1 files changed, 112 insertions, 41 deletions

diff --git a/drivers/pci/controller/pci-hyperv.c b/drivers/pci/controller/pci-hyperv.c
index a53bd8728d0d..eaec915ffe62 100644
--- a/drivers/pci/controller/pci-hyperv.c
+++ b/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>
@@ -64,6 +65,7 @@ enum pci_protocol_version_t {
 	PCI_PROTOCOL_VERSION_1_1 = PCI_MAKE_VERSION(1, 1),	/* Win10 */
 	PCI_PROTOCOL_VERSION_1_2 = PCI_MAKE_VERSION(1, 2),	/* RS1 */
 	PCI_PROTOCOL_VERSION_1_3 = PCI_MAKE_VERSION(1, 3),	/* Vibranium */
+	PCI_PROTOCOL_VERSION_1_4 = PCI_MAKE_VERSION(1, 4),	/* WS2022 */
 };
 
 #define CPU_AFFINITY_ALL	-1ULL
@@ -73,6 +75,7 @@ enum pci_protocol_version_t {
  * first.
  */
 static enum pci_protocol_version_t pci_protocol_versions[] = {
+	PCI_PROTOCOL_VERSION_1_4,
 	PCI_PROTOCOL_VERSION_1_3,
 	PCI_PROTOCOL_VERSION_1_2,
 	PCI_PROTOCOL_VERSION_1_1,
@@ -122,6 +125,8 @@ enum pci_message_type {
 	PCI_CREATE_INTERRUPT_MESSAGE2	= PCI_MESSAGE_BASE + 0x17,
 	PCI_DELETE_INTERRUPT_MESSAGE2	= PCI_MESSAGE_BASE + 0x18, /* unused */
 	PCI_BUS_RELATIONS2		= PCI_MESSAGE_BASE + 0x19,
+	PCI_RESOURCES_ASSIGNED3         = PCI_MESSAGE_BASE + 0x1A,
+	PCI_CREATE_INTERRUPT_MESSAGE3   = PCI_MESSAGE_BASE + 0x1B,
 	PCI_MESSAGE_MAXIMUM
 };
 
@@ -235,6 +240,21 @@ struct hv_msi_desc2 {
 	u16	processor_array[32];
 } __packed;
 
+/*
+ * struct hv_msi_desc3 - 1.3 version of hv_msi_desc
+ *	Everything is the same as in 'hv_msi_desc2' except that the size of the
+ *	'vector' field is larger to support bigger vector values. For ex: LPI
+ *	vectors on ARM.
+ */
+struct hv_msi_desc3 {
+	u32	vector;
+	u8	delivery_mode;
+	u8	reserved;
+	u16	vector_count;
+	u16	processor_count;
+	u16	processor_array[32];
+} __packed;
+
 /**
  * struct tran_int_desc
  * @reserved:		unused, padding
@@ -383,6 +403,12 @@ struct pci_create_interrupt2 {
 	struct hv_msi_desc2 int_desc;
 } __packed;
 
+struct pci_create_interrupt3 {
+	struct pci_message message_type;
+	union win_slot_encoding wslot;
+	struct hv_msi_desc3 int_desc;
+} __packed;
+
 struct pci_delete_interrupt {
 	struct pci_message message_type;
 	union win_slot_encoding wslot;
@@ -448,7 +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;
@@ -464,8 +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;
 
@@ -1328,6 +1358,15 @@ static u32 hv_compose_msi_req_v1(
 	return sizeof(*int_pkt);
 }
 
+/*
+ * Create MSI w/ dummy vCPU set targeting just one vCPU, overwritten
+ * by subsequent retarget in hv_irq_unmask().
+ */
+static int hv_compose_msi_req_get_cpu(struct cpumask *affinity)
+{
+	return cpumask_first_and(affinity, cpu_online_mask);
+}
+
 static u32 hv_compose_msi_req_v2(
 	struct pci_create_interrupt2 *int_pkt, struct cpumask *affinity,
 	u32 slot, u8 vector)
@@ -1339,12 +1378,27 @@ static u32 hv_compose_msi_req_v2(
 	int_pkt->int_desc.vector = vector;
 	int_pkt->int_desc.vector_count = 1;
 	int_pkt->int_desc.delivery_mode = APIC_DELIVERY_MODE_FIXED;
+	cpu = hv_compose_msi_req_get_cpu(affinity);
+	int_pkt->int_desc.processor_array[0] =
+		hv_cpu_number_to_vp_number(cpu);
+	int_pkt->int_desc.processor_count = 1;
 
-	/*
-	 * Create MSI w/ dummy vCPU set targeting just one vCPU, overwritten
-	 * by subsequent retarget in hv_irq_unmask().
-	 */
-	cpu = cpumask_first_and(affinity, cpu_online_mask);
+	return sizeof(*int_pkt);
+}
+
+static u32 hv_compose_msi_req_v3(
+	struct pci_create_interrupt3 *int_pkt, struct cpumask *affinity,
+	u32 slot, u32 vector)
+{
+	int cpu;
+
+	int_pkt->message_type.type = PCI_CREATE_INTERRUPT_MESSAGE3;
+	int_pkt->wslot.slot = slot;
+	int_pkt->int_desc.vector = vector;
+	int_pkt->int_desc.reserved = 0;
+	int_pkt->int_desc.vector_count = 1;
+	int_pkt->int_desc.delivery_mode = APIC_DELIVERY_MODE_FIXED;
+	cpu = hv_compose_msi_req_get_cpu(affinity);
 	int_pkt->int_desc.processor_array[0] =
 		hv_cpu_number_to_vp_number(cpu);
 	int_pkt->int_desc.processor_count = 1;
@@ -1379,6 +1433,7 @@ static void hv_compose_msi_msg(struct irq_data *data, struct msi_msg *msg)
 		union {
 			struct pci_create_interrupt v1;
 			struct pci_create_interrupt2 v2;
+			struct pci_create_interrupt3 v3;
 		} int_pkts;
 	} __packed ctxt;
 
@@ -1426,6 +1481,13 @@ static void hv_compose_msi_msg(struct irq_data *data, struct msi_msg *msg)
 					cfg->vector);
 		break;
 
+	case PCI_PROTOCOL_VERSION_1_4:
+		size = hv_compose_msi_req_v3(&ctxt.int_pkts.v3,
+					dest,
+					hpdev->desc.win_slot.slot,
+					cfg->vector);
+		break;
+
 	default:
 		/* As we only negotiate protocol versions known to this driver,
 		 * this path should never hit. However, this is it not a hot
@@ -1566,7 +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) {
@@ -1575,6 +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;
 }
 
@@ -1797,7 +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);
@@ -1827,7 +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) {
@@ -1850,21 +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;
@@ -2127,7 +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();
@@ -2295,11 +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);
@@ -2662,8 +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) {
@@ -2682,8 +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;
@@ -3002,6 +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;
@@ -3014,6 +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
@@ -3035,6 +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;
 
@@ -3066,17 +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;
@@ -3113,9 +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;
 	}
@@ -3193,7 +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:
@@ -3203,7 +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;
@@ -3295,9 +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();
 	}
 
@@ -3307,12 +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;
@@ -3390,7 +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)