// SPDX-License-Identifier: GPL-2.0 /* * Volume Management Device driver * Copyright (c) 2015, Intel Corporation. */ #include #include #include #include #include #include #include #include #include #include #include #include #include #include #define VMD_CFGBAR 0 #define VMD_MEMBAR1 2 #define VMD_MEMBAR2 4 #define PCI_REG_VMCAP 0x40 #define BUS_RESTRICT_CAP(vmcap) (vmcap & 0x1) #define PCI_REG_VMCONFIG 0x44 #define BUS_RESTRICT_CFG(vmcfg) ((vmcfg >> 8) & 0x3) #define PCI_REG_VMLOCK 0x70 #define MB2_SHADOW_EN(vmlock) (vmlock & 0x2) #define MB2_SHADOW_OFFSET 0x2000 #define MB2_SHADOW_SIZE 16 enum vmd_features { /* * Device may contain registers which hint the physical location of the * membars, in order to allow proper address translation during * resource assignment to enable guest virtualization */ VMD_FEAT_HAS_MEMBAR_SHADOW = (1 << 0), /* * Device may provide root port configuration information which limits * bus numbering */ VMD_FEAT_HAS_BUS_RESTRICTIONS = (1 << 1), /* * Device contains physical location shadow registers in * vendor-specific capability space */ VMD_FEAT_HAS_MEMBAR_SHADOW_VSCAP = (1 << 2), }; /* * Lock for manipulating VMD IRQ lists. */ static DEFINE_RAW_SPINLOCK(list_lock); /** * struct vmd_irq - private data to map driver IRQ to the VMD shared vector * @node: list item for parent traversal. * @irq: back pointer to parent. * @enabled: true if driver enabled IRQ * @virq: the virtual IRQ value provided to the requesting driver. * * Every MSI/MSI-X IRQ requested for a device in a VMD domain will be mapped to * a VMD IRQ using this structure. */ struct vmd_irq { struct list_head node; struct vmd_irq_list *irq; bool enabled; unsigned int virq; }; /** * struct vmd_irq_list - list of driver requested IRQs mapping to a VMD vector * @irq_list: the list of irq's the VMD one demuxes to. * @srcu: SRCU struct for local synchronization. * @count: number of child IRQs assigned to this vector; used to track * sharing. */ struct vmd_irq_list { struct list_head irq_list; struct srcu_struct srcu; unsigned int count; }; struct vmd_dev { struct pci_dev *dev; spinlock_t cfg_lock; char __iomem *cfgbar; int msix_count; struct vmd_irq_list *irqs; struct pci_sysdata sysdata; struct resource resources[3]; struct irq_domain *irq_domain; struct pci_bus *bus; u8 busn_start; }; static inline struct vmd_dev *vmd_from_bus(struct pci_bus *bus) { return container_of(bus->sysdata, struct vmd_dev, sysdata); } static inline unsigned int index_from_irqs(struct vmd_dev *vmd, struct vmd_irq_list *irqs) { return irqs - vmd->irqs; } /* * Drivers managing a device in a VMD domain allocate their own IRQs as before, * but the MSI entry for the hardware it's driving will be programmed with a * destination ID for the VMD MSI-X table. The VMD muxes interrupts in its * domain into one of its own, and the VMD driver de-muxes these for the * handlers sharing that VMD IRQ. The vmd irq_domain provides the operations * and irq_chip to set this up. */ static void vmd_compose_msi_msg(struct irq_data *data, struct msi_msg *msg) { struct vmd_irq *vmdirq = data->chip_data; struct vmd_irq_list *irq = vmdirq->irq; struct vmd_dev *vmd = irq_data_get_irq_handler_data(data); msg->address_hi = MSI_ADDR_BASE_HI; msg->address_lo = MSI_ADDR_BASE_LO | MSI_ADDR_DEST_ID(index_from_irqs(vmd, irq)); msg->data = 0; } /* * We rely on MSI_FLAG_USE_DEF_CHIP_OPS to set the IRQ mask/unmask ops. */ static void vmd_irq_enable(struct irq_data *data) { struct vmd_irq *vmdirq = data->chip_data; unsigned long flags; raw_spin_lock_irqsave(&list_lock, flags); WARN_ON(vmdirq->enabled); list_add_tail_rcu(&vmdirq->node, &vmdirq->irq->irq_list); vmdirq->enabled = true; raw_spin_unlock_irqrestore(&list_lock, flags); data->chip->irq_unmask(data); } static void vmd_irq_disable(struct irq_data *data) { struct vmd_irq *vmdirq = data->chip_data; unsigned long flags; data->chip->irq_mask(data); raw_spin_lock_irqsave(&list_lock, flags); if (vmdirq->enabled) { list_del_rcu(&vmdirq->node); vmdirq->enabled = false; } raw_spin_unlock_irqrestore(&list_lock, flags); } /* * XXX: Stubbed until we develop acceptable way to not create conflicts with * other devices sharing the same vector. */ static int vmd_irq_set_affinity(struct irq_data *data, const struct cpumask *dest, bool force) { return -EINVAL; } static struct irq_chip vmd_msi_controller = { .name = "VMD-MSI", .irq_enable = vmd_irq_enable, .irq_disable = vmd_irq_disable, .irq_compose_msi_msg = vmd_compose_msi_msg, .irq_set_affinity = vmd_irq_set_affinity, }; static irq_hw_number_t vmd_get_hwirq(struct msi_domain_info *info, msi_alloc_info_t *arg) { return 0; } /* * XXX: We can be even smarter selecting the best IRQ once we solve the * affinity problem. */ static struct vmd_irq_list *vmd_next_irq(struct vmd_dev *vmd, struct msi_desc *desc) { int i, best = 1; unsigned long flags; if (vmd->msix_count == 1) return &vmd->irqs[0]; /* * White list for fast-interrupt handlers. All others will share the * "slow" interrupt vector. */ switch (msi_desc_to_pci_dev(desc)->class) { case PCI_CLASS_STORAGE_EXPRESS: break; default: return &vmd->irqs[0]; } raw_spin_lock_irqsave(&list_lock, flags); for (i = 1; i < vmd->msix_count; i++) if (vmd->irqs[i].count < vmd->irqs[best].count) best = i; vmd->irqs[best].count++; raw_spin_unlock_irqrestore(&list_lock, flags); return &vmd->irqs[best]; } static int vmd_msi_init(struct irq_domain *domain, struct msi_domain_info *info, unsigned int virq, irq_hw_number_t hwirq, msi_alloc_info_t *arg) { struct msi_desc *desc = arg->desc; struct vmd_dev *vmd = vmd_from_bus(msi_desc_to_pci_dev(desc)->bus); struct vmd_irq *vmdirq = kzalloc(sizeof(*vmdirq), GFP_KERNEL); unsigned int index, vector; if (!vmdirq) return -ENOMEM; INIT_LIST_HEAD(&vmdirq->node); vmdirq->irq = vmd_next_irq(vmd, desc); vmdirq->virq = virq; index = index_from_irqs(vmd, vmdirq->irq); vector = pci_irq_vector(vmd->dev, index); irq_domain_set_info(domain, virq, vector, info->chip, vmdirq, handle_untracked_irq, vmd, NULL); return 0; } static void vmd_msi_free(struct irq_domain *domain, struct msi_domain_info *info, unsigned int virq) { struct vmd_irq *vmdirq = irq_get_chip_data(virq); unsigned long flags; synchronize_srcu(&vmdirq->irq->srcu); /* XXX: Potential optimization to rebalance */ raw_spin_lock_irqsave(&list_lock, flags); vmdirq->irq->count--; raw_spin_unlock_irqrestore(&list_lock, flags); kfree(vmdirq); } static int vmd_msi_prepare(struct irq_domain *domain, struct