[PATCH v4 2/5] Drivers: hv: Add logical device ID registry for vPCI devices

[Yu Zhang]

Hyper-V identifies each PCI pass-thru device by a logical device ID in
its hypercall interface. This ID consists of a per-bus prefix, derived
from the VMBus device instance GUID, combined with the PCI function
number of the endpoint device.

Add a registry in hv_common.c that maps a PCI domain number to its
logical device ID prefix. The vPCI bus driver (pci-hyperv) registers the
prefix when a bus is probed and unregisters it when the bus is removed.
Consumers such as the para-virtualized IOMMU driver look up the prefix
by PCI domain number and combine it with the function number to form the
complete logical device ID for hypercalls.

Use rhashtable for the sparse exact-match mapping. Lookups copy the
prefix while holding the RCU read lock, and removal defers freeing the
entry until existing readers have completed.

The prefix construction is shared via hv_build_logical_dev_id_prefix() so
that pci-hyperv's interrupt retargeting path and the registry use exactly
the same byte layout. It is derived on demand from the constant hv_device
instance GUID rather than cached in struct hv_pcibus_device, which is
private to the pci-hyperv module; this keeps the interface narrow and
avoids depending on pci-hyperv internals.

Co-developed-by: Easwar Hariharan <easwar.hariharan@xxxxxxxxxxxxxxxxxxx>
Signed-off-by: Easwar Hariharan <easwar.hariharan@xxxxxxxxxxxxxxxxxxx>
Signed-off-by: Yu Zhang <zhangyu1@xxxxxxxxxxxxxxxxxxx>
---
 drivers/hv/hv_common.c              | 112 ++++++++++++++++++++++++++++
 drivers/pci/controller/pci-hyperv.c |  21 ++++--
 include/asm-generic/mshyperv.h      |   4 +
 include/linux/hyperv.h              |   8 ++
 4 files changed, 140 insertions(+), 5 deletions(-)

diff --git a/drivers/hv/hv_common.c b/drivers/hv/hv_common.c
index b5d2d6cd65ae..808751aa356b 100644
--- a/drivers/hv/hv_common.c
+++ b/drivers/hv/hv_common.c
@@ -21,6 +21,7 @@
 #include <linux/panic_notifier.h>
 #include <linux/ptrace.h>
 #include <linux/random.h>
+#include <linux/rhashtable.h>
 #include <linux/efi.h>
 #include <linux/kdebug.h>
 #include <linux/kmsg_dump.h>
@@ -78,6 +79,22 @@ static struct ctl_table_header *hv_ctl_table_hdr;
 u8 * __percpu *hv_synic_eventring_tail;
 EXPORT_SYMBOL_GPL(hv_synic_eventring_tail);
 
+struct hv_pci_busdata {
+	int pci_domain_nr;
+	u32 logical_dev_id_prefix;
+	struct rhash_head node;
+	struct rcu_head rcu;
+};
+
+static struct rhashtable hv_pci_bus_ht;
+static bool hv_pci_bus_ht_initialized;
+
+static const struct rhashtable_params hv_pci_bus_ht_params = {
+	.key_len	= sizeof_field(struct hv_pci_busdata, pci_domain_nr),
+	.key_offset	= offsetof(struct hv_pci_busdata, pci_domain_nr),
+	.head_offset	= offsetof(struct hv_pci_busdata, node),
+};
+
 /*
  * Hyper-V specific initialization and shutdown code that is
  * common across all architectures.  Called from architecture
@@ -86,6 +103,11 @@ EXPORT_SYMBOL_GPL(hv_synic_eventring_tail);
 
 void __init hv_common_free(void)
 {
+	if (hv_pci_bus_ht_initialized) {
+		rhashtable_destroy(&hv_pci_bus_ht);
+		hv_pci_bus_ht_initialized = false;
+	}
+
 	unregister_sysctl_table(hv_ctl_table_hdr);
 	hv_ctl_table_hdr = NULL;
 
@@ -315,6 +337,7 @@ u8 __init get_vtl(void)
 int __init hv_common_init(void)
 {
 	int i;
+	int ret;
 	union hv_hypervisor_version_info version;
 
