diff --git a/Documentation/userspace-api/iommufd.rst b/Documentation/userspace-api/iommufd.rst index aa004fa..70289d6 100644 --- a/Documentation/userspace-api/iommufd.rst +++ b/Documentation/userspace-api/iommufd.rst @@ -41,46 +41,133 @@ Following IOMMUFD objects are exposed to userspace: - IOMMUFD_OBJ_DEVICE, representing a device that is bound to iommufd by an external driver. -- IOMMUFD_OBJ_HW_PAGETABLE, representing an actual hardware I/O page table - (i.e. a single struct iommu_domain) managed by the iommu driver. - - The IOAS has a list of HW_PAGETABLES that share the same IOVA mapping and - it will synchronize its mapping with each member HW_PAGETABLE. +- IOMMUFD_OBJ_HWPT_PAGING, representing an actual hardware I/O page table + (i.e. a single struct iommu_domain) managed by the iommu driver. "PAGING" + primarly indicates this type of HWPT should be linked to an IOAS. It also + indicates that it is backed by an iommu_domain with __IOMMU_DOMAIN_PAGING + feature flag. This can be either an UNMANAGED stage-1 domain for a device + running in the user space, or a nesting parent stage-2 domain for mappings + from guest-level physical addresses to host-level physical addresses. + + The IOAS has a list of HWPT_PAGINGs that share the same IOVA mapping and + it will synchronize its mapping with each member HWPT_PAGING. + +- IOMMUFD_OBJ_HWPT_NESTED, representing an actual hardware I/O page table + (i.e. a single struct iommu_domain) managed by user space (e.g. guest OS). + "NESTED" indicates that this type of HWPT should be linked to an HWPT_PAGING. + It also indicates that it is backed by an iommu_domain that has a type of + IOMMU_DOMAIN_NESTED. This must be a stage-1 domain for a device running in + the user space (e.g. in a guest VM enabling the IOMMU nested translation + feature.) As such, it must be created with a given nesting parent stage-2 + domain to associate to. This nested stage-1 page table managed by the user + space usually has mappings from guest-level I/O virtual addresses to guest- + level physical addresses. + +- IOMMUFD_OBJ_VIOMMU, representing a slice of the physical IOMMU instance, + passed to or shared with a VM. It may be some HW-accelerated virtualization + features and some SW resources used by the VM. For examples: + + * Security namespace for guest owned ID, e.g. guest-controlled cache tags + * Non-device-affiliated event reporting, e.g. invalidation queue errors + * Access to a sharable nesting parent pagetable across physical IOMMUs + * Virtualization of various platforms IDs, e.g. RIDs and others + * Delivery of paravirtualized invalidation + * Direct assigned invalidation queues + * Direct assigned interrupts + + Such a vIOMMU object generally has the access to a nesting parent pagetable + to support some HW-accelerated virtualization features. So, a vIOMMU object + must be created given a nesting parent HWPT_PAGING object, and then it would + encapsulate that HWPT_PAGING object. Therefore, a vIOMMU object can be used + to allocate an HWPT_NESTED object in place of the encapsulated HWPT_PAGING. + + .. note:: + + The name "vIOMMU" isn't necessarily identical to a virtualized IOMMU in a + VM. A VM can have one giant virtualized IOMMU running on a machine having + multiple physical IOMMUs, in which case the VMM will dispatch the requests + or configurations from this single virtualized IOMMU instance to multiple + vIOMMU objects created for individual slices of different physical IOMMUs. + In other words, a vIOMMU object is always a representation of one physical + IOMMU, not necessarily of a virtualized IOMMU. For VMMs that want the full + virtualization features from physical IOMMUs, it is suggested to build the + same number of virtualized IOMMUs as the number of physical IOMMUs, so the + passed-through devices would be connected to their own virtualized IOMMUs + backed by corresponding vIOMMU objects, in which case a guest OS would do + the "dispatch" naturally instead of VMM trappings. + +- IOMMUFD_OBJ_VDEVICE, representing a virtual device for an IOMMUFD_OBJ_DEVICE + against an IOMMUFD_OBJ_VIOMMU. This virtual device holds the device's virtual + information or attributes (related to the vIOMMU) in a VM. An immediate vDATA + example can be the virtual ID of the device on a vIOMMU, which is a unique ID + that VMM assigns to the device for a translation channel/port of the vIOMMU, + e.g. vSID of ARM SMMUv3, vDeviceID of AMD IOMMU, and vRID of Intel VT-d to a + Context Table. Potential use cases of some advanced security information can + be forwarded via this object too, such as security level or realm information + in a Confidential Compute Architecture. A VMM should create a vDEVICE object + to forward all the device information in a VM, when it connects a device to a + vIOMMU, which is a separate ioctl call from attaching the same device to an + HWPT_PAGING that the vIOMMU holds. All user-visible objects are destroyed via the IOMMU_DESTROY uAPI. -The diagram below shows relationship between user-visible objects and kernel +The diagrams below show relationships between user-visible objects and kernel datastructures (external to iommufd), with numbers referred to operations creating the objects and links:: - _________________________________________________________ - | iommufd | - | [1] | - | _________________ | - | | | | - | | | | - | | | | - | | | | - | | | | - | | | | - | | | [3] [2] | - | | | ____________ __________ | - | | IOAS |<--| |<------| | | - | | | |HW_PAGETABLE| | DEVICE | | - | | | |____________| |__________| | - | | | | | | - | | | | | | - | | | | | | - | | | | | | - | | | | | | - | |_________________| | | | - | | | | | - |_________|___________________|___________________|_______| - | | | - | _____v______ _______v_____ - | PFN storage | | | | - |------------>|iommu_domain| |struct device| - |____________| |_____________| + _______________________________________________________________________ + | iommufd (HWPT_PAGING only) | + | | + | [1] [3] [2] | + | ________________ _____________ ________ | + | | | | | | | | + | | IOAS |<---| HWPT_PAGING |<---------------------| DEVICE | | + | |________________| |_____________| |________| | + | | | | | + |_________|____________________|__________________________________|_____| + | | | + | ______v_____ ___v__ + | PFN storage | (paging) | |struct| + |------------>|iommu_domain|<-----------------------|device| + |____________| |______| + + _______________________________________________________________________ + | iommufd (with HWPT_NESTED) | + | | + | [1] [3] [4] [2] | + | ________________ _____________ _____________ ________ | + | | | | | | | | | | + | | IOAS |<---| HWPT_PAGING |<---| HWPT_NESTED |<--| DEVICE | | + | |________________| |_____________| |_____________| |________| | + | | | | | | + |_________|____________________|__________________|_______________|_____| + | | | | + | ______v_____ ______v_____ ___v__ + | PFN storage | (paging) | | (nested) | |struct| + |------------>|iommu_domain|<----|iommu_domain|<----|device| + |____________| |____________| |______| + + _______________________________________________________________________ + | iommufd (with vIOMMU/vDEVICE) | + | | + | [5] [6] | + | _____________ _____________ | + | | | | | | + | |----------------| vIOMMU |<---| vDEVICE |<----| | + | | | | |_____________| | | + | | | | | | + | | [1] | | [4] | [2] | + | | ______ | | _____________ _|______ | + | | | | | [3] | | | | | | + | | | IOAS |<---|(HWPT_PAGING)|<---| HWPT_NESTED |<--| DEVICE | | + | | |______| |_____________| |_____________| |________| | + | | | | | | | + |______|________|______________|__________________|_______________|_____| + | | | | | + ______v_____ | ______v_____ ______v_____ ___v__ + | struct | | PFN | (paging) | | (nested) | |struct| + |iommu_device| |------>|iommu_domain|<----|iommu_domain|<----|device| + |____________| storage|____________| |____________| |______| 1. IOMMUFD_OBJ_IOAS is created via the IOMMU_IOAS_ALLOC uAPI. An iommufd can hold multiple IOAS objects. IOAS is the most generic object and does not @@ -94,21 +181,63 @@ creating the objects and links:: device. The driver must also set the driver_managed_dma flag and must not touch the device until this operation succeeds. -3. IOMMUFD_OBJ_HW_PAGETABLE is created when an external driver calls the IOMMUFD - kAPI to attach a bound device to an IOAS. Similarly the external driver uAPI - allows userspace to initiate the attaching operation. If a compatible - pagetable already exists then it is reused for the attachment. Otherwise a - new pagetable object and iommu_domain is created. Successful completion of - this operation sets up the linkages among IOAS, device and iommu_domain. Once - this completes the device could do DMA. - - Every iommu_domain inside the IOAS is also represented to userspace as a - HW_PAGETABLE object. +3. IOMMUFD_OBJ_HWPT_PAGING can be created in two ways: + + * IOMMUFD_OBJ_HWPT_PAGING is automatically created when an external driver + calls the IOMMUFD kAPI to attach a bound device to an IOAS. Similarly the + external driver uAPI allows userspace to initiate the attaching operation. + If a compatible member HWPT_PAGING object exists in the IOAS's HWPT_PAGING + list, then it will be reused. Otherwise a new HWPT_PAGING that represents + an iommu_domain to userspace will be created, and then added to the list. + Successful completion of this operation sets up the linkages among IOAS, + device and iommu_domain. Once this completes the device could do DMA. + + * IOMMUFD_OBJ_HWPT_PAGING can be manually created via the IOMMU_HWPT_ALLOC + uAPI, provided an ioas_id via @pt_id to associate the new HWPT_PAGING to + the corresponding IOAS object. The benefit of this manual allocation is to + allow allocation flags (defined in enum iommufd_hwpt_alloc_flags), e.g. it + allocates a nesting parent HWPT_PAGING if the IOMMU_HWPT_ALLOC_NEST_PARENT + flag is set. + +4. IOMMUFD_OBJ_HWPT_NESTED can be only manually created via the IOMMU_HWPT_ALLOC + uAPI, provided an hwpt_id or a viommu_id of a vIOMMU object encapsulating a + nesting parent HWPT_PAGING via @pt_id to associate the new HWPT_NESTED object + to the corresponding HWPT_PAGING object. The associating HWPT_PAGING object + must be a nesting parent manually allocated via the same uAPI previously with + an IOMMU_HWPT_ALLOC_NEST_PARENT flag, otherwise the allocation will fail. The + allocation will be further validated by the IOMMU driver to ensure that the + nesting parent domain and the nested domain being allocated are compatible. + Successful completion of this operation sets up linkages among IOAS, device, + and iommu_domains. Once this completes the device could do DMA via a 2-stage + translation, a.k.a nested translation. Note that multiple HWPT_NESTED objects + can be allocated by (and then associated to) the same nesting parent. .. note:: - Future IOMMUFD updates will provide an API to create and manipulate the - HW_PAGETABLE directly. + Either a manual IOMMUFD_OBJ_HWPT_PAGING or an IOMMUFD_OBJ_HWPT_NESTED is + created via the same IOMMU_HWPT_ALLOC uAPI. The difference is at the type + of the object passed in via the @pt_id field of struct iommufd_hwpt_alloc. + +5. IOMMUFD_OBJ_VIOMMU can be only manually created via the IOMMU_VIOMMU_ALLOC + uAPI, provided a dev_id (for the device's physical IOMMU to back the vIOMMU) + and an hwpt_id (to associate the vIOMMU to a nesting parent HWPT_PAGING). The + iommufd core will link the vIOMMU object to the struct iommu_device that the + struct device is behind. And an IOMMU driver can implement a viommu_alloc op + to allocate its own vIOMMU data structure embedding the core-level structure + iommufd_viommu and some driver-specific data. If necessary, the driver can + also configure its HW virtualization feature for that vIOMMU (and thus for + the VM). Successful completion of this operation sets up the linkages between + the vIOMMU object and the HWPT_PAGING, then this vIOMMU object can be used + as a nesting parent object to allocate an HWPT_NESTED object described above. + +6. IOMMUFD_OBJ_VDEVICE can be only manually created via the IOMMU_VDEVICE_ALLOC + uAPI, provided a viommu_id for an iommufd_viommu object and a dev_id for an + iommufd_device object. The vDEVICE object will be the binding between these + two parent objects. Another @virt_id will be also set via the uAPI providing + the iommufd core an index to store the vDEVICE object to a vDEVICE array per + vIOMMU. If necessary, the IOMMU driver may choose to implement a vdevce_alloc + op to init its HW for virtualization feature related to a vDEVICE. Successful + completion of this operation sets up the linkages between vIOMMU and device. A device can only bind to an iommufd due to DMA ownership claim and attach to at most one IOAS object (no support of PASID yet). @@ -120,7 +249,10 @@ User visible objects are backed by following datastructures: - iommufd_ioas for IOMMUFD_OBJ_IOAS. - iommufd_device for IOMMUFD_OBJ_DEVICE. -- iommufd_hw_pagetable for IOMMUFD_OBJ_HW_PAGETABLE. +- iommufd_hwpt_paging for IOMMUFD_OBJ_HWPT_PAGING. +- iommufd_hwpt_nested for IOMMUFD_OBJ_HWPT_NESTED. +- iommufd_viommu for IOMMUFD_OBJ_VIOMMU. +- iommufd_vdevice for IOMMUFD_OBJ_VDEVICE. Several terminologies when looking at these datastructures: diff --git a/drivers/acpi/arm64/iort.c b/drivers/acpi/arm64/iort.c index 4c745a2..1f7e4c6 100644 --- a/drivers/acpi/arm64/iort.c +++ b/drivers/acpi/arm64/iort.c @@ -1218,6 +1218,17 @@ static bool iort_pci_rc_supports_ats(struct acpi_iort_node *node) return pci_rc->ats_attribute & ACPI_IORT_ATS_SUPPORTED; } +static bool iort_pci_rc_supports_canwbs(struct acpi_iort_node *node) +{ + struct acpi_iort_memory_access *memory_access; + struct acpi_iort_root_complex *pci_rc; + + pci_rc = (struct acpi_iort_root_complex *)node->node_data; + memory_access = + (struct acpi_iort_memory_access *)&pci_rc->memory_properties; + return memory_access->memory_flags & ACPI_IORT_MF_CANWBS; +} + static int iort_iommu_xlate(struct device *dev, struct acpi_iort_node *node, u32 streamid) { @@ -1335,6 +1346,8 @@ int iort_iommu_configure_id(struct device *dev, const u32 *id_in) fwspec = dev_iommu_fwspec_get(dev); if (fwspec && iort_pci_rc_supports_ats(node)) fwspec->flags |= IOMMU_FWSPEC_PCI_RC_ATS; + if (fwspec && iort_pci_rc_supports_canwbs(node)) + fwspec->flags |= IOMMU_FWSPEC_PCI_RC_CANWBS; } else { node = iort_scan_node(ACPI_IORT_NODE_NAMED_COMPONENT, iort_match_node_callback, dev); diff --git a/drivers/iommu/Kconfig b/drivers/iommu/Kconfig index b3aa1f5..0c9bceb 100644 --- a/drivers/iommu/Kconfig +++ b/drivers/iommu/Kconfig @@ -415,6 +415,15 @@ config ARM_SMMU_V3_SVA Say Y here if your system supports SVA extensions such as PCIe PASID and PRI. +config ARM_SMMU_V3_IOMMUFD + bool "Enable IOMMUFD features for ARM SMMUv3 (EXPERIMENTAL)" + depends on IOMMUFD + help + Support for IOMMUFD features intended to support virtual machines + with accelerated virtual IOMMUs. + + Say Y here if you are doing development and testing on this feature. + config ARM_SMMU_V3_KUNIT_TEST tristate "KUnit tests for arm-smmu-v3 driver" if !KUNIT_ALL_TESTS depends on KUNIT diff --git a/drivers/iommu/arm/arm-smmu-v3/Makefile b/drivers/iommu/arm/arm-smmu-v3/Makefile index dc98c88..493a659 100644 --- a/drivers/iommu/arm/arm-smmu-v3/Makefile +++ b/drivers/iommu/arm/arm-smmu-v3/Makefile @@ -1,6 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 obj-$(CONFIG_ARM_SMMU_V3) += arm_smmu_v3.o arm_smmu_v3-y := arm-smmu-v3.o +arm_smmu_v3-$(CONFIG_ARM_SMMU_V3_IOMMUFD) += arm-smmu-v3-iommufd.o arm_smmu_v3-$(CONFIG_ARM_SMMU_V3_SVA) += arm-smmu-v3-sva.o arm_smmu_v3-$(CONFIG_TEGRA241_CMDQV) += tegra241-cmdqv.o diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-iommufd.c b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-iommufd.c new file mode 100644 index 0000000..6cc14d8 --- /dev/null +++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-iommufd.c @@ -0,0 +1,401 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (c) 2024, NVIDIA CORPORATION & AFFILIATES + */ + +#include + +#include "arm-smmu-v3.h" + +void *arm_smmu_hw_info(struct device *dev, u32 *length, u32 *type) +{ + struct arm_smmu_master *master = dev_iommu_priv_get(dev); + struct iommu_hw_info_arm_smmuv3 *info; + u32 __iomem *base_idr; + unsigned int i; + + info = kzalloc(sizeof(*info), GFP_KERNEL); + if (!info) + return ERR_PTR(-ENOMEM); + + base_idr = master->smmu->base + ARM_SMMU_IDR0; + for (i = 0; i <= 5; i++) + info->idr[i] = readl_relaxed(base_idr + i); + info->iidr = readl_relaxed(master->smmu->base + ARM_SMMU_IIDR); + info->aidr = readl_relaxed(master->smmu->base + ARM_SMMU_AIDR); + + *length = sizeof(*info); + *type = IOMMU_HW_INFO_TYPE_ARM_SMMUV3; + + return info; +} + +static void arm_smmu_make_nested_cd_table_ste( + struct arm_smmu_ste *target, struct arm_smmu_master *master, + struct arm_smmu_nested_domain *nested_domain, bool ats_enabled) +{ + arm_smmu_make_s2_domain_ste( + target, master, nested_domain->vsmmu->s2_parent, ats_enabled); + + target->data[0] = cpu_to_le64(STRTAB_STE_0_V | + FIELD_PREP(STRTAB_STE_0_CFG, + STRTAB_STE_0_CFG_NESTED)); + target->data[0] |= nested_domain->ste[0] & + ~cpu_to_le64(STRTAB_STE_0_CFG); + target->data[1] |= nested_domain->ste[1]; +} + +/* + * Create a physical STE from the virtual STE that userspace provided when it + * created the nested domain. Using the vSTE userspace can request: + * - Non-valid STE + * - Abort STE + * - Bypass STE (install the S2, no CD table) + * - CD table STE (install the S2 and the userspace CD table) + */ +static void arm_smmu_make_nested_domain_ste( + struct arm_smmu_ste *target, struct arm_smmu_master *master, + struct arm_smmu_nested_domain *nested_domain, bool ats_enabled) +{ + unsigned int cfg = + FIELD_GET(STRTAB_STE_0_CFG, le64_to_cpu(nested_domain->ste[0])); + + /* + * Userspace can request a non-valid STE through the nesting interface. + * We relay that into an abort physical STE with the intention that + * C_BAD_STE for this SID can be generated to userspace. + */ + if (!(nested_domain->ste[0] & cpu_to_le64(STRTAB_STE_0_V))) + cfg = STRTAB_STE_0_CFG_ABORT; + + switch (cfg) { + case STRTAB_STE_0_CFG_S1_TRANS: + arm_smmu_make_nested_cd_table_ste(target, master, nested_domain, + ats_enabled); + break; + case STRTAB_STE_0_CFG_BYPASS: + arm_smmu_make_s2_domain_ste(target, master, + nested_domain->vsmmu->s2_parent, + ats_enabled); + break; + case STRTAB_STE_0_CFG_ABORT: + default: + arm_smmu_make_abort_ste(target); + break; + } +} + +static int arm_smmu_attach_dev_nested(struct iommu_domain *domain, + struct device *dev) +{ + struct arm_smmu_nested_domain *nested_domain = + to_smmu_nested_domain(domain); + struct arm_smmu_master *master = dev_iommu_priv_get(dev); + struct arm_smmu_attach_state state = { + .master = master, + .old_domain = iommu_get_domain_for_dev(dev), + .ssid = IOMMU_NO_PASID, + }; + struct arm_smmu_ste ste; + int ret; + + if (nested_domain->vsmmu->smmu != master->smmu) + return -EINVAL; + if (arm_smmu_ssids_in_use(&master->cd_table)) + return -EBUSY; + + mutex_lock(&arm_smmu_asid_lock); + /* + * The VM has to control the actual ATS state at the PCI device because + * we forward the invalidations directly from the VM. If the VM doesn't + * think ATS is on it will not generate ATC flushes and the ATC will + * become incoherent. Since we can't access the actual virtual PCI ATS + * config bit here base this off the EATS value in the STE. If the EATS + * is set then the VM must generate ATC flushes. + */ + state.disable_ats = !nested_domain->enable_ats; + ret = arm_smmu_attach_prepare(&state, domain); + if (ret) { + mutex_unlock(&arm_smmu_asid_lock); + return ret; + } + + arm_smmu_make_nested_domain_ste(&ste, master, nested_domain, + state.ats_enabled); + arm_smmu_install_ste_for_dev(master, &ste); + arm_smmu_attach_commit(&state); + mutex_unlock(&arm_smmu_asid_lock); + return 0; +} + +static void arm_smmu_domain_nested_free(struct iommu_domain *domain) +{ + kfree(to_smmu_nested_domain(domain)); +} + +static const struct iommu_domain_ops arm_smmu_nested_ops = { + .attach_dev = arm_smmu_attach_dev_nested, + .free = arm_smmu_domain_nested_free, +}; + +static int arm_smmu_validate_vste(struct iommu_hwpt_arm_smmuv3 *arg, + bool *enable_ats) +{ + unsigned int eats; + unsigned int cfg; + + if (!