device *dev, int nvec, msi_alloc_info_t *arg) { struct pci_dev *pdev = to_pci_dev(dev); struct vmd_dev *vmd = vmd_from_bus(pdev->bus); if (nvec > vmd->msix_count) return vmd->msix_count; memset(arg, 0, sizeof(*arg)); return 0; } static void vmd_set_desc(msi_alloc_info_t *arg, struct msi_desc *desc) { arg->desc = desc; } static struct msi_domain_ops vmd_msi_domain_ops = { .get_hwirq = vmd_get_hwirq, .msi_init = vmd_msi_init, .msi_free = vmd_msi_free, .msi_prepare = vmd_msi_prepare, .set_desc = vmd_set_desc, }; static struct msi_domain_info vmd_msi_domain_info = { .flags = MSI_FLAG_USE_DEF_DOM_OPS | MSI_FLAG_USE_DEF_CHIP_OPS | MSI_FLAG_PCI_MSIX, .ops = &vmd_msi_domain_ops, .chip = &vmd_msi_controller, }; static char __iomem *vmd_cfg_addr(struct vmd_dev *vmd, struct pci_bus *bus, unsigned int devfn, int reg, int len) { char __iomem *addr = vmd->cfgbar + ((bus->number - vmd->busn_start) << 20) + (devfn << 12) + reg; if ((addr - vmd->cfgbar) + len >= resource_size(&vmd->dev->resource[VMD_CFGBAR])) return NULL; return addr; } /* * CPU may deadlock if config space is not serialized on some versions of this * hardware, so all config space access is done under a spinlock. */ static int vmd_pci_read(struct pci_bus *bus, unsigned int devfn, int reg, int len, u32 *value) { struct vmd_dev *vmd = vmd_from_bus(bus); char __iomem *addr = vmd_cfg_addr(vmd, bus, devfn, reg, len); unsigned long flags; int ret = 0; if (!addr) return -EFAULT; spin_lock_irqsave(&vmd->cfg_lock, flags); switch (len) { case 1: *value = readb(addr); break; case 2: *value = readw(addr); break; case 4: *value = readl(addr); break; default: ret = -EINVAL; break; } spin_unlock_irqrestore(&vmd->cfg_lock, flags); return ret; } /* * VMD h/w converts non-posted config writes to posted memory writes. The * read-back in this function forces the completion so it returns only after * the config space was written, as expected. */ static int vmd_pci_write(struct pci_bus *bus, unsigned int devfn, int reg, int len, u32 value) { struct vmd_dev *vmd = vmd_from_bus(bus); char __iomem *addr = vmd_cfg_addr(vmd, bus, devfn, reg, len); unsigned long flags; int ret = 0; if (!addr) return -EFAULT; spin_lock_irqsave(&vmd->cfg_lock, flags); switch (len) { case 1: writeb(value, addr); readb(addr); break; case 2: writew(value, addr); readw(addr); break; case 4: writel(value, addr); readl(addr); break; default: ret = -EINVAL; break; } spin_unlock_irqrestore(&vmd->cfg_lock, flags); return ret; } static struct pci_ops vmd_ops = { .read = vmd_pci_read, .write = vmd_pci_write, }; static void vmd_attach_resources(struct vmd_dev *vmd) { vmd->dev->resource[VMD_MEMBAR1].child = &vmd->resources[1]; vmd->dev->resource[VMD_MEMBAR2].child = &vmd->resources[2]; } static void vmd_detach_resources(struct vmd_dev *vmd) { vmd->dev->resource[VMD_MEMBAR1].child = NULL; vmd->dev->resource[VMD_MEMBAR2].child = NULL; } /* * VMD domains start at 0x10000 to not clash with ACPI _SEG domains. * Per ACPI r6.0, sec 6.5.6, _SEG returns an integer, of which the lower * 16 bits are the PCI Segment Group (domain) number. Other bits are * currently reserved. */ static int vmd_find_free_domain(void) { int domain = 0xffff; struct pci_bus *bus = NULL; while ((bus = pci_find_next_bus(bus)) != NULL) domain = max_t(int, domain, pci_domain_nr(bus)); return domain + 1; } static int vmd_enable_domain(struct vmd_dev *vmd, unsigned long features) { struct pci_sysdata *sd = &vmd->sysdata; struct fwnode_handle *fn; struct resource *res; u32 upper_bits; unsigned long flags; LIST_HEAD(resources); resource_size_t offset[2] = {0}; resource_size_t membar2_offset = 0x2000; struct pci_bus *child; /* * Shadow registers may exist in certain VMD device ids which allow * guests to correctly assign host physical addresses to the root ports * and child devices. These registers will either return the host value * or 0, depending on an enable bit in the VMD device. */ if (features & VMD_FEAT_HAS_MEMBAR_SHADOW) { u32 vmlock; int ret; membar2_offset = MB2_SHADOW_OFFSET + MB2_SHADOW_SIZE; ret = pci_read_config_dword(vmd->dev, PCI_REG_VMLOCK, &vmlock); if (ret || vmlock == ~0) return -ENODEV; if (MB2_SHADOW_EN(vmlock)) { void __iomem *membar2; membar2 = pci_iomap(vmd->dev, VMD_MEMBAR2, 0); if (!membar2) return -ENOMEM; offset[0] = vmd->dev->resource[VMD_MEMBAR1].start - (readq(membar2 + MB2_SHADOW_OFFSET) & PCI_BASE_ADDRESS_MEM_MASK); offset[1] = vmd->dev->resource[VMD_MEMBAR2].start - (readq(membar2 + MB2_SHADOW_OFFSET + 8) & PCI_BASE_ADDRESS_MEM_MASK); pci_iounmap(vmd->dev, membar2); } } if (features & VMD_FEAT_HAS_MEMBAR_SHADOW_VSCAP) { int pos = pci_find_capability(vmd->dev, PCI_CAP_ID_VNDR); u32 reg, regu; pci_read_config_dword(vmd->dev, pos + 4, ®); /* "SHDW" */ if (pos && reg == 0x53484457) { pci_read_config_dword(vmd->dev, pos + 8, ®); pci_read_config_dword(vmd->dev, pos + 12, ®u); offset[0] = vmd->dev->resource[VMD_MEMBAR1].start - (((u64) regu << 32 | reg) & PCI_BASE_ADDRESS_MEM_MASK); pci_read_config_dword(vmd->dev, pos + 16, ®); pci_read_config_dword(vmd->dev, pos + 20, ®u); offset[1] = vmd->dev->resource[VMD_MEMBAR2].start - (((u64) regu << 32 | reg) & PCI_BASE_ADDRESS_MEM_MASK); } } /* * Certain VMD devices may have a root port configuration option which * limits the bus range to between 0-127, 128-255, or 224-255 */ if (features & VMD_FEAT_HAS_BUS_RESTRICTIONS) { u16 reg16; pci_read_config_word(vmd->dev, PCI_REG_VMCAP, ®16); if (BUS_RESTRICT_CAP(reg16)) { pci_read_config_word(vmd->dev, PCI_REG_VMCONFIG, ®16); switch (BUS_RESTRICT_CFG(reg16)) { case 1: vmd->busn_start = 128; break; case 2: vmd->busn_start = 224; break; case 3: pci_err(vmd->dev, "Unknown Bus Offset Setting\n"); return -ENODEV; default: break; } } } res = &vmd->dev->resource[VMD_CFGBAR]; vmd->resources[0] = (struct resource) { .name = "VMD CFGBAR", .start = vmd->busn_start, .end = vmd->busn_start + (resource_size(res) >> 20) - 1, .flags = IORESOURCE_BUS | IORESOURCE_PCI_FIXED, }; /* * If the window is below 4GB, clear IORESOURCE_MEM_64 so we can * put 32-bit resources in the window. * * There's no hardware reason why a 64-bit window *couldn't* * contain a 32-bit resource, but pbus_size_mem() computes the * bridge window size assuming a 64-bit window will contain no * 32-bit resources. __pci_assign_resource() enforces that * artificial restriction to make sure everything will fit. * * The only way we could use a 64-bit non-prefetchable MEMBAR is * if its address is <4GB