain number's bit, so it will not be used */
 	set_bit(HVPCI_DOM_INVALID, hvpci_dom_map);
 

include/asm-generic/hyperv-tlfs.h

@@ -539,39 +539,6 @@ enum hv_interrupt_source {
 	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 {
-		union hv_msi_address_register address;
-		union hv_msi_data_register data;
-	} __packed;
-};
-
 union hv_ioapic_rte {
 	u64 as_uint64;
 

include/asm-generic/mshyperv.h

@@ -256,6 +256,7 @@ enum hv_isolation_type hv_get_isolation_type(void);
 bool hv_is_isolation_supported(void);
 void hyperv_cleanup(void);
 bool hv_query_ext_cap(u64 cap_query);
+void hv_setup_dma_ops(struct device *dev, bool coherent);
 #else /* CONFIG_HYPERV */
 static inline bool hv_is_hyperv_initialized(void) { return false; }
 static inline bool hv_is_hibernation_supported(void) { return false; }