 	/* Get information about the Microsoft Hypervisor version */
@@ -394,6 +417,13 @@ int __init hv_common_init(void)
 	for (i = 0; i < nr_cpu_ids; i++)
 		hv_vp_index[i] = VP_INVAL;
 
+	ret = rhashtable_init(&hv_pci_bus_ht, &hv_pci_bus_ht_params);
+	if (ret) {
+		hv_common_free();
+		return ret;
+	}
+	hv_pci_bus_ht_initialized = true;
+
 	return 0;
 }
 
@@ -864,3 +894,85 @@ const char *hv_result_to_string(u64 status)
 	return "Unknown";
 }
 EXPORT_SYMBOL_GPL(hv_result_to_string);
+
+/*
+ * Logical device ID registry for Hyper-V PCI buses. The pci-hyperv
+ * driver registers each bus's logical device ID prefix before scanning
+ * its devices. Consumers look up the prefix by PCI domain number when
+ * building logical device IDs for Hyper-V interfaces.
+ */
+int hv_pci_register_dev_id(int pci_domain_nr, u32 logical_dev_id_prefix)
+{
+	struct hv_pci_busdata *bus, *new;
+	int ret;
+
+	new = kzalloc_obj(*new, GFP_KERNEL);
+	if (!new)
+		return -ENOMEM;
+
+	new->pci_domain_nr = pci_domain_nr;
+	new->logical_dev_id_prefix = logical_dev_id_prefix;
+
+	bus = rhashtable_lookup_get_insert_fast(&hv_pci_bus_ht, &new->node,
+						hv_pci_bus_ht_params);
+	if (IS_ERR(bus)) {
+		ret = PTR_ERR(bus);
+		goto free_new;
+	}
+
+	if (WARN_ONCE(bus != NULL,
+		      "Hyper-V PCI domain %d is already registered\n",
+		      pci_domain_nr)) {
+		ret = -EEXIST;
+		goto free_new;
+	}
+
+	return 0;
+
+free_new:
+	kfree(new);
+	return ret;
+}
+EXPORT_SYMBOL_FOR_MODULES(hv_pci_register_dev_id, "pci-hyperv");
+
+void hv_pci_unregister_dev_id(int pci_domain_nr)
+{
+	struct hv_pci_busdata *bus;
+	int ret = -ENOENT;
+
+	rcu_read_lock();
+	bus = rhashtable_lookup(&hv_pci_bus_ht, &pci_domain_nr,
+				hv_pci_bus_ht_params);
+	if (bus)
+		ret = rhashtable_remove_fast(&hv_pci_bus_ht, &bus->node,
+					     hv_pci_bus_ht_params);
+	rcu_read_unlock();
+
+	if (WARN_ON_ONCE(ret))
+		return;
+
+	kfree_rcu(bus, rcu);
+}
+EXPORT_SYMBOL_FOR_MODULES(hv_pci_unregister_dev_id, "pci-hyperv");
+
+/*
+ * Look up the logical device ID prefix registered for @pci_domain_nr.
+ * Returns 0 on success with *prefix filled in; -ENODEV if no entry is
+ * registered for that PCI domain.
+ */
+int hv_pci_lookup_dev_id(int pci_domain_nr, u32 *prefix)
+{
+	struct hv_pci_busdata *bus;
+	int ret = -ENODEV;
+
+	rcu_read_lock();
+	bus = rhashtable_lookup(&hv_pci_bus_ht, &pci_domain_nr,
+				hv_pci_bus_ht_params);
+	if (bus) {
+		*prefix = bus->logical_dev_id_prefix;
+		ret = 0;
+	}
+	rcu_read_unlock();
+
+	return ret;
+}
diff --git a/drivers/pci/controller/pci-hyperv.c b/drivers/pci/controller/pci-hyperv.c
index cfc8fa403dad..55c0a098fef1 100644
--- a/drivers/pci/controller/pci-hyperv.c
+++ b/drivers/pci/controller/pci-hyperv.c
@@ -641,10 +641,7 @@ static void hv_irq_retarget_interrupt(struct irq_data *data)
 	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) |
+	params->device_id = hv_build_logical_dev_id_prefix(hbus->hdev) |
 			   PCI_FUNC(pdev->devfn);
 	params->int_target.vector = hv_msi_get_int_vector(data);
 
