Merge branch 'remotes/lorenzo/pci/hyper-v'

- Add domain_nr in struct pci_host_bridge (Boqun Feng)

- Use host bridge MSI domain for root buses if present (Boqun Feng)

- Allow ARM64 virtual host bridge with no ACPI companion (e.g., Hyper-V)
  (Boqun Feng)

- Make Hyper-V enumeration more generic (Arnd Bergmann)

- Set Hyper-V domain_nr at probe-time (Boqun Feng)

- Set up Hyper-V MSI domain at bridge probe-time (Boqun Feng)

- Enable Hyper-V bridge probing on ARM64 (Boqun Feng)

* remotes/lorenzo/pci/hyper-v:
  PCI: hv: Turn on the host bridge probing on ARM64
  PCI: hv: Set up MSI domain at bridge probing time
  PCI: hv: Set ->domain_nr of pci_host_bridge at probing time
  PCI: hv: Generify PCI probing
  arm64: PCI: Support root bridge preparation for Hyper-V
  arm64: PCI: Restructure pcibios_root_bridge_prepare()
  PCI: Support populating MSI domains of root buses via bridges
  PCI: Introduce domain_nr in pci_host_bridge

arch/arm64/kernel/pci.c

@@ -82,14 +82,29 @@ int acpi_pci_bus_find_domain_nr(struct pci_bus *bus)
 
 int pcibios_root_bridge_prepare(struct pci_host_bridge *bridge)
 {
-	if (!acpi_disabled) {
-		struct pci_config_window *cfg = bridge->bus->sysdata;
-		struct acpi_device *adev = to_acpi_device(cfg->parent);
-		struct device *bus_dev = &bridge->bus->dev;
+	struct pci_config_window *cfg;
+	struct acpi_device *adev;
+	struct device *bus_dev;
 
-		ACPI_COMPANION_SET(&bridge->dev, adev);
-		set_dev_node(bus_dev, acpi_get_node(acpi_device_handle(adev)));
-	}
+	if (acpi_disabled)
+		return 0;
+
+	cfg = bridge->bus->sysdata;
+
+	/*
+	 * On Hyper-V there is no corresponding ACPI device for a root bridge,
+	 * therefore ->parent is set as NULL by the driver. And set 'adev' as
+	 * NULL in this case because there is no proper ACPI device.
+	 */
+	if (!cfg->parent)
+		adev = NULL;
+	else
+		adev = to_acpi_device(cfg->parent);
+
+	bus_dev = &bridge->bus->dev;
+
+	ACPI_COMPANION_SET(&bridge->dev, adev);
+	set_dev_node(bus_dev, acpi_get_node(acpi_device_handle(adev)));
 
 	return 0;
 }

drivers/pci/controller/pci-hyperv.c

@@ -40,6 +40,7 @@
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/pci.h>
+#include <linux/pci-ecam.h>
 #include <linux/delay.h>
 #include <linux/semaphore.h>
 #include <linux/irqdomain.h>
@@ -473,7 +474,13 @@ enum hv_pcibus_state {
 };
 
 struct hv_pcibus_device {
+#ifdef CONFIG_X86
 	struct pci_sysdata sysdata;
+#elif defined(CONFIG_ARM64)
+	struct pci_config_window sysdata;
+#endif
+	struct pci_host_bridge *bridge;
+	struct fwnode_handle *fwnode;
 	/* Protocol version negotiated with the host */
 	enum pci_protocol_version_t protocol_version;
 	enum hv_pcibus_state state;
@@ -489,8 +496,6 @@ struct hv_pcibus_device {
 	spinlock_t device_list_lock;	/* Protect lists below */
 	void __iomem *cfg_addr;
 
-	struct list_head resources_for_children;
-
 	struct list_head children;
 	struct list_head dr_list;
 
@@ -1623,7 +1628,7 @@ static int hv_pcie_init_irq_domain(struct hv_pcibus_device *hbus)
 	hbus->msi_info.handler = handle_edge_irq;
 	hbus->msi_info.handler_name = "edge";
 	hbus->msi_info.data = hbus;
-	hbus->irq_domain = pci_msi_create_irq_domain(hbus->sysdata.fwnode,
+	hbus->irq_domain = pci_msi_create_irq_domain(hbus->fwnode,
 						     &hbus->msi_info,
 						     x86_vector_domain);
 	if (!hbus->irq_domain) {
@@ -1632,6 +1637,8 @@ static int hv_pcie_init_irq_domain(struct hv_pcibus_device *hbus)
 		return -ENODEV;
 	}
 
