From 8f6a6b3c50ce1caa81c47bb5855be02050c0eff7 Mon Sep 17 00:00:00 2001 From: Sunil Muthuswamy Date: Mon, 12 Jul 2021 21:58:18 +0000 Subject: PCI: hv: Support for create interrupt v3 Hyper-V vPCI protocol version 1_4 adds support for create interrupt v3. Create interrupt v3 essentially makes the size of the vector field bigger in the message, thereby allowing bigger vector values. For example, that will come into play for supporting LPI vectors on ARM, which start at 8192. Link: https://lore.kernel.org/r/MW4PR21MB20026A6EA554A0B9EC696AA8C0159@MW4PR21MB2002.namprd21.prod.outlook.com Signed-off-by: Sunil Muthuswamy Signed-off-by: Lorenzo Pieralisi Reviewed-by: Michael Kelley Reviewed-by: Wei Liu --- drivers/pci/controller/pci-hyperv.c | 67 ++++++++++++++++++++++++++++++++++--- 1 file changed, 62 insertions(+), 5 deletions(-) (limited to 'drivers/pci/controller/pci-hyperv.c') diff --git a/drivers/pci/controller/pci-hyperv.c b/drivers/pci/controller/pci-hyperv.c index a53bd8728d0d..c1575a5d0352 100644 --- a/drivers/pci/controller/pci-hyperv.c +++ b/drivers/pci/controller/pci-hyperv.c @@ -64,6 +64,7 @@ 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 +74,7 @@ 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 +124,8 @@ 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 +239,21 @@ 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 +402,12 @@ 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; @@ -1328,6 +1353,15 @@ 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 +1373,27 @@ 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 +1428,7 @@ 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 +1476,13 @@ 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 -- cgit From 418cb6c8e051119125b886c879efdacb04df7165 Mon Sep 17 00:00:00 2001 From: Arnd Bergmann Date: Tue, 27 Jul 2021 02:06:54 +0800 Subject: PCI: hv: Generify PCI probing In order to support ARM64 Hyper-V PCI, we need to set up the bridge at probing time because ARM64 is a PCI_DOMAIN_GENERIC=y arch and we don't have pci_config_window (ARM64 sysdata) for a PCI root bus on Hyper-V, so it's impossible to retrieve the information (e.g. PCI domains, MSI domains) from bus sysdata on ARM64 after creation. Originally in create_root_hv_pci_bus(), pci_create_root_bus() is used to create the root bus and the corresponding bridge based on x86 sysdata. Now we create a bridge first and then call pci_scan_root_bus_bridge(), which allows us to do the necessary set-ups for the bridge. Link: https://lore.kernel.org/r/20210726180657.142727-6-boqun.feng@gmail.com Signed-off-by: Arnd Bergmann Signed-off-by: Boqun Feng Signed-off-by: Lorenzo Pieralisi --- drivers/pci/controller/pci-hyperv.c | 57 +++++++++++++++++++------------------ 1 file changed, 30 insertions(+), 27 deletions(-) (limited to 'drivers/pci/controller/pci-hyperv.c') diff --git a/drivers/pci/controller/pci-hyperv.c b/drivers/pci/controller/pci-hyperv.c index a53bd8728d0d..8d42da5dd1d4 100644 --- a/drivers/pci/controller/pci-hyperv.c +++ b/drivers/pci/controller/pci-hyperv.c @@ -449,6 +449,7 @@ enum hv_pcibus_state { struct hv_pcibus_device { struct pci_sysdata sysdata; + struct pci_host_bridge *bridge; /* Protocol version negotiated with the host */ enum pci_protocol_version_t protocol_version; enum hv_pcibus_state state; @@ -464,8 +465,6 @@ 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; @@ -1797,7 +1796,7 @@ 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 +1826,7 @@ 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 +1849,22 @@ 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 +2127,7 @@ 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(); @@ -2295,8 +2295,8 @@ 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); @@ -2662,8 +2662,7 @@ 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 +2681,7 @@ 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 +3000,7 @@ 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 +3013,10 @@ 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 +3038,8 @@ 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; @@ -3071,7 +3076,6 @@ static int hv_pci_probe(struct hv_device *hdev, 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); @@ -3295,9 +3299,9 @@ 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(); } @@ -3307,7 +3311,6 @@ 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); @@ -3390,7 +3393,7 @@ 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) -- cgit From 38c0d266dc80b81f7f72314620f01ff6a1e119fe Mon Sep 17 00:00:00 2001 From: Boqun Feng Date: Tue, 27 Jul 2021 02:06:55 +0800 Subject: PCI: hv: Set ->domain_nr of pci_host_bridge at probing time No functional change, just store and maintain the PCI domain number in the ->domain_nr of pci_host_bridge. Note that we still need to keep the copy of domain number in x86-specific pci_sysdata, because x86 is not a PCI_DOMAINS_GENERIC=y architecture, so the ->domain_nr of pci_host_bridge doesn't work for it yet. Link: https://lore.kernel.org/r/20210726180657.142727-7-boqun.feng@gmail.com Signed-off-by: Boqun Feng Signed-off-by: Lorenzo Pieralisi --- drivers/pci/controller/pci-hyperv.