so that we can convert it to a 32-bit * resource. To be visible to the host OS, all VMD endpoints must * be initially configured by platform BIOS, which includes setting * up these resources. We can assume the device is configured * according to the platform needs. */ res = &vmd->dev->resource[VMD_MEMBAR1]; upper_bits = upper_32_bits(res->end); flags = res->flags & ~IORESOURCE_SIZEALIGN; if (!upper_bits) flags &= ~IORESOURCE_MEM_64; vmd->resources[1] = (struct resource) { .name = "VMD MEMBAR1", .start = res->start, .end = res->end, .flags = flags, .parent = res, }; res = &vmd->dev->resource[VMD_MEMBAR2]; upper_bits = upper_32_bits(res->end); flags = res->flags & ~IORESOURCE_SIZEALIGN; if (!upper_bits) flags &= ~IORESOURCE_MEM_64; vmd->resources[2] = (struct resource) { .name = "VMD MEMBAR2", .start = res->start + membar2_offset, .end = res->end, .flags = flags, .parent = res, }; sd->vmd_dev = vmd->dev; sd->domain = vmd_find_free_domain(); if (sd->domain < 0) return sd->domain; sd->node = pcibus_to_node(vmd->dev->bus); fn = irq_domain_alloc_named_id_fwnode("VMD-MSI", vmd->sysdata.domain); if (!fn) return -ENODEV; vmd->irq_domain = pci_msi_create_irq_domain(fn, &vmd_msi_domain_info, NULL); if (!vmd->irq_domain) { irq_domain_free_fwnode(fn); return -ENODEV; } /* * Override the irq domain bus token so the domain can be distinguished * from a regular PCI/MSI domain. */ irq_domain_update_bus_token(vmd->irq_domain, DOMAIN_BUS_VMD_MSI); pci_add_resource(&resources, &vmd->resources[0]); pci_add_resource_offset(&resources, &vmd->resources[1], offset[0]); pci_add_resource_offset(&resources, &vmd->resources[2], offset[1]); vmd->bus = pci_create_root_bus(&vmd->dev->dev, vmd->busn_start, &vmd_ops, sd, &resources); if (!vmd->bus) { pci_free_resource_list(&resources); irq_domain_remove(vmd->irq_domain); irq_domain_free_fwnode(fn); return -ENODEV; } vmd_attach_resources(vmd); dev_set_msi_domain(&vmd->bus->dev, vmd->irq_domain); pci_scan_child_bus(vmd->bus); pci_assign_unassigned_bus_resources(vmd->bus); /* * VMD root buses are virtual and don't return true on pci_is_pcie() * and will fail pcie_bus_configure_settings() early. It can instead be * run on each of the real root ports. */ list_for_each_entry(child, &vmd->bus->children, node) pcie_bus_configure_settings(child); pci_bus_add_devices(vmd->bus); WARN(sysfs_create_link(&vmd->dev->dev.kobj, &vmd->bus->dev.kobj, "domain"), "Can't create symlink to domain\n"); return 0; } static irqreturn_t vmd_irq(int irq, void *data) { struct vmd_irq_list *irqs = data; struct vmd_irq *vmdirq; int idx; idx = srcu_read_lock(&irqs->srcu); list_for_each_entry_rcu(vmdirq, &irqs->irq_list, node) generic_handle_irq(vmdirq->virq); srcu_read_unlock(&irqs->srcu, idx); return IRQ_HANDLED; } static int vmd_probe(struct pci_dev *dev, const struct pci_device_id *id) { struct vmd_dev *vmd; int i, err; if (resource_size(&dev->resource[VMD_CFGBAR]) < (1 << 20)) return -ENOMEM; vmd = devm_kzalloc(&dev->dev, sizeof(*vmd), GFP_KERNEL); if (!vmd) return -ENOMEM; vmd->dev = dev; err = pcim_enable_device(dev); if (err < 0) return err; vmd->cfgbar = pcim_iomap(dev, VMD_CFGBAR, 0); if (!vmd->cfgbar) return -ENOMEM; pci_set_master(dev); if (dma_set_mask_and_coherent(&dev->dev, DMA_BIT_MASK(64)) && dma_set_mask_and_coherent(&dev->dev, DMA_BIT_MASK(32))) return -ENODEV; vmd->msix_count = pci_msix_vec_count(dev); if (vmd->msix_count < 0) return -ENODEV; vmd->msix_count = pci_alloc_irq_vectors(dev, 1, vmd->msix_count, PCI_IRQ_MSIX); if (vmd->msix_count < 0) return vmd->msix_count; vmd->irqs = devm_kcalloc(&dev->dev, vmd->msix_count, sizeof(*vmd->irqs), GFP_KERNEL); if (!vmd->irqs) return -ENOMEM; for (i = 0; i < vmd->msix_count; i++) { err = init_srcu_struct(&vmd->irqs[i].srcu); if (err) return err; INIT_LIST_HEAD(&vmd->irqs[i].irq_list); err = devm_request_irq(&dev->dev, pci_irq_vector(dev, i), vmd_irq, IRQF_NO_THREAD, "vmd", &vmd->irqs[i]); if (err) return err; } spin_lock_init(&vmd->cfg_lock); pci_set_drvdata(dev, vmd); err = vmd_enable_domain(vmd, (unsigned long) id->driver_data); if (err) return err; dev_info(&vmd->dev->dev, "Bound to PCI domain %04x\n", vmd->sysdata.domain); return 0; } static void vmd_cleanup_srcu(struct vmd_dev *vmd) { int i; for (i = 0; i < vmd->msix_count; i++) cleanup_srcu_struct(&vmd->irqs[i].srcu); } static void vmd_remove(struct pci_dev *dev) { struct vmd_dev *vmd = pci_get_drvdata(dev); struct fwnode_handle *fn = vmd->irq_domain->fwnode; sysfs_remove_link(&vmd->dev->dev.kobj, "domain"); pci_stop_root_bus(vmd->bus); pci_remove_root_bus(vmd->bus); vmd_cleanup_srcu(vmd); vmd_detach_resources(vmd); irq_domain_remove(vmd->irq_domain); irq_domain_free_fwnode(fn); } #ifdef CONFIG_PM_SLEEP static int vmd_suspend(struct device *dev) { struct pci_dev *pdev = to_pci_dev(dev); struct vmd_dev *vmd = pci_get_drvdata(pdev); int i; for (i = 0; i < vmd->msix_count; i++) devm_free_irq(dev, pci_irq_vector(pdev, i), &vmd->irqs[i]); pci_save_state(pdev); return 0; } static int vmd_resume(struct device *dev) { struct pci_dev *pdev = to_pci_dev(dev); struct vmd_dev *vmd = pci_get_drvdata(pdev); int err, i; for (i = 0; i < vmd->msix_count; i++) { err = devm_request_irq(dev, pci_irq_vector(pdev, i), vmd_irq, IRQF_NO_THREAD, "vmd", &vmd->irqs[i]); if (err) return err; } pci_restore_state(pdev); return 0; } #endif static SIMPLE_DEV_PM_OPS(vmd_dev_pm_ops, vmd_suspend, vmd_resume); static const struct pci_device_id vmd_ids[] = { {PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_VMD_201D), .driver_data = VMD_FEAT_HAS_MEMBAR_SHADOW_VSCAP,}, {PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_VMD_28C0), .driver_data = VMD_FEAT_HAS_MEMBAR_SHADOW | VMD_FEAT_HAS_BUS_RESTRICTIONS,}, {PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x467f), .driver_data = VMD_FEAT_HAS_MEMBAR_SHADOW_VSCAP | VMD_FEAT_HAS_BUS_RESTRICTIONS,}, {PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x4c3d), .driver_data = VMD_FEAT_HAS_MEMBAR_SHADOW_VSCAP | VMD_FEAT_HAS_BUS_RESTRICTIONS,}, {PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_VMD_9A0B), .driver_data = VMD_FEAT_HAS_MEMBAR_SHADOW_VSCAP | VMD_FEAT_HAS_BUS_RESTRICTIONS,}, {0,} }; MODULE_DEVICE_TABLE(pci, vmd_ids); static struct pci_driver vmd_drv = { .name = "vmd", .id_table = vmd_ids, .probe = vmd_probe, .remove = vmd_remove, .driver = { .pm = &vmd_dev_pm_ops, }, }; module_pci_driver(vmd_drv); MODULE_AUTHOR("Intel Corporation"); MODULE_LICENSE("GPL v2"); MODULE_VERSION("0.6");