+	dev_set_msi_domain(&hbus->bridge->dev, hbus->irq_domain);
+
 	return 0;
 }
 
@@ -1854,7 +1861,7 @@ static void hv_pci_assign_slots(struct hv_pcibus_device *hbus)
 
 		slot_nr = PCI_SLOT(wslot_to_devfn(hpdev->desc.win_slot.slot));
 		snprintf(name, SLOT_NAME_SIZE, "%u", hpdev->desc.ser);
-		hpdev->pci_slot = pci_create_slot(hbus->pci_bus, slot_nr,
+		hpdev->pci_slot = pci_create_slot(hbus->bridge->bus, slot_nr,
 					  name, NULL);
 		if (IS_ERR(hpdev->pci_slot)) {
 			pr_warn("pci_create slot %s failed\n", name);
@@ -1884,7 +1891,7 @@ static void hv_pci_remove_slots(struct hv_pcibus_device *hbus)
 static void hv_pci_assign_numa_node(struct hv_pcibus_device *hbus)
 {
 	struct pci_dev *dev;
-	struct pci_bus *bus = hbus->pci_bus;
+	struct pci_bus *bus = hbus->bridge->bus;
 	struct hv_pci_dev *hv_dev;
 
 	list_for_each_entry(dev, &bus->devices, bus_list) {
@@ -1907,21 +1914,22 @@ static void hv_pci_assign_numa_node(struct hv_pcibus_device *hbus)
  */
 static int create_root_hv_pci_bus(struct hv_pcibus_device *hbus)
 {
-	/* Register the device */
-	hbus->pci_bus = pci_create_root_bus(&hbus->hdev->device,
-					    0, /* bus number is always zero */
-					    &hv_pcifront_ops,
-					    &hbus->sysdata,
-					    &hbus->resources_for_children);
-	if (!hbus->pci_bus)
-		return -ENODEV;
+	int error;
+	struct pci_host_bridge *bridge = hbus->bridge;
+
+	bridge->dev.parent = &hbus->hdev->device;
+	bridge->sysdata = &hbus->sysdata;
+	bridge->ops = &hv_pcifront_ops;
+
+	error = pci_scan_root_bus_bridge(bridge);
+	if (error)
+		return error;
 
 	pci_lock_rescan_remove();
-	pci_scan_child_bus(hbus->pci_bus);
 	hv_pci_assign_numa_node(hbus);
-	pci_bus_assign_resources(hbus->pci_bus);
+	pci_bus_assign_resources(bridge->bus);
 	hv_pci_assign_slots(hbus);
-	pci_bus_add_devices(hbus->pci_bus);
+	pci_bus_add_devices(bridge->bus);
 	pci_unlock_rescan_remove();
 	hbus->state = hv_pcibus_installed;
 	return 0;
@@ -2184,7 +2192,7 @@ static void pci_devices_present_work(struct work_struct *work)
 		 * because there may have been changes.
 		 */
 		pci_lock_rescan_remove();
-		pci_scan_child_bus(hbus->pci_bus);
+		pci_scan_child_bus(hbus->bridge->bus);
 		hv_pci_assign_numa_node(hbus);
 		hv_pci_assign_slots(hbus);
 		pci_unlock_rescan_remove();
@@ -2352,11 +2360,11 @@ static void hv_eject_device_work(struct work_struct *work)
 	/*
 	 * Ejection can come before or after the PCI bus has been set up, so
 	 * attempt to find it and tear down the bus state, if it exists.  This
-	 * must be done without constructs like pci_domain_nr(hbus->pci_bus)
-	 * because hbus->pci_bus may not exist yet.
+	 * must be done without constructs like pci_domain_nr(hbus->bridge->bus)
+	 * because hbus->bridge->bus may not exist yet.
 	 */
 	wslot = wslot_to_devfn(hpdev->desc.win_slot.slot);
-	pdev = pci_get_domain_bus_and_slot(hbus->sysdata.domain, 0, wslot);
+	pdev = pci_get_domain_bus_and_slot(hbus->bridge->domain_nr, 0, wslot);
 	if (pdev) {
 		pci_lock_rescan_remove();
 		pci_stop_and_remove_bus_device(pdev);
@@ -2719,8 +2727,7 @@ static int hv_pci_allocate_bridge_windows(struct hv_pcibus_device *hbus)
 		/* Modify this resource to become a bridge window. */
 		hbus->low_mmio_res->flags |= IORESOURCE_WINDOW;
 		hbus->low_mmio_res->flags &= ~IORESOURCE_BUSY;
-		pci_add_resource(&hbus->resources_for_children,
-				 hbus->low_mmio_res);
+		pci_add_resource(&hbus->bridge->windows, hbus->low_mmio_res);
 	}
 