(arg->ste[0] & cpu_to_le64(STRTAB_STE_0_V))) { + memset(arg->ste, 0, sizeof(arg->ste)); + return 0; + } + + /* EIO is reserved for invalid STE data. */ + if ((arg->ste[0] & ~STRTAB_STE_0_NESTING_ALLOWED) || + (arg->ste[1] & ~STRTAB_STE_1_NESTING_ALLOWED)) + return -EIO; + + cfg = FIELD_GET(STRTAB_STE_0_CFG, le64_to_cpu(arg->ste[0])); + if (cfg != STRTAB_STE_0_CFG_ABORT && cfg != STRTAB_STE_0_CFG_BYPASS && + cfg != STRTAB_STE_0_CFG_S1_TRANS) + return -EIO; + + /* + * Only Full ATS or ATS UR is supported + * The EATS field will be set by arm_smmu_make_nested_domain_ste() + */ + eats = FIELD_GET(STRTAB_STE_1_EATS, le64_to_cpu(arg->ste[1])); + arg->ste[1] &= ~cpu_to_le64(STRTAB_STE_1_EATS); + if (eats != STRTAB_STE_1_EATS_ABT && eats != STRTAB_STE_1_EATS_TRANS) + return -EIO; + + if (cfg == STRTAB_STE_0_CFG_S1_TRANS) + *enable_ats = (eats == STRTAB_STE_1_EATS_TRANS); + return 0; +} + +static struct iommu_domain * +arm_vsmmu_alloc_domain_nested(struct iommufd_viommu *viommu, u32 flags, + const struct iommu_user_data *user_data) +{ + struct arm_vsmmu *vsmmu = container_of(viommu, struct arm_vsmmu, core); + const u32 SUPPORTED_FLAGS = IOMMU_HWPT_FAULT_ID_VALID; + struct arm_smmu_nested_domain *nested_domain; + struct iommu_hwpt_arm_smmuv3 arg; + bool enable_ats = false; + int ret; + + /* + * Faults delivered to the nested domain are faults that originated by + * the S1 in the domain. The core code will match all PASIDs when + * delivering the fault due to user_pasid_table + */ + if (flags & ~SUPPORTED_FLAGS) + return ERR_PTR(-EOPNOTSUPP); + + ret = iommu_copy_struct_from_user(&arg, user_data, + IOMMU_HWPT_DATA_ARM_SMMUV3, ste); + if (ret) + return ERR_PTR(ret); + + ret = arm_smmu_validate_vste(&arg, &enable_ats); + if (ret) + return ERR_PTR(ret); + + nested_domain = kzalloc(sizeof(*nested_domain), GFP_KERNEL_ACCOUNT); + if (!nested_domain) + return ERR_PTR(-ENOMEM); + + nested_domain->domain.type = IOMMU_DOMAIN_NESTED; + nested_domain->domain.ops = &arm_smmu_nested_ops; + nested_domain->enable_ats = enable_ats; + nested_domain->vsmmu = vsmmu; + nested_domain->ste[0] = arg.ste[0]; + nested_domain->ste[1] = arg.ste[1] & ~cpu_to_le64(STRTAB_STE_1_EATS); + + return &nested_domain->domain; +} + +static int arm_vsmmu_vsid_to_sid(struct arm_vsmmu *vsmmu, u32 vsid, u32 *sid) +{ + struct arm_smmu_master *master; + struct device *dev; + int ret = 0; + + xa_lock(&vsmmu->core.vdevs); + dev = iommufd_viommu_find_dev(&vsmmu->core, (unsigned long)vsid); + if (!dev) { + ret = -EIO; + goto unlock; + } + master = dev_iommu_priv_get(dev); + + /* At this moment, iommufd only supports PCI device that has one SID */ + if (sid) + *sid = master->streams[0].id; +unlock: + xa_unlock(&vsmmu->core.vdevs); + return ret; +} + +/* This is basically iommu_viommu_arm_smmuv3_invalidate in u64 for conversion */ +struct arm_vsmmu_invalidation_cmd { + union { + u64 cmd[2]; + struct iommu_viommu_arm_smmuv3_invalidate ucmd; + }; +}; + +/* + * Convert, in place, the raw invalidation command into an internal format that + * can be passed to arm_smmu_cmdq_issue_cmdlist(). Internally commands are + * stored in CPU endian. + * + * Enforce the VMID or SID on the command. + */ +static int arm_vsmmu_convert_user_cmd(struct arm_vsmmu *vsmmu, + struct arm_vsmmu_invalidation_cmd *cmd) +{ + /* Commands are le64 stored in u64 */ + cmd->cmd[0] = le64_to_cpu(cmd->ucmd.cmd[0]); + cmd->cmd[1] = le64_to_cpu(cmd->ucmd.cmd[1]); + + switch (cmd->cmd[0] & CMDQ_0_OP) { + case CMDQ_OP_TLBI_NSNH_ALL: + /* Convert to NH_ALL */ + cmd->cmd[0] = CMDQ_OP_TLBI_NH_ALL | + FIELD_PREP(CMDQ_TLBI_0_VMID, vsmmu->vmid); + cmd->cmd[1] = 0; + break; + case CMDQ_OP_TLBI_NH_VA: + case CMDQ_OP_TLBI_NH_VAA: + case CMDQ_OP_TLBI_NH_ALL: + case CMDQ_OP_TLBI_NH_ASID: + cmd->cmd[0] &= ~CMDQ_TLBI_0_VMID; + cmd->cmd[0] |= FIELD_PREP(CMDQ_TLBI_0_VMID, vsmmu->vmid); + break; + case CMDQ_OP_ATC_INV: + case CMDQ_OP_CFGI_CD: + case CMDQ_OP_CFGI_CD_ALL: { + u32 sid, vsid = FIELD_GET(CMDQ_CFGI_0_SID, cmd->cmd[0]); + + if (arm_vsmmu_vsid_to_sid(vsmmu, vsid, &sid)) + return -EIO; + cmd->cmd[0] &= ~CMDQ_CFGI_0_SID; + cmd->cmd[0] |= FIELD_PREP(CMDQ_CFGI_0_SID, sid); + break; + } + default: + return -EIO; + } + return 0; +} + +static int arm_vsmmu_cache_invalidate(struct iommufd_viommu *viommu, + struct iommu_user_data_array *array) +{ + struct arm_vsmmu *vsmmu = container_of(viommu, struct arm_vsmmu, core); + struct arm_smmu_device *smmu = vsmmu->smmu; + struct arm_vsmmu_invalidation_cmd *last; + struct arm_vsmmu_invalidation_cmd *cmds; + struct arm_vsmmu_invalidation_cmd *cur; + struct arm_vsmmu_invalidation_cmd *end; + int ret; + + cmds = kcalloc(array->entry_num, sizeof(*cmds), GFP_KERNEL); + if (!cmds) + return -ENOMEM; + cur = cmds; + end = cmds + array->entry_num; + + static_assert(sizeof(*cmds) == 2 * sizeof(u64)); + ret = iommu_copy_struct_from_full_user_array( + cmds, sizeof(*cmds), array, + IOMMU_VIOMMU_INVALIDATE_DATA_ARM_SMMUV3); + if (ret) + goto out; + + last = cmds; + while (cur != end) { + ret = arm_vsmmu_convert_user_cmd(vsmmu, cur); + if (ret) + goto out; + + /* FIXME work in blocks of CMDQ_BATCH_ENTRIES and copy each block? */ + cur++; + if (cur != end && (cur - last) != CMDQ_BATCH_ENTRIES - 1) + continue; + + /* FIXME always uses the main cmdq rather than trying to group by type */ + ret = arm_smmu_cmdq_issue_cmdlist(smmu, &smmu->cmdq, last->cmd, + cur - last, true); + if (ret) { + cur--; + goto out; + } + last = cur; + } +out: + array->entry_num = cur - cmds; + kfree(cmds); + return ret; +} + +static const struct iommufd_viommu_ops arm_vsmmu_ops = { + .alloc_domain_nested = arm_vsmmu_alloc_domain_nested, + .cache_invalidate = arm_vsmmu_cache_invalidate, +}; + +struct iommufd_viommu *arm_vsmmu_alloc(struct device *dev, + struct iommu_domain *parent, + struct iommufd_ctx *ictx, + unsigned int viommu_type) +{ + struct arm_smmu_device *smmu = + iommu_get_iommu_dev(dev, struct arm_smmu_device, iommu); + struct arm_smmu_master *master = dev_iommu_priv_get(dev); + struct arm_smmu_domain *s2_parent = to_smmu_domain(parent); + struct arm_vsmmu *vsmmu; + + if (viommu_type != IOMMU_VIOMMU_TYPE_ARM_SMMUV3) + return ERR_PTR(-EOPNOTSUPP); + + if (!(smmu->features & ARM_SMMU_FEAT_NESTING)) + return ERR_PTR(-EOPNOTSUPP); + + if (s2_parent->smmu != master->smmu) + return ERR_PTR(-EINVAL); + + /* + * FORCE_SYNC is not set with FEAT_NESTING. Some study of the exact HW + * defect is needed to determine if arm_vsmmu_cache_invalidate() needs + * any change to remove this. + */ + if (WARN_ON(smmu->options & ARM_SMMU_OPT_CMDQ_FORCE_SYNC)) + return ERR_PTR(-EOPNOTSUPP); + + /* + * Must support some way to prevent the VM from bypassing the cache + * because VFIO currently does not do any cache maintenance. canwbs + * indicates the device is fully coherent and no cache maintenance is + * ever required, even for PCI No-Snoop. S2FWB means the S1 can't make + * things non-coherent using the memattr, but No-Snoop behavior is not + * effected. + */ + if (!arm_smmu_master_canwbs(master) && + !(smmu->features & ARM_SMMU_FEAT_S2FWB)) + return ERR_PTR(-EOPNOTSUPP); + + vsmmu = iommufd_viommu_alloc(ictx, struct arm_vsmmu, core, + &arm_vsmmu_ops); + if (IS_ERR(vsmmu)) + return ERR_CAST(vsmmu); + + vsmmu->smmu = smmu; + vsmmu->s2_parent = s2_parent; + /* FIXME Move VMID allocation from the S2 domain allocation to here */ + vsmmu->vmid = s2_parent->s2_cfg.vmid; + + return &vsmmu->core; +} + +MODULE_IMPORT_NS(IOMMUFD); diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c index 353fea5..10b4dbc 100644 --- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c +++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c @@ -295,6 +295,7 @@ static int arm_smmu_cmdq_build_cmd(u64 *cmd, struct arm_smmu_cmdq_ent *ent) case CMDQ_OP_TLBI_NH_ASID: cmd[0] |= FIELD_PREP(CMDQ_TLBI_0_ASID, ent->tlbi.asid); fallthrough; + case CMDQ_OP_TLBI_NH_ALL: case CMDQ_OP_TLBI_S12_VMALL: cmd[0] |= FIELD_PREP(CMDQ_TLBI_0_VMID, ent->tlbi.vmid); break; @@ -765,9 +766,9 @@ static void arm_smmu_cmdq_write_entries(struct arm_smmu_cmdq *cmdq, u64 *cmds, * insert their own list of commands then all of the commands from one * CPU will appear before any of the commands from the other CPU. */ -static int arm_smmu_cmdq_issue_cmdlist(struct arm_smmu_device *smmu, - struct arm_smmu_cmdq *cmdq, - u64 *cmds, int n, bool sync) +int arm_smmu_cmdq_issue_cmdlist(struct arm_smmu_device *smmu, + struct arm_smmu_cmdq *cmdq, u64 *cmds, int n, + bool sync) { u64 cmd_sync[CMDQ_ENT_DWORDS]; u32 prod; @@ -1045,7 +1046,8 @@ void arm_smmu_get_ste_used(const __le64 *ent, __le64 *used_bits) /* S2 translates */ if (cfg & BIT(1)) { used_bits[1] |= - cpu_to_le64(STRTAB_STE_1_EATS | STRTAB_STE_1_SHCFG); + cpu_to_le64(STRTAB_STE_1_S2FWB | STRTAB_STE_1_EATS | + STRTAB_STE_1_SHCFG); used_bits[2] |= cpu_to_le64(STRTAB_STE_2_S2VMID | STRTAB_STE_2_VTCR | STRTAB_STE_2_S2AA64 | STRTAB_STE_2_S2ENDI | @@ -1549,7 +1551,6 @@ static void arm_smmu_write_ste(struct arm_smmu_master *master, u32 sid, } } -VISIBLE_IF_KUNIT void arm_smmu_make_abort_ste(struct arm_smmu_ste *target) { memset(target, 0, sizeof(*target)); @@ -1632,7 +1633,6 @@ void arm_smmu_make_cdtable_ste(struct arm_smmu_ste *target, } EXPORT_SYMBOL_IF_KUNIT(arm_smmu_make_cdtable_ste); -VISIBLE_IF_KUNIT void arm_smmu_make_s2_domain_ste(struct arm_smmu_ste *target, struct arm_smmu_master *master, struct arm_smmu_domain *smmu_domain, @@ -1655,6 +1655,8 @@ void arm_smmu_make_s2_domain_ste(struct arm_smmu_ste *target, FIELD_PREP(STRTAB_STE_1_EATS, ats_enabled ? STRTAB_STE_1_EATS_TRANS : 0)); + if (pgtbl_cfg->quirks & IO_PGTABLE_QUIRK_ARM_S2FWB) + target->data[1] |= cpu_to_le64(STRTAB_STE_1_S2FWB); if (smmu->features & ARM_SMMU_FEAT_ATTR_TYPES_OVR) target->data[1] |= cpu_to_le64(FIELD_PREP(STRTAB_STE_1_SHCFG, STRTAB_STE_1_SHCFG_INCOMING)); @@ -2105,7 +2107,16 @@ int arm_smmu_atc_inv_domain(struct arm_smmu_domain *smmu_domain, if (!master->ats_enabled) continue; - arm_smmu_atc_inv_to_cmd(master_domain->ssid, iova, size, &cmd); + if (master_domain->nested_ats_flush) { + /* + * If a S2 used as a nesting parent is changed we have + * no option but to completely flush the ATC. + */ + arm_smmu_atc_inv_to_cmd(IOMMU_NO_PASID, 0, 0, &cmd); + } else { + arm_smmu_atc_inv_to_cmd(master_domain->ssid, iova, size, + &cmd); + } for (i = 0; i < master->num_streams; i++) { cmd.atc.sid = master->streams[i].id; @@ -2232,6 +2243,15 @@ static void arm_smmu_tlb_inv_range_domain(unsigned long iova, size_t size, } __arm_smmu_tlb_inv_range(&cmd, iova, size, granule, smmu_domain); + if (smmu_domain->nest_parent) { + /* + * When the S2 domain changes all the nested S1 ASIDs have to be + * flushed too. + */ + cmd.opcode = CMDQ_OP_TLBI_NH_ALL; + arm_smmu_cmdq_issue_cmd_with_sync(smmu_domain->smmu, &cmd); + } + /* * Unfortunately, this can't be leaf-only since we may have * zapped an entire table. @@ -2293,6 +2313,8 @@ static bool arm_smmu_capable(struct device *dev, enum iommu_cap cap) case IOMMU_CAP_CACHE_COHERENCY: /* Assume that a coherent TCU implies coherent TBUs */ return master->smmu->features & ARM_SMMU_FEAT_COHERENCY; + case IOMMU_CAP_ENFORCE_CACHE_COHERENCY: + return arm_smmu_master_canwbs(master); case IOMMU_CAP_NOEXEC: case IOMMU_CAP_DEFERRED_FLUSH: return true; @@ -2303,6 +2325,26 @@ static bool arm_smmu_capable(struct device *dev, enum iommu_cap cap) } } +static bool arm_smmu_enforce_cache_coherency(struct iommu_domain *domain) +{ + struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain); + struct arm_smmu_master_domain *master_domain; + unsigned long flags; + bool ret = true; + + spin_lock_irqsave(&smmu_domain->devices_lock, flags); + list_for_each_entry(master_domain, &smmu_domain->devices, + devices_elm) { + if (!arm_smmu_master_canwbs(master_domain->master)) { + ret = false; + break; + } + } + smmu_domain->enforce_cache_coherency = ret; + spin_unlock_irqrestore(&smmu_domain->devices_lock, flags); + return ret; +} + struct arm_smmu_domain *arm_smmu_domain_alloc(void) { struct arm_smmu_domain *smmu_domain; @@ -2442,6 +2484,9 @@ static int arm_smmu_domain_finalise(struct arm_smmu_domain *smmu_domain, pgtbl_cfg.oas = smmu->oas; fmt = ARM_64_LPAE_S2; finalise_stage_fn = arm_smmu_domain_finalise_s2; + if ((smmu->features & ARM_SMMU_FEAT_S2FWB) && + (flags & IOMMU_HWPT_ALLOC_NEST_PARENT)) + pgtbl_cfg.quirks |= IO_PGTABLE_QUIRK_ARM_S2FWB; break; default: return -EINVAL; @@ -2483,8 +2528,8 @@ arm_smmu_get_step_for_sid(struct arm_smmu_device *smmu, u32 sid) } } -static void arm_smmu_install_ste_for_dev(struct arm_smmu_master *master, - const struct arm_smmu_ste *target) +void arm_smmu_install_ste_for_dev(struct arm_smmu_master *master, + const struct arm_smmu_ste *target) { int i, j; struct arm_smmu_device *smmu = master->smmu; @@ -2595,7 +2640,7 @@ static void arm_smmu_disable_pasid(struct arm_smmu_master *master) static struct arm_smmu_master_domain * arm_smmu_find_master_domain(struct arm_smmu_domain *smmu_domain, struct arm_smmu_master *master, - ioasid_t ssid) + ioasid_t ssid, bool nested_ats_flush) { struct arm_smmu_master_domain *master_domain; @@ -2604,7 +2649,8 @@ arm_smmu_find_master_domain(struct arm_smmu_domain *smmu_domain, list_for_each_entry(master_domain, &smmu_domain->devices, devices_elm) { if (master_domain->master == master && - master_domain->ssid == ssid) + master_domain->ssid == ssid && + master_domain->nested_ats_flush == nested_ats_flush) return master_domain; } return NULL; @@ -2624,6 +2670,8 @@ to_smmu_domain_devices(struct iommu_domain *domain) if ((domain->type & __IOMMU_DOMAIN_PAGING) || domain->type == IOMMU_DOMAIN_SVA) return to_smmu_domain(domain); + if (domain->type == IOMMU_DOMAIN_NESTED) + return to_smmu_nested_domain(domain)->vsmmu->s2_parent; return NULL; } @@ -2633,13 +2681,18 @@ static void arm_smmu_remove_master_domain(struct arm_smmu_master *master, { struct arm_smmu_domain *smmu_domain = to_smmu_domain_devices(domain); struct arm_smmu_master_domain *master_domain; + bool nested_ats_flush = false; unsigned long flags; if (!smmu_domain) return; + if (domain->type == IOMMU_DOMAIN_NESTED) + nested_ats_flush = to_smmu_nested_domain(domain)->enable_ats; + spin_lock_irqsave(&smmu_domain->devices_lock, flags); - master_domain = arm_smmu_find_master_domain(smmu_domain, master, ssid); + master_domain = arm_smmu_find_master_domain(smmu_domain, master, ssid, + nested_ats_flush); if (master_domain) { list_del(&master_domain->devices_elm); kfree(master_domain); @@ -2649,16 +2702,6 @@ static void arm_smmu_remove_master_domain(struct arm_smmu_master *master, spin_unlock_irqrestore(&smmu_domain->devices_lock, flags); } -struct arm_smmu_attach_state { - /* Inputs */ - struct iommu_domain *old_domain; - struct arm_smmu_master *master; - bool cd_needs_ats; - ioasid_t ssid; - /* Resulting state */ - bool ats_enabled; -}; - /* * Start the sequence to attach a domain to a master. The sequence contains three * steps: @@ -2679,8 +2722,8 @@ struct arm_smmu_attach_state { * new_domain can be a non-paging domain. In this case ATS will not be enabled, * and invalidations won't be tracked. */ -static int arm_smmu_attach_prepare(struct arm_smmu_attach_state *state, - struct iommu_domain *new_domain) +int arm_smmu_attach_prepare(struct arm_smmu_attach_state *state, + struct iommu_domain *new_domain) { struct arm_smmu_master *master = state->master; struct arm_smmu_master_domain *master_domain; @@ -2706,7 +2749,8 @@ static int arm_smmu_attach_prepare(struct arm_smmu_attach_state *state, * enabled if we have arm_smmu_domain, those always have page * tables. */ - state->ats_enabled = arm_smmu_ats_supported(master); + state->ats_enabled = !state->disable_ats && + arm_smmu_ats_supported(master); } if (smmu_domain) { @@ -2715,6 +2759,9 @@ static int arm_smmu_attach_prepare(struct arm_smmu_attach_state *state, return -ENOMEM; master_domain->master = master; master_domain->ssid = state->ssid; + if (new_domain->type == IOMMU_DOMAIN_NESTED) + master_domain->nested_ats_flush = + to_smmu_nested_domain(new_domain)->enable_ats; /* * During prepare we want the current smmu_domain and new @@ -2731,6 +2778,14 @@ static int arm_smmu_attach_prepare(struct arm_smmu_attach_state *state, * one of them. */ spin_lock_irqsave(&smmu_domain->devices_lock, flags); + if (smmu_domain->enforce_cache_coherency && + !arm_smmu_master_canwbs(master)) { + spin_unlock_irqrestore(&smmu_domain->devices_lock, + flags); + kfree(master_domain); + return -EINVAL; + } + if (state->ats_enabled) atomic_inc(&smmu_domain->nr_ats_masters); list_add(&master_domain->devices_elm, &smmu_domain->devices); @@ -2754,7 +2809,7 @@ static int arm_smmu_attach_prepare(struct arm_smmu_attach_state *state, * completes synchronizing the PCI device's ATC and finishes manipulating the * smmu_domain->devices list. */ -static void arm_smmu_attach_commit(struct arm_smmu_attach_state *state) +void arm_smmu_attach_commit(struct arm_smmu_attach_state *state) { struct arm_smmu_master *master = state->master; @@ -3084,7 +3139,8 @@ arm_smmu_domain_alloc_user(struct device *dev, u32 flags, const struct iommu_user_data *user_data) { struct arm_smmu_master *master = dev_iommu_priv_get(dev); - const u32 PAGING_FLAGS = IOMMU_HWPT_ALLOC_DIRTY_TRACKING; + const u32 PAGING_FLAGS = IOMMU_HWPT_ALLOC_DIRTY_TRACKING | + IOMMU_HWPT_ALLOC_NEST_PARENT; struct arm_smmu_domain *smmu_domain; int ret; @@ -3097,6 +3153,15 @@ arm_smmu_domain_alloc_user(struct device *dev, u32 flags, if (IS_ERR(smmu_domain)) return ERR_CAST(smmu_domain); + if (flags & IOMMU_HWPT_ALLOC_NEST_PARENT) { + if (!(master->smmu->features & ARM_SMMU_FEAT_NESTING)) { + ret = -EOPNOTSUPP; + goto err_free; + } + smmu_domain->stage = ARM_SMMU_DOMAIN_S2; + smmu_domain->nest_parent = true; + } + smmu_domain->domain.type = IOMMU_DOMAIN_UNMANAGED; smmu_domain->domain.ops = arm_smmu_ops.default_domain_ops; ret = arm_smmu_domain_finalise(smmu_domain, master->smmu, flags); @@ -3378,21 +3443,6 @@ static struct iommu_group *arm_smmu_device_group(struct device *dev) return group; } -static int arm_smmu_enable_nesting(struct iommu_domain *domain) -{ - struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain); - int ret = 0; - - mutex_lock(&smmu_domain->init_mutex); - if (smmu_domain->smmu) - ret = -EPERM; - else - smmu_domain->stage = ARM_SMMU_DOMAIN_S2; - mutex_unlock(&smmu_domain->init_mutex); - - return ret; -} - static int arm_smmu_of_xlate(struct device *dev, const struct of_phandle_args *args) { @@ -3491,6 +3541,7 @@ static struct iommu_ops arm_smmu_ops = { .identity_domain = &arm_smmu_identity_domain, .blocked_domain = &arm_smmu_blocked_domain, .capable = arm_smmu_capable, + .hw_info = arm_smmu_hw_info, .domain_alloc_paging = arm_smmu_domain_alloc_paging, .domain_alloc_sva = arm_smmu_sva_domain_alloc, .domain_alloc_user = arm_smmu_domain_alloc_user, @@ -3504,17 +3555,19 @@ static struct iommu_ops arm_smmu_ops = { .dev_disable_feat = arm_smmu_dev_disable_feature, .page_response = arm_smmu_page_response, .def_domain_type = arm_smmu_def_domain_type, + .viommu_alloc = arm_vsmmu_alloc, + .user_pasid_table = 1, .pgsize_bitmap = -1UL, /* Restricted during device attach */ .owner = THIS_MODULE, .default_domain_ops = &(const struct iommu_domain_ops) { .attach_dev = arm_smmu_attach_dev, + .enforce_cache_coherency = arm_smmu_enforce_cache_coherency, .set_dev_pasid = arm_smmu_s1_set_dev_pasid, .map_pages = arm_smmu_map_pages, .unmap_pages = arm_smmu_unmap_pages, .flush_iotlb_all = arm_smmu_flush_iotlb_all, .iotlb_sync = arm_smmu_iotlb_sync, .iova_to_phys = arm_smmu_iova_to_phys, - .enable_nesting = arm_smmu_enable_nesting, .free = arm_smmu_domain_free_paging, } }; diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h index 1e9952c..af25f09 100644 --- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h +++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h @@ -10,6 +10,7 @@ #include #include +#include #include #include #include @@ -57,6 +58,7 @@ struct arm_smmu_device; #define IDR1_SIDSIZE GENMASK(5, 0) #define ARM_SMMU_IDR3 0xc +#define IDR3_FWB (1 << 8) #define IDR3_RIL (1 << 10) #define ARM_SMMU_IDR5 0x14 @@ -81,6 +83,8 @@ struct arm_smmu_device; #define IIDR_REVISION GENMASK(15, 12) #define IIDR_IMPLEMENTER GENMASK(11, 0) +#define ARM_SMMU_AIDR 0x1C + #define ARM_SMMU_CR0 0x20 #define CR0_ATSCHK (1 << 4) #define CR0_CMDQEN (1 << 3) @@ -241,6 +245,7 @@ static inline u32 arm_smmu_strtab_l2_idx(u32 sid) #define STRTAB_STE_0_CFG_BYPASS 4 #define STRTAB_STE_0_CFG_S1_TRANS 5 #define STRTAB_STE_0_CFG_S2_TRANS 6 +#define STRTAB_STE_0_CFG_NESTED 7 #define STRTAB_STE_0_S1FMT GENMASK_ULL(5, 4) #define STRTAB_STE_0_S1FMT_LINEAR 0 @@ -261,6 +266,7 @@ static inline u32 arm_smmu_strtab_l2_idx(u32 sid) #define STRTAB_STE_1_S1COR GENMASK_ULL(5, 4) #define STRTAB_STE_1_S1CSH GENMASK_ULL(7, 6) +#define STRTAB_STE_1_S2FWB (1UL << 25) #define STRTAB_STE_1_S1STALLD (1UL << 27) #define STRTAB_STE_1_EATS GENMASK_ULL(29, 28) @@ -292,6 +298,15 @@ static inline u32 arm_smmu_strtab_l2_idx(u32 sid) #define STRTAB_STE_3_S2TTB_MASK GENMASK_ULL(51, 4) +/* These bits can be controlled by userspace for STRTAB_STE_0_CFG_NESTED */ +#define STRTAB_STE_0_NESTING_ALLOWED \ + cpu_to_le64(STRTAB_STE_0_V | STRTAB_STE_0_CFG | STRTAB_STE_0_S1FMT | \ + STRTAB_STE_0_S1CTXPTR_MASK | STRTAB_STE_0_S1CDMAX) +#define STRTAB_STE_1_NESTING_ALLOWED \ + cpu_to_le64(STRTAB_STE_1_S1DSS | STRTAB_STE_1_S1CIR | \ + STRTAB_STE_1_S1COR | STRTAB_STE_1_S1CSH | \ + STRTAB_STE_1_S1STALLD | STRTAB_STE_1_EATS) + /* * Context descriptors. * @@ -511,8 +526,10 @@ struct arm_smmu_cmdq_ent { }; } cfgi; + #define CMDQ_OP_TLBI_NH_ALL 0x10 #define CMDQ_OP_TLBI_NH_ASID 0x11 #define CMDQ_OP_TLBI_NH_VA 0x12 + #define CMDQ_OP_TLBI_NH_VAA 0x13 #define CMDQ_OP_TLBI_EL2_ALL 0x20 #define CMDQ_OP_TLBI_EL2_ASID 0x21 #define CMDQ_OP_TLBI_EL2_VA 0x22 @@ -726,6 +743,7 @@ struct arm_smmu_device { #define ARM_SMMU_FEAT_ATTR_TYPES_OVR (1 << 20) #define ARM_SMMU_FEAT_HA (1 << 21) #define ARM_SMMU_FEAT_HD (1 << 22) +#define ARM_SMMU_FEAT_S2FWB (1 << 23) u32 features; #define ARM_SMMU_OPT_SKIP_PREFETCH (1 << 0) @@ -811,10 +829,20 @@ struct arm_smmu_domain { /* List of struct arm_smmu_master_domain */ struct list_head devices; spinlock_t devices_lock; + bool enforce_cache_coherency : 1; + bool nest_parent : 1; struct mmu_notifier mmu_notifier; }; +struct arm_smmu_nested_domain { + struct iommu_domain domain; + struct arm_vsmmu *vsmmu; + bool enable_ats : 1; + + __le64 ste[2]; +}; + /* The following are exposed for testing purposes. */ struct arm_smmu_entry_writer_ops; struct arm_smmu_entry_writer { @@ -827,21 +855,22 @@ struct arm_smmu_entry_writer_ops { void (*sync)(struct arm_smmu_entry_writer *writer); }; +void arm_smmu_make_abort_ste(struct arm_smmu_ste *target); +void arm_smmu_make_s2_domain_ste(struct arm_smmu_ste *target, + struct arm_smmu_master *master, + struct arm_smmu_domain *smmu_domain, + bool ats_enabled); + #if IS_ENABLED(CONFIG_KUNIT) void arm_smmu_get_ste_used(const __le64 *ent, __le64 *used_bits); void arm_smmu_write_entry(struct arm_smmu_entry_writer *writer, __le64 *cur, const __le64 *target); void arm_smmu_get_cd_used(const __le64 *ent, __le64 *used_bits); -void arm_smmu_make_abort_ste(struct arm_smmu_ste *target); void arm_smmu_make_bypass_ste(struct arm_smmu_device *smmu, struct arm_smmu_ste *target); void arm_smmu_make_cdtable_ste(struct arm_smmu_ste *target, struct arm_smmu_master *master, bool ats_enabled, unsigned int s1dss); -void arm_smmu_make_s2_domain_ste(struct arm_smmu_ste *target, - struct arm_smmu_master *master, - struct arm_smmu_domain *smmu_domain, - bool ats_enabled); void arm_smmu_make_sva_cd(struct arm_smmu_cd *target, struct arm_smmu_master *master, struct mm_struct *mm, u16 asid); @@ -851,6 +880,7 @@ struct arm_smmu_master_domain { struct list_head devices_elm; struct arm_smmu_master *master; ioasid_t ssid; + bool nested_ats_flush : 1; }; static inline struct arm_smmu_domain *to_smmu_domain(struct iommu_domain *dom) @@ -858,6 +888,12 @@ static inline struct arm_smmu_domain *to_smmu_domain(struct iommu_domain *dom) return container_of(dom, struct arm_smmu_domain, domain); } +static inline struct arm_smmu_nested_domain * +to_smmu_nested_domain(struct iommu_domain *dom) +{ + return container_of(dom, struct arm_smmu_nested_domain, domain); +} + extern struct xarray arm_smmu_asid_xa; extern