@@ -3715,6 +3712,7 @@ static int hv_pci_probe(struct hv_device *hdev,
 	struct hv_pcibus_device *hbus;
 	int ret, dom;
 	u16 dom_req;
+	u32 prefix;
 	char *name;
 
 	bridge = devm_pci_alloc_host_bridge(&hdev->device, 0);
@@ -3857,13 +3855,22 @@ static int hv_pci_probe(struct hv_device *hdev,
 
 	hbus->state = hv_pcibus_probed;
 
-	ret = create_root_hv_pci_bus(hbus);
+	/* Register the bus before scanning any devices on it. */
+	prefix = hv_build_logical_dev_id_prefix(hdev);
+
+	ret = hv_pci_register_dev_id(dom, prefix);
 	if (ret)
 		goto free_windows;
 
+	ret = create_root_hv_pci_bus(hbus);
+	if (ret)
+		goto unregister_pci_bus;
+
 	mutex_unlock(&hbus->state_lock);
 	return 0;
 
+unregister_pci_bus:
+	hv_pci_unregister_dev_id(dom);
 free_windows:
 	hv_pci_free_bridge_windows(hbus);
 exit_d0:
@@ -3977,6 +3984,8 @@ static void hv_pci_remove(struct hv_device *hdev)
 
 	hbus = hv_get_drvdata(hdev);
 	if (hbus->state == hv_pcibus_installed) {
+		int dom = hbus->bridge->domain_nr;
+
 		tasklet_disable(&hdev->channel->callback_event);
 		hbus->state = hv_pcibus_removing;
 		tasklet_enable(&hdev->channel->callback_event);
@@ -3994,6 +4003,8 @@ static void hv_pci_remove(struct hv_device *hdev)
 		hv_pci_remove_slots(hbus);
 		pci_remove_root_bus(hbus->bridge->bus);
 		pci_unlock_rescan_remove();
+
+		hv_pci_unregister_dev_id(dom);
 	}
 
 	hv_pci_bus_exit(hdev, false);
diff --git a/include/asm-generic/mshyperv.h b/include/asm-generic/mshyperv.h
index bf601d67cecb..34d4c332449c 100644
--- a/include/asm-generic/mshyperv.h
+++ b/include/asm-generic/mshyperv.h
@@ -73,6 +73,10 @@ extern enum hv_partition_type hv_curr_partition_type;
 extern void * __percpu *hyperv_pcpu_input_arg;
 extern void * __percpu *hyperv_pcpu_output_arg;
 
+int hv_pci_register_dev_id(int pci_domain_nr, u32 logical_dev_id_prefix);
+void hv_pci_unregister_dev_id(int pci_domain_nr);
+int hv_pci_lookup_dev_id(int pci_domain_nr, u32 *prefix);
+
 u64 hv_do_hypercall(u64 control, void *inputaddr, void *outputaddr);
 u64 hv_do_fast_hypercall8(u16 control, u64 input8);
 u64 hv_do_fast_hypercall16(u16 control, u64 input1, u64 input2);
diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h
index a2b484679eb4..7bc7b9b60002 100644
--- a/include/linux/hyperv.h
+++ b/include/linux/hyperv.h
@@ -1287,6 +1287,14 @@ struct hv_device {
 #define device_to_hv_device(d)	container_of_const(d, struct hv_device, device)
 #define drv_to_hv_drv(d)	container_of_const(d, struct hv_driver, driver)
 
+static inline u32 hv_build_logical_dev_id_prefix(struct hv_device *hdev)
+{
+	return ((u32)hdev->dev_instance.b[5] << 24) |
+	       ((u32)hdev->dev_instance.b[4] << 16) |
+	       ((u32)hdev->dev_instance.b[7] << 8) |
+	       (hdev->dev_instance.b[6] & 0xf8u);
+}
+
 static inline void hv_set_drvdata(struct hv_device *dev, void *data)
 {
 	dev_set_drvdata(&dev->device, data);
-- 
2.52.0