PCI: hv: Add arm64 Hyper-V vPCI support

Add arm64 Hyper-V vPCI support by implementing the arch specific
interfaces. Introduce an IRQ domain and chip specific to Hyper-v vPCI that
is based on SPIs. The IRQ domain parents itself to the arch GIC IRQ domain
for basic vector management.

[bhelgaas: squash in fix from Yang Li <[email protected]>:
https://lore.kernel.org/r/[email protected]]
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Sunil Muthuswamy <[email protected]>
Signed-off-by: Lorenzo Pieralisi <[email protected]>
Signed-off-by: Bjorn Helgaas <[email protected]>
Reviewed-by: Marc Zyngier <[email protected]>
Reviewed-by: Michael Kelley <[email protected]>
Signed-off-by: Tyler Hicks <[email protected]>
Signed-off-by: Allen Pais <[email protected]>

Author: sunilmut

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

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

@@ -47,6 +47,8 @@
 #include <linux/msi.h>
 #include <linux/hyperv.h>
 #include <linux/refcount.h>
+#include <linux/irqdomain.h>
+#include <linux/acpi.h>
 #include <asm/mshyperv.h>
 
 /*
@@ -602,19 +604,237 @@ static unsigned int hv_msi_get_int_vector(struct irq_data *data)
 	return cfg->vector;
 }
 
-static void hv_set_msi_entry_from_desc(union hv_msi_entry *msi_entry,
-				       struct msi_desc *msi_desc)
+static int hv_msi_prepare(struct irq_domain *domain, struct device *dev,
+			  int nvec, msi_alloc_info_t *info)
 {
-	msi_entry->address.as_uint32 = msi_desc->msg.address_lo;
-	msi_entry->data.as_uint32 = msi_desc->msg.data;
+	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;
 }
 
-static int hv_msi_prepare(struct irq_domain *domain, struct device *dev,
-			  int nvec, msi_alloc_info_t *info)
+#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)
 {
-	return pci_msi_prepare(domain, dev, nvec, info);
+	int cpu = cpumask_first(cpu_present_mask);
+
+	irq_data_update_effective_affinity(irqd, cpumask_of(cpu));
+
+	return 0;
 }
-#endif /* CONFIG_X86 */
+
+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;
+}
+#endif /* CONFIG_ARM64 */
 
 /**
  * hv_pci_generic_compl() - Invoked for a completion packet
@@ -1231,28 +1451,8 @@ static void hv_msi_free(struct irq_domain *domain, struct msi_domain_info *info,
 static void hv_irq_mask(struct irq_data *data)
 {
 	pci_msi_mask_irq(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;
+	if (data->parent_data->chip->irq_mask)
+		irq_chip_mask_parent(data);
 }
 
 /**
@@ -1372,6 +1572,8 @@ static void hv_irq_unmask(struct irq_data *data)
 		dev_err(&hbus->hdev->device,
 			"%s() failed: %#llx", __func__, res);
 
+	if (data->parent_data->chip->irq_unmask)
+		irq_chip_unmask_parent(data);
 	pci_msi_unmask_irq(data);
 }
 
@@ -1685,7 +1887,11 @@ static struct irq_chip hv_msi_irq_chip = {
 	.name			= "Hyper-V PCIe MSI",
 	.irq_compose_msi_msg	= hv_compose_msi_msg,
 	.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,
 };