struct mutex arm_smmu_asid_lock; @@ -893,6 +929,33 @@ int arm_smmu_init_one_queue(struct arm_smmu_device *smmu, int arm_smmu_cmdq_init(struct arm_smmu_device *smmu, struct arm_smmu_cmdq *cmdq); +static inline bool arm_smmu_master_canwbs(struct arm_smmu_master *master) +{ + return dev_iommu_fwspec_get(master->dev)->flags & + IOMMU_FWSPEC_PCI_RC_CANWBS; +} + +struct arm_smmu_attach_state { + /* Inputs */ + struct iommu_domain *old_domain; + struct arm_smmu_master *master; + bool cd_needs_ats; + bool disable_ats; + ioasid_t ssid; + /* Resulting state */ + bool ats_enabled; +}; + +int arm_smmu_attach_prepare(struct arm_smmu_attach_state *state, + struct iommu_domain *new_domain); +void arm_smmu_attach_commit(struct arm_smmu_attach_state *state); +void arm_smmu_install_ste_for_dev(struct arm_smmu_master *master, + const struct arm_smmu_ste *target); + +int arm_smmu_cmdq_issue_cmdlist(struct arm_smmu_device *smmu, + struct arm_smmu_cmdq *cmdq, u64 *cmds, int n, + bool sync); + #ifdef CONFIG_ARM_SMMU_V3_SVA bool arm_smmu_sva_supported(struct arm_smmu_device *smmu); bool arm_smmu_master_sva_supported(struct arm_smmu_master *master); @@ -949,4 +1012,23 @@ tegra241_cmdqv_probe(struct arm_smmu_device *smmu) return ERR_PTR(-ENODEV); } #endif /* CONFIG_TEGRA241_CMDQV */ + +struct arm_vsmmu { + struct iommufd_viommu core; + struct arm_smmu_device *smmu; + struct arm_smmu_domain *s2_parent; + u16 vmid; +}; + +#if IS_ENABLED(CONFIG_ARM_SMMU_V3_IOMMUFD) +void *arm_smmu_hw_info(struct device *dev, u32 *length, u32 *type); +struct iommufd_viommu *arm_vsmmu_alloc(struct device *dev, + struct iommu_domain *parent, + struct iommufd_ctx *ictx, + unsigned int viommu_type); +#else +#define arm_smmu_hw_info NULL +#define arm_vsmmu_alloc NULL +#endif /* CONFIG_ARM_SMMU_V3_IOMMUFD */ + #endif /* _ARM_SMMU_V3_H */ diff --git a/drivers/iommu/arm/arm-smmu/arm-smmu.c b/drivers/iommu/arm/arm-smmu/arm-smmu.c index 8321962..12b173e 100644 --- a/drivers/iommu/arm/arm-smmu/arm-smmu.c +++ b/drivers/iommu/arm/arm-smmu/arm-smmu.c @@ -1558,21 +1558,6 @@ static struct iommu_group *arm_smmu_device_group(struct device *dev) return group; } -static int arm_smmu_enable_nesting(struct iommu_domain *domain) -{ - struct arm_smmu_domain *smmu_domain = to_smmu_domain(domain); - int ret = 0; - - mutex_lock(&smmu_domain->init_mutex); - if (smmu_domain->smmu) - ret = -EPERM; - else - smmu_domain->stage = ARM_SMMU_DOMAIN_NESTED; - mutex_unlock(&smmu_domain->init_mutex); - - return ret; -} - static int arm_smmu_set_pgtable_quirks(struct iommu_domain *domain, unsigned long quirks) { @@ -1656,7 +1641,6 @@ static struct iommu_ops arm_smmu_ops = { .flush_iotlb_all = arm_smmu_flush_iotlb_all, .iotlb_sync = arm_smmu_iotlb_sync, .iova_to_phys = arm_smmu_iova_to_phys, - .enable_nesting = arm_smmu_enable_nesting, .set_pgtable_quirks = arm_smmu_set_pgtable_quirks, .free = arm_smmu_domain_free, } diff --git a/drivers/iommu/io-pgtable-arm.c b/drivers/iommu/io-pgtable-arm.c index 0e67f17..74f58c6 100644 --- a/drivers/iommu/io-pgtable-arm.c +++ b/drivers/iommu/io-pgtable-arm.c @@ -106,6 +106,18 @@ #define ARM_LPAE_PTE_HAP_FAULT (((arm_lpae_iopte)0) << 6) #define ARM_LPAE_PTE_HAP_READ (((arm_lpae_iopte)1) << 6) #define ARM_LPAE_PTE_HAP_WRITE (((arm_lpae_iopte)2) << 6) +/* + * For !FWB these code to: + * 1111 = Normal outer write back cachable / Inner Write Back Cachable + * Permit S1 to override + * 0101 = Normal Non-cachable / Inner Non-cachable + * 0001 = Device / Device-nGnRE + * For S2FWB these code: + * 0110 Force Normal Write Back + * 0101 Normal* is forced Normal-NC, Device unchanged + * 0001 Force Device-nGnRE + */ +#define ARM_LPAE_PTE_MEMATTR_FWB_WB (((arm_lpae_iopte)0x6) << 2) #define ARM_LPAE_PTE_MEMATTR_OIWB (((arm_lpae_iopte)0xf) << 2) #define ARM_LPAE_PTE_MEMATTR_NC (((arm_lpae_iopte)0x5) << 2) #define ARM_LPAE_PTE_MEMATTR_DEV (((arm_lpae_iopte)0x1) << 2) @@ -458,12 +470,16 @@ static arm_lpae_iopte arm_lpae_prot_to_pte(struct arm_lpae_io_pgtable *data, */ if (data->iop.fmt == ARM_64_LPAE_S2 || data->iop.fmt == ARM_32_LPAE_S2) { - if (prot & IOMMU_MMIO) + if (prot & IOMMU_MMIO) { pte |= ARM_LPAE_PTE_MEMATTR_DEV; - else if (prot & IOMMU_CACHE) - pte |= ARM_LPAE_PTE_MEMATTR_OIWB; - else + } else if (prot & IOMMU_CACHE) { + if (data->iop.cfg.quirks & IO_PGTABLE_QUIRK_ARM_S2FWB) + pte |= ARM_LPAE_PTE_MEMATTR_FWB_WB; + else + pte |= ARM_LPAE_PTE_MEMATTR_OIWB; + } else { pte |= ARM_LPAE_PTE_MEMATTR_NC; + } } else { if (prot & IOMMU_MMIO) pte |= (ARM_LPAE_MAIR_ATTR_IDX_DEV @@ -1035,8 +1051,7 @@ arm_64_lpae_alloc_pgtable_s2(struct io_pgtable_cfg *cfg, void *cookie) struct arm_lpae_io_pgtable *data; typeof(&cfg->arm_lpae_s2_cfg.vtcr) vtcr = &cfg->arm_lpae_s2_cfg.vtcr; - /* The NS quirk doesn't apply at stage 2 */ - if (cfg->quirks) + if (cfg->quirks & ~(IO_PGTABLE_QUIRK_ARM_S2FWB)) return NULL; data = arm_lpae_alloc_pgtable(cfg); diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c index 83c8e61..dbd70d5 100644 --- a/drivers/iommu/iommu.c +++ b/drivers/iommu/iommu.c @@ -2723,16 +2723,6 @@ static int __init iommu_init(void) } core_initcall(iommu_init); -int iommu_enable_nesting(struct iommu_domain *domain) -{ - if (domain->type != IOMMU_DOMAIN_UNMANAGED) - return -EINVAL; - if (!domain->ops->enable_nesting) - return -EINVAL; - return domain->ops->enable_nesting(domain); -} -EXPORT_SYMBOL_GPL(iommu_enable_nesting); - int iommu_set_pgtable_quirks(struct iommu_domain *domain, unsigned long quirk) { diff --git a/drivers/iommu/iommufd/Kconfig b/drivers/iommu/iommufd/Kconfig index 76656fe..0a07f94 100644 --- a/drivers/iommu/iommufd/Kconfig +++ b/drivers/iommu/iommufd/Kconfig @@ -1,4 +1,8 @@ # SPDX-License-Identifier: GPL-2.0-only +config IOMMUFD_DRIVER_CORE + tristate + default (IOMMUFD_DRIVER || IOMMUFD) if IOMMUFD!=n + config IOMMUFD tristate "IOMMU Userspace API" select INTERVAL_TREE diff --git a/drivers/iommu/iommufd/Makefile b/drivers/iommu/iommufd/Makefile index cf46059..cb784da 100644 --- a/drivers/iommu/iommufd/Makefile +++ b/drivers/iommu/iommufd/Makefile @@ -7,9 +7,13 @@ iommufd-y := \ ioas.o \ main.o \ pages.o \ - vfio_compat.o + vfio_compat.o \ + viommu.o iommufd-$(CONFIG_IOMMUFD_TEST) += selftest.o obj-$(CONFIG_IOMMUFD) += iommufd.o obj-$(CONFIG_IOMMUFD_DRIVER) += iova_bitmap.o + +iommufd_driver-y := driver.o +obj-$(CONFIG_IOMMUFD_DRIVER_CORE) += iommufd_driver.o diff --git a/drivers/iommu/iommufd/driver.c b/drivers/iommu/iommufd/driver.c new file mode 100644 index 0000000..7b67fdf --- /dev/null +++ b/drivers/iommu/iommufd/driver.c @@ -0,0 +1,53 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Copyright (c) 2024, NVIDIA CORPORATION & AFFILIATES + */ +#include "iommufd_private.h" + +struct iommufd_object *_iommufd_object_alloc(struct iommufd_ctx *ictx, + size_t size, + enum iommufd_object_type type) +{ + struct iommufd_object *obj; + int rc; + + obj = kzalloc(size, GFP_KERNEL_ACCOUNT); + if (!obj) + return ERR_PTR(-ENOMEM); + obj->type = type; + /* Starts out bias'd by 1 until it is removed from the xarray */ + refcount_set(&obj->shortterm_users, 1); + refcount_set(&obj->users, 1); + + /* + * Reserve an ID in the xarray but do not publish the pointer yet since + * the caller hasn't initialized it yet. Once the pointer is published + * in the xarray and visible to other threads we can't reliably destroy + * it anymore, so the caller must complete all errorable operations + * before calling iommufd_object_finalize(). + */ + rc = xa_alloc(&ictx->objects, &obj->id, XA_ZERO_ENTRY, xa_limit_31b, + GFP_KERNEL_ACCOUNT); + if (rc) + goto out_free; + return obj; +out_free: + kfree(obj); + return ERR_PTR(rc); +} +EXPORT_SYMBOL_NS_GPL(_iommufd_object_alloc, IOMMUFD); + +/* Caller should xa_lock(&viommu->vdevs) to protect the return value */ +struct device *iommufd_viommu_find_dev(struct iommufd_viommu *viommu, + unsigned long vdev_id) +{ + struct iommufd_vdevice *vdev; + + lockdep_assert_held(&viommu->vdevs.xa_lock); + + vdev = xa_load(&viommu->vdevs, vdev_id); + return vdev ? vdev->dev : NULL; +} +EXPORT_SYMBOL_NS_GPL(iommufd_viommu_find_dev, IOMMUFD); + +MODULE_DESCRIPTION("iommufd code shared with builtin modules"); +MODULE_LICENSE("GPL"); diff --git a/drivers/iommu/iommufd/fault.c b/drivers/iommu/iommufd/fault.c index e590973..053b0e3 100644 --- a/drivers/iommu/iommufd/fault.c +++ b/drivers/iommu/iommufd/fault.c @@ -10,6 +10,7 @@ #include #include #include +#include #include #include @@ -27,8 +28,12 @@ static int iommufd_fault_iopf_enable(struct iommufd_device *idev) * resource between PF and VFs. There is no coordination for this * shared capability. This waits for a vPRI reset to recover. */ - if (dev_is_pci(dev) && to_pci_dev(dev)->is_virtfn) - return -EINVAL; + if (dev_is_pci(dev)) { + struct pci_dev *pdev = to_pci_dev(dev); + + if (pdev->is_virtfn && pci_pri_supported(pdev)) + return -EINVAL; + } mutex_lock(&idev->iopf_lock); /* Device iopf has already been on. */ diff --git a/drivers/iommu/iommufd/hw_pagetable.c b/drivers/iommu/iommufd/hw_pagetable.c index d06bf6e..7020576 100644 --- a/drivers/iommu/iommufd/hw_pagetable.c +++ b/drivers/iommu/iommufd/hw_pagetable.c @@ -57,7 +57,10 @@ void iommufd_hwpt_nested_destroy(struct iommufd_object *obj) container_of(obj, struct iommufd_hwpt_nested, common.obj); __iommufd_hwpt_destroy(&hwpt_nested->common); - refcount_dec(&hwpt_nested->parent->common.obj.users); + if (hwpt_nested->viommu) + refcount_dec(&hwpt_nested->viommu->obj.users); + else + refcount_dec(&hwpt_nested->parent->common.obj.users); } void iommufd_hwpt_nested_abort(struct iommufd_object *obj) @@ -248,8 +251,7 @@ iommufd_hwpt_nested_alloc(struct iommufd_ctx *ictx, } hwpt->domain->owner = ops; - if (WARN_ON_ONCE(hwpt->domain->type != IOMMU_DOMAIN_NESTED || - !hwpt->domain->ops->cache_invalidate_user)) { + if (WARN_ON_ONCE(hwpt->domain->type != IOMMU_DOMAIN_NESTED)) { rc = -EINVAL; goto out_abort; } @@ -260,6 +262,58 @@ out_abort: return ERR_PTR(rc); } +/** + * iommufd_viommu_alloc_hwpt_nested() - Get a hwpt_nested for a vIOMMU + * @viommu: vIOMMU ojbect to associate the hwpt_nested/domain with + * @flags: Flags from userspace + * @user_data: user_data pointer. Must be valid + * + * Allocate a new IOMMU_DOMAIN_NESTED for a vIOMMU and return it as a NESTED + * hw_pagetable. + */ +static struct iommufd_hwpt_nested * +iommufd_viommu_alloc_hwpt_nested(struct iommufd_viommu *viommu, u32 flags, + const struct iommu_user_data *user_data) +{ + struct iommufd_hwpt_nested *hwpt_nested; + struct iommufd_hw_pagetable *hwpt; + int rc; + + if (!user_data->len) + return ERR_PTR(-EOPNOTSUPP); + if (!viommu->ops || !viommu->ops->alloc_domain_nested) + return ERR_PTR(-EOPNOTSUPP); + + hwpt_nested = __iommufd_object_alloc( + viommu->ictx, hwpt_nested, IOMMUFD_OBJ_HWPT_NESTED, common.obj); + if (IS_ERR(hwpt_nested)) + return ERR_CAST(hwpt_nested); + hwpt = &hwpt_nested->common; + + hwpt_nested->viommu = viommu; + refcount_inc(&viommu->obj.users); + hwpt_nested->parent = viommu->hwpt; + + hwpt->domain = + viommu->ops->alloc_domain_nested(viommu, flags, user_data); + if (IS_ERR(hwpt->domain)) { + rc = PTR_ERR(hwpt->domain); + hwpt->domain = NULL; + goto out_abort; + } + hwpt->domain->owner = viommu->iommu_dev->ops; + + if (WARN_ON_ONCE(hwpt->domain->type != IOMMU_DOMAIN_NESTED)) { + rc = -EINVAL; + goto out_abort; + } + return hwpt_nested; + +out_abort: + iommufd_object_abort_and_destroy(viommu->ictx, &hwpt->obj); + return ERR_PTR(rc); +} + int iommufd_hwpt_alloc(struct iommufd_ucmd *ucmd) { struct iommu_hwpt_alloc *cmd = ucmd->cmd; @@ -316,6 +370,22 @@ int iommufd_hwpt_alloc(struct iommufd_ucmd *ucmd) goto out_unlock; } hwpt = &hwpt_nested->common; + } else if (pt_obj->type == IOMMUFD_OBJ_VIOMMU) { + struct iommufd_hwpt_nested *hwpt_nested; + struct iommufd_viommu *viommu; + + viommu = container_of(pt_obj, struct iommufd_viommu, obj); + if (viommu->iommu_dev != __iommu_get_iommu_dev(idev->dev)) { + rc = -EINVAL; + goto out_unlock; + } + hwpt_nested = iommufd_viommu_alloc_hwpt_nested( + viommu, cmd->flags, &user_data); + if (IS_ERR(hwpt_nested)) { + rc = PTR_ERR(hwpt_nested); + goto out_unlock; + } + hwpt = &hwpt_nested->common; } else { rc = -EINVAL; goto out_put_pt; @@ -412,7 +482,7 @@ int iommufd_hwpt_invalidate(struct iommufd_ucmd *ucmd) .entry_len = cmd->entry_len, .entry_num = cmd->entry_num, }; - struct iommufd_hw_pagetable *hwpt; + struct iommufd_object *pt_obj; u32 done_num = 0; int rc; @@ -426,17 +496,40 @@ int iommufd_hwpt_invalidate(struct iommufd_ucmd *ucmd) goto out; } - hwpt = iommufd_get_hwpt_nested(ucmd, cmd->hwpt_id); - if (IS_ERR(hwpt)) { - rc = PTR_ERR(hwpt); + pt_obj = iommufd_get_object(ucmd->ictx, cmd->hwpt_id, IOMMUFD_OBJ_ANY); + if (IS_ERR(pt_obj)) { + rc = PTR_ERR(pt_obj); goto out; } + if (pt_obj->type == IOMMUFD_OBJ_HWPT_NESTED) { + struct iommufd_hw_pagetable *hwpt = + container_of(pt_obj, struct iommufd_hw_pagetable, obj); + + if (!hwpt->domain->ops || + !hwpt->domain->ops->cache_invalidate_user) { + rc = -EOPNOTSUPP; + goto out_put_pt; + } + rc = hwpt->domain->ops->cache_invalidate_user(hwpt->domain, + &data_array); + } else if (pt_obj->type == IOMMUFD_OBJ_VIOMMU) { + struct iommufd_viommu *viommu = + container_of(pt_obj, struct iommufd_viommu, obj); + + if (!viommu->ops || !viommu->ops->cache_invalidate) { + rc = -EOPNOTSUPP; + goto out_put_pt; + } + rc = viommu->ops->cache_invalidate(viommu, &data_array); + } else { + rc = -EINVAL; + goto out_put_pt; + } - rc = hwpt->domain->ops->cache_invalidate_user(hwpt->domain, - &data_array); done_num = data_array.entry_num; - iommufd_put_object(ucmd->ictx, &hwpt->obj); +out_put_pt: + iommufd_put_object(ucmd->ictx, pt_obj); out: cmd->entry_num = done_num; if (iommufd_ucmd_respond(ucmd, sizeof(*cmd))) diff --git a/drivers/iommu/iommufd/io_pagetable.c b/drivers/iommu/iommufd/io_pagetable.c index 4bf7ccd..8a790e5 100644 --- a/drivers/iommu/iommufd/io_pagetable.c +++ b/drivers/iommu/iommufd/io_pagetable.c @@ -107,9 +107,9 @@ static bool __alloc_iova_check_used(struct interval_tree_span_iter *span, * Does not return a 0 IOVA even if it is valid. */ static int iopt_alloc_iova(struct io_pagetable *iopt, unsigned long *iova, - unsigned long uptr, unsigned long length) + unsigned long addr, unsigned long length) { - unsigned long page_offset = uptr % PAGE_SIZE; + unsigned long page_offset = addr % PAGE_SIZE; struct interval_tree_double_span_iter used_span; struct interval_tree_span_iter allowed_span; unsigned long max_alignment = PAGE_SIZE; @@ -122,15 +122,15 @@ static int iopt_alloc_iova(struct io_pagetable *iopt, unsigned long *iova, return -EOVERFLOW; /* - * Keep alignment present in the uptr when building the IOVA, this + * Keep alignment present in addr when building the IOVA, which * increases the chance we can map a THP. */ - if (!uptr) + if (!addr) iova_alignment = roundup_pow_of_two(length); else iova_alignment = min_t(unsigned long, roundup_pow_of_two(length), - 1UL << __ffs64(uptr)); + 1UL << __ffs64(addr)); #ifdef CONFIG_TRANSPARENT_HUGEPAGE max_alignment = HPAGE_SIZE; @@ -248,6 +248,7 @@ static int iopt_alloc_area_pages(struct io_pagetable *iopt, int iommu_prot, unsigned int flags) { struct iopt_pages_list *elm; + unsigned long start; unsigned long iova; int rc = 0; @@ -267,9 +268,15 @@ static int iopt_alloc_area_pages(struct io_pagetable *iopt, /* Use the first entry to guess the ideal IOVA alignment */ elm = list_first_entry(pages_list, struct iopt_pages_list, next); - rc = iopt_alloc_iova( - iopt, dst_iova, - (uintptr_t)elm->pages->uptr + elm->start_byte, length); + switch (elm->pages->type) { + case IOPT_ADDRESS_USER: + start = elm->start_byte + (uintptr_t)elm->pages->uptr; + break; + case IOPT_ADDRESS_FILE: + start = elm->start_byte + elm->pages->start; + break; + } + rc = iopt_alloc_iova(iopt, dst_iova, start, length); if (rc) goto out_unlock; if (IS_ENABLED(CONFIG_IOMMUFD_TEST) && @@ -384,6 +391,34 @@ out_unlock_domains: return rc; } +static int iopt_map_common(struct iommufd_ctx *ictx, struct io_pagetable *iopt, + struct iopt_pages *pages, unsigned long *iova, + unsigned long length, unsigned long start_byte, + int iommu_prot, unsigned int flags) +{ + struct iopt_pages_list elm = {}; + LIST_HEAD(pages_list); + int rc; + + elm.pages = pages; + elm.start_byte = start_byte; + if (ictx->account_mode == IOPT_PAGES_ACCOUNT_MM && + elm.pages->account_mode == IOPT_PAGES_ACCOUNT_USER) + elm.pages->account_mode = IOPT_PAGES_ACCOUNT_MM; + elm.length = length; + list_add(&elm.next, &pages_list); + + rc = iopt_map_pages(iopt, &pages_list, length, iova, iommu_prot, flags); + if (rc) { + if (elm.area) + iopt_abort_area(elm.area); + if (elm.pages) + iopt_put_pages(elm.pages); + return rc; + } + return 0; +} + /** * iopt_map_user_pages() - Map a user VA to an iova in the io page table * @ictx: iommufd_ctx the iopt is part of @@ -408,29 +443,41 @@ int iopt_map_user_pages(struct iommufd_ctx *ictx, struct io_pagetable *iopt, unsigned long length, int iommu_prot, unsigned int flags) { - struct iopt_pages_list elm = {}; - LIST_HEAD(pages_list); - int rc; + struct iopt_pages *pages; - elm.pages = iopt_alloc_pages(uptr, length, iommu_prot & IOMMU_WRITE); - if (IS_ERR(elm.pages)) - return PTR_ERR(elm.pages); - if (ictx->account_mode == IOPT_PAGES_ACCOUNT_MM && - elm.pages->account_mode == IOPT_PAGES_ACCOUNT_USER) - elm.pages->account_mode = IOPT_PAGES_ACCOUNT_MM; - elm.start_byte = uptr - elm.pages->uptr; - elm.length = length; - list_add(&elm.next, &pages_list); + pages = iopt_alloc_user_pages(uptr, length, iommu_prot & IOMMU_WRITE); + if (IS_ERR(pages)) + return PTR_ERR(pages); - rc = iopt_map_pages(iopt, &pages_list, length, iova, iommu_prot, flags); - if (rc) { - if (elm.area) - iopt_abort_area(elm.area); - if (elm.pages) - iopt_put_pages(elm.pages); - return rc; - } - return 0; + return iopt_map_common(ictx, iopt, pages, iova, length, + uptr - pages->uptr, iommu_prot, flags); +} + +/** + * iopt_map_file_pages() - Like iopt_map_user_pages, but map a file. + * @ictx: iommufd_ctx the iopt is part of + * @iopt: io_pagetable to act on + * @iova: If IOPT_ALLOC_IOVA is set this is unused on input and contains + * the chosen iova on output. Otherwise is the iova to map to on input + * @file: file to map + * @start: map file starting at this byte offset + * @length: Number of bytes to map + * @iommu_prot: Combination of IOMMU_READ/WRITE/etc bits for the mapping + * @flags: IOPT_ALLOC_IOVA or zero + */ +int iopt_map_file_pages(struct iommufd_ctx *ictx, struct io_pagetable *iopt, + unsigned long *iova, struct file *file, + unsigned long start, unsigned long length, + int iommu_prot, unsigned int flags) +{ + struct iopt_pages *pages; + + pages = iopt_alloc_file_pages(file, start, length, + iommu_prot & IOMMU_WRITE); + if (IS_ERR(pages)) + return PTR_ERR(pages); + return iopt_map_common(ictx, iopt, pages, iova, length, + start - pages->start, iommu_prot, flags); } struct iova_bitmap_fn_arg { diff --git a/drivers/iommu/iommufd/io_pagetable.h b/drivers/iommu/iommufd/io_pagetable.h index c61d744..10c928a 100644 --- a/drivers/iommu/iommufd/io_pagetable.h +++ b/drivers/iommu/iommufd/io_pagetable.h @@ -173,6 +173,12 @@ enum { IOPT_PAGES_ACCOUNT_NONE = 0, IOPT_PAGES_ACCOUNT_USER = 1, IOPT_PAGES_ACCOUNT_MM = 2, + IOPT_PAGES_ACCOUNT_MODE_NUM = 3, +}; + +enum iopt_address_type { + IOPT_ADDRESS_USER = 0, + IOPT_ADDRESS_FILE = 1, }; /* @@ -195,7 +201,14 @@ struct iopt_pages { struct task_struct *source_task; struct mm_struct *source_mm; struct user_struct *source_user; - void __user *uptr; + enum iopt_address_type type; + union { + void __user *uptr; /* IOPT_ADDRESS_USER */ + struct { /* IOPT_ADDRESS_FILE */ + struct file *file; + unsigned long start; + }; + }; bool writable:1; u8 account_mode; @@ -206,8 +219,10 @@ struct iopt_pages { struct rb_root_cached domains_itree; }; -struct iopt_pages *iopt_alloc_pages(void __user *uptr, unsigned long length, - bool writable); +struct iopt_pages *iopt_alloc_user_pages(void __user *uptr, + unsigned long length, bool writable); +struct iopt_pages *iopt_alloc_file_pages(struct file *file, unsigned long start, + unsigned long length, bool writable); void iopt_release_pages(struct kref *kref); static inline void iopt_put_pages(struct iopt_pages *pages) { @@ -238,4 +253,9 @@ struct iopt_pages_access { unsigned int users; }; +struct pfn_reader_user; + +int iopt_pages_update_pinned(struct iopt_pages *pages, unsigned long npages, + bool inc, struct pfn_reader_user *user); + #endif diff --git a/drivers/iommu/iommufd/ioas.c b/drivers/iommu/iommufd/ioas.c index 2c4b2bb..1542c5f 100644 --- a/drivers/iommu/iommufd/ioas.c +++ b/drivers/iommu/iommufd/ioas.c @@ -2,6 +2,7 @@ /* * Copyright (c) 2021-2022, NVIDIA CORPORATION & AFFILIATES */ +#include #include #include #include @@ -51,7 +52,10 @@ int iommufd_ioas_alloc_ioctl(struct iommufd_ucmd *ucmd) rc = iommufd_ucmd_respond(ucmd, sizeof(*cmd)); if (rc) goto out_table; + + down_read(&ucmd->ictx->ioas_creation_lock); iommufd_object_finalize(ucmd->ictx, &ioas->obj); + up_read(&ucmd->ictx->ioas_creation_lock); return 0; out_table: @@ -197,6 +201,52 @@ static int conv_iommu_prot(u32 map_flags) return iommu_prot; } +int iommufd_ioas_map_file(struct iommufd_ucmd *ucmd) +{ + struct iommu_ioas_map_file *cmd = ucmd->cmd; + unsigned long iova = cmd->iova; + struct iommufd_ioas *ioas; + unsigned int flags = 0; + struct file *file; + int rc; + + if (cmd->flags & + ~(IOMMU_IOAS_MAP_FIXED_IOVA | IOMMU_IOAS_MAP_WRITEABLE | + IOMMU_IOAS_MAP_READABLE)) + return -EOPNOTSUPP; + + if (cmd->iova >= ULONG_MAX || cmd->length >= ULONG_MAX) + return -EOVERFLOW; + + if (!(cmd->flags & + (IOMMU_IOAS_MAP_WRITEABLE | IOMMU_IOAS_MAP_READABLE))) + return -EINVAL; + + ioas = iommufd_get_ioas(ucmd->ictx, cmd->ioas_id); + if (IS_ERR(ioas)) + return PTR_ERR(ioas); + + if (!