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) (limited to 'drivers/pci/controller/pci-hyperv.c') diff --git a/drivers/pci/controller/pci-hyperv.c b/drivers/pci/controller/pci-hyperv.c index 8d42da5dd1d4..5741b1dd3c14 100644 --- a/drivers/pci/controller/pci-hyperv.c +++ b/drivers/pci/controller/pci-hyperv.c @@ -2299,7 +2299,7 @@ static void hv_eject_device_work(struct work_struct *work) * 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); @@ -3071,6 +3071,7 @@ 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; hbus->sysdata.domain = dom; hbus->hdev = hdev; @@ -3080,7 +3081,7 @@ static int hv_pci_probe(struct hv_device *hdev, 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; @@ -3207,7 +3208,7 @@ 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; @@ -3315,7 +3316,7 @@ static int hv_pci_remove(struct hv_device *hdev) irq_domain_remove(hbus->irq_domain); irq_domain_free_fwnode(hbus->sysdata.fwnode); - hv_put_dom_num(hbus->sysdata.domain); + hv_put_dom_num(hbus->bridge->domain_nr); kfree(hbus); return ret; -- cgit From 9e7f9178ab4943b3a7294a12bc38925c515ca3f0 Mon Sep 17 00:00:00 2001 From: Boqun Feng Date: Tue, 27 Jul 2021 02:06:56 +0800 Subject: PCI: hv: Set up MSI domain at bridge probing time Since PCI_HYPERV depends on PCI_MSI_IRQ_DOMAIN which selects GENERIC_MSI_IRQ_DOMAIN, we can use dev_set_msi_domain() to set up the MSI domain at probing time, and this works for both x86 and ARM64. Therefore use it as the preparation for ARM64 Hyper-V PCI support. As a result, no longer need to maintain ->fwnode in x86 specific pci_sysdata, and make hv_pcibus_device own it instead. Link: https://lore.kernel.org/r/20210726180657.142727-8-boqun.feng@gmail.com Signed-off-by: Boqun Feng Signed-off-by: Lorenzo Pieralisi --- drivers/pci/controller/pci-hyperv.c | 13 ++++++++----- 1 file changed, 8 insertions(+), 5 deletions(-) (limited to 'drivers/pci/controller/pci-hyperv.c') diff --git a/drivers/pci/controller/pci-hyperv.c b/drivers/pci/controller/pci-hyperv.c index 5741b1dd3c14..e6276aaa4659 100644 --- a/drivers/pci/controller/pci-hyperv.c +++ b/drivers/pci/controller/pci-hyperv.c @@ -450,6 +450,7 @@ enum hv_pcibus_state { struct hv_pcibus_device { struct pci_sysdata sysdata; 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; @@ -1565,7 +1566,7 @@ 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) { @@ -1574,6 +1575,8 @@ 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; } @@ -3118,9 +3121,9 @@ 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; } @@ -3198,7 +3201,7 @@ 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: @@ -3314,7 +3317,7 @@ static int hv_pci_remove(struct hv_device *hdev) hv_free_config_window(hbus); 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->bridge->domain_nr); -- cgit From 88f94c7f8f40d7e26f991f6f6ed914ff44361d75 Mon Sep 17 00:00:00 2001 From: Boqun Feng Date: Tue, 27 Jul 2021 02:06:57 +0800 Subject: PCI: hv: Turn on the host bridge probing on ARM64 Now we have everything we need, just provide a proper sysdata type for the bus to use on ARM64 and everything else works. Link: https://lore.kernel.org/r/20210726180657.142727-9-boqun.feng@gmail.com Signed-off-by: Boqun Feng Signed-off-by: Lorenzo Pieralisi --- drivers/pci/controller/pci-hyperv.c | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'drivers/pci/controller/pci-hyperv.c') diff --git a/drivers/pci/controller/pci-hyperv.c b/drivers/pci/controller/pci-hyperv.c index e6276aaa4659..62dbe98d1fe1 100644 --- a/drivers/pci/controller/pci-hyperv.c +++ b/drivers/pci/controller/pci-hyperv.c @@ -40,6 +40,7 @@ #include #include #include +#include #include #include #include @@ -448,7 +449,11 @@ 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 */ @@ -3075,7 +3080,9 @@ static int hv_pci_probe(struct hv_device *hdev, dom_req, dom); hbus->bridge->domain_nr = dom; +#ifdef CONFIG_X86 hbus->sysdata.domain = dom; +#endif hbus->hdev = hdev; INIT_LIST_HEAD(&hbus->children); -- cgit