 	if (hbus->high_mmio_space) {
@@ -2739,8 +2746,7 @@ static int hv_pci_allocate_bridge_windows(struct hv_pcibus_device *hbus)
 		/* Modify this resource to become a bridge window. */
 		hbus->high_mmio_res->flags |= IORESOURCE_WINDOW;
 		hbus->high_mmio_res->flags &= ~IORESOURCE_BUSY;
-		pci_add_resource(&hbus->resources_for_children,
-				 hbus->high_mmio_res);
+		pci_add_resource(&hbus->bridge->windows, hbus->high_mmio_res);
 	}
 
 	return 0;
@@ -3059,6 +3065,7 @@ static void hv_put_dom_num(u16 dom)
 static int hv_pci_probe(struct hv_device *hdev,
 			const struct hv_vmbus_device_id *dev_id)
 {
+	struct pci_host_bridge *bridge;
 	struct hv_pcibus_device *hbus;
 	u16 dom_req, dom;
 	char *name;
@@ -3071,6 +3078,10 @@ static int hv_pci_probe(struct hv_device *hdev,
 	 */
 	BUILD_BUG_ON(sizeof(*hbus) > HV_HYP_PAGE_SIZE);
 
+	bridge = devm_pci_alloc_host_bridge(&hdev->device, 0);
+	if (!bridge)
+		return -ENOMEM;
+
 	/*
 	 * With the recent 59bb47985c1d ("mm, sl[aou]b: guarantee natural
 	 * alignment for kmalloc(power-of-two)"), kzalloc() is able to allocate
@@ -3092,6 +3103,8 @@ static int hv_pci_probe(struct hv_device *hdev,
 	hbus = kzalloc(HV_HYP_PAGE_SIZE, GFP_KERNEL);
 	if (!hbus)
 		return -ENOMEM;
+
+	hbus->bridge = bridge;
 	hbus->state = hv_pcibus_init;
 	hbus->wslot_res_allocated = -1;
 
@@ -3123,17 +3136,19 @@ static int hv_pci_probe(struct hv_device *hdev,
 			 "PCI dom# 0x%hx has collision, using 0x%hx",
 			 dom_req, dom);
 
+	hbus->bridge->domain_nr = dom;
+#ifdef CONFIG_X86
 	hbus->sysdata.domain = dom;
+#endif
 
 	hbus->hdev = hdev;
 	INIT_LIST_HEAD(&hbus->children);
 	INIT_LIST_HEAD(&hbus->dr_list);
-	INIT_LIST_HEAD(&hbus->resources_for_children);
 	spin_lock_init(&hbus->config_lock);
 	spin_lock_init(&hbus->device_list_lock);
 	spin_lock_init(&hbus->retarget_msi_interrupt_lock);
 	hbus->wq = alloc_ordered_workqueue("hv_pci_%x", 0,
-					   hbus->sysdata.domain);
+					   hbus->bridge->domain_nr);
 	if (!hbus->wq) {
 		ret = -ENOMEM;
 		goto free_dom;
@@ -3170,9 +3185,9 @@ static int hv_pci_probe(struct hv_device *hdev,
 		goto unmap;
 	}
 
-	hbus->sysdata.fwnode = irq_domain_alloc_named_fwnode(name);
+	hbus->fwnode = irq_domain_alloc_named_fwnode(name);
 	kfree(name);
-	if (!hbus->sysdata.fwnode) {
+	if (!hbus->fwnode) {
 		ret = -ENOMEM;
 		goto unmap;
 	}
@@ -3250,7 +3265,7 @@ exit_d0:
 free_irq_domain:
 	irq_domain_remove(hbus->irq_domain);
 free_fwnode:
-	irq_domain_free_fwnode(hbus->sysdata.fwnode);
+	irq_domain_free_fwnode(hbus->fwnode);
 unmap:
 	iounmap(hbus->cfg_addr);
 free_config:
@@ -3260,7 +3275,7 @@ close:
 destroy_wq:
 	destroy_workqueue(hbus->wq);
 free_dom:
-	hv_put_dom_num(hbus->sysdata.domain);
+	hv_put_dom_num(hbus->bridge->domain_nr);
 free_bus:
 	kfree(hbus);
 	return ret;
@@ -3352,9 +3367,9 @@ static int hv_pci_remove(struct hv_device *hdev)
 