(cmd->flags & IOMMU_IOAS_MAP_FIXED_IOVA)) + flags = IOPT_ALLOC_IOVA; + + file = fget(cmd->fd); + if (!file) + return -EBADF; + + rc = iopt_map_file_pages(ucmd->ictx, &ioas->iopt, &iova, file, + cmd->start, cmd->length, + conv_iommu_prot(cmd->flags), flags); + if (rc) + goto out_put; + + cmd->iova = iova; + rc = iommufd_ucmd_respond(ucmd, sizeof(*cmd)); +out_put: + iommufd_put_object(ucmd->ictx, &ioas->obj); + fput(file); + return rc; +} + int iommufd_ioas_map(struct iommufd_ucmd *ucmd) { struct iommu_ioas_map *cmd = ucmd->cmd; @@ -327,6 +377,215 @@ out_put: return rc; } +static void iommufd_release_all_iova_rwsem(struct iommufd_ctx *ictx, + struct xarray *ioas_list) +{ + struct iommufd_ioas *ioas; + unsigned long index; + + xa_for_each(ioas_list, index, ioas) { + up_write(&ioas->iopt.iova_rwsem); + refcount_dec(&ioas->obj.users); + } + up_write(&ictx->ioas_creation_lock); + xa_destroy(ioas_list); +} + +static int iommufd_take_all_iova_rwsem(struct iommufd_ctx *ictx, + struct xarray *ioas_list) +{ + struct iommufd_object *obj; + unsigned long index; + int rc; + + /* + * This is very ugly, it is done instead of adding a lock around + * pages->source_mm, which is a performance path for mdev, we just + * obtain the write side of all the iova_rwsems which also protects the + * pages->source_*. Due to copies we can't know which IOAS could read + * from the pages, so we just lock everything. This is the only place + * locks are nested and they are uniformly taken in ID order. + * + * ioas_creation_lock prevents new IOAS from being installed in the + * xarray while we do this, and also prevents more than one thread from + * holding nested locks. + */ + down_write(&ictx->ioas_creation_lock); + xa_lock(&ictx->objects); + xa_for_each(&ictx->objects, index, obj) { + struct iommufd_ioas *ioas; + + if (!obj || obj->type != IOMMUFD_OBJ_IOAS) + continue; + + if (!refcount_inc_not_zero(&obj->users)) + continue; + + xa_unlock(&ictx->objects); + + ioas = container_of(obj, struct iommufd_ioas, obj); + down_write_nest_lock(&ioas->iopt.iova_rwsem, + &ictx->ioas_creation_lock); + + rc = xa_err(xa_store(ioas_list, index, ioas, GFP_KERNEL)); + if (rc) { + iommufd_release_all_iova_rwsem(ictx, ioas_list); + return rc; + } + + xa_lock(&ictx->objects); + } + xa_unlock(&ictx->objects); + return 0; +} + +static bool need_charge_update(struct iopt_pages *pages) +{ + switch (pages->account_mode) { + case IOPT_PAGES_ACCOUNT_NONE: + return false; + case IOPT_PAGES_ACCOUNT_MM: + return pages->source_mm != current->mm; + case IOPT_PAGES_ACCOUNT_USER: + /* + * Update when mm changes because it also accounts + * in mm->pinned_vm. + */ + return (pages->source_user != current_user()) || + (pages->source_mm != current->mm); + } + return true; +} + +static int charge_current(unsigned long *npinned) +{ + struct iopt_pages tmp = { + .source_mm = current->mm, + .source_task = current->group_leader, + .source_user = current_user(), + }; + unsigned int account_mode; + int rc; + + for (account_mode = 0; account_mode != IOPT_PAGES_ACCOUNT_MODE_NUM; + account_mode++) { + if (!npinned[account_mode]) + continue; + + tmp.account_mode = account_mode; + rc = iopt_pages_update_pinned(&tmp, npinned[account_mode], true, + NULL); + if (rc) + goto err_undo; + } + return 0; + +err_undo: + while (account_mode != 0) { + account_mode--; + if (!npinned[account_mode]) + continue; + tmp.account_mode = account_mode; + iopt_pages_update_pinned(&tmp, npinned[account_mode], false, + NULL); + } + return rc; +} + +static void change_mm(struct iopt_pages *pages) +{ + struct task_struct *old_task = pages->source_task; + struct user_struct *old_user = pages->source_user; + struct mm_struct *old_mm = pages->source_mm; + + pages->source_mm = current->mm; + mmgrab(pages->source_mm); + mmdrop(old_mm); + + pages->source_task = current->group_leader; + get_task_struct(pages->source_task); + put_task_struct(old_task); + + pages->source_user = get_uid(current_user()); + free_uid(old_user); +} + +#define for_each_ioas_area(_xa, _index, _ioas, _area) \ + xa_for_each((_xa), (_index), (_ioas)) \ + for (_area = iopt_area_iter_first(&_ioas->iopt, 0, ULONG_MAX); \ + _area; \ + _area = iopt_area_iter_next(_area, 0, ULONG_MAX)) + +int iommufd_ioas_change_process(struct iommufd_ucmd *ucmd) +{ + struct iommu_ioas_change_process *cmd = ucmd->cmd; + struct iommufd_ctx *ictx = ucmd->ictx; + unsigned long all_npinned[IOPT_PAGES_ACCOUNT_MODE_NUM] = {}; + struct iommufd_ioas *ioas; + struct iopt_area *area; + struct iopt_pages *pages; + struct xarray ioas_list; + unsigned long index; + int rc; + + if (cmd->__reserved) + return -EOPNOTSUPP; + + xa_init(&ioas_list); + rc = iommufd_take_all_iova_rwsem(ictx, &ioas_list); + if (rc) + return rc; + + for_each_ioas_area(&ioas_list, index, ioas, area) { + if (area->pages->type != IOPT_ADDRESS_FILE) { + rc = -EINVAL; + goto out; + } + } + + /* + * Count last_pinned pages, then clear it to avoid double counting + * if the same iopt_pages is visited multiple times in this loop. + * Since we are under all the locks, npinned == last_npinned, so we + * can easily restore last_npinned before we return. + */ + for_each_ioas_area(&ioas_list, index, ioas, area) { + pages = area->pages; + + if (need_charge_update(pages)) { + all_npinned[pages->account_mode] += pages->last_npinned; + pages->last_npinned = 0; + } + } + + rc = charge_current(all_npinned); + + if (rc) { + /* Charge failed. Fix last_npinned and bail. */ + for_each_ioas_area(&ioas_list, index, ioas, area) + area->pages->last_npinned = area->pages->npinned; + goto out; + } + + for_each_ioas_area(&ioas_list, index, ioas, area) { + pages = area->pages; + + /* Uncharge the old one (which also restores last_npinned) */ + if (need_charge_update(pages)) { + int r = iopt_pages_update_pinned(pages, pages->npinned, + false, NULL); + + if (WARN_ON(r)) + rc = r; + } + change_mm(pages); + } + +out: + iommufd_release_all_iova_rwsem(ictx, &ioas_list); + return rc; +} + int iommufd_option_rlimit_mode(struct iommu_option *cmd, struct iommufd_ctx *ictx) { diff --git a/drivers/iommu/iommufd/iommufd_private.h b/drivers/iommu/iommufd/iommufd_private.h index f1d865e..b6d706c 100644 --- a/drivers/iommu/iommufd/iommufd_private.h +++ b/drivers/iommu/iommufd/iommufd_private.h @@ -5,8 +5,8 @@ #define __IOMMUFD_PRIVATE_H #include +#include #include -#include #include #include #include @@ -24,6 +24,7 @@ struct iommufd_ctx { struct xarray objects; struct xarray groups; wait_queue_head_t destroy_wait; + struct rw_semaphore ioas_creation_lock; u8 account_mode; /* Compatibility with VFIO no iommu */ @@ -69,6 +70,10 @@ int iopt_map_user_pages(struct iommufd_ctx *ictx, struct io_pagetable *iopt, unsigned long *iova, void __user *uptr, unsigned long length, int iommu_prot, unsigned int flags); +int iopt_map_file_pages(struct iommufd_ctx *ictx, struct io_pagetable *iopt, + unsigned long *iova, struct file *file, + unsigned long start, unsigned long length, + int iommu_prot, unsigned int flags); int iopt_map_pages(struct io_pagetable *iopt, struct list_head *pages_list, unsigned long length, unsigned long *dst_iova, int iommu_prot, unsigned int flags); @@ -122,29 +127,6 @@ static inline int iommufd_ucmd_respond(struct iommufd_ucmd *ucmd, return 0; } -enum iommufd_object_type { - IOMMUFD_OBJ_NONE, - IOMMUFD_OBJ_ANY = IOMMUFD_OBJ_NONE, - IOMMUFD_OBJ_DEVICE, - IOMMUFD_OBJ_HWPT_PAGING, - IOMMUFD_OBJ_HWPT_NESTED, - IOMMUFD_OBJ_IOAS, - IOMMUFD_OBJ_ACCESS, - IOMMUFD_OBJ_FAULT, -#ifdef CONFIG_IOMMUFD_TEST - IOMMUFD_OBJ_SELFTEST, -#endif - IOMMUFD_OBJ_MAX, -}; - -/* Base struct for all objects with a userspace ID handle. */ -struct iommufd_object { - refcount_t shortterm_users; - refcount_t users; - enum iommufd_object_type type; - unsigned int id; -}; - static inline bool iommufd_lock_obj(struct iommufd_object *obj) { if (!refcount_inc_not_zero(&obj->users)) @@ -225,10 +207,6 @@ iommufd_object_put_and_try_destroy(struct iommufd_ctx *ictx, iommufd_object_remove(ictx, obj, obj->id, 0); } -struct iommufd_object *_iommufd_object_alloc(struct iommufd_ctx *ictx, - size_t size, - enum iommufd_object_type type); - #define __iommufd_object_alloc(ictx, ptr, type, obj) \ container_of(_iommufd_object_alloc( \ ictx, \ @@ -276,6 +254,8 @@ void iommufd_ioas_destroy(struct iommufd_object *obj); int iommufd_ioas_iova_ranges(struct iommufd_ucmd *ucmd); int iommufd_ioas_allow_iovas(struct iommufd_ucmd *ucmd); int iommufd_ioas_map(struct iommufd_ucmd *ucmd); +int iommufd_ioas_map_file(struct iommufd_ucmd *ucmd); +int iommufd_ioas_change_process(struct iommufd_ucmd *ucmd); int iommufd_ioas_copy(struct iommufd_ucmd *ucmd); int iommufd_ioas_unmap(struct iommufd_ucmd *ucmd); int iommufd_ioas_option(struct iommufd_ucmd *ucmd); @@ -312,6 +292,7 @@ struct iommufd_hwpt_paging { struct iommufd_hwpt_nested { struct iommufd_hw_pagetable common; struct iommufd_hwpt_paging *parent; + struct iommufd_viommu *viommu; }; static inline bool hwpt_is_paging(struct iommufd_hw_pagetable *hwpt) @@ -528,6 +509,27 @@ static inline int iommufd_hwpt_replace_device(struct iommufd_device *idev, return iommu_group_replace_domain(idev->igroup->group, hwpt->domain); } +static inline struct iommufd_viommu * +iommufd_get_viommu(struct iommufd_ucmd *ucmd, u32 id) +{ + return container_of(iommufd_get_object(ucmd->ictx, id, + IOMMUFD_OBJ_VIOMMU), + struct iommufd_viommu, obj); +} + +int iommufd_viommu_alloc_ioctl(struct iommufd_ucmd *ucmd); +void iommufd_viommu_destroy(struct iommufd_object *obj); +int iommufd_vdevice_alloc_ioctl(struct iommufd_ucmd *ucmd); +void iommufd_vdevice_destroy(struct iommufd_object *obj); + +struct iommufd_vdevice { + struct iommufd_object obj; + struct iommufd_ctx *ictx; + struct iommufd_viommu *viommu; + struct device *dev; + u64 id; /* per-vIOMMU virtual ID */ +}; + #ifdef CONFIG_IOMMUFD_TEST int iommufd_test(struct iommufd_ucmd *ucmd); void iommufd_selftest_destroy(struct iommufd_object *obj); diff --git a/drivers/iommu/iommufd/iommufd_test.h b/drivers/iommu/iommufd/iommufd_test.h index f4bc23a..a6b7a16 100644 --- a/drivers/iommu/iommufd/iommufd_test.h +++ b/drivers/iommu/iommufd/iommufd_test.h @@ -23,6 +23,7 @@ enum { IOMMU_TEST_OP_DIRTY, IOMMU_TEST_OP_MD_CHECK_IOTLB, IOMMU_TEST_OP_TRIGGER_IOPF, + IOMMU_TEST_OP_DEV_CHECK_CACHE, }; enum { @@ -54,6 +55,11 @@ enum { MOCK_NESTED_DOMAIN_IOTLB_NUM = 4, }; +enum { + MOCK_DEV_CACHE_ID_MAX = 3, + MOCK_DEV_CACHE_NUM = 4, +}; + struct iommu_test_cmd { __u32 size; __u32 op; @@ -135,6 +141,10 @@ struct iommu_test_cmd { __u32 perm; __u64 addr; } trigger_iopf; + struct { + __u32 id; + __u32 cache; + } check_dev_cache; }; __u32 last; }; @@ -152,6 +162,7 @@ struct iommu_test_hw_info { /* Should not be equal to any defined value in enum iommu_hwpt_data_type */ #define IOMMU_HWPT_DATA_SELFTEST 0xdead #define IOMMU_TEST_IOTLB_DEFAULT 0xbadbeef +#define IOMMU_TEST_DEV_CACHE_DEFAULT 0xbaddad /** * struct iommu_hwpt_selftest @@ -180,4 +191,25 @@ struct iommu_hwpt_invalidate_selftest { __u32 iotlb_id; }; +#define IOMMU_VIOMMU_TYPE_SELFTEST 0xdeadbeef + +/* Should not be equal to any defined value in enum iommu_viommu_invalidate_data_type */ +#define IOMMU_VIOMMU_INVALIDATE_DATA_SELFTEST 0xdeadbeef +#define IOMMU_VIOMMU_INVALIDATE_DATA_SELFTEST_INVALID 0xdadbeef + +/** + * struct iommu_viommu_invalidate_selftest - Invalidation data for Mock VIOMMU + * (IOMMU_VIOMMU_INVALIDATE_DATA_SELFTEST) + * @flags: Invalidate flags + * @cache_id: Invalidate cache entry index + * + * If IOMMU_TEST_INVALIDATE_ALL is set in @flags, @cache_id will be ignored + */ +struct iommu_viommu_invalidate_selftest { +#define IOMMU_TEST_INVALIDATE_FLAG_ALL (1 << 0) + __u32 flags; + __u32 vdev_id; + __u32 cache_id; +}; + #endif diff --git a/drivers/iommu/iommufd/main.c b/drivers/iommu/iommufd/main.c index b5f5d27..0a96cc8 100644 --- a/drivers/iommu/iommufd/main.c +++ b/drivers/iommu/iommufd/main.c @@ -29,38 +29,6 @@ struct iommufd_object_ops { static const struct iommufd_object_ops iommufd_object_ops[]; static struct miscdevice vfio_misc_dev; -struct iommufd_object *_iommufd_object_alloc(struct iommufd_ctx *ictx, - size_t size, - enum iommufd_object_type type) -{ - struct iommufd_object *obj; - int rc; - - obj = kzalloc(size, GFP_KERNEL_ACCOUNT); - if (!obj) - return ERR_PTR(-ENOMEM); - obj->type = type; - /* Starts out bias'd by 1 until it is removed from the xarray */ - refcount_set(&obj->shortterm_users, 1); - refcount_set(&obj->users, 1); - - /* - * Reserve an ID in the xarray but do not publish the pointer yet since - * the caller hasn't initialized it yet. Once the pointer is published - * in the xarray and visible to other threads we can't reliably destroy - * it anymore, so the caller must complete all errorable operations - * before calling iommufd_object_finalize(). - */ - rc = xa_alloc(&ictx->objects, &obj->id, XA_ZERO_ENTRY, - xa_limit_31b, GFP_KERNEL_ACCOUNT); - if (rc) - goto out_free; - return obj; -out_free: - kfree(obj); - return ERR_PTR(rc); -} - /* * Allow concurrent access to the object. * @@ -73,20 +41,26 @@ out_free: void iommufd_object_finalize(struct iommufd_ctx *ictx, struct iommufd_object *obj) { + XA_STATE(xas, &ictx->objects, obj->id); void *old; - old = xa_store(&ictx->objects, obj->id, obj, GFP_KERNEL); - /* obj->id was returned from xa_alloc() so the xa_store() cannot fail */ - WARN_ON(old); + xa_lock(&ictx->objects); + old = xas_store(&xas, obj); + xa_unlock(&ictx->objects); + /* obj->id was returned from xa_alloc() so the xas_store() cannot fail */ + WARN_ON(old != XA_ZERO_ENTRY); } /* Undo _iommufd_object_alloc() if iommufd_object_finalize() was not called */ void iommufd_object_abort(struct iommufd_ctx *ictx, struct iommufd_object *obj) { + XA_STATE(xas, &ictx->objects, obj->id); void *old; - old = xa_erase(&ictx->objects, obj->id); - WARN_ON(old); + xa_lock(&ictx->objects); + old = xas_store(&xas, NULL); + xa_unlock(&ictx->objects); + WARN_ON(old != XA_ZERO_ENTRY); kfree(obj); } @@ -248,6 +222,7 @@ static int iommufd_fops_open(struct inode *inode, struct file *filp) pr_info_once("IOMMUFD is providing /dev/vfio/vfio, not VFIO.\n"); } + init_rwsem(&ictx->ioas_creation_lock); xa_init_flags(&ictx->objects, XA_FLAGS_ALLOC1 | XA_FLAGS_ACCOUNT); xa_init(&ictx->groups); ictx->file = filp; @@ -333,6 +308,8 @@ union ucmd_buffer { struct iommu_ioas_unmap unmap; struct iommu_option option; struct iommu_vfio_ioas vfio_ioas; + struct iommu_viommu_alloc viommu; + struct iommu_vdevice_alloc vdev; #ifdef CONFIG_IOMMUFD_TEST struct iommu_test_cmd test; #endif @@ -372,18 +349,26 @@ static const struct iommufd_ioctl_op iommufd_ioctl_ops[] = { struct iommu_ioas_alloc, out_ioas_id), IOCTL_OP(IOMMU_IOAS_ALLOW_IOVAS, iommufd_ioas_allow_iovas, struct iommu_ioas_allow_iovas, allowed_iovas), + IOCTL_OP(IOMMU_IOAS_CHANGE_PROCESS, iommufd_ioas_change_process, + struct iommu_ioas_change_process, __reserved), IOCTL_OP(IOMMU_IOAS_COPY, iommufd_ioas_copy, struct iommu_ioas_copy, src_iova), IOCTL_OP(IOMMU_IOAS_IOVA_RANGES, iommufd_ioas_iova_ranges, struct iommu_ioas_iova_ranges, out_iova_alignment), IOCTL_OP(IOMMU_IOAS_MAP, iommufd_ioas_map, struct iommu_ioas_map, iova), + IOCTL_OP(IOMMU_IOAS_MAP_FILE, iommufd_ioas_map_file, + struct iommu_ioas_map_file, iova), IOCTL_OP(IOMMU_IOAS_UNMAP, iommufd_ioas_unmap, struct iommu_ioas_unmap, length), IOCTL_OP(IOMMU_OPTION, iommufd_option, struct iommu_option, val64), IOCTL_OP(IOMMU_VFIO_IOAS, iommufd_vfio_ioas, struct iommu_vfio_ioas, __reserved), + IOCTL_OP(IOMMU_VIOMMU_ALLOC, iommufd_viommu_alloc_ioctl, + struct iommu_viommu_alloc, out_viommu_id), + IOCTL_OP(IOMMU_VDEVICE_ALLOC, iommufd_vdevice_alloc_ioctl, + struct iommu_vdevice_alloc, virt_id), #ifdef CONFIG_IOMMUFD_TEST IOCTL_OP(IOMMU_TEST_CMD, iommufd_test, struct iommu_test_cmd, last), #endif @@ -519,6 +504,12 @@ static const struct iommufd_object_ops iommufd_object_ops[] = { [IOMMUFD_OBJ_FAULT] = { .destroy = iommufd_fault_destroy, }, + [IOMMUFD_OBJ_VIOMMU] = { + .destroy = iommufd_viommu_destroy, + }, + [IOMMUFD_OBJ_VDEVICE] = { + .destroy = iommufd_vdevice_destroy, + }, #ifdef CONFIG_IOMMUFD_TEST [IOMMUFD_OBJ_SELFTEST] = { .destroy = iommufd_selftest_destroy, diff --git a/drivers/iommu/iommufd/pages.c b/drivers/iommu/iommufd/pages.c index 93d806c..3427749 100644 --- a/drivers/iommu/iommufd/pages.c +++ b/drivers/iommu/iommufd/pages.c @@ -45,6 +45,7 @@ * last_iova + 1 can overflow. An iopt_pages index will always be much less than * ULONG_MAX so last_index + 1 cannot overflow. */ +#include #include #include #include @@ -346,27 +347,41 @@ static void batch_destroy(struct pfn_batch *batch, void *backup) kfree(batch->pfns); } -/* true if the pfn was added, false otherwise */ -static bool batch_add_pfn(struct pfn_batch *batch, unsigned long pfn) +static bool batch_add_pfn_num(struct pfn_batch *batch, unsigned long pfn, + u32 nr) { const unsigned int MAX_NPFNS = type_max(typeof(*batch->npfns)); - - if (batch->end && - pfn == batch->pfns[batch->end - 1] + batch->npfns[batch->end - 1] && - batch->npfns[batch->end - 1] != MAX_NPFNS) { - batch->npfns[batch->end - 1]++; - batch->total_pfns++; - return true; - } - if (batch->end == batch->array_size) + unsigned int end = batch->end; + + if (end && pfn == batch->pfns[end - 1] + batch->npfns[end - 1] && + nr <= MAX_NPFNS - batch->npfns[end - 1]) { + batch->npfns[end - 1] += nr; + } else if (end < batch->array_size) { + batch->pfns[end] = pfn; + batch->npfns[end] = nr; + batch->end++; + } else { return false; - batch->total_pfns++; - batch->pfns[batch->end] = pfn; - batch->npfns[batch->end] = 1; - batch->end++; + } + + batch->total_pfns += nr; return true; } +static void batch_remove_pfn_num(struct pfn_batch *batch, unsigned long nr) +{ + batch->npfns[batch->end - 1] -= nr; + if (batch->npfns[batch->end - 1] == 0) + batch->end--; + batch->total_pfns -= nr; +} + +/* true if the pfn was added, false otherwise */ +static bool batch_add_pfn(struct pfn_batch *batch, unsigned long pfn) +{ + return batch_add_pfn_num(batch, pfn, 1); +} + /* * Fill the batch with pfns from the domain. When the batch is full, or it * reaches last_index, the function will return. The caller should use @@ -622,6 +637,41 @@ static void batch_from_pages(struct pfn_batch *batch, struct page **pages, break; } +static int batch_from_folios(struct pfn_batch *batch, struct folio ***folios_p, + unsigned long *offset_p, unsigned long npages) +{ + int rc = 0; + struct folio **folios = *folios_p; + unsigned long offset = *offset_p; + + while (npages) { + struct folio *folio = *folios; + unsigned long nr = folio_nr_pages(folio) - offset; + unsigned long pfn = page_to_pfn(folio_page(folio, offset)); + + nr = min(nr, npages); + npages -= nr; + + if (!batch_add_pfn_num(batch, pfn, nr)) + break; + if (nr > 1) { + rc = folio_add_pins(folio, nr - 1); + if (rc) { + batch_remove_pfn_num(batch, nr); + goto out; + } + } + + folios++; + offset = 0; + } + +out: + *folios_p = folios; + *offset_p = offset; + return rc; +} + static void batch_unpin(struct pfn_batch *batch, struct iopt_pages *pages, unsigned int first_page_off, size_t npages) { @@ -703,19 +753,32 @@ struct pfn_reader_user { * neither */ int locked; + + /* The following are only valid if file != NULL. */ + struct file *file; + struct folio **ufolios; + size_t ufolios_len; + unsigned long ufolios_offset; + struct folio **ufolios_next; }; static void pfn_reader_user_init(struct pfn_reader_user *user, struct iopt_pages *pages) { user->upages = NULL; + user->upages_len = 0; user->upages_start = 0; user->upages_end = 0; user->locked = -1; - user->gup_flags = FOLL_LONGTERM; if (pages->writable) user->gup_flags |= FOLL_WRITE; + + user->file = (pages->type == IOPT_ADDRESS_FILE) ? pages->file : NULL; + user->ufolios = NULL; + user->ufolios_len = 0; + user->ufolios_next = NULL; + user->ufolios_offset = 0; } static void pfn_reader_user_destroy(struct pfn_reader_user *user, @@ -724,13 +787,67 @@ static void pfn_reader_user_destroy(struct pfn_reader_user *user, if (user->locked != -1) { if (user->locked) mmap_read_unlock(pages->source_mm); - if (pages->source_mm != current->mm) + if (!user->file && pages->source_mm != current->mm) mmput(pages->source_mm); user->locked = -1; } kfree(user->upages); user->upages = NULL; + kfree(user->ufolios); + user->ufolios = NULL; +} + +static long pin_memfd_pages(struct pfn_reader_user *user, unsigned long start, + unsigned long npages) +{ + unsigned long i; + unsigned long offset; + unsigned long npages_out = 0; + struct page **upages = user->upages; + unsigned long end = start + (npages << PAGE_SHIFT) - 1; + long nfolios = user->ufolios_len / sizeof(*user->ufolios); + + /* + * todo: memfd_pin_folios should return the last pinned offset so + * we can compute npages pinned, and avoid looping over folios here + * if upages == NULL. + */ + nfolios = memfd_pin_folios(user->file, start, end, user->ufolios, + nfolios, &offset); + if (nfolios <= 0) + return nfolios; + + offset >>= PAGE_SHIFT; + user->ufolios_next = user->ufolios; + user->ufolios_offset = offset; + + for (i = 0; i < nfolios; i++) { + struct folio *folio = user->ufolios[i]; + unsigned long nr = folio_nr_pages(folio); + unsigned long npin = min(nr - offset, npages); + + npages -= npin; + npages_out += npin; + + if (upages) { + if (npin == 1) { + *upages++ = folio_page(folio, offset); + } else { + int rc = folio_add_pins(folio, npin - 1); + + if (rc) + return rc; + + while (npin--) + *upages++ = folio_page(folio, offset++); + } + } + + offset = 0; + } + + return npages_out; } static int pfn_reader_user_pin(struct pfn_reader_user *user, @@ -739,7 +856,9 @@ static int pfn_reader_user_pin(struct pfn_reader_user *user, unsigned long last_index) { bool remote_mm = pages->source_mm != current->mm; - unsigned long npages; + unsigned long npages = last_index - start_index + 1; + unsigned long start; + unsigned long unum; uintptr_t uptr; long rc; @@ -747,40 +866,50 @@ static int pfn_reader_user_pin(struct pfn_reader_user *user, WARN_ON(last_index < start_index)) return -EINVAL; - if (!user->upages) { + if (!user->file && !user->upages) { /* All undone in pfn_reader_destroy() */ - user->upages_len = - (last_index - start_index + 1) * sizeof(*user->upages); + user->upages_len = npages * sizeof(*user->upages); user->upages = temp_kmalloc(&user->upages_len, NULL, 0); if (!user->upages) return -ENOMEM; } + if (user->file && !user->ufolios) { + user->ufolios_len = npages * sizeof(*user->ufolios); + user->ufolios = temp_kmalloc(&user->ufolios_len, NULL, 0); + if (!user->ufolios) + return -ENOMEM; + } + if (user->locked == -1) { /* * The majority of usages will run the map task within the mm * providing the pages, so we can optimize into * get_user_pages_fast() */ - if (remote_mm) { + if (!user->file && remote_mm) { if (!mmget_not_zero(pages->source_mm)) return -EFAULT; } user->locked = 0; } - npages = min_t(unsigned long, last_index - start_index + 1, - user->upages_len / sizeof(*user->upages)); - + unum = user->file ? user->ufolios_len / sizeof(*user->ufolios) : + user->upages_len / sizeof(*user->upages); + npages = min_t(unsigned long, npages, unum); if (iommufd_should_fail()) return -EFAULT; - uptr = (uintptr_t)(pages->uptr + start_index * PAGE_SIZE); - if (!remote_mm) + if (user->file) { + start = pages->start + (start_index * PAGE_SIZE); + rc = pin_memfd_pages(user, start, npages); + } else if (!remote_mm) { + uptr = (uintptr_t)(pages->uptr + start_index * PAGE_SIZE); rc = pin_user_pages_fast(uptr, npages, user->gup_flags, user->upages); - else { + } else { + uptr = (uintptr_t)(pages->uptr + start_index * PAGE_SIZE); if (!user->locked) { mmap_read_lock(pages->source_mm); user->locked = 1; @@ -838,7 +967,8 @@ static int update_mm_locked_vm(struct iopt_pages *pages, unsigned long npages, mmap_read_unlock(pages->source_mm); user->locked = 0; /* If we had the lock then we also have a get */ - } else if ((!user || !user->upages) && + + } else if ((!user || (!user->upages && !user->ufolios)) && pages->source_mm != current->mm) { if (!mmget_not_zero(pages->source_mm)) return -EINVAL; @@ -855,8 +985,8 @@ static int update_mm_locked_vm(struct iopt_pages *pages, unsigned long npages, return rc; } -static int do_update_pinned(struct iopt_pages *pages, unsigned long npages, - bool inc, struct pfn_reader_user *user) +int iopt_pages_update_pinned(struct iopt_pages *pages, unsigned long npages, + bool inc, struct pfn_reader_user *user) { int rc = 0; @@ -890,8 +1020,8 @@ static void update_unpinned(struct iopt_pages *pages) return; if (pages->npinned == pages->last_npinned) return; - do_update_pinned(pages, pages->last_npinned - pages->npinned, false, - NULL); + iopt_pages_update_pinned(pages, pages->last_npinned - pages->npinned, + false, NULL); } /* @@ -921,7 +1051,7 @@ static int pfn_reader_user_update_pinned(struct pfn_reader_user *user, npages = pages->npinned - pages->last_npinned; inc = true; } - return do_update_pinned(pages, npages, inc, user); + return iopt_pages_update_pinned(pages, npages, inc, user); } /* @@ -978,6 +1108,8 @@ static int pfn_reader_fill_span(struct pfn_reader *pfns) { struct interval_tree_double_span_iter *span = &pfns->span; unsigned long start_index = pfns->batch_end_index; + struct pfn_reader_user *user = &pfns->user; + unsigned long npages; struct iopt_area *area; int rc; @@ -1015,11 +1147,17 @@ static int pfn_reader_fill_span(struct pfn_reader *pfns) return rc; } - batch_from_pages(&pfns->batch, - pfns->user.upages + - (start_index - pfns->user.upages_start), - pfns->user.upages_end - start_index); - return 0; + npages = user->upages_end - start_index; + start_index -= user->upages_start; + rc = 0; + + if (!user->file) + batch_from_pages(&pfns->batch, user->upages + start_index, + npages); + else + rc = batch_from_folios(&pfns->batch, &user->ufolios_next, + &user->ufolios_offset, npages); + return rc; } static bool pfn_reader_done(struct pfn_reader *pfns) @@ -1092,16 +1230,25 @@ static int pfn_reader_init(struct pfn_reader *pfns, struct iopt_pages *pages, static void pfn_reader_release_pins(struct pfn_reader *pfns) { struct iopt_pages *pages = pfns->pages; + struct pfn_reader_user *user = &pfns->user; - if (pfns->user.upages_end > pfns->batch_end_index) { - size_t npages = pfns->user.upages_end - pfns->batch_end_index; - + if (user->upages_end > pfns->batch_end_index) { /* Any pages not transferred to the batch are just unpinned */ - unpin_user_pages(pfns->user.upages + (pfns->batch_end_index - - pfns->user.upages_start), - npages); + + unsigned long npages = user->upages_end - pfns->batch_end_index; + unsigned long start_index = pfns->batch_end_index - + user->upages_start; + + if (!user->file) { + unpin_user_pages(user->upages + start_index, npages); + } else { + long n = user->ufolios_len / sizeof(*user->ufolios); + + unpin_folios(user->ufolios_next, + user->ufolios + n - user->ufolios_next); + } iopt_pages_sub_npinned(pages, npages); - pfns->user.upages_end = pfns->batch_end_index; + user->upages_end = pfns->batch_end_index; } if (pfns->batch_start_index != pfns->batch_end_index) { pfn_reader_unpin(pfns); @@ -1139,11 +1286,11 @@ static int pfn_reader_first(struct pfn_reader *pfns, struct iopt_pages *pages, return 0; } -struct iopt_pages *iopt_alloc_pages(void __user *uptr, unsigned long length, - bool writable) +static struct iopt_pages *iopt_alloc_pages(unsigned long start_byte, + unsigned long length, + bool writable) { struct iopt_pages *pages; - unsigned long end; /* * The iommu API uses size_t as the length, and protect the DIV_ROUND_UP @@ -1152,9 +1299,6 @@ struct iopt_pages *iopt_alloc_pages(void __user *uptr, unsigned long length, if (length > SIZE_MAX - PAGE_SIZE || length == 0) return ERR_PTR(-EINVAL); - if (check_add_overflow((unsigned long)uptr, length, &end)) - return ERR_PTR(-EOVERFLOW); - pages = kzalloc(sizeof(*pages), GFP_KERNEL_ACCOUNT); if (!pages) return ERR_PTR(-ENOMEM); @@ -1164,8 +1308,7 @@ struct iopt_pages *iopt_alloc_pages(void __user *uptr, unsigned long length, mutex_init(&pages->mutex); pages->source_mm = current->mm; mmgrab(pages->source_mm); - pages->uptr = (void __user *)ALIGN_DOWN((uintptr_t)uptr, PAGE_SIZE); - pages->npages = DIV_ROUND_UP(length + (uptr - pages->uptr), PAGE_SIZE); + pages->npages = DIV_ROUND_UP(length + start_byte, PAGE_SIZE); pages->access_itree = RB_ROOT_CACHED; pages->domains_itree = RB_ROOT_CACHED; pages->writable = writable; @@ -1179,6 +1322,45 @@ struct iopt_pages *iopt_alloc_pages(void __user *uptr, unsigned long length, return pages; } +struct iopt_pages *iopt_alloc_user_pages(void __user *uptr, + unsigned long length, bool writable) +{ + struct iopt_pages *pages; + unsigned long end; + void __user *uptr_down = + (void __user *) ALIGN_DOWN((uintptr_t)uptr, PAGE_SIZE); + + if (check_add_overflow((unsigned long)uptr, length, &end)) + return ERR_PTR(-EOVERFLOW); + + pages = iopt_alloc_pages(uptr - uptr_down, length, writable); + if (IS_ERR(pages)) + return pages; + pages->uptr = uptr_down; + pages->type = IOPT_ADDRESS_USER; + return pages; +} + +struct iopt_pages *iopt_alloc_file_pages(struct file *file, unsigned long start, + unsigned long length, bool writable) + +{ + struct iopt_pages *pages; + unsigned long start_down = ALIGN_DOWN(start, PAGE_SIZE); + unsigned long end; + + if (length && check_add_overflow(start, length - 1, &end)) + return ERR_PTR(-EOVERFLOW); + + pages = iopt_alloc_pages(start - start_down, length, writable); + if (IS_ERR(pages)) + return pages; + pages->file = get_file(file); + pages->start = start_down; + pages->type = IOPT_ADDRESS_FILE; + return pages; +} + void iopt_release_pages(struct kref *kref) { struct iopt_pages *pages = container_of(kref, struct iopt_pages, kref); @@ -1191,6 +1373,8 @@ void iopt_release_pages(struct kref *kref) mutex_destroy(&pages->mutex); put_task_struct(pages->source_task); free_uid(pages->source_user); + if (pages->type == IOPT_ADDRESS_FILE) + fput(pages->file); kfree(pages); } @@ -1630,11 +1814,11 @@ static int iopt_pages_fill_from_domain(struct iopt_pages *pages, return 0; } -static int iopt_pages_fill_from_mm(struct iopt_pages *pages, - struct pfn_reader_user *user, - unsigned long start_index, - unsigned long last_index, - struct page **out_pages) +static int iopt_pages_fill(struct iopt_pages *pages, + struct pfn_reader_user *user, + unsigned long start_index, + unsigned long last_index, + struct page **out_pages) { unsigned long cur_index = start_index; int rc; @@ -1708,8 +1892,8 @@ int iopt_pages_fill_xarray(struct iopt_pages *pages, unsigned long start_index, /* hole */ cur_pages = out_pages + (span.start_hole - start_index); - rc = iopt_pages_fill_from_mm(pages, &user, span.start_hole, - span.last_hole, cur_pages); + rc = iopt_pages_fill(pages, &user, span.start_hole, + span.last_hole, cur_pages); if (rc) goto out_clean_xa; rc = pages_to_xarray(&pages->pinned_pfns, span.start_hole, @@ -1789,6 +1973,10 @@ static int iopt_pages_rw_page(struct iopt_pages *pages, unsigned long index, struct page *page = NULL; int rc; + if (IS_ENABLED(CONFIG_IOMMUFD_TEST) && + WARN_ON(pages->type != IOPT_ADDRESS_USER)) + return -EINVAL; + if (!mmget_not_zero(pages->source_mm)) return iopt_pages_rw_slow(pages, index, index, offset, data, length, flags); @@ -1844,6 +2032,15 @@ int iopt_pages_rw_access(struct iopt_pages *pages, unsigned long start_byte, if ((flags & IOMMUFD_ACCESS_RW_WRITE) && !pages->writable) return -EPERM; + if (pages->type == IOPT_ADDRESS_FILE) + return iopt_pages_rw_slow(pages, start_index, last_index, + start_byte % PAGE_SIZE, data, length, + flags); + + if (IS_ENABLED(CONFIG_IOMMUFD_TEST) && + WARN_ON(pages->type != IOPT_ADDRESS_USER)) + return -EINVAL; + if (!(flags & IOMMUFD_ACCESS_RW_KTHREAD) && change_mm) { if (start_index == last_index) return iopt_pages_rw_page(pages, start_index, diff --git a/drivers/iommu/iommufd/selftest.c b/drivers/iommu/iommufd/selftest.c index 540437b..2f9de17 100644 --- a/drivers/iommu/iommufd/selftest.c +++ b/drivers/iommu/iommufd/selftest.c @@ -126,12 +126,35 @@ struct mock_iommu_domain { struct xarray pfns; }; +static inline struct mock_iommu_domain * +to_mock_domain(struct iommu_domain *domain) +{ + return container_of(domain, struct mock_iommu_domain, domain); +} + struct mock_iommu_domain_nested { struct iommu_domain domain; + struct mock_viommu *mock_viommu; struct mock_iommu_domain *parent; u32 iotlb[MOCK_NESTED_DOMAIN_IOTLB_NUM]; }; +static inline struct mock_iommu_domain_nested * +to_mock_nested(struct iommu_domain *domain) +{ + return container_of(domain, struct mock_iommu_domain_nested, domain); +} + +struct mock_viommu { + struct iommufd_viommu core; + struct mock_iommu_domain *s2_parent; +}; + +static inline struct mock_viommu *to_mock_viommu(struct iommufd_viommu *viommu) +{ + return container_of(viommu, struct mock_viommu, core); +} + enum selftest_obj_type { TYPE_IDEV, }; @@ -140,8 +163,14 @@ struct mock_dev { struct device dev; unsigned long flags; int id; + u32 cache[MOCK_DEV_CACHE_NUM]; }; +static inline struct mock_dev *to_mock_dev(struct device *dev) +{ + return container_of(dev, struct mock_dev, dev); +} + struct selftest_obj { struct iommufd_object obj; enum selftest_obj_type type; @@ -155,10 +184,15 @@ struct selftest_obj { }; }; +static inline struct selftest_obj *to_selftest_obj(struct iommufd_object *obj) +{ + return container_of(obj, struct selftest_obj, obj); +} + static int mock_domain_nop_attach(struct iommu_domain *domain, struct device *dev) { - struct mock_dev *mdev = container_of(dev, struct mock_dev, dev); + struct mock_dev *mdev = to_mock_dev(dev); if (domain->dirty_ops && (mdev->flags & MOCK_FLAGS_DEVICE_NO_DIRTY)) return -EINVAL; @@ -193,8 +227,7 @@ static void *mock_domain_hw_info(struct device *dev, u32 *length, u32 *type) static int mock_domain_set_dirty_tracking(struct iommu_domain *domain, bool enable) { - struct mock_iommu_domain *mock = - container_of(domain, struct mock_iommu_domain, domain); + struct mock_iommu_domain *mock = to_mock_domain(domain); unsigned long flags = mock->flags; if (enable && !domain->dirty_ops) @@ -243,8 +276,7 @@ static int mock_domain_read_and_clear_dirty(struct iommu_domain *domain, unsigned long flags, struct iommu_dirty_bitmap *dirty) { - struct mock_iommu_domain *mock = - container_of(domain, struct mock_iommu_domain, domain); + struct mock_iommu_domain *mock = to_mock_domain(domain); unsigned long end = iova + size; void *ent; @@ -281,7 +313,7 @@ static const struct iommu_dirty_ops dirty_ops = { static struct iommu_domain *mock_domain_alloc_paging(struct device *dev) { - struct mock_dev *mdev = container_of(dev, struct mock_dev, dev); + struct mock_dev *mdev = to_mock_dev(dev); struct mock_iommu_domain *mock; mock = kzalloc(sizeof(*mock), GFP_KERNEL); @@ -298,76 +330,85 @@ static struct iommu_domain *mock_domain_alloc_paging(struct device *dev) return &mock->domain; } -static struct iommu_domain * -__mock_domain_alloc_nested(struct mock_iommu_domain *mock_parent, - const struct iommu_hwpt_selftest *user_cfg) +static struct mock_iommu_domain_nested * +__mock_domain_alloc_nested(const struct iommu_user_data *user_data) { struct mock_iommu_domain_nested *mock_nested; - int i; + struct iommu_hwpt_selftest user_cfg; + int rc, i; + + if (user_data->type != IOMMU_HWPT_DATA_SELFTEST) + return ERR_PTR(-EOPNOTSUPP); + + rc = iommu_copy_struct_from_user(&user_cfg, user_data, + IOMMU_HWPT_DATA_SELFTEST, iotlb); + if (rc) + return ERR_PTR(rc); mock_nested = kzalloc(sizeof(*mock_nested), GFP_KERNEL); if (!mock_nested) return ERR_PTR(-ENOMEM); - mock_nested->parent = mock_parent; mock_nested->domain.ops = &domain_nested_ops; mock_nested->domain.type = IOMMU_DOMAIN_NESTED; for (i = 0; i < MOCK_NESTED_DOMAIN_IOTLB_NUM; i++) - mock_nested->iotlb[i] = user_cfg->iotlb; - return &mock_nested->domain; + mock_nested->iotlb[i] = user_cfg.iotlb; + return mock_nested; } static struct iommu_domain * -mock_domain_alloc_user(struct device *dev, u32 flags, - struct iommu_domain *parent, - const struct iommu_user_data *user_data) +mock_domain_alloc_nested(struct iommu_domain *parent, u32 flags, + const struct iommu_user_data *user_data) { + struct mock_iommu_domain_nested *mock_nested; struct mock_iommu_domain *mock_parent; - struct iommu_hwpt_selftest user_cfg; - int rc; - - /* must be mock_domain */ - if (!parent) { - struct mock_dev *mdev = container_of(dev, struct mock_dev, dev); - bool has_dirty_flag = flags & IOMMU_HWPT_ALLOC_DIRTY_TRACKING; - bool no_dirty_ops = mdev->flags & MOCK_FLAGS_DEVICE_NO_DIRTY; - struct iommu_domain *domain; - - if (flags & (~(IOMMU_HWPT_ALLOC_NEST_PARENT | - IOMMU_HWPT_ALLOC_DIRTY_TRACKING))) - return ERR_PTR(-EOPNOTSUPP); - if (user_data || (has_dirty_flag && no_dirty_ops)) - return ERR_PTR(-EOPNOTSUPP); - domain = mock_domain_alloc_paging(dev); - if (!domain) - return ERR_PTR(-ENOMEM); - if (has_dirty_flag) - container_of(domain, struct mock_iommu_domain, domain) - ->domain.dirty_ops = &dirty_ops; - return domain; - } - /* must be mock_domain_nested */ - if (user_data->type != IOMMU_HWPT_DATA_SELFTEST || flags) + if (flags) return ERR_PTR(-EOPNOTSUPP); if (!parent || parent->ops != mock_ops.default_domain_ops) return ERR_PTR(-EINVAL); - mock_parent = container_of(parent, struct mock_iommu_domain, domain); + mock_parent = to_mock_domain(parent); if (!mock_parent) return ERR_PTR(-EINVAL); - rc = iommu_copy_struct_from_user(&user_cfg, user_data, - IOMMU_HWPT_DATA_SELFTEST, iotlb); - if (rc) - return ERR_PTR(rc); + mock_nested = __mock_domain_alloc_nested(user_data); + if (IS_ERR(mock_nested)) + return ERR_CAST(mock_nested); + mock_nested->parent = mock_parent; + return &mock_nested->domain; +} + +static struct iommu_domain * +mock_domain_alloc_user(struct device *dev, u32 flags, + struct iommu_domain *parent, + const struct iommu_user_data *user_data) +{ + bool has_dirty_flag = flags & IOMMU_HWPT_ALLOC_DIRTY_TRACKING; + const u32 PAGING_FLAGS = IOMMU_HWPT_ALLOC_DIRTY_TRACKING | + IOMMU_HWPT_ALLOC_NEST_PARENT; + bool no_dirty_ops = to_mock_dev(dev)->flags & + MOCK_FLAGS_DEVICE_NO_DIRTY; + struct iommu_domain *domain; - return __mock_domain_alloc_nested(mock_parent, &user_cfg); + if (parent) + return mock_domain_alloc_nested(parent, flags, user_data); + + if (user_data) + return ERR_PTR(-EOPNOTSUPP); + if ((flags & ~PAGING_FLAGS) || (has_dirty_flag && no_dirty_ops)) + return ERR_PTR(-EOPNOTSUPP); + + domain = mock_domain_alloc_paging(dev); + if (!domain) + return ERR_PTR(-ENOMEM); + if (has_dirty_flag) + domain->dirty_ops = &dirty_ops; + return domain; } static void mock_domain_free(struct iommu_domain *domain) { - struct mock_iommu_domain *mock = - container_of(domain, struct mock_iommu_domain, domain); + struct mock_iommu_domain *mock = to_mock_domain(domain); WARN_ON(!xa_empty(&mock->pfns)); kfree(mock); @@ -378,8 +419,7 @@ static int mock_domain_map_pages(struct iommu_domain *domain, size_t pgsize, size_t pgcount, int prot, gfp_t gfp, size_t *mapped) { - struct mock_iommu_domain *mock = - container_of(domain, struct mock_iommu_domain, domain); + struct mock_iommu_domain *mock = to_mock_domain(domain); unsigned long flags = MOCK_PFN_START_IOVA; unsigned long start_iova = iova; @@ -430,8 +470,7 @@ static size_t mock_domain_unmap_pages(struct iommu_domain *domain, size_t pgcount, struct iommu_iotlb_gather *iotlb_gather) { - struct mock_iommu_domain *mock = - container_of(domain, struct mock_iommu_domain, domain); + struct mock_iommu_domain *mock = to_mock_domain(domain); bool first = true; size_t ret = 0; void *ent; @@ -479,8 +518,7 @@ static size_t mock_domain_unmap_pages(struct iommu_domain *domain, static phys_addr_t mock_domain_iova_to_phys(struct iommu_domain *domain, dma_addr_t iova) { - struct mock_iommu_domain *mock = - container_of(domain, struct mock_iommu_domain, domain); + struct mock_iommu_domain *mock = to_mock_domain(domain); void *ent; WARN_ON(iova % MOCK_IO_PAGE_SIZE); @@ -491,7 +529,7 @@ static phys_addr_t mock_domain_iova_to_phys(struct iommu_domain *domain, static bool mock_domain_capable(struct device *dev, enum iommu_cap cap) { - struct mock_dev *mdev = container_of(dev, struct mock_dev, dev); + struct mock_dev *mdev = to_mock_dev(dev); switch (cap) { case IOMMU_CAP_CACHE_COHERENCY: @@ -507,14 +545,17 @@ static bool mock_domain_capable(struct device *dev, enum iommu_cap cap) static struct iopf_queue *mock_iommu_iopf_queue; -static struct iommu_device mock_iommu_device = { -}; +static struct mock_iommu_device { + struct iommu_device iommu_dev; + struct completion complete; + refcount_t users; +} mock_iommu; static struct iommu_device *mock_probe_device(struct device *dev) { if (dev->bus != &iommufd_mock_bus_type.bus) return ERR_PTR(-ENODEV); - return &mock_iommu_device; + return &mock_iommu.iommu_dev; } static void mock_domain_page_response(struct device *dev, struct iopf_fault *evt, @@ -540,6 +581,132 @@ static int mock_dev_disable_feat(struct device *dev, enum iommu_dev_features fea return 0; } +static void mock_viommu_destroy(struct iommufd_viommu *viommu) +{ + struct mock_iommu_device *mock_iommu = container_of( + viommu->iommu_dev, struct mock_iommu_device, iommu_dev); + + if (refcount_dec_and_test(&mock_iommu->users)) + complete(&mock_iommu->complete); + + /* iommufd core frees mock_viommu and viommu */ +} + +static struct iommu_domain * +mock_viommu_alloc_domain_nested(struct iommufd_viommu *viommu, u32 flags, + const struct iommu_user_data *user_data) +{ + struct mock_viommu *mock_viommu = to_mock_viommu(viommu); + struct mock_iommu_domain_nested *mock_nested; + + if (flags & ~IOMMU_HWPT_FAULT_ID_VALID) + return ERR_PTR(-EOPNOTSUPP); + + mock_nested = __mock_domain_alloc_nested(user_data); + if (IS_ERR(mock_nested)) + return ERR_CAST(mock_nested); + mock_nested->mock_viommu = mock_viommu; + mock_nested->parent = mock_viommu->s2_parent; + return &mock_nested->domain; +} + +static int mock_viommu_cache_invalidate(struct iommufd_viommu *viommu, + struct iommu_user_data_array *array) +{ + struct iommu_viommu_invalidate_selftest *cmds; + struct iommu_viommu_invalidate_selftest *cur; + struct iommu_viommu_invalidate_selftest *end; + int rc; + + /* A zero-length array is allowed to validate the array type */ + if (array->entry_num == 0 && + array->type == IOMMU_VIOMMU_INVALIDATE_DATA_SELFTEST) { + array->entry_num = 0; + return 0; + } + + cmds = kcalloc(array->entry_num, sizeof(*cmds), GFP_KERNEL); + if (!cmds) + return -ENOMEM; + cur = cmds; + end = cmds + array->entry_num; + + static_assert(sizeof(*cmds) == 3 * sizeof(u32)); + rc = iommu_copy_struct_from_full_user_array( + cmds, sizeof(*cmds), array, + IOMMU_VIOMMU_INVALIDATE_DATA_SELFTEST); + if (rc) + goto out; + + while (cur != end) { + struct mock_dev *mdev; + struct device *dev; + int i; + + if (cur->flags & ~IOMMU_TEST_INVALIDATE_FLAG_ALL) { + rc = -EOPNOTSUPP; + goto out; + } + + if (cur->cache_id > MOCK_DEV_CACHE_ID_MAX) { + rc = -EINVAL; + goto out; + } + + xa_lock(&viommu->vdevs); + dev = iommufd_viommu_find_dev(viommu, + (unsigned long)cur->vdev_id); + if (!dev) { + xa_unlock(&viommu->vdevs); + rc = -EINVAL; + goto out; + } + mdev = container_of(dev, struct mock_dev, dev); + + if (cur->flags & IOMMU_TEST_INVALIDATE_FLAG_ALL) { + /* Invalidate all cache entries and ignore cache_id */ + for (i = 0; i < MOCK_DEV_CACHE_NUM; i++) + mdev->cache[i] = 0; + } else { + mdev->cache[cur->cache_id] = 0; + } + xa_unlock(&viommu->vdevs); + + cur++; + } +out: + array->entry_num = cur - cmds; + kfree(cmds); + return rc; +} + +static struct iommufd_viommu_ops mock_viommu_ops = { + .destroy = mock_viommu_destroy, + .alloc_domain_nested = mock_viommu_alloc_domain_nested, + .cache_invalidate = mock_viommu_cache_invalidate, +}; + +static struct iommufd_viommu *mock_viommu_alloc(struct device *dev, + struct iommu_domain *domain, + struct iommufd_ctx *ictx, + unsigned int viommu_type) +{ + struct mock_iommu_device *mock_iommu = + iommu_get_iommu_dev(dev, struct mock_iommu_device, iommu_dev); + struct mock_viommu *mock_viommu; + + if (viommu_type != IOMMU_VIOMMU_TYPE_SELFTEST) + return ERR_PTR(-EOPNOTSUPP); + + mock_viommu = iommufd_viommu_alloc(ictx, struct mock_viommu, core, + &mock_viommu_ops); + if (IS_ERR(mock_viommu)) + return ERR_CAST(mock_viommu); + + refcount_inc(&mock_iommu->users); + return &mock_viommu->core; +} + static const struct iommu_ops mock_ops = { /* * IOMMU_DOMAIN_BLOCKED cannot be returned from def_domain_type() @@ -559,6 +726,7 @@ static const struct iommu_ops mock_ops = { .dev_enable_feat = mock_dev_enable_feat, .dev_disable_feat = mock_dev_disable_feat, .user_pasid_table = true, + .viommu_alloc = mock_viommu_alloc, .default_domain_ops = &(struct iommu_domain_ops){ .free = mock_domain_free, @@ -571,18 +739,14 @@ static const struct iommu_ops mock_ops = { static void mock_domain_free_nested(struct iommu_domain *domain) { - struct mock_iommu_domain_nested *mock_nested = - container_of(domain, struct mock_iommu_domain_nested, domain); - - kfree(mock_nested); + kfree(to_mock_nested(domain)); } static int mock_domain_cache_invalidate_user(struct iommu_domain *domain, struct iommu_user_data_array *array) { - struct mock_iommu_domain_nested *mock_nested = - container_of(domain, struct mock_iommu_domain_nested, domain); + struct mock_iommu_domain_nested *mock_nested = to_mock_nested(domain); struct iommu_hwpt_invalidate_selftest inv; u32 processed = 0; int i = 0, j; @@ -657,7 +821,7 @@ get_md_pagetable(struct iommufd_ucmd *ucmd, u32 mockpt_id, iommufd_put_object(ucmd->ictx, &hwpt->obj); return ERR_PTR(-EINVAL); } - *mock = container_of(hwpt->domain, struct mock_iommu_domain, domain); + *mock = to_mock_domain(hwpt->domain); return hwpt; } @@ -675,14 +839,13 @@ get_md_pagetable_nested(struct iommufd_ucmd *ucmd, u32 mockpt_id, iommufd_put_object(ucmd->ictx, &hwpt->obj); return ERR_PTR(-EINVAL); } - *mock_nested = container_of(hwpt->domain, - struct mock_iommu_domain_nested, domain); + *mock_nested = to_mock_nested(hwpt->domain); return hwpt; } static void mock_dev_release(struct device *dev) { - struct mock_dev *mdev = container_of(dev, struct mock_dev, dev); + struct mock_dev *mdev = to_mock_dev(dev); ida_free(&mock_dev_ida, mdev->id); kfree(mdev); @@ -691,7 +854,7 @@ static void mock_dev_release(struct device *dev) static struct mock_dev *mock_dev_create(unsigned long dev_flags) { struct mock_dev *mdev; - int rc; + int rc, i; if (dev_flags & ~(MOCK_FLAGS_DEVICE_NO_DIRTY | MOCK_FLAGS_DEVICE_HUGE_IOVA)) @@ -705,6 +868,8 @@ static struct mock_dev *mock_dev_create(unsigned long dev_flags) mdev->flags = dev_flags; mdev->dev.release = mock_dev_release; mdev->dev.bus = &iommufd_mock_bus_type.bus; + for (i = 0; i < MOCK_DEV_CACHE_NUM; i++) + mdev->cache[i] = IOMMU_TEST_DEV_CACHE_DEFAULT; rc = ida_alloc(&mock_dev_ida, GFP_KERNEL); if (rc < 0) @@ -813,7 +978,7 @@ static int iommufd_test_mock_domain_replace(struct iommufd_ucmd *ucmd, if (IS_ERR(dev_obj)) return PTR_ERR(dev_obj); - sobj = container_of(dev_obj, struct selftest_obj, obj); + sobj = to_selftest_obj(dev_obj); if (sobj->type != TYPE_IDEV) { rc = -EINVAL; goto out_dev_obj; @@ -951,8 +1116,7 @@ static int iommufd_test_md_check_iotlb(struct iommufd_ucmd *ucmd, if (IS_ERR(hwpt)) return PTR_ERR(hwpt); - mock_nested = container_of(hwpt->domain, - struct mock_iommu_domain_nested, domain); + mock_nested = to_mock_nested(hwpt->domain); if (iotlb_id > MOCK_NESTED_DOMAIN_IOTLB_ID_MAX || mock_nested->iotlb[iotlb_id] != iotlb) @@ -961,6 +1125,24 @@ static int iommufd_test_md_check_iotlb(struct iommufd_ucmd *ucmd, return rc; } +static int iommufd_test_dev_check_cache(struct iommufd_ucmd *ucmd, u32 idev_id, + unsigned int cache_id, u32 cache) +{ + struct iommufd_device *idev; + struct mock_dev *mdev; + int rc = 0; + + idev = iommufd_get_device(ucmd, idev_id); + if (IS_ERR(idev)) + return PTR_ERR(idev); + mdev = container_of(idev->dev, struct mock_dev, dev); + + if (cache_id > MOCK_DEV_CACHE_ID_MAX || mdev->cache[cache_id] != cache) + rc = -EINVAL; + iommufd_put_object(ucmd->ictx, &idev->obj); + return rc; +} + struct selftest_access { struct iommufd_access *access; struct file *file; @@ -1431,7 +1613,7 @@ static int iommufd_test_trigger_iopf(struct iommufd_ucmd *ucmd, void iommufd_selftest_destroy(struct iommufd_object *obj) { - struct selftest_obj *sobj = container_of(obj, struct selftest_obj, obj); + struct selftest_obj *sobj = to_selftest_obj(obj); switch (sobj->type) { case TYPE_IDEV: @@ -1470,6 +1652,10 @@ int iommufd_test(struct iommufd_ucmd *ucmd) return iommufd_test_md_check_iotlb(ucmd, cmd->id, cmd->check_iotlb.id, cmd->check_iotlb.iotlb); + case IOMMU_TEST_OP_DEV_CHECK_CACHE: + return iommufd_test_dev_check_cache(ucmd, cmd->id, + cmd->check_dev_cache.id, + cmd->check_dev_cache.cache); case IOMMU_TEST_OP_CREATE_ACCESS: return iommufd_test_create_access(ucmd, cmd->id, cmd->create_access.flags); @@ -1536,24 +1722,27 @@ int __init iommufd_test_init(void) if (rc) goto err_platform; - rc = iommu_device_sysfs_add(&mock_iommu_device, + rc = iommu_device_sysfs_add(&mock_iommu.iommu_dev, &selftest_iommu_dev->dev, NULL, "%s", dev_name(&selftest_iommu_dev->dev)); if (rc) goto err_bus; - rc = iommu_device_register_bus(&mock_iommu_device, &mock_ops, + rc = iommu_device_register_bus(&mock_iommu.iommu_dev, &mock_ops, &iommufd_mock_bus_type.bus, &iommufd_mock_bus_type.nb); if (rc) goto err_sysfs; + refcount_set(&mock_iommu.users, 1); + init_completion(&mock_iommu.complete); + mock_iommu_iopf_queue = iopf_queue_alloc("mock-iopfq"); return 0; err_sysfs: - iommu_device_sysfs_remove(&mock_iommu_device); + iommu_device_sysfs_remove(&mock_iommu.iommu_dev); err_bus: bus_unregister(&iommufd_mock_bus_type.bus); err_platform: @@ -1563,6 +1752,22 @@ err_dbgfs: return rc; } +static void iommufd_test_wait_for_users(void) +{ + if (refcount_dec_and_test(&mock_iommu.users)) + return; + /* + * Time out waiting for iommu device user count to become 0. + * + * Note that this is just making an example here, since the selftest is + * built into the iommufd module, i.e. it only unplugs the iommu device + * when unloading the module. So, it is expected that this WARN_ON will + * not trigger, as long as any iommufd FDs are open. + */ + WARN_ON(!wait_for_completion_timeout(&mock_iommu.complete, + msecs_to_jiffies(10000))); +} + void iommufd_test_exit(void) { if (mock_iommu_iopf_queue) { @@ -1570,8 +1775,9 @@ void iommufd_test_exit(void) mock_iommu_iopf_queue = NULL; } - iommu_device_sysfs_remove(&mock_iommu_device); - iommu_device_unregister_bus(&mock_iommu_device, + iommufd_test_wait_for_users(); + iommu_device_sysfs_remove(&mock_iommu.iommu_dev); + iommu_device_unregister_bus(&mock_iommu.iommu_dev, &iommufd_mock_bus_type.bus, &iommufd_mock_bus_type.nb); bus_unregister(&iommufd_mock_bus_type.bus); diff --git a/drivers/iommu/iommufd/vfio_compat.c b/drivers/iommu/iommufd/vfio_compat.c index a3ad5f0..514aacd 100644 --- a/drivers/iommu/iommufd/vfio_compat.c +++ b/drivers/iommu/iommufd/vfio_compat.c @@ -291,12 +291,7 @@ static int iommufd_vfio_check_extension(struct iommufd_ctx *ictx, case VFIO_DMA_CC_IOMMU: return iommufd_vfio_cc_iommu(ictx); - /* - * This is obsolete, and to be removed from VFIO. It was an incomplete - * idea that got merged. - * https://lore.kernel.org/kvm/0-v1-0093c9b0e345+19-vfio_no_nesting_jgg@nvidia.com/ - */ - case VFIO_TYPE1_NESTING_IOMMU: + case __VFIO_RESERVED_TYPE1_NESTING_IOMMU: return 0; /* diff --git a/drivers/iommu/iommufd/viommu.c b/drivers/iommu/iommufd/viommu.c new file mode 100644 index 0000000..69b88e8 --- /dev/null +++ b/drivers/iommu/iommufd/viommu.c @@ -0,0 +1,157 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Copyright (c) 2024, NVIDIA CORPORATION & AFFILIATES + */ +#include "iommufd_private.h" + +void iommufd_viommu_destroy(struct iommufd_object *obj) +{ + struct iommufd_viommu *viommu = + container_of(obj, struct iommufd_viommu, obj); + + if (viommu->ops && viommu->ops->destroy) + viommu->ops->destroy(viommu); + refcount_dec(&viommu->hwpt->common.obj.users); + xa_destroy(&viommu->vdevs); +} + +int iommufd_viommu_alloc_ioctl(struct iommufd_ucmd *ucmd) +{ + struct iommu_viommu_alloc *cmd = ucmd->cmd; + struct iommufd_hwpt_paging *hwpt_paging; + struct iommufd_viommu *viommu; + struct iommufd_device *idev; + const struct iommu_ops *ops; + int rc; + + if (cmd->flags || cmd->type == IOMMU_VIOMMU_TYPE_DEFAULT) + return -EOPNOTSUPP; + + idev = iommufd_get_device(ucmd, cmd->dev_id); + if (IS_ERR(idev)) + return PTR_ERR(idev); + + ops = dev_iommu_ops(idev->dev); + if (!ops->viommu_alloc) { + rc = -EOPNOTSUPP; + goto out_put_idev; + } + + hwpt_paging = iommufd_get_hwpt_paging(ucmd, cmd->hwpt_id); + if (IS_ERR(hwpt_paging)) { + rc = PTR_ERR(hwpt_paging); + goto out_put_idev; + } + + if (!hwpt_paging->nest_parent) { + rc = -EINVAL; + goto out_put_hwpt; + } + + viommu = ops->viommu_alloc(idev->dev, hwpt_paging->common.domain, + ucmd->ictx, cmd->type); + if (IS_ERR(viommu)) { + rc = PTR_ERR(viommu); + goto out_put_hwpt; + } + + xa_init(&viommu->vdevs); + viommu->type = cmd->type; + viommu->ictx = ucmd->ictx; + viommu->hwpt = hwpt_paging; + refcount_inc(&viommu->hwpt->common.obj.users); + /* + * It is the most likely case that a physical IOMMU is unpluggable. A + * pluggable IOMMU instance (if exists) is responsible for refcounting + * on its own. + */ + viommu->iommu_dev = __iommu_get_iommu_dev(idev->dev); + + cmd->out_viommu_id = viommu->obj.id; + rc = iommufd_ucmd_respond(ucmd, sizeof(*cmd)); + if (rc) + goto out_abort; + iommufd_object_finalize(ucmd->ictx, &viommu->obj); + goto out_put_hwpt; + +out_abort: + iommufd_object_abort_and_destroy(ucmd->ictx, &viommu->obj); +out_put_hwpt: + iommufd_put_object(ucmd->ictx, &hwpt_paging->common.obj); +out_put_idev: + iommufd_put_object(ucmd->ictx, &idev->obj); + return rc; +} + +void iommufd_vdevice_destroy(struct iommufd_object *obj) +{ + struct iommufd_vdevice *vdev = + container_of(obj, struct iommufd_vdevice, obj); + struct iommufd_viommu *viommu = vdev->viommu; + + /* xa_cmpxchg is okay to fail if alloc failed xa_cmpxchg previously */ + xa_cmpxchg(&viommu->vdevs, vdev->id, vdev, NULL, GFP_KERNEL); + refcount_dec(&viommu->obj.users); + put_device(vdev->dev); +} + +int iommufd_vdevice_alloc_ioctl(struct iommufd_ucmd *ucmd) +{ + struct iommu_vdevice_alloc *cmd = ucmd->cmd; + struct iommufd_vdevice *vdev, *curr; + struct iommufd_viommu *viommu; + struct iommufd_device *idev; + u64 virt_id = cmd->virt_id; + int rc = 0; + + /* virt_id indexes an xarray */ + if (virt_id > ULONG_MAX) + return -EINVAL; + + viommu = iommufd_get_viommu(ucmd, cmd->viommu_id); + if (IS_ERR(viommu)) + return PTR_ERR(viommu); + + idev = iommufd_get_device(ucmd, cmd->dev_id); + if (IS_ERR(idev)) { + rc = PTR_ERR(idev); + goto out_put_viommu; + } + + if (viommu->iommu_dev != __iommu_get_iommu_dev(idev->dev)) { + rc = -EINVAL; + goto out_put_idev; + } + + vdev = iommufd_object_alloc(ucmd->ictx, vdev, IOMMUFD_OBJ_VDEVICE); + if (IS_ERR(vdev)) { + rc = PTR_ERR(vdev); + goto out_put_idev; + } + + vdev->id = virt_id; + vdev->dev = idev->dev; + get_device(idev->dev); + vdev->viommu = viommu; + refcount_inc(&viommu->obj.users); + + curr = xa_cmpxchg(&viommu->vdevs, virt_id, NULL, vdev, GFP_KERNEL); + if (curr) { + rc = xa_err(curr) ?: -EEXIST; + goto out_abort; + } + + cmd->out_vdevice_id = vdev->obj.id; + rc = iommufd_ucmd_respond(ucmd, sizeof(*cmd)); + if (rc) + goto out_abort; + iommufd_object_finalize(ucmd->ictx, &vdev->obj); + goto out_put_idev; + +out_abort: + iommufd_object_abort_and_destroy(ucmd->ictx, &vdev->obj); +out_put_idev: + iommufd_put_object(ucmd->ictx, &idev->obj); +out_put_viommu: + iommufd_put_object(ucmd->ictx, &viommu->obj); + return rc; +} diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c index bf391b4..50ebc95 100644 --- a/drivers/vfio/vfio_iommu_type1.c +++ b/drivers/vfio/vfio_iommu_type1.c @@ -72,7 +72,6 @@ struct vfio_iommu { uint64_t pgsize_bitmap; uint64_t num_non_pinned_groups; bool v2; - bool nesting; bool dirty_page_tracking; struct list_head emulated_iommu_groups; }; @@ -2195,12 +2194,6 @@ static int vfio_iommu_type1_attach_group(void *iommu_data, goto out_free_domain; } - if (iommu->nesting) { - ret = iommu_enable_nesting(domain->domain); - if (ret) - goto out_domain; - } - ret = iommu_attach_group(domain->domain, group->iommu_group); if (ret) goto out_domain; @@ -2541,9 +2534,7 @@ static void *vfio_iommu_type1_open(unsigned long arg) switch (arg) { case VFIO_TYPE1_IOMMU: break; - case VFIO_TYPE1_NESTING_IOMMU: - iommu->nesting = true; - fallthrough; + case __VFIO_RESERVED_TYPE1_NESTING_IOMMU: case VFIO_TYPE1v2_IOMMU: iommu->v2 = true; break; @@ -2638,7 +2629,6 @@ static int vfio_iommu_type1_check_extension(struct vfio_iommu *iommu, switch (arg) { case VFIO_TYPE1_IOMMU: case VFIO_TYPE1v2_IOMMU: - case VFIO_TYPE1_NESTING_IOMMU: case VFIO_UNMAP_ALL: return 1; case VFIO_UPDATE_VADDR: diff --git a/include/acpi/actbl2.h b/include/acpi/actbl2.h index d3858ee..2e917a8 100644 --- a/include/acpi/actbl2.h +++ b/include/acpi/actbl2.h @@ -453,7 +453,7 @@ struct acpi_table_ccel { * IORT - IO Remapping Table * * Conforms to "IO Remapping Table System Software on ARM Platforms", - * Document number: ARM DEN 0049E.e, Sep 2022 + * Document number: ARM DEN 0049E.f, Apr 2024 * ******************************************************************************/ @@ -524,6 +524,7 @@ struct acpi_iort_memory_access { #define ACPI_IORT_MF_COHERENCY (1) #define ACPI_IORT_MF_ATTRIBUTES (1<<1) +#define ACPI_IORT_MF_CANWBS (1<<2) /* * IORT node specific subtables diff --git a/include/linux/io-pgtable.h b/include/linux/io-pgtable.h index b1ecfc3..ce86b09 100644 --- a/include/linux/io-pgtable.h +++ b/include/linux/io-pgtable.h @@ -87,6 +87,7 @@ struct io_pgtable_cfg { * attributes set in the TCR for a non-coherent page-table walker. * * IO_PGTABLE_QUIRK_ARM_HD: Enables dirty tracking in stage 1 pagetable. + * IO_PGTABLE_QUIRK_ARM_S2FWB: Use the FWB format for the MemAttrs bits */ #define IO_PGTABLE_QUIRK_ARM_NS BIT(0) #define IO_PGTABLE_QUIRK_NO_PERMS BIT(1) @@ -95,6 +96,7 @@ struct io_pgtable_cfg { #define IO_PGTABLE_QUIRK_ARM_TTBR1 BIT(5) #define IO_PGTABLE_QUIRK_ARM_OUTER_WBWA BIT(6) #define IO_PGTABLE_QUIRK_ARM_HD BIT(7) + #define IO_PGTABLE_QUIRK_ARM_S2FWB BIT(8) unsigned long quirks; unsigned long pgsize_bitmap; unsigned int ias; diff --git a/include/linux/iommu.h b/include/linux/iommu.h index bd722f4..8b02adb 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -42,6 +42,8 @@ struct notifier_block; struct iommu_sva; struct iommu_dma_cookie; struct iommu_fault_param; +struct iommufd_ctx; +struct iommufd_viommu; #define IOMMU_FAULT_PERM_READ (1 << 0) /* read */ #define IOMMU_FAULT_PERM_WRITE (1 << 1) /* write */ @@ -491,7 +493,9 @@ static inline int __iommu_copy_struct_from_user_array( * @index: Index to the location in the array to copy user data from * @min_last: The last member of the data structure @kdst points in the * initial version. - * Return 0 for success, otherwise -error. + * + * Copy a single entry from a user array. Return 0 for success, otherwise + * -error. */ #define iommu_copy_struct_from_user_array(kdst, user_array, data_type, index, \ min_last) \ @@ -500,6 +504,50 @@ static inline int __iommu_copy_struct_from_user_array( offsetofend(typeof(*(kdst)), min_last)) /** + * iommu_copy_struct_from_full_user_array - Copy iommu driver specific user + * space data from an iommu_user_data_array + * @kdst: Pointer to an iommu driver specific user data that is defined in + * include/uapi/linux/iommufd.h + * @kdst_entry_size: sizeof(*kdst) + * @user_array: Pointer to a struct iommu_user_data_array for a user space + * array + * @data_type: The data type of the @kdst. Must match with @user_array->type + * + * Copy the entire user array. kdst must have room for kdst_entry_size * + * user_array->entry_num bytes. Return 0 for success, otherwise -error. + */ +static inline int +iommu_copy_struct_from_full_user_array(void *kdst, size_t kdst_entry_size, + struct iommu_user_data_array *user_array, + unsigned int data_type) +{ + unsigned int i; + int ret; + + if (user_array->type != data_type) + return -EINVAL; + if (!user_array->entry_num) + return -EINVAL; + if (likely(user_array->entry_len == kdst_entry_size)) { + if (copy_from_user(kdst, user_array->uptr, + user_array->entry_num * + user_array->entry_len)) + return -EFAULT; + } + + /* Copy item by item */ + for (i = 0; i != user_array->entry_num; i++) { + ret = copy_struct_from_user( + kdst + kdst_entry_size * i, kdst_entry_size, + user_array->uptr + user_array->entry_len * i, + user_array->entry_len); + if (ret) + return ret; + } + return 0; +} + +/** * struct iommu_ops - iommu ops and capabilities * @capable: check capability * @hw_info: report iommu hardware information. The data buffer returned by this @@ -542,6 +590,14 @@ static inline int __iommu_copy_struct_from_user_array( * @remove_dev_pasid: Remove any translation configurations of a specific * pasid, so that any DMA transactions with this pasid * will be blocked by the hardware. + * @viommu_alloc: Allocate an iommufd_viommu on a physical IOMMU instance behind + * the @dev, as the set of virtualization resources shared/passed + * to user space IOMMU instance. And associate it with a nesting + * @parent_domain. The @viommu_type must be defined in the header + * include/uapi/linux/iommufd.h + * It is required to call iommufd_viommu_alloc() helper for + * a bundled allocation of the core and the driver structures, + * using the given @ictx pointer. * @pgsize_bitmap: bitmap of all possible supported page sizes * @owner: Driver module providing these ops * @identity_domain: An always available, always attachable identity @@ -591,6 +647,10 @@ struct iommu_ops { void (*remove_dev_pasid)(struct device *dev, ioasid_t pasid, struct iommu_domain *domain); + struct iommufd_viommu *(*viommu_alloc)( + struct device *dev, struct iommu_domain *parent_domain, + struct iommufd_ctx *ictx, unsigned int viommu_type); + const struct iommu_domain_ops *default_domain_ops; unsigned long pgsize_bitmap; struct module *owner; @@ -635,7 +695,6 @@ struct iommu_ops { * @enforce_cache_coherency: Prevent any kind of DMA from bypassing IOMMU_CACHE, * including no-snoop TLPs on PCIe or other platform * specific mechanisms. - * @enable_nesting: Enable nesting * @set_pgtable_quirks: Set io page table quirks (IO_PGTABLE_QUIRK_*) * @free: Release the domain after use. */ @@ -663,7 +722,6 @@ struct iommu_domain_ops { dma_addr_t iova); bool (*enforce_cache_coherency)(struct iommu_domain *domain); - int (*enable_nesting)(struct iommu_domain *domain); int (*set_pgtable_quirks)(struct iommu_domain *domain, unsigned long quirks); @@ -844,7 +902,6 @@ extern void iommu_group_put(struct iommu_group *group); extern int iommu_group_id(struct iommu_group *group); extern struct iommu_domain *iommu_group_default_domain(struct iommu_group *); -int iommu_enable_nesting(struct iommu_domain *domain); int iommu_set_pgtable_quirks(struct iommu_domain *domain, unsigned long quirks); @@ -994,6 +1051,8 @@ struct iommu_fwspec { /* ATS is supported */ #define IOMMU_FWSPEC_PCI_RC_ATS (1 << 0) +/* CANWBS is supported */ +#define IOMMU_FWSPEC_PCI_RC_CANWBS (1 << 1) /* * An iommu attach handle represents a relationship between an iommu domain diff --git a/include/linux/iommufd.h b/include/linux/iommufd.h index 30f832a..11110c7 100644 --- a/include/linux/iommufd.h +++ b/include/linux/iommufd.h @@ -8,16 +8,46 @@ #include #include +#include #include +#include struct device; struct file; struct iommu_group; +struct iommu_user_data; +struct iommu_user_data_array; struct iommufd_access; struct iommufd_ctx; struct iommufd_device; +struct iommufd_viommu_ops; struct page; +enum iommufd_object_type { + IOMMUFD_OBJ_NONE, + IOMMUFD_OBJ_ANY = IOMMUFD_OBJ_NONE, + IOMMUFD_OBJ_DEVICE, + IOMMUFD_OBJ_HWPT_PAGING, + IOMMUFD_OBJ_HWPT_NESTED, + IOMMUFD_OBJ_IOAS, + IOMMUFD_OBJ_ACCESS, + IOMMUFD_OBJ_FAULT, + IOMMUFD_OBJ_VIOMMU, + IOMMUFD_OBJ_VDEVICE, +#ifdef CONFIG_IOMMUFD_TEST + IOMMUFD_OBJ_SELFTEST, +#endif + IOMMUFD_OBJ_MAX, +}; + +/* Base struct for all objects with a userspace ID handle. */ +struct iommufd_object { + refcount_t shortterm_users; + refcount_t users; + enum iommufd_object_type type; + unsigned int id; +}; + struct iommufd_device *iommufd_device_bind(struct iommufd_ctx *ictx, struct device *dev, u32 *id); void iommufd_device_unbind(struct iommufd_device *idev); @@ -54,6 +84,45 @@ void iommufd_access_detach(struct iommufd_access *access); void iommufd_ctx_get(struct iommufd_ctx *ictx); +struct iommufd_viommu { + struct iommufd_object obj; + struct iommufd_ctx *ictx; + struct iommu_device *iommu_dev; + struct iommufd_hwpt_paging *hwpt; + + const struct iommufd_viommu_ops *ops; + + struct xarray vdevs; + + unsigned int type; +}; + +/** + * struct iommufd_viommu_ops - vIOMMU specific operations + * @destroy: Clean up all driver-specific parts of an iommufd_viommu. The memory + * of the vIOMMU will be free-ed by iommufd core after calling this op + * @alloc_domain_nested: Allocate a IOMMU_DOMAIN_NESTED on a vIOMMU that holds a + * nesting parent domain (IOMMU_DOMAIN_PAGING). @user_data + * must be defined in include/uapi/linux/iommufd.h. + * It must fully initialize the new iommu_domain before + * returning. Upon failure, ERR_PTR must be returned. + * @cache_invalidate: Flush hardware cache used by a vIOMMU. It can be used for + * any IOMMU hardware specific cache: TLB and device cache. + * The @array passes in the cache invalidation requests, in + * form of a driver data structure. A driver must update the + * array->entry_num to report the number of handled requests. + * The data structure of the array entry must be defined in + * include/uapi/linux/iommufd.h + */ +struct iommufd_viommu_ops { + void (*destroy)(struct iommufd_viommu *viommu); + struct iommu_domain *(*alloc_domain_nested)( + struct iommufd_viommu *viommu, u32 flags, + const struct iommu_user_data *user_data); + int (*cache_invalidate)(struct iommufd_viommu *viommu, + struct iommu_user_data_array *array); +}; + #if IS_ENABLED(CONFIG_IOMMUFD) struct iommufd_ctx *iommufd_ctx_from_file(struct file *file); struct iommufd_ctx *iommufd_ctx_from_fd(int fd); @@ -111,4 +180,43 @@ static inline int iommufd_vfio_compat_set_no_iommu(struct iommufd_ctx *ictx) return -EOPNOTSUPP; } #endif /* CONFIG_IOMMUFD */ + +#if IS_ENABLED(CONFIG_IOMMUFD_DRIVER_CORE) +struct iommufd_object *_iommufd_object_alloc(struct iommufd_ctx *ictx, + size_t size, + enum iommufd_object_type type); +struct device *iommufd_viommu_find_dev(struct iommufd_viommu *viommu, + unsigned long vdev_id); +#else /* !CONFIG_IOMMUFD_DRIVER_CORE */ +static inline struct iommufd_object * +_iommufd_object_alloc(struct iommufd_ctx *ictx, size_t size, + enum iommufd_object_type type) +{ + return ERR_PTR(-EOPNOTSUPP); +} + +static inline struct device * +iommufd_viommu_find_dev(struct iommufd_viommu *viommu, unsigned long vdev_id) +{ + return NULL; +} +#endif /* CONFIG_IOMMUFD_DRIVER_CORE */ + +/* + * Helpers for IOMMU driver to allocate driver structures that will be freed by + * the iommufd core. The free op will be called prior to freeing the memory. + */ +#define iommufd_viommu_alloc(ictx, drv_struct, member, viommu_ops) \ + ({ \ + drv_struct *ret; \ + \ + static_assert(__same_type(struct iommufd_viommu, \ + ((drv_struct *)NULL)->member)); \ + static_assert(offsetof(drv_struct, member.obj) == 0); \ + ret = (drv_struct *)_iommufd_object_alloc( \ + ictx, sizeof(drv_struct), IOMMUFD_OBJ_VIOMMU); \ + if (!IS_ERR(ret)) \ + ret->member.ops = viommu_ops; \ + ret; \ + }) #endif diff --git a/include/linux/mm.h b/include/linux/mm.h index feb5c80..673771f 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2536,6 +2536,7 @@ long pin_user_pages_unlocked(unsigned long start, unsigned long nr_pages, long memfd_pin_folios(struct file *memfd, loff_t start, loff_t end, struct folio **folios, unsigned int max_folios, pgoff_t *offset); +int folio_add_pins(struct folio *folio, unsigned int pins); int get_user_pages_fast(unsigned long start, int nr_pages, unsigned int gup_flags, struct page **pages); diff --git a/include/uapi/linux/iommufd.h b/include/uapi/linux/iommufd.h index 72010f7..4ae8b1e 100644 --- a/include/uapi/linux/iommufd.h +++ b/include/uapi/linux/iommufd.h @@ -51,6 +51,10 @@ enum { IOMMUFD_CMD_HWPT_GET_DIRTY_BITMAP = 0x8c, IOMMUFD_CMD_HWPT_INVALIDATE = 0x8d, IOMMUFD_CMD_FAULT_QUEUE_ALLOC = 0x8e, + IOMMUFD_CMD_IOAS_MAP_FILE = 0x8f, + IOMMUFD_CMD_VIOMMU_ALLOC = 0x90, + IOMMUFD_CMD_VDEVICE_ALLOC = 0x91, + IOMMUFD_CMD_IOAS_CHANGE_PROCESS = 0x92, }; /** @@ -214,6 +218,30 @@ struct iommu_ioas_map { #define IOMMU_IOAS_MAP _IO(IOMMUFD_TYPE, IOMMUFD_CMD_IOAS_MAP) /** + * struct iommu_ioas_map_file - ioctl(IOMMU_IOAS_MAP_FILE) + * @size: sizeof(struct iommu_ioas_map_file) + * @flags: same as for iommu_ioas_map + * @ioas_id: same as for iommu_ioas_map + * @fd: the memfd to map + * @start: byte offset from start of file to map from + * @length: same as for iommu_ioas_map + * @iova: same as for iommu_ioas_map + * + * Set an IOVA mapping from a memfd file. All other arguments and semantics + * match those of IOMMU_IOAS_MAP. + */ +struct iommu_ioas_map_file { + __u32 size; + __u32 flags; + __u32 ioas_id; + __s32 fd; + __aligned_u64 start; + __aligned_u64 length; + __aligned_u64 iova; +}; +#define IOMMU_IOAS_MAP_FILE _IO(IOMMUFD_TYPE, IOMMUFD_CMD_IOAS_MAP_FILE) + +/** * struct iommu_ioas_copy - ioctl(IOMMU_IOAS_COPY) * @size: sizeof(struct iommu_ioas_copy) * @flags: Combination of enum iommufd_ioas_map_flags @@ -395,13 +423,35 @@ struct iommu_hwpt_vtd_s1 { }; /** + * struct iommu_hwpt_arm_smmuv3 - ARM SMMUv3 nested STE + * (IOMMU_HWPT_DATA_ARM_SMMUV3) + * + * @ste: The first two double words of the user space Stream Table Entry for + * the translation. Must be little-endian. + * Allowed fields: (Refer to "5.2 Stream Table Entry" in SMMUv3 HW Spec) + * - word-0: V, Cfg, S1Fmt, S1ContextPtr, S1CDMax + * - word-1: EATS, S1DSS, S1CIR, S1COR, S1CSH, S1STALLD + * + * -EIO will be returned if @ste is not legal or contains any non-allowed field. + * Cfg can be used to select a S1, Bypass or Abort configuration. A Bypass + * nested domain will translate the same as the nesting parent. The S1 will + * install a Context Descriptor Table pointing at userspace memory translated + * by the nesting parent. + */ +struct iommu_hwpt_arm_smmuv3 { + __aligned_le64 ste[2]; +}; + +/** * enum iommu_hwpt_data_type - IOMMU HWPT Data Type * @IOMMU_HWPT_DATA_NONE: no data * @IOMMU_HWPT_DATA_VTD_S1: Intel VT-d stage-1 page table + * @IOMMU_HWPT_DATA_ARM_SMMUV3: ARM SMMUv3 Context Descriptor Table */ enum iommu_hwpt_data_type { IOMMU_HWPT_DATA_NONE = 0, IOMMU_HWPT_DATA_VTD_S1 = 1, + IOMMU_HWPT_DATA_ARM_SMMUV3 = 2, }; /** @@ -409,7 +459,7 @@ enum iommu_hwpt_data_type { * @size: sizeof(struct iommu_hwpt_alloc) * @flags: Combination of enum iommufd_hwpt_alloc_flags * @dev_id: The device to allocate this HWPT for - * @pt_id: The IOAS or HWPT to connect this HWPT to + * @pt_id: The IOAS or HWPT or vIOMMU to connect this HWPT to * @out_hwpt_id: The ID of the new HWPT * @__reserved: Must be 0 * @data_type: One of enum iommu_hwpt_data_type @@ -428,11 +478,13 @@ enum iommu_hwpt_data_type { * IOMMU_HWPT_DATA_NONE. The HWPT can be allocated as a parent HWPT for a * nesting configuration by passing IOMMU_HWPT_ALLOC_NEST_PARENT via @flags. * - * A user-managed nested HWPT will be created from a given parent HWPT via - * @pt_id, in which the parent HWPT must be allocated previously via the - * same ioctl from a given IOAS (@pt_id). In this case, the @data_type - * must be set to a pre-defined type corresponding to an I/O page table - * type supported by the underlying IOMMU hardware. + * A user-managed nested HWPT will be created from a given vIOMMU (wrapping a + * parent HWPT) or a parent HWPT via @pt_id, in which the parent HWPT must be + * allocated previously via the same ioctl from a given IOAS (@pt_id). In this + * case, the @data_type must be set to a pre-defined type corresponding to an + * I/O page table type supported by the underlying IOMMU hardware. The device + * via @dev_id and the vIOMMU via @pt_id must be associated to the same IOMMU + * instance. * * If the @data_type is set to IOMMU_HWPT_DATA_NONE, @data_len and * @data_uptr should be zero. Otherwise, both @data_len and @data_uptr @@ -485,14 +537,49 @@ struct iommu_hw_info_vtd { }; /** + * struct iommu_hw_info_arm_smmuv3 - ARM SMMUv3 hardware information + * (IOMMU_HW_INFO_TYPE_ARM_SMMUV3) + * + * @flags: Must be set to 0 + * @__reserved: Must be 0 + * @idr: Implemented features for ARM SMMU Non-secure programming interface + * @iidr: Information about the implementation and implementer of ARM SMMU, + * and architecture version supported + * @aidr: ARM SMMU architecture version + * + * For the details of @idr, @iidr and @aidr, please refer to the chapters + * from 6.3.1 to 6.3.6 in the SMMUv3 Spec. + * + * User space should read the underlying ARM SMMUv3 hardware information for + * the list of supported features. + * + * Note that these values reflect the raw HW capability, without any insight if + * any required kernel driver support is present. Bits may be set indicating the + * HW has functionality that is lacking kernel software support, such as BTM. If + * a VMM is using this information to construct emulated copies of these + * registers it should only forward bits that it knows it can support. + * + * In future, presence of required kernel support will be indicated in flags. + */ +struct iommu_hw_info_arm_smmuv3 { + __u32 flags; + __u32 __reserved; + __u32 idr[6]; + __u32 iidr; + __u32 aidr; +}; + +/** * enum iommu_hw_info_type - IOMMU Hardware Info Types * @IOMMU_HW_INFO_TYPE_NONE: Used by the drivers that do not report hardware * info * @IOMMU_HW_INFO_TYPE_INTEL_VTD: Intel VT-d iommu info type + * @IOMMU_HW_INFO_TYPE_ARM_SMMUV3: ARM SMMUv3 iommu info type */ enum iommu_hw_info_type { IOMMU_HW_INFO_TYPE_NONE = 0, IOMMU_HW_INFO_TYPE_INTEL_VTD = 1, + IOMMU_HW_INFO_TYPE_ARM_SMMUV3 = 2, }; /** @@ -627,9 +714,11 @@ struct iommu_hwpt_get_dirty_bitmap { * enum iommu_hwpt_invalidate_data_type - IOMMU HWPT Cache Invalidation * Data Type * @IOMMU_HWPT_INVALIDATE_DATA_VTD_S1: Invalidation data for VTD_S1 + * @IOMMU_VIOMMU_INVALIDATE_DATA_ARM_SMMUV3: Invalidation data for ARM SMMUv3 */ enum iommu_hwpt_invalidate_data_type { IOMMU_HWPT_INVALIDATE_DATA_VTD_S1 = 0, + IOMMU_VIOMMU_INVALIDATE_DATA_ARM_SMMUV3 = 1, }; /** @@ -669,9 +758,31 @@ struct iommu_hwpt_vtd_s1_invalidate { }; /** + * struct iommu_viommu_arm_smmuv3_invalidate - ARM SMMUv3 cahce invalidation + * (IOMMU_VIOMMU_INVALIDATE_DATA_ARM_SMMUV3) + * @cmd: 128-bit cache invalidation command that runs in SMMU CMDQ. + * Must be little-endian. + * + * Supported command list only when passing in a vIOMMU via @hwpt_id: + * CMDQ_OP_TLBI_NSNH_ALL + * CMDQ_OP_TLBI_NH_VA + * CMDQ_OP_TLBI_NH_VAA + * CMDQ_OP_TLBI_NH_ALL + * CMDQ_OP_TLBI_NH_ASID + * CMDQ_OP_ATC_INV + * CMDQ_OP_CFGI_CD + * CMDQ_OP_CFGI_CD_ALL + * + * -EIO will be returned if the command is not supported. + */ +struct iommu_viommu_arm_smmuv3_invalidate { + __aligned_le64 cmd[2]; +}; + +/** * struct iommu_hwpt_invalidate - ioctl(IOMMU_HWPT_INVALIDATE) * @size: sizeof(struct iommu_hwpt_invalidate) - * @hwpt_id: ID of a nested HWPT for cache invalidation + * @hwpt_id: ID of a nested HWPT or a vIOMMU, for cache invalidation * @data_uptr: User pointer to an array of driver-specific cache invalidation * data. * @data_type: One of enum iommu_hwpt_invalidate_data_type, defining the data @@ -682,8 +793,11 @@ struct iommu_hwpt_vtd_s1_invalidate { * Output the number of requests successfully handled by kernel. * @__reserved: Must be 0. * - * Invalidate the iommu cache for user-managed page table. Modifications on a - * user-managed page table should be followed by this operation to sync cache. + * Invalidate iommu cache for user-managed page table or vIOMMU. Modifications + * on a user-managed page table should be followed by this operation, if a HWPT + * is passed in via @hwpt_id. Other caches, such as device cache or descriptor + * cache can be flushed if a vIOMMU is passed in via the @hwpt_id field. + * * Each ioctl can support one or more cache invalidation requests in the array * that has a total size of @entry_len * @entry_num. * @@ -797,4 +911,88 @@ struct iommu_fault_alloc { __u32 out_fault_fd; }; #define IOMMU_FAULT_QUEUE_ALLOC _IO(IOMMUFD_TYPE, IOMMUFD_CMD_FAULT_QUEUE_ALLOC) + +/** + * enum iommu_viommu_type - Virtual IOMMU Type + * @IOMMU_VIOMMU_TYPE_DEFAULT: Reserved for future use + * @IOMMU_VIOMMU_TYPE_ARM_SMMUV3: ARM SMMUv3 driver specific type + */ +enum iommu_viommu_type { + IOMMU_VIOMMU_TYPE_DEFAULT = 0, + IOMMU_VIOMMU_TYPE_ARM_SMMUV3 = 1, +}; + +/** + * struct iommu_viommu_alloc - ioctl(IOMMU_VIOMMU_ALLOC) + * @size: sizeof(struct iommu_viommu_alloc) + * @flags: Must be 0 + * @type: Type of the virtual IOMMU. Must be defined in enum iommu_viommu_type + * @dev_id: The device's physical IOMMU will be used to back the virtual IOMMU + * @hwpt_id: ID of a nesting parent HWPT to associate to + * @out_viommu_id: Output virtual IOMMU ID for the allocated object + * + * Allocate a virtual IOMMU object, representing the underlying physical IOMMU's + * virtualization support that is a security-isolated slice of the real IOMMU HW + * that is unique to a specific VM. Operations global to the IOMMU are connected + * to the vIOMMU, such as: + * - Security namespace for guest owned ID, e.g. guest-controlled cache tags + * - Non-device-affiliated event reporting, e.g. invalidation queue errors + * - Access to a sharable nesting parent pagetable across physical IOMMUs + * - Virtualization of various platforms IDs, e.g. RIDs and others + * - Delivery of paravirtualized invalidation + * - Direct assigned invalidation queues + * - Direct assigned interrupts + */ +struct iommu_viommu_alloc { + __u32 size; + __u32 flags; + __u32 type; + __u32 dev_id; + __u32 hwpt_id; + __u32 out_viommu_id; +}; +#define IOMMU_VIOMMU_ALLOC _IO(IOMMUFD_TYPE, IOMMUFD_CMD_VIOMMU_ALLOC) + +/** + * struct iommu_vdevice_alloc - ioctl(IOMMU_VDEVICE_ALLOC) + * @size: sizeof(struct iommu_vdevice_alloc) + * @viommu_id: vIOMMU ID to associate with the virtual device + * @dev_id: The physical device to allocate a virtual instance on the vIOMMU + * @out_vdevice_id: Object handle for the vDevice. Pass to IOMMU_DESTORY + * @virt_id: Virtual device ID per vIOMMU, e.g. vSID of ARM SMMUv3, vDeviceID + * of AMD IOMMU, and vRID of a nested Intel VT-d to a Context Table + * + * Allocate a virtual device instance (for a physical device) against a vIOMMU. + * This instance holds the device's information (related to its vIOMMU) in a VM. + */ +struct iommu_vdevice_alloc { + __u32 size; + __u32 viommu_id; + __u32 dev_id; + __u32 out_vdevice_id; + __aligned_u64 virt_id; +}; +#define IOMMU_VDEVICE_ALLOC _IO(IOMMUFD_TYPE, IOMMUFD_CMD_VDEVICE_ALLOC) + +/** + * struct iommu_ioas_change_process - ioctl(VFIO_IOAS_CHANGE_PROCESS) + * @size: sizeof(struct iommu_ioas_change_process) + * @__reserved: Must be 0 + * + * This transfers pinned memory counts for every memory map in every IOAS + * in the context to the current process. This only supports maps created + * with IOMMU_IOAS_MAP_FILE, and returns EINVAL if other maps are present. + * If the ioctl returns a failure status, then nothing is changed. + * + * This API is useful for transferring operation of a device from one process + * to another, such as during userland live update. + */ +struct iommu_ioas_change_process { + __u32 size; + __u32 __reserved; +}; + +#define IOMMU_IOAS_CHANGE_PROCESS \ + _IO(IOMMUFD_TYPE, IOMMUFD_CMD_IOAS_CHANGE_PROCESS) + #endif diff --git a/include/uapi/linux/vfio.h b/include/uapi/linux/vfio.h index 2b68e6c..c8dbf82 100644 --- a/include/uapi/linux/vfio.h +++ b/include/uapi/linux/vfio.h @@ -35,7 +35,7 @@ #define VFIO_EEH 5 /* Two-stage IOMMU */ -#define VFIO_TYPE1_NESTING_IOMMU 6 /* Implies v2 */ +#define __VFIO_RESERVED_TYPE1_NESTING_IOMMU 6 /* Implies v2 */ #define VFIO_SPAPR_TCE_v2_IOMMU 7 diff --git a/mm/gup.c b/mm/gup.c index ad0c892..2b84eea 100644 --- a/mm/gup.c +++ b/mm/gup.c @@ -3760,3 +3760,27 @@ err: return ret; } EXPORT_SYMBOL_GPL(memfd_pin_folios); + +/** + * folio_add_pins() - add pins to an already-pinned folio + * @folio: the folio to add more pins to + * @pins: number of pins to add + * + * Try to add more pins to an already-pinned folio. The semantics + * of the pin (e.g., FOLL_WRITE) follow any existing pin and cannot + * be changed. + * + * This function is helpful when having obtained a pin on a large folio + * using memfd_pin_folios(), but wanting to logically unpin parts + * (e.g., individual pages) of the folio later, for example, using + * unpin_user_page_range_dirty_lock(). + * + * This is not the right interface to initially pin a folio. + */ +int folio_add_pins(struct folio *folio, unsigned int pins) +{ + VM_WARN_ON_ONCE(!folio_maybe_dma_pinned(folio)); + + return try_grab_folio(folio, pins, FOLL_PIN); +} +EXPORT_SYMBOL_GPL(folio_add_pins); diff --git a/tools/testing/selftests/iommu/Makefile b/tools/testing/selftests/iommu/Makefile index fd64779..84abeb2 100644 --- a/tools/testing/selftests/iommu/Makefile +++ b/tools/testing/selftests/iommu/Makefile @@ -1,6 +1,7 @@ # SPDX-License-Identifier: GPL-2.0-only CFLAGS += -Wall -O2 -Wno-unused-function CFLAGS += $(KHDR_INCLUDES) +LDLIBS += -lcap TEST_GEN_PROGS := TEST_GEN_PROGS += iommufd diff --git a/tools/testing/selftests/iommu/iommufd.c b/tools/testing/selftests/iommu/iommufd.c index 4927b9a..a1b2b65 100644 --- a/tools/testing/selftests/iommu/iommufd.c +++ b/tools/testing/selftests/iommu/iommufd.c @@ -1,6 +1,8 @@ // SPDX-License-Identifier: GPL-2.0-only /* Copyright (c) 2021-2022, NVIDIA CORPORATION & AFFILIATES */ +#include #include +#include #include #include @@ -49,6 +51,9 @@ static __attribute__((constructor)) void setup_sizes(void) vrc = mmap(buffer, BUFFER_SIZE, PROT_READ | PROT_WRITE, MAP_SHARED | MAP_ANONYMOUS | MAP_FIXED, -1, 0); assert(vrc == buffer); + + mfd_buffer = memfd_mmap(BUFFER_SIZE, PROT_READ | PROT_WRITE, MAP_SHARED, + &mfd); } FIXTURE(iommufd) @@ -128,6 +133,11 @@ TEST_F(iommufd, cmd_length) TEST_LENGTH(iommu_ioas_unmap, IOMMU_IOAS_UNMAP, length); TEST_LENGTH(iommu_option, IOMMU_OPTION, val64); TEST_LENGTH(iommu_vfio_ioas, IOMMU_VFIO_IOAS, __reserved); + TEST_LENGTH(iommu_ioas_map_file, IOMMU_IOAS_MAP_FILE, iova); + TEST_LENGTH(iommu_viommu_alloc, IOMMU_VIOMMU_ALLOC, out_viommu_id); + TEST_LENGTH(iommu_vdevice_alloc, IOMMU_VDEVICE_ALLOC, virt_id); + TEST_LENGTH(iommu_ioas_change_process, IOMMU_IOAS_CHANGE_PROCESS, + __reserved); #undef TEST_LENGTH } @@ -186,6 +196,144 @@ TEST_F(iommufd, global_options) EXPECT_ERRNO(ENOENT, ioctl(self->fd, IOMMU_OPTION, &cmd)); } +static void drop_cap_ipc_lock(struct __test_metadata *_metadata) +{ + cap_t caps; + cap_value_t cap_list[1] = { CAP_IPC_LOCK }; + + caps = cap_get_proc(); + ASSERT_NE(caps, NULL); + ASSERT_NE(-1, + cap_set_flag(caps, CAP_EFFECTIVE, 1, cap_list, CAP_CLEAR)); + ASSERT_NE(-1, cap_set_proc(caps)); + cap_free(caps); +} + +static long get_proc_status_value(pid_t pid, const char *var) +{ + FILE *fp; + char buf[80], tag[80]; + long val = -1; + + snprintf(buf, sizeof(buf), "/proc/%d/status", pid); + fp = fopen(buf, "r"); + if (!fp) + return val; + + while (fgets(buf, sizeof(buf), fp)) + if (fscanf(fp, "%s %ld\n", tag, &val) == 2 && !strcmp(tag, var)) + break; + + fclose(fp); + return val; +} + +static long get_vm_pinned(pid_t pid) +{ + return get_proc_status_value(pid, "VmPin:"); +} + +static long get_vm_locked(pid_t pid) +{ + return get_proc_status_value(pid, "VmLck:"); +} + +FIXTURE(change_process) +{ + int fd; + uint32_t ioas_id; +}; + +FIXTURE_VARIANT(change_process) +{ + int accounting; +}; + +FIXTURE_SETUP(change_process) +{ + self->fd = open("/dev/iommu", O_RDWR); + ASSERT_NE(-1, self->fd); + + drop_cap_ipc_lock(_metadata); + if (variant->accounting != IOPT_PAGES_ACCOUNT_NONE) { + struct iommu_option set_limit_cmd = { + .size = sizeof(set_limit_cmd), + .option_id = IOMMU_OPTION_RLIMIT_MODE, + .op = IOMMU_OPTION_OP_SET, + .val64 = (variant->accounting == IOPT_PAGES_ACCOUNT_MM), + }; + ASSERT_EQ(0, ioctl(self->fd, IOMMU_OPTION, &set_limit_cmd)); + } + + test_ioctl_ioas_alloc(&self->ioas_id); + test_cmd_mock_domain(self->ioas_id, NULL, NULL, NULL); +} + +FIXTURE_TEARDOWN(change_process) +{ + teardown_iommufd(self->fd, _metadata); +} + +FIXTURE_VARIANT_ADD(change_process, account_none) +{ + .accounting = IOPT_PAGES_ACCOUNT_NONE, +}; + +FIXTURE_VARIANT_ADD(change_process, account_user) +{ + .accounting = IOPT_PAGES_ACCOUNT_USER, +}; + +FIXTURE_VARIANT_ADD(change_process, account_mm) +{ + .accounting = IOPT_PAGES_ACCOUNT_MM, +}; + +TEST_F(change_process, basic) +{ + pid_t parent = getpid(); + pid_t child; + __u64 iova; + struct iommu_ioas_change_process cmd = { + .size = sizeof(cmd), + }; + + /* Expect failure if non-file maps exist */ + test_ioctl_ioas_map(buffer, PAGE_SIZE, &iova); + EXPECT_ERRNO(EINVAL, ioctl(self->fd, IOMMU_IOAS_CHANGE_PROCESS, &cmd)); + test_ioctl_ioas_unmap(iova, PAGE_SIZE); + + /* Change process works in current process. */ + test_ioctl_ioas_map_file(mfd, 0, PAGE_SIZE, &iova); + ASSERT_EQ(0, ioctl(self->fd, IOMMU_IOAS_CHANGE_PROCESS, &cmd)); + + /* Change process works in another process */ + child = fork(); + if (!child) { + int nlock = PAGE_SIZE / 1024; + + /* Parent accounts for locked memory before */ + ASSERT_EQ(nlock, get_vm_pinned(parent)); + if (variant->accounting == IOPT_PAGES_ACCOUNT_MM) + ASSERT_EQ(nlock, get_vm_locked(parent)); + ASSERT_EQ(0, get_vm_pinned(getpid())); + ASSERT_EQ(0, get_vm_locked(getpid())); + + ASSERT_EQ(0, ioctl(self->fd, IOMMU_IOAS_CHANGE_PROCESS, &cmd)); + + /* Child accounts for locked memory after */ + ASSERT_EQ(0, get_vm_pinned(parent)); + ASSERT_EQ(0, get_vm_locked(parent)); + ASSERT_EQ(nlock, get_vm_pinned(getpid())); + if (variant->accounting == IOPT_PAGES_ACCOUNT_MM) + ASSERT_EQ(nlock, get_vm_locked(getpid())); + + exit(0); + } + ASSERT_NE(-1, child); + ASSERT_EQ(child, waitpid(child, NULL, 0)); +} + FIXTURE(iommufd_ioas) { int fd; @@ -220,6 +368,8 @@ FIXTURE_SETUP(iommufd_ioas) for (i = 0; i != variant->mock_domains; i++) { test_cmd_mock_domain(self->ioas_id, &self->stdev_id, &self->hwpt_id, &self->device_id); + test_cmd_dev_check_cache_all(self->device_id, + IOMMU_TEST_DEV_CACHE_DEFAULT); self->base_iova = MOCK_APERTURE_START; } } @@ -360,9 +510,9 @@ TEST_F(iommufd_ioas, alloc_hwpt_nested) EXPECT_ERRNO(EBUSY, _test_ioctl_destroy(self->fd, parent_hwpt_id)); - /* hwpt_invalidate only supports a user-managed hwpt (nested) */ + /* hwpt_invalidate does not support a parent hwpt */ num_inv = 1; - test_err_hwpt_invalidate(ENOENT, parent_hwpt_id, inv_reqs, + test_err_hwpt_invalidate(EINVAL, parent_hwpt_id, inv_reqs, IOMMU_HWPT_INVALIDATE_DATA_SELFTEST, sizeof(*inv_reqs), &num_inv); assert(!num_inv); @@ -1372,6 +1522,7 @@ FIXTURE_VARIANT(iommufd_mock_domain) { unsigned int mock_domains; bool hugepages; + bool file; }; FIXTURE_SETUP(iommufd_mock_domain) @@ -1384,9 +1535,12 @@ FIXTURE_SETUP(iommufd_mock_domain) ASSERT_GE(ARRAY_SIZE(self->hwpt_ids), variant->mock_domains); - for (i = 0; i != variant->mock_domains; i++) + for (i = 0; i != variant->mock_domains; i++) { test_cmd_mock_domain(self->ioas_id, &self->stdev_ids[i], &self->hwpt_ids[i], &self->idev_ids[i]); + test_cmd_dev_check_cache_all(self->idev_ids[0], + IOMMU_TEST_DEV_CACHE_DEFAULT); + } self->hwpt_id = self->hwpt_ids[0]; self->mmap_flags = MAP_SHARED | MAP_ANONYMOUS; @@ -1410,26 +1564,45 @@ FIXTURE_VARIANT_ADD(iommufd_mock_domain, one_domain) { .mock_domains = 1, .hugepages = false, + .file = false, }; FIXTURE_VARIANT_ADD(iommufd_mock_domain, two_domains) { .mock_domains = 2, .hugepages = false, + .file = false, }; FIXTURE_VARIANT_ADD(iommufd_mock_domain, one_domain_hugepage) { .mock_domains = 1, .hugepages = true, + .file = false, }; FIXTURE_VARIANT_ADD(iommufd_mock_domain, two_domains_hugepage) { .mock_domains = 2, .hugepages = true, + .file = false, }; +FIXTURE_VARIANT_ADD(iommufd_mock_domain, one_domain_file) +{ + .mock_domains = 1, + .hugepages = false, + .file = true, +}; + +FIXTURE_VARIANT_ADD(iommufd_mock_domain, one_domain_file_hugepage) +{ + .mock_domains = 1, + .hugepages = true, + .file = true, +}; + + /* Have the kernel check that the user pages made it to the iommu_domain */ #define check_mock_iova(_ptr, _iova, _length) \ ({ \ @@ -1455,7 +1628,10 @@ FIXTURE_VARIANT_ADD(iommufd_mock_domain, two_domains_hugepage) } \ }) -TEST_F(iommufd_mock_domain, basic) +static void +test_basic_mmap(struct __test_metadata *_metadata, + struct _test_data_iommufd_mock_domain *self, + const struct _fixture_variant_iommufd_mock_domain *variant) { size_t buf_size = self->mmap_buf_size; uint8_t *buf; @@ -1478,6 +1654,40 @@ TEST_F(iommufd_mock_domain, basic) test_err_ioctl_ioas_map(EFAULT, buf, buf_size, &iova); } +static void +test_basic_file(struct __test_metadata *_metadata, + struct _test_data_iommufd_mock_domain *self, + const struct _fixture_variant_iommufd_mock_domain *variant) +{ + size_t buf_size = self->mmap_buf_size; + uint8_t *buf; + __u64 iova; + int mfd_tmp; + int prot = PROT_READ | PROT_WRITE; + + /* Simple one page map */ + test_ioctl_ioas_map_file(mfd, 0, PAGE_SIZE, &iova); + check_mock_iova(mfd_buffer, iova, PAGE_SIZE); + + buf = memfd_mmap(buf_size, prot, MAP_SHARED, &mfd_tmp); + ASSERT_NE(MAP_FAILED, buf); + + test_err_ioctl_ioas_map_file(EINVAL, mfd_tmp, 0, buf_size + 1, &iova); + + ASSERT_EQ(0, ftruncate(mfd_tmp, 0)); + test_err_ioctl_ioas_map_file(EINVAL, mfd_tmp, 0, buf_size, &iova); + + close(mfd_tmp); +} + +TEST_F(iommufd_mock_domain, basic) +{ + if (variant->file) + test_basic_file(_metadata, self, variant); + else + test_basic_mmap(_metadata, self, variant); +} + TEST_F(iommufd_mock_domain, ro_unshare) { uint8_t *buf; @@ -1513,9 +1723,13 @@ TEST_F(iommufd_mock_domain, all_aligns) unsigned int start; unsigned int end; uint8_t *buf; + int prot = PROT_READ | PROT_WRITE; + int mfd; - buf = mmap(0, buf_size, PROT_READ | PROT_WRITE, self->mmap_flags, -1, - 0); + if (variant->file) + buf = memfd_mmap(buf_size, prot, MAP_SHARED, &mfd); + else + buf = mmap(0, buf_size, prot, self->mmap_flags, -1, 0); ASSERT_NE(MAP_FAILED, buf); check_refs(buf, buf_size, 0); @@ -1532,7 +1746,12 @@ TEST_F(iommufd_mock_domain, all_aligns) size_t length = end - start; __u64 iova; - test_ioctl_ioas_map(buf + start, length, &iova); + if (variant->file) { + test_ioctl_ioas_map_file(mfd, start, length, + &iova); + } else { + test_ioctl_ioas_map(buf + start, length, &iova); + } check_mock_iova(buf + start, iova, length); check_refs(buf + start / PAGE_SIZE * PAGE_SIZE, end / PAGE_SIZE * PAGE_SIZE - @@ -1544,6 +1763,8 @@ TEST_F(iommufd_mock_domain, all_aligns) } check_refs(buf, buf_size, 0); ASSERT_EQ(0, munmap(buf, buf_size)); + if (variant->file) + close(mfd); } TEST_F(iommufd_mock_domain, all_aligns_copy) @@ -1554,9 +1775,13 @@ TEST_F(iommufd_mock_domain, all_aligns_copy) unsigned int start; unsigned int end; uint8_t *buf; + int prot = PROT_READ | PROT_WRITE; + int mfd; - buf = mmap(0, buf_size, PROT_READ | PROT_WRITE, self->mmap_flags, -1, - 0); + if (variant->file) + buf = memfd_mmap(buf_size, prot, MAP_SHARED, &mfd); + else + buf = mmap(0, buf_size, prot, self->mmap_flags, -1, 0); ASSERT_NE(MAP_FAILED, buf); check_refs(buf, buf_size, 0); @@ -1575,7 +1800,12 @@ TEST_F(iommufd_mock_domain, all_aligns_copy) uint32_t mock_stdev_id; __u64 iova; - test_ioctl_ioas_map(buf + start, length, &iova); + if (variant->file) { + test_ioctl_ioas_map_file(mfd, start, length, + &iova); + } else { + test_ioctl_ioas_map(buf + start, length, &iova); + } /* Add and destroy a domain while the area exists */ old_id = self->hwpt_ids[1]; @@ -1596,15 +1826,18 @@ TEST_F(iommufd_mock_domain, all_aligns_copy) } check_refs(buf, buf_size, 0); ASSERT_EQ(0, munmap(buf, buf_size)); + if (variant->file) + close(mfd); } TEST_F(iommufd_mock_domain, user_copy) { + void *buf = variant->file ? mfd_buffer : buffer; struct iommu_test_cmd access_cmd = { .size = sizeof(access_cmd), .op = IOMMU_TEST_OP_ACCESS_PAGES, .access_pages = { .length = BUFFER_SIZE, - .uptr = (uintptr_t)buffer }, + .uptr = (uintptr_t)buf }, }; struct iommu_ioas_copy copy_cmd = { .size = sizeof(copy_cmd), @@ -1623,9 +1856,13 @@ TEST_F(iommufd_mock_domain, user_copy) /* Pin the pages in an IOAS with no domains then copy to an IOAS with domains */ test_ioctl_ioas_alloc(&ioas_id); - test_ioctl_ioas_map_id(ioas_id, buffer, BUFFER_SIZE, - ©_cmd.src_iova); - + if (variant->file) { + test_ioctl_ioas_map_id_file(ioas_id, mfd, 0, BUFFER_SIZE, + ©_cmd.src_iova); + } else { + test_ioctl_ioas_map_id(ioas_id, buf, BUFFER_SIZE, + ©_cmd.src_iova); + } test_cmd_create_access(ioas_id, &access_cmd.id, MOCK_FLAGS_ACCESS_CREATE_NEEDS_PIN_PAGES); @@ -1635,12 +1872,17 @@ TEST_F(iommufd_mock_domain, user_copy) &access_cmd)); copy_cmd.src_ioas_id = ioas_id; ASSERT_EQ(0, ioctl(self->fd, IOMMU_IOAS_COPY, ©_cmd)); - check_mock_iova(buffer, MOCK_APERTURE_START, BUFFER_SIZE); + check_mock_iova(buf, MOCK_APERTURE_START, BUFFER_SIZE); /* Now replace the ioas with a new one */ test_ioctl_ioas_alloc(&new_ioas_id); - test_ioctl_ioas_map_id(new_ioas_id, buffer, BUFFER_SIZE, - ©_cmd.src_iova); + if (variant->file) { + test_ioctl_ioas_map_id_file(new_ioas_id, mfd, 0, BUFFER_SIZE, + ©_cmd.src_iova); + } else { + test_ioctl_ioas_map_id(new_ioas_id, buf, BUFFER_SIZE, + ©_cmd.src_iova); + } test_cmd_access_replace_ioas(access_cmd.id, new_ioas_id); /* Destroy the old ioas and cleanup copied mapping */ @@ -1654,7 +1896,7 @@ TEST_F(iommufd_mock_domain, user_copy) &access_cmd)); copy_cmd.src_ioas_id = new_ioas_id; ASSERT_EQ(0, ioctl(self->fd, IOMMU_IOAS_COPY, ©_cmd)); - check_mock_iova(buffer, MOCK_APERTURE_START, BUFFER_SIZE); + check_mock_iova(buf, MOCK_APERTURE_START, BUFFER_SIZE); test_cmd_destroy_access_pages( access_cmd.id, access_cmd.access_pages.out_access_pages_id); @@ -2386,4 +2628,332 @@ TEST_F(vfio_compat_mock_domain, huge_map) } } +FIXTURE(iommufd_viommu) +{ + int fd; + uint32_t ioas_id; + uint32_t stdev_id; + uint32_t hwpt_id; + uint32_t nested_hwpt_id; + uint32_t device_id; + uint32_t viommu_id; +}; + +FIXTURE_VARIANT(iommufd_viommu) +{ + unsigned int viommu; +}; + +FIXTURE_SETUP(iommufd_viommu) +{ + self->fd = open("/dev/iommu", O_RDWR); + ASSERT_NE(-1, self->fd); + test_ioctl_ioas_alloc(&self->ioas_id); + test_ioctl_set_default_memory_limit(); + + if (variant->viommu) { + struct iommu_hwpt_selftest data = { + .iotlb = IOMMU_TEST_IOTLB_DEFAULT, + }; + + test_cmd_mock_domain(self->ioas_id, &self->stdev_id, NULL, + &self->device_id); + + /* Allocate a nesting parent hwpt */ + test_cmd_hwpt_alloc(self->device_id, self->ioas_id, + IOMMU_HWPT_ALLOC_NEST_PARENT, + &self->hwpt_id); + + /* Allocate a vIOMMU taking refcount of the parent hwpt */ + test_cmd_viommu_alloc(self->device_id, self->hwpt_id, + IOMMU_VIOMMU_TYPE_SELFTEST, + &self->viommu_id); + + /* Allocate a regular nested hwpt */ + test_cmd_hwpt_alloc_nested(self->device_id, self->viommu_id, 0, + &self->nested_hwpt_id, + IOMMU_HWPT_DATA_SELFTEST, &data, + sizeof(data)); + } +} + +FIXTURE_TEARDOWN(iommufd_viommu) +{ + teardown_iommufd(self->fd, _metadata); +} + +FIXTURE_VARIANT_ADD(iommufd_viommu, no_viommu) +{ + .viommu = 0, +}; + +FIXTURE_VARIANT_ADD(iommufd_viommu, mock_viommu) +{ + .viommu = 1, +}; + +TEST_F(iommufd_viommu, viommu_auto_destroy) +{ +} + +TEST_F(iommufd_viommu, viommu_negative_tests) +{ + uint32_t device_id = self->device_id; + uint32_t ioas_id = self->ioas_id; + uint32_t hwpt_id; + + if (self->device_id) { + /* Negative test -- invalid hwpt (hwpt_id=0) */ + test_err_viommu_alloc(ENOENT, device_id, 0, + IOMMU_VIOMMU_TYPE_SELFTEST, NULL); + + /* Negative test -- not a nesting parent hwpt */ + test_cmd_hwpt_alloc(device_id, ioas_id, 0, &hwpt_id); + test_err_viommu_alloc(EINVAL, device_id, hwpt_id, + IOMMU_VIOMMU_TYPE_SELFTEST, NULL); + test_ioctl_destroy(hwpt_id); + + /* Negative test -- unsupported viommu type */ + test_err_viommu_alloc(EOPNOTSUPP, device_id, self->hwpt_id, + 0xdead, NULL); + EXPECT_ERRNO(EBUSY, + _test_ioctl_destroy(self->fd, self->hwpt_id)); + EXPECT_ERRNO(EBUSY, + _test_ioctl_destroy(self->fd, self->viommu_id)); + } else { + test_err_viommu_alloc(ENOENT, self->device_id, self->hwpt_id, + IOMMU_VIOMMU_TYPE_SELFTEST, NULL); + } +} + +TEST_F(iommufd_viommu, viommu_alloc_nested_iopf) +{ + struct iommu_hwpt_selftest data = { + .iotlb = IOMMU_TEST_IOTLB_DEFAULT, + }; + uint32_t viommu_id = self->viommu_id; + uint32_t dev_id = self->device_id; + uint32_t iopf_hwpt_id; + uint32_t fault_id; + uint32_t fault_fd; + + if (self->device_id) { + test_ioctl_fault_alloc(&fault_id, &fault_fd); + test_err_hwpt_alloc_iopf( + ENOENT, dev_id, viommu_id, UINT32_MAX, + IOMMU_HWPT_FAULT_ID_VALID, &iopf_hwpt_id, + IOMMU_HWPT_DATA_SELFTEST, &data, sizeof(data)); + test_err_hwpt_alloc_iopf( + EOPNOTSUPP, dev_id, viommu_id, fault_id, + IOMMU_HWPT_FAULT_ID_VALID | (1 << 31), &iopf_hwpt_id, + IOMMU_HWPT_DATA_SELFTEST, &data, sizeof(data)); + test_cmd_hwpt_alloc_iopf( + dev_id, viommu_id, fault_id, IOMMU_HWPT_FAULT_ID_VALID, + &iopf_hwpt_id, IOMMU_HWPT_DATA_SELFTEST, &data, + sizeof(data)); + + test_cmd_mock_domain_replace(self->stdev_id, iopf_hwpt_id); + EXPECT_ERRNO(EBUSY, + _test_ioctl_destroy(self->fd, iopf_hwpt_id)); + test_cmd_trigger_iopf(dev_id, fault_fd); + + test_cmd_mock_domain_replace(self->stdev_id, self->ioas_id); + test_ioctl_destroy(iopf_hwpt_id); + close(fault_fd); + test_ioctl_destroy(fault_id); + } +} + +TEST_F(iommufd_viommu, vdevice_alloc) +{ + uint32_t viommu_id = self->viommu_id; + uint32_t dev_id = self->device_id; + uint32_t vdev_id = 0; + + if (dev_id) { + /* Set vdev_id to 0x99, unset it, and set to 0x88 */ + test_cmd_vdevice_alloc(viommu_id, dev_id, 0x99, &vdev_id); + test_err_vdevice_alloc(EEXIST, viommu_id, dev_id, 0x99, + &vdev_id); + test_ioctl_destroy(vdev_id); + test_cmd_vdevice_alloc(viommu_id, dev_id, 0x88, &vdev_id); + test_ioctl_destroy(vdev_id); + } else { + test_err_vdevice_alloc(ENOENT, viommu_id, dev_id, 0x99, NULL); + } +} + +TEST_F(iommufd_viommu, vdevice_cache) +{ + struct iommu_viommu_invalidate_selftest inv_reqs[2] = {}; + uint32_t viommu_id = self->viommu_id; + uint32_t dev_id = self->device_id; + uint32_t vdev_id = 0; + uint32_t num_inv; + + if (dev_id) { + test_cmd_vdevice_alloc(viommu_id, dev_id, 0x99, &vdev_id); + + test_cmd_dev_check_cache_all(dev_id, + IOMMU_TEST_DEV_CACHE_DEFAULT); + + /* Check data_type by passing zero-length array */ + num_inv = 0; + test_cmd_viommu_invalidate(viommu_id, inv_reqs, + sizeof(*inv_reqs), &num_inv); + assert(!num_inv); + + /* Negative test: Invalid data_type */ + num_inv = 1; + test_err_viommu_invalidate(EINVAL, viommu_id, inv_reqs, + IOMMU_VIOMMU_INVALIDATE_DATA_SELFTEST_INVALID, + sizeof(*inv_reqs), &num_inv); + assert(!num_inv); + + /* Negative test: structure size sanity */ + num_inv = 1; + test_err_viommu_invalidate(EINVAL, viommu_id, inv_reqs, + IOMMU_VIOMMU_INVALIDATE_DATA_SELFTEST, + sizeof(*inv_reqs) + 1, &num_inv); + assert(!num_inv); + + num_inv = 1; + test_err_viommu_invalidate(EINVAL, viommu_id, inv_reqs, + IOMMU_VIOMMU_INVALIDATE_DATA_SELFTEST, + 1, &num_inv); + assert(!num_inv); + + /* Negative test: invalid flag is passed */ + num_inv = 1; + inv_reqs[0].flags = 0xffffffff; + inv_reqs[0].vdev_id = 0x99; + test_err_viommu_invalidate(EOPNOTSUPP, viommu_id, inv_reqs, + IOMMU_VIOMMU_INVALIDATE_DATA_SELFTEST, + sizeof(*inv_reqs), &num_inv); + assert(!num_inv); + + /* Negative test: invalid data_uptr when array is not empty */ + num_inv = 1; + inv_reqs[0].flags = 0; + inv_reqs[0].vdev_id = 0x99; + test_err_viommu_invalidate(EINVAL, viommu_id, NULL, + IOMMU_VIOMMU_INVALIDATE_DATA_SELFTEST, + sizeof(*inv_reqs), &num_inv); + assert(!num_inv); + + /* Negative test: invalid entry_len when array is not empty */ + num_inv = 1; + inv_reqs[0].flags = 0; + inv_reqs[0].vdev_id = 0x99; + test_err_viommu_invalidate(EINVAL, viommu_id, inv_reqs, + IOMMU_VIOMMU_INVALIDATE_DATA_SELFTEST, + 0, &num_inv); + assert(!num_inv); + + /* Negative test: invalid cache_id */ + num_inv = 1; + inv_reqs[0].flags = 0; + inv_reqs[0].vdev_id = 0x99; + inv_reqs[0].cache_id = MOCK_DEV_CACHE_ID_MAX + 1; + test_err_viommu_invalidate(EINVAL, viommu_id, inv_reqs, + IOMMU_VIOMMU_INVALIDATE_DATA_SELFTEST, + sizeof(*inv_reqs), &num_inv); + assert(!num_inv); + + /* Negative test: invalid vdev_id */ + num_inv = 1; + inv_reqs[0].flags = 0; + inv_reqs[0].vdev_id = 0x9; + inv_reqs[0].cache_id = 0; + test_err_viommu_invalidate(EINVAL, viommu_id, inv_reqs, + IOMMU_VIOMMU_INVALIDATE_DATA_SELFTEST, + sizeof(*inv_reqs), &num_inv); + assert(!num_inv); + + /* + * Invalidate the 1st cache entry but fail the 2nd request + * due to invalid flags configuration in the 2nd request. + */ + num_inv = 2; + inv_reqs[0].flags = 0; + inv_reqs[0].vdev_id = 0x99; + inv_reqs[0].cache_id = 0; + inv_reqs[1].flags = 0xffffffff; + inv_reqs[1].vdev_id = 0x99; + inv_reqs[1].cache_id = 1; + test_err_viommu_invalidate(EOPNOTSUPP, viommu_id, inv_reqs, + IOMMU_VIOMMU_INVALIDATE_DATA_SELFTEST, + sizeof(*inv_reqs), &num_inv); + assert(num_inv == 1); + test_cmd_dev_check_cache(dev_id, 0, 0); + test_cmd_dev_check_cache(dev_id, 1, + IOMMU_TEST_DEV_CACHE_DEFAULT); + test_cmd_dev_check_cache(dev_id, 2, + IOMMU_TEST_DEV_CACHE_DEFAULT); + test_cmd_dev_check_cache(dev_id, 3, + IOMMU_TEST_DEV_CACHE_DEFAULT); + + /* + * Invalidate the 1st cache entry but fail the 2nd request + * due to invalid cache_id configuration in the 2nd request. + */ + num_inv = 2; + inv_reqs[0].flags = 0; + inv_reqs[0].vdev_id = 0x99; + inv_reqs[0].cache_id = 0; + inv_reqs[1].flags = 0; + inv_reqs[1].vdev_id = 0x99; + inv_reqs[1].cache_id = MOCK_DEV_CACHE_ID_MAX + 1; + test_err_viommu_invalidate(EINVAL, viommu_id, inv_reqs, + IOMMU_VIOMMU_INVALIDATE_DATA_SELFTEST, + sizeof(*inv_reqs), &num_inv); + assert(num_inv == 1); + test_cmd_dev_check_cache(dev_id, 0, 0); + test_cmd_dev_check_cache(dev_id, 1, + IOMMU_TEST_DEV_CACHE_DEFAULT); + test_cmd_dev_check_cache(dev_id, 2, + IOMMU_TEST_DEV_CACHE_DEFAULT); + test_cmd_dev_check_cache(dev_id, 3, + IOMMU_TEST_DEV_CACHE_DEFAULT); + + /* Invalidate the 2nd cache entry and verify */ + num_inv = 1; + inv_reqs[0].flags = 0; + inv_reqs[0].vdev_id = 0x99; + inv_reqs[0].cache_id = 1; + test_cmd_viommu_invalidate(viommu_id, inv_reqs, + sizeof(*inv_reqs), &num_inv); + assert(num_inv == 1); + test_cmd_dev_check_cache(dev_id, 0, 0); + test_cmd_dev_check_cache(dev_id, 1, 0); + test_cmd_dev_check_cache(dev_id, 2, + IOMMU_TEST_DEV_CACHE_DEFAULT); + test_cmd_dev_check_cache(dev_id, 3, + IOMMU_TEST_DEV_CACHE_DEFAULT); + + /* Invalidate the 3rd and 4th cache entries and verify */ + num_inv = 2; + inv_reqs[0].flags = 0; + inv_reqs[0].vdev_id = 0x99; + inv_reqs[0].cache_id = 2; + inv_reqs[1].flags = 0; + inv_reqs[1].vdev_id = 0x99; + inv_reqs[1].cache_id = 3; + test_cmd_viommu_invalidate(viommu_id, inv_reqs, + sizeof(*inv_reqs), &num_inv); + assert(num_inv == 2); + test_cmd_dev_check_cache_all(dev_id, 0); + + /* Invalidate all cache entries for nested_dev_id[1] and verify */ + num_inv = 1; + inv_reqs[0].vdev_id = 0x99; + inv_reqs[0].flags = IOMMU_TEST_INVALIDATE_FLAG_ALL; + test_cmd_viommu_invalidate(viommu_id, inv_reqs, + sizeof(*inv_reqs), &num_inv); + assert(num_inv == 1); + test_cmd_dev_check_cache_all(dev_id, 0); + test_ioctl_destroy(vdev_id); + } +} + TEST_HARNESS_MAIN diff --git a/tools/testing/selftests/iommu/iommufd_fail_nth.c b/tools/testing/selftests/iommu/iommufd_fail_nth.c index c5d5e69..22f6fd5 100644 --- a/tools/testing/selftests/iommu/iommufd_fail_nth.c +++ b/tools/testing/selftests/iommu/iommufd_fail_nth.c @@ -47,6 +47,9 @@ static __attribute__((constructor)) void setup_buffer(void) buffer = mmap(0, BUFFER_SIZE, PROT_READ | PROT_WRITE, MAP_SHARED | MAP_ANONYMOUS, -1, 0); + + mfd_buffer = memfd_mmap(BUFFER_SIZE, PROT_READ | PROT_WRITE, MAP_SHARED, + &mfd); } /* @@ -331,6 +334,42 @@ TEST_FAIL_NTH(basic_fail_nth, map_domain) return 0; } +/* iopt_area_fill_domains() and iopt_area_fill_domain() */ +TEST_FAIL_NTH(basic_fail_nth, map_file_domain) +{ + uint32_t ioas_id; + __u32 stdev_id; + __u32 hwpt_id; + __u64 iova; + + self->fd = open("/dev/iommu", O_RDWR); + if (self->fd == -1) + return -1; + + if (_test_ioctl_ioas_alloc(self->fd, &ioas_id)) + return -1; + + if (_test_ioctl_set_temp_memory_limit(self->fd, 32)) + return -1; + + fail_nth_enable(); + + if (_test_cmd_mock_domain(self->fd, ioas_id, &stdev_id, &hwpt_id, NULL)) + return -1; + + if (_test_ioctl_ioas_map_file(self->fd, ioas_id, mfd, 0, 262144, &iova, + IOMMU_IOAS_MAP_WRITEABLE | + IOMMU_IOAS_MAP_READABLE)) + return -1; + + if (_test_ioctl_destroy(self->fd, stdev_id)) + return -1; + + if (_test_cmd_mock_domain(self->fd, ioas_id, &stdev_id, &hwpt_id, NULL)) + return -1; + return 0; +} + TEST_FAIL_NTH(basic_fail_nth, map_two_domains) { uint32_t ioas_id; @@ -582,6 +621,8 @@ TEST_FAIL_NTH(basic_fail_nth, device) uint32_t stdev_id; uint32_t idev_id; uint32_t hwpt_id; + uint32_t viommu_id; + uint32_t vdev_id; __u64 iova; self->fd = open("/dev/iommu", O_RDWR); @@ -624,6 +665,19 @@ TEST_FAIL_NTH(basic_fail_nth, device) if (_test_cmd_mock_domain_replace(self->fd, stdev_id, hwpt_id, NULL)) return -1; + + if (_test_cmd_hwpt_alloc(self->fd, idev_id, ioas_id, 0, + IOMMU_HWPT_ALLOC_NEST_PARENT, &hwpt_id, + IOMMU_HWPT_DATA_NONE, 0, 0)) + return -1; + + if (_test_cmd_viommu_alloc(self->fd, idev_id, hwpt_id, + IOMMU_VIOMMU_TYPE_SELFTEST, 0, &viommu_id)) + return -1; + + if (_test_cmd_vdevice_alloc(self->fd, viommu_id, idev_id, 0, &vdev_id)) + return -1; + return 0; } diff --git a/tools/testing/selftests/iommu/iommufd_utils.h b/tools/testing/selftests/iommu/iommufd_utils.h index 40f6f14..d979f5b 100644 --- a/tools/testing/selftests/iommu/iommufd_utils.h +++ b/tools/testing/selftests/iommu/iommufd_utils.h @@ -22,6 +22,12 @@ #define BIT_MASK(nr) (1UL << ((nr) % __BITS_PER_LONG)) #define BIT_WORD(nr) ((nr) / __BITS_PER_LONG) +enum { + IOPT_PAGES_ACCOUNT_NONE = 0, + IOPT_PAGES_ACCOUNT_USER = 1, + IOPT_PAGES_ACCOUNT_MM = 2, +}; + #define DIV_ROUND_UP(n, d) (((n) + (d) - 1) / (d)) static inline void set_bit(unsigned int nr, unsigned long *addr) @@ -40,12 +46,28 @@ static inline bool test_bit(unsigned int nr, unsigned long *addr) static void *buffer; static unsigned long BUFFER_SIZE; +static void *mfd_buffer; +static int mfd; + static unsigned long PAGE_SIZE; #define sizeof_field(TYPE, MEMBER) sizeof((((TYPE *)0)->MEMBER)) #define offsetofend(TYPE, MEMBER) \ (offsetof(TYPE, MEMBER) + sizeof_field(TYPE, MEMBER)) +static inline void *memfd_mmap(size_t length, int prot, int flags, int *mfd_p) +{ + int mfd_flags = (flags & MAP_HUGETLB) ? MFD_HUGETLB : 0; + int mfd = memfd_create("buffer", mfd_flags); + + if (mfd <= 0) + return MAP_FAILED; + if (ftruncate(mfd, length)) + return MAP_FAILED; + *mfd_p = mfd; + return mmap(0, length, prot, flags, mfd, 0); +} + /* * Have the kernel check the refcount on pages. I don't know why a freshly * mmap'd anon non-compound page starts out with a ref of 3 @@ -234,6 +256,30 @@ static int _test_cmd_hwpt_alloc(int fd, __u32 device_id, __u32 pt_id, __u32 ft_i test_cmd_hwpt_check_iotlb(hwpt_id, i, expected); \ }) +#define test_cmd_dev_check_cache(device_id, cache_id, expected) \ + ({ \ + struct iommu_test_cmd test_cmd = { \ + .size = sizeof(test_cmd), \ + .op = IOMMU_TEST_OP_DEV_CHECK_CACHE, \ + .id = device_id, \ + .check_dev_cache = { \ + .id = cache_id, \ + .cache = expected, \ + }, \ + }; \ + ASSERT_EQ(0, ioctl(self->fd, \ + _IOMMU_TEST_CMD( \ + IOMMU_TEST_OP_DEV_CHECK_CACHE), \ + &test_cmd)); \ + }) + +#define test_cmd_dev_check_cache_all(device_id, expected) \ + ({ \ + int c; \ + for (c = 0; c < MOCK_DEV_CACHE_NUM; c++) \ + test_cmd_dev_check_cache(device_id, c, expected); \ + }) + static int _test_cmd_hwpt_invalidate(int fd, __u32 hwpt_id, void *reqs, uint32_t data_type, uint32_t lreq, uint32_t *nreqs) @@ -265,6 +311,38 @@ static int _test_cmd_hwpt_invalidate(int fd, __u32 hwpt_id, void *reqs, data_type, lreq, nreqs)); \ }) +static int _test_cmd_viommu_invalidate(int fd, __u32 viommu_id, void *reqs, + uint32_t data_type, uint32_t lreq, + uint32_t *nreqs) +{ + struct iommu_hwpt_invalidate cmd = { + .size = sizeof(cmd), + .hwpt_id = viommu_id, + .data_type = data_type, + .data_uptr = (uint64_t)reqs, + .entry_len = lreq, + .entry_num = *nreqs, + }; + int rc = ioctl(fd, IOMMU_HWPT_INVALIDATE, &cmd); + *nreqs = cmd.entry_num; + return rc; +} + +#define test_cmd_viommu_invalidate(viommu, reqs, lreq, nreqs) \ + ({ \ + ASSERT_EQ(0, \ + _test_cmd_viommu_invalidate(self->fd, viommu, reqs, \ + IOMMU_VIOMMU_INVALIDATE_DATA_SELFTEST, \ + lreq, nreqs)); \ + }) +#define test_err_viommu_invalidate(_errno, viommu_id, reqs, data_type, lreq, \ + nreqs) \ + ({ \ + EXPECT_ERRNO(_errno, _test_cmd_viommu_invalidate( \ + self->fd, viommu_id, reqs, \ + data_type, lreq, nreqs)); \ + }) + static int _test_cmd_access_replace_ioas(int fd, __u32 access_id, unsigned int ioas_id) { @@ -589,6 +667,47 @@ static int _test_ioctl_ioas_unmap(int fd, unsigned int ioas_id, uint64_t iova, EXPECT_ERRNO(_errno, _test_ioctl_ioas_unmap(self->fd, self->ioas_id, \ iova, length, NULL)) +static int _test_ioctl_ioas_map_file(int fd, unsigned int ioas_id, int mfd, + size_t start, size_t length, __u64 *iova, + unsigned int flags) +{ + struct iommu_ioas_map_file cmd = { + .size = sizeof(cmd), + .flags = flags, + .ioas_id = ioas_id, + .fd = mfd, + .start = start, + .length = length, + }; + int ret; + + if (flags & IOMMU_IOAS_MAP_FIXED_IOVA) + cmd.iova = *iova; + + ret = ioctl(fd, IOMMU_IOAS_MAP_FILE, &cmd); + *iova = cmd.iova; + return ret; +} + +#define test_ioctl_ioas_map_file(mfd, start, length, iova_p) \ + ASSERT_EQ(0, \ + _test_ioctl_ioas_map_file( \ + self->fd, self->ioas_id, mfd, start, length, iova_p, \ + IOMMU_IOAS_MAP_WRITEABLE | IOMMU_IOAS_MAP_READABLE)) + +#define test_err_ioctl_ioas_map_file(_errno, mfd, start, length, iova_p) \ + EXPECT_ERRNO( \ + _errno, \ + _test_ioctl_ioas_map_file( \ + self->fd, self->ioas_id, mfd, start, length, iova_p, \ + IOMMU_IOAS_MAP_WRITEABLE | IOMMU_IOAS_MAP_READABLE)) + +#define test_ioctl_ioas_map_id_file(ioas_id, mfd, start, length, iova_p) \ + ASSERT_EQ(0, \ + _test_ioctl_ioas_map_file( \ + self->fd, ioas_id, mfd, start, length, iova_p, \ + IOMMU_IOAS_MAP_WRITEABLE | IOMMU_IOAS_MAP_READABLE)) + static int _test_ioctl_set_temp_memory_limit(int fd, unsigned int limit) { struct iommu_test_cmd memlimit_cmd = { @@ -762,3 +881,58 @@ static int _test_cmd_trigger_iopf(int fd, __u32 device_id, __u32 fault_fd) #define test_cmd_trigger_iopf(device_id, fault_fd) \ ASSERT_EQ(0, _test_cmd_trigger_iopf(self->fd, device_id, fault_fd)) + +static int _test_cmd_viommu_alloc(int fd, __u32 device_id, __u32 hwpt_id, + __u32 type, __u32 flags, __u32 *viommu_id) +{ + struct iommu_viommu_alloc cmd = { + .size = sizeof(cmd), + .flags = flags, + .type = type, + .dev_id = device_id, + .hwpt_id = hwpt_id, + }; + int ret; + + ret = ioctl(fd, IOMMU_VIOMMU_ALLOC, &cmd); + if (ret) + return ret; + if (viommu_id) + *viommu_id = cmd.out_viommu_id; + return 0; +} + +#define test_cmd_viommu_alloc(device_id, hwpt_id, type, viommu_id) \ + ASSERT_EQ(0, _test_cmd_viommu_alloc(self->fd, device_id, hwpt_id, \ + type, 0, viommu_id)) +#define test_err_viommu_alloc(_errno, device_id, hwpt_id, type, viommu_id) \ + EXPECT_ERRNO(_errno, \ + _test_cmd_viommu_alloc(self->fd, device_id, hwpt_id, \ + type, 0, viommu_id)) + +static int _test_cmd_vdevice_alloc(int fd, __u32 viommu_id, __u32 idev_id, + __u64 virt_id, __u32 *vdev_id) +{ + struct iommu_vdevice_alloc cmd = { + .size = sizeof(cmd), + .dev_id = idev_id, + .viommu_id = viommu_id, + .virt_id = virt_id, + }; + int ret; + + ret = ioctl(fd, IOMMU_VDEVICE_ALLOC, &cmd); + if (ret) + return ret; + if (vdev_id) + *vdev_id = cmd.out_vdevice_id; + return 0; +} + +#define test_cmd_vdevice_alloc(viommu_id, idev_id, virt_id, vdev_id) \ + ASSERT_EQ(0, _test_cmd_vdevice_alloc(self->fd, viommu_id, idev_id, \ + virt_id, vdev_id)) +#define test_err_vdevice_alloc(_errno, viommu_id, idev_id, virt_id, vdev_id) \ + EXPECT_ERRNO(_errno, \ + _test_cmd_vdevice_alloc(self->fd, viommu_id, idev_id, \ + virt_id, vdev_id))