 		/* Remove the bus from PCI's point of view. */
 		pci_lock_rescan_remove();
-		pci_stop_root_bus(hbus->pci_bus);
+		pci_stop_root_bus(hbus->bridge->bus);
 		hv_pci_remove_slots(hbus);
-		pci_remove_root_bus(hbus->pci_bus);
+		pci_remove_root_bus(hbus->bridge->bus);
 		pci_unlock_rescan_remove();
 	}
 
@@ -3364,12 +3379,11 @@ static int hv_pci_remove(struct hv_device *hdev)
 
 	iounmap(hbus->cfg_addr);
 	hv_free_config_window(hbus);
-	pci_free_resource_list(&hbus->resources_for_children);
 	hv_pci_free_bridge_windows(hbus);
 	irq_domain_remove(hbus->irq_domain);
-	irq_domain_free_fwnode(hbus->sysdata.fwnode);
+	irq_domain_free_fwnode(hbus->fwnode);
 
-	hv_put_dom_num(hbus->sysdata.domain);
+	hv_put_dom_num(hbus->bridge->domain_nr);
 
 	kfree(hbus);
 	return ret;
@@ -3447,7 +3461,7 @@ static int hv_pci_restore_msi_msg(struct pci_dev *pdev, void *arg)
  */
 static void hv_pci_restore_msi_state(struct hv_pcibus_device *hbus)
 {
-	pci_walk_bus(hbus->pci_bus, hv_pci_restore_msi_msg, NULL);
+	pci_walk_bus(hbus->bridge->bus, hv_pci_restore_msi_msg, NULL);
 }
 
 static int hv_pci_resume(struct hv_device *hdev)

drivers/pci/probe.c

@@ -595,6 +595,7 @@ static void pci_init_host_bridge(struct pci_host_bridge *bridge)
 	bridge->native_pme = 1;
 	bridge->native_ltr = 1;
 	bridge->native_dpc = 1;
+	bridge->domain_nr = PCI_DOMAIN_NR_NOT_SET;
 
 	device_initialize(&bridge->dev);
 }
@@ -829,11 +830,15 @@ static struct irq_domain *pci_host_bridge_msi_domain(struct pci_bus *bus)
 {
 	struct irq_domain *d;
 
+	/* If the host bridge driver sets a MSI domain of the bridge, use it */
+	d = dev_get_msi_domain(bus->bridge);
+
 	/*
 	 * Any firmware interface that can resolve the msi_domain
 	 * should be called from here.
 	 */
-	d = pci_host_bridge_of_msi_domain(bus);
+	if (!d)
+		d = pci_host_bridge_of_msi_domain(bus);
 	if (!d)
 		d = pci_host_bridge_acpi_msi_domain(bus);
 
@@ -899,7 +904,10 @@ static int pci_register_host_bridge(struct pci_host_bridge *bridge)
 	bus->ops = bridge->ops;
 	bus->number = bus->busn_res.start = bridge->busnr;
 #ifdef CONFIG_PCI_DOMAINS_GENERIC
-	bus->domain_nr = pci_bus_find_domain_nr(bus, parent);
+	if (bridge->domain_nr == PCI_DOMAIN_NR_NOT_SET)
+		bus->domain_nr = pci_bus_find_domain_nr(bus, parent);
+	else
+		bus->domain_nr = bridge->domain_nr;
 #endif
 
 	b = pci_find_bus(pci_domain_nr(bus), bridge->busnr);

include/linux/pci.h

@@ -529,6 +529,16 @@ static inline int pci_channel_offline(struct pci_dev *pdev)
 	return (pdev->error_state != pci_channel_io_normal);
 }
 
+/*
+ * Currently in ACPI spec, for each PCI host bridge, PCI Segment
+ * Group number is limited to a 16-bit value, therefore (int)-1 is
+ * not a valid PCI domain number, and can be used as a sentinel
+ * value indicating ->domain_nr is not set by the driver (and
+ * CONFIG_PCI_DOMAINS_GENERIC=y archs will set it with
+ * pci_bus_find_domain_nr()).
+ */
+#define PCI_DOMAIN_NR_NOT_SET (-1)
+
 struct pci_host_bridge {
 	struct device	dev;
 	struct pci_bus	*bus;		/* Root bus */
@@ -536,6 +546,7 @@ struct pci_host_bridge {
 	struct pci_ops	*child_ops;
 	void		*sysdata;
 	int		busnr;
+	int		domain_nr;
 	struct list_head windows;	/* resource_entry */
 	struct list_head dma_ranges;	/* dma ranges resource list */
 	u8 (*swizzle_irq)(struct pci_dev *, u8 *); /* Platform